From a2beb5f1efede6924a4258462a5660572e6ca864 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 11 Aug 2020 18:38:57 -0700 Subject: [PATCH] mm: clean up the last pieces of page fault accountings Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Cc: Albert Ou Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Chris Zankel Cc: Dave Hansen Cc: David S. Miller Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Greentime Hu Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James E.J. Bottomley Cc: John Hubbard Cc: Jonas Bonn Cc: Ley Foon Tan Cc: "Luck, Tony" Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds --- arch/powerpc/mm/copro_fault.c | 5 ----- arch/um/kernel/trap.c | 4 ---- mm/gup.c | 13 ------------- mm/memory.c | 17 ++++++++++------- 4 files changed, 10 insertions(+), 29 deletions(-) diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 2d0276abe0a6..8acd00178956 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, BUG(); } - if (*flt & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - out_unlock: mmap_read_unlock(mm); return ret; diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 8d9870d76da1..ad12f78bda7e 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -88,10 +88,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/mm/gup.c b/mm/gup.c index ae7121d729fa..d5d44c68fa19 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -893,13 +893,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, BUG(); } - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - if (ret & VM_FAULT_RETRY) { if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; @@ -1255,12 +1248,6 @@ retry: goto retry; } - if (tsk) { - if (major) - tsk->maj_flt++; - else - tsk->min_flt++; - } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); diff --git a/mm/memory.c b/mm/memory.c index 9b7d35734caa..2b7f0e00f312 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4400,20 +4400,23 @@ static inline void mm_account_fault(struct pt_regs *regs, */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); + if (major) + current->maj_flt++; + else + current->min_flt++; + /* - * If the fault is done for GUP, regs will be NULL, and we will skip - * the fault accounting. + * If the fault is done for GUP, regs will be NULL. We only do the + * accounting for the per thread fault counters who triggered the + * fault, and we skip the perf event updates. */ if (!regs) return; - if (major) { - current->maj_flt++; + if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); - } else { - current->min_flt++; + else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } } /* -- 2.34.1