2014-11-06 15:19:44 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2009 Wind River Systems Inc
|
|
|
|
* Implemented by fredrik.markstrom@gmail.com and ivarholmqvist@gmail.com
|
|
|
|
*
|
|
|
|
* based on arch/mips/mm/fault.c which is:
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995-2000 Ralf Baechle
|
|
|
|
*
|
|
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
|
|
* for more details.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/signal.h>
|
|
|
|
#include <linux/sched.h>
|
2017-02-09 01:51:35 +08:00
|
|
|
#include <linux/sched/debug.h>
|
2014-11-06 15:19:44 +08:00
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/mm.h>
|
2017-01-10 22:51:08 +08:00
|
|
|
#include <linux/extable.h>
|
2014-11-06 15:19:44 +08:00
|
|
|
#include <linux/uaccess.h>
|
2020-08-12 09:38:22 +08:00
|
|
|
#include <linux/perf_event.h>
|
2014-11-06 15:19:44 +08:00
|
|
|
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/traps.h>
|
|
|
|
|
|
|
|
#define EXC_SUPERV_INSN_ACCESS 9 /* Supervisor only instruction address */
|
|
|
|
#define EXC_SUPERV_DATA_ACCESS 11 /* Supervisor only data address */
|
|
|
|
#define EXC_X_PROTECTION_FAULT 13 /* TLB permission violation (x) */
|
|
|
|
#define EXC_R_PROTECTION_FAULT 14 /* TLB permission violation (r) */
|
|
|
|
#define EXC_W_PROTECTION_FAULT 15 /* TLB permission violation (w) */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This routine handles page faults. It determines the address,
|
|
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
|
|
* routines.
|
|
|
|
*/
|
|
|
|
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
|
|
|
|
unsigned long address)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma = NULL;
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
struct mm_struct *mm = tsk->mm;
|
|
|
|
int code = SEGV_MAPERR;
|
2018-08-18 06:44:47 +08:00
|
|
|
vm_fault_t fault;
|
2020-04-02 12:08:37 +08:00
|
|
|
unsigned int flags = FAULT_FLAG_DEFAULT;
|
2014-11-06 15:19:44 +08:00
|
|
|
|
|
|
|
cause >>= 2;
|
|
|
|
|
|
|
|
/* Restart the instruction */
|
|
|
|
regs->ea -= 4;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We fault-in kernel-space virtual memory on-demand. The
|
|
|
|
* 'reference' page table is init_mm.pgd.
|
|
|
|
*
|
|
|
|
* NOTE! We MUST NOT take any locks for this case. We may
|
|
|
|
* be in an interrupt or a critical region, and should
|
|
|
|
* only copy the information from the master page table,
|
|
|
|
* nothing more.
|
|
|
|
*/
|
|
|
|
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END)) {
|
|
|
|
if (user_mode(regs))
|
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
else
|
|
|
|
goto vmalloc_fault;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(address >= TASK_SIZE))
|
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're in an interrupt or have no user
|
|
|
|
* context, we must not take the fault..
|
|
|
|
*/
|
2015-05-11 23:52:11 +08:00
|
|
|
if (faulthandler_disabled() || !mm)
|
2014-11-06 15:19:44 +08:00
|
|
|
goto bad_area_nosemaphore;
|
|
|
|
|
|
|
|
if (user_mode(regs))
|
|
|
|
flags |= FAULT_FLAG_USER;
|
|
|
|
|
2020-08-12 09:38:22 +08:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
|
|
|
|
2020-06-09 12:33:25 +08:00
|
|
|
if (!mmap_read_trylock(mm)) {
|
2014-11-06 15:19:44 +08:00
|
|
|
if (!user_mode(regs) && !search_exception_tables(regs->ea))
|
|
|
|
goto bad_area_nosemaphore;
|
2015-02-09 18:11:29 +08:00
|
|
|
retry:
|
2020-06-09 12:33:25 +08:00
|
|
|
mmap_read_lock(mm);
|
2014-11-06 15:19:44 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
vma = find_vma(mm, address);
|
|
|
|
if (!vma)
|
|
|
|
goto bad_area;
|
|
|
|
if (vma->vm_start <= address)
|
|
|
|
goto good_area;
|
|
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
|
|
goto bad_area;
|
|
|
|
if (expand_stack(vma, address))
|
|
|
|
goto bad_area;
|
|
|
|
/*
|
|
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
|
|
* we can handle it..
|
|
|
|
*/
|
|
|
|
good_area:
|
|
|
|
code = SEGV_ACCERR;
|
|
|
|
|
|
|
|
switch (cause) {
|
|
|
|
case EXC_SUPERV_INSN_ACCESS:
|
|
|
|
goto bad_area;
|
|
|
|
case EXC_SUPERV_DATA_ACCESS:
|
|
|
|
goto bad_area;
|
|
|
|
case EXC_X_PROTECTION_FAULT:
|
|
|
|
if (!(vma->vm_flags & VM_EXEC))
|
|
|
|
goto bad_area;
|
|
|
|
break;
|
|
|
|
case EXC_R_PROTECTION_FAULT:
|
|
|
|
if (!(vma->vm_flags & VM_READ))
|
|
|
|
goto bad_area;
|
|
|
|
break;
|
|
|
|
case EXC_W_PROTECTION_FAULT:
|
|
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
|
|
goto bad_area;
|
|
|
|
flags = FAULT_FLAG_WRITE;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If for any reason at all we couldn't handle the fault,
|
|
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
|
|
* the fault.
|
|
|
|
*/
|
2020-08-12 09:38:22 +08:00
|
|
|
fault = handle_mm_fault(vma, address, flags, regs);
|
2015-02-09 18:11:29 +08:00
|
|
|
|
2020-04-02 12:08:06 +08:00
|
|
|
if (fault_signal_pending(fault, regs))
|
2015-02-09 18:11:29 +08:00
|
|
|
return;
|
|
|
|
|
mm: avoid unnecessary page fault retires on shared memory types
I observed that for each of the shared file-backed page faults, we're very
likely to retry one more time for the 1st write fault upon no page. It's
because we'll need to release the mmap lock for dirty rate limit purpose
with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()).
Then after that throttling we return VM_FAULT_RETRY.
We did that probably because VM_FAULT_RETRY is the only way we can return
to the fault handler at that time telling it we've released the mmap lock.
However that's not ideal because it's very likely the fault does not need
to be retried at all since the pgtable was well installed before the
throttling, so the next continuous fault (including taking mmap read lock,
walk the pgtable, etc.) could be in most cases unnecessary.
It's not only slowing down page faults for shared file-backed, but also add
more mmap lock contention which is in most cases not needed at all.
To observe this, one could try to write to some shmem page and look at
"pgfault" value in /proc/vmstat, then we should expect 2 counts for each
shmem write simply because we retried, and vm event "pgfault" will capture
that.
To make it more efficient, add a new VM_FAULT_COMPLETED return code just to
show that we've completed the whole fault and released the lock. It's also
a hint that we should very possibly not need another fault immediately on
this page because we've just completed it.
This patch provides a ~12% perf boost on my aarch64 test VM with a simple
program sequentially dirtying 400MB shmem file being mmap()ed and these are
the time it needs:
Before: 650.980 ms (+-1.94%)
After: 569.396 ms (+-1.38%)
I believe it could help more than that.
We need some special care on GUP and the s390 pgfault handler (for gmap
code before returning from pgfault), the rest changes in the page fault
handlers should be relatively straightforward.
Another thing to mention is that mm_account_fault() does take this new
fault as a generic fault to be accounted, unlike VM_FAULT_RETRY.
I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do
not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping
them as-is.
Link: https://lkml.kernel.org/r/20220530183450.42886-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vineet Gupta <vgupta@kernel.org>
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> [arm part]
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Brian Cain <bcain@quicinc.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Richard Weinberger <richard@nod.at>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Will Deacon <will@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Chris Zankel <chris@zankel.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Rich Felker <dalias@libc.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Helge Deller <deller@gmx.de>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-31 02:34:50 +08:00
|
|
|
/* The fault is fully completed (including releasing mmap lock) */
|
|
|
|
if (fault & VM_FAULT_COMPLETED)
|
|
|
|
return;
|
|
|
|
|
2014-11-06 15:19:44 +08:00
|
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
|
|
if (fault & VM_FAULT_OOM)
|
|
|
|
goto out_of_memory;
|
vm: add VM_FAULT_SIGSEGV handling support
The core VM already knows about VM_FAULT_SIGBUS, but cannot return a
"you should SIGSEGV" error, because the SIGSEGV case was generally
handled by the caller - usually the architecture fault handler.
That results in lots of duplication - all the architecture fault
handlers end up doing very similar "look up vma, check permissions, do
retries etc" - but it generally works. However, there are cases where
the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV.
In particular, when accessing the stack guard page, libsigsegv expects a
SIGSEGV. And it usually got one, because the stack growth is handled by
that duplicated architecture fault handler.
However, when the generic VM layer started propagating the error return
from the stack expansion in commit fee7e49d4514 ("mm: propagate error
from stack expansion even for guard page"), that now exposed the
existing VM_FAULT_SIGBUS result to user space. And user space really
expected SIGSEGV, not SIGBUS.
To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those
duplicate architecture fault handlers about it. They all already have
the code to handle SIGSEGV, so it's about just tying that new return
value to the existing code, but it's all a bit annoying.
This is the mindless minimal patch to do this. A more extensive patch
would be to try to gather up the mostly shared fault handling logic into
one generic helper routine, and long-term we really should do that
cleanup.
Just from this patch, you can generally see that most architectures just
copied (directly or indirectly) the old x86 way of doing things, but in
the meantime that original x86 model has been improved to hold the VM
semaphore for shorter times etc and to handle VM_FAULT_RETRY and other
"newer" things, so it would be a good idea to bring all those
improvements to the generic case and teach other architectures about
them too.
Reported-and-tested-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Jan Engelhardt <jengelh@inai.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots"
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-30 02:51:32 +08:00
|
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
|
|
|
goto bad_area;
|
2014-11-06 15:19:44 +08:00
|
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
|
|
goto do_sigbus;
|
|
|
|
BUG();
|
|
|
|
}
|
2015-02-09 18:11:29 +08:00
|
|
|
|
2022-01-15 06:05:51 +08:00
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
flags |= FAULT_FLAG_TRIED;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* No need to mmap_read_unlock(mm) as we would
|
|
|
|
* have already released it in __lock_page_or_retry
|
|
|
|
* in mm/filemap.c.
|
|
|
|
*/
|
|
|
|
|
|
|
|
goto retry;
|
2015-02-09 18:11:29 +08:00
|
|
|
}
|
2014-11-06 15:19:44 +08:00
|
|
|
|
2020-06-09 12:33:25 +08:00
|
|
|
mmap_read_unlock(mm);
|
2014-11-06 15:19:44 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Something tried to access memory that isn't in our memory map..
|
|
|
|
* Fix it, but check if it's kernel or user first..
|
|
|
|
*/
|
|
|
|
bad_area:
|
2020-06-09 12:33:25 +08:00
|
|
|
mmap_read_unlock(mm);
|
2014-11-06 15:19:44 +08:00
|
|
|
|
|
|
|
bad_area_nosemaphore:
|
|
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
|
|
if (user_mode(regs)) {
|
2015-02-09 09:40:50 +08:00
|
|
|
if (unhandled_signal(current, SIGSEGV) && printk_ratelimit()) {
|
|
|
|
pr_info("%s: unhandled page fault (%d) at 0x%08lx, "
|
|
|
|
"cause %ld\n", current->comm, SIGSEGV, address, cause);
|
|
|
|
show_regs(regs);
|
|
|
|
}
|
2014-11-06 15:19:44 +08:00
|
|
|
_exception(SIGSEGV, regs, code, address);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
no_context:
|
|
|
|
/* Are we prepared to handle this kernel fault? */
|
|
|
|
if (fixup_exception(regs))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
|
|
* terminate things with extreme prejudice.
|
|
|
|
*/
|
|
|
|
bust_spinlocks(1);
|
|
|
|
|
|
|
|
pr_alert("Unable to handle kernel %s at virtual address %08lx",
|
|
|
|
address < PAGE_SIZE ? "NULL pointer dereference" :
|
|
|
|
"paging request", address);
|
|
|
|
pr_alert("ea = %08lx, ra = %08lx, cause = %ld\n", regs->ea, regs->ra,
|
|
|
|
cause);
|
|
|
|
panic("Oops");
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We ran out of memory, or some other thing happened to us that made
|
|
|
|
* us unable to handle the page fault gracefully.
|
|
|
|
*/
|
|
|
|
out_of_memory:
|
2020-06-09 12:33:25 +08:00
|
|
|
mmap_read_unlock(mm);
|
2014-11-06 15:19:44 +08:00
|
|
|
if (!user_mode(regs))
|
|
|
|
goto no_context;
|
|
|
|
pagefault_out_of_memory();
|
|
|
|
return;
|
|
|
|
|
|
|
|
do_sigbus:
|
2020-06-09 12:33:25 +08:00
|
|
|
mmap_read_unlock(mm);
|
2014-11-06 15:19:44 +08:00
|
|
|
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
|
|
if (!user_mode(regs))
|
|
|
|
goto no_context;
|
|
|
|
|
|
|
|
_exception(SIGBUS, regs, BUS_ADRERR, address);
|
|
|
|
return;
|
|
|
|
|
|
|
|
vmalloc_fault:
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Synchronize this task's top level page-table
|
|
|
|
* with the 'reference' page table.
|
|
|
|
*
|
|
|
|
* Do _not_ use "tsk" here. We might be inside
|
|
|
|
* an interrupt in the middle of a task switch..
|
|
|
|
*/
|
|
|
|
int offset = pgd_index(address);
|
|
|
|
pgd_t *pgd, *pgd_k;
|
2020-06-05 07:46:35 +08:00
|
|
|
p4d_t *p4d, *p4d_k;
|
2014-11-06 15:19:44 +08:00
|
|
|
pud_t *pud, *pud_k;
|
|
|
|
pmd_t *pmd, *pmd_k;
|
|
|
|
pte_t *pte_k;
|
|
|
|
|
|
|
|
pgd = pgd_current + offset;
|
|
|
|
pgd_k = init_mm.pgd + offset;
|
|
|
|
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
|
|
goto no_context;
|
|
|
|
set_pgd(pgd, *pgd_k);
|
|
|
|
|
2020-06-05 07:46:35 +08:00
|
|
|
p4d = p4d_offset(pgd, address);
|
|
|
|
p4d_k = p4d_offset(pgd_k, address);
|
|
|
|
if (!p4d_present(*p4d_k))
|
|
|
|
goto no_context;
|
|
|
|
pud = pud_offset(p4d, address);
|
|
|
|
pud_k = pud_offset(p4d_k, address);
|
2014-11-06 15:19:44 +08:00
|
|
|
if (!pud_present(*pud_k))
|
|
|
|
goto no_context;
|
|
|
|
pmd = pmd_offset(pud, address);
|
|
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
|
|
if (!pmd_present(*pmd_k))
|
|
|
|
goto no_context;
|
|
|
|
set_pmd(pmd, *pmd_k);
|
|
|
|
|
|
|
|
pte_k = pte_offset_kernel(pmd_k, address);
|
|
|
|
if (!pte_present(*pte_k))
|
|
|
|
goto no_context;
|
|
|
|
|
2018-11-05 10:00:15 +08:00
|
|
|
flush_tlb_kernel_page(address);
|
2014-11-06 15:19:44 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|