diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/filemap.c | 33 | ||||
| -rw-r--r-- | mm/hugetlb.c | 2 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 5 | ||||
| -rw-r--r-- | mm/ksm.c | 8 | ||||
| -rw-r--r-- | mm/memcontrol.c | 41 | ||||
| -rw-r--r-- | mm/memory-failure.c | 14 | ||||
| -rw-r--r-- | mm/memory.c | 21 | ||||
| -rw-r--r-- | mm/page-writeback.c | 6 | ||||
| -rw-r--r-- | mm/page_alloc.c | 31 | ||||
| -rw-r--r-- | mm/percpu.c | 3 |
10 files changed, 95 insertions, 69 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index dafb06f70a0..65d44fd88c7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -241,18 +241,6 @@ void delete_from_page_cache(struct page *page) } EXPORT_SYMBOL(delete_from_page_cache); -static int sleep_on_page(void *word) -{ - io_schedule(); - return 0; -} - -static int sleep_on_page_killable(void *word) -{ - sleep_on_page(word); - return fatal_signal_pending(current) ? -EINTR : 0; -} - static int filemap_check_errors(struct address_space *mapping) { int ret = 0; @@ -692,7 +680,7 @@ void wait_on_page_bit(struct page *page, int bit_nr) DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); if (test_bit(bit_nr, &page->flags)) - __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_on_page_bit); @@ -705,7 +693,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) return 0; return __wait_on_bit(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } /** @@ -806,7 +794,7 @@ void __lock_page(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); @@ -816,7 +804,7 @@ int __lock_page_killable(struct page *page) DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); return __wait_on_bit_lock(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); @@ -1031,18 +1019,21 @@ EXPORT_SYMBOL(find_lock_entry); * @mapping: the address_space to search * @offset: the page index * @fgp_flags: PCG flags - * @gfp_mask: gfp mask to use if a page is to be allocated + * @cache_gfp_mask: gfp mask to use for the page cache data page allocation + * @radix_gfp_mask: gfp mask to use for radix tree node allocation * * Looks up the page cache slot at @mapping & @offset. * - * PCG flags modify how the page is returned + * PCG flags modify how the page is returned. * * FGP_ACCESSED: the page will be marked accessed * FGP_LOCK: Page is return locked * FGP_CREAT: If page is not present then a new page is allocated using - * @gfp_mask and added to the page cache and the VM's LRU - * list. The page is returned locked and with an increased - * refcount. Otherwise, %NULL is returned. + * @cache_gfp_mask and added to the page cache and the VM's LRU + * list. If radix tree nodes are allocated during page cache + * insertion then @radix_gfp_mask is used. The page is returned + * locked and with an increased refcount. Otherwise, %NULL is + * returned. * * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even * if the GFP flags specified for FGP_CREAT are atomic. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9221c02ed9e..7a0a73d2fcf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -856,7 +856,7 @@ struct hstate *size_to_hstate(unsigned long size) return NULL; } -static void free_huge_page(struct page *page) +void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 493f758445e..9aae6f47433 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -358,9 +358,8 @@ static void __init __hugetlb_cgroup_file_init(int idx) cft = &h->cgroup_files[4]; memset(cft, 0, sizeof(*cft)); - WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files)); - - return; + WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, + h->cgroup_files)); } void __init hugetlb_cgroup_file_init(void) @@ -1978,18 +1978,12 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage) #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE -static int just_wait(void *word) -{ - schedule(); - return 0; -} - static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), - just_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a2c7bcb0e6e..f009a14918d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5415,8 +5415,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { struct mem_cgroup_eventfd_list *ev; + spin_lock(&memcg_oom_lock); + list_for_each_entry(ev, &memcg->oom_notify, list) eventfd_signal(ev->eventfd, 1); + + spin_unlock(&memcg_oom_lock); return 0; } @@ -6003,7 +6007,6 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "use_hierarchy", - .flags = CFTYPE_INSANE, .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, @@ -6407,6 +6410,29 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) __mem_cgroup_free(memcg); } +/** + * mem_cgroup_css_reset - reset the states of a mem_cgroup + * @css: the target css + * + * Reset the states of the mem_cgroup associated with @css. This is + * invoked when the userland requests disabling on the default hierarchy + * but the memcg is pinned through dependency. The memcg should stop + * applying policies and should revert to the vanilla state as it may be + * made visible again. + * + * The current implementation only resets the essential configurations. + * This needs to be expanded to cover all the visible parts. + */ +static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + mem_cgroup_resize_limit(memcg, ULLONG_MAX); + mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX); + memcg_update_kmem_limit(memcg, ULLONG_MAX); + res_counter_set_soft_limit(&memcg->res, ULLONG_MAX); +} + #ifdef CONFIG_MMU /* Handlers for move charge at task migration. */ #define PRECHARGE_COUNT_AT_ONCE 256 @@ -7001,16 +7027,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, /* * Cgroup retains root cgroups across [un]mount cycles making it necessary - * to verify sane_behavior flag on each mount attempt. + * to verify whether we're attached to the default hierarchy on each mount + * attempt. */ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) { /* - * use_hierarchy is forced with sane_behavior. cgroup core + * use_hierarchy is forced on the default hierarchy. cgroup core * guarantees that @root doesn't have any children, so turning it * on for the root memcg is enough. */ - if (cgroup_sane_behavior(root_css->cgroup)) + if (cgroup_on_dfl(root_css->cgroup)) mem_cgroup_from_css(root_css)->use_hierarchy = true; } @@ -7019,11 +7046,12 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, .css_free = mem_cgroup_css_free, + .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, - .base_cftypes = mem_cgroup_files, + .legacy_cftypes = mem_cgroup_files, .early_init = 0, }; @@ -7040,7 +7068,8 @@ __setup("swapaccount=", enable_swap_account); static void __init memsw_file_init(void) { - WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files)); + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, + memsw_cgroup_files)); } static void __init enable_swap_cgroup(void) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7211a73ba14..a013bc94ebb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -895,7 +895,13 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, struct page *hpage = *hpagep; struct page *ppage; - if (PageReserved(p) || PageSlab(p) || !PageLRU(p)) + /* + * Here we are interested only in user-mapped pages, so skip any + * other types of pages. + */ + if (PageReserved(p) || PageSlab(p)) + return SWAP_SUCCESS; + if (!(PageLRU(hpage) || PageHuge(p))) return SWAP_SUCCESS; /* @@ -905,8 +911,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!page_mapped(hpage)) return SWAP_SUCCESS; - if (PageKsm(p)) + if (PageKsm(p)) { + pr_err("MCE %#lx: can't handle KSM pages.\n", pfn); return SWAP_FAIL; + } if (PageSwapCache(p)) { printk(KERN_ERR @@ -1229,7 +1237,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage) != SWAP_SUCCESS) { - printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn); + action_result(pfn, "unmapping failed", IGNORED); res = -EBUSY; goto out; } diff --git a/mm/memory.c b/mm/memory.c index 7e8d8205b61..8b44f765b64 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2758,23 +2758,18 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, update_mmu_cache(vma, address, pte); } -static unsigned long fault_around_bytes = 65536; +static unsigned long fault_around_bytes = rounddown_pow_of_two(65536); -/* - * fault_around_pages() and fault_around_mask() round down fault_around_bytes - * to nearest page order. It's what do_fault_around() expects to see. - */ static inline unsigned long fault_around_pages(void) { - return rounddown_pow_of_two(fault_around_bytes) / PAGE_SIZE; + return fault_around_bytes >> PAGE_SHIFT; } static inline unsigned long fault_around_mask(void) { - return ~(rounddown_pow_of_two(fault_around_bytes) - 1) & PAGE_MASK; + return ~(fault_around_bytes - 1) & PAGE_MASK; } - #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { @@ -2782,11 +2777,19 @@ static int fault_around_bytes_get(void *data, u64 *val) return 0; } +/* + * fault_around_pages() and fault_around_mask() expects fault_around_bytes + * rounded down to nearest page order. It's what do_fault_around() expects to + * see. + */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; - fault_around_bytes = val; + if (val > PAGE_SIZE) + fault_around_bytes = rounddown_pow_of_two(val); + else + fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 518e2c3f4c7..e0c943014eb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1306,9 +1306,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); if (bdi_bg_thresh) - *bdi_bg_thresh = div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh); + *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * + background_thresh, + dirty_thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0ea758b898f..ef44ad736ca 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2447,7 +2447,7 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const gfp_t wait = gfp_mask & __GFP_WAIT; + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2456,20 +2456,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (!wait) { + if (atomic) { /* - * Not worth trying to allocate harder for - * __GFP_NOMEMALLOC even if it can't schedule. + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) + if (!(gfp_mask & __GFP_NOMEMALLOC)) alloc_flags |= ALLOC_HARDER; /* - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the + * comment for __cpuset_node_allowed_softwall(). */ alloc_flags &= ~ALLOC_CPUSET; } else if (unlikely(rt_task(current)) && !in_interrupt()) @@ -6062,11 +6062,13 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) } /** - * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages + * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest to retrieve - * @end_bitidx: The last bit of interest - * returns pageblock_bits flags + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest to retrieve + * @mask: mask of bits that the caller is interested in + * + * Return: pageblock_bits flags */ unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, @@ -6091,9 +6093,10 @@ unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, /** * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest - * @start_bitidx: The first bit of interest - * @end_bitidx: The last bit of interest * @flags: The flags to set + * @pfn: The target page frame number + * @end_bitidx: The last bit of interest + * @mask: mask of bits that the caller is interested in */ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, diff --git a/mm/percpu.c b/mm/percpu.c index 2ddf9a990db..2139e30a4b4 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -720,8 +720,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved) if (unlikely(align < 2)) align = 2; - if (unlikely(size & 1)) - size++; + size = ALIGN(size, 2); if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) { WARN(true, "illegal size (%zu) or align (%zu) for " |