WSL2-Linux-Kernel/mm/memory.c

5527 строки
150 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/memory.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* demand-loading started 01.12.91 - seems it is high on the list of
* things wanted, and it should be easy to implement. - Linus
*/
/*
* Ok, demand-loading was easy, shared pages a little bit tricker. Shared
* pages started 02.12.91, seems to work. - Linus.
*
* Tested sharing by executing about 30 /bin/sh: under the old kernel it
* would have taken more than the 6M I have free, but it worked well as
* far as I could see.
*
* Also corrected some "invalidate()"s - I wasn't doing enough of them.
*/
/*
* Real VM (paging to/from disk) started 18.12.91. Much more work and
* thought has to go into this. Oh, well..
* 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
* Found it. Everything seems to work now.
* 20.12.91 - Ok, making the swap-device changeable like the root.
*/
/*
* 05.04.94 - Multi-page memory management added for v1.1.
* Idea by Alex Bligh (alex@cconcepts.co.uk)
*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
*
* Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/task.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
#include <linux/memremap.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/pfn_t.h>
#include <linux/writeback.h>
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 11:13:53 +03:00
#include <linux/memcontrol.h>
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
#include <linux/mmu_notifier.h>
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
#include <linux/swapops.h>
#include <linux/elf.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
#include <linux/debugfs.h>
#include <linux/userfaultfd_k.h>
#include <linux/dax.h>
mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Wenwei Tao <wenwei.tww@alibaba-inc.com> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andrea Argangeli <andrea@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-19 01:16:15 +03:00
#include <linux/oom.h>
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:42:58 +03:00
#include <linux/numa.h>
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
#include <linux/perf_event.h>
#include <linux/ptrace.h>
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
#include <linux/vmalloc.h>
mm: emit tracepoint when RSS changes Useful to track how RSS is changing per TGID to detect spikes in RSS and memory hogs. Several Android teams have been using this patch in various kernel trees for half a year now. Many reported to me it is really useful so I'm posting it upstream. Initial patch developed by Tim Murray. Changes I made from original patch: o Prevent any additional space consumed by mm_struct. Regarding the fact that the RSS may change too often thus flooding the traces - note that, there is some "hysterisis" with this already. That is - We update the counter only if we receive 64 page faults due to SPLIT_RSS_ACCOUNTING. However, during zapping or copying of pte range, the RSS is updated immediately which can become noisy/flooding. In a previous discussion, we agreed that BPF or ftrace can be used to rate limit the signal if this becomes an issue. Also note that I added wrappers to trace_rss_stat to prevent compiler errors where linux/mm.h is included from tracing code, causing errors such as: CC kernel/trace/power-traces.o In file included from ./include/trace/define_trace.h:102, from ./include/trace/events/kmem.h:342, from ./include/linux/mm.h:31, from ./include/linux/ring_buffer.h:5, from ./include/linux/trace_events.h:6, from ./include/trace/events/power.h:12, from kernel/trace/power-traces.c:15: ./include/trace/trace_events.h:113:22: error: field `ent' has incomplete type struct trace_entry ent; \ Link: http://lore.kernel.org/r/20190903200905.198642-1-joel@joelfernandes.org Link: http://lkml.kernel.org/r/20191001172817.234886-1-joel@joelfernandes.org Co-developed-by: Tim Murray <timmurray@google.com> Signed-off-by: Tim Murray <timmurray@google.com> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Carmen Jackson <carmenjackson@google.com> Cc: Mayank Gupta <mayankgupta@google.com> Cc: Daniel Colascione <dancol@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Minchan Kim <minchan@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:30 +03:00
#include <trace/events/kmem.h>
#include <asm/io.h>
mm/gup, x86/mm/pkeys: Check VMAs and PTEs for protection keys Today, for normal faults and page table walks, we check the VMA and/or PTE to ensure that it is compatible with the action. For instance, if we get a write fault on a non-writeable VMA, we SIGSEGV. We try to do the same thing for protection keys. Basically, we try to make sure that if a user does this: mprotect(ptr, size, PROT_NONE); *ptr = foo; they see the same effects with protection keys when they do this: mprotect(ptr, size, PROT_READ|PROT_WRITE); set_pkey(ptr, size, 4); wrpkru(0xffffff3f); // access disable pkey 4 *ptr = foo; The state to do that checking is in the VMA, but we also sometimes have to do it on the page tables only, like when doing a get_user_pages_fast() where we have no VMA. We add two functions and expose them to generic code: arch_pte_access_permitted(pte_flags, write) arch_vma_access_permitted(vma, write) These are, of course, backed up in x86 arch code with checks against the PTE or VMA's protection key. But, there are also cases where we do not want to respect protection keys. When we ptrace(), for instance, we do not want to apply the tracer's PKRU permissions to the PTEs from the process being traced. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Alexey Kardashevskiy <aik@ozlabs.ru> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Boaz Harrosh <boaz@plexistor.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave@sr71.net> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Dominik Dingel <dingel@linux.vnet.ibm.com> Cc: Dominik Vogt <vogt@linux.vnet.ibm.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Low <jason.low2@hp.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Mikulas Patocka <mpatocka@redhat.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Shachar Raindel <raindel@mellanox.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20160212210219.14D5D715@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-13 00:02:19 +03:00
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
#include "pgalloc-track.h"
#include "internal.h"
#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
#ifndef CONFIG_NUMA
unsigned long max_mapnr;
EXPORT_SYMBOL(max_mapnr);
struct page *mem_map;
EXPORT_SYMBOL(mem_map);
#endif
/*
* A number of key systems in x86 including ioremap() rely on the assumption
* that high_memory defines the upper bound on direct map memory, then end
* of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and
* highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
void *high_memory;
EXPORT_SYMBOL(high_memory);
/*
* Randomize the address space (stacks, mmaps, brk, etc.).
*
* ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
* as ancient (libc5 based) binaries can segfault. )
*/
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
1;
#else
2;
#endif
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
#ifndef arch_faults_on_old_pte
static inline bool arch_faults_on_old_pte(void)
{
/*
* Those arches which don't have hw access flag feature need to
* implement their own helper. By default, "true" means pagefault
* will be hit on old pte.
*/
return true;
}
#endif
2020-11-24 21:48:26 +03:00
#ifndef arch_wants_old_prefaulted_pte
static inline bool arch_wants_old_prefaulted_pte(void)
{
/*
* Transitioning a PTE from 'old' to 'young' can be expensive on
* some architectures, even if it's performed in hardware. By
* default, "false" means prefaulted entries will be 'young'.
*/
return false;
}
#endif
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
return 1;
}
__setup("norandmaps", disable_randmaps);
unsigned long zero_pfn __read_mostly;
EXPORT_SYMBOL(zero_pfn);
unsigned long highest_memmap_pfn __read_mostly;
mm: reinstate ZERO_PAGE KAMEZAWA Hiroyuki has observed customers of earlier kernels taking advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from using in 2.6.24. And there were a couple of regression reports on LKML. Following suggestions from Linus, reinstate do_anonymous_page() use of the ZERO_PAGE; but this time avoid dirtying its struct page cacheline with (map)count updates - let vm_normal_page() regard it as abnormal. Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32, most powerpc): that's not essential, but minimizes additional branches (keeping them in the unlikely pte_special case); and incidentally excludes mips (some models of which needed eight colours of ZERO_PAGE to avoid costly exceptions). Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages() callers won't want to make exceptions for it, so increment its count there. Changes to mlock and migration? happily seems not needed. In most places it's quicker to check pfn than struct page address: prepare a __read_mostly zero_pfn for that. Does get_dump_page() still need its ZERO_PAGE check? probably not, but keep it anyway. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:03:30 +04:00
/*
* CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
*/
static int __init init_zero_pfn(void)
{
zero_pfn = page_to_pfn(ZERO_PAGE(0));
return 0;
}
mm: fix race by making init_zero_pfn() early_initcall There are code paths that rely on zero_pfn to be fully initialized before core_initcall. For example, wq_sysfs_init() is a core_initcall function that eventually results in a call to kernel_execve, which causes a page fault with a subsequent mmput. If zero_pfn is not initialized by then it may not get cleaned up properly and result in an error: BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:1 Here is an analysis of the race as seen on a MIPS device. On this particular MT7621 device (Ubiquiti ER-X), zero_pfn is PFN 0 until initialized, at which point it becomes PFN 5120: 1. wq_sysfs_init calls into kobject_uevent_env at core_initcall: kobject_uevent_env+0x7e4/0x7ec kset_register+0x68/0x88 bus_register+0xdc/0x34c subsys_virtual_register+0x34/0x78 wq_sysfs_init+0x1c/0x4c do_one_initcall+0x50/0x1a8 kernel_init_freeable+0x230/0x2c8 kernel_init+0x10/0x100 ret_from_kernel_thread+0x14/0x1c 2. kobject_uevent_env() calls call_usermodehelper_exec() which executes kernel_execve asynchronously. 3. Memory allocations in kernel_execve cause a page fault, bumping the MM reference counter: add_mm_counter_fast+0xb4/0xc0 handle_mm_fault+0x6e4/0xea0 __get_user_pages.part.78+0x190/0x37c __get_user_pages_remote+0x128/0x360 get_arg_page+0x34/0xa0 copy_string_kernel+0x194/0x2a4 kernel_execve+0x11c/0x298 call_usermodehelper_exec_async+0x114/0x194 4. In case zero_pfn has not been initialized yet, zap_pte_range does not decrement the MM_ANONPAGES RSS counter and the BUG message is triggered shortly afterwards when __mmdrop checks the ref counters: __mmdrop+0x98/0x1d0 free_bprm+0x44/0x118 kernel_execve+0x160/0x1d8 call_usermodehelper_exec_async+0x114/0x194 ret_from_kernel_thread+0x14/0x1c To avoid races such as described above, initialize init_zero_pfn at early_initcall level. Depending on the architecture, ZERO_PAGE is either constant or gets initialized even earlier, at paging_init, so there is no issue with initializing zero_pfn earlier. Link: https://lkml.kernel.org/r/CALCv0x2YqOXEAy2Q=hafjhHCtTHVodChv1qpM=niAXOpqEbt7w@mail.gmail.com Signed-off-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: stable@vger.kernel.org Tested-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-30 07:42:08 +03:00
early_initcall(init_zero_pfn);
rss_stat: add support to detect RSS updates of external mm When a process updates the RSS of a different process, the rss_stat tracepoint appears in the context of the process doing the update. This can confuse userspace that the RSS of process doing the update is updated, while in reality a different process's RSS was updated. This issue happens in reclaim paths such as with direct reclaim or background reclaim. This patch adds more information to the tracepoint about whether the mm being updated belongs to the current process's context (curr field). We also include a hash of the mm pointer so that the process who the mm belongs to can be uniquely identified (mm_id field). Also vsprintf.c is refactored a bit to allow reuse of hashing code. [akpm@linux-foundation.org: remove unused local `str'] [joelaf@google.com: inline call to ptr_to_hashval] Link: http://lore.kernel.org/r/20191113153816.14b95acd@gandalf.local.home Link: http://lkml.kernel.org/r/20191114164622.GC233237@google.com Link: http://lkml.kernel.org/r/20191106024452.81923-1-joel@joelfernandes.org Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Reported-by: Ioannis Ilkos <ilkos@google.com> Acked-by: Petr Mladek <pmladek@suse.com> [lib/vsprintf.c] Cc: Tim Murray <timmurray@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Carmen Jackson <carmenjackson@google.com> Cc: Mayank Gupta <mayankgupta@google.com> Cc: Daniel Colascione <dancol@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Minchan Kim <minchan@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:33 +03:00
void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
mm: emit tracepoint when RSS changes Useful to track how RSS is changing per TGID to detect spikes in RSS and memory hogs. Several Android teams have been using this patch in various kernel trees for half a year now. Many reported to me it is really useful so I'm posting it upstream. Initial patch developed by Tim Murray. Changes I made from original patch: o Prevent any additional space consumed by mm_struct. Regarding the fact that the RSS may change too often thus flooding the traces - note that, there is some "hysterisis" with this already. That is - We update the counter only if we receive 64 page faults due to SPLIT_RSS_ACCOUNTING. However, during zapping or copying of pte range, the RSS is updated immediately which can become noisy/flooding. In a previous discussion, we agreed that BPF or ftrace can be used to rate limit the signal if this becomes an issue. Also note that I added wrappers to trace_rss_stat to prevent compiler errors where linux/mm.h is included from tracing code, causing errors such as: CC kernel/trace/power-traces.o In file included from ./include/trace/define_trace.h:102, from ./include/trace/events/kmem.h:342, from ./include/linux/mm.h:31, from ./include/linux/ring_buffer.h:5, from ./include/linux/trace_events.h:6, from ./include/trace/events/power.h:12, from kernel/trace/power-traces.c:15: ./include/trace/trace_events.h:113:22: error: field `ent' has incomplete type struct trace_entry ent; \ Link: http://lore.kernel.org/r/20190903200905.198642-1-joel@joelfernandes.org Link: http://lkml.kernel.org/r/20191001172817.234886-1-joel@joelfernandes.org Co-developed-by: Tim Murray <timmurray@google.com> Signed-off-by: Tim Murray <timmurray@google.com> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Carmen Jackson <carmenjackson@google.com> Cc: Mayank Gupta <mayankgupta@google.com> Cc: Daniel Colascione <dancol@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Minchan Kim <minchan@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:30 +03:00
{
rss_stat: add support to detect RSS updates of external mm When a process updates the RSS of a different process, the rss_stat tracepoint appears in the context of the process doing the update. This can confuse userspace that the RSS of process doing the update is updated, while in reality a different process's RSS was updated. This issue happens in reclaim paths such as with direct reclaim or background reclaim. This patch adds more information to the tracepoint about whether the mm being updated belongs to the current process's context (curr field). We also include a hash of the mm pointer so that the process who the mm belongs to can be uniquely identified (mm_id field). Also vsprintf.c is refactored a bit to allow reuse of hashing code. [akpm@linux-foundation.org: remove unused local `str'] [joelaf@google.com: inline call to ptr_to_hashval] Link: http://lore.kernel.org/r/20191113153816.14b95acd@gandalf.local.home Link: http://lkml.kernel.org/r/20191114164622.GC233237@google.com Link: http://lkml.kernel.org/r/20191106024452.81923-1-joel@joelfernandes.org Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Reported-by: Ioannis Ilkos <ilkos@google.com> Acked-by: Petr Mladek <pmladek@suse.com> [lib/vsprintf.c] Cc: Tim Murray <timmurray@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Carmen Jackson <carmenjackson@google.com> Cc: Mayank Gupta <mayankgupta@google.com> Cc: Daniel Colascione <dancol@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Minchan Kim <minchan@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:33 +03:00
trace_rss_stat(mm, member, count);
mm: emit tracepoint when RSS changes Useful to track how RSS is changing per TGID to detect spikes in RSS and memory hogs. Several Android teams have been using this patch in various kernel trees for half a year now. Many reported to me it is really useful so I'm posting it upstream. Initial patch developed by Tim Murray. Changes I made from original patch: o Prevent any additional space consumed by mm_struct. Regarding the fact that the RSS may change too often thus flooding the traces - note that, there is some "hysterisis" with this already. That is - We update the counter only if we receive 64 page faults due to SPLIT_RSS_ACCOUNTING. However, during zapping or copying of pte range, the RSS is updated immediately which can become noisy/flooding. In a previous discussion, we agreed that BPF or ftrace can be used to rate limit the signal if this becomes an issue. Also note that I added wrappers to trace_rss_stat to prevent compiler errors where linux/mm.h is included from tracing code, causing errors such as: CC kernel/trace/power-traces.o In file included from ./include/trace/define_trace.h:102, from ./include/trace/events/kmem.h:342, from ./include/linux/mm.h:31, from ./include/linux/ring_buffer.h:5, from ./include/linux/trace_events.h:6, from ./include/trace/events/power.h:12, from kernel/trace/power-traces.c:15: ./include/trace/trace_events.h:113:22: error: field `ent' has incomplete type struct trace_entry ent; \ Link: http://lore.kernel.org/r/20190903200905.198642-1-joel@joelfernandes.org Link: http://lkml.kernel.org/r/20191001172817.234886-1-joel@joelfernandes.org Co-developed-by: Tim Murray <timmurray@google.com> Signed-off-by: Tim Murray <timmurray@google.com> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Carmen Jackson <carmenjackson@google.com> Cc: Mayank Gupta <mayankgupta@google.com> Cc: Daniel Colascione <dancol@google.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Minchan Kim <minchan@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:30 +03:00
}
#if defined(SPLIT_RSS_COUNTING)
void sync_mm_rss(struct mm_struct *mm)
{
int i;
for (i = 0; i < NR_MM_COUNTERS; i++) {
if (current->rss_stat.count[i]) {
add_mm_counter(mm, i, current->rss_stat.count[i]);
current->rss_stat.count[i] = 0;
}
}
current->rss_stat.events = 0;
}
static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
{
struct task_struct *task = current;
if (likely(task->mm == mm))
task->rss_stat.count[member] += val;
else
add_mm_counter(mm, member, val);
}
#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1)
#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1)
/* sync counter once per 64 page faults */
#define TASK_RSS_EVENTS_THRESH (64)
static void check_sync_rss_stat(struct task_struct *task)
{
if (unlikely(task != current))
return;
if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
sync_mm_rss(task->mm);
}
#else /* SPLIT_RSS_COUNTING */
#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
static void check_sync_rss_stat(struct task_struct *task)
{
}
#endif /* SPLIT_RSS_COUNTING */
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long addr)
{
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:22:04 +03:00
pgtable_t token = pmd_pgtable(*pmd);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
pmd_clear(pmd);
pte_free_tlb(tlb, token, addr);
mm_dec_nr_ptes(tlb->mm);
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
unsigned long start;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
start = addr;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
free_pte_range(tlb, pmd, addr);
} while (pmd++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
start &= PUD_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PUD_MASK;
if (!ceiling)
return;
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
if (end - 1 > ceiling - 1)
return;
pmd = pmd_offset(pud, start);
pud_clear(pud);
pmd_free_tlb(tlb, pmd, start);
mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/prctl.h> #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: David Rientjes <rientjes@google.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 02:26:50 +03:00
mm_dec_nr_pmds(tlb->mm);
}
static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
unsigned long start;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
start = addr;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
start &= P4D_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= P4D_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pud = pud_offset(p4d, start);
p4d_clear(p4d);
pud_free_tlb(tlb, pud, start);
mm_dec_nr_puds(tlb->mm);
}
static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
p4d_t *p4d;
unsigned long next;
unsigned long start;
start = addr;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d))
continue;
free_pud_range(tlb, p4d, addr, next, floor, ceiling);
} while (p4d++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
start &= PGDIR_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PGDIR_MASK;
if (!ceiling)
return;
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
if (end - 1 > ceiling - 1)
return;
p4d = p4d_offset(pgd, start);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
pgd_clear(pgd);
p4d_free_tlb(tlb, p4d, start);
}
/*
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
* This function frees user-level page tables of a process.
*/
void free_pgd_range(struct mmu_gather *tlb,
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
/*
* The next few lines have given us lots of grief...
*
* Why are we testing PMD* at this top level? Because often
* there will be no work to do at all, and we'd prefer not to
* go all the way down to the bottom just to discover that.
*
* Why all these "- 1"s? Because 0 represents both the bottom
* of the address space and the top of it (using -1 for the
* top wouldn't help much: the masks would do the wrong thing).
* The rule is that addr 0 and floor 0 refer to the bottom of
* the address space, but end 0 and ceiling 0 refer to the top
* Comparisons need to use "end - 1" and "ceiling - 1" (though
* that end 0 case should be mythical).
*
* Wherever addr is brought up or ceiling brought down, we must
* be careful to reject "the opposite 0" before it confuses the
* subsequent tests. But what about where end is brought down
* by PMD_SIZE below? no, end can't go down to 0 there.
*
* Whereas we round start (addr) and ceiling down, by different
* masks at different levels, in order to test whether a table
* now has no other vmas using it, so can be freed, we don't
* bother to round floor or end up - the tests don't need that.
*/
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
addr &= PMD_MASK;
if (addr < floor) {
addr += PMD_SIZE;
if (!addr)
return;
}
if (ceiling) {
ceiling &= PMD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
end -= PMD_SIZE;
if (addr > end - 1)
return;
/*
* We add page table cache pages with PAGE_SIZE,
* (see pte_free_tlb()), flush the tlb if we need
*/
tlb_change_page_size(tlb, PAGE_SIZE);
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
}
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long floor, unsigned long ceiling)
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
{
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
[PATCH] mm: unlink vma before pagetables In most places the descent from pgd to pud to pmd to pte holds mmap_sem (exclusively or not), which ensures that free_pgtables cannot be freeing page tables from any level at the same time. But truncation and reverse mapping descend without mmap_sem. No problem: just make sure that a vma is unlinked from its prio_tree (or nonlinear list) and from its anon_vma list, after zapping the vma, but before freeing its page tables. Then neither vmtruncate nor rmap can reach that vma whose page tables are now volatile (nor do they need to reach it, since all its page entries have been zapped by this stage). The i_mmap_lock and anon_vma->lock already serialize this correctly; but the locking hierarchy is such that we cannot take them while holding page_table_lock. Well, we're trying to push that down anyway. So in this patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the same time as moving page_table_lock around calls to unmap_vmas. tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but we made them preempt_disable and preempt_enable earlier; and a long source audit of all the architectures has shown no problem with removing page_table_lock from them. free_pgtables doesn't need page_table_lock for itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and vm_unacct_memory don't need page_table_lock either. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:29 +03:00
/*
* Hide vma from rmap and truncate_pagecache before freeing
* pgtables
[PATCH] mm: unlink vma before pagetables In most places the descent from pgd to pud to pmd to pte holds mmap_sem (exclusively or not), which ensures that free_pgtables cannot be freeing page tables from any level at the same time. But truncation and reverse mapping descend without mmap_sem. No problem: just make sure that a vma is unlinked from its prio_tree (or nonlinear list) and from its anon_vma list, after zapping the vma, but before freeing its page tables. Then neither vmtruncate nor rmap can reach that vma whose page tables are now volatile (nor do they need to reach it, since all its page entries have been zapped by this stage). The i_mmap_lock and anon_vma->lock already serialize this correctly; but the locking hierarchy is such that we cannot take them while holding page_table_lock. Well, we're trying to push that down anyway. So in this patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the same time as moving page_table_lock around calls to unmap_vmas. tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but we made them preempt_disable and preempt_enable earlier; and a long source audit of all the architectures has shown no problem with removing page_table_lock from them. free_pgtables doesn't need page_table_lock for itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and vm_unacct_memory don't need page_table_lock either. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:29 +03:00
*/
mm: change anon_vma linking to fix multi-process server scalability issue The old anon_vma code can lead to scalability issues with heavily forking workloads. Specifically, each anon_vma will be shared between the parent process and all its child processes. In a workload with 1000 child processes and a VMA with 1000 anonymous pages per process that get COWed, this leads to a system with a million anonymous pages in the same anon_vma, each of which is mapped in just one of the 1000 processes. However, the current rmap code needs to walk them all, leading to O(N) scanning complexity for each page. This can result in systems where one CPU is walking the page tables of 1000 processes in page_referenced_one, while all other CPUs are stuck on the anon_vma lock. This leads to catastrophic failure for a benchmark like AIM7, where the total number of processes can reach in the tens of thousands. Real workloads are still a factor 10 less process intensive than AIM7, but they are catching up. This patch changes the way anon_vmas and VMAs are linked, which allows us to associate multiple anon_vmas with a VMA. At fork time, each child process gets its own anon_vmas, in which its COWed pages will be instantiated. The parents' anon_vma is also linked to the VMA, because non-COWed pages could be present in any of the children. This reduces rmap scanning complexity to O(1) for the pages of the 1000 child processes, with O(N) complexity for at most 1/N pages in the system. This reduces the average scanning cost in heavily forking workloads from O(N) to 2. The only real complexity in this patch stems from the fact that linking a VMA to anon_vmas now involves memory allocations. This means vma_adjust can fail, if it needs to attach a VMA to anon_vma structures. This in turn means error handling needs to be added to the calling functions. A second source of complexity is that, because there can be multiple anon_vmas, the anon_vma linking in vma_adjust can no longer be done under "the" anon_vma lock. To prevent the rmap code from walking up an incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h to make sure it is impossible to compile a kernel that needs both symbolic values for the same bitflag. Some test results: Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test box with 16GB RAM and not quite enough IO), the system ends up running >99% in system time, with every CPU on the same anon_vma lock in the pageout code. With these changes, AIM7 hits the cross-over point around 29.7k users. This happens with ~99% IO wait time, there never seems to be any spike in system time. The anon_vma lock contention appears to be resolved. [akpm@linux-foundation.org: cleanups] Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 00:42:07 +03:00
unlink_anon_vmas(vma);
[PATCH] mm: unlink vma before pagetables In most places the descent from pgd to pud to pmd to pte holds mmap_sem (exclusively or not), which ensures that free_pgtables cannot be freeing page tables from any level at the same time. But truncation and reverse mapping descend without mmap_sem. No problem: just make sure that a vma is unlinked from its prio_tree (or nonlinear list) and from its anon_vma list, after zapping the vma, but before freeing its page tables. Then neither vmtruncate nor rmap can reach that vma whose page tables are now volatile (nor do they need to reach it, since all its page entries have been zapped by this stage). The i_mmap_lock and anon_vma->lock already serialize this correctly; but the locking hierarchy is such that we cannot take them while holding page_table_lock. Well, we're trying to push that down anyway. So in this patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the same time as moving page_table_lock around calls to unmap_vmas. tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but we made them preempt_disable and preempt_enable earlier; and a long source audit of all the architectures has shown no problem with removing page_table_lock from them. free_pgtables doesn't need page_table_lock for itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and vm_unacct_memory don't need page_table_lock either. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:29 +03:00
unlink_file_vma(vma);
[PATCH] hugepage: Fix hugepage logic in free_pgtables() free_pgtables() has special logic to call hugetlb_free_pgd_range() instead of the normal free_pgd_range() on hugepage VMAs. However, the test it uses to do so is incorrect: it calls is_hugepage_only_range on a hugepage sized range at the start of the vma. is_hugepage_only_range() will return true if the given range has any intersection with a hugepage address region, and in this case the given region need not be hugepage aligned. So, for example, this test can return true if called on, say, a 4k VMA immediately preceding a (nicely aligned) hugepage VMA. At present we get away with this because the powerpc version of hugetlb_free_pgd_range() is just a call to free_pgd_range(). On ia64 (the only other arch with a non-trivial is_hugepage_only_range()) we get away with it for a different reason; the hugepage area is not contiguous with the rest of the user address space, and VMAs are not permitted in between, so the test can't return a false positive there. Nonetheless this should be fixed. We do that in the patch below by replacing the is_hugepage_only_range() test with an explicit test of the VMA using is_vm_hugetlb_page(). This in turn changes behaviour for platforms where is_hugepage_only_range() returns false always (everything except powerpc and ia64). We address this by ensuring that hugetlb_free_pgd_range() is defined to be identical to free_pgd_range() (instead of a no-op) on everything except ia64. Even so, it will prevent some otherwise possible coalescing of calls down to free_pgd_range(). Since this only happens for hugepage VMAs, removing this small optimization seems unlikely to cause any trouble. This patch causes no regressions on the libhugetlbfs testsuite - ppc64 POWER5 (8-way), ppc64 G5 (2-way) and i386 Pentium M (UP). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Acked-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 11:08:57 +03:00
if (is_vm_hugetlb_page(vma)) {
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
floor, next ? next->vm_start : ceiling);
} else {
/*
* Optimization: gather nearby vmas into one call down
*/
while (next && next->vm_start <= vma->vm_end + PMD_SIZE
&& !is_vm_hugetlb_page(next)) {
vma = next;
next = vma->vm_next;
mm: change anon_vma linking to fix multi-process server scalability issue The old anon_vma code can lead to scalability issues with heavily forking workloads. Specifically, each anon_vma will be shared between the parent process and all its child processes. In a workload with 1000 child processes and a VMA with 1000 anonymous pages per process that get COWed, this leads to a system with a million anonymous pages in the same anon_vma, each of which is mapped in just one of the 1000 processes. However, the current rmap code needs to walk them all, leading to O(N) scanning complexity for each page. This can result in systems where one CPU is walking the page tables of 1000 processes in page_referenced_one, while all other CPUs are stuck on the anon_vma lock. This leads to catastrophic failure for a benchmark like AIM7, where the total number of processes can reach in the tens of thousands. Real workloads are still a factor 10 less process intensive than AIM7, but they are catching up. This patch changes the way anon_vmas and VMAs are linked, which allows us to associate multiple anon_vmas with a VMA. At fork time, each child process gets its own anon_vmas, in which its COWed pages will be instantiated. The parents' anon_vma is also linked to the VMA, because non-COWed pages could be present in any of the children. This reduces rmap scanning complexity to O(1) for the pages of the 1000 child processes, with O(N) complexity for at most 1/N pages in the system. This reduces the average scanning cost in heavily forking workloads from O(N) to 2. The only real complexity in this patch stems from the fact that linking a VMA to anon_vmas now involves memory allocations. This means vma_adjust can fail, if it needs to attach a VMA to anon_vma structures. This in turn means error handling needs to be added to the calling functions. A second source of complexity is that, because there can be multiple anon_vmas, the anon_vma linking in vma_adjust can no longer be done under "the" anon_vma lock. To prevent the rmap code from walking up an incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h to make sure it is impossible to compile a kernel that needs both symbolic values for the same bitflag. Some test results: Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test box with 16GB RAM and not quite enough IO), the system ends up running >99% in system time, with every CPU on the same anon_vma lock in the pageout code. With these changes, AIM7 hits the cross-over point around 29.7k users. This happens with ~99% IO wait time, there never seems to be any spike in system time. The anon_vma lock contention appears to be resolved. [akpm@linux-foundation.org: cleanups] Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 00:42:07 +03:00
unlink_anon_vmas(vma);
[PATCH] mm: unlink vma before pagetables In most places the descent from pgd to pud to pmd to pte holds mmap_sem (exclusively or not), which ensures that free_pgtables cannot be freeing page tables from any level at the same time. But truncation and reverse mapping descend without mmap_sem. No problem: just make sure that a vma is unlinked from its prio_tree (or nonlinear list) and from its anon_vma list, after zapping the vma, but before freeing its page tables. Then neither vmtruncate nor rmap can reach that vma whose page tables are now volatile (nor do they need to reach it, since all its page entries have been zapped by this stage). The i_mmap_lock and anon_vma->lock already serialize this correctly; but the locking hierarchy is such that we cannot take them while holding page_table_lock. Well, we're trying to push that down anyway. So in this patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the same time as moving page_table_lock around calls to unmap_vmas. tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but we made them preempt_disable and preempt_enable earlier; and a long source audit of all the architectures has shown no problem with removing page_table_lock from them. free_pgtables doesn't need page_table_lock for itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and vm_unacct_memory don't need page_table_lock either. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:29 +03:00
unlink_file_vma(vma);
}
free_pgd_range(tlb, addr, vma->vm_end,
floor, next ? next->vm_start : ceiling);
}
[PATCH] freepgt: free_pgtables use vma list Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-04-20 00:29:15 +04:00
vma = next;
}
}
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
{
spinlock_t *ptl = pmd_lock(mm, pmd);
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */
mm_inc_nr_ptes(mm);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
/*
* Ensure all pte setup (eg. pte page lock and page clearing) are
* visible before the pte is made visible to other CPUs by being
* put into page tables.
*
* The other side of the story is the pointer chasing in the page
* table walking code (when walking the page table without locking;
* ie. most of the time). Fortunately, these data accesses consist
* of a chain of data-dependent loads, meaning most CPUs (alpha
* being the notable exception) will already guarantee loads are
* seen in-order. See the alpha page table accessors for the
* smp_rmb() barriers in page table walking code.
*/
smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
pmd_populate(mm, pmd, *pte);
*pte = NULL;
}
spin_unlock(ptl);
}
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
{
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
pgtable_t new = pte_alloc_one(mm);
if (!new)
return -ENOMEM;
pmd_install(mm, pmd, &new);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:22:04 +03:00
if (new)
pte_free(mm, new);
return 0;
}
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
int __pte_alloc_kernel(pmd_t *pmd)
{
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
pte_t *new = pte_alloc_one_kernel(&init_mm);
if (!new)
return -ENOMEM;
spin_lock(&init_mm.page_table_lock);
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
smp_wmb(); /* See comment in pmd_install() */
pmd_populate_kernel(&init_mm, pmd, new);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:22:04 +03:00
new = NULL;
}
spin_unlock(&init_mm.page_table_lock);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:22:04 +03:00
if (new)
pte_free_kernel(&init_mm, new);
return 0;
}
static inline void init_rss_vec(int *rss)
{
memset(rss, 0, sizeof(int) * NR_MM_COUNTERS);
}
static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
{
int i;
if (current->mm == mm)
sync_mm_rss(mm);
for (i = 0; i < NR_MM_COUNTERS; i++)
if (rss[i])
add_mm_counter(mm, i, rss[i]);
}
2005-10-30 04:16:12 +03:00
/*
* This function is called to print an error when a bad pte
* is found. For example, we might have a PFN-mapped pte in
* a region that doesn't allow it.
2005-10-30 04:16:12 +03:00
*
* The calling function must still handle the error.
*/
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
2005-10-30 04:16:12 +03:00
{
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
p4d_t *p4d = p4d_offset(pgd, addr);
pud_t *pud = pud_offset(p4d, addr);
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
return;
}
if (nr_unshown) {
pr_alert("BUG: Bad page map: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
index = linear_page_index(vma, addr);
pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n",
current->comm,
(long long)pte_val(pte), (long long)pmd_val(*pmd));
if (page)
dump_page(page, "bad pte");
pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n",
(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
2019-03-25 22:32:28 +03:00
pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n",
vma->vm_file,
vma->vm_ops ? vma->vm_ops->fault : NULL,
vma->vm_file ? vma->vm_file->f_op->mmap : NULL,
mapping ? mapping->a_ops->readpage : NULL);
2005-10-30 04:16:12 +03:00
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
2005-10-30 04:16:12 +03:00
}
/*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* "Special" mappings do not wish to be associated with a "struct page" (either
* it doesn't exist, or it exists but they don't want to touch it). In this
* case, NULL is returned here. "Normal" mappings do have a struct page.
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* There are 2 broad cases. Firstly, an architecture may define a pte_special()
* pte bit, in which case this function is trivial. Secondly, an architecture
* may not have a spare pte bit, which requires a more complicated scheme,
* described below.
*
* A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
* special mapping (even if there are underlying and valid "struct pages").
* COWed pages of a VM_PFNMAP are always normal.
*
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
* The way we recognize COWed pages within VM_PFNMAP mappings is through the
* rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* set, and the vm_pgoff will point to the first PFN mapped: thus every special
* mapping will always honor the rule
*
* pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* And for normal mappings this is false.
*
* This restricts such mappings to be a linear translation from virtual address
* to pfn. To get around this restriction, we allow arbitrary mappings so long
* as the vma is not a COW mapping; in that case, we know that all ptes are
* special (because none can have been COWed).
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
*
*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
*
* VM_MIXEDMAP mappings can likewise contain memory with or without "struct
* page" backing, however the difference is that _all_ pages with a struct
* page (that is, those where pfn_valid is true) are refcounted and considered
* normal pages by the VM. The disadvantage is that pages are refcounted
* (which can be slower and simply not an option for some PFNMAP users). The
* advantage is that we don't have to follow the strict linearity rule of
* PFNMAP mappings in order to support COWable mappings.
*
*/
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) {
x86,mm: fix pte_special versus pte_numa Sasha Levin has shown oopses on ffffea0003480048 and ffffea0003480008 at mm/memory.c:1132, running Trinity on different 3.16-rc-next kernels: where zap_pte_range() checks page->mapping to see if PageAnon(page). Those addresses fit struct pages for pfns d2001 and d2000, and in each dump a register or a stack slot showed d2001730 or d2000730: pte flags 0x730 are PCD ACCESSED PROTNONE SPECIAL IOMAP; and Sasha's e820 map has a hole between cfffffff and 100000000, which would need special access. Commit c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") has broken vm_normal_page(): a PROTNONE SPECIAL pte no longer passes the pte_special() test, so zap_pte_range() goes on to try to access a non-existent struct page. Fix this by refining pte_special() (SPECIAL with PRESENT or PROTNONE) to complement pte_numa() (SPECIAL with neither PRESENT nor PROTNONE). A hint that this was a problem was that c46a7c817e66 added pte_numa() test to vm_normal_page(), and moved its is_zero_pfn() test from slow to fast path: This was papering over a pte_special() snag when the zero page was encountered during zap. This patch reverts vm_normal_page() to how it was before, relying on pte_special(). It still appears that this patch may be incomplete: aren't there other places which need to be handling PROTNONE along with PRESENT? For example, pte_mknuma() clears _PAGE_PRESENT and sets _PAGE_NUMA, but on a PROT_NONE area, that would make it pte_special(). This is side-stepped by the fact that NUMA hinting faults skipped PROT_NONE VMAs and there are no grounds where a NUMA hinting fault on a PROT_NONE VMA would be interesting. Fixes: c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") Reported-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: <stable@vger.kernel.org> [3.16] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-30 02:18:44 +04:00
if (likely(!pte_special(pte)))
goto check_pfn;
if (vma->vm_ops && vma->vm_ops->find_special_page)
return vma->vm_ops->find_special_page(vma, addr);
mm: reinstate ZERO_PAGE KAMEZAWA Hiroyuki has observed customers of earlier kernels taking advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from using in 2.6.24. And there were a couple of regression reports on LKML. Following suggestions from Linus, reinstate do_anonymous_page() use of the ZERO_PAGE; but this time avoid dirtying its struct page cacheline with (map)count updates - let vm_normal_page() regard it as abnormal. Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32, most powerpc): that's not essential, but minimizes additional branches (keeping them in the unlikely pte_special case); and incidentally excludes mips (some models of which needed eight colours of ZERO_PAGE to avoid costly exceptions). Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages() callers won't want to make exceptions for it, so increment its count there. Changes to mlock and migration? happily seems not needed. In most places it's quicker to check pfn than struct page address: prepare a __read_mostly zero_pfn for that. Does get_dump_page() still need its ZERO_PAGE check? probably not, but keep it anyway. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:03:30 +04:00
if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
if (is_zero_pfn(pfn))
return NULL;
dax: remove VM_MIXEDMAP for fsdax and device dax This patch is reworked from an earlier patch that Dan has posted: https://patchwork.kernel.org/patch/10131727/ VM_MIXEDMAP is used by dax to direct mm paths like vm_normal_page() that the memory page it is dealing with is not typical memory from the linear map. The get_user_pages_fast() path, since it does not resolve the vma, is already using {pte,pmd}_devmap() as a stand-in for VM_MIXEDMAP, so we use that as a VM_MIXEDMAP replacement in some locations. In the cases where there is no pte to consult we fallback to using vma_is_dax() to detect the VM_MIXEDMAP special case. Now that we have explicit driver pfn_t-flag opt-in/opt-out for get_user_pages() support for DAX we can stop setting VM_MIXEDMAP. This also means we no longer need to worry about safely manipulating vm_flags in a future where we support dynamically changing the dax mode of a file. DAX should also now be supported with madvise_behavior(), vma_merge(), and copy_page_range(). This patch has been tested against ndctl unit test. It has also been tested against xfstests commit: 625515d using fake pmem created by memmap and no additional issues have been observed. Link: http://lkml.kernel.org/r/152847720311.55924.16999195879201817653.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:43:40 +03:00
if (pte_devmap(pte))
return NULL;
print_bad_pte(vma, addr, pte, NULL);
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
return NULL;
}
/* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
goto out;
} else {
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
x86,mm: fix pte_special versus pte_numa Sasha Levin has shown oopses on ffffea0003480048 and ffffea0003480008 at mm/memory.c:1132, running Trinity on different 3.16-rc-next kernels: where zap_pte_range() checks page->mapping to see if PageAnon(page). Those addresses fit struct pages for pfns d2001 and d2000, and in each dump a register or a stack slot showed d2001730 or d2000730: pte flags 0x730 are PCD ACCESSED PROTNONE SPECIAL IOMAP; and Sasha's e820 map has a hole between cfffffff and 100000000, which would need special access. Commit c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") has broken vm_normal_page(): a PROTNONE SPECIAL pte no longer passes the pte_special() test, so zap_pte_range() goes on to try to access a non-existent struct page. Fix this by refining pte_special() (SPECIAL with PRESENT or PROTNONE) to complement pte_numa() (SPECIAL with neither PRESENT nor PROTNONE). A hint that this was a problem was that c46a7c817e66 added pte_numa() test to vm_normal_page(), and moved its is_zero_pfn() test from slow to fast path: This was papering over a pte_special() snag when the zero page was encountered during zap. This patch reverts vm_normal_page() to how it was before, relying on pte_special(). It still appears that this patch may be incomplete: aren't there other places which need to be handling PROTNONE along with PRESENT? For example, pte_mknuma() clears _PAGE_PRESENT and sets _PAGE_NUMA, but on a PROT_NONE area, that would make it pte_special(). This is side-stepped by the fact that NUMA hinting faults skipped PROT_NONE VMAs and there are no grounds where a NUMA hinting fault on a PROT_NONE VMA would be interesting. Fixes: c46a7c817e66 ("x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels") Reported-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: <stable@vger.kernel.org> [3.16] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-30 02:18:44 +04:00
if (is_zero_pfn(pfn))
return NULL;
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/*
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
mm: introduce VM_MIXEDMAP This series introduces some important infrastructure work. The overall result is that: 1. We now support XIP backed filesystems using memory that have no struct page allocated to them. And patches 6 and 7 actually implement this for s390. This is pretty important in a number of cases. As far as I understand, in the case of virtualisation (eg. s390), each guest may mount a readonly copy of the same filesystem (eg. the distro). Currently, guests need to allocate struct pages for this image. So if you have 100 guests, you already need to allocate more memory for the struct pages than the size of the image. I think. (Carsten?) For other (eg. embedded) systems, you may have a very large non- volatile filesystem. If you have to have struct pages for this, then your RAM consumption will go up proportionally to fs size. Even though it is just a small proportion, the RAM can be much more costly eg in terms of power, so every KB less that Linux uses makes it more attractive to a lot of these guys. 2. VM_MIXEDMAP allows us to support mappings where you actually do want to refcount _some_ pages in the mapping, but not others, and support COW on arbitrary (non-linear) mappings. Jared needs this for his NVRAM filesystem in progress. Future iterations of this filesystem will most likely want to migrate pages between pagecache and XIP backing, which is where the requirement for mixed (some refcounted, some not) comes from. 3. pte_special also has a peripheral usage that I need for my lockless get_user_pages patch. That was shown to speed up "oltp" on db2 by 10% on a 2 socket system, which is kind of significant because they scrounge for months to try to find 0.1% improvement on these workloads. I'm hoping we might finally be faster than AIX on pSeries with this :). My reference to lockless get_user_pages is not meant to justify this patchset (which doesn't include lockless gup), but just to show that pte_special is not some s390 specific thing that should be hidden in arch code or xip code: I definitely want to use it on at least x86 and powerpc as well. This patch: Introduce a new type of mapping, VM_MIXEDMAP. This is unlike VM_PFNMAP in that it can support COW mappings of arbitrary ranges including ranges without struct page *and* ranges with a struct page that we actually want to refcount (PFNMAP can only support COW in those cases where the un-COW-ed translations are mapped linearly in the virtual address, and can only support non refcounted ranges). VM_MIXEDMAP achieves this by refcounting all pfn_valid pages, and not refcounting !pfn_valid pages (which is not an option for VM_PFNMAP, because it needs to avoid refcounting pfn_valid pages eg. for /dev/mem mappings). Signed-off-by: Jared Hulbert <jaredeh@gmail.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:12:58 +04:00
out:
return pfn_to_page(pfn);
}
numa: fix /proc/<pid>/numa_maps for THP In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> [4.3+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-29 02:18:35 +03:00
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t pmd)
{
unsigned long pfn = pmd_pfn(pmd);
/*
* There is no pmd_special() but there may be special pmds, e.g.
* in a direct-access (dax) mapping, so let's just replicate the
* !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here.
numa: fix /proc/<pid>/numa_maps for THP In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> [4.3+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-29 02:18:35 +03:00
*/
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
goto out;
} else {
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
dax: remove VM_MIXEDMAP for fsdax and device dax This patch is reworked from an earlier patch that Dan has posted: https://patchwork.kernel.org/patch/10131727/ VM_MIXEDMAP is used by dax to direct mm paths like vm_normal_page() that the memory page it is dealing with is not typical memory from the linear map. The get_user_pages_fast() path, since it does not resolve the vma, is already using {pte,pmd}_devmap() as a stand-in for VM_MIXEDMAP, so we use that as a VM_MIXEDMAP replacement in some locations. In the cases where there is no pte to consult we fallback to using vma_is_dax() to detect the VM_MIXEDMAP special case. Now that we have explicit driver pfn_t-flag opt-in/opt-out for get_user_pages() support for DAX we can stop setting VM_MIXEDMAP. This also means we no longer need to worry about safely manipulating vm_flags in a future where we support dynamically changing the dax mode of a file. DAX should also now be supported with madvise_behavior(), vma_merge(), and copy_page_range(). This patch has been tested against ndctl unit test. It has also been tested against xfstests commit: 625515d using fake pmem created by memmap and no additional issues have been observed. Link: http://lkml.kernel.org/r/152847720311.55924.16999195879201817653.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:43:40 +03:00
if (pmd_devmap(pmd))
return NULL;
if (is_huge_zero_pmd(pmd))
numa: fix /proc/<pid>/numa_maps for THP In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> [4.3+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-29 02:18:35 +03:00
return NULL;
if (unlikely(pfn > highest_memmap_pfn))
return NULL;
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
out:
return pfn_to_page(pfn);
}
#endif
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
static void restore_exclusive_pte(struct vm_area_struct *vma,
struct page *page, unsigned long address,
pte_t *ptep)
{
pte_t pte;
swp_entry_t entry;
pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
if (pte_swp_soft_dirty(*ptep))
pte = pte_mksoft_dirty(pte);
entry = pte_to_swp_entry(*ptep);
if (pte_swp_uffd_wp(*ptep))
pte = pte_mkuffd_wp(pte);
else if (is_writable_device_exclusive_entry(entry))
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
/*
* No need to take a page reference as one was already
* created when the swap entry was made.
*/
if (PageAnon(page))
page_add_anon_rmap(page, vma, address, false);
else
/*
* Currently device exclusive access only supports anonymous
* memory so the entry shouldn't point to a filebacked page.
*/
WARN_ON_ONCE(!PageAnon(page));
mm: change page type prior to adding page table entry Patch series "page table check", v3. Ensure that some memory corruptions are prevented by checking at the time of insertion of entries into user page tables that there is no illegal sharing. We have recently found a problem [1] that existed in kernel since 4.14. The problem was caused by broken page ref count and led to memory leaking from one process into another. The problem was accidentally detected by studying a dump of one process and noticing that one page contains memory that should not belong to this process. There are some other page->_refcount related problems that were recently fixed: [2], [3] which potentially could also lead to illegal sharing. In addition to hardening refcount [4] itself, this work is an attempt to prevent this class of memory corruption issues. It uses a simple state machine that is independent from regular MM logic to check for illegal sharing at time pages are inserted and removed from page tables. [1] https://lore.kernel.org/all/xr9335nxwc5y.fsf@gthelen2.svl.corp.google.com [2] https://lore.kernel.org/all/1582661774-30925-2-git-send-email-akaher@vmware.com [3] https://lore.kernel.org/all/20210622021423.154662-3-mike.kravetz@oracle.com [4] https://lore.kernel.org/all/20211221150140.988298-1-pasha.tatashin@soleen.com This patch (of 4): There are a few places where we first update the entry in the user page table, and later change the struct page to indicate that this is anonymous or file page. In most places, however, we first configure the page metadata and then insert entries into the page table. Page table check, will use the information from struct page to verify the type of entry is inserted. Change the order in all places to first update struct page, and later to update page table. This means that we first do calls that may change the type of page (anon or file): page_move_anon_rmap page_add_anon_rmap do_page_add_anon_rmap page_add_new_anon_rmap page_add_file_rmap hugepage_add_anon_rmap hugepage_add_new_anon_rmap And after that do calls that add entries to the page table: set_huge_pte_at set_pte_at Link: https://lkml.kernel.org/r/20211221154650.1047963-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20211221154650.1047963-2-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: David Rientjes <rientjes@google.com> Cc: Paul Turner <pjt@google.com> Cc: Wei Xu <weixugc@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Will Deacon <will@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Sami Tolvanen <samitolvanen@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-15 01:06:29 +03:00
set_pte_at(vma->vm_mm, address, ptep, pte);
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
/*
* No need to invalidate - it was non-present before. However
* secondary CPUs may have mappings that need invalidating.
*/
update_mmu_cache(vma, address, ptep);
}
/*
* Tries to restore an exclusive pte if the page lock can be acquired without
* sleeping.
*/
static int
try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr)
{
swp_entry_t entry = pte_to_swp_entry(*src_pte);
struct page *page = pfn_swap_entry_to_page(entry);
if (trylock_page(page)) {
restore_exclusive_pte(vma, page, addr, src_pte);
unlock_page(page);
return 0;
}
return -EBUSY;
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*/
static unsigned long
copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma, unsigned long addr, int *rss)
{
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
unsigned long vm_flags = dst_vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
swp_entry_t entry = pte_to_swp_entry(pte);
if (likely(!non_swap_entry(entry))) {
if (swap_duplicate(entry) < 0)
return -EIO;
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
if (list_empty(&dst_mm->mmlist))
list_add(&dst_mm->mmlist,
&src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
rss[MM_SWAPENTS]++;
} else if (is_migration_entry(entry)) {
mm: remove special swap entry functions Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:06 +03:00
page = pfn_swap_entry_to_page(entry);
rss[mm_counter(page)]++;
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
if (is_writable_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
/*
* COW mappings require pages in both
* parent and child to be set to read.
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
*/
entry = make_readable_migration_entry(
swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(*src_pte))
pte = pte_swp_mksoft_dirty(pte);
if (pte_swp_uffd_wp(*src_pte))
pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
} else if (is_device_private_entry(entry)) {
mm: remove special swap entry functions Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:06 +03:00
page = pfn_swap_entry_to_page(entry);
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
/*
* Update rss count even for unaddressable pages, as
* they should treated just like normal pages in this
* respect.
*
* We will likely want to have some new rss counters
* for unaddressable pages, at some point. But for now
* keep things as they are.
*/
get_page(page);
rss[mm_counter(page)]++;
page_dup_rmap(page, false);
/*
* We do not preserve soft-dirty information, because so
* far, checkpoint/restore is the only feature that
* requires that. And checkpoint/restore does not work
* when a device driver is involved (you cannot easily
* save and restore device driver state).
*/
if (is_writable_device_private_entry(entry) &&
is_cow_mapping(vm_flags)) {
entry = make_readable_device_private_entry(
swp_offset(entry));
pte = swp_entry_to_pte(entry);
if (pte_swp_uffd_wp(*src_pte))
pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
} else if (is_device_exclusive_entry(entry)) {
/*
* Make device exclusive entries present by restoring the
* original entry then copying as for a present pte. Device
* exclusive entries currently only support private writable
* (ie. COW) mappings.
*/
VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags));
if (try_restore_exclusive_pte(src_pte, src_vma, addr))
return -EBUSY;
return -ENOENT;
}
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
if (!userfaultfd_wp(dst_vma))
pte = pte_swp_clear_uffd_wp(pte);
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
/*
* Copy a present and normal page if necessary.
*
* NOTE! The usual case is that this doesn't need to do
* anything, and can just return a positive value. That
* will let the caller know that it can just increase
* the page refcount and re-use the pte the traditional
* way.
*
* But _if_ we need to copy it because it needs to be
* pinned in the parent (and the child should get its own
* copy rather than just a reference to the same page),
* we'll do that here and return zero to let the caller
* know we're done.
*
* And if we need a pre-allocated page but don't yet have
* one, return a negative error to let the preallocation
* code know so that it can do so outside the page table
* lock.
*/
static inline int
copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
struct page **prealloc, pte_t pte, struct page *page)
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
{
struct page *new_page;
/*
* What we want to do is to check whether this page may
* have been pinned by the parent process. If so,
* instead of wrprotect the pte on both sides, we copy
* the page immediately so that we'll always guarantee
* the pinned page won't be randomly replaced in the
* future.
*
mm: avoid early COW write protect games during fork() In commit 70e806e4e645 ("mm: Do early cow for pinned pages during fork() for ptes") we write-protected the PTE before doing the page pinning check, in order to avoid a race with concurrent fast-GUP pinning (which doesn't take the mm semaphore or the page table lock). That trick doesn't actually work - it doesn't handle memory ordering properly, and doing so would be prohibitively expensive. It also isn't really needed. While we're moving in the direction of allowing and supporting page pinning without marking the pinned area with MADV_DONTFORK, the fact is that we've never really supported this kind of odd "concurrent fork() and page pinning", and doing the serialization on a pte level is just wrong. We can add serialization with a per-mm sequence counter, so we know how to solve that race properly, but we'll do that at a more appropriate time. Right now this just removes the write protect games. It also turns out that the write protect games actually break on Power, as reported by Aneesh Kumar: "Architecture like ppc64 expects set_pte_at to be not used for updating a valid pte. This is further explained in commit 56eecdb912b5 ("mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit")" and the code triggered a warning there: WARNING: CPU: 0 PID: 30613 at arch/powerpc/mm/pgtable.c:185 set_pte_at+0x2a8/0x3a0 arch/powerpc/mm/pgtable.c:185 Call Trace: copy_present_page mm/memory.c:857 [inline] copy_present_pte mm/memory.c:899 [inline] copy_pte_range mm/memory.c:1014 [inline] copy_pmd_range mm/memory.c:1092 [inline] copy_pud_range mm/memory.c:1127 [inline] copy_p4d_range mm/memory.c:1150 [inline] copy_page_range+0x1f6c/0x2cc0 mm/memory.c:1212 dup_mmap kernel/fork.c:592 [inline] dup_mm+0x77c/0xab0 kernel/fork.c:1355 copy_mm kernel/fork.c:1411 [inline] copy_process+0x1f00/0x2740 kernel/fork.c:2070 _do_fork+0xc4/0x10b0 kernel/fork.c:2429 Link: https://lore.kernel.org/lkml/CAHk-=wiWr+gO0Ro4LvnJBMs90OiePNyrE3E+pJvc9PzdBShdmw@mail.gmail.com/ Link: https://lore.kernel.org/linuxppc-dev/20201008092541.398079-1-aneesh.kumar@linux.ibm.com/ Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Tested-by: Leon Romanovsky <leonro@nvidia.com> Cc: Peter Xu <peterx@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-28 22:50:03 +03:00
* The page pinning checks are just "has this mm ever
* seen pinning", along with the (inexact) check of
* the page count. That might give false positives for
* for pinning, but it will work correctly.
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
*/
mm: introduce page_needs_cow_for_dma() for deciding whether cow We've got quite a few places (pte, pmd, pud) that explicitly checked against whether we should break the cow right now during fork(). It's easier to provide a helper, especially before we work the same thing on hugetlbfs. Since we'll reference is_cow_mapping() in mm.h, move it there too. Actually it suites mm.h more since internal.h is mm/ only, but mm.h is exported to the whole kernel. With that we should expect another patch to use is_cow_mapping() whenever we can across the kernel since we do use it quite a lot but it's always done with raw code against VM_* flags. Link: https://lkml.kernel.org/r/20210217233547.93892-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jason Gunthorpe <jgg@ziepe.ca> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: David Airlie <airlied@linux.ie> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Gal Pressman <galpress@amazon.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Roland Scheidegger <sroland@vmware.com> Cc: VMware Graphics <linux-graphics-maintainer@vmware.com> Cc: Wei Zhang <wzam@amazon.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-13 08:07:26 +03:00
if (likely(!page_needs_cow_for_dma(src_vma, page)))
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
return 1;
new_page = *prealloc;
if (!new_page)
return -EAGAIN;
/*
* We have a prealloc page, all good! Take it
* over and copy the page & arm it.
*/
*prealloc = NULL;
copy_user_highpage(new_page, page, addr, src_vma);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
__SetPageUptodate(new_page);
page_add_new_anon_rmap(new_page, dst_vma, addr, false);
lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
rss[mm_counter(new_page)]++;
/* All done, just insert the new page copy in the child */
pte = mk_pte(new_page, dst_vma->vm_page_prot);
pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
if (userfaultfd_pte_wp(dst_vma, *src_pte))
/* Uffd-wp needs to be delivered to dest pte as well */
pte = pte_wrprotect(pte_mkuffd_wp(pte));
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
return 0;
}
/*
* Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page
* is required to copy this pte.
*/
static inline int
copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
struct page **prealloc)
{
struct mm_struct *src_mm = src_vma->vm_mm;
unsigned long vm_flags = src_vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
page = vm_normal_page(src_vma, addr, pte);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
if (page) {
int retval;
retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
addr, rss, prealloc, pte, page);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
if (retval <= 0)
return retval;
get_page(page);
page_dup_rmap(page, false);
rss[mm_counter(page)]++;
}
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
if (is_cow_mapping(vm_flags) && pte_write(pte)) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = pte_wrprotect(pte);
}
/*
* If it's a shared mapping, mark it clean in
* the child
*/
if (vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
if (!userfaultfd_wp(dst_vma))
pte = pte_clear_uffd_wp(pte);
set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
return 0;
}
static inline struct page *
page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
unsigned long addr)
{
struct page *new_page;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr);
if (!new_page)
return NULL;
if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) {
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
put_page(new_page);
return NULL;
}
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
cgroup_throttle_swaprate(new_page, GFP_KERNEL);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
return new_page;
}
static int
copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
int progress, ret = 0;
int rss[NR_MM_COUNTERS];
swap_info: swap count continuations Swap is duplicated (reference count incremented by one) whenever the same swap page is inserted into another mm (when forking finds a swap entry in place of a pte, or when reclaim unmaps a pte to insert the swap entry). swap_info_struct's vmalloc'ed swap_map is the array of these reference counts: but what happens when the unsigned short (or unsigned char since the preceding patch) is full? (and its high bit is kept for a cache flag) We then lose track of it, never freeing, leaving it in use until swapoff: at which point we _hope_ that a single pass will have found all instances, assume there are no more, and will lose user data if we're wrong. Swapping of KSM pages has not yet been enabled; but it is implemented, and makes it very easy for a user to overflow the maximum swap count: possible with ordinary process pages, but unlikely, even when pid_max has been raised from PID_MAX_DEFAULT. This patch implements swap count continuations: when the count overflows, a continuation page is allocated and linked to the original vmalloc'ed map page, and this used to hold the continuation counts for that entry and its neighbours. These continuation pages are seldom referenced: the common paths all work on the original swap_map, only referring to a continuation page when the low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:58:46 +03:00
swp_entry_t entry = (swp_entry_t){0};
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
struct page *prealloc = NULL;
again:
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
progress = 0;
init_rss_vec(rss);
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
if (!dst_pte) {
ret = -ENOMEM;
goto out;
}
src_pte = pte_offset_map(src_pmd, addr);
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:40 +03:00
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
orig_src_pte = src_pte;
orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();
do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32) {
progress = 0;
if (need_resched() ||
spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
break;
}
if (pte_none(*src_pte)) {
progress++;
continue;
}
if (unlikely(!pte_present(*src_pte))) {
ret = copy_nonpresent_pte(dst_mm, src_mm,
dst_pte, src_pte,
dst_vma, src_vma,
addr, rss);
if (ret == -EIO) {
entry = pte_to_swp_entry(*src_pte);
break;
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
} else if (ret == -EBUSY) {
break;
} else if (!ret) {
progress += 8;
continue;
}
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
/*
* Device exclusive entry restored, continue by copying
* the now present pte.
*/
WARN_ON_ONCE(ret != -ENOENT);
}
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
/* copy_present_pte() will clear `*prealloc' if consumed */
ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
addr, rss, &prealloc);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
/*
* If we need a pre-allocated page for this pte, drop the
* locks, allocate, and try again.
*/
if (unlikely(ret == -EAGAIN))
break;
if (unlikely(prealloc)) {
/*
* pre-alloc page cannot be reused by next time so as
* to strictly follow mempolicy (e.g., alloc_page_vma()
* will allocate page according to address). This
* could only happen if one pinned pte changed.
*/
put_page(prealloc);
prealloc = NULL;
}
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
pte_unmap(orig_src_pte);
add_mm_rss_vec(dst_mm, rss);
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
swap_info: swap count continuations Swap is duplicated (reference count incremented by one) whenever the same swap page is inserted into another mm (when forking finds a swap entry in place of a pte, or when reclaim unmaps a pte to insert the swap entry). swap_info_struct's vmalloc'ed swap_map is the array of these reference counts: but what happens when the unsigned short (or unsigned char since the preceding patch) is full? (and its high bit is kept for a cache flag) We then lose track of it, never freeing, leaving it in use until swapoff: at which point we _hope_ that a single pass will have found all instances, assume there are no more, and will lose user data if we're wrong. Swapping of KSM pages has not yet been enabled; but it is implemented, and makes it very easy for a user to overflow the maximum swap count: possible with ordinary process pages, but unlikely, even when pid_max has been raised from PID_MAX_DEFAULT. This patch implements swap count continuations: when the count overflows, a continuation page is allocated and linked to the original vmalloc'ed map page, and this used to hold the continuation counts for that entry and its neighbours. These continuation pages are seldom referenced: the common paths all work on the original swap_map, only referring to a continuation page when the low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:58:46 +03:00
if (ret == -EIO) {
VM_WARN_ON_ONCE(!entry.val);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
ret = -ENOMEM;
goto out;
}
entry.val = 0;
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
} else if (ret == -EBUSY) {
goto out;
} else if (ret == -EAGAIN) {
prealloc = page_copy_prealloc(src_mm, src_vma, addr);
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
if (!prealloc)
swap_info: swap count continuations Swap is duplicated (reference count incremented by one) whenever the same swap page is inserted into another mm (when forking finds a swap entry in place of a pte, or when reclaim unmaps a pte to insert the swap entry). swap_info_struct's vmalloc'ed swap_map is the array of these reference counts: but what happens when the unsigned short (or unsigned char since the preceding patch) is full? (and its high bit is kept for a cache flag) We then lose track of it, never freeing, leaving it in use until swapoff: at which point we _hope_ that a single pass will have found all instances, assume there are no more, and will lose user data if we're wrong. Swapping of KSM pages has not yet been enabled; but it is implemented, and makes it very easy for a user to overflow the maximum swap count: possible with ordinary process pages, but unlikely, even when pid_max has been raised from PID_MAX_DEFAULT. This patch implements swap count continuations: when the count overflows, a continuation page is allocated and linked to the original vmalloc'ed map page, and this used to hold the continuation counts for that entry and its neighbours. These continuation pages are seldom referenced: the common paths all work on the original swap_map, only referring to a continuation page when the low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:58:46 +03:00
return -ENOMEM;
} else if (ret) {
VM_WARN_ON_ONCE(1);
swap_info: swap count continuations Swap is duplicated (reference count incremented by one) whenever the same swap page is inserted into another mm (when forking finds a swap entry in place of a pte, or when reclaim unmaps a pte to insert the swap entry). swap_info_struct's vmalloc'ed swap_map is the array of these reference counts: but what happens when the unsigned short (or unsigned char since the preceding patch) is full? (and its high bit is kept for a cache flag) We then lose track of it, never freeing, leaving it in use until swapoff: at which point we _hope_ that a single pass will have found all instances, assume there are no more, and will lose user data if we're wrong. Swapping of KSM pages has not yet been enabled; but it is implemented, and makes it very easy for a user to overflow the maximum swap count: possible with ordinary process pages, but unlikely, even when pid_max has been raised from PID_MAX_DEFAULT. This patch implements swap count continuations: when the count overflows, a continuation page is allocated and linked to the original vmalloc'ed map page, and this used to hold the continuation counts for that entry and its neighbours. These continuation pages are seldom referenced: the common paths all work on the original swap_map, only referring to a continuation page when the low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:58:46 +03:00
}
/* We've captured and resolved the error. Reset, try again. */
ret = 0;
if (addr != end)
goto again;
mm: Do early cow for pinned pages during fork() for ptes This allows copy_pte_range() to do early cow if the pages were pinned on the source mm. Currently we don't have an accurate way to know whether a page is pinned or not. The only thing we have is page_maybe_dma_pinned(). However that's good enough for now. Especially, with the newly added mm->has_pinned flag to make sure we won't affect processes that never pinned any pages. It would be easier if we can do GFP_KERNEL allocation within copy_one_pte(). Unluckily, we can't because we're with the page table locks held for both the parent and child processes. So the page allocation needs to be done outside copy_one_pte(). Some trick is there in copy_present_pte(), majorly the wrprotect trick to block concurrent fast-gup. Comments in the function should explain better in place. Oleg Nesterov reported a (probably harmless) bug during review that we didn't reset entry.val properly in copy_pte_range() so that potentially there's chance to call add_swap_count_continuation() multiple times on the same swp entry. However that should be harmless since even if it happens, the same function (add_swap_count_continuation()) will return directly noticing that there're enough space for the swp counter. So instead of a standalone stable patch, it is touched up in this patch directly. Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@nvidia.com/ Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-26 01:25:59 +03:00
out:
if (unlikely(prealloc))
put_page(prealloc);
return ret;
}
static inline int
copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
if (!dst_pmd)
return -ENOMEM;
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
mm: thp: check pmd migration entry in common path When THP migration is being used, memory management code needs to handle pmd migration entries properly. This patch uses !pmd_present() or is_swap_pmd() (depending on whether pmd_none() needs separate code or not) to check pmd migration entries at the places where a pmd entry is present. Since pmd-related code uses split_huge_page(), split_huge_pmd(), pmd_trans_huge(), pmd_trans_unstable(), or pmd_none_or_trans_huge_or_clear_bad(), this patch: 1. adds pmd migration entry split code in split_huge_pmd(), 2. takes care of pmd migration entries whenever pmd_trans_huge() is present, 3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware. Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable() is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change them. Until this commit, a pmd entry should be: 1. pointing to a pte page, 2. is_swap_pmd(), 3. pmd_trans_huge(), 4. pmd_devmap(), or 5. pmd_none(). Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:01 +03:00
if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
|| pmd_devmap(*src_pmd)) {
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu <peterx@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:02 +03:00
err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
addr, dst_vma, src_vma);
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
continue;
/* fall through */
}
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd,
addr, next))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
}
static inline int
copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
pud_t *src_pud, *dst_pud;
unsigned long next;
dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
if (!dst_pud)
return -ENOMEM;
src_pud = pud_offset(src_p4d, addr);
do {
next = pud_addr_end(addr, end);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
err = copy_huge_pud(dst_mm, src_mm,
dst_pud, src_pud, addr, src_vma);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
continue;
/* fall through */
}
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud,
addr, next))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
}
static inline int
copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr,
unsigned long end)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
p4d_t *src_p4d, *dst_p4d;
unsigned long next;
dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
if (!dst_p4d)
return -ENOMEM;
src_p4d = p4d_offset(src_pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(src_p4d))
continue;
if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d,
addr, next))
return -ENOMEM;
} while (dst_p4d++, src_p4d++, addr = next, addr != end);
return 0;
}
int
copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long next;
unsigned long addr = src_vma->vm_start;
unsigned long end = src_vma->vm_end;
struct mm_struct *dst_mm = dst_vma->vm_mm;
struct mm_struct *src_mm = src_vma->vm_mm;
struct mmu_notifier_range range;
mm: move all mmu notifier invocations to be done outside the PT lock In order to allow sleeping during mmu notifier calls, we need to avoid invoking them under the page table spinlock. This patch solves the problem by calling invalidate_page notification after releasing the lock (but before freeing the page itself), or by wrapping the page invalidation with calls to invalidate_range_begin and invalidate_range_end. To prevent accidental changes to the invalidate_range_end arguments after the call to invalidate_range_begin, the patch introduces a convention of saving the arguments in consistently named locals: unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ ... mmun_start = ... mmun_end = ... mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ... mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); The patch changes code to use this convention for all calls to mmu_notifier_invalidate_range_start/end, except those where the calls are close enough so that anyone who glances at the code can see the values aren't changing. This patchset is a preliminary step towards on-demand paging design to be added to the RDMA stack. Why do we want on-demand paging for Infiniband? Applications register memory with an RDMA adapter using system calls, and subsequently post IO operations that refer to the corresponding virtual addresses directly to HW. Until now, this was achieved by pinning the memory during the registration calls. The goal of on demand paging is to avoid pinning the pages of registered memory regions (MRs). This will allow users the same flexibility they get when swapping any other part of their processes address spaces. Instead of requiring the entire MR to fit in physical memory, we can allow the MR to be larger, and only fit the current working set in physical memory. Why should anyone care? What problems are users currently experiencing? This can make programming with RDMA much simpler. Today, developers that are working with more data than their RAM can hold need either to deregister and reregister memory regions throughout their process's life, or keep a single memory region and copy the data to it. On demand paging will allow these developers to register a single MR at the beginning of their process's life, and let the operating system manage which pages needs to be fetched at a given time. In the future, we might be able to provide a single memory access key for each process that would provide the entire process's address as one large memory region, and the developers wouldn't need to register memory regions at all. Is there any prospect that any other subsystems will utilise these infrastructural changes? If so, which and how, etc? As for other subsystems, I understand that XPMEM wanted to sleep in MMU notifiers, as Christoph Lameter wrote at http://lkml.indiana.edu/hypermail/linux/kernel/0802.1/0460.html and perhaps Andrea knows about other use cases. Scheduling in mmu notifications is required since we need to sync the hardware with the secondary page tables change. A TLB flush of an IO device is inherently slower than a CPU TLB flush, so our design works by sending the invalidation request to the device, and waiting for an interrupt before exiting the mmu notifier handler. Avi said: kvm may be a buyer. kvm::mmu_lock, which serializes guest page faults, also protects long operations such as destroying large ranges. It would be good to convert it into a spinlock, but as it is used inside mmu notifiers, this cannot be done. (there are alternatives, such as keeping the spinlock and using a generation counter to do the teardown in O(1), which is what the "may" is doing up there). [akpm@linux-foundation.orgpossible speed tweak in hugetlb_cow(), cleanups] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Haggai Eran <haggaie@mellanox.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Haggai Eran <haggaie@mellanox.com> Cc: Shachar Raindel <raindel@mellanox.com> Cc: Liran Liss <liranl@mellanox.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Avi Kivity <avi@redhat.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:33:33 +04:00
bool is_cow;
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
int ret;
/*
* Don't copy ptes where a page fault will fill them correctly.
* Fork becomes much lighter when there are big shared or private
* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
!src_vma->anon_vma)
return 0;
if (is_vm_hugetlb_page(src_vma))
return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
/*
* We do not free on error cases below as remove_vma
* gets called on error from higher level routine
*/
ret = track_pfn_copy(src_vma);
if (ret)
return ret;
}
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
/*
* We need to invalidate the secondary MMU mappings only when
* there could be a permission downgrade on the ptes of the
* parent mm. And a permission downgrade will only happen if
* is_cow_mapping() returns true.
*/
is_cow = is_cow_mapping(src_vma->vm_flags);
if (is_cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
0, src_vma, src_mm, addr, end);
mmu_notifier_invalidate_range_start(&range);
mm/gup: prevent gup_fast from racing with COW during fork Since commit 70e806e4e645 ("mm: Do early cow for pinned pages during fork() for ptes") pages under a FOLL_PIN will not be write protected during COW for fork. This means that pages returned from pin_user_pages(FOLL_WRITE) should not become write protected while the pin is active. However, there is a small race where get_user_pages_fast(FOLL_PIN) can establish a FOLL_PIN at the same time copy_present_page() is write protecting it: CPU 0 CPU 1 get_user_pages_fast() internal_get_user_pages_fast() copy_page_range() pte_alloc_map_lock() copy_present_page() atomic_read(has_pinned) == 0 page_maybe_dma_pinned() == false atomic_set(has_pinned, 1); gup_pgd_range() gup_pte_range() pte_t pte = gup_get_pte(ptep) pte_access_permitted(pte) try_grab_compound_head() pte = pte_wrprotect(pte) set_pte_at(); pte_unmap_unlock() // GUP now returns with a write protected page The first attempt to resolve this by using the write protect caused problems (and was missing a barrrier), see commit f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Instead wrap copy_p4d_range() with the write side of a seqcount and check the read side around gup_pgd_range(). If there is a collision then get_user_pages_fast() fails and falls back to slow GUP. Slow GUP is safe against this race because copy_page_range() is only called while holding the exclusive side of the mmap_lock on the src mm_struct. [akpm@linux-foundation.org: coding style fixes] Link: https://lore.kernel.org/r/CAHk-=wi=iCnYCARbPGjkVJu9eyYeZ13N64tZYLdOB8CP5Q_PLw@mail.gmail.com Link: https://lkml.kernel.org/r/2-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com Fixes: f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Peter Xu <peterx@redhat.com> Acked-by: "Ahmed S. Darwish" <a.darwish@linutronix.de> [seqcount_t parts] Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hugh Dickins <hughd@google.com> Cc: Jann Horn <jannh@google.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Leon Romanovsky <leonro@nvidia.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 06:05:44 +03:00
/*
* Disabling preemption is not needed for the write side, as
* the read side doesn't spin, but goes to the mmap_lock.
*
* Use the raw variant of the seqcount_t write API to avoid
* lockdep complaining about preemptibility.
*/
mmap_assert_write_locked(src_mm);
raw_write_seqcount_begin(&src_mm->write_protect_seq);
}
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
ret = 0;
dst_pgd = pgd_offset(dst_mm, addr);
src_pgd = pgd_offset(src_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
addr, next))) {
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
ret = -ENOMEM;
break;
}
} while (dst_pgd++, src_pgd++, addr = next, addr != end);
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
mm/gup: prevent gup_fast from racing with COW during fork Since commit 70e806e4e645 ("mm: Do early cow for pinned pages during fork() for ptes") pages under a FOLL_PIN will not be write protected during COW for fork. This means that pages returned from pin_user_pages(FOLL_WRITE) should not become write protected while the pin is active. However, there is a small race where get_user_pages_fast(FOLL_PIN) can establish a FOLL_PIN at the same time copy_present_page() is write protecting it: CPU 0 CPU 1 get_user_pages_fast() internal_get_user_pages_fast() copy_page_range() pte_alloc_map_lock() copy_present_page() atomic_read(has_pinned) == 0 page_maybe_dma_pinned() == false atomic_set(has_pinned, 1); gup_pgd_range() gup_pte_range() pte_t pte = gup_get_pte(ptep) pte_access_permitted(pte) try_grab_compound_head() pte = pte_wrprotect(pte) set_pte_at(); pte_unmap_unlock() // GUP now returns with a write protected page The first attempt to resolve this by using the write protect caused problems (and was missing a barrrier), see commit f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Instead wrap copy_p4d_range() with the write side of a seqcount and check the read side around gup_pgd_range(). If there is a collision then get_user_pages_fast() fails and falls back to slow GUP. Slow GUP is safe against this race because copy_page_range() is only called while holding the exclusive side of the mmap_lock on the src mm_struct. [akpm@linux-foundation.org: coding style fixes] Link: https://lore.kernel.org/r/CAHk-=wi=iCnYCARbPGjkVJu9eyYeZ13N64tZYLdOB8CP5Q_PLw@mail.gmail.com Link: https://lkml.kernel.org/r/2-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com Fixes: f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Peter Xu <peterx@redhat.com> Acked-by: "Ahmed S. Darwish" <a.darwish@linutronix.de> [seqcount_t parts] Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hugh Dickins <hughd@google.com> Cc: Jann Horn <jannh@google.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Leon Romanovsky <leonro@nvidia.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 06:05:44 +03:00
if (is_cow) {
raw_write_seqcount_end(&src_mm->write_protect_seq);
mmu_notifier_invalidate_range_end(&range);
mm/gup: prevent gup_fast from racing with COW during fork Since commit 70e806e4e645 ("mm: Do early cow for pinned pages during fork() for ptes") pages under a FOLL_PIN will not be write protected during COW for fork. This means that pages returned from pin_user_pages(FOLL_WRITE) should not become write protected while the pin is active. However, there is a small race where get_user_pages_fast(FOLL_PIN) can establish a FOLL_PIN at the same time copy_present_page() is write protecting it: CPU 0 CPU 1 get_user_pages_fast() internal_get_user_pages_fast() copy_page_range() pte_alloc_map_lock() copy_present_page() atomic_read(has_pinned) == 0 page_maybe_dma_pinned() == false atomic_set(has_pinned, 1); gup_pgd_range() gup_pte_range() pte_t pte = gup_get_pte(ptep) pte_access_permitted(pte) try_grab_compound_head() pte = pte_wrprotect(pte) set_pte_at(); pte_unmap_unlock() // GUP now returns with a write protected page The first attempt to resolve this by using the write protect caused problems (and was missing a barrrier), see commit f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Instead wrap copy_p4d_range() with the write side of a seqcount and check the read side around gup_pgd_range(). If there is a collision then get_user_pages_fast() fails and falls back to slow GUP. Slow GUP is safe against this race because copy_page_range() is only called while holding the exclusive side of the mmap_lock on the src mm_struct. [akpm@linux-foundation.org: coding style fixes] Link: https://lore.kernel.org/r/CAHk-=wi=iCnYCARbPGjkVJu9eyYeZ13N64tZYLdOB8CP5Q_PLw@mail.gmail.com Link: https://lkml.kernel.org/r/2-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com Fixes: f3c64eda3e50 ("mm: avoid early COW write protect games during fork()") Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Peter Xu <peterx@redhat.com> Acked-by: "Ahmed S. Darwish" <a.darwish@linutronix.de> [seqcount_t parts] Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hugh Dickins <hughd@google.com> Cc: Jann Horn <jannh@google.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Leon Romanovsky <leonro@nvidia.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 06:05:44 +03:00
}
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 02:46:29 +04:00
return ret;
}
/*
* Parameter block passed down to zap_pte_range in exceptional cases.
*/
struct zap_details {
struct folio *single_folio; /* Locked folio to be unmapped */
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
bool even_cows; /* Zap COWed private pages too? */
};
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
/* Whether we should zap all COWed (private) pages too */
static inline bool should_zap_cows(struct zap_details *details)
{
/* By default, zap all pages */
if (!details)
return true;
/* Or, we zap COWed pages only if the caller wants to */
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
return details->even_cows;
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
}
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
/* Decides whether we should zap this page with the page pointer specified */
static inline bool should_zap_page(struct zap_details *details, struct page *page)
{
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
/* If we can make a decision without *page.. */
if (should_zap_cows(details))
return true;
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
/* E.g. the caller passes NULL for the case of a zero page */
if (!page)
return true;
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
/* Otherwise we should only zap non-anon pages */
return !PageAnon(page);
}
static unsigned long zap_pte_range(struct mmu_gather *tlb,
2005-10-30 04:16:12 +03:00
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
2005-10-30 04:16:12 +03:00
struct mm_struct *mm = tlb->mm;
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
int force_flush = 0;
int rss[NR_MM_COUNTERS];
spinlock_t *ptl;
mm: fix wrong kunmap_atomic() pointer Running a ktest.pl test, I hit the following bug on x86_32: ------------[ cut here ]------------ WARNING: at arch/x86/mm/highmem_32.c:81 __kunmap_atomic+0x64/0xc1() Hardware name: Modules linked in: Pid: 93, comm: sh Not tainted 2.6.39-test+ #1 Call Trace: [<c04450da>] warn_slowpath_common+0x7c/0x91 [<c042f5df>] ? __kunmap_atomic+0x64/0xc1 [<c042f5df>] ? __kunmap_atomic+0x64/0xc1^M [<c0445111>] warn_slowpath_null+0x22/0x24 [<c042f5df>] __kunmap_atomic+0x64/0xc1 [<c04d4a22>] unmap_vmas+0x43a/0x4e0 [<c04d9065>] exit_mmap+0x91/0xd2 [<c0443057>] mmput+0x43/0xad [<c0448358>] exit_mm+0x111/0x119 [<c044855f>] do_exit+0x1ff/0x5fa [<c0454ea2>] ? set_current_blocked+0x3c/0x40 [<c0454f24>] ? sigprocmask+0x7e/0x8e [<c0448b55>] do_group_exit+0x65/0x88 [<c0448b90>] sys_exit_group+0x18/0x1c [<c0c3915f>] sysenter_do_call+0x12/0x38 ---[ end trace 8055f74ea3c0eb62 ]--- Running a ktest.pl git bisect, found the culprit: commit e303297e6c3a ("mm: extended batches for generic mmu_gather") But although this was the commit triggering the bug, it was not the one originally responsible for the bug. That was commit d16dfc550f53 ("mm: mmu_gather rework"). The code in zap_pte_range() has something that looks like the following: pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { [...] } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(pte - 1, ptl); The pte starts off pointing at the first element in the page table directory that was returned by the pte_offset_map_lock(). When it's done with the page, pte will be pointing to anything between the next entry and the first entry of the next page inclusive. By doing a pte - 1, this puts the pte back onto the original page, which is all that pte_unmap_unlock() needs. In most archs (64 bit), this is not an issue as the pte is ignored in the pte_unmap_unlock(). But on 32 bit archs, where things may be kmapped, it is essential that the pte passed to pte_unmap_unlock() resides on the same page that was given by pte_offest_map_lock(). The problem came in d16dfc55 ("mm: mmu_gather rework") where it introduced a "break;" from the while loop. This alone did not seem to easily trigger the bug. But the modifications made by e303297e6 caused that "break;" to be hit on the first iteration, before the pte++. The pte not being incremented will now cause pte_unmap_unlock(pte - 1) to be pointing to the previous page. This will cause the wrong page to be unmapped, and also trigger the warning above. The simple solution is to just save the pointer given by pte_offset_map_lock() and use it in the unlock. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-06-16 02:08:23 +04:00
pte_t *start_pte;
pte_t *pte;
swp_entry_t entry;
tlb_change_page_size(tlb, PAGE_SIZE);
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
again:
init_rss_vec(rss);
mm: fix wrong kunmap_atomic() pointer Running a ktest.pl test, I hit the following bug on x86_32: ------------[ cut here ]------------ WARNING: at arch/x86/mm/highmem_32.c:81 __kunmap_atomic+0x64/0xc1() Hardware name: Modules linked in: Pid: 93, comm: sh Not tainted 2.6.39-test+ #1 Call Trace: [<c04450da>] warn_slowpath_common+0x7c/0x91 [<c042f5df>] ? __kunmap_atomic+0x64/0xc1 [<c042f5df>] ? __kunmap_atomic+0x64/0xc1^M [<c0445111>] warn_slowpath_null+0x22/0x24 [<c042f5df>] __kunmap_atomic+0x64/0xc1 [<c04d4a22>] unmap_vmas+0x43a/0x4e0 [<c04d9065>] exit_mmap+0x91/0xd2 [<c0443057>] mmput+0x43/0xad [<c0448358>] exit_mm+0x111/0x119 [<c044855f>] do_exit+0x1ff/0x5fa [<c0454ea2>] ? set_current_blocked+0x3c/0x40 [<c0454f24>] ? sigprocmask+0x7e/0x8e [<c0448b55>] do_group_exit+0x65/0x88 [<c0448b90>] sys_exit_group+0x18/0x1c [<c0c3915f>] sysenter_do_call+0x12/0x38 ---[ end trace 8055f74ea3c0eb62 ]--- Running a ktest.pl git bisect, found the culprit: commit e303297e6c3a ("mm: extended batches for generic mmu_gather") But although this was the commit triggering the bug, it was not the one originally responsible for the bug. That was commit d16dfc550f53 ("mm: mmu_gather rework"). The code in zap_pte_range() has something that looks like the following: pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { [...] } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(pte - 1, ptl); The pte starts off pointing at the first element in the page table directory that was returned by the pte_offset_map_lock(). When it's done with the page, pte will be pointing to anything between the next entry and the first entry of the next page inclusive. By doing a pte - 1, this puts the pte back onto the original page, which is all that pte_unmap_unlock() needs. In most archs (64 bit), this is not an issue as the pte is ignored in the pte_unmap_unlock(). But on 32 bit archs, where things may be kmapped, it is essential that the pte passed to pte_unmap_unlock() resides on the same page that was given by pte_offest_map_lock(). The problem came in d16dfc55 ("mm: mmu_gather rework") where it introduced a "break;" from the while loop. This alone did not seem to easily trigger the bug. But the modifications made by e303297e6 caused that "break;" to be hit on the first iteration, before the pte++. The pte not being incremented will now cause pte_unmap_unlock(pte - 1) to be pointing to the previous page. This will cause the wrong page to be unmapped, and also trigger the warning above. The simple solution is to just save the pointer given by pte_offset_map_lock() and use it in the unlock. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-06-16 02:08:23 +04:00
start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
pte = start_pte;
mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries Nadav Amit identified a theoritical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. For some operations like mprotect, it's not necessarily a data integrity issue but it is a correctness issue as there is a window where an mprotect that limits access still allows access. For munmap, it's potentially a data integrity issue although the race is massive as an munmap, mmap and return to userspace must all complete between the window when reclaim drops the PTL and flushes the TLB. However, it's theoritically possible so handle this issue by flushing the mm if reclaim is potentially currently batching TLB flushes. Other instances where a flush is required for a present pte should be ok as either the page lock is held preventing parallel reclaim or a page reference count is elevated preventing a parallel free leading to corruption. In the case of page_mkclean there isn't an obvious path that userspace could take advantage of without using the operations that are guarded by this patch. Other users such as gup as a race with reclaim looks just at PTEs. huge page variants should be ok as they don't race with reclaim. mincore only looks at PTEs. userfault also should be ok as if a parallel reclaim takes place, it will either fault the page back in or read some of the data before the flush occurs triggering a fault. Note that a variant of this patch was acked by Andy Lutomirski but this was for the x86 parts on top of his PCID work which didn't make the 4.13 merge window as expected. His ack is dropped from this version and there will be a follow-on patch on top of PCID that will include his ack. [akpm@linux-foundation.org: tweak comments] [akpm@linux-foundation.org: fix spello] Link: http://lkml.kernel.org/r/20170717155523.emckq2esjro6hf3z@suse.de Reported-by: Nadav Amit <nadav.amit@gmail.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: <stable@vger.kernel.org> [v4.4+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-02 23:31:52 +03:00
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
do {
pte_t ptent = *pte;
struct page *page;
if (pte_none(ptent))
continue;
mm: release the spinlock on zap_pte_range In our testing (camera recording), Miguel and Wei found unmap_page_range() takes above 6ms with preemption disabled easily. When I see that, the reason is it holds page table spinlock during entire 512 page operation in a PMD. 6.2ms is never trivial for user experince if RT task couldn't run in the time because it could make frame drop or glitch audio problem. I had a time to benchmark it via adding some trace_printk hooks between pte_offset_map_lock and pte_unmap_unlock in zap_pte_range. The testing device is 2018 premium mobile device. I can get 2ms delay rather easily to release 2M(ie, 512 pages) when the task runs on little core even though it doesn't have any IPI and LRU lock contention. It's already too heavy. If I remove activate_page, 35-40% overhead of zap_pte_range is gone so most of overhead(about 0.7ms) comes from activate_page via mark_page_accessed. Thus, if there are LRU contention, that 0.7ms could accumulate up to several ms. So this patch adds a check for need_resched() in the loop, and a preemption point if necessary. Link: http://lkml.kernel.org/r/20190731061440.GC155569@google.com Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: Miguel de Dios <migueldedios@google.com> Reported-by: Wei Wang <wvw@google.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 03:02:24 +03:00
if (need_resched())
break;
if (pte_present(ptent)) {
page = vm_normal_page(vma, addr, ptent);
if (unlikely(!should_zap_page(details, page)))
continue;
2005-10-30 04:16:12 +03:00
ptent = ptep_get_and_clear_full(mm, addr, pte,
2005-09-04 02:55:04 +04:00
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
if (!PageAnon(page)) {
if (pte_dirty(ptent)) {
force_flush = 1;
set_page_dirty(page);
}
if (pte_young(ptent) &&
likely(!(vma->vm_flags & VM_SEQ_READ)))
mark_page_accessed(page);
}
rss[mm_counter(page)]--;
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
page_remove_rmap(page, vma, false);
badpage: replace page_remove_rmap Eeek and BUG Now that bad pages are kept out of circulation, there is no need for the infamous page_remove_rmap() BUG() - once that page is freed, its negative mapcount will issue a "Bad page state" message and the page won't be freed. Removing the BUG() allows more info, on subsequent pages, to be gathered. We do have more info about the page at this point than bad_page() can know - notably, what the pmd is, which might pinpoint something like low 64kB corruption - but page_remove_rmap() isn't given the address to find that. In practice, there is only one call to page_remove_rmap() which has ever reported anything, that from zap_pte_range() (usually on exit, sometimes on munmap). It has all the info, so remove page_remove_rmap()'s "Eeek" message and leave it all to zap_pte_range(). mm/memory.c already has a hardly used print_bad_pte() function, showing some of the appropriate info: extend it to show what we want for the rmap case: pte info, page info (when there is a page) and vma info to compare. zap_pte_range() already knows the pmd, but print_bad_pte() is easier to use if it works that out for itself. Some of this info is also shown in bad_page()'s "Bad page state" message. Keep them separate, but adjust them to match each other as far as possible. Say "Bad page map" in print_bad_pte(), and add a TAINT_BAD_PAGE there too. print_bad_pte() show current->comm unconditionally (though it should get repeated in the usually irrelevant stack trace): sorry, I misled Nick Piggin to make it conditional on vm_mm == current->mm, but current->mm is already NULL in the exit case. Usually current->comm is good, though exceptionally it may not be that of the mm (when "swapoff" for example). Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 01:40:08 +03:00
if (unlikely(page_mapcount(page) < 0))
print_bad_pte(vma, addr, ptent, page);
mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 01:24:09 +03:00
if (unlikely(__tlb_remove_page(tlb, page))) {
force_flush = 1;
addr += PAGE_SIZE;
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
break;
}
continue;
}
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
entry = pte_to_swp_entry(ptent);
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
if (is_device_private_entry(entry) ||
is_device_exclusive_entry(entry)) {
page = pfn_swap_entry_to_page(entry);
if (unlikely(!should_zap_page(details, page)))
continue;
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
rss[mm_counter(page)]--;
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
if (is_device_private_entry(entry))
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
page_remove_rmap(page, vma, false);
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
put_page(page);
} else if (!non_swap_entry(entry)) {
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
/* Genuine swap entry, hence a private anon page */
if (!should_zap_cows(details))
continue;
rss[MM_SWAPENTS]--;
if (unlikely(!free_swap_and_cache(entry)))
print_bad_pte(vma, addr, ptent, NULL);
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
} else if (is_migration_entry(entry)) {
mm: remove special swap entry functions Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:06 +03:00
page = pfn_swap_entry_to_page(entry);
if (!should_zap_page(details, page))
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
continue;
rss[mm_counter(page)]--;
mm: don't skip swap entry even if zap_details specified Patch series "mm: Rework zap ptes on swap entries", v5. Patch 1 should fix a long standing bug for zap_pte_range() on zap_details usage. The risk is we could have some swap entries skipped while we should have zapped them. Migration entries are not the major concern because file backed memory always zap in the pattern that "first time without page lock, then re-zap with page lock" hence the 2nd zap will always make sure all migration entries are already recovered. However there can be issues with real swap entries got skipped errornoously. There's a reproducer provided in commit message of patch 1 for that. Patch 2-4 are cleanups that are based on patch 1. After the whole patchset applied, we should have a very clean view of zap_pte_range(). Only patch 1 needs to be backported to stable if necessary. This patch (of 4): The "details" pointer shouldn't be the token to decide whether we should skip swap entries. For example, when the callers specified details->zap_mapping==NULL, it means the user wants to zap all the pages (including COWed pages), then we need to look into swap entries because there can be private COWed pages that was swapped out. Skipping some swap entries when details is non-NULL may lead to wrongly leaving some of the swap entries while we should have zapped them. A reproducer of the problem: ===8<=== #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <assert.h> #include <unistd.h> #include <sys/mman.h> #include <sys/types.h> int page_size; int shmem_fd; char *buffer; void main(void) { int ret; char val; page_size = getpagesize(); shmem_fd = memfd_create("test", 0); assert(shmem_fd >= 0); ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); buffer = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE, shmem_fd, 0); assert(buffer != MAP_FAILED); /* Write private page, swap it out */ buffer[page_size] = 1; madvise(buffer, page_size * 2, MADV_PAGEOUT); /* This should drop private buffer[page_size] already */ ret = ftruncate(shmem_fd, page_size); assert(ret == 0); /* Recover the size */ ret = ftruncate(shmem_fd, page_size * 2); assert(ret == 0); /* Re-read the data, it should be all zero */ val = buffer[page_size]; if (val == 0) printf("Good\n"); else printf("BUG\n"); } ===8<=== We don't need to touch up the pmd path, because pmd never had a issue with swap entries. For example, shmem pmd migration will always be split into pte level, and same to swapping on anonymous. Add another helper should_zap_cows() so that we can also check whether we should zap private mappings when there's no page pointer specified. This patch drops that trick, so we handle swap ptes coherently. Meanwhile we should do the same check upon migration entry, hwpoison entry and genuine swap entries too. To be explicit, we should still remember to keep the private entries if even_cows==false, and always zap them when even_cows==true. The issue seems to exist starting from the initial commit of git. [peterx@redhat.com: comment tweaks] Link: https://lkml.kernel.org/r/20220217060746.71256-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20220217060746.71256-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220216094810.60572-2-peterx@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:15 +03:00
} else if (is_hwpoison_entry(entry)) {
if (!should_zap_cows(details))
continue;
} else {
/* We should have covered all the swap entry types */
WARN_ON_ONCE(1);
}
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} while (pte++, addr += PAGE_SIZE, addr != end);
add_mm_rss_vec(mm, rss);
arch_leave_lazy_mmu_mode();
/* Do the actual TLB flush before dropping ptl */
if (force_flush)
tlb_flush_mmu_tlbonly(tlb);
pte_unmap_unlock(start_pte, ptl);
/*
* If we forced a TLB flush (either due to running out of
* batch buffers or because we needed to flush dirty TLB
* entries before releasing the ptl), free the batched
* memory too. Restart if we didn't do everything.
*/
if (force_flush) {
force_flush = 0;
tlb_flush_mmu(tlb);
mm: release the spinlock on zap_pte_range In our testing (camera recording), Miguel and Wei found unmap_page_range() takes above 6ms with preemption disabled easily. When I see that, the reason is it holds page table spinlock during entire 512 page operation in a PMD. 6.2ms is never trivial for user experince if RT task couldn't run in the time because it could make frame drop or glitch audio problem. I had a time to benchmark it via adding some trace_printk hooks between pte_offset_map_lock and pte_unmap_unlock in zap_pte_range. The testing device is 2018 premium mobile device. I can get 2ms delay rather easily to release 2M(ie, 512 pages) when the task runs on little core even though it doesn't have any IPI and LRU lock contention. It's already too heavy. If I remove activate_page, 35-40% overhead of zap_pte_range is gone so most of overhead(about 0.7ms) comes from activate_page via mark_page_accessed. Thus, if there are LRU contention, that 0.7ms could accumulate up to several ms. So this patch adds a check for need_resched() in the loop, and a preemption point if necessary. Link: http://lkml.kernel.org/r/20190731061440.GC155569@google.com Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: Miguel de Dios <migueldedios@google.com> Reported-by: Wei Wang <wvw@google.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 03:02:24 +03:00
}
if (addr != end) {
cond_resched();
goto again;
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
}
return addr;
}
static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
2005-10-30 04:16:12 +03:00
struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
mm: thp: check pmd migration entry in common path When THP migration is being used, memory management code needs to handle pmd migration entries properly. This patch uses !pmd_present() or is_swap_pmd() (depending on whether pmd_none() needs separate code or not) to check pmd migration entries at the places where a pmd entry is present. Since pmd-related code uses split_huge_page(), split_huge_pmd(), pmd_trans_huge(), pmd_trans_unstable(), or pmd_none_or_trans_huge_or_clear_bad(), this patch: 1. adds pmd migration entry split code in split_huge_pmd(), 2. takes care of pmd migration entries whenever pmd_trans_huge() is present, 3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware. Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable() is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change them. Until this commit, a pmd entry should be: 1. pointing to a pte page, 2. is_swap_pmd(), 3. pmd_trans_huge(), 4. pmd_devmap(), or 5. pmd_none(). Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:01 +03:00
if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
__split_huge_pmd(vma, pmd, addr, false, NULL);
else if (zap_huge_pmd(tlb, vma, pmd, addr))
mm: thp: fix pmd_bad() triggering in code paths holding mmap_sem read mode In some cases it may happen that pmd_none_or_clear_bad() is called with the mmap_sem hold in read mode. In those cases the huge page faults can allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a false positive from pmd_bad() that will not like to see a pmd materializing as trans huge. It's not khugepaged causing the problem, khugepaged holds the mmap_sem in write mode (and all those sites must hold the mmap_sem in read mode to prevent pagetables to go away from under them, during code review it seems vm86 mode on 32bit kernels requires that too unless it's restricted to 1 thread per process or UP builds). The race is only with the huge pagefaults that can convert a pmd_none() into a pmd_trans_huge(). Effectively all these pmd_none_or_clear_bad() sites running with mmap_sem in read mode are somewhat speculative with the page faults, and the result is always undefined when they run simultaneously. This is probably why it wasn't common to run into this. For example if the madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page fault, the hugepage will not be zapped, if the page fault runs first it will be zapped. Altering pmd_bad() not to error out if it finds hugepmds won't be enough to fix this, because zap_pmd_range would then proceed to call zap_pte_range (which would be incorrect if the pmd become a pmd_trans_huge()). The simplest way to fix this is to read the pmd in the local stack (regardless of what we read, no need of actual CPU barriers, only compiler barrier needed), and be sure it is not changing under the code that computes its value. Even if the real pmd is changing under the value we hold on the stack, we don't care. If we actually end up in zap_pte_range it means the pmd was not none already and it was not huge, and it can't become huge from under us (khugepaged locking explained above). All we need is to enforce that there is no way anymore that in a code path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad can run into a hugepmd. The overhead of a barrier() is just a compiler tweak and should not be measurable (I only added it for THP builds). I don't exclude different compiler versions may have prevented the race too by caching the value of *pmd on the stack (that hasn't been verified, but it wouldn't be impossible considering pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines and there's no external function called in between pmd_trans_huge and pmd_none_or_clear_bad). if (pmd_trans_huge(*pmd)) { if (next-addr != HPAGE_PMD_SIZE) { VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) continue; /* fall through */ } if (pmd_none_or_clear_bad(pmd)) Because this race condition could be exercised without special privileges this was reported in CVE-2012-1179. The race was identified and fully explained by Ulrich who debugged it. I'm quoting his accurate explanation below, for reference. ====== start quote ======= mapcount 0 page_mapcount 1 kernel BUG at mm/huge_memory.c:1384! At some point prior to the panic, a "bad pmd ..." message similar to the following is logged on the console: mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7). The "bad pmd ..." message is logged by pmd_clear_bad() before it clears the page's PMD table entry. 143 void pmd_clear_bad(pmd_t *pmd) 144 { -> 145 pmd_ERROR(*pmd); 146 pmd_clear(pmd); 147 } After the PMD table entry has been cleared, there is an inconsistency between the actual number of PMD table entries that are mapping the page and the page's map count (_mapcount field in struct page). When the page is subsequently reclaimed, __split_huge_page() detects this inconsistency. 1381 if (mapcount != page_mapcount(page)) 1382 printk(KERN_ERR "mapcount %d page_mapcount %d\n", 1383 mapcount, page_mapcount(page)); -> 1384 BUG_ON(mapcount != page_mapcount(page)); The root cause of the problem is a race of two threads in a multithreaded process. Thread B incurs a page fault on a virtual address that has never been accessed (PMD entry is zero) while Thread A is executing an madvise() system call on a virtual address within the same 2 MB (huge page) range. virtual address space .---------------------. | | | | .-|---------------------| | | | | | |<-- B(fault) | | | 2 MB | |/////////////////////|-. huge < |/////////////////////| > A(range) page | |/////////////////////|-' | | | | | | '-|---------------------| | | | | '---------------------' - Thread A is executing an madvise(..., MADV_DONTNEED) system call on the virtual address range "A(range)" shown in the picture. sys_madvise // Acquire the semaphore in shared mode. down_read(&current->mm->mmap_sem) ... madvise_vma switch (behavior) case MADV_DONTNEED: madvise_dontneed zap_page_range unmap_vmas unmap_page_range zap_pud_range zap_pmd_range // // Assume that this huge page has never been accessed. // I.e. content of the PMD entry is zero (not mapped). // if (pmd_trans_huge(*pmd)) { // We don't get here due to the above assumption. } // // Assume that Thread B incurred a page fault and .---------> // sneaks in here as shown below. | // | if (pmd_none_or_clear_bad(pmd)) | { | if (unlikely(pmd_bad(*pmd))) | pmd_clear_bad | { | pmd_ERROR | // Log "bad pmd ..." message here. | pmd_clear | // Clear the page's PMD entry. | // Thread B incremented the map count | // in page_add_new_anon_rmap(), but | // now the page is no longer mapped | // by a PMD entry (-> inconsistency). | } | } | v - Thread B is handling a page fault on virtual address "B(fault)" shown in the picture. ... do_page_fault __do_page_fault // Acquire the semaphore in shared mode. down_read_trylock(&mm->mmap_sem) ... handle_mm_fault if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) // We get here due to the above assumption (PMD entry is zero). do_huge_pmd_anonymous_page alloc_hugepage_vma // Allocate a new transparent huge page here. ... __do_huge_pmd_anonymous_page ... spin_lock(&mm->page_table_lock) ... page_add_new_anon_rmap // Here we increment the page's map count (starts at -1). atomic_set(&page->_mapcount, 0) set_pmd_at // Here we set the page's PMD entry which will be cleared // when Thread A calls pmd_clear_bad(). ... spin_unlock(&mm->page_table_lock) The mmap_sem does not prevent the race because both threads are acquiring it in shared mode (down_read). Thread B holds the page_table_lock while the page's map count and PMD table entry are updated. However, Thread A does not synchronize on that lock. ====== end quote ======= [akpm@linux-foundation.org: checkpatch fixes] Reported-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Jones <davej@redhat.com> Acked-by: Larry Woodman <lwoodman@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> [2.6.38+] Cc: Mark Salter <msalter@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 03:33:42 +04:00
goto next;
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
/* fall through */
} else if (details && details->single_folio &&
folio_test_pmd_mappable(details->single_folio) &&
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
/*
* Take and drop THP pmd lock so that we cannot return
* prematurely, while zap_huge_pmd() has cleared *pmd,
* but not yet decremented compound_mapcount().
*/
spin_unlock(ptl);
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
}
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
mm: thp: fix pmd_bad() triggering in code paths holding mmap_sem read mode In some cases it may happen that pmd_none_or_clear_bad() is called with the mmap_sem hold in read mode. In those cases the huge page faults can allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a false positive from pmd_bad() that will not like to see a pmd materializing as trans huge. It's not khugepaged causing the problem, khugepaged holds the mmap_sem in write mode (and all those sites must hold the mmap_sem in read mode to prevent pagetables to go away from under them, during code review it seems vm86 mode on 32bit kernels requires that too unless it's restricted to 1 thread per process or UP builds). The race is only with the huge pagefaults that can convert a pmd_none() into a pmd_trans_huge(). Effectively all these pmd_none_or_clear_bad() sites running with mmap_sem in read mode are somewhat speculative with the page faults, and the result is always undefined when they run simultaneously. This is probably why it wasn't common to run into this. For example if the madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page fault, the hugepage will not be zapped, if the page fault runs first it will be zapped. Altering pmd_bad() not to error out if it finds hugepmds won't be enough to fix this, because zap_pmd_range would then proceed to call zap_pte_range (which would be incorrect if the pmd become a pmd_trans_huge()). The simplest way to fix this is to read the pmd in the local stack (regardless of what we read, no need of actual CPU barriers, only compiler barrier needed), and be sure it is not changing under the code that computes its value. Even if the real pmd is changing under the value we hold on the stack, we don't care. If we actually end up in zap_pte_range it means the pmd was not none already and it was not huge, and it can't become huge from under us (khugepaged locking explained above). All we need is to enforce that there is no way anymore that in a code path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad can run into a hugepmd. The overhead of a barrier() is just a compiler tweak and should not be measurable (I only added it for THP builds). I don't exclude different compiler versions may have prevented the race too by caching the value of *pmd on the stack (that hasn't been verified, but it wouldn't be impossible considering pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines and there's no external function called in between pmd_trans_huge and pmd_none_or_clear_bad). if (pmd_trans_huge(*pmd)) { if (next-addr != HPAGE_PMD_SIZE) { VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) continue; /* fall through */ } if (pmd_none_or_clear_bad(pmd)) Because this race condition could be exercised without special privileges this was reported in CVE-2012-1179. The race was identified and fully explained by Ulrich who debugged it. I'm quoting his accurate explanation below, for reference. ====== start quote ======= mapcount 0 page_mapcount 1 kernel BUG at mm/huge_memory.c:1384! At some point prior to the panic, a "bad pmd ..." message similar to the following is logged on the console: mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7). The "bad pmd ..." message is logged by pmd_clear_bad() before it clears the page's PMD table entry. 143 void pmd_clear_bad(pmd_t *pmd) 144 { -> 145 pmd_ERROR(*pmd); 146 pmd_clear(pmd); 147 } After the PMD table entry has been cleared, there is an inconsistency between the actual number of PMD table entries that are mapping the page and the page's map count (_mapcount field in struct page). When the page is subsequently reclaimed, __split_huge_page() detects this inconsistency. 1381 if (mapcount != page_mapcount(page)) 1382 printk(KERN_ERR "mapcount %d page_mapcount %d\n", 1383 mapcount, page_mapcount(page)); -> 1384 BUG_ON(mapcount != page_mapcount(page)); The root cause of the problem is a race of two threads in a multithreaded process. Thread B incurs a page fault on a virtual address that has never been accessed (PMD entry is zero) while Thread A is executing an madvise() system call on a virtual address within the same 2 MB (huge page) range. virtual address space .---------------------. | | | | .-|---------------------| | | | | | |<-- B(fault) | | | 2 MB | |/////////////////////|-. huge < |/////////////////////| > A(range) page | |/////////////////////|-' | | | | | | '-|---------------------| | | | | '---------------------' - Thread A is executing an madvise(..., MADV_DONTNEED) system call on the virtual address range "A(range)" shown in the picture. sys_madvise // Acquire the semaphore in shared mode. down_read(&current->mm->mmap_sem) ... madvise_vma switch (behavior) case MADV_DONTNEED: madvise_dontneed zap_page_range unmap_vmas unmap_page_range zap_pud_range zap_pmd_range // // Assume that this huge page has never been accessed. // I.e. content of the PMD entry is zero (not mapped). // if (pmd_trans_huge(*pmd)) { // We don't get here due to the above assumption. } // // Assume that Thread B incurred a page fault and .---------> // sneaks in here as shown below. | // | if (pmd_none_or_clear_bad(pmd)) | { | if (unlikely(pmd_bad(*pmd))) | pmd_clear_bad | { | pmd_ERROR | // Log "bad pmd ..." message here. | pmd_clear | // Clear the page's PMD entry. | // Thread B incremented the map count | // in page_add_new_anon_rmap(), but | // now the page is no longer mapped | // by a PMD entry (-> inconsistency). | } | } | v - Thread B is handling a page fault on virtual address "B(fault)" shown in the picture. ... do_page_fault __do_page_fault // Acquire the semaphore in shared mode. down_read_trylock(&mm->mmap_sem) ... handle_mm_fault if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) // We get here due to the above assumption (PMD entry is zero). do_huge_pmd_anonymous_page alloc_hugepage_vma // Allocate a new transparent huge page here. ... __do_huge_pmd_anonymous_page ... spin_lock(&mm->page_table_lock) ... page_add_new_anon_rmap // Here we increment the page's map count (starts at -1). atomic_set(&page->_mapcount, 0) set_pmd_at // Here we set the page's PMD entry which will be cleared // when Thread A calls pmd_clear_bad(). ... spin_unlock(&mm->page_table_lock) The mmap_sem does not prevent the race because both threads are acquiring it in shared mode (down_read). Thread B holds the page_table_lock while the page's map count and PMD table entry are updated. However, Thread A does not synchronize on that lock. ====== end quote ======= [akpm@linux-foundation.org: checkpatch fixes] Reported-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Jones <davej@redhat.com> Acked-by: Larry Woodman <lwoodman@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> [2.6.38+] Cc: Mark Salter <msalter@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 03:33:42 +04:00
/*
* Here there can be other concurrent MADV_DONTNEED or
* trans huge page faults running, and if the pmd is
* none or trans huge it can change under us. This is
* because MADV_DONTNEED holds the mmap_lock in read
mm: thp: fix pmd_bad() triggering in code paths holding mmap_sem read mode In some cases it may happen that pmd_none_or_clear_bad() is called with the mmap_sem hold in read mode. In those cases the huge page faults can allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a false positive from pmd_bad() that will not like to see a pmd materializing as trans huge. It's not khugepaged causing the problem, khugepaged holds the mmap_sem in write mode (and all those sites must hold the mmap_sem in read mode to prevent pagetables to go away from under them, during code review it seems vm86 mode on 32bit kernels requires that too unless it's restricted to 1 thread per process or UP builds). The race is only with the huge pagefaults that can convert a pmd_none() into a pmd_trans_huge(). Effectively all these pmd_none_or_clear_bad() sites running with mmap_sem in read mode are somewhat speculative with the page faults, and the result is always undefined when they run simultaneously. This is probably why it wasn't common to run into this. For example if the madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page fault, the hugepage will not be zapped, if the page fault runs first it will be zapped. Altering pmd_bad() not to error out if it finds hugepmds won't be enough to fix this, because zap_pmd_range would then proceed to call zap_pte_range (which would be incorrect if the pmd become a pmd_trans_huge()). The simplest way to fix this is to read the pmd in the local stack (regardless of what we read, no need of actual CPU barriers, only compiler barrier needed), and be sure it is not changing under the code that computes its value. Even if the real pmd is changing under the value we hold on the stack, we don't care. If we actually end up in zap_pte_range it means the pmd was not none already and it was not huge, and it can't become huge from under us (khugepaged locking explained above). All we need is to enforce that there is no way anymore that in a code path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad can run into a hugepmd. The overhead of a barrier() is just a compiler tweak and should not be measurable (I only added it for THP builds). I don't exclude different compiler versions may have prevented the race too by caching the value of *pmd on the stack (that hasn't been verified, but it wouldn't be impossible considering pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines and there's no external function called in between pmd_trans_huge and pmd_none_or_clear_bad). if (pmd_trans_huge(*pmd)) { if (next-addr != HPAGE_PMD_SIZE) { VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) continue; /* fall through */ } if (pmd_none_or_clear_bad(pmd)) Because this race condition could be exercised without special privileges this was reported in CVE-2012-1179. The race was identified and fully explained by Ulrich who debugged it. I'm quoting his accurate explanation below, for reference. ====== start quote ======= mapcount 0 page_mapcount 1 kernel BUG at mm/huge_memory.c:1384! At some point prior to the panic, a "bad pmd ..." message similar to the following is logged on the console: mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7). The "bad pmd ..." message is logged by pmd_clear_bad() before it clears the page's PMD table entry. 143 void pmd_clear_bad(pmd_t *pmd) 144 { -> 145 pmd_ERROR(*pmd); 146 pmd_clear(pmd); 147 } After the PMD table entry has been cleared, there is an inconsistency between the actual number of PMD table entries that are mapping the page and the page's map count (_mapcount field in struct page). When the page is subsequently reclaimed, __split_huge_page() detects this inconsistency. 1381 if (mapcount != page_mapcount(page)) 1382 printk(KERN_ERR "mapcount %d page_mapcount %d\n", 1383 mapcount, page_mapcount(page)); -> 1384 BUG_ON(mapcount != page_mapcount(page)); The root cause of the problem is a race of two threads in a multithreaded process. Thread B incurs a page fault on a virtual address that has never been accessed (PMD entry is zero) while Thread A is executing an madvise() system call on a virtual address within the same 2 MB (huge page) range. virtual address space .---------------------. | | | | .-|---------------------| | | | | | |<-- B(fault) | | | 2 MB | |/////////////////////|-. huge < |/////////////////////| > A(range) page | |/////////////////////|-' | | | | | | '-|---------------------| | | | | '---------------------' - Thread A is executing an madvise(..., MADV_DONTNEED) system call on the virtual address range "A(range)" shown in the picture. sys_madvise // Acquire the semaphore in shared mode. down_read(&current->mm->mmap_sem) ... madvise_vma switch (behavior) case MADV_DONTNEED: madvise_dontneed zap_page_range unmap_vmas unmap_page_range zap_pud_range zap_pmd_range // // Assume that this huge page has never been accessed. // I.e. content of the PMD entry is zero (not mapped). // if (pmd_trans_huge(*pmd)) { // We don't get here due to the above assumption. } // // Assume that Thread B incurred a page fault and .---------> // sneaks in here as shown below. | // | if (pmd_none_or_clear_bad(pmd)) | { | if (unlikely(pmd_bad(*pmd))) | pmd_clear_bad | { | pmd_ERROR | // Log "bad pmd ..." message here. | pmd_clear | // Clear the page's PMD entry. | // Thread B incremented the map count | // in page_add_new_anon_rmap(), but | // now the page is no longer mapped | // by a PMD entry (-> inconsistency). | } | } | v - Thread B is handling a page fault on virtual address "B(fault)" shown in the picture. ... do_page_fault __do_page_fault // Acquire the semaphore in shared mode. down_read_trylock(&mm->mmap_sem) ... handle_mm_fault if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) // We get here due to the above assumption (PMD entry is zero). do_huge_pmd_anonymous_page alloc_hugepage_vma // Allocate a new transparent huge page here. ... __do_huge_pmd_anonymous_page ... spin_lock(&mm->page_table_lock) ... page_add_new_anon_rmap // Here we increment the page's map count (starts at -1). atomic_set(&page->_mapcount, 0) set_pmd_at // Here we set the page's PMD entry which will be cleared // when Thread A calls pmd_clear_bad(). ... spin_unlock(&mm->page_table_lock) The mmap_sem does not prevent the race because both threads are acquiring it in shared mode (down_read). Thread B holds the page_table_lock while the page's map count and PMD table entry are updated. However, Thread A does not synchronize on that lock. ====== end quote ======= [akpm@linux-foundation.org: checkpatch fixes] Reported-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Jones <davej@redhat.com> Acked-by: Larry Woodman <lwoodman@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> [2.6.38+] Cc: Mark Salter <msalter@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 03:33:42 +04:00
* mode.
*/
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
goto next;
next = zap_pte_range(tlb, vma, pmd, addr, next, details);
mm: thp: fix pmd_bad() triggering in code paths holding mmap_sem read mode In some cases it may happen that pmd_none_or_clear_bad() is called with the mmap_sem hold in read mode. In those cases the huge page faults can allocate hugepmds under pmd_none_or_clear_bad() and that can trigger a false positive from pmd_bad() that will not like to see a pmd materializing as trans huge. It's not khugepaged causing the problem, khugepaged holds the mmap_sem in write mode (and all those sites must hold the mmap_sem in read mode to prevent pagetables to go away from under them, during code review it seems vm86 mode on 32bit kernels requires that too unless it's restricted to 1 thread per process or UP builds). The race is only with the huge pagefaults that can convert a pmd_none() into a pmd_trans_huge(). Effectively all these pmd_none_or_clear_bad() sites running with mmap_sem in read mode are somewhat speculative with the page faults, and the result is always undefined when they run simultaneously. This is probably why it wasn't common to run into this. For example if the madvise(MADV_DONTNEED) runs zap_page_range() shortly before the page fault, the hugepage will not be zapped, if the page fault runs first it will be zapped. Altering pmd_bad() not to error out if it finds hugepmds won't be enough to fix this, because zap_pmd_range would then proceed to call zap_pte_range (which would be incorrect if the pmd become a pmd_trans_huge()). The simplest way to fix this is to read the pmd in the local stack (regardless of what we read, no need of actual CPU barriers, only compiler barrier needed), and be sure it is not changing under the code that computes its value. Even if the real pmd is changing under the value we hold on the stack, we don't care. If we actually end up in zap_pte_range it means the pmd was not none already and it was not huge, and it can't become huge from under us (khugepaged locking explained above). All we need is to enforce that there is no way anymore that in a code path like below, pmd_trans_huge can be false, but pmd_none_or_clear_bad can run into a hugepmd. The overhead of a barrier() is just a compiler tweak and should not be measurable (I only added it for THP builds). I don't exclude different compiler versions may have prevented the race too by caching the value of *pmd on the stack (that hasn't been verified, but it wouldn't be impossible considering pmd_none_or_clear_bad, pmd_bad, pmd_trans_huge, pmd_none are all inlines and there's no external function called in between pmd_trans_huge and pmd_none_or_clear_bad). if (pmd_trans_huge(*pmd)) { if (next-addr != HPAGE_PMD_SIZE) { VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) continue; /* fall through */ } if (pmd_none_or_clear_bad(pmd)) Because this race condition could be exercised without special privileges this was reported in CVE-2012-1179. The race was identified and fully explained by Ulrich who debugged it. I'm quoting his accurate explanation below, for reference. ====== start quote ======= mapcount 0 page_mapcount 1 kernel BUG at mm/huge_memory.c:1384! At some point prior to the panic, a "bad pmd ..." message similar to the following is logged on the console: mm/memory.c:145: bad pmd ffff8800376e1f98(80000000314000e7). The "bad pmd ..." message is logged by pmd_clear_bad() before it clears the page's PMD table entry. 143 void pmd_clear_bad(pmd_t *pmd) 144 { -> 145 pmd_ERROR(*pmd); 146 pmd_clear(pmd); 147 } After the PMD table entry has been cleared, there is an inconsistency between the actual number of PMD table entries that are mapping the page and the page's map count (_mapcount field in struct page). When the page is subsequently reclaimed, __split_huge_page() detects this inconsistency. 1381 if (mapcount != page_mapcount(page)) 1382 printk(KERN_ERR "mapcount %d page_mapcount %d\n", 1383 mapcount, page_mapcount(page)); -> 1384 BUG_ON(mapcount != page_mapcount(page)); The root cause of the problem is a race of two threads in a multithreaded process. Thread B incurs a page fault on a virtual address that has never been accessed (PMD entry is zero) while Thread A is executing an madvise() system call on a virtual address within the same 2 MB (huge page) range. virtual address space .---------------------. | | | | .-|---------------------| | | | | | |<-- B(fault) | | | 2 MB | |/////////////////////|-. huge < |/////////////////////| > A(range) page | |/////////////////////|-' | | | | | | '-|---------------------| | | | | '---------------------' - Thread A is executing an madvise(..., MADV_DONTNEED) system call on the virtual address range "A(range)" shown in the picture. sys_madvise // Acquire the semaphore in shared mode. down_read(&current->mm->mmap_sem) ... madvise_vma switch (behavior) case MADV_DONTNEED: madvise_dontneed zap_page_range unmap_vmas unmap_page_range zap_pud_range zap_pmd_range // // Assume that this huge page has never been accessed. // I.e. content of the PMD entry is zero (not mapped). // if (pmd_trans_huge(*pmd)) { // We don't get here due to the above assumption. } // // Assume that Thread B incurred a page fault and .---------> // sneaks in here as shown below. | // | if (pmd_none_or_clear_bad(pmd)) | { | if (unlikely(pmd_bad(*pmd))) | pmd_clear_bad | { | pmd_ERROR | // Log "bad pmd ..." message here. | pmd_clear | // Clear the page's PMD entry. | // Thread B incremented the map count | // in page_add_new_anon_rmap(), but | // now the page is no longer mapped | // by a PMD entry (-> inconsistency). | } | } | v - Thread B is handling a page fault on virtual address "B(fault)" shown in the picture. ... do_page_fault __do_page_fault // Acquire the semaphore in shared mode. down_read_trylock(&mm->mmap_sem) ... handle_mm_fault if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) // We get here due to the above assumption (PMD entry is zero). do_huge_pmd_anonymous_page alloc_hugepage_vma // Allocate a new transparent huge page here. ... __do_huge_pmd_anonymous_page ... spin_lock(&mm->page_table_lock) ... page_add_new_anon_rmap // Here we increment the page's map count (starts at -1). atomic_set(&page->_mapcount, 0) set_pmd_at // Here we set the page's PMD entry which will be cleared // when Thread A calls pmd_clear_bad(). ... spin_unlock(&mm->page_table_lock) The mmap_sem does not prevent the race because both threads are acquiring it in shared mode (down_read). Thread B holds the page_table_lock while the page's map count and PMD table entry are updated. However, Thread A does not synchronize on that lock. ====== end quote ======= [akpm@linux-foundation.org: checkpatch fixes] Reported-by: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Jones <davej@redhat.com> Acked-by: Larry Woodman <lwoodman@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> [2.6.38+] Cc: Mark Salter <msalter@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 03:33:42 +04:00
next:
cond_resched();
} while (pmd++, addr = next, addr != end);
return addr;
}
static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, p4d_t *p4d,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
if (next - addr != HPAGE_PUD_SIZE) {
mmap_assert_locked(tlb->mm);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
split_huge_pud(vma, pud, addr);
} else if (zap_huge_pud(tlb, vma, pud, addr))
goto next;
/* fall through */
}
if (pud_none_or_clear_bad(pud))
continue;
next = zap_pmd_range(tlb, vma, pud, addr, next, details);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
next:
cond_resched();
} while (pud++, addr = next, addr != end);
return addr;
}
static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_none_or_clear_bad(p4d))
continue;
next = zap_pud_range(tlb, vma, p4d, addr, next, details);
} while (p4d++, addr = next, addr != end);
return addr;
}
mm, oom: introduce oom reaper This patch (of 5): This is based on the idea from Mel Gorman discussed during LSFMM 2015 and independently brought up by Oleg Nesterov. The OOM killer currently allows to kill only a single task in a good hope that the task will terminate in a reasonable time and frees up its memory. Such a task (oom victim) will get an access to memory reserves via mark_oom_victim to allow a forward progress should there be a need for additional memory during exit path. It has been shown (e.g. by Tetsuo Handa) that it is not that hard to construct workloads which break the core assumption mentioned above and the OOM victim might take unbounded amount of time to exit because it might be blocked in the uninterruptible state waiting for an event (e.g. lock) which is blocked by another task looping in the page allocator. This patch reduces the probability of such a lockup by introducing a specialized kernel thread (oom_reaper) which tries to reclaim additional memory by preemptively reaping the anonymous or swapped out memory owned by the oom victim under an assumption that such a memory won't be needed when its owner is killed and kicked from the userspace anyway. There is one notable exception to this, though, if the OOM victim was in the process of coredumping the result would be incomplete. This is considered a reasonable constrain because the overall system health is more important than debugability of a particular application. A kernel thread has been chosen because we need a reliable way of invocation so workqueue context is not appropriate because all the workers might be busy (e.g. allocating memory). Kswapd which sounds like another good fit is not appropriate as well because it might get blocked on locks during reclaim as well. oom_reaper has to take mmap_sem on the target task for reading so the solution is not 100% because the semaphore might be held or blocked for write but the probability is reduced considerably wrt. basically any lock blocking forward progress as described above. In order to prevent from blocking on the lock without any forward progress we are using only a trylock and retry 10 times with a short sleep in between. Users of mmap_sem which need it for write should be carefully reviewed to use _killable waiting as much as possible and reduce allocations requests done with the lock held to absolute minimum to reduce the risk even further. The API between oom killer and oom reaper is quite trivial. wake_oom_reaper updates mm_to_reap with cmpxchg to guarantee only NULL->mm transition and oom_reaper clear this atomically once it is done with the work. This means that only a single mm_struct can be reaped at the time. As the operation is potentially disruptive we are trying to limit it to the ncessary minimum and the reaper blocks any updates while it operates on an mm. mm_struct is pinned by mm_count to allow parallel exit_mmap and a race is detected by atomic_inc_not_zero(mm_users). Signed-off-by: Michal Hocko <mhocko@suse.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Suggested-by: Mel Gorman <mgorman@suse.de> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Argangeli <andrea@kernel.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-26 00:20:24 +03:00
void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pgd_t *pgd;
unsigned long next;
BUG_ON(addr >= end);
tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
}
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr,
struct zap_details *details)
{
unsigned long start = max(vma->vm_start, start_addr);
unsigned long end;
if (start >= vma->vm_end)
return;
end = min(vma->vm_end, end_addr);
if (end <= vma->vm_start)
return;
uprobes/core: Decrement uprobe count before the pages are unmapped Uprobes has a callback (uprobe_munmap()) in the unmap path to maintain the uprobes count. In the exit path this callback gets called in unlink_file_vma(). However by the time unlink_file_vma() is called, the pages would have been unmapped (in unmap_vmas()) and the task->rss_stat counts accounted (in zap_pte_range()). If the exiting process has probepoints, uprobe_munmap() checks if the breakpoint instruction was around before decrementing the probe count. This results in a file backed page being reread by uprobe_munmap() and hence it does not find the breakpoint. This patch fixes this problem by moving the callback to unmap_single_vma(). Since unmap_single_vma() may not unmap the complete vma, add start and end parameters to uprobe_munmap(). This bug became apparent courtesy of commit c3f0327f8e9d ("mm: add rss counters consistency check"). Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@linux.vnet.ibm.com> Cc: Linux-mm <linux-mm@kvack.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120411103527.23245.9835.sendpatchset@srdronam.in.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-04-11 14:35:27 +04:00
if (vma->vm_file)
uprobe_munmap(vma, start, end);
mm, x86, pat: rework linear pfn-mmap tracking Replace the generic vma-flag VM_PFN_AT_MMAP with x86-only VM_PAT. We can toss mapping address from remap_pfn_range() into track_pfn_vma_new(), and collect all PAT-related logic together in arch/x86/. This patch also restores orignal frustration-free is_cow_mapping() check in remap_pfn_range(), as it was before commit v2.6.28-rc8-88-g3c8bb73 ("x86: PAT: store vm_pgoff for all linear_over_vma_region mappings - v3") is_linear_pfn_mapping() checks can be removed from mm/huge_memory.c, because it already handled by VM_PFNMAP in VM_NO_THP bit-mask. [suresh.b.siddha@intel.com: Reset the VM_PAT flag as part of untrack_pfn_vma()] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venki@google.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:34 +04:00
if (unlikely(vma->vm_flags & VM_PFNMAP))
x86, pat: separate the pfn attribute tracking for remap_pfn_range and vm_insert_pfn With PAT enabled, vm_insert_pfn() looks up the existing pfn memory attribute and uses it. Expectation is that the driver reserves the memory attributes for the pfn before calling vm_insert_pfn(). remap_pfn_range() (when called for the whole vma) will setup a new attribute (based on the prot argument) for the specified pfn range. This addresses the legacy usage which typically calls remap_pfn_range() with a desired memory attribute. For ranges smaller than the vma size (which is typically not the case), remap_pfn_range() will use the existing memory attribute for the pfn range. Expose two different API's for these different behaviors. track_pfn_insert() for tracking the pfn attribute set by vm_insert_pfn() and track_pfn_remap() for the remap_pfn_range(). This cleanup also prepares the ground for the track/untrack pfn vma routines to take over the ownership of setting PAT specific vm_flag in the 'vma'. [khlebnikov@openvz.org: Clear checks in track_pfn_remap()] [akpm@linux-foundation.org: tweak a few comments] Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Venkatesh Pallipadi <venki@google.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:29 +04:00
untrack_pfn(vma, 0, 0);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
/*
* It is undesirable to test vma->vm_file as it
* should be non-null for valid hugetlb area.
* However, vm_file will be NULL in the error
* cleanup path of mmap_region. When
* hugetlbfs ->mmap method fails,
* mmap_region() nullifies vma->vm_file
* before calling this function to clean up.
* Since no pte has actually been setup, it is
* safe to do nothing in this case.
*/
if (vma->vm_file) {
i_mmap_lock_write(vma->vm_file->f_mapping);
mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables If a process creates a large hugetlbfs mapping that is eligible for page table sharing and forks heavily with children some of whom fault and others which destroy the mapping then it is possible for page tables to get corrupted. Some teardowns of the mapping encounter a "bad pmd" and output a message to the kernel log. The final teardown will trigger a BUG_ON in mm/filemap.c. This was reproduced in 3.4 but is known to have existed for a long time and goes back at least as far as 2.6.37. It was probably was introduced in 2.6.20 by [39dde65c: shared page table for hugetlb page]. The messages look like this; [ ..........] Lots of bad pmd messages followed by this [ 127.164256] mm/memory.c:391: bad pmd ffff880412e04fe8(80000003de4000e7). [ 127.164257] mm/memory.c:391: bad pmd ffff880412e04ff0(80000003de6000e7). [ 127.164258] mm/memory.c:391: bad pmd ffff880412e04ff8(80000003de0000e7). [ 127.186778] ------------[ cut here ]------------ [ 127.186781] kernel BUG at mm/filemap.c:134! [ 127.186782] invalid opcode: 0000 [#1] SMP [ 127.186783] CPU 7 [ 127.186784] Modules linked in: af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq mperf ext3 jbd dm_mod coretemp crc32c_intel usb_storage ghash_clmulni_intel aesni_intel i2c_i801 r8169 mii uas sr_mod cdrom sg iTCO_wdt iTCO_vendor_support shpchp serio_raw cryptd aes_x86_64 e1000e pci_hotplug dcdbas aes_generic container microcode ext4 mbcache jbd2 crc16 sd_mod crc_t10dif i915 drm_kms_helper drm i2c_algo_bit ehci_hcd ahci libahci usbcore rtc_cmos usb_common button i2c_core intel_agp video intel_gtt fan processor thermal thermal_sys hwmon ata_generic pata_atiixp libata scsi_mod [ 127.186801] [ 127.186802] Pid: 9017, comm: hugetlbfs-test Not tainted 3.4.0-autobuild #53 Dell Inc. OptiPlex 990/06D7TR [ 127.186804] RIP: 0010:[<ffffffff810ed6ce>] [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186809] RSP: 0000:ffff8804144b5c08 EFLAGS: 00010002 [ 127.186810] RAX: 0000000000000001 RBX: ffffea000a5c9000 RCX: 00000000ffffffc0 [ 127.186811] RDX: 0000000000000000 RSI: 0000000000000009 RDI: ffff88042dfdad00 [ 127.186812] RBP: ffff8804144b5c18 R08: 0000000000000009 R09: 0000000000000003 [ 127.186813] R10: 0000000000000000 R11: 000000000000002d R12: ffff880412ff83d8 [ 127.186814] R13: ffff880412ff83d8 R14: 0000000000000000 R15: ffff880412ff83d8 [ 127.186815] FS: 00007fe18ed2c700(0000) GS:ffff88042dce0000(0000) knlGS:0000000000000000 [ 127.186816] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 127.186817] CR2: 00007fe340000503 CR3: 0000000417a14000 CR4: 00000000000407e0 [ 127.186818] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 127.186819] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 127.186820] Process hugetlbfs-test (pid: 9017, threadinfo ffff8804144b4000, task ffff880417f803c0) [ 127.186821] Stack: [ 127.186822] ffffea000a5c9000 0000000000000000 ffff8804144b5c48 ffffffff810ed83b [ 127.186824] ffff8804144b5c48 000000000000138a 0000000000001387 ffff8804144b5c98 [ 127.186825] ffff8804144b5d48 ffffffff811bc925 ffff8804144b5cb8 0000000000000000 [ 127.186827] Call Trace: [ 127.186829] [<ffffffff810ed83b>] delete_from_page_cache+0x3b/0x80 [ 127.186832] [<ffffffff811bc925>] truncate_hugepages+0x115/0x220 [ 127.186834] [<ffffffff811bca43>] hugetlbfs_evict_inode+0x13/0x30 [ 127.186837] [<ffffffff811655c7>] evict+0xa7/0x1b0 [ 127.186839] [<ffffffff811657a3>] iput_final+0xd3/0x1f0 [ 127.186840] [<ffffffff811658f9>] iput+0x39/0x50 [ 127.186842] [<ffffffff81162708>] d_kill+0xf8/0x130 [ 127.186843] [<ffffffff81162812>] dput+0xd2/0x1a0 [ 127.186845] [<ffffffff8114e2d0>] __fput+0x170/0x230 [ 127.186848] [<ffffffff81236e0e>] ? rb_erase+0xce/0x150 [ 127.186849] [<ffffffff8114e3ad>] fput+0x1d/0x30 [ 127.186851] [<ffffffff81117db7>] remove_vma+0x37/0x80 [ 127.186853] [<ffffffff81119182>] do_munmap+0x2d2/0x360 [ 127.186855] [<ffffffff811cc639>] sys_shmdt+0xc9/0x170 [ 127.186857] [<ffffffff81410a39>] system_call_fastpath+0x16/0x1b [ 127.186858] Code: 0f 1f 44 00 00 48 8b 43 08 48 8b 00 48 8b 40 28 8b b0 40 03 00 00 85 f6 0f 88 df fe ff ff 48 89 df e8 e7 cb 05 00 e9 d2 fe ff ff <0f> 0b 55 83 e2 fd 48 89 e5 48 83 ec 30 48 89 5d d8 4c 89 65 e0 [ 127.186868] RIP [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186870] RSP <ffff8804144b5c08> [ 127.186871] ---[ end trace 7cbac5d1db69f426 ]--- The bug is a race and not always easy to reproduce. To reproduce it I was doing the following on a single socket I7-based machine with 16G of RAM. $ hugeadm --pool-pages-max DEFAULT:13G $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmmax $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmall $ for i in `seq 1 9000`; do ./hugetlbfs-test; done On my particular machine, it usually triggers within 10 minutes but enabling debug options can change the timing such that it never hits. Once the bug is triggered, the machine is in trouble and needs to be rebooted. The machine will respond but processes accessing proc like "ps aux" will hang due to the BUG_ON. shutdown will also hang and needs a hard reset or a sysrq-b. The basic problem is a race between page table sharing and teardown. For the most part page table sharing depends on i_mmap_mutex. In some cases, it is also taking the mm->page_table_lock for the PTE updates but with shared page tables, it is the i_mmap_mutex that is more important. Unfortunately it appears to be also insufficient. Consider the following situation Process A Process B --------- --------- hugetlb_fault shmdt LockWrite(mmap_sem) do_munmap unmap_region unmap_vmas unmap_single_vma unmap_hugepage_range Lock(i_mmap_mutex) Lock(mm->page_table_lock) huge_pmd_unshare/unmap tables <--- (1) Unlock(mm->page_table_lock) Unlock(i_mmap_mutex) huge_pte_alloc ... Lock(i_mmap_mutex) ... vma_prio_walk, find svma, spte ... Lock(mm->page_table_lock) ... share spte ... Unlock(mm->page_table_lock) ... Unlock(i_mmap_mutex) ... hugetlb_no_page <--- (2) free_pgtables unlink_file_vma hugetlb_free_pgd_range remove_vma_list In this scenario, it is possible for Process A to share page tables with Process B that is trying to tear them down. The i_mmap_mutex on its own does not prevent Process A walking Process B's page tables. At (1) above, the page tables are not shared yet so it unmaps the PMDs. Process A sets up page table sharing and at (2) faults a new entry. Process B then trips up on it in free_pgtables. This patch fixes the problem by adding a new function __unmap_hugepage_range_final that is only called when the VMA is about to be destroyed. This function clears VM_MAYSHARE during unmap_hugepage_range() under the i_mmap_mutex. This makes the VMA ineligible for sharing and avoids the race. Superficially this looks like it would then be vunerable to truncate and madvise issues but hugetlbfs has its own truncate handlers so does not use unmap_mapping_range() and does not support madvise(DONTNEED). This should be treated as a -stable candidate if it is merged. Test program is as follows. The test case was mostly written by Michal Hocko with a few minor changes to reproduce this bug. ==== CUT HERE ==== static size_t huge_page_size = (2UL << 20); static size_t nr_huge_page_A = 512; static size_t nr_huge_page_B = 5632; unsigned int get_random(unsigned int max) { struct timeval tv; gettimeofday(&tv, NULL); srandom(tv.tv_usec); return random() % max; } static void play(void *addr, size_t size) { unsigned char *start = addr, *end = start + size, *a; start += get_random(size/2); /* we could itterate on huge pages but let's give it more time. */ for (a = start; a < end; a += 4096) *a = 0; } int main(int argc, char **argv) { key_t key = IPC_PRIVATE; size_t sizeA = nr_huge_page_A * huge_page_size; size_t sizeB = nr_huge_page_B * huge_page_size; int shmidA, shmidB; void *addrA = NULL, *addrB = NULL; int nr_children = 300, n = 0; if ((shmidA = shmget(key, sizeA, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrA = shmat(shmidA, addrA, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } if ((shmidB = shmget(key, sizeB, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrB = shmat(shmidB, addrB, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } fork_child: switch(fork()) { case 0: switch (n%3) { case 0: play(addrA, sizeA); break; case 1: play(addrB, sizeB); break; case 2: break; } break; case -1: perror("fork:"); break; default: if (++n < nr_children) goto fork_child; play(addrA, sizeA); break; } shmdt(addrA); shmdt(addrB); do { wait(NULL); } while (--n > 0); shmctl(shmidA, IPC_RMID, NULL); shmctl(shmidB, IPC_RMID, NULL); return 0; } [akpm@linux-foundation.org: name the declaration's args, fix CONFIG_HUGETLBFS=n build] Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 03:46:20 +04:00
__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
i_mmap_unlock_write(vma->vm_file->f_mapping);
}
} else
unmap_page_range(tlb, vma, start, end, details);
}
}
/**
* unmap_vmas - unmap a range of memory covered by a list of vma's
* @tlb: address of the caller's struct mmu_gather
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
*
* Unmap all pages in the vma list.
*
* Only addresses between `start' and `end' will be unmapped.
*
* The VMA list must be sorted in ascending virtual address order.
*
* unmap_vmas() assumes that the caller will flush the whole unmapped address
* range after unmap_vmas() returns. So the only responsibility here is to
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
void unmap_vmas(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr)
{
struct mmu_notifier_range range;
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
start_addr, end_addr);
mmu_notifier_invalidate_range_start(&range);
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
mmu_notifier_invalidate_range_end(&range);
}
/**
* zap_page_range - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @start: starting address of pages to zap
* @size: number of bytes to zap
*
* Caller must protect the VMA list
*/
void zap_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long size)
{
struct mmu_notifier_range range;
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
struct mmu_gather tlb;
lru_add_drain();
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
start, start + size);
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next)
unmap_single_vma(&tlb, vma, start, range.end, NULL);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
/**
* zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @address: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of shared cache invalidation
*
* The range must fit into one VMA.
*/
static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
struct mmu_notifier_range range;
mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Richard Weinberger <richard@nod.at> Cc: Tony Luck <tony.luck@intel.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Namhyung Kim <namhyung@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:45 +04:00
struct mmu_gather tlb;
lru_add_drain();
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
address, address + size);
tlb_gather_mmu(&tlb, vma->vm_mm);
update_hiwater_rss(vma->vm_mm);
mmu_notifier_invalidate_range_start(&range);
unmap_single_vma(&tlb, vma, address, range.end, details);
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb);
}
/**
* zap_vma_ptes - remove ptes mapping the vma
* @vma: vm_area_struct holding ptes to be zapped
* @address: starting address of pages to zap
* @size: number of bytes to zap
*
* This function only unmaps ptes assigned to VM_PFNMAP vmas.
*
* The entire address range must be fully contained within the vma.
*
*/
void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size)
{
if (!range_in_vma(vma, address, address + size) ||
!(vma->vm_flags & VM_PFNMAP))
return;
zap_page_range_single(vma, address, size, NULL);
}
EXPORT_SYMBOL_GPL(zap_vma_ptes);
static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pgd = pgd_offset(mm, addr);
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return NULL;
pud = pud_alloc(mm, p4d, addr);
if (!pud)
return NULL;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return NULL;
VM_BUG_ON(pmd_trans_huge(*pmd));
return pmd;
}
pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
pmd_t *pmd = walk_to_pmd(mm, addr);
if (!pmd)
return NULL;
return pte_alloc_map_lock(mm, pmd, addr, ptl);
}
static int validate_page_before_insert(struct page *page)
{
if (PageAnon(page) || PageSlab(page) || page_has_type(page))
return -EINVAL;
flush_dcache_page(page);
return 0;
}
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, struct page *page, pgprot_t prot)
{
if (!pte_none(*pte))
return -EBUSY;
/* Ok, finally just insert the thing.. */
get_page(page);
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
page_add_file_rmap(page, vma, false);
set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot));
return 0;
}
/*
* This is the old fallback for page remapping.
*
* For historical reasons, it only allows reserved pages. Only
* old drivers should use this, and they needed to mark their
* pages reserved for the old functions anyway.
*/
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page, pgprot_t prot)
{
int retval;
pte_t *pte;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 11:13:53 +03:00
spinlock_t *ptl;
retval = validate_page_before_insert(page);
if (retval)
goto out;
retval = -ENOMEM;
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
pte = get_locked_pte(vma->vm_mm, addr, &ptl);
if (!pte)
goto out;
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
retval = insert_page_into_pte_locked(vma, pte, addr, page, prot);
pte_unmap_unlock(pte, ptl);
out:
return retval;
}
#ifdef pte_index
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, struct page *page, pgprot_t prot)
{
int err;
if (!page_count(page))
return -EINVAL;
err = validate_page_before_insert(page);
if (err)
return err;
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
return insert_page_into_pte_locked(vma, pte, addr, page, prot);
}
/* insert_pages() amortizes the cost of spinlock operations
* when inserting pages in a loop. Arch *must* define pte_index.
*/
static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num, pgprot_t prot)
{
pmd_t *pmd = NULL;
pte_t *start_pte, *pte;
spinlock_t *pte_lock;
struct mm_struct *const mm = vma->vm_mm;
unsigned long curr_page_idx = 0;
unsigned long remaining_pages_total = *num;
unsigned long pages_to_write_in_pmd;
int ret;
more:
ret = -EFAULT;
pmd = walk_to_pmd(mm, addr);
if (!pmd)
goto out;
pages_to_write_in_pmd = min_t(unsigned long,
remaining_pages_total, PTRS_PER_PTE - pte_index(addr));
/* Allocate the PTE if necessary; takes PMD lock once only. */
ret = -ENOMEM;
if (pte_alloc(mm, pmd))
goto out;
while (pages_to_write_in_pmd) {
int pte_idx = 0;
const int batch_size = min_t(int, pages_to_write_in_pmd, 8);
start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock);
for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) {
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
int err = insert_page_in_batch_locked(vma, pte,
addr, pages[curr_page_idx], prot);
if (unlikely(err)) {
pte_unmap_unlock(start_pte, pte_lock);
ret = err;
remaining_pages_total -= pte_idx;
goto out;
}
addr += PAGE_SIZE;
++curr_page_idx;
}
pte_unmap_unlock(start_pte, pte_lock);
pages_to_write_in_pmd -= batch_size;
remaining_pages_total -= batch_size;
}
if (remaining_pages_total)
goto more;
ret = 0;
out:
*num = remaining_pages_total;
return ret;
}
#endif /* ifdef pte_index */
/**
* vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
* @vma: user vma to map to
* @addr: target start user address of these pages
* @pages: source kernel pages
* @num: in: number of pages to map. out: number of pages that were *not*
* mapped. (0 means all pages were successfully mapped).
*
* Preferred over vm_insert_page() when inserting multiple pages.
*
* In case of error, we may have mapped a subset of the provided
* pages. It is the caller's responsibility to account for this case.
*
* The same restrictions apply as in vm_insert_page().
*/
int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
struct page **pages, unsigned long *num)
{
#ifdef pte_index
const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
if (addr < vma->vm_start || end_addr >= vma->vm_end)
return -EFAULT;
if (!(vma->vm_flags & VM_MIXEDMAP)) {
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
BUG_ON(mmap_read_trylock(vma->vm_mm));
BUG_ON(vma->vm_flags & VM_PFNMAP);
vma->vm_flags |= VM_MIXEDMAP;
}
/* Defer page refcount checking till we're about to map that page. */
return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
#else
unsigned long idx = 0, pgcount = *num;
int err = -EINVAL;
for (; idx < pgcount; ++idx) {
err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]);
if (err)
break;
}
*num = pgcount - idx;
return err;
#endif /* ifdef pte_index */
}
EXPORT_SYMBOL(vm_insert_pages);
/**
* vm_insert_page - insert single page into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @page: source kernel page
*
* This allows drivers to insert individual pages they've allocated
* into a user vma.
*
* The page has to be a nice clean _individual_ kernel allocation.
* If you allocate a compound page, you need to have marked it as
* such (__GFP_COMP), or manually just split the page up yourself
* (see split_page()).
*
* NOTE! Traditionally this was done with "remap_pfn_range()" which
* took an arbitrary page protection parameter. This doesn't allow
* that. Your vma protection will have to be set up correctly, which
* means that if you want a shared writable mapping, you'd better
* ask for a shared writable mapping!
*
* The page does not need to be reserved.
mm: kill vma flag VM_INSERTPAGE Merge VM_INSERTPAGE into VM_MIXEDMAP. VM_MIXEDMAP VMA can mix pure-pfn ptes, special ptes and normal ptes. Now copy_page_range() always copies VM_MIXEDMAP VMA on fork like VM_PFNMAP. If driver populates whole VMA at mmap() it probably not expects page-faults. This patch removes special check from vma_wants_writenotify() which disables pages write tracking for VMA populated via vm_instert_page(). BDI below mapped file should not use dirty-accounting, moreover do_wp_page() can handle this. vm_insert_page() still marks vma after first usage. Usually it is called from f_op->mmap() handler under mm->mmap_sem write-lock, so it able to change vma->vm_flags. Caller must set VM_MIXEDMAP at mmap time if it wants to call this function from other places, for example from page-fault handler. Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:40 +04:00
*
* Usually this function is called from f_op->mmap() handler
* under mm->mmap_lock write-lock, so it can change vma->vm_flags.
mm: kill vma flag VM_INSERTPAGE Merge VM_INSERTPAGE into VM_MIXEDMAP. VM_MIXEDMAP VMA can mix pure-pfn ptes, special ptes and normal ptes. Now copy_page_range() always copies VM_MIXEDMAP VMA on fork like VM_PFNMAP. If driver populates whole VMA at mmap() it probably not expects page-faults. This patch removes special check from vma_wants_writenotify() which disables pages write tracking for VMA populated via vm_instert_page(). BDI below mapped file should not use dirty-accounting, moreover do_wp_page() can handle this. vm_insert_page() still marks vma after first usage. Usually it is called from f_op->mmap() handler under mm->mmap_sem write-lock, so it able to change vma->vm_flags. Caller must set VM_MIXEDMAP at mmap time if it wants to call this function from other places, for example from page-fault handler. Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:40 +04:00
* Caller must set VM_MIXEDMAP on vma if it wants to call this
* function from other places, for example from page-fault handler.
*
* Return: %0 on success, negative error code otherwise.
*/
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
{
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
if (!page_count(page))
return -EINVAL;
mm: kill vma flag VM_INSERTPAGE Merge VM_INSERTPAGE into VM_MIXEDMAP. VM_MIXEDMAP VMA can mix pure-pfn ptes, special ptes and normal ptes. Now copy_page_range() always copies VM_MIXEDMAP VMA on fork like VM_PFNMAP. If driver populates whole VMA at mmap() it probably not expects page-faults. This patch removes special check from vma_wants_writenotify() which disables pages write tracking for VMA populated via vm_instert_page(). BDI below mapped file should not use dirty-accounting, moreover do_wp_page() can handle this. vm_insert_page() still marks vma after first usage. Usually it is called from f_op->mmap() handler under mm->mmap_sem write-lock, so it able to change vma->vm_flags. Caller must set VM_MIXEDMAP at mmap time if it wants to call this function from other places, for example from page-fault handler. Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:40 +04:00
if (!(vma->vm_flags & VM_MIXEDMAP)) {
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
BUG_ON(mmap_read_trylock(vma->vm_mm));
mm: kill vma flag VM_INSERTPAGE Merge VM_INSERTPAGE into VM_MIXEDMAP. VM_MIXEDMAP VMA can mix pure-pfn ptes, special ptes and normal ptes. Now copy_page_range() always copies VM_MIXEDMAP VMA on fork like VM_PFNMAP. If driver populates whole VMA at mmap() it probably not expects page-faults. This patch removes special check from vma_wants_writenotify() which disables pages write tracking for VMA populated via vm_instert_page(). BDI below mapped file should not use dirty-accounting, moreover do_wp_page() can handle this. vm_insert_page() still marks vma after first usage. Usually it is called from f_op->mmap() handler under mm->mmap_sem write-lock, so it able to change vma->vm_flags. Caller must set VM_MIXEDMAP at mmap time if it wants to call this function from other places, for example from page-fault handler. Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:40 +04:00
BUG_ON(vma->vm_flags & VM_PFNMAP);
vma->vm_flags |= VM_MIXEDMAP;
}
return insert_page(vma, addr, page, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_page);
mm: introduce new vm_map_pages() and vm_map_pages_zero() API Patch series "mm: Use vm_map_pages() and vm_map_pages_zero() API", v5. This patch (of 5): Previouly drivers have their own way of mapping range of kernel pages/memory into user vma and this was done by invoking vm_insert_page() within a loop. As this pattern is common across different drivers, it can be generalized by creating new functions and using them across the drivers. vm_map_pages() is the API which can be used to map kernel memory/pages in drivers which have considered vm_pgoff vm_map_pages_zero() is the API which can be used to map a range of kernel memory/pages in drivers which have not considered vm_pgoff. vm_pgoff is passed as default 0 for those drivers. We _could_ then at a later "fix" these drivers which are using vm_map_pages_zero() to behave according to the normal vm_pgoff offsetting simply by removing the _zero suffix on the function name and if that causes regressions, it gives us an easy way to revert. Tested on Rockchip hardware and display is working, including talking to Lima via prime. Link: http://lkml.kernel.org/r/751cb8a0f4c3e67e95c58a3b072937617f338eea.1552921225.git.jrdr.linux@gmail.com Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Suggested-by: Russell King <linux@armlinux.org.uk> Suggested-by: Matthew Wilcox <willy@infradead.org> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Tested-by: Heiko Stuebner <heiko@sntech.de> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Rik van Riel <riel@surriel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Thierry Reding <treding@nvidia.com> Cc: Kees Cook <keescook@chromium.org> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Sandy Huang <hjc@rock-chips.com> Cc: David Airlie <airlied@linux.ie> Cc: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Pawel Osciak <pawel@osciak.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:21:56 +03:00
/*
* __vm_map_pages - maps range of kernel pages into user vma
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
* @offset: user's requested vm_pgoff
*
* This allows drivers to map range of kernel pages into a user vma.
*
* Return: 0 on success and error code otherwise.
*/
static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num, unsigned long offset)
{
unsigned long count = vma_pages(vma);
unsigned long uaddr = vma->vm_start;
int ret, i;
/* Fail if the user requested offset is beyond the end of the object */
if (offset >= num)
mm: introduce new vm_map_pages() and vm_map_pages_zero() API Patch series "mm: Use vm_map_pages() and vm_map_pages_zero() API", v5. This patch (of 5): Previouly drivers have their own way of mapping range of kernel pages/memory into user vma and this was done by invoking vm_insert_page() within a loop. As this pattern is common across different drivers, it can be generalized by creating new functions and using them across the drivers. vm_map_pages() is the API which can be used to map kernel memory/pages in drivers which have considered vm_pgoff vm_map_pages_zero() is the API which can be used to map a range of kernel memory/pages in drivers which have not considered vm_pgoff. vm_pgoff is passed as default 0 for those drivers. We _could_ then at a later "fix" these drivers which are using vm_map_pages_zero() to behave according to the normal vm_pgoff offsetting simply by removing the _zero suffix on the function name and if that causes regressions, it gives us an easy way to revert. Tested on Rockchip hardware and display is working, including talking to Lima via prime. Link: http://lkml.kernel.org/r/751cb8a0f4c3e67e95c58a3b072937617f338eea.1552921225.git.jrdr.linux@gmail.com Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Suggested-by: Russell King <linux@armlinux.org.uk> Suggested-by: Matthew Wilcox <willy@infradead.org> Reviewed-by: Mike Rapoport <rppt@linux.ibm.com> Tested-by: Heiko Stuebner <heiko@sntech.de> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Rik van Riel <riel@surriel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Thierry Reding <treding@nvidia.com> Cc: Kees Cook <keescook@chromium.org> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Sandy Huang <hjc@rock-chips.com> Cc: David Airlie <airlied@linux.ie> Cc: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Pawel Osciak <pawel@osciak.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:21:56 +03:00
return -ENXIO;
/* Fail if the user requested size exceeds available object size */
if (count > num - offset)
return -ENXIO;
for (i = 0; i < count; i++) {
ret = vm_insert_page(vma, uaddr, pages[offset + i]);
if (ret < 0)
return ret;
uaddr += PAGE_SIZE;
}
return 0;
}
/**
* vm_map_pages - maps range of kernel pages starts with non zero offset
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
*
* Maps an object consisting of @num pages, catering for the user's
* requested vm_pgoff
*
* If we fail to insert any page into the vma, the function will return
* immediately leaving any previously inserted pages present. Callers
* from the mmap handler may immediately return the error as their caller
* will destroy the vma, removing any successfully inserted pages. Other
* callers should make their own arrangements for calling unmap_region().
*
* Context: Process context. Called by mmap handlers.
* Return: 0 on success and error code otherwise.
*/
int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num)
{
return __vm_map_pages(vma, pages, num, vma->vm_pgoff);
}
EXPORT_SYMBOL(vm_map_pages);
/**
* vm_map_pages_zero - map range of kernel pages starts with zero offset
* @vma: user vma to map to
* @pages: pointer to array of source kernel pages
* @num: number of pages in page array
*
* Similar to vm_map_pages(), except that it explicitly sets the offset
* to 0. This function is intended for the drivers that did not consider
* vm_pgoff.
*
* Context: Process context. Called by mmap handlers.
* Return: 0 on success and error code otherwise.
*/
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
unsigned long num)
{
return __vm_map_pages(vma, pages, num, 0);
}
EXPORT_SYMBOL(vm_map_pages_zero);
static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
pfn_t pfn, pgprot_t prot, bool mkwrite)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte, entry;
spinlock_t *ptl;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
return VM_FAULT_OOM;
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
if (!pte_none(*pte)) {
if (mkwrite) {
/*
* For read faults on private mappings the PFN passed
* in may not match the PFN we have mapped if the
* mapped PFN is a writeable COW page. In the mkwrite
* case we are creating a writable PTE for a shared
* mapping and we expect the PFNs to match. If they
* don't match, we are likely racing with block
* allocation and mapping invalidation so just skip the
* update.
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
*/
if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) {
WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
goto out_unlock;
}
entry = pte_mkyoung(*pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (ptep_set_access_flags(vma, addr, pte, entry, 1))
update_mmu_cache(vma, addr, pte);
}
goto out_unlock;
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
}
/* Ok, finally just insert the thing.. */
if (pfn_t_devmap(pfn))
entry = pte_mkdevmap(pfn_t_pte(pfn, prot));
else
entry = pte_mkspecial(pfn_t_pte(pfn, prot));
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
if (mkwrite) {
entry = pte_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
}
set_pte_at(mm, addr, pte, entry);
update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
out_unlock:
pte_unmap_unlock(pte, ptl);
return VM_FAULT_NOPAGE;
}
/**
* vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
* @pgprot: pgprot flags for the inserted page
*
* This is exactly like vmf_insert_pfn(), except that it allows drivers
* to override pgprot on a per-page basis.
*
* This only makes sense for IO mappings, and it makes no sense for
* COW mappings. In general, using multiple vmas is preferable;
* vmf_insert_pfn_prot should only be used if using multiple VMAs is
* impractical.
*
* See vmf_insert_mixed_prot() for a discussion of the implication of using
* a value of @pgprot different from that of @vma->vm_page_prot.
*
* Context: Process context. May allocate using %GFP_KERNEL.
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, pgprot_t pgprot)
{
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
* consistency in testing and feature parity among all, so we should
* try to keep these invariants in place for everybody.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (!pfn_modify_allowed(pfn, pgprot))
return VM_FAULT_SIGBUS;
track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
false);
}
EXPORT_SYMBOL(vmf_insert_pfn_prot);
/**
* vmf_insert_pfn - insert single pfn into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
*
* Similar to vm_insert_page, this allows drivers to insert individual pages
* they've allocated into a user vma. Same comments apply.
*
* This function should only be called from a vm_ops->fault handler, and
* in that case the handler should return the result of this function.
*
* vma cannot be a COW mapping.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
* Context: Process context. May allocate using %GFP_KERNEL.
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
}
EXPORT_SYMBOL(vmf_insert_pfn);
static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
{
/* these checks mirror the abort conditions in vm_normal_page */
if (vma->vm_flags & VM_MIXEDMAP)
return true;
if (pfn_t_devmap(pfn))
return true;
if (pfn_t_special(pfn))
return true;
if (is_zero_pfn(pfn_t_to_pfn(pfn)))
return true;
return false;
}
static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn, pgprot_t pgprot,
bool mkwrite)
{
int err;
BUG_ON(!vm_mixed_ok(vma, pfn));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
track_pfn_insert(vma, &pgprot, pfn);
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
return VM_FAULT_SIGBUS;
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
/*
* If we don't have pte special, then we have to use the pfn_valid()
* based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
* refcount the page if pfn_valid is true (hence insert_page rather
* than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
* without pte special, it would there be refcounted as a normal page.
*/
if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) &&
!pfn_t_devmap(pfn) && pfn_t_valid(pfn)) {
struct page *page;
/*
* At this point we are committed to insert_page()
* regardless of whether the caller specified flags that
* result in pfn_t_has_page() == false.
*/
page = pfn_to_page(pfn_t_to_pfn(pfn));
err = insert_page(vma, addr, page, pgprot);
} else {
return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
}
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
if (err == -ENOMEM)
return VM_FAULT_OOM;
if (err < 0 && err != -EBUSY)
return VM_FAULT_SIGBUS;
return VM_FAULT_NOPAGE;
}
/**
* vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
* @pgprot: pgprot flags for the inserted page
*
* This is exactly like vmf_insert_mixed(), except that it allows drivers
* to override pgprot on a per-page basis.
*
* Typically this function should be used by drivers to set caching- and
* encryption bits different than those of @vma->vm_page_prot, because
* the caching- or encryption mode may not be known at mmap() time.
* This is ok as long as @vma->vm_page_prot is not used by the core vm
* to set caching and encryption bits for those vmas (except for COW pages).
* This is ensured by core vm only modifying these page table entries using
* functions that don't touch caching- or encryption bits, using pte_modify()
* if needed. (See for example mprotect()).
* Also when new page-table entries are created, this is only done using the
* fault() callback, and never using the value of vma->vm_page_prot,
* except for page-table entries that point to anonymous pages as the result
* of COW.
*
* Context: Process context. May allocate using %GFP_KERNEL.
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn, pgprot_t pgprot)
{
return __vm_insert_mixed(vma, addr, pfn, pgprot, false);
}
EXPORT_SYMBOL(vmf_insert_mixed_prot);
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn)
{
return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false);
}
EXPORT_SYMBOL(vmf_insert_mixed);
/*
* If the insertion of PTE failed because someone else already added a
* different entry in the mean time, we treat that as success as we assume
* the same entry was actually inserted.
*/
vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn)
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
{
return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true);
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
}
EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);
mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:18:35 +03:00
/*
* maps a range of physical memory into the requested pages. the old
* mappings are removed. any references to nonexistent pages results
* in null mappings (currently treated as "copy-on-access")
*/
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pte_t *pte, *mapped_pte;
spinlock_t *ptl;
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
int err = 0;
mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
arch_enter_lazy_mmu_mode();
do {
BUG_ON(!pte_none(*pte));
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
if (!pfn_modify_allowed(pfn, prot)) {
err = -EACCES;
break;
}
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 13:13:00 +04:00
set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(mapped_pte, ptl);
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
return err;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
int err;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
VM_BUG_ON(pmd_trans_huge(*pmd));
do {
next = pmd_addr_end(addr, end);
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
err = remap_pte_range(mm, pmd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
int err;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
err = remap_pmd_range(mm, pud, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
p4d_t *p4d;
unsigned long next;
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
int err;
pfn -= addr >> PAGE_SHIFT;
p4d = p4d_alloc(mm, pgd, addr);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings For L1TF PROT_NONE mappings are protected by inverting the PFN in the page table entry. This sets the high bits in the CPU's address space, thus making sure to point to not point an unmapped entry to valid cached memory. Some server system BIOSes put the MMIO mappings high up in the physical address space. If such an high mapping was mapped to unprivileged users they could attack low memory by setting such a mapping to PROT_NONE. This could happen through a special device driver which is not access protected. Normal /dev/mem is of course access protected. To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings. Valid page mappings are allowed because the system is then unsafe anyways. It's not expected that users commonly use PROT_NONE on MMIO. But to minimize any impact this is only enforced if the mapping actually refers to a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip the check for root. For mmaps this is straight forward and can be handled in vm_insert_pfn and in remap_pfn_range(). For mprotect it's a bit trickier. At the point where the actual PTEs are accessed a lot of state has been changed and it would be difficult to undo on an error. Since this is a uncommon case use a separate early page talk walk pass for MMIO PROT_NONE mappings that checks for this condition early. For non MMIO and non PROT_NONE there are no changes. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Dave Hansen <dave.hansen@intel.com>
2018-06-14 01:48:27 +03:00
err = remap_pud_range(mm, p4d, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (p4d++, addr = next, addr != end);
return 0;
}
/*
* Variant of remap_pfn_range that does not call track_pfn_remap. The caller
* must have pre-validated the caching bits of the pgprot_t.
*/
int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
int err;
if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
return -EINVAL;
/*
* Physically remapped pages are special. Tell the
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
* VM_PFNMAP tells the core MM that the base pages are just
* raw PFN mappings, and do not have a "struct page" associated
* with them.
mm: kill vma flag VM_RESERVED and mm->reserved_vm counter A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA, currently it lost original meaning but still has some effects: | effect | alternative flags -+------------------------+--------------------------------------------- 1| account as reserved_vm | VM_IO 2| skip in core dump | VM_IO, VM_DONTDUMP 3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP 4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP This patch removes reserved_vm counter from mm_struct. Seems like nobody cares about it, it does not exported into userspace directly, it only reduces total_vm showed in proc. Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP. remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP. remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP. [akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:29:02 +04:00
* VM_DONTEXPAND
* Disable vma merging and expanding with mremap().
* VM_DONTDUMP
* Omit vma from core dump, even when VM_IO turned off.
*
* There's a horrible special case to handle copy-on-write
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
mm, x86, pat: rework linear pfn-mmap tracking Replace the generic vma-flag VM_PFN_AT_MMAP with x86-only VM_PAT. We can toss mapping address from remap_pfn_range() into track_pfn_vma_new(), and collect all PAT-related logic together in arch/x86/. This patch also restores orignal frustration-free is_cow_mapping() check in remap_pfn_range(), as it was before commit v2.6.28-rc8-88-g3c8bb73 ("x86: PAT: store vm_pgoff for all linear_over_vma_region mappings - v3") is_linear_pfn_mapping() checks can be removed from mm/huge_memory.c, because it already handled by VM_PFNMAP in VM_NO_THP bit-mask. [suresh.b.siddha@intel.com: Reset the VM_PAT flag as part of untrack_pfn_vma()] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venki@google.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:34 +04:00
* See vm_normal_page() for details.
*/
mm, x86, pat: rework linear pfn-mmap tracking Replace the generic vma-flag VM_PFN_AT_MMAP with x86-only VM_PAT. We can toss mapping address from remap_pfn_range() into track_pfn_vma_new(), and collect all PAT-related logic together in arch/x86/. This patch also restores orignal frustration-free is_cow_mapping() check in remap_pfn_range(), as it was before commit v2.6.28-rc8-88-g3c8bb73 ("x86: PAT: store vm_pgoff for all linear_over_vma_region mappings - v3") is_linear_pfn_mapping() checks can be removed from mm/huge_memory.c, because it already handled by VM_PFNMAP in VM_NO_THP bit-mask. [suresh.b.siddha@intel.com: Reset the VM_PAT flag as part of untrack_pfn_vma()] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venki@google.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:34 +04:00
if (is_cow_mapping(vma->vm_flags)) {
if (addr != vma->vm_start || end != vma->vm_end)
return -EINVAL;
vma->vm_pgoff = pfn;
mm, x86, pat: rework linear pfn-mmap tracking Replace the generic vma-flag VM_PFN_AT_MMAP with x86-only VM_PAT. We can toss mapping address from remap_pfn_range() into track_pfn_vma_new(), and collect all PAT-related logic together in arch/x86/. This patch also restores orignal frustration-free is_cow_mapping() check in remap_pfn_range(), as it was before commit v2.6.28-rc8-88-g3c8bb73 ("x86: PAT: store vm_pgoff for all linear_over_vma_region mappings - v3") is_linear_pfn_mapping() checks can be removed from mm/huge_memory.c, because it already handled by VM_PFNMAP in VM_NO_THP bit-mask. [suresh.b.siddha@intel.com: Reset the VM_PAT flag as part of untrack_pfn_vma()] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venki@google.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:28:34 +04:00
}
mm: kill vma flag VM_RESERVED and mm->reserved_vm counter A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA, currently it lost original meaning but still has some effects: | effect | alternative flags -+------------------------+--------------------------------------------- 1| account as reserved_vm | VM_IO 2| skip in core dump | VM_IO, VM_DONTDUMP 3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP 4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP This patch removes reserved_vm counter from mm_struct. Seems like nobody cares about it, it does not exported into userspace directly, it only reduces total_vm showed in proc. Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP. remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP. remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP. [akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 03:29:02 +04:00
vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
do {
next = pgd_addr_end(addr, end);
err = remap_p4d_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
return 0;
}
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
* @addr: target page aligned user address to start at
* @pfn: page frame number of kernel physical memory address
* @size: size of mapping area
* @prot: page protection flags for this mapping
*
* Note: this is only safe if the mm semaphore is held when called.
*
* Return: %0 on success, negative error code otherwise.
*/
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
int err;
err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
if (err)
return -EINVAL;
err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
if (err)
untrack_pfn(vma, pfn, PAGE_ALIGN(size));
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
/**
* vm_iomap_memory - remap memory to userspace
* @vma: user vma to map to
* @start: start of the physical memory to be mapped
* @len: size of area
*
* This is a simplified io_remap_pfn_range() for common driver use. The
* driver just needs to give us the physical memory range to be mapped,
* we'll figure out the rest from the vma information.
*
* NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
* whatever write-combining details or similar.
*
* Return: %0 on success, negative error code otherwise.
*/
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
unsigned long vm_len, pfn, pages;
/* Check that the physical memory area passed in looks valid */
if (start + len < start)
return -EINVAL;
/*
* You *really* shouldn't map things that aren't page-aligned,
* but we've historically allowed it because IO memory might
* just have smaller alignment.
*/
len += start & ~PAGE_MASK;
pfn = start >> PAGE_SHIFT;
pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
if (pfn + pages < pfn)
return -EINVAL;
/* We start the mapping 'vm_pgoff' pages into the area */
if (vma->vm_pgoff > pages)
return -EINVAL;
pfn += vma->vm_pgoff;
pages -= vma->vm_pgoff;
/* Can we fit all of the mapping? */
vm_len = vma->vm_end - vma->vm_start;
if (vm_len >> PAGE_SHIFT > pages)
return -EINVAL;
/* Ok, let it rip */
return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_iomap_memory);
static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pte_t *pte, *mapped_pte;
int err = 0;
treewide: Remove uninitialized_var() usage Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. In preparation for removing[2] the[3] macro[4], remove all remaining needless uses with the following script: git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \ xargs perl -pi -e \ 's/\buninitialized_var\(([^\)]+)\)/\1/g; s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;' drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid pathological white-space. No outstanding warnings were found building allmodconfig with GCC 9.3.0 for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64, alpha, and m68k. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5 Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs Signed-off-by: Kees Cook <keescook@chromium.org>
2020-06-03 23:09:38 +03:00
spinlock_t *ptl;
if (create) {
mapped_pte = pte = (mm == &init_mm) ?
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pte_alloc_kernel_track(pmd, addr, mask) :
pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
} else {
mapped_pte = pte = (mm == &init_mm) ?
pte_offset_kernel(pmd, addr) :
pte_offset_map_lock(mm, pmd, addr, &ptl);
}
BUG_ON(pmd_huge(*pmd));
arch_enter_lazy_mmu_mode();
if (fn) {
do {
if (create || !pte_none(*pte)) {
err = fn(pte++, addr, data);
if (err)
break;
}
} while (addr += PAGE_SIZE, addr != end);
}
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
*mask |= PGTBL_PTE_MODIFIED;
arch_leave_lazy_mmu_mode();
if (mm != &init_mm)
pte_unmap_unlock(mapped_pte, ptl);
return err;
}
static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
int err = 0;
BUG_ON(pud_huge(*pud));
if (create) {
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pmd = pmd_alloc_track(mm, pud, addr, mask);
if (!pmd)
return -ENOMEM;
} else {
pmd = pmd_offset(pud, addr);
}
do {
next = pmd_addr_end(addr, end);
if (pmd_none(*pmd) && !create)
continue;
if (WARN_ON_ONCE(pmd_leaf(*pmd)))
return -EINVAL;
if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
if (!create)
continue;
pmd_clear_bad(pmd);
}
err = apply_to_pte_range(mm, pmd, addr, next,
fn, data, create, mask);
if (err)
break;
} while (pmd++, addr = next, addr != end);
return err;
}
static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
int err = 0;
if (create) {
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pud = pud_alloc_track(mm, p4d, addr, mask);
if (!pud)
return -ENOMEM;
} else {
pud = pud_offset(p4d, addr);
}
do {
next = pud_addr_end(addr, end);
if (pud_none(*pud) && !create)
continue;
if (WARN_ON_ONCE(pud_leaf(*pud)))
return -EINVAL;
if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) {
if (!create)
continue;
pud_clear_bad(pud);
}
err = apply_to_pmd_range(mm, pud, addr, next,
fn, data, create, mask);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pte_fn_t fn, void *data, bool create,
pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
int err = 0;
if (create) {
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
p4d = p4d_alloc_track(mm, pgd, addr, mask);
if (!p4d)
return -ENOMEM;
} else {
p4d = p4d_offset(pgd, addr);
}
do {
next = p4d_addr_end(addr, end);
if (p4d_none(*p4d) && !create)
continue;
if (WARN_ON_ONCE(p4d_leaf(*p4d)))
return -EINVAL;
if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
if (!create)
continue;
p4d_clear_bad(p4d);
}
err = apply_to_pud_range(mm, p4d, addr, next,
fn, data, create, mask);
if (err)
break;
} while (p4d++, addr = next, addr != end);
return err;
}
static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn,
void *data, bool create)
{
pgd_t *pgd;
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
unsigned long start = addr, next;
unsigned long end = addr + size;
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
pgtbl_mod_mask mask = 0;
int err = 0;
if (WARN_ON(addr >= end))
return -EINVAL;
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none(*pgd) && !create)
continue;
if (WARN_ON_ONCE(pgd_leaf(*pgd)))
return -EINVAL;
if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
if (!create)
continue;
pgd_clear_bad(pgd);
}
err = apply_to_p4d_range(mm, pgd, addr, next,
fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
mm: track page table modifications in __apply_to_page_range() __apply_to_page_range() is also used to change and/or allocate page-table pages in the vmalloc area of the address space. Make sure these changes get synchronized to other page-tables in the system by calling arch_sync_kernel_mappings() when necessary. The impact appears limited to x86-32, where apply_to_page_range may miss updating the PMD. That leads to explosions in drivers like BUG: unable to handle page fault for address: fe036000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 00000000 Oops: 0002 [#1] SMP CPU: 3 PID: 1300 Comm: gem_concurrent_ Not tainted 5.9.0-rc1+ #16 Hardware name: /NUC6i3SYB, BIOS SYSKLi35.86A.0024.2015.1027.2142 10/27/2015 EIP: __execlists_context_alloc+0x132/0x2d0 [i915] Code: 31 d2 89 f0 e8 2f 55 02 00 89 45 e8 3d 00 f0 ff ff 0f 87 11 01 00 00 8b 4d e8 03 4b 30 b8 5a 5a 5a 5a ba 01 00 00 00 8d 79 04 <c7> 01 5a 5a 5a 5a c7 81 fc 0f 00 00 5a 5a 5a 5a 83 e7 fc 29 f9 81 EAX: 5a5a5a5a EBX: f60ca000 ECX: fe036000 EDX: 00000001 ESI: f43b7340 EDI: fe036004 EBP: f6389cb8 ESP: f6389c9c DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010286 CR0: 80050033 CR2: fe036000 CR3: 2d361000 CR4: 001506d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: fffe0ff0 DR7: 00000400 Call Trace: execlists_context_alloc+0x10/0x20 [i915] intel_context_alloc_state+0x3f/0x70 [i915] __intel_context_do_pin+0x117/0x170 [i915] i915_gem_do_execbuffer+0xcc7/0x2500 [i915] i915_gem_execbuffer2_ioctl+0xcd/0x1f0 [i915] drm_ioctl_kernel+0x8f/0xd0 drm_ioctl+0x223/0x3d0 __ia32_sys_ioctl+0x1ab/0x760 __do_fast_syscall_32+0x3f/0x70 do_fast_syscall_32+0x29/0x60 do_SYSENTER_32+0x15/0x20 entry_SYSENTER_32+0x9f/0xf2 EIP: 0xb7f28559 Code: 03 74 c0 01 10 05 03 74 b8 01 10 06 03 74 b4 01 10 07 03 74 b0 01 10 08 03 74 d8 01 00 00 00 00 00 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 8d 76 00 58 b8 77 00 00 00 cd 80 90 8d 76 EAX: ffffffda EBX: 00000005 ECX: c0406469 EDX: bf95556c ESI: b7e68000 EDI: c0406469 EBP: 00000005 ESP: bf9554d8 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00000296 Modules linked in: i915 x86_pkg_temp_thermal intel_powerclamp crc32_pclmul crc32c_intel intel_cstate intel_uncore intel_gtt drm_kms_helper intel_pch_thermal video button autofs4 i2c_i801 i2c_smbus fan CR2: 00000000fe036000 It looks like kasan, xen and i915 are vulnerable. Actual impact is "on thinkpad X60 in 5.9-rc1, screen starts blinking after 30-or-so minutes, and machine is unusable" [sfr@canb.auug.org.au: ARCH_PAGE_TABLE_SYNC_MASK needs vmalloc.h] Link: https://lkml.kernel.org/r/20200825172508.16800a4f@canb.auug.org.au [chris@chris-wilson.co.uk: changelog addition] [pavel@ucw.cz: changelog addition] Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified") Fixes: 86cf69f1d893 ("x86/mm/32: implement arch_sync_kernel_mappings()") Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Chris Wilson <chris@chris-wilson.co.uk> [x86-32] Tested-by: Pavel Machek <pavel@ucw.cz> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: <stable@vger.kernel.org> [5.8+] Link: https://lkml.kernel.org/r/20200821123746.16904-1-joro@8bytes.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-05 02:35:43 +03:00
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, start + size);
return err;
}
/*
* Scan a region of virtual memory, filling in page tables as necessary
* and calling a provided function on each leaf page table.
*/
int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn, void *data)
{
return __apply_to_page_range(mm, addr, size, fn, data, true);
}
EXPORT_SYMBOL_GPL(apply_to_page_range);
/*
* Scan a region of virtual memory, calling a provided function on
* each leaf page table where it exists.
*
* Unlike apply_to_page_range, this does _not_ fill in page tables
* where they are absent.
*/
int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn, void *data)
{
return __apply_to_page_range(mm, addr, size, fn, data, false);
}
EXPORT_SYMBOL_GPL(apply_to_existing_page_range);
/*
* handle_pte_fault chooses page fault handler according to an entry which was
* read non-atomically. Before making any commitment, on those architectures
* or configurations (e.g. i386 with PAE) which might give a mix of unmatched
* parts, do_swap_page must check under lock before unmapping the pte and
* proceeding (but do_wp_page is only called after already making such a check;
* and do_anonymous_page can safely check later on).
*/
static inline int pte_unmap_same(struct vm_fault *vmf)
{
int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION)
if (sizeof(pte_t) > sizeof(unsigned long)) {
spinlock_t *ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:40 +03:00
spin_lock(ptl);
same = pte_same(*vmf->pte, vmf->orig_pte);
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:40 +03:00
spin_unlock(ptl);
}
#endif
pte_unmap(vmf->pte);
vmf->pte = NULL;
return same;
}
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
static inline bool cow_user_page(struct page *dst, struct page *src,
struct vm_fault *vmf)
{
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
bool ret;
void *kaddr;
void __user *uaddr;
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
bool locked = false;
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = vmf->address;
if (likely(src)) {
copy_user_highpage(dst, src, addr, vma);
return true;
}
/*
* If the source page was a PFN mapping, we don't have
* a "struct page" for it. We do a best-effort copy by
* just copying from the original user address. If that
* fails, we just zero-fill it. Live with it.
*/
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
kaddr = kmap_atomic(dst);
uaddr = (void __user *)(addr & PAGE_MASK);
/*
* On architectures with software "accessed" bits, we would
* take a double page fault, so mark it accessed here.
*/
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
pte_t entry;
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
locked = true;
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
/*
* Other thread has already handled the fault
* and update local tlb only
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
*/
update_mmu_tlb(vma, addr, vmf->pte);
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
ret = false;
goto pte_unlock;
}
entry = pte_mkyoung(vmf->orig_pte);
if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
update_mmu_cache(vma, addr, vmf->pte);
}
/*
* This really shouldn't fail, because the page is there
* in the page tables. But it might just be unreadable,
* in which case we just give up and fill the result with
* zeroes.
*/
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
if (locked)
goto warn;
/* Re-validate under PTL if the page is still mapped */
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
locked = true;
if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
/* The PTE changed under us, update local tlb */
update_mmu_tlb(vma, addr, vmf->pte);
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
ret = false;
goto pte_unlock;
}
/*
* The same page can be mapped back since last copy attempt.
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
* Try to copy again under PTL.
*/
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
/*
* Give a warn in case there can be some obscure
* use-case
*/
warn:
WARN_ON_ONCE(1);
clear_page(kaddr);
}
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
}
ret = true;
pte_unlock:
mm: avoid data corruption on CoW fault into PFN-mapped VMA Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem: WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30 The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page. This happens because of race between MADV_DONTNEED and CoW page fault: CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page() The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte. The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page. Reported-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Cc: Justin He <Justin.He@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-06 09:28:32 +03:00
if (locked)
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
pte_unmap_unlock(vmf->pte, vmf->ptl);
kunmap_atomic(kaddr);
flush_dcache_page(dst);
return ret;
}
mm: allow GFP_{FS,IO} for page_cache_read page cache allocation page_cache_read has been historically using page_cache_alloc_cold to allocate a new page. This means that mapping_gfp_mask is used as the base for the gfp_mask. Many filesystems are setting this mask to GFP_NOFS to prevent from fs recursion issues. page_cache_read is called from the vm_operations_struct::fault() context during the page fault. This context doesn't need the reclaim protection normally. ceph and ocfs2 which call filemap_fault from their fault handlers seem to be OK because they are not taking any fs lock before invoking generic implementation. xfs which takes XFS_MMAPLOCK_SHARED is safe from the reclaim recursion POV because this lock serializes truncate and punch hole with the page faults and it doesn't get involved in the reclaim. There is simply no reason to deliberately use a weaker allocation context when a __GFP_FS | __GFP_IO can be used. The GFP_NOFS protection might be even harmful. There is a push to fail GFP_NOFS allocations rather than loop within allocator indefinitely with a very limited reclaim ability. Once we start failing those requests the OOM killer might be triggered prematurely because the page cache allocation failure is propagated up the page fault path and end up in pagefault_out_of_memory. We cannot play with mapping_gfp_mask directly because that would be racy wrt. parallel page faults and it might interfere with other users who really rely on NOFS semantic from the stored gfp_mask. The mask is also inode proper so it would even be a layering violation. What we can do instead is to push the gfp_mask into struct vm_fault and allow fs layer to overwrite it should the callback need to be called with a different allocation context. Initialize the default to (mapping_gfp_mask | __GFP_FS | __GFP_IO) because this should be safe from the page fault path normally. Why do we care about mapping_gfp_mask at all then? Because this doesn't hold only reclaim protection flags but it also might contain zone and movability restrictions (GFP_DMA32, __GFP_MOVABLE and others) so we have to respect those. Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Jan Kara <jack@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Cc: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 02:20:12 +03:00
static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
{
struct file *vm_file = vma->vm_file;
if (vm_file)
return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO;
/*
* Special mappings (e.g. VDSO) do not have any file so fake
* a default GFP_KERNEL for them.
*/
return GFP_KERNEL;
}
/*
* Notify the address space that the page is about to become writable so that
* it can prohibit this or wait for the page to get into an appropriate state.
*
* We do this without the lock held, so that it can sleep if it needs to.
*/
static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
{
vm_fault_t ret;
struct page *page = vmf->page;
unsigned int old_flags = vmf->flags;
vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
if (vmf->vma->vm_file &&
IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host))
return VM_FAULT_SIGBUS;
ret = vmf->vma->vm_ops->page_mkwrite(vmf);
/* Restore original flags so that caller is not surprised */
vmf->flags = old_flags;
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
return ret;
if (unlikely(!(ret & VM_FAULT_LOCKED))) {
lock_page(page);
if (!page->mapping) {
unlock_page(page);
return 0; /* retry */
}
ret |= VM_FAULT_LOCKED;
} else
VM_BUG_ON_PAGE(!PageLocked(page), page);
return ret;
}
/*
* Handle dirtying of a page in shared file mapping on a write fault.
*
* The function expects the page to be locked and unlocks it.
*/
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
{
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping;
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
struct page *page = vmf->page;
bool dirtied;
bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
dirtied = set_page_dirty(page);
VM_BUG_ON_PAGE(PageAnon(page), page);
/*
* Take a local copy of the address_space - page.mapping may be zeroed
* by truncate after unlock_page(). The address_space itself remains
* pinned by vma->vm_file's reference. We rely on unlock_page()'s
* release semantics to prevent the compiler from undoing this copying.
*/
mapping = page_rmapping(page);
unlock_page(page);
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
if (!page_mkwrite)
file_update_time(vma->vm_file);
/*
* Throttle page dirtying rate down to writeback speed.
*
* mapping may be NULL here because some device drivers do not
* set page.mapping but still dirty their pages
*
* Drop the mmap_lock before waiting on IO, if we can. The file
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
* is pinning the mapping, as per above.
*/
if ((dirtied || page_mkwrite) && mapping) {
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
struct file *fpin;
fpin = maybe_unlock_mmap_for_io(vmf, NULL);
balance_dirty_pages_ratelimited(mapping);
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
if (fpin) {
fput(fpin);
return VM_FAULT_RETRY;
}
}
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
return 0;
}
mm: refactor do_wp_page, extract the reuse case Currently do_wp_page contains 265 code lines. It also contains 9 goto statements, of which 5 are targeting labels which are not cleanup related. This makes the function extremely difficult to understand. The following patches are an attempt at breaking the function to its basic components, and making it easier to understand. The patches are straight forward function extractions from do_wp_page. As we extract functions, we remove unneeded parameters and simplify the code as much as possible. However, the functionality is supposed to remain completely unchanged. The patches also attempt to document the functionality of each extracted function. In patch 2, we split the unlock logic to the contain logic relevant to specific needs of each use case, instead of having huge number of conditional decisions in a single unlock flow. This patch (of 4): When do_wp_page is ending, in several cases it needs to reuse the existing page. This is achieved by making the page table writable, and possibly updating the page-cache state. Currently, this logic was "called" by using a goto jump. This makes following the control flow of the function harder. It is also against the coding style guidelines for using goto. As the code can easily be refactored into a specialized function, refactor it out and simplify the code flow in do_wp_page. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Haggai Eran <haggaie@mellanox.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Feiner <pfeiner@google.com> Cc: Michel Lespinasse <walken@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 01:46:25 +03:00
/*
* Handle write page faults for pages that can be reused in the current vma
*
* This can happen either due to the mapping being with the VM_SHARED flag,
* or due to us being the last reference standing to the page. In either
* case, all we need to do here is to mark the page as writable and update
* any related book-keeping.
*/
static inline void wp_page_reuse(struct vm_fault *vmf)
__releases(vmf->ptl)
mm: refactor do_wp_page, extract the reuse case Currently do_wp_page contains 265 code lines. It also contains 9 goto statements, of which 5 are targeting labels which are not cleanup related. This makes the function extremely difficult to understand. The following patches are an attempt at breaking the function to its basic components, and making it easier to understand. The patches are straight forward function extractions from do_wp_page. As we extract functions, we remove unneeded parameters and simplify the code as much as possible. However, the functionality is supposed to remain completely unchanged. The patches also attempt to document the functionality of each extracted function. In patch 2, we split the unlock logic to the contain logic relevant to specific needs of each use case, instead of having huge number of conditional decisions in a single unlock flow. This patch (of 4): When do_wp_page is ending, in several cases it needs to reuse the existing page. This is achieved by making the page table writable, and possibly updating the page-cache state. Currently, this logic was "called" by using a goto jump. This makes following the control flow of the function harder. It is also against the coding style guidelines for using goto. As the code can easily be refactored into a specialized function, refactor it out and simplify the code flow in do_wp_page. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Haggai Eran <haggaie@mellanox.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Feiner <pfeiner@google.com> Cc: Michel Lespinasse <walken@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 01:46:25 +03:00
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = vmf->page;
mm: refactor do_wp_page, extract the reuse case Currently do_wp_page contains 265 code lines. It also contains 9 goto statements, of which 5 are targeting labels which are not cleanup related. This makes the function extremely difficult to understand. The following patches are an attempt at breaking the function to its basic components, and making it easier to understand. The patches are straight forward function extractions from do_wp_page. As we extract functions, we remove unneeded parameters and simplify the code as much as possible. However, the functionality is supposed to remain completely unchanged. The patches also attempt to document the functionality of each extracted function. In patch 2, we split the unlock logic to the contain logic relevant to specific needs of each use case, instead of having huge number of conditional decisions in a single unlock flow. This patch (of 4): When do_wp_page is ending, in several cases it needs to reuse the existing page. This is achieved by making the page table writable, and possibly updating the page-cache state. Currently, this logic was "called" by using a goto jump. This makes following the control flow of the function harder. It is also against the coding style guidelines for using goto. As the code can easily be refactored into a specialized function, refactor it out and simplify the code flow in do_wp_page. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Haggai Eran <haggaie@mellanox.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Feiner <pfeiner@google.com> Cc: Michel Lespinasse <walken@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 01:46:25 +03:00
pte_t entry;
/*
* Clear the pages cpupid information as the existing
* information potentially belongs to a now completely
* unrelated process.
*/
if (page)
page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1);
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = pte_mkyoung(vmf->orig_pte);
mm: refactor do_wp_page, extract the reuse case Currently do_wp_page contains 265 code lines. It also contains 9 goto statements, of which 5 are targeting labels which are not cleanup related. This makes the function extremely difficult to understand. The following patches are an attempt at breaking the function to its basic components, and making it easier to understand. The patches are straight forward function extractions from do_wp_page. As we extract functions, we remove unneeded parameters and simplify the code as much as possible. However, the functionality is supposed to remain completely unchanged. The patches also attempt to document the functionality of each extracted function. In patch 2, we split the unlock logic to the contain logic relevant to specific needs of each use case, instead of having huge number of conditional decisions in a single unlock flow. This patch (of 4): When do_wp_page is ending, in several cases it needs to reuse the existing page. This is achieved by making the page table writable, and possibly updating the page-cache state. Currently, this logic was "called" by using a goto jump. This makes following the control flow of the function harder. It is also against the coding style guidelines for using goto. As the code can easily be refactored into a specialized function, refactor it out and simplify the code flow in do_wp_page. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Haggai Eran <haggaie@mellanox.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Feiner <pfeiner@google.com> Cc: Michel Lespinasse <walken@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 01:46:25 +03:00
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
update_mmu_cache(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
count_vm_event(PGREUSE);
mm: refactor do_wp_page, extract the reuse case Currently do_wp_page contains 265 code lines. It also contains 9 goto statements, of which 5 are targeting labels which are not cleanup related. This makes the function extremely difficult to understand. The following patches are an attempt at breaking the function to its basic components, and making it easier to understand. The patches are straight forward function extractions from do_wp_page. As we extract functions, we remove unneeded parameters and simplify the code as much as possible. However, the functionality is supposed to remain completely unchanged. The patches also attempt to document the functionality of each extracted function. In patch 2, we split the unlock logic to the contain logic relevant to specific needs of each use case, instead of having huge number of conditional decisions in a single unlock flow. This patch (of 4): When do_wp_page is ending, in several cases it needs to reuse the existing page. This is achieved by making the page table writable, and possibly updating the page-cache state. Currently, this logic was "called" by using a goto jump. This makes following the control flow of the function harder. It is also against the coding style guidelines for using goto. As the code can easily be refactored into a specialized function, refactor it out and simplify the code flow in do_wp_page. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Haggai Eran <haggaie@mellanox.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Feiner <pfeiner@google.com> Cc: Michel Lespinasse <walken@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 01:46:25 +03:00
}
/*
* Handle the case of a page which we actually need to copy to a new page.
*
* Called with mmap_lock locked and the old page referenced, but
* without the ptl held.
*
* High level logic flow:
*
* - Allocate a page, copy the content of the old page to the new one.
* - Handle book keeping and accounting - cgroups, mmu-notifiers, etc.
* - Take the PTL. If the pte changed, bail out and release the allocated page
* - If the pte is still the way we remember it, update the page table and all
* relevant references. This includes dropping the reference the page-table
* held to the old page, as well as updating the rmap.
* - In any case, unlock the PTL and drop the reference we took to the old page.
*/
static vm_fault_t wp_page_copy(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct mm_struct *mm = vma->vm_mm;
struct page *old_page = vmf->page;
struct page *new_page = NULL;
pte_t entry;
int page_copied = 0;
struct mmu_notifier_range range;
if (unlikely(anon_vma_prepare(vma)))
goto oom;
if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
new_page = alloc_zeroed_user_highpage_movable(vma,
vmf->address);
if (!new_page)
goto oom;
} else {
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
vmf->address);
if (!new_page)
goto oom;
mm: fix double page fault on arm64 if PTE_AF is cleared When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page. To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24 The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3 As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64." This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page() Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill). [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork Signed-off-by: Jia He <justin.he@arm.com> Reported-by: Yibo Cai <Yibo.Cai@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2019-10-11 17:09:39 +03:00
if (!cow_user_page(new_page, old_page, vmf)) {
/*
* COW failed, if the fault was solved by other,
* it's fine. If not, userspace would re-fault on
* the same address and we will handle the fault
* from the second attempt.
*/
put_page(new_page);
if (old_page)
put_page(old_page);
return 0;
}
}
if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL))
goto oom_free_new;
cgroup_throttle_swaprate(new_page, GFP_KERNEL);
mm, memcg: Try charging a page before setting page up to date Historically memcg overhead was high even if memcg was unused. This has improved a lot but it still showed up in a profile summary as being a problem. /usr/src/linux-4.0-vanilla/mm/memcontrol.c 6.6441 395842 mem_cgroup_try_charge 2.950% 175781 __mem_cgroup_count_vm_event 1.431% 85239 mem_cgroup_page_lruvec 0.456% 27156 mem_cgroup_commit_charge 0.392% 23342 uncharge_list 0.323% 19256 mem_cgroup_update_lru_size 0.278% 16538 memcg_check_events 0.216% 12858 mem_cgroup_charge_statistics.isra.22 0.188% 11172 try_charge 0.150% 8928 commit_charge 0.141% 8388 get_mem_cgroup_from_mm 0.121% 7184 That is showing that 6.64% of system CPU cycles were in memcontrol.c and dominated by mem_cgroup_try_charge. The annotation shows that the bulk of the cost was checking PageSwapCache which is expected to be cache hot but is very expensive. The problem appears to be that __SetPageUptodate is called just before the check which is a write barrier. It is required to make sure struct page and page data is written before the PTE is updated and the data visible to userspace. memcg charging does not require or need the barrier but gets unfairly hit with the cost so this patch attempts the charging before the barrier. Aside from the accidental cost to memcg there is the added benefit that the barrier is avoided if the page cannot be charged. When applied the relevant profile summary is as follows. /usr/src/linux-4.0-chargefirst-v2r1/mm/memcontrol.c 3.7907 223277 __mem_cgroup_count_vm_event 1.143% 67312 mem_cgroup_page_lruvec 0.465% 27403 mem_cgroup_commit_charge 0.381% 22452 uncharge_list 0.332% 19543 mem_cgroup_update_lru_size 0.284% 16704 get_mem_cgroup_from_mm 0.271% 15952 mem_cgroup_try_charge 0.237% 13982 memcg_check_events 0.222% 13058 mem_cgroup_charge_statistics.isra.22 0.185% 10920 commit_charge 0.140% 8235 try_charge 0.131% 7716 That brings the overhead down to 3.79% and leaves the memcg fault accounting to the root cgroup but it's an improvement. The difference in headline performance of the page fault microbench is marginal as memcg is such a small component of it. pft faults 4.0.0 4.0.0 vanilla chargefirst Hmean faults/cpu-1 1443258.1051 ( 0.00%) 1509075.7561 ( 4.56%) Hmean faults/cpu-3 1340385.9270 ( 0.00%) 1339160.7113 ( -0.09%) Hmean faults/cpu-5 875599.0222 ( 0.00%) 874174.1255 ( -0.16%) Hmean faults/cpu-7 601146.6726 ( 0.00%) 601370.9977 ( 0.04%) Hmean faults/cpu-8 510728.2754 ( 0.00%) 510598.8214 ( -0.03%) Hmean faults/sec-1 1432084.7845 ( 0.00%) 1497935.5274 ( 4.60%) Hmean faults/sec-3 3943818.1437 ( 0.00%) 3941920.1520 ( -0.05%) Hmean faults/sec-5 3877573.5867 ( 0.00%) 3869385.7553 ( -0.21%) Hmean faults/sec-7 3991832.0418 ( 0.00%) 3992181.4189 ( 0.01%) Hmean faults/sec-8 3987189.8167 ( 0.00%) 3986452.2204 ( -0.02%) It's only visible at single threaded. The overhead is there for higher threads but other factors dominate. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 02:57:27 +03:00
__SetPageUptodate(new_page);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
/*
* Re-check the pte - we dropped the lock
*/
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
dec_mm_counter_fast(mm,
mm_counter_file(old_page));
inc_mm_counter_fast(mm, MM_ANONPAGES);
}
} else {
inc_mm_counter_fast(mm, MM_ANONPAGES);
}
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/*
* Clear the pte entry and flush it first, before updating the
* pte with the new entry, to keep TLBs on different CPUs in
* sync. This code used to set the new PTE then flush TLBs, but
* that left a window where the new PTE could be loaded into
* some TLBs while the old PTE remains in others.
*/
ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
page_add_new_anon_rmap(new_page, vma, vmf->address, false);
mm/vmscan: protect the workingset on anonymous LRU In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:30:40 +03:00
lru_cache_add_inactive_or_unevictable(new_page, vma);
/*
* We call the notify macro here because, when using secondary
* mmu page tables (such as kvm shadow page tables), we want the
* new page to be mapped directly into the secondary page table.
*/
set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
update_mmu_cache(vma, vmf->address, vmf->pte);
if (old_page) {
/*
* Only after switching the pte to the new page may
* we remove the mapcount here. Otherwise another
* process may come and find the rmap count decremented
* before the pte is switched to the new page, and
* "reuse" the old page writing into it while our pte
* here still points into it and can be read by other
* threads.
*
* The critical issue is to order this
* page_remove_rmap with the ptp_clear_flush above.
* Those stores are ordered by (if nothing else,)
* the barrier present in the atomic_add_negative
* in page_remove_rmap.
*
* Then the TLB flush in ptep_clear_flush ensures that
* no process can access the old page before the
* decremented mapcount is visible. And the old page
* cannot be reused until after the decremented
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
page_remove_rmap(old_page, vma, false);
}
/* Free the old page.. */
new_page = old_page;
page_copied = 1;
} else {
update_mmu_tlb(vma, vmf->address, vmf->pte);
}
if (new_page)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(new_page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
mm/mmu_notifier: avoid call to invalidate_range() in range_end() This is an optimization patch that only affect mmu_notifier users which rely on the invalidate_range() callback. This patch avoids calling that callback twice in a row from inside __mmu_notifier_invalidate_range_end Existing pattern (before this patch): mmu_notifier_invalidate_range_start() pte/pmd/pud_clear_flush_notify() mmu_notifier_invalidate_range() mmu_notifier_invalidate_range_end() mmu_notifier_invalidate_range() New pattern (after this patch): mmu_notifier_invalidate_range_start() pte/pmd/pud_clear_flush_notify() mmu_notifier_invalidate_range() mmu_notifier_invalidate_range_only_end() We call the invalidate_range callback after clearing the page table under the page table lock and we skip the call to invalidate_range inside the __mmu_notifier_invalidate_range_end() function. Idea from Andrea Arcangeli Link: http://lkml.kernel.org/r/20171017031003.7481-3-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Joerg Roedel <jroedel@suse.de> Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Alistair Popple <alistair@popple.id.au> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-16 04:34:11 +03:00
/*
* No need to double call mmu_notifier->invalidate_range() callback as
* the above ptep_clear_flush_notify() did already call it.
*/
mmu_notifier_invalidate_range_only_end(&range);
if (old_page) {
mm: free idle swap cache page after COW With commit 09854ba94c6a ("mm: do_wp_page() simplification"), after COW, the idle swap cache page (neither the page nor the corresponding swap entry is mapped by any process) will be left in the LRU list, even if it's in the active list or the head of the inactive list. So, the page reclaimer may take quite some overhead to reclaim these actually unused pages. To help the page reclaiming, in this patch, after COW, the idle swap cache page will be tried to be freed. To avoid to introduce much overhead to the hot COW code path, a) there's almost zero overhead for non-swap case via checking PageSwapCache() firstly. b) the page lock is acquired via trylock only. To test the patch, we used pmbench memory accessing benchmark with working-set larger than available memory on a 2-socket Intel server with a NVMe SSD as swap device. Test results shows that the pmbench score increases up to 23.8% with the decreased size of swap cache and swapin throughput. Link: https://lkml.kernel.org/r/20210601053143.1380078-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Johannes Weiner <hannes@cmpxchg.org> [use free_swap_cache()] Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@surriel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-29 05:37:12 +03:00
if (page_copied)
free_swap_cache(old_page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(old_page);
}
return page_copied ? VM_FAULT_WRITE : 0;
oom_free_new:
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(new_page);
oom:
if (old_page)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(old_page);
return VM_FAULT_OOM;
}
/**
* finish_mkwrite_fault - finish page fault for a shared mapping, making PTE
* writeable once the page is prepared
*
* @vmf: structure describing the fault
*
* This function handles all that is needed to finish a write page fault in a
* shared mapping due to PTE being read-only once the mapped page is prepared.
* It handles locking of PTE and modifying it.
*
* The function expects the page to be locked or other protection against
* concurrent faults / writeback (such as DAX radix tree locks).
*
* Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before
* we acquired PTE lock.
*/
vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
{
WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
/*
* We might have raced with another page fault while we released the
* pte_offset_map_lock.
*/
if (!pte_same(*vmf->pte, vmf->orig_pte)) {
update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return VM_FAULT_NOPAGE;
}
wp_page_reuse(vmf);
return 0;
}
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
/*
* Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
* mapping
*/
static vm_fault_t wp_pfn_shared(struct vm_fault *vmf)
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
{
struct vm_area_struct *vma = vmf->vma;
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
vm_fault_t ret;
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
pte_unmap_unlock(vmf->pte, vmf->ptl);
vmf->flags |= FAULT_FLAG_MKWRITE;
ret = vma->vm_ops->pfn_mkwrite(vmf);
if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
return ret;
return finish_mkwrite_fault(vmf);
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
}
wp_page_reuse(vmf);
return VM_FAULT_WRITE;
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
}
static vm_fault_t wp_page_shared(struct vm_fault *vmf)
__releases(vmf->ptl)
{
struct vm_area_struct *vma = vmf->vma;
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
vm_fault_t ret = VM_FAULT_WRITE;
get_page(vmf->page);
if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
vm_fault_t tmp;
pte_unmap_unlock(vmf->pte, vmf->ptl);
tmp = do_page_mkwrite(vmf);
if (unlikely(!tmp || (tmp &
(VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
put_page(vmf->page);
return tmp;
}
tmp = finish_mkwrite_fault(vmf);
if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
unlock_page(vmf->page);
put_page(vmf->page);
return tmp;
}
} else {
wp_page_reuse(vmf);
lock_page(vmf->page);
}
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
ret |= fault_dirty_shared_page(vmf);
put_page(vmf->page);
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
return ret;
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus we can safely just mark it writable once we've done any necessary
* COW.
*
* We also mark the page dirty at this point even though the page will
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), with pte both mapped and locked.
* We return with mmap_lock still held, but pte unmapped and unlocked.
*/
static vm_fault_t do_wp_page(struct vm_fault *vmf)
__releases(vmf->ptl)
{
struct vm_area_struct *vma = vmf->vma;
userfaultfd: wp: apply _PAGE_UFFD_WP bit Firstly, introduce two new flags MM_CP_UFFD_WP[_RESOLVE] for change_protection() when used with uffd-wp and make sure the two new flags are exclusively used. Then, - For MM_CP_UFFD_WP: apply the _PAGE_UFFD_WP bit and remove _PAGE_RW when a range of memory is write protected by uffd - For MM_CP_UFFD_WP_RESOLVE: remove the _PAGE_UFFD_WP bit and recover _PAGE_RW when write protection is resolved from userspace And use this new interface in mwriteprotect_range() to replace the old MM_CP_DIRTY_ACCT. Do this change for both PTEs and huge PMDs. Then we can start to identify which PTE/PMD is write protected by general (e.g., COW or soft dirty tracking), and which is for userfaultfd-wp. Since we should keep the _PAGE_UFFD_WP when doing pte_modify(), add it into _PAGE_CHG_MASK as well. Meanwhile, since we have this new bit, we can be even more strict when detecting uffd-wp page faults in either do_wp_page() or wp_huge_pmd(). After we're with _PAGE_UFFD_WP, a special case is when a page is both protected by the general COW logic and also userfault-wp. Here the userfault-wp will have higher priority and will be handled first. Only after the uffd-wp bit is cleared on the PTE/PMD will we continue to handle the general COW. These are the steps on what will happen with such a page: 1. CPU accesses write protected shared page (so both protected by general COW and uffd-wp), blocked by uffd-wp first because in do_wp_page we'll handle uffd-wp first, so it has higher priority than general COW. 2. Uffd service thread receives the request, do UFFDIO_WRITEPROTECT to remove the uffd-wp bit upon the PTE/PMD. However here we still keep the write bit cleared. Notify the blocked CPU. 3. The blocked CPU resumes the page fault process with a fault retry, during retry it'll notice it was not with the uffd-wp bit this time but it is still write protected by general COW, then it'll go though the COW path in the fault handler, copy the page, apply write bit where necessary, and retry again. 4. The CPU will be able to access this page with write bit set. Suggested-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Brian Geffon <bgeffon@google.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: David Hildenbrand <david@redhat.com> Cc: Martin Cracauer <cracauer@cons.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shli@fb.com> Link: http://lkml.kernel.org/r/20200220163112.11409-8-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:05:49 +03:00
if (userfaultfd_pte_wp(vma, *vmf->pte)) {
userfaultfd: wp: hook userfault handler to write protection fault There are several cases write protection fault happens. It could be a write to zero page, swaped page or userfault write protected page. When the fault happens, there is no way to know if userfault write protect the page before. Here we just blindly issue a userfault notification for vma with VM_UFFD_WP regardless if app write protects it yet. Application should be ready to handle such wp fault. In the swapin case, always swapin as readonly. This will cause false positive userfaults. We need to decide later if to eliminate them with a flag like soft-dirty in the swap entry (see _PAGE_SWP_SOFT_DIRTY). hugetlbfs wouldn't need to worry about swapouts but and tmpfs would be handled by a swap entry bit like anonymous memory. The main problem with no easy solution to eliminate the false positives, will be if/when userfaultfd is extended to real filesystem pagecache. When the pagecache is freed by reclaim we can't leave the radix tree pinned if the inode and in turn the radix tree is reclaimed as well. The estimation is that full accuracy and lack of false positives could be easily provided only to anonymous memory (as long as there's no fork or as long as MADV_DONTFORK is used on the userfaultfd anonymous range) tmpfs and hugetlbfs, it's most certainly worth to achieve it but in a later incremental patch. [peterx@redhat.com: don't conditionally drop FAULT_FLAG_WRITE in do_swap_page] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Cc: Shaohua Li <shli@fb.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/20200220163112.11409-3-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:05:29 +03:00
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_WP);
}
mm/userfaultfd: fix memory corruption due to writeprotect Userfaultfd self-test fails occasionally, indicating a memory corruption. Analyzing this problem indicates that there is a real bug since mmap_lock is only taken for read in mwriteprotect_range() and defers flushes, and since there is insufficient consideration of concurrent deferred TLB flushes in wp_page_copy(). Although the PTE is flushed from the TLBs in wp_page_copy(), this flush takes place after the copy has already been performed, and therefore changes of the page are possible between the time of the copy and the time in which the PTE is flushed. To make matters worse, memory-unprotection using userfaultfd also poses a problem. Although memory unprotection is logically a promotion of PTE permissions, and therefore should not require a TLB flush, the current userrfaultfd code might actually cause a demotion of the architectural PTE permission: when userfaultfd_writeprotect() unprotects memory region, it unintentionally *clears* the RW-bit if it was already set. Note that this unprotecting a PTE that is not write-protected is a valid use-case: the userfaultfd monitor might ask to unprotect a region that holds both write-protected and write-unprotected PTEs. The scenario that happens in selftests/vm/userfaultfd is as follows: cpu0 cpu1 cpu2 ---- ---- ---- [ Writable PTE cached in TLB ] userfaultfd_writeprotect() [ write-*unprotect* ] mwriteprotect_range() mmap_read_lock() change_protection() change_protection_range() ... change_pte_range() [ *clear* “write”-bit ] [ defer TLB flushes ] [ page-fault ] ... wp_page_copy() cow_user_page() [ copy page ] [ write to old page ] ... set_pte_at_notify() A similar scenario can happen: cpu0 cpu1 cpu2 cpu3 ---- ---- ---- ---- [ Writable PTE cached in TLB ] userfaultfd_writeprotect() [ write-protect ] [ deferred TLB flush ] userfaultfd_writeprotect() [ write-unprotect ] [ deferred TLB flush] [ page-fault ] wp_page_copy() cow_user_page() [ copy page ] ... [ write to page ] set_pte_at_notify() This race exists since commit 292924b26024 ("userfaultfd: wp: apply _PAGE_UFFD_WP bit"). Yet, as Yu Zhao pointed, these races became apparent since commit 09854ba94c6a ("mm: do_wp_page() simplification") which made wp_page_copy() more likely to take place, specifically if page_count(page) > 1. To resolve the aforementioned races, check whether there are pending flushes on uffd-write-protected VMAs, and if there are, perform a flush before doing the COW. Further optimizations will follow to avoid during uffd-write-unprotect unnecassary PTE write-protection and TLB flushes. Link: https://lkml.kernel.org/r/20210304095423.3825684-1-namit@vmware.com Fixes: 09854ba94c6a ("mm: do_wp_page() simplification") Signed-off-by: Nadav Amit <namit@vmware.com> Suggested-by: Yu Zhao <yuzhao@google.com> Reviewed-by: Peter Xu <peterx@redhat.com> Tested-by: Peter Xu <peterx@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Will Deacon <will@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: <stable@vger.kernel.org> [5.9+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-03-13 08:08:17 +03:00
/*
* Userfaultfd write-protect can defer flushes. Ensure the TLB
* is flushed in this case before copying.
*/
if (unlikely(userfaultfd_wp(vmf->vma) &&
mm_tlb_flush_pending(vmf->vma->vm_mm)))
flush_tlb_page(vmf->vma, vmf->address);
vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
if (!vmf->page) {
mm: dirty page accounting vs VM_MIXEDMAP Dirty page accounting accurately measures the amound of dirty pages in writable shared mappings by mapping the pages RO (as indicated by vma_wants_writenotify). We then trap on first write and call set_page_dirty() on the page, after which we map the page RW and continue execution. When we launder dirty pages, we call clear_page_dirty_for_io() which clears both the dirty flag, and maps the page RO again before we start writeout so that the story can repeat itself. vma_wants_writenotify() excludes VM_PFNMAP on the basis that we cannot do the regular dirty page stuff on raw PFNs and the memory isn't going anywhere anyway. The recently introduced VM_MIXEDMAP mixes both !pfn_valid() and pfn_valid() pages in a single mapping. We can't do dirty page accounting on !pfn_valid() pages as stated above, and mapping them RO causes them to be COW'ed on write, which breaks VM_SHARED semantics. Excluding VM_MIXEDMAP in vma_wants_writenotify() would mean we don't do the regular dirty page accounting for the pfn_valid() pages, which would bring back all the head-aches from inaccurate dirty page accounting. So instead, we let the !pfn_valid() pages get mapped RO, but fix them up unconditionally in the fault path. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: "Jared Hulbert" <jaredeh@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-04 20:59:24 +04:00
/*
mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared For VMAs that don't want write notifications, PTEs created for read faults have their write bit set. If the read fault happens after VM_SOFTDIRTY is cleared, then the PTE's softdirty bit will remain clear after subsequent writes. Here's a simple code snippet to demonstrate the bug: char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_SHARED, -1, 0); system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */ assert(*m == '\0'); /* new PTE allows write access */ assert(!soft_dirty(x)); *m = 'x'; /* should dirty the page */ assert(soft_dirty(x)); /* fails */ With this patch, write notifications are enabled when VM_SOFTDIRTY is cleared. Furthermore, to avoid unnecessary faults, write notifications are disabled when VM_SOFTDIRTY is set. As a side effect of enabling and disabling write notifications with care, this patch fixes a bug in mprotect where vm_page_prot bits set by drivers were zapped on mprotect. An analogous bug was fixed in mmap by commit c9d0bf241451 ("mm: uncached vma support with writenotify"). Signed-off-by: Peter Feiner <pfeiner@google.com> Reported-by: Peter Feiner <pfeiner@google.com> Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Jamie Liu <jamieliu@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 02:55:46 +04:00
* VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
* VM_PFNMAP VMA.
mm: dirty page accounting vs VM_MIXEDMAP Dirty page accounting accurately measures the amound of dirty pages in writable shared mappings by mapping the pages RO (as indicated by vma_wants_writenotify). We then trap on first write and call set_page_dirty() on the page, after which we map the page RW and continue execution. When we launder dirty pages, we call clear_page_dirty_for_io() which clears both the dirty flag, and maps the page RO again before we start writeout so that the story can repeat itself. vma_wants_writenotify() excludes VM_PFNMAP on the basis that we cannot do the regular dirty page stuff on raw PFNs and the memory isn't going anywhere anyway. The recently introduced VM_MIXEDMAP mixes both !pfn_valid() and pfn_valid() pages in a single mapping. We can't do dirty page accounting on !pfn_valid() pages as stated above, and mapping them RO causes them to be COW'ed on write, which breaks VM_SHARED semantics. Excluding VM_MIXEDMAP in vma_wants_writenotify() would mean we don't do the regular dirty page accounting for the pfn_valid() pages, which would bring back all the head-aches from inaccurate dirty page accounting. So instead, we let the !pfn_valid() pages get mapped RO, but fix them up unconditionally in the fault path. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: "Jared Hulbert" <jaredeh@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-04 20:59:24 +04:00
*
* We should not cow pages in a shared writeable mapping.
mm: new pfn_mkwrite same as page_mkwrite for VM_PFNMAP This will allow FS that uses VM_PFNMAP | VM_MIXEDMAP (no page structs) to get notified when access is a write to a read-only PFN. This can happen if we mmap() a file then first mmap-read from it to page-in a read-only PFN, than we mmap-write to the same page. We need this functionality to fix a DAX bug, where in the scenario above we fail to set ctime/mtime though we modified the file. An xfstest is attached to this patchset that shows the failure and the fix. (A DAX patch will follow) This functionality is extra important for us, because upon dirtying of a pmem page we also want to RDMA the page to a remote cluster node. We define a new pfn_mkwrite and do not reuse page_mkwrite because 1 - The name ;-) 2 - But mainly because it would take a very long and tedious audit of all page_mkwrite functions of VM_MIXEDMAP/VM_PFNMAP users. To make sure they do not now CRASH. For example current DAX code (which this is for) would crash. If we would want to reuse page_mkwrite, We will need to first patch all users, so to not-crash-on-no-page. Then enable this patch. But even if I did that I would not sleep so well at night. Adding a new vector is the safest thing to do, and is not that expensive. an extra pointer at a static function vector per driver. Also the new vector is better for performance, because else we Will call all current Kernel vectors, so to: check-ha-no-page-do-nothing and return. No need to call it from do_shared_fault because do_wp_page is called to change pte permissions anyway. Signed-off-by: Yigal Korman <yigal@plexistor.com> Signed-off-by: Boaz Harrosh <boaz@plexistor.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 02:15:11 +03:00
* Just mark the pages writable and/or call ops->pfn_mkwrite.
mm: dirty page accounting vs VM_MIXEDMAP Dirty page accounting accurately measures the amound of dirty pages in writable shared mappings by mapping the pages RO (as indicated by vma_wants_writenotify). We then trap on first write and call set_page_dirty() on the page, after which we map the page RW and continue execution. When we launder dirty pages, we call clear_page_dirty_for_io() which clears both the dirty flag, and maps the page RO again before we start writeout so that the story can repeat itself. vma_wants_writenotify() excludes VM_PFNMAP on the basis that we cannot do the regular dirty page stuff on raw PFNs and the memory isn't going anywhere anyway. The recently introduced VM_MIXEDMAP mixes both !pfn_valid() and pfn_valid() pages in a single mapping. We can't do dirty page accounting on !pfn_valid() pages as stated above, and mapping them RO causes them to be COW'ed on write, which breaks VM_SHARED semantics. Excluding VM_MIXEDMAP in vma_wants_writenotify() would mean we don't do the regular dirty page accounting for the pfn_valid() pages, which would bring back all the head-aches from inaccurate dirty page accounting. So instead, we let the !pfn_valid() pages get mapped RO, but fix them up unconditionally in the fault path. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: "Jared Hulbert" <jaredeh@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-04 20:59:24 +04:00
*/
if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))
return wp_pfn_shared(vmf);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return wp_page_copy(vmf);
mm: dirty page accounting vs VM_MIXEDMAP Dirty page accounting accurately measures the amound of dirty pages in writable shared mappings by mapping the pages RO (as indicated by vma_wants_writenotify). We then trap on first write and call set_page_dirty() on the page, after which we map the page RW and continue execution. When we launder dirty pages, we call clear_page_dirty_for_io() which clears both the dirty flag, and maps the page RO again before we start writeout so that the story can repeat itself. vma_wants_writenotify() excludes VM_PFNMAP on the basis that we cannot do the regular dirty page stuff on raw PFNs and the memory isn't going anywhere anyway. The recently introduced VM_MIXEDMAP mixes both !pfn_valid() and pfn_valid() pages in a single mapping. We can't do dirty page accounting on !pfn_valid() pages as stated above, and mapping them RO causes them to be COW'ed on write, which breaks VM_SHARED semantics. Excluding VM_MIXEDMAP in vma_wants_writenotify() would mean we don't do the regular dirty page accounting for the pfn_valid() pages, which would bring back all the head-aches from inaccurate dirty page accounting. So instead, we let the !pfn_valid() pages get mapped RO, but fix them up unconditionally in the fault path. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: "Jared Hulbert" <jaredeh@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-04 20:59:24 +04:00
}
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 10:30:57 +04:00
/*
* Take out anonymous pages first, anonymous shared vmas are
* not dirty accountable.
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 10:30:57 +04:00
*/
mm: reuse only-pte-mapped KSM page in do_wp_page() Add an optimization for KSM pages almost in the same way that we have for ordinary anonymous pages. If there is a write fault in a page, which is mapped to an only pte, and it is not related to swap cache; the page may be reused without copying its content. [ Note that we do not consider PageSwapCache() pages at least for now, since we don't want to complicate __get_ksm_page(), which has nice optimization based on this (for the migration case). Currenly it is spinning on PageSwapCache() pages, waiting for when they have unfreezed counters (i.e., for the migration finish). But we don't want to make it also spinning on swap cache pages, which we try to reuse, since there is not a very high probability to reuse them. So, for now we do not consider PageSwapCache() pages at all. ] So in reuse_ksm_page() we check for 1) PageSwapCache() and 2) page_stable_node(), to skip a page, which KSM is currently trying to link to stable tree. Then we do page_ref_freeze() to prohibit KSM to merge one more page into the page, we are reusing. After that, nobody can refer to the reusing page: KSM skips !PageSwapCache() pages with zero refcount; and the protection against of all other participants is the same as for reused ordinary anon pages pte lock, page lock and mmap_sem. [akpm@linux-foundation.org: replace BUG_ON()s with WARN_ON()s] Link: http://lkml.kernel.org/r/154471491016.31352.1168978849911555609.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com> Cc: Rik van Riel <riel@surriel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:43:06 +03:00
if (PageAnon(vmf->page)) {
struct page *page = vmf->page;
mm: optimize do_wp_page() for exclusive pages in the swapcache Patch series "mm: COW fixes part 1: fix the COW security issue for THP and swap", v3. This series attempts to optimize and streamline the COW logic for ordinary anon pages and THP anon pages, fixing two remaining instances of CVE-2020-29374 in do_swap_page() and do_huge_pmd_wp_page(): information can leak from a parent process to a child process via anonymous pages shared during fork(). This issue, including other related COW issues, has been summarized in [2]: "1. Observing Memory Modifications of Private Pages From A Child Process Long story short: process-private memory might not be as private as you think once you fork(): successive modifications of private memory regions in the parent process can still be observed by the child process, for example, by smart use of vmsplice()+munmap(). The core problem is that pinning pages readable in a child process, such as done via the vmsplice system call, can result in a child process observing memory modifications done in the parent process the child is not supposed to observe. [1] contains an excellent summary and [2] contains further details. This issue was assigned CVE-2020-29374 [9]. For this to trigger, it's required to use a fork() without subsequent exec(), for example, as used under Android zygote. Without further details about an application that forks less-privileged child processes, one cannot really say what's actually affected and what's not -- see the details section the end of this mail for a short sshd/openssh analysis. While commit 17839856fd58 ("gup: document and work around "COW can break either way" issue") fixed this issue and resulted in other problems (e.g., ptrace on pmem), commit 09854ba94c6a ("mm: do_wp_page() simplification") re-introduced part of the problem unfortunately. The original reproducer can be modified quite easily to use THP [3] and make the issue appear again on upstream kernels. I modified it to use hugetlb [4] and it triggers as well. The problem is certainly less severe with hugetlb than with THP; it merely highlights that we still have plenty of open holes we should be closing/fixing. Regarding vmsplice(), the only known workaround is to disallow the vmsplice() system call ... or disable THP and hugetlb. But who knows what else is affected (RDMA? O_DIRECT?) to achieve the same goal -- in the end, it's a more generic issue" This security issue was first reported by Jann Horn on 27 May 2020 and it currently affects anonymous pages during swapin, anonymous THP and hugetlb. This series tackles anonymous pages during swapin and anonymous THP: - do_swap_page() for handling COW on PTEs during swapin directly - do_huge_pmd_wp_page() for handling COW on PMD-mapped THP during write faults With this series, we'll apply the same COW logic we have in do_wp_page() to all swappable anon pages: don't reuse (map writable) the page in case there are additional references (page_count() != 1). All users of reuse_swap_page() are remove, and consequently reuse_swap_page() is removed. In general, we're struggling with the following COW-related issues: (1) "missed COW": we miss to copy on write and reuse the page (map it writable) although we must copy because there are pending references from another process to this page. The result is a security issue. (2) "wrong COW": we copy on write although we wouldn't have to and shouldn't: if there are valid GUP references, they will become out of sync with the pages mapped into the page table. We fail to detect that such a page can be reused safely, especially if never more than a single process mapped the page. The result is an intra process memory corruption. (3) "unnecessary COW": we copy on write although we wouldn't have to: performance degradation and temporary increases swap+memory consumption can be the result. While this series fixes (1) for swappable anon pages, it tries to reduce reported cases of (3) first as good and easy as possible to limit the impact when streamlining. The individual patches try to describe in which cases we will run into (3). This series certainly makes (2) worse for THP, because a THP will now get PTE-mapped on write faults if there are additional references, even if there was only ever a single process involved: once PTE-mapped, we'll copy each and every subpage and won't reuse any subpage as long as the underlying compound page wasn't split. I'm working on an approach to fix (2) and improve (3): PageAnonExclusive to mark anon pages that are exclusive to a single process, allow GUP pins only on such exclusive pages, and allow turning exclusive pages shared (clearing PageAnonExclusive) only if there are no GUP pins. Anon pages with PageAnonExclusive set never have to be copied during write faults, but eventually during fork() if they cannot be turned shared. The improved reuse logic in this series will essentially also be the logic to reset PageAnonExclusive. This work will certainly take a while, but I'm planning on sharing details before having code fully ready. #1-#5 can be applied independently of the rest. #6-#9 are mostly only cleanups related to reuse_swap_page(). Notes: * For now, I'll leave hugetlb code untouched: "unnecessary COW" might easily break existing setups because hugetlb pages are a scarce resource and we could just end up having to crash the application when we run out of hugetlb pages. We have to be very careful and the security aspect with hugetlb is most certainly less relevant than for unprivileged anon pages. * Instead of lru_add_drain() we might actually just drain the lru_add list or even just remove the single page of interest from the lru_add list. This would require a new helper function, and could be added if the conditional lru_add_drain() turn out to be a problem. * I extended the test case already included in [1] to also test for the newly found do_swap_page() case. I'll send that out separately once/if this part was merged. [1] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com [2] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com This patch (of 9): Liang Zhang reported [1] that the current COW logic in do_wp_page() is sub-optimal when it comes to swap+read fault+write fault of anonymous pages that have a single user, visible via a performance degradation in the redis benchmark. Something similar was previously reported [2] by Nadav with a simple reproducer. After we put an anon page into the swapcache and unmapped it from a single process, that process might read that page again and refault it read-only. If that process then writes to that page, the process is actually the exclusive user of the page, however, the COW logic in do_co_page() won't be able to reuse it due to the additional reference from the swapcache. Let's optimize for pages that have been added to the swapcache but only have an exclusive user. Try removing the swapcache reference if there is hope that we're the exclusive user. We will fail removing the swapcache reference in two scenarios: (1) There are additional swap entries referencing the page: copying instead of reusing is the right thing to do. (2) The page is under writeback: theoretically we might be able to reuse in some cases, however, we cannot remove the additional reference and will have to copy. Note that we'll only try removing the page from the swapcache when it's highly likely that we'll be the exclusive owner after removing the page from the swapache. As we're about to map that page writable and redirty it, that should not affect reclaim but is rather the right thing to do. Further, we might have additional references from the LRU pagevecs, which will force us to copy instead of being able to reuse. We'll try handling such references for some scenarios next. Concurrent writeback cannot be handled easily and we'll always have to copy. While at it, remove the superfluous page_mapcount() check: it's implicitly covered by the page_count() for ordinary anon pages. [1] https://lkml.kernel.org/r/20220113140318.11117-1-zhangliang5@huawei.com [2] https://lkml.kernel.org/r/0480D692-D9B2-429A-9A88-9BBA1331AC3A@gmail.com Link: https://lkml.kernel.org/r/20220131162940.210846-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Liang Zhang <zhangliang5@huawei.com> Reported-by: Nadav Amit <nadav.amit@gmail.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jann Horn <jannh@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:30 +03:00
/*
* We have to verify under page lock: these early checks are
* just an optimization to avoid locking the page and freeing
* the swapcache if there is little hope that we can reuse.
*
* PageKsm() doesn't necessarily raise the page refcount.
*/
mm: optimize do_wp_page() for fresh pages in local LRU pagevecs For example, if a page just got swapped in via a read fault, the LRU pagevecs might still hold a reference to the page. If we trigger a write fault on such a page, the additional reference from the LRU pagevecs will prohibit reusing the page. Let's conditionally drain the local LRU pagevecs when we stumble over a !PageLRU() page. We cannot easily drain remote LRU pagevecs and it might not be desirable performance-wise. Consequently, this will only avoid copying in some cases. Add a simple "page_count(page) > 3" check first but keep the "page_count(page) > 1 + PageSwapCache(page)" check in place, as we want to minimize cases where we remove a page from the swapcache but won't be able to reuse it, for example, because another process has it mapped R/O, to not affect reclaim. We cannot easily handle the following cases and we will always have to copy: (1) The page is referenced in the LRU pagevecs of other CPUs. We really would have to drain the LRU pagevecs of all CPUs -- most probably copying is much cheaper. (2) The page is already PageLRU() but is getting moved between LRU lists, for example, for activation (e.g., mark_page_accessed()), deactivation (MADV_COLD), or lazyfree (MADV_FREE). We'd have to drain mostly unconditionally, which might be bad performance-wise. Most probably this won't happen too often in practice. Note that there are other reasons why an anon page might temporarily not be PageLRU(): for example, compaction and migration have to isolate LRU pages from the LRU lists first (isolate_lru_page()), moving them to temporary local lists and clearing PageLRU() and holding an additional reference on the page. In that case, we'll always copy. This change seems to be fairly effective with the reproducer [1] shared by Nadav, as long as writeback is done synchronously, for example, using zram. However, with asynchronous writeback, we'll usually fail to free the swapcache because the page is still under writeback: something we cannot easily optimize for, and maybe it's not really relevant in practice. [1] https://lkml.kernel.org/r/0480D692-D9B2-429A-9A88-9BBA1331AC3A@gmail.com Link: https://lkml.kernel.org/r/20220131162940.210846-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:34 +03:00
if (PageKsm(page) || page_count(page) > 3)
goto copy;
if (!PageLRU(page))
/*
* Note: We cannot easily detect+handle references from
* remote LRU pagevecs or references to PageLRU() pages.
*/
lru_add_drain();
if (page_count(page) > 1 + PageSwapCache(page))
goto copy;
if (!trylock_page(page))
goto copy;
mm: optimize do_wp_page() for exclusive pages in the swapcache Patch series "mm: COW fixes part 1: fix the COW security issue for THP and swap", v3. This series attempts to optimize and streamline the COW logic for ordinary anon pages and THP anon pages, fixing two remaining instances of CVE-2020-29374 in do_swap_page() and do_huge_pmd_wp_page(): information can leak from a parent process to a child process via anonymous pages shared during fork(). This issue, including other related COW issues, has been summarized in [2]: "1. Observing Memory Modifications of Private Pages From A Child Process Long story short: process-private memory might not be as private as you think once you fork(): successive modifications of private memory regions in the parent process can still be observed by the child process, for example, by smart use of vmsplice()+munmap(). The core problem is that pinning pages readable in a child process, such as done via the vmsplice system call, can result in a child process observing memory modifications done in the parent process the child is not supposed to observe. [1] contains an excellent summary and [2] contains further details. This issue was assigned CVE-2020-29374 [9]. For this to trigger, it's required to use a fork() without subsequent exec(), for example, as used under Android zygote. Without further details about an application that forks less-privileged child processes, one cannot really say what's actually affected and what's not -- see the details section the end of this mail for a short sshd/openssh analysis. While commit 17839856fd58 ("gup: document and work around "COW can break either way" issue") fixed this issue and resulted in other problems (e.g., ptrace on pmem), commit 09854ba94c6a ("mm: do_wp_page() simplification") re-introduced part of the problem unfortunately. The original reproducer can be modified quite easily to use THP [3] and make the issue appear again on upstream kernels. I modified it to use hugetlb [4] and it triggers as well. The problem is certainly less severe with hugetlb than with THP; it merely highlights that we still have plenty of open holes we should be closing/fixing. Regarding vmsplice(), the only known workaround is to disallow the vmsplice() system call ... or disable THP and hugetlb. But who knows what else is affected (RDMA? O_DIRECT?) to achieve the same goal -- in the end, it's a more generic issue" This security issue was first reported by Jann Horn on 27 May 2020 and it currently affects anonymous pages during swapin, anonymous THP and hugetlb. This series tackles anonymous pages during swapin and anonymous THP: - do_swap_page() for handling COW on PTEs during swapin directly - do_huge_pmd_wp_page() for handling COW on PMD-mapped THP during write faults With this series, we'll apply the same COW logic we have in do_wp_page() to all swappable anon pages: don't reuse (map writable) the page in case there are additional references (page_count() != 1). All users of reuse_swap_page() are remove, and consequently reuse_swap_page() is removed. In general, we're struggling with the following COW-related issues: (1) "missed COW": we miss to copy on write and reuse the page (map it writable) although we must copy because there are pending references from another process to this page. The result is a security issue. (2) "wrong COW": we copy on write although we wouldn't have to and shouldn't: if there are valid GUP references, they will become out of sync with the pages mapped into the page table. We fail to detect that such a page can be reused safely, especially if never more than a single process mapped the page. The result is an intra process memory corruption. (3) "unnecessary COW": we copy on write although we wouldn't have to: performance degradation and temporary increases swap+memory consumption can be the result. While this series fixes (1) for swappable anon pages, it tries to reduce reported cases of (3) first as good and easy as possible to limit the impact when streamlining. The individual patches try to describe in which cases we will run into (3). This series certainly makes (2) worse for THP, because a THP will now get PTE-mapped on write faults if there are additional references, even if there was only ever a single process involved: once PTE-mapped, we'll copy each and every subpage and won't reuse any subpage as long as the underlying compound page wasn't split. I'm working on an approach to fix (2) and improve (3): PageAnonExclusive to mark anon pages that are exclusive to a single process, allow GUP pins only on such exclusive pages, and allow turning exclusive pages shared (clearing PageAnonExclusive) only if there are no GUP pins. Anon pages with PageAnonExclusive set never have to be copied during write faults, but eventually during fork() if they cannot be turned shared. The improved reuse logic in this series will essentially also be the logic to reset PageAnonExclusive. This work will certainly take a while, but I'm planning on sharing details before having code fully ready. #1-#5 can be applied independently of the rest. #6-#9 are mostly only cleanups related to reuse_swap_page(). Notes: * For now, I'll leave hugetlb code untouched: "unnecessary COW" might easily break existing setups because hugetlb pages are a scarce resource and we could just end up having to crash the application when we run out of hugetlb pages. We have to be very careful and the security aspect with hugetlb is most certainly less relevant than for unprivileged anon pages. * Instead of lru_add_drain() we might actually just drain the lru_add list or even just remove the single page of interest from the lru_add list. This would require a new helper function, and could be added if the conditional lru_add_drain() turn out to be a problem. * I extended the test case already included in [1] to also test for the newly found do_swap_page() case. I'll send that out separately once/if this part was merged. [1] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com [2] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com This patch (of 9): Liang Zhang reported [1] that the current COW logic in do_wp_page() is sub-optimal when it comes to swap+read fault+write fault of anonymous pages that have a single user, visible via a performance degradation in the redis benchmark. Something similar was previously reported [2] by Nadav with a simple reproducer. After we put an anon page into the swapcache and unmapped it from a single process, that process might read that page again and refault it read-only. If that process then writes to that page, the process is actually the exclusive user of the page, however, the COW logic in do_co_page() won't be able to reuse it due to the additional reference from the swapcache. Let's optimize for pages that have been added to the swapcache but only have an exclusive user. Try removing the swapcache reference if there is hope that we're the exclusive user. We will fail removing the swapcache reference in two scenarios: (1) There are additional swap entries referencing the page: copying instead of reusing is the right thing to do. (2) The page is under writeback: theoretically we might be able to reuse in some cases, however, we cannot remove the additional reference and will have to copy. Note that we'll only try removing the page from the swapcache when it's highly likely that we'll be the exclusive owner after removing the page from the swapache. As we're about to map that page writable and redirty it, that should not affect reclaim but is rather the right thing to do. Further, we might have additional references from the LRU pagevecs, which will force us to copy instead of being able to reuse. We'll try handling such references for some scenarios next. Concurrent writeback cannot be handled easily and we'll always have to copy. While at it, remove the superfluous page_mapcount() check: it's implicitly covered by the page_count() for ordinary anon pages. [1] https://lkml.kernel.org/r/20220113140318.11117-1-zhangliang5@huawei.com [2] https://lkml.kernel.org/r/0480D692-D9B2-429A-9A88-9BBA1331AC3A@gmail.com Link: https://lkml.kernel.org/r/20220131162940.210846-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Liang Zhang <zhangliang5@huawei.com> Reported-by: Nadav Amit <nadav.amit@gmail.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jann Horn <jannh@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:30 +03:00
if (PageSwapCache(page))
try_to_free_swap(page);
if (PageKsm(page) || page_count(page) != 1) {
unlock_page(page);
mm: reuse only-pte-mapped KSM page in do_wp_page() Add an optimization for KSM pages almost in the same way that we have for ordinary anonymous pages. If there is a write fault in a page, which is mapped to an only pte, and it is not related to swap cache; the page may be reused without copying its content. [ Note that we do not consider PageSwapCache() pages at least for now, since we don't want to complicate __get_ksm_page(), which has nice optimization based on this (for the migration case). Currenly it is spinning on PageSwapCache() pages, waiting for when they have unfreezed counters (i.e., for the migration finish). But we don't want to make it also spinning on swap cache pages, which we try to reuse, since there is not a very high probability to reuse them. So, for now we do not consider PageSwapCache() pages at all. ] So in reuse_ksm_page() we check for 1) PageSwapCache() and 2) page_stable_node(), to skip a page, which KSM is currently trying to link to stable tree. Then we do page_ref_freeze() to prohibit KSM to merge one more page into the page, we are reusing. After that, nobody can refer to the reusing page: KSM skips !PageSwapCache() pages with zero refcount; and the protection against of all other participants is the same as for reused ordinary anon pages pte lock, page lock and mmap_sem. [akpm@linux-foundation.org: replace BUG_ON()s with WARN_ON()s] Link: http://lkml.kernel.org/r/154471491016.31352.1168978849911555609.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com> Cc: Rik van Riel <riel@surriel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:43:06 +03:00
goto copy;
do_wp_page: remove the 'reuse' flag mlocking a shared, writable vma currently causes the corresponding pages to be marked as dirty and queued for writeback. This seems rather unnecessary given that the pages are not being actually modified during mlock. It is understood that for non-shared mappings (file or anon) we want to use a write fault in order to break COW, but there is just no such need for shared mappings. The first two patches in this series do not introduce any behavior change. The intent there is to make it obvious that dirtying file pages is only done in the (writable, shared) case. I think this clarifies the code, but I wouldn't mind dropping these two patches if there is no consensus about them. The last patch is where we actually avoid dirtying shared mappings during mlock. Note that as a side effect of this, we won't call page_mkwrite() for the mappings that define it, and won't be pre-allocating data blocks at the FS level if the mapped file was sparsely allocated. My understanding is that mlock does not need to provide such guarantee, as evidenced by the fact that it never did for the filesystems that don't define page_mkwrite() - including some common ones like ext3. However, I would like to gather feedback on this from filesystem people as a precaution. If this turns out to be a showstopper, maybe block preallocation can be added back on using a different interface. Large shared mlocks are getting significantly (>2x) faster in my tests, as the disk can be fully used for reading the file instead of having to share between this and writeback. This patch: Reorganize the code to remove the 'reuse' flag. No behavior changes. Signed-off-by: Michel Lespinasse <walken@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Theodore Tso <tytso@google.com> Cc: Michael Rubin <mrubin@google.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:07 +03:00
}
/*
mm: optimize do_wp_page() for exclusive pages in the swapcache Patch series "mm: COW fixes part 1: fix the COW security issue for THP and swap", v3. This series attempts to optimize and streamline the COW logic for ordinary anon pages and THP anon pages, fixing two remaining instances of CVE-2020-29374 in do_swap_page() and do_huge_pmd_wp_page(): information can leak from a parent process to a child process via anonymous pages shared during fork(). This issue, including other related COW issues, has been summarized in [2]: "1. Observing Memory Modifications of Private Pages From A Child Process Long story short: process-private memory might not be as private as you think once you fork(): successive modifications of private memory regions in the parent process can still be observed by the child process, for example, by smart use of vmsplice()+munmap(). The core problem is that pinning pages readable in a child process, such as done via the vmsplice system call, can result in a child process observing memory modifications done in the parent process the child is not supposed to observe. [1] contains an excellent summary and [2] contains further details. This issue was assigned CVE-2020-29374 [9]. For this to trigger, it's required to use a fork() without subsequent exec(), for example, as used under Android zygote. Without further details about an application that forks less-privileged child processes, one cannot really say what's actually affected and what's not -- see the details section the end of this mail for a short sshd/openssh analysis. While commit 17839856fd58 ("gup: document and work around "COW can break either way" issue") fixed this issue and resulted in other problems (e.g., ptrace on pmem), commit 09854ba94c6a ("mm: do_wp_page() simplification") re-introduced part of the problem unfortunately. The original reproducer can be modified quite easily to use THP [3] and make the issue appear again on upstream kernels. I modified it to use hugetlb [4] and it triggers as well. The problem is certainly less severe with hugetlb than with THP; it merely highlights that we still have plenty of open holes we should be closing/fixing. Regarding vmsplice(), the only known workaround is to disallow the vmsplice() system call ... or disable THP and hugetlb. But who knows what else is affected (RDMA? O_DIRECT?) to achieve the same goal -- in the end, it's a more generic issue" This security issue was first reported by Jann Horn on 27 May 2020 and it currently affects anonymous pages during swapin, anonymous THP and hugetlb. This series tackles anonymous pages during swapin and anonymous THP: - do_swap_page() for handling COW on PTEs during swapin directly - do_huge_pmd_wp_page() for handling COW on PMD-mapped THP during write faults With this series, we'll apply the same COW logic we have in do_wp_page() to all swappable anon pages: don't reuse (map writable) the page in case there are additional references (page_count() != 1). All users of reuse_swap_page() are remove, and consequently reuse_swap_page() is removed. In general, we're struggling with the following COW-related issues: (1) "missed COW": we miss to copy on write and reuse the page (map it writable) although we must copy because there are pending references from another process to this page. The result is a security issue. (2) "wrong COW": we copy on write although we wouldn't have to and shouldn't: if there are valid GUP references, they will become out of sync with the pages mapped into the page table. We fail to detect that such a page can be reused safely, especially if never more than a single process mapped the page. The result is an intra process memory corruption. (3) "unnecessary COW": we copy on write although we wouldn't have to: performance degradation and temporary increases swap+memory consumption can be the result. While this series fixes (1) for swappable anon pages, it tries to reduce reported cases of (3) first as good and easy as possible to limit the impact when streamlining. The individual patches try to describe in which cases we will run into (3). This series certainly makes (2) worse for THP, because a THP will now get PTE-mapped on write faults if there are additional references, even if there was only ever a single process involved: once PTE-mapped, we'll copy each and every subpage and won't reuse any subpage as long as the underlying compound page wasn't split. I'm working on an approach to fix (2) and improve (3): PageAnonExclusive to mark anon pages that are exclusive to a single process, allow GUP pins only on such exclusive pages, and allow turning exclusive pages shared (clearing PageAnonExclusive) only if there are no GUP pins. Anon pages with PageAnonExclusive set never have to be copied during write faults, but eventually during fork() if they cannot be turned shared. The improved reuse logic in this series will essentially also be the logic to reset PageAnonExclusive. This work will certainly take a while, but I'm planning on sharing details before having code fully ready. #1-#5 can be applied independently of the rest. #6-#9 are mostly only cleanups related to reuse_swap_page(). Notes: * For now, I'll leave hugetlb code untouched: "unnecessary COW" might easily break existing setups because hugetlb pages are a scarce resource and we could just end up having to crash the application when we run out of hugetlb pages. We have to be very careful and the security aspect with hugetlb is most certainly less relevant than for unprivileged anon pages. * Instead of lru_add_drain() we might actually just drain the lru_add list or even just remove the single page of interest from the lru_add list. This would require a new helper function, and could be added if the conditional lru_add_drain() turn out to be a problem. * I extended the test case already included in [1] to also test for the newly found do_swap_page() case. I'll send that out separately once/if this part was merged. [1] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com [2] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com This patch (of 9): Liang Zhang reported [1] that the current COW logic in do_wp_page() is sub-optimal when it comes to swap+read fault+write fault of anonymous pages that have a single user, visible via a performance degradation in the redis benchmark. Something similar was previously reported [2] by Nadav with a simple reproducer. After we put an anon page into the swapcache and unmapped it from a single process, that process might read that page again and refault it read-only. If that process then writes to that page, the process is actually the exclusive user of the page, however, the COW logic in do_co_page() won't be able to reuse it due to the additional reference from the swapcache. Let's optimize for pages that have been added to the swapcache but only have an exclusive user. Try removing the swapcache reference if there is hope that we're the exclusive user. We will fail removing the swapcache reference in two scenarios: (1) There are additional swap entries referencing the page: copying instead of reusing is the right thing to do. (2) The page is under writeback: theoretically we might be able to reuse in some cases, however, we cannot remove the additional reference and will have to copy. Note that we'll only try removing the page from the swapcache when it's highly likely that we'll be the exclusive owner after removing the page from the swapache. As we're about to map that page writable and redirty it, that should not affect reclaim but is rather the right thing to do. Further, we might have additional references from the LRU pagevecs, which will force us to copy instead of being able to reuse. We'll try handling such references for some scenarios next. Concurrent writeback cannot be handled easily and we'll always have to copy. While at it, remove the superfluous page_mapcount() check: it's implicitly covered by the page_count() for ordinary anon pages. [1] https://lkml.kernel.org/r/20220113140318.11117-1-zhangliang5@huawei.com [2] https://lkml.kernel.org/r/0480D692-D9B2-429A-9A88-9BBA1331AC3A@gmail.com Link: https://lkml.kernel.org/r/20220131162940.210846-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reported-by: Liang Zhang <zhangliang5@huawei.com> Reported-by: Nadav Amit <nadav.amit@gmail.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jann Horn <jannh@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:30 +03:00
* Ok, we've got the only page reference from our mapping
* and the page is locked, it's dark out, and we're wearing
* sunglasses. Hit it.
*/
unlock_page(page);
mm: fix misplaced unlock_page in do_wp_page() Commit 09854ba94c6a ("mm: do_wp_page() simplification") reorganized all the code around the page re-use vs copy, but in the process also moved the final unlock_page() around to after the wp_page_reuse() call. That normally doesn't matter - but it means that the unlock_page() is now done after releasing the page table lock. Again, not a big deal, you'd think. But it turns out that it's very wrong indeed, because once we've released the page table lock, we've basically lost our only reference to the page - the page tables - and it could now be free'd at any time. We do hold the mmap_sem, so no actual unmap() can happen, but madvise can come in and a MADV_DONTNEED will zap the page range - and free the page. So now the page may be free'd just as we're unlocking it, which in turn will usually trigger a "Bad page state" error in the freeing path. To make matters more confusing, by the time the debug code prints out the page state, the unlock has typically completed and everything looks fine again. This all doesn't happen in any normal situations, but it does trigger with the dirtyc0w_child LTP test. And it seems to trigger much more easily (but not expclusively) on s390 than elsewhere, probably because s390 doesn't do the "batch pages up for freeing after the TLB flush" that gives the unlock_page() more time to complete and makes the race harder to hit. Fixes: 09854ba94c6a ("mm: do_wp_page() simplification") Link: https://lore.kernel.org/lkml/a46e9bbef2ed4e17778f5615e818526ef848d791.camel@redhat.com/ Link: https://lore.kernel.org/linux-mm/c41149a8-211e-390b-af1d-d5eee690fecb@linux.alibaba.com/ Reported-by: Qian Cai <cai@redhat.com> Reported-by: Alex Shi <alex.shi@linux.alibaba.com> Bisected-and-analyzed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Tested-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-09-24 18:41:32 +03:00
wp_page_reuse(vmf);
return VM_FAULT_WRITE;
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 10:30:57 +04:00
(VM_WRITE|VM_SHARED))) {
return wp_page_shared(vmf);
}
mm: reuse only-pte-mapped KSM page in do_wp_page() Add an optimization for KSM pages almost in the same way that we have for ordinary anonymous pages. If there is a write fault in a page, which is mapped to an only pte, and it is not related to swap cache; the page may be reused without copying its content. [ Note that we do not consider PageSwapCache() pages at least for now, since we don't want to complicate __get_ksm_page(), which has nice optimization based on this (for the migration case). Currenly it is spinning on PageSwapCache() pages, waiting for when they have unfreezed counters (i.e., for the migration finish). But we don't want to make it also spinning on swap cache pages, which we try to reuse, since there is not a very high probability to reuse them. So, for now we do not consider PageSwapCache() pages at all. ] So in reuse_ksm_page() we check for 1) PageSwapCache() and 2) page_stable_node(), to skip a page, which KSM is currently trying to link to stable tree. Then we do page_ref_freeze() to prohibit KSM to merge one more page into the page, we are reusing. After that, nobody can refer to the reusing page: KSM skips !PageSwapCache() pages with zero refcount; and the protection against of all other participants is the same as for reused ordinary anon pages pte lock, page lock and mmap_sem. [akpm@linux-foundation.org: replace BUG_ON()s with WARN_ON()s] Link: http://lkml.kernel.org/r/154471491016.31352.1168978849911555609.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com> Cc: Rik van Riel <riel@surriel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:43:06 +03:00
copy:
/*
* Ok, we need to copy. Oh, well..
*/
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return wp_page_copy(vmf);
}
static void unmap_mapping_range_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr,
struct zap_details *details)
{
zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}
static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
pgoff_t first_index,
pgoff_t last_index,
struct zap_details *details)
{
struct vm_area_struct *vma;
pgoff_t vba, vea, zba, zea;
vma_interval_tree_foreach(vma, root, first_index, last_index) {
vba = vma->vm_pgoff;
vea = vba + vma_pages(vma) - 1;
zba = max(first_index, vba);
zea = min(last_index, vea);
unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
details);
}
}
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
/**
* unmap_mapping_folio() - Unmap single folio from processes.
* @folio: The locked folio to be unmapped.
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
*
* Unmap this folio from any userspace process which still has it mmaped.
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
* Typically, for efficiency, the range of nearby pages has already been
* unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
* truncation or invalidation holds the lock on a folio, it may find that
* the page has been remapped again: and then uses unmap_mapping_folio()
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
* to unmap it finally.
*/
void unmap_mapping_folio(struct folio *folio)
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
{
struct address_space *mapping = folio->mapping;
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
struct zap_details details = { };
pgoff_t first_index;
pgoff_t last_index;
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
VM_BUG_ON(!folio_test_locked(folio));
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
first_index = folio->index;
last_index = folio->index + folio_nr_pages(folio) - 1;
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
details.even_cows = false;
details.single_folio = folio;
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
unmap_mapping_range_tree(&mapping->i_mmap, first_index,
last_index, &details);
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped. The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page. However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside. The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside. Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly. This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe. Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped. Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Jan Kara <jack@suse.cz> Cc: Jue Wang <juew@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Wang Yugui <wangyugui@e16-tech.com> Cc: Zi Yan <ziy@nvidia.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-16 04:24:03 +03:00
i_mmap_unlock_write(mapping);
}
/**
* unmap_mapping_pages() - Unmap pages from processes.
* @mapping: The address space containing pages to be unmapped.
* @start: Index of first page to be unmapped.
* @nr: Number of pages to be unmapped. 0 to unmap to end of file.
* @even_cows: Whether to unmap even private COWed pages.
*
* Unmap the pages in this address space from any userspace process which
* has them mmaped. Generally, you want to remove COWed pages as well when
* a file is being truncated, but not when invalidating pages from the page
* cache.
*/
void unmap_mapping_pages(struct address_space *mapping, pgoff_t start,
pgoff_t nr, bool even_cows)
{
struct zap_details details = { };
pgoff_t first_index = start;
pgoff_t last_index = start + nr - 1;
mm: change zap_details.zap_mapping into even_cows Currently we have a zap_mapping pointer maintained in zap_details, when it is specified we only want to zap the pages that has the same mapping with what the caller has specified. But what we want to do is actually simpler: we want to skip zapping private (COW-ed) pages in some cases. We can refer to unmap_mapping_pages() callers where we could have passed in different even_cows values. The other user is unmap_mapping_folio() where we always want to skip private pages. According to Hugh, we used a mapping pointer for historical reason, as explained here: https://lore.kernel.org/lkml/391aa58d-ce84-9d4-d68d-d98a9c533255@google.com/ Quoting partly from Hugh: Which raises the question again of why I did not just use a boolean flag there originally: aah, I think I've found why. In those days there was a horrible "optimization", for better performance on some benchmark I guess, which when you read from /dev/zero into a private mapping, would map the zero page there (look up read_zero_pagealigned() and zeromap_page_range() if you dare). So there was another category of page to be skipped along with the anon COWs, and I didn't want multiple tests in the zap loop, so checking check_mapping against page->mapping did both. I think nowadays you could do it by checking for PageAnon page (or genuine swap entry) instead. This patch replaces the zap_details.zap_mapping pointer into the even_cows boolean, then we check it against PageAnon. Link: https://lkml.kernel.org/r/20220216094810.60572-4-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Suggested-by: Hugh Dickins <hughd@google.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:42:21 +03:00
details.even_cows = even_cows;
if (last_index < first_index)
last_index = ULONG_MAX;
i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
unmap_mapping_range_tree(&mapping->i_mmap, first_index,
last_index, &details);
i_mmap_unlock_write(mapping);
}
afs: Fix mmap coherency vs 3rd-party changes Fix the coherency management of mmap'd data such that 3rd-party changes become visible as soon as possible after the callback notification is delivered by the fileserver. This is done by the following means: (1) When we break a callback on a vnode specified by the CB.CallBack call from the server, we queue a work item (vnode->cb_work) to go and clobber all the PTEs mapping to that inode. This causes the CPU to trip through the ->map_pages() and ->page_mkwrite() handlers if userspace attempts to access the page(s) again. (Ideally, this would be done in the service handler for CB.CallBack, but the server is waiting for our reply before considering, and we have a list of vnodes, all of which need breaking - and the process of getting the mmap_lock and stripping the PTEs on all CPUs could be quite slow.) (2) Call afs_validate() from the ->map_pages() handler to check to see if the file has changed and to get a new callback promise from the server. Also handle the fileserver telling us that it's dropping all callbacks, possibly after it's been restarted by sending us a CB.InitCallBackState* call by the following means: (3) Maintain a per-cell list of afs files that are currently mmap'd (cell->fs_open_mmaps). (4) Add a work item to each server that is invoked if there are any open mmaps when CB.InitCallBackState happens. This work item goes through the aforementioned list and invokes the vnode->cb_work work item for each one that is currently using this server. This causes the PTEs to be cleared, causing ->map_pages() or ->page_mkwrite() to be called again, thereby calling afs_validate() again. I've chosen to simply strip the PTEs at the point of notification reception rather than invalidate all the pages as well because (a) it's faster, (b) we may get a notification for other reasons than the data being altered (in which case we don't want to clobber the pagecache) and (c) we need to ask the server to find out - and I don't want to wait for the reply before holding up userspace. This was tested using the attached test program: #include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> #include <sys/mman.h> int main(int argc, char *argv[]) { size_t size = getpagesize(); unsigned char *p; bool mod = (argc == 3); int fd; if (argc != 2 && argc != 3) { fprintf(stderr, "Format: %s <file> [mod]\n", argv[0]); exit(2); } fd = open(argv[1], mod ? O_RDWR : O_RDONLY); if (fd < 0) { perror(argv[1]); exit(1); } p = mmap(NULL, size, mod ? PROT_READ|PROT_WRITE : PROT_READ, MAP_SHARED, fd, 0); if (p == MAP_FAILED) { perror("mmap"); exit(1); } for (;;) { if (mod) { p[0]++; msync(p, size, MS_ASYNC); fsync(fd); } printf("%02x", p[0]); fflush(stdout); sleep(1); } } It runs in two modes: in one mode, it mmaps a file, then sits in a loop reading the first byte, printing it and sleeping for a second; in the second mode it mmaps a file, then sits in a loop incrementing the first byte and flushing, then printing and sleeping. Two instances of this program can be run on different machines, one doing the reading and one doing the writing. The reader should see the changes made by the writer, but without this patch, they aren't because validity checking is being done lazily - only on entry to the filesystem. Testing the InitCallBackState change is more complicated. The server has to be taken offline, the saved callback state file removed and then the server restarted whilst the reading-mode program continues to run. The client machine then has to poke the server to trigger the InitCallBackState call. Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Markus Suvanto <markus.suvanto@gmail.com> cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111668833.283156.382633263709075739.stgit@warthog.procyon.org.uk/
2021-09-02 18:43:10 +03:00
EXPORT_SYMBOL_GPL(unmap_mapping_pages);
/**
* unmap_mapping_range - unmap the portion of all mmaps in the specified
* address_space corresponding to the specified byte range in the underlying
* file.
*
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
* boundary. Note that this is different from truncate_pagecache(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
* up to a PAGE_SIZE boundary. A holelen of zero truncates to the
* end of the file.
* @even_cows: 1 when truncating a file, unmap even private COWed pages;
* but 0 when invalidating pagecache, don't throw away private data.
*/
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
pgoff_t hba = holebegin >> PAGE_SHIFT;
pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
long long holeend =
(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (holeend & ~(long long)ULONG_MAX)
hlen = ULONG_MAX - hba + 1;
}
unmap_mapping_pages(mapping, hba, hlen, even_cows);
}
EXPORT_SYMBOL(unmap_mapping_range);
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
/*
* Restore a potential device exclusive pte to a working pte entry
*/
static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct vm_area_struct *vma = vmf->vma;
struct mmu_notifier_range range;
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags))
return VM_FAULT_RETRY;
mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
vma->vm_mm, vmf->address & PAGE_MASK,
(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
mmu_notifier_invalidate_range_start(&range);
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
restore_exclusive_pte(vma, page, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
unlock_page(page);
mmu_notifier_invalidate_range_end(&range);
return 0;
}
mm: streamline COW logic in do_swap_page() Currently we have a different COW logic when: * triggering a read-fault to swapin first and then trigger a write-fault -> do_swap_page() + do_wp_page() * triggering a write-fault to swapin -> do_swap_page() + do_wp_page() only if we fail reuse in do_swap_page() The COW logic in do_swap_page() is different than our reuse logic in do_wp_page(). The COW logic in do_wp_page() -- page_count() == 1 -- makes currently sure that we certainly don't have a remaining reference, e.g., via GUP, on the target page we want to reuse: if there is any unexpected reference, we have to copy to avoid information leaks. As do_swap_page() behaves differently, in environments with swap enabled we can currently have an unintended information leak from the parent to the child, similar as known from CVE-2020-29374: 1. Parent writes to anonymous page -> Page is mapped writable and modified 2. Page is swapped out -> Page is unmapped and replaced by swap entry 3. fork() -> Swap entries are copied to child 4. Child pins page R/O -> Page is mapped R/O into child 5. Child unmaps page -> Child still holds GUP reference 6. Parent writes to page -> Page is reused in do_swap_page() -> Child can observe changes Exchanging 2. and 3. should have the same effect. Let's apply the same COW logic as in do_wp_page(), conditionally trying to remove the page from the swapcache after freeing the swap entry, however, before actually mapping our page. We can change the order now that we use try_to_free_swap(), which doesn't care about the mapcount, instead of reuse_swap_page(). To handle references from the LRU pagevecs, conditionally drain the local LRU pagevecs when required, however, don't consider the page_count() when deciding whether to drain to keep it simple for now. Link: https://lkml.kernel.org/r/20220131162940.210846-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:40 +03:00
static inline bool should_try_to_free_swap(struct page *page,
struct vm_area_struct *vma,
unsigned int fault_flags)
{
if (!PageSwapCache(page))
return false;
if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) ||
PageMlocked(page))
return true;
/*
* If we want to map a page that's in the swapcache writable, we
* have to detect via the refcount if we're really the exclusive
* user. Try freeing the swapcache to get rid of the swapcache
* reference only in case it's likely that we'll be the exlusive user.
*/
return (fault_flags & FAULT_FLAG_WRITE) && !PageKsm(page) &&
page_count(page) == 2;
}
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with pte unmapped and unlocked.
*
* We return with the mmap_lock locked or unlocked in the same cases
* as does filemap_fault().
*/
vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL, *swapcache;
swap: fix do_swap_page() race with swapoff When I was investigating the swap code, I found the below possible race window: CPU 1 CPU 2 ----- ----- do_swap_page if (data_race(si->flags & SWP_SYNCHRONOUS_IO) swap_readpage if (data_race(sis->flags & SWP_FS_OPS)) { swapoff .. p->swap_file = NULL; .. struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping;[oops!] Note that for the pages that are swapped in through swap cache, this isn't an issue. Because the page is locked, and the swap entry will be marked with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been unlocked. Fix this race by using get/put_swap_device() to guard against concurrent swapoff. Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device") Signed-off-by: Miaohe Lin <linmiaohe@huawei.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Alex Shi <alexs@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-29 05:36:50 +03:00
struct swap_info_struct *si = NULL;
swp_entry_t entry;
pte_t pte;
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 01:21:57 +04:00
int locked;
int exclusive = 0;
vm_fault_t ret = 0;
void *shadow = NULL;
if (!pte_unmap_same(vmf))
goto out;
entry = pte_to_swp_entry(vmf->orig_pte);
if (unlikely(non_swap_entry(entry))) {
if (is_migration_entry(entry)) {
migration_entry_wait(vma->vm_mm, vmf->pmd,
vmf->address);
mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:25 +03:00
} else if (is_device_exclusive_entry(entry)) {
vmf->page = pfn_swap_entry_to_page(entry);
ret = remove_device_exclusive_entry(vmf);
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:43 +03:00
} else if (is_device_private_entry(entry)) {
mm: remove special swap entry functions Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:54:06 +03:00
vmf->page = pfn_swap_entry_to_page(entry);
ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
} else {
print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
ret = VM_FAULT_SIGBUS;
}
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:35 +04:00
goto out;
}
swap: fix do_swap_page() race with swapoff When I was investigating the swap code, I found the below possible race window: CPU 1 CPU 2 ----- ----- do_swap_page if (data_race(si->flags & SWP_SYNCHRONOUS_IO) swap_readpage if (data_race(sis->flags & SWP_FS_OPS)) { swapoff .. p->swap_file = NULL; .. struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping;[oops!] Note that for the pages that are swapped in through swap cache, this isn't an issue. Because the page is locked, and the swap entry will be marked with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been unlocked. Fix this race by using get/put_swap_device() to guard against concurrent swapoff. Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device") Signed-off-by: Miaohe Lin <linmiaohe@huawei.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Alex Shi <alexs@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-29 05:36:50 +03:00
/* Prevent swapoff from happening to us. */
si = get_swap_device(entry);
if (unlikely(!si))
goto out;
page = lookup_swap_cache(entry, vma, vmf->address);
swapcache = page;
if (!page) {
mm/swapfile: fix and annotate various data races swap_info_struct si.highest_bit, si.swap_map[offset] and si.flags could be accessed concurrently separately as noticed by KCSAN, === si.highest_bit === write to 0xffff8d5abccdc4d4 of 4 bytes by task 5353 on cpu 24: swap_range_alloc+0x81/0x130 swap_range_alloc at mm/swapfile.c:681 scan_swap_map_slots+0x371/0xb90 get_swap_pages+0x39d/0x5c0 get_swap_page+0xf2/0x524 add_to_swap+0xe4/0x1c0 shrink_page_list+0x1795/0x2870 shrink_inactive_list+0x316/0x880 shrink_lruvec+0x8dc/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 read to 0xffff8d5abccdc4d4 of 4 bytes by task 6672 on cpu 70: scan_swap_map_slots+0x4a6/0xb90 scan_swap_map_slots at mm/swapfile.c:892 get_swap_pages+0x39d/0x5c0 get_swap_page+0xf2/0x524 add_to_swap+0xe4/0x1c0 shrink_page_list+0x1795/0x2870 shrink_inactive_list+0x316/0x880 shrink_lruvec+0x8dc/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 Reported by Kernel Concurrency Sanitizer on: CPU: 70 PID: 6672 Comm: oom01 Tainted: G W L 5.5.0-next-20200205+ #3 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 === si.swap_map[offset] === write to 0xffffbc370c29a64c of 1 bytes by task 6856 on cpu 86: __swap_entry_free_locked+0x8c/0x100 __swap_entry_free_locked at mm/swapfile.c:1209 (discriminator 4) __swap_entry_free.constprop.20+0x69/0xb0 free_swap_and_cache+0x53/0xa0 unmap_page_range+0x7f8/0x1d70 unmap_single_vma+0xcd/0x170 unmap_vmas+0x18b/0x220 exit_mmap+0xee/0x220 mmput+0x10e/0x270 do_exit+0x59b/0xf40 do_group_exit+0x8b/0x180 read to 0xffffbc370c29a64c of 1 bytes by task 6855 on cpu 20: _swap_info_get+0x81/0xa0 _swap_info_get at mm/swapfile.c:1140 free_swap_and_cache+0x40/0xa0 unmap_page_range+0x7f8/0x1d70 unmap_single_vma+0xcd/0x170 unmap_vmas+0x18b/0x220 exit_mmap+0xee/0x220 mmput+0x10e/0x270 do_exit+0x59b/0xf40 do_group_exit+0x8b/0x180 === si.flags === write to 0xffff956c8fc6c400 of 8 bytes by task 6087 on cpu 23: scan_swap_map_slots+0x6fe/0xb50 scan_swap_map_slots at mm/swapfile.c:887 get_swap_pages+0x39d/0x5c0 get_swap_page+0x377/0x524 add_to_swap+0xe4/0x1c0 shrink_page_list+0x1795/0x2870 shrink_inactive_list+0x316/0x880 shrink_lruvec+0x8dc/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 read to 0xffff956c8fc6c400 of 8 bytes by task 6207 on cpu 63: _swap_info_get+0x41/0xa0 __swap_info_get at mm/swapfile.c:1114 put_swap_page+0x84/0x490 __remove_mapping+0x384/0x5f0 shrink_page_list+0xff1/0x2870 shrink_inactive_list+0x316/0x880 shrink_lruvec+0x8dc/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 The writes are under si->lock but the reads are not. For si.highest_bit and si.swap_map[offset], data race could trigger logic bugs, so fix them by having WRITE_ONCE() for the writes and READ_ONCE() for the reads except those isolated reads where they compare against zero which a data race would cause no harm. Thus, annotate them as intentional data races using the data_race() macro. For si.flags, the readers are only interested in a single bit where a data race there would cause no issue there. [cai@lca.pw: add a missing annotation for si->flags in memory.c] Link: http://lkml.kernel.org/r/1581612647-5958-1-git-send-email-cai@lca.pw Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Marco Elver <elver@google.com> Cc: Hugh Dickins <hughd@google.com> Link: http://lkml.kernel.org/r/1581095163-12198-1-git-send-email-cai@lca.pw Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-15 03:31:31 +03:00
if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
__swap_count(entry) == 1) {
/* skip swapcache */
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
vmf->address);
if (page) {
__SetPageLocked(page);
__SetPageSwapBacked(page);
mm: memcontrol: charge swapin pages on instantiation Right now, users that are otherwise memory controlled can easily escape their containment and allocate significant amounts of memory that they're not being charged for. That's because swap readahead pages are not being charged until somebody actually faults them into their page table. This can be exploited with MADV_WILLNEED, which triggers arbitrary readahead allocations without charging the pages. There are additional problems with the delayed charging of swap pages: 1. To implement refault/workingset detection for anonymous pages, we need to have a target LRU available at swapin time, but the LRU is not determinable until the page has been charged. 2. To implement per-cgroup LRU locking, we need page->mem_cgroup to be stable when the page is isolated from the LRU; otherwise, the locks change under us. But swapcache gets charged after it's already on the LRU, and even if we cannot isolate it ourselves (since charging is not exactly optional). The previous patch ensured we always maintain cgroup ownership records for swap pages. This patch moves the swapcache charging point from the fault handler to swapin time to fix all of the above problems. v2: simplify swapin error checking (Joonsoo) [hughd@google.com: fix livelock in __read_swap_cache_async()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2005212246080.8458@eggly.anvils Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Link: http://lkml.kernel.org/r/20200508183105.225460-17-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 02:02:17 +03:00
memcg: charge before adding to swapcache on swapin Currently the kernel adds the page, allocated for swapin, to the swapcache before charging the page. This is fine but now we want a per-memcg swapcache stat which is essential for folks who wants to transparently migrate from cgroup v1's memsw to cgroup v2's memory and swap counters. In addition charging a page before exposing it to other parts of the kernel is a step in the right direction. To correctly maintain the per-memcg swapcache stat, this patch has adopted to charge the page before adding it to swapcache. One challenge in this option is the failure case of add_to_swap_cache() on which we need to undo the mem_cgroup_charge(). Specifically undoing mem_cgroup_uncharge_swap() is not simple. To resolve the issue, this patch decouples the charging for swapin pages from mem_cgroup_charge(). Two new functions are introduced, mem_cgroup_swapin_charge_page() for just charging the swapin page and mem_cgroup_swapin_uncharge_swap() for uncharging the swap slot once the page has been successfully added to the swapcache. [shakeelb@google.com: set page->private before calling swap_readpage] Link: https://lkml.kernel.org/r/20210318015959.2986837-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20210305212639.775498-1-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Acked-by: Roman Gushchin <guro@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Hugh Dickins <hughd@google.com> Tested-by: Heiko Carstens <hca@linux.ibm.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:56:36 +03:00
if (mem_cgroup_swapin_charge_page(page,
vma->vm_mm, GFP_KERNEL, entry)) {
ret = VM_FAULT_OOM;
mm: memcontrol: charge swapin pages on instantiation Right now, users that are otherwise memory controlled can easily escape their containment and allocate significant amounts of memory that they're not being charged for. That's because swap readahead pages are not being charged until somebody actually faults them into their page table. This can be exploited with MADV_WILLNEED, which triggers arbitrary readahead allocations without charging the pages. There are additional problems with the delayed charging of swap pages: 1. To implement refault/workingset detection for anonymous pages, we need to have a target LRU available at swapin time, but the LRU is not determinable until the page has been charged. 2. To implement per-cgroup LRU locking, we need page->mem_cgroup to be stable when the page is isolated from the LRU; otherwise, the locks change under us. But swapcache gets charged after it's already on the LRU, and even if we cannot isolate it ourselves (since charging is not exactly optional). The previous patch ensured we always maintain cgroup ownership records for swap pages. This patch moves the swapcache charging point from the fault handler to swapin time to fix all of the above problems. v2: simplify swapin error checking (Joonsoo) [hughd@google.com: fix livelock in __read_swap_cache_async()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2005212246080.8458@eggly.anvils Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Link: http://lkml.kernel.org/r/20200508183105.225460-17-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 02:02:17 +03:00
goto out_page;
}
memcg: charge before adding to swapcache on swapin Currently the kernel adds the page, allocated for swapin, to the swapcache before charging the page. This is fine but now we want a per-memcg swapcache stat which is essential for folks who wants to transparently migrate from cgroup v1's memsw to cgroup v2's memory and swap counters. In addition charging a page before exposing it to other parts of the kernel is a step in the right direction. To correctly maintain the per-memcg swapcache stat, this patch has adopted to charge the page before adding it to swapcache. One challenge in this option is the failure case of add_to_swap_cache() on which we need to undo the mem_cgroup_charge(). Specifically undoing mem_cgroup_uncharge_swap() is not simple. To resolve the issue, this patch decouples the charging for swapin pages from mem_cgroup_charge(). Two new functions are introduced, mem_cgroup_swapin_charge_page() for just charging the swapin page and mem_cgroup_swapin_uncharge_swap() for uncharging the swap slot once the page has been successfully added to the swapcache. [shakeelb@google.com: set page->private before calling swap_readpage] Link: https://lkml.kernel.org/r/20210318015959.2986837-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20210305212639.775498-1-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Acked-by: Roman Gushchin <guro@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Hugh Dickins <hughd@google.com> Tested-by: Heiko Carstens <hca@linux.ibm.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:56:36 +03:00
mem_cgroup_swapin_uncharge_swap(entry);
mm: memcontrol: charge swapin pages on instantiation Right now, users that are otherwise memory controlled can easily escape their containment and allocate significant amounts of memory that they're not being charged for. That's because swap readahead pages are not being charged until somebody actually faults them into their page table. This can be exploited with MADV_WILLNEED, which triggers arbitrary readahead allocations without charging the pages. There are additional problems with the delayed charging of swap pages: 1. To implement refault/workingset detection for anonymous pages, we need to have a target LRU available at swapin time, but the LRU is not determinable until the page has been charged. 2. To implement per-cgroup LRU locking, we need page->mem_cgroup to be stable when the page is isolated from the LRU; otherwise, the locks change under us. But swapcache gets charged after it's already on the LRU, and even if we cannot isolate it ourselves (since charging is not exactly optional). The previous patch ensured we always maintain cgroup ownership records for swap pages. This patch moves the swapcache charging point from the fault handler to swapin time to fix all of the above problems. v2: simplify swapin error checking (Joonsoo) [hughd@google.com: fix livelock in __read_swap_cache_async()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2005212246080.8458@eggly.anvils Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Link: http://lkml.kernel.org/r/20200508183105.225460-17-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 02:02:17 +03:00
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
workingset_refault(page_folio(page),
shadow);
lru_cache_add(page);
memcg: charge before adding to swapcache on swapin Currently the kernel adds the page, allocated for swapin, to the swapcache before charging the page. This is fine but now we want a per-memcg swapcache stat which is essential for folks who wants to transparently migrate from cgroup v1's memsw to cgroup v2's memory and swap counters. In addition charging a page before exposing it to other parts of the kernel is a step in the right direction. To correctly maintain the per-memcg swapcache stat, this patch has adopted to charge the page before adding it to swapcache. One challenge in this option is the failure case of add_to_swap_cache() on which we need to undo the mem_cgroup_charge(). Specifically undoing mem_cgroup_uncharge_swap() is not simple. To resolve the issue, this patch decouples the charging for swapin pages from mem_cgroup_charge(). Two new functions are introduced, mem_cgroup_swapin_charge_page() for just charging the swapin page and mem_cgroup_swapin_uncharge_swap() for uncharging the swap slot once the page has been successfully added to the swapcache. [shakeelb@google.com: set page->private before calling swap_readpage] Link: https://lkml.kernel.org/r/20210318015959.2986837-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20210305212639.775498-1-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Acked-by: Roman Gushchin <guro@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Hugh Dickins <hughd@google.com> Tested-by: Heiko Carstens <hca@linux.ibm.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:56:36 +03:00
/* To provide entry to swap_readpage() */
set_page_private(page, entry.val);
swap_readpage(page, true);
memcg: charge before adding to swapcache on swapin Currently the kernel adds the page, allocated for swapin, to the swapcache before charging the page. This is fine but now we want a per-memcg swapcache stat which is essential for folks who wants to transparently migrate from cgroup v1's memsw to cgroup v2's memory and swap counters. In addition charging a page before exposing it to other parts of the kernel is a step in the right direction. To correctly maintain the per-memcg swapcache stat, this patch has adopted to charge the page before adding it to swapcache. One challenge in this option is the failure case of add_to_swap_cache() on which we need to undo the mem_cgroup_charge(). Specifically undoing mem_cgroup_uncharge_swap() is not simple. To resolve the issue, this patch decouples the charging for swapin pages from mem_cgroup_charge(). Two new functions are introduced, mem_cgroup_swapin_charge_page() for just charging the swapin page and mem_cgroup_swapin_uncharge_swap() for uncharging the swap slot once the page has been successfully added to the swapcache. [shakeelb@google.com: set page->private before calling swap_readpage] Link: https://lkml.kernel.org/r/20210318015959.2986837-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20210305212639.775498-1-shakeelb@google.com Signed-off-by: Shakeel Butt <shakeelb@google.com> Acked-by: Roman Gushchin <guro@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Hugh Dickins <hughd@google.com> Tested-by: Heiko Carstens <hca@linux.ibm.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:56:36 +03:00
set_page_private(page, 0);
}
} else {
page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
vmf);
swapcache = page;
}
if (!page) {
/*
* Back out if somebody else faulted in this pte
* while we released the pte lock.
*/
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
goto unlock;
}
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 12:55:45 +04:00
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
} else if (PageHWPoison(page)) {
/*
* hwpoisoned dirty swapcache pages are kept for killing
* owner processes (which may be unknown at hwpoison time)
*/
ret = VM_FAULT_HWPOISON;
goto out_release;
}
locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags);
mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 01:21:57 +04:00
if (!locked) {
ret |= VM_FAULT_RETRY;
goto out_release;
}
mm: slightly clarify KSM logic in do_swap_page() Let's make it clearer that KSM might only have to copy a page in case we have a page in the swapcache, not if we allocated a fresh page and bypassed the swapcache. While at it, add a comment why this is usually necessary and merge the two swapcache conditions. [akpm@linux-foundation.org: fix comment, per David] Link: https://lkml.kernel.org/r/20220131162940.210846-4-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:37 +03:00
if (swapcache) {
/*
* Make sure try_to_free_swap or swapoff did not release the
* swapcache from under us. The page pin, and pte_same test
* below, are not enough to exclude that. Even if it is still
* swapcache, we need to check that the page's swap has not
* changed.
*/
if (unlikely(!PageSwapCache(page) ||
page_private(page) != entry.val))
goto out_page;
/*
* KSM sometimes has to copy on read faults, for example, if
* page->index of !PageKSM() pages would be nonlinear inside the
* anon VMA -- PageKSM() is lost on actual swapout.
*/
page = ksm_might_need_to_copy(page, vma, vmf->address);
if (unlikely(!page)) {
ret = VM_FAULT_OOM;
page = swapcache;
goto out_page;
}
mm: streamline COW logic in do_swap_page() Currently we have a different COW logic when: * triggering a read-fault to swapin first and then trigger a write-fault -> do_swap_page() + do_wp_page() * triggering a write-fault to swapin -> do_swap_page() + do_wp_page() only if we fail reuse in do_swap_page() The COW logic in do_swap_page() is different than our reuse logic in do_wp_page(). The COW logic in do_wp_page() -- page_count() == 1 -- makes currently sure that we certainly don't have a remaining reference, e.g., via GUP, on the target page we want to reuse: if there is any unexpected reference, we have to copy to avoid information leaks. As do_swap_page() behaves differently, in environments with swap enabled we can currently have an unintended information leak from the parent to the child, similar as known from CVE-2020-29374: 1. Parent writes to anonymous page -> Page is mapped writable and modified 2. Page is swapped out -> Page is unmapped and replaced by swap entry 3. fork() -> Swap entries are copied to child 4. Child pins page R/O -> Page is mapped R/O into child 5. Child unmaps page -> Child still holds GUP reference 6. Parent writes to page -> Page is reused in do_swap_page() -> Child can observe changes Exchanging 2. and 3. should have the same effect. Let's apply the same COW logic as in do_wp_page(), conditionally trying to remove the page from the swapcache after freeing the swap entry, however, before actually mapping our page. We can change the order now that we use try_to_free_swap(), which doesn't care about the mapcount, instead of reuse_swap_page(). To handle references from the LRU pagevecs, conditionally drain the local LRU pagevecs when required, however, don't consider the page_count() when deciding whether to drain to keep it simple for now. Link: https://lkml.kernel.org/r/20220131162940.210846-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:40 +03:00
/*
* If we want to map a page that's in the swapcache writable, we
* have to detect via the refcount if we're really the exclusive
* owner. Try removing the extra reference from the local LRU
* pagevecs if required.
*/
if ((vmf->flags & FAULT_FLAG_WRITE) && page == swapcache &&
!PageKsm(page) && !PageLRU(page))
lru_add_drain();
ksm: let shared pages be swappable Initial implementation for swapping out KSM's shared pages: add page_referenced_ksm() and try_to_unmap_ksm(), which rmap.c calls when faced with a PageKsm page. Most of what's needed can be got from the rmap_items listed from the stable_node of the ksm page, without discovering the actual vma: so in this patch just fake up a struct vma for page_referenced_one() or try_to_unmap_one(), then refine that in the next patch. Add VM_NONLINEAR to ksm_madvise()'s list of exclusions: it has always been implicit there (being only set with VM_SHARED, already excluded), but let's make it explicit, to help justify the lack of nonlinear unmap. Rely on the page lock to protect against concurrent modifications to that page's node of the stable tree. The awkward part is not swapout but swapin: do_swap_page() and page_add_anon_rmap() now have to allow for new possibilities - perhaps a ksm page still in swapcache, perhaps a swapcache page associated with one location in one anon_vma now needed for another location or anon_vma. (And the vma might even be no longer VM_MERGEABLE when that happens.) ksm_might_need_to_copy() checks for that case, and supplies a duplicate page when necessary, simply leaving it to a subsequent pass of ksmd to rediscover the identity and merge them back into one ksm page. Disappointingly primitive: but the alternative would have to accumulate unswappable info about the swapped out ksm pages, limiting swappability. Remove page_add_ksm_rmap(): page_add_anon_rmap() now has to allow for the particular case it was handling, so just use it instead. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Izik Eidus <ieidus@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Chris Wright <chrisw@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:59:24 +03:00
}
cgroup_throttle_swaprate(page, GFP_KERNEL);
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 11:13:53 +03:00
/*
* Back out if somebody else already faulted in this pte.
*/
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
goto out_nomap;
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
goto out_nomap;
}
memcg: mem+swap controller core This patch implements per cgroup limit for usage of memory+swap. However there are SwapCache, double counting of swap-cache and swap-entry is avoided. Mem+Swap controller works as following. - memory usage is limited by memory.limit_in_bytes. - memory + swap usage is limited by memory.memsw_limit_in_bytes. This has following benefits. - A user can limit total resource usage of mem+swap. Without this, because memory resource controller doesn't take care of usage of swap, a process can exhaust all the swap (by memory leak.) We can avoid this case. And Swap is shared resource but it cannot be reclaimed (goes back to memory) until it's used. This characteristic can be trouble when the memory is divided into some parts by cpuset or memcg. Assume group A and group B. After some application executes, the system can be.. Group A -- very large free memory space but occupy 99% of swap. Group B -- under memory shortage but cannot use swap...it's nearly full. Ability to set appropriate swap limit for each group is required. Maybe someone wonder "why not swap but mem+swap ?" - The global LRU(kswapd) can swap out arbitrary pages. Swap-out means to move account from memory to swap...there is no change in usage of mem+swap. In other words, when we want to limit the usage of swap without affecting global LRU, mem+swap limit is better than just limiting swap. Accounting target information is stored in swap_cgroup which is per swap entry record. Charge is done as following. map - charge page and memsw. unmap - uncharge page/memsw if not SwapCache. swap-out (__delete_from_swap_cache) - uncharge page - record mem_cgroup information to swap_cgroup. swap-in (do_swap_page) - charged as page and memsw. record in swap_cgroup is cleared. memsw accounting is decremented. swap-free (swap_free()) - if swap entry is freed, memsw is uncharged by PAGE_SIZE. There are people work under never-swap environments and consider swap as something bad. For such people, this mem+swap controller extension is just an overhead. This overhead is avoided by config or boot option. (see Kconfig. detail is not in this patch.) TODO: - maybe more optimization can be don in swap-in path. (but not very safe.) But we just do simple accounting at this stage. [nishimura@mxp.nes.nec.co.jp: make resize limit hold mutex] [hugh@veritas.com: memswap controller core swapcache fixes] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 05:08:00 +03:00
/*
mm: streamline COW logic in do_swap_page() Currently we have a different COW logic when: * triggering a read-fault to swapin first and then trigger a write-fault -> do_swap_page() + do_wp_page() * triggering a write-fault to swapin -> do_swap_page() + do_wp_page() only if we fail reuse in do_swap_page() The COW logic in do_swap_page() is different than our reuse logic in do_wp_page(). The COW logic in do_wp_page() -- page_count() == 1 -- makes currently sure that we certainly don't have a remaining reference, e.g., via GUP, on the target page we want to reuse: if there is any unexpected reference, we have to copy to avoid information leaks. As do_swap_page() behaves differently, in environments with swap enabled we can currently have an unintended information leak from the parent to the child, similar as known from CVE-2020-29374: 1. Parent writes to anonymous page -> Page is mapped writable and modified 2. Page is swapped out -> Page is unmapped and replaced by swap entry 3. fork() -> Swap entries are copied to child 4. Child pins page R/O -> Page is mapped R/O into child 5. Child unmaps page -> Child still holds GUP reference 6. Parent writes to page -> Page is reused in do_swap_page() -> Child can observe changes Exchanging 2. and 3. should have the same effect. Let's apply the same COW logic as in do_wp_page(), conditionally trying to remove the page from the swapcache after freeing the swap entry, however, before actually mapping our page. We can change the order now that we use try_to_free_swap(), which doesn't care about the mapcount, instead of reuse_swap_page(). To handle references from the LRU pagevecs, conditionally drain the local LRU pagevecs when required, however, don't consider the page_count() when deciding whether to drain to keep it simple for now. Link: https://lkml.kernel.org/r/20220131162940.210846-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:40 +03:00
* Remove the swap entry and conditionally try to free up the swapcache.
* We're already holding a reference on the page but haven't mapped it
* yet.
memcg: mem+swap controller core This patch implements per cgroup limit for usage of memory+swap. However there are SwapCache, double counting of swap-cache and swap-entry is avoided. Mem+Swap controller works as following. - memory usage is limited by memory.limit_in_bytes. - memory + swap usage is limited by memory.memsw_limit_in_bytes. This has following benefits. - A user can limit total resource usage of mem+swap. Without this, because memory resource controller doesn't take care of usage of swap, a process can exhaust all the swap (by memory leak.) We can avoid this case. And Swap is shared resource but it cannot be reclaimed (goes back to memory) until it's used. This characteristic can be trouble when the memory is divided into some parts by cpuset or memcg. Assume group A and group B. After some application executes, the system can be.. Group A -- very large free memory space but occupy 99% of swap. Group B -- under memory shortage but cannot use swap...it's nearly full. Ability to set appropriate swap limit for each group is required. Maybe someone wonder "why not swap but mem+swap ?" - The global LRU(kswapd) can swap out arbitrary pages. Swap-out means to move account from memory to swap...there is no change in usage of mem+swap. In other words, when we want to limit the usage of swap without affecting global LRU, mem+swap limit is better than just limiting swap. Accounting target information is stored in swap_cgroup which is per swap entry record. Charge is done as following. map - charge page and memsw. unmap - uncharge page/memsw if not SwapCache. swap-out (__delete_from_swap_cache) - uncharge page - record mem_cgroup information to swap_cgroup. swap-in (do_swap_page) - charged as page and memsw. record in swap_cgroup is cleared. memsw accounting is decremented. swap-free (swap_free()) - if swap entry is freed, memsw is uncharged by PAGE_SIZE. There are people work under never-swap environments and consider swap as something bad. For such people, this mem+swap controller extension is just an overhead. This overhead is avoided by config or boot option. (see Kconfig. detail is not in this patch.) TODO: - maybe more optimization can be don in swap-in path. (but not very safe.) But we just do simple accounting at this stage. [nishimura@mxp.nes.nec.co.jp: make resize limit hold mutex] [hugh@veritas.com: memswap controller core swapcache fixes] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 05:08:00 +03:00
*/
mm: streamline COW logic in do_swap_page() Currently we have a different COW logic when: * triggering a read-fault to swapin first and then trigger a write-fault -> do_swap_page() + do_wp_page() * triggering a write-fault to swapin -> do_swap_page() + do_wp_page() only if we fail reuse in do_swap_page() The COW logic in do_swap_page() is different than our reuse logic in do_wp_page(). The COW logic in do_wp_page() -- page_count() == 1 -- makes currently sure that we certainly don't have a remaining reference, e.g., via GUP, on the target page we want to reuse: if there is any unexpected reference, we have to copy to avoid information leaks. As do_swap_page() behaves differently, in environments with swap enabled we can currently have an unintended information leak from the parent to the child, similar as known from CVE-2020-29374: 1. Parent writes to anonymous page -> Page is mapped writable and modified 2. Page is swapped out -> Page is unmapped and replaced by swap entry 3. fork() -> Swap entries are copied to child 4. Child pins page R/O -> Page is mapped R/O into child 5. Child unmaps page -> Child still holds GUP reference 6. Parent writes to page -> Page is reused in do_swap_page() -> Child can observe changes Exchanging 2. and 3. should have the same effect. Let's apply the same COW logic as in do_wp_page(), conditionally trying to remove the page from the swapcache after freeing the swap entry, however, before actually mapping our page. We can change the order now that we use try_to_free_swap(), which doesn't care about the mapcount, instead of reuse_swap_page(). To handle references from the LRU pagevecs, conditionally drain the local LRU pagevecs when required, however, don't consider the page_count() when deciding whether to drain to keep it simple for now. Link: https://lkml.kernel.org/r/20220131162940.210846-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:40 +03:00
swap_free(entry);
if (should_try_to_free_swap(page, vma, vmf->flags))
try_to_free_swap(page);
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
pte = mk_pte(page, vma->vm_page_prot);
mm: streamline COW logic in do_swap_page() Currently we have a different COW logic when: * triggering a read-fault to swapin first and then trigger a write-fault -> do_swap_page() + do_wp_page() * triggering a write-fault to swapin -> do_swap_page() + do_wp_page() only if we fail reuse in do_swap_page() The COW logic in do_swap_page() is different than our reuse logic in do_wp_page(). The COW logic in do_wp_page() -- page_count() == 1 -- makes currently sure that we certainly don't have a remaining reference, e.g., via GUP, on the target page we want to reuse: if there is any unexpected reference, we have to copy to avoid information leaks. As do_swap_page() behaves differently, in environments with swap enabled we can currently have an unintended information leak from the parent to the child, similar as known from CVE-2020-29374: 1. Parent writes to anonymous page -> Page is mapped writable and modified 2. Page is swapped out -> Page is unmapped and replaced by swap entry 3. fork() -> Swap entries are copied to child 4. Child pins page R/O -> Page is mapped R/O into child 5. Child unmaps page -> Child still holds GUP reference 6. Parent writes to page -> Page is reused in do_swap_page() -> Child can observe changes Exchanging 2. and 3. should have the same effect. Let's apply the same COW logic as in do_wp_page(), conditionally trying to remove the page from the swapcache after freeing the swap entry, however, before actually mapping our page. We can change the order now that we use try_to_free_swap(), which doesn't care about the mapcount, instead of reuse_swap_page(). To handle references from the LRU pagevecs, conditionally drain the local LRU pagevecs when required, however, don't consider the page_count() when deciding whether to drain to keep it simple for now. Link: https://lkml.kernel.org/r/20220131162940.210846-5-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: David Rientjes <rientjes@google.com> Cc: Don Dutile <ddutile@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Liang Zhang <zhangliang5@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Rik van Riel <riel@surriel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-25 04:13:40 +03:00
/*
* Same logic as in do_wp_page(); however, optimize for fresh pages
* that are certainly not shared because we just allocated them without
* exposing them to the swapcache.
*/
if ((vmf->flags & FAULT_FLAG_WRITE) && !PageKsm(page) &&
(page != swapcache || page_count(page) == 1)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
vmf->flags &= ~FAULT_FLAG_WRITE;
ret |= VM_FAULT_WRITE;
exclusive = RMAP_EXCLUSIVE;
}
flush_icache_page(vma, page);
if (pte_swp_soft_dirty(vmf->orig_pte))
pte = pte_mksoft_dirty(pte);
userfaultfd: wp: support swap and page migration For either swap and page migration, we all use the bit 2 of the entry to identify whether this entry is uffd write-protected. It plays a similar role as the existing soft dirty bit in swap entries but only for keeping the uffd-wp tracking for a specific PTE/PMD. Something special here is that when we want to recover the uffd-wp bit from a swap/migration entry to the PTE bit we'll also need to take care of the _PAGE_RW bit and make sure it's cleared, otherwise even with the _PAGE_UFFD_WP bit we can't trap it at all. In change_pte_range() we do nothing for uffd if the PTE is a swap entry. That can lead to data mismatch if the page that we are going to write protect is swapped out when sending the UFFDIO_WRITEPROTECT. This patch also applies/removes the uffd-wp bit even for the swap entries. Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shli@fb.com> Link: http://lkml.kernel.org/r/20200220163112.11409-11-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:06:01 +03:00
if (pte_swp_uffd_wp(vmf->orig_pte)) {
pte = pte_mkuffd_wp(pte);
pte = pte_wrprotect(pte);
}
vmf->orig_pte = pte;
/* ksm created a completely new copy */
if (unlikely(page != swapcache && swapcache)) {
page_add_new_anon_rmap(page, vma, vmf->address, false);
mm/vmscan: protect the workingset on anonymous LRU In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:30:40 +03:00
lru_cache_add_inactive_or_unevictable(page, vma);
} else {
do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
mm: memcontrol: rewrite charge API These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 01:19:20 +04:00
}
mm: change page type prior to adding page table entry Patch series "page table check", v3. Ensure that some memory corruptions are prevented by checking at the time of insertion of entries into user page tables that there is no illegal sharing. We have recently found a problem [1] that existed in kernel since 4.14. The problem was caused by broken page ref count and led to memory leaking from one process into another. The problem was accidentally detected by studying a dump of one process and noticing that one page contains memory that should not belong to this process. There are some other page->_refcount related problems that were recently fixed: [2], [3] which potentially could also lead to illegal sharing. In addition to hardening refcount [4] itself, this work is an attempt to prevent this class of memory corruption issues. It uses a simple state machine that is independent from regular MM logic to check for illegal sharing at time pages are inserted and removed from page tables. [1] https://lore.kernel.org/all/xr9335nxwc5y.fsf@gthelen2.svl.corp.google.com [2] https://lore.kernel.org/all/1582661774-30925-2-git-send-email-akaher@vmware.com [3] https://lore.kernel.org/all/20210622021423.154662-3-mike.kravetz@oracle.com [4] https://lore.kernel.org/all/20211221150140.988298-1-pasha.tatashin@soleen.com This patch (of 4): There are a few places where we first update the entry in the user page table, and later change the struct page to indicate that this is anonymous or file page. In most places, however, we first configure the page metadata and then insert entries into the page table. Page table check, will use the information from struct page to verify the type of entry is inserted. Change the order in all places to first update struct page, and later to update page table. This means that we first do calls that may change the type of page (anon or file): page_move_anon_rmap page_add_anon_rmap do_page_add_anon_rmap page_add_new_anon_rmap page_add_file_rmap hugepage_add_anon_rmap hugepage_add_new_anon_rmap And after that do calls that add entries to the page table: set_huge_pte_at set_pte_at Link: https://lkml.kernel.org/r/20211221154650.1047963-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20211221154650.1047963-2-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: David Rientjes <rientjes@google.com> Cc: Paul Turner <pjt@google.com> Cc: Wei Xu <weixugc@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Will Deacon <will@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Sami Tolvanen <samitolvanen@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-15 01:06:29 +03:00
set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
unlock_page(page);
if (page != swapcache && swapcache) {
/*
* Hold the lock to avoid the swap entry to be reused
* until we take the PT lock for the pte_same() check
* (to avoid false positives from pte_same). For
* further safety release the lock after the swap_free
* so that the swap count won't change under a
* parallel locked swapcache.
*/
unlock_page(swapcache);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(swapcache);
}
if (vmf->flags & FAULT_FLAG_WRITE) {
ret |= do_wp_page(vmf);
if (ret & VM_FAULT_ERROR)
ret &= VM_FAULT_ERROR;
goto out;
}
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, vmf->address, vmf->pte);
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
out:
swap: fix do_swap_page() race with swapoff When I was investigating the swap code, I found the below possible race window: CPU 1 CPU 2 ----- ----- do_swap_page if (data_race(si->flags & SWP_SYNCHRONOUS_IO) swap_readpage if (data_race(sis->flags & SWP_FS_OPS)) { swapoff .. p->swap_file = NULL; .. struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping;[oops!] Note that for the pages that are swapped in through swap cache, this isn't an issue. Because the page is locked, and the swap entry will be marked with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been unlocked. Fix this race by using get/put_swap_device() to guard against concurrent swapoff. Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device") Signed-off-by: Miaohe Lin <linmiaohe@huawei.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Alex Shi <alexs@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-29 05:36:50 +03:00
if (si)
put_swap_device(si);
return ret;
out_nomap:
pte_unmap_unlock(vmf->pte, vmf->ptl);
out_page:
unlock_page(page);
out_release:
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
if (page != swapcache && swapcache) {
unlock_page(swapcache);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(swapcache);
}
swap: fix do_swap_page() race with swapoff When I was investigating the swap code, I found the below possible race window: CPU 1 CPU 2 ----- ----- do_swap_page if (data_race(si->flags & SWP_SYNCHRONOUS_IO) swap_readpage if (data_race(sis->flags & SWP_FS_OPS)) { swapoff .. p->swap_file = NULL; .. struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping;[oops!] Note that for the pages that are swapped in through swap cache, this isn't an issue. Because the page is locked, and the swap entry will be marked with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been unlocked. Fix this race by using get/put_swap_device() to guard against concurrent swapoff. Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device") Signed-off-by: Miaohe Lin <linmiaohe@huawei.com> Reviewed-by: "Huang, Ying" <ying.huang@intel.com> Cc: Alex Shi <alexs@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-29 05:36:50 +03:00
if (si)
put_swap_device(si);
return ret;
}
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_lock still held, but pte unmapped and unlocked.
*/
static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page;
vm_fault_t ret = 0;
pte_t entry;
/* File mapping without ->vm_ops ? */
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
/*
* Use pte_alloc() instead of pte_alloc_map(). We can't run
* pte_offset_map() on pmds where a huge pmd might be created
* from a different thread.
*
* pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
* parallel threads are excluded by other means.
*
* Here we only have mmap_read_lock(mm).
*/
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
if (pte_alloc(vma->vm_mm, vmf->pmd))
return VM_FAULT_OOM;
/* See comment in handle_pte_fault() */
if (unlikely(pmd_trans_unstable(vmf->pmd)))
return 0;
/* Use the zero-page for reads */
if (!(vmf->flags & FAULT_FLAG_WRITE) &&
!mm_forbids_zeropage(vma->vm_mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
vma->vm_page_prot));
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
if (!pte_none(*vmf->pte)) {
update_mmu_tlb(vma, vmf->address, vmf->pte);
mm: reinstate ZERO_PAGE KAMEZAWA Hiroyuki has observed customers of earlier kernels taking advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from using in 2.6.24. And there were a couple of regression reports on LKML. Following suggestions from Linus, reinstate do_anonymous_page() use of the ZERO_PAGE; but this time avoid dirtying its struct page cacheline with (map)count updates - let vm_normal_page() regard it as abnormal. Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32, most powerpc): that's not essential, but minimizes additional branches (keeping them in the unlikely pte_special case); and incidentally excludes mips (some models of which needed eight colours of ZERO_PAGE to avoid costly exceptions). Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages() callers won't want to make exceptions for it, so increment its count there. Changes to mlock and migration? happily seems not needed. In most places it's quicker to check pfn than struct page address: prepare a __read_mostly zero_pfn for that. Does get_dump_page() still need its ZERO_PAGE check? probably not, but keep it anyway. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:03:30 +04:00
goto unlock;
}
mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Wenwei Tao <wenwei.tww@alibaba-inc.com> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andrea Argangeli <andrea@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-19 01:16:15 +03:00
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto unlock;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
mm: reinstate ZERO_PAGE KAMEZAWA Hiroyuki has observed customers of earlier kernels taking advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from using in 2.6.24. And there were a couple of regression reports on LKML. Following suggestions from Linus, reinstate do_anonymous_page() use of the ZERO_PAGE; but this time avoid dirtying its struct page cacheline with (map)count updates - let vm_normal_page() regard it as abnormal. Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32, most powerpc): that's not essential, but minimizes additional branches (keeping them in the unlikely pte_special case); and incidentally excludes mips (some models of which needed eight colours of ZERO_PAGE to avoid costly exceptions). Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages() callers won't want to make exceptions for it, so increment its count there. Changes to mlock and migration? happily seems not needed. In most places it's quicker to check pfn than struct page address: prepare a __read_mostly zero_pfn for that. Does get_dump_page() still need its ZERO_PAGE check? probably not, but keep it anyway. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:03:30 +04:00
goto setpte;
}
remove ZERO_PAGE The commit b5810039a54e5babf428e9a1e89fc1940fabff11 contains the note A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. And indeed this cacheline bouncing has shown up on large SGI systems. There was a situation where an Altix system was essentially livelocked tearing down ZERO_PAGE pagetables when an HPC app aborted during startup. This situation can be avoided in userspace, but it does highlight the potential scalability problem with refcounting ZERO_PAGE, and corner cases where it can really hurt (we don't want the system to livelock!). There are several broad ways to fix this problem: 1. add back some special casing to avoid refcounting ZERO_PAGE 2. per-node or per-cpu ZERO_PAGES 3. remove the ZERO_PAGE completely I will argue for 3. The others should also fix the problem, but they result in more complex code than does 3, with little or no real benefit that I can see. Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a false optimisation: if an application is performance critical, it would not be doing many read faults of new memory, or at least it could be expected to write to that memory soon afterwards. If cache or memory use is critical, it should not be working with a significant number of ZERO_PAGEs anyway (a more compact representation of zeroes should be used). As a sanity check -- mesuring on my desktop system, there are never many mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not increase much without it. When running a make -j4 kernel compile on my dual core system, there are about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000 ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second is torn down without being COWed). So removing ZERO_PAGE will save 1,000 page faults per second when running kbuild, while keeping it only saves less than 1 page clearing operation per second. 1 page clear is cheaper than a thousand faults, presumably, so there isn't an obvious loss. Neither the logical argument nor these basic tests give a guarantee of no regressions. However, this is a reasonable opportunity to try to remove the ZERO_PAGE from the pagefault path. If it is found to cause regressions, we can reintroduce it and just avoid refcounting it. The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see much use to them except on benchmarks. All other users of ZERO_PAGE are converted just to use ZERO_PAGE(0) for simplicity. We can look at replacing them all and maybe ripping out ZERO_PAGE completely when we are more satisfied with this solution. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus "snif" Torvalds <torvalds@linux-foundation.org>
2007-10-16 12:24:40 +04:00
/* Allocate our own private page. */
if (unlikely(anon_vma_prepare(vma)))
goto oom;
page = alloc_zeroed_user_highpage_movable(vma, vmf->address);
remove ZERO_PAGE The commit b5810039a54e5babf428e9a1e89fc1940fabff11 contains the note A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. And indeed this cacheline bouncing has shown up on large SGI systems. There was a situation where an Altix system was essentially livelocked tearing down ZERO_PAGE pagetables when an HPC app aborted during startup. This situation can be avoided in userspace, but it does highlight the potential scalability problem with refcounting ZERO_PAGE, and corner cases where it can really hurt (we don't want the system to livelock!). There are several broad ways to fix this problem: 1. add back some special casing to avoid refcounting ZERO_PAGE 2. per-node or per-cpu ZERO_PAGES 3. remove the ZERO_PAGE completely I will argue for 3. The others should also fix the problem, but they result in more complex code than does 3, with little or no real benefit that I can see. Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a false optimisation: if an application is performance critical, it would not be doing many read faults of new memory, or at least it could be expected to write to that memory soon afterwards. If cache or memory use is critical, it should not be working with a significant number of ZERO_PAGEs anyway (a more compact representation of zeroes should be used). As a sanity check -- mesuring on my desktop system, there are never many mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not increase much without it. When running a make -j4 kernel compile on my dual core system, there are about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000 ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second is torn down without being COWed). So removing ZERO_PAGE will save 1,000 page faults per second when running kbuild, while keeping it only saves less than 1 page clearing operation per second. 1 page clear is cheaper than a thousand faults, presumably, so there isn't an obvious loss. Neither the logical argument nor these basic tests give a guarantee of no regressions. However, this is a reasonable opportunity to try to remove the ZERO_PAGE from the pagefault path. If it is found to cause regressions, we can reintroduce it and just avoid refcounting it. The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see much use to them except on benchmarks. All other users of ZERO_PAGE are converted just to use ZERO_PAGE(0) for simplicity. We can look at replacing them all and maybe ripping out ZERO_PAGE completely when we are more satisfied with this solution. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus "snif" Torvalds <torvalds@linux-foundation.org>
2007-10-16 12:24:40 +04:00
if (!page)
goto oom;
mm, memcg: Try charging a page before setting page up to date Historically memcg overhead was high even if memcg was unused. This has improved a lot but it still showed up in a profile summary as being a problem. /usr/src/linux-4.0-vanilla/mm/memcontrol.c 6.6441 395842 mem_cgroup_try_charge 2.950% 175781 __mem_cgroup_count_vm_event 1.431% 85239 mem_cgroup_page_lruvec 0.456% 27156 mem_cgroup_commit_charge 0.392% 23342 uncharge_list 0.323% 19256 mem_cgroup_update_lru_size 0.278% 16538 memcg_check_events 0.216% 12858 mem_cgroup_charge_statistics.isra.22 0.188% 11172 try_charge 0.150% 8928 commit_charge 0.141% 8388 get_mem_cgroup_from_mm 0.121% 7184 That is showing that 6.64% of system CPU cycles were in memcontrol.c and dominated by mem_cgroup_try_charge. The annotation shows that the bulk of the cost was checking PageSwapCache which is expected to be cache hot but is very expensive. The problem appears to be that __SetPageUptodate is called just before the check which is a write barrier. It is required to make sure struct page and page data is written before the PTE is updated and the data visible to userspace. memcg charging does not require or need the barrier but gets unfairly hit with the cost so this patch attempts the charging before the barrier. Aside from the accidental cost to memcg there is the added benefit that the barrier is avoided if the page cannot be charged. When applied the relevant profile summary is as follows. /usr/src/linux-4.0-chargefirst-v2r1/mm/memcontrol.c 3.7907 223277 __mem_cgroup_count_vm_event 1.143% 67312 mem_cgroup_page_lruvec 0.465% 27403 mem_cgroup_commit_charge 0.381% 22452 uncharge_list 0.332% 19543 mem_cgroup_update_lru_size 0.284% 16704 get_mem_cgroup_from_mm 0.271% 15952 mem_cgroup_try_charge 0.237% 13982 memcg_check_events 0.222% 13058 mem_cgroup_charge_statistics.isra.22 0.185% 10920 commit_charge 0.140% 8235 try_charge 0.131% 7716 That brings the overhead down to 3.79% and leaves the memcg fault accounting to the root cgroup but it's an improvement. The difference in headline performance of the page fault microbench is marginal as memcg is such a small component of it. pft faults 4.0.0 4.0.0 vanilla chargefirst Hmean faults/cpu-1 1443258.1051 ( 0.00%) 1509075.7561 ( 4.56%) Hmean faults/cpu-3 1340385.9270 ( 0.00%) 1339160.7113 ( -0.09%) Hmean faults/cpu-5 875599.0222 ( 0.00%) 874174.1255 ( -0.16%) Hmean faults/cpu-7 601146.6726 ( 0.00%) 601370.9977 ( 0.04%) Hmean faults/cpu-8 510728.2754 ( 0.00%) 510598.8214 ( -0.03%) Hmean faults/sec-1 1432084.7845 ( 0.00%) 1497935.5274 ( 4.60%) Hmean faults/sec-3 3943818.1437 ( 0.00%) 3941920.1520 ( -0.05%) Hmean faults/sec-5 3877573.5867 ( 0.00%) 3869385.7553 ( -0.21%) Hmean faults/sec-7 3991832.0418 ( 0.00%) 3992181.4189 ( 0.01%) Hmean faults/sec-8 3987189.8167 ( 0.00%) 3986452.2204 ( -0.02%) It's only visible at single threaded. The overhead is there for higher threads but other factors dominate. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 02:57:27 +03:00
if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
mm, memcg: Try charging a page before setting page up to date Historically memcg overhead was high even if memcg was unused. This has improved a lot but it still showed up in a profile summary as being a problem. /usr/src/linux-4.0-vanilla/mm/memcontrol.c 6.6441 395842 mem_cgroup_try_charge 2.950% 175781 __mem_cgroup_count_vm_event 1.431% 85239 mem_cgroup_page_lruvec 0.456% 27156 mem_cgroup_commit_charge 0.392% 23342 uncharge_list 0.323% 19256 mem_cgroup_update_lru_size 0.278% 16538 memcg_check_events 0.216% 12858 mem_cgroup_charge_statistics.isra.22 0.188% 11172 try_charge 0.150% 8928 commit_charge 0.141% 8388 get_mem_cgroup_from_mm 0.121% 7184 That is showing that 6.64% of system CPU cycles were in memcontrol.c and dominated by mem_cgroup_try_charge. The annotation shows that the bulk of the cost was checking PageSwapCache which is expected to be cache hot but is very expensive. The problem appears to be that __SetPageUptodate is called just before the check which is a write barrier. It is required to make sure struct page and page data is written before the PTE is updated and the data visible to userspace. memcg charging does not require or need the barrier but gets unfairly hit with the cost so this patch attempts the charging before the barrier. Aside from the accidental cost to memcg there is the added benefit that the barrier is avoided if the page cannot be charged. When applied the relevant profile summary is as follows. /usr/src/linux-4.0-chargefirst-v2r1/mm/memcontrol.c 3.7907 223277 __mem_cgroup_count_vm_event 1.143% 67312 mem_cgroup_page_lruvec 0.465% 27403 mem_cgroup_commit_charge 0.381% 22452 uncharge_list 0.332% 19543 mem_cgroup_update_lru_size 0.284% 16704 get_mem_cgroup_from_mm 0.271% 15952 mem_cgroup_try_charge 0.237% 13982 memcg_check_events 0.222% 13058 mem_cgroup_charge_statistics.isra.22 0.185% 10920 commit_charge 0.140% 8235 try_charge 0.131% 7716 That brings the overhead down to 3.79% and leaves the memcg fault accounting to the root cgroup but it's an improvement. The difference in headline performance of the page fault microbench is marginal as memcg is such a small component of it. pft faults 4.0.0 4.0.0 vanilla chargefirst Hmean faults/cpu-1 1443258.1051 ( 0.00%) 1509075.7561 ( 4.56%) Hmean faults/cpu-3 1340385.9270 ( 0.00%) 1339160.7113 ( -0.09%) Hmean faults/cpu-5 875599.0222 ( 0.00%) 874174.1255 ( -0.16%) Hmean faults/cpu-7 601146.6726 ( 0.00%) 601370.9977 ( 0.04%) Hmean faults/cpu-8 510728.2754 ( 0.00%) 510598.8214 ( -0.03%) Hmean faults/sec-1 1432084.7845 ( 0.00%) 1497935.5274 ( 4.60%) Hmean faults/sec-3 3943818.1437 ( 0.00%) 3941920.1520 ( -0.05%) Hmean faults/sec-5 3877573.5867 ( 0.00%) 3869385.7553 ( -0.21%) Hmean faults/sec-7 3991832.0418 ( 0.00%) 3992181.4189 ( 0.01%) Hmean faults/sec-8 3987189.8167 ( 0.00%) 3986452.2204 ( -0.02%) It's only visible at single threaded. The overhead is there for higher threads but other factors dominate. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 02:57:27 +03:00
goto oom_free_page;
cgroup_throttle_swaprate(page, GFP_KERNEL);
mm, memcg: Try charging a page before setting page up to date Historically memcg overhead was high even if memcg was unused. This has improved a lot but it still showed up in a profile summary as being a problem. /usr/src/linux-4.0-vanilla/mm/memcontrol.c 6.6441 395842 mem_cgroup_try_charge 2.950% 175781 __mem_cgroup_count_vm_event 1.431% 85239 mem_cgroup_page_lruvec 0.456% 27156 mem_cgroup_commit_charge 0.392% 23342 uncharge_list 0.323% 19256 mem_cgroup_update_lru_size 0.278% 16538 memcg_check_events 0.216% 12858 mem_cgroup_charge_statistics.isra.22 0.188% 11172 try_charge 0.150% 8928 commit_charge 0.141% 8388 get_mem_cgroup_from_mm 0.121% 7184 That is showing that 6.64% of system CPU cycles were in memcontrol.c and dominated by mem_cgroup_try_charge. The annotation shows that the bulk of the cost was checking PageSwapCache which is expected to be cache hot but is very expensive. The problem appears to be that __SetPageUptodate is called just before the check which is a write barrier. It is required to make sure struct page and page data is written before the PTE is updated and the data visible to userspace. memcg charging does not require or need the barrier but gets unfairly hit with the cost so this patch attempts the charging before the barrier. Aside from the accidental cost to memcg there is the added benefit that the barrier is avoided if the page cannot be charged. When applied the relevant profile summary is as follows. /usr/src/linux-4.0-chargefirst-v2r1/mm/memcontrol.c 3.7907 223277 __mem_cgroup_count_vm_event 1.143% 67312 mem_cgroup_page_lruvec 0.465% 27403 mem_cgroup_commit_charge 0.381% 22452 uncharge_list 0.332% 19543 mem_cgroup_update_lru_size 0.284% 16704 get_mem_cgroup_from_mm 0.271% 15952 mem_cgroup_try_charge 0.237% 13982 memcg_check_events 0.222% 13058 mem_cgroup_charge_statistics.isra.22 0.185% 10920 commit_charge 0.140% 8235 try_charge 0.131% 7716 That brings the overhead down to 3.79% and leaves the memcg fault accounting to the root cgroup but it's an improvement. The difference in headline performance of the page fault microbench is marginal as memcg is such a small component of it. pft faults 4.0.0 4.0.0 vanilla chargefirst Hmean faults/cpu-1 1443258.1051 ( 0.00%) 1509075.7561 ( 4.56%) Hmean faults/cpu-3 1340385.9270 ( 0.00%) 1339160.7113 ( -0.09%) Hmean faults/cpu-5 875599.0222 ( 0.00%) 874174.1255 ( -0.16%) Hmean faults/cpu-7 601146.6726 ( 0.00%) 601370.9977 ( 0.04%) Hmean faults/cpu-8 510728.2754 ( 0.00%) 510598.8214 ( -0.03%) Hmean faults/sec-1 1432084.7845 ( 0.00%) 1497935.5274 ( 4.60%) Hmean faults/sec-3 3943818.1437 ( 0.00%) 3941920.1520 ( -0.05%) Hmean faults/sec-5 3877573.5867 ( 0.00%) 3869385.7553 ( -0.21%) Hmean faults/sec-7 3991832.0418 ( 0.00%) 3992181.4189 ( 0.01%) Hmean faults/sec-8 3987189.8167 ( 0.00%) 3986452.2204 ( -0.02%) It's only visible at single threaded. The overhead is there for higher threads but other factors dominate. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 02:57:27 +03:00
/*
* The memory barrier inside __SetPageUptodate makes sure that
* preceding stores to the page contents become visible before
* the set_pte_at() write.
*/
mm: fix PageUptodate data race After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 09:29:34 +03:00
__SetPageUptodate(page);
remove ZERO_PAGE The commit b5810039a54e5babf428e9a1e89fc1940fabff11 contains the note A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. And indeed this cacheline bouncing has shown up on large SGI systems. There was a situation where an Altix system was essentially livelocked tearing down ZERO_PAGE pagetables when an HPC app aborted during startup. This situation can be avoided in userspace, but it does highlight the potential scalability problem with refcounting ZERO_PAGE, and corner cases where it can really hurt (we don't want the system to livelock!). There are several broad ways to fix this problem: 1. add back some special casing to avoid refcounting ZERO_PAGE 2. per-node or per-cpu ZERO_PAGES 3. remove the ZERO_PAGE completely I will argue for 3. The others should also fix the problem, but they result in more complex code than does 3, with little or no real benefit that I can see. Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a false optimisation: if an application is performance critical, it would not be doing many read faults of new memory, or at least it could be expected to write to that memory soon afterwards. If cache or memory use is critical, it should not be working with a significant number of ZERO_PAGEs anyway (a more compact representation of zeroes should be used). As a sanity check -- mesuring on my desktop system, there are never many mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not increase much without it. When running a make -j4 kernel compile on my dual core system, there are about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000 ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second is torn down without being COWed). So removing ZERO_PAGE will save 1,000 page faults per second when running kbuild, while keeping it only saves less than 1 page clearing operation per second. 1 page clear is cheaper than a thousand faults, presumably, so there isn't an obvious loss. Neither the logical argument nor these basic tests give a guarantee of no regressions. However, this is a reasonable opportunity to try to remove the ZERO_PAGE from the pagefault path. If it is found to cause regressions, we can reintroduce it and just avoid refcounting it. The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see much use to them except on benchmarks. All other users of ZERO_PAGE are converted just to use ZERO_PAGE(0) for simplicity. We can look at replacing them all and maybe ripping out ZERO_PAGE completely when we are more satisfied with this solution. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus "snif" Torvalds <torvalds@linux-foundation.org>
2007-10-16 12:24:40 +04:00
entry = mk_pte(page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
&vmf->ptl);
if (!pte_none(*vmf->pte)) {
update_mmu_cache(vma, vmf->address, vmf->pte);
remove ZERO_PAGE The commit b5810039a54e5babf428e9a1e89fc1940fabff11 contains the note A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. And indeed this cacheline bouncing has shown up on large SGI systems. There was a situation where an Altix system was essentially livelocked tearing down ZERO_PAGE pagetables when an HPC app aborted during startup. This situation can be avoided in userspace, but it does highlight the potential scalability problem with refcounting ZERO_PAGE, and corner cases where it can really hurt (we don't want the system to livelock!). There are several broad ways to fix this problem: 1. add back some special casing to avoid refcounting ZERO_PAGE 2. per-node or per-cpu ZERO_PAGES 3. remove the ZERO_PAGE completely I will argue for 3. The others should also fix the problem, but they result in more complex code than does 3, with little or no real benefit that I can see. Why? Inserting a ZERO_PAGE for anonymous read faults appears to be a false optimisation: if an application is performance critical, it would not be doing many read faults of new memory, or at least it could be expected to write to that memory soon afterwards. If cache or memory use is critical, it should not be working with a significant number of ZERO_PAGEs anyway (a more compact representation of zeroes should be used). As a sanity check -- mesuring on my desktop system, there are never many mappings to the ZERO_PAGE (eg. 2 or 3), thus memory usage here should not increase much without it. When running a make -j4 kernel compile on my dual core system, there are about 1,000 mappings to the ZERO_PAGE created per second, but about 1,000 ZERO_PAGE COW faults per second (less than 1 ZERO_PAGE mapping per second is torn down without being COWed). So removing ZERO_PAGE will save 1,000 page faults per second when running kbuild, while keeping it only saves less than 1 page clearing operation per second. 1 page clear is cheaper than a thousand faults, presumably, so there isn't an obvious loss. Neither the logical argument nor these basic tests give a guarantee of no regressions. However, this is a reasonable opportunity to try to remove the ZERO_PAGE from the pagefault path. If it is found to cause regressions, we can reintroduce it and just avoid refcounting it. The /dev/zero ZERO_PAGE usage and TLB tricks also get nuked. I don't see much use to them except on benchmarks. All other users of ZERO_PAGE are converted just to use ZERO_PAGE(0) for simplicity. We can look at replacing them all and maybe ripping out ZERO_PAGE completely when we are more satisfied with this solution. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus "snif" Torvalds <torvalds@linux-foundation.org>
2007-10-16 12:24:40 +04:00
goto release;
}
ksm: fix oom deadlock There's a now-obvious deadlock in KSM's out-of-memory handling: imagine ksmd or KSM_RUN_UNMERGE handling, holding ksm_thread_mutex, trying to allocate a page to break KSM in an mm which becomes the OOM victim (quite likely in the unmerge case): it's killed and goes to exit, and hangs there waiting to acquire ksm_thread_mutex. Clearly we must not require ksm_thread_mutex in __ksm_exit, simple though that made everything else: perhaps use mmap_sem somehow? And part of the answer lies in the comments on unmerge_ksm_pages: __ksm_exit should also leave all the rmap_item removal to ksmd. But there's a fundamental problem, that KSM relies upon mmap_sem to guarantee the consistency of the mm it's dealing with, yet exit_mmap tears down an mm without taking mmap_sem. And bumping mm_users won't help at all, that just ensures that the pages the OOM killer assumes are on their way to being freed will not be freed. The best answer seems to be, to move the ksm_exit callout from just before exit_mmap, to the middle of exit_mmap: after the mm's pages have been freed (if the mmu_gather is flushed), but before its page tables and vma structures have been freed; and down_write,up_write mmap_sem there to serialize with KSM's own reliance on mmap_sem. But KSM then needs to be careful, whenever it downs mmap_sem, to check that the mm is not already exiting: there's a danger of using find_vma on a layout that's being torn apart, or writing into page tables which have been freed for reuse; and even do_anonymous_page and __do_fault need to check they're not being called by break_ksm to reinstate a pte after zap_pte_range has zapped that page table. Though it might be clearer to add an exiting flag, set while holding mmap_sem in __ksm_exit, that wouldn't cover the issue of reinstating a zapped pte. All we need is to check whether mm_users is 0 - but must remember that ksmd may detect that before __ksm_exit is reached. So, ksm_test_exit(mm) added to comment such checks on mm->mm_users. __ksm_exit now has to leave clearing up the rmap_items to ksmd, that needs ksm_thread_mutex; but shift the exiting mm just after the ksm_scan cursor so that it will soon be dealt with. __ksm_enter raise mm_count to hold the mm_struct, ksmd's exit processing (exactly like its processing when it finds all VM_MERGEABLEs unmapped) mmdrop it, similar procedure for KSM_RUN_UNMERGE (which has stopped ksmd). But also give __ksm_exit a fast path: when there's no complication (no rmap_items attached to mm and it's not at the ksm_scan cursor), it can safely do all the exiting work itself. This is not just an optimization: when ksmd is not running, the raised mm_count would otherwise leak mm_structs. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Izik Eidus <ieidus@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:02:20 +04:00
mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Wenwei Tao <wenwei.tww@alibaba-inc.com> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andrea Argangeli <andrea@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-19 01:16:15 +03:00
ret = check_stable_address_space(vma->vm_mm);
if (ret)
goto release;
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, vmf->address, false);
mm/vmscan: protect the workingset on anonymous LRU In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:30:40 +03:00
lru_cache_add_inactive_or_unevictable(page, vma);
mm: reinstate ZERO_PAGE KAMEZAWA Hiroyuki has observed customers of earlier kernels taking advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from using in 2.6.24. And there were a couple of regression reports on LKML. Following suggestions from Linus, reinstate do_anonymous_page() use of the ZERO_PAGE; but this time avoid dirtying its struct page cacheline with (map)count updates - let vm_normal_page() regard it as abnormal. Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32, most powerpc): that's not essential, but minimizes additional branches (keeping them in the unlikely pte_special case); and incidentally excludes mips (some models of which needed eight colours of ZERO_PAGE to avoid costly exceptions). Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages() callers won't want to make exceptions for it, so increment its count there. Changes to mlock and migration? happily seems not needed. In most places it's quicker to check pfn than struct page address: prepare a __read_mostly zero_pfn for that. Does get_dump_page() still need its ZERO_PAGE check? probably not, but keep it anyway. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 04:03:30 +04:00
setpte:
set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, vmf->address, vmf->pte);
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Wenwei Tao <wenwei.tww@alibaba-inc.com> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andrea Argangeli <andrea@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-19 01:16:15 +03:00
return ret;
release:
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
goto unlock;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 11:13:53 +03:00
oom_free_page:
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
oom:
return VM_FAULT_OOM;
}
/*
* The mmap_lock must have been held on entry, and may have been
* released depending on flags and vma->vm_ops->fault() return value.
* See filemap_fault() and __lock_page_retry().
*/
static vm_fault_t __do_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret;
mm, memcg: fix reclaim deadlock with writeback Liu Bo has experienced a deadlock between memcg (legacy) reclaim and the ext4 writeback task1: wait_on_page_bit+0x82/0xa0 shrink_page_list+0x907/0x960 shrink_inactive_list+0x2c7/0x680 shrink_node_memcg+0x404/0x830 shrink_node+0xd8/0x300 do_try_to_free_pages+0x10d/0x330 try_to_free_mem_cgroup_pages+0xd5/0x1b0 try_charge+0x14d/0x720 memcg_kmem_charge_memcg+0x3c/0xa0 memcg_kmem_charge+0x7e/0xd0 __alloc_pages_nodemask+0x178/0x260 alloc_pages_current+0x95/0x140 pte_alloc_one+0x17/0x40 __pte_alloc+0x1e/0x110 alloc_set_pte+0x5fe/0xc20 do_fault+0x103/0x970 handle_mm_fault+0x61e/0xd10 __do_page_fault+0x252/0x4d0 do_page_fault+0x30/0x80 page_fault+0x28/0x30 task2: __lock_page+0x86/0xa0 mpage_prepare_extent_to_map+0x2e7/0x310 [ext4] ext4_writepages+0x479/0xd60 do_writepages+0x1e/0x30 __writeback_single_inode+0x45/0x320 writeback_sb_inodes+0x272/0x600 __writeback_inodes_wb+0x92/0xc0 wb_writeback+0x268/0x300 wb_workfn+0xb4/0x390 process_one_work+0x189/0x420 worker_thread+0x4e/0x4b0 kthread+0xe6/0x100 ret_from_fork+0x41/0x50 He adds "task1 is waiting for the PageWriteback bit of the page that task2 has collected in mpd->io_submit->io_bio, and tasks2 is waiting for the LOCKED bit the page which tasks1 has locked" More precisely task1 is handling a page fault and it has a page locked while it charges a new page table to a memcg. That in turn hits a memory limit reclaim and the memcg reclaim for legacy controller is waiting on the writeback but that is never going to finish because the writeback itself is waiting for the page locked in the #PF path. So this is essentially ABBA deadlock: lock_page(A) SetPageWriteback(A) unlock_page(A) lock_page(B) lock_page(B) pte_alloc_pne shrink_page_list wait_on_page_writeback(A) SetPageWriteback(B) unlock_page(B) # flush A, B to clear the writeback This accumulating of more pages to flush is used by several filesystems to generate a more optimal IO patterns. Waiting for the writeback in legacy memcg controller is a workaround for pre-mature OOM killer invocations because there is no dirty IO throttling available for the controller. There is no easy way around that unfortunately. Therefore fix this specific issue by pre-allocating the page table outside of the page lock. We have that handy infrastructure for that already so simply reuse the fault-around pattern which already does this. There are probably other hidden __GFP_ACCOUNT | GFP_KERNEL allocations from under a fs page locked but they should be really rare. I am not aware of a better solution unfortunately. [akpm@linux-foundation.org: fix mm/memory.c:__do_fault()] [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: enhance comment, per Johannes] Link: http://lkml.kernel.org/r/20181214084948.GA5624@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181213092221.27270-1-mhocko@kernel.org Fixes: c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Liu Bo <bo.liu@linux.alibaba.com> Debugged-by: Liu Bo <bo.liu@linux.alibaba.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-09 02:23:07 +03:00
/*
* Preallocate pte before we take page_lock because this might lead to
* deadlocks for memcg reclaim which waits for pages under writeback:
* lock_page(A)
* SetPageWriteback(A)
* unlock_page(A)
* lock_page(B)
* lock_page(B)
* pte_alloc_one
mm, memcg: fix reclaim deadlock with writeback Liu Bo has experienced a deadlock between memcg (legacy) reclaim and the ext4 writeback task1: wait_on_page_bit+0x82/0xa0 shrink_page_list+0x907/0x960 shrink_inactive_list+0x2c7/0x680 shrink_node_memcg+0x404/0x830 shrink_node+0xd8/0x300 do_try_to_free_pages+0x10d/0x330 try_to_free_mem_cgroup_pages+0xd5/0x1b0 try_charge+0x14d/0x720 memcg_kmem_charge_memcg+0x3c/0xa0 memcg_kmem_charge+0x7e/0xd0 __alloc_pages_nodemask+0x178/0x260 alloc_pages_current+0x95/0x140 pte_alloc_one+0x17/0x40 __pte_alloc+0x1e/0x110 alloc_set_pte+0x5fe/0xc20 do_fault+0x103/0x970 handle_mm_fault+0x61e/0xd10 __do_page_fault+0x252/0x4d0 do_page_fault+0x30/0x80 page_fault+0x28/0x30 task2: __lock_page+0x86/0xa0 mpage_prepare_extent_to_map+0x2e7/0x310 [ext4] ext4_writepages+0x479/0xd60 do_writepages+0x1e/0x30 __writeback_single_inode+0x45/0x320 writeback_sb_inodes+0x272/0x600 __writeback_inodes_wb+0x92/0xc0 wb_writeback+0x268/0x300 wb_workfn+0xb4/0x390 process_one_work+0x189/0x420 worker_thread+0x4e/0x4b0 kthread+0xe6/0x100 ret_from_fork+0x41/0x50 He adds "task1 is waiting for the PageWriteback bit of the page that task2 has collected in mpd->io_submit->io_bio, and tasks2 is waiting for the LOCKED bit the page which tasks1 has locked" More precisely task1 is handling a page fault and it has a page locked while it charges a new page table to a memcg. That in turn hits a memory limit reclaim and the memcg reclaim for legacy controller is waiting on the writeback but that is never going to finish because the writeback itself is waiting for the page locked in the #PF path. So this is essentially ABBA deadlock: lock_page(A) SetPageWriteback(A) unlock_page(A) lock_page(B) lock_page(B) pte_alloc_pne shrink_page_list wait_on_page_writeback(A) SetPageWriteback(B) unlock_page(B) # flush A, B to clear the writeback This accumulating of more pages to flush is used by several filesystems to generate a more optimal IO patterns. Waiting for the writeback in legacy memcg controller is a workaround for pre-mature OOM killer invocations because there is no dirty IO throttling available for the controller. There is no easy way around that unfortunately. Therefore fix this specific issue by pre-allocating the page table outside of the page lock. We have that handy infrastructure for that already so simply reuse the fault-around pattern which already does this. There are probably other hidden __GFP_ACCOUNT | GFP_KERNEL allocations from under a fs page locked but they should be really rare. I am not aware of a better solution unfortunately. [akpm@linux-foundation.org: fix mm/memory.c:__do_fault()] [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: enhance comment, per Johannes] Link: http://lkml.kernel.org/r/20181214084948.GA5624@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181213092221.27270-1-mhocko@kernel.org Fixes: c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Liu Bo <bo.liu@linux.alibaba.com> Debugged-by: Liu Bo <bo.liu@linux.alibaba.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-09 02:23:07 +03:00
* shrink_page_list
* wait_on_page_writeback(A)
* SetPageWriteback(B)
* unlock_page(B)
* # flush A, B to clear the writeback
*/
if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) {
vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
mm, memcg: fix reclaim deadlock with writeback Liu Bo has experienced a deadlock between memcg (legacy) reclaim and the ext4 writeback task1: wait_on_page_bit+0x82/0xa0 shrink_page_list+0x907/0x960 shrink_inactive_list+0x2c7/0x680 shrink_node_memcg+0x404/0x830 shrink_node+0xd8/0x300 do_try_to_free_pages+0x10d/0x330 try_to_free_mem_cgroup_pages+0xd5/0x1b0 try_charge+0x14d/0x720 memcg_kmem_charge_memcg+0x3c/0xa0 memcg_kmem_charge+0x7e/0xd0 __alloc_pages_nodemask+0x178/0x260 alloc_pages_current+0x95/0x140 pte_alloc_one+0x17/0x40 __pte_alloc+0x1e/0x110 alloc_set_pte+0x5fe/0xc20 do_fault+0x103/0x970 handle_mm_fault+0x61e/0xd10 __do_page_fault+0x252/0x4d0 do_page_fault+0x30/0x80 page_fault+0x28/0x30 task2: __lock_page+0x86/0xa0 mpage_prepare_extent_to_map+0x2e7/0x310 [ext4] ext4_writepages+0x479/0xd60 do_writepages+0x1e/0x30 __writeback_single_inode+0x45/0x320 writeback_sb_inodes+0x272/0x600 __writeback_inodes_wb+0x92/0xc0 wb_writeback+0x268/0x300 wb_workfn+0xb4/0x390 process_one_work+0x189/0x420 worker_thread+0x4e/0x4b0 kthread+0xe6/0x100 ret_from_fork+0x41/0x50 He adds "task1 is waiting for the PageWriteback bit of the page that task2 has collected in mpd->io_submit->io_bio, and tasks2 is waiting for the LOCKED bit the page which tasks1 has locked" More precisely task1 is handling a page fault and it has a page locked while it charges a new page table to a memcg. That in turn hits a memory limit reclaim and the memcg reclaim for legacy controller is waiting on the writeback but that is never going to finish because the writeback itself is waiting for the page locked in the #PF path. So this is essentially ABBA deadlock: lock_page(A) SetPageWriteback(A) unlock_page(A) lock_page(B) lock_page(B) pte_alloc_pne shrink_page_list wait_on_page_writeback(A) SetPageWriteback(B) unlock_page(B) # flush A, B to clear the writeback This accumulating of more pages to flush is used by several filesystems to generate a more optimal IO patterns. Waiting for the writeback in legacy memcg controller is a workaround for pre-mature OOM killer invocations because there is no dirty IO throttling available for the controller. There is no easy way around that unfortunately. Therefore fix this specific issue by pre-allocating the page table outside of the page lock. We have that handy infrastructure for that already so simply reuse the fault-around pattern which already does this. There are probably other hidden __GFP_ACCOUNT | GFP_KERNEL allocations from under a fs page locked but they should be really rare. I am not aware of a better solution unfortunately. [akpm@linux-foundation.org: fix mm/memory.c:__do_fault()] [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: enhance comment, per Johannes] Link: http://lkml.kernel.org/r/20181214084948.GA5624@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181213092221.27270-1-mhocko@kernel.org Fixes: c3b94f44fcb0 ("memcg: further prevent OOM with too many dirty pages") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Liu Bo <bo.liu@linux.alibaba.com> Debugged-by: Liu Bo <bo.liu@linux.alibaba.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-09 02:23:07 +03:00
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
}
ret = vma->vm_ops->fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
VM_FAULT_DONE_COW)))
return ret;
if (unlikely(PageHWPoison(vmf->page))) {
vm_fault_t poisonret = VM_FAULT_HWPOISON;
if (ret & VM_FAULT_LOCKED) {
/* Retry if a clean page was removed from the cache. */
if (invalidate_inode_page(vmf->page))
poisonret = 0;
unlock_page(vmf->page);
}
put_page(vmf->page);
vmf->page = NULL;
return poisonret;
}
if (unlikely(!(ret & VM_FAULT_LOCKED)))
lock_page(vmf->page);
else
VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page);
return ret;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void deposit_prealloc_pte(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
/*
* We are going to consume the prealloc table,
* count that as nr_ptes.
*/
mm_inc_nr_ptes(vma->vm_mm);
vmf->prealloc_pte = NULL;
}
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
{
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
pmd_t entry;
int i;
vm_fault_t ret = VM_FAULT_FALLBACK;
if (!transhuge_vma_suitable(vma, haddr))
return ret;
page = compound_head(page);
if (compound_order(page) != HPAGE_PMD_ORDER)
return ret;
mm: filemap: check if THP has hwpoisoned subpage for PMD page fault When handling shmem page fault the THP with corrupted subpage could be PMD mapped if certain conditions are satisfied. But kernel is supposed to send SIGBUS when trying to map hwpoisoned page. There are two paths which may do PMD map: fault around and regular fault. Before commit f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") the thing was even worse in fault around path. The THP could be PMD mapped as long as the VMA fits regardless what subpage is accessed and corrupted. After this commit as long as head page is not corrupted the THP could be PMD mapped. In the regular fault path the THP could be PMD mapped as long as the corrupted page is not accessed and the VMA fits. This loophole could be fixed by iterating every subpage to check if any of them is hwpoisoned or not, but it is somewhat costly in page fault path. So introduce a new page flag called HasHWPoisoned on the first tail page. It indicates the THP has hwpoisoned subpage(s). It is set if any subpage of THP is found hwpoisoned by memory failure and after the refcount is bumped successfully, then cleared when the THP is freed or split. The soft offline path doesn't need this since soft offline handler just marks a subpage hwpoisoned when the subpage is migrated successfully. But shmem THP didn't get split then migrated at all. Link: https://lkml.kernel.org/r/20211020210755.23964-3-shy828301@gmail.com Fixes: 800d8c63b2e9 ("shmem: add huge pages support") Signed-off-by: Yang Shi <shy828301@gmail.com> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-10-29 00:36:11 +03:00
/*
* Just backoff if any subpage of a THP is corrupted otherwise
* the corrupted page may mapped by PMD silently to escape the
* check. This kind of THP just can be PTE mapped. Access to
* the corrupted subpage should trigger SIGBUS as expected.
*/
if (unlikely(PageHasHWPoisoned(page)))
return ret;
/*
* Archs like ppc64 need additional space to store information
* related to pte entry. Use the preallocated table for that.
*/
if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_none(*vmf->pmd)))
goto out;
for (i = 0; i < HPAGE_PMD_NR; i++)
flush_icache_page(vma, page + i);
entry = mk_huge_pmd(page, vma->vm_page_prot);
if (write)
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR);
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
page_add_file_rmap(page, vma, true);
/*
* deposit and withdraw with pmd lock held
*/
if (arch_needs_pgtable_deposit())
deposit_prealloc_pte(vmf);
set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
update_mmu_cache_pmd(vma, haddr, vmf->pmd);
/* fault is handled */
ret = 0;
count_vm_event(THP_FILE_MAPPED);
out:
spin_unlock(vmf->ptl);
return ret;
}
#else
vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
{
return VM_FAULT_FALLBACK;
}
#endif
void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
{
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
bool prefault = vmf->address != addr;
pte_t entry;
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
2020-11-24 21:48:26 +03:00
if (prefault && arch_wants_old_prefaulted_pte())
entry = pte_mkold(entry);
else
entry = pte_sw_mkyoung(entry);
2020-11-24 21:48:26 +03:00
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, addr, false);
mm/vmscan: protect the workingset on anonymous LRU In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:30:40 +03:00
lru_cache_add_inactive_or_unevictable(page, vma);
} else {
inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2022-02-15 05:26:39 +03:00
page_add_file_rmap(page, vma, false);
}
set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
}
/**
* finish_fault - finish page fault once we have prepared the page to fault
*
* @vmf: structure describing the fault
*
* This function handles all that is needed to finish a page fault once the
* page to fault in is prepared. It handles locking of PTEs, inserts PTE for
* given page, adds reverse page mapping, handles memcg charges and LRU
* addition.
*
* The function expects the page to be locked and on success it consumes a
* reference of a page being mapped (for the PTE which maps it).
*
* Return: %0 on success, %VM_FAULT_ code in case of error.
*/
vm_fault_t finish_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page;
vm_fault_t ret;
/* Did we COW the page? */
if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
page = vmf->cow_page;
else
page = vmf->page;
mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Wenwei Tao <wenwei.tww@alibaba-inc.com> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Andrea Argangeli <andrea@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-19 01:16:15 +03:00
/*
* check even for read faults because we might have lost our CoWed
* page
*/
if (!(vma->vm_flags & VM_SHARED)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret)
return ret;
}
if (pmd_none(*vmf->pmd)) {
if (PageTransCompound(page)) {
ret = do_set_pmd(vmf, page);
if (ret != VM_FAULT_FALLBACK)
return ret;
}
if (vmf->prealloc_pte)
pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte);
else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
return VM_FAULT_OOM;
}
/* See comment in handle_pte_fault() */
if (pmd_devmap_trans_unstable(vmf->pmd))
return 0;
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
ret = 0;
/* Re-check under ptl */
if (likely(pte_none(*vmf->pte)))
do_set_pte(vmf, page, vmf->address);
else
ret = VM_FAULT_NOPAGE;
update_mmu_tlb(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
}
static unsigned long fault_around_bytes __read_mostly =
rounddown_pow_of_two(65536);
#ifdef CONFIG_DEBUG_FS
static int fault_around_bytes_get(void *data, u64 *val)
{
*val = fault_around_bytes;
return 0;
}
/*
* fault_around_bytes must be rounded down to the nearest page order as it's
* what do_fault_around() expects to see.
*/
static int fault_around_bytes_set(void *data, u64 val)
{
if (val / PAGE_SIZE > PTRS_PER_PTE)
return -EINVAL;
if (val > PAGE_SIZE)
fault_around_bytes = rounddown_pow_of_two(val);
else
fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops,
fault_around_bytes_get, fault_around_bytes_set, "%llu\n");
static int __init fault_around_debugfs(void)
{
debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
&fault_around_bytes_fops);
return 0;
}
late_initcall(fault_around_debugfs);
#endif
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
/*
* do_fault_around() tries to map few pages around the fault address. The hope
* is that the pages will be needed soon and this will lower the number of
* faults to handle.
*
* It uses vm_ops->map_pages() to map the pages, which skips the page if it's
* not ready to be mapped: not up-to-date, locked, etc.
*
* This function is called with the page table lock taken. In the split ptlock
* case the page table lock only protects only those entries which belong to
* the page table corresponding to the fault address.
*
* This function doesn't cross the VMA boundaries, in order to call map_pages()
* only once.
*
* fault_around_bytes defines how many bytes we'll try to map.
* do_fault_around() expects it to be set to a power of two less than or equal
* to PTRS_PER_PTE.
*
* The virtual address of the area that we map is naturally aligned to
* fault_around_bytes rounded down to the machine page size
* (and therefore to page order). This way it's easier to guarantee
* that we don't cross page table boundaries.
*/
static vm_fault_t do_fault_around(struct vm_fault *vmf)
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
{
unsigned long address = vmf->address, nr_pages, mask;
pgoff_t start_pgoff = vmf->pgoff;
pgoff_t end_pgoff;
int off;
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT;
mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
address = max(address & mask, vmf->vma->vm_start);
off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
start_pgoff -= off;
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
/*
* end_pgoff is either the end of the page table, the end of
* the vma or nr_pages from start_pgoff, depending what is nearest.
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
*/
end_pgoff = start_pgoff -
((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
PTRS_PER_PTE - 1;
end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1,
start_pgoff + nr_pages - 1);
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
if (pmd_none(*vmf->pmd)) {
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:28:34 +03:00
vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
if (!vmf->prealloc_pte)
return VM_FAULT_OOM;
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
}
return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
}
static vm_fault_t do_read_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret = 0;
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
/*
* Let's call ->map_pages() first and use ->fault() as fallback
* if page by the offset is not ready to be mapped (cold cache or
* something).
*/
if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
userfaultfd/shmem: support minor fault registration for shmem This patch allows shmem-backed VMAs to be registered for minor faults. Minor faults are appropriately relayed to userspace in the fault path, for VMAs with the relevant flag. This commit doesn't hook up the UFFDIO_CONTINUE ioctl for shmem-backed minor faults, though, so userspace doesn't yet have a way to resolve such faults. Because of this, we also don't yet advertise this as a supported feature. That will be done in a separate commit when the feature is fully implemented. Link: https://lkml.kernel.org/r/20210503180737.2487560-4-axelrasmussen@google.com Signed-off-by: Axel Rasmussen <axelrasmussen@google.com> Acked-by: Peter Xu <peterx@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Brian Geffon <bgeffon@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Wang Qing <wangqing@vivo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:49:20 +03:00
if (likely(!userfaultfd_minor(vmf->vma))) {
ret = do_fault_around(vmf);
if (ret)
return ret;
}
mm: introduce vm_ops->map_pages() Here's new version of faultaround patchset. It took a while to tune it and collect performance data. First patch adds new callback ->map_pages to vm_operations_struct. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "pgoff" till "max_pgoff". ->map_pages() is called with page table locked and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with offset "pgoff" is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". Currently VM use ->map_pages only on read page fault path. We try to map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now. Performance data for different FAULT_AROUND_ORDER is below. TODO: - implement ->map_pages() for shmem/tmpfs; - modify get_user_pages() to be able to use ->map_pages() and implement mmap(MAP_POPULATE|MAP_NONBLOCK) on top. ========================================================================= Tested on 4-socket machine (120 threads) with 128GiB of RAM. Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is somewhere between 3 and 5. Let's say 4 :) Linux build (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 283,301,572 247,151,987 212,215,789 204,772,882 199,568,944 194,703,779 193,381,485 time, seconds 151.227629483 153.920996480 151.356125472 150.863792049 150.879207877 151.150764954 151.450962358 Linux rebuild (make -j60) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 5,396,854 4,148,444 2,855,286 2,577,282 2,361,957 2,169,573 2,112,643 time, seconds 27.404543757 27.559725591 27.030057426 26.855045126 26.678618635 26.974523490 26.761320095 Git test suite (make -j60 test) FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 minor-faults 129,591,823 99,200,751 66,106,718 57,606,410 51,510,808 45,776,813 44,085,515 time, seconds 66.087215026 64.784546905 64.401156567 65.282708668 66.034016829 66.793780811 67.237810413 Two synthetic tests: access every word in file in sequential/random order. It doesn't improve much after FAULT_AROUND_ORDER == 4. Sequential access 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 4,195,437 2,098,275 525,068 262,251 131,170 32,856 8,282 time, seconds 7.250461742 6.461711074 5.493859139 5.488488147 5.707213983 5.898510832 5.109232856 8 threads minor-faults 33,557,540 16,892,728 4,515,848 2,366,999 1,423,382 442,732 142,339 time, seconds 16.649304881 9.312555263 6.612490639 6.394316732 6.669827501 6.75078944 6.371900528 32 threads minor-faults 134,228,222 67,526,810 17,725,386 9,716,537 4,763,731 1,668,921 537,200 time, seconds 49.164430543 29.712060103 12.938649729 10.175151004 11.840094583 9.594081325 9.928461797 60 threads minor-faults 251,687,988 126,146,952 32,919,406 18,208,804 10,458,947 2,733,907 928,217 time, seconds 86.260656897 49.626551828 22.335007632 17.608243696 16.523119035 16.339489186 16.326390902 120 threads minor-faults 503,352,863 252,939,677 67,039,168 35,191,827 19,170,091 4,688,357 1,471,862 time, seconds 124.589206333 79.757867787 39.508707872 32.167281632 29.972989292 28.729834575 28.042251622 Random access 1GiB file 1 thread minor-faults 262,636 132,743 34,369 17,299 8,527 3,451 1,222 time, seconds 15.351890914 16.613802482 16.569227308 15.179220992 16.557356122 16.578247824 15.365266994 8 threads minor-faults 2,098,948 1,061,871 273,690 154,501 87,110 25,663 7,384 time, seconds 15.040026343 15.096933500 14.474757288 14.289129964 14.411537468 14.296316837 14.395635804 32 threads minor-faults 8,390,734 4,231,023 1,054,432 528,847 269,242 97,746 26,881 time, seconds 20.430433109 21.585235358 22.115062928 14.872878951 14.880856305 14.883370649 14.821261690 60 threads minor-faults 15,733,258 7,892,809 1,973,393 988,266 594,789 164,994 51,691 time, seconds 26.577302548 25.692397770 18.728863715 20.153026398 21.619101933 17.745086260 17.613215273 120 threads minor-faults 31,471,111 15,816,616 3,959,209 1,978,685 1,008,299 264,635 96,010 time, seconds 41.835322703 40.459786095 36.085306105 35.313894834 35.814445675 36.552633793 34.289210594 Touch only one page in page table in 16GiB file FAULT_AROUND_ORDER Baseline 1 3 4 5 7 9 1 thread minor-faults 8,372 8,324 8,270 8,260 8,249 8,239 8,237 time, seconds 0.039892712 0.045369149 0.051846126 0.063681685 0.079095975 0.17652406 0.541213386 8 threads minor-faults 65,731 65,681 65,628 65,620 65,608 65,599 65,596 time, seconds 0.124159196 0.488600638 0.156854426 0.191901957 0.242631486 0.543569456 1.677303984 32 threads minor-faults 262,388 262,341 262,285 262,276 262,266 262,257 263,183 time, seconds 0.452421421 0.488600638 0.565020946 0.648229739 0.789850823 1.651584361 5.000361559 60 threads minor-faults 491,822 491,792 491,723 491,711 491,701 491,691 491,825 time, seconds 0.763288616 0.869620515 0.980727360 1.161732354 1.466915814 3.04041448 9.308612938 120 threads minor-faults 983,466 983,655 983,366 983,372 983,363 984,083 984,164 time, seconds 1.595846553 1.667902182 2.008959376 2.425380942 2.941368804 5.977807890 18.401846125 This patch (of 2): Introduce new vm_ops callback ->map_pages() and uses it for mapping easy accessible pages around fault address. On read page fault, if filesystem provides ->map_pages(), we try to map up to FAULT_AROUND_PAGES pages around page fault address in hope to reduce number of minor page faults. We call ->map_pages first and use ->fault() as fallback if page by the offset is not ready to be mapped (cold page cache or something). Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 02:37:18 +04:00
}
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
ret |= finish_fault(vmf);
unlock_page(vmf->page);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
put_page(vmf->page);
return ret;
}
static vm_fault_t do_cow_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address);
if (!vmf->cow_page)
return VM_FAULT_OOM;
if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm,
GFP_KERNEL)) {
put_page(vmf->cow_page);
return VM_FAULT_OOM;
}
cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL);
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
if (ret & VM_FAULT_DONE_COW)
return ret;
copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma);
__SetPageUptodate(vmf->cow_page);
ret |= finish_fault(vmf);
unlock_page(vmf->page);
put_page(vmf->page);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
return ret;
uncharge_out:
put_page(vmf->cow_page);
return ret;
}
static vm_fault_t do_shared_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
vm_fault_t ret, tmp;
mm: preallocate page before lock_page() at filemap COW Currently we are keeping faulted page locked throughout whole __do_fault call (except for page_mkwrite code path) after calling file system's fault code. If we do early COW, we allocate a new page which has to be charged for a memcg (mem_cgroup_newpage_charge). This function, however, might block for unbounded amount of time if memcg oom killer is disabled or fork-bomb is running because the only way out of the OOM situation is either an external event or OOM-situation fix. In the end we are keeping the faulted page locked and blocking other processes from faulting it in which is not good at all because we are basically punishing potentially an unrelated process for OOM condition in a different group (I have seen stuck system because of ld-2.11.1.so being locked). We can do test easily. % cgcreate -g memory:A % cgset -r memory.limit_in_bytes=64M A % cgset -r memory.memsw.limit_in_bytes=64M A % cd kernel_dir; cgexec -g memory:A make -j Then, the whole system will live-locked until you kill 'make -j' by hands (or push reboot...) This is because some important page in a a shared library are locked. Considering again, the new page is not necessary to be allocated with lock_page() held. And usual page allocation may dive into long memory reclaim loop with holding lock_page() and can cause very long latency. There are 3 ways. 1. do allocation/charge before lock_page() Pros. - simple and can handle page allocation in the same manner. This will reduce holding time of lock_page() in general. Cons. - we do page allocation even if ->fault() returns error. 2. do charge after unlock_page(). Even if charge fails, it's just OOM. Pros. - no impact to non-memcg path. Cons. - implemenation requires special cares of LRU and we need to modify page_add_new_anon_rmap()... 3. do unlock->charge->lock again method. Pros. - no impact to non-memcg path. Cons. - This may kill LOCK_PAGE_RETRY optimization. We need to release lock and get it again... This patch moves "charge" and memory allocation for COW page before lock_page(). Then, we can avoid scanning LRU with holding a lock on a page and latency under lock_page() will be reduced. Then, above livelock disappears. [akpm@linux-foundation.org: fix code layout] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reported-by: Lutz Vieweg <lvml@5t9.de> Original-idea-by: Michal Hocko <mhocko@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-26 04:12:27 +04:00
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
/*
* Check if the backing address space wants to know that the page is
* about to become writable
*/
if (vma->vm_ops->page_mkwrite) {
unlock_page(vmf->page);
tmp = do_page_mkwrite(vmf);
if (unlikely(!tmp ||
(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
put_page(vmf->page);
return tmp;
}
}
ret |= finish_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
VM_FAULT_RETRY))) {
unlock_page(vmf->page);
put_page(vmf->page);
return ret;
}
mm: close page_mkwrite races Change page_mkwrite to allow implementations to return with the page locked, and also change it's callers (in page fault paths) to hold the lock until the page is marked dirty. This allows the filesystem to have full control of page dirtying events coming from the VM. Rather than simply hold the page locked over the page_mkwrite call, we call page_mkwrite with the page unlocked and allow callers to return with it locked, so filesystems can avoid LOR conditions with page lock. The problem with the current scheme is this: a filesystem that wants to associate some metadata with a page as long as the page is dirty, will perform this manipulation in its ->page_mkwrite. It currently then must return with the page unlocked and may not hold any other locks (according to existing page_mkwrite convention). In this window, the VM could write out the page, clearing page-dirty. The filesystem has no good way to detect that a dirty pte is about to be attached, so it will happily write out the page, at which point, the filesystem may manipulate the metadata to reflect that the page is no longer dirty. It is not always possible to perform the required metadata manipulation in ->set_page_dirty, because that function cannot block or fail. The filesystem may need to allocate some data structure, for example. And the VM cannot mark the pte dirty before page_mkwrite, because page_mkwrite is allowed to fail, so we must not allow any window where the page could be written to if page_mkwrite does fail. This solution of holding the page locked over the 3 critical operations (page_mkwrite, setting the pte dirty, and finally setting the page dirty) closes out races nicely, preventing page cleaning for writeout being initiated in that window. This provides the filesystem with a strong synchronisation against the VM here. - Sage needs this race closed for ceph filesystem. - Trond for NFS (http://bugzilla.kernel.org/show_bug.cgi?id=12913). - I need it for fsblock. - I suspect other filesystems may need it too (eg. btrfs). - I have converted buffer.c to the new locking. Even simple block allocation under dirty pages might be susceptible to i_size changing under partial page at the end of file (we also have a buffer.c-side problem here, but it cannot be fixed properly without this patch). - Other filesystems (eg. NFS, maybe btrfs) will need to change their page_mkwrite functions themselves. [ This also moves page_mkwrite another step closer to fault, which should eventually allow page_mkwrite to be moved into ->fault, and thus avoiding a filesystem calldown and page lock/unlock cycle in __do_fault. ] [akpm@linux-foundation.org: fix derefs of NULL ->mapping] Cc: Sage Weil <sage@newdream.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-05-01 02:08:16 +04:00
mm: drop mmap_sem before calling balance_dirty_pages() in write fault One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 04:50:22 +03:00
ret |= fault_dirty_shared_page(vmf);
mm: preallocate page before lock_page() at filemap COW Currently we are keeping faulted page locked throughout whole __do_fault call (except for page_mkwrite code path) after calling file system's fault code. If we do early COW, we allocate a new page which has to be charged for a memcg (mem_cgroup_newpage_charge). This function, however, might block for unbounded amount of time if memcg oom killer is disabled or fork-bomb is running because the only way out of the OOM situation is either an external event or OOM-situation fix. In the end we are keeping the faulted page locked and blocking other processes from faulting it in which is not good at all because we are basically punishing potentially an unrelated process for OOM condition in a different group (I have seen stuck system because of ld-2.11.1.so being locked). We can do test easily. % cgcreate -g memory:A % cgset -r memory.limit_in_bytes=64M A % cgset -r memory.memsw.limit_in_bytes=64M A % cd kernel_dir; cgexec -g memory:A make -j Then, the whole system will live-locked until you kill 'make -j' by hands (or push reboot...) This is because some important page in a a shared library are locked. Considering again, the new page is not necessary to be allocated with lock_page() held. And usual page allocation may dive into long memory reclaim loop with holding lock_page() and can cause very long latency. There are 3 ways. 1. do allocation/charge before lock_page() Pros. - simple and can handle page allocation in the same manner. This will reduce holding time of lock_page() in general. Cons. - we do page allocation even if ->fault() returns error. 2. do charge after unlock_page(). Even if charge fails, it's just OOM. Pros. - no impact to non-memcg path. Cons. - implemenation requires special cares of LRU and we need to modify page_add_new_anon_rmap()... 3. do unlock->charge->lock again method. Pros. - no impact to non-memcg path. Cons. - This may kill LOCK_PAGE_RETRY optimization. We need to release lock and get it again... This patch moves "charge" and memory allocation for COW page before lock_page(). Then, we can avoid scanning LRU with holding a lock on a page and latency under lock_page() will be reduced. Then, above livelock disappears. [akpm@linux-foundation.org: fix code layout] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reported-by: Lutz Vieweg <lvml@5t9.de> Original-idea-by: Michal Hocko <mhocko@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Ying Han <yinghan@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-26 04:12:27 +04:00
return ret;
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:46:59 +04:00
}
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:46:57 +04:00
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults).
* The mmap_lock may have been released depending on flags and our
* return value. See filemap_fault() and __folio_lock_or_retry().
* If mmap_lock is released, vma may become invalid (for example
mm/memory.c: do_fault: avoid usage of stale vm_area_struct LTP testcase mtest06 [1] can trigger a crash on s390x running 5.0.0-rc8. This is a stress test, where one thread mmaps/writes/munmaps memory area and other thread is trying to read from it: CPU: 0 PID: 2611 Comm: mmap1 Not tainted 5.0.0-rc8+ #51 Hardware name: IBM 2964 N63 400 (z/VM 6.4.0) Krnl PSW : 0404e00180000000 00000000001ac8d8 (__lock_acquire+0x7/0x7a8) Call Trace: ([<0000000000000000>] (null)) [<00000000001adae4>] lock_acquire+0xec/0x258 [<000000000080d1ac>] _raw_spin_lock_bh+0x5c/0x98 [<000000000012a780>] page_table_free+0x48/0x1a8 [<00000000002f6e54>] do_fault+0xdc/0x670 [<00000000002fadae>] __handle_mm_fault+0x416/0x5f0 [<00000000002fb138>] handle_mm_fault+0x1b0/0x320 [<00000000001248cc>] do_dat_exception+0x19c/0x2c8 [<000000000080e5ee>] pgm_check_handler+0x19e/0x200 page_table_free() is called with NULL mm parameter, but because "0" is a valid address on s390 (see S390_lowcore), it keeps going until it eventually crashes in lockdep's lock_acquire. This crash is reproducible at least since 4.14. Problem is that "vmf->vma" used in do_fault() can become stale. Because mmap_sem may be released, other threads can come in, call munmap() and cause "vma" be returned to kmem cache, and get zeroed/re-initialized and re-used: handle_mm_fault | __handle_mm_fault | do_fault | vma = vmf->vma | do_read_fault | __do_fault | vma->vm_ops->fault(vmf); | mmap_sem is released | | | do_munmap() | remove_vma_list() | remove_vma() | vm_area_free() | # vma is released | ... | # same vma is allocated | # from kmem cache | do_mmap() | vm_area_alloc() | memset(vma, 0, ...) | pte_free(vma->vm_mm, ...); | page_table_free | spin_lock_bh(&mm->context.lock);| <crash> | Cache mm_struct to avoid using potentially stale "vma". [1] https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/mem/mtest06/mmap1.c Link: http://lkml.kernel.org/r/5b3fdf19e2a5be460a384b936f5b56e13733f1b8.1551595137.git.jstancek@redhat.com Signed-off-by: Jan Stancek <jstancek@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Matthew Wilcox <willy@infradead.org> Acked-by: Rafael Aquini <aquini@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@surriel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:50:08 +03:00
* by other thread calling munmap()).
*/
static vm_fault_t do_fault(struct vm_fault *vmf)
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:46:59 +04:00
{
struct vm_area_struct *vma = vmf->vma;
mm/memory.c: do_fault: avoid usage of stale vm_area_struct LTP testcase mtest06 [1] can trigger a crash on s390x running 5.0.0-rc8. This is a stress test, where one thread mmaps/writes/munmaps memory area and other thread is trying to read from it: CPU: 0 PID: 2611 Comm: mmap1 Not tainted 5.0.0-rc8+ #51 Hardware name: IBM 2964 N63 400 (z/VM 6.4.0) Krnl PSW : 0404e00180000000 00000000001ac8d8 (__lock_acquire+0x7/0x7a8) Call Trace: ([<0000000000000000>] (null)) [<00000000001adae4>] lock_acquire+0xec/0x258 [<000000000080d1ac>] _raw_spin_lock_bh+0x5c/0x98 [<000000000012a780>] page_table_free+0x48/0x1a8 [<00000000002f6e54>] do_fault+0xdc/0x670 [<00000000002fadae>] __handle_mm_fault+0x416/0x5f0 [<00000000002fb138>] handle_mm_fault+0x1b0/0x320 [<00000000001248cc>] do_dat_exception+0x19c/0x2c8 [<000000000080e5ee>] pgm_check_handler+0x19e/0x200 page_table_free() is called with NULL mm parameter, but because "0" is a valid address on s390 (see S390_lowcore), it keeps going until it eventually crashes in lockdep's lock_acquire. This crash is reproducible at least since 4.14. Problem is that "vmf->vma" used in do_fault() can become stale. Because mmap_sem may be released, other threads can come in, call munmap() and cause "vma" be returned to kmem cache, and get zeroed/re-initialized and re-used: handle_mm_fault | __handle_mm_fault | do_fault | vma = vmf->vma | do_read_fault | __do_fault | vma->vm_ops->fault(vmf); | mmap_sem is released | | | do_munmap() | remove_vma_list() | remove_vma() | vm_area_free() | # vma is released | ... | # same vma is allocated | # from kmem cache | do_mmap() | vm_area_alloc() | memset(vma, 0, ...) | pte_free(vma->vm_mm, ...); | page_table_free | spin_lock_bh(&mm->context.lock);| <crash> | Cache mm_struct to avoid using potentially stale "vma". [1] https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/mem/mtest06/mmap1.c Link: http://lkml.kernel.org/r/5b3fdf19e2a5be460a384b936f5b56e13733f1b8.1551595137.git.jstancek@redhat.com Signed-off-by: Jan Stancek <jstancek@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Matthew Wilcox <willy@infradead.org> Acked-by: Rafael Aquini <aquini@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@surriel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:50:08 +03:00
struct mm_struct *vm_mm = vma->vm_mm;
vm_fault_t ret;
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:46:59 +04:00
/*
* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
*/
if (!vma->vm_ops->fault) {
/*
* If we find a migration pmd entry or a none pmd entry, which
* should never happen, return SIGBUS
*/
if (unlikely(!pmd_present(*vmf->pmd)))
ret = VM_FAULT_SIGBUS;
else {
vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm,
vmf->pmd,
vmf->address,
&vmf->ptl);
/*
* Make sure this is not a temporary clearing of pte
* by holding ptl and checking again. A R/M/W update
* of pte involves: take ptl, clearing the pte so that
* we don't have concurrent modification by hardware
* followed by an update.
*/
if (unlikely(pte_none(*vmf->pte)))
ret = VM_FAULT_SIGBUS;
else
ret = VM_FAULT_NOPAGE;
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
} else if (!(vmf->flags & FAULT_FLAG_WRITE))
mm: stop leaking PageTables 4.10-rc loadtest (even on x86, and even without THPCache) fails with "fork: Cannot allocate memory" or some such; and /proc/meminfo shows PageTables growing. Commit 953c66c2b22a ("mm: THP page cache support for ppc64") that got merged in rc1 removed the freeing of an unused preallocated pagetable after do_fault_around() has called map_pages(). This is usually a good optimization, so that the followup doesn't have to reallocate one; but it's not sufficient to shift the freeing into alloc_set_pte(), since there are failure cases (most commonly VM_FAULT_RETRY) which never reach finish_fault(). Check and free it at the outer level in do_fault(), then we don't need to worry in alloc_set_pte(), and can restore that to how it was (I cannot find any reason to pte_free() under lock as it was doing). And fix a separate pagetable leak, or crash, introduced by the same change, that could only show up on some ppc64: why does do_set_pmd()'s failure case attempt to withdraw a pagetable when it never deposited one, at the same time overwriting (so leaking) the vmf->prealloc_pte? Residue of an earlier implementation, perhaps? Delete it. Fixes: 953c66c2b22a ("mm: THP page cache support for ppc64") Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Neuling <mikey@neuling.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-08 02:37:31 +03:00
ret = do_read_fault(vmf);
else if (!(vma->vm_flags & VM_SHARED))
ret = do_cow_fault(vmf);
else
ret = do_shared_fault(vmf);
/* preallocated pagetable is unused: free it */
if (vmf->prealloc_pte) {
mm/memory.c: do_fault: avoid usage of stale vm_area_struct LTP testcase mtest06 [1] can trigger a crash on s390x running 5.0.0-rc8. This is a stress test, where one thread mmaps/writes/munmaps memory area and other thread is trying to read from it: CPU: 0 PID: 2611 Comm: mmap1 Not tainted 5.0.0-rc8+ #51 Hardware name: IBM 2964 N63 400 (z/VM 6.4.0) Krnl PSW : 0404e00180000000 00000000001ac8d8 (__lock_acquire+0x7/0x7a8) Call Trace: ([<0000000000000000>] (null)) [<00000000001adae4>] lock_acquire+0xec/0x258 [<000000000080d1ac>] _raw_spin_lock_bh+0x5c/0x98 [<000000000012a780>] page_table_free+0x48/0x1a8 [<00000000002f6e54>] do_fault+0xdc/0x670 [<00000000002fadae>] __handle_mm_fault+0x416/0x5f0 [<00000000002fb138>] handle_mm_fault+0x1b0/0x320 [<00000000001248cc>] do_dat_exception+0x19c/0x2c8 [<000000000080e5ee>] pgm_check_handler+0x19e/0x200 page_table_free() is called with NULL mm parameter, but because "0" is a valid address on s390 (see S390_lowcore), it keeps going until it eventually crashes in lockdep's lock_acquire. This crash is reproducible at least since 4.14. Problem is that "vmf->vma" used in do_fault() can become stale. Because mmap_sem may be released, other threads can come in, call munmap() and cause "vma" be returned to kmem cache, and get zeroed/re-initialized and re-used: handle_mm_fault | __handle_mm_fault | do_fault | vma = vmf->vma | do_read_fault | __do_fault | vma->vm_ops->fault(vmf); | mmap_sem is released | | | do_munmap() | remove_vma_list() | remove_vma() | vm_area_free() | # vma is released | ... | # same vma is allocated | # from kmem cache | do_mmap() | vm_area_alloc() | memset(vma, 0, ...) | pte_free(vma->vm_mm, ...); | page_table_free | spin_lock_bh(&mm->context.lock);| <crash> | Cache mm_struct to avoid using potentially stale "vma". [1] https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/mem/mtest06/mmap1.c Link: http://lkml.kernel.org/r/5b3fdf19e2a5be460a384b936f5b56e13733f1b8.1551595137.git.jstancek@redhat.com Signed-off-by: Jan Stancek <jstancek@redhat.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: Matthew Wilcox <willy@infradead.org> Acked-by: Rafael Aquini <aquini@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@surriel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:50:08 +03:00
pte_free(vm_mm, vmf->prealloc_pte);
vmf->prealloc_pte = NULL;
mm: stop leaking PageTables 4.10-rc loadtest (even on x86, and even without THPCache) fails with "fork: Cannot allocate memory" or some such; and /proc/meminfo shows PageTables growing. Commit 953c66c2b22a ("mm: THP page cache support for ppc64") that got merged in rc1 removed the freeing of an unused preallocated pagetable after do_fault_around() has called map_pages(). This is usually a good optimization, so that the followup doesn't have to reallocate one; but it's not sufficient to shift the freeing into alloc_set_pte(), since there are failure cases (most commonly VM_FAULT_RETRY) which never reach finish_fault(). Check and free it at the outer level in do_fault(), then we don't need to worry in alloc_set_pte(), and can restore that to how it was (I cannot find any reason to pte_free() under lock as it was doing). And fix a separate pagetable leak, or crash, introduced by the same change, that could only show up on some ppc64: why does do_set_pmd()'s failure case attempt to withdraw a pagetable when it never deposited one, at the same time overwriting (so leaking) the vmf->prealloc_pte? Residue of an earlier implementation, perhaps? Delete it. Fixes: 953c66c2b22a ("mm: THP page cache support for ppc64") Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Neuling <mikey@neuling.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-08 02:37:31 +03:00
}
return ret;
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:46:59 +04:00
}
int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
unsigned long addr, int page_nid, int *flags)
{
get_page(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
if (page_nid == numa_node_id()) {
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
*flags |= TNF_FAULT_LOCAL;
}
return mpol_misplaced(page, vma, addr);
}
static vm_fault_t do_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL;
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:42:58 +03:00
int page_nid = NUMA_NO_NODE;
int last_cpupid;
int target_nid;
pte_t pte, old_pte;
mm/autonuma: let architecture override how the write bit should be stashed in a protnone pte. Patch series "Numabalancing preserve write fix", v2. This patch series address an issue w.r.t THP migration and autonuma preserve write feature. migrate_misplaced_transhuge_page() cannot deal with concurrent modification of the page. It does a page copy without following the migration pte sequence. IIUC, this was done to keep the migration simpler and at the time of implemenation we didn't had THP page cache which would have required a more elaborate migration scheme. That means thp autonuma migration expect the protnone with saved write to be done such that both kernel and user cannot update the page content. This patch series enables archs like ppc64 to do that. We are good with the hash translation mode with the current code, because we never create a hardware page table entry for a protnone pte. This patch (of 2): Autonuma preserves the write permission across numa fault to avoid taking a writefault after a numa fault (Commit: b191f9b106ea " mm: numa: preserve PTE write permissions across a NUMA hinting fault"). Architecture can implement protnone in different ways and some may choose to implement that by clearing Read/ Write/Exec bit of pte. Setting the write bit on such pte can result in wrong behaviour. Fix this up by allowing arch to override how to save the write bit on a protnone pte. [aneesh.kumar@linux.vnet.ibm.com: don't mark pte saved write in case of dirty_accountable] Link: http://lkml.kernel.org/r/1487942884-16517-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com [aneesh.kumar@linux.vnet.ibm.com: v3] Link: http://lkml.kernel.org/r/1487498625-10891-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1487050314-3892-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Michael Neuling <mikey@neuling.org> Cc: Rik van Riel <riel@surriel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <michaele@au1.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:59:16 +03:00
bool was_writable = pte_savedwrite(vmf->orig_pte);
int flags = 0;
/*
* The "pte" at this point cannot be used safely without
* validation through pte_unmap_same(). It's of NUMA type but
* the pfn may be screwed if the read is non atomic.
*/
vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
spin_lock(vmf->ptl);
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
}
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
/* Get the normal PTE */
old_pte = ptep_get(vmf->pte);
pte = pte_modify(old_pte, vma->vm_page_prot);
page = vm_normal_page(vma, vmf->address, pte);
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
if (!page)
goto out_map;
/* TODO: handle PTE-mapped THP */
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
if (PageCompound(page))
goto out_map;
/*
mm: numa: group related processes based on VMA flags instead of page table flags These are three follow-on patches based on the xfsrepair workload Dave Chinner reported was problematic in 4.0-rc1 due to changes in page table management -- https://lkml.org/lkml/2015/3/1/226. Much of the problem was reduced by commit 53da3bc2ba9e ("mm: fix up numa read-only thread grouping logic") and commit ba68bc0115eb ("mm: thp: Return the correct value for change_huge_pmd"). It was known that the performance in 3.19 was still better even if is far less safe. This series aims to restore the performance without compromising on safety. For the test of this mail, I'm comparing 3.19 against 4.0-rc4 and the three patches applied on top autonumabench 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8 Time System-NUMA01 124.00 ( 0.00%) 161.86 (-30.53%) 107.13 ( 13.60%) 103.13 ( 16.83%) 145.01 (-16.94%) Time System-NUMA01_THEADLOCAL 115.54 ( 0.00%) 107.64 ( 6.84%) 131.87 (-14.13%) 83.30 ( 27.90%) 92.35 ( 20.07%) Time System-NUMA02 9.35 ( 0.00%) 10.44 (-11.66%) 8.95 ( 4.28%) 10.72 (-14.65%) 8.16 ( 12.73%) Time System-NUMA02_SMT 3.87 ( 0.00%) 4.63 (-19.64%) 4.57 (-18.09%) 3.99 ( -3.10%) 3.36 ( 13.18%) Time Elapsed-NUMA01 570.06 ( 0.00%) 567.82 ( 0.39%) 515.78 ( 9.52%) 517.26 ( 9.26%) 543.80 ( 4.61%) Time Elapsed-NUMA01_THEADLOCAL 393.69 ( 0.00%) 384.83 ( 2.25%) 384.10 ( 2.44%) 384.31 ( 2.38%) 380.73 ( 3.29%) Time Elapsed-NUMA02 49.09 ( 0.00%) 49.33 ( -0.49%) 48.86 ( 0.47%) 48.78 ( 0.63%) 50.94 ( -3.77%) Time Elapsed-NUMA02_SMT 47.51 ( 0.00%) 47.15 ( 0.76%) 47.98 ( -0.99%) 48.12 ( -1.28%) 49.56 ( -4.31%) 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 User 46334.60 46391.94 44383.95 43971.89 44372.12 System 252.84 284.66 252.61 201.24 249.00 Elapsed 1062.14 1050.96 998.68 1000.94 1026.78 Overall the system CPU usage is comparable and the test is naturally a bit variable. The slowing of the scanner hurts numa01 but on this machine it is an adverse workload and patches that dramatically help it often hurt absolutely everything else. Due to patch 2, the fault activity is interesting 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Minor Faults 2097811 2656646 2597249 1981230 1636841 Major Faults 362 450 365 364 365 Note the impact preserving the write bit across protection updates and fault reduces faults. NUMA alloc hit 1229008 1217015 1191660 1178322 1199681 NUMA alloc miss 0 0 0 0 0 NUMA interleave hit 0 0 0 0 0 NUMA alloc local 1228514 1216317 1190871 1177448 1199021 NUMA base PTE updates 245706197 240041607 238195516 244704842 115012800 NUMA huge PMD updates 479530 468448 464868 477573 224487 NUMA page range updates 491225557 479886983 476207932 489222218 229950144 NUMA hint faults 659753 656503 641678 656926 294842 NUMA hint local faults 381604 373963 360478 337585 186249 NUMA hint local percent 57 56 56 51 63 NUMA pages migrated 5412140 6374899 6266530 5277468 5755096 AutoNUMA cost 5121% 5083% 4994% 5097% 2388% Here the impact of slowing the PTE scanner on migratrion failures is obvious as "NUMA base PTE updates" and "NUMA huge PMD updates" are massively reduced even though the headline performance is very similar. As xfsrepair was the reported workload here is the impact of the series on it. xfsrepair 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanilla vmwrite-v5r8 preserve-v5r8 slowscan-v5r8 Min real-fsmark 1183.29 ( 0.00%) 1165.73 ( 1.48%) 1152.78 ( 2.58%) 1153.64 ( 2.51%) 1177.62 ( 0.48%) Min syst-fsmark 4107.85 ( 0.00%) 4027.75 ( 1.95%) 3986.74 ( 2.95%) 3979.16 ( 3.13%) 4048.76 ( 1.44%) Min real-xfsrepair 441.51 ( 0.00%) 463.96 ( -5.08%) 449.50 ( -1.81%) 440.08 ( 0.32%) 439.87 ( 0.37%) Min syst-xfsrepair 195.76 ( 0.00%) 278.47 (-42.25%) 262.34 (-34.01%) 203.70 ( -4.06%) 143.64 ( 26.62%) Amean real-fsmark 1188.30 ( 0.00%) 1177.34 ( 0.92%) 1157.97 ( 2.55%) 1158.21 ( 2.53%) 1182.22 ( 0.51%) Amean syst-fsmark 4111.37 ( 0.00%) 4055.70 ( 1.35%) 3987.19 ( 3.02%) 3998.72 ( 2.74%) 4061.69 ( 1.21%) Amean real-xfsrepair 450.88 ( 0.00%) 468.32 ( -3.87%) 454.14 ( -0.72%) 442.36 ( 1.89%) 440.59 ( 2.28%) Amean syst-xfsrepair 199.66 ( 0.00%) 290.60 (-45.55%) 277.20 (-38.84%) 204.68 ( -2.51%) 150.55 ( 24.60%) Stddev real-fsmark 4.12 ( 0.00%) 10.82 (-162.29%) 4.14 ( -0.28%) 5.98 (-45.05%) 4.60 (-11.53%) Stddev syst-fsmark 2.63 ( 0.00%) 20.32 (-671.82%) 0.37 ( 85.89%) 16.47 (-525.59%) 15.05 (-471.79%) Stddev real-xfsrepair 6.87 ( 0.00%) 4.55 ( 33.75%) 3.46 ( 49.58%) 1.78 ( 74.12%) 0.52 ( 92.50%) Stddev syst-xfsrepair 3.02 ( 0.00%) 10.30 (-241.37%) 13.17 (-336.37%) 0.71 ( 76.63%) 5.00 (-65.61%) CoeffVar real-fsmark 0.35 ( 0.00%) 0.92 (-164.73%) 0.36 ( -2.91%) 0.52 (-48.82%) 0.39 (-12.10%) CoeffVar syst-fsmark 0.06 ( 0.00%) 0.50 (-682.41%) 0.01 ( 85.45%) 0.41 (-543.22%) 0.37 (-478.78%) CoeffVar real-xfsrepair 1.52 ( 0.00%) 0.97 ( 36.21%) 0.76 ( 49.94%) 0.40 ( 73.62%) 0.12 ( 92.33%) CoeffVar syst-xfsrepair 1.51 ( 0.00%) 3.54 (-134.54%) 4.75 (-214.31%) 0.34 ( 77.20%) 3.32 (-119.63%) Max real-fsmark 1193.39 ( 0.00%) 1191.77 ( 0.14%) 1162.90 ( 2.55%) 1166.66 ( 2.24%) 1188.50 ( 0.41%) Max syst-fsmark 4114.18 ( 0.00%) 4075.45 ( 0.94%) 3987.65 ( 3.08%) 4019.45 ( 2.30%) 4082.80 ( 0.76%) Max real-xfsrepair 457.80 ( 0.00%) 474.60 ( -3.67%) 457.82 ( -0.00%) 444.42 ( 2.92%) 441.03 ( 3.66%) Max syst-xfsrepair 203.11 ( 0.00%) 303.65 (-49.50%) 294.35 (-44.92%) 205.33 ( -1.09%) 155.28 ( 23.55%) The really relevant lines as syst-xfsrepair which is the system CPU usage when running xfsrepair. Note that on my machine the overhead was 45% higher on 4.0-rc4 which may be part of what Dave is seeing. Once we preserve the write bit across faults, it's only 2.51% higher on average. With the full series applied, system CPU usage is 24.6% lower on average. Again, the impact of preserving the write bit on minor faults is obvious and the impact of slowing scanning after migration failures is obvious on the PTE updates. Note also that the number of pages migrated is much reduced even though the headline performance is comparable. 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Minor Faults 153466827 254507978 249163829 153501373 105737890 Major Faults 610 702 690 649 724 NUMA base PTE updates 217735049 210756527 217729596 216937111 144344993 NUMA huge PMD updates 129294 85044 106921 127246 79887 NUMA pages migrated 21938995 29705270 28594162 22687324 16258075 3.19.0 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 4.0.0-rc4 vanilla vanillavmwrite-v5r8preserve-v5r8slowscan-v5r8 Mean sdb-avgqusz 13.47 2.54 2.55 2.47 2.49 Mean sdb-avgrqsz 202.32 140.22 139.50 139.02 138.12 Mean sdb-await 25.92 5.09 5.33 5.02 5.22 Mean sdb-r_await 4.71 0.19 0.83 0.51 0.11 Mean sdb-w_await 104.13 5.21 5.38 5.05 5.32 Mean sdb-svctm 0.59 0.13 0.14 0.13 0.14 Mean sdb-rrqm 0.16 0.00 0.00 0.00 0.00 Mean sdb-wrqm 3.59 1799.43 1826.84 1812.21 1785.67 Max sdb-avgqusz 111.06 12.13 14.05 11.66 15.60 Max sdb-avgrqsz 255.60 190.34 190.01 187.33 191.78 Max sdb-await 168.24 39.28 49.22 44.64 65.62 Max sdb-r_await 660.00 52.00 280.00 76.00 12.00 Max sdb-w_await 7804.00 39.28 49.22 44.64 65.62 Max sdb-svctm 4.00 2.82 2.86 1.98 2.84 Max sdb-rrqm 8.30 0.00 0.00 0.00 0.00 Max sdb-wrqm 34.20 5372.80 5278.60 5386.60 5546.15 FWIW, I also checked SPECjbb in different configurations but it's similar observations -- minor faults lower, PTE update activity lower and performance is roughly comparable against 3.19. This patch (of 3): Threads that share writable data within pages are grouped together as related tasks. This decision is based on whether the PTE is marked dirty which is subject to timing races between the PTE scanner update and when the application writes the page. If the page is file-backed, then background flushes and sync also affect placement. This is unpredictable behaviour which is impossible to reason about so this patch makes grouping decisions based on the VMA flags. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-26 01:55:37 +03:00
* Avoid grouping on RO pages in general. RO pages shouldn't hurt as
* much anyway since they can be in shared cache state. This misses
* the case where a mapping is writable but the process never writes
* to it but pte_write gets cleared during protection updates and
* pte_dirty has unpredictable behaviour between PTE scan updates,
* background writeback, dirty balancing and application behaviour.
*/
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
if (!was_writable)
flags |= TNF_NO_GROUP;
/*
* Flag if the page is shared between multiple address spaces. This
* is later used when determining whether to group tasks together
*/
if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
flags |= TNF_SHARED;
last_cpupid = page_cpupid_last(page);
page_nid = page_to_nid(page);
target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
&flags);
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:42:58 +03:00
if (target_nid == NUMA_NO_NODE) {
put_page(page);
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
goto out_map;
}
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
pte_unmap_unlock(vmf->pte, vmf->ptl);
/* Migrate to the requested node */
if (migrate_misplaced_page(page, vma, target_nid)) {
page_nid = target_nid;
flags |= TNF_MIGRATED;
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
} else {
mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-26 01:55:42 +03:00
flags |= TNF_MIGRATE_FAIL;
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
spin_lock(vmf->ptl);
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
}
goto out_map;
}
out:
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 02:42:58 +03:00
if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, 1, flags);
return 0;
NUMA balancing: reduce TLB flush via delaying mapping on hint page fault With NUMA balancing, in hint page fault handler, the faulting page will be migrated to the accessing node if necessary. During the migration, TLB will be shot down on all CPUs that the process has run on recently. Because in the hint page fault handler, the PTE will be made accessible before the migration is tried. The overhead of TLB shooting down can be high, so it's better to be avoided if possible. In fact, if we delay mapping the page until migration, that can be avoided. This is what this patch doing. For the multiple threads applications, it's possible that a page is accessed by multiple threads almost at the same time. In the original implementation, because the first thread will install the accessible PTE before migrating the page, the other threads may access the page directly before the page is made inaccessible again during migration. While with the patch, the second thread will go through the page fault handler too. And because of the PageLRU() checking in the following code path, migrate_misplaced_page() numamigrate_isolate_page() isolate_lru_page() the migrate_misplaced_page() will return 0, and the PTE will be made accessible in the second thread. This will introduce a little more overhead. But we think the possibility for a page to be accessed by the multiple threads at the same time is low, and the overhead difference isn't too large. If this becomes a problem in some workloads, we need to consider how to reduce the overhead. To test the patch, we run a test case as follows on a 2-socket Intel server (1 NUMA node per socket) with 128GB DRAM (64GB per socket). 1. Run a memory eater on NUMA node 1 to use 40GB memory before running pmbench. 2. Run pmbench (normal accessing pattern) with 8 processes, and 8 threads per process, so there are 64 threads in total. The working-set size of each process is 8960MB, so the total working-set size is 8 * 8960MB = 70GB. The CPU of all pmbench processes is bound to node 1. The pmbench processes will access some DRAM on node 0. 3. After the pmbench processes run for 10 seconds, kill the memory eater. Now, some pages will be migrated from node 0 to node 1 via NUMA balancing. Test results show that, with the patch, the pmbench throughput (page accesses/s) increases 5.5%. The number of the TLB shootdowns interrupts reduces 98% (from ~4.7e7 to ~9.7e5) with about 9.2e6 pages (35.8GB) migrated. From the perf profile, it can be found that the CPU cycles spent by try_to_unmap() and its callees reduces from 6.02% to 0.47%. That is, the CPU cycles spent by TLB shooting down decreases greatly. Link: https://lkml.kernel.org/r/20210408132236.1175607-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Matthew Wilcox" <willy@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Michel Lespinasse <walken@google.com> Cc: Arjun Roy <arjunroy@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-04-30 08:57:41 +03:00
out_map:
/*
* Make it present again, depending on how arch implements
* non-accessible ptes, some can allow access by kernel mode.
*/
old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
pte = pte_modify(old_pte, vma->vm_page_prot);
pte = pte_mkyoung(pte);
if (was_writable)
pte = pte_mkwrite(pte);
ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
update_mmu_cache(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
}
static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
{
if (vma_is_anonymous(vmf->vma))
return do_huge_pmd_anonymous_page(vmf);
mm,fs,dax: change ->pmd_fault to ->huge_fault Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:56:59 +03:00
if (vmf->vma->vm_ops->huge_fault)
return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
return VM_FAULT_FALLBACK;
}
/* `inline' is required to avoid gcc 4.1.2 build error */
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
{
userfaultfd: wp: hook userfault handler to write protection fault There are several cases write protection fault happens. It could be a write to zero page, swaped page or userfault write protected page. When the fault happens, there is no way to know if userfault write protect the page before. Here we just blindly issue a userfault notification for vma with VM_UFFD_WP regardless if app write protects it yet. Application should be ready to handle such wp fault. In the swapin case, always swapin as readonly. This will cause false positive userfaults. We need to decide later if to eliminate them with a flag like soft-dirty in the swap entry (see _PAGE_SWP_SOFT_DIRTY). hugetlbfs wouldn't need to worry about swapouts but and tmpfs would be handled by a swap entry bit like anonymous memory. The main problem with no easy solution to eliminate the false positives, will be if/when userfaultfd is extended to real filesystem pagecache. When the pagecache is freed by reclaim we can't leave the radix tree pinned if the inode and in turn the radix tree is reclaimed as well. The estimation is that full accuracy and lack of false positives could be easily provided only to anonymous memory (as long as there's no fork or as long as MADV_DONTFORK is used on the userfaultfd anonymous range) tmpfs and hugetlbfs, it's most certainly worth to achieve it but in a later incremental patch. [peterx@redhat.com: don't conditionally drop FAULT_FLAG_WRITE in do_swap_page] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Cc: Shaohua Li <shli@fb.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/20200220163112.11409-3-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:05:29 +03:00
if (vma_is_anonymous(vmf->vma)) {
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
userfaultfd: wp: hook userfault handler to write protection fault There are several cases write protection fault happens. It could be a write to zero page, swaped page or userfault write protected page. When the fault happens, there is no way to know if userfault write protect the page before. Here we just blindly issue a userfault notification for vma with VM_UFFD_WP regardless if app write protects it yet. Application should be ready to handle such wp fault. In the swapin case, always swapin as readonly. This will cause false positive userfaults. We need to decide later if to eliminate them with a flag like soft-dirty in the swap entry (see _PAGE_SWP_SOFT_DIRTY). hugetlbfs wouldn't need to worry about swapouts but and tmpfs would be handled by a swap entry bit like anonymous memory. The main problem with no easy solution to eliminate the false positives, will be if/when userfaultfd is extended to real filesystem pagecache. When the pagecache is freed by reclaim we can't leave the radix tree pinned if the inode and in turn the radix tree is reclaimed as well. The estimation is that full accuracy and lack of false positives could be easily provided only to anonymous memory (as long as there's no fork or as long as MADV_DONTFORK is used on the userfaultfd anonymous range) tmpfs and hugetlbfs, it's most certainly worth to achieve it but in a later incremental patch. [peterx@redhat.com: don't conditionally drop FAULT_FLAG_WRITE in do_swap_page] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Cc: Shaohua Li <shli@fb.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/20200220163112.11409-3-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:05:29 +03:00
return handle_userfault(vmf, VM_UFFD_WP);
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
return do_huge_pmd_wp_page(vmf);
userfaultfd: wp: hook userfault handler to write protection fault There are several cases write protection fault happens. It could be a write to zero page, swaped page or userfault write protected page. When the fault happens, there is no way to know if userfault write protect the page before. Here we just blindly issue a userfault notification for vma with VM_UFFD_WP regardless if app write protects it yet. Application should be ready to handle such wp fault. In the swapin case, always swapin as readonly. This will cause false positive userfaults. We need to decide later if to eliminate them with a flag like soft-dirty in the swap entry (see _PAGE_SWP_SOFT_DIRTY). hugetlbfs wouldn't need to worry about swapouts but and tmpfs would be handled by a swap entry bit like anonymous memory. The main problem with no easy solution to eliminate the false positives, will be if/when userfaultfd is extended to real filesystem pagecache. When the pagecache is freed by reclaim we can't leave the radix tree pinned if the inode and in turn the radix tree is reclaimed as well. The estimation is that full accuracy and lack of false positives could be easily provided only to anonymous memory (as long as there's no fork or as long as MADV_DONTFORK is used on the userfaultfd anonymous range) tmpfs and hugetlbfs, it's most certainly worth to achieve it but in a later incremental patch. [peterx@redhat.com: don't conditionally drop FAULT_FLAG_WRITE in do_swap_page] Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Cc: Shaohua Li <shli@fb.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rik van Riel <riel@redhat.com> Link: http://lkml.kernel.org/r/20200220163112.11409-3-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 06:05:29 +03:00
}
if (vmf->vma->vm_ops->huge_fault) {
vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
}
/* COW or write-notify handled on pte level: split pmd. */
__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
return VM_FAULT_FALLBACK;
}
static vm_fault_t create_huge_pud(struct vm_fault *vmf)
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
{
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
/* No support for anonymous transparent PUD pages yet */
if (vma_is_anonymous(vmf->vma))
goto split;
if (vmf->vma->vm_ops->huge_fault) {
vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
}
split:
/* COW or write-notify not handled on PUD level: split pud.*/
__split_huge_pud(vmf->vma, vmf->pud, vmf->address);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return VM_FAULT_FALLBACK;
}
static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* No support for anonymous transparent PUD pages yet */
if (vma_is_anonymous(vmf->vma))
return VM_FAULT_FALLBACK;
if (vmf->vma->vm_ops->huge_fault)
return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
return VM_FAULT_FALLBACK;
}
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
* RISC architectures). The early dirtying is also good on the i386.
*
* There is also a hook called "update_mmu_cache()" that architectures
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
* We enter with non-exclusive mmap_lock (to exclude vma changes, but allow
* concurrent faults).
*
* The mmap_lock may have been released depending on flags and our return value.
* See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
{
pte_t entry;
if (unlikely(pmd_none(*vmf->pmd))) {
/*
* Leave __pte_alloc() until later: because vm_ops->fault may
* want to allocate huge page, and if we expose page table
* for an instant, it will be difficult to retract from
* concurrent faults and from rmap lookups.
*/
vmf->pte = NULL;
} else {
/*
* If a huge pmd materialized under us just retry later. Use
* pmd_trans_unstable() via pmd_devmap_trans_unstable() instead
* of pmd_trans_huge() to ensure the pmd didn't become
* pmd_trans_huge under us and then back to pmd_none, as a
* result of MADV_DONTNEED running immediately after a huge pmd
* fault in a different thread of this mm, in turn leading to a
* misleading pmd_trans_huge() retval. All we have to ensure is
* that it is a regular pmd that we can walk with
* pte_offset_map() and we can do that through an atomic read
* in C, which is what pmd_trans_unstable() provides.
*/
mm: avoid spurious 'bad pmd' warning messages When the pmd_devmap() checks were added by 5c7fb56e5e3f ("mm, dax: dax-pmd vs thp-pmd vs hugetlbfs-pmd") to add better support for DAX huge pages, they were all added to the end of if() statements after existing pmd_trans_huge() checks. So, things like: - if (pmd_trans_huge(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) When further checks were added after pmd_trans_unstable() checks by commit 7267ec008b5c ("mm: postpone page table allocation until we have page to map") they were also added at the end of the conditional: + if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) This ordering is fine for pmd_trans_huge(), but doesn't work for pmd_trans_unstable(). This is because DAX huge pages trip the bad_pmd() check inside of pmd_none_or_trans_huge_or_clear_bad() (called by pmd_trans_unstable()), which prints out a warning and returns 1. So, we do end up doing the right thing, but only after spamming dmesg with suspicious looking messages: mm/pgtable-generic.c:39: bad pmd ffff8808daa49b88(84000001006000a5) Reorder these checks in a helper so that pmd_devmap() is checked first, avoiding the error messages, and add a comment explaining why the ordering is important. Fixes: commit 7267ec008b5c ("mm: postpone page table allocation until we have page to map") Link: http://lkml.kernel.org/r/20170522215749.23516-1-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Pawel Lebioda <pawel.lebioda@intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Xiong Zhou <xzhou@redhat.com> Cc: Eryu Guan <eguan@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-03 00:46:34 +03:00
if (pmd_devmap_trans_unstable(vmf->pmd))
return 0;
/*
* A regular pmd is established and it can't morph into a huge
* pmd from under us anymore at this point because we hold the
* mmap_lock read mode and khugepaged takes it in write mode.
* So now it's safe to run pte_offset_map().
*/
vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
vmf->orig_pte = *vmf->pte;
/*
* some architectures can have larger ptes than wordsize,
* e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and
locking/atomics, mm: Convert ACCESS_ONCE() to READ_ONCE()/WRITE_ONCE() For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't currently harmful. However, for some features it is necessary to instrument reads and writes separately, which is not possible with ACCESS_ONCE(). This distinction is critical to correct operation. It's possible to transform the bulk of kernel code using the Coccinelle script below. However, this doesn't handle comments, leaving references to ACCESS_ONCE() instances which have been removed. As a preparatory step, this patch converts the mm code and comments to use {READ,WRITE}_ONCE() consistently. ---- virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Will Deacon <will.deacon@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Link: http://lkml.kernel.org/r/1508792849-3115-15-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 00:07:25 +03:00
* CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic
* accesses. The code below just needs a consistent view
* for the ifs and we later double check anyway with the
* ptl lock held. So here a barrier will do.
*/
barrier();
if (pte_none(vmf->orig_pte)) {
pte_unmap(vmf->pte);
vmf->pte = NULL;
}
}
if (!vmf->pte) {
if (vma_is_anonymous(vmf->vma))
return do_anonymous_page(vmf);
else
return do_fault(vmf);
}
if (!pte_present(vmf->orig_pte))
return do_swap_page(vmf);
if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma))
return do_numa_page(vmf);
vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
spin_lock(vmf->ptl);
entry = vmf->orig_pte;
if (unlikely(!pte_same(*vmf->pte, entry))) {
update_mmu_tlb(vmf->vma, vmf->address, vmf->pte);
goto unlock;
}
if (vmf->flags & FAULT_FLAG_WRITE) {
Revert "mm: replace p??_write with pte_access_permitted in fault + gup paths" This reverts commits 5c9d2d5c269c, c7da82b894e9, and e7fe7b5cae90. We'll probably need to revisit this, but basically we should not complicate the get_user_pages_fast() case, and checking the actual page table protection key bits will require more care anyway, since the protection keys depend on the exact state of the VM in question. Particularly when doing a "remote" page lookup (ie in somebody elses VM, not your own), you need to be much more careful than this was. Dave Hansen says: "So, the underlying bug here is that we now a get_user_pages_remote() and then go ahead and do the p*_access_permitted() checks against the current PKRU. This was introduced recently with the addition of the new p??_access_permitted() calls. We have checks in the VMA path for the "remote" gups and we avoid consulting PKRU for them. This got missed in the pkeys selftests because I did a ptrace read, but not a *write*. I also didn't explicitly test it against something where a COW needed to be done" It's also not entirely clear that it makes sense to check the protection key bits at this level at all. But one possible eventual solution is to make the get_user_pages_fast() case just abort if it sees protection key bits set, which makes us fall back to the regular get_user_pages() case, which then has a vma and can do the check there if we want to. We'll see. Somewhat related to this all: what we _do_ want to do some day is to check the PAGE_USER bit - it should obviously always be set for user pages, but it would be a good check to have back. Because we have no generic way to test for it, we lost it as part of moving over from the architecture-specific x86 GUP implementation to the generic one in commit e585513b76f7 ("x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"). Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-12-16 05:53:22 +03:00
if (!pte_write(entry))
return do_wp_page(vmf);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
vmf->flags & FAULT_FLAG_WRITE)) {
update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
} else {
/* Skip spurious TLB flush for retried page fault */
if (vmf->flags & FAULT_FLAG_TRIED)
goto unlock;
/*
* This is needed only for protection faults but the arch code
* is not yet telling us if this is a protection fault or not.
* This still avoids useless tlb flushes for .text page faults
* with threads.
*/
if (vmf->flags & FAULT_FLAG_WRITE)
flush_tlb_fix_spurious_fault(vmf->vma, vmf->address);
}
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 12:47:05 +04:00
return 0;
}
/*
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
* return value. See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
struct vm_fault vmf = {
.vma = vma,
.address = address & PAGE_MASK,
userfaultfd: provide unmasked address on page-fault Userfaultfd is supposed to provide the full address (i.e., unmasked) of the faulting access back to userspace. However, that is not the case for quite some time. Even running "userfaultfd_demo" from the userfaultfd man page provides the wrong output (and contradicts the man page). Notice that "UFFD_EVENT_PAGEFAULT event" shows the masked address (7fc5e30b3000) and not the first read address (0x7fc5e30b300f). Address returned by mmap() = 0x7fc5e30b3000 fault_handler_thread(): poll() returns: nready = 1; POLLIN = 1; POLLERR = 0 UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fc5e30b3000 (uffdio_copy.copy returned 4096) Read address 0x7fc5e30b300f in main(): A Read address 0x7fc5e30b340f in main(): A Read address 0x7fc5e30b380f in main(): A Read address 0x7fc5e30b3c0f in main(): A The exact address is useful for various reasons and specifically for prefetching decisions. If it is known that the memory is populated by certain objects whose size is not page-aligned, then based on the faulting address, the uffd-monitor can decide whether to prefetch and prefault the adjacent page. This bug has been for quite some time in the kernel: since commit 1a29d85eb0f1 ("mm: use vmf->address instead of of vmf->virtual_address") vmf->virtual_address"), which dates back to 2016. A concern has been raised that existing userspace application might rely on the old/wrong behavior in which the address is masked. Therefore, it was suggested to provide the masked address unless the user explicitly asks for the exact address. Add a new userfaultfd feature UFFD_FEATURE_EXACT_ADDRESS to direct userfaultfd to provide the exact address. Add a new "real_address" field to vmf to hold the unmasked address. Provide the address to userspace accordingly. Initialize real_address in various code-paths to be consistent with address, even when it is not used, to be on the safe side. [namit@vmware.com: initialize real_address on all code paths, per Jan] Link: https://lkml.kernel.org/r/20220226022655.350562-1-namit@vmware.com [akpm@linux-foundation.org: fix typo in comment, per Jan] Link: https://lkml.kernel.org/r/20220218041003.3508-1-namit@vmware.com Signed-off-by: Nadav Amit <namit@vmware.com> Acked-by: Peter Xu <peterx@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 00:45:32 +03:00
.real_address = address,
.flags = flags,
.pgoff = linear_page_index(vma, address),
.gfp_mask = __get_fault_gfp_mask(vma),
};
unsigned int dirty = flags & FAULT_FLAG_WRITE;
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
p4d_t *p4d;
vm_fault_t ret;
pgd = pgd_offset(mm, address);
p4d = p4d_alloc(mm, pgd, address);
if (!p4d)
return VM_FAULT_OOM;
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
vmf.pud = pud_alloc(mm, p4d, address);
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
if (!vmf.pud)
return VM_FAULT_OOM;
retry_pud:
mm, thp, proc: report THP eligibility for each vma Userspace falls short when trying to find out whether a specific memory range is eligible for THP. There are usecases that would like to know that http://lkml.kernel.org/r/alpine.DEB.2.21.1809251248450.50347@chino.kir.corp.google.com : This is used to identify heap mappings that should be able to fault thp : but do not, and they normally point to a low-on-memory or fragmentation : issue. The only way to deduce this now is to query for hg resp. nh flags and confronting the state with the global setting. Except that there is also PR_SET_THP_DISABLE that might change the picture. So the final logic is not trivial. Moreover the eligibility of the vma depends on the type of VMA as well. In the past we have supported only anononymous memory VMAs but things have changed and shmem based vmas are supported as well these days and the query logic gets even more complicated because the eligibility depends on the mount option and another global configuration knob. Simplify the current state and report the THP eligibility in /proc/<pid>/smaps for each existing vma. Reuse transparent_hugepage_enabled for this purpose. The original implementation of this function assumes that the caller knows that the vma itself is supported for THP so make the core checks into __transparent_hugepage_enabled and use it for existing callers. __show_smap just use the new transparent_hugepage_enabled which also checks the vma support status (please note that this one has to be out of line due to include dependency issues). [mhocko@kernel.org: fix oops with NULL ->f_mapping] Link: http://lkml.kernel.org/r/20181224185106.GC16738@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181211143641.3503-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Paul Oppenheimer <bepvte@gmail.com> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 11:38:21 +03:00
if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
pud_t orig_pud = *vmf.pud;
barrier();
if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
/* NUMA case for anonymous PUDs would go here */
Revert "mm: replace p??_write with pte_access_permitted in fault + gup paths" This reverts commits 5c9d2d5c269c, c7da82b894e9, and e7fe7b5cae90. We'll probably need to revisit this, but basically we should not complicate the get_user_pages_fast() case, and checking the actual page table protection key bits will require more care anyway, since the protection keys depend on the exact state of the VM in question. Particularly when doing a "remote" page lookup (ie in somebody elses VM, not your own), you need to be much more careful than this was. Dave Hansen says: "So, the underlying bug here is that we now a get_user_pages_remote() and then go ahead and do the p*_access_permitted() checks against the current PKRU. This was introduced recently with the addition of the new p??_access_permitted() calls. We have checks in the VMA path for the "remote" gups and we avoid consulting PKRU for them. This got missed in the pkeys selftests because I did a ptrace read, but not a *write*. I also didn't explicitly test it against something where a COW needed to be done" It's also not entirely clear that it makes sense to check the protection key bits at this level at all. But one possible eventual solution is to make the get_user_pages_fast() case just abort if it sees protection key bits set, which makes us fall back to the regular get_user_pages() case, which then has a vma and can do the check there if we want to. We'll see. Somewhat related to this all: what we _do_ want to do some day is to check the PAGE_USER bit - it should obviously always be set for user pages, but it would be a good check to have back. Because we have no generic way to test for it, we lost it as part of moving over from the architecture-specific x86 GUP implementation to the generic one in commit e585513b76f7 ("x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"). Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-12-16 05:53:22 +03:00
if (dirty && !pud_write(orig_pud)) {
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
ret = wp_huge_pud(&vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
huge_pud_set_accessed(&vmf, orig_pud);
return 0;
}
}
}
vmf.pmd = pmd_alloc(mm, vmf.pud, address);
if (!vmf.pmd)
return VM_FAULT_OOM;
/* Huge pud page fault raced with pmd_alloc? */
if (pud_trans_unstable(vmf.pud))
goto retry_pud;
mm, thp, proc: report THP eligibility for each vma Userspace falls short when trying to find out whether a specific memory range is eligible for THP. There are usecases that would like to know that http://lkml.kernel.org/r/alpine.DEB.2.21.1809251248450.50347@chino.kir.corp.google.com : This is used to identify heap mappings that should be able to fault thp : but do not, and they normally point to a low-on-memory or fragmentation : issue. The only way to deduce this now is to query for hg resp. nh flags and confronting the state with the global setting. Except that there is also PR_SET_THP_DISABLE that might change the picture. So the final logic is not trivial. Moreover the eligibility of the vma depends on the type of VMA as well. In the past we have supported only anononymous memory VMAs but things have changed and shmem based vmas are supported as well these days and the query logic gets even more complicated because the eligibility depends on the mount option and another global configuration knob. Simplify the current state and report the THP eligibility in /proc/<pid>/smaps for each existing vma. Reuse transparent_hugepage_enabled for this purpose. The original implementation of this function assumes that the caller knows that the vma itself is supported for THP so make the core checks into __transparent_hugepage_enabled and use it for existing callers. __show_smap just use the new transparent_hugepage_enabled which also checks the vma support status (please note that this one has to be out of line due to include dependency issues). [mhocko@kernel.org: fix oops with NULL ->f_mapping] Link: http://lkml.kernel.org/r/20181224185106.GC16738@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181211143641.3503-3-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Paul Oppenheimer <bepvte@gmail.com> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 11:38:21 +03:00
if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) {
mm,fs,dax: change ->pmd_fault to ->huge_fault Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:56:59 +03:00
ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
} else {
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
vmf.orig_pmd = *vmf.pmd;
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
barrier();
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
mm: thp: check pmd migration entry in common path When THP migration is being used, memory management code needs to handle pmd migration entries properly. This patch uses !pmd_present() or is_swap_pmd() (depending on whether pmd_none() needs separate code or not) to check pmd migration entries at the places where a pmd entry is present. Since pmd-related code uses split_huge_page(), split_huge_pmd(), pmd_trans_huge(), pmd_trans_unstable(), or pmd_none_or_trans_huge_or_clear_bad(), this patch: 1. adds pmd migration entry split code in split_huge_pmd(), 2. takes care of pmd migration entries whenever pmd_trans_huge() is present, 3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware. Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable() is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change them. Until this commit, a pmd entry should be: 1. pointing to a pte page, 2. is_swap_pmd(), 3. pmd_trans_huge(), 4. pmd_devmap(), or 5. pmd_none(). Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:01 +03:00
VM_BUG_ON(thp_migration_supported() &&
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
!is_pmd_migration_entry(vmf.orig_pmd));
if (is_pmd_migration_entry(vmf.orig_pmd))
mm: thp: check pmd migration entry in common path When THP migration is being used, memory management code needs to handle pmd migration entries properly. This patch uses !pmd_present() or is_swap_pmd() (depending on whether pmd_none() needs separate code or not) to check pmd migration entries at the places where a pmd entry is present. Since pmd-related code uses split_huge_page(), split_huge_pmd(), pmd_trans_huge(), pmd_trans_unstable(), or pmd_none_or_trans_huge_or_clear_bad(), this patch: 1. adds pmd migration entry split code in split_huge_pmd(), 2. takes care of pmd migration entries whenever pmd_trans_huge() is present, 3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware. Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable() is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change them. Until this commit, a pmd entry should be: 1. pointing to a pte page, 2. is_swap_pmd(), 3. pmd_trans_huge(), 4. pmd_devmap(), or 5. pmd_none(). Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Minchan Kim <minchan@kernel.org> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 02:11:01 +03:00
pmd_migration_entry_wait(mm, vmf.pmd);
return 0;
}
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf);
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
if (dirty && !pmd_write(vmf.orig_pmd)) {
ret = wp_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Hugh Dickins <hughd@google.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-01 04:51:35 +03:00
huge_pmd_set_accessed(&vmf);
return 0;
}
thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/time.h> #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
}
}
return handle_pte_fault(&vmf);
}
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
/**
* mm_account_fault - Do page fault accounting
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
*
* @regs: the pt_regs struct pointer. When set to NULL, will skip accounting
* of perf event counters, but we'll still do the per-task accounting to
* the task who triggered this page fault.
* @address: the faulted address.
* @flags: the fault flags.
* @ret: the fault retcode.
*
* This will take care of most of the page fault accounting. Meanwhile, it
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
* will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter
* updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
* still be in per-arch page fault handlers at the entry of page fault.
*/
static inline void mm_account_fault(struct pt_regs *regs,
unsigned long address, unsigned int flags,
vm_fault_t ret)
{
bool major;
/*
* We don't do accounting for some specific faults:
*
* - Unsuccessful faults (e.g. when the address wasn't valid). That
* includes arch_vma_access_permitted() failing before reaching here.
* So this is not a "this many hardware page faults" counter. We
* should use the hw profiling for that.
*
* - Incomplete faults (VM_FAULT_RETRY). They will only be counted
* once they're completed.
*/
if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY))
return;
/*
* We define the fault as a major fault when the final successful fault
* is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't
* handle it immediately previously).
*/
major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED);
mm: clean up the last pieces of page fault accountings Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:38:57 +03:00
if (major)
current->maj_flt++;
else
current->min_flt++;
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
/*
mm: clean up the last pieces of page fault accountings Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:38:57 +03:00
* If the fault is done for GUP, regs will be NULL. We only do the
* accounting for the per thread fault counters who triggered the
* fault, and we skip the perf event updates.
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
*/
if (!regs)
return;
mm: clean up the last pieces of page fault accountings Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:38:57 +03:00
if (major)
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
mm: clean up the last pieces of page fault accountings Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:38:57 +03:00
else
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
}
/*
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
* return value. See filemap_fault() and __folio_lock_or_retry().
*/
vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
unsigned int flags, struct pt_regs *regs)
{
vm_fault_t ret;
__set_current_state(TASK_RUNNING);
count_vm_event(PGFAULT);
count_memcg_event_mm(vma->vm_mm, PGFAULT);
/* do counter updates before entering really critical section. */
check_sync_rss_stat(current);
if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
flags & FAULT_FLAG_INSTRUCTION,
flags & FAULT_FLAG_REMOTE))
return VM_FAULT_SIGSEGV;
/*
* Enable the memcg OOM handling for faults triggered in user
* space. Kernel faults are handled more gracefully.
*/
if (flags & FAULT_FLAG_USER)
memcg, oom: move out_of_memory back to the charge path Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full callstack on OOM") has changed the ENOMEM semantic of memcg charges. Rather than invoking the oom killer from the charging context it delays the oom killer to the page fault path (pagefault_out_of_memory). This in turn means that many users (e.g. slab or g-u-p) will get ENOMEM when the corresponding memcg hits the hard limit and the memcg is is OOM. This is behavior is inconsistent with !memcg case where the oom killer is invoked from the allocation context and the allocator keeps retrying until it succeeds. The difference in the behavior is user visible. mmap(MAP_POPULATE) might result in not fully populated ranges while the mmap return code doesn't tell that to the userspace. Random syscalls might fail with ENOMEM etc. The primary motivation of the different memcg oom semantic was the deadlock avoidance. Things have changed since then, though. We have an async oom teardown by the oom reaper now and so we do not have to rely on the victim to tear down its memory anymore. Therefore we can return to the original semantic as long as the memcg oom killer is not handed over to the users space. There is still one thing to be careful about here though. If the oom killer is not able to make any forward progress - e.g. because there is no eligible task to kill - then we have to bail out of the charge path to prevent from same class of deadlocks. We have basically two options here. Either we fail the charge with ENOMEM or force the charge and allow overcharge. The first option has been considered more harmful than useful because rare inconsistencies in the ENOMEM behavior is hard to test for and error prone. Basically the same reason why the page allocator doesn't fail allocations under such conditions. The later might allow runaways but those should be really unlikely unless somebody misconfigures the system. E.g. allowing to migrate tasks away from the memcg to a different unlimited memcg with move_charge_at_immigrate disabled. Link: http://lkml.kernel.org/r/20180628151101.25307-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:47:11 +03:00
mem_cgroup_enter_user_fault();
if (unlikely(is_vm_hugetlb_page(vma)))
ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
else
ret = __handle_mm_fault(vma, address, flags);
if (flags & FAULT_FLAG_USER) {
memcg, oom: move out_of_memory back to the charge path Commit 3812c8c8f395 ("mm: memcg: do not trap chargers with full callstack on OOM") has changed the ENOMEM semantic of memcg charges. Rather than invoking the oom killer from the charging context it delays the oom killer to the page fault path (pagefault_out_of_memory). This in turn means that many users (e.g. slab or g-u-p) will get ENOMEM when the corresponding memcg hits the hard limit and the memcg is is OOM. This is behavior is inconsistent with !memcg case where the oom killer is invoked from the allocation context and the allocator keeps retrying until it succeeds. The difference in the behavior is user visible. mmap(MAP_POPULATE) might result in not fully populated ranges while the mmap return code doesn't tell that to the userspace. Random syscalls might fail with ENOMEM etc. The primary motivation of the different memcg oom semantic was the deadlock avoidance. Things have changed since then, though. We have an async oom teardown by the oom reaper now and so we do not have to rely on the victim to tear down its memory anymore. Therefore we can return to the original semantic as long as the memcg oom killer is not handed over to the users space. There is still one thing to be careful about here though. If the oom killer is not able to make any forward progress - e.g. because there is no eligible task to kill - then we have to bail out of the charge path to prevent from same class of deadlocks. We have basically two options here. Either we fail the charge with ENOMEM or force the charge and allow overcharge. The first option has been considered more harmful than useful because rare inconsistencies in the ENOMEM behavior is hard to test for and error prone. Basically the same reason why the page allocator doesn't fail allocations under such conditions. The later might allow runaways but those should be really unlikely unless somebody misconfigures the system. E.g. allowing to migrate tasks away from the memcg to a different unlimited memcg with move_charge_at_immigrate disabled. Link: http://lkml.kernel.org/r/20180628151101.25307-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:47:11 +03:00
mem_cgroup_exit_user_fault();
/*
* The task may have entered a memcg OOM situation but
* if the allocation error was handled gracefully (no
* VM_FAULT_OOM), there is no need to kill anything.
* Just clean up the OOM state peacefully.
*/
if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
mem_cgroup_oom_synchronize(false);
}
mm: memcg: do not trap chargers with full callstack on OOM The memcg OOM handling is incredibly fragile and can deadlock. When a task fails to charge memory, it invokes the OOM killer and loops right there in the charge code until it succeeds. Comparably, any other task that enters the charge path at this point will go to a waitqueue right then and there and sleep until the OOM situation is resolved. The problem is that these tasks may hold filesystem locks and the mmap_sem; locks that the selected OOM victim may need to exit. For example, in one reported case, the task invoking the OOM killer was about to charge a page cache page during a write(), which holds the i_mutex. The OOM killer selected a task that was just entering truncate() and trying to acquire the i_mutex: OOM invoking task: mem_cgroup_handle_oom+0x241/0x3b0 mem_cgroup_cache_charge+0xbe/0xe0 add_to_page_cache_locked+0x4c/0x140 add_to_page_cache_lru+0x22/0x50 grab_cache_page_write_begin+0x8b/0xe0 ext3_write_begin+0x88/0x270 generic_file_buffered_write+0x116/0x290 __generic_file_aio_write+0x27c/0x480 generic_file_aio_write+0x76/0xf0 # takes ->i_mutex do_sync_write+0xea/0x130 vfs_write+0xf3/0x1f0 sys_write+0x51/0x90 system_call_fastpath+0x18/0x1d OOM kill victim: do_truncate+0x58/0xa0 # takes i_mutex do_last+0x250/0xa30 path_openat+0xd7/0x440 do_filp_open+0x49/0xa0 do_sys_open+0x106/0x240 sys_open+0x20/0x30 system_call_fastpath+0x18/0x1d The OOM handling task will retry the charge indefinitely while the OOM killed task is not releasing any resources. A similar scenario can happen when the kernel OOM killer for a memcg is disabled and a userspace task is in charge of resolving OOM situations. In this case, ALL tasks that enter the OOM path will be made to sleep on the OOM waitqueue and wait for userspace to free resources or increase the group's limit. But a userspace OOM handler is prone to deadlock itself on the locks held by the waiting tasks. For example one of the sleeping tasks may be stuck in a brk() call with the mmap_sem held for writing but the userspace handler, in order to pick an optimal victim, may need to read files from /proc/<pid>, which tries to acquire the same mmap_sem for reading and deadlocks. This patch changes the way tasks behave after detecting a memcg OOM and makes sure nobody loops or sleeps with locks held: 1. When OOMing in a user fault, invoke the OOM killer and restart the fault instead of looping on the charge attempt. This way, the OOM victim can not get stuck on locks the looping task may hold. 2. When OOMing in a user fault but somebody else is handling it (either the kernel OOM killer or a userspace handler), don't go to sleep in the charge context. Instead, remember the OOMing memcg in the task struct and then fully unwind the page fault stack with -ENOMEM. pagefault_out_of_memory() will then call back into the memcg code to check if the -ENOMEM came from the memcg, and then either put the task to sleep on the memcg's OOM waitqueue or just restart the fault. The OOM victim can no longer get stuck on any lock a sleeping task may hold. Debugged by Michal Hocko. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: azurIt <azurit@pobox.sk> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-13 02:13:44 +04:00
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 04:37:44 +03:00
mm_account_fault(regs, address, flags, ret);
return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
#ifndef __PAGETABLE_P4D_FOLDED
/*
* Allocate p4d page table.
* We've already handled the fast-path in-line.
*/
int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
p4d_t *new = p4d_alloc_one(mm, address);
if (!new)
return -ENOMEM;
spin_lock(&mm->page_table_lock);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
if (pgd_present(*pgd)) { /* Another has populated it */
p4d_free(mm, new);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
} else {
smp_wmb(); /* See comment in pmd_install() */
pgd_populate(mm, pgd, new);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
}
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_P4D_FOLDED */
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
[PATCH] mm: init_mm without ptlock First step in pushing down the page_table_lock. init_mm.page_table_lock has been used throughout the architectures (usually for ioremap): not to serialize kernel address space allocation (that's usually vmlist_lock), but because pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it. Reverse that: don't lock or unlock init_mm.page_table_lock in any of the architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take and drop it when allocating a new one, to check lest a racing task already did. Similarly no page_table_lock in vmalloc's map_vm_area. Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle user mms, which are converted only by a later patch, for now they have to lock differently according to whether or not it's init_mm. If sources get muddled, there's a danger that an arch source taking init_mm.page_table_lock will be mixed with common source also taking it (or neither take it). So break the rules and make another change, which should break the build for such a mismatch: remove the redundant mm arg from pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13). Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64 used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64 map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free took page_table_lock for no good reason. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:21 +03:00
* We've already handled the fast-path in-line.
*/
int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
{
pud_t *new = pud_alloc_one(mm, address);
if (!new)
return -ENOMEM;
[PATCH] mm: init_mm without ptlock First step in pushing down the page_table_lock. init_mm.page_table_lock has been used throughout the architectures (usually for ioremap): not to serialize kernel address space allocation (that's usually vmlist_lock), but because pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it. Reverse that: don't lock or unlock init_mm.page_table_lock in any of the architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take and drop it when allocating a new one, to check lest a racing task already did. Similarly no page_table_lock in vmalloc's map_vm_area. Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle user mms, which are converted only by a later patch, for now they have to lock differently according to whether or not it's init_mm. If sources get muddled, there's a danger that an arch source taking init_mm.page_table_lock will be mixed with common source also taking it (or neither take it). So break the rules and make another change, which should break the build for such a mismatch: remove the redundant mm arg from pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13). Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64 used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64 map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free took page_table_lock for no good reason. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:21 +03:00
spin_lock(&mm->page_table_lock);
if (!p4d_present(*p4d)) {
mm_inc_nr_puds(mm);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
smp_wmb(); /* See comment in pmd_install() */
p4d_populate(mm, p4d, new);
} else /* Another has populated it */
pud_free(mm, new);
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Allocate page middle directory.
[PATCH] mm: init_mm without ptlock First step in pushing down the page_table_lock. init_mm.page_table_lock has been used throughout the architectures (usually for ioremap): not to serialize kernel address space allocation (that's usually vmlist_lock), but because pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it. Reverse that: don't lock or unlock init_mm.page_table_lock in any of the architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take and drop it when allocating a new one, to check lest a racing task already did. Similarly no page_table_lock in vmalloc's map_vm_area. Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle user mms, which are converted only by a later patch, for now they have to lock differently according to whether or not it's init_mm. If sources get muddled, there's a danger that an arch source taking init_mm.page_table_lock will be mixed with common source also taking it (or neither take it). So break the rules and make another change, which should break the build for such a mismatch: remove the redundant mm arg from pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13). Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64 used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64 map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free took page_table_lock for no good reason. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 04:16:21 +03:00
* We've already handled the fast-path in-line.
*/
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
spinlock_t *ptl;
pmd_t *new = pmd_alloc_one(mm, address);
if (!new)
return -ENOMEM;
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
ptl = pud_lock(mm, pud);
mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/prctl.h> #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: David Rientjes <rientjes@google.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 02:26:50 +03:00
if (!pud_present(*pud)) {
mm_inc_nr_pmds(mm);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
smp_wmb(); /* See comment in pmd_install() */
pud_populate(mm, pud, new);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
} else { /* Another has populated it */
pmd_free(mm, new);
mm: remove redundant smp_wmb() The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes setup is visible before the pte is made visible to other CPUs by being put into page tables. We only need this when the pte is actually populated, so move it to pmd_install(). __pte_alloc_kernel(), __p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case. We can also defer smp_wmb() to the place where the pmd entry is really populated by preallocated pte. There are two kinds of user of preallocated pte, one is filemap & finish_fault(), another is THP. The former does not need another smp_wmb() because the smp_wmb() has been done by pmd_install(). Fortunately, the latter also does not need another smp_wmb() because there is already a smp_wmb() before populating the new pte when the THP uses a preallocated pte to split a huge pmd. Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mika Penttila <mika.penttila@nextfour.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-05 23:38:41 +03:00
}
mm, x86: add support for PUD-sized transparent hugepages The current transparent hugepage code only supports PMDs. This patch adds support for transparent use of PUDs with DAX. It does not include support for anonymous pages. x86 support code also added. Most of this patch simply parallels the work that was done for huge PMDs. The only major difference is how the new ->pud_entry method in mm_walk works. The ->pmd_entry method replaces the ->pte_entry method, whereas the ->pud_entry method works along with either ->pmd_entry or ->pte_entry. The pagewalk code takes care of locking the PUD before calling ->pud_walk, so handlers do not need to worry whether the PUD is stable. [dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()] Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com [dave.jiang@intel.com: native_pud_clear missing on i386 build] Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:57:02 +03:00
spin_unlock(ptl);
return 0;
[PATCH] Workaround for gcc 2.96 (undefined references) LD .tmp_vmlinux1 mm/built-in.o(.text+0x100d6): In function `copy_page_range': : undefined reference to `__pud_alloc' mm/built-in.o(.text+0x1010b): In function `copy_page_range': : undefined reference to `__pmd_alloc' mm/built-in.o(.text+0x11ef4): In function `__handle_mm_fault': : undefined reference to `__pud_alloc' fs/built-in.o(.text+0xc930): In function `install_arg_page': : undefined reference to `__pud_alloc' make: *** [.tmp_vmlinux1] Error 1 Those missing references in mm/memory.c arise from this code in include/linux/mm.h, combined with the fact that __PGTABLE_PMD_FOLDED and __PGTABLE_PUD_FOLDED are both set and __ARCH_HAS_4LEVEL_HACK is not: /* * The following ifdef needed to get the 4level-fixup.h header to work. * Remove it when 4level-fixup.h has been removed. */ #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? NULL: pud_offset(pgd, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ With my configuration the pgd_none and pud_none routines are inlines returning a constant 0. Apparently the old compiler avoids generating calls to __pud_alloc and __pmd_alloc but still lists them as undefined references in the module's symbol table. I don't know which change caused this problem. I think it was added somewhere between 2.6.14 and 2.6.15-rc1, because I remember building several 2.6.14-rc kernels without difficulty. However I can't point to an individual culprit. Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-29 00:43:44 +03:00
}
#endif /* __PAGETABLE_PMD_FOLDED */
int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
struct mmu_notifier_range *range, pte_t **ptepp,
pmd_t **pmdpp, spinlock_t **ptlp)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
goto out;
pud = pud_offset(p4d, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
goto out;
pmd = pmd_offset(pud, address);
VM_BUG_ON(pmd_trans_huge(*pmd));
if (pmd_huge(*pmd)) {
if (!pmdpp)
goto out;
if (range) {
mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0,
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
NULL, mm, address & PMD_MASK,
(address & PMD_MASK) + PMD_SIZE);
mmu_notifier_invalidate_range_start(range);
}
*ptlp = pmd_lock(mm, pmd);
if (pmd_huge(*pmd)) {
*pmdpp = pmd;
return 0;
}
spin_unlock(*ptlp);
if (range)
mmu_notifier_invalidate_range_end(range);
}
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
if (range) {
mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
mm/mmu_notifier: contextual information for event triggering invalidation CPU page table update can happens for many reasons, not only as a result of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as a result of kernel activities (memory compression, reclaim, migration, ...). Users of mmu notifier API track changes to the CPU page table and take specific action for them. While current API only provide range of virtual address affected by the change, not why the changes is happening. This patchset do the initial mechanical convertion of all the places that calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP event as well as the vma if it is know (most invalidation happens against a given vma). Passing down the vma allows the users of mmu notifier to inspect the new vma page protection. The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier should assume that every for the range is going away when that event happens. A latter patch do convert mm call path to use a more appropriate events for each call. This is done as 2 patches so that no call site is forgotten especialy as it uses this following coccinelle patch: %<---------------------------------------------------------------------- @@ identifier I1, I2, I3, I4; @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1, +enum mmu_notifier_event event, +unsigned flags, +struct vm_area_struct *vma, struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... } @@ @@ -#define mmu_notifier_range_init(range, mm, start, end) +#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end) @@ expression E1, E3, E4; identifier I1; @@ <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, I1, I1->vm_mm, E3, E4) ...> @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(..., struct vm_area_struct *VMA, ...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN, VMA; @@ FN(...) { struct vm_area_struct *VMA; <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, VMA, E2, E3, E4) ...> } @@ expression E1, E2, E3, E4; identifier FN; @@ FN(...) { <... mmu_notifier_range_init(E1, +MMU_NOTIFY_UNMAP, 0, NULL, E2, E3, E4) ...> } ---------------------------------------------------------------------->% Applied with: spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place spatch --sp-file mmu-notifier.spatch --dir mm --in-place Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:20:49 +03:00
address & PAGE_MASK,
(address & PAGE_MASK) + PAGE_SIZE);
mmu_notifier_invalidate_range_start(range);
}
ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
if (!pte_present(*ptep))
goto unlock;
*ptepp = ptep;
return 0;
unlock:
pte_unmap_unlock(ptep, *ptlp);
if (range)
mmu_notifier_invalidate_range_end(range);
out:
return -EINVAL;
}
/**
* follow_pte - look up PTE at a user virtual address
* @mm: the mm_struct of the target address space
* @address: user virtual address
* @ptepp: location to store found PTE
* @ptlp: location to store the lock for the PTE
*
* On a successful return, the pointer to the PTE is stored in @ptepp;
* the corresponding lock is taken and its location is stored in @ptlp.
* The contents of the PTE are only stable until @ptlp is released;
* any further use, if any, must be protected against invalidation
* with MMU notifiers.
*
* Only IO mappings and raw PFN mappings are allowed. The mmap semaphore
* should be taken for read.
*
* KVM uses this function. While it is arguably less bad than ``follow_pfn``,
* it is not a good general-purpose API.
*
* Return: zero on success, -ve otherwise.
*/
int follow_pte(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, spinlock_t **ptlp)
{
return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
}
EXPORT_SYMBOL_GPL(follow_pte);
/**
* follow_pfn - look up PFN at a user virtual address
* @vma: memory mapping
* @address: user virtual address
* @pfn: location to store found PFN
*
* Only IO mappings and raw PFN mappings are allowed.
*
* This function does not allow the caller to read the permissions
* of the PTE. Do not use it.
*
* Return: zero and the pfn at @pfn on success, -ve otherwise.
*/
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn)
{
int ret = -EINVAL;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
return ret;
ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
if (ret)
return ret;
*pfn = pte_pfn(*ptep);
pte_unmap_unlock(ptep, ptl);
return 0;
}
EXPORT_SYMBOL(follow_pfn);
#ifdef CONFIG_HAVE_IOREMAP_PROT
int follow_phys(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned long *prot, resource_size_t *phys)
{
int ret = -EINVAL;
pte_t *ptep, pte;
spinlock_t *ptl;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
goto out;
if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
goto out;
pte = *ptep;
Revert "mm: replace p??_write with pte_access_permitted in fault + gup paths" This reverts commits 5c9d2d5c269c, c7da82b894e9, and e7fe7b5cae90. We'll probably need to revisit this, but basically we should not complicate the get_user_pages_fast() case, and checking the actual page table protection key bits will require more care anyway, since the protection keys depend on the exact state of the VM in question. Particularly when doing a "remote" page lookup (ie in somebody elses VM, not your own), you need to be much more careful than this was. Dave Hansen says: "So, the underlying bug here is that we now a get_user_pages_remote() and then go ahead and do the p*_access_permitted() checks against the current PKRU. This was introduced recently with the addition of the new p??_access_permitted() calls. We have checks in the VMA path for the "remote" gups and we avoid consulting PKRU for them. This got missed in the pkeys selftests because I did a ptrace read, but not a *write*. I also didn't explicitly test it against something where a COW needed to be done" It's also not entirely clear that it makes sense to check the protection key bits at this level at all. But one possible eventual solution is to make the get_user_pages_fast() case just abort if it sees protection key bits set, which makes us fall back to the regular get_user_pages() case, which then has a vma and can do the check there if we want to. We'll see. Somewhat related to this all: what we _do_ want to do some day is to check the PAGE_USER bit - it should obviously always be set for user pages, but it would be a good check to have back. Because we have no generic way to test for it, we lost it as part of moving over from the architecture-specific x86 GUP implementation to the generic one in commit e585513b76f7 ("x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"). Cc: Peter Zijlstra <peterz@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-12-16 05:53:22 +03:00
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
*prot = pgprot_val(pte_pgprot(pte));
*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
ret = 0;
unlock:
pte_unmap_unlock(ptep, ptl);
out:
return ret;
}
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
/**
* generic_access_phys - generic implementation for iomem mmap access
* @vma: the vma to access
* @addr: userspace address, not relative offset within @vma
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
* @buf: buffer to read/write
* @len: length of transfer
* @write: set to FOLL_WRITE when writing, otherwise reading
*
* This is a generic implementation for &vm_operations_struct.access for an
* iomem mapping. This callback is used by access_process_vm() when the @vma is
* not page based.
*/
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write)
{
resource_size_t phys_addr;
unsigned long prot = 0;
void __iomem *maddr;
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
pte_t *ptep, pte;
spinlock_t *ptl;
int offset = offset_in_page(addr);
int ret = -EINVAL;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
return -EINVAL;
retry:
Fixes around VM_FPNMAP and follow_pfn - replace mm/frame_vector.c by get_user_pages in misc/habana and drm/exynos drivers, then move that into media as it's sole user - close race in generic_access_phys - s390 pci ioctl fix of this series landed in 5.11 already - properly revoke iomem mappings (/dev/mem, pci files) -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEb4nG6jLu8Y5XI+PfTA9ye/CYqnEFAmAzgywACgkQTA9ye/CY qnFPbA//RUHB5bD7vwnEglfJhonKSi/Vt3dNQwUI+pCFK8muWvvPyTkGXKjjT2dI uAOY2F23wymtIexV3fNLgnMez7kMcupOLkdxJic4GiO+HJn1jnkshdX7/dGtUW7O G3yfnf/D27i912tT3j6PN7dVnasAYYtndCgImM027Zigzn4ibY+02tnzd5XTj1F8 yq8Swx88oqF8v10HxfpF3RLShqT3S17mFmd9dTv0GkZX497Pe75O44XcXzkD33Bj wasH2Tz8gMEQx6TNAGlJe13dzDHReh2cG0z2r+6PTA6KnaMMxbEIImHNuhWOmHb/ nf8Jpu9uMOLzB+3hG3TzISTDBhAgPfoJ8Ov40VJCWMtCVBnyMyPJr28Oobb8Dj3V SXvjSVlLeobOLt+E9vAS+Rmas07LCGBdNP9sexxV7S/sveSQ5W+FptaQW03EghwA nBYEUC68WqpX99lJCFPmv5zmy5xkecjpU6mLHZljtV1ORzktqWZdVhmC8njHMAMY Hi/emnPxEX1FpOD38rr7F9KUUSsy4t/ZaCgVaLcxCcbglCHXSHC41R09p9TBRSJo G6Lksjyj4aa+UL5dZDAtLY0shg0bv2u93dGQNaDAC+uzj6D0ErBBzDK570zBKjp/ 75+nqezJlD0d7I6rOl6FwiEYeSrYXJxYEveKVUr8CnH6sfeBlwo= =lQoR -----END PGP SIGNATURE----- Merge tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm Pull follow_pfn() updates from Daniel Vetter: "Fixes around VM_FPNMAP and follow_pfn: - replace mm/frame_vector.c by get_user_pages in misc/habana and drm/exynos drivers, then move that into media as it's sole user - close race in generic_access_phys - s390 pci ioctl fix of this series landed in 5.11 already - properly revoke iomem mappings (/dev/mem, pci files)" * tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm: PCI: Revoke mappings like devmem PCI: Also set up legacy files only after sysfs init sysfs: Support zapping of binary attr mmaps resource: Move devmem revoke code to resource framework /dev/mem: Only set filp->f_mapping PCI: Obey iomem restrictions for procfs mmap mm: Close race in generic_access_phys media: videobuf2: Move frame_vector into media subsystem mm/frame-vector: Use FOLL_LONGTERM misc/habana: Use FOLL_LONGTERM for userptr misc/habana: Stop using frame_vector helpers drm/exynos: Use FOLL_LONGTERM for g2d cmdlists drm/exynos: Stop using frame_vector helpers
2021-02-23 04:45:02 +03:00
if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
return -EINVAL;
pte = *ptep;
pte_unmap_unlock(ptep, ptl);
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
prot = pgprot_val(pte_pgprot(pte));
phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
if ((write & FOLL_WRITE) && !pte_write(pte))
return -EINVAL;
maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
if (!maddr)
return -ENOMEM;
Fixes around VM_FPNMAP and follow_pfn - replace mm/frame_vector.c by get_user_pages in misc/habana and drm/exynos drivers, then move that into media as it's sole user - close race in generic_access_phys - s390 pci ioctl fix of this series landed in 5.11 already - properly revoke iomem mappings (/dev/mem, pci files) -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEb4nG6jLu8Y5XI+PfTA9ye/CYqnEFAmAzgywACgkQTA9ye/CY qnFPbA//RUHB5bD7vwnEglfJhonKSi/Vt3dNQwUI+pCFK8muWvvPyTkGXKjjT2dI uAOY2F23wymtIexV3fNLgnMez7kMcupOLkdxJic4GiO+HJn1jnkshdX7/dGtUW7O G3yfnf/D27i912tT3j6PN7dVnasAYYtndCgImM027Zigzn4ibY+02tnzd5XTj1F8 yq8Swx88oqF8v10HxfpF3RLShqT3S17mFmd9dTv0GkZX497Pe75O44XcXzkD33Bj wasH2Tz8gMEQx6TNAGlJe13dzDHReh2cG0z2r+6PTA6KnaMMxbEIImHNuhWOmHb/ nf8Jpu9uMOLzB+3hG3TzISTDBhAgPfoJ8Ov40VJCWMtCVBnyMyPJr28Oobb8Dj3V SXvjSVlLeobOLt+E9vAS+Rmas07LCGBdNP9sexxV7S/sveSQ5W+FptaQW03EghwA nBYEUC68WqpX99lJCFPmv5zmy5xkecjpU6mLHZljtV1ORzktqWZdVhmC8njHMAMY Hi/emnPxEX1FpOD38rr7F9KUUSsy4t/ZaCgVaLcxCcbglCHXSHC41R09p9TBRSJo G6Lksjyj4aa+UL5dZDAtLY0shg0bv2u93dGQNaDAC+uzj6D0ErBBzDK570zBKjp/ 75+nqezJlD0d7I6rOl6FwiEYeSrYXJxYEveKVUr8CnH6sfeBlwo= =lQoR -----END PGP SIGNATURE----- Merge tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm Pull follow_pfn() updates from Daniel Vetter: "Fixes around VM_FPNMAP and follow_pfn: - replace mm/frame_vector.c by get_user_pages in misc/habana and drm/exynos drivers, then move that into media as it's sole user - close race in generic_access_phys - s390 pci ioctl fix of this series landed in 5.11 already - properly revoke iomem mappings (/dev/mem, pci files)" * tag 'topic/iomem-mmap-vs-gup-2021-02-22' of git://anongit.freedesktop.org/drm/drm: PCI: Revoke mappings like devmem PCI: Also set up legacy files only after sysfs init sysfs: Support zapping of binary attr mmaps resource: Move devmem revoke code to resource framework /dev/mem: Only set filp->f_mapping PCI: Obey iomem restrictions for procfs mmap mm: Close race in generic_access_phys media: videobuf2: Move frame_vector into media subsystem mm/frame-vector: Use FOLL_LONGTERM misc/habana: Use FOLL_LONGTERM for userptr misc/habana: Stop using frame_vector helpers drm/exynos: Use FOLL_LONGTERM for g2d cmdlists drm/exynos: Stop using frame_vector helpers
2021-02-23 04:45:02 +03:00
if (follow_pte(vma->vm_mm, addr, &ptep, &ptl))
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
goto out_unmap;
if (!pte_same(pte, *ptep)) {
pte_unmap_unlock(ptep, ptl);
iounmap(maddr);
goto retry;
}
if (write)
memcpy_toio(maddr + offset, buf, len);
else
memcpy_fromio(buf, maddr + offset, len);
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
ret = len;
pte_unmap_unlock(ptep, ptl);
out_unmap:
iounmap(maddr);
mm: Close race in generic_access_phys Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Benjamin Herrensmidt <benh@kernel.crashing.org> Cc: Dave Airlie <airlied@linux.ie> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch
2020-11-27 19:41:21 +03:00
return ret;
}
EXPORT_SYMBOL_GPL(generic_access_phys);
#endif
/*
* Access another process' address space as given in mm.
*/
int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
int len, unsigned int gup_flags)
{
struct vm_area_struct *vma;
void *old_buf = buf;
int write = gup_flags & FOLL_WRITE;
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
if (mmap_read_lock_killable(mm))
return 0;
/* ignore errors, just check how much was successfully transferred */
while (len) {
int bytes, ret, offset;
void *maddr;
struct page *page = NULL;
ret = get_user_pages_remote(mm, addr, 1,
mm: add locked parameter to get_user_pages_remote() Patch series "mm: unexport __get_user_pages_unlocked()". This patch series continues the cleanup of get_user_pages*() functions taking advantage of the fact we can now pass gup_flags as we please. It firstly adds an additional 'locked' parameter to get_user_pages_remote() to allow for its callers to utilise VM_FAULT_RETRY functionality. This is necessary as the invocation of __get_user_pages_unlocked() in process_vm_rw_single_vec() makes use of this and no other existing higher level function would allow it to do so. Secondly existing callers of __get_user_pages_unlocked() are replaced with the appropriate higher-level replacement - get_user_pages_unlocked() if the current task and memory descriptor are referenced, or get_user_pages_remote() if other task/memory descriptors are referenced (having acquiring mmap_sem.) This patch (of 2): Add a int *locked parameter to get_user_pages_remote() to allow VM_FAULT_RETRY faulting behaviour similar to get_user_pages_[un]locked(). Taking into account the previous adjustments to get_user_pages*() functions allowing for the passing of gup_flags, we are now in a position where __get_user_pages_unlocked() need only be exported for his ability to allow VM_FAULT_RETRY behaviour, this adjustment allows us to subsequently unexport __get_user_pages_unlocked() as well as allowing for future flexibility in the use of get_user_pages_remote(). [sfr@canb.auug.org.au: merge fix for get_user_pages_remote API change] Link: http://lkml.kernel.org/r/20161122210511.024ec341@canb.auug.org.au Link: http://lkml.kernel.org/r/20161027095141.2569-2-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Jan Kara <jack@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-12-15 02:06:52 +03:00
gup_flags, &page, &vma, NULL);
if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
break;
#else
/*
* Check if this is a VM_IO | VM_PFNMAP VMA, which
* we can access using slightly different code.
*/
vma = vma_lookup(mm, addr);
if (!vma)
break;
if (vma->vm_ops && vma->vm_ops->access)
ret = vma->vm_ops->access(vma, addr, buf,
len, write);
if (ret <= 0)
break;
bytes = ret;
#endif
} else {
bytes = len;
offset = addr & (PAGE_SIZE-1);
if (bytes > PAGE_SIZE-offset)
bytes = PAGE_SIZE-offset;
maddr = kmap(page);
if (write) {
copy_to_user_page(vma, page, addr,
maddr + offset, buf, bytes);
set_page_dirty_lock(page);
} else {
copy_from_user_page(vma, page, addr,
buf, maddr + offset, bytes);
}
kunmap(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
}
len -= bytes;
buf += bytes;
addr += bytes;
}
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
mmap_read_unlock(mm);
return buf - old_buf;
}
/**
* access_remote_vm - access another process' address space
* @mm: the mm_struct of the target address space
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
* @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*
* Return: number of bytes copied from source to destination.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
return __access_remote_vm(mm, addr, buf, len, gup_flags);
}
/*
* Access another process' address space.
* Source/target buffer must be kernel space,
* Do not walk the page table directly, use get_user_pages
*/
int access_process_vm(struct task_struct *tsk, unsigned long addr,
void *buf, int len, unsigned int gup_flags)
{
struct mm_struct *mm;
int ret;
mm = get_task_mm(tsk);
if (!mm)
return 0;
ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
mmput(mm);
return ret;
}
EXPORT_SYMBOL_GPL(access_process_vm);
/*
* Print the name of a VMA.
*/
void print_vma_addr(char *prefix, unsigned long ip)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
x86: fix "BUG: sleeping function called from invalid context" in print_vma_addr() Jiri Kosina reported the following deadlock scenario with show_unhandled_signals enabled: [ 68.379022] gnome-settings-[2941] trap int3 ip:3d2c840f34 sp:7fff36f5d100 error:0<3>BUG: sleeping function called from invalid context at kernel/rwsem.c:21 [ 68.379039] in_atomic():1, irqs_disabled():0 [ 68.379044] no locks held by gnome-settings-/2941. [ 68.379050] Pid: 2941, comm: gnome-settings- Not tainted 2.6.25-rc1 #30 [ 68.379054] [ 68.379056] Call Trace: [ 68.379061] <#DB> [<ffffffff81064883>] ? __debug_show_held_locks+0x13/0x30 [ 68.379109] [<ffffffff81036765>] __might_sleep+0xe5/0x110 [ 68.379123] [<ffffffff812f2240>] down_read+0x20/0x70 [ 68.379137] [<ffffffff8109cdca>] print_vma_addr+0x3a/0x110 [ 68.379152] [<ffffffff8100f435>] do_trap+0xf5/0x170 [ 68.379168] [<ffffffff8100f52b>] do_int3+0x7b/0xe0 [ 68.379180] [<ffffffff812f4a6f>] int3+0x9f/0xd0 [ 68.379203] <<EOE>> [ 68.379229] in libglib-2.0.so.0.1505.0[3d2c800000+dc000] and tracked it down to: commit 03252919b79891063cf99145612360efbdf9500b Author: Andi Kleen <ak@suse.de> Date: Wed Jan 30 13:33:18 2008 +0100 x86: print which shared library/executable faulted in segfault etc. messages the problem is that we call down_read() from an atomic context. Solve this by returning from print_vma_addr() if the preempt count is elevated. Update preempt_conditional_sti / preempt_conditional_cli to unconditionally lift the preempt count even on !CONFIG_PREEMPT. Reported-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-13 22:21:06 +03:00
/*
mm: do not rely on preempt_count in print_vma_addr The preempt count check on print_vma_addr has been added by commit e8bff74afbdb ("x86: fix "BUG: sleeping function called from invalid context" in print_vma_addr()") and it relied on the elevated preempt count from preempt_conditional_sti because preempt_count check doesn't work on non preemptive kernels by default. The code has evolved though and commit d99e1bd175f4 ("x86/entry/traps: Refactor preemption and interrupt flag handling") has replaced preempt_conditional_sti by an explicit preempt_disable which is noop on !PREEMPT so the check in print_vma_addr is broken. Fix the issue by using trylock on mmap_sem rather than chacking the preempt count. The allocation we are relying on has to be GFP_NOWAIT as well. There is a chance that we won't dump the vma state if the lock is contended or the memory short but this is acceptable outcome and much less fragile than the not working preemption check or tricks around it. Link: http://lkml.kernel.org/r/20171106134031.g6dbelg55mrbyc6i@dhcp22.suse.cz Fixes: d99e1bd175f4 ("x86/entry/traps: Refactor preemption and interrupt flag handling") Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Yang Shi <yang.s@alibaba-inc.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-16 04:38:59 +03:00
* we might be running from an atomic context so we cannot sleep
x86: fix "BUG: sleeping function called from invalid context" in print_vma_addr() Jiri Kosina reported the following deadlock scenario with show_unhandled_signals enabled: [ 68.379022] gnome-settings-[2941] trap int3 ip:3d2c840f34 sp:7fff36f5d100 error:0<3>BUG: sleeping function called from invalid context at kernel/rwsem.c:21 [ 68.379039] in_atomic():1, irqs_disabled():0 [ 68.379044] no locks held by gnome-settings-/2941. [ 68.379050] Pid: 2941, comm: gnome-settings- Not tainted 2.6.25-rc1 #30 [ 68.379054] [ 68.379056] Call Trace: [ 68.379061] <#DB> [<ffffffff81064883>] ? __debug_show_held_locks+0x13/0x30 [ 68.379109] [<ffffffff81036765>] __might_sleep+0xe5/0x110 [ 68.379123] [<ffffffff812f2240>] down_read+0x20/0x70 [ 68.379137] [<ffffffff8109cdca>] print_vma_addr+0x3a/0x110 [ 68.379152] [<ffffffff8100f435>] do_trap+0xf5/0x170 [ 68.379168] [<ffffffff8100f52b>] do_int3+0x7b/0xe0 [ 68.379180] [<ffffffff812f4a6f>] int3+0x9f/0xd0 [ 68.379203] <<EOE>> [ 68.379229] in libglib-2.0.so.0.1505.0[3d2c800000+dc000] and tracked it down to: commit 03252919b79891063cf99145612360efbdf9500b Author: Andi Kleen <ak@suse.de> Date: Wed Jan 30 13:33:18 2008 +0100 x86: print which shared library/executable faulted in segfault etc. messages the problem is that we call down_read() from an atomic context. Solve this by returning from print_vma_addr() if the preempt count is elevated. Update preempt_conditional_sti / preempt_conditional_cli to unconditionally lift the preempt count even on !CONFIG_PREEMPT. Reported-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-13 22:21:06 +03:00
*/
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
if (!mmap_read_trylock(mm))
x86: fix "BUG: sleeping function called from invalid context" in print_vma_addr() Jiri Kosina reported the following deadlock scenario with show_unhandled_signals enabled: [ 68.379022] gnome-settings-[2941] trap int3 ip:3d2c840f34 sp:7fff36f5d100 error:0<3>BUG: sleeping function called from invalid context at kernel/rwsem.c:21 [ 68.379039] in_atomic():1, irqs_disabled():0 [ 68.379044] no locks held by gnome-settings-/2941. [ 68.379050] Pid: 2941, comm: gnome-settings- Not tainted 2.6.25-rc1 #30 [ 68.379054] [ 68.379056] Call Trace: [ 68.379061] <#DB> [<ffffffff81064883>] ? __debug_show_held_locks+0x13/0x30 [ 68.379109] [<ffffffff81036765>] __might_sleep+0xe5/0x110 [ 68.379123] [<ffffffff812f2240>] down_read+0x20/0x70 [ 68.379137] [<ffffffff8109cdca>] print_vma_addr+0x3a/0x110 [ 68.379152] [<ffffffff8100f435>] do_trap+0xf5/0x170 [ 68.379168] [<ffffffff8100f52b>] do_int3+0x7b/0xe0 [ 68.379180] [<ffffffff812f4a6f>] int3+0x9f/0xd0 [ 68.379203] <<EOE>> [ 68.379229] in libglib-2.0.so.0.1505.0[3d2c800000+dc000] and tracked it down to: commit 03252919b79891063cf99145612360efbdf9500b Author: Andi Kleen <ak@suse.de> Date: Wed Jan 30 13:33:18 2008 +0100 x86: print which shared library/executable faulted in segfault etc. messages the problem is that we call down_read() from an atomic context. Solve this by returning from print_vma_addr() if the preempt count is elevated. Update preempt_conditional_sti / preempt_conditional_cli to unconditionally lift the preempt count even on !CONFIG_PREEMPT. Reported-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-02-13 22:21:06 +03:00
return;
vma = find_vma(mm, ip);
if (vma && vma->vm_file) {
struct file *f = vma->vm_file;
mm: do not rely on preempt_count in print_vma_addr The preempt count check on print_vma_addr has been added by commit e8bff74afbdb ("x86: fix "BUG: sleeping function called from invalid context" in print_vma_addr()") and it relied on the elevated preempt count from preempt_conditional_sti because preempt_count check doesn't work on non preemptive kernels by default. The code has evolved though and commit d99e1bd175f4 ("x86/entry/traps: Refactor preemption and interrupt flag handling") has replaced preempt_conditional_sti by an explicit preempt_disable which is noop on !PREEMPT so the check in print_vma_addr is broken. Fix the issue by using trylock on mmap_sem rather than chacking the preempt count. The allocation we are relying on has to be GFP_NOWAIT as well. There is a chance that we won't dump the vma state if the lock is contended or the memory short but this is acceptable outcome and much less fragile than the not working preemption check or tricks around it. Link: http://lkml.kernel.org/r/20171106134031.g6dbelg55mrbyc6i@dhcp22.suse.cz Fixes: d99e1bd175f4 ("x86/entry/traps: Refactor preemption and interrupt flag handling") Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Yang Shi <yang.s@alibaba-inc.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-16 04:38:59 +03:00
char *buf = (char *)__get_free_page(GFP_NOWAIT);
if (buf) {
char *p;
p = file_path(f, buf, PAGE_SIZE);
if (IS_ERR(p))
p = "?";
printk("%s%s[%lx+%lx]", prefix, kbasename(p),
vma->vm_start,
vma->vm_end - vma->vm_start);
free_page((unsigned long)buf);
}
}
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 07:33:25 +03:00
mmap_read_unlock(mm);
}
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 18:52:07 +03:00
void __might_fault(const char *file, int line)
{
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 18:52:07 +03:00
if (pagefault_disabled())
return;
__might_sleep(file, line);
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 18:52:07 +03:00
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
if (current->mm)
might_lock_read(&current->mm->mmap_lock);
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 18:52:07 +03:00
#endif
}
sched/preempt, mm/fault: Trigger might_sleep() in might_fault() with disabled pagefaults Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with pagefault_disable()") removed might_sleep() checks for all user access code (that uses might_fault()). The reason was to disable wrong "sleep in atomic" warnings in the following scenario: pagefault_disable() rc = copy_to_user(...) pagefault_enable() Which is valid, as pagefault_disable() increments the preempt counter and therefore disables the pagefault handler. copy_to_user() will not sleep and return an error code if a page is not available. However, as all might_sleep() checks are removed, CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: spin_lock(&lock); rc = copy_to_user(...) spin_unlock(&lock) If the kernel is compiled with preemption turned on, preempt_disable() will make in_atomic() detect disabled preemption. The fault handler would correctly never sleep on user access. However, with preemption turned off, preempt_disable() is usually a NOP (with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to detect disabled preemption nor disabled pagefaults. The fault handler could sleep. We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access functions again, otherwise we can end up with horrible deadlocks. Root of all evil is that pagefault_disable() acts almost as preempt_disable(), depending on preemption being turned on/off. As we now have pagefault_disabled(), we can use it to distinguish whether user acces functions might sleep. Convert might_fault() into a makro that calls __might_fault(), to allow proper file + line messages in case of a might_sleep() warning. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-3-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 18:52:07 +03:00
EXPORT_SYMBOL(__might_fault);
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/*
* Process all subpages of the specified huge page with the specified
* operation. The target subpage will be processed last to keep its
* cache lines hot.
*/
static inline void process_huge_page(
unsigned long addr_hint, unsigned int pages_per_huge_page,
void (*process_subpage)(unsigned long addr, int idx, void *arg),
void *arg)
{
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
int i, n, base, l;
unsigned long addr = addr_hint &
~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/* Process target subpage last to keep its cache lines hot */
might_sleep();
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
n = (addr_hint - addr) / PAGE_SIZE;
if (2 * n <= pages_per_huge_page) {
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/* If target subpage in first half of huge page */
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
base = 0;
l = n;
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/* Process subpages at the end of huge page */
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
cond_resched();
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
process_subpage(addr + i * PAGE_SIZE, i, arg);
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
}
} else {
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/* If target subpage in second half of huge page */
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
l = pages_per_huge_page - n;
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
/* Process subpages at the begin of huge page */
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
for (i = 0; i < base; i++) {
cond_resched();
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
process_subpage(addr + i * PAGE_SIZE, i, arg);
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
}
}
/*
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
* Process remaining subpages in left-right-left-right pattern
* towards the target subpage
mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen <andi.kleen@intel.com> Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Jan Kara <jack@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-07 02:25:04 +03:00
*/
for (i = 0; i < l; i++) {
int left_idx = base + i;
int right_idx = base + 2 * l - 1 - i;
cond_resched();
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg);
cond_resched();
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg);
}
}
mm, clear_huge_page: move order algorithm into a separate function Patch series "mm, huge page: Copy target sub-page last when copy huge page", v2. Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patchset. The patchset is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patchset, we have tested it with vm-scalability run on transparent huge page. With this patchset, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. This patch (of 4): In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. This optimization could be applied to copying huge page too with the same order algorithm. To avoid code duplication and reduce maintenance overhead, in this patch, the order algorithm is moved out of clear_huge_page() into a separate function: process_huge_page(). So that we can use it for copying huge page too. This will change the direct calls to clear_user_highpage() into the indirect calls. But with the proper inline support of the compilers, the indirect call will be optimized to be the direct call. Our tests show no performance change with the patch. This patch is a code cleanup without functionality change. Link: http://lkml.kernel.org/r/20180524005851.4079-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:46 +03:00
static void clear_gigantic_page(struct page *page,
unsigned long addr,
unsigned int pages_per_huge_page)
{
int i;
struct page *p = page;
might_sleep();
for (i = 0; i < pages_per_huge_page;
i++, p = mem_map_next(p, page, i)) {
cond_resched();
clear_user_highpage(p, addr + i * PAGE_SIZE);
}
}
static void clear_subpage(unsigned long addr, int idx, void *arg)
{
struct page *page = arg;
clear_user_highpage(page + idx, addr);
}
void clear_huge_page(struct page *page,
unsigned long addr_hint, unsigned int pages_per_huge_page)
{
unsigned long addr = addr_hint &
~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
clear_gigantic_page(page, addr, pages_per_huge_page);
return;
}
process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page);
}
static void copy_user_gigantic_page(struct page *dst, struct page *src,
unsigned long addr,
struct vm_area_struct *vma,
unsigned int pages_per_huge_page)
{
int i;
struct page *dst_base = dst;
struct page *src_base = src;
for (i = 0; i < pages_per_huge_page; ) {
cond_resched();
copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
i++;
dst = mem_map_next(dst, dst_base, i);
src = mem_map_next(src, src_base, i);
}
}
mm, huge page: copy target sub-page last when copy huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patch. Because we have put the order algorithm into a separate function, the implementation is quite simple. The patch is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patch, we tested it with vm-scalability run on transparent huge page. With this patch, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. Link: http://lkml.kernel.org/r/20180524005851.4079-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:49 +03:00
struct copy_subpage_arg {
struct page *dst;
struct page *src;
struct vm_area_struct *vma;
};
static void copy_subpage(unsigned long addr, int idx, void *arg)
{
struct copy_subpage_arg *copy_arg = arg;
copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx,
addr, copy_arg->vma);
}
void copy_user_huge_page(struct page *dst, struct page *src,
mm, huge page: copy target sub-page last when copy huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patch. Because we have put the order algorithm into a separate function, the implementation is quite simple. The patch is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patch, we tested it with vm-scalability run on transparent huge page. With this patch, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. Link: http://lkml.kernel.org/r/20180524005851.4079-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:49 +03:00
unsigned long addr_hint, struct vm_area_struct *vma,
unsigned int pages_per_huge_page)
{
mm, huge page: copy target sub-page last when copy huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patch. Because we have put the order algorithm into a separate function, the implementation is quite simple. The patch is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patch, we tested it with vm-scalability run on transparent huge page. With this patch, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. Link: http://lkml.kernel.org/r/20180524005851.4079-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:49 +03:00
unsigned long addr = addr_hint &
~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
struct copy_subpage_arg arg = {
.dst = dst,
.src = src,
.vma = vma,
};
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
copy_user_gigantic_page(dst, src, addr, vma,
pages_per_huge_page);
return;
}
mm, huge page: copy target sub-page last when copy huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when copying huge page on x86_64 platform, the cache footprint is 4M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache contention is heavy when copying the huge page, and we copy the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing copying the end of the huge page. And it is possible for the application to access the begin of the huge page after copying the huge page. In c79b57e462b5d ("mm: hugetlb: clear target sub-page last when clearing huge page"), to keep the cache lines of the target subpage hot, the order to clear the subpages in the huge page in clear_huge_page() is changed to clearing the subpage which is furthest from the target subpage firstly, and the target subpage last. The similar order changing helps huge page copying too. That is implemented in this patch. Because we have put the order algorithm into a separate function, the implementation is quite simple. The patch is a generic optimization which should benefit quite some workloads, not for a specific use case. To demonstrate the performance benefit of the patch, we tested it with vm-scalability run on transparent huge page. With this patch, the throughput increases ~16.6% in vm-scalability anon-cow-seq test case with 36 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case set /sys/kernel/mm/transparent_hugepage/enabled to be always, mmap() a big anonymous memory area and populate it, then forked 36 child processes, each writes to the anonymous memory area from the begin to the end, so cause copy on write. For each child process, other child processes could be seen as other workloads which generate heavy cache pressure. At the same time, the IPC (instruction per cycle) increased from 0.63 to 0.78, and the time spent in user space is reduced ~7.2%. Link: http://lkml.kernel.org/r/20180524005851.4079-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Shaohua Li <shli@fb.com> Cc: Christopher Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 01:45:49 +03:00
process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg);
}
long copy_huge_page_from_user(struct page *dst_page,
const void __user *usr_src,
unsigned int pages_per_huge_page,
bool allow_pagefault)
{
void *page_kaddr;
unsigned long i, rc = 0;
unsigned long ret_val = pages_per_huge_page * PAGE_SIZE;
struct page *subpage = dst_page;
for (i = 0; i < pages_per_huge_page;
i++, subpage = mem_map_next(subpage, dst_page, i)) {
if (allow_pagefault)
page_kaddr = kmap(subpage);
else
page_kaddr = kmap_atomic(subpage);
rc = copy_from_user(page_kaddr,
usr_src + i * PAGE_SIZE, PAGE_SIZE);
if (allow_pagefault)
kunmap(subpage);
else
kunmap_atomic(page_kaddr);
ret_val -= (PAGE_SIZE - rc);
if (rc)
break;
flush_dcache_page(subpage);
cond_resched();
}
return ret_val;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
static struct kmem_cache *page_ptl_cachep;
void __init ptlock_cache_init(void)
{
page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
SLAB_PANIC, NULL);
}
bool ptlock_alloc(struct page *page)
{
spinlock_t *ptl;
ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!ptl)
return false;
page->ptl = ptl;
return true;
}
void ptlock_free(struct page *page)
{
kmem_cache_free(page_ptl_cachep, page->ptl);
}
#endif