WSL2-Linux-Kernel/fs/proc/meminfo.c

232 строки
5.9 KiB
C
Исходник Обычный вид История

#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/mmzone.h>
#include <linux/proc_fs.h>
#include <linux/quicklist.h>
#include <linux/seq_file.h>
#include <linux/swap.h>
#include <linux/vmstat.h>
#include <linux/atomic.h>
#include <linux/vmalloc.h>
fs/proc/meminfo.c: include cma info in proc/meminfo This patch include CMA info (CMATotal, CMAFree) in /proc/meminfo. Currently, in a CMA enabled system, if somebody wants to know the total CMA size declared, there is no way to tell, other than the dmesg or /var/log/messages logs. With this patch we are showing the CMA info as part of meminfo, so that it can be determined at any point of time. This will be populated only when CMA is enabled. Below is the sample output from a ARM based device with RAM:512MB and CMA:16MB. MemTotal: 471172 kB MemFree: 111712 kB MemAvailable: 271172 kB . . . CmaTotal: 16384 kB CmaFree: 6144 kB This patch also fix below checkpatch errors that were found during these changes. ERROR: space required after that ',' (ctx:ExV) 199: FILE: fs/proc/meminfo.c:199: + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) ^ ERROR: space required after that ',' (ctx:ExV) 202: FILE: fs/proc/meminfo.c:202: + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * ^ ERROR: space required after that ',' (ctx:ExV) 206: FILE: fs/proc/meminfo.c:206: + ,K(totalcma_pages) ^ total: 3 errors, 0 warnings, 2 checks, 236 lines checked Signed-off-by: Pintu Kumar <pintu.k@samsung.com> Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:18 +03:00
#ifdef CONFIG_CMA
#include <linux/cma.h>
#endif
#include <asm/page.h>
#include <asm/pgtable.h>
#include "internal.h"
void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
{
}
static int meminfo_proc_show(struct seq_file *m, void *v)
{
struct sysinfo i;
unsigned long committed;
long cached;
long available;
unsigned long pagecache;
unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS];
struct zone *zone;
int lru;
/*
* display in kilobytes.
*/
#define K(x) ((x) << (PAGE_SHIFT - 10))
si_meminfo(&i);
si_swapinfo(&i);
mm: fix Committed_AS underflow on large NR_CPUS environment The Committed_AS field can underflow in certain situations: > # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c > 1 Committed_AS: 18446744073709323392 kB > 11 Committed_AS: 18446744073709455488 kB > 6 Committed_AS: 35136 kB > 5 Committed_AS: 18446744073709454400 kB > 7 Committed_AS: 35904 kB > 3 Committed_AS: 18446744073709453248 kB > 2 Committed_AS: 34752 kB > 9 Committed_AS: 18446744073709453248 kB > 8 Committed_AS: 34752 kB > 3 Committed_AS: 18446744073709320960 kB > 7 Committed_AS: 18446744073709454080 kB > 3 Committed_AS: 18446744073709320960 kB > 5 Committed_AS: 18446744073709454080 kB > 6 Committed_AS: 18446744073709320960 kB Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does not check for underflow. But NR_CPUS proportional isn't good calculation. In general, possibility of lock contention is proportional to the number of online cpus, not theorical maximum cpus (NR_CPUS). The current kernel has generic percpu-counter stuff. using it is right way. it makes code simplify and percpu_counter_read_positive() don't make underflow issue. Reported-by: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> [All kernel versions] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-05-01 02:08:51 +04:00
committed = percpu_counter_read_positive(&vm_committed_as);
cached = global_page_state(NR_FILE_PAGES) -
total_swapcache_pages() - i.bufferram;
if (cached < 0)
cached = 0;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
*
* Free memory cannot be taken below the low watermark, before the
* system starts swapping.
*/
available = i.freeram - wmark_low;
/*
* Not all the page cache can be freed, otherwise the system will
* start swapping. Assume at least half of the page cache, or the
* low watermark worth of cache, needs to stay.
*/
pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
pagecache -= min(pagecache / 2, wmark_low);
available += pagecache;
/*
* Part of the reclaimable slab consists of items that are in use,
* and cannot be freed. Cap this estimate at the low watermark.
*/
available += global_page_state(NR_SLAB_RECLAIMABLE) -
min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
if (available < 0)
available = 0;
/*
* Tagged format, for easy grepping and expansion.
*/
seq_printf(m,
"MemTotal: %8lu kB\n"
"MemFree: %8lu kB\n"
"MemAvailable: %8lu kB\n"
"Buffers: %8lu kB\n"
"Cached: %8lu kB\n"
"SwapCached: %8lu kB\n"
"Active: %8lu kB\n"
"Inactive: %8lu kB\n"
"Active(anon): %8lu kB\n"
"Inactive(anon): %8lu kB\n"
"Active(file): %8lu kB\n"
"Inactive(file): %8lu kB\n"
"Unevictable: %8lu kB\n"
"Mlocked: %8lu kB\n"
#ifdef CONFIG_HIGHMEM
"HighTotal: %8lu kB\n"
"HighFree: %8lu kB\n"
"LowTotal: %8lu kB\n"
"LowFree: %8lu kB\n"
NOMMU: Make VMAs per MM as for MMU-mode linux Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Mike Frysinger <vapier.adi@gmail.com> Acked-by: Paul Mundt <lethal@linux-sh.org>
2009-01-08 15:04:47 +03:00
#endif
#ifndef CONFIG_MMU
"MmapCopy: %8lu kB\n"
#endif
"SwapTotal: %8lu kB\n"
"SwapFree: %8lu kB\n"
"Dirty: %8lu kB\n"
"Writeback: %8lu kB\n"
"AnonPages: %8lu kB\n"
"Mapped: %8lu kB\n"
"Shmem: %8lu kB\n"
"Slab: %8lu kB\n"
"SReclaimable: %8lu kB\n"
"SUnreclaim: %8lu kB\n"
"KernelStack: %8lu kB\n"
"PageTables: %8lu kB\n"
#ifdef CONFIG_QUICKLIST
"Quicklists: %8lu kB\n"
#endif
"NFS_Unstable: %8lu kB\n"
"Bounce: %8lu kB\n"
"WritebackTmp: %8lu kB\n"
"CommitLimit: %8lu kB\n"
"Committed_AS: %8lu kB\n"
"VmallocTotal: %8lu kB\n"
"VmallocUsed: %8lu kB\n"
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 13:50:15 +04:00
"VmallocChunk: %8lu kB\n"
#ifdef CONFIG_MEMORY_FAILURE
"HardwareCorrupted: %5lu kB\n"
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
"AnonHugePages: %8lu kB\n"
fs/proc/meminfo.c: include cma info in proc/meminfo This patch include CMA info (CMATotal, CMAFree) in /proc/meminfo. Currently, in a CMA enabled system, if somebody wants to know the total CMA size declared, there is no way to tell, other than the dmesg or /var/log/messages logs. With this patch we are showing the CMA info as part of meminfo, so that it can be determined at any point of time. This will be populated only when CMA is enabled. Below is the sample output from a ARM based device with RAM:512MB and CMA:16MB. MemTotal: 471172 kB MemFree: 111712 kB MemAvailable: 271172 kB . . . CmaTotal: 16384 kB CmaFree: 6144 kB This patch also fix below checkpatch errors that were found during these changes. ERROR: space required after that ',' (ctx:ExV) 199: FILE: fs/proc/meminfo.c:199: + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) ^ ERROR: space required after that ',' (ctx:ExV) 202: FILE: fs/proc/meminfo.c:202: + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * ^ ERROR: space required after that ',' (ctx:ExV) 206: FILE: fs/proc/meminfo.c:206: + ,K(totalcma_pages) ^ total: 3 errors, 0 warnings, 2 checks, 236 lines checked Signed-off-by: Pintu Kumar <pintu.k@samsung.com> Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:18 +03:00
#endif
#ifdef CONFIG_CMA
"CmaTotal: %8lu kB\n"
"CmaFree: %8lu kB\n"
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 13:50:15 +04:00
#endif
,
K(i.totalram),
K(i.freeram),
K(available),
K(i.bufferram),
K(cached),
K(total_swapcache_pages()),
K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]),
K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
K(pages[LRU_ACTIVE_ANON]),
K(pages[LRU_INACTIVE_ANON]),
K(pages[LRU_ACTIVE_FILE]),
K(pages[LRU_INACTIVE_FILE]),
K(pages[LRU_UNEVICTABLE]),
K(global_page_state(NR_MLOCK)),
#ifdef CONFIG_HIGHMEM
K(i.totalhigh),
K(i.freehigh),
K(i.totalram-i.totalhigh),
K(i.freeram-i.freehigh),
NOMMU: Make VMAs per MM as for MMU-mode linux Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Mike Frysinger <vapier.adi@gmail.com> Acked-by: Paul Mundt <lethal@linux-sh.org>
2009-01-08 15:04:47 +03:00
#endif
#ifndef CONFIG_MMU
K((unsigned long) atomic_long_read(&mmap_pages_allocated)),
#endif
K(i.totalswap),
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
K(global_page_state(NR_ANON_PAGES)),
K(global_page_state(NR_FILE_MAPPED)),
K(i.sharedram),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_SLAB_RECLAIMABLE)),
K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
K(global_page_state(NR_PAGETABLE)),
#ifdef CONFIG_QUICKLIST
K(quicklist_total_size()),
#endif
K(global_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
K(global_page_state(NR_WRITEBACK_TEMP)),
K(vm_commit_limit()),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
mm: get rid of 'vmalloc_info' from /proc/meminfo It turns out that at least some versions of glibc end up reading /proc/meminfo at every single startup, because glibc wants to know the amount of memory the machine has. And while that's arguably insane, it's just how things are. And it turns out that it's not all that expensive most of the time, but the vmalloc information statistics (amount of virtual memory used in the vmalloc space, and the biggest remaining chunk) can be rather expensive to compute. The 'get_vmalloc_info()' function actually showed up on my profiles as 4% of the CPU usage of "make test" in the git source repository, because the git tests are lots of very short-lived shell-scripts etc. It turns out that apparently this same silly vmalloc info gathering shows up on the facebook servers too, according to Dave Jones. So it's not just "make test" for git. We had two patches to just cache the information (one by me, one by Ingo) to mitigate this issue, but the whole vmalloc information of of rather dubious value to begin with, and people who *actually* want to know what the situation is wrt the vmalloc area should just look at the much more complete /proc/vmallocinfo instead. In fact, according to my testing - and perhaps more importantly, according to that big search engine in the sky: Google - there is nothing out there that actually cares about those two expensive fields: VmallocUsed and VmallocChunk. So let's try to just remove them entirely. Actually, this just removes the computation and reports the numbers as zero for now, just to try to be minimally intrusive. If this breaks anything, we'll obviously have to re-introduce the code to compute this all and add the caching patches on top. But if given the option, I'd really prefer to just remove this bad idea entirely rather than add even more code to work around our historical mistake that likely nobody really cares about. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-02 04:09:15 +03:00
0ul, // used to be vmalloc 'used'
0ul // used to be vmalloc 'largest_chunk'
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 13:50:15 +04:00
#ifdef CONFIG_MEMORY_FAILURE
fs/proc/meminfo.c: include cma info in proc/meminfo This patch include CMA info (CMATotal, CMAFree) in /proc/meminfo. Currently, in a CMA enabled system, if somebody wants to know the total CMA size declared, there is no way to tell, other than the dmesg or /var/log/messages logs. With this patch we are showing the CMA info as part of meminfo, so that it can be determined at any point of time. This will be populated only when CMA is enabled. Below is the sample output from a ARM based device with RAM:512MB and CMA:16MB. MemTotal: 471172 kB MemFree: 111712 kB MemAvailable: 271172 kB . . . CmaTotal: 16384 kB CmaFree: 6144 kB This patch also fix below checkpatch errors that were found during these changes. ERROR: space required after that ',' (ctx:ExV) 199: FILE: fs/proc/meminfo.c:199: + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) ^ ERROR: space required after that ',' (ctx:ExV) 202: FILE: fs/proc/meminfo.c:202: + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * ^ ERROR: space required after that ',' (ctx:ExV) 206: FILE: fs/proc/meminfo.c:206: + ,K(totalcma_pages) ^ total: 3 errors, 0 warnings, 2 checks, 236 lines checked Signed-off-by: Pintu Kumar <pintu.k@samsung.com> Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:18 +03:00
, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
fs/proc/meminfo.c: include cma info in proc/meminfo This patch include CMA info (CMATotal, CMAFree) in /proc/meminfo. Currently, in a CMA enabled system, if somebody wants to know the total CMA size declared, there is no way to tell, other than the dmesg or /var/log/messages logs. With this patch we are showing the CMA info as part of meminfo, so that it can be determined at any point of time. This will be populated only when CMA is enabled. Below is the sample output from a ARM based device with RAM:512MB and CMA:16MB. MemTotal: 471172 kB MemFree: 111712 kB MemAvailable: 271172 kB . . . CmaTotal: 16384 kB CmaFree: 6144 kB This patch also fix below checkpatch errors that were found during these changes. ERROR: space required after that ',' (ctx:ExV) 199: FILE: fs/proc/meminfo.c:199: + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) ^ ERROR: space required after that ',' (ctx:ExV) 202: FILE: fs/proc/meminfo.c:202: + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * ^ ERROR: space required after that ',' (ctx:ExV) 206: FILE: fs/proc/meminfo.c:206: + ,K(totalcma_pages) ^ total: 3 errors, 0 warnings, 2 checks, 236 lines checked Signed-off-by: Pintu Kumar <pintu.k@samsung.com> Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:18 +03:00
, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
HPAGE_PMD_NR)
fs/proc/meminfo.c: include cma info in proc/meminfo This patch include CMA info (CMATotal, CMAFree) in /proc/meminfo. Currently, in a CMA enabled system, if somebody wants to know the total CMA size declared, there is no way to tell, other than the dmesg or /var/log/messages logs. With this patch we are showing the CMA info as part of meminfo, so that it can be determined at any point of time. This will be populated only when CMA is enabled. Below is the sample output from a ARM based device with RAM:512MB and CMA:16MB. MemTotal: 471172 kB MemFree: 111712 kB MemAvailable: 271172 kB . . . CmaTotal: 16384 kB CmaFree: 6144 kB This patch also fix below checkpatch errors that were found during these changes. ERROR: space required after that ',' (ctx:ExV) 199: FILE: fs/proc/meminfo.c:199: + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) ^ ERROR: space required after that ',' (ctx:ExV) 202: FILE: fs/proc/meminfo.c:202: + ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * ^ ERROR: space required after that ',' (ctx:ExV) 206: FILE: fs/proc/meminfo.c:206: + ,K(totalcma_pages) ^ total: 3 errors, 0 warnings, 2 checks, 236 lines checked Signed-off-by: Pintu Kumar <pintu.k@samsung.com> Signed-off-by: Vishnu Pratap Singh <vishnu.ps@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:18 +03:00
#endif
#ifdef CONFIG_CMA
, K(totalcma_pages)
, K(global_page_state(NR_FREE_CMA_PAGES))
HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 13:50:15 +04:00
#endif
);
hugetlb_report_meminfo(m);
arch_report_meminfo(m);
return 0;
#undef K
}
static int meminfo_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, meminfo_proc_show, NULL);
}
static const struct file_operations meminfo_proc_fops = {
.open = meminfo_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init proc_meminfo_init(void)
{
proc_create("meminfo", 0, NULL, &meminfo_proc_fops);
return 0;
}
fs_initcall(proc_meminfo_init);