The UML port uses 4 and 5 level fixups to support higher level page
table directories in the generic VM code.
Implement primitives necessary for the 4th level folding, add walks of
p4d level where appropriate and drop usage of __ARCH_USE_5LEVEL_HACK.
Link: http://lkml.kernel.org/r/1572938135-31886-13-git-send-email-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Anatoly Pugachev <matorola@gmail.com>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Helge Deller <deller@gmx.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Mark Salter <msalter@redhat.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Peter Rosin <peda@axentia.se>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rolf Eike Beer <eike-kernel@sf-tec.de>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Sam Creasey <sammy@sammy.net>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Convert files to use SPDX header. All files are licensed under the
GPLv2.
Signed-off-by: Alex Dewar <alex.dewar@gmx.co.uk>
Signed-off-by: Richard Weinberger <richard@nod.at>
All of the remaining callers pass current into force_sig so
remove the task parameter to make this obvious and to make
misuse more difficult in the future.
This also makes it clear force_sig passes current into force_sig_info.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
When UML handles a fork the page tables need to be brought up
to date. That was done using brute force - full tlb flush.
This is actually unnecessary, because the mapped-in mappings are
all correct and the only mappings which need to be updated
after a flush are any unmaps (so that paging works) as well as
any pending protection changes.
This optimization squeezes out up to 3% from a full kernel rebuild
time under memory pressure.
Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Skip TLB flushing for all cases where it is not needed, not
just flush_tlb_mm_range
Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Make the code to merge mmap/munmap/mprotect operations in tlb.c
common for userspace and kernel. Kernel tlb operations can now
be merged as well.
Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
We are going to split <linux/sched/signal.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.
Create a trivial placeholder <linux/sched/signal.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Once x86 exports its do_signal(), the prototypes will clash.
Fix the clash and also improve the code a bit: remove the
unnecessary kern_do_signal() indirection. This allows
interrupt_end() to share the 'regs' parameter calculation.
Also remove the unused return code to match x86.
Minimally build and boot tested.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Weinberger <richard.weinberger@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/67c57eac09a589bac3c6c5ff22f9623ec55a184a.1435952415.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If do_ops() fails we have to release current->mm->mmap_sem
otherwise the failing task will never terminate.
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
Trinity discovered an execution path such that a task
can unmap his stub page.
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Richard Weinberger <richard@nod.at>
In case we encounter a bad operation in do_ops() something is really
broken and it's better to BUG().
Signed-off-by: Richard Weinberger <richard@nod.at>
ksyms.c is down to the stuff defined in various USER_OBJS
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Richard Weinberger <richard@nod.at>
Joe Perches noticed some printks in smp.c that needed fixing.
While I was in there, I did the usual tidying in arch/um/kernel, which
should be fairly style-clean at this point:
copyright updates
emacs formatting comments removal
include tidying
style fixes
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Customize the hooks in tlb.h to optimize TLB flushing some more.
Add start and end fields to tlb_gather_mmu, which are used to limit
the address space range scanned when a region is unmapped.
The interfaces which just free page tables, without actually changing
mappings, don't need to cause a TLB flush.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Some 64-bit tlb fixes -
moved pmd_page_vaddr to pgtable.h since it's the same for both
2-level and 3-level page tables
fixed a bogus cast on pud_page_vaddr
made the address checking in update_*_range more careful
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Give the stubs a VMA. This allows the removal of a truly nasty kludge to make
sure that mm->nr_ptes was correct in exit_mmap. The underlying problem was
always that the stubs, which have ptes, and thus allocated a page table,
weren't covered by a VMA.
This patch fixes that by using install_special_mapping in arch_dup_mmap and
activate_context to create the VMA. The stubs have to be moved, since
shift_arg_pages seems to assume that the stack is the only VMA present at that
point during exec, and uses vma_adjust to fiddle its VMA. However, that
extends the stub VMA by the amount removed from the stack VMA.
To avoid this problem, the stubs were moved to a different fixed location at
the start of the address space.
The init_stub_pte calls were moved from init_new_context to arch_dup_mmap
because I was occasionally seeing arch_dup_mmap not being called, causing
exit_mmap to die. Rather than figure out what was really happening, I decided
it was cleaner to just move the calls so that there's no doubt that both the
pte and VMA creation happen, no matter what. arch_exit_mmap is used to clear
the stub ptes at exit time.
The STUB_* constants in as-layout.h no longer depend on UM_TASK_SIZE, that
that definition is removed, along with the comments complaining about gcc.
Because the stubs are no longer at the top of the address space, some care is
needed while flushing TLBs. update_pte_range checks for addresses in the stub
range and skips them. flush_thread now issues two unmaps, one for the range
before STUB_START and one for the range after STUB_END.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Clean up the calculation and use of the usable address space size on the host.
task_size is gone, replaced with TASK_SIZE, which is calculated from
CONFIG_TOP_ADDR. get_kmem_end and set_task_sizes_skas are also gone.
host_task_size, which refers to the entire address space usable by the UML
kernel and which may be larger than the address space usable by a UML process,
since that has to end on a pgdir boundary, is replaced by CONFIG_TOP_ADDR.
STACK_TOP is now TASK_SIZE minus the two stub pages.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Untangle UML headers somewhat and add some includes where they were
needed explicitly, but gotten accidentally via some other header.
arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no
fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and
archsetjmp.h, because it needs jmp_buf.
pmd_alloc_one is uninlined because it needs mm_struct, and that's
inconvenient to provide in asm-um/pgtable-3level.h.
elf_core_copy_fpregs is also uninlined from elf-i386.h and
elf-x86_64.h, which duplicated the code anyway, to
arch/um/kernel/process.c, so that the reference to current_thread
doesn't pull sched.h or anything related into asm/elf.h.
arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and
arch/um/kernel/skas/uaccess.c got sched.h because they dereference
task_structs. Its includes of linux and asm headers got turned from
"" to <>.
arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno
constants.
asm/elf-i386 gets asm/user.h because it needs user_regs_struct.
asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and
system.h for BUG_ON.
asm/pgtable doesn't need sched.h.
asm/processor-generic.h defined mm_segment_t, but didn't use it. So,
that definition is moved to uaccess.h, which defines a bunch of
mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and
includes uaccess.h, which causes a recursion. So, the definition is
placed above the include of thread_info. in uaccess.h. thread_info.h
also gets page.h because it needs PAGE_SIZE.
ObCheckpatchViolationJustification - I'm not adding a typedef; I'm
moving mm_segment_t from one place to another.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The calculation of CONFIG_STUB_CODE and CONFIG_STUB_DATA didn't take into
account anything but 3G/1G and 2G/2G, leaving the other vmsplits out in the
cold.
I'd rather not duplicate the four known host vmsplit cases for each of these
symbols. I'd also like to calculate them based on the highest userspace
address.
The Kconfig language seems not to allow calculation of hex constants, so I
moved this to as-layout.h. CONFIG_STUB_CODE, CONFIG_STUB_DATA, and
CONFIG_STUB_START are now gone. In their place are STUB_CODE, STUB_DATA, and
STUB_START in as-layout.h.
i386 and x86_64 seem to differ as to whether an unadorned constant is an int
or a long, so I cast them to unsigned long so they can be printed
consistently. However, they are also used in stub.S, where C types don't work
so well. So, there are ASM_ versions of these constants for use in stub.S. I
also ifdef-ed the non-asm-friendly portion of as-layout.h.
With this in place, most of the rest of this patch is changing CONFIG_STUB_*
to STUB_*, except in stub.S, where they are changed to ASM_STUB_*.
defconfig has the old symbols deleted.
I also print these addresses out in case there is any problem mapping them on
the host.
The two stub.S files had some trailing whitespace, so that is cleaned up here.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tidy the tlb flushing code.
With tt mode gone, there is no reason to have the capability to have
called directly from do_mmap, do_mprotect, and do_munmap, rather than
calling a function pointer that it is given.
There was a large amount of data that was passed from function to
function, being used at the lowest level, without being changed. This
stuff is now encapsulated in a structure which is initialized at the
top layer and passed down. This simplifies the code, reduces the
amount of code needed to pass the parameters around, and saves on
stack space.
A somewhat more subtle change is the meaning of the current operation
index. It used to start at -1, being pre-incremented when adding an
operation. It now starts at 0, being post-incremented, with
associated adjustments of +/- 1 on comparisons.
In addition, tlb.h contained a couple of declarations which had no
users outside of tlb.c, so they could be moved or deleted.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch folds mmu_context_skas into struct mm_context, changing all users
of these structures as needed.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Formatting changes in the files which have been changed in the course
of folding foo_skas functions into their callers. These include:
copyright updates
header file trimming
style fixes
adding severity to printks
These changes should be entirely non-functional.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch makes a number of simplifications enabled by the removal of
CHOOSE_MODE. There were lots of functions that looked like
int foo(args){
foo_skas(args);
}
The bodies of foo_skas are now folded into foo, and their declarations (and
sometimes entire header files) are deleted.
In addition, the union uml_pt_regs, which was a union between the tt and skas
register formats, is now a struct, with the tt-mode arm of the union being
removed.
It turns out that usr2_handler was unused, so it is gone.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The next stage after removing code which depends on CONFIG_MODE_TT is removing
the CHOOSE_MODE abstraction, which provided both compile-time and run-time
branching to either tt-mode or skas-mode code.
This patch removes choose-mode.h and all inclusions of it, and replaces all
CHOOSE_MODE invocations with the skas branch. This leaves a number of trivial
functions which will be dealt with in a later patch.
There are some changes in the uaccess and tls support which go somewhat beyond
this and eliminate some of the now-redundant functions.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
More trimming of the page fault path.
Permissions are passed around in a single int rather than one bit per
int. The permission values are copied from libc so that they can be
passed to mmap and mprotect without any further conversion.
The register sets used by do_syscall_stub and copy_context_skas0 are
initialized once, at boot time, rather than once per call.
wait_stub_done checks whether it is getting the signals it expects by
comparing the wait status to a mask containing bits for the signals of
interest rather than comparing individually to the signal numbers. It
also has one check for a wait failure instead of two. The caller is
expected to do the initial continue of the stub. This gets rid of an
argument and some logic. The fname argument is gone, as that can be
had from a stack trace.
user_signal() is collapsed into userspace() as it is basically one or
two lines of code afterwards.
The physical memory remapping stuff is gone, as it is unused.
flush_tlb_page is inlined.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I missed removing another piece of debugging in an earlier patch.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Give the page fault code a specialized path. There is only one page to look
at, so there's no point in going into the general page table walking code.
There's only going to be one host operation, so there are no opportunities for
merging. So, we go straight to the pte we want, figure out what needs doing,
and do it.
While I was in here, I fixed the wart where the address passed to unmap was a
void *, but an unsigned long to map and protect.
This gives me just under 10% on a kernel build.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I accidentally left the remnants of some debugging in an earlier patch.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The previous page table walking code was horribly inefficient. This patch
replaces it with code taken from elsewhere in the kernel.
Forking from bash is now ~5% faster and page faults are handled ~10% faster.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
user_util.h isn't needed any more, so delete it and remove all includes of it.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch moves all the the symbols defined in um_arch.c, which are mostly
boundaries between different parts of the UML kernel address space, to a new
header, as-layout.h. There are also a few things here which aren't really
related to address space layout, but which don't really have a better place to
go.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
arch/um/kernel/tlb.c had some pretty serious whitespace problems. I also
fixed some returns.
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There were a bunch of missed ARRAY_SIZE opportunities.
Also, some formatting fixes in the affected areas of code.
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Avoid setting w = 0 twice. Spotted this (trivial) thing which is needed for
another patch.
Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The serial UML OS-abstraction layer patch (um/kernel dir).
This moves all system calls from mem_user.c and tempfile.c files under
os-Linux dir.
Signed-off-by: Gennady Sharapov <Gennady.V.Sharapov@intel.com>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Cc: Paolo Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Change syscall-stub's data to include a "expected retval".
Stub now checks syscalls retval and aborts execution of syscall list, if
retval != expected retval.
run_syscall_stub prints the data of the failed syscall, using the data pointer
and retval written by the stub to the beginning of the stack.
one_syscall_stub is removed, to simplify code, because only some instructions
are saved by one_syscall_stub, no host-syscall.
Using the stub with additional data (modify_ldt via stub)
is prepared also.
Signed-off-by: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This adds VM op batching to skas0. Rather than having a context switch to and
from the userspace stub for each address space change, we write a number of
operations to the stub data page and invoke a different stub which loops over
them and executes them all in one go.
The operations are stored as [ system call number, arg1, arg2, ... ] tuples.
The set is terminated by a system call number of 0. Single operations, i.e.
page faults, are handled in the old way, since that is slightly more
efficient.
For a kernel build, a minority (~1/4) of the operations are part of a set.
These sets averaged ~100 in length, so for this quarter, the context switching
overhead is greatly reduced.
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Cc: Paolo Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
UML has had two modes of operation - an insecure, slow mode (tt mode) in
which the kernel is mapped into every process address space which requires
no host kernel modifications, and a secure, faster mode (skas mode) in
which the UML kernel is in a separate host address space, which requires a
patch to the host kernel.
This patch implements something very close to skas mode for hosts which
don't support skas - I'm calling this skas0. It provides the security of
the skas host patch, and some of the performance gains.
The two main things that are provided by the skas patch, /proc/mm and
PTRACE_FAULTINFO, are implemented in a way that require no host patch.
For the remote address space changing stuff (mmap, munmap, and mprotect),
we set aside two pages in the process above its stack, one of which
contains a little bit of code which can call mmap et al.
To update the address space, the system call information (system call
number and arguments) are written to the stub page above the code. The
%esp is set to the beginning of the data, the %eip is set the the start of
the stub, and it repeatedly pops the information into its registers and
makes the system call until it sees a system call number of zero. This is
to amortize the cost of the context switch across multiple address space
updates.
When the updates are done, it SIGSTOPs itself, and the kernel process
continues what it was doing.
For a PTRACE_FAULTINFO replacement, we set up a SIGSEGV handler in the
child, and let it handle segfaults rather than nullifying them. The
handler is in the same page as the mmap stub. The second page is used as
the stack. The handler reads cr2 and err from the sigcontext, sticks them
at the base of the stack in a faultinfo struct, and SIGSTOPs itself. The
kernel then reads the faultinfo and handles the fault.
A complication on x86_64 is that this involves resetting the registers to
the segfault values when the process is inside the kill system call. This
breaks on x86_64 because %rcx will contain %rip because you tell SYSRET
where to return to by putting the value in %rcx. So, this corrupts $rcx on
return from the segfault. To work around this, I added an
arch_finish_segv, which on x86 does nothing, but which on x86_64 ptraces
the child back through the sigreturn. This causes %rcx to be restored by
sigreturn and avoids the corruption. Ultimately, I think I will replace
this with the trick of having it send itself a blocked signal which will be
unblocked by the sigreturn. This will allow it to be stopped just after
the sigreturn, and PTRACE_SYSCALLed without all the back-and-forth of
PTRACE_SYSCALLing it through sigreturn.
This runs on a stock host, so theoretically (and hopefully), tt mode isn't
needed any more. We need to make sure that this is better in every way
than tt mode, though. I'm concerned about the speed of address space
updates and page fault handling, since they involve extra round-trips to
the child. We can amortize the round-trip cost for large address space
updates by writing all of the operations to the data page and having the
child execute them all at the same time. This will help fork and exec, but
not page faults, since they involve only one page.
I can't think of any way to help page faults, except to add something like
PTRACE_FAULTINFO to the host. There is PTRACE_SIGINFO, but UML doesn't use
siginfo for SIGSEGV (or anything else) because there isn't enough
information in the siginfo struct to handle page faults (the faulting
operation type is missing). Adding that would make PTRACE_SIGINFO a usable
equivalent to PTRACE_FAULTINFO.
As for the code itself:
- The system call stub is in arch/um/kernel/sys-$(SUBARCH)/stub.S. It is
put in its own section of the binary along with stub_segv_handler in
arch/um/kernel/skas/process.c. This is manipulated with run_syscall_stub
in arch/um/kernel/skas/mem_user.c. syscall_stub will execute any system
call at all, but it's only used for mmap, munmap, and mprotect.
- The x86_64 stub calls sigreturn by hand rather than allowing the normal
sigreturn to happen, because the normal sigreturn is a SA_RESTORER in
UML's address space provided by libc. Needless to say, this is not
available in the child's address space. Also, it does a couple of odd
pops before that which restore the stack to the state it was in at the
time the signal handler was called.
- There is a new field in the arch mmu_context, which is now a union.
This is the pid to be manipulated rather than the /proc/mm file
descriptor. Code which deals with this now checks proc_mm to see whether
it should use the usual skas code or the new code.
- userspace_tramp is now used to create a new host process for every UML
process, rather than one per UML processor. It checks proc_mm and
ptrace_faultinfo to decide whether to map in the pages above its stack.
- start_userspace now makes CLONE_VM conditional on proc_mm since we need
separate address spaces now.
- switch_mm_skas now just sets userspace_pid[0] to the new pid rather
than PTRACE_SWITCH_MM. There is an addition to userspace which updates
its idea of the pid being manipulated each time around the loop. This is
important on exec, when the pid will change underneath userspace().
- The stub page has a pte, but it can't be mapped in using tlb_flush
because it is part of tlb_flush. This is why it's required for it to be
mapped in by userspace_tramp.
Other random things:
- The stub section in uml.lds.S is page aligned. This page is written
out to the backing vm file in setup_physmem because it is mapped from
there into user processes.
- There's some confusion with TASK_SIZE now that there are a couple of
extra pages that the process can't use. TASK_SIZE is considered by the
elf code to be the usable process memory, which is reasonable, so it is
decreased by two pages. This confuses the definition of
USER_PGDS_IN_LAST_PML4, making it too small because of the rounding down
of the uneven division. So we round it to the nearest PGDIR_SIZE rather
than the lower one.
- I added a missing PT_SYSCALL_ARG6_OFFSET macro.
- um_mmu.h was made into a userspace-usable file.
- proc_mm and ptrace_faultinfo are globals which say whether the host
supports these features.
- There is a bad interaction between the mm.nr_ptes check at the end of
exit_mmap, stack randomization, and skas0. exit_mmap will stop freeing
pages at the PGDIR_SIZE boundary after the last vma. If the stack isn't
on the last page table page, the last pte page won't be freed, as it
should be since the stub ptes are there, and exit_mmap will BUG because
there is an unfreed page. To get around this, TASK_SIZE is set to the
next lowest PGDIR_SIZE boundary and mm->nr_ptes is decremented after the
calls to init_stub_pte. This ensures that we know the process stack (and
all other process mappings) will be below the top page table page, and
thus we know that mm->nr_ptes will be one too many, and can be
decremented.
Things that need fixing:
- We may need better assurrences that the stub code is PIC.
- The stub pte is set up in init_new_context_skas.
- alloc_pgdir is probably the right place.
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Mike Rapoport
Alex Dewar
Eric W. Biederman
Anton Ivanov
Ingo Molnar
Richard Weinberger
Al Viro
Al Viro
Jeff Dike
Paolo 'Blaisorblade' Giarrusso
Bodo Stroesser
Linus Torvalds