NFS: fix nfs_release_folio() to not deadlock via kcompactd writeback

Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so
nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd.

Otherwise NFS can deadlock waiting for kcompactd enduced writeback which
recurses back to NFS (which triggers writeback to NFSD via NFS loopback
mount on the same host, NFSD blocks waiting for XFS's call to
__filemap_get_folio):

6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds.

{---
[58] "kcompactd0"
[<0>] folio_wait_bit+0xe8/0x200
[<0>] folio_wait_writeback+0x2b/0x80
[<0>] nfs_wb_folio+0x80/0x1b0 [nfs]
[<0>] nfs_release_folio+0x68/0x130 [nfs]
[<0>] split_huge_page_to_list_to_order+0x362/0x840
[<0>] migrate_pages_batch+0x43d/0xb90
[<0>] migrate_pages_sync+0x9a/0x240
[<0>] migrate_pages+0x93c/0x9f0
[<0>] compact_zone+0x8e2/0x1030
[<0>] compact_node+0xdb/0x120
[<0>] kcompactd+0x121/0x2e0
[<0>] kthread+0xcf/0x100
[<0>] ret_from_fork+0x31/0x40
[<0>] ret_from_fork_asm+0x1a/0x30
---}

[akpm@linux-foundation.org: fix build]
Link: https://lkml.kernel.org/r/20250225022002.26141-1-snitzer@kernel.org
Fixes: 96780ca55e3c ("NFS: fix up nfs_release_folio() to try to release the page")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 1bb646752e4663ee79dc94c0b1f8231bf77ca598..033feeab8c346ee89ad001487d543d78a3fe7b3d 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 #include <linux/uaccess.h>
 #include <linux/filelock.h>
@@ -457,7 +458,7 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
        /* If the private flag is set, then the folio is not freeable */
        if (folio_test_private(folio)) {
                if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
-                   current_is_kswapd())
+                   current_is_kswapd() || current_is_kcompactd())
                        return false;
                if (nfs_wb_folio(folio->mapping->host, folio) < 0)
                        return false;

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index e947764960496470aa3d9afc6b811fac05871712..7bf0c521db6340198823de8b8a6cfd670baf9bd8 100644 (file)
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order)
        return 2UL << order;
 }
 
+static inline int current_is_kcompactd(void)
+{
+       return current->flags & PF_KCOMPACTD;
+}
+
 #ifdef CONFIG_COMPACTION
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9632e3318e0d6bcc5abb647118d9aebb55edefe8..9c15365a30c08b64db65f0e88a88b761aecd807e 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1701,7 +1701,7 @@ extern struct pid *cad_pid;
 #define PF_USED_MATH           0x00002000      /* If unset the fpu must be initialized before use */
 #define PF_USER_WORKER         0x00004000      /* Kernel thread cloned from userspace thread */
 #define PF_NOFREEZE            0x00008000      /* This thread should not be frozen */
-#define PF__HOLE__00010000     0x00010000
+#define PF_KCOMPACTD           0x00010000      /* I am kcompactd */
 #define PF_KSWAPD              0x00020000      /* I am kswapd */
 #define PF_MEMALLOC_NOFS       0x00040000      /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
 #define PF_MEMALLOC_NOIO       0x00080000      /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */

diff --git a/mm/compaction.c b/mm/compaction.c
index 12ed8425fa175c5dec50bac3dddb13499abaaa11..a3203d97123eadeb9cd9ae87341e3e9e15ac2cac 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3181,6 +3181,7 @@ static int kcompactd(void *p)
        long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
        long timeout = default_timeout;
 
+       current->flags |= PF_KCOMPACTD;
        set_freezable();
 
        pgdat->kcompactd_max_order = 0;
@@ -3237,6 +3238,8 @@ static int kcompactd(void *p)
                        pgdat->proactive_compact_trigger = false;
        }
 
+       current->flags &= ~PF_KCOMPACTD;
+
        return 0;
 }