- 08 Oct, 2016 40 commits
-
-
Yisheng Xie authored
Arm64 supports gigantic pages after commit 084bd298 ("ARM64: mm: HugeTLB support.") however, it can only be allocated at boottime and can't be freed. This patch selects ARCH_HAS_GIGANTIC_PAGE to make gigantic pages can be allocated and freed at runtime for arch arm64. Link: http://lkml.kernel.org/r/1475227569-63446-3-git-send-email-xieyisheng1@huawei.comSigned-off-by:
Yisheng Xie <xieyisheng1@huawei.com> Acked-by:
Michal Hocko <mhocko@suse.com> Acked-by:
Catalin Marinas <catalin.marinas@arm.com> Acked-by:
Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Rob Herring <robh+dt@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Yisheng Xie authored
Avoid making ifdef get pretty unwieldy if many ARCHs support gigantic page. No functional change with this patch. Link: http://lkml.kernel.org/r/1475227569-63446-2-git-send-email-xieyisheng1@huawei.comSigned-off-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by:
-
Michal Hocko authored
We have received a hard to explain oom report from a customer. The oom triggered regardless there is a lot of free memory: PoolThread invoked oom-killer: gfp_mask=0x280da, order=0, oom_adj=0, oom_score_adj=0 PoolThread cpuset=/ mems_allowed=0-7 Pid: 30055, comm: PoolThread Tainted: G E X 3.0.101-80-default #1 Call Trace: dump_trace+0x75/0x300 dump_stack+0x69/0x6f dump_header+0x8e/0x110 oom_kill_process+0xa6/0x350 out_of_memory+0x2b7/0x310 __alloc_pages_slowpath+0x7dd/0x820 __alloc_pages_nodemask+0x1e9/0x200 alloc_pages_vma+0xe1/0x290 do_anonymous_page+0x13e/0x300 do_page_fault+0x1fd/0x4c0 page_fault+0x25/0x30 [...] active_anon:1135959151 inactive_anon:1051962 isolated_anon:0 active_file:13093 inactive_file:222506 isolated_file:0 unevictable:262144 dirty:2 writeback:0 unstable:0 free:432672819 slab_reclaimable:7917 slab_unreclaimable:95308 mapped:261139 shmem:166297 pagetables:2228282 bounce:0 [...] Node 0 DMA free:15896kB 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:15672kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes lowmem_reserve[]: 0 2892 775542 775542 Node 0 DMA32 free:2783784kB min:28kB low:32kB high:40kB active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:2961572kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes lowmem_reserve[]: 0 0 772650 772650 Node 0 Normal free:8120kB min:8160kB low:10200kB high:12240kB active_anon:779334960kB inactive_anon:2198744kB active_file:0kB inactive_file:180kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:791193600kB mlocked:131072kB dirty:0kB writeback:0kB mapped:372940kB shmem:361480kB slab_reclaimable:4536kB slab_unreclaimable:68472kB kernel_stack:10104kB pagetables:1414820kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:2280 all_unreclaimable? yes lowmem_reserve[]: 0 0 0 0 Node 1 Normal free:476718144kB min:8192kB low:10240kB high:12288kB active_anon:307623696kB inactive_anon:283620kB active_file:10392kB inactive_file:69908kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:4kB writeback:0kB mapped:257208kB shmem:189896kB slab_reclaimable:3868kB slab_unreclaimable:44756kB kernel_stack:1848kB pagetables:1369432kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 2 Normal free:386002452kB min:8192kB low:10240kB high:12288kB active_anon:398563752kB inactive_anon:68184kB active_file:10292kB inactive_file:29936kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:0kB writeback:0kB mapped:32084kB shmem:776kB slab_reclaimable:6888kB slab_unreclaimable:60056kB kernel_stack:8208kB pagetables:1282880kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 3 Normal free:196406760kB min:8192kB low:10240kB high:12288kB active_anon:587445640kB inactive_anon:164396kB active_file:5716kB inactive_file:709844kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:0kB writeback:0kB mapped:291776kB shmem:111416kB slab_reclaimable:5152kB slab_unreclaimable:44516kB kernel_stack:2168kB pagetables:1455956kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 4 Normal free:425338880kB min:8192kB low:10240kB high:12288kB active_anon:359695204kB inactive_anon:43216kB active_file:5748kB inactive_file:14772kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:0kB writeback:0kB mapped:24708kB shmem:1120kB slab_reclaimable:1884kB slab_unreclaimable:41060kB kernel_stack:1856kB pagetables:1100208kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 5 Normal free:11140kB min:8192kB low:10240kB high:12288kB active_anon:784240872kB inactive_anon:1217164kB active_file:28kB inactive_file:48kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:0kB writeback:0kB mapped:11408kB shmem:0kB slab_reclaimable:2008kB slab_unreclaimable:49220kB kernel_stack:1360kB pagetables:531600kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:1202 all_unreclaimable? yes lowmem_reserve[]: 0 0 0 0 Node 6 Normal free:243395332kB min:8192kB low:10240kB high:12288kB active_anon:542015544kB inactive_anon:40208kB active_file:968kB inactive_file:8484kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:0kB writeback:0kB mapped:19992kB shmem:496kB slab_reclaimable:1672kB slab_unreclaimable:37052kB kernel_stack:2088kB pagetables:750264kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 Node 7 Normal free:10768kB min:8192kB low:10240kB high:12288kB active_anon:784916936kB inactive_anon:192316kB active_file:19228kB inactive_file:56852kB unevictable:131072kB isolated(anon):0kB isolated(file):0kB present:794296320kB mlocked:131072kB dirty:4kB writeback:0kB mapped:34440kB shmem:4kB slab_reclaimable:5660kB slab_unreclaimable:36100kB kernel_stack:1328kB pagetables:1007968kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no lowmem_reserve[]: 0 0 0 0 So all nodes but Node 0 have a lot of free memory which should suggest that there is an available memory especially when mems_allowed=0-7. One could speculate that a massive process has managed to terminate and free up a lot of memory while racing with the above allocation request. Although this is highly unlikely it cannot be ruled out. A further debugging, however shown that the faulting process had mempolicy (not cpuset) to bind to Node 0. We cannot see that information from the report though. mems_allowed turned out to be more confusing than really helpful. Fix this by always priting the nodemask. It is either mempolicy mask (and non-null) or the one defined by the cpusets. The new output for the above oom report would be PoolThread invoked oom-killer: gfp_mask=0x280da(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), nodemask=0, order=0, oom_adj=0, oom_score_adj=0 This patch doesn't touch show_mem and the node filtering based on the cpuset node mask because mempolicy is always a subset of cpusets and seeing the full cpuset oom context might be helpful for tunning more specific mempolicies inside cpusets (e.g. when they turn out to be too restrictive). To prevent from ugly ifdefs the mask is printed even for !NUMA configurations but this should be OK (a single node will be printed). Link: http://lkml.kernel.org/r/20160930214146.28600-1-mhocko@kernel.orgSigned-off-by:Sellami Abdelkader <abdelkader.sellami@sap.com> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Sellami Abdelkader <abdelkader.sellami@sap.com> Signed-off-by:
-
Kirill A. Shutemov authored
Let's add comment on why we skip page_mapcount() for sl[aou]b pages. Link: http://lkml.kernel.org/r/20160922105532.GB24593@nodeSigned-off-by:
Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by:
-
Andrea Arcangeli authored
The old code was always doing: vma->vm_end = next->vm_end vma_rb_erase(next) // in __vma_unlink vma->vm_next = next->vm_next // in __vma_unlink next = vma->vm_next vma_gap_update(next) The new code still does the above for remove_next == 1 and 2, but for remove_next == 3 it has been changed and it does: next->vm_start = vma->vm_start vma_rb_erase(vma) // in __vma_unlink vma_gap_update(next) In the latter case, while unlinking "vma", validate_mm_rb() is told to ignore "vma" that is being removed, but next->vm_start was reduced instead. So for the new case, to avoid the false positive from validate_mm_rb, it should be "next" that is ignored when "vma" is being unlinked. "vma" and "next" in the above comment, considered pre-swap(). Link: http://lkml.kernel.org/r/1474492522-2261-4-git-send-email-aarcange@redhat.comSigned-off-by:
Andrea Arcangeli <aarcange@redhat.com> Tested-by:
Shaun Tancheff <shaun.tancheff@seagate.com> Cc: Rik van Riel <riel@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Jan Vorlicek <janvorli@microsoft.com> Signed-off-by:
-
Andrea Arcangeli authored
The cases are three not two. Link: http://lkml.kernel.org/r/1474492522-2261-3-git-send-email-aarcange@redhat.comSigned-off-by:
-
Andrea Arcangeli authored
If next would be NULL we couldn't reach such code path. Link: http://lkml.kernel.org/r/1474309513-20313-2-git-send-email-aarcange@redhat.comSigned-off-by:
-
Andrea Arcangeli authored
The rmap_walk can access vm_page_prot (and potentially vm_flags in the pte/pmd manipulations). So it's not safe to wait the caller to update the vm_page_prot/vm_flags after vma_merge returned potentially removing the "next" vma and extending the "current" vma over the next->vm_start,vm_end range, but still with the "current" vma vm_page_prot, after releasing the rmap locks. The vm_page_prot/vm_flags must be transferred from the "next" vma to the current vma while vma_merge still holds the rmap locks. The side effect of this race condition is pte corruption during migrate as remove_migration_ptes when run on a address of the "next" vma that got removed, used the vm_page_prot of the current vma. migrate mprotect ------------ ------------- migrating in "next" vma vma_merge() # removes "next" vma and # extends "current" vma # current vma is not with # vm_page_prot updated remove_migration_ptes read vm_page_prot of current "vma" establish pte with wrong permissions vm_set_page_prot(vma) # too late! change_protection in the old vma range only, next range is not updated This caused segmentation faults and potentially memory corruption in heavy mprotect loads with some light page migration caused by compaction in the background. Hugh Dickins pointed out the comment about the Odd case 8 in vma_merge which confirms the case 8 is only buggy one where the race can trigger, in all other vma_merge cases the above cannot happen. This fix removes the oddness factor from case 8 and it converts it from: AAAA PPPPNNNNXXXX -> PPPPNNNNNNNN to: AAAA PPPPNNNNXXXX -> PPPPXXXXXXXX XXXX has the right vma properties for the whole merged vma returned by vma_adjust, so it solves the problem fully. It has the added benefits that the callers could stop updating vma properties when vma_merge succeeds however the callers are not updated by this patch (there are bits like VM_SOFTDIRTY that still need special care for the whole range, as the vma merging ignores them, but as long as they're not processed by rmap walks and instead they're accessed with the mmap_sem at least for reading, they are fine not to be updated within vma_adjust before releasing the rmap_locks). Link: http://lkml.kernel.org/r/1474309513-20313-1-git-send-email-aarcange@redhat.comSigned-off-by:Aditya Mandaleeka <adityam@microsoft.com> Cc: Rik van Riel <riel@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Jan Vorlicek <janvorli@microsoft.com> Signed-off-by:
-
Andrea Arcangeli authored
mm->highest_vm_end doesn't need any update. After finally removing the oddness from vma_merge case 8 that was causing: 1) constant risk of trouble whenever anybody would check vma fields from rmap_walks, like it happened when page migration was introduced and it read the vma->vm_page_prot from a rmap_walk 2) the callers of vma_merge to re-initialize any value different from the current vma, instead of vma_merge() more reliably returning a vma that already matches all fields passed as parameter .. it is also worth to take the opportunity of cleaning up superfluous code in vma_adjust(), that if not removed adds up to the hard readability of the function. Link: http://lkml.kernel.org/r/1474492522-2261-5-git-send-email-aarcange@redhat.comSigned-off-by:
-
Andrea Arcangeli authored
vma->vm_page_prot is read lockless from the rmap_walk, it may be updated concurrently and this prevents the risk of reading intermediate values. Link: http://lkml.kernel.org/r/1474660305-19222-1-git-send-email-aarcange@redhat.comSigned-off-by:
-
zhong jiang authored
According to Hugh's suggestion, alloc_stable_node() with GFP_KERNEL can in rare cases cause a hung task warning. At present, if alloc_stable_node() allocation fails, two break_cows may want to allocate a couple of pages, and the issue will come up when free memory is under pressure. We fix it by adding __GFP_HIGH to GFP, to grant access to memory reserves, increasing the likelihood of allocation success. [akpm@linux-foundation.org: tweak comment] Link: http://lkml.kernel.org/r/1474354484-58233-1-git-send-email-zhongjiang@huawei.comSigned-off-by:
zhong jiang <zhongjiang@huawei.com> Suggested-by:
Hugh Dickins <hughd@google.com> Acked-by:
-
Yisheng Xie authored
Fix typo in comment. Link: http://lkml.kernel.org/r/1474788764-5774-1-git-send-email-ysxie@foxmail.comSigned-off-by:
-
Gerald Schaefer authored
For every pfn aligned to minimum_order, dissolve_free_huge_pages() will call dissolve_free_huge_page() which takes the hugetlb spinlock, even if the page is not huge at all or a hugepage that is in-use. Improve this by doing the PageHuge() and page_count() checks already in dissolve_free_huge_pages() before calling dissolve_free_huge_page(). In dissolve_free_huge_page(), when holding the spinlock, those checks need to be revalidated. Link: http://lkml.kernel.org/r/20160926172811.94033-4-gerald.schaefer@de.ibm.comSigned-off-by:
Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by:
-
Gerald Schaefer authored
In dissolve_free_huge_pages(), free hugepages will be dissolved without making sure that there are enough of them left to satisfy hugepage reservations. Fix this by adding a return value to dissolve_free_huge_pages() and checking h->free_huge_pages vs. h->resv_huge_pages. Note that this may lead to the situation where dissolve_free_huge_page() returns an error and all free hugepages that were dissolved before that error are lost, while the memory block still cannot be set offline. Fixes: c8721bbb ("mm: memory-hotplug: enable memory hotplug to handle hugepage") Link: http://lkml.kernel.org/r/20160926172811.94033-3-gerald.schaefer@de.ibm.comSigned-off-by:
-
Gerald Schaefer authored
Patch series "mm/hugetlb: memory offline issues with hugepages", v4. This addresses several issues with hugepages and memory offline. While the first patch fixes a panic, and is therefore rather important, the last patch is just a performance optimization. The second patch fixes a theoretical issue with reserved hugepages, while still leaving some ugly usability issue, see description. This patch (of 3): dissolve_free_huge_pages() will either run into the VM_BUG_ON() or a list corruption and addressing exception when trying to set a memory block offline that is part (but not the first part) of a "gigantic" hugetlb page with a size > memory block size. When no other smaller hugetlb page sizes are present, the VM_BUG_ON() will trigger directly. In the other case we will run into an addressing exception later, because dissolve_free_huge_page() will not work on the head page of the compound hugetlb page which will result in a NULL hstate from page_hstate(). To fix this, first remove the VM_BUG_ON() because it is wrong, and then use the compound head page in dissolve_free_huge_page(). This means that an unused pre-allocated gigantic page that has any part of itself inside the memory block that is going offline will be dissolved completely. Losing an unused gigantic hugepage is preferable to failing the memory offline, for example in the situation where a (possibly faulty) memory DIMM needs to go offline. Fixes: c8721bbb ("mm: memory-hotplug: enable memory hotplug to handle hugepage") Link: http://lkml.kernel.org/r/20160926172811.94033-2-gerald.schaefer@de.ibm.comSigned-off-by:
-
Wanlong Gao authored
Commit b4def350 ("mm, nobootmem: clean-up of free_low_memory_core_early()") removed the unnecessary nodeid argument, after that, this comment becomes more confused. We should move it to the right place. Fixes: b4def350 ("mm, nobootmem: clean-up of free_low_memory_core_early()") Link: http://lkml.kernel.org/r/1473996082-14603-1-git-send-email-wanlong.gao@gmail.comSigned-off-by:
Wanlong Gao <wanlong.gao@gmail.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
-
Rasmus Villemoes authored
Every other dentry_operations instance is const, and this one might as well be. Link: http://lkml.kernel.org/r/1473890528-7009-1-git-send-email-linux@rasmusvillemoes.dkSigned-off-by:
Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by:
-
Johannes Weiner authored
The cgroup core and the memory controller need to track socket ownership for different purposes, but the tracking sites being entirely different is kind of ugly. Be a better citizen and rename the memory controller callbacks to match the cgroup core callbacks, then move them to the same place. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20160914194846.11153-3-hannes@cmpxchg.orgSigned-off-by:
Johannes Weiner <hannes@cmpxchg.org> Acked-by:
Tejun Heo <tj@kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Michal Hocko <mhocko@suse.cz> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Signed-off-by:
-
Baoyou Xie authored
We get 1 warning when building kernel with W=1: drivers/char/mem.c:220:12: warning: no previous prototype for 'phys_mem_access_prot_allowed' [-Wmissing-prototypes] int __weak phys_mem_access_prot_allowed(struct file *file, In fact, its declaration is spreading to several header files in different architecture, but need to be declare in common header file. So this patch moves phys_mem_access_prot_allowed() to pgtable.h. Link: http://lkml.kernel.org/r/1473751597-12139-1-git-send-email-baoyou.xie@linaro.orgSigned-off-by:
Baoyou Xie <baoyou.xie@linaro.org> Acked-by:
Thomas Gleixner <tglx@linutronix.de> Acked-by:
Ralf Baechle <ralf@linux-mips.org> Signed-off-by:
-
Andrew Morton authored
So they are CONFIG_DEBUG_VM-only and more informative. Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: David S. Miller <davem@davemloft.net> Cc: Hugh Dickins <hughd@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Joe Perches <joe@perches.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Rik van Riel <riel@redhat.com> Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by:
-
Tetsuo Handa authored
Commit c32b3cbe ("oom, PM: make OOM detection in the freezer path raceless") inserted a WARN_ON() into pagefault_out_of_memory() in order to warn when we raced with disabling the OOM killer. Now, patch "oom, suspend: fix oom_killer_disable vs. pm suspend properly" introduced a timeout for oom_killer_disable(). Even if we raced with disabling the OOM killer and the system is OOM livelocked, the OOM killer will be enabled eventually (in 20 seconds by default) and the OOM livelock will be solved. Therefore, we no longer need to warn when we raced with disabling the OOM killer. Link: http://lkml.kernel.org/r/1473442120-7246-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jpSigned-off-by:
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by:
Michal Hocko <mhocko@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
-
Vlastimil Babka authored
Fragmentation index and the vm.extfrag_threshold sysctl is meant as a heuristic to prevent excessive compaction for costly orders (i.e. THP). It's unlikely to make any difference for non-costly orders, especially with the default threshold. But we cannot afford any uncertainty for the non-costly orders where the only alternative to successful reclaim/compaction is OOM. After the recent patches we are guaranteed maximum effort without heuristics from compaction before deciding OOM, and fragindex is the last remaining heuristic. Therefore skip fragindex altogether for non-costly orders. Suggested-by:
-
Vlastimil Babka authored
The compaction_zonelist_suitable() function tries to determine if compaction will be able to proceed after sufficient reclaim, i.e. whether there are enough reclaimable pages to provide enough order-0 freepages for compaction. This addition of reclaimable pages to the free pages works well for the order-0 watermark check, but in the fragmentation index check we only consider truly free pages. Thus we can get fragindex value close to 0 which indicates failure do to lack of memory, and wrongly decide that compaction won't be suitable even after reclaim. Instead of trying to somehow adjust fragindex for reclaimable pages, let's just skip it from compaction_zonelist_suitable(). Link: http://lkml.kernel.org/r/20160926162025.21555-4-vbabka@suse.czSigned-off-by:
-
Vlastimil Babka authored
The should_reclaim_retry() makes decisions based on no_progress_loops, so it makes sense to also update the counter there. It will be also consistent with should_compact_retry() and compaction_retries. No functional change. [hillf.zj@alibaba-inc.com: fix missing pointer dereferences] Link: http://lkml.kernel.org/r/20160926162025.21555-3-vbabka@suse.czSigned-off-by:
-
Vlastimil Babka authored
Several people have reported premature OOMs for order-2 allocations (stack) due to OOM rework in 4.7. In the scenario (parallel kernel build and dd writing to two drives) many pageblocks get marked as Unmovable and compaction free scanner struggles to isolate free pages. Joonsoo Kim pointed out that the free scanner skips pageblocks that are not movable to prevent filling them and forcing non-movable allocations to fallback to other pageblocks. Such heuristic makes sense to help prevent long-term fragmentation, but premature OOMs are relatively more urgent problem. As a compromise, this patch disables the heuristic only for the ultimate compaction priority. Link: http://lkml.kernel.org/r/20160906135258.18335-5-vbabka@suse.czReported-by:
Ralf-Peter Rohbeck <Ralf-Peter.Rohbeck@quantum.com> Reported-by:
Arkadiusz Miskiewicz <a.miskiewicz@gmail.com> Reported-by:
Olaf Hering <olaf@aepfle.de> Suggested-by:
Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
-
Vlastimil Babka authored
The new ultimate compaction priority disables some heuristics, which may result in excessive cost. This is fine for non-costly orders where we want to try hard before resulting for OOM, but might be disruptive for costly orders which do not trigger OOM and should generally have some fallback. Thus, we disable the full priority for costly orders. Suggested-by:
Michal Hocko <mhocko@kernel.org> Link: http://lkml.kernel.org/r/20160906135258.18335-4-vbabka@suse.czSigned-off-by:
-
Vlastimil Babka authored
During reclaim/compaction loop, compaction priority can be increased by the should_compact_retry() function, but the current code is not optimal. Priority is only increased when compaction_failed() is true, which means that compaction has scanned the whole zone. This may not happen even after multiple attempts with a lower priority due to parallel activity, so we might needlessly struggle on the lower priorities and possibly run out of compaction retry attempts in the process. After this patch we are guaranteed at least one attempt at the highest compaction priority even if we exhaust all retries at the lower priorities. Link: http://lkml.kernel.org/r/20160906135258.18335-3-vbabka@suse.czSigned-off-by:
-
Vlastimil Babka authored
Patch series "reintroduce compaction feedback for OOM decisions". After several people reported OOM's for order-2 allocations in 4.7 due to Michal Hocko's OOM rework, he reverted the part that considered compaction feedback [1] in the decisions to retry reclaim/compaction. This was to provide a fix quickly for 4.8 rc and 4.7 stable series, while mmotm had an almost complete solution that instead improved compaction reliability. This series completes the mmotm solution and reintroduces the compaction feedback into OOM decisions. The first two patches restore the state of mmotm before the temporary solution was merged, the last patch should be the missing piece for reliability. The third patch restricts the hardened compaction to non-costly orders, since costly orders don't result in OOMs in the first place. [1] http://marc.info/?i=20160822093249.GA14916%40dhcp22.suse.cz%3E This patch (of 4): Commit 6b4e3181 ("mm, oom: prevent premature OOM killer invocation for high order request") was intended as a quick fix of OOM regressions for 4.8 and stable 4.7.x kernels. For a better long-term solution, we still want to consider compaction feedback, which should be possible after some more improvements in the following patches. This reverts commit 6b4e3181. Link: http://lkml.kernel.org/r/20160906135258.18335-2-vbabka@suse.czSigned-off-by:
-
Huang Ying authored
After using the offset of the swap entry as the key of the swap cache, the page_index() becomes exactly same as page_file_index(). So the page_file_index() is removed and the callers are changed to use page_index() instead. Link: http://lkml.kernel.org/r/1473270649-27229-2-git-send-email-ying.huang@intel.comSigned-off-by:
"Huang, Ying" <ying.huang@intel.com> Cc: Trond Myklebust <trond.myklebust@primarydata.com> Cc: Anna Schumaker <anna.schumaker@netapp.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Huang Ying authored
This patch is to improve the performance of swap cache operations when the type of the swap device is not 0. Originally, the whole swap entry value is used as the key of the swap cache, even though there is one radix tree for each swap device. If the type of the swap device is not 0, the height of the radix tree of the swap cache will be increased unnecessary, especially on 64bit architecture. For example, for a 1GB swap device on the x86_64 architecture, the height of the radix tree of the swap cache is 11. But if the offset of the swap entry is used as the key of the swap cache, the height of the radix tree of the swap cache is 4. The increased height causes unnecessary radix tree descending and increased cache footprint. This patch reduces the height of the radix tree of the swap cache via using the offset of the swap entry instead of the whole swap entry value as the key of the swap cache. In 32 processes sequential swap out test case on a Xeon E5 v3 system with RAM disk as swap, the lock contention for the spinlock of the swap cache is reduced from 20.15% to 12.19%, when the type of the swap device is 1. Use the whole swap entry as key, perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 10.37, perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 9.78, Use the swap offset as key, perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 6.25, perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 5.94, Link: http://lkml.kernel.org/r/1473270649-27229-1-git-send-email-ying.huang@intel.comSigned-off-by:
-
Dan Williams authored
vm_insert_mixed() unlike vm_insert_pfn_prot() and vmf_insert_pfn_pmd(), fails to check the pgprot_t it uses for the mapping against the one recorded in the memtype tracking tree. Add the missing call to track_pfn_insert() to preclude cases where incompatible aliased mappings are established for a given physical address range. Link: http://lkml.kernel.org/r/147328717909.35069.14256589123570653697.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
Dan Williams <dan.j.williams@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by:
-
Reza Arbab authored
If store_mem_state() is called to online memory which is already online, it will return 1, the value it got from device_online(). This is wrong because store_mem_state() is a device_attribute .store function. Thus a non-negative return value represents input bytes read. Set the return value to -EINVAL in this case. Link: http://lkml.kernel.org/r/1472743777-24266-1-git-send-email-arbab@linux.vnet.ibm.comSigned-off-by:
Reza Arbab <arbab@linux.vnet.ibm.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Chen Yucong <slaoub@gmail.com> Cc: Andrew Banman <abanman@sgi.com> Cc: Seth Jennings <sjenning@redhat.com> Signed-off-by:
-
James Morse authored
mem_cgroup_count_precharge() and mem_cgroup_move_charge() both call walk_page_range() on the range 0 to ~0UL, neither provide a pte_hole callback, which causes the current implementation to skip non-vma regions. This is all fine but follow up changes would like to make walk_page_range more generic so it is better to be explicit about which range to traverse so let's use highest_vm_end to explicitly traverse only user mmaped memory. [mhocko@kernel.org: rewrote changelog] Link: http://lkml.kernel.org/r/1472655897-22532-1-git-send-email-james.morse@arm.comSigned-off-by:
James Morse <james.morse@arm.com> Acked-by:
-
Aaron Lu authored
The global zero page is used to satisfy an anonymous read fault. If THP(Transparent HugePage) is enabled then the global huge zero page is used. The global huge zero page uses an atomic counter for reference counting and is allocated/freed dynamically according to its counter value. CPU time spent on that counter will greatly increase if there are a lot of processes doing anonymous read faults. This patch proposes a way to reduce the access to the global counter so that the CPU load can be reduced accordingly. To do this, a new flag of the mm_struct is introduced: MMF_USED_HUGE_ZERO_PAGE. With this flag, the process only need to touch the global counter in two cases: 1 The first time it uses the global huge zero page; 2 The time when mm_user of its mm_struct reaches zero. Note that right now, the huge zero page is eligible to be freed as soon as its last use goes away. With this patch, the page will not be eligible to be freed until the exit of the last process from which it was ever used. And with the use of mm_user, the kthread is not eligible to use huge zero page either. Since no kthread is using huge zero page today, there is no difference after applying this patch. But if that is not desired, I can change it to when mm_count reaches zero. Case used for test on Haswell EP: usemem -n 72 --readonly -j 0x200000 100G Which spawns 72 processes and each will mmap 100G anonymous space and then do read only access to that space sequentially with a step of 2MB. CPU cycles from perf report for base commit: 54.03% usemem [kernel.kallsyms] [k] get_huge_zero_page CPU cycles from perf report for this commit: 0.11% usemem [kernel.kallsyms] [k] mm_get_huge_zero_page Performance(throughput) of the workload for base commit: 1784430792 Performance(throughput) of the workload for this commit: 4726928591 164% increase. Runtime of the workload for base commit: 707592 us Runtime of the workload for this commit: 303970 us 50% drop. Link: http://lkml.kernel.org/r/fe51a88f-446a-4622-1363-ad1282d71385@intel.comSigned-off-by:Aaron Lu <aaron.lu@intel.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com> Signed-off-by:
-
James Morse authored
Trying to walk all of virtual memory requires architecture specific knowledge. On x86_64, addresses must be sign extended from bit 48, whereas on arm64 the top VA_BITS of address space have their own set of page tables. clear_refs_write() calls walk_page_range() on the range 0 to ~0UL, it provides a test_walk() callback that only expects to be walking over VMAs. Currently walk_pmd_range() will skip memory regions that don't have a VMA, reporting them as a hole. As this call only expects to walk user address space, make it walk 0 to 'highest_vm_end'. Link: http://lkml.kernel.org/r/1472655792-22439-1-git-send-email-james.morse@arm.comSigned-off-by:
-
Tim Chen authored
In current kernel code, we only call node_set_state(cpu_to_node(cpu), N_CPU) when a cpu is hot plugged. But we do not set the node state for N_CPU when the cpus are brought online during boot. So this could lead to failure when we check to see if a node contains cpu with node_state(node_id, N_CPU). One use case is in the node_reclaime function: /* * Only run node reclaim on the local node or on nodes that do * not * have associated processors. This will favor the local * processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; I instrumented the kernel to call this function after boot and it always returns 0 on a x86 desktop machine until I apply the attached patch. int num_cpu_node(void) { int i, nr_cpu_nodes = 0; for_each_node(i) { if (node_state(i, N_CPU)) ++ nr_cpu_nodes; } return nr_cpu_nodes; } Fix this by checking each node for online CPU when we initialize vmstat that's responsible for maintaining node state. Link: http://lkml.kernel.org/r/20160829175922.GA21775@linux.intel.comSigned-off-by:Tim Chen <tim.c.chen@linux.intel.com> Acked-by:
David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: <Huang@linux.intel.com> Cc: Ying <ying.huang@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Signed-off-by:
-
Toshi Kani authored
To support DAX pmd mappings with unmodified applications, filesystems need to align an mmap address by the pmd size. Call thp_get_unmapped_area() from f_op->get_unmapped_area. Note, there is no change in behavior for a non-DAX file. Link: http://lkml.kernel.org/r/1472497881-9323-3-git-send-email-toshi.kani@hpe.comSigned-off-by:
Toshi Kani <toshi.kani@hpe.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jan Kara <jack@suse.cz> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
-
Toshi Kani authored
When CONFIG_FS_DAX_PMD is set, DAX supports mmap() using pmd page size. This feature relies on both mmap virtual address and FS block (i.e. physical address) to be aligned by the pmd page size. Users can use mkfs options to specify FS to align block allocations. However, aligning mmap address requires code changes to existing applications for providing a pmd-aligned address to mmap(). For instance, fio with "ioengine=mmap" performs I/Os with mmap() [1]. It calls mmap() with a NULL address, which needs to be changed to provide a pmd-aligned address for testing with DAX pmd mappings. Changing all applications that call mmap() with NULL is undesirable. Add thp_get_unmapped_area(), which can be called by filesystem's get_unmapped_area to align an mmap address by the pmd size for a DAX file. It calls the default handler, mm->get_unmapped_area(), to find a range and then aligns it for a DAX file. The patch is based on Matthew Wilcox's change that allows adding support of the pud page size easily. [1]: https://github.com/axboe/fio/blob/master/engines/mmap.c Link: http://lkml.kernel.org/r/1472497881-9323-2-git-send-email-toshi.kani@hpe.comSigned-off-by:
-
Simon Guo authored
This patch will randomly perform mlock/mlock2 on a given memory region, and verify the RLIMIT_MEMLOCK limitation works properly. Suggested-by:
Simon Guo <wei.guo.simon@gmail.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Eric B Munson <emunson@akamai.com> Cc: Simon Guo <wei.guo.simon@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Alexey Klimov <klimov.linux@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Thierry Reding <treding@nvidia.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by:
-
Simon Guo authored
Function seek_to_smaps_entry() can be useful for other selftest functionalities, so move it out to header file. Link: http://lkml.kernel.org/r/1473325970-11393-3-git-send-email-wei.guo.simon@gmail.comSigned-off-by:
-
