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>
341 lines
8.5 KiB
C
341 lines
8.5 KiB
C
/*
|
|
* 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.
|
|
*
|
|
* Copyright (C) 1995 - 2000 by Ralf Baechle
|
|
*/
|
|
#include <linux/context_tracking.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/sched.h>
|
|
#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/ratelimit.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/branch.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/highmem.h> /* For VMALLOC_END */
|
|
#include <linux/kdebug.h>
|
|
|
|
int show_unhandled_signals = 1;
|
|
|
|
/*
|
|
* This routine handles page faults. It determines the address,
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
* routines.
|
|
*/
|
|
static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
|
|
unsigned long address)
|
|
{
|
|
struct vm_area_struct * vma = NULL;
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm = tsk->mm;
|
|
const int field = sizeof(unsigned long) * 2;
|
|
int si_code;
|
|
vm_fault_t fault;
|
|
unsigned int flags = FAULT_FLAG_DEFAULT;
|
|
|
|
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
|
|
|
|
#if 0
|
|
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
|
|
current->comm, current->pid, field, address, write,
|
|
field, regs->cp0_epc);
|
|
#endif
|
|
|
|
#ifdef CONFIG_KPROBES
|
|
/*
|
|
* This is to notify the fault handler of the kprobes.
|
|
*/
|
|
if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
|
|
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
|
|
return;
|
|
#endif
|
|
|
|
si_code = SEGV_MAPERR;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
# define VMALLOC_FAULT_TARGET no_context
|
|
#else
|
|
# define VMALLOC_FAULT_TARGET vmalloc_fault
|
|
#endif
|
|
|
|
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END))
|
|
goto VMALLOC_FAULT_TARGET;
|
|
#ifdef MODULE_START
|
|
if (unlikely(address >= MODULE_START && address < MODULE_END))
|
|
goto VMALLOC_FAULT_TARGET;
|
|
#endif
|
|
|
|
/*
|
|
* If we're in an interrupt or have no user
|
|
* context, we must not take the fault..
|
|
*/
|
|
if (faulthandler_disabled() || !mm)
|
|
goto bad_area_nosemaphore;
|
|
|
|
if (user_mode(regs))
|
|
flags |= FAULT_FLAG_USER;
|
|
retry:
|
|
mmap_read_lock(mm);
|
|
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:
|
|
si_code = SEGV_ACCERR;
|
|
|
|
if (write) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
} else {
|
|
if (cpu_has_rixi) {
|
|
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
|
|
#if 0
|
|
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] XI violation\n",
|
|
raw_smp_processor_id(),
|
|
current->comm, current->pid,
|
|
field, address, write,
|
|
field, regs->cp0_epc);
|
|
#endif
|
|
goto bad_area;
|
|
}
|
|
if (!(vma->vm_flags & VM_READ) &&
|
|
exception_epc(regs) != address) {
|
|
#if 0
|
|
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
|
|
raw_smp_processor_id(),
|
|
current->comm, current->pid,
|
|
field, address, write,
|
|
field, regs->cp0_epc);
|
|
#endif
|
|
goto bad_area;
|
|
}
|
|
} else {
|
|
if (unlikely(!vma_is_accessible(vma)))
|
|
goto bad_area;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If for any reason at all we couldn't handle the fault,
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
* the fault.
|
|
*/
|
|
fault = handle_mm_fault(vma, address, flags, NULL);
|
|
|
|
if (fault_signal_pending(fault, regs))
|
|
return;
|
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM)
|
|
goto out_of_memory;
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
|
goto bad_area;
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
goto do_sigbus;
|
|
BUG();
|
|
}
|
|
if (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
if (fault & VM_FAULT_MAJOR) {
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
|
|
regs, address);
|
|
tsk->maj_flt++;
|
|
} else {
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
|
|
regs, address);
|
|
tsk->min_flt++;
|
|
}
|
|
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;
|
|
}
|
|
}
|
|
|
|
mmap_read_unlock(mm);
|
|
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:
|
|
mmap_read_unlock(mm);
|
|
|
|
bad_area_nosemaphore:
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
if (user_mode(regs)) {
|
|
tsk->thread.cp0_badvaddr = address;
|
|
tsk->thread.error_code = write;
|
|
if (show_unhandled_signals &&
|
|
unhandled_signal(tsk, SIGSEGV) &&
|
|
__ratelimit(&ratelimit_state)) {
|
|
pr_info("do_page_fault(): sending SIGSEGV to %s for invalid %s %0*lx\n",
|
|
tsk->comm,
|
|
write ? "write access to" : "read access from",
|
|
field, address);
|
|
pr_info("epc = %0*lx in", field,
|
|
(unsigned long) regs->cp0_epc);
|
|
print_vma_addr(KERN_CONT " ", regs->cp0_epc);
|
|
pr_cont("\n");
|
|
pr_info("ra = %0*lx in", field,
|
|
(unsigned long) regs->regs[31]);
|
|
print_vma_addr(KERN_CONT " ", regs->regs[31]);
|
|
pr_cont("\n");
|
|
}
|
|
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
|
|
force_sig_fault(SIGSEGV, si_code, (void __user *)address);
|
|
return;
|
|
}
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this kernel fault? */
|
|
if (fixup_exception(regs)) {
|
|
current->thread.cp0_baduaddr = address;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
* terminate things with extreme prejudice.
|
|
*/
|
|
bust_spinlocks(1);
|
|
|
|
printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at "
|
|
"virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
|
|
raw_smp_processor_id(), field, address, field, regs->cp0_epc,
|
|
field, regs->regs[31]);
|
|
die("Oops", regs);
|
|
|
|
out_of_memory:
|
|
/*
|
|
* We ran out of memory, call the OOM killer, and return the userspace
|
|
* (which will retry the fault, or kill us if we got oom-killed).
|
|
*/
|
|
mmap_read_unlock(mm);
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
pagefault_out_of_memory();
|
|
return;
|
|
|
|
do_sigbus:
|
|
mmap_read_unlock(mm);
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
|
|
/*
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
* or user mode.
|
|
*/
|
|
#if 0
|
|
printk("do_page_fault() #3: sending SIGBUS to %s for "
|
|
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
|
|
tsk->comm,
|
|
write ? "write access to" : "read access from",
|
|
field, address,
|
|
field, (unsigned long) regs->cp0_epc,
|
|
field, (unsigned long) regs->regs[31]);
|
|
#endif
|
|
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
|
|
tsk->thread.cp0_badvaddr = address;
|
|
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
|
|
|
|
return;
|
|
#ifndef CONFIG_64BIT
|
|
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;
|
|
p4d_t *p4d, *p4d_k;
|
|
pud_t *pud, *pud_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
pte_t *pte_k;
|
|
|
|
pgd = (pgd_t *) pgd_current[raw_smp_processor_id()] + offset;
|
|
pgd_k = init_mm.pgd + offset;
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
goto no_context;
|
|
set_pgd(pgd, *pgd_k);
|
|
|
|
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);
|
|
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;
|
|
return;
|
|
}
|
|
#endif
|
|
}
|
|
|
|
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
|
|
unsigned long write, unsigned long address)
|
|
{
|
|
enum ctx_state prev_state;
|
|
|
|
prev_state = exception_enter();
|
|
__do_page_fault(regs, write, address);
|
|
exception_exit(prev_state);
|
|
}
|