From d92725256b4f22d084b813b37ddc394da79aacab Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 30 May 2022 14:34:50 -0400 Subject: [PATCH] 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 Acked-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Vineet Gupta Acked-by: Guo Ren Acked-by: Max Filippov Acked-by: Christian Borntraeger Acked-by: Michael Ellerman (powerpc) Acked-by: Catalin Marinas Reviewed-by: Alistair Popple Reviewed-by: Ingo Molnar Acked-by: Russell King (Oracle) [arm part] Acked-by: Heiko Carstens Cc: Vasily Gorbik Cc: Stafford Horne Cc: David S. Miller Cc: Johannes Berg Cc: Brian Cain Cc: Richard Henderson Cc: Richard Weinberger Cc: Benjamin Herrenschmidt Cc: Thomas Gleixner Cc: Janosch Frank Cc: Albert Ou Cc: Anton Ivanov Cc: Dave Hansen Cc: Borislav Petkov Cc: Sven Schnelle Cc: Andrea Arcangeli Cc: James Bottomley Cc: Al Viro Cc: Alexander Gordeev Cc: Jonas Bonn Cc: Will Deacon Cc: Vlastimil Babka Cc: Michal Simek Cc: Matt Turner Cc: Paul Mackerras Cc: David Hildenbrand Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Stefan Kristiansson Cc: Paul Walmsley Cc: Ivan Kokshaysky Cc: Chris Zankel Cc: Hugh Dickins Cc: Dinh Nguyen Cc: Rich Felker Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Thomas Bogendoerfer Cc: Helge Deller Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/alpha/mm/fault.c | 4 ++++ arch/arc/mm/fault.c | 4 ++++ arch/arm/mm/fault.c | 4 ++++ arch/arm64/mm/fault.c | 4 ++++ arch/csky/mm/fault.c | 4 ++++ arch/hexagon/mm/vm_fault.c | 4 ++++ arch/ia64/mm/fault.c | 4 ++++ arch/m68k/mm/fault.c | 4 ++++ arch/microblaze/mm/fault.c | 4 ++++ arch/mips/mm/fault.c | 4 ++++ arch/nios2/mm/fault.c | 4 ++++ arch/openrisc/mm/fault.c | 4 ++++ arch/parisc/mm/fault.c | 4 ++++ arch/powerpc/mm/copro_fault.c | 5 +++++ arch/powerpc/mm/fault.c | 5 +++++ arch/riscv/mm/fault.c | 4 ++++ arch/s390/mm/fault.c | 12 ++++++++++++ arch/sh/mm/fault.c | 4 ++++ arch/sparc/mm/fault_32.c | 4 ++++ arch/sparc/mm/fault_64.c | 5 +++++ arch/um/kernel/trap.c | 4 ++++ arch/x86/mm/fault.c | 4 ++++ arch/xtensa/mm/fault.c | 4 ++++ include/linux/mm_types.h | 2 ++ mm/gup.c | 34 +++++++++++++++++++++++++++++++++- mm/memory.c | 2 +- 26 files changed, 139 insertions(+), 2 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c10..ef427a6 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ retry: 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; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4..5ca59a4 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ retry: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07..46cccd6 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c5e1176..de166cd 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -608,6 +608,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46..e15f736 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9e..f73c7cb 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1..ef78c2d 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ retry: 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)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6..4d2837e 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ good_area: if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6..5c40c3e 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ good_area: 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; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index b08bc55..a27045f 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ good_area: 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; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72..edaca0a 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ good_area: 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; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 53b760a..b4762d6 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -165,6 +165,10 @@ good_area: 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; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 84bc437..9ad80d4 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -311,6 +311,10 @@ good_area: 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)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a..7c507fb 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4..0140054 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ retry: if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 40694f0..f2fbd14 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -326,6 +326,10 @@ good_area: 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_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e173b61..973dcd0 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ retry: goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + if (gmap) { + mmap_read_lock(mm); + goto out_gmap; + } + fault = 0; + goto out; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ retry: mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667..acd2f5e 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ good_area: if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9..91259f2 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ good_area: 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; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e070..4acc12e 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ good_area: if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ good_area: } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0b..d3ce21c 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ good_area: if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fad8faa..fe10c6d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 16f0a5f..8c781b0 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -172,6 +172,10 @@ good_area: 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; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c29ab4c..6b961a2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -729,6 +729,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +747,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/gup.c b/mm/gup.c index 5512644..407a81d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -951,6 +951,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * what has happened - we've just fully completed a page + * fault, with the mmap lock released. Use -EAGAIN to show + * that we want to take the mmap lock _again_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1177,6 +1196,7 @@ retry: case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1303,6 +1323,18 @@ retry: return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * NOTE: it's a pity that we need to retake the lock here + * to pair with the unlock() in the callers. Ideally we + * could tell the callers so they do not need to unlock. + */ + mmap_read_lock(mm); + *unlocked = true; + return 0; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1368,7 +1400,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 7a08914..580c62f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3020,7 +3020,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } -- 2.7.4