[permalink] [raw]

Subject: [PATCH 32/33] pnfsblock: Implement release_inval_marks

From: Zhang Jingwang <[email protected]>

Leaving it unimplemented will cause memory leak.

Signed-off-by: Zhang Jingwang <[email protected]>
Signed-off-by: Benny Halevy <[email protected]>
---
fs/nfs/blocklayout/blocklayout.c | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 6de800f..3187c4f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -523,10 +523,15 @@ release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range)
spin_unlock(&bl->bl_ext_lock);
}

-/* STUB */
static void
release_inval_marks(struct pnfs_inval_markings *marks)
{
+ struct pnfs_inval_tracking *pos, *temp;
+
+ list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) {
+ list_del(&pos->it_link);
+ kfree(pos);
+ }
return;
}

--
1.7.4.1

2011-06-14 02:33:25

by Jim Rees

[permalink] [raw]

Subject: [PATCH 33/33] pnfsblock DEVONLY: Add configurable prefetch size for layoutget

From: Peng Tao <[email protected]>

Do not send upstream. Only for dealing with servers that return small
layouts.

pnfs_layout_prefetch_kb can be modified via sysctl.
default to 0 so no effect if not set via sysctl.

Signed-off-by: Peng Tao <[email protected]>
---
fs/nfs/pnfs.c | 17 +++++++++++++++++
fs/nfs/pnfs.h | 1 +
fs/nfs/sysctl.c | 10 ++++++++++
3 files changed, 28 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 7912635..4f63ebd 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -46,6 +46,11 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
*/
static LIST_HEAD(pnfs_modules_tbl);

+/*
+ * layoutget prefetch size
+ */
+unsigned int pnfs_layout_prefetch_kb;
+
/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
find_pnfs_driver_locked(u32 id)
@@ -909,6 +914,16 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
}

/*
+ * Set layout prefetch length.
+ */
+static void
+pnfs_set_layout_prefetch(struct pnfs_layout_range *range)
+{
+ if (range->length < (pnfs_layout_prefetch_kb << 10))
+ range->length = pnfs_layout_prefetch_kb << 10;
+}
+
+/*
* Layout segment is retreived from the server if not cached.
* The appropriate layout segment is referenced and returned to the caller.
*/
@@ -959,6 +974,8 @@ pnfs_update_layout(struct inode *ino,

if (pnfs_layoutgets_blocked(lo, NULL, 0))
goto out_unlock;
+
+ pnfs_set_layout_prefetch(&arg);
atomic_inc(&lo->plh_outstanding);

get_layout_hdr(lo);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index d7f203b..6718053 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -180,6 +180,7 @@ extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);

/* pnfs.c */
+extern unsigned int pnfs_layout_prefetch_kb;
void get_layout_hdr(struct pnfs_layout_hdr *lo);
void put_lseg(struct pnfs_layout_segment *lseg);

diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 978aaeb..79a5134 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -14,6 +14,7 @@
#include <linux/nfs_fs.h>

#include "callback.h"
+#include "pnfs.h"

#ifdef CONFIG_NFS_V4
static const int nfs_set_port_min = 0;
@@ -42,6 +43,15 @@ static ctl_table nfs_cb_sysctls[] = {
},
#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
#endif
+#ifdef CONFIG_NFS_V4_1
+ {
+ .procname = "pnfs_layout_prefetch_kb",
+ .data = &pnfs_layout_prefetch_kb,
+ .maxlen = sizeof(pnfs_layout_prefetch_kb),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
{
.procname = "nfs_mountpoint_timeout",
.data = &nfs_mountpoint_expiry_timeout,
--
1.7.4.1

2011-06-14 02:32:09

by Jim Rees

[permalink] [raw]

Subject: [PATCH 03/33] pnfs: let layoutcommit code handle multiple segments

From: Peng Tao <[email protected]>

Some layout driver like block will have multiple segments.
Generic code should be able to handle it.

Signed-off-by: Peng Tao <[email protected]>
---
fs/nfs/pnfs.c | 18 ++++++++++++++----
fs/nfs/pnfs.h | 1 +
2 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 593a9aa..e252af1 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -893,7 +893,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
dprintk("%s:Begin\n", __func__);

assert_spin_locked(&lo->plh_inode->i_lock);
- list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
+ list_for_each_entry_reverse(lseg, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
is_matching_lseg(&lseg->pls_range, range)) {
ret = get_lseg(lseg);
@@ -1243,10 +1243,19 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode)
{
struct pnfs_layout_segment *lseg, *rv = NULL;
+ loff_t max_pos = 0;
+
+ list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+ if (lseg->pls_range.iomode == IOMODE_RW) {
+ if (max_pos < lseg->pls_end_pos)
+ max_pos = lseg->pls_end_pos;
+ if (test_and_clear_bit
+ (NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+ rv = lseg;
+ }
+ }
+ rv->pls_end_pos = max_pos;

- list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
- if (lseg->pls_range.iomode == IOMODE_RW)
- rv = lseg;
return rv;
}

@@ -1261,6 +1270,7 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
/* references matched in nfs4_layoutcommit_release */
get_lseg(wdata->lseg);
+ set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags);
wdata->lseg->pls_lc_cred =
get_rpccred(wdata->args.context->state->owner->so_cred);
mark_as_dirty = true;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index f984598..0ac820f 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -36,6 +36,7 @@
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 */
};

struct pnfs_layout_segment {
--
1.7.4.1

2011-06-14 02:32:38

by Jim Rees

[permalink] [raw]

Subject: [PATCH 14/33] pnfsblock: remove device operations

Signed-off-by: Jim Rees <[email protected]>
Signed-off-by: Fred Isaman <[email protected]>
Signed-off-by: Benny Halevy <[email protected]>
---
fs/nfs/blocklayout/Makefile | 2 +-
fs/nfs/blocklayout/blocklayout.h | 2 +
fs/nfs/blocklayout/blocklayoutdm.c | 120 ++++++++++++++++++++++++++++++++++++
3 files changed, 123 insertions(+), 1 deletions(-)
create mode 100644 fs/nfs/blocklayout/blocklayoutdm.c

diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile
index bd69aad..bdbf180 100644
--- a/fs/nfs/blocklayout/Makefile
+++ b/fs/nfs/blocklayout/Makefile
@@ -2,4 +2,4 @@
# Makefile for the pNFS block layout driver kernel module
#
obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o
-blocklayoutdriver-objs := blocklayout.o block-device-discovery-pipe.o extents.o blocklayoutdev.o
+blocklayoutdriver-objs := blocklayout.o block-device-discovery-pipe.o extents.o blocklayoutdev.o blocklayoutdm.o
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index cda7ea1..839b81d 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -101,6 +101,8 @@ struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
struct list_head *sdlist);
int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
+/* blocklayoutdm.c */
+void free_block_dev(struct pnfs_block_dev *bdev);

#include <linux/sunrpc/simple_rpc_pipefs.h>

diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
new file mode 100644
index 0000000..097dd05
--- /dev/null
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -0,0 +1,120 @@
+/*
+ * linux/fs/nfs/blocklayout/blocklayoutdm.c
+ *
+ * Module for the NFSv4.1 pNFS block layout driver.
+ *
+ * Copyright (c) 2007 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ * Fred Isaman <[email protected]>
+ * Andy Adamson <[email protected]>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization. if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose. the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include <linux/genhd.h> /* gendisk - used in a dprintk*/
+#include <linux/sched.h>
+#include <linux/hash.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY NFSDBG_PNFS_LD
+
+/* Defines used for calculating memory usage in nfs4_blk_flatten() */
+#define ARGSIZE 24 /* Max bytes needed for linear target arg string */
+#define SPECSIZE (sizeof8(struct dm_target_spec) + ARGSIZE)
+#define SPECS_PER_PAGE (PAGE_SIZE / SPECSIZE)
+#define SPEC_HEADER_ADJUST (SPECS_PER_PAGE - \
+ (PAGE_SIZE - sizeof8(struct dm_ioctl)) / SPECSIZE)
+#define roundup8(x) (((x)+7) & ~7)
+#define sizeof8(x) roundup8(sizeof(x))
+
+static int dev_remove(dev_t dev)
+{
+ int ret = 1;
+ struct pipefs_hdr *msg = NULL, *reply = NULL;
+ uint64_t bl_dev;
+ uint32_t major = MAJOR(dev), minor = MINOR(dev);
+
+ dprintk("Entering %s\n", __func__);
+
+ if (IS_ERR(bl_device_pipe))
+ return ret;
+
+ memcpy((void *)&bl_dev, &major, sizeof(uint32_t));
+ memcpy((void *)&bl_dev + sizeof(uint32_t), &minor, sizeof(uint32_t));
+ msg = pipefs_alloc_init_msg(0, BL_DEVICE_UMOUNT, 0, (void *)&bl_dev,
+ sizeof(uint64_t));
+ if (IS_ERR(msg)) {
+ dprintk("ERROR: couldn't make pipefs message.\n");
+ goto out;
+ }
+ msg->msgid = hash_ptr(&msg, sizeof(msg->msgid) * 8);
+ msg->status = BL_DEVICE_REQUEST_INIT;
+
+ reply = pipefs_queue_upcall_waitreply(bl_device_pipe, msg,
+ &bl_device_list, 0, 0);
+ if (IS_ERR(reply)) {
+ dprintk("ERROR: upcall_waitreply failed\n");
+ goto out;
+ }
+
+ if (reply->status == BL_DEVICE_REQUEST_PROC)
+ ret = 0; /*TODO: what to return*/
+out:
+ if (!IS_ERR(reply))
+ kfree(reply);
+ if (!IS_ERR(msg))
+ kfree(msg);
+ return ret;
+}
+
+/*
+ * Release meta device
+ */
+static int nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
+{
+ int rv;
+
+ dprintk("%s Releasing\n", __func__);
+ /* XXX Check return? */
+ rv = nfs4_blkdev_put(bdev->bm_mdev);
+ dprintk("%s nfs4_blkdev_put returns %d\n", __func__, rv);
+
+ rv = dev_remove(bdev->bm_mdev->bd_dev);
+ dprintk("%s Returns %d\n", __func__, rv);
+ return rv;
+}
+
+void free_block_dev(struct pnfs_block_dev *bdev)
+{
+ if (bdev) {
+ if (bdev->bm_mdev) {
+ dprintk("%s Removing DM device: %d:%d\n",
+ __func__,
+ MAJOR(bdev->bm_mdev->bd_dev),
+ MINOR(bdev->bm_mdev->bd_dev));
+ /* XXX Check status ?? */
+ nfs4_blk_metadev_release(bdev);
+ }
+ kfree(bdev);
+ }
+}
--
1.7.4.1

2011-06-14 02:32:15

by Jim Rees

[permalink] [raw]

Subject: [PATCH 05/33] pnfs: ask for layout_blksize and save it in nfs_server

From: Peng Tao <[email protected]>

Block layout needs it to determine IO size.

Signed-off-by: Fred Isaman <[email protected]>
Signed-off-by: Tao Guo <[email protected]>
Signed-off-by: Benny Halevy <[email protected]>
Signed-off-by: Peng Tao <[email protected]>
---
fs/nfs/client.c | 1 +
fs/nfs/nfs4_fs.h | 2 +-
fs/nfs/nfs4proc.c | 5 +-
fs/nfs/nfs4xdr.c | 101 +++++++++++++++++++++++++++++++++++++--------
include/linux/nfs_fs_sb.h | 4 +-
include/linux/nfs_xdr.h | 3 +-
6 files changed, 93 insertions(+), 23 deletions(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d630bb7..3b75943 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -938,6 +938,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
if (server->wsize > NFS_MAX_FILE_IO_SIZE)
server->wsize = NFS_MAX_FILE_IO_SIZE;
server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ server->pnfs_blksize = fsinfo->blksize;
set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);

server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index c4a6983..5725a7e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -315,7 +315,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
extern const u32 nfs4_fattr_bitmap[2];
extern const u32 nfs4_statfs_bitmap[2];
extern const u32 nfs4_pathconf_bitmap[2];
-extern const u32 nfs4_fsinfo_bitmap[2];
+extern const u32 nfs4_fsinfo_bitmap[3];
extern const u32 nfs4_fs_locations_bitmap[2];

/* nfs4renewd.c */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ec580a8..04450bf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -137,12 +137,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
0
};

-const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
+const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
| FATTR4_WORD0_MAXREAD
| FATTR4_WORD0_MAXWRITE
| FATTR4_WORD0_LEASE_TIME,
FATTR4_WORD1_TIME_DELTA
- | FATTR4_WORD1_FS_LAYOUT_TYPES
+ | FATTR4_WORD1_FS_LAYOUT_TYPES,
+ FATTR4_WORD2_LAYOUT_BLKSIZE
};

const u32 nfs4_fs_locations_bitmap[2] = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 60e9d44..b8f375e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -91,7 +91,7 @@ static int nfs4_stat_to_errno(int);
#define encode_getfh_maxsz (op_encode_hdr_maxsz)
#define decode_getfh_maxsz (op_decode_hdr_maxsz + 1 + \
((3+NFS4_FHSIZE) >> 2))
-#define nfs4_fattr_bitmap_maxsz 3
+#define nfs4_fattr_bitmap_maxsz 4
#define encode_getattr_maxsz (op_encode_hdr_maxsz + nfs4_fattr_bitmap_maxsz)
#define nfs4_name_maxsz (1 + ((3 + NFS4_MAXNAMLEN) >> 2))
#define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2))
@@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int);
#define encode_restorefh_maxsz (op_encode_hdr_maxsz)
#define decode_restorefh_maxsz (op_decode_hdr_maxsz)
#define encode_fsinfo_maxsz (encode_getattr_maxsz)
-#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + 15)
+/* The 5 accounts for the PNFS attributes, and assumes that at most three
+ * layout types will be returned.
+ */
+#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + \
+ nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
#define encode_renew_maxsz (op_encode_hdr_maxsz + 3)
#define decode_renew_maxsz (op_decode_hdr_maxsz)
#define encode_setclientid_maxsz \
@@ -1095,6 +1099,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
hdr->replen += decode_getattr_maxsz;
}

+static void
+encode_getattr_three(struct xdr_stream *xdr,
+ uint32_t bm0, uint32_t bm1, uint32_t bm2,
+ struct compound_hdr *hdr)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(OP_GETATTR);
+ if (bm2) {
+ p = reserve_space(xdr, 16);
+ *p++ = cpu_to_be32(3);
+ *p++ = cpu_to_be32(bm0);
+ *p++ = cpu_to_be32(bm1);
+ *p = cpu_to_be32(bm2);
+ } else if (bm1) {
+ p = reserve_space(xdr, 12);
+ *p++ = cpu_to_be32(2);
+ *p++ = cpu_to_be32(bm0);
+ *p = cpu_to_be32(bm1);
+ } else {
+ p = reserve_space(xdr, 8);
+ *p++ = cpu_to_be32(1);
+ *p = cpu_to_be32(bm0);
+ }
+ hdr->nops++;
+ hdr->replen += decode_getattr_maxsz;
+}
+
static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
{
encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0],
@@ -1103,8 +1136,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c

static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
{
- encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0],
- bitmask[1] & nfs4_fsinfo_bitmap[1], hdr);
+ encode_getattr_three(xdr,
+ bitmask[0] & nfs4_fsinfo_bitmap[0],
+ bitmask[1] & nfs4_fsinfo_bitmap[1],
+ bitmask[2] & nfs4_fsinfo_bitmap[2],
+ hdr);
}

static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -2575,7 +2611,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
struct compound_hdr hdr = {
.nops = 0,
};
- const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+ const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME, 0, 0 };

encode_compound_hdr(xdr, req, &hdr);
encode_setclientid_confirm(xdr, arg, &hdr);
@@ -2719,7 +2755,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
};
- const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+ const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME, 0, 0 };

encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->la_seq_args, &hdr);
@@ -2947,14 +2983,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
goto out_overflow;
bmlen = be32_to_cpup(p);

- bitmap[0] = bitmap[1] = 0;
+ bitmap[0] = bitmap[1] = bitmap[2] = 0;
p = xdr_inline_decode(xdr, (bmlen << 2));
if (unlikely(!p))
goto out_overflow;
if (bmlen > 0) {
bitmap[0] = be32_to_cpup(p++);
- if (bmlen > 1)
- bitmap[1] = be32_to_cpup(p);
+ if (bmlen > 1) {
+ bitmap[1] = be32_to_cpup(p++);
+ if (bmlen > 2)
+ bitmap[2] = be32_to_cpup(p);
+ }
}
return 0;
out_overflow:
@@ -2986,8 +3025,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
return ret;
bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
} else
- bitmask[0] = bitmask[1] = 0;
- dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]);
+ bitmask[0] = bitmask[1] = bitmask[2] = 0;
+ dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__,
+ bitmask[0], bitmask[1], bitmask[2]);
return 0;
}

@@ -4041,7 +4081,7 @@ out_overflow:
static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
{
__be32 *savep;
- uint32_t attrlen, bitmap[2] = {0};
+ uint32_t attrlen, bitmap[3] = {0};
int status;

if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4067,7 +4107,7 @@ xdr_error:
static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
{
__be32 *savep;
- uint32_t attrlen, bitmap[2] = {0};
+ uint32_t attrlen, bitmap[3] = {0};
int status;

if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4099,7 +4139,7 @@ xdr_error:
static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
{
__be32 *savep;
- uint32_t attrlen, bitmap[2] = {0};
+ uint32_t attrlen, bitmap[3] = {0};
int status;

if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4239,7 +4279,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
{
__be32 *savep;
uint32_t attrlen,
- bitmap[2] = {0};
+ bitmap[3] = {0};
int status;

status = decode_op_hdr(xdr, OP_GETATTR);
@@ -4325,10 +4365,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
return status;
}

+/*
+ * The prefered block size for layout directed io
+ */
+static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
+ uint32_t *res)
+{
+ __be32 *p;
+
+ dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+ *res = 0;
+ if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p)) {
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+ }
+ *res = be32_to_cpup(p);
+ bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
+ }
+ return 0;
+}
+
static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
{
__be32 *savep;
- uint32_t attrlen, bitmap[2];
+ uint32_t attrlen, bitmap[3];
int status;

if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4356,6 +4418,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
if (status != 0)
goto xdr_error;
+ status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
+ if (status)
+ goto xdr_error;

status = verify_attr_len(xdr, savep, attrlen);
xdr_error:
@@ -4775,7 +4840,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
{
__be32 *savep;
uint32_t attrlen,
- bitmap[2] = {0};
+ bitmap[3] = {0};
struct kvec *iov = req->rq_rcv_buf.head;
int status;

@@ -6607,7 +6672,7 @@ out:
int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
int plus)
{
- uint32_t bitmap[2] = {0};
+ uint32_t bitmap[3] = {0};
uint32_t len;
__be32 *p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 87694ca..79cc4ca 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -130,7 +130,7 @@ struct nfs_server {
#endif

#ifdef CONFIG_NFS_V4
- u32 attr_bitmask[2];/* V4 bitmask representing the set
+ u32 attr_bitmask[3];/* V4 bitmask representing the set
of attributes supported on this
filesystem */
u32 cache_consistency_bitmask[2];
@@ -143,6 +143,8 @@ struct nfs_server {
filesystem */
struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */
struct rpc_wait_queue roc_rpcwaitq;
+ void *pnfs_ld_data; /* per mount point data */
+ u32 pnfs_blksize; /* layout_blksize attr */

/* the following fields are protected by nfs_client->cl_lock */
struct rb_root state_owners;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0863228..1fa6f7a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -122,6 +122,7 @@ struct nfs_fsinfo {
struct timespec time_delta; /* server time granularity */
__u32 lease_time; /* in seconds */
__u32 layouttype; /* supported pnfs layout driver */
+ __u32 blksize; /* preferred pnfs io block size */
};

struct nfs_fsstat {
@@ -953,7 +954,7 @@ struct nfs4_server_caps_arg {
};

struct nfs4_server_caps_res {
- u32 attr_bitmask[2];
+ u32 attr_bitmask[3];
u32 acl_bitmask;
u32 has_links;
u32 has_symlinks;
--
1.7.4.1