From 89c02e69fc5245f8a2f34b58b42d43a737af1a5e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Apr 2019 22:23:37 -0700 Subject: mm/memory_hotplug.c: drop memory device reference after find_memory_block() Right now we are using find_memory_block() to get the node id for the pfn range to online. We are missing to drop a reference to the memory block device. While the device still gets unregistered via device_unregister(), resulting in no user visible problem, the device is never released via device_release(), resulting in a memory leak. Fix that by properly using a put_device(). Link: http://lkml.kernel.org/r/20190411110955.1430-1-david@redhat.com Fixes: d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug") Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Reviewed-by: Wei Yang Acked-by: Michal Hocko Acked-by: Pankaj Gupta Cc: David Hildenbrand Cc: Pavel Tatashin Cc: Qian Cai Cc: Arun KS Cc: Mathieu Malaterre Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0082d699be94..b236069ff0d8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ mem = find_memory_block(__pfn_to_section(pfn)); nid = mem->nid; + put_device(&mem->dev); /* associate pfn range with the zone */ zone = move_pfn_range(online_type, nid, pfn, nr_pages); -- cgit v1.2.3-70-g09d2 From 24512228b7a3f412b5a51f189df302616b021c33 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 25 Apr 2019 22:23:51 -0700 Subject: mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model Mikulas Patocka reported that commit 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") "broke" memory management on parisc. The machine is not NUMA but the DISCONTIG model creates three pgdats even though it's a UMA machine for the following ranges 0) Start 0x0000000000000000 End 0x000000003fffffff Size 1024 MB 1) Start 0x0000000100000000 End 0x00000001bfdfffff Size 3070 MB 2) Start 0x0000004040000000 End 0x00000040ffffffff Size 3072 MB Mikulas reported: With the patch 1c30844d2, the kernel will incorrectly reclaim the first zone when it fills up, ignoring the fact that there are two completely free zones. Basiscally, it limits cache size to 1GiB. For example, if I run: # dd if=/dev/sda of=/dev/null bs=1M count=2048 - with the proper kernel, there should be "Buffers - 2GiB" when this command finishes. With the patch 1c30844d2, buffers will consume just 1GiB or slightly more, because the kernel was incorrectly reclaiming them. The page allocator and reclaim makes assumptions that pgdats really represent NUMA nodes and zones represent ranges and makes decisions on that basis. Watermark boosting for small pgdats leads to unexpected results even though this would have behaved reasonably on SPARSEMEM. DISCONTIG is essentially deprecated and even parisc plans to move to SPARSEMEM so there is no need to be fancy, this patch simply disables watermark boosting by default on DISCONTIGMEM. Link: http://lkml.kernel.org/r/20190419094335.GJ18914@techsingularity.net Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") Signed-off-by: Mel Gorman Reported-by: Mikulas Patocka Tested-by: Mikulas Patocka Acked-by: Vlastimil Babka Cc: James Bottomley Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 16 ++++++++-------- mm/page_alloc.c | 13 +++++++++++++ 2 files changed, 21 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 6af24cdb25cc..3f13d8599337 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to increase the success rate of future high-order allocations such as SLUB allocations, THP and hugetlbfs pages. -To make it sensible with respect to the watermark_scale_factor parameter, -the unit is in fractions of 10,000. The default value of 15,000 means -that up to 150% of the high watermark will be reclaimed in the event of -a pageblock being mixed due to fragmentation. The level of reclaim is -determined by the number of fragmentation events that occurred in the -recent past. If this value is smaller than a pageblock then a pageblocks -worth of pages will be reclaimed (e.g. 2MB on 64-bit x86). A boost factor -of 0 will disable the feature. +To make it sensible with respect to the watermark_scale_factor +parameter, the unit is in fractions of 10,000. The default value of +15,000 on !DISCONTIGMEM configurations means that up to 150% of the high +watermark will be reclaimed in the event of a pageblock being mixed due +to fragmentation. The level of reclaim is determined by the number of +fragmentation events that occurred in the recent past. If this value is +smaller than a pageblock then a pageblocks worth of pages will be reclaimed +(e.g. 2MB on 64-bit x86). A boost factor of 0 will disable the feature. ============================================================= diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c6ce20aaf80b..6c6d9f1c404e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +#ifdef CONFIG_DISCONTIGMEM +/* + * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges + * are not on separate NUMA nodes. Functionally this works but with + * watermark_boost_factor, it can reclaim prematurely as the ranges can be + * quite small. By default, do not boost watermarks on discontigmem as in + * many cases very high-order allocations like THP are likely to be + * unsupported and the premature reclaim offsets the advantage of long-term + * fragmentation avoidance. + */ +int watermark_boost_factor __read_mostly; +#else int watermark_boost_factor __read_mostly = 15000; +#endif int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __initdata; -- cgit v1.2.3-70-g09d2 From ee8ab0eeb49bd3982090c8f14dc9cc65bcd13c5c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 25 Apr 2019 22:23:54 -0700 Subject: mm, page_alloc: always use a captured page regardless of compaction result During the development of commit 5e1f0f098b46 ("mm, compaction: capture a page under direct compaction"), a paranoid check was added to ensure that if a captured page was available after compaction that it was consistent with the final state of compaction. The intent was to catch serious programming bugs such as using a stale page pointer and causing corruption problems. However, it is possible to get a captured page even if compaction was unsuccessful if an interrupt triggered and happened to free pages in interrupt context that got merged into a suitable high-order page. It's highly unlikely but Li Wang did report the following warning on s390 occuring when testing OOM handling. Note that the warning is slightly edited for clarity. WARNING: CPU: 0 PID: 9783 at mm/page_alloc.c:3777 __alloc_pages_direct_compact+0x182/0x190 Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache sunrpc pkey ghash_s390 prng xts aes_s390 des_s390 des_generic sha512_s390 zcrypt_cex4 zcrypt vmur binfmt_misc ip_tables xfs libcrc32c dasd_fba_mod qeth_l2 dasd_eckd_mod dasd_mod qeth qdio lcs ctcm ccwgroup fsm dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 9783 Comm: copy.sh Kdump: loaded Not tainted 5.1.0-rc 5 #1 This patch simply removes the check entirely instead of trying to be clever about pages freed from interrupt context. If a serious programming error was introduced, it is highly likely to be caught by prep_new_page() instead. Link: http://lkml.kernel.org/r/20190419085133.GH18914@techsingularity.net Fixes: 5e1f0f098b46 ("mm, compaction: capture a page under direct compaction") Signed-off-by: Mel Gorman Reported-by: Li Wang Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6c6d9f1c404e..d167c48d913c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3786,11 +3786,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - if (*compact_result <= COMPACT_INACTIVE) { - WARN_ON_ONCE(page); - return NULL; - } - /* * At least in one zone compaction wasn't deferred or skipped, so let's * count a compaction stall -- cgit v1.2.3-70-g09d2 From 8139ad043d632c0e9e12d760068a7a8e91659aa1 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 25 Apr 2019 22:23:58 -0700 Subject: mm/page_alloc.c: avoid potential NULL pointer dereference ac.preferred_zoneref->zone passed to alloc_flags_nofragment() can be NULL. 'zone' pointer unconditionally derefernced in alloc_flags_nofragment(). Bail out on NULL zone to avoid potential crash. Currently we don't see any crashes only because alloc_flags_nofragment() has another bug which allows compiler to optimize away all accesses to 'zone'. Link: http://lkml.kernel.org/r/20190423120806.3503-1-aryabinin@virtuozzo.com Fixes: 6bb154504f8b ("mm, page_alloc: spread allocations across zones before introducing fragmentation") Signed-off-by: Andrey Ryabinin Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d167c48d913c..9992ca7f29f1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3432,6 +3432,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) alloc_flags |= ALLOC_KSWAPD; #ifdef CONFIG_ZONE_DMA32 + if (!zone) + return alloc_flags; + if (zone_idx(zone) != ZONE_NORMAL) goto out; -- cgit v1.2.3-70-g09d2 From 8118b82eb756e271929697e8ada5f637dc443af1 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 25 Apr 2019 22:24:01 -0700 Subject: mm/page_alloc.c: fix never set ALLOC_NOFRAGMENT flag Commit 0a79cdad5eb2 ("mm: use alloc_flags to record if kswapd can wake") removed setting of the ALLOC_NOFRAGMENT flag. Bring it back. The runtime effect is that ALLOC_NOFRAGMENT behaviour is restored so that allocations are spread across local zones to avoid fragmentation due to mixing pageblocks as long as possible. Link: http://lkml.kernel.org/r/20190423120806.3503-2-aryabinin@virtuozzo.com Fixes: 0a79cdad5eb2 ("mm: use alloc_flags to record if kswapd can wake") Signed-off-by: Andrey Ryabinin Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9992ca7f29f1..c02cff1ed56e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3436,7 +3436,7 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) return alloc_flags; if (zone_idx(zone) != ZONE_NORMAL) - goto out; + return alloc_flags; /* * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and @@ -3445,9 +3445,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) */ BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1); if (nr_online_nodes > 1 && !populated_zone(--zone)) - goto out; + return alloc_flags; -out: + alloc_flags |= ALLOC_NOFRAGMENT; #endif /* CONFIG_ZONE_DMA32 */ return alloc_flags; } -- cgit v1.2.3-70-g09d2