From becaba65f62f88e553ec92ed98370e9d2b18e629 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 5 Dec 2020 22:14:45 -0800 Subject: mm: memcg/slab: fix obj_cgroup_charge() return value handling Commit 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations") introduced a regression into the handling of the obj_cgroup_charge() return value. If a non-zero value is returned (indicating of exceeding one of memory.max limits), the allocation should fail, instead of falling back to non-accounted mode. To make the code more readable, move memcg_slab_pre_alloc_hook() and memcg_slab_post_alloc_hook() calling conditions into bodies of these hooks. Fixes: 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations") Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Link: https://lkml.kernel.org/r/20201127161828.GD840171@carbon.dhcp.thefacebook.com Signed-off-by: Linus Torvalds --- mm/slab.h | 40 ++++++++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 16 deletions(-) (limited to 'mm') diff --git a/mm/slab.h b/mm/slab.h index 6d7c6a5056ba..f9977d6613d6 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -274,22 +274,32 @@ static inline size_t obj_full_size(struct kmem_cache *s) return s->size + sizeof(struct obj_cgroup *); } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +/* + * Returns false if the allocation should fail. + */ +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { struct obj_cgroup *objcg; + if (!memcg_kmem_enabled()) + return true; + + if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)) + return true; + objcg = get_obj_cgroup_from_current(); if (!objcg) - return NULL; + return true; if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) { obj_cgroup_put(objcg); - return NULL; + return false; } - return objcg; + *objcgp = objcg; + return true; } static inline void mod_objcg_state(struct obj_cgroup *objcg, @@ -315,7 +325,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, unsigned long off; size_t i; - if (!objcg) + if (!memcg_kmem_enabled() || !objcg) return; flags &= ~__GFP_ACCOUNT; @@ -400,11 +410,11 @@ static inline void memcg_free_page_obj_cgroups(struct page *page) { } -static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s, - size_t objects, - gfp_t flags) +static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct obj_cgroup **objcgp, + size_t objects, gfp_t flags) { - return NULL; + return true; } static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -508,9 +518,8 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (should_failslab(s, flags)) return NULL; - if (memcg_kmem_enabled() && - ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT))) - *objcgp = memcg_slab_pre_alloc_hook(s, size, flags); + if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags)) + return NULL; return s; } @@ -529,8 +538,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, s->flags, flags); } - if (memcg_kmem_enabled()) - memcg_slab_post_alloc_hook(s, objcg, flags, size, p); + memcg_slab_post_alloc_hook(s, objcg, flags, size, p); } #ifndef CONFIG_SLOB -- cgit v1.2.3-58-ga151 From 8199be001a470209f5c938570cc199abb012fe53 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Sat, 5 Dec 2020 22:14:48 -0800 Subject: mm: list_lru: set shrinker map bit when child nr_items is not zero When investigating a slab cache bloat problem, significant amount of negative dentry cache was seen, but confusingly they neither got shrunk by reclaimer (the host has very tight memory) nor be shrunk by dropping cache. The vmcore shows there are over 14M negative dentry objects on lru, but tracing result shows they were even not scanned at all. Further investigation shows the memcg's vfs shrinker_map bit is not set. So the reclaimer or dropping cache just skip calling vfs shrinker. So we have to reboot the hosts to get the memory back. I didn't manage to come up with a reproducer in test environment, and the problem can't be reproduced after rebooting. But it seems there is race between shrinker map bit clear and reparenting by code inspection. The hypothesis is elaborated as below. The memcg hierarchy on our production environment looks like: root / \ system user The main workloads are running under user slice's children, and it creates and removes memcg frequently. So reparenting happens very often under user slice, but no task is under user slice directly. So with the frequent reparenting and tight memory pressure, the below hypothetical race condition may happen: CPU A CPU B reparent dst->nr_items == 0 shrinker: total_objects == 0 add src->nr_items to dst set_bit return SHRINK_EMPTY clear_bit child memcg offline replace child's kmemcg_id with parent's (in memcg_offline_kmem()) list_lru_del() between shrinker runs see parent's kmemcg_id dec dst->nr_items reparent again dst->nr_items may go negative due to concurrent list_lru_del() The second run of shrinker: read nr_items without any synchronization, so it may see intermediate negative nr_items then total_objects may return 0 coincidently keep the bit cleared dst->nr_items != 0 skip set_bit add scr->nr_item to dst After this point dst->nr_item may never go zero, so reparenting will not set shrinker_map bit anymore. And since there is no task under user slice directly, so no new object will be added to its lru to set the shrinker map bit either. That bit is kept cleared forever. How does list_lru_del() race with reparenting? It is because reparenting replaces children's kmemcg_id to parent's without protecting from nlru->lock, so list_lru_del() may see parent's kmemcg_id but actually deleting items from child's lru, but dec'ing parent's nr_items, so the parent's nr_items may go negative as commit 2788cf0c401c ("memcg: reparent list_lrus and free kmemcg_id on css offline") says. Since it is impossible that dst->nr_items goes negative and src->nr_items goes zero at the same time, so it seems we could set the shrinker map bit iff src->nr_items != 0. We could synchronize list_lru_count_one() and reparenting with nlru->lock, but it seems checking src->nr_items in reparenting is the simplest and avoids lock contention. Fixes: fae91d6d8be5 ("mm/list_lru.c: set bit in memcg shrinker bitmap on first list_lru item appearance") Suggested-by: Roman Gushchin Signed-off-by: Yang Shi Signed-off-by: Andrew Morton Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Kirill Tkhai Cc: Vladimir Davydov Cc: [4.19] Link: https://lkml.kernel.org/r/20201202171749.264354-1-shy828301@gmail.com Signed-off-by: Linus Torvalds --- mm/list_lru.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/list_lru.c b/mm/list_lru.c index 5aa6e44bc2ae..fe230081690b 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -534,7 +534,6 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; - bool set; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, @@ -546,11 +545,12 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); - set = (!dst->nr_items && src->nr_items); - dst->nr_items += src->nr_items; - if (set) + + if (src->nr_items) { + dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); - src->nr_items = 0; + src->nr_items = 0; + } spin_unlock_irq(&nlru->lock); } -- cgit v1.2.3-58-ga151 From e91d8d78237de8d7120c320b3645b7100848f24d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 5 Dec 2020 22:14:51 -0800 Subject: mm/zsmalloc.c: drop ZSMALLOC_PGTABLE_MAPPING While I was doing zram testing, I found sometimes decompression failed since the compression buffer was corrupted. With investigation, I found below commit calls cond_resched unconditionally so it could make a problem in atomic context if the task is reschedule. BUG: sleeping function called from invalid context at mm/vmalloc.c:108 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog 3 locks held by memhog/946: #0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160 #1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160 #2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0 CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 Call Trace: unmap_kernel_range_noflush+0x2eb/0x350 unmap_kernel_range+0x14/0x30 zs_unmap_object+0xd5/0xe0 zram_bvec_rw.isra.0+0x38c/0x8e0 zram_rw_page+0x90/0x101 bdev_write_page+0x92/0xe0 __swap_writepage+0x94/0x4a0 pageout+0xe3/0x3a0 shrink_page_list+0xb94/0xd60 shrink_inactive_list+0x158/0x460 We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which contains the offending calling code) from zsmalloc. Even though this option showed some amount improvement(e.g., 30%) in some arm32 platforms, it has been headache to maintain since it have abused APIs[1](e.g., unmap_kernel_range in atomic context). Since we are approaching to deprecate 32bit machines and already made the config option available for only builtin build since v5.8, lastly it has been not default option in zsmalloc, it's time to drop the option for better maintenance. [1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@kernel.org Fixes: e47110e90584 ("mm/vunmap: add cond_resched() in vunmap_pmd_range") Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Reviewed-by: Sergey Senozhatsky Cc: Tony Lindgren Cc: Christoph Hellwig Cc: Harish Sriram Cc: Uladzislau Rezki Cc: Link: https://lkml.kernel.org/r/20201117202916.GA3856507@google.com Signed-off-by: Linus Torvalds --- arch/arm/configs/omap2plus_defconfig | 1 - include/linux/zsmalloc.h | 1 - mm/Kconfig | 13 --------- mm/zsmalloc.c | 54 ------------------------------------ 4 files changed, 69 deletions(-) (limited to 'mm') diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 34793aabdb65..58df9fd79a76 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=y CONFIG_CMA=y CONFIG_ZSMALLOC=m -CONFIG_ZSMALLOC_PGTABLE_MAPPING=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 0fdbf653b173..4807ca4d52e0 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,6 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ diff --git a/mm/Kconfig b/mm/Kconfig index d42423f884a7..390165ffbb0f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -707,19 +707,6 @@ config ZSMALLOC returned by an alloc(). This handle must be mapped in order to access the allocated space. -config ZSMALLOC_PGTABLE_MAPPING - bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC=y - help - By default, zsmalloc uses a copy-based object mapping method to - access allocations that span two pages. However, if a particular - architecture (ex, ARM) performs VM mapping faster than copying, - then you should select this. This causes zsmalloc to use page table - mapping rather than copying for object mapping. - - You can check speed with zsmalloc benchmark: - https://github.com/spartacus06/zsmapbench - config ZSMALLOC_STAT bool "Export zsmalloc statistics" depends on ZSMALLOC diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 918c7b019b3d..cdfaaadea8ff 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -293,11 +293,7 @@ struct zspage { }; struct mapping_area { -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING - struct vm_struct *vm; /* vm area for mapping object that span pages */ -#else char *vm_buf; /* copy buffer for objects that span pages */ -#endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; @@ -1113,54 +1109,6 @@ static struct zspage *find_get_zspage(struct size_class *class) return zspage; } -#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING -static inline int __zs_cpu_up(struct mapping_area *area) -{ - /* - * Make sure we don't leak memory if a cpu UP notification - * and zs_init() race and both call zs_cpu_up() on the same cpu - */ - if (area->vm) - return 0; - area->vm = get_vm_area(PAGE_SIZE * 2, 0); - if (!area->vm) - return -ENOMEM; - - /* - * Populate ptes in advance to avoid pte allocation with GFP_KERNEL - * in non-preemtible context of zs_map_object. - */ - return apply_to_page_range(&init_mm, (unsigned long)area->vm->addr, - PAGE_SIZE * 2, NULL, NULL); -} - -static inline void __zs_cpu_down(struct mapping_area *area) -{ - if (area->vm) - free_vm_area(area->vm); - area->vm = NULL; -} - -static inline void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm->addr; - - BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0); - area->vm_addr = area->vm->addr; - return area->vm_addr + off; -} - -static inline void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm_addr; - - unmap_kernel_range(addr, PAGE_SIZE * 2); -} - -#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static inline int __zs_cpu_up(struct mapping_area *area) { /* @@ -1241,8 +1189,6 @@ out: pagefault_enable(); } -#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ - static int zs_cpu_prepare(unsigned int cpu) { struct mapping_area *area; -- cgit v1.2.3-58-ga151 From b11a76b37a5aa7b07c3e3eeeaae20b25475bddd3 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 5 Dec 2020 22:14:55 -0800 Subject: mm/swapfile: do not sleep with a spin lock held We can't call kvfree() with a spin lock held, so defer it. Fixes a might_sleep() runtime warning. Fixes: 873d7bcfd066 ("mm/swapfile.c: use kvzalloc for swap_info_struct allocation") Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Hugh Dickins Cc: Link: https://lkml.kernel.org/r/20201202151549.10350-1-qcai@redhat.com Signed-off-by: Linus Torvalds --- mm/swapfile.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index c4a613688a17..d58361109066 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2867,6 +2867,7 @@ late_initcall(max_swapfiles_check); static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; unsigned int type; int i; @@ -2895,7 +2896,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); } else { - kvfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() @@ -2908,6 +2909,7 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); + kvfree(defer); spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); -- cgit v1.2.3-58-ga151 From 3351b16af4946fff0d46481d155fb91adb28b1f9 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Sat, 5 Dec 2020 22:15:09 -0800 Subject: mm/filemap: add static for function __add_to_page_cache_locked mm/filemap.c:830:14: warning: no previous prototype for `__add_to_page_cache_locked' [-Wmissing-prototypes] Signed-off-by: Alex Shi Signed-off-by: Andrew Morton Cc: Souptick Joarder Link: https://lkml.kernel.org/r/1604661895-5495-1-git-send-email-alex.shi@linux.alibaba.com Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 0b2067b3c328..331f4261d723 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -827,7 +827,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -noinline int __add_to_page_cache_locked(struct page *page, +static noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) -- cgit v1.2.3-58-ga151 From 7a5bde37983d37783161681ff7c6122dfd081791 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sat, 5 Dec 2020 22:15:12 -0800 Subject: hugetlb_cgroup: fix offline of hugetlb cgroup with reservations Adrian Moreno was ruuning a kubernetes 1.19 + containerd/docker workload using hugetlbfs. In this environment the issue is reproduced by: - Start a simple pod that uses the recently added HugePages medium feature (pod yaml attached) - Start a DPDK app. It doesn't need to run successfully (as in transfer packets) nor interact with real hardware. It seems just initializing the EAL layer (which handles hugepage reservation and locking) is enough to trigger the issue - Delete the Pod (or let it "Complete"). This would result in a kworker thread going into a tight loop (top output): 1425 root 20 0 0 0 0 R 99.7 0.0 5:22.45 kworker/28:7+cgroup_destroy 'perf top -g' reports: - 63.28% 0.01% [kernel] [k] worker_thread - 49.97% worker_thread - 52.64% process_one_work - 62.08% css_killed_work_fn - hugetlb_cgroup_css_offline 41.52% _raw_spin_lock - 2.82% _cond_resched rcu_all_qs 2.66% PageHuge - 0.57% schedule - 0.57% __schedule We are spinning in the do-while loop in hugetlb_cgroup_css_offline. Worse yet, we are holding the master cgroup lock (cgroup_mutex) while infinitely spinning. Little else can be done on the system as the cgroup_mutex can not be acquired. Do note that the issue can be reproduced by simply offlining a hugetlb cgroup containing pages with reservation counts. The loop in hugetlb_cgroup_css_offline is moving page counts from the cgroup being offlined to the parent cgroup. This is done for each hstate, and is repeated until hugetlb_cgroup_have_usage returns false. The routine moving counts (hugetlb_cgroup_move_parent) is only moving 'usage' counts. The routine hugetlb_cgroup_have_usage is checking for both 'usage' and 'reservation' counts. Discussion about what to do with reservation counts when reparenting was discussed here: https://lore.kernel.org/linux-kselftest/CAHS8izMFAYTgxym-Hzb_JmkTK1N_S9tGN71uS6MFV+R7swYu5A@mail.gmail.com/ The decision was made to leave a zombie cgroup for with reservation counts. Unfortunately, the code checking reservation counts was incorrectly added to hugetlb_cgroup_have_usage. To fix the issue, simply remove the check for reservation counts. While fixing this issue, a related bug in hugetlb_cgroup_css_offline was noticed. The hstate index is not reinitialized each time through the do-while loop. Fix this as well. Fixes: 1adc4d419aa2 ("hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations") Reported-by: Adrian Moreno Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Tested-by: Adrian Moreno Reviewed-by: Shakeel Butt Cc: Mina Almasry Cc: David Rientjes Cc: Greg Thelen Cc: Sandipan Das Cc: Shuah Khan Cc: Link: https://lkml.kernel.org/r/20201203220242.158165-1-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- mm/hugetlb_cgroup.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 1f87aec9ab5c..9182848dda3e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -82,11 +82,8 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) for (idx = 0; idx < hugetlb_max_hstate; idx++) { if (page_counter_read( - hugetlb_cgroup_counter_from_cgroup(h_cg, idx)) || - page_counter_read(hugetlb_cgroup_counter_from_cgroup_rsvd( - h_cg, idx))) { + hugetlb_cgroup_counter_from_cgroup(h_cg, idx))) return true; - } } return false; } @@ -202,9 +199,10 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; - int idx = 0; + int idx; do { + idx = 0; for_each_hstate(h) { spin_lock(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) -- cgit v1.2.3-58-ga151 From 309d08d9b3a3659ab3f239d27d4e38b670b08fc9 Mon Sep 17 00:00:00 2001 From: Liu Zixian Date: Sat, 5 Dec 2020 22:15:15 -0800 Subject: mm/mmap.c: fix mmap return value when vma is merged after call_mmap() On success, mmap should return the begin address of newly mapped area, but patch "mm: mmap: merge vma after call_mmap() if possible" set vm_start of newly merged vma to return value addr. Users of mmap will get wrong address if vma is merged after call_mmap(). We fix this by moving the assignment to addr before merging vma. We have a driver which changes vm_flags, and this bug is found by our testcases. Fixes: d70cec898324 ("mm: mmap: merge vma after call_mmap() if possible") Signed-off-by: Liu Zixian Signed-off-by: Andrew Morton Reviewed-by: Jason Gunthorpe Reviewed-by: David Hildenbrand Cc: Miaohe Lin Cc: Hongxiang Lou Cc: Hu Shiyuan Cc: Matthew Wilcox Link: https://lkml.kernel.org/r/20201203085350.22624-1-liuzixian4@huawei.com Signed-off-by: Linus Torvalds --- mm/mmap.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index d91ecb00d38c..5c8b4485860d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1808,6 +1808,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (error) goto unmap_and_free_vma; + /* Can addr have changed?? + * + * Answer: Yes, several device drivers can do it in their + * f_op->mmap method. -DaveM + * Bug: If addr is changed, prev, rb_link, rb_parent should + * be updated for vma_link() + */ + WARN_ON_ONCE(addr != vma->vm_start); + + addr = vma->vm_start; + /* If vm_flags changed after call_mmap(), we should try merge vma again * as we may succeed this time. */ @@ -1822,25 +1833,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, fput(vma->vm_file); vm_area_free(vma); vma = merge; - /* Update vm_flags and possible addr to pick up the change. We don't - * warn here if addr changed as the vma is not linked by vma_link(). - */ - addr = vma->vm_start; + /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } - /* Can addr have changed?? - * - * Answer: Yes, several device drivers can do it in their - * f_op->mmap method. -DaveM - * Bug: If addr is changed, prev, rb_link, rb_parent should - * be updated for vma_link() - */ - WARN_ON_ONCE(addr != vma->vm_start); - - addr = vma->vm_start; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); -- cgit v1.2.3-58-ga151 From a68a0262abdaa251e12c53715f48e698a18ef402 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 8 Dec 2020 20:57:18 -0800 Subject: mm/madvise: remove racy mm ownership check Jann spotted the security hole due to race of mm ownership check. If the task is sharing the mm_struct but goes through execve() before mm_access(), it could skip process_madvise_behavior_valid check. That makes *any advice hint* to reach into the remote process. This patch removes the mm ownership check. With it, it will lose the ability that local process could give *any* advice hint with vector interface for some reason (e.g., performance). Since there is no concrete example in upstream yet, it would be better to remove the abiliity at this moment and need to review when such new advice comes up. Fixes: ecb8ac8b1f14 ("mm/madvise: introduce process_madvise() syscall: an external memory hinting API") Reported-by: Jann Horn Suggested-by: Jann Horn Signed-off-by: Minchan Kim Signed-off-by: Linus Torvalds --- mm/madvise.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/madvise.c b/mm/madvise.c index a8d8d48a57fe..13f5677b9322 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1204,8 +1204,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, goto put_pid; } - if (task->mm != current->mm && - !process_madvise_behavior_valid(behavior)) { + if (!process_madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_task; } -- cgit v1.2.3-58-ga151 From 16c0cc0ce3059e315a0aab6538061d95a6612589 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 11 Dec 2020 13:36:27 -0800 Subject: revert "mm/filemap: add static for function __add_to_page_cache_locked" Revert commit 3351b16af494 ("mm/filemap: add static for function __add_to_page_cache_locked") due to incompatibility with ALLOW_ERROR_INJECTION which result in build errors. Link: https://lkml.kernel.org/r/CAADnVQJ6tmzBXvtroBuEH6QA0H+q7yaSKxrVvVxhqr3KBZdEXg@mail.gmail.com Tested-by: Justin Forbes Tested-by: Greg Thelen Acked-by: Alexei Starovoitov Cc: Michal Kubecek Cc: Alex Shi Cc: Souptick Joarder Cc: Daniel Borkmann Cc: Josef Bacik Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 331f4261d723..0b2067b3c328 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -827,7 +827,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static noinline int __add_to_page_cache_locked(struct page *page, +noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) -- cgit v1.2.3-58-ga151 From 6c82d45c7f0348b44e00bd7dcccfc47dec7577d1 Mon Sep 17 00:00:00 2001 From: Kuan-Ying Lee Date: Fri, 11 Dec 2020 13:36:49 -0800 Subject: kasan: fix object remaining in offline per-cpu quarantine We hit this issue in our internal test. When enabling generic kasan, a kfree()'d object is put into per-cpu quarantine first. If the cpu goes offline, object still remains in the per-cpu quarantine. If we call kmem_cache_destroy() now, slub will report "Objects remaining" error. ============================================================================= BUG test_module_slab (Not tainted): Objects remaining in test_module_slab on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0x(____ptrval____) objects=34 used=1 fp=0x(____ptrval____) flags=0x2ffff00000010200 CPU: 3 PID: 176 Comm: cat Tainted: G B 5.10.0-rc1-00007-g4525c8781ec0-dirty #10 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2b0 show_stack+0x18/0x68 dump_stack+0xfc/0x168 slab_err+0xac/0xd4 __kmem_cache_shutdown+0x1e4/0x3c8 kmem_cache_destroy+0x68/0x130 test_version_show+0x84/0xf0 module_attr_show+0x40/0x60 sysfs_kf_seq_show+0x128/0x1c0 kernfs_seq_show+0xa0/0xb8 seq_read+0x1f0/0x7e8 kernfs_fop_read+0x70/0x338 vfs_read+0xe4/0x250 ksys_read+0xc8/0x180 __arm64_sys_read+0x44/0x58 el0_svc_common.constprop.0+0xac/0x228 do_el0_svc+0x38/0xa0 el0_sync_handler+0x170/0x178 el0_sync+0x174/0x180 INFO: Object 0x(____ptrval____) @offset=15848 INFO: Allocated in test_version_show+0x98/0xf0 age=8188 cpu=6 pid=172 stack_trace_save+0x9c/0xd0 set_track+0x64/0xf0 alloc_debug_processing+0x104/0x1a0 ___slab_alloc+0x628/0x648 __slab_alloc.isra.0+0x2c/0x58 kmem_cache_alloc+0x560/0x588 test_version_show+0x98/0xf0 module_attr_show+0x40/0x60 sysfs_kf_seq_show+0x128/0x1c0 kernfs_seq_show+0xa0/0xb8 seq_read+0x1f0/0x7e8 kernfs_fop_read+0x70/0x338 vfs_read+0xe4/0x250 ksys_read+0xc8/0x180 __arm64_sys_read+0x44/0x58 el0_svc_common.constprop.0+0xac/0x228 kmem_cache_destroy test_module_slab: Slab cache still has objects Register a cpu hotplug function to remove all objects in the offline per-cpu quarantine when cpu is going offline. Set a per-cpu variable to indicate this cpu is offline. [qiang.zhang@windriver.com: fix slab double free when cpu-hotplug] Link: https://lkml.kernel.org/r/20201204102206.20237-1-qiang.zhang@windriver.com Link: https://lkml.kernel.org/r/1606895585-17382-2-git-send-email-Kuan-Ying.Lee@mediatek.com Signed-off-by: Kuan-Ying Lee Signed-off-by: Zqiang Suggested-by: Dmitry Vyukov Reported-by: Guangye Yang Reviewed-by: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Matthias Brugger Cc: Nicholas Tang Cc: Miles Chen Cc: Qian Cai Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/quarantine.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'mm') diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 4c5375810449..0e3f8494628f 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "../slab.h" #include "kasan.h" @@ -43,6 +44,7 @@ struct qlist_head { struct qlist_node *head; struct qlist_node *tail; size_t bytes; + bool offline; }; #define QLIST_INIT { NULL, NULL, 0 } @@ -188,6 +190,10 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) local_irq_save(flags); q = this_cpu_ptr(&cpu_quarantine); + if (q->offline) { + local_irq_restore(flags); + return; + } qlist_put(q, &info->quarantine_link, cache->size); if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); @@ -328,3 +334,36 @@ void quarantine_remove_cache(struct kmem_cache *cache) synchronize_srcu(&remove_cache_srcu); } + +static int kasan_cpu_online(unsigned int cpu) +{ + this_cpu_ptr(&cpu_quarantine)->offline = false; + return 0; +} + +static int kasan_cpu_offline(unsigned int cpu) +{ + struct qlist_head *q; + + q = this_cpu_ptr(&cpu_quarantine); + /* Ensure the ordering between the writing to q->offline and + * qlist_free_all. Otherwise, cpu_quarantine may be corrupted + * by interrupt. + */ + WRITE_ONCE(q->offline, true); + barrier(); + qlist_free_all(q, NULL); + return 0; +} + +static int __init kasan_cpu_quarantine_init(void) +{ + int ret = 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online", + kasan_cpu_online, kasan_cpu_offline); + if (ret < 0) + pr_err("kasan cpu quarantine register failed [%d]\n", ret); + return ret; +} +late_initcall(kasan_cpu_quarantine_init); -- cgit v1.2.3-58-ga151 From ba9c1201beaa86a773e83be5654602a0667e4a4d Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Fri, 11 Dec 2020 13:36:53 -0800 Subject: mm/hugetlb: clear compound_nr before freeing gigantic pages Commit 1378a5ee451a ("mm: store compound_nr as well as compound_order") added compound_nr counter to first tail struct page, overlaying with page->mapping. The overlay itself is fine, but while freeing gigantic hugepages via free_contig_range(), a "bad page" check will trigger for non-NULL page->mapping on the first tail page: BUG: Bad page state in process bash pfn:380001 page:00000000c35f0856 refcount:0 mapcount:0 mapping:00000000126b68aa index:0x0 pfn:0x380001 aops:0x0 flags: 0x3ffff00000000000() raw: 3ffff00000000000 0000000000000100 0000000000000122 0000000100000000 raw: 0000000000000000 0000000000000000 ffffffff00000000 0000000000000000 page dumped because: non-NULL mapping Modules linked in: CPU: 6 PID: 616 Comm: bash Not tainted 5.10.0-rc7-next-20201208 #1 Hardware name: IBM 3906 M03 703 (LPAR) Call Trace: show_stack+0x6e/0xe8 dump_stack+0x90/0xc8 bad_page+0xd6/0x130 free_pcppages_bulk+0x26a/0x800 free_unref_page+0x6e/0x90 free_contig_range+0x94/0xe8 update_and_free_page+0x1c4/0x2c8 free_pool_huge_page+0x11e/0x138 set_max_huge_pages+0x228/0x300 nr_hugepages_store_common+0xb8/0x130 kernfs_fop_write+0xd2/0x218 vfs_write+0xb0/0x2b8 ksys_write+0xac/0xe0 system_call+0xe6/0x288 Disabling lock debugging due to kernel taint This is because only the compound_order is cleared in destroy_compound_gigantic_page(), and compound_nr is set to 1U << order == 1 for order 0 in set_compound_order(page, 0). Fix this by explicitly clearing compound_nr for first tail page after calling set_compound_order(page, 0). Link: https://lkml.kernel.org/r/20201208182813.66391-2-gerald.schaefer@linux.ibm.com Fixes: 1378a5ee451a ("mm: store compound_nr as well as compound_order") Signed-off-by: Gerald Schaefer Reviewed-by: Matthew Wilcox (Oracle) Cc: Heiko Carstens Cc: Mike Kravetz Cc: Christian Borntraeger Cc: [5.9+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 37f15c3c24dc..d029d938d26d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1216,6 +1216,7 @@ static void destroy_compound_gigantic_page(struct page *page, } set_compound_order(page, 0); + page[1].compound_nr = 0; __ClearPageHead(page); } -- cgit v1.2.3-58-ga151