From ddeaab32a89f04b7e2a2df8771583a719c4ac6b7 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 8 Jan 2019 15:23:36 -0800 Subject: hugetlbfs: revert "use i_mmap_rwsem for more pmd sharing synchronization" This reverts b43a9990055958e70347c56f90ea2ae32c67334c The reverted commit caused issues with migration and poisoning of anon huge pages. The LTP move_pages12 test will cause an "unable to handle kernel NULL pointer" BUG would occur with stack similar to: RIP: 0010:down_write+0x1b/0x40 Call Trace: migrate_pages+0x81f/0xb90 __ia32_compat_sys_migrate_pages+0x190/0x190 do_move_pages_to_node.isra.53.part.54+0x2a/0x50 kernel_move_pages+0x566/0x7b0 __x64_sys_move_pages+0x24/0x30 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The purpose of the reverted patch was to fix some long existing races with huge pmd sharing. It used i_mmap_rwsem for this purpose with the idea that this could also be used to address truncate/page fault races with another patch. Further analysis has determined that i_mmap_rwsem can not be used to address all these hugetlbfs synchronization issues. Therefore, revert this patch while working an another approach to the underlying issues. Link: http://lkml.kernel.org/r/20190103235452.29335-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reported-by: Jan Stancek Cc: Michal Hocko Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: "Aneesh Kumar K . V" Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Davidlohr Bueso Cc: Prakash Sangappa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/userfaultfd.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 065c1ce191c4..d59b5a73dfb3 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -267,14 +267,10 @@ retry: VM_BUG_ON(dst_addr & ~huge_page_mask(h)); /* - * Serialize via i_mmap_rwsem and hugetlb_fault_mutex. - * i_mmap_rwsem ensures the dst_pte remains valid even - * in the case of shared pmds. fault mutex prevents - * races with other faulting threads. + * Serialize via hugetlb_fault_mutex */ - mapping = dst_vma->vm_file->f_mapping; - i_mmap_lock_read(mapping); idx = linear_page_index(dst_vma, dst_addr); + mapping = dst_vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping, idx, dst_addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -283,7 +279,6 @@ retry: dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); goto out_unlock; } @@ -291,7 +286,6 @@ retry: dst_pteval = huge_ptep_get(dst_pte); if (!huge_pte_none(dst_pteval)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); goto out_unlock; } @@ -299,7 +293,6 @@ retry: dst_addr, src_addr, &page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); vm_alloc_shared = vm_shared; cond_resched(); -- cgit