From ce6f0ff8d1031931df7031a88f4085e5f196a854 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Mon, 30 Jul 2012 14:39:04 -0700 Subject: mm: fix wrong argument of migrate_huge_pages() in soft_offline_huge_page() commit dc32f63453f56d07a1073a697dcd843dd3098c09 upstream. Commit a6bc32b89922 ("mm: compaction: introduce sync-light migration for use by compaction") changed the declaration of migrate_pages() and migrate_huge_pages(). But it missed changing the argument of migrate_huge_pages() in soft_offline_huge_page(). In this case, we should call migrate_huge_pages() with MIGRATE_SYNC. Additionally, there is a mismatch between type the of argument and the function declaration for migrate_pages(). Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Mel Gorman Acked-by: David Rientjes Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memory-failure.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0de20d7168f7..274c3cc5fbc0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1433,8 +1433,8 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, - true); + ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false, + MIGRATE_SYNC); if (ret) { struct page *page1, *page2; list_for_each_entry_safe(page1, page2, &pagelist, lru) @@ -1563,7 +1563,7 @@ int soft_offline_page(struct page *page, int flags) page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - 0, MIGRATE_SYNC); + false, MIGRATE_SYNC); if (ret) { putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", -- cgit v1.2.3 From cc9fdb9cdde35aafad3b11ce74e244f5da7ac3c0 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Tue, 31 Jul 2012 16:45:52 -0700 Subject: mm: mmu_notifier: fix freed page still mapped in secondary MMU commit 3ad3d901bbcfb15a5e4690e55350db0899095a68 upstream. mmu_notifier_release() is called when the process is exiting. It will delete all the mmu notifiers. But at this time the page belonging to the process is still present in page tables and is present on the LRU list, so this race will happen: CPU 0 CPU 1 mmu_notifier_release: try_to_unmap: hlist_del_init_rcu(&mn->hlist); ptep_clear_flush_notify: mmu nofifler not found free page !!!!!! /* * At the point, the page has been * freed, but it is still mapped in * the secondary MMU. */ mn->ops->release(mn, mm); Then the box is not stable and sometimes we can get this bug: [ 738.075923] BUG: Bad page state in process migrate-perf pfn:03bec [ 738.075931] page:ffffea00000efb00 count:0 mapcount:0 mapping: (null) index:0x8076 [ 738.075936] page flags: 0x20000000000014(referenced|dirty) The same issue is present in mmu_notifier_unregister(). We can call ->release before deleting the notifier to ensure the page has been unmapped from the secondary MMU before it is freed. Signed-off-by: Xiao Guangrong Cc: Avi Kivity Cc: Marcelo Tosatti Cc: Paul Gortmaker Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/mmu_notifier.c | 45 +++++++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 22 deletions(-) (limited to 'mm') diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 9a611d3a1848..862b60822d9f 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -33,6 +33,24 @@ void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; + struct hlist_node *n; + + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { @@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm) * mmu_notifier_unregister to return. */ hlist_del_init_rcu(&mn->hlist); - /* - * RCU here will block mmu_notifier_unregister until - * ->release returns. - */ - rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); - /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - rcu_read_unlock(); - spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); @@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); - spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { - hlist_del_rcu(&mn->hlist); - /* * RCU here will force exit_mmap to wait ->release to finish * before freeing the pages. */ rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); + /* * exit_mmap will block in mmu_notifier_release to * guarantee ->release is called before freeing the @@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) if (mn->ops->release) mn->ops->release(mn, mm); rcu_read_unlock(); - } else + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_del_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); + } /* * Wait any running method to finish, of course including -- cgit v1.2.3 From 49ca240411df57586fecddd1152ff30cbef82d59 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 31 Jul 2012 16:46:20 -0700 Subject: mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables commit d833352a4338dc31295ed832a30c9ccff5c7a183 upstream. If a process creates a large hugetlbfs mapping that is eligible for page table sharing and forks heavily with children some of whom fault and others which destroy the mapping then it is possible for page tables to get corrupted. Some teardowns of the mapping encounter a "bad pmd" and output a message to the kernel log. The final teardown will trigger a BUG_ON in mm/filemap.c. This was reproduced in 3.4 but is known to have existed for a long time and goes back at least as far as 2.6.37. It was probably was introduced in 2.6.20 by [39dde65c: shared page table for hugetlb page]. The messages look like this; [ ..........] Lots of bad pmd messages followed by this [ 127.164256] mm/memory.c:391: bad pmd ffff880412e04fe8(80000003de4000e7). [ 127.164257] mm/memory.c:391: bad pmd ffff880412e04ff0(80000003de6000e7). [ 127.164258] mm/memory.c:391: bad pmd ffff880412e04ff8(80000003de0000e7). [ 127.186778] ------------[ cut here ]------------ [ 127.186781] kernel BUG at mm/filemap.c:134! [ 127.186782] invalid opcode: 0000 [#1] SMP [ 127.186783] CPU 7 [ 127.186784] Modules linked in: af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq mperf ext3 jbd dm_mod coretemp crc32c_intel usb_storage ghash_clmulni_intel aesni_intel i2c_i801 r8169 mii uas sr_mod cdrom sg iTCO_wdt iTCO_vendor_support shpchp serio_raw cryptd aes_x86_64 e1000e pci_hotplug dcdbas aes_generic container microcode ext4 mbcache jbd2 crc16 sd_mod crc_t10dif i915 drm_kms_helper drm i2c_algo_bit ehci_hcd ahci libahci usbcore rtc_cmos usb_common button i2c_core intel_agp video intel_gtt fan processor thermal thermal_sys hwmon ata_generic pata_atiixp libata scsi_mod [ 127.186801] [ 127.186802] Pid: 9017, comm: hugetlbfs-test Not tainted 3.4.0-autobuild #53 Dell Inc. OptiPlex 990/06D7TR [ 127.186804] RIP: 0010:[] [] __delete_from_page_cache+0x15e/0x160 [ 127.186809] RSP: 0000:ffff8804144b5c08 EFLAGS: 00010002 [ 127.186810] RAX: 0000000000000001 RBX: ffffea000a5c9000 RCX: 00000000ffffffc0 [ 127.186811] RDX: 0000000000000000 RSI: 0000000000000009 RDI: ffff88042dfdad00 [ 127.186812] RBP: ffff8804144b5c18 R08: 0000000000000009 R09: 0000000000000003 [ 127.186813] R10: 0000000000000000 R11: 000000000000002d R12: ffff880412ff83d8 [ 127.186814] R13: ffff880412ff83d8 R14: 0000000000000000 R15: ffff880412ff83d8 [ 127.186815] FS: 00007fe18ed2c700(0000) GS:ffff88042dce0000(0000) knlGS:0000000000000000 [ 127.186816] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 127.186817] CR2: 00007fe340000503 CR3: 0000000417a14000 CR4: 00000000000407e0 [ 127.186818] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 127.186819] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 127.186820] Process hugetlbfs-test (pid: 9017, threadinfo ffff8804144b4000, task ffff880417f803c0) [ 127.186821] Stack: [ 127.186822] ffffea000a5c9000 0000000000000000 ffff8804144b5c48 ffffffff810ed83b [ 127.186824] ffff8804144b5c48 000000000000138a 0000000000001387 ffff8804144b5c98 [ 127.186825] ffff8804144b5d48 ffffffff811bc925 ffff8804144b5cb8 0000000000000000 [ 127.186827] Call Trace: [ 127.186829] [] delete_from_page_cache+0x3b/0x80 [ 127.186832] [] truncate_hugepages+0x115/0x220 [ 127.186834] [] hugetlbfs_evict_inode+0x13/0x30 [ 127.186837] [] evict+0xa7/0x1b0 [ 127.186839] [] iput_final+0xd3/0x1f0 [ 127.186840] [] iput+0x39/0x50 [ 127.186842] [] d_kill+0xf8/0x130 [ 127.186843] [] dput+0xd2/0x1a0 [ 127.186845] [] __fput+0x170/0x230 [ 127.186848] [] ? rb_erase+0xce/0x150 [ 127.186849] [] fput+0x1d/0x30 [ 127.186851] [] remove_vma+0x37/0x80 [ 127.186853] [] do_munmap+0x2d2/0x360 [ 127.186855] [] sys_shmdt+0xc9/0x170 [ 127.186857] [] system_call_fastpath+0x16/0x1b [ 127.186858] Code: 0f 1f 44 00 00 48 8b 43 08 48 8b 00 48 8b 40 28 8b b0 40 03 00 00 85 f6 0f 88 df fe ff ff 48 89 df e8 e7 cb 05 00 e9 d2 fe ff ff <0f> 0b 55 83 e2 fd 48 89 e5 48 83 ec 30 48 89 5d d8 4c 89 65 e0 [ 127.186868] RIP [] __delete_from_page_cache+0x15e/0x160 [ 127.186870] RSP [ 127.186871] ---[ end trace 7cbac5d1db69f426 ]--- The bug is a race and not always easy to reproduce. To reproduce it I was doing the following on a single socket I7-based machine with 16G of RAM. $ hugeadm --pool-pages-max DEFAULT:13G $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmmax $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmall $ for i in `seq 1 9000`; do ./hugetlbfs-test; done On my particular machine, it usually triggers within 10 minutes but enabling debug options can change the timing such that it never hits. Once the bug is triggered, the machine is in trouble and needs to be rebooted. The machine will respond but processes accessing proc like "ps aux" will hang due to the BUG_ON. shutdown will also hang and needs a hard reset or a sysrq-b. The basic problem is a race between page table sharing and teardown. For the most part page table sharing depends on i_mmap_mutex. In some cases, it is also taking the mm->page_table_lock for the PTE updates but with shared page tables, it is the i_mmap_mutex that is more important. Unfortunately it appears to be also insufficient. Consider the following situation Process A Process B --------- --------- hugetlb_fault shmdt LockWrite(mmap_sem) do_munmap unmap_region unmap_vmas unmap_single_vma unmap_hugepage_range Lock(i_mmap_mutex) Lock(mm->page_table_lock) huge_pmd_unshare/unmap tables <--- (1) Unlock(mm->page_table_lock) Unlock(i_mmap_mutex) huge_pte_alloc ... Lock(i_mmap_mutex) ... vma_prio_walk, find svma, spte ... Lock(mm->page_table_lock) ... share spte ... Unlock(mm->page_table_lock) ... Unlock(i_mmap_mutex) ... hugetlb_no_page <--- (2) free_pgtables unlink_file_vma hugetlb_free_pgd_range remove_vma_list In this scenario, it is possible for Process A to share page tables with Process B that is trying to tear them down. The i_mmap_mutex on its own does not prevent Process A walking Process B's page tables. At (1) above, the page tables are not shared yet so it unmaps the PMDs. Process A sets up page table sharing and at (2) faults a new entry. Process B then trips up on it in free_pgtables. This patch fixes the problem by adding a new function __unmap_hugepage_range_final that is only called when the VMA is about to be destroyed. This function clears VM_MAYSHARE during unmap_hugepage_range() under the i_mmap_mutex. This makes the VMA ineligible for sharing and avoids the race. Superficially this looks like it would then be vunerable to truncate and madvise issues but hugetlbfs has its own truncate handlers so does not use unmap_mapping_range() and does not support madvise(DONTNEED). This should be treated as a -stable candidate if it is merged. Test program is as follows. The test case was mostly written by Michal Hocko with a few minor changes to reproduce this bug. ==== CUT HERE ==== static size_t huge_page_size = (2UL << 20); static size_t nr_huge_page_A = 512; static size_t nr_huge_page_B = 5632; unsigned int get_random(unsigned int max) { struct timeval tv; gettimeofday(&tv, NULL); srandom(tv.tv_usec); return random() % max; } static void play(void *addr, size_t size) { unsigned char *start = addr, *end = start + size, *a; start += get_random(size/2); /* we could itterate on huge pages but let's give it more time. */ for (a = start; a < end; a += 4096) *a = 0; } int main(int argc, char **argv) { key_t key = IPC_PRIVATE; size_t sizeA = nr_huge_page_A * huge_page_size; size_t sizeB = nr_huge_page_B * huge_page_size; int shmidA, shmidB; void *addrA = NULL, *addrB = NULL; int nr_children = 300, n = 0; if ((shmidA = shmget(key, sizeA, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrA = shmat(shmidA, addrA, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } if ((shmidB = shmget(key, sizeB, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrB = shmat(shmidB, addrB, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } fork_child: switch(fork()) { case 0: switch (n%3) { case 0: play(addrA, sizeA); break; case 1: play(addrB, sizeB); break; case 2: break; } break; case -1: perror("fork:"); break; default: if (++n < nr_children) goto fork_child; play(addrA, sizeA); break; } shmdt(addrA); shmdt(addrB); do { wait(NULL); } while (--n > 0); shmctl(shmidA, IPC_RMID, NULL); shmctl(shmidB, IPC_RMID, NULL); return 0; } [akpm@linux-foundation.org: name the declaration's args, fix CONFIG_HUGETLBFS=n build] Signed-off-by: Hugh Dickins Reviewed-by: Michal Hocko Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 263e17703b31..a799df59d310 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2392,6 +2392,22 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); __unmap_hugepage_range(vma, start, end, ref_page); + /* + * Clear this flag so that x86's huge_pmd_share page_table_shareable + * test will fail on a vma being torn down, and not grab a page table + * on its way out. We're lucky that the flag has such an appropriate + * name, and can in fact be safely cleared here. We could clear it + * before the __unmap_hugepage_range above, but all that's necessary + * is to clear it before releasing the i_mmap_mutex below. + * + * This works because in the contexts this is called, the VMA is + * going to be destroyed. It is not vunerable to madvise(DONTNEED) + * because madvise is not supported on hugetlbfs. The same applies + * for direct IO. unmap_hugepage_range() is only being called just + * before free_pgtables() so clearing VM_MAYSHARE will not cause + * surprises later. + */ + vma->vm_flags &= ~VM_MAYSHARE; mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } @@ -2958,9 +2974,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); - + /* + * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * may have cleared our pud entry and done put_page on the page table: + * once we release i_mmap_mutex, another task can do the final put_page + * and that page table be reused and filled with junk. + */ flush_tlb_range(vma, start, end); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } int hugetlb_reserve_pages(struct inode *inode, -- cgit v1.2.3