nfs41: add a helper to mark layout for return

It marks all matching layout segments as NFS_LSEG_LAYOUTRETURN,
which is an indicator for pnfs_put_lseg() to send layoutreturn,
and also prevents pnfs_update_layout() from using the returning
segments. Once it is set, it never gets cleared.

It also sets proper io failure bit so that pnfs path can be retried
after PNFS_LAYOUTGET_RETRY_TIMEOUT second.

Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <Thomas.Haynes@primarydata.com>

2 files changed, 59 insertions, 0 deletions

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 1b9720992608..0bd149baca71 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1479,6 +1479,61 @@ out_forget_reply:
         goto out;
 }
 
+static void
+pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
+                                struct list_head *tmp_list,
+                                struct pnfs_layout_range *return_range)
+{
+        struct pnfs_layout_segment *lseg, *next;
+
+        dprintk("%s:Begin lo %p\n", __func__, lo);
+
+        if (list_empty(&lo->plh_segs))
+                return;
+
+        list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
+                if (should_free_lseg(&lseg->pls_range, return_range)) {
+                        dprintk("%s: marking lseg %p iomode %d "
+                                "offset %llu length %llu\n", __func__,
+                                lseg, lseg->pls_range.iomode,
+                                lseg->pls_range.offset,
+                                lseg->pls_range.length);
+                        set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
+                        mark_lseg_invalid(lseg, tmp_list);
+                }
+}
+
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+                                       struct pnfs_layout_segment *lseg)
+{
+        struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
+        int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode);
+        struct pnfs_layout_range range = {
+                .iomode = lseg->pls_range.iomode,
+                .offset = 0,
+                .length = NFS4_MAX_UINT64,
+        };
+        LIST_HEAD(free_me);
+
+        spin_lock(&inode->i_lock);
+        /* set failure bit so that pnfs path will be retried later */
+        pnfs_layout_set_fail_bit(lo, iomode);
+        set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+        if (lo->plh_return_iomode == 0)
+                lo->plh_return_iomode = range.iomode;
+        else if (lo->plh_return_iomode != range.iomode)
+                lo->plh_return_iomode = IOMODE_ANY;
+        /*
+         * mark all matching lsegs so that we are sure to have no live
+         * segments at hand when sending layoutreturn. See pnfs_put_lseg()
+         * for how it works.
+         */
+        pnfs_mark_matching_lsegs_return(lo, &free_me, &range);
+        spin_unlock(&inode->i_lock);
+        pnfs_free_lseg_list(&free_me);
+}
+EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 4cf0d54e14c3..bea2030eec74 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -38,6 +38,7 @@ enum {
         NFS_LSEG_VALID = 0,     /* cleared when lseg is recalled/returned */
         NFS_LSEG_ROC,           /* roc bit received from server */
         NFS_LSEG_LAYOUTCOMMIT,  /* layoutcommit bit set for layoutcommit */
+        NFS_LSEG_LAYOUTRETURN,  /* layoutreturn bit set for layoutreturn */
 };
 
 /* Individual ip address */
@@ -184,6 +185,7 @@ struct pnfs_layout_hdr {
         u32                     plh_barrier; /* ignore lower seqids */
         unsigned long           plh_retry_timestamp;
         unsigned long           plh_flags;
+        enum pnfs_iomode        plh_return_iomode;
         loff_t                  plh_lwb; /* last write byte for layoutcommit */
         struct rpc_cred         *plh_lc_cred; /* layoutcommit cred */
         struct inode            *plh_inode;
@@ -274,6 +276,8 @@ void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);
 int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+                                       struct pnfs_layout_segment *lseg);
 
 /* nfs4_deviceid_flags */
 enum {