From 8a1f780e7f28c7c1d640118242cf68d528c456cd Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Tue, 24 Jan 2017 15:17:45 -0800 Subject: memory_hotplug: make zone_can_shift() return a boolean value online_{kernel|movable} is used to change the memory zone to ZONE_{NORMAL|MOVABLE} and online the memory. To check that memory zone can be changed, zone_can_shift() is used. Currently the function returns minus integer value, plus integer value and 0. When the function returns minus or plus integer value, it means that the memory zone can be changed to ZONE_{NORNAL|MOVABLE}. But when the function returns 0, there are two meanings. One of the meanings is that the memory zone does not need to be changed. For example, when memory is in ZONE_NORMAL and onlined by online_kernel the memory zone does not need to be changed. Another meaning is that the memory zone cannot be changed. When memory is in ZONE_NORMAL and onlined by online_movable, the memory zone may not be changed to ZONE_MOVALBE due to memory online limitation(see Documentation/memory-hotplug.txt). In this case, memory must not be onlined. The patch changes the return type of zone_can_shift() so that memory online operation fails when memory zone cannot be changed as follows: Before applying patch: # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 # echo online_movable > memory4097/state # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 8388608 managed 8388608 online_movable operation succeeded. But memory is onlined as ZONE_NORMAL, not ZONE_MOVABLE. After applying patch: # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 # echo online_movable > memory4097/state bash: echo: write error: Invalid argument # grep -A 35 "Node 2" /proc/zoneinfo Node 2, zone Normal node_scanned 0 spanned 8388608 present 7864320 managed 7864320 online_movable operation failed because of failure of changing the memory zone from ZONE_NORMAL to ZONE_MOVABLE Fixes: df429ac03936 ("memory-hotplug: more general validation of zone during online") Link: http://lkml.kernel.org/r/2f9c3837-33d7-b6e5-59c0-6ca4372b2d84@gmail.com Signed-off-by: Yasuaki Ishimatsu Reviewed-by: Reza Arbab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e43142c15631..ca2723d47338 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1033,36 +1033,39 @@ static void node_states_set_node(int node, struct memory_notify *arg) node_set_state(node, N_MEMORY); } -int zone_can_shift(unsigned long pfn, unsigned long nr_pages, - enum zone_type target) +bool zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target, int *zone_shift) { struct zone *zone = page_zone(pfn_to_page(pfn)); enum zone_type idx = zone_idx(zone); int i; + *zone_shift = 0; + if (idx < target) { /* pages must be at end of current zone */ if (pfn + nr_pages != zone_end_pfn(zone)) - return 0; + return false; /* no zones in use between current zone and target */ for (i = idx + 1; i < target; i++) if (zone_is_initialized(zone - idx + i)) - return 0; + return false; } if (target < idx) { /* pages must be at beginning of current zone */ if (pfn != zone->zone_start_pfn) - return 0; + return false; /* no zones in use between current zone and target */ for (i = target + 1; i < idx; i++) if (zone_is_initialized(zone - idx + i)) - return 0; + return false; } - return target - idx; + *zone_shift = target - idx; + return true; } /* Must be protected by mem_hotplug_begin() */ @@ -1089,10 +1092,13 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ !can_online_high_movable(zone)) return -EINVAL; - if (online_type == MMOP_ONLINE_KERNEL) - zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL); - else if (online_type == MMOP_ONLINE_MOVABLE) - zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE); + if (online_type == MMOP_ONLINE_KERNEL) { + if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift)) + return -EINVAL; + } else if (online_type == MMOP_ONLINE_MOVABLE) { + if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift)) + return -EINVAL; + } zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages); if (!zone) -- cgit v1.2.3 From 8310d48b125d19fcd9521d83b8293e63eb1646aa Mon Sep 17 00:00:00 2001 From: Keno Fischer Date: Tue, 24 Jan 2017 15:17:48 -0800 Subject: mm/huge_memory.c: respect FOLL_FORCE/FOLL_COW for thp In commit 19be0eaffa3a ("mm: remove gup_flags FOLL_WRITE games from __get_user_pages()"), the mm code was changed from unsetting FOLL_WRITE after a COW was resolved to setting the (newly introduced) FOLL_COW instead. Simultaneously, the check in gup.c was updated to still allow writes with FOLL_FORCE set if FOLL_COW had also been set. However, a similar check in huge_memory.c was forgotten. As a result, remote memory writes to ro regions of memory backed by transparent huge pages cause an infinite loop in the kernel (handle_mm_fault sets FOLL_COW and returns 0 causing a retry, but follow_trans_huge_pmd bails out immidiately because `(flags & FOLL_WRITE) && !pmd_write(*pmd)` is true. While in this state the process is stil SIGKILLable, but little else works (e.g. no ptrace attach, no other signals). This is easily reproduced with the following code (assuming thp are set to always): #include #include #include #include #include #include #include #include #include #include #define TEST_SIZE 5 * 1024 * 1024 int main(void) { int status; pid_t child; int fd = open("/proc/self/mem", O_RDWR); void *addr = mmap(NULL, TEST_SIZE, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); assert(addr != MAP_FAILED); pid_t parent_pid = getpid(); if ((child = fork()) == 0) { void *addr2 = mmap(NULL, TEST_SIZE, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); assert(addr2 != MAP_FAILED); memset(addr2, 'a', TEST_SIZE); pwrite(fd, addr2, TEST_SIZE, (uintptr_t)addr); return 0; } assert(child == waitpid(child, &status, 0)); assert(WIFEXITED(status) && WEXITSTATUS(status) == 0); return 0; } Fix this by updating follow_trans_huge_pmd in huge_memory.c analogously to the update in gup.c in the original commit. The same pattern exists in follow_devmap_pmd. However, we should not be able to reach that check with FOLL_COW set, so add WARN_ONCE to make sure we notice if we ever do. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170106015025.GA38411@juliacomputing.com Signed-off-by: Keno Fischer Acked-by: Kirill A. Shutemov Cc: Greg Thelen Cc: Nicholas Piggin Cc: Willy Tarreau Cc: Oleg Nesterov Cc: Kees Cook Cc: Andy Lutomirski Cc: Michal Hocko Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9a6bd6c8d55a..5f3ad65c85de 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -783,6 +783,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); + /* + * When we COW a devmap PMD entry, we split it into PTEs, so we should + * not be in this function with `flags & FOLL_COW` set. + */ + WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); + if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; @@ -1128,6 +1134,16 @@ out_unlock: return ret; } +/* + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +{ + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); +} + struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -1138,7 +1154,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !pmd_write(*pmd)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) goto out; /* Avoid dumping huge zero page */ -- cgit v1.2.3 From aa2efd5ea4041754da4046c3d2e7edaac9526258 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Tue, 24 Jan 2017 15:18:02 -0800 Subject: mm/slub.c: trace free objects at KERN_INFO Currently when trace is enabled (e.g. slub_debug=T,kmalloc-128 ) the trace messages are mostly output at KERN_INFO. However the trace code also calls print_section() to hexdump the head of a free object. This is hard coded to use KERN_ERR, meaning the console is deluged with trace messages even if we've asked for quiet. Fix this the obvious way but adding a level parameter to print_section(), allowing calls from the trace code to use the same trace level as other trace messages. Link: http://lkml.kernel.org/r/20170113154850.518-1-daniel.thompson@linaro.org Signed-off-by: Daniel Thompson Acked-by: Christoph Lameter Acked-by: David Rientjes Cc: Pekka Enberg Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 067598a00849..7aa6f433f4de 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -496,10 +496,11 @@ static inline int check_valid_pointer(struct kmem_cache *s, return 1; } -static void print_section(char *text, u8 *addr, unsigned int length) +static void print_section(char *level, char *text, u8 *addr, + unsigned int length) { metadata_access_enable(); - print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, length, 1); metadata_access_disable(); } @@ -636,14 +637,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p - s->red_left_pad, s->red_left_pad); + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + s->red_left_pad); else if (p > addr + 16) - print_section("Bytes b4 ", p - 16, 16); + print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section("Object ", p, min_t(unsigned long, s->object_size, - PAGE_SIZE)); + print_section(KERN_ERR, "Object ", p, + min_t(unsigned long, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section("Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); if (s->offset) @@ -658,7 +660,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section("Padding ", p + off, size_from_object(s) - off); + print_section(KERN_ERR, "Padding ", p + off, + size_from_object(s) - off); dump_stack(); } @@ -820,7 +823,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) end--; slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); - print_section("Padding ", end - remainder, remainder); + print_section(KERN_ERR, "Padding ", end - remainder, remainder); restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end); return 0; @@ -973,7 +976,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, page->freelist); if (!alloc) - print_section("Object ", (void *)object, + print_section(KERN_INFO, "Object ", (void *)object, s->object_size); dump_stack(); -- cgit v1.2.3 From 424f6c4818bbf1b8ccf58aa012ecc19c0bb9b446 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Tue, 24 Jan 2017 15:18:05 -0800 Subject: mm: alloc_contig: re-allow CMA to compact FS pages Commit 73e64c51afc5 ("mm, compaction: allow compaction for GFP_NOFS requests") changed compation to skip FS pages if not explicitly allowed to touch them, but missed to update the CMA compact_control. This leads to a very high isolation failure rate, crippling performance of CMA even on a lightly loaded system. Re-allow CMA to compact FS pages by setting the correct GFP flags, restoring CMA behavior and performance to the kernel 4.9 level. Fixes: 73e64c51afc5 (mm, compaction: allow compaction for GFP_NOFS requests) Link: http://lkml.kernel.org/r/20170113115155.24335-1-l.stach@pengutronix.de Signed-off-by: Lucas Stach Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Joonsoo Kim Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d604d2596b7b..41d5e2e2d8ce 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7248,6 +7248,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .zone = page_zone(pfn_to_page(start)), .mode = MIGRATE_SYNC, .ignore_skip_hint = true, + .gfp_mask = GFP_KERNEL, }; INIT_LIST_HEAD(&cc.migratepages); -- cgit v1.2.3 From 3674534b775354516e5c148ea48f51d4d1909a78 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 24 Jan 2017 15:18:10 -0800 Subject: mm, memcg: do not retry precharge charges When memory.move_charge_at_immigrate is enabled and precharges are depleted during move, mem_cgroup_move_charge_pte_range() will attempt to increase the size of the precharge. Prevent precharges from ever looping by setting __GFP_NORETRY. This was probably the intention of the GFP_KERNEL & ~__GFP_NORETRY, which is pointless as written. Fixes: 0029e19ebf84 ("mm: memcontrol: remove explicit OOM parameter in charge path") Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1701130208510.69402@chino.kir.corp.google.com Signed-off-by: David Rientjes Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a63a8f832664..b822e158b319 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4353,9 +4353,9 @@ static int mem_cgroup_do_precharge(unsigned long count) return ret; } - /* Try charges one by one with reclaim */ + /* Try charges one by one with reclaim, but do not retry */ while (count--) { - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1); + ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); if (ret) return ret; mc.precharge++; -- cgit v1.2.3 From d51e9894d27492783fc6d1b489070b4ba66ce969 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:18 -0800 Subject: mm/mempolicy.c: do not put mempolicy before using its nodemask Since commit be97a41b291e ("mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma") alloc_pages_vma() can potentially free a mempolicy by mpol_cond_put() before accessing the embedded nodemask by __alloc_pages_nodemask(). The commit log says it's so "we can use a single exit path within the function" but that's clearly wrong. We can still do that when doing mpol_cond_put() after the allocation attempt. Make sure the mempolicy is not freed prematurely, otherwise __alloc_pages_nodemask() can end up using a bogus nodemask, which could lead e.g. to premature OOM. Fixes: be97a41b291e ("mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma") Link: http://lkml.kernel.org/r/20170118141124.8345-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Acked-by: Michal Hocko Acked-by: David Rientjes Cc: Aneesh Kumar K.V Cc: Andrea Arcangeli Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2e346645eb80..1e7873e40c9a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2017,8 +2017,8 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); zl = policy_zonelist(gfp, pol, node); - mpol_cond_put(pol); page = __alloc_pages_nodemask(gfp, order, zl, nmask); + mpol_cond_put(pol); out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; -- cgit v1.2.3 From ea57485af8f4221312a5a95d63c382b45e7840dc Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:32 -0800 Subject: mm, page_alloc: fix check for NULL preferred_zone Patch series "fix premature OOM regression in 4.7+ due to cpuset races". This is v2 of my attempt to fix the recent report based on LTP cpuset stress test [1]. The intention is to go to stable 4.9 LTSS with this, as triggering repeated OOMs is not nice. That's why the patches try to be not too intrusive. Unfortunately why investigating I found that modifying the testcase to use per-VMA policies instead of per-task policies will bring the OOM's back, but that seems to be much older and harder to fix problem. I have posted a RFC [2] but I believe that fixing the recent regressions has a higher priority. Longer-term we might try to think how to fix the cpuset mess in a better and less error prone way. I was for example very surprised to learn, that cpuset updates change not only task->mems_allowed, but also nodemask of mempolicies. Until now I expected the parameter to alloc_pages_nodemask() to be stable. I wonder why do we then treat cpusets specially in get_page_from_freelist() and distinguish HARDWALL etc, when there's unconditional intersection between mempolicy and cpuset. I would expect the nodemask adjustment for saving overhead in g_p_f(), but that clearly doesn't happen in the current form. So we have both crazy complexity and overhead, AFAICS. [1] https://lkml.kernel.org/r/CAFpQJXUq-JuEP=QPidy4p_=FN0rkH5Z-kfB4qBvsf6jMS87Edg@mail.gmail.com [2] https://lkml.kernel.org/r/7c459f26-13a6-a817-e508-b65b903a8378@suse.cz This patch (of 4): Since commit c33d6c06f60f ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") we have a wrong check for NULL preferred_zone, which can theoretically happen due to concurrent cpuset modification. We check the zoneref pointer which is never NULL and we should check the zone pointer. Also document this in first_zones_zonelist() comment per Michal Hocko. Fixes: c33d6c06f60f ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") Link: http://lkml.kernel.org/r/20170120103843.24587-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Ganapatrao Kulkarni Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++++- mm/page_alloc.c | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 36d9896fbc1e..f4aac87adcc3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter + * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. + * + * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is + * never NULL). This may happen either genuinely, or due to concurrent nodemask + * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 41d5e2e2d8ce..85cf0f715eb0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3784,7 +3784,7 @@ retry_cpuset: */ ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, ac.nodemask); - if (!ac.preferred_zoneref) { + if (!ac.preferred_zoneref->zone) { page = NULL; goto no_zone; } -- cgit v1.2.3 From 16096c25bf0ca5d87e4fa6ec6108ba53feead212 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:35 -0800 Subject: mm, page_alloc: fix fast-path race with cpuset update or removal Ganapatrao Kulkarni reported that the LTP test cpuset01 in stress mode triggers OOM killer in few seconds, despite lots of free memory. The test attempts to repeatedly fault in memory in one process in a cpuset, while changing allowed nodes of the cpuset between 0 and 1 in another process. One possible cause is that in the fast path we find the preferred zoneref according to current mems_allowed, so that it points to the middle of the zonelist, skipping e.g. zones of node 1 completely. If the mems_allowed is updated to contain only node 1, we never reach it in the zonelist, and trigger OOM before checking the cpuset_mems_cookie. This patch fixes the particular case by redoing the preferred zoneref search if we switch back to the original nodemask. The condition is also slightly changed so that when the last non-root cpuset is removed, we don't miss it. Note that this is not a full fix, and more patches will follow. Link: http://lkml.kernel.org/r/20170120103843.24587-3-vbabka@suse.cz Fixes: 682a3385e773 ("mm, page_alloc: inline the fast path of the zonelist iterator") Signed-off-by: Vlastimil Babka Reported-by: Ganapatrao Kulkarni Acked-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 85cf0f715eb0..6f28b7e926d1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3804,9 +3804,17 @@ retry_cpuset: /* * Restore the original nodemask if it was potentially replaced with * &cpuset_current_mems_allowed to optimize the fast-path attempt. + * Also recalculate the starting point for the zonelist iterator or + * we could end up iterating over non-eligible zones endlessly. */ - if (cpusets_enabled()) + if (unlikely(ac.nodemask != nodemask)) { ac.nodemask = nodemask; + ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, + ac.high_zoneidx, ac.nodemask); + if (!ac.preferred_zoneref->zone) + goto no_zone; + } + page = __alloc_pages_slowpath(alloc_mask, order, &ac); no_zone: -- cgit v1.2.3 From 5ce9bfef1d27944c119a397a9d827bef795487ce Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:38 -0800 Subject: mm, page_alloc: move cpuset seqcount checking to slowpath This is a preparation for the following patch to make review simpler. While the primary motivation is a bug fix, this also simplifies the fast path, although the moved code is only enabled when cpusets are in use. Link: http://lkml.kernel.org/r/20170120103843.24587-4-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Ganapatrao Kulkarni Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 47 ++++++++++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 21 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6f28b7e926d1..0df3c089d3af 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3523,12 +3523,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned int alloc_flags; unsigned long did_some_progress; - enum compact_priority compact_priority = DEF_COMPACT_PRIORITY; + enum compact_priority compact_priority; enum compact_result compact_result; - int compaction_retries = 0; - int no_progress_loops = 0; + int compaction_retries; + int no_progress_loops; unsigned long alloc_start = jiffies; unsigned int stall_timeout = 10 * HZ; + unsigned int cpuset_mems_cookie; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -3549,6 +3550,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; +retry_cpuset: + compaction_retries = 0; + no_progress_loops = 0; + compact_priority = DEF_COMPACT_PRIORITY; + cpuset_mems_cookie = read_mems_allowed_begin(); + /* * The fast path uses conservative alloc_flags to succeed only until * kswapd needs to be woken up, and to avoid the cost of setting up @@ -3720,6 +3727,15 @@ retry: } nopage: + /* + * When updating a task's mems_allowed, it is possible to race with + * parallel threads in such a way that an allocation can fail while + * the mask is being updated. If a page allocation is about to fail, + * check if the cpuset changed during allocation and if so, retry. + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry_cpuset; + warn_alloc(gfp_mask, "page allocation failure: order:%u", order); got_pg: @@ -3734,7 +3750,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, nodemask_t *nodemask) { struct page *page; - unsigned int cpuset_mems_cookie; unsigned int alloc_flags = ALLOC_WMARK_LOW; gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { @@ -3771,9 +3786,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; -retry_cpuset: - cpuset_mems_cookie = read_mems_allowed_begin(); - /* Dirty zone balancing only done in the fast path */ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE); @@ -3786,6 +3798,11 @@ retry_cpuset: ac.high_zoneidx, ac.nodemask); if (!ac.preferred_zoneref->zone) { page = NULL; + /* + * This might be due to race with cpuset_current_mems_allowed + * update, so make sure we retry with original nodemask in the + * slow path. + */ goto no_zone; } @@ -3794,6 +3811,7 @@ retry_cpuset: if (likely(page)) goto out; +no_zone: /* * Runtime PM, block IO and its error handling path can deadlock * because I/O on the device might not complete. @@ -3811,24 +3829,11 @@ retry_cpuset: ac.nodemask = nodemask; ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, ac.nodemask); - if (!ac.preferred_zoneref->zone) - goto no_zone; + /* If we have NULL preferred zone, slowpath wll handle that */ } page = __alloc_pages_slowpath(alloc_mask, order, &ac); -no_zone: - /* - * When updating a task's mems_allowed, it is possible to race with - * parallel threads in such a way that an allocation can fail while - * the mask is being updated. If a page allocation is about to fail, - * check if the cpuset changed during allocation and if so, retry. - */ - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) { - alloc_mask = gfp_mask; - goto retry_cpuset; - } - out: if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) { -- cgit v1.2.3 From e47483bca2cc59a4593b37a270b16ee42b1d9f08 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 24 Jan 2017 15:18:41 -0800 Subject: mm, page_alloc: fix premature OOM when racing with cpuset mems update Ganapatrao Kulkarni reported that the LTP test cpuset01 in stress mode triggers OOM killer in few seconds, despite lots of free memory. The test attempts to repeatedly fault in memory in one process in a cpuset, while changing allowed nodes of the cpuset between 0 and 1 in another process. The problem comes from insufficient protection against cpuset changes, which can cause get_page_from_freelist() to consider all zones as non-eligible due to nodemask and/or current->mems_allowed. This was masked in the past by sufficient retries, but since commit 682a3385e773 ("mm, page_alloc: inline the fast path of the zonelist iterator") we fix the preferred_zoneref once, and don't iterate over the whole zonelist in further attempts, thus the only eligible zones might be placed in the zonelist before our starting point and we always miss them. A previous patch fixed this problem for current->mems_allowed. However, cpuset changes also update the task's mempolicy nodemask. The fix has two parts. We have to repeat the preferred_zoneref search when we detect cpuset update by way of seqcount, and we have to check the seqcount before considering OOM. [akpm@linux-foundation.org: fix typo in comment] Link: http://lkml.kernel.org/r/20170120103843.24587-5-vbabka@suse.cz Fixes: c33d6c06f60f ("mm, page_alloc: avoid looking up the first zone in a zonelist twice") Signed-off-by: Vlastimil Babka Reported-by: Ganapatrao Kulkarni Acked-by: Mel Gorman Acked-by: Hillf Danton Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0df3c089d3af..f3e0c69a97b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3555,6 +3555,17 @@ retry_cpuset: no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + /* + * We need to recalculate the starting point for the zonelist iterator + * because we might have used different nodemask in the fast path, or + * there was a cpuset modification and we are retrying - otherwise we + * could end up iterating over non-eligible zones endlessly. + */ + ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, ac->nodemask); + if (!ac->preferred_zoneref->zone) + goto nopage; + /* * The fast path uses conservative alloc_flags to succeed only until @@ -3715,6 +3726,13 @@ retry: &compaction_retries)) goto retry; + /* + * It's possible we raced with cpuset update so the OOM would be + * premature (see below the nopage: label for full explanation). + */ + if (read_mems_allowed_retry(cpuset_mems_cookie)) + goto retry_cpuset; + /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); if (page) @@ -3728,10 +3746,11 @@ retry: nopage: /* - * When updating a task's mems_allowed, it is possible to race with - * parallel threads in such a way that an allocation can fail while - * the mask is being updated. If a page allocation is about to fail, - * check if the cpuset changed during allocation and if so, retry. + * When updating a task's mems_allowed or mempolicy nodemask, it is + * possible to race with parallel threads in such a way that our + * allocation can fail while the mask is being updated. If we are about + * to fail, check if the cpuset changed during allocation and if so, + * retry. */ if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry_cpuset; @@ -3822,15 +3841,9 @@ no_zone: /* * Restore the original nodemask if it was potentially replaced with * &cpuset_current_mems_allowed to optimize the fast-path attempt. - * Also recalculate the starting point for the zonelist iterator or - * we could end up iterating over non-eligible zones endlessly. */ - if (unlikely(ac.nodemask != nodemask)) { + if (unlikely(ac.nodemask != nodemask)) ac.nodemask = nodemask; - ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, - ac.high_zoneidx, ac.nodemask); - /* If we have NULL preferred zone, slowpath wll handle that */ - } page = __alloc_pages_slowpath(alloc_mask, order, &ac); -- cgit v1.2.3