diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/filemap.c | 20 | ||||
-rw-r--r-- | mm/frontswap.c | 8 | ||||
-rw-r--r-- | mm/gup.c | 118 | ||||
-rw-r--r-- | mm/hmm.c | 3 | ||||
-rw-r--r-- | mm/hugetlb.c | 35 | ||||
-rw-r--r-- | mm/internal.h | 8 | ||||
-rw-r--r-- | mm/kmemleak.c | 2 | ||||
-rw-r--r-- | mm/ksm.c | 3 | ||||
-rw-r--r-- | mm/list_lru.c | 2 | ||||
-rw-r--r-- | mm/madvise.c | 190 | ||||
-rw-r--r-- | mm/memory-failure.c | 15 | ||||
-rw-r--r-- | mm/memory.c | 73 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 42 | ||||
-rw-r--r-- | mm/mempolicy.c | 29 | ||||
-rw-r--r-- | mm/mempool.c | 2 | ||||
-rw-r--r-- | mm/migrate.c | 51 | ||||
-rw-r--r-- | mm/page_alloc.c | 8 | ||||
-rw-r--r-- | mm/page_counter.c | 13 | ||||
-rw-r--r-- | mm/page_io.c | 8 | ||||
-rw-r--r-- | mm/page_isolation.c | 5 | ||||
-rw-r--r-- | mm/process_vm_access.c | 2 | ||||
-rw-r--r-- | mm/rmap.c | 2 | ||||
-rw-r--r-- | mm/swap.c | 5 | ||||
-rw-r--r-- | mm/swap_state.c | 4 | ||||
-rw-r--r-- | mm/swapfile.c | 31 |
25 files changed, 437 insertions, 242 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 9d43acdba8aa..cf4bdf7803b6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2425,6 +2425,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; pgoff_t offset = vmf->pgoff; + unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) @@ -2440,14 +2441,15 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) } /* Avoid banging the cache line if not needed */ - if (ra->mmap_miss < MMAP_LOTSAMISS * 10) - ra->mmap_miss++; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss < MMAP_LOTSAMISS * 10) + WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ - if (ra->mmap_miss > MMAP_LOTSAMISS) + if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* @@ -2473,13 +2475,15 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; + unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; - if (ra->mmap_miss > 0) - ra->mmap_miss--; + mmap_miss = READ_ONCE(ra->mmap_miss); + if (mmap_miss) + WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, @@ -2645,6 +2649,7 @@ void filemap_map_pages(struct vm_fault *vmf, unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *page; + unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); rcu_read_lock(); xas_for_each(&xas, page, end_pgoff) { @@ -2681,8 +2686,8 @@ void filemap_map_pages(struct vm_fault *vmf, if (page->index >= max_idx) goto unlock; - if (file->f_ra.mmap_miss > 0) - file->f_ra.mmap_miss--; + if (mmap_miss > 0) + mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) @@ -2702,6 +2707,7 @@ next: break; } rcu_read_unlock(); + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); } EXPORT_SYMBOL(filemap_map_pages); diff --git a/mm/frontswap.c b/mm/frontswap.c index 9d977b1fc016..2183a56c7874 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -61,16 +61,16 @@ static u64 frontswap_failed_stores; static u64 frontswap_invalidates; static inline void inc_frontswap_loads(void) { - frontswap_loads++; + data_race(frontswap_loads++); } static inline void inc_frontswap_succ_stores(void) { - frontswap_succ_stores++; + data_race(frontswap_succ_stores++); } static inline void inc_frontswap_failed_stores(void) { - frontswap_failed_stores++; + data_race(frontswap_failed_stores++); } static inline void inc_frontswap_invalidates(void) { - frontswap_invalidates++; + data_race(frontswap_invalidates++); } #else static inline void inc_frontswap_loads(void) { } @@ -859,7 +859,7 @@ unmap: * does not include FOLL_NOWAIT, the mmap_lock may be released. If it * is, *@locked will be set to 0 and -EBUSY returned. */ -static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, +static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int *flags, int *locked) { unsigned int fault_flags = 0; @@ -884,7 +884,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, fault_flags |= FAULT_FLAG_TRIED; } - ret = handle_mm_fault(vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -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; @@ -969,7 +962,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) /** * __get_user_pages() - pin user pages in memory - * @tsk: task_struct of target task * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -1028,7 +1020,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ -static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, +static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1110,8 +1102,7 @@ retry: page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page) { - ret = faultin_page(tsk, vma, start, &foll_flags, - locked); + ret = faultin_page(vma, start, &foll_flags, locked); switch (ret) { case 0: goto retry; @@ -1185,8 +1176,6 @@ static bool vma_permits_fault(struct vm_area_struct *vma, /** * fixup_user_fault() - manually resolve a user page fault - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() @@ -1214,7 +1203,7 @@ static bool vma_permits_fault(struct vm_area_struct *vma, * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ -int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, +int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { @@ -1238,7 +1227,7 @@ retry: fatal_signal_pending(current)) return -EINTR; - ret = handle_mm_fault(vma, address, fault_flags); + ret = handle_mm_fault(vma, address, fault_flags, NULL); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1255,12 +1244,6 @@ retry: goto retry; } - if (tsk) { - if (major) - tsk->maj_flt++; - else - tsk->min_flt++; - } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); @@ -1269,8 +1252,7 @@ EXPORT_SYMBOL_GPL(fixup_user_fault); * Please note that this function, unlike __get_user_pages will not * return 0 for nr_pages > 0 without FOLL_NOWAIT */ -static __always_inline long __get_user_pages_locked(struct task_struct *tsk, - struct mm_struct *mm, +static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1303,7 +1285,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, pages_done = 0; lock_dropped = false; for (;;) { - ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages, + ret = __get_user_pages(mm, start, nr_pages, flags, pages, vmas, locked); if (!locked) /* VM_FAULT_RETRY couldn't trigger, bypass */ @@ -1363,7 +1345,7 @@ retry: } *locked = 1; - ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED, + ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, NULL, locked); if (!*locked) { /* Continue to retry until we succeeded */ @@ -1449,7 +1431,7 @@ long populate_vma_page_range(struct vm_area_struct *vma, * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ - return __get_user_pages(current, mm, start, nr_pages, gup_flags, + return __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); } @@ -1533,7 +1515,7 @@ struct page *get_dump_page(unsigned long addr) struct vm_area_struct *vma; struct page *page; - if (__get_user_pages(current, current->mm, addr, 1, + if (__get_user_pages(current->mm, addr, 1, FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, NULL) < 1) return NULL; @@ -1542,8 +1524,7 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ #else /* CONFIG_MMU */ -static long __get_user_pages_locked(struct task_struct *tsk, - struct mm_struct *mm, unsigned long start, +static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, struct vm_area_struct **vmas, int *locked, unsigned int foll_flags) @@ -1659,8 +1640,7 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private) return __alloc_pages_node(nid, gfp_mask, 0); } -static long check_and_migrate_cma_pages(struct task_struct *tsk, - struct mm_struct *mm, +static long check_and_migrate_cma_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1734,7 +1714,7 @@ check_again: * again migrating any new CMA pages which we failed to isolate * earlier. */ - ret = __get_user_pages_locked(tsk, mm, start, nr_pages, + ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL, gup_flags); @@ -1748,8 +1728,7 @@ check_again: return ret; } #else -static long check_and_migrate_cma_pages(struct task_struct *tsk, - struct mm_struct *mm, +static long check_and_migrate_cma_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1764,8 +1743,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk, * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ -static long __gup_longterm_locked(struct task_struct *tsk, - struct mm_struct *mm, +static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, @@ -1790,7 +1768,7 @@ static long __gup_longterm_locked(struct task_struct *tsk, flags = memalloc_nocma_save(); } - rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, + rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas_tmp, NULL, gup_flags); if (gup_flags & FOLL_LONGTERM) { @@ -1805,7 +1783,7 @@ static long __gup_longterm_locked(struct task_struct *tsk, goto out; } - rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages, + rc = check_and_migrate_cma_pages(mm, start, rc, pages, vmas_tmp, gup_flags); } @@ -1815,22 +1793,20 @@ out: return rc; } #else /* !CONFIG_FS_DAX && !CONFIG_CMA */ -static __always_inline long __gup_longterm_locked(struct task_struct *tsk, - struct mm_struct *mm, +static __always_inline long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, struct vm_area_struct **vmas, unsigned int flags) { - return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL, flags); } #endif /* CONFIG_FS_DAX || CONFIG_CMA */ #ifdef CONFIG_MMU -static long __get_user_pages_remote(struct task_struct *tsk, - struct mm_struct *mm, +static long __get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1849,20 +1825,18 @@ static long __get_user_pages_remote(struct task_struct *tsk, * This will check the vmas (even if our vmas arg is NULL) * and return -ENOTSUPP if DAX isn't allowed in this case: */ - return __gup_longterm_locked(tsk, mm, start, nr_pages, pages, + return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH | FOLL_REMOTE); } - return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, + return __get_user_pages_locked(mm, start, nr_pages, pages, vmas, locked, gup_flags | FOLL_TOUCH | FOLL_REMOTE); } /** * get_user_pages_remote() - pin user pages in memory - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -1921,7 +1895,7 @@ static long __get_user_pages_remote(struct task_struct *tsk, * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1933,13 +1907,13 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, pages, vmas, locked); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1947,8 +1921,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, return 0; } -static long __get_user_pages_remote(struct task_struct *tsk, - struct mm_struct *mm, +static long __get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -1968,11 +1941,10 @@ static long __get_user_pages_remote(struct task_struct *tsk, * @vmas: array of pointers to vmas corresponding to each page. * Or NULL if the caller does not require them. * - * This is the same as get_user_pages_remote(), just with a - * less-flexible calling convention where we assume that the task - * and mm being operated on are the current task's and don't allow - * passing of a locked parameter. We also obviously don't pass - * FOLL_REMOTE in here. + * This is the same as get_user_pages_remote(), just with a less-flexible + * calling convention where we assume that the mm being operated on belongs to + * the current task, and doesn't allow passing of a locked parameter. We also + * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -1985,7 +1957,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __gup_longterm_locked(current, current->mm, start, nr_pages, + return __gup_longterm_locked(current->mm, start, nr_pages, pages, vmas, gup_flags | FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); @@ -1995,7 +1967,7 @@ EXPORT_SYMBOL(get_user_pages); * * mmap_read_lock(mm); * do_something() - * get_user_pages(tsk, mm, ..., pages, NULL); + * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * to: @@ -2003,7 +1975,7 @@ EXPORT_SYMBOL(get_user_pages); * int locked = 1; * mmap_read_lock(mm); * do_something() - * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * get_user_pages_locked(mm, ..., pages, &locked); * if (locked) * mmap_read_unlock(mm); * @@ -2041,7 +2013,7 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_PIN)) return -EINVAL; - return __get_user_pages_locked(current, current->mm, start, nr_pages, + return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, gup_flags | FOLL_TOUCH); } @@ -2051,12 +2023,12 @@ EXPORT_SYMBOL(get_user_pages_locked); * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); - * get_user_pages(tsk, mm, ..., pages, NULL); + * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * - * get_user_pages_unlocked(tsk, mm, ..., pages); + * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags @@ -2079,7 +2051,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, return -EINVAL; mmap_read_lock(mm); - ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL, + ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL, &locked, gup_flags | FOLL_TOUCH); if (locked) mmap_read_unlock(mm); @@ -2724,7 +2696,7 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages, */ if (gup_flags & FOLL_LONGTERM) { mmap_read_lock(current->mm); - ret = __gup_longterm_locked(current, current->mm, + ret = __gup_longterm_locked(current->mm, start, nr_pages, pages, NULL, gup_flags); mmap_read_unlock(current->mm); @@ -2967,10 +2939,8 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages, EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); /** - * pin_user_pages_remote() - pin pages of a remote process (task != current) + * pin_user_pages_remote() - pin pages of a remote process * - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin @@ -2991,7 +2961,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. */ -long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked) @@ -3001,7 +2971,7 @@ long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, return -EINVAL; gup_flags |= FOLL_PIN; - return __get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, + return __get_user_pages_remote(mm, start, nr_pages, gup_flags, pages, vmas, locked); } EXPORT_SYMBOL(pin_user_pages_remote); @@ -3033,7 +3003,7 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, return -EINVAL; gup_flags |= FOLL_PIN; - return __gup_longterm_locked(current, current->mm, start, nr_pages, + return __gup_longterm_locked(current->mm, start, nr_pages, pages, vmas, gup_flags); } EXPORT_SYMBOL(pin_user_pages); @@ -3078,7 +3048,7 @@ long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, return -EINVAL; gup_flags |= FOLL_PIN; - return __get_user_pages_locked(current, current->mm, start, nr_pages, + return __get_user_pages_locked(current->mm, start, nr_pages, pages, NULL, locked, gup_flags | FOLL_TOUCH); } @@ -75,7 +75,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end, } for (; addr < end; addr += PAGE_SIZE) - if (handle_mm_fault(vma, addr, fault_flags) & VM_FAULT_ERROR) + if (handle_mm_fault(vma, addr, fault_flags, NULL) & + VM_FAULT_ERROR) return -EFAULT; return -EBUSY; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0da89305a555..589c330df4db 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1092,15 +1092,6 @@ retry_cpuset: return NULL; } -/* Movability of hugepages depends on migration support. */ -static inline gfp_t htlb_alloc_mask(struct hstate *h) -{ - if (hugepage_movable_supported(h)) - return GFP_HIGHUSER_MOVABLE; - else - return GFP_HIGHUSER; -} - static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, @@ -2022,31 +2013,9 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, } /* page migration callback function */ -struct page *alloc_huge_page_node(struct hstate *h, int nid) -{ - gfp_t gfp_mask = htlb_alloc_mask(h); - struct page *page = NULL; - - if (nid != NUMA_NO_NODE) - gfp_mask |= __GFP_THISNODE; - - spin_lock(&hugetlb_lock); - if (h->free_huge_pages - h->resv_huge_pages > 0) - page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL); - spin_unlock(&hugetlb_lock); - - if (!page) - page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL); - - return page; -} - -/* page migration callback function */ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask) + nodemask_t *nmask, gfp_t gfp_mask) { - gfp_t gfp_mask = htlb_alloc_mask(h); - spin_lock(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) { struct page *page; @@ -2074,7 +2043,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = alloc_huge_page_nodemask(h, node, nodemask); + page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); return page; diff --git a/mm/internal.h b/mm/internal.h index dd14c5311d7f..10c677655912 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -613,5 +613,11 @@ static inline bool is_migrate_highatomic_page(struct page *page) } void setup_zone_pageset(struct zone *zone); -extern struct page *alloc_new_node_page(struct page *page, unsigned long node); + +struct migration_target_control { + int nid; /* preferred node id */ + nodemask_t *nmask; + gfp_t gfp_mask; +}; + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 29a684a4656a..4e644dc074b1 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1169,8 +1169,10 @@ static bool update_checksum(struct kmemleak_object *object) u32 old_csum = object->checksum; kasan_disable_current(); + kcsan_disable_current(); object->checksum = crc32(0, (void *)object->pointer, object->size); kasan_enable_current(); + kcsan_enable_current(); return object->checksum != old_csum; } @@ -480,7 +480,8 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) break; if (PageKsm(page)) ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE); + FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + NULL); else ret = VM_FAULT_WRITE; put_page(page); diff --git a/mm/list_lru.c b/mm/list_lru.c index e825804b3928..5aa6e44bc2ae 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -180,7 +180,7 @@ unsigned long list_lru_count_one(struct list_lru *lru, rcu_read_lock(); l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); - count = l->nr_items; + count = READ_ONCE(l->nr_items); rcu_read_unlock(); return count; diff --git a/mm/madvise.c b/mm/madvise.c index 1fe2e55c0a9b..7b5ca96108cd 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -17,17 +17,20 @@ #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/compat.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <linux/sched/mm.h> +#include <linux/uio.h> #include <asm/tlb.h> @@ -36,6 +39,7 @@ struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; + struct task_struct *target_task; }; /* @@ -255,6 +259,7 @@ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { + struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; @@ -289,12 +294,12 @@ static long madvise_willneed(struct vm_area_struct *vma, */ *prev = NULL; /* tell sys_madvise we drop mmap_lock */ get_file(file); - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return 0; } @@ -315,6 +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; @@ -476,12 +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); @@ -489,7 +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) { @@ -502,19 +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); @@ -538,7 +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) { @@ -554,7 +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; @@ -683,7 +698,6 @@ out: if (nr_swap) { if (current->mm == mm) sync_mm_rss(mm); - add_mm_counter(mm, MM_SWAPENTS, nr_swap); } arch_leave_lazy_mmu_mode(); @@ -763,6 +777,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, unsigned long start, unsigned long end, int behavior) { + struct mm_struct *mm = vma->vm_mm; + *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; @@ -770,8 +786,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_lock has been dropped, prev is stale */ - mmap_read_lock(current->mm); - vma = find_vma(current->mm, start); + mmap_read_lock(mm); + vma = find_vma(mm, start); if (!vma) return -ENOMEM; if (start < vma->vm_start) { @@ -825,6 +841,7 @@ static long madvise_remove(struct vm_area_struct *vma, loff_t offset; int error; struct file *f; + struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_lock */ @@ -852,13 +869,13 @@ static long madvise_remove(struct vm_area_struct *vma, get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); - mmap_read_lock(current->mm); + mmap_read_lock(mm); return error; } @@ -927,7 +944,8 @@ 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) { @@ -936,9 +954,9 @@ 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); @@ -985,6 +1003,18 @@ madvise_behavior_valid(int behavior) } } +static bool +process_madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_COLD: + case MADV_PAGEOUT: + return true; + default: + return false; + } +} + /* * The madvise(2) system call. * @@ -1032,6 +1062,11 @@ madvise_behavior_valid(int behavior) * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. + * MADV_COLD - the application is not expected to use this memory soon, + * deactivate pages in this range so that they can be reclaimed + * easily if memory pressure hanppens. + * MADV_PAGEOUT - the application is not expected to use this memory soon, + * page out the pages in this range immediately. * * return values: * zero - success @@ -1046,7 +1081,8 @@ madvise_behavior_valid(int behavior) * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. */ -int do_madvise(unsigned long start, size_t len_in, int behavior) +int do_madvise(struct task_struct *target_task, struct mm_struct *mm, + unsigned long start, size_t len_in, int behavior) { unsigned long end, tmp; struct vm_area_struct *vma, *prev; @@ -1084,7 +1120,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) write = madvise_need_mmap_write(behavior); if (write) { - if (mmap_write_lock_killable(current->mm)) + if (mmap_write_lock_killable(mm)) return -EINTR; /* @@ -1099,12 +1135,12 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * but for now we have the mmget_still_valid() * model. */ - if (!mmget_still_valid(current->mm)) { - mmap_write_unlock(current->mm); + if (!mmget_still_valid(mm)) { + mmap_write_unlock(mm); return -EINTR; } } else { - mmap_read_lock(current->mm); + mmap_read_lock(mm); } /* @@ -1112,7 +1148,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; @@ -1137,7 +1173,8 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) 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; @@ -1149,19 +1186,122 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_lock */ - vma = find_vma(current->mm, start); + vma = find_vma(mm, start); } out: blk_finish_plug(&plug); if (write) - mmap_write_unlock(current->mm); + mmap_write_unlock(mm); else - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { - return do_madvise(start, len_in, behavior); + return do_madvise(current, current->mm, start, len_in, behavior); +} + +static int process_madvise_vec(struct task_struct *target_task, + struct mm_struct *mm, struct iov_iter *iter, int behavior) +{ + struct iovec iovec; + int ret = 0; + + while (iov_iter_count(iter)) { + iovec = iov_iter_iovec(iter); + ret = do_madvise(target_task, mm, (unsigned long)iovec.iov_base, + iovec.iov_len, behavior); + if (ret < 0) + break; + iov_iter_advance(iter, iovec.iov_len); + } + + return ret; +} + +static ssize_t do_process_madvise(int pidfd, struct iov_iter *iter, + int behavior, unsigned int flags) +{ + ssize_t ret; + struct pid *pid; + struct task_struct *task; + struct mm_struct *mm; + size_t total_len = iov_iter_count(iter); + + if (flags != 0) + return -EINVAL; + + pid = pidfd_get_pid(pidfd); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) { + ret = -ESRCH; + goto put_pid; + } + + if (task->mm != current->mm && + !process_madvise_behavior_valid(behavior)) { + ret = -EINVAL; + goto release_task; + } + + mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS); + if (IS_ERR_OR_NULL(mm)) { + ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + goto release_task; + } + + ret = process_madvise_vec(task, mm, iter, behavior); + if (ret >= 0) + ret = total_len - iov_iter_count(iter); + + mmput(mm); +release_task: + put_task_struct(task); +put_pid: + put_pid(pid); + return ret; +} + +SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, + unsigned long, vlen, int, behavior, unsigned int, flags) +{ + ssize_t ret; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + + ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + ret = do_process_madvise(pidfd, &iter, behavior, flags); + kfree(iov); + } + return ret; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE5(process_madvise, compat_int_t, pidfd, + const struct compat_iovec __user *, vec, + compat_ulong_t, vlen, + compat_int_t, behavior, + compat_uint_t, flags) + +{ + ssize_t ret; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + + ret = compat_import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), + &iov, &iter); + if (ret >= 0) { + ret = do_process_madvise(pidfd, &iter, behavior, flags); + kfree(iov); + } + return ret; } +#endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7359164c3fe9..9523515be997 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1659,13 +1659,6 @@ int unpoison_memory(unsigned long pfn) } EXPORT_SYMBOL(unpoison_memory); -static struct page *new_page(struct page *p, unsigned long private) -{ - int nid = page_to_nid(p); - - return new_page_nodemask(p, nid, &node_states[N_MEMORY]); -} - /* * Safely get reference count of an arbitrary page. * Returns 0 for a free page, -EIO for a zero refcount page @@ -1770,6 +1763,10 @@ static int __soft_offline_page(struct page *page) const char *msg_page[] = {"page", "hugepage"}; bool huge = PageHuge(page); LIST_HEAD(pagelist); + struct migration_target_control mtc = { + .nid = NUMA_NO_NODE, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; /* * Check PageHWPoison again inside page lock because PageHWPoison @@ -1806,8 +1803,8 @@ static int __soft_offline_page(struct page *page) } if (isolate_page(hpage, &pagelist)) { - ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, - MIGRATE_SYNC, MR_MEMORY_FAILURE); + ret = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (!ret) { page_handle_poison(page, true, true, huge); } else { diff --git a/mm/memory.c b/mm/memory.c index 9ffbe8fa08e6..45e1dc0547ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -71,6 +71,8 @@ #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> +#include <linux/perf_event.h> +#include <linux/ptrace.h> #include <trace/events/kmem.h> @@ -3127,8 +3129,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!page) { struct swap_info_struct *si = swp_swap_info(entry); - if (si->flags & SWP_SYNCHRONOUS_IO && - __swap_count(entry) == 1) { + if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); @@ -4366,6 +4368,67 @@ retry_pud: return handle_pte_fault(&vmf); } +/** + * mm_account_fault - Do page fault accountings + * + * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting + * of perf event counters, but we'll still do the per-task accounting to + * the task who triggered this page fault. + * @address: the faulted address. + * @flags: the fault flags. + * @ret: the fault retcode. + * + * This will take care of most of the page fault accountings. Meanwhile, it + * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter + * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should + * still be in per-arch page fault handlers at the entry of page fault. + */ +static inline void mm_account_fault(struct pt_regs *regs, + unsigned long address, unsigned int flags, + vm_fault_t ret) +{ + bool major; + + /* + * We don't do accounting for some specific faults: + * + * - Unsuccessful faults (e.g. when the address wasn't valid). That + * includes arch_vma_access_permitted() failing before reaching here. + * So this is not a "this many hardware page faults" counter. We + * should use the hw profiling for that. + * + * - Incomplete faults (VM_FAULT_RETRY). They will only be counted + * once they're completed. + */ + if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) + return; + + /* + * We define the fault as a major fault when the final successful fault + * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't + * handle it immediately previously). + */ + 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. 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) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); +} + /* * By the time we get here, we already hold the mm semaphore * @@ -4373,7 +4436,7 @@ retry_pud: * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, - unsigned int flags) + unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; @@ -4414,6 +4477,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } + mm_account_fault(regs, address, flags, ret); + return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); @@ -4687,7 +4752,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, void *maddr; struct page *page = NULL; - ret = get_user_pages_remote(tsk, mm, addr, 1, + ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0204de3f9601..dcdf3271f87e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1275,23 +1275,6 @@ found: return 0; } -static struct page *new_node_page(struct page *page, unsigned long private) -{ - int nid = page_to_nid(page); - nodemask_t nmask = node_states[N_MEMORY]; - - /* - * try to allocate from a different node but reuse this node if there - * are no other online nodes to be used (e.g. we are offlining a part - * of the only existing node) - */ - node_clear(nid, nmask); - if (nodes_empty(nmask)) - node_set(nid, nmask); - - return new_page_nodemask(page, nid, &nmask); -} - static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { @@ -1351,9 +1334,28 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) put_page(page); } if (!list_empty(&source)) { - /* Allocate a new page from the nearest neighbor node */ - ret = migrate_pages(&source, new_node_page, NULL, 0, - MIGRATE_SYNC, MR_MEMORY_HOTPLUG); + nodemask_t nmask = node_states[N_MEMORY]; + struct migration_target_control mtc = { + .nmask = &nmask, + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; + + /* + * We have checked that migration range is on a single zone so + * we can use the nid of the first page to all the others. + */ + mtc.nid = page_to_nid(list_first_entry(&source, struct page, lru)); + + /* + * try to allocate from a different node but reuse this node + * if there are no other online nodes to be used (e.g. we are + * offlining a part of the only existing node) + */ + node_clear(mtc.nid, nmask); + if (nodes_empty(nmask)) + node_set(mtc.nid, nmask); + ret = migrate_pages(&source, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) { list_for_each_entry(page, &source, lru) { pr_warn("migrating pfn %lx failed ret:%d ", diff --git a/mm/mempolicy.c b/mm/mempolicy.c index dabcee8630f2..93fcfc1f2fa2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1065,27 +1065,6 @@ static int migrate_page_add(struct page *page, struct list_head *pagelist, return 0; } -/* page allocation callback for NUMA node migration */ -struct page *alloc_new_node_page(struct page *page, unsigned long node) -{ - if (PageHuge(page)) - return alloc_huge_page_node(page_hstate(compound_head(page)), - node); - else if (PageTransHuge(page)) { - struct page *thp; - - thp = alloc_pages_node(node, - (GFP_TRANSHUGE | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } else - return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE, 0); -} - /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. @@ -1096,6 +1075,10 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; + struct migration_target_control mtc = { + .nid = dest, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; nodes_clear(nmask); node_set(source, nmask); @@ -1110,8 +1093,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, alloc_new_node_page, NULL, dest, - MIGRATE_SYNC, MR_SYSCALL); + err = migrate_pages(&pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); } diff --git a/mm/mempool.c b/mm/mempool.c index 85efab3da720..79bff63ecf27 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -489,7 +489,7 @@ void mempool_free(void *element, mempool_t *pool) * ensures that there will be frees which return elements to the * pool waking up the waiters. */ - if (unlikely(pool->curr_nr < pool->min_nr)) { + if (unlikely(READ_ONCE(pool->curr_nr) < pool->min_nr)) { spin_lock_irqsave(&pool->lock, flags); if (likely(pool->curr_nr < pool->min_nr)) { add_element(pool, element); diff --git a/mm/migrate.c b/mm/migrate.c index de0f3662c605..c23378169762 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1533,6 +1533,49 @@ out: return rc; } +struct page *alloc_migration_target(struct page *page, unsigned long private) +{ + struct migration_target_control *mtc; + gfp_t gfp_mask; + unsigned int order = 0; + struct page *new_page = NULL; + int nid; + int zidx; + + mtc = (struct migration_target_control *)private; + gfp_mask = mtc->gfp_mask; + nid = mtc->nid; + if (nid == NUMA_NO_NODE) + nid = page_to_nid(page); + + if (PageHuge(page)) { + struct hstate *h = page_hstate(compound_head(page)); + + gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); + return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); + } + + if (PageTransHuge(page)) { + /* + * clear __GFP_RECLAIM to make the migration callback + * consistent with regular THP allocations. + */ + gfp_mask &= ~__GFP_RECLAIM; + gfp_mask |= GFP_TRANSHUGE; + order = HPAGE_PMD_ORDER; + } + zidx = zone_idx(page_zone(page)); + if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask); + + if (new_page && PageTransHuge(new_page)) + prep_transhuge_page(new_page); + + return new_page; +} + #ifdef CONFIG_NUMA static int store_status(int __user *status, int start, int value, int nr) @@ -1550,9 +1593,13 @@ static int do_move_pages_to_node(struct mm_struct *mm, struct list_head *pagelist, int node) { int err; + struct migration_target_control mtc = { + .nid = node, + .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + }; - err = migrate_pages(pagelist, alloc_new_node_page, NULL, node, - MIGRATE_SYNC, MR_SYSCALL); + err = migrate_pages(pagelist, alloc_migration_target, NULL, + (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(pagelist); return err; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6f4056cf7384..b31f310c2545 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8349,6 +8349,10 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long pfn = start; unsigned int tries = 0; int ret = 0; + struct migration_target_control mtc = { + .nid = zone_to_nid(cc->zone), + .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + }; migrate_prep(); @@ -8375,8 +8379,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; - ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - NULL, 0, cc->mode, MR_CONTIG_RANGE); + ret = migrate_pages(&cc->migratepages, alloc_migration_target, + NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE); } if (ret < 0) { putback_movable_pages(&cc->migratepages); diff --git a/mm/page_counter.c b/mm/page_counter.c index c56db2d5e159..e3a205275a0b 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -77,8 +77,8 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } } @@ -119,9 +119,10 @@ bool page_counter_try_charge(struct page_counter *counter, propagate_protected_usage(counter, new); /* * This is racy, but we can live with some - * inaccuracy in the failcnt. + * inaccuracy in the failcnt which is only used + * to report stats. */ - c->failcnt++; + data_race(c->failcnt++); *fail = c; goto failed; } @@ -130,8 +131,8 @@ bool page_counter_try_charge(struct page_counter *counter, * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } return true; diff --git a/mm/page_io.c b/mm/page_io.c index eaaecb75a8c5..739cb5b458dc 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -85,7 +85,7 @@ static void swap_slot_free_notify(struct page *page) return; sis = page_swap_info(page); - if (!(sis->flags & SWP_BLKDEV)) + if (data_race(!(sis->flags & SWP_BLKDEV))) return; /* @@ -312,7 +312,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -403,7 +403,7 @@ int swap_readpage(struct page *page, bool synchronous) goto out; } - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -465,7 +465,7 @@ int swap_set_page_dirty(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); - if (sis->flags & SWP_FS) { + if (data_race(sis->flags & SWP_FS)) { struct address_space *mapping = sis->swap_file->f_mapping; VM_BUG_ON_PAGE(!PageSwapCache(page), page); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f6d07c5f0d34..242c03121d73 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -306,8 +306,3 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, return pfn < end_pfn ? -EBUSY : 0; } - -struct page *alloc_migrate_target(struct page *page, unsigned long private) -{ - return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]); -} diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index cc85ce81914a..29c052099aff 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -105,7 +105,7 @@ static int process_vm_rw_single_vec(unsigned long addr, * current/current->mm */ mmap_read_lock(mm); - pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages, + pinned_pages = pin_user_pages_remote(mm, pa, pinned_pages, flags, process_pages, NULL, &locked); if (locked) diff --git a/mm/rmap.c b/mm/rmap.c index c56fab5826c1..b970353c06ed 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -672,7 +672,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ void flush_tlb_batched_pending(struct mm_struct *mm) { - if (mm->tlb_flush_batched) { + if (data_race(mm->tlb_flush_batched)) { flush_tlb_mm(mm); /* diff --git a/mm/swap.c b/mm/swap.c index 28ab40041b47..587be74a68de 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -631,7 +631,8 @@ void lru_add_drain_cpu(int cpu) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); - if (pagevec_count(pvec)) { + /* Disabling interrupts below acts as a compiler barrier. */ + if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ @@ -792,7 +793,7 @@ void lru_add_drain_all(void) struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || - pagevec_count(&per_cpu(lru_rotate.pvec, cpu)) || + data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || diff --git a/mm/swap_state.c b/mm/swap_state.c index 1983be226b1c..66e750f361ed 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -57,8 +57,8 @@ static bool enable_vma_readahead __read_mostly = true; #define GET_SWAP_RA_VAL(vma) \ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) -#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) -#define ADD_CACHE_INFO(x, nr) do { swap_cache_info.x += (nr); } while (0) +#define INC_CACHE_INFO(x) data_race(swap_cache_info.x++) +#define ADD_CACHE_INFO(x, nr) data_race(swap_cache_info.x += (nr)) static struct { unsigned long add_total; diff --git a/mm/swapfile.c b/mm/swapfile.c index 7d22347264e6..7b0974f0fcc4 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -672,7 +672,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) - si->highest_bit -= nr_entries; + WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); si->inuse_pages += nr_entries; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; @@ -704,7 +704,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, if (end > si->highest_bit) { bool was_full = !si->highest_bit; - si->highest_bit = end; + WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } @@ -869,7 +869,7 @@ checks: else goto done; } - si->swap_map[offset] = usage; + WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); @@ -928,12 +928,13 @@ done: scan: spin_unlock(&si->lock); - while (++offset <= si->highest_bit) { - if (!si->swap_map[offset]) { + while (++offset <= READ_ONCE(si->highest_bit)) { + if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } @@ -945,11 +946,12 @@ scan: } offset = si->lowest_bit; while (offset < scan_base) { - if (!si->swap_map[offset]) { + if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); goto checks; } - if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + if (vm_swap_full() && + READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } @@ -1148,7 +1150,7 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry) p = swp_swap_info(entry); if (!p) goto bad_nofile; - if (!(p->flags & SWP_USED)) + if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) @@ -1174,7 +1176,7 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry) p = __swap_info_get(entry); if (!p) goto out; - if (!p->swap_map[swp_offset(entry)]) + if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; @@ -1243,7 +1245,10 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } usage = count | has_cache; - p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; + if (usage) + WRITE_ONCE(p->swap_map[offset], usage); + else + WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } @@ -1295,7 +1300,7 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) goto bad_nofile; rcu_read_lock(); - if (!(si->flags & SWP_VALID)) + if (data_race(!(si->flags & SWP_VALID))) goto unlock_out; offset = swp_offset(entry); if (offset >= si->max) @@ -3484,7 +3489,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) } else err = -ENOENT; /* unused swap entry */ - p->swap_map[offset] = count | has_cache; + WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); |