diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/frame_vector.c | 2 | ||||
-rw-r--r-- | mm/gup.c | 4 | ||||
-rw-r--r-- | mm/huge_memory.c | 51 | ||||
-rw-r--r-- | mm/internal.h | 2 | ||||
-rw-r--r-- | mm/madvise.c | 268 | ||||
-rw-r--r-- | mm/memcontrol.c | 15 | ||||
-rw-r--r-- | mm/mempolicy.c | 48 | ||||
-rw-r--r-- | mm/memremap.c | 2 | ||||
-rw-r--r-- | mm/migrate.c | 2 | ||||
-rw-r--r-- | mm/mincore.c | 2 | ||||
-rw-r--r-- | mm/mlock.c | 4 | ||||
-rw-r--r-- | mm/mmap.c | 34 | ||||
-rw-r--r-- | mm/mprotect.c | 2 | ||||
-rw-r--r-- | mm/mremap.c | 3 | ||||
-rw-r--r-- | mm/msync.c | 2 | ||||
-rw-r--r-- | mm/oom_kill.c | 2 | ||||
-rw-r--r-- | mm/page_alloc.c | 30 | ||||
-rw-r--r-- | mm/shmem.c | 8 | ||||
-rw-r--r-- | mm/shuffle.c | 2 | ||||
-rw-r--r-- | mm/slab_common.c | 19 | ||||
-rw-r--r-- | mm/slob.c | 62 | ||||
-rw-r--r-- | mm/slub.c | 14 | ||||
-rw-r--r-- | mm/sparse.c | 2 | ||||
-rw-r--r-- | mm/swap.c | 42 | ||||
-rw-r--r-- | mm/usercopy.c | 8 | ||||
-rw-r--r-- | mm/vmalloc.c | 5 | ||||
-rw-r--r-- | mm/vmpressure.c | 20 | ||||
-rw-r--r-- | mm/vmscan.c | 134 | ||||
-rw-r--r-- | mm/z3fold.c | 10 |
29 files changed, 697 insertions, 102 deletions
diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..c431ca81dad5 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -46,6 +46,8 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) nr_frames = vec->nr_allocated; + start = untagged_addr(start); + down_read(&mm->mmap_sem); locked = 1; vma = find_vma_intersection(mm, start, start + 1); @@ -788,6 +788,8 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (!nr_pages) return 0; + start = untagged_addr(start); + VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); /* @@ -950,6 +952,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, struct vm_area_struct *vma; vm_fault_t ret, major = 0; + address = untagged_addr(address); + if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 73fc517c08d2..c5cb6dcd6c69 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -659,40 +659,30 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - gfp_t this_node = 0; - -#ifdef CONFIG_NUMA - struct mempolicy *pol; - /* - * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not - * specified, to express a general desire to stay on the current - * node for optimistic allocation attempts. If the defrag mode - * and/or madvise hint requires the direct reclaim then we prefer - * to fallback to other node rather than node reclaim because that - * can lead to excessive reclaim even though there is free memory - * on other nodes. We expect that NUMA preferences are specified - * by memory policies. - */ - pol = get_vma_policy(vma, addr); - if (pol->mode != MPOL_BIND) - this_node = __GFP_THISNODE; - mpol_cond_put(pol); -#endif + /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + + /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + + /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM | this_node); + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); + + /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - this_node); - return GFP_TRANSHUGE_LIGHT | this_node; + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + + return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ @@ -764,8 +754,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma, haddr); - page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); + gfp = alloc_hugepage_direct_gfpmask(vma); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1372,9 +1362,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (__transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); - new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, - haddr, numa_node_id()); + huge_gfp = alloc_hugepage_direct_gfpmask(vma); + new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); } else new_page = NULL; diff --git a/mm/internal.h b/mm/internal.h index e32390802fd3..0d5f720c75ab 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -39,7 +39,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); -static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma) +static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } diff --git a/mm/madvise.c b/mm/madvise.c index 68ab988ad433..2be9f3fdb05e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -11,6 +11,7 @@ #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> +#include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> @@ -31,6 +32,11 @@ #include "internal.h" +struct madvise_walk_private { + struct mmu_gather *tlb; + bool pageout; +}; + /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_sem for writing. Others, which simply traverse vmas, need @@ -42,6 +48,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: + case MADV_COLD: + case MADV_PAGEOUT: case MADV_FREE: return 0; default: @@ -289,6 +297,254 @@ static long madvise_willneed(struct vm_area_struct *vma, return 0; } +static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct madvise_walk_private *private = walk->private; + struct mmu_gather *tlb = private->tlb; + bool pageout = private->pageout; + struct mm_struct *mm = tlb->mm; + struct vm_area_struct *vma = walk->vma; + pte_t *orig_pte, *pte, ptent; + spinlock_t *ptl; + struct page *page = NULL; + LIST_HEAD(page_list); + + if (fatal_signal_pending(current)) + return -EINTR; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(*pmd)) { + pmd_t orig_pmd; + unsigned long next = pmd_addr_end(addr, end); + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + + orig_pmd = *pmd; + if (is_huge_zero_pmd(orig_pmd)) + goto huge_unlock; + + if (unlikely(!pmd_present(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !is_pmd_migration_entry(orig_pmd)); + goto huge_unlock; + } + + page = pmd_page(orig_pmd); + if (next - addr != HPAGE_PMD_SIZE) { + int err; + + if (page_mapcount(page) != 1) + goto huge_unlock; + + get_page(page); + spin_unlock(ptl); + lock_page(page); + err = split_huge_page(page); + unlock_page(page); + put_page(page); + if (!err) + goto regular_page; + return 0; + } + + if (pmd_young(orig_pmd)) { + pmdp_invalidate(vma, addr, pmd); + orig_pmd = pmd_mkold(orig_pmd); + + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + } + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) + list_add(&page->lru, &page_list); + } else + deactivate_page(page); +huge_unlock: + spin_unlock(ptl); + if (pageout) + reclaim_pages(&page_list); + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; +regular_page: +#endif + tlb_change_page_size(tlb, PAGE_SIZE); + orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + flush_tlb_batched_pending(mm); + arch_enter_lazy_mmu_mode(); + for (; addr < end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + + if (pte_none(ptent)) + continue; + + if (!pte_present(ptent)) + continue; + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + /* + * Creating a THP page is expensive so split it only if we + * are sure it's worth. Split it if we are only owner. + */ + if (PageTransCompound(page)) { + if (page_mapcount(page) != 1) + break; + get_page(page); + if (!trylock_page(page)) { + put_page(page); + break; + } + pte_unmap_unlock(orig_pte, ptl); + if (split_huge_page(page)) { + unlock_page(page); + put_page(page); + pte_offset_map_lock(mm, pmd, addr, &ptl); + break; + } + unlock_page(page); + put_page(page); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte--; + addr -= PAGE_SIZE; + continue; + } + + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (pte_young(ptent)) { + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + ptent = pte_mkold(ptent); + set_pte_at(mm, addr, pte, ptent); + tlb_remove_tlb_entry(tlb, pte, addr); + } + + /* + * We are deactivating a page for accelerating reclaiming. + * VM couldn't reclaim the page unless we clear PG_young. + * As a side effect, it makes confuse idle-page tracking + * because they will miss recent referenced history. + */ + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (pageout) { + if (!isolate_lru_page(page)) + list_add(&page->lru, &page_list); + } else + deactivate_page(page); + } + + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(orig_pte, ptl); + if (pageout) + reclaim_pages(&page_list); + cond_resched(); + + return 0; +} + +static const struct mm_walk_ops cold_walk_ops = { + .pmd_entry = madvise_cold_or_pageout_pte_range, +}; + +static void madvise_cold_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = false, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static long madvise_cold(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_cold_page_range(&tlb, 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 vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct madvise_walk_private walk_private = { + .pageout = true, + .tlb = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); + tlb_end_vma(tlb, vma); +} + +static inline bool can_do_pageout(struct vm_area_struct *vma) +{ + if (vma_is_anonymous(vma)) + return true; + if (!vma->vm_file) + return false; + /* + * paging out pagecache only for non-anonymous mappings that correspond + * to the files the calling process could (if tried) open for writing; + * otherwise we'd be including shared non-exclusive mappings, which + * opens a side channel. + */ + return inode_owner_or_capable(file_inode(vma->vm_file)) || + inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; +} + +static long madvise_pageout(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start_addr, unsigned long end_addr) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + *prev = vma; + if (!can_madv_lru_vma(vma)) + return -EINVAL; + + if (!can_do_pageout(vma)) + return 0; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start_addr, end_addr); + madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + tlb_finish_mmu(&tlb, start_addr, end_addr); + + return 0; +} + static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -493,7 +749,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, int behavior) { *prev = vma; - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) return -EINVAL; if (!userfaultfd_remove(vma, start, end)) { @@ -515,7 +771,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ return -ENOMEM; } - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) return -EINVAL; if (end > vma->vm_end) { /* @@ -669,6 +925,10 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, return madvise_remove(vma, prev, start, end); case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); + case MADV_COLD: + return madvise_cold(vma, prev, start, end); + case MADV_PAGEOUT: + return madvise_pageout(vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); @@ -690,6 +950,8 @@ madvise_behavior_valid(int behavior) case MADV_WILLNEED: case MADV_DONTNEED: case MADV_FREE: + case MADV_COLD: + case MADV_PAGEOUT: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: @@ -784,6 +1046,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) size_t len; struct blk_plug plug; + start = untagged_addr(start); + if (!madvise_behavior_valid(behavior)) return error; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2156ef775d04..bdac56009a38 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1567,6 +1567,11 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return max; } +unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return page_counter_read(&memcg->memory); +} + static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { @@ -2943,6 +2948,16 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { + + /* + * Enforce __GFP_NOFAIL allocation because callers are not + * prepared to see failures and likely do not have any failure + * handling code. + */ + if (gfp & __GFP_NOFAIL) { + page_counter_charge(&memcg->kmem, nr_pages); + return 0; + } cancel_charge(memcg, nr_pages); return -ENOMEM; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 464406e8da91..4ae967bcf954 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1179,8 +1179,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, - address, numa_node_id()); + thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, + HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1405,6 +1405,7 @@ static long kernel_mbind(unsigned long start, unsigned long len, int err; unsigned short mode_flags; + start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) @@ -1558,6 +1559,8 @@ static int kernel_get_mempolicy(int __user *policy, int uninitialized_var(pval); nodemask_t nodes; + addr = untagged_addr(addr); + if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; @@ -1729,7 +1732,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2078,6 +2081,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2088,7 +2092,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; @@ -2106,6 +2110,42 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { + int hpage_node = node; + + /* + * For hugepage allocation and non-interleave policy which + * allows the current node (or other explicitly preferred + * node) we only try to allocate from the current/preferred + * node and don't fall back to other nodes, as the cost of + * remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) + hpage_node = pol->v.preferred_node; + + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(hpage_node, *nmask)) { + mpol_cond_put(pol); + page = __alloc_pages_node(hpage_node, + gfp | __GFP_THISNODE, order); + + /* + * If hugepage allocations are configured to always + * synchronous compact or the vma has been madvised + * to prefer hugepage backing, retry allowing remote + * memory as well. + */ + if (!page && (gfp & __GFP_DIRECT_RECLAIM)) + page = __alloc_pages_node(hpage_node, + gfp | __GFP_NORETRY, order); + + goto out; + } + } + nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/memremap.c b/mm/memremap.c index 32c79b51af86..68204912cc0a 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -13,8 +13,6 @@ #include <linux/xarray.h> static DEFINE_XARRAY(pgmap_array); -#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) -#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); diff --git a/mm/migrate.c b/mm/migrate.c index 73d476d690b1..4fe45d1428c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1612,7 +1612,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, goto out_flush; if (get_user(node, nodes + i)) goto out_flush; - addr = (unsigned long)p; + addr = (unsigned long)untagged_addr(p); err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) diff --git a/mm/mincore.c b/mm/mincore.c index f9a9dbe8cd33..49b6fa2f6aa1 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -256,6 +256,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len, unsigned long pages; unsigned char *tmp; + start = untagged_addr(start); + /* Check the start address: needs to be page-aligned.. */ if (start & ~PAGE_MASK) return -EINVAL; diff --git a/mm/mlock.c b/mm/mlock.c index a90099da4fb4..a72c1eeded77 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla unsigned long lock_limit; int error = -ENOMEM; + start = untagged_addr(start); + if (!can_do_mlock()) return -EPERM; @@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; + start = untagged_addr(start); + len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; diff --git a/mm/mmap.c b/mm/mmap.c index f1e8c7f93e04..a7d8c84d19b7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -201,6 +201,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) bool downgraded = false; LIST_HEAD(uf); + brk = untagged_addr(brk); + if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -289,9 +291,9 @@ out: return retval; } -static long vma_compute_subtree_gap(struct vm_area_struct *vma) +static inline unsigned long vma_compute_gap(struct vm_area_struct *vma) { - unsigned long max, prev_end, subtree_gap; + unsigned long gap, prev_end; /* * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we @@ -299,14 +301,21 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma) * an unmapped area; whereas when expanding we only require one. * That's a little inconsistent, but keeps the code here simpler. */ - max = vm_start_gap(vma); + gap = vm_start_gap(vma); if (vma->vm_prev) { prev_end = vm_end_gap(vma->vm_prev); - if (max > prev_end) - max -= prev_end; + if (gap > prev_end) + gap -= prev_end; else - max = 0; + gap = 0; } + return gap; +} + +#ifdef CONFIG_DEBUG_VM_RB +static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma) +{ + unsigned long max = vma_compute_gap(vma), subtree_gap; if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; @@ -322,7 +331,6 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma) return max; } -#ifdef CONFIG_DEBUG_VM_RB static int browse_rb(struct mm_struct *mm) { struct rb_root *root = &mm->mm_rb; @@ -428,8 +436,9 @@ static void validate_mm(struct mm_struct *mm) #define validate_mm(mm) do { } while (0) #endif -RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, - unsigned long, rb_subtree_gap, vma_compute_subtree_gap) +RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, + struct vm_area_struct, vm_rb, + unsigned long, rb_subtree_gap, vma_compute_gap) /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or @@ -439,8 +448,8 @@ RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, static void vma_gap_update(struct vm_area_struct *vma) { /* - * As it turns out, RB_DECLARE_CALLBACKS() already created a callback - * function that does exactly what we want. + * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created + * a callback function that does exactly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } @@ -1580,6 +1589,8 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, struct file *file = NULL; unsigned long retval; + addr = untagged_addr(addr); + if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); @@ -2878,6 +2889,7 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { + addr = untagged_addr(addr); profile_munmap(addr); return __vm_munmap(addr, len, true); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 675e5d34a507..7967825f6d33 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -459,6 +459,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len, const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); + start = untagged_addr(start); + prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP); if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */ return -EINVAL; diff --git a/mm/mremap.c b/mm/mremap.c index fc241d23cd97..1fc8a29fbe3f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -606,6 +606,9 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, LIST_HEAD(uf_unmap_early); LIST_HEAD(uf_unmap); + addr = untagged_addr(addr); + new_addr = untagged_addr(new_addr); + if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; diff --git a/mm/msync.c b/mm/msync.c index ef30a429623a..c3bd3e75f687 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) int unmapped_error = 0; int error = -EINVAL; + start = untagged_addr(start); + if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC)) goto out; if (offset_in_page(start)) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c1d9496b4c43..71e3acea7817 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -523,7 +523,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) set_bit(MMF_UNSTABLE, &mm->flags); for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_dontneed_vma(vma)) + if (!can_madv_lru_vma(vma)) continue; /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3334a769eb91..c0b2e0306720 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1175,11 +1175,17 @@ static __always_inline bool free_pages_prepare(struct page *page, debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } - arch_free_page(page, order); if (want_init_on_free()) kernel_init_free_pages(page, 1 << order); kernel_poison_pages(page, 1 << order, 0); + /* + * arch_free_page() can make the page's contents inaccessible. s390 + * does this. So nothing which can access the page's contents should + * happen after this. + */ + arch_free_page(page, order); + if (debug_pagealloc_enabled()) kernel_map_pages(page, 1 << order, 0); @@ -4467,6 +4473,28 @@ retry_cpuset: if (page) goto got_pg; + if (order >= pageblock_order && (gfp_mask & __GFP_IO)) { + /* + * If allocating entire pageblock(s) and compaction + * failed because all zones are below low watermarks + * or is prohibited because it recently failed at this + * order, fail immediately. + * + * Reclaim is + * - potentially very expensive because zones are far + * below their low watermarks or this is part of very + * bursty high order allocations, + * - not guaranteed to help because isolate_freepages() + * may not iterate over freed pages as part of its + * linear scan, and + * - unlikely to make entire pageblocks free on its + * own. + */ + if (compact_result == COMPACT_SKIPPED || + compact_result == COMPACT_DEFERRED) + goto nopage; + } + /* * Checks for costly allocations with __GFP_NORETRY, which * includes THP page fault allocations diff --git a/mm/shmem.c b/mm/shmem.c index 30ce722c23fa..220be9fa2c41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1481,7 +1481,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); @@ -3482,6 +3482,12 @@ static int shmem_parse_options(struct fs_context *fc, void *data) { char *options = data; + if (options) { + int err = security_sb_eat_lsm_opts(options, &fc->security); + if (err) + return err; + } + while (options != NULL) { char *this_char = options; for (;;) { diff --git a/mm/shuffle.c b/mm/shuffle.c index 3ce12481b1dc..b3fe97fd6654 100644 --- a/mm/shuffle.c +++ b/mm/shuffle.c @@ -33,7 +33,7 @@ __meminit void page_alloc_shuffle(enum mm_shuffle_ctl ctl) } static bool shuffle_param; -extern int shuffle_show(char *buffer, const struct kernel_param *kp) +static int shuffle_show(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c\n", test_bit(SHUFFLE_ENABLE, &shuffle_state) ? 'Y' : 'N'); diff --git a/mm/slab_common.c b/mm/slab_common.c index 6491c3a41805..c29f03adca91 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1030,10 +1030,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, unsigned int useroffset, unsigned int usersize) { int err; + unsigned int align = ARCH_KMALLOC_MINALIGN; s->name = name; s->size = s->object_size = size; - s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size); + + /* + * For power of two sizes, guarantee natural alignment for kmalloc + * caches, regardless of SL*B debugging options. + */ + if (is_power_of_2(size)) + align = max(align, size); + s->align = calculate_alignment(flags, align, size); + s->useroffset = useroffset; s->usersize = usersize; @@ -1287,12 +1296,16 @@ void __init create_kmalloc_caches(slab_flags_t flags) */ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) { - void *ret; + void *ret = NULL; struct page *page; flags |= __GFP_COMP; page = alloc_pages(flags, order); - ret = page ? page_address(page) : NULL; + if (likely(page)) { + ret = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } ret = kasan_kmalloc_large(ret, size, flags); /* As ret might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ret, size, 1, flags); diff --git a/mm/slob.c b/mm/slob.c index cf377beab962..fa53e9f73893 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -190,7 +190,7 @@ static int slob_last(slob_t *s) static void *slob_new_pages(gfp_t gfp, int order, int node) { - void *page; + struct page *page; #ifdef CONFIG_NUMA if (node != NUMA_NO_NODE) @@ -202,14 +202,21 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) if (!page) return NULL; + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); return page_address(page); } static void slob_free_pages(void *b, int order) { + struct page *sp = virt_to_page(b); + if (current->reclaim_state) current->reclaim_state->reclaimed_slab += 1 << order; - free_pages((unsigned long)b, order); + + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); } /* @@ -217,6 +224,7 @@ static void slob_free_pages(void *b, int order) * @sp: Page to look in. * @size: Size of the allocation. * @align: Allocation alignment. + * @align_offset: Offset in the allocated block that will be aligned. * @page_removed_from_list: Return parameter. * * Tries to find a chunk of memory at least @size bytes big within @page. @@ -227,7 +235,7 @@ static void slob_free_pages(void *b, int order) * true (set to false otherwise). */ static void *slob_page_alloc(struct page *sp, size_t size, int align, - bool *page_removed_from_list) + int align_offset, bool *page_removed_from_list) { slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); @@ -236,8 +244,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { slobidx_t avail = slob_units(cur); + /* + * 'aligned' will hold the address of the slob block so that the + * address 'aligned'+'align_offset' is aligned according to the + * 'align' parameter. This is for kmalloc() which prepends the + * allocated block with its size, so that the block itself is + * aligned when needed. + */ if (align) { - aligned = (slob_t *)ALIGN((unsigned long)cur, align); + aligned = (slob_t *) + (ALIGN((unsigned long)cur + align_offset, align) + - align_offset); delta = aligned - cur; } if (avail >= units + delta) { /* room enough? */ @@ -281,7 +298,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, /* * slob_alloc: entry point into the slob allocator. */ -static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) +static void *slob_alloc(size_t size, gfp_t gfp, int align, int node, + int align_offset) { struct page *sp; struct list_head *slob_list; @@ -312,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) if (sp->units < SLOB_UNITS(size)) continue; - b = slob_page_alloc(sp, size, align, &page_removed_from_list); + b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list); if (!b) continue; @@ -349,7 +367,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) INIT_LIST_HEAD(&sp->slab_list); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); - b = slob_page_alloc(sp, size, align, &_unused); + b = slob_page_alloc(sp, size, align, align_offset, &_unused); BUG_ON(!b); spin_unlock_irqrestore(&slob_lock, flags); } @@ -451,7 +469,7 @@ static __always_inline void * __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; - int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; gfp &= gfp_allowed_mask; @@ -459,19 +477,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) fs_reclaim_acquire(gfp); fs_reclaim_release(gfp); - if (size < PAGE_SIZE - align) { + if (size < PAGE_SIZE - minalign) { + int align = minalign; + + /* + * For power of two sizes, guarantee natural alignment for + * kmalloc()'d objects. + */ + if (is_power_of_2(size)) + align = max(minalign, (int) size); + if (!size) return ZERO_SIZE_PTR; - m = slob_alloc(size + align, gfp, align, node); + m = slob_alloc(size + minalign, gfp, align, node, minalign); if (!m) return NULL; *m = size; - ret = (void *)m + align; + ret = (void *)m + minalign; trace_kmalloc_node(caller, ret, - size, size + align, gfp, node); + size, size + minalign, gfp, node); } else { unsigned int order = get_order(size); @@ -521,8 +548,13 @@ void kfree(const void *block) int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); - } else - __free_pages(sp, compound_order(sp)); + } else { + unsigned int order = compound_order(sp); + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); + + } } EXPORT_SYMBOL(kfree); @@ -567,7 +599,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) fs_reclaim_release(flags); if (c->size < PAGE_SIZE) { - b = slob_alloc(c->size, flags, c->align, node); + b = slob_alloc(c->size, flags, c->align, node, 0); trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size, SLOB_UNITS(c->size) * SLOB_UNIT, flags, node); diff --git a/mm/slub.c b/mm/slub.c index 42c1b3af3c98..3d63ae320d31 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3821,11 +3821,15 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) { struct page *page; void *ptr = NULL; + unsigned int order = get_order(size); flags |= __GFP_COMP; - page = alloc_pages_node(node, flags, get_order(size)); - if (page) + page = alloc_pages_node(node, flags, order); + if (page) { ptr = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } return kmalloc_large_node_hook(ptr, size, flags); } @@ -3951,9 +3955,13 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { + unsigned int order = compound_order(page); + BUG_ON(!PageCompound(page)); kfree_hook(object); - __free_pages(page, compound_order(page)); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(page, order); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); diff --git a/mm/sparse.c b/mm/sparse.c index bf32de9e666b..f6891c1992b1 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -219,7 +219,7 @@ static inline unsigned long first_present_section_nr(void) return next_present_section_nr(-1); } -void subsection_mask_set(unsigned long *map, unsigned long pfn, +static void subsection_mask_set(unsigned long *map, unsigned long pfn, unsigned long nr_pages) { int idx = subsection_map_index(pfn); diff --git a/mm/swap.c b/mm/swap.c index 784dc1620620..38c3fa4308e2 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -47,6 +47,7 @@ int page_cluster; static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs); #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); @@ -538,6 +539,22 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, update_page_reclaim_stat(lruvec, file, 0); } +static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + int file = page_is_file_cache(page); + int lru = page_lru_base_type(page); + + del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + ClearPageActive(page); + ClearPageReferenced(page); + add_page_to_lru_list(page, lruvec, lru); + + __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); + update_page_reclaim_stat(lruvec, file, 0); + } +} static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) @@ -590,6 +607,10 @@ void lru_add_drain_cpu(int cpu) if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + pvec = &per_cpu(lru_deactivate_pvecs, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + pvec = &per_cpu(lru_lazyfree_pvecs, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); @@ -623,6 +644,26 @@ void deactivate_file_page(struct page *page) } } +/* + * deactivate_page - deactivate a page + * @page: page to deactivate + * + * deactivate_page() moves @page to the inactive list if @page was on the active + * list and was not an unevictable page. This is done to accelerate the reclaim + * of @page. + */ +void deactivate_page(struct page *page) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + put_cpu_var(lru_deactivate_pvecs); + } +} + /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate @@ -687,6 +728,7 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); diff --git a/mm/usercopy.c b/mm/usercopy.c index 98e924864554..660717a1ea5c 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> @@ -227,7 +228,12 @@ static inline void check_heap_object(const void *ptr, unsigned long n, if (!virt_addr_valid(ptr)) return; - page = virt_to_head_page(ptr); + /* + * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the + * highmem page or fallback to virt_to_page(). The following + * is effectively a highmem-aware virt_to_head_page(). + */ + page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index fcadd3e25c0c..a3c70e275f4e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -396,9 +396,8 @@ compute_subtree_max_size(struct vmap_area *va) get_subtree_max_size(va->rb_node.rb_right)); } -RB_DECLARE_CALLBACKS(static, free_vmap_area_rb_augment_cb, - struct vmap_area, rb_node, unsigned long, subtree_max_size, - compute_subtree_max_size) +RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, + struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void purge_vmap_area_lazy(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index f3b50811497a..4bac22fe1aa2 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * "hierarchy" or "local"). * * To be used as memcg event method. + * + * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could + * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) @@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; - enum vmpressure_levels level = -1; + enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; @@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg, /* Find required level */ token = strsep(&spec, ","); - level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); - if (level < 0) { - ret = level; + ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); + if (ret < 0) goto out; - } + level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { - mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); - if (mode < 0) { - ret = mode; + ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); + if (ret < 0) goto out; - } + mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); + ret = 0; out: kfree(spec_orig); return ret; diff --git a/mm/vmscan.c b/mm/vmscan.c index 4911754c93b7..c6659bb758a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1123,7 +1123,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct scan_control *sc, enum ttu_flags ttu_flags, struct reclaim_stat *stat, - bool force_reclaim) + bool ignore_references) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); @@ -1137,7 +1137,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct address_space *mapping; struct page *page; int may_enter_fs; - enum page_references references = PAGEREF_RECLAIM_CLEAN; + enum page_references references = PAGEREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; @@ -1268,7 +1268,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!force_reclaim) + if (!ignore_references) references = page_check_references(page, sc); switch (references) { @@ -2145,6 +2145,62 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_deactivate, nr_rotated, sc->priority, file); } +unsigned long reclaim_pages(struct list_head *page_list) +{ + int nid = -1; + unsigned long nr_reclaimed = 0; + LIST_HEAD(node_page_list); + struct reclaim_stat dummy_stat; + struct page *page; + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .priority = DEF_PRIORITY, + .may_writepage = 1, + .may_unmap = 1, + .may_swap = 1, + }; + + while (!list_empty(page_list)) { + page = lru_to_page(page_list); + if (nid == -1) { + nid = page_to_nid(page); + INIT_LIST_HEAD(&node_page_list); + } + + if (nid == page_to_nid(page)) { + ClearPageActive(page); + list_move(&page->lru, &node_page_list); + continue; + } + + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, 0, + &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + + nid = -1; + } + + if (!list_empty(&node_page_list)) { + nr_reclaimed += shrink_page_list(&node_page_list, + NODE_DATA(nid), + &sc, 0, + &dummy_stat, false); + while (!list_empty(&node_page_list)) { + page = lru_to_page(&node_page_list); + list_del(&page->lru); + putback_lru_page(page); + } + } + + return nr_reclaimed; +} + /* * The inactive anon list should be small enough that the VM never has * to do too much work. @@ -2403,17 +2459,70 @@ out: *lru_pages = 0; for_each_evictable_lru(lru) { int file = is_file_lru(lru); - unsigned long size; + unsigned long lruvec_size; unsigned long scan; + unsigned long protection; + + lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + protection = mem_cgroup_protection(memcg, + sc->memcg_low_reclaim); + + if (protection) { + /* + * Scale a cgroup's reclaim pressure by proportioning + * its current usage to its memory.low or memory.min + * setting. + * + * This is important, as otherwise scanning aggression + * becomes extremely binary -- from nothing as we + * approach the memory protection threshold, to totally + * nominal as we exceed it. This results in requiring + * setting extremely liberal protection thresholds. It + * also means we simply get no protection at all if we + * set it too low, which is not ideal. + * + * If there is any protection in place, we reduce scan + * pressure by how much of the total memory used is + * within protection thresholds. + * + * There is one special case: in the first reclaim pass, + * we skip over all groups that are within their low + * protection. If that fails to reclaim enough pages to + * satisfy the reclaim goal, we come back and override + * the best-effort low protection. However, we still + * ideally want to honor how well-behaved groups are in + * that case instead of simply punishing them all + * equally. As such, we reclaim them based on how much + * memory they are using, reducing the scan pressure + * again by how much of the total memory used is under + * hard protection. + */ + unsigned long cgroup_size = mem_cgroup_size(memcg); + + /* Avoid TOCTOU with earlier protection check */ + cgroup_size = max(cgroup_size, protection); + + scan = lruvec_size - lruvec_size * protection / + cgroup_size; + + /* + * Minimally target SWAP_CLUSTER_MAX pages to keep + * reclaim moving forwards, avoiding decremeting + * sc->priority further than desirable. + */ + scan = max(scan, SWAP_CLUSTER_MAX); + } else { + scan = lruvec_size; + } + + scan >>= sc->priority; - size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - scan = size >> sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) - scan = min(size, SWAP_CLUSTER_MAX); + scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: @@ -2433,7 +2542,7 @@ out: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) { - size = 0; + lruvec_size = 0; scan = 0; } break; @@ -2442,7 +2551,7 @@ out: BUG(); } - *lru_pages += size; + *lru_pages += lruvec_size; nr[lru] = scan; } } @@ -2686,6 +2795,13 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) memcg_memory_event(memcg, MEMCG_LOW); break; case MEMCG_PROT_NONE: + /* + * All protection thresholds breached. We may + * still choose to vary the scan pressure + * applied based on by how much the cgroup in + * question has exceeded its protection + * thresholds (see get_scan_count). + */ break; } diff --git a/mm/z3fold.c b/mm/z3fold.c index 05bdf90646e7..6d3d3f698ebb 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) struct z3fold_header *zhdr; struct page *page; enum buddy bud; + bool page_claimed; zhdr = handle_to_z3fold_header(handle); page = virt_to_page(zhdr); + page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); if (test_bit(PAGE_HEADLESS, &page->private)) { /* if a headless page is under reclaim, just leave. @@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) * has not been set before, we release this page * immediately so we don't care about its value any more. */ - if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) { + if (!page_claimed) { spin_lock(&pool->lock); list_del(&page->lru); spin_unlock(&pool->lock); @@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(PAGE_CLAIMED, &page->private)) { + if (page_claimed) { + /* the page has not been claimed by us */ z3fold_page_unlock(zhdr); return; } if (unlikely(PageIsolated(page)) || test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); return; } if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { @@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) zhdr->cpu = -1; kref_get(&zhdr->refcount); do_compact_page(zhdr, true); + clear_bit(PAGE_CLAIMED, &page->private); return; } kref_get(&zhdr->refcount); queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } |