From 8f4fc071b1926d0b20336e2b3f8ab85c94c734c5 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 May 2015 15:16:55 -0700 Subject: gfp: add __GFP_NOACCOUNT Not all kmem allocations should be accounted to memcg. The following patch gives an example when accounting of a certain type of allocations to memcg can effectively result in a memory leak. This patch adds the __GFP_NOACCOUNT flag which if passed to kmalloc and friends will force the allocation to go through the root cgroup. It will be used by the next patch. Note, since in case of kmemleak enabled each kmalloc implies yet another allocation from the kmemleak_object cache, we add __GFP_NOACCOUNT to gfp_kmemleak_mask. Alternatively, we could introduce a per kmem cache flag disabling accounting for all allocations of a particular kind, but (a) we would not be able to bypass accounting for kmalloc then and (b) a kmem cache with this flag set could not be merged with a kmem cache without this flag, which would increase the number of global caches and therefore fragmentation even if the memory cgroup controller is not used. Despite its generic name, currently __GFP_NOACCOUNT disables accounting only for kmem allocations while user page allocations are always charged. To catch abusing of this flag, a warning is issued on an attempt of passing it to mem_cgroup_try_charge. Signed-off-by: Vladimir Davydov Cc: Tejun Heo Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Greg Thelen Cc: Greg Kroah-Hartman Cc: [4.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 5405aff5a590..f0fe4f2c1fa7 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -115,7 +115,8 @@ #define BYTES_PER_POINTER sizeof(void *) /* GFP bitmask for kmemleak internal allocations */ -#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \ + __GFP_NOACCOUNT)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ __GFP_NOWARN) -- cgit v1.2.3 From 1ae7013dfa4281644a9a9591105c24d639216b22 Mon Sep 17 00:00:00 2001 From: Hui Zhu Date: Thu, 14 May 2015 15:17:04 -0700 Subject: CMA: page_isolation: check buddy before accessing it I had an issue: Unable to handle kernel NULL pointer dereference at virtual address 0000082a pgd = cc970000 [0000082a] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM PC is at get_pageblock_flags_group+0x5c/0xb0 LR is at unset_migratetype_isolate+0x148/0x1b0 pc : [] lr : [] psr: 80000093 sp : c7029d00 ip : 00000105 fp : c7029d1c r10: 00000001 r9 : 0000000a r8 : 00000004 r7 : 60000013 r6 : 000000a4 r5 : c0a357e4 r4 : 00000000 r3 : 00000826 r2 : 00000002 r1 : 00000000 r0 : 0000003f Flags: Nzcv IRQs off FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c5387d Table: 2cb7006a DAC: 00000015 Backtrace: get_pageblock_flags_group+0x0/0xb0 unset_migratetype_isolate+0x0/0x1b0 undo_isolate_page_range+0x0/0xdc __alloc_contig_range+0x0/0x34c alloc_contig_range+0x0/0x18 This issue is because when calling unset_migratetype_isolate() to unset a part of CMA memory, it try to access the buddy page to get its status: if (order >= pageblock_order) { page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); if (!is_migrate_isolate_page(buddy)) { But the begin addr of this part of CMA memory is very close to a part of memory that is reserved at boot time (not in buddy system). So add a check before accessing it. [akpm@linux-foundation.org: use conventional code layout] Signed-off-by: Hui Zhu Suggested-by: Laura Abbott Suggested-by: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 755a42c76eb4..303c908790ef 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -101,7 +101,8 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); - if (!is_migrate_isolate_page(buddy)) { + if (pfn_valid_within(page_to_pfn(buddy)) && + !is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); -- cgit v1.2.3 From b0dc2b9bb4ab782115b964310518ee0b17784277 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 14 May 2015 15:17:09 -0700 Subject: mm, numa: really disable NUMA balancing by default on single node machines NUMA balancing is meant to be disabled by default on UMA machines but the check is using nr_node_ids (highest node) instead of num_online_nodes (online nodes). The consequences are that a UMA machine with a node ID of 1 or higher will enable NUMA balancing. This will incur useless overhead due to minor faults with the impact depending on the workload. These are the impact on the stats when running a kernel build on a single node machine whose node ID happened to be 1: vanilla patched NUMA base PTE updates 5113158 0 NUMA huge PMD updates 643 0 NUMA page range updates 5442374 0 NUMA hint faults 2109622 0 NUMA hint local faults 2109622 0 NUMA hint local percent 100 100 NUMA pages migrated 0 0 Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: [3.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ede26291d4aa..747743237d9f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2518,7 +2518,7 @@ static void __init check_numabalancing_enable(void) if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); - if (nr_node_ids > 1 && !numabalancing_override) { + if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. " "Configure with numa_balancing= or the " "kernel.numa_balancing sysctl", -- cgit v1.2.3 From aad653a0bc09dd4ebcb5579f9f835bbae9ef2ba3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 19 May 2015 15:58:37 +1000 Subject: block: discard bdi_unregister() in favour of bdi_destroy() bdi_unregister() now contains very little functionality. It contains a "WARN_ON" if bdi->dev is NULL. This warning is of no real consequence as bdi->dev isn't needed by anything else in the function, and it triggers if blk_cleanup_queue() -> bdi_destroy() is called before bdi_unregister, which happens since Commit: 6cd18e711dd8 ("block: destroy bdi before blockdev is unregistered.") So this isn't wanted. It also calls bdi_set_min_ratio(). This needs to be called after writes through the bdi have all been flushed, and before the bdi is destroyed. Calling it early is better than calling it late as it frees up a global resource. Calling it immediately after bdi_wb_shutdown() in bdi_destroy() perfectly fits these requirements. So bdi_unregister() can be discarded with the important content moved to bdi_destroy(), as can the writeback_bdi_unregister event which is already not used. Reported-by: Mike Snitzer Cc: stable@vger.kernel.org (v4.0) Fixes: c4db59d31e39 ("fs: don't reassign dirty inodes to default_backing_dev_info") Fixes: 6cd18e711dd8 ("block: destroy bdi before blockdev is unregistered.") Acked-by: Peter Zijlstra (Intel) Acked-by: Dan Williams Tested-by: Nicholas Moulin Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/genhd.c | 1 - include/linux/backing-dev.h | 1 - include/trace/events/writeback.h | 1 - mm/backing-dev.c | 18 +----------------- 4 files changed, 1 insertion(+), 20 deletions(-) (limited to 'mm') diff --git a/block/genhd.c b/block/genhd.c index 0a536dc05f3b..666e11b83983 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -653,7 +653,6 @@ void del_gendisk(struct gendisk *disk) disk->flags &= ~GENHD_FL_UP; sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); - bdi_unregister(&disk->queue->backing_dev_info); blk_unregister_queue(disk); blk_unregister_region(disk_devt(disk), disk->minors); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index aff923ae8c4b..d87d8eced064 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -116,7 +116,6 @@ __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); -void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 880dd7437172..c178d13d6f4c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -250,7 +250,6 @@ DEFINE_EVENT(writeback_class, name, \ DEFINE_WRITEBACK_EVENT(writeback_nowork); DEFINE_WRITEBACK_EVENT(writeback_wake_background); DEFINE_WRITEBACK_EVENT(writeback_bdi_register); -DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6dc4580df2af..000e7b3b9896 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -359,23 +359,6 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) flush_delayed_work(&bdi->wb.dwork); } -/* - * Called when the device behind @bdi has been removed or ejected. - * - * We can't really do much here except for reducing the dirty ratio at - * the moment. In the future we should be able to set a flag so that - * the filesystem can handle errors at mark_inode_dirty time instead - * of only at writeback time. - */ -void bdi_unregister(struct backing_dev_info *bdi) -{ - if (WARN_ON_ONCE(!bdi->dev)) - return; - - bdi_set_min_ratio(bdi, 0); -} -EXPORT_SYMBOL(bdi_unregister); - static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) { memset(wb, 0, sizeof(*wb)); @@ -443,6 +426,7 @@ void bdi_destroy(struct backing_dev_info *bdi) int i; bdi_wb_shutdown(bdi); + bdi_set_min_ratio(bdi, 0); WARN_ON(!list_empty(&bdi->work_list)); WARN_ON(delayed_work_pending(&bdi->wb.dwork)); -- cgit v1.2.3