summaryrefslogtreecommitdiffstats
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/callback_xdr.c12
-rw-r--r--fs/nfs/dir.c2
-rw-r--r--fs/nfs/file.c100
-rw-r--r--fs/nfs/inode.c2
-rw-r--r--fs/nfs/internal.h2
-rw-r--r--fs/nfs/nfs3proc.c1
-rw-r--r--fs/nfs/nfs4filelayout.c8
-rw-r--r--fs/nfs/nfs4proc.c10
-rw-r--r--fs/nfs/nfs4xdr.c2
-rw-r--r--fs/nfs/objlayout/objio_osd.c872
-rw-r--r--fs/nfs/objlayout/objlayout.c209
-rw-r--r--fs/nfs/objlayout/objlayout.h48
-rw-r--r--fs/nfs/pagelist.c3
-rw-r--r--fs/nfs/pnfs.c52
-rw-r--r--fs/nfs/pnfs_dev.c1
-rw-r--r--fs/nfs/proc.c1
-rw-r--r--fs/nfs/read.c14
-rw-r--r--fs/nfs/super.c37
-rw-r--r--fs/nfs/write.c4
19 files changed, 437 insertions, 943 deletions
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 918ad647afe..726e59a9e50 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -488,17 +488,18 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
struct xdr_stream *xdr,
struct cb_recallanyargs *args)
{
- __be32 *p;
+ uint32_t bitmap[2];
+ __be32 *p, status;
args->craa_addr = svc_addr(rqstp);
p = read_buf(xdr, 4);
if (unlikely(p == NULL))
return htonl(NFS4ERR_BADXDR);
args->craa_objs_to_keep = ntohl(*p++);
- p = read_buf(xdr, 4);
- if (unlikely(p == NULL))
- return htonl(NFS4ERR_BADXDR);
- args->craa_type_mask = ntohl(*p);
+ status = decode_bitmap(xdr, bitmap);
+ if (unlikely(status))
+ return status;
+ args->craa_type_mask = bitmap[0];
return 0;
}
@@ -986,4 +987,5 @@ struct svc_version nfs4_callback_version4 = {
.vs_proc = nfs4_callback_procedures1,
.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
.vs_dispatch = NULL,
+ .vs_hidden = 1,
};
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b238d95ac48..ac289909814 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1468,12 +1468,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
res = NULL;
goto out;
/* This turned out not to be a regular file */
+ case -EISDIR:
case -ENOTDIR:
goto no_open;
case -ELOOP:
if (!(nd->intent.open.flags & O_NOFOLLOW))
goto no_open;
- /* case -EISDIR: */
/* case -EINVAL: */
default:
res = ERR_CAST(inode);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 91c01f0a4c3..eca56d4b39c 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -40,48 +40,8 @@
#define NFSDBG_FACILITY NFSDBG_FILE
-static int nfs_file_open(struct inode *, struct file *);
-static int nfs_file_release(struct inode *, struct file *);
-static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin);
-static int nfs_file_mmap(struct file *, struct vm_area_struct *);
-static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t count, unsigned int flags);
-static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
- struct file *filp, loff_t *ppos,
- size_t count, unsigned int flags);
-static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos);
-static int nfs_file_flush(struct file *, fl_owner_t id);
-static int nfs_file_fsync(struct file *, loff_t, loff_t, int datasync);
-static int nfs_check_flags(int flags);
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
-
static const struct vm_operations_struct nfs_file_vm_ops;
-const struct file_operations nfs_file_operations = {
- .llseek = nfs_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = nfs_file_read,
- .aio_write = nfs_file_write,
- .mmap = nfs_file_mmap,
- .open = nfs_file_open,
- .flush = nfs_file_flush,
- .release = nfs_file_release,
- .fsync = nfs_file_fsync,
- .lock = nfs_lock,
- .flock = nfs_flock,
- .splice_read = nfs_file_splice_read,
- .splice_write = nfs_file_splice_write,
- .check_flags = nfs_check_flags,
- .setlease = nfs_setlease,
-};
-
const struct inode_operations nfs_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
@@ -137,11 +97,9 @@ nfs_file_open(struct inode *inode, struct file *filp)
static int
nfs_file_release(struct inode *inode, struct file *filp)
{
- struct dentry *dentry = filp->f_path.dentry;
-
dprintk("NFS: release(%s/%s)\n",
- dentry->d_parent->d_name.name,
- dentry->d_name.name);
+ filp->f_path.dentry->d_parent->d_name.name,
+ filp->f_path.dentry->d_name.name);
nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
return nfs_release(inode, filp);
@@ -228,14 +186,13 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
struct dentry * dentry = iocb->ki_filp->f_path.dentry;
struct inode * inode = dentry->d_inode;
ssize_t result;
- size_t count = iov_length(iov, nr_segs);
if (iocb->ki_filp->f_flags & O_DIRECT)
return nfs_file_direct_read(iocb, iov, nr_segs, pos);
dprintk("NFS: read(%s/%s, %lu@%lu)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
- (unsigned long) count, (unsigned long) pos);
+ (unsigned long) iov_length(iov, nr_segs), (unsigned long) pos);
result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
if (!result) {
@@ -889,3 +846,54 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
file->f_path.dentry->d_name.name, arg);
return -EINVAL;
}
+
+const struct file_operations nfs_file_operations = {
+ .llseek = nfs_file_llseek,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = nfs_file_read,
+ .aio_write = nfs_file_write,
+ .mmap = nfs_file_mmap,
+ .open = nfs_file_open,
+ .flush = nfs_file_flush,
+ .release = nfs_file_release,
+ .fsync = nfs_file_fsync,
+ .lock = nfs_lock,
+ .flock = nfs_flock,
+ .splice_read = nfs_file_splice_read,
+ .splice_write = nfs_file_splice_write,
+ .check_flags = nfs_check_flags,
+ .setlease = nfs_setlease,
+};
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+ /*
+ * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+ * this point, then something is very wrong
+ */
+ dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+ return -ENOTDIR;
+}
+
+const struct file_operations nfs4_file_operations = {
+ .llseek = nfs_file_llseek,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = nfs_file_read,
+ .aio_write = nfs_file_write,
+ .mmap = nfs_file_mmap,
+ .open = nfs4_file_open,
+ .flush = nfs_file_flush,
+ .release = nfs_file_release,
+ .fsync = nfs_file_fsync,
+ .lock = nfs_lock,
+ .flock = nfs_flock,
+ .splice_read = nfs_file_splice_read,
+ .splice_write = nfs_file_splice_write,
+ .check_flags = nfs_check_flags,
+ .setlease = nfs_setlease,
+};
+#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c07a55aec83..50a15fa8cf9 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
*/
inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
if (S_ISREG(inode->i_mode)) {
- inode->i_fop = &nfs_file_operations;
+ inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
inode->i_data.a_ops = &nfs_file_aops;
inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
} else if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index c1a1bd8ddf1..3f4d95751d5 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -299,6 +299,8 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
struct list_head *head);
+extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+ struct inode *inode);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_readdata_release(struct nfs_read_data *rdata);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 85f1690ca08..d4bc9ed9174 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.dentry_ops = &nfs_dentry_operations,
.dir_inode_ops = &nfs3_dir_inode_operations,
.file_inode_ops = &nfs3_file_inode_operations,
+ .file_ops = &nfs_file_operations,
.getroot = nfs3_proc_get_root,
.getattr = nfs3_proc_getattr,
.setattr = nfs3_proc_setattr,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 09119418402..a62d36b9a99 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -31,6 +31,7 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
+#include <linux/module.h>
#include "internal.h"
#include "nfs4filelayout.h"
@@ -449,9 +450,8 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
fl->dsaddr = dsaddr;
- if (fl->first_stripe_index < 0 ||
- fl->first_stripe_index >= dsaddr->stripe_count) {
- dprintk("%s Bad first_stripe_index %d\n",
+ if (fl->first_stripe_index >= dsaddr->stripe_count) {
+ dprintk("%s Bad first_stripe_index %u\n",
__func__, fl->first_stripe_index);
goto out_put;
}
@@ -552,7 +552,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
/* Note that a zero value for num_fh is legal for STRIPE_SPARSE.
* Futher checking is done in filelayout_check_layout */
- if (fl->num_fh < 0 || fl->num_fh >
+ if (fl->num_fh >
max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT))
goto out_err;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d2ae413c986..be2bbac1381 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2464,8 +2464,7 @@ static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qst
case -NFS4ERR_BADNAME:
return -ENOENT;
case -NFS4ERR_MOVED:
- err = nfs4_get_referral(dir, name, fattr, fhandle);
- break;
+ return nfs4_get_referral(dir, name, fattr, fhandle);
case -NFS4ERR_WRONGSEC:
nfs_fixup_secinfo_attributes(fattr, fhandle);
}
@@ -5950,6 +5949,7 @@ static void nfs4_layoutcommit_release(void *calldata)
{
struct nfs4_layoutcommit_data *data = calldata;
struct pnfs_layout_segment *lseg, *tmp;
+ unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
pnfs_cleanup_layoutcommit(data);
/* Matched by references in pnfs_set_layoutcommit */
@@ -5959,6 +5959,11 @@ static void nfs4_layoutcommit_release(void *calldata)
&lseg->pls_flags))
put_lseg(lseg);
}
+
+ clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+
put_rpccred(data->cred);
kfree(data);
}
@@ -6247,6 +6252,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.dentry_ops = &nfs4_dentry_operations,
.dir_inode_ops = &nfs4_dir_inode_operations,
.file_inode_ops = &nfs4_file_inode_operations,
+ .file_ops = &nfs4_file_operations,
.getroot = nfs4_proc_get_root,
.getattr = nfs4_proc_getattr,
.setattr = nfs4_proc_setattr,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1dce12f41a4..e6161b213ed 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -6602,8 +6602,6 @@ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp,
if (status)
goto out;
status = decode_secinfo(xdr, res);
- if (status)
- goto out;
out:
return status;
}
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index d0cda12fddc..c807ab93140 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -38,21 +38,15 @@
*/
#include <linux/module.h>
-#include <scsi/osd_initiator.h>
+#include <scsi/osd_ore.h>
#include "objlayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-#define _LLU(x) ((unsigned long long)x)
-
-enum { BIO_MAX_PAGES_KMALLOC =
- (PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),
-};
-
struct objio_dev_ent {
struct nfs4_deviceid_node id_node;
- struct osd_dev *od;
+ struct ore_dev od;
};
static void
@@ -60,8 +54,8 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d)
{
struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
- dprintk("%s: free od=%p\n", __func__, de->od);
- osduld_put_device(de->od);
+ dprintk("%s: free od=%p\n", __func__, de->od.od);
+ osduld_put_device(de->od.od);
kfree(de);
}
@@ -98,12 +92,12 @@ _dev_list_add(const struct nfs_server *nfss,
nfss->pnfs_curr_ld,
nfss->nfs_client,
d_id);
- de->od = od;
+ de->od.od = od;
d = nfs4_insert_deviceid_node(&de->id_node);
n = container_of(d, struct objio_dev_ent, id_node);
if (n != de) {
- dprintk("%s: Race with other n->od=%p\n", __func__, n->od);
+ dprintk("%s: Race with other n->od=%p\n", __func__, n->od.od);
objio_free_deviceid_node(&de->id_node);
de = n;
}
@@ -111,28 +105,11 @@ _dev_list_add(const struct nfs_server *nfss,
return de;
}
-struct caps_buffers {
- u8 caps_key[OSD_CRYPTO_KEYID_SIZE];
- u8 creds[OSD_CAP_LEN];
-};
-
struct objio_segment {
struct pnfs_layout_segment lseg;
- struct pnfs_osd_object_cred *comps;
-
- unsigned mirrors_p1;
- unsigned stripe_unit;
- unsigned group_width; /* Data stripe_units without integrity comps */
- u64 group_depth;
- unsigned group_count;
-
- unsigned max_io_size;
-
- unsigned comps_index;
- unsigned num_comps;
- /* variable length */
- struct objio_dev_ent *ods[];
+ struct ore_layout layout;
+ struct ore_components oc;
};
static inline struct objio_segment *
@@ -141,59 +118,44 @@ OBJIO_LSEG(struct pnfs_layout_segment *lseg)
return container_of(lseg, struct objio_segment, lseg);
}
-struct objio_state;
-typedef ssize_t (*objio_done_fn)(struct objio_state *ios);
-
struct objio_state {
/* Generic layer */
- struct objlayout_io_state ol_state;
-
- struct objio_segment *layout;
-
- struct kref kref;
- objio_done_fn done;
- void *private;
-
- unsigned long length;
- unsigned numdevs; /* Actually used devs in this IO */
- /* A per-device variable array of size numdevs */
- struct _objio_per_comp {
- struct bio *bio;
- struct osd_request *or;
- unsigned long length;
- u64 offset;
- unsigned dev;
- } per_dev[];
+ struct objlayout_io_res oir;
+
+ bool sync;
+ /*FIXME: Support for extra_bytes at ore_get_rw_state() */
+ struct ore_io_state *ios;
};
/* Send and wait for a get_device_info of devices in the layout,
then look them up with the osd_initiator library */
-static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay,
- struct objio_segment *objio_seg, unsigned comp,
- gfp_t gfp_flags)
+static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
+ struct objio_segment *objio_seg, unsigned c, struct nfs4_deviceid *d_id,
+ gfp_t gfp_flags)
{
struct pnfs_osd_deviceaddr *deviceaddr;
- struct nfs4_deviceid *d_id;
struct objio_dev_ent *ode;
struct osd_dev *od;
struct osd_dev_info odi;
int err;
- d_id = &objio_seg->comps[comp].oc_object_id.oid_device_id;
-
ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
- if (ode)
- return ode;
+ if (ode) {
+ objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
+ return 0;
+ }
err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
if (unlikely(err)) {
dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
__func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
- return ERR_PTR(err);
+ return err;
}
odi.systemid_len = deviceaddr->oda_systemid.len;
if (odi.systemid_len > sizeof(odi.systemid)) {
+ dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
+ __func__, sizeof(odi.systemid));
err = -EINVAL;
goto out;
} else if (odi.systemid_len)
@@ -218,96 +180,53 @@ static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay,
ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
gfp_flags);
-
+ objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
+ dprintk("Adding new dev_id(%llx:%llx)\n",
+ _DEVID_LO(d_id), _DEVID_HI(d_id));
out:
- dprintk("%s: return=%d\n", __func__, err);
objlayout_put_deviceinfo(deviceaddr);
- return err ? ERR_PTR(err) : ode;
+ return err;
}
-static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
- struct objio_segment *objio_seg,
- gfp_t gfp_flags)
+static void copy_single_comp(struct ore_components *oc, unsigned c,
+ struct pnfs_osd_object_cred *src_comp)
{
- unsigned i;
- int err;
+ struct ore_comp *ocomp = &oc->comps[c];
- /* lookup all devices */
- for (i = 0; i < objio_seg->num_comps; i++) {
- struct objio_dev_ent *ode;
+ WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
+ WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
- ode = _device_lookup(pnfslay, objio_seg, i, gfp_flags);
- if (unlikely(IS_ERR(ode))) {
- err = PTR_ERR(ode);
- goto out;
- }
- objio_seg->ods[i] = ode;
- }
- err = 0;
+ ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
+ ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
-out:
- dprintk("%s: return=%d\n", __func__, err);
- return err;
+ memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
}
-static int _verify_data_map(struct pnfs_osd_layout *layout)
+int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
+ struct objio_segment **pseg)
{
- struct pnfs_osd_data_map *data_map = &layout->olo_map;
- u64 stripe_length;
- u32 group_width;
-
-/* FIXME: Only raid0 for now. if not go through MDS */
- if (data_map->odm_raid_algorithm != PNFS_OSD_RAID_0) {
- printk(KERN_ERR "Only RAID_0 for now\n");
- return -ENOTSUPP;
- }
- if (0 != (data_map->odm_num_comps % (data_map->odm_mirror_cnt + 1))) {
- printk(KERN_ERR "Data Map wrong, num_comps=%u mirrors=%u\n",
- data_map->odm_num_comps, data_map->odm_mirror_cnt);
- return -EINVAL;
- }
+ struct __alloc_objio_segment {
+ struct objio_segment olseg;
+ struct ore_dev *ods[numdevs];
+ struct ore_comp comps[numdevs];
+ } *aolseg;
- if (data_map->odm_group_width)
- group_width = data_map->odm_group_width;
- else
- group_width = data_map->odm_num_comps /
- (data_map->odm_mirror_cnt + 1);
-
- stripe_length = (u64)data_map->odm_stripe_unit * group_width;
- if (stripe_length >= (1ULL << 32)) {
- printk(KERN_ERR "Total Stripe length(0x%llx)"
- " >= 32bit is not supported\n", _LLU(stripe_length));
- return -ENOTSUPP;
+ aolseg = kzalloc(sizeof(*aolseg), gfp_flags);
+ if (unlikely(!aolseg)) {
+ dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__,
+ numdevs, sizeof(*aolseg));
+ return -ENOMEM;
}
- if (0 != (data_map->odm_stripe_unit & ~PAGE_MASK)) {
- printk(KERN_ERR "Stripe Unit(0x%llx)"
- " must be Multples of PAGE_SIZE(0x%lx)\n",
- _LLU(data_map->odm_stripe_unit), PAGE_SIZE);
- return -ENOTSUPP;
- }
+ aolseg->olseg.oc.numdevs = numdevs;
+ aolseg->olseg.oc.single_comp = EC_MULTPLE_COMPS;
+ aolseg->olseg.oc.comps = aolseg->comps;
+ aolseg->olseg.oc.ods = aolseg->ods;
+ *pseg = &aolseg->olseg;
return 0;
}
-static void copy_single_comp(struct pnfs_osd_object_cred *cur_comp,
- struct pnfs_osd_object_cred *src_comp,
- struct caps_buffers *caps_p)
-{
- WARN_ON(src_comp->oc_cap_key.cred_len > sizeof(caps_p->caps_key));
- WARN_ON(src_comp->oc_cap.cred_len > sizeof(caps_p->creds));
-
- *cur_comp = *src_comp;
-
- memcpy(caps_p->caps_key, src_comp->oc_cap_key.cred,
- sizeof(caps_p->caps_key));
- cur_comp->oc_cap_key.cred = caps_p->caps_key;
-
- memcpy(caps_p->creds, src_comp->oc_cap.cred,
- sizeof(caps_p->creds));
- cur_comp->oc_cap.cred = caps_p->creds;
-}
-
int objio_alloc_lseg(struct pnfs_layout_segment **outp,
struct pnfs_layout_hdr *pnfslay,
struct pnfs_layout_range *range,
@@ -317,59 +236,43 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
struct objio_segment *objio_seg;
struct pnfs_osd_xdr_decode_layout_iter iter;
struct pnfs_osd_layout layout;
- struct pnfs_osd_object_cred *cur_comp, src_comp;
- struct caps_buffers *caps_p;
+ struct pnfs_osd_object_cred src_comp;
+ unsigned cur_comp;
int err;
err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
if (unlikely(err))
return err;
- err = _verify_data_map(&layout);
+ err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
if (unlikely(err))
return err;
- objio_seg = kzalloc(sizeof(*objio_seg) +
- sizeof(objio_seg->ods[0]) * layout.olo_num_comps +
- sizeof(*objio_seg->comps) * layout.olo_num_comps +
- sizeof(struct caps_buffers) * layout.olo_num_comps,
- gfp_flags);
- if (!objio_seg)
- return -ENOMEM;
+ objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
+ objio_seg->layout.group_width = layout.olo_map.odm_group_width;
+ objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
+ objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
+ objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
- objio_seg->comps = (void *)(objio_seg->ods + layout.olo_num_comps);
- cur_comp = objio_seg->comps;
- caps_p = (void *)(cur_comp + layout.olo_num_comps);
- while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err))
- copy_single_comp(cur_comp++, &src_comp, caps_p++);
+ err = ore_verify_layout(layout.olo_map.odm_num_comps,
+ &objio_seg->layout);
if (unlikely(err))
goto err;
- objio_seg->num_comps = layout.olo_num_comps;
- objio_seg->comps_index = layout.olo_comps_index;
- err = objio_devices_lookup(pnfslay, objio_seg, gfp_flags);
- if (err)
- goto err;
-
- objio_seg->mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
- objio_seg->stripe_unit = layout.olo_map.odm_stripe_unit;
- if (layout.olo_map.odm_group_width) {
- objio_seg->group_width = layout.olo_map.odm_group_width;
- objio_seg->group_depth = layout.olo_map.odm_group_depth;
- objio_seg->group_count = layout.olo_map.odm_num_comps /
- objio_seg->mirrors_p1 /
- objio_seg->group_width;
- } else {
- objio_seg->group_width = layout.olo_map.odm_num_comps /
- objio_seg->mirrors_p1;
- objio_seg->group_depth = -1;
- objio_seg->group_count = 1;
+ objio_seg->oc.first_dev = layout.olo_comps_index;
+ cur_comp = 0;
+ while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
+ copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
+ err = objio_devices_lookup(pnfslay, objio_seg, cur_comp,
+ &src_comp.oc_object_id.oid_device_id,
+ gfp_flags);
+ if (err)
+ goto err;
+ ++cur_comp;
}
-
- /* Cache this calculation it will hit for every page */
- objio_seg->max_io_size = (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE -
- objio_seg->stripe_unit) *
- objio_seg->group_width;
+ /* pnfs_osd_xdr_decode_layout_comp returns false on error */
+ if (unlikely(err))
+ goto err;
*outp = &objio_seg->lseg;
return 0;
@@ -386,43 +289,63 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
int i;
struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
- for (i = 0; i < objio_seg->num_comps; i++) {
- if (!objio_seg->ods[i])
+ for (i = 0; i < objio_seg->oc.numdevs; i++) {
+ struct ore_dev *od = objio_seg->oc.ods[i];
+ struct objio_dev_ent *ode;
+
+ if (!od)
break;
- nfs4_put_deviceid_node(&objio_seg->ods[i]->id_node);
+ ode = container_of(od, typeof(*ode), od);
+ nfs4_put_deviceid_node(&ode->id_node);
}
kfree(objio_seg);
}
-int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
- struct objlayout_io_state **outp,
- gfp_t gfp_flags)
+static int
+objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading,
+ struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
+ loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
+ struct objio_state **outp)
{
struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
- struct objio_state *ios;
- const unsigned first_size = sizeof(*ios) +
- objio_seg->num_comps * sizeof(ios->per_dev[0]);
- const unsigned sec_size = objio_seg->num_comps *
- sizeof(ios->ol_state.ioerrs[0]);
-
- ios = kzalloc(first_size + sec_size, gfp_flags);
- if (unlikely(!ios))
+ struct ore_io_state *ios;
+ int ret;
+ struct __alloc_objio_state {
+ struct objio_state objios;
+ struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
+ } *aos;
+
+ aos = kzalloc(sizeof(*aos), gfp_flags);
+ if (unlikely(!aos))
return -ENOMEM;
- ios->layout = objio_seg;
- ios->ol_state.ioerrs = ((void *)ios) + first_size;
- ios->ol_state.num_comps = objio_seg->num_comps;
+ objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
+ aos->ioerrs, rpcdata, pnfs_layout_type);
- *outp = &ios->ol_state;
+ ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading,
+ offset, count, &ios);
+ if (unlikely(ret)) {
+ kfree(aos);
+ return ret;
+ }
+
+ ios->pages = pages;
+ ios->pgbase = pgbase;
+ ios->private = aos;
+ BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
+
+ aos->objios.sync = 0;
+ aos->objios.ios = ios;
+ *outp = &aos->objios;
return 0;
}
-void objio_free_io_state(struct objlayout_io_state *ol_state)
+void objio_free_result(struct objlayout_io_res *oir)
{
- struct objio_state *ios = container_of(ol_state, struct objio_state,
- ol_state);
+ struct objio_state *objios = container_of(oir, struct objio_state, oir);
- kfree(ios);
+ ore_put_io_state(objios->ios);
+ kfree(objios);
}
enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
@@ -455,539 +378,152 @@ enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
}
}
-static void _clear_bio(struct bio *bio)
+static void __on_dev_error(struct ore_io_state *ios,
+ struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
+ u64 dev_offset, u64 dev_len)
{
- struct bio_vec *bv;
- unsigned i;
-
- __bio_for_each_segment(bv, bio, i, 0) {
- unsigned this_count = bv->bv_len;
-
- if (likely(PAGE_SIZE == this_count))
- clear_highpage(bv->bv_page);
- else
- zero_user(bv->bv_page, bv->bv_offset, this_count);
- }
-}
-
-static int _io_check(struct objio_state *ios, bool is_write)
-{
- enum osd_err_priority oep = OSD_ERR_PRI_NO_ERROR;
- int lin_ret = 0;
- int i;
-
- for (i = 0; i < ios->numdevs; i++) {
- struct osd_sense_info osi;
- struct osd_request *or = ios->per_dev[i].or;
- int ret;
-
- if (!or)
- continue;
+ struct objio_state *objios = ios->private;
+ struct pnfs_osd_objid pooid;
+ struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
+ /* FIXME: what to do with more-then-one-group layouts. We need to
+ * translate from ore_io_state index to oc->comps index
+ */
+ unsigned comp = dev_index;
- ret = osd_req_decode_sense(or, &osi);
- if (likely(!ret))
- continue;
+ pooid.oid_device_id = ode->id_node.deviceid;
+ pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
+ pooid.oid_object_id = ios->oc->comps[comp].obj.id;
- if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) {
- /* start read offset passed endof file */
- BUG_ON(is_write);
- _clear_bio(ios->per_dev[i].bio);
- dprintk("%s: start read offset passed end of file "
- "offset=0x%llx, length=0x%lx\n", __func__,
- _LLU(ios->per_dev[i].offset),
- ios->per_dev[i].length);
-
- continue; /* we recovered */
- }
- objlayout_io_set_result(&ios->ol_state, i,
- &ios->layout->comps[i].oc_object_id,
- osd_pri_2_pnfs_err(osi.osd_err_pri),
- ios->per_dev[i].offset,
- ios->per_dev[i].length,
- is_write);
-
- if (osi.osd_err_pri >= oep) {
- oep = osi.osd_err_pri;
- lin_ret = ret;
- }
- }
-
- return lin_ret;
-}
-
-/*
- * Common IO state helpers.
- */
-static void _io_free(struct objio_state *ios)
-{
- unsigned i;
-
- for (i = 0; i < ios->numdevs; i++) {
- struct _objio_per_comp *per_dev = &ios->per_dev[i];
-
- if (per_dev->or) {
- osd_end_request(per_dev->or);
- per_dev->or = NULL;
- }
-
- if (per_dev->bio) {
- bio_put(per_dev->bio);
- per_dev->bio = NULL;
- }
- }
-}
-
-struct osd_dev *_io_od(struct objio_state *ios, unsigned dev)
-{
- unsigned min_dev = ios->layout->comps_index;
- unsigned max_dev = min_dev + ios->layout->num_comps;
-
- BUG_ON(dev < min_dev || max_dev <= dev);
- return ios->layout->ods[dev - min_dev]->od;
-}
-
-struct _striping_info {
- u64 obj_offset;
- u64 group_length;
- unsigned dev;
- unsigned unit_off;
-};
-
-static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
- struct _striping_info *si)
-{
- u32 stripe_unit = ios->layout->stripe_unit;
- u32 group_width = ios->layout->group_width;
- u64 group_depth = ios->layout->group_depth;
- u32 U = stripe_unit * group_width;
-
- u64 T = U * group_depth;
- u64 S = T * ios->layout->group_count;
- u64 M = div64_u64(file_offset, S);
-
- /*
- G = (L - (M * S)) / T
- H = (L - (M * S)) % T
- */
- u64 LmodU = file_offset - M * S;
- u32 G = div64_u64(LmodU, T);
- u64 H = LmodU - G * T;
-
- u32 N = div_u64(H, U);
-
- div_u64_rem(file_offset, stripe_unit, &si->unit_off);
- si->obj_offset = si->unit_off + (N * stripe_unit) +
- (M * group_depth * stripe_unit);
-
- /* "H - (N * U)" is just "H % U" so it's bound to u32 */
- si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width;
- si->dev *= ios->layout->mirrors_p1;
-
- si->group_length = T - H;
-}
-
-static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg,
- unsigned pgbase, struct _objio_per_comp *per_dev, int len,
- gfp_t gfp_flags)
-{
- unsigned pg = *cur_pg;
- int cur_len = len;
- struct request_queue *q =
- osd_request_queue(_io_od(ios, per_dev->dev));
-
- if (per_dev->bio == NULL) {
- unsigned pages_in_stripe = ios->layout->group_width *
- (ios->layout->stripe_unit / PAGE_SIZE);
- unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
- ios->layout->group_width;
-
- if (BIO_MAX_PAGES_KMALLOC < bio_size)
- bio_size = BIO_MAX_PAGES_KMALLOC;
-
- per_dev->bio = bio_kmalloc(gfp_flags, bio_size);
- if (unlikely(!per_dev->bio)) {
- dprintk("Faild to allocate BIO size=%u\n", bio_size);
- return -ENOMEM;
- }
- }
-
- while (cur_len > 0) {
- unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
- unsigned added_len;
-
- BUG_ON(ios->ol_state.nr_pages <= pg);
- cur_len -= pglen;
-
- added_len = bio_add_pc_page(q, per_dev->bio,
- ios->ol_state.pages[pg], pglen, pgbase);
- if (unlikely(pglen != added_len))
- return -ENOMEM;
- pgbase = 0;
- ++pg;
- }
- BUG_ON(cur_len);
-
- per_dev->length += len;
- *cur_pg = pg;
- return 0;
-}
-
-static int _prepare_one_group(struct objio_state *ios, u64 length,
- struct _striping_info *si, unsigned *last_pg,
- gfp_t gfp_flags)
-{
- unsigned stripe_unit = ios->layout->stripe_unit;
- unsigned mirrors_p1 = ios->layout->mirrors_p1;
- unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
- unsigned dev = si->dev;
- unsigned first_dev = dev - (dev % devs_in_group);
- unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0;
- unsigned cur_pg = *last_pg;
- int ret = 0;
-
- while (length) {
- struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev];
- unsigned cur_len, page_off = 0;
-
- if (!per_dev->length) {
- per_dev->dev = dev;
- if (dev < si->dev) {
- per_dev->offset = si->obj_offset + stripe_unit -
- si->unit_off;
- cur_len = stripe_unit;
- } else if (dev == si->dev) {
- per_dev->offset = si->obj_offset;
- cur_len = stripe_unit - si->unit_off;
- page_off = si->unit_off & ~PAGE_MASK;
- BUG_ON(page_off &&
- (page_off != ios->ol_state.pgbase));
- } else { /* dev > si->dev */
- per_dev->offset = si->obj_offset - si->unit_off;
- cur_len = stripe_unit;
- }
-
- if (max_comp < dev - first_dev)
- max_comp = dev - first_dev;
- } else {
- cur_len = stripe_unit;
- }
- if (cur_len >= length)
- cur_len = length;
-
- ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev,
- cur_len, gfp_flags);
- if (unlikely(ret))
- goto out;
-
- dev += mirrors_p1;
- dev = (dev % devs_in_group) + first_dev;
-
- length -= cur_len;
- ios->length += cur_len;
- }
-out:
- ios->numdevs = max_comp + mirrors_p1;
- *last_pg = cur_pg;
- return ret;
-}
-
-static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
-{
- u64 length = ios->ol_state.count;
- u64 offset = ios->ol_state.offset;
- struct _striping_info si;
- unsigned last_pg = 0;
- int ret = 0;
-
- while (length) {
- _calc_stripe_info(ios, offset, &si);
-
- if (length < si.group_length)
- si.group_length = length;
-
- ret = _prepare_one_group(ios, si.group_length, &si, &last_pg, gfp_flags);
- if (unlikely(ret))
- goto out;
-
- offset += si.group_length;
- length -= si.group_length;
- }
-
-out:
- if (!ios->length)
- return ret;
-
- return 0;
-}
-
-static ssize_t _sync_done(struct objio_state *ios)
-{
- struct completion *waiting = ios->private;
-
- complete(waiting);
- return 0;
-}
-
-static void _last_io(struct kref *kref)
-{
- struct objio_state *ios = container_of(kref, struct objio_state, kref);
-
- ios->done(ios);
-}
-
-static void _done_io(struct osd_request *or, void *p)
-{
- struct objio_state *ios = p;
-
- kref_put(&ios->kref, _last_io);
-}
-
-static ssize_t _io_exec(struct objio_state *ios)
-{
- DECLARE_COMPLETION_ONSTACK(wait);
- ssize_t status = 0; /* sync status */
- unsigned i;
- objio_done_fn saved_done_fn = ios->done;
- bool sync = ios->ol_state.sync;
-
- if (sync) {
- ios->done = _sync_done;
- ios->private = &wait;
- }
-
- kref_init(&ios->kref);
-
- for (i = 0; i < ios->numdevs; i++) {
- struct osd_request *or = ios->per_dev[i].or;
-
- if (!or)
- continue;
-
- kref_get(&ios->kref);
- osd_execute_request_async(or, _done_io, ios);
- }
-
- kref_put(&ios->kref, _last_io);
-
- if (sync) {
- wait_for_completion(&wait);
- status = saved_done_fn(ios);
- }
-
- return status;
+ objlayout_io_set_result(&objios->oir, comp,
+ &pooid, osd_pri_2_pnfs_err(oep),
+ dev_offset, dev_len, !ios->reading);
}
/*
* read
*/
-static ssize_t _read_done(struct objio_state *ios)
+static void _read_done(struct ore_io_state *ios, void *private)
{
+ struct objio_state *objios = private;
ssize_t status;
- int ret = _io_check(ios, false);
+ int ret = ore_check_io(ios, &__on_dev_error);
- _io_free(ios);
+ /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
if (likely(!ret))
status = ios->length;
else
status = ret;
- objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync);
- return status;
+ objlayout_read_done(&objios->oir, status, objios->sync);
}
-static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
+int objio_read_pagelist(struct nfs_read_data *rdata)
{
- struct osd_request *or = NULL;
- struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
- unsigned dev = per_dev->dev;
- struct pnfs_osd_object_cred *cred =
- &ios->layout->comps[cur_comp];
- struct osd_obj_id obj = {
- .partition = cred->oc_object_id.oid_partition_id,
- .id = cred->oc_object_id.oid_object_id,
- };
+ struct objio_state *objios;
int ret;
- or = osd_start_request(_io_od(ios, dev), GFP_KERNEL);
- if (unlikely(!or)) {
- ret = -ENOMEM;
- goto err;
- }
- per_dev->or = or;
-
- osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length);
-
- ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
- if (ret) {
- dprintk("%s: Faild to osd_finalize_request() => %d\n",
- __func__, ret);
- goto err;
- }
-
- dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
- __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
- per_dev->length);
-
-err:
- return ret;
-}
-
-static ssize_t _read_exec(struct objio_state *ios)
-{
- unsigned i;
- int ret;
-
- for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
- if (!ios->per_dev[i].length)
- continue;
- ret = _read_mirrors(ios, i);
- if (unlikely(ret))
- goto err;
- }
-
- ios->done = _read_done;
- return _io_exec(ios); /* In sync mode exec returns the io status */
-
-err:
- _io_free(ios);
- return ret;
-}
-
-ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state)
-{
- struct objio_state *ios = container_of(ol_state, struct objio_state,
- ol_state);
- int ret;
-
- ret = _io_rw_pagelist(ios, GFP_KERNEL);
+ ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true,
+ rdata->lseg, rdata->args.pages, rdata->args.pgbase,
+ rdata->args.offset, rdata->args.count, rdata,
+ GFP_KERNEL, &objios);
if (unlikely(ret))
return ret;
- return _read_exec(ios);
+ objios->ios->done = _read_done;
+ dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
+ rdata->args.offset, rdata->args.count);
+ return ore_read(objios->ios);
}
/*
* write
*/
-static ssize_t _write_done(struct objio_state *ios)
+static void _write_done(struct ore_io_state *ios, void *private)
{
+ struct objio_state *objios = private;
ssize_t status;
- int ret = _io_check(ios, true);
+ int ret = ore_check_io(ios, &__on_dev_error);
- _io_free(ios);
+ /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
if (likely(!ret)) {
/* FIXME: should be based on the OSD's persistence model
* See OSD2r05 Section 4.13 Data persistence model */
- ios->ol_state.committed = NFS_FILE_SYNC;
+ objios->oir.committed = NFS_FILE_SYNC;
status = ios->length;
} else {
status = ret;
}
- objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync);
- return status;
+ objlayout_write_done(&objios->oir, status, objios->sync);
}
-static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
+static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
{
- struct _objio_per_comp *master_dev = &ios->per_dev[cur_comp];
- unsigned dev = ios->per_dev[cur_comp].dev;
- unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
- int ret;
-
- for (; cur_comp < last_comp; ++cur_comp, ++dev) {
- struct osd_request *or = NULL;
- struct pnfs_osd_object_cred *cred =
- &ios->layout->comps[cur_comp];
- struct osd_obj_id obj = {
- .partition = cred->oc_object_id.oid_partition_id,
- .id = cred->oc_object_id.oid_object_id,
- };
- struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
- struct bio *bio;
-
- or = osd_start_request(_io_od(ios, dev), GFP_NOFS);
- if (unlikely(!or)) {
- ret = -ENOMEM;
- goto err;
- }
- per_dev->or = or;
-
- if (per_dev != master_dev) {
- bio = bio_kmalloc(GFP_NOFS,
- master_dev->bio->bi_max_vecs);
- if (unlikely(!bio)) {
- dprintk("Faild to allocate BIO size=%u\n",
- master_dev->bio->bi_max_vecs);
- ret = -ENOMEM;
- goto err;
- }
-
- __bio_clone(bio, master_dev->bio);
- bio->bi_bdev = NULL;
- bio->bi_next = NULL;
- per_dev->bio = bio;
- per_dev->dev = dev;
- per_dev->length = master_dev->length;
- per_dev->offset = master_dev->offset;
- } else {
- bio = master_dev->bio;
- bio->bi_rw |= REQ_WRITE;
- }
-
- osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length);
+ struct objio_state *objios = priv;
+ struct nfs_write_data *wdata = objios->oir.rpcdata;
+ pgoff_t index = offset / PAGE_SIZE;
+ struct page *page = find_get_page(wdata->inode->i_mapping, index);
- ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
- if (ret) {
- dprintk("%s: Faild to osd_finalize_request() => %d\n",
- __func__, ret);
- goto err;
+ if (!page) {
+ page = find_or_create_page(wdata->inode->i_mapping,
+ index, GFP_NOFS);
+ if (unlikely(!page)) {
+ dprintk("%s: grab_cache_page Failed index=0x%lx\n",
+ __func__, index);
+ return NULL;
}
-
- dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
- __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
- per_dev->length);
+ unlock_page(page);
}
+ if (PageDirty(page) || PageWriteback(page))
+ *uptodate = true;
+ else
+ *uptodate = PageUptodate(page);
+ dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
+ return page;
+}
-err:
- return ret;
+static void __r4w_put_page(void *priv, struct page *page)
+{
+ dprintk("%s: index=0x%lx\n", __func__, page->index);
+ page_cache_release(page);
+ return;
}
-static ssize_t _write_exec(struct objio_state *ios)
+static const struct _ore_r4w_op _r4w_op = {
+ .get_page = &__r4w_get_page,
+ .put_page = &__r4w_put_page,
+};
+
+int objio_write_pagelist(struct nfs_write_data *wdata, int how)
{
- unsigned i;
+ struct objio_state *objios;
int ret;
- for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
- if (!ios->per_dev[i].length)
- continue;
- ret = _write_mirrors(ios, i);
- if (unlikely(ret))
- goto err;
- }
-
- ios->done = _write_done;
- return _io_exec(ios); /* In sync mode exec returns the io->status */
+ ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false,
+ wdata->lseg, wdata->args.pages, wdata->args.pgbase,
+ wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
+ &objios);
+ if (unlikely(ret))
+ return ret;
-err:
- _io_free(ios);
- return ret;
-}
+ objios->sync = 0 != (how & FLUSH_SYNC);
+ objios->ios->r4w = &_r4w_op;
-ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
-{
- struct objio_state *ios = container_of(ol_state, struct objio_state,
- ol_state);
- int ret;
+ if (!objios->sync)
+ objios->ios->done = _write_done;
- /* TODO: ios->stable = stable; */
- ret = _io_rw_pagelist(ios, GFP_NOFS);
+ dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
+ wdata->args.offset, wdata->args.count);
+ ret = ore_write(objios->ios);
if (unlikely(ret))
return ret;
- return _write_exec(ios);
+ if (objios->sync)
+ _write_done(objios->ios, objios);
+
+ return 0;
}
static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
@@ -997,7 +533,7 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
return false;
return pgio->pg_count + req->wb_bytes <=
- OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
+ OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
}
static const struct nfs_pageio_ops objio_pg_read_ops = {
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 1d06f8e2ade..72074e3a04f 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -156,77 +156,39 @@ last_byte_offset(u64 start, u64 len)
return end > start ? end - 1 : NFS4_MAX_UINT64;
}
-static struct objlayout_io_state *
-objlayout_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type,
- struct page **pages,
- unsigned pgbase,
- loff_t offset,
- size_t count,
- struct pnfs_layout_segment *lseg,
- void *rpcdata,
- gfp_t gfp_flags)
+void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
+ struct page ***p_pages, unsigned *p_pgbase,
+ u64 offset, unsigned long count)
{
- struct objlayout_io_state *state;
u64 lseg_end_offset;
- dprintk("%s: allocating io_state\n", __func__);
- if (objio_alloc_io_state(lseg, &state, gfp_flags))
- return NULL;
-
BUG_ON(offset < lseg->pls_range.offset);
lseg_end_offset = end_offset(lseg->pls_range.offset,
lseg->pls_range.length);
BUG_ON(offset >= lseg_end_offset);
- if (offset + count > lseg_end_offset) {
- count = lseg->pls_range.length -
- (offset - lseg->pls_range.offset);
- dprintk("%s: truncated count %Zd\n", __func__, count);
- }
+ WARN_ON(offset + count > lseg_end_offset);
- if (pgbase > PAGE_SIZE) {
- pages += pgbase >> PAGE_SHIFT;
- pgbase &= ~PAGE_MASK;
+ if (*p_pgbase > PAGE_SIZE) {
+ dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
+ *p_pages += *p_pgbase >> PAGE_SHIFT;
+ *p_pgbase &= ~PAGE_MASK;
}
-
- INIT_LIST_HEAD(&state->err_list);
- state->lseg = lseg;
- state->rpcdata = rpcdata;
- state->pages = pages;
- state->pgbase = pgbase;
- state->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT;
- state->offset = offset;
- state->count = count;
- state->sync = 0;
-
- return state;
-}
-
-static void
-objlayout_free_io_state(struct objlayout_io_state *state)
-{
- dprintk("%s: freeing io_state\n", __func__);
- if (unlikely(!state))
- return;
-
- objio_free_io_state(state);
}
/*
* I/O done common code
*/
static void
-objlayout_iodone(struct objlayout_io_state *state)
+objlayout_iodone(struct objlayout_io_res *oir)
{
- dprintk("%s: state %p status\n", __func__, state);
-
- if (likely(state->status >= 0)) {
- objlayout_free_io_state(state);
+ if (likely(oir->status >= 0)) {
+ objio_free_result(oir);
} else {
- struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+ struct objlayout *objlay = oir->objlay;
spin_lock(&objlay->lock);
objlay->delta_space_valid = OBJ_DSU_INVALID;
- list_add(&objlay->err_list, &state->err_list);
+ list_add(&objlay->err_list, &oir->err_list);
spin_unlock(&objlay->lock);
}
}
@@ -238,13 +200,13 @@ objlayout_iodone(struct objlayout_io_state *state)
* the error for later reporting at layout-return.
*/
void
-objlayout_io_set_result(struct objlayout_io_state *state, unsigned index,
+objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
struct pnfs_osd_objid *pooid, int osd_error,
u64 offset, u64 length, bool is_write)
{
- struct pnfs_osd_ioerr *ioerr = &state->ioerrs[index];
+ struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
- BUG_ON(index >= state->num_comps);
+ BUG_ON(index >= oir->num_comps);
if (osd_error) {
ioerr->oer_component = *pooid;
ioerr->oer_comp_offset = offset;
@@ -285,21 +247,18 @@ static void _rpc_read_complete(struct work_struct *work)
}
void
-objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
+objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
{
- int eof = state->eof;
- struct nfs_read_data *rdata;
+ struct nfs_read_data *rdata = oir->rpcdata;
- state->status = status;
- dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof);
- rdata = state->rpcdata;
- rdata->task.tk_status = status;
- if (status >= 0) {
+ oir->status = rdata->task.tk_status = status;
+ if (status >= 0)
rdata->res.count = status;
- rdata->res.eof = eof;
- }
- objlayout_iodone(state);
- /* must not use state after this point */
+ objlayout_iodone(oir);
+ /* must not use oir after this point */
+
+ dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
+ status, rdata->res.eof, sync);
if (sync)
pnfs_ld_read_done(rdata);
@@ -317,40 +276,36 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
{
loff_t offset = rdata->args.offset;
size_t count = rdata->args.count;
- struct objlayout_io_state *state;
- ssize_t status = 0;
+ int err;
loff_t eof;
- dprintk("%s: Begin inode %p offset %llu count %d\n",
- __func__, rdata->inode, offset, (int)count);
-
eof = i_size_read(rdata->inode);
if (unlikely(offset + count > eof)) {
if (offset >= eof) {
- status = 0;
+ err = 0;
rdata->res.count = 0;
rdata->res.eof = 1;
+ /*FIXME: do we need to call pnfs_ld_read_done() */
goto out;
}
count = eof - offset;
}
- state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout,
- rdata->args.pages, rdata->args.pgbase,
- offset, count,
- rdata->lseg, rdata,
- GFP_KERNEL);
- if (unlikely(!state)) {
- status = -ENOMEM;
- goto out;
- }
+ rdata->res.eof = (offset + count) >= eof;
+ _fix_verify_io_params(rdata->lseg, &rdata->args.pages,
+ &rdata->args.pgbase,
+ rdata->args.offset, rdata->args.count);
- state->eof = state->offset + state->count >= eof;
+ dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
+ __func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
- status = objio_read_pagelist(state);
+ err = objio_read_pagelist(rdata);
out:
- dprintk("%s: Return status %Zd\n", __func__, status);
- rdata->pnfs_error = status;
+ if (unlikely(err)) {
+ rdata->pnfs_error = err;
+ dprintk("%s: Returned Error %d\n", __func__, err);
+ return PNFS_NOT_ATTEMPTED;
+ }
return PNFS_ATTEMPTED;
}
@@ -371,26 +326,20 @@ static void _rpc_write_complete(struct work_struct *work)
}
void
-objlayout_write_done(struct objlayout_io_state *state, ssize_t status,
- bool sync)
+objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
{
- struct nfs_write_data *wdata;
+ struct nfs_write_data *wdata = oir->rpcdata;
- dprintk("%s: Begin\n", __func__);
- wdata = state->rpcdata;
- state->status = status;
- wdata->task.tk_status = status;
+ oir->status = wdata->task.tk_status = status;
if (status >= 0) {
wdata->res.count = status;
- wdata->verf.committed = state->committed;
- dprintk("%s: Return status %d committed %d\n",
- __func__, wdata->task.tk_status,
- wdata->verf.committed);
- } else
- dprintk("%s: Return status %d\n",
- __func__, wdata->task.tk_status);
- objlayout_iodone(state);
- /* must not use state after this point */
+ wdata->verf.committed = oir->committed;
+ }
+ objlayout_iodone(oir);
+ /* must not use oir after this point */
+
+ dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
+ status, wdata->verf.committed, sync);
if (sync)
pnfs_ld_write_done(wdata);
@@ -407,30 +356,18 @@ enum pnfs_try_status
objlayout_write_pagelist(struct nfs_write_data *wdata,
int how)
{
- struct objlayout_io_state *state;
- ssize_t status;
-
- dprintk("%s: Begin inode %p offset %llu count %u\n",
- __func__, wdata->inode, wdata->args.offset, wdata->args.count);
-
- state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout,
- wdata->args.pages,
- wdata->args.pgbase,
- wdata->args.offset,
- wdata->args.count,
- wdata->lseg, wdata,
- GFP_NOFS);
- if (unlikely(!state)) {
- status = -ENOMEM;
- goto out;
- }
+ int err;
- state->sync = how & FLUSH_SYNC;
+ _fix_verify_io_params(wdata->lseg, &wdata->args.pages,
+ &wdata->args.pgbase,
+ wdata->args.offset, wdata->args.count);
- status = objio_write_pagelist(state, how & FLUSH_STABLE);
- out:
- dprintk("%s: Return status %Zd\n", __func__, status);
- wdata->pnfs_error = status;
+ err = objio_write_pagelist(wdata, how);
+ if (unlikely(err)) {
+ wdata->pnfs_error = err;
+ dprintk("%s: Returned Error %d\n", __func__, err);
+ return PNFS_NOT_ATTEMPTED;
+ }
return PNFS_ATTEMPTED;
}
@@ -537,14 +474,14 @@ merge_ioerr(struct pnfs_osd_ioerr *dest_err,
static void
encode_accumulated_error(struct objlayout *objlay, __be32 *p)
{
- struct objlayout_io_state *state, *tmp;
+ struct objlayout_io_res *oir, *tmp;
struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
- list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+ list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
unsigned i;
- for (i = 0; i < state->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+ for (i = 0; i < oir->num_comps; i++) {
+ struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
if (!ioerr->oer_errno)
continue;
@@ -563,8 +500,8 @@ encode_accumulated_error(struct objlayout *objlay, __be32 *p)
merge_ioerr(&accumulated_err, ioerr);
}
- list_del(&state->err_list);
- objlayout_free_io_state(state);
+ list_del(&oir->err_list);
+ objio_free_result(oir);
}
pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
@@ -576,7 +513,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
const struct nfs4_layoutreturn_args *args)
{
struct objlayout *objlay = OBJLAYOUT(pnfslay);
- struct objlayout_io_state *state, *tmp;
+ struct objlayout_io_res *oir, *tmp;
__be32 *start;
dprintk("%s: Begin\n", __func__);
@@ -585,13 +522,13 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
spin_lock(&objlay->lock);
- list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+ list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
__be32 *last_xdr = NULL, *p;
unsigned i;
int res = 0;
- for (i = 0; i < state->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+ for (i = 0; i < oir->num_comps; i++) {
+ struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
if (!ioerr->oer_errno)
continue;
@@ -615,7 +552,7 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
}
last_xdr = p;
- pnfs_osd_xdr_encode_ioerr(p, &state->ioerrs[i]);
+ pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
}
/* TODO: use xdr_write_pages */
@@ -631,8 +568,8 @@ objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
encode_accumulated_error(objlay, last_xdr);
goto loop_done;
}
- list_del(&state->err_list);
- objlayout_free_io_state(state);
+ list_del(&oir->err_list);
+ objio_free_result(oir);
}
loop_done:
spin_unlock(&objlay->lock);
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index a8244c8e042..8ec34727ed2 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -74,19 +74,11 @@ OBJLAYOUT(struct pnfs_layout_hdr *lo)
* per-I/O operation state
* embedded in objects provider io_state data structure
*/
-struct objlayout_io_state {
- struct pnfs_layout_segment *lseg;
-
- struct page **pages;
- unsigned pgbase;
- unsigned nr_pages;
- unsigned long count;
- loff_t offset;
- bool sync;
+struct objlayout_io_res {
+ struct objlayout *objlay;
void *rpcdata;
int status; /* res */
- int eof; /* res */
int committed; /* res */
/* Error reporting (layout_return) */
@@ -100,6 +92,18 @@ struct objlayout_io_state {
struct pnfs_osd_ioerr *ioerrs;
};
+static inline
+void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
+ struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
+ struct pnfs_layout_hdr *pnfs_layout_type)
+{
+ oir->objlay = OBJLAYOUT(pnfs_layout_type);
+ oir->rpcdata = rpcdata;
+ INIT_LIST_HEAD(&oir->err_list);
+ oir->num_comps = num_comps;
+ oir->ioerrs = ioerrs;
+}
+
/*
* Raid engine I/O API
*/
@@ -110,28 +114,24 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
gfp_t gfp_flags);
extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
-extern int objio_alloc_io_state(
- struct pnfs_layout_segment *lseg,
- struct objlayout_io_state **outp,
- gfp_t gfp_flags);
-extern void objio_free_io_state(struct objlayout_io_state *state);
+/* objio_free_result will free these @oir structs recieved from
+ * objlayout_{read,write}_done
+ */
+extern void objio_free_result(struct objlayout_io_res *oir);
-extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state);
-extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
- bool stable);
+extern int objio_read_pagelist(struct nfs_read_data *rdata);
+extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);
/*
* callback API
*/
-extern void objlayout_io_set_result(struct objlayout_io_state *state,
+extern void objlayout_io_set_result(struct objlayout_io_res *oir,
unsigned index, struct pnfs_osd_objid *pooid,
int osd_error, u64 offset, u64 length, bool is_write);
static inline void
-objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
+objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
{
- struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
-
/* If one of the I/Os errored out and the delta_space_used was
* invalid we render the complete report as invalid. Protocol mandate
* the DSU be accurate or not reported.
@@ -144,9 +144,9 @@ objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
spin_unlock(&objlay->lock);
}
-extern void objlayout_read_done(struct objlayout_io_state *state,
+extern void objlayout_read_done(struct objlayout_io_res *oir,
ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_state *state,
+extern void objlayout_write_done(struct objlayout_io_res *oir,
ssize_t status, bool sync);
extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index b60970cc7f1..5668f7c54c4 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -18,6 +18,7 @@
#include <linux/nfs_page.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
+#include <linux/export.h>
#include "internal.h"
#include "pnfs.h"
@@ -41,7 +42,7 @@ nfs_page_free(struct nfs_page *p)
/**
* nfs_create_request - Create an NFS read/write request.
- * @file: file descriptor to use
+ * @ctx: open context to use
* @inode: inode to which the request is attached
* @page: page to write
* @offset: starting offset within the page for the write
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ee73d9a4f70..8e672a2b2d6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -29,6 +29,7 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
+#include <linux/module.h>
#include "internal.h"
#include "pnfs.h"
#include "iostat.h"
@@ -1259,6 +1260,25 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
+static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+{
+ struct nfs_pageio_descriptor pgio;
+
+ put_lseg(data->lseg);
+ data->lseg = NULL;
+ dprintk("pnfs write error = %d\n", data->pnfs_error);
+
+ nfs_pageio_init_read_mds(&pgio, data->inode);
+
+ while (!list_empty(&data->pages)) {
+ struct nfs_page *req = nfs_list_entry(data->pages.next);
+
+ nfs_list_remove_request(req);
+ nfs_pageio_add_request(&pgio, req);
+ }
+ nfs_pageio_complete(&pgio);
+}
+
/*
* Called by non rpc-based layout drivers
*/
@@ -1267,11 +1287,8 @@ void pnfs_ld_read_done(struct nfs_read_data *data)
if (likely(!data->pnfs_error)) {
__nfs4_read_done_cb(data);
data->mds_ops->rpc_call_done(&data->task, data);
- } else {
- put_lseg(data->lseg);
- data->lseg = NULL;
- dprintk("pnfs write error = %d\n", data->pnfs_error);
- }
+ } else
+ pnfs_ld_handle_read_error(data);
data->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
@@ -1443,17 +1460,31 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
data = kzalloc(sizeof(*data), GFP_NOFS);
if (!data) {
- mark_inode_dirty_sync(inode);
status = -ENOMEM;
goto out;
}
+ if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+ goto out_free;
+
+ if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
+ if (!sync) {
+ status = -EAGAIN;
+ goto out_free;
+ }
+ status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (status)
+ goto out_free;
+ }
+
INIT_LIST_HEAD(&data->lseg_list);
spin_lock(&inode->i_lock);
if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+ clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
spin_unlock(&inode->i_lock);
- kfree(data);
- goto out;
+ wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
+ goto out_free;
}
pnfs_list_write_lseg(inode, &data->lseg_list);
@@ -1475,6 +1506,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
status = nfs4_proc_layoutcommit(data, sync);
out:
+ if (status)
+ mark_inode_dirty_sync(inode);
dprintk("<-- %s status %d\n", __func__, status);
return status;
+out_free:
+ kfree(data);
+ goto out;
}
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 6fda5228ef5..4f359d2a26e 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -28,6 +28,7 @@
* such damages.
*/
+#include <linux/export.h>
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ac40b8535d7..f48125da198 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.dentry_ops = &nfs_dentry_operations,
.dir_inode_ops = &nfs_dir_inode_operations,
.file_inode_ops = &nfs_file_inode_operations,
+ .file_ops = &nfs_file_operations,
.getroot = nfs_proc_get_root,
.getattr = nfs_proc_getattr,
.setattr = nfs_proc_setattr,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 8b48ec63f72..cfa175c223d 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -109,7 +109,7 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
}
}
-static void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode)
{
nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
@@ -534,23 +534,13 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
static void nfs_readpage_release_full(void *calldata)
{
struct nfs_read_data *data = calldata;
- struct nfs_pageio_descriptor pgio;
- if (data->pnfs_error) {
- nfs_pageio_init_read_mds(&pgio, data->inode);
- pgio.pg_recoalesce = 1;
- }
while (!list_empty(&data->pages)) {
struct nfs_page *req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- if (!data->pnfs_error)
- nfs_readpage_release(req);
- else
- nfs_pageio_add_request(&pgio, req);
+ nfs_readpage_release(req);
}
- if (data->pnfs_error)
- nfs_pageio_complete(&pgio);
nfs_readdata_release(calldata);
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 480b3b6bf71..134777406ee 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2787,43 +2787,18 @@ static void nfs_referral_loop_unprotect(void)
static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
const char *export_path)
{
- struct mnt_namespace *ns_private;
- struct super_block *s;
struct dentry *dentry;
- struct path path;
- int ret;
-
- ns_private = create_mnt_ns(root_mnt);
- ret = PTR_ERR(ns_private);
- if (IS_ERR(ns_private))
- goto out_mntput;
-
- ret = nfs_referral_loop_protect();
- if (ret != 0)
- goto out_put_mnt_ns;
+ int ret = nfs_referral_loop_protect();
- ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
- export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+ if (ret) {
+ mntput(root_mnt);
+ return ERR_PTR(ret);
+ }
+ dentry = mount_subtree(root_mnt, export_path);
nfs_referral_loop_unprotect();
- put_mnt_ns(ns_private);
-
- if (ret != 0)
- goto out_err;
-
- s = path.mnt->mnt_sb;
- atomic_inc(&s->s_active);
- dentry = dget(path.dentry);
- path_put(&path);
- down_write(&s->s_umount);
return dentry;
-out_put_mnt_ns:
- put_mnt_ns(ns_private);
-out_mntput:
- mntput(root_mnt);
-out_err:
- return ERR_PTR(ret);
}
static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2219c88d96b..1dda78db6a7 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -20,6 +20,7 @@
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/backing-dev.h>
+#include <linux/export.h>
#include <asm/uaccess.h>
@@ -1243,7 +1244,6 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
{
struct nfs_writeargs *argp = &data->args;
struct nfs_writeres *resp = &data->res;
- struct nfs_server *server = NFS_SERVER(data->inode);
int status;
dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
@@ -1277,7 +1277,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
if (time_before(complain, jiffies)) {
dprintk("NFS: faulty NFS server %s:"
" (committed = %d) != (stable = %d)\n",
- server->nfs_client->cl_hostname,
+ NFS_SERVER(data->inode)->nfs_client->cl_hostname,
resp->verf->committed, argp->stable);
complain = jiffies + 300 * HZ;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-01-16 16:06:02 +0000