From cfc9a5c88f91f7b4d606fce89505e1f404691ea5 Mon Sep 17 00:00:00 2001
From: Brian Behlendorf <behlendorf1@llnl.gov>
Date: Tue, 19 Jul 2011 11:48:46 -0700
Subject: [PATCH] Fix zpl_writepage() deadlock

Disable the normal reclaim path for zpl_putpage().  This ensures that
all memory allocations under this call path will never enter direct
reclaim.  If this were to happen the VM might try to write out
additional pages by calling zpl_putpage() again resulting in a
deadlock.

This sitution is typically handled in Linux by marking each offending
allocation GFP_NOFS.  However, since much of the code used is common
it makes more sense to use PF_MEMALLOC to flag the entire call tree.
Alternately, the code could be updated to pass the needed allocation
flags but that's a more invasive change.

The following example of the above described deadlock was triggered
by test 074 in the xfstest suite.

Call Trace:
 [<ffffffff814dcdb2>] down_write+0x32/0x40
 [<ffffffffa05af6e4>] dnode_new_blkid+0x94/0x2d0 [zfs]
 [<ffffffffa0597d66>] dbuf_dirty+0x556/0x750 [zfs]
 [<ffffffffa05987d1>] dmu_buf_will_dirty+0x81/0xd0 [zfs]
 [<ffffffffa059ee70>] dmu_write+0x90/0x170 [zfs]
 [<ffffffffa0611afe>] zfs_putpage+0x2ce/0x360 [zfs]
 [<ffffffffa062875e>] zpl_putpage+0x1e/0x60 [zfs]
 [<ffffffffa06287b2>] zpl_writepage+0x12/0x20 [zfs]
 [<ffffffff8115f907>] writeout+0xa7/0xd0
 [<ffffffff8115fa6b>] move_to_new_page+0x13b/0x170
 [<ffffffff8115fed4>] migrate_pages+0x434/0x4c0
 [<ffffffff811559ab>] compact_zone+0x4fb/0x780
 [<ffffffff81155ed1>] compact_zone_order+0xa1/0xe0
 [<ffffffff8115602c>] try_to_compact_pages+0x11c/0x190
 [<ffffffff811200bb>] __alloc_pages_nodemask+0x5eb/0x8b0
 [<ffffffff8115464a>] alloc_pages_current+0xaa/0x110
 [<ffffffff8111e36e>] __get_free_pages+0xe/0x50
 [<ffffffffa03f0e2f>] kv_alloc+0x3f/0xb0 [spl]
 [<ffffffffa03f11d9>] spl_kmem_cache_alloc+0x339/0x660 [spl]
 [<ffffffffa05950b3>] dbuf_create+0x43/0x370 [zfs]
 [<ffffffffa0596fb1>] __dbuf_hold_impl+0x241/0x480 [zfs]
 [<ffffffffa0597276>] dbuf_hold_impl+0x86/0xc0 [zfs]
 [<ffffffffa05977ff>] dbuf_hold_level+0x1f/0x30 [zfs]
 [<ffffffffa05a9dde>] dmu_tx_check_ioerr+0x4e/0x110 [zfs]
 [<ffffffffa05aa1f9>] dmu_tx_count_write+0x359/0x6f0 [zfs]
 [<ffffffffa05aa5df>] dmu_tx_hold_write+0x4f/0x70 [zfs]
 [<ffffffffa0611a6d>] zfs_putpage+0x23d/0x360 [zfs]
 [<ffffffffa062875e>] zpl_putpage+0x1e/0x60 [zfs]
 [<ffffffff811221f9>] write_cache_pages+0x1c9/0x4a0
 [<ffffffffa0628738>] zpl_writepages+0x18/0x20 [zfs]
 [<ffffffff81122521>] do_writepages+0x21/0x40
 [<ffffffff8119bbbd>] writeback_single_inode+0xdd/0x2c0
 [<ffffffff8119bfbe>] writeback_sb_inodes+0xce/0x180
 [<ffffffff8119c11b>] writeback_inodes_wb+0xab/0x1b0
 [<ffffffff8119c4bb>] wb_writeback+0x29b/0x3f0
 [<ffffffff8119c6cb>] wb_do_writeback+0xbb/0x240
 [<ffffffff811308ea>] bdi_forker_task+0x6a/0x310
 [<ffffffff8108ddf6>] kthread+0x96/0xa0

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #327
---
 module/zfs/zpl_file.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/module/zfs/zpl_file.c b/module/zfs/zpl_file.c
index fc2b81329..c2e3a6bdc 100644
--- a/module/zfs/zpl_file.c
+++ b/module/zfs/zpl_file.c
@@ -354,7 +354,16 @@ zpl_putpage(struct page *pp, struct writeback_control *wbc, void *data)
 {
 	int error;
 
+	/*
+	 * Disable the normal reclaim path for zpl_putpage().  This
+	 * ensures that all memory allocations under this call path
+	 * will never enter direct reclaim.  If this were to happen
+	 * the VM might try to write out additional pages by calling
+	 * zpl_putpage() again resulting in a deadlock.
+	 */
+	current->flags |= PF_MEMALLOC;
 	error = -zfs_putpage(pp, wbc, data);
+	current->flags &= ~PF_MEMALLOC;
 
 	if (error) {
 		SetPageError(pp);