kernel.git/mm/swap.c, branch linux-3.18.y

4.1.28 Fix bad backport of 8f182270dfec "mm/swap.c: flush lru pvecs on compound page arrival"

2016-07-20T15:35:52Z

When I pulled in 4.1.28 into my stable 4.1-rt tree and ran the tests, it crashed with a severe OOM killing everything. I then tested 4.1.28 without -rt and it had the same issue. I did a bisect between 4.1.27 and 4.1.28 and found that the bug started at: commit 8f182270dfec "mm/swap.c: flush lru pvecs on compound page arrival" Looking at that patch and what's in mainline, I see that there's a mismatch in one of the hunks: Mainline: @@ -391,9 +391,8 @@ static void __lru_cache_add(struct page *page) struct pagevec *pvec = &get_cpu_var(lru_add_pvec); get_page(page); - if (!pagevec_space(pvec)) + if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); - pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } Stable 4.1.28: @@ -631,9 +631,8 @@ static void __lru_cache_add(struct page *page) struct pagevec *pvec = &get_cpu_var(lru_add_pvec); page_cache_get(page); - if (!pagevec_space(pvec)) + if (!pagevec_space(pvec) || PageCompound(page)) __pagevec_lru_add(pvec); - pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } Where mainline replace pagevec_space() with pagevec_add, and stable did not. Fixing this makes the OOM go away. Note, 3.18 has the same bug. Signed-off-by: Steven Rostedt Signed-off-by: Sasha Levin

mm/swap.c: flush lru pvecs on compound page arrival

2016-07-12T12:47:11Z

[ Upstream commit 8f182270dfec432e93fae14f9208a6b9af01009f ] Currently we can have compound pages held on per cpu pagevecs, which leads to a lot of memory unavailable for reclaim when needed. In the systems with hundreads of processors it can be GBs of memory. On of the way of reproducing the problem is to not call munmap explicitly on all mapped regions (i.e. after receiving SIGTERM). After that some pages (with THP enabled also huge pages) may end up on lru_add_pvec, example below. void main() { #pragma omp parallel { size_t size = 55 * 1000 * 1000; // smaller than MEM/CPUS void *p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS , -1, 0); if (p != MAP_FAILED) memset(p, 0, size); //munmap(p, size); // uncomment to make the problem go away } } When we run it with THP enabled it will leave significant amount of memory on lru_add_pvec. This memory will be not reclaimed if we hit OOM, so when we run above program in a loop: for i in `seq 100`; do ./a.out; done many processes (95% in my case) will be killed by OOM. The primary point of the LRU add cache is to save the zone lru_lock contention with a hope that more pages will belong to the same zone and so their addition can be batched. The huge page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like a safer option when compared to a potential excess in the caching which can be quite large and much harder to fix because lru_add_drain_all is way to expensive and it is not really clear what would be a good moment to call it. Similarly we can reproduce the problem on lru_deactivate_pvec by adding: madvise(p, size, MADV_FREE); after memset. This patch flushes lru pvecs on compound page arrival making the problem less severe - after applying it kill rate of above example drops to 0%, due to reducing maximum amount of memory held on pvec from 28MB (with THP) to 56kB per CPU. Suggested-by: Michal Hocko Link: http://lkml.kernel.org/r/1466180198-18854-1-git-send-email-lukasz.odzioba@intel.com Signed-off-by: Lukasz Odzioba Acked-by: Michal Hocko Cc: Kirill Shutemov Cc: Andrea Arcangeli Cc: Vladimir Davydov Cc: Ming Li Cc: Minchan Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin

mm: rename deactivate_page to deactivate_file_page

2016-07-12T12:47:10Z

[ Upstream commit cc5993bd7b8cff4a3e37042ee1358d1d5eafa70c ] "deactivate_page" was created for file invalidation so it has too specific logic for file-backed pages. So, let's change the name of the function and date to a file-specific one and yield the generic name. Signed-off-by: Minchan Kim Cc: Michal Hocko Cc: Johannes Weiner Cc: Mel Gorman Cc: Rik van Riel Cc: Shaohua Li Cc: Wang, Yalin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin

mm: memcontrol: do not kill uncharge batching in free_pages_and_swap_cache

2014-10-10T02:25:59Z

free_pages_and_swap_cache limits release_pages to PAGEVEC_SIZE chunks. This is not a big deal for the normal release path but it completely kills memcg uncharge batching which reduces res_counter spin_lock contention. Dave has noticed this with his page fault scalability test case on a large machine when the lock was basically dominating on all CPUs: 80.18% 80.18% [kernel] [k] _raw_spin_lock | --- _raw_spin_lock | |--66.59%-- res_counter_uncharge_until | res_counter_uncharge | uncharge_batch | uncharge_list | mem_cgroup_uncharge_list | release_pages | free_pages_and_swap_cache | tlb_flush_mmu_free | | | |--90.12%-- unmap_single_vma | | unmap_vmas | | unmap_region | | do_munmap | | vm_munmap | | sys_munmap | | system_call_fastpath | | __GI___munmap | | | --9.88%-- tlb_flush_mmu | tlb_finish_mmu | unmap_region | do_munmap | vm_munmap | sys_munmap | system_call_fastpath | __GI___munmap In his case the load was running in the root memcg and that part has been handled by reverting 05b843012335 ("mm: memcontrol: use root_mem_cgroup res_counter") because this is a clear regression, but the problem remains inside dedicated memcgs. There is no reason to limit release_pages to PAGEVEC_SIZE batches other than lru_lock held times. This logic, however, can be moved inside the function. mem_cgroup_uncharge_list and free_hot_cold_page_list do not hold any lock for the whole pages_to_free list so it is safe to call them in a single run. The release_pages() code was previously breaking the lru_lock each PAGEVEC_SIZE pages (ie, 14 pages). However this code has no usage of pagevecs so switch to breaking the lock at least every SWAP_CLUSTER_MAX (32) pages. This means that the lock acquisition frequency is approximately halved and the max hold times are approximately doubled. The now unneeded batching is removed from free_pages_and_swap_cache(). Also update the grossly out-of-date release_pages documentation. Signed-off-by: Michal Hocko Signed-off-by: Johannes Weiner Reported-by: Dave Hansen Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: memcontrol: use page lists for uncharge batching

2014-08-08T22:57:18Z

Pages are now uncharged at release time, and all sources of batched uncharges operate on lists of pages. Directly use those lists, and get rid of the per-task batching state. This also batches statistics accounting, in addition to the res counter charges, to reduce IRQ-disabling and re-enabling. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Cc: Naoya Horiguchi Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: memcontrol: rewrite uncharge API

2014-08-08T22:57:17Z

The memcg uncharging code that is involved towards the end of a page's lifetime - truncation, reclaim, swapout, migration - is impressively complicated and fragile. Because anonymous and file pages were always charged before they had their page->mapping established, uncharges had to happen when the page type could still be known from the context; as in unmap for anonymous, page cache removal for file and shmem pages, and swap cache truncation for swap pages. However, these operations happen well before the page is actually freed, and so a lot of synchronization is necessary: - Charging, uncharging, page migration, and charge migration all need to take a per-page bit spinlock as they could race with uncharging. - Swap cache truncation happens during both swap-in and swap-out, and possibly repeatedly before the page is actually freed. This means that the memcg swapout code is called from many contexts that make no sense and it has to figure out the direction from page state to make sure memory and memory+swap are always correctly charged. - On page migration, the old page might be unmapped but then reused, so memcg code has to prevent untimely uncharging in that case. Because this code - which should be a simple charge transfer - is so special-cased, it is not reusable for replace_page_cache(). But now that charged pages always have a page->mapping, introduce mem_cgroup_uncharge(), which is called after the final put_page(), when we know for sure that nobody is looking at the page anymore. For page migration, introduce mem_cgroup_migrate(), which is called after the migration is successful and the new page is fully rmapped. Because the old page is no longer uncharged after migration, prevent double charges by decoupling the page's memcg association (PCG_USED and pc->mem_cgroup) from the page holding an actual charge. The new bits PCG_MEM and PCG_MEMSW represent the respective charges and are transferred to the new page during migration. mem_cgroup_migrate() is suitable for replace_page_cache() as well, which gets rid of mem_cgroup_replace_page_cache(). However, care needs to be taken because both the source and the target page can already be charged and on the LRU when fuse is splicing: grab the page lock on the charge moving side to prevent changing pc->mem_cgroup of a page under migration. Also, the lruvecs of both pages change as we uncharge the old and charge the new during migration, and putback may race with us, so grab the lru lock and isolate the pages iff on LRU to prevent races and ensure the pages are on the right lruvec afterward. Swap accounting is massively simplified: because the page is no longer uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry before the final put_page() in page reclaim. Finally, page_cgroup changes are now protected by whatever protection the page itself offers: anonymous pages are charged under the page table lock, whereas page cache insertions, swapin, and migration hold the page lock. Uncharging happens under full exclusion with no outstanding references. Charging and uncharging also ensure that the page is off-LRU, which serializes against charge migration. Remove the very costly page_cgroup lock and set pc->flags non-atomically. [mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable] [vdavydov@parallels.com: fix flags definition] Signed-off-by: Johannes Weiner Cc: Hugh Dickins Cc: Tejun Heo Cc: Vladimir Davydov Tested-by: Jet Chen Acked-by: Michal Hocko Tested-by: Felipe Balbi Signed-off-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: memcontrol: rewrite charge API

2014-08-08T22:57:17Z

These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Vladimir Davydov Signed-off-by: Hugh Dickins Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: pagemap: avoid unnecessary overhead when tracepoints are deactivated

2014-08-07T01:01:20Z

This was formerly the series "Improve sequential read throughput" which noted some major differences in performance of tiobench since 3.0. While there are a number of factors, two that dominated were the introduction of the fair zone allocation policy and changes to CFQ. The behaviour of fair zone allocation policy makes more sense than tiobench as a benchmark and CFQ defaults were not changed due to insufficient benchmarking. This series is what's left. It's one functional fix to the fair zone allocation policy when used on NUMA machines and a reduction of overhead in general. tiobench was used for the comparison despite its flaws as an IO benchmark as in this case we are primarily interested in the overhead of page allocator and page reclaim activity. On UMA, it makes little difference to overhead 3.16.0-rc3 3.16.0-rc3 vanilla lowercost-v5 User 383.61 386.77 System 403.83 401.74 Elapsed 5411.50 5413.11 On a 4-socket NUMA machine it's a bit more noticable 3.16.0-rc3 3.16.0-rc3 vanilla lowercost-v5 User 746.94 802.00 System 65336.22 40852.33 Elapsed 27553.52 27368.46 This patch (of 6): The LRU insertion and activate tracepoints take PFN as a parameter forcing the overhead to the caller. Move the overhead to the tracepoint fast-assign method to ensure the cost is only incurred when the tracepoint is active. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: replace init_page_accessed by __SetPageReferenced

2014-08-07T01:01:19Z

Do we really need an exported alias for __SetPageReferenced()? Its callers better know what they're doing, in which case the page would not be already marked referenced. Kill init_page_accessed(), just __SetPageReferenced() inline. Signed-off-by: Hugh Dickins Acked-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Michal Hocko Cc: Dave Hansen Cc: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

mm: non-atomically mark page accessed during page cache allocation where possible

2014-06-04T23:54:10Z

aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Tested-by: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds