Bail out to prevent unnecessary CPU overhead if target process has pending fatal signal during (MADV_COLD|MADV_PAGEOUT) operation.
Link: http://lkml.kernel.org/r/20200302193630.68771-4-minc...@kernel.org Signed-off-by: Minchan Kim <minc...@kernel.org> Reviewed-by: Suren Baghdasaryan <sur...@google.com> Reviewed-by: Vlastimil Babka <vba...@suse.cz> Cc: Alexander Duyck <alexander.h.du...@linux.intel.com> Cc: Brian Geffon <bgef...@google.com> Cc: Christian Brauner <christ...@brauner.io> Cc: Daniel Colascione <dan...@google.com> Cc: Jann Horn <ja...@google.com> Cc: Jens Axboe <ax...@kernel.dk> Cc: Joel Fernandes <j...@joelfernandes.org> Cc: Johannes Weiner <han...@cmpxchg.org> Cc: John Dias <joaod...@google.com> Cc: Kirill Tkhai <ktk...@virtuozzo.com> Cc: Michal Hocko <mho...@suse.com> Cc: Oleksandr Natalenko <oleksa...@redhat.com> Cc: Sandeep Patil <sspa...@google.com> Cc: SeongJae Park <sj38.p...@gmail.com> Cc: SeongJae Park <sjp...@amazon.de> Cc: Shakeel Butt <shake...@google.com> Cc: Sonny Rao <sonny...@google.com> Cc: Tim Murray <timmur...@google.com> Cc: Christian Brauner <christian.brau...@ubuntu.com> Cc: <linux-...@vger.kernel.org> --- mm/madvise.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index 23abca3f93fa..a16dba21cdf6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -39,6 +39,7 @@ struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; + struct task_struct *target_task; }; /* @@ -319,6 +320,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, if (fatal_signal_pending(current)) return -EINTR; + if (private->target_task && + fatal_signal_pending(private->target_task)) + return -EINTR; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; @@ -480,12 +485,14 @@ static const struct mm_walk_ops cold_walk_ops = { }; static void madvise_cold_page_range(struct mmu_gather *tlb, + struct task_struct *task, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, + .target_task = task, }; tlb_start_vma(tlb, vma); @@ -493,7 +500,8 @@ static void madvise_cold_page_range(struct mmu_gather *tlb, tlb_end_vma(tlb, vma); } -static long madvise_cold(struct vm_area_struct *vma, +static long madvise_cold(struct task_struct *task, + struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { @@ -506,19 +514,21 @@ static long madvise_cold(struct vm_area_struct *vma, lru_add_drain(); tlb_gather_mmu(&tlb, mm, start_addr, end_addr); - madvise_cold_page_range(&tlb, vma, start_addr, end_addr); + madvise_cold_page_range(&tlb, task, vma, start_addr, end_addr); tlb_finish_mmu(&tlb, start_addr, end_addr); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, + struct task_struct *task, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, + .target_task = task, }; tlb_start_vma(tlb, vma); @@ -542,7 +552,8 @@ static inline bool can_do_pageout(struct vm_area_struct *vma) inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; } -static long madvise_pageout(struct vm_area_struct *vma, +static long madvise_pageout(struct task_struct *task, + struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { @@ -558,7 +569,7 @@ static long madvise_pageout(struct vm_area_struct *vma, lru_add_drain(); tlb_gather_mmu(&tlb, mm, start_addr, end_addr); - madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + madvise_pageout_page_range(&tlb, task, vma, start_addr, end_addr); tlb_finish_mmu(&tlb, start_addr, end_addr); return 0; @@ -938,7 +949,8 @@ static int madvise_inject_error(int behavior, #endif static long -madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, +madvise_vma(struct task_struct *task, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { switch (behavior) { @@ -947,9 +959,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); case MADV_COLD: - return madvise_cold(vma, prev, start, end); + return madvise_cold(task, vma, prev, start, end); case MADV_PAGEOUT: - return madvise_pageout(vma, prev, start, end); + return madvise_pageout(task, vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); @@ -1166,7 +1178,8 @@ int do_madvise(struct task_struct *target_task, struct mm_struct *mm, tmp = end; /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ - error = madvise_vma(vma, &prev, start, tmp, behavior); + error = madvise_vma(target_task, vma, &prev, + start, tmp, behavior); if (error) goto out; start = tmp; -- 2.27.0.111.gc72c7da667-goog