From a7306c3436e9c8e584a4b9fad5f3dc91be2a6076 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 2 Jun 2017 14:46:11 -0700 Subject: ksm: prevent crash after write_protect_page fails "err" needs to be left set to -EFAULT if split_huge_page succeeds. Otherwise if "err" gets clobbered with zero and write_protect_page fails, try_to_merge_one_page() will succeed instead of returning -EFAULT and then try_to_merge_with_ksm_page() will continue thinking kpage is a PageKsm when in fact it's still an anonymous page. Eventually it'll crash in page_add_anon_rmap. This has been reproduced on Fedora25 kernel but I can reproduce with upstream too. The bug was introduced in commit f765f540598a ("ksm: prepare to new THP semantics") introduced in v4.5. page:fffff67546ce1cc0 count:4 mapcount:2 mapping:ffffa094551e36e1 index:0x7f0f46673 flags: 0x2ffffc0004007c(referenced|uptodate|dirty|lru|active|swapbacked) page dumped because: VM_BUG_ON_PAGE(!PageLocked(page)) page->mem_cgroup:ffffa09674bf0000 ------------[ cut here ]------------ kernel BUG at mm/rmap.c:1222! CPU: 1 PID: 76 Comm: ksmd Not tainted 4.9.3-200.fc25.x86_64 #1 RIP: do_page_add_anon_rmap+0x1c4/0x240 Call Trace: page_add_anon_rmap+0x18/0x20 try_to_merge_with_ksm_page+0x50b/0x780 ksm_scan_thread+0x1211/0x1410 ? prepare_to_wait_event+0x100/0x100 ? try_to_merge_with_ksm_page+0x780/0x780 kthread+0xd9/0xf0 ? kthread_park+0x60/0x60 ret_from_fork+0x25/0x30 Fixes: f765f54059 ("ksm: prepare to new THP semantics") Link: http://lkml.kernel.org/r/20170513131040.21732-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: Federico Simoncelli Acked-by: Kirill A. Shutemov Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/ksm.c b/mm/ksm.c index d9fc0e456128..216184af0e19 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1028,8 +1028,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, goto out; if (PageTransCompound(page)) { - err = split_huge_page(page); - if (err) + if (split_huge_page(page)) goto out_unlock; } -- cgit v1.2.3-70-g09d2 From 4f4f2ba9c531b3d7cee293dd3654ba3b86e7d220 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Jun 2017 14:46:19 -0700 Subject: mm: clarify why we want kmalloc before falling backto vmallock While converting drm_[cm]alloc* helpers to kvmalloc* variants Chris Wilson has wondered why we want to try kmalloc before vmalloc fallback even for larger allocations requests. Let's clarify that one larger physically contiguous block is less likely to fragment memory than many scattered pages which can prevent more large blocks from being created. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170517080932.21423-1-mhocko@kernel.org Signed-off-by: Michal Hocko Suggested-by: Chris Wilson Reviewed-by: Chris Wilson Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/util.c b/mm/util.c index 464df3489903..26be6407abd7 100644 --- a/mm/util.c +++ b/mm/util.c @@ -357,8 +357,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL); /* - * Make sure that larger requests are not too disruptive - no OOM - * killer and no allocation failure warnings as we have a fallback + * We want to attempt a large physically contiguous block first because + * it is less likely to fragment multiple larger blocks and therefore + * contribute to a long term fragmentation less than vmalloc fallback. + * However make sure that larger requests are not too disruptive - no + * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; -- cgit v1.2.3-70-g09d2 From 478fe3037b2278d276d4cd9cd0ab06c4cb2e9b32 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 2 Jun 2017 14:46:25 -0700 Subject: slub/memcg: cure the brainless abuse of sysfs attributes memcg_propagate_slab_attrs() abuses the sysfs attribute file functions to propagate settings from the root kmem_cache to a newly created kmem_cache. It does that with: attr->show(root, buf); attr->store(new, buf, strlen(bug); Aside of being a lazy and absurd hackery this is broken because it does not check the return value of the show() function. Some of the show() functions return 0 w/o touching the buffer. That means in such a case the store function is called with the stale content of the previous show(). That causes nonsense like invoking kmem_cache_shrink() on a newly created kmem_cache. In the worst case it would cause handing in an uninitialized buffer. This should be rewritten proper by adding a propagate() callback to those slub_attributes which must be propagated and avoid that insane conversion to and from ASCII, but that's too large for a hot fix. Check at least the return value of the show() function, so calling store() with stale content is prevented. Steven said: "It can cause a deadlock with get_online_cpus() that has been uncovered by recent cpu hotplug and lockdep changes that Thomas and Peter have been doing. Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(cpu_hotplug.lock); lock(slab_mutex); lock(cpu_hotplug.lock); lock(slab_mutex); *** DEADLOCK ***" Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1705201244540.2255@nanos Signed-off-by: Thomas Gleixner Reported-by: Steven Rostedt Acked-by: David Rientjes Cc: Johannes Weiner Cc: Michal Hocko Cc: Peter Zijlstra Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Christoph Hellwig Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 57e5156f02be..7449593fca72 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5512,6 +5512,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) char mbuf[64]; char *buf; struct slab_attribute *attr = to_slab_attr(slab_attrs[i]); + ssize_t len; if (!attr || !attr->store || !attr->show) continue; @@ -5536,8 +5537,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) buf = buffer; } - attr->show(root_cache, buf); - attr->store(s, buf, strlen(buf)); + len = attr->show(root_cache, buf); + if (len > 0) + attr->store(s, buf, len); } if (buffer) -- cgit v1.2.3-70-g09d2 From c288983dddf714216428774e022ad78f48dd8cb1 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 2 Jun 2017 14:46:31 -0700 Subject: mm/page_alloc.c: make sure OOM victim can try allocations with no watermarks once Roman Gushchin has reported that the OOM killer can trivially selects next OOM victim when a thread doing memory allocation from page fault path was selected as first OOM victim. allocate invoked oom-killer: gfp_mask=0x14280ca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), nodemask=(null), order=0, oom_score_adj=0 allocate cpuset=/ mems_allowed=0 CPU: 1 PID: 492 Comm: allocate Not tainted 4.12.0-rc1-mm1+ #181 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Call Trace: oom_kill_process+0x219/0x3e0 out_of_memory+0x11d/0x480 __alloc_pages_slowpath+0xc84/0xd40 __alloc_pages_nodemask+0x245/0x260 alloc_pages_vma+0xa2/0x270 __handle_mm_fault+0xca9/0x10c0 handle_mm_fault+0xf3/0x210 __do_page_fault+0x240/0x4e0 trace_do_page_fault+0x37/0xe0 do_async_page_fault+0x19/0x70 async_page_fault+0x28/0x30 ... Out of memory: Kill process 492 (allocate) score 899 or sacrifice child Killed process 492 (allocate) total-vm:2052368kB, anon-rss:1894576kB, file-rss:4kB, shmem-rss:0kB allocate: page allocation failure: order:0, mode:0x14280ca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), nodemask=(null) allocate cpuset=/ mems_allowed=0 CPU: 1 PID: 492 Comm: allocate Not tainted 4.12.0-rc1-mm1+ #181 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Call Trace: __alloc_pages_slowpath+0xd32/0xd40 __alloc_pages_nodemask+0x245/0x260 alloc_pages_vma+0xa2/0x270 __handle_mm_fault+0xca9/0x10c0 handle_mm_fault+0xf3/0x210 __do_page_fault+0x240/0x4e0 trace_do_page_fault+0x37/0xe0 do_async_page_fault+0x19/0x70 async_page_fault+0x28/0x30 ... oom_reaper: reaped process 492 (allocate), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB ... allocate invoked oom-killer: gfp_mask=0x0(), nodemask=(null), order=0, oom_score_adj=0 allocate cpuset=/ mems_allowed=0 CPU: 1 PID: 492 Comm: allocate Not tainted 4.12.0-rc1-mm1+ #181 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Call Trace: oom_kill_process+0x219/0x3e0 out_of_memory+0x11d/0x480 pagefault_out_of_memory+0x68/0x80 mm_fault_error+0x8f/0x190 ? handle_mm_fault+0xf3/0x210 __do_page_fault+0x4b2/0x4e0 trace_do_page_fault+0x37/0xe0 do_async_page_fault+0x19/0x70 async_page_fault+0x28/0x30 ... Out of memory: Kill process 233 (firewalld) score 10 or sacrifice child Killed process 233 (firewalld) total-vm:246076kB, anon-rss:20956kB, file-rss:0kB, shmem-rss:0kB There is a race window that the OOM reaper completes reclaiming the first victim's memory while nothing but mutex_trylock() prevents the first victim from calling out_of_memory() from pagefault_out_of_memory() after memory allocation for page fault path failed due to being selected as an OOM victim. This is a side effect of commit 9a67f6488eca926f ("mm: consolidate GFP_NOFAIL checks in the allocator slowpath") because that commit silently changed the behavior from /* Avoid allocations with no watermarks from looping endlessly */ to /* * Give up allocations without trying memory reserves if selected * as an OOM victim */ in __alloc_pages_slowpath() by moving the location to check TIF_MEMDIE flag. I have noticed this change but I didn't post a patch because I thought it is an acceptable change other than noise by warn_alloc() because !__GFP_NOFAIL allocations are allowed to fail. But we overlooked that failing memory allocation from page fault path makes difference due to the race window explained above. While it might be possible to add a check to pagefault_out_of_memory() that prevents the first victim from calling out_of_memory() or remove out_of_memory() from pagefault_out_of_memory(), changing pagefault_out_of_memory() does not suppress noise by warn_alloc() when allocating thread was selected as an OOM victim. There is little point with printing similar backtraces and memory information from both out_of_memory() and warn_alloc(). Instead, if we guarantee that current thread can try allocations with no watermarks once when current thread looping inside __alloc_pages_slowpath() was selected as an OOM victim, we can follow "who can use memory reserves" rules and suppress noise by warn_alloc() and prevent memory allocations from page fault path from calling pagefault_out_of_memory(). If we take the comment literally, this patch would do - if (test_thread_flag(TIF_MEMDIE)) - goto nopage; + if (alloc_flags == ALLOC_NO_WATERMARKS || (gfp_mask & __GFP_NOMEMALLOC)) + goto nopage; because gfp_pfmemalloc_allowed() returns false if __GFP_NOMEMALLOC is given. But if I recall correctly (I couldn't find the message), the condition is meant to apply to only OOM victims despite the comment. Therefore, this patch preserves TIF_MEMDIE check. Fixes: 9a67f6488eca926f ("mm: consolidate GFP_NOFAIL checks in the allocator slowpath") Link: http://lkml.kernel.org/r/201705192112.IAF69238.OQOHSJLFOFFMtV@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Reported-by: Roman Gushchin Tested-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: [4.11] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f9e450c6b6e4..b7a6f583a373 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3870,7 +3870,9 @@ retry: goto got_pg; /* Avoid allocations with no watermarks from looping endlessly */ - if (test_thread_flag(TIF_MEMDIE)) + if (test_thread_flag(TIF_MEMDIE) && + (alloc_flags == ALLOC_NO_WATERMARKS || + (gfp_mask & __GFP_NOMEMALLOC))) goto nopage; /* Retry as long as the OOM killer is making progress */ -- cgit v1.2.3-70-g09d2 From d0f0931de936a0a468d7e59284d39581c16d3a73 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 2 Jun 2017 14:46:34 -0700 Subject: mm: avoid spurious 'bad pmd' warning messages When the pmd_devmap() checks were added by 5c7fb56e5e3f ("mm, dax: dax-pmd vs thp-pmd vs hugetlbfs-pmd") to add better support for DAX huge pages, they were all added to the end of if() statements after existing pmd_trans_huge() checks. So, things like: - if (pmd_trans_huge(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) When further checks were added after pmd_trans_unstable() checks by commit 7267ec008b5c ("mm: postpone page table allocation until we have page to map") they were also added at the end of the conditional: + if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) This ordering is fine for pmd_trans_huge(), but doesn't work for pmd_trans_unstable(). This is because DAX huge pages trip the bad_pmd() check inside of pmd_none_or_trans_huge_or_clear_bad() (called by pmd_trans_unstable()), which prints out a warning and returns 1. So, we do end up doing the right thing, but only after spamming dmesg with suspicious looking messages: mm/pgtable-generic.c:39: bad pmd ffff8808daa49b88(84000001006000a5) Reorder these checks in a helper so that pmd_devmap() is checked first, avoiding the error messages, and add a comment explaining why the ordering is important. Fixes: commit 7267ec008b5c ("mm: postpone page table allocation until we have page to map") Link: http://lkml.kernel.org/r/20170522215749.23516-1-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Pawel Lebioda Cc: "Darrick J. Wong" Cc: Alexander Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Dave Hansen Cc: Matthew Wilcox Cc: "Kirill A . Shutemov" Cc: Dave Jiang Cc: Xiong Zhou Cc: Eryu Guan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 40 ++++++++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 6ff5d729ded0..2e65df1831d9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3029,6 +3029,17 @@ static int __do_fault(struct vm_fault *vmf) return ret; } +/* + * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. + * If we check pmd_trans_unstable() first we will trip the bad_pmd() check + * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly + * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. + */ +static int pmd_devmap_trans_unstable(pmd_t *pmd) +{ + return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); +} + static int pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; @@ -3052,18 +3063,27 @@ static int pte_alloc_one_map(struct vm_fault *vmf) map_pte: /* * If a huge pmd materialized under us just retry later. Use - * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd - * didn't become pmd_trans_huge under us and then back to pmd_none, as - * a result of MADV_DONTNEED running immediately after a huge pmd fault - * in a different thread of this mm, in turn leading to a misleading - * pmd_trans_huge() retval. All we have to ensure is that it is a - * regular pmd that we can walk with pte_offset_map() and we can do that - * through an atomic read in C, which is what pmd_trans_unstable() - * provides. + * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of + * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge + * under us and then back to pmd_none, as a result of MADV_DONTNEED + * running immediately after a huge pmd fault in a different thread of + * this mm, in turn leading to a misleading pmd_trans_huge() retval. + * All we have to ensure is that it is a regular pmd that we can walk + * with pte_offset_map() and we can do that through an atomic read in + * C, which is what pmd_trans_unstable() provides. */ - if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd)) + if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; + /* + * At this point we know that our vmf->pmd points to a page of ptes + * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() + * for the duration of the fault. If a racing MADV_DONTNEED runs and + * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still + * be valid and we will re-check to make sure the vmf->pte isn't + * pte_none() under vmf->ptl protection when we return to + * alloc_set_pte(). + */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; @@ -3690,7 +3710,7 @@ static int handle_pte_fault(struct vm_fault *vmf) vmf->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ - if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd)) + if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge -- cgit v1.2.3-70-g09d2 From 30809f559a0d348c2dfd7ab05e9a451e2384962e Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Fri, 2 Jun 2017 14:46:40 -0700 Subject: mm/migrate: fix refcount handling when !hugepage_migration_supported() On failing to migrate a page, soft_offline_huge_page() performs the necessary update to the hugepage ref-count. But when !hugepage_migration_supported() , unmap_and_move_hugepage() also decrements the page ref-count for the hugepage. The combined behaviour leaves the ref-count in an inconsistent state. This leads to soft lockups when running the overcommitted hugepage test from mce-tests suite. Soft offlining pfn 0x83ed600 at process virtual address 0x400000000000 soft offline: 0x83ed600: migration failed 1, type 1fffc00000008008 (uptodate|head) INFO: rcu_preempt detected stalls on CPUs/tasks: Tasks blocked on level-0 rcu_node (CPUs 0-7): P2715 (detected by 7, t=5254 jiffies, g=963, c=962, q=321) thugetlb_overco R running task 0 2715 2685 0x00000008 Call trace: dump_backtrace+0x0/0x268 show_stack+0x24/0x30 sched_show_task+0x134/0x180 rcu_print_detail_task_stall_rnp+0x54/0x7c rcu_check_callbacks+0xa74/0xb08 update_process_times+0x34/0x60 tick_sched_handle.isra.7+0x38/0x70 tick_sched_timer+0x4c/0x98 __hrtimer_run_queues+0xc0/0x300 hrtimer_interrupt+0xac/0x228 arch_timer_handler_phys+0x3c/0x50 handle_percpu_devid_irq+0x8c/0x290 generic_handle_irq+0x34/0x50 __handle_domain_irq+0x68/0xc0 gic_handle_irq+0x5c/0xb0 Address this by changing the putback_active_hugepage() in soft_offline_huge_page() to putback_movable_pages(). This only triggers on systems that enable memory failure handling (ARCH_SUPPORTS_MEMORY_FAILURE) but not hugepage migration (!ARCH_ENABLE_HUGEPAGE_MIGRATION). I imagine this wasn't triggered as there aren't many systems running this configuration. [akpm@linux-foundation.org: remove dead comment, per Naoya] Link: http://lkml.kernel.org/r/20170525135146.32011-1-punit.agrawal@arm.com Reported-by: Manoj Iyer Tested-by: Manoj Iyer Suggested-by: Naoya Horiguchi Signed-off-by: Punit Agrawal Cc: Joonsoo Kim Cc: Wanpeng Li Cc: Christoph Lameter Cc: Mel Gorman Cc: [3.14+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2527dfeddb00..342fac9ba89b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1595,12 +1595,8 @@ static int soft_offline_huge_page(struct page *page, int flags) if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n", pfn, ret, page->flags, &page->flags); - /* - * We know that soft_offline_huge_page() tries to migrate - * only one hugepage pointed to by hpage, so we need not - * run through the pagelist here. - */ - putback_active_hugepage(hpage); + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); if (ret > 0) ret = -EIO; } else { -- cgit v1.2.3-70-g09d2 From 70feee0e1ef331b22cc51f383d532a0d043fbdcc Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Fri, 2 Jun 2017 14:46:43 -0700 Subject: mlock: fix mlock count can not decrease in race condition Kefeng reported that when running the follow test, the mlock count in meminfo will increase permanently: [1] testcase linux:~ # cat test_mlockal grep Mlocked /proc/meminfo for j in `seq 0 10` do for i in `seq 4 15` do ./p_mlockall >> log & done sleep 0.2 done # wait some time to let mlock counter decrease and 5s may not enough sleep 5 grep Mlocked /proc/meminfo linux:~ # cat p_mlockall.c #include #include #include #define SPACE_LEN 4096 int main(int argc, char ** argv) { int ret; void *adr = malloc(SPACE_LEN); if (!adr) return -1; ret = mlockall(MCL_CURRENT | MCL_FUTURE); printf("mlcokall ret = %d\n", ret); ret = munlockall(); printf("munlcokall ret = %d\n", ret); free(adr); return 0; } In __munlock_pagevec() we should decrement NR_MLOCK for each page where we clear the PageMlocked flag. Commit 1ebb7cc6a583 ("mm: munlock: batch NR_MLOCK zone state updates") has introduced a bug where we don't decrement NR_MLOCK for pages where we clear the flag, but fail to isolate them from the lru list (e.g. when the pages are on some other cpu's percpu pagevec). Since PageMlocked stays cleared, the NR_MLOCK accounting gets permanently disrupted by this. Fix it by counting the number of page whose PageMlock flag is cleared. Fixes: 1ebb7cc6a583 (" mm: munlock: batch NR_MLOCK zone state updates") Link: http://lkml.kernel.org/r/1495678405-54569-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie Reported-by: Kefeng Wang Tested-by: Kefeng Wang Cc: Vlastimil Babka Cc: Joern Engel Cc: Mel Gorman Cc: Michel Lespinasse Cc: Hugh Dickins Cc: Rik van Riel Cc: Johannes Weiner Cc: Michal Hocko Cc: Xishi Qiu Cc: zhongjiang Cc: Hanjun Guo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mlock.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/mlock.c b/mm/mlock.c index c483c5c20b4b..b562b5523a65 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -284,7 +284,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) { int i; int nr = pagevec_count(pvec); - int delta_munlocked; + int delta_munlocked = -nr; struct pagevec pvec_putback; int pgrescued = 0; @@ -304,6 +304,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) continue; else __munlock_isolation_failed(page); + } else { + delta_munlocked++; } /* @@ -315,7 +317,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pagevec_add(&pvec_putback, pvec->pages[i]); pvec->pages[i] = NULL; } - delta_munlocked = -nr + pagevec_count(&pvec_putback); __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); spin_unlock_irq(zone_lru_lock(zone)); -- cgit v1.2.3-70-g09d2 From 9a291a7c9428155e8e623e4a3989f8be47134df5 Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 2 Jun 2017 14:46:46 -0700 Subject: mm/hugetlb: report -EHWPOISON not -EFAULT when FOLL_HWPOISON is specified KVM uses get_user_pages() to resolve its stage2 faults. KVM sets the FOLL_HWPOISON flag causing faultin_page() to return -EHWPOISON when it finds a VM_FAULT_HWPOISON. KVM handles these hwpoison pages as a special case. (check_user_page_hwpoison()) When huge pages are involved, this doesn't work so well. get_user_pages() calls follow_hugetlb_page(), which stops early if it receives VM_FAULT_HWPOISON from hugetlb_fault(), eventually returning -EFAULT to the caller. The step to map this to -EHWPOISON based on the FOLL_ flags is missing. The hwpoison special case is skipped, and -EFAULT is returned to user-space, causing Qemu or kvmtool to exit. Instead, move this VM_FAULT_ to errno mapping code into a header file and use it from faultin_page() and follow_hugetlb_page(). With this, KVM works as expected. This isn't a problem for arm64 today as we haven't enabled MEMORY_FAILURE, but I can't see any reason this doesn't happen on x86 too, so I think this should be a fix. This doesn't apply earlier than stable's v4.11.1 due to all sorts of cleanup. [james.morse@arm.com: add vm_fault_to_errno() call to faultin_page()] suggested. Link: http://lkml.kernel.org/r/20170525171035.16359-1-james.morse@arm.com [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170524160900.28786-1-james.morse@arm.com Signed-off-by: James Morse Acked-by: Punit Agrawal Acked-by: Naoya Horiguchi Cc: "Kirill A . Shutemov" Cc: [4.11.1+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 11 +++++++++++ mm/gup.c | 20 ++++++++------------ mm/hugetlb.c | 5 +++++ 3 files changed, 24 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7cb17c6b97de..b892e95d4929 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2327,6 +2327,17 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +static inline int vm_fault_to_errno(int vm_fault, int foll_flags) +{ + if (vm_fault & VM_FAULT_OOM) + return -ENOMEM; + if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) + return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; + if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) + return -EFAULT; + return 0; +} + typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, diff --git a/mm/gup.c b/mm/gup.c index d9e6fddcc51f..b3c7214d710d 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -407,12 +407,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, ret = handle_mm_fault(vma, address, fault_flags); if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) - return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; - if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) - return -EFAULT; + int err = vm_fault_to_errno(ret, *flags); + + if (err) + return err; BUG(); } @@ -723,12 +721,10 @@ retry: ret = handle_mm_fault(vma, address, fault_flags); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) - return -EHWPOISON; - if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) - return -EFAULT; + int err = vm_fault_to_errno(ret, 0); + + if (err) + return err; BUG(); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e5828875f7bb..3eedb187e549 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4170,6 +4170,11 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, } ret = hugetlb_fault(mm, vma, vaddr, fault_flags); if (ret & VM_FAULT_ERROR) { + int err = vm_fault_to_errno(ret, flags); + + if (err) + return err; + remainder = 0; break; } -- cgit v1.2.3-70-g09d2 From 864b9a393dcb5aed09b8fd31b9bbda0fdda99374 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Jun 2017 14:46:49 -0700 Subject: mm: consider memblock reservations for deferred memory initialization sizing We have seen an early OOM killer invocation on ppc64 systems with crashkernel=4096M: kthreadd invoked oom-killer: gfp_mask=0x16040c0(GFP_KERNEL|__GFP_COMP|__GFP_NOTRACK), nodemask=7, order=0, oom_score_adj=0 kthreadd cpuset=/ mems_allowed=7 CPU: 0 PID: 2 Comm: kthreadd Not tainted 4.4.68-1.gd7fe927-default #1 Call Trace: dump_stack+0xb0/0xf0 (unreliable) dump_header+0xb0/0x258 out_of_memory+0x5f0/0x640 __alloc_pages_nodemask+0xa8c/0xc80 kmem_getpages+0x84/0x1a0 fallback_alloc+0x2a4/0x320 kmem_cache_alloc_node+0xc0/0x2e0 copy_process.isra.25+0x260/0x1b30 _do_fork+0x94/0x470 kernel_thread+0x48/0x60 kthreadd+0x264/0x330 ret_from_kernel_thread+0x5c/0xa4 Mem-Info: active_anon:0 inactive_anon:0 isolated_anon:0 active_file:0 inactive_file:0 isolated_file:0 unevictable:0 dirty:0 writeback:0 unstable:0 slab_reclaimable:5 slab_unreclaimable:73 mapped:0 shmem:0 pagetables:0 bounce:0 free:0 free_pcp:0 free_cma:0 Node 7 DMA free:0kB min:0kB low:0kB high:0kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:52428800kB managed:110016kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:320kB slab_unreclaimable:4672kB kernel_stack:1152kB pagetables:0kB unstable:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes lowmem_reserve[]: 0 0 0 0 Node 7 DMA: 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB = 0kB 0 total pagecache pages 0 pages in swap cache Swap cache stats: add 0, delete 0, find 0/0 Free swap = 0kB Total swap = 0kB 819200 pages RAM 0 pages HighMem/MovableOnly 817481 pages reserved 0 pages cma reserved 0 pages hwpoisoned the reason is that the managed memory is too low (only 110MB) while the rest of the the 50GB is still waiting for the deferred intialization to be done. update_defer_init estimates the initial memoty to initialize to 2GB at least but it doesn't consider any memory allocated in that range. In this particular case we've had Reserving 4096MB of memory at 128MB for crashkernel (System RAM: 51200MB) so the low 2GB is mostly depleted. Fix this by considering memblock allocations in the initial static initialization estimation. Move the max_initialise to reset_deferred_meminit and implement a simple memblock_reserved_memory helper which iterates all reserved blocks and sums the size of all that start below the given address. The cumulative size is than added on top of the initial estimation. This is still not ideal because reset_deferred_meminit doesn't consider holes and so reservation might be above the initial estimation whihch we ignore but let's make the logic simpler until we really need to handle more complicated cases. Fixes: 3a80a7fa7989 ("mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set") Link: http://lkml.kernel.org/r/20170531104010.GI27783@dhcp22.suse.cz Signed-off-by: Michal Hocko Acked-by: Mel Gorman Tested-by: Srikar Dronamraju Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 8 ++++++++ include/linux/mmzone.h | 1 + mm/memblock.c | 23 +++++++++++++++++++++++ mm/page_alloc.c | 33 ++++++++++++++++++++++----------- 4 files changed, 54 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 4ce24a376262..8098695e5d8d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -425,12 +425,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif +extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr); #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { return 0; } +static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + return 0; +} + #endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ebaccd4e7d8c..ef6a13b7bd3e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -678,6 +678,7 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; + unsigned long static_init_size; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/memblock.c b/mm/memblock.c index b049c9b2dba8..7b8a5db76a2f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1739,6 +1739,29 @@ static void __init_memblock memblock_dump(struct memblock_type *type) } } +extern unsigned long __init_memblock +memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr) +{ + struct memblock_region *rgn; + unsigned long size = 0; + int idx; + + for_each_memblock_type((&memblock.reserved), rgn) { + phys_addr_t start, end; + + if (rgn->base + rgn->size < start_addr) + continue; + if (rgn->base > end_addr) + continue; + + start = rgn->base; + end = start + rgn->size; + size += end - start; + } + + return size; +} + void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b7a6f583a373..2302f250d6b1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -292,6 +292,26 @@ int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void reset_deferred_meminit(pg_data_t *pgdat) { + unsigned long max_initialise; + unsigned long reserved_lowmem; + + /* + * Initialise at least 2G of a node but also take into account that + * two large system hashes that can take up 1GB for 0.25TB/node. + */ + max_initialise = max(2UL << (30 - PAGE_SHIFT), + (pgdat->node_spanned_pages >> 8)); + + /* + * Compensate the all the memblock reservations (e.g. crash kernel) + * from the initial estimation to make sure we will initialize enough + * memory to boot. + */ + reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, + pgdat->node_start_pfn + max_initialise); + max_initialise += reserved_lowmem; + + pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } @@ -314,20 +334,11 @@ static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) { - unsigned long max_initialise; - /* Always populate low zones for address-contrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; - /* - * Initialise at least 2G of a node but also take into account that - * two large system hashes that can take up 1GB for 0.25TB/node. - */ - max_initialise = max(2UL << (30 - PAGE_SHIFT), - (pgdat->node_spanned_pages >> 8)); - (*nr_initialised)++; - if ((*nr_initialised > max_initialise) && + if ((*nr_initialised > pgdat->static_init_size) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; @@ -6138,7 +6149,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx); - reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; pgdat->per_cpu_nodestats = NULL; @@ -6160,6 +6170,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif + reset_deferred_meminit(pgdat); free_area_init_core(pgdat); } -- cgit v1.2.3-70-g09d2