From 00206a69ee32f03e6f40837684dcbe475ea02266 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 18 Mar 2019 02:32:36 +0100 Subject: percpu: stop printing kernel addresses Since commit ad67b74d2469d9b8 ("printk: hash addresses printed with %p"), at boot "____ptrval____" is printed instead of actual addresses: percpu: Embedded 38 pages/cpu @(____ptrval____) s124376 r0 d31272 u524288 Instead of changing the print to "%px", and leaking kernel addresses, just remove the print completely, cfr. e.g. commit 071929dbdd865f77 ("arm64: Stop printing the virtual memory layout"). Signed-off-by: Matteo Croce Signed-off-by: Dennis Zhou --- mm/percpu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 2e6fc8d552c9..68dd2e7e73b5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2567,8 +2567,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, ai->groups[group].base_offset = areas[group] - base; } - pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", - PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); rc = pcpu_setup_first_chunk(ai, base); @@ -2692,8 +2692,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, } /* we're ready, commit */ - pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n", - unit_pages, psize_str, vm.addr, ai->static_size, + pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", + unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); rc = pcpu_setup_first_chunk(ai, vm.addr); -- cgit v1.2.3-73-gaa49b From 6b0868c820ff7370d15d6ddfe71b1ce6bbe8a25d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 4 Apr 2019 11:54:09 +0100 Subject: mm/compaction.c: correct zone boundary handling when resetting pageblock skip hints Mikhail Gavrilo reported the following bug being triggered in a Fedora kernel based on 5.1-rc1 but it is relevant to a vanilla kernel. kernel: page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) kernel: ------------[ cut here ]------------ kernel: kernel BUG at include/linux/mm.h:1021! kernel: invalid opcode: 0000 [#1] SMP NOPTI kernel: CPU: 6 PID: 116 Comm: kswapd0 Tainted: G C 5.1.0-0.rc1.git1.3.fc31.x86_64 #1 kernel: Hardware name: System manufacturer System Product Name/ROG STRIX X470-I GAMING, BIOS 1201 12/07/2018 kernel: RIP: 0010:__reset_isolation_pfn+0x244/0x2b0 kernel: Code: fe 06 e8 0f 8e fc ff 44 0f b6 4c 24 04 48 85 c0 0f 85 dc fe ff ff e9 68 fe ff ff 48 c7 c6 58 b7 2e 8c 4c 89 ff e8 0c 75 00 00 <0f> 0b 48 c7 c6 58 b7 2e 8c e8 fe 74 00 00 0f 0b 48 89 fa 41 b8 01 kernel: RSP: 0018:ffff9e2d03f0fde8 EFLAGS: 00010246 kernel: RAX: 0000000000000034 RBX: 000000000081f380 RCX: ffff8cffbddd6c20 kernel: RDX: 0000000000000000 RSI: 0000000000000006 RDI: ffff8cffbddd6c20 kernel: RBP: 0000000000000001 R08: 0000009898b94613 R09: 0000000000000000 kernel: R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000100000 kernel: R13: 0000000000100000 R14: 0000000000000001 R15: ffffca7de07ce000 kernel: FS: 0000000000000000(0000) GS:ffff8cffbdc00000(0000) knlGS:0000000000000000 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel: CR2: 00007fc1670e9000 CR3: 00000007f5276000 CR4: 00000000003406e0 kernel: Call Trace: kernel: __reset_isolation_suitable+0x62/0x120 kernel: reset_isolation_suitable+0x3b/0x40 kernel: kswapd+0x147/0x540 kernel: ? finish_wait+0x90/0x90 kernel: kthread+0x108/0x140 kernel: ? balance_pgdat+0x560/0x560 kernel: ? kthread_park+0x90/0x90 kernel: ret_from_fork+0x27/0x50 He bisected it down to e332f741a8dd ("mm, compaction: be selective about what pageblocks to clear skip hints"). The problem is that the patch in question was sloppy with respect to the handling of zone boundaries. In some instances, it was possible for PFNs outside of a zone to be examined and if those were not properly initialised or poisoned then it would trigger the VM_BUG_ON. This patch corrects the zone boundary issues when resetting pageblock skip hints and Mikhail reported that the bug did not trigger after 30 hours of testing. Link: http://lkml.kernel.org/r/20190327085424.GL3189@techsingularity.net Fixes: e332f741a8dd ("mm, compaction: be selective about what pageblocks to clear skip hints") Reported-by: Mikhail Gavrilov Tested-by: Mikhail Gavrilov Cc: Daniel Jordan Cc: Qian Cai Cc: Vlastimil Babka Signed-off-by: Mel Gorman --- mm/compaction.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/mm/compaction.c b/mm/compaction.c index f171a83707ce..b4930bf93c8a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -242,6 +242,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, bool check_target) { struct page *page = pfn_to_online_page(pfn); + struct page *block_page; struct page *end_page; unsigned long block_pfn; @@ -267,20 +268,26 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, get_pageblock_migratetype(page) != MIGRATE_MOVABLE) return false; + /* Ensure the start of the pageblock or zone is online and valid */ + block_pfn = pageblock_start_pfn(pfn); + block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn)); + if (block_page) { + page = block_page; + pfn = block_pfn; + } + + /* Ensure the end of the pageblock or zone is online and valid */ + block_pfn += pageblock_nr_pages; + block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); + end_page = pfn_to_online_page(block_pfn); + if (!end_page) + return false; + /* * Only clear the hint if a sample indicates there is either a * free page or an LRU page in the block. One or other condition * is necessary for the block to be a migration source/target. */ - block_pfn = pageblock_start_pfn(pfn); - pfn = max(block_pfn, zone->zone_start_pfn); - page = pfn_to_page(pfn); - if (zone != page_zone(page)) - return false; - pfn = block_pfn + pageblock_nr_pages; - pfn = min(pfn, zone_end_pfn(zone)); - end_page = pfn_to_page(pfn); - do { if (pfn_valid_within(pfn)) { if (check_source && PageLRU(page)) { @@ -309,7 +316,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, static void __reset_isolation_suitable(struct zone *zone) { unsigned long migrate_pfn = zone->zone_start_pfn; - unsigned long free_pfn = zone_end_pfn(zone); + unsigned long free_pfn = zone_end_pfn(zone) - 1; unsigned long reset_migrate = free_pfn; unsigned long reset_free = migrate_pfn; bool source_set = false; -- cgit v1.2.3-73-gaa49b From 5b56d996dd50a9d2ca87c25ebb50c07b255b7e04 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 4 Apr 2019 11:54:41 +0100 Subject: mm/compaction.c: abort search if isolation fails Running LTP oom01 in a tight loop or memory stress testing put the system in a low-memory situation could triggers random memory corruption like page flag corruption below due to in fast_isolate_freepages(), if isolation fails, next_search_order() does not abort the search immediately could lead to improper accesses. UBSAN: Undefined behaviour in ./include/linux/mm.h:1195:50 index 7 is out of range for type 'zone [5]' Call Trace: dump_stack+0x62/0x9a ubsan_epilogue+0xd/0x7f __ubsan_handle_out_of_bounds+0x14d/0x192 __isolate_free_page+0x52c/0x600 compaction_alloc+0x886/0x25f0 unmap_and_move+0x37/0x1e70 migrate_pages+0x2ca/0xb20 compact_zone+0x19cb/0x3620 kcompactd_do_work+0x2df/0x680 kcompactd+0x1d8/0x6c0 kthread+0x32c/0x3f0 ret_from_fork+0x35/0x40 ------------[ cut here ]------------ kernel BUG at mm/page_alloc.c:3124! invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI RIP: 0010:__isolate_free_page+0x464/0x600 RSP: 0000:ffff888b9e1af848 EFLAGS: 00010007 RAX: 0000000030000000 RBX: ffff888c39fcf0f8 RCX: 0000000000000000 RDX: 1ffff111873f9e25 RSI: 0000000000000004 RDI: ffffed1173c35ef6 RBP: ffff888b9e1af898 R08: fffffbfff4fc2461 R09: fffffbfff4fc2460 R10: fffffbfff4fc2460 R11: ffffffffa7e12303 R12: 0000000000000008 R13: dffffc0000000000 R14: 0000000000000000 R15: 0000000000000007 FS: 0000000000000000(0000) GS:ffff888ba8e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc7abc00000 CR3: 0000000752416004 CR4: 00000000001606a0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: compaction_alloc+0x886/0x25f0 unmap_and_move+0x37/0x1e70 migrate_pages+0x2ca/0xb20 compact_zone+0x19cb/0x3620 kcompactd_do_work+0x2df/0x680 kcompactd+0x1d8/0x6c0 kthread+0x32c/0x3f0 ret_from_fork+0x35/0x40 Link: http://lkml.kernel.org/r/20190320192648.52499-1-cai@lca.pw Fixes: dbe2d4e4f12e ("mm, compaction: round-robin the order while searching the free lists for a target") Signed-off-by: Qian Cai Acked-by: Mel Gorman Cc: Daniel Jordan Cc: Mikhail Gavrilov Cc: Vlastimil Babka Cc: Pavel Tatashin Signed-off-by: Mel Gorman --- mm/compaction.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/compaction.c b/mm/compaction.c index b4930bf93c8a..3319e0872d01 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1370,7 +1370,7 @@ fast_isolate_freepages(struct compact_control *cc) count_compact_events(COMPACTISOLATED, nr_isolated); } else { /* If isolation fails, abort the search */ - order = -1; + order = cc->search_order + 1; page = NULL; } } -- cgit v1.2.3-73-gaa49b From 298a32b132087550d3fa80641ca58323c5dfd4d9 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 5 Apr 2019 18:38:49 -0700 Subject: kmemleak: powerpc: skip scanning holes in the .bss section Commit 2d4f567103ff ("KVM: PPC: Introduce kvm_tmp framework") adds kvm_tmp[] into the .bss section and then free the rest of unused spaces back to the page allocator. kernel_init kvm_guest_init kvm_free_tmp free_reserved_area free_unref_page free_unref_page_prepare With DEBUG_PAGEALLOC=y, it will unmap those pages from kernel. As the result, kmemleak scan will trigger a panic when it scans the .bss section with unmapped pages. This patch creates dedicated kmemleak objects for the .data, .bss and potentially .data..ro_after_init sections to allow partial freeing via the kmemleak_free_part() in the powerpc kvm_free_tmp() function. Link: http://lkml.kernel.org/r/20190321171917.62049-1-catalin.marinas@arm.com Signed-off-by: Catalin Marinas Reported-by: Qian Cai Acked-by: Michael Ellerman (powerpc) Tested-by: Qian Cai Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Avi Kivity Cc: Paolo Bonzini Cc: Radim Krcmar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/kvm.c | 7 +++++++ mm/kmemleak.c | 16 +++++++++++----- 2 files changed, 18 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 683b5b3805bd..cd381e2291df 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -712,6 +713,12 @@ static void kvm_use_magic_page(void) static __init void kvm_free_tmp(void) { + /* + * Inform kmemleak about the hole in the .bss section since the + * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y. + */ + kmemleak_free_part(&kvm_tmp[kvm_tmp_index], + ARRAY_SIZE(kvm_tmp) - kvm_tmp_index); free_reserved_area(&kvm_tmp[kvm_tmp_index], &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 707fa5579f66..6c318f5ac234 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1529,11 +1529,6 @@ static void kmemleak_scan(void) } rcu_read_unlock(); - /* data/bss scanning */ - scan_large_block(_sdata, _edata); - scan_large_block(__bss_start, __bss_stop); - scan_large_block(__start_ro_after_init, __end_ro_after_init); - #ifdef CONFIG_SMP /* per-cpu sections scanning */ for_each_possible_cpu(i) @@ -2071,6 +2066,17 @@ void __init kmemleak_init(void) } local_irq_restore(flags); + /* register the data/bss sections */ + create_object((unsigned long)_sdata, _edata - _sdata, + KMEMLEAK_GREY, GFP_ATOMIC); + create_object((unsigned long)__bss_start, __bss_stop - __bss_start, + KMEMLEAK_GREY, GFP_ATOMIC); + /* only register .data..ro_after_init if not within .data */ + if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata) + create_object((unsigned long)__start_ro_after_init, + __end_ro_after_init - __start_ro_after_init, + KMEMLEAK_GREY, GFP_ATOMIC); + /* * This is the point where tracking allocations is safe. Automatic * scanning is started during the late initcall. Add the early logged -- cgit v1.2.3-73-gaa49b From c6f3c5ee40c10bb65725047a220570f718507001 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 5 Apr 2019 18:39:10 -0700 Subject: mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd() With some architectures like ppc64, set_pmd_at() cannot cope with a situation where there is already some (different) valid entry present. Use pmdp_set_access_flags() instead to modify the pfn which is built to deal with modifying existing PMD entries. This is similar to commit cae85cb8add3 ("mm/memory.c: fix modifying of page protection by insert_pfn()") We also do similar update w.r.t insert_pfn_pud eventhough ppc64 don't support pud pfn entries now. Without this patch we also see the below message in kernel log "BUG: non-zero pgtables_bytes on freeing mm:" Link: http://lkml.kernel.org/r/20190402115125.18803-1-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reported-by: Chandan Rajendra Reviewed-by: Jan Kara Cc: Dan Williams Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 404acdcd0455..165ea46bf149 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -755,6 +755,21 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, spinlock_t *ptl; ptl = pmd_lock(mm, pmd); + if (!pmd_none(*pmd)) { + if (write) { + if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); + goto out_unlock; + } + entry = pmd_mkyoung(*pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) + update_mmu_cache_pmd(vma, addr, pmd); + } + + goto out_unlock; + } + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); @@ -766,11 +781,16 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); + pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); + +out_unlock: spin_unlock(ptl); + if (pgtable) + pte_free(mm, pgtable); } vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -821,6 +841,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, spinlock_t *ptl; ptl = pud_lock(mm, pud); + if (!pud_none(*pud)) { + if (write) { + if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + goto out_unlock; + } + entry = pud_mkyoung(*pud); + entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); + if (pudp_set_access_flags(vma, addr, pud, entry, 1)) + update_mmu_cache_pud(vma, addr, pud); + } + goto out_unlock; + } + entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); @@ -830,6 +864,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); + +out_unlock: spin_unlock(ptl); } -- cgit v1.2.3-73-gaa49b From 0b3d6e6f2dd0a7b697b1aa8c167265908940624b Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Fri, 5 Apr 2019 18:39:18 -0700 Subject: mm: writeback: use exact memcg dirty counts Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") memcg dirty and writeback counters are managed as: 1) per-memcg per-cpu values in range of [-32..32] 2) per-memcg atomic counter When a per-cpu counter cannot fit in [-32..32] it's flushed to the atomic. Stat readers only check the atomic. Thus readers such as balance_dirty_pages() may see a nontrivial error margin: 32 pages per cpu. Assuming 100 cpus: 4k x86 page_size: 13 MiB error per memcg 64k ppc page_size: 200 MiB error per memcg Considering that dirty+writeback are used together for some decisions the errors double. This inaccuracy can lead to undeserved oom kills. One nasty case is when all per-cpu counters hold positive values offsetting an atomic negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32). balance_dirty_pages() only consults the atomic and does not consider throttling the next n_cpu*32 dirty pages. If the file_lru is in the 13..200 MiB range then there's absolutely no dirty throttling, which burdens vmscan with only dirty+writeback pages thus resorting to oom kill. It could be argued that tiny containers are not supported, but it's more subtle. It's the amount the space available for file lru that matters. If a container has memory.max-200MiB of non reclaimable memory, then it will also suffer such oom kills on a 100 cpu machine. The following test reliably ooms without this patch. This patch avoids oom kills. $ cat test mount -t cgroup2 none /dev/cgroup cd /dev/cgroup echo +io +memory > cgroup.subtree_control mkdir test cd test echo 10M > memory.max (echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo) (echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100) $ cat memcg-writeback-stress.c /* * Dirty pages from all but one cpu. * Clean pages from the non dirtying cpu. * This is to stress per cpu counter imbalance. * On a 100 cpu machine: * - per memcg per cpu dirty count is 32 pages for each of 99 cpus * - per memcg atomic is -99*32 pages * - thus the complete dirty limit: sum of all counters 0 * - balance_dirty_pages() only sees atomic count -99*32 pages, which * it max()s to 0. * - So a workload can dirty -99*32 pages before balance_dirty_pages() * cares. */ #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include static char *buf; static int bufSize; static void set_affinity(int cpu) { cpu_set_t affinity; CPU_ZERO(&affinity); CPU_SET(cpu, &affinity); if (sched_setaffinity(0, sizeof(affinity), &affinity)) err(1, "sched_setaffinity"); } static void dirty_on(int output_fd, int cpu) { int i, wrote; set_affinity(cpu); for (i = 0; i < 32; i++) { for (wrote = 0; wrote < bufSize; ) { int ret = write(output_fd, buf+wrote, bufSize-wrote); if (ret == -1) err(1, "write"); wrote += ret; } } } int main(int argc, char **argv) { int cpu, flush_cpu = 1, output_fd; const char *output; if (argc != 2) errx(1, "usage: output_file"); output = argv[1]; bufSize = getpagesize(); buf = malloc(getpagesize()); if (buf == NULL) errx(1, "malloc failed"); output_fd = open(output, O_CREAT|O_RDWR); if (output_fd == -1) err(1, "open(%s)", output); for (cpu = 0; cpu < get_nprocs(); cpu++) { if (cpu != flush_cpu) dirty_on(output_fd, cpu); } set_affinity(flush_cpu); if (fsync(output_fd)) err(1, "fsync(%s)", output); if (close(output_fd)) err(1, "close(%s)", output); free(buf); } Make balance_dirty_pages() and wb_over_bg_thresh() work harder to collect exact per memcg counters. This avoids the aforementioned oom kills. This does not affect the overhead of memory.stat, which still reads the single atomic counter. Why not use percpu_counter? memcg already handles cpus going offline, so no need for that overhead from percpu_counter. And the percpu_counter spinlocks are more heavyweight than is required. It probably also makes sense to use exact dirty and writeback counters in memcg oom reports. But that is saved for later. Link: http://lkml.kernel.org/r/20190329174609.164344-1-gthelen@google.com Signed-off-by: Greg Thelen Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Cc: [4.16+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1f3d880b7ca1..dbb6118370c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); -/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 532e0e2a4817..81a0d3914ec9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) return &memcg->cgwb_domain; } +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX; -- cgit v1.2.3-73-gaa49b From e91455217d8c7b128c158432869f6e697283f3ec Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 5 Apr 2019 18:39:34 -0700 Subject: mm/util.c: fix strndup_user() comment The kerneldoc misdescribes strndup_user()'s return value. Cc: Dan Carpenter Cc: Timur Tabi Cc: Mihai Caraman Cc: Kumar Gala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/util.c b/mm/util.c index d559bde497a9..43a2984bccaa 100644 --- a/mm/util.c +++ b/mm/util.c @@ -204,7 +204,7 @@ EXPORT_SYMBOL(vmemdup_user); * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * - * Return: newly allocated copy of @s or %NULL in case of error + * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { -- cgit v1.2.3-73-gaa49b From fcf88917dd435c6a4cb2830cb086ee58605a1d85 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 6 Apr 2019 18:59:01 -0400 Subject: slab: fix a crash by reading /proc/slab_allocators The commit 510ded33e075 ("slab: implement slab_root_caches list") changes the name of the list node within "struct kmem_cache" from "list" to "root_caches_node", but leaks_show() still use the "list" which causes a crash when reading /proc/slab_allocators. You need to have CONFIG_SLAB=y and CONFIG_MEMCG=y to see the problem, because without MEMCG all slab caches are root caches, and the "list" node happens to be the right one. Fixes: 510ded33e075 ("slab: implement slab_root_caches list") Signed-off-by: Qian Cai Reviewed-by: Tobin C. Harding Cc: Tejun Heo Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index 329bfe67f2ca..47a380a486ee 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4308,7 +4308,8 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { - struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, + root_caches_node); struct page *page; struct kmem_cache_node *n; const char *name; -- cgit v1.2.3-73-gaa49b From 8fde12ca79aff9b5ba951fce1a2641901b8d8e64 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:49:19 -0700 Subject: mm: prevent get_user_pages() from overflowing page refcount If the page refcount wraps around past zero, it will be freed while there are still four billion references to it. One of the possible avenues for an attacker to try to make this happen is by doing direct IO on a page multiple times. This patch makes get_user_pages() refuse to take a new page reference if there are already more than two billion references to the page. Reported-by: Jann Horn Acked-by: Matthew Wilcox Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- mm/gup.c | 48 ++++++++++++++++++++++++++++++++++++------------ mm/hugetlb.c | 13 +++++++++++++ 2 files changed, 49 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/gup.c b/mm/gup.c index 75029649baca..81e0bdefa2cc 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -157,8 +157,12 @@ retry: goto retry; } - if (flags & FOLL_GET) - get_page(page); + if (flags & FOLL_GET) { + if (unlikely(!try_get_page(page))) { + page = ERR_PTR(-ENOMEM); + goto out; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -295,7 +299,10 @@ retry_locked: if (pmd_trans_unstable(pmd)) ret = -EBUSY; } else { - get_page(page); + if (unlikely(!try_get_page(page))) { + spin_unlock(ptl); + return ERR_PTR(-ENOMEM); + } spin_unlock(ptl); lock_page(page); ret = split_huge_page(page); @@ -497,7 +504,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, if (is_device_public_page(*page)) goto unmap; } - get_page(*page); + if (unlikely(!try_get_page(*page))) { + ret = -ENOMEM; + goto unmap; + } out: ret = 0; unmap: @@ -1393,6 +1403,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) } } +/* + * Return the compund head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(head) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + return head; +} + #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) @@ -1427,9 +1451,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - head = compound_head(page); - if (!page_cache_get_speculative(head)) + head = try_get_compound_head(page, 1); + if (!head) goto pte_unmap; if (unlikely(pte_val(pte) != pte_val(*ptep))) { @@ -1568,8 +1592,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pmd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pmd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1606,8 +1630,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pud_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pud_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1643,8 +1667,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pgd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pgd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8dfdffc34a99..c220315dc533 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4298,6 +4298,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + + /* + * Instead of doing 'try_get_page()' below in the same_page + * loop, just check the count once here. + */ + if (unlikely(page_count(page) <= 0)) { + if (pages) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } + } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); -- cgit v1.2.3-73-gaa49b From 1a62b18d51e5c5ecc0345c85bb9fef870ab721ed Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 18 Apr 2019 17:49:55 -0700 Subject: slab: store tagged freelist for off-slab slabmgmt Commit 51dedad06b5f ("kasan, slab: make freelist stored without tags") calls kasan_reset_tag() for off-slab slab management object leading to freelist being stored non-tagged. However, cache_grow_begin() calls alloc_slabmgmt() which calls kmem_cache_alloc_node() assigns a tag for the address and stores it in the shadow address. As the result, it causes endless errors below during boot due to drain_freelist() -> slab_destroy() -> kasan_slab_free() which compares already untagged freelist against the stored tag in the shadow address. Since off-slab slab management object freelist is such a special case, just store it tagged. Non-off-slab management object freelist is still stored untagged which has not been assigned a tag and should not cause any other troubles with this inconsistency. BUG: KASAN: double-free or invalid-free in slab_destroy+0x84/0x88 Pointer tag: [ff], memory tag: [99] CPU: 0 PID: 1376 Comm: kworker/0:4 Tainted: G W 5.1.0-rc3+ #8 Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.0.6 07/10/2018 Workqueue: cgroup_destroy css_killed_work_fn Call trace: print_address_description+0x74/0x2a4 kasan_report_invalid_free+0x80/0xc0 __kasan_slab_free+0x204/0x208 kasan_slab_free+0xc/0x18 kmem_cache_free+0xe4/0x254 slab_destroy+0x84/0x88 drain_freelist+0xd0/0x104 __kmem_cache_shrink+0x1ac/0x224 __kmemcg_cache_deactivate+0x1c/0x28 memcg_deactivate_kmem_caches+0xa0/0xe8 memcg_offline_kmem+0x8c/0x3d4 mem_cgroup_css_offline+0x24c/0x290 css_killed_work_fn+0x154/0x618 process_one_work+0x9cc/0x183c worker_thread+0x9b0/0xe38 kthread+0x374/0x390 ret_from_fork+0x10/0x18 Allocated by task 1625: __kasan_kmalloc+0x168/0x240 kasan_slab_alloc+0x18/0x20 kmem_cache_alloc_node+0x1f8/0x3a0 cache_grow_begin+0x4fc/0xa24 cache_alloc_refill+0x2f8/0x3e8 kmem_cache_alloc+0x1bc/0x3bc sock_alloc_inode+0x58/0x334 alloc_inode+0xb8/0x164 new_inode_pseudo+0x20/0xec sock_alloc+0x74/0x284 __sock_create+0xb0/0x58c sock_create+0x98/0xb8 __sys_socket+0x60/0x138 __arm64_sys_socket+0xa4/0x110 el0_svc_handler+0x2c0/0x47c el0_svc+0x8/0xc Freed by task 1625: __kasan_slab_free+0x114/0x208 kasan_slab_free+0xc/0x18 kfree+0x1a8/0x1e0 single_release+0x7c/0x9c close_pdeo+0x13c/0x43c proc_reg_release+0xec/0x108 __fput+0x2f8/0x784 ____fput+0x1c/0x28 task_work_run+0xc0/0x1b0 do_notify_resume+0xb44/0x1278 work_pending+0x8/0x10 The buggy address belongs to the object at ffff809681b89e00 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 0 bytes inside of 128-byte region [ffff809681b89e00, ffff809681b89e80) The buggy address belongs to the page: page:ffff7fe025a06e00 count:1 mapcount:0 mapping:01ff80082000fb00 index:0xffff809681b8fe04 flags: 0x17ffffffc000200(slab) raw: 017ffffffc000200 ffff7fe025a06d08 ffff7fe022ef7b88 01ff80082000fb00 raw: ffff809681b8fe04 ffff809681b80000 00000001000000e0 0000000000000000 page dumped because: kasan: bad access detected page allocated via order 0, migratetype Unmovable, gfp_mask 0x2420c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_COMP|__GFP_THISNODE) prep_new_page+0x4e0/0x5e0 get_page_from_freelist+0x4ce8/0x50d4 __alloc_pages_nodemask+0x738/0x38b8 cache_grow_begin+0xd8/0xa24 ____cache_alloc_node+0x14c/0x268 __kmalloc+0x1c8/0x3fc ftrace_free_mem+0x408/0x1284 ftrace_free_init_mem+0x20/0x28 kernel_init+0x24/0x548 ret_from_fork+0x10/0x18 Memory state around the buggy address: ffff809681b89c00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe ffff809681b89d00: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe >ffff809681b89e00: 99 99 99 99 99 99 99 99 fe fe fe fe fe fe fe fe ^ ffff809681b89f00: 43 43 43 43 43 fe fe fe fe fe fe fe fe fe fe fe ffff809681b8a000: 6d fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe Link: http://lkml.kernel.org/r/20190403022858.97584-1-cai@lca.pw Fixes: 51dedad06b5f ("kasan, slab: make freelist stored without tags") Signed-off-by: Qian Cai Reviewed-by: Andrey Konovalov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index 47a380a486ee..9142ee992493 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2374,7 +2374,6 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, /* Slab management obj is off-slab. */ freelist = kmem_cache_alloc_node(cachep->freelist_cache, local_flags, nodeid); - freelist = kasan_reset_tag(freelist); if (!freelist) return NULL; } else { -- cgit v1.2.3-73-gaa49b From 87039546544479d4bedb19d0ea525270c43c1c9b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:49:58 -0700 Subject: mm: swapoff: shmem_find_swap_entries() filter out other types Swapfile "type" was passed all the way down to shmem_unuse_inode(), but then forgotten from shmem_find_swap_entries(): with the result that removing one swapfile would try to free up all the swap from shmem - no problem when only one swapfile anyway, but counter-productive when more, causing swapoff to be unnecessarily OOM-killed when it should succeed. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081254470.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: Konstantin Khlebnikov Cc: "Alex Xu (Hello71)" Cc: Vineeth Pillai Cc: Kelley Nielsen Cc: Rik van Riel Cc: Huang Ying Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index b3db3779a30a..859e8628071f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1099,10 +1099,11 @@ extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, - bool frontswap) + unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; + swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) @@ -1116,13 +1117,12 @@ static int shmem_find_swap_entries(struct address_space *mapping, if (!xa_is_value(page)) continue; - if (frontswap) { - swp_entry_t entry = radix_to_swp_entry(page); - - if (!frontswap_test(swap_info[swp_type(entry)], - swp_offset(entry))) - continue; - } + entry = radix_to_swp_entry(page); + if (swp_type(entry) != type) + continue; + if (frontswap && + !frontswap_test(swap_info[type], swp_offset(entry))) + continue; indices[ret] = xas.xa_index; entries[ret] = page; @@ -1194,7 +1194,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, - frontswap); + type, frontswap); if (pvec.nr == 0) { ret = 0; break; -- cgit v1.2.3-73-gaa49b From dd862deb151aad2548e72b077a82ad3aa91b715f Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:02 -0700 Subject: mm: swapoff: remove too limiting SWAP_UNUSE_MAX_TRIES SWAP_UNUSE_MAX_TRIES 3 appeared to work well in earlier testing, but further testing has proved it to be a source of unnecessary swapoff EBUSY failures (which can then be followed by unmount EBUSY failures). When mmget_not_zero() or shmem's igrab() fails, there is an mm exiting or inode being evicted, freeing up swap independent of try_to_unuse(). Those typically completed much sooner than the old quadratic swapoff, but now it's more common that swapoff may need to wait for them. It's possible to move those cases from init_mm.mmlist and shmem_swaplist to separate "exiting" swaplists, and try_to_unuse() then wait for those lists to be emptied; but we've not bothered with that in the past, and don't want to risk missing some other forgotten case. So just revert to cycling around until the swap is gone, without any retries limit. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081256170.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index 2b8d9c3fbb47..bf4ef2e40f23 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2023,7 +2023,6 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ -#define SWAP_UNUSE_MAX_TRIES 3 int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { @@ -2035,7 +2034,6 @@ int try_to_unuse(unsigned int type, bool frontswap, struct page *page; swp_entry_t entry; unsigned int i; - int retries = 0; if (!si->inuse_pages) return 0; @@ -2117,14 +2115,16 @@ retry: * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. - * Its not worth continuosuly retrying to unuse the swap in this case. - * So we try SWAP_UNUSE_MAX_TRIES times. + * + * Limit the number of retries? No: when shmem_unuse()'s igrab() fails, + * a shmem inode using swap is being evicted; and when mmget_not_zero() + * above fails, that mm is likely to be freeing swap from exit_mmap(). + * Both proceed at their own independent pace: we could move them to + * separate lists, and wait for those lists to be emptied; but it's + * easier and more robust (though cpu-intensive) just to keep retrying. */ - if (++retries >= SWAP_UNUSE_MAX_TRIES) - retval = -EBUSY; - else if (si->inuse_pages) + if (si->inuse_pages) goto retry; - out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } -- cgit v1.2.3-73-gaa49b From 64165b1affc5bc16231ac971e66aae7d68d57f2c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:09 -0700 Subject: mm: swapoff: take notice of completion sooner The old try_to_unuse() implementation was driven by find_next_to_unuse(), which terminated as soon as all the swap had been freed. Add inuse_pages checks now (alongside signal_pending()) to stop scanning mms and swap_map once finished. The same ought to be done in shmem_unuse() too, but never was before, and needs a different interface: so leave it as is for now. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081258200.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index bf4ef2e40f23..71383625a582 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2051,11 +2051,9 @@ retry: spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while ((p = p->next) != &init_mm.mmlist) { - if (signal_pending(current)) { - retval = -EINTR; - break; - } + while (si->inuse_pages && + !signal_pending(current) && + (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) @@ -2082,7 +2080,9 @@ retry: mmput(prev_mm); i = 0; - while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { + while (si->inuse_pages && + !signal_pending(current) && + (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); @@ -2123,8 +2123,11 @@ retry: * separate lists, and wait for those lists to be emptied; but it's * easier and more robust (though cpu-intensive) just to keep retrying. */ - if (si->inuse_pages) - goto retry; + if (si->inuse_pages) { + if (!signal_pending(current)) + goto retry; + retval = -EINTR; + } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } -- cgit v1.2.3-73-gaa49b From af53d3e9e04024885de5b4fda51e5fa362ae2bd8 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:13 -0700 Subject: mm: swapoff: shmem_unuse() stop eviction without igrab() The igrab() in shmem_unuse() looks good, but we forgot that it gives no protection against concurrent unmounting: a point made by Konstantin Khlebnikov eight years ago, and then fixed in 2.6.39 by 778dd893ae78 ("tmpfs: fix race between umount and swapoff"). The current 5.1-rc swapoff is liable to hit "VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds. Have a nice day..." followed by GPF. Once again, give up on using igrab(); but don't go back to making such heavy-handed use of shmem_swaplist_mutex as last time: that would spoil the new design, and I expect could deadlock inside shmem_swapin_page(). Instead, shmem_unuse() just raise a "stop_eviction" count in the shmem- specific inode, and shmem_evict_inode() wait for that to go down to 0. Call it "stop_eviction" rather than "swapoff_busy" because it can be put to use for others later (huge tmpfs patches expect to use it). That simplifies shmem_unuse(), protecting it from both unlink and unmount; and in practice lets it locate all the swap in its first try. But do not rely on that: there's still a theoretical case, when shmem_writepage() might have been preempted after its get_swap_page(), before making the swap entry visible to swapoff. [hughd@google.com: remove incorrect list_del()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904091133570.1898@eggly.anvils Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081259400.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + mm/shmem.c | 40 ++++++++++++++++++---------------------- mm/swapfile.c | 11 +++++------ 3 files changed, 24 insertions(+), 28 deletions(-) (limited to 'mm') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; diff --git a/mm/shmem.c b/mm/shmem.c index 859e8628071f..2275a0ff7c30 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode) } spin_unlock(&sbinfo->shrinklist_lock); } - if (!list_empty(&info->swaplist)) { + while (!list_empty(&info->swaplist)) { + /* Wait while shmem_unuse() is scanning this inode... */ + wait_var_event(&info->stop_eviction, + !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); - list_del_init(&info->swaplist); + /* ...but beware of the race if we peeked too early */ + if (!atomic_read(&info->stop_eviction)) + list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } @@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; - struct inode *inode; - struct inode *prev_inode = NULL; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); - - /* - * The extra refcount on the inode is necessary to safely dereference - * p->next after re-acquiring the lock. New shmem inodes with swap - * get added to the end of the list and we will scan them all. - */ list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } - - inode = igrab(&info->vfs_inode); - if (!inode) - continue; - + /* + * Drop the swaplist mutex while searching the inode for swap; + * but before doing so, make sure shmem_evict_inode() will not + * remove placeholder inode from swaplist, nor let it be freed + * (igrab() would protect from unlink, but not from unmount). + */ + atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - prev_inode = inode; - error = shmem_unuse_inode(inode, type, frontswap, + error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); @@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap, next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); + if (atomic_dec_and_test(&info->stop_eviction)) + wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - return error; } @@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); diff --git a/mm/swapfile.c b/mm/swapfile.c index 71383625a582..cf63b5f01adf 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2116,12 +2116,11 @@ retry: * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * - * Limit the number of retries? No: when shmem_unuse()'s igrab() fails, - * a shmem inode using swap is being evicted; and when mmget_not_zero() - * above fails, that mm is likely to be freeing swap from exit_mmap(). - * Both proceed at their own independent pace: we could move them to - * separate lists, and wait for those lists to be emptied; but it's - * easier and more robust (though cpu-intensive) just to keep retrying. + * Limit the number of retries? No: when mmget_not_zero() above fails, + * that mm is likely to be freeing swap from exit_mmap(), which proceeds + * at its own independent pace; and even shmem_writepage() could have + * been preempted after get_swap_page(), temporarily hiding that swap. + * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (si->inuse_pages) { if (!signal_pending(current)) -- cgit v1.2.3-73-gaa49b From e8277b3b52240ec1caad8e6df278863e4bf42eac Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 18 Apr 2019 17:50:20 -0700 Subject: mm/vmstat.c: fix /proc/vmstat format for CONFIG_DEBUG_TLBFLUSH=y CONFIG_SMP=n Commit 58bc4c34d249 ("mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly") depends on skipping vmstat entries with empty name introduced in 7aaf77272358 ("mm: don't show nr_indirectly_reclaimable in /proc/vmstat") but reverted in b29940c1abd7 ("mm: rename and change semantics of nr_indirectly_reclaimable_bytes"). So skipping no longer works and /proc/vmstat has misformatted lines " 0". This patch simply shows debug counters "nr_tlb_remote_*" for UP. Link: http://lkml.kernel.org/r/155481488468.467.4295519102880913454.stgit@buzz Fixes: 58bc4c34d249 ("mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly") Signed-off-by: Konstantin Khlebnikov Acked-by: Vlastimil Babka Cc: Roman Gushchin Cc: Jann Horn Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 36b56f858f0f..a7d493366a65 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1274,13 +1274,8 @@ const char * const vmstat_text[] = { #endif #endif /* CONFIG_MEMORY_BALLOON */ #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#else - "", /* nr_tlb_remote_flush */ - "", /* nr_tlb_remote_flush_received */ -#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ -- cgit v1.2.3-73-gaa49b From 1a9f219157b22d0ffb340a9c5f431afd02cd2cf3 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 18 Apr 2019 17:50:30 -0700 Subject: mm/hotplug: treat CMA pages as unmovable has_unmovable_pages() is used by allocating CMA and gigantic pages as well as the memory hotplug. The later doesn't know how to offline CMA pool properly now, but if an unused (free) CMA page is encountered, then has_unmovable_pages() happily considers it as a free memory and propagates this up the call chain. Memory offlining code then frees the page without a proper CMA tear down which leads to an accounting issues. Moreover if the same memory range is onlined again then the memory never gets back to the CMA pool. State after memory offline: # grep cma /proc/vmstat nr_free_cma 205824 # cat /sys/kernel/debug/cma/cma-kvm_cma/count 209920 Also, kmemleak still think those memory address are reserved below but have already been used by the buddy allocator after onlining. This patch fixes the situation by treating CMA pageblocks as unmovable except when has_unmovable_pages() is called as part of CMA allocation. Offlined Pages 4096 kmemleak: Cannot insert 0xc000201f7d040008 into the object search tree (overlaps existing) Call Trace: dump_stack+0xb0/0xf4 (unreliable) create_object+0x344/0x380 __kmalloc_node+0x3ec/0x860 kvmalloc_node+0x58/0x110 seq_read+0x41c/0x620 __vfs_read+0x3c/0x70 vfs_read+0xbc/0x1a0 ksys_read+0x7c/0x140 system_call+0x5c/0x70 kmemleak: Kernel memory leak detector disabled kmemleak: Object 0xc000201cc8000000 (size 13757317120): kmemleak: comm "swapper/0", pid 0, jiffies 4294937297 kmemleak: min_count = -1 kmemleak: count = 0 kmemleak: flags = 0x5 kmemleak: checksum = 0 kmemleak: backtrace: cma_declare_contiguous+0x2a4/0x3b0 kvm_cma_reserve+0x11c/0x134 setup_arch+0x300/0x3f8 start_kernel+0x9c/0x6e8 start_here_common+0x1c/0x4b0 kmemleak: Automatic memory scanning thread ended [cai@lca.pw: use is_migrate_cma_page() and update commit log] Link: http://lkml.kernel.org/r/20190416170510.20048-1-cai@lca.pw Link: http://lkml.kernel.org/r/20190413002623.8967-1-cai@lca.pw Signed-off-by: Qian Cai Acked-by: Michal Hocko Acked-by: Vlastimil Babka Reviewed-by: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d96ca5bc555b..c6ce20aaf80b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8005,7 +8005,10 @@ void *__init alloc_large_system_hash(const char *tablename, bool has_unmovable_pages(struct zone *zone, struct page *page, int count, int migratetype, int flags) { - unsigned long pfn, iter, found; + unsigned long found; + unsigned long iter = 0; + unsigned long pfn = page_to_pfn(page); + const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -8015,17 +8018,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * can still lead to having bootmem allocations in zone_movable. */ - /* - * CMA allocations (alloc_contig_range) really need to mark isolate - * CMA pageblocks even when they are not movable in fact so consider - * them movable here. - */ - if (is_migrate_cma(migratetype) && - is_migrate_cma(get_pageblock_migratetype(page))) - return false; + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return false; + + reason = "CMA page"; + goto unmovable; + } - pfn = page_to_pfn(page); - for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + for (found = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; if (!pfn_valid_within(check)) @@ -8105,7 +8111,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn+iter), "unmovable page"); + dump_page(pfn_to_page(pfn + iter), reason); return true; } -- cgit v1.2.3-73-gaa49b From 3b991208b897f52507168374033771a984b947b1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 18 Apr 2019 17:50:34 -0700 Subject: mm: fix inactive list balancing between NUMA nodes and cgroups During !CONFIG_CGROUP reclaim, we expand the inactive list size if it's thrashing on the node that is about to be reclaimed. But when cgroups are enabled, we suddenly ignore the node scope and use the cgroup scope only. The result is that pressure bleeds between NUMA nodes depending on whether cgroups are merely compiled into Linux. This behavioral difference is unexpected and undesirable. When the refault adaptivity of the inactive list was first introduced, there were no statistics at the lruvec level - the intersection of node and memcg - so it was better than nothing. But now that we have that infrastructure, use lruvec_page_state() to make the list balancing decision always NUMA aware. [hannes@cmpxchg.org: fix bisection hole] Link: http://lkml.kernel.org/r/20190417155241.GB23013@cmpxchg.org Link: http://lkml.kernel.org/r/20190412144438.2645-1-hannes@cmpxchg.org Fixes: 2a2e48854d70 ("mm: vmscan: fix IO/refault regression in cache workingset transition") Signed-off-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index a5ad0b35ab8e..a815f73ee4d5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2176,7 +2176,6 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct mem_cgroup *memcg, struct scan_control *sc, bool actual_reclaim) { enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; @@ -2197,16 +2196,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - /* * When refaults are being observed, it means a new workingset * is being established. Disable active list protection to get * rid of the stale workingset quickly. */ + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); if (file && actual_reclaim && lruvec->refaults != refaults) { inactive_ratio = 0; } else { @@ -2227,12 +2222,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct mem_cgroup *memcg, - struct scan_control *sc) + struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, is_file_lru(lru), - memcg, sc, true)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -2332,7 +2325,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anonymous pages on the LRU in eligible zones. * Otherwise, the small LRU gets thrashed. */ - if (!inactive_list_is_low(lruvec, false, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, false, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_ANON; @@ -2350,7 +2343,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * lruvec even if it has plenty of old anonymous pages unless the * system is under heavy pressure. */ - if (!inactive_list_is_low(lruvec, true, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, true, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_FILE; goto out; @@ -2503,7 +2496,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, memcg, sc); + lruvec, sc); } } @@ -2570,7 +2563,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2969,12 +2962,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) unsigned long refaults; struct lruvec *lruvec; - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - lruvec = mem_cgroup_lruvec(pgdat, memcg); + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); lruvec->refaults = refaults; } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); } @@ -3339,7 +3328,7 @@ static void age_active_anon(struct pglist_data *pgdat, do { struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); -- cgit v1.2.3-73-gaa49b From dce5b0bdeec61bdbee56121ceb1d014151d5cab1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Apr 2019 17:50:48 -0700 Subject: mm/kmemleak.c: fix unused-function warning The only references outside of the #ifdef have been removed, so now we get a warning in non-SMP configurations: mm/kmemleak.c:1404:13: error: unused function 'scan_large_block' [-Werror,-Wunused-function] Add a new #ifdef around it. Link: http://lkml.kernel.org/r/20190416123148.3502045-1-arnd@arndb.de Fixes: 298a32b13208 ("kmemleak: powerpc: skip scanning holes in the .bss section") Signed-off-by: Arnd Bergmann Acked-by: Catalin Marinas Cc: Vincent Whitchurch Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 6c318f5ac234..2e435b8142e5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1401,6 +1401,7 @@ static void scan_block(void *_start, void *_end, /* * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency. */ +#ifdef CONFIG_SMP static void scan_large_block(void *start, void *end) { void *next; @@ -1412,6 +1413,7 @@ static void scan_large_block(void *start, void *end) cond_resched(); } } +#endif /* * Scan a memory block corresponding to a kmemleak_object. A condition is -- cgit v1.2.3-73-gaa49b From 04f5866e41fb70690e28397487d8bd8eea7d712a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 18 Apr 2019 17:50:52 -0700 Subject: coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping The core dumping code has always run without holding the mmap_sem for writing, despite that is the only way to ensure that the entire vma layout will not change from under it. Only using some signal serialization on the processes belonging to the mm is not nearly enough. This was pointed out earlier. For example in Hugh's post from Jul 2017: https://lkml.kernel.org/r/alpine.LSU.2.11.1707191716030.2055@eggly.anvils "Not strictly relevant here, but a related note: I was very surprised to discover, only quite recently, how handle_mm_fault() may be called without down_read(mmap_sem) - when core dumping. That seems a misguided optimization to me, which would also be nice to correct" In particular because the growsdown and growsup can move the vm_start/vm_end the various loops the core dump does around the vma will not be consistent if page faults can happen concurrently. Pretty much all users calling mmget_not_zero()/get_task_mm() and then taking the mmap_sem had the potential to introduce unexpected side effects in the core dumping code. Adding mmap_sem for writing around the ->core_dump invocation is a viable long term fix, but it requires removing all copy user and page faults and to replace them with get_dump_page() for all binary formats which is not suitable as a short term fix. For the time being this solution manually covers the places that can confuse the core dump either by altering the vma layout or the vma flags while it runs. Once ->core_dump runs under mmap_sem for writing the function mmget_still_valid() can be dropped. Allowing mmap_sem protected sections to run in parallel with the coredump provides some minor parallelism advantage to the swapoff code (which seems to be safe enough by never mangling any vma field and can keep doing swapins in parallel to the core dumping) and to some other corner case. In order to facilitate the backporting I added "Fixes: 86039bd3b4e6" however the side effect of this same race condition in /proc/pid/mem should be reproducible since before 2.6.12-rc2 so I couldn't add any other "Fixes:" because there's no hash beyond the git genesis commit. Because find_extend_vma() is the only location outside of the process context that could modify the "mm" structures under mmap_sem for reading, by adding the mmget_still_valid() check to it, all other cases that take the mmap_sem for reading don't need the new check after mmget_not_zero()/get_task_mm(). The expand_stack() in page fault context also doesn't need the new check, because all tasks under core dumping are frozen. Link: http://lkml.kernel.org/r/20190325224949.11068-1-aarcange@redhat.com Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Andrea Arcangeli Reported-by: Jann Horn Suggested-by: Oleg Nesterov Acked-by: Peter Xu Reviewed-by: Mike Rapoport Reviewed-by: Oleg Nesterov Reviewed-by: Jann Horn Acked-by: Jason Gunthorpe Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/core/uverbs_main.c | 3 +++ fs/proc/task_mmu.c | 18 ++++++++++++++++++ fs/userfaultfd.c | 9 +++++++++ include/linux/sched/mm.h | 21 +++++++++++++++++++++ mm/mmap.c | 7 ++++++- 5 files changed, 57 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..f2e7ffe6fc54 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -993,6 +993,8 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * will only be one mm, so no big deal. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1007,6 +1009,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: up_write(&mm->mmap_sem); mmput(mm); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; -- cgit v1.2.3-73-gaa49b 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 v1.2.3-73-gaa49b 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 v1.2.3-73-gaa49b 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 v1.2.3-73-gaa49b 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 v1.2.3-73-gaa49b 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 v1.2.3-73-gaa49b