- 04 Jun, 2014 40 commits
-
-
David Rientjes authored
Synchronous memory compaction can be very expensive: it can iterate an enormous amount of memory without aborting, constantly rescheduling, waiting on page locks and lru_lock, etc, if a pageblock cannot be defragmented. Unfortunately, it's too expensive for transparent hugepage page faults and it's much better to simply fallback to pages. On 128GB machines, we find that synchronous memory compaction can take O(seconds) for a single thp fault. Now that async compaction remembers where it left off without strictly relying on sync compaction, this makes thp allocations best-effort without causing egregious latency during fault. We still need to retry async compaction after reclaim, but this won't stall for seconds. Signed-off-by:
David Rientjes <rientjes@google.com> Acked-by:
Mel Gorman <mgorman@suse.de> Cc: Greg Thelen <gthelen@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
David Rientjes authored
We're going to want to manipulate the migration mode for compaction in the page allocator, and currently compact_control's sync field is only a bool. Currently, we only do MIGRATE_ASYNC or MIGRATE_SYNC_LIGHT compaction depending on the value of this bool. Convert the bool to enum migrate_mode and pass the migration mode in directly. Later, we'll want to avoid MIGRATE_SYNC_LIGHT for thp allocations in the pagefault patch to avoid unnecessary latency. This also alters compaction triggered from sysfs, either for the entire system or for a node, to force MIGRATE_SYNC. [akpm@linux-foundation.org: fix build] [iamjoonsoo.kim@lge.com: use MIGRATE_SYNC in alloc_contig_range()] Signed-off-by:
Vlastimil Babka <vbabka@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by:
Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
-
David Rientjes authored
Each zone has a cached migration scanner pfn for memory compaction so that subsequent calls to memory compaction can start where the previous call left off. Currently, the compaction migration scanner only updates the per-zone cached pfn when pageblocks were not skipped for async compaction. This creates a dependency on calling sync compaction to avoid having subsequent calls to async compaction from scanning an enormous amount of non-MOVABLE pageblocks each time it is called. On large machines, this could be potentially very expensive. This patch adds a per-zone cached migration scanner pfn only for async compaction. It is updated everytime a pageblock has been scanned in its entirety and when no pages from it were successfully isolated. The cached migration scanner pfn for sync compaction is updated only when called for sync compaction. Signed-off-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Greg Thelen <gthelen@google.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by:
-
David Rientjes authored
Greg reported that he found isolated free pages were returned back to the VM rather than the compaction freelist. This will cause holes behind the free scanner and cause it to reallocate additional memory if necessary later. He detected the problem at runtime seeing that ext4 metadata pages (esp the ones read by "sbi->s_group_desc[i] = sb_bread(sb, block)") were constantly visited by compaction calls of migrate_pages(). These pages had a non-zero b_count which caused fallback_migrate_page() -> try_to_release_page() -> try_to_free_buffers() to fail. Memory compaction works by having a "freeing scanner" scan from one end of a zone which isolates pages as migration targets while another "migrating scanner" scans from the other end of the same zone which isolates pages for migration. When page migration fails for an isolated page, the target page is returned to the system rather than the freelist built by the freeing scanner. This may require the freeing scanner to continue scanning memory after suitable migration targets have already been returned to the system needlessly. This patch returns destination pages to the freeing scanner freelist when page migration fails. This prevents unnecessary work done by the freeing scanner but also encourages memory to be as compacted as possible at the end of the zone. Signed-off-by:
Greg Thelen <gthelen@google.com> Acked-by:
-
David Rientjes authored
Memory migration uses a callback defined by the caller to determine how to allocate destination pages. When migration fails for a source page, however, it frees the destination page back to the system. This patch adds a memory migration callback defined by the caller to determine how to free destination pages. If a caller, such as memory compaction, builds its own freelist for migration targets, this can reuse already freed memory instead of scanning additional memory. If the caller provides a function to handle freeing of destination pages, it is called when page migration fails. If the caller passes NULL then freeing back to the system will be handled as usual. This patch introduces no functional change. Signed-off-by:
-
Vladimir Davydov authored
It isn't worth complicating the code by allocating it on the first access, because it only takes 256 bytes. Signed-off-by:
Vladimir Davydov <vdavydov@parallels.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
-
Vladimir Davydov authored
Instead of calling back to memcontrol.c from kmem_cache_create_memcg in order to just create the name of a per memcg cache, let's allocate it in place. We only need to pass the memcg name to kmem_cache_create_memcg for that - everything else can be done in slab_common.c. Signed-off-by:
Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
-
Qiang Huang authored
Signed-off-by:
Qiang Huang <h.huangqiang@huawei.com> Acked-by:
-
Qiang Huang authored
It is only used in __mem_cgroup_begin_update_page_stat(), the name is confusing and 2 routines for one thing also confuse people, so fold this function seems more clear. [akpm@linux-foundation.org: fix typo, per Michal] Signed-off-by:
-
Kirill A. Shutemov authored
With ELF extended numbering 16-bit bound is not hard limit any more. [akpm@linux-foundation.org: fix typo] Signed-off-by:
Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by:
-
Emil Medve authored
Signed-off-by:
Emil Medve <Emilian.Medve@Freescale.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by:
-
Fabian Frederick authored
Also fixes kernel-doc warning Signed-off-by:
Fabian Frederick <fabf@skynet.be> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by:
-
Kirill A. Shutemov authored
KSM was converted to use rmap_walk() and now nobody uses these functions outside mm/rmap.c. Let's covert them back to static. Signed-off-by:
-
Cyrill Gorcunov authored
Tracking dirty status on 2 level pages requires very ugly macros and taking into account how old the machines who can operate without PAE mode only are, lets drop soft dirty tracker from them for code simplicity (note I can't drop all the macros from 2 level pages by now since _PAGE_BIT_PROTNONE and _PAGE_BIT_FILE are still used even without tracker). Linus proposed to completely rip off softdirty support on x86-32 (even with PAE) and since for CRIU we're not planning to support native x86-32 mode, lets do that. (Softdirty tracker is relatively new feature which is mostly used by CRIU so I don't expect if such API change would cause problems for userspace). Signed-off-by:
Cyrill Gorcunov <gorcunov@openvz.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Steven Noonan <steven@uplinklabs.net> Cc: Rik van Riel <riel@redhat.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by:
-
Cyrill Gorcunov authored
_PAGE_BIT_FILE (bit 6) is always less than _PAGE_BIT_PROTNONE (bit 8), so drop redundant #ifdef. Signed-off-by:
-
Kirill A. Shutemov authored
Get rid of two nested loops over nr_pages, extract vma flags checking to separate function and other random cleanups. Signed-off-by:
-
Kirill A. Shutemov authored
Nesting level in __get_user_pages() is just insane. Let's try to fix it a bit. Signed-off-by:
-
Kirill A. Shutemov authored
Cleanups: - move pte-related code to separate function. It's about half of the function; - get rid of some goto-logic; - use 'return NULL' instead of 'return page' where page can only be NULL; Signed-off-by:
-
Kirill A. Shutemov authored
The case is special and disturb from reading main __get_user_pages() code path. Let's move it to separate function. Signed-off-by:
-
Kirill A. Shutemov authored
mm/memory.c is overloaded: over 4k lines. get_user_pages() code is pretty much self-contained let's move it to separate file. No other changes made. Signed-off-by:
-
Fabian Frederick authored
Replace seq_printf where possible Signed-off-by:
-
Fabian Frederick authored
static values are automatically initialized to NULL Signed-off-by:
-
Dave Hansen authored
Now that we are doing NUMA-aware shrinking, and can have shrinkers running in parallel, or working on individual nodes, it seems like we should also be sticking the node in the output. Signed-off-by:
Dave Hansen <dave.hansen@linux.intel.com> Acked-by:
Dave Chinner <david@fromorbit.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Signed-off-by:
-
Dave Hansen authored
I was looking at a trace of the slab shrinkers (attachment in this comment): https://bugs.freedesktop.org/show_bug.cgi?id=72742#c67 and noticed that "total_scan" can go negative in some cases. We used to dump out the "total_scan" variable directly, but some of the shrinker modifications along the way changed that. This patch just dumps it out directly, again. It doesn't make any sense to derive it from new_nr and nr any more since there are now other shrinkers that can be running in parallel and mucking with those values. Here's an example of the negative numbers in the output: > kswapd0-840 [000] 160.869398: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 10 new scan count 39 total_scan 29 last shrinker return val 256 > kswapd0-840 [000] 160.869618: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 39 new scan count 102 total_scan 63 last shrinker return val 256 > kswapd0-840 [000] 160.870031: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 102 new scan count 47 total_scan -55 last shrinker return val 768 > kswapd0-840 [000] 160.870464: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 47 new scan count 45 total_scan -2 last shrinker return val 768 > kswapd0-840 [000] 163.384144: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 45 new scan count 56 total_scan 11 last shrinker return val 0 > kswapd0-840 [000] 163.384297: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 56 new scan count 15 total_scan -41 last shrinker return val 256 > kswapd0-840 [000] 163.384414: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 15 new scan count 117 total_scan 102 last shrinker return val 0 > kswapd0-840 [000] 163.384657: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 117 new scan count 36 total_scan -81 last shrinker return val 512 > kswapd0-840 [000] 163.384880: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 36 new scan count 111 total_scan 75 last shrinker return val 256 > kswapd0-840 [000] 163.385256: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 111 new scan count 34 total_scan -77 last shrinker return val 768 > kswapd0-840 [000] 163.385598: mm_shrink_slab_end: i915_gem_inactive_scan+0x0 0xffff8800037cbc68: unused scan count 34 new scan count 122 total_scan 88 last shrinker return val 512 Signed-off-by:
-
Daeseok Youn authored
"dev" cannot be NULL because it is already checked before calling dma_pool_create(). If dev ever was NULL, the code would oops in dev_to_node() after enabling CONFIG_NUMA. It is possible that some driver is using dev==NULL and has never been run on a NUMA machine. Such a driver is probably outdated, possibly buggy and will need some attention if it starts triggering NULL derefs. Signed-off-by:
Daeseok Youn <daeseok.youn@gmail.com> Signed-off-by:
-
Wang Sheng-Hui authored
Use BOOTMEM_DEFAULT instead of 0 in the comment. Signed-off-by:
Wang Sheng-Hui <shhuiw@gmail.com> Signed-off-by:
-
Jianyu Zhan authored
Currently, in put_compound_page(), we have ====== if (likely(!PageTail(page))) { <------ (1) if (put_page_testzero(page)) { /* ¦* By the time all refcounts have been released ¦* split_huge_page cannot run anymore from under us. ¦*/ if (PageHead(page)) __put_compound_page(page); else __put_single_page(page); } return; } /* __split_huge_page_refcount can run under us */ page_head = compound_head(page); <------------ (2) ====== if at (1) , we fail the check, this means page is *likely* a tail page. Then at (2), as compoud_head(page) is inlined, it is : ====== static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) { <----------- (3) struct page *head = page->first_page; smp_rmb(); if (likely(PageTail(page))) return head; } return page; } ====== here, the (3) unlikely in the case is a negative hint, because it is *likely* a tail page. So the check (3) in this case is not good, so I introduce a helper for this case. So this patch introduces compound_head_by_tail() which deals with a possible tail page(though it could be spilt by a racy thread), and make compound_head() a wrapper on it. This patch has no functional change, and it reduces the object size slightly: text data bss dec hex filename 11003 1328 16 12347 303b mm/swap.o.orig 10971 1328 16 12315 301b mm/swap.o.patched I've ran "perf top -e branch-miss" to observe branch-miss in this case. As Michael points out, it's a slow path, so only very few times this case happens. But I grep'ed the code base, and found there still are some other call sites could be benifited from this helper. And given that it only bloating up the source by only 5 lines, but with a reduced object size. I still believe this helper deserves to exsit. Signed-off-by:Jianyu Zhan <nasa4836@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
-
Jianyu Zhan authored
Currently, put_compound_page() carefully handles tricky cases to avoid racing with compound page releasing or splitting, which makes it quite lenthy (about 200+ lines) and needs deep tab indention, which makes it quite hard to follow and maintain. Now based on two helpers introduced in the previous patch ("mm/swap.c: introduce put_[un]refcounted_compound_page helpers for spliting put_compound_page"), this patch replaces those two lengthy code paths with these two helpers, respectively. Also, it has some comment rephrasing. After this patch, the put_compound_page() is very compact, thus easy to read and maintain. After splitting, the object file is of same size as the original one. Actually, I've diff'ed put_compound_page()'s orginal disassemble code and the patched disassemble code, the are 100% the same! This fact shows that this splitting has no functional change, but it brings readability. This patch and the previous one blow the code by 32 lines, mostly due to comments. Signed-off-by: -
Jianyu Zhan authored
Currently, put_compound_page() carefully handles tricky cases to avoid racing with compound page releasing or splitting, which makes it quite lenthy (about 200+ lines) and needs deep tab indention, which makes it quite hard to follow and maintain. This patch and the next patch refactor this function. Based on the code skeleton of put_compound_page: put_compound_pge: if !PageTail(page) put head page fastpath; return; /* else PageTail */ page_head = compound_head(page) if !__compound_tail_refcounted(page_head) put head page optimal path; <---(1) return; else put head page slowpath; <--- (2) return; This patch introduces two helpers, put_[un]refcounted_compound_page, handling the code path (1) and code path (2), respectively. They both are tagged __always_inline, thus elmiating function call overhead, making them operating the same way as before. They are almost copied verbatim(except one place, a "goto out_put_single" is expanded), with some comments rephrasing. Signed-off-by: -
Rasmus Villemoes authored
The nmask argument to set_mempolicy() is const according to the user-space header numaif.h, and since the kernel does indeed not modify it, it might as well be declared const in the kernel. Signed-off-by:
Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by:
-
Rasmus Villemoes authored
The nmask argument to mbind() is const according to the userspace header numaif.h, and since the kernel does indeed not modify it, it might as well be declared const in the kernel. Signed-off-by:
Rik van Riel <riel@redhat.com> Signed-off-by:
-
Christoph Lameter authored
Replace places where __get_cpu_var() is used for an address calculation with this_cpu_ptr(). Signed-off-by:
Christoph Lameter <cl@linux.com> Cc: Tejun Heo <tj@kernel.org> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
-
Oleg Nesterov authored
Remove start_kernel()->mm_init_owner(&init_mm, &init_task). This doesn't really hurt but unnecessary and misleading. init_task is the "swapper" thread == current, its ->mm is always NULL. And init_mm can only be used as ->active_mm, not as ->mm. mm_init_owner() has a single caller with this patch, perhaps it should die. mm_init() can initialize ->owner under #ifdef. Signed-off-by:
Oleg Nesterov <oleg@redhat.com> Reviewed-by:
-
Oleg Nesterov authored
for_each_process_thread() is sub-optimal. All threads share the same ->mm, we can swicth to the next process once we found a thread with ->mm != NULL and ->mm != mm. Signed-off-by:
-
Oleg Nesterov authored
"Search through everything else" in mm_update_next_owner() can hit a kthread which adopted this "mm" via use_mm(), it should not be used as mm->owner. Add the PF_KTHREAD check. While at it, change this code to use for_each_process_thread() instead of deprecated do_each_thread/while_each_thread. Signed-off-by:
-
Fabian Frederick authored
Replace ((x) >> PAGE_SHIFT) with the pfn macro. Signed-off-by:
-
Fabian Frederick authored
Replace ((x) >> PAGE_SHIFT) with the pfn macro. Signed-off-by:
-
Matthew Wilcox authored
brd is effectively a thinly provisioned device. Thinly provisioned devices return -ENOSPC when they can't write a new block. -ENOMEM is an implementation detail that callers shouldn't know. Signed-off-by:
Matthew Wilcox <matthew.r.wilcox@intel.com> Acked-by:
-
Matthew Wilcox authored
Signed-off-by:
-
Matthew Wilcox authored
By calling the device driver to write the page directly, we avoid allocating a BIO, which allows us to free memory without allocating memory. [akpm@linux-foundation.org: fix used-uninitialized bug] Signed-off-by:
-
