From: Peng Tao <tao.peng@xxxxxxxxxxxxxxx>
Also take care to stop waiting if someone clears retry bit.
Signed-off-by: Peng Tao <tao.peng@xxxxxxxxxxxxxxx>
---
fs/nfs/nfs4proc.c | 4 +++-
fs/nfs/pnfs.c | 39 ++++++++++++++++++++++++++++++++++++++-
fs/nfs/pnfs.h | 5 ++++-
3 files changed, 45 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 91733bb..297c8f6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7787,7 +7787,9 @@ static void nfs4_layoutreturn_release(void *calldata)
spin_lock(&lo->plh_inode->i_lock);
if (lrp->res.lrs_present)
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
- clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+ clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
+ smp_mb__after_atomic();
+ wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
lo->plh_block_lgets--;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index fec1d897..8c1440d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1404,6 +1404,26 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
return ret;
}
+/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+{
+ if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
+ return 1;
+ return nfs_wait_bit_killable(key);
+}
+
+static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
+{
+ /*
+ * send layoutcommit as it can hold up layoutreturn due to lseg
+ * reference
+ */
+ pnfs_layoutcommit_inode(lo->plh_inode, false);
+ return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
+ pnfs_layoutget_retry_bit_wait,
+ TASK_UNINTERRUPTIBLE);
+}
+
/*
* Layout segment is retreived from the server if not cached.
* The appropriate layout segment is referenced and returned to the caller.
@@ -1450,7 +1470,8 @@ lookup_again:
}
/* if LAYOUTGET already failed once we don't try again */
- if (pnfs_layout_io_test_failed(lo, iomode))
+ if (pnfs_layout_io_test_failed(lo, iomode) &&
+ !pnfs_should_retry_layoutget(lo))
goto out_unlock;
first = list_empty(&lo->plh_segs);
@@ -1475,6 +1496,22 @@ lookup_again:
goto out_unlock;
}
+ /*
+ * Because we free lsegs before sending LAYOUTRETURN, we need to wait
+ * for LAYOUTRETURN even if first is true.
+ */
+ if (!lseg && pnfs_should_retry_layoutget(lo) &&
+ test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+ spin_unlock(&ino->i_lock);
+ dprintk("%s wait for layoutreturn\n", __func__);
+ if (pnfs_prepare_to_retry_layoutget(lo)) {
+ pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
+ goto lookup_again;
+ }
+ goto out_put_layout_hdr;
+ }
+
if (pnfs_layoutgets_blocked(lo, &arg, 0))
goto out_unlock;
atomic_inc(&lo->plh_outstanding);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 67a436b..c2b4328 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -358,8 +358,11 @@ static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo)
static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo)
{
- if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags))
+ if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) {
atomic_dec(&lo->plh_refcount);
+ /* wake up waiters for LAYOUTRETURN as that is not needed */
+ wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+ }
}
static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo)
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
