From: The pNFS Team <linux-nfs@xxxxxxxxxxxxxxx>
In particular, server reboot will invalidate all layouts.
Note that in order to have an active layout, we must get a successful response
from the server. To avoid adding that machinery, this patch just includes a
stub that fakes up a successful return. Since the layout is never referenced
for io, this is not a problem.
Signed-off-by: TBD - melding/reorganization of several patches
---
fs/nfs/client.c | 4 +-
fs/nfs/nfs4state.c | 2 +
fs/nfs/pnfs.c | 130 +++++++++++++++++++++++++++++++++++++++++++-
fs/nfs/pnfs.h | 20 +++++++
include/linux/nfs_fs_sb.h | 1 +
5 files changed, 153 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index eed1212..6fc5c84 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -156,7 +156,9 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
cred = rpc_lookup_machine_cred();
if (!IS_ERR(cred))
clp->cl_machine_cred = cred;
-
+#if defined(CONFIG_NFS_V4_1)
+ INIT_LIST_HEAD(&clp->cl_layouts);
+#endif
nfs_fscache_get_client_cookie(clp);
return clp;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3e2f19b..b53a4ce 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -53,6 +53,7 @@
#include "callback.h"
#include "delegation.h"
#include "internal.h"
+#include "pnfs.h"
#define OPENOWNER_POOL_SIZE 8
@@ -1447,6 +1448,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
}
clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+ pnfs_destroy_all_layouts(clp);
}
if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 65f923b..cbce942 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -28,6 +28,7 @@
*/
#include <linux/nfs_fs.h>
+#include "internal.h"
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
@@ -168,11 +169,67 @@ put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
lo->refcount--;
if (!lo->refcount) {
dprintk("%s: freeing layout cache %p\n", __func__, lo);
+ BUG_ON(!list_empty(&lo->layouts));
NFS_I(lo->inode)->layout = NULL;
kfree(lo);
}
}
+static void
+init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
+{
+ INIT_LIST_HEAD(&lseg->fi_list);
+ kref_init(&lseg->kref);
+ lseg->layout = lo;
+}
+
+static void
+destroy_lseg(struct kref *kref)
+{
+ struct pnfs_layout_segment *lseg =
+ container_of(kref, struct pnfs_layout_segment, kref);
+ struct pnfs_layout_hdr *local = lseg->layout;
+
+ dprintk("--> %s\n", __func__);
+ kfree(lseg);
+ /* Matched by get_layout_hdr_locked in pnfs_insert_layout */
+ put_layout_hdr_locked(local);
+}
+
+static void
+put_lseg_locked(struct pnfs_layout_segment *lseg)
+{
+ if (!lseg)
+ return;
+
+ dprintk("%s: lseg %p ref %d\n", __func__, lseg,
+ atomic_read(&lseg->kref.refcount));
+ kref_put(&lseg->kref, destroy_lseg);
+}
+
+static void
+pnfs_clear_lseg_list(struct pnfs_layout_hdr *lo)
+{
+ struct pnfs_layout_segment *lseg, *next;
+ struct nfs_client *clp;
+
+ dprintk("%s:Begin lo %p\n", __func__, lo);
+
+ assert_spin_locked(&lo->inode->i_lock);
+ list_for_each_entry_safe(lseg, next, &lo->segs, fi_list) {
+ dprintk("%s: freeing lseg %p\n", __func__, lseg);
+ list_del(&lseg->fi_list);
+ put_lseg_locked(lseg);
+ }
+ clp = PNFS_NFS_SERVER(lo)->nfs_client;
+ spin_lock(&clp->cl_lock);
+ /* List does not take a reference, so no need for put here */
+ list_del_init(&lo->layouts);
+ spin_unlock(&clp->cl_lock);
+
+ dprintk("%s:Return\n", __func__);
+}
+
void
pnfs_destroy_layout(struct nfs_inode *nfsi)
{
@@ -181,25 +238,90 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
spin_lock(&nfsi->vfs_inode.i_lock);
lo = nfsi->layout;
if (lo) {
+ pnfs_clear_lseg_list(lo);
/* Matched by refcount set to 1 in alloc_init_layout_hdr */
put_layout_hdr_locked(lo);
}
spin_unlock(&nfsi->vfs_inode.i_lock);
}
-/* STUB - pretend LAYOUTGET to server failed */
+/*
+ * Called by the state manger to remove all layouts established under an
+ * expired lease.
+ */
+void
+pnfs_destroy_all_layouts(struct nfs_client *clp)
+{
+ struct pnfs_layout_hdr *lo;
+ LIST_HEAD(tmp_list);
+
+ spin_lock(&clp->cl_lock);
+ list_splice_init(&clp->cl_layouts, &tmp_list);
+ spin_unlock(&clp->cl_lock);
+
+ while (!list_empty(&tmp_list)) {
+ lo = list_entry(tmp_list.next, struct pnfs_layout_hdr,
+ layouts);
+ dprintk("%s freeing layout for inode %lu\n", __func__,
+ lo->inode->i_ino);
+ pnfs_destroy_layout(NFS_I(lo->inode));
+ }
+}
+
+static void pnfs_insert_layout(struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg);
+
+/* Get layout from server. */
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
struct nfs_open_context *ctx,
u32 iomode)
{
struct inode *ino = lo->inode;
+ struct pnfs_layout_segment *lseg;
- set_bit(lo_fail_bit(iomode), &lo->state);
+ /* Lets pretend we sent LAYOUTGET and got a response */
+ lseg = kzalloc(sizeof(*lseg), GFP_KERNEL);
+ if (!lseg) {
+ set_bit(lo_fail_bit(iomode), &lo->state);
+ spin_lock(&ino->i_lock);
+ put_layout_hdr_locked(lo);
+ spin_unlock(&ino->i_lock);
+ return NULL;
+ }
+ init_lseg(lo, lseg);
+ lseg->iomode = IOMODE_RW;
spin_lock(&ino->i_lock);
+ pnfs_insert_layout(lo, lseg);
put_layout_hdr_locked(lo);
spin_unlock(&ino->i_lock);
- return NULL;
+ return lseg;
+}
+
+static void
+pnfs_insert_layout(struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg)
+{
+ dprintk("%s:Begin\n", __func__);
+
+ assert_spin_locked(&lo->inode->i_lock);
+ if (list_empty(&lo->segs)) {
+ struct nfs_client *clp = PNFS_NFS_SERVER(lo)->nfs_client;
+
+ spin_lock(&clp->cl_lock);
+ BUG_ON(!list_empty(&lo->layouts));
+ list_add_tail(&lo->layouts, &clp->cl_layouts);
+ spin_unlock(&clp->cl_lock);
+ }
+ /* STUB - add the constructed lseg if necessary */
+ if (list_empty(&lo->segs)) {
+ list_add_tail(&lseg->fi_list, &lo->segs);
+ get_layout_hdr_locked(lo);
+ dprintk("%s: inserted lseg %p iomode %d at tail\n",
+ __func__, lseg, lseg->iomode);
+ }
+
+ dprintk("%s:Return\n", __func__);
}
static struct pnfs_layout_hdr *
@@ -211,6 +333,8 @@ alloc_init_layout_hdr(struct inode *ino)
if (!lo)
return NULL;
lo->refcount = 1;
+ INIT_LIST_HEAD(&lo->layouts);
+ INIT_LIST_HEAD(&lo->segs);
lo->inode = ino;
return lo;
}
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index b63b445..dac6a72 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -10,6 +10,13 @@
#ifndef FS_NFS_PNFS_H
#define FS_NFS_PNFS_H
+struct pnfs_layout_segment {
+ struct list_head fi_list;
+ u32 iomode;
+ struct kref kref;
+ struct pnfs_layout_hdr *layout;
+};
+
#ifdef CONFIG_NFS_V4_1
#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
@@ -29,6 +36,8 @@ struct pnfs_layoutdriver_type {
struct pnfs_layout_hdr {
int refcount;
+ struct list_head layouts; /* other client layouts */
+ struct list_head segs; /* layout segments list */
unsigned long state;
struct inode *inode;
};
@@ -43,12 +52,19 @@ struct layoutdriver_io_operations {
extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
+static inline struct nfs_server *
+PNFS_NFS_SERVER(struct pnfs_layout_hdr *lo)
+{
+ return NFS_SERVER(lo->inode);
+}
+
struct pnfs_layout_segment *
pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
enum pnfs_iomode access_type);
void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
void unset_pnfs_layoutdriver(struct nfs_server *);
void pnfs_destroy_layout(struct nfs_inode *);
+void pnfs_destroy_all_layouts(struct nfs_client *);
static inline int lo_fail_bit(u32 iomode)
@@ -65,6 +81,10 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
#else /* CONFIG_NFS_V4_1 */
+static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
+{
+}
+
static inline void pnfs_destroy_layout(struct nfs_inode *nfsi)
{
}
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 29a821d..e670a9c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -82,6 +82,7 @@ struct nfs_client {
/* The flags used for obtaining the clientid during EXCHANGE_ID */
u32 cl_exchange_flags;
struct nfs4_session *cl_session; /* sharred session */
+ struct list_head cl_layouts;
#endif /* CONFIG_NFS_V4_1 */
#ifdef CONFIG_NFS_FSCACHE
--
1.7.2.1
--
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
