mirror of
https://github.com/torvalds/linux.git
synced 2025-01-01 07:42:07 +00:00
d92725256b
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>
396 lines
8.9 KiB
C
396 lines
8.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* fault.c: Page fault handlers for the Sparc.
|
|
*
|
|
* Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
|
|
* Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
|
|
* Copyright (C) 1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
|
|
*/
|
|
|
|
#include <asm/head.h>
|
|
|
|
#include <linux/string.h>
|
|
#include <linux/types.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kdebug.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/extable.h>
|
|
|
|
#include <asm/page.h>
|
|
#include <asm/openprom.h>
|
|
#include <asm/oplib.h>
|
|
#include <asm/setup.h>
|
|
#include <asm/smp.h>
|
|
#include <asm/traps.h>
|
|
|
|
#include "mm_32.h"
|
|
|
|
int show_unhandled_signals = 1;
|
|
|
|
static void __noreturn unhandled_fault(unsigned long address,
|
|
struct task_struct *tsk,
|
|
struct pt_regs *regs)
|
|
{
|
|
if ((unsigned long) address < PAGE_SIZE) {
|
|
printk(KERN_ALERT
|
|
"Unable to handle kernel NULL pointer dereference\n");
|
|
} else {
|
|
printk(KERN_ALERT "Unable to handle kernel paging request at virtual address %08lx\n",
|
|
address);
|
|
}
|
|
printk(KERN_ALERT "tsk->{mm,active_mm}->context = %08lx\n",
|
|
(tsk->mm ? tsk->mm->context : tsk->active_mm->context));
|
|
printk(KERN_ALERT "tsk->{mm,active_mm}->pgd = %08lx\n",
|
|
(tsk->mm ? (unsigned long) tsk->mm->pgd :
|
|
(unsigned long) tsk->active_mm->pgd));
|
|
die_if_kernel("Oops", regs);
|
|
}
|
|
|
|
static inline void
|
|
show_signal_msg(struct pt_regs *regs, int sig, int code,
|
|
unsigned long address, struct task_struct *tsk)
|
|
{
|
|
if (!unhandled_signal(tsk, sig))
|
|
return;
|
|
|
|
if (!printk_ratelimit())
|
|
return;
|
|
|
|
printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
|
|
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
|
|
tsk->comm, task_pid_nr(tsk), address,
|
|
(void *)regs->pc, (void *)regs->u_regs[UREG_I7],
|
|
(void *)regs->u_regs[UREG_FP], code);
|
|
|
|
print_vma_addr(KERN_CONT " in ", regs->pc);
|
|
|
|
printk(KERN_CONT "\n");
|
|
}
|
|
|
|
static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs,
|
|
unsigned long addr)
|
|
{
|
|
if (unlikely(show_unhandled_signals))
|
|
show_signal_msg(regs, sig, code,
|
|
addr, current);
|
|
|
|
force_sig_fault(sig, code, (void __user *) addr);
|
|
}
|
|
|
|
static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
|
|
{
|
|
unsigned int insn;
|
|
|
|
if (text_fault)
|
|
return regs->pc;
|
|
|
|
if (regs->psr & PSR_PS)
|
|
insn = *(unsigned int *) regs->pc;
|
|
else
|
|
__get_user(insn, (unsigned int *) regs->pc);
|
|
|
|
return safe_compute_effective_address(regs, insn);
|
|
}
|
|
|
|
static noinline void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
|
|
int text_fault)
|
|
{
|
|
unsigned long addr = compute_si_addr(regs, text_fault);
|
|
|
|
__do_fault_siginfo(code, sig, regs, addr);
|
|
}
|
|
|
|
asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
|
|
unsigned long address)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm = tsk->mm;
|
|
int from_user = !(regs->psr & PSR_PS);
|
|
int code;
|
|
vm_fault_t fault;
|
|
unsigned int flags = FAULT_FLAG_DEFAULT;
|
|
|
|
if (text_fault)
|
|
address = regs->pc;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
code = SEGV_MAPERR;
|
|
if (address >= TASK_SIZE)
|
|
goto vmalloc_fault;
|
|
|
|
/*
|
|
* If we're in an interrupt or have no user
|
|
* context, we must not take the fault..
|
|
*/
|
|
if (pagefault_disabled() || !mm)
|
|
goto no_context;
|
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
|
|
|
retry:
|
|
mmap_read_lock(mm);
|
|
|
|
if (!from_user && address >= PAGE_OFFSET)
|
|
goto bad_area;
|
|
|
|
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;
|
|
if (write) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
} else {
|
|
/* Allow reads even for write-only mappings */
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
|
|
goto bad_area;
|
|
}
|
|
|
|
if (from_user)
|
|
flags |= FAULT_FLAG_USER;
|
|
if (write)
|
|
flags |= FAULT_FLAG_WRITE;
|
|
|
|
/*
|
|
* 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, regs);
|
|
|
|
if (fault_signal_pending(fault, regs))
|
|
return;
|
|
|
|
/* The fault is fully completed (including releasing mmap lock) */
|
|
if (fault & VM_FAULT_COMPLETED)
|
|
return;
|
|
|
|
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 (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 (from_user) {
|
|
do_fault_siginfo(code, SIGSEGV, regs, text_fault);
|
|
return;
|
|
}
|
|
|
|
/* Is this in ex_table? */
|
|
no_context:
|
|
if (!from_user) {
|
|
const struct exception_table_entry *entry;
|
|
|
|
entry = search_exception_tables(regs->pc);
|
|
#ifdef DEBUG_EXCEPTIONS
|
|
printk("Exception: PC<%08lx> faddr<%08lx>\n",
|
|
regs->pc, address);
|
|
printk("EX_TABLE: insn<%08lx> fixup<%08x>\n",
|
|
regs->pc, entry->fixup);
|
|
#endif
|
|
regs->pc = entry->fixup;
|
|
regs->npc = regs->pc + 4;
|
|
return;
|
|
}
|
|
|
|
unhandled_fault(address, tsk, regs);
|
|
|
|
/*
|
|
* 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:
|
|
mmap_read_unlock(mm);
|
|
if (from_user) {
|
|
pagefault_out_of_memory();
|
|
return;
|
|
}
|
|
goto no_context;
|
|
|
|
do_sigbus:
|
|
mmap_read_unlock(mm);
|
|
do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, text_fault);
|
|
if (!from_user)
|
|
goto no_context;
|
|
|
|
vmalloc_fault:
|
|
{
|
|
/*
|
|
* Synchronize this task's top level page-table
|
|
* with the 'reference' page table.
|
|
*/
|
|
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;
|
|
|
|
pgd = tsk->active_mm->pgd + offset;
|
|
pgd_k = init_mm.pgd + offset;
|
|
|
|
if (!pgd_present(*pgd)) {
|
|
if (!pgd_present(*pgd_k))
|
|
goto bad_area_nosemaphore;
|
|
pgd_val(*pgd) = pgd_val(*pgd_k);
|
|
return;
|
|
}
|
|
|
|
p4d = p4d_offset(pgd, address);
|
|
pud = pud_offset(p4d, address);
|
|
pmd = pmd_offset(pud, address);
|
|
|
|
p4d_k = p4d_offset(pgd_k, address);
|
|
pud_k = pud_offset(p4d_k, address);
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
|
|
if (pmd_present(*pmd) || !pmd_present(*pmd_k))
|
|
goto bad_area_nosemaphore;
|
|
|
|
*pmd = *pmd_k;
|
|
return;
|
|
}
|
|
}
|
|
|
|
/* This always deals with user addresses. */
|
|
static void force_user_fault(unsigned long address, int write)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm = tsk->mm;
|
|
unsigned int flags = FAULT_FLAG_USER;
|
|
int code;
|
|
|
|
code = SEGV_MAPERR;
|
|
|
|
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;
|
|
good_area:
|
|
code = SEGV_ACCERR;
|
|
if (write) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
} else {
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
|
|
goto bad_area;
|
|
}
|
|
switch (handle_mm_fault(vma, address, flags, NULL)) {
|
|
case VM_FAULT_SIGBUS:
|
|
case VM_FAULT_OOM:
|
|
goto do_sigbus;
|
|
}
|
|
mmap_read_unlock(mm);
|
|
return;
|
|
bad_area:
|
|
mmap_read_unlock(mm);
|
|
__do_fault_siginfo(code, SIGSEGV, tsk->thread.kregs, address);
|
|
return;
|
|
|
|
do_sigbus:
|
|
mmap_read_unlock(mm);
|
|
__do_fault_siginfo(BUS_ADRERR, SIGBUS, tsk->thread.kregs, address);
|
|
}
|
|
|
|
static void check_stack_aligned(unsigned long sp)
|
|
{
|
|
if (sp & 0x7UL)
|
|
force_sig(SIGILL);
|
|
}
|
|
|
|
void window_overflow_fault(void)
|
|
{
|
|
unsigned long sp;
|
|
|
|
sp = current_thread_info()->rwbuf_stkptrs[0];
|
|
if (((sp + 0x38) & PAGE_MASK) != (sp & PAGE_MASK))
|
|
force_user_fault(sp + 0x38, 1);
|
|
force_user_fault(sp, 1);
|
|
|
|
check_stack_aligned(sp);
|
|
}
|
|
|
|
void window_underflow_fault(unsigned long sp)
|
|
{
|
|
if (((sp + 0x38) & PAGE_MASK) != (sp & PAGE_MASK))
|
|
force_user_fault(sp + 0x38, 0);
|
|
force_user_fault(sp, 0);
|
|
|
|
check_stack_aligned(sp);
|
|
}
|
|
|
|
void window_ret_fault(struct pt_regs *regs)
|
|
{
|
|
unsigned long sp;
|
|
|
|
sp = regs->u_regs[UREG_FP];
|
|
if (((sp + 0x38) & PAGE_MASK) != (sp & PAGE_MASK))
|
|
force_user_fault(sp + 0x38, 0);
|
|
force_user_fault(sp, 0);
|
|
|
|
check_stack_aligned(sp);
|
|
}
|