diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/filemap.c | 148 | ||||
-rw-r--r-- | mm/gup.c | 10 | ||||
-rw-r--r-- | mm/huge_memory.c | 38 | ||||
-rw-r--r-- | mm/hugetlb.c | 23 | ||||
-rw-r--r-- | mm/memblock.c | 2 | ||||
-rw-r--r-- | mm/memcontrol.c | 2 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 1 | ||||
-rw-r--r-- | mm/mempolicy.c | 35 | ||||
-rw-r--r-- | mm/page_alloc.c | 28 | ||||
-rw-r--r-- | mm/page_io.c | 4 | ||||
-rw-r--r-- | mm/page_poison.c | 6 | ||||
-rw-r--r-- | mm/percpu.c | 2 | ||||
-rw-r--r-- | mm/shmem.c | 6 | ||||
-rw-r--r-- | mm/swapfile.c | 6 | ||||
-rw-r--r-- | mm/vmstat.c | 7 | ||||
-rw-r--r-- | mm/z3fold.c | 101 |
16 files changed, 280 insertions, 139 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 218d0b2ec82d..81adec8ee02c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2049,7 +2049,7 @@ find_page: !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ - if (unlikely(iter->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; @@ -2825,6 +2825,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping, EXPORT_SYMBOL(read_cache_page_gfp); /* + * Don't operate on ranges the page cache doesn't support, and don't exceed the + * LFS limits. If pos is under the limit it becomes a short access. If it + * exceeds the limit we return -EFBIG. + */ +static int generic_access_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + struct inode *inode = file->f_mapping->host; + loff_t max_size = inode->i_sb->s_maxbytes; + + if (!(file->f_flags & O_LARGEFILE)) + max_size = MAX_NON_LFS; + + if (unlikely(pos >= max_size)) + return -EFBIG; + *count = min(*count, max_size - pos); + return 0; +} + +static int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + loff_t limit = rlimit(RLIMIT_FSIZE); + + if (limit != RLIM_INFINITY) { + if (pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + *count = min(*count, limit - pos); + } + + return generic_access_check_limits(file, pos, count); +} + +/* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. @@ -2835,8 +2871,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - unsigned long limit = rlimit(RLIMIT_FSIZE); - loff_t pos; + loff_t count; + int ret; if (!iov_iter_count(from)) return 0; @@ -2845,43 +2881,99 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); - pos = iocb->ki_pos; - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) return -EINVAL; - if (limit != RLIM_INFINITY) { - if (iocb->ki_pos >= limit) { - send_sig(SIGXFSZ, current, 0); - return -EFBIG; - } - iov_iter_truncate(from, limit - (unsigned long)pos); - } + count = iov_iter_count(from); + ret = generic_write_check_limits(file, iocb->ki_pos, &count); + if (ret) + return ret; + + iov_iter_truncate(from, count); + return iov_iter_count(from); +} +EXPORT_SYMBOL(generic_write_checks); + +/* + * Performs necessary checks before doing a clone. + * + * Can adjust amount of bytes to clone. + * Returns appropriate error code that caller should return or + * zero in case the clone should be allowed. + */ +int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *req_count, unsigned int remap_flags) +{ + struct inode *inode_in = file_in->f_mapping->host; + struct inode *inode_out = file_out->f_mapping->host; + uint64_t count = *req_count; + uint64_t bcount; + loff_t size_in, size_out; + loff_t bs = inode_out->i_sb->s_blocksize; + int ret; + + /* The start of both ranges must be aligned to an fs block. */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) + return -EINVAL; + + /* Ensure offsets don't wrap. */ + if (pos_in + count < pos_in || pos_out + count < pos_out) + return -EINVAL; + + size_in = i_size_read(inode_in); + size_out = i_size_read(inode_out); + + /* Dedupe requires both ranges to be within EOF. */ + if ((remap_flags & REMAP_FILE_DEDUP) && + (pos_in >= size_in || pos_in + count > size_in || + pos_out >= size_out || pos_out + count > size_out)) + return -EINVAL; + + /* Ensure the infile range is within the infile. */ + if (pos_in >= size_in) + return -EINVAL; + count = min(count, size_in - (uint64_t)pos_in); + + ret = generic_access_check_limits(file_in, pos_in, &count); + if (ret) + return ret; + + ret = generic_write_check_limits(file_out, pos_out, &count); + if (ret) + return ret; /* - * LFS rule + * If the user wanted us to link to the infile's EOF, round up to the + * next block boundary for this check. + * + * Otherwise, make sure the count is also block-aligned, having + * already confirmed the starting offsets' block alignment. */ - if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS && - !(file->f_flags & O_LARGEFILE))) { - if (pos >= MAX_NON_LFS) - return -EFBIG; - iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos); + if (pos_in + count == size_in) { + bcount = ALIGN(size_in, bs) - pos_in; + } else { + if (!IS_ALIGNED(count, bs)) + count = ALIGN_DOWN(count, bs); + bcount = count; } + /* Don't allow overlapped cloning within the same file. */ + if (inode_in == inode_out && + pos_out + bcount > pos_in && + pos_out < pos_in + bcount) + return -EINVAL; + /* - * Are we about to exceed the fs block limit ? - * - * If we have written data it becomes a short write. If we have - * exceeded without writing data we send a signal and return EFBIG. - * Linus frestrict idea will clean these up nicely.. + * We shortened the request but the caller can't deal with that, so + * bounce the request back to userspace. */ - if (unlikely(pos >= inode->i_sb->s_maxbytes)) - return -EFBIG; + if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return -EINVAL; - iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos); - return iov_iter_count(from); + *req_count = count; + return 0; } -EXPORT_SYMBOL(generic_write_checks); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, @@ -385,11 +385,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour - * @page_mask: on output, *page_mask is set according to the size of the page + * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a + * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * - * Returns the mapped (struct page *), %NULL if no mapping exists, or + * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches + * the device's dev_pagemap metadata to avoid repeating expensive lookups. + * + * On output, the @ctx->page_mask is set according to the size of the page. + * + * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4e4ef8fa479d..55478ab3c83b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -629,21 +629,40 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { 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 if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; 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); + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - 0); - return GFP_TRANSHUGE_LIGHT; + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ @@ -715,8 +734,8 @@ 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); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1286,8 +1305,9 @@ 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); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c007fb5fb8d5..7f2a28ab46d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3233,7 +3233,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { - pte_t *src_pte, *dst_pte, entry; + pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; int cow; @@ -3261,15 +3261,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, break; } - /* If the pagetables are shared don't copy or take references */ - if (dst_pte == src_pte) + /* + * If the pagetables are shared don't copy or take references. + * dst_pte == src_pte is the common case of src/dest sharing. + * + * However, src could have 'unshared' and dst shares with + * another vma. If dst_pte !none, this implies sharing. + * Check here before taking page table lock, and once again + * after taking the lock below. + */ + dst_entry = huge_ptep_get(dst_pte); + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) continue; dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); - if (huge_pte_none(entry)) { /* skip none entry */ + dst_entry = huge_ptep_get(dst_pte); + if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { + /* + * Skip if src entry none. Also, skip in the + * unlikely case dst entry !none as this implies + * sharing with another vma. + */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { diff --git a/mm/memblock.c b/mm/memblock.c index 7df468c8ebc8..9a2d5ae81ae1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1179,7 +1179,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * Common iterator interface used to define for_each_mem_range(). + * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 54920cbc46bf..6e1469b80cb7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2593,7 +2593,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) struct mem_cgroup *memcg; int ret = 0; - if (memcg_kmem_bypass()) + if (mem_cgroup_disabled() || memcg_kmem_bypass()) return 0; memcg = get_mem_cgroup_from_current(); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 61972da38d93..2b2b3ccbbfb5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -586,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; + cond_resched(); ret = __remove_section(zone, __pfn_to_section(pfn), map_offset, altmap); map_offset = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cfd26d7e61a1..5837a067124d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1662,7 +1662,7 @@ 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. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2011,7 +2011,6 @@ 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. @@ -2022,7 +2021,7 @@ 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, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2040,32 +2039,6 @@ 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); - 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/page_alloc.c b/mm/page_alloc.c index a919ba5cb3c8..6847177dc4a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4061,17 +4061,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int reserve_flags; /* - * In the slowpath, we sanity check order to avoid ever trying to - * reclaim >= MAX_ORDER areas which will never succeed. Callers may - * be using allocators in order of preference for an area that is - * too large. - */ - if (order >= MAX_ORDER) { - WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); - return NULL; - } - - /* * We also sanity check to catch abuse of atomic reserves being used by * callers that are not in atomic context. */ @@ -4364,6 +4353,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { }; + /* + * There are several places where we assume that the order value is sane + * so bail out early if the request is out of bound. + */ + if (unlikely(order >= MAX_ORDER)) { + WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); + return NULL; + } + gfp_mask &= gfp_allowed_mask; alloc_mask = gfp_mask; if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)) @@ -7789,6 +7787,14 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, goto unmovable; /* + * If the zone is movable and we have ruled out all reserved + * pages then it should be reasonably safe to assume the rest + * is movable. + */ + if (zone_idx(zone) == ZONE_MOVABLE) + continue; + + /* * Hugepages are not in LRU lists, but they're movable. * We need not scan over tail pages bacause we don't * handle each tail page individually in migration. diff --git a/mm/page_io.c b/mm/page_io.c index a451ffa9491c..d4d1c89bcddd 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, }; struct iov_iter from; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); @@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); - bio_associate_blkg_from_page(bio, page); + bio_associate_blkcg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); diff --git a/mm/page_poison.c b/mm/page_poison.c index f7e2a676365a..f0c15e9017c0 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -17,6 +17,11 @@ static int __init early_page_poison_param(char *buf) } early_param("page_poison", early_page_poison_param); +/** + * page_poisoning_enabled - check if page poisoning is enabled + * + * Return true if page poisoning is enabled, or false if not. + */ bool page_poisoning_enabled(void) { /* @@ -29,6 +34,7 @@ bool page_poisoning_enabled(void) (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && debug_pagealloc_enabled())); } +EXPORT_SYMBOL_GPL(page_poisoning_enabled); static void poison_page(struct page *page) { diff --git a/mm/percpu.c b/mm/percpu.c index a6b74c6fe0be..db86282fd024 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2591,7 +2591,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); - if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) { + if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } diff --git a/mm/shmem.c b/mm/shmem.c index 56bf122e0bb4..d44991ea5ed4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1435,7 +1435,7 @@ 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(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); @@ -2563,9 +2563,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) + if (offset < 0 || offset >= inode->i_size) offset = -ENXIO; else { start = offset >> PAGE_SHIFT; diff --git a/mm/swapfile.c b/mm/swapfile.c index 644f746e167a..8688ae65ef58 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void) unsigned int type; int i; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kvzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); - kfree(p); + kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); nr_swapfiles++; } else { - kfree(p); + kvfree(p); p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() diff --git a/mm/vmstat.c b/mm/vmstat.c index 6038ce593ce3..9c624595e904 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1827,12 +1827,13 @@ static bool need_update(int cpu) /* * The fast way of checking if there are any vmstat diffs. - * This works because the diffs are byte sized items. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS)) + if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(p->vm_stat_diff[0]))) return true; #ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS)) + if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * + sizeof(p->vm_numa_stat_diff[0]))) return true; #endif } diff --git a/mm/z3fold.c b/mm/z3fold.c index 4b366d181f35..aee9b0b8d907 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -99,6 +99,7 @@ struct z3fold_header { #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) #define BUDDY_MASK (0x3) +#define BUDDY_SHIFT 2 /** * struct z3fold_pool - stores metadata for each z3fold pool @@ -145,7 +146,7 @@ enum z3fold_page_flags { MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, PAGE_STALE, - UNDER_RECLAIM + PAGE_CLAIMED, /* by either reclaim or free */ }; /***************** @@ -174,7 +175,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -223,8 +224,11 @@ static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) unsigned long handle; handle = (unsigned long)zhdr; - if (bud != HEADLESS) - handle += (bud + zhdr->first_num) & BUDDY_MASK; + if (bud != HEADLESS) { + handle |= (bud + zhdr->first_num) & BUDDY_MASK; + if (bud == LAST) + handle |= (zhdr->last_chunks << BUDDY_SHIFT); + } return handle; } @@ -234,6 +238,12 @@ static struct z3fold_header *handle_to_z3fold_header(unsigned long handle) return (struct z3fold_header *)(handle & PAGE_MASK); } +/* only for LAST bud, returns zero otherwise */ +static unsigned short handle_to_chunks(unsigned long handle) +{ + return (handle & ~PAGE_MASK) >> BUDDY_SHIFT; +} + /* * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle * but that doesn't matter. because the masking will result in the @@ -720,37 +730,39 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) { - /* HEADLESS page stored */ - bud = HEADLESS; - } else { - z3fold_page_lock(zhdr); - bud = handle_to_buddy(handle); - - switch (bud) { - case FIRST: - zhdr->first_chunks = 0; - break; - case MIDDLE: - zhdr->middle_chunks = 0; - zhdr->start_middle = 0; - break; - case LAST: - zhdr->last_chunks = 0; - break; - default: - pr_err("%s: unknown bud %d\n", __func__, bud); - WARN_ON(1); - z3fold_page_unlock(zhdr); - return; + /* if a headless page is under reclaim, just leave. + * NB: we use test_and_set_bit for a reason: if the bit + * 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)) { + spin_lock(&pool->lock); + list_del(&page->lru); + spin_unlock(&pool->lock); + free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); } + return; } - if (bud == HEADLESS) { - spin_lock(&pool->lock); - list_del(&page->lru); - spin_unlock(&pool->lock); - free_z3fold_page(page); - atomic64_dec(&pool->pages_nr); + /* Non-headless case */ + z3fold_page_lock(zhdr); + bud = handle_to_buddy(handle); + + switch (bud) { + case FIRST: + zhdr->first_chunks = 0; + break; + case MIDDLE: + zhdr->middle_chunks = 0; + break; + case LAST: + zhdr->last_chunks = 0; + break; + default: + pr_err("%s: unknown bud %d\n", __func__, bud); + WARN_ON(1); + z3fold_page_unlock(zhdr); return; } @@ -758,7 +770,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(UNDER_RECLAIM, &page->private)) { + if (test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); return; } @@ -836,20 +848,30 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) } list_for_each_prev(pos, &pool->lru) { page = list_entry(pos, struct page, lru); + + /* this bit could have been set by free, in which case + * we pass over to the next page in the pool. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + + zhdr = page_address(page); if (test_bit(PAGE_HEADLESS, &page->private)) - /* candidate found */ break; - zhdr = page_address(page); - if (!z3fold_page_trylock(zhdr)) + if (!z3fold_page_trylock(zhdr)) { + zhdr = NULL; continue; /* can't evict at this point */ + } kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; - set_bit(UNDER_RECLAIM, &page->private); break; } + if (!zhdr) + break; + list_del_init(&page->lru); spin_unlock(&pool->lock); @@ -898,6 +920,7 @@ next: if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); return 0; } spin_lock(&pool->lock); @@ -905,7 +928,7 @@ next: spin_unlock(&pool->lock); } else { z3fold_page_lock(zhdr); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { atomic64_dec(&pool->pages_nr); @@ -964,7 +987,7 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) set_bit(MIDDLE_CHUNK_MAPPED, &page->private); break; case LAST: - addr += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT); break; default: pr_err("unknown buddy id %d\n", buddy); |