Use KM_PUSHPAGE in l2arc_write_buffers

There is potential for deadlock in the l2arc_feed thread if KM_PUSHPAGE
is not used for the allocations made in l2arc_write_buffers.
Specifically, if KM_PUSHPAGE is not used for these allocations, it is
possible for reclaim to be triggered which can cause the l2arc_feed
thread to deadlock itself on the ARC_mru mutex. An example of this is
demonstrated in the following backtrace of the l2arc_feed thread:

    crash> bt 4123
    PID: 4123   TASK: ffff88062f8c1500  CPU: 6   COMMAND: "l2arc_feed"
      0 [ffff88062511d610] schedule at ffffffff814eeee0
      1 [ffff88062511d6d8] __mutex_lock_slowpath at ffffffff814f057e
      2 [ffff88062511d748] mutex_lock at ffffffff814f041b
      3 [ffff88062511d768] arc_evict at ffffffffa05130ca [zfs]
      4 [ffff88062511d858] arc_adjust at ffffffffa05139a9 [zfs]
      5 [ffff88062511d878] arc_shrink at ffffffffa0513a95 [zfs]
      6 [ffff88062511d898] arc_kmem_reap_now at ffffffffa0513be8 [zfs]
      7 [ffff88062511d8c8] arc_shrinker_func at ffffffffa0513ccc [zfs]
      8 [ffff88062511d8f8] shrink_slab at ffffffff8112a17a
      9 [ffff88062511d958] do_try_to_free_pages at ffffffff8112bfdf
     10 [ffff88062511d9e8] try_to_free_pages at ffffffff8112c3ed
     11 [ffff88062511da98] __alloc_pages_nodemask at ffffffff8112431d
     12 [ffff88062511dbb8] kmem_getpages at ffffffff8115e632
     13 [ffff88062511dbe8] fallback_alloc at ffffffff8115f24a
     14 [ffff88062511dc68] ____cache_alloc_node at ffffffff8115efc9
     15 [ffff88062511dcc8] __kmalloc at ffffffff8115fbf9
     16 [ffff88062511dd18] kmem_alloc_debug at ffffffffa047b8cb [spl]
     17 [ffff88062511dda8] l2arc_feed_thread at ffffffffa0511e71 [zfs]
     18 [ffff88062511dea8] thread_generic_wrapper at ffffffffa047d1a1 [spl]
     19 [ffff88062511dee8] kthread at ffffffff81090a86
     20 [ffff88062511df48] kernel_thread at ffffffff8100c14a

Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>

diff --git a/module/zfs/arc.c b/module/zfs/arc.c
index e9f84f5..cbc27d3 100644 (file)
--- a/module/zfs/arc.c
+++ b/module/zfs/arc.c
@@ -1017,7 +1017,8 @@ arc_cksum_compute(arc_buf_t *buf, boolean_t force)
                mutex_exit(&buf->b_hdr->b_freeze_lock);
                return;
        }
-       buf->b_hdr->b_freeze_cksum = kmem_alloc(sizeof (zio_cksum_t), KM_SLEEP);
+       buf->b_hdr->b_freeze_cksum = kmem_alloc(sizeof (zio_cksum_t),
+                                               KM_PUSHPAGE);
        fletcher_2_native(buf->b_data, buf->b_hdr->b_size,
            buf->b_hdr->b_freeze_cksum);
        mutex_exit(&buf->b_hdr->b_freeze_lock);
@@ -4623,8 +4624,8 @@ l2arc_write_buffers(spa_t *spa, l2arc_dev_t *dev, uint64_t target_sz)
                                 */
                                list_insert_head(dev->l2ad_buflist, head);
 
-                               cb = kmem_alloc(
-                                   sizeof (l2arc_write_callback_t), KM_SLEEP);
+                               cb = kmem_alloc(sizeof (l2arc_write_callback_t),
+                                               KM_PUSHPAGE);
                                cb->l2wcb_dev = dev;
                                cb->l2wcb_head = head;
                                pio = zio_root(spa, l2arc_write_done, cb,
@@ -4634,7 +4635,8 @@ l2arc_write_buffers(spa_t *spa, l2arc_dev_t *dev, uint64_t target_sz)
                        /*
                         * Create and add a new L2ARC header.
                         */
-                       hdrl2 = kmem_zalloc(sizeof (l2arc_buf_hdr_t), KM_SLEEP);
+                       hdrl2 = kmem_zalloc(sizeof (l2arc_buf_hdr_t),
+                                           KM_PUSHPAGE);
                        hdrl2->b_dev = dev;
                        hdrl2->b_daddr = dev->l2ad_hand;