summaryrefslogtreecommitdiff
path: root/mm/internal.h
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2019-11-30 17:50:22 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-12-01 06:29:18 -0800
commit89b15332af7c0312a41e50846819ca6613b58b4c (patch)
tree2c8e96f022d14c6ec65abcb904aacfc1b59d45cb /mm/internal.h
parent1603c8d1b1fbfbc20dcb363543b690de862849c0 (diff)
mm: drop mmap_sem before calling balance_dirty_pages() in write fault
One of our services is observing hanging ps/top/etc under heavy write IO, and the task states show this is an mmap_sem priority inversion: A write fault is holding the mmap_sem in read-mode and waiting for (heavily cgroup-limited) IO in balance_dirty_pages(): balance_dirty_pages+0x724/0x905 balance_dirty_pages_ratelimited+0x254/0x390 fault_dirty_shared_page.isra.96+0x4a/0x90 do_wp_page+0x33e/0x400 __handle_mm_fault+0x6f0/0xfa0 handle_mm_fault+0xe4/0x200 __do_page_fault+0x22b/0x4a0 page_fault+0x45/0x50 Somebody tries to change the address space, contending for the mmap_sem in write-mode: call_rwsem_down_write_failed_killable+0x13/0x20 do_mprotect_pkey+0xa8/0x330 SyS_mprotect+0xf/0x20 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 The waiting writer locks out all subsequent readers to avoid lock starvation, and several threads can be seen hanging like this: call_rwsem_down_read_failed+0x14/0x30 proc_pid_cmdline_read+0xa0/0x480 __vfs_read+0x23/0x140 vfs_read+0x87/0x130 SyS_read+0x42/0x90 do_syscall_64+0x5b/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 To fix this, do what we do for cache read faults already: drop the mmap_sem before calling into anything IO bound, in this case the balance_dirty_pages() function, and return VM_FAULT_RETRY. Link: http://lkml.kernel.org/r/20190924194238.GA29030@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/internal.h')
-rw-r--r--mm/internal.h21
1 files changed, 21 insertions, 0 deletions
diff --git a/mm/internal.h b/mm/internal.h
index 0d5f720c75ab..7dd7fbb577a9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -362,6 +362,27 @@ vma_address(struct page *page, struct vm_area_struct *vma)
return max(start, vma->vm_start);
}
+static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
+ struct file *fpin)
+{
+ int flags = vmf->flags;
+
+ if (fpin)
+ return fpin;
+
+ /*
+ * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+ * anything, so we only pin the file and drop the mmap_sem if only
+ * FAULT_FLAG_ALLOW_RETRY is set.
+ */
+ if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
+ FAULT_FLAG_ALLOW_RETRY) {
+ fpin = get_file(vmf->vma->vm_file);
+ up_read(&vmf->vma->vm_mm->mmap_sem);
+ }
+ return fpin;
+}
+
#else /* !CONFIG_MMU */
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }