summaryrefslogtreecommitdiff
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/blocklayout/blocklayout.h2
-rw-r--r--fs/nfs/blocklayout/dev.c76
-rw-r--r--fs/nfs/direct.c134
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c18
-rw-r--r--fs/nfs/nfs42proc.c3
-rw-r--r--fs/nfs/nfs4client.c6
-rw-r--r--fs/nfs/nfs4proc.c12
-rw-r--r--fs/nfs/nfs4state.c45
-rw-r--r--fs/nfs/pnfs.c33
-rw-r--r--fs/nfs/write.c27
10 files changed, 228 insertions, 128 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 716bc75e9ed2..b4294a8aa2d4 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -108,7 +108,7 @@ struct pnfs_block_dev {
struct pnfs_block_dev *children;
u64 chunk_size;
- struct block_device *bdev;
+ struct bdev_handle *bdev_handle;
u64 disk_offset;
u64 pr_key;
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index 65cbb5607a5f..f318a05a80e1 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -25,17 +25,17 @@ bl_free_device(struct pnfs_block_dev *dev)
} else {
if (dev->pr_registered) {
const struct pr_ops *ops =
- dev->bdev->bd_disk->fops->pr_ops;
+ dev->bdev_handle->bdev->bd_disk->fops->pr_ops;
int error;
- error = ops->pr_register(dev->bdev, dev->pr_key, 0,
- false);
+ error = ops->pr_register(dev->bdev_handle->bdev,
+ dev->pr_key, 0, false);
if (error)
pr_err("failed to unregister PR key.\n");
}
- if (dev->bdev)
- blkdev_put(dev->bdev, NULL);
+ if (dev->bdev_handle)
+ bdev_release(dev->bdev_handle);
}
}
@@ -169,7 +169,7 @@ static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
map->start = dev->start;
map->len = dev->len;
map->disk_offset = dev->disk_offset;
- map->bdev = dev->bdev;
+ map->bdev = dev->bdev_handle->bdev;
return true;
}
@@ -236,28 +236,26 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
struct pnfs_block_volume *v = &volumes[idx];
- struct block_device *bdev;
+ struct bdev_handle *bdev_handle;
dev_t dev;
dev = bl_resolve_deviceid(server, v, gfp_mask);
if (!dev)
return -EIO;
- bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL,
- NULL);
- if (IS_ERR(bdev)) {
+ bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
+ NULL, NULL);
+ if (IS_ERR(bdev_handle)) {
printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
- MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
- return PTR_ERR(bdev);
+ MAJOR(dev), MINOR(dev), PTR_ERR(bdev_handle));
+ return PTR_ERR(bdev_handle);
}
- d->bdev = bdev;
-
-
- d->len = bdev_nr_bytes(d->bdev);
+ d->bdev_handle = bdev_handle;
+ d->len = bdev_nr_bytes(bdev_handle->bdev);
d->map = bl_map_simple;
printk(KERN_INFO "pNFS: using block device %s\n",
- d->bdev->bd_disk->disk_name);
+ bdev_handle->bdev->bd_disk->disk_name);
return 0;
}
@@ -302,10 +300,10 @@ bl_validate_designator(struct pnfs_block_volume *v)
}
}
-static struct block_device *
+static struct bdev_handle *
bl_open_path(struct pnfs_block_volume *v, const char *prefix)
{
- struct block_device *bdev;
+ struct bdev_handle *bdev_handle;
const char *devname;
devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN",
@@ -313,15 +311,15 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
if (!devname)
return ERR_PTR(-ENOMEM);
- bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL,
- NULL);
- if (IS_ERR(bdev)) {
+ bdev_handle = bdev_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
+ NULL, NULL);
+ if (IS_ERR(bdev_handle)) {
pr_warn("pNFS: failed to open device %s (%ld)\n",
- devname, PTR_ERR(bdev));
+ devname, PTR_ERR(bdev_handle));
}
kfree(devname);
- return bdev;
+ return bdev_handle;
}
static int
@@ -329,7 +327,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
{
struct pnfs_block_volume *v = &volumes[idx];
- struct block_device *bdev;
+ struct bdev_handle *bdev_handle;
const struct pr_ops *ops;
int error;
@@ -342,32 +340,32 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
* On other distributions like Debian, the default SCSI by-id path will
* point to the dm-multipath device if one exists.
*/
- bdev = bl_open_path(v, "dm-uuid-mpath-0x");
- if (IS_ERR(bdev))
- bdev = bl_open_path(v, "wwn-0x");
- if (IS_ERR(bdev))
- return PTR_ERR(bdev);
- d->bdev = bdev;
-
- d->len = bdev_nr_bytes(d->bdev);
+ bdev_handle = bl_open_path(v, "dm-uuid-mpath-0x");
+ if (IS_ERR(bdev_handle))
+ bdev_handle = bl_open_path(v, "wwn-0x");
+ if (IS_ERR(bdev_handle))
+ return PTR_ERR(bdev_handle);
+ d->bdev_handle = bdev_handle;
+
+ d->len = bdev_nr_bytes(d->bdev_handle->bdev);
d->map = bl_map_simple;
d->pr_key = v->scsi.pr_key;
pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
- d->bdev->bd_disk->disk_name, d->pr_key);
+ d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
- ops = d->bdev->bd_disk->fops->pr_ops;
+ ops = d->bdev_handle->bdev->bd_disk->fops->pr_ops;
if (!ops) {
pr_err("pNFS: block device %s does not support reservations.",
- d->bdev->bd_disk->disk_name);
+ d->bdev_handle->bdev->bd_disk->disk_name);
error = -EINVAL;
goto out_blkdev_put;
}
- error = ops->pr_register(d->bdev, 0, d->pr_key, true);
+ error = ops->pr_register(d->bdev_handle->bdev, 0, d->pr_key, true);
if (error) {
pr_err("pNFS: failed to register key for block device %s.",
- d->bdev->bd_disk->disk_name);
+ d->bdev_handle->bdev->bd_disk->disk_name);
goto out_blkdev_put;
}
@@ -375,7 +373,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
return 0;
out_blkdev_put:
- blkdev_put(d->bdev, NULL);
+ bdev_release(d->bdev_handle);
return error;
}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 47d892a1d363..f6c74f424691 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -93,12 +93,10 @@ nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
dreq->max_count = dreq_len;
if (dreq->count > dreq_len)
dreq->count = dreq_len;
-
- if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
- dreq->error = hdr->error;
- else /* Clear outstanding error if this is EOF */
- dreq->error = 0;
}
+
+ if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && !dreq->error)
+ dreq->error = hdr->error;
}
static void
@@ -120,6 +118,18 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq,
dreq->count = dreq_len;
}
+static void nfs_direct_truncate_request(struct nfs_direct_req *dreq,
+ struct nfs_page *req)
+{
+ loff_t offs = req_offset(req);
+ size_t req_start = (size_t)(offs - dreq->io_start);
+
+ if (req_start < dreq->max_count)
+ dreq->max_count = req_start;
+ if (req_start < dreq->count)
+ dreq->count = req_start;
+}
+
/**
* nfs_swap_rw - NFS address space operation for swap I/O
* @iocb: target I/O control block
@@ -488,7 +498,9 @@ static void nfs_direct_add_page_head(struct list_head *list,
kref_get(&head->wb_kref);
}
-static void nfs_direct_join_group(struct list_head *list, struct inode *inode)
+static void nfs_direct_join_group(struct list_head *list,
+ struct nfs_commit_info *cinfo,
+ struct inode *inode)
{
struct nfs_page *req, *subreq;
@@ -510,7 +522,7 @@ static void nfs_direct_join_group(struct list_head *list, struct inode *inode)
nfs_release_request(subreq);
}
} while ((subreq = subreq->wb_this_page) != req);
- nfs_join_page_group(req, inode);
+ nfs_join_page_group(req, cinfo, inode);
}
}
@@ -528,20 +540,15 @@ nfs_direct_write_scan_commit_list(struct inode *inode,
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
{
struct nfs_pageio_descriptor desc;
- struct nfs_page *req, *tmp;
+ struct nfs_page *req;
LIST_HEAD(reqs);
struct nfs_commit_info cinfo;
- LIST_HEAD(failed);
nfs_init_cinfo_from_dreq(&cinfo, dreq);
nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
- nfs_direct_join_group(&reqs, dreq->inode);
+ nfs_direct_join_group(&reqs, &cinfo, dreq->inode);
- dreq->count = 0;
- dreq->max_count = 0;
- list_for_each_entry(req, &reqs, wb_list)
- dreq->max_count += req->wb_bytes;
nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
get_dreq(dreq);
@@ -549,27 +556,40 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
- list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
+ while (!list_empty(&reqs)) {
+ req = nfs_list_entry(reqs.next);
/* Bump the transmission count */
req->wb_nio++;
if (!nfs_pageio_add_request(&desc, req)) {
- nfs_list_move_request(req, &failed);
- spin_lock(&cinfo.inode->i_lock);
- dreq->flags = 0;
- if (desc.pg_error < 0)
+ spin_lock(&dreq->lock);
+ if (dreq->error < 0) {
+ desc.pg_error = dreq->error;
+ } else if (desc.pg_error != -EAGAIN) {
+ dreq->flags = 0;
+ if (!desc.pg_error)
+ desc.pg_error = -EIO;
dreq->error = desc.pg_error;
- else
- dreq->error = -EIO;
- spin_unlock(&cinfo.inode->i_lock);
+ } else
+ dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+ spin_unlock(&dreq->lock);
+ break;
}
nfs_release_request(req);
}
nfs_pageio_complete(&desc);
- while (!list_empty(&failed)) {
- req = nfs_list_entry(failed.next);
+ while (!list_empty(&reqs)) {
+ req = nfs_list_entry(reqs.next);
nfs_list_remove_request(req);
nfs_unlock_and_release_request(req);
+ if (desc.pg_error == -EAGAIN) {
+ nfs_mark_request_commit(req, NULL, &cinfo, 0);
+ } else {
+ spin_lock(&dreq->lock);
+ nfs_direct_truncate_request(dreq, req);
+ spin_unlock(&dreq->lock);
+ nfs_release_request(req);
+ }
}
if (put_dreq(dreq))
@@ -589,8 +609,6 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
if (status < 0) {
/* Errors in commit are fatal */
dreq->error = status;
- dreq->max_count = 0;
- dreq->count = 0;
dreq->flags = NFS_ODIRECT_DONE;
} else {
status = dreq->error;
@@ -601,7 +619,12 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- if (status >= 0 && !nfs_write_match_verf(verf, req)) {
+ if (status < 0) {
+ spin_lock(&dreq->lock);
+ nfs_direct_truncate_request(dreq, req);
+ spin_unlock(&dreq->lock);
+ nfs_release_request(req);
+ } else if (!nfs_write_match_verf(verf, req)) {
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
/*
* Despite the reboot, the write was successful,
@@ -609,7 +632,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
*/
req->wb_nio = 0;
nfs_mark_request_commit(req, NULL, &cinfo, 0);
- } else /* Error or match */
+ } else
nfs_release_request(req);
nfs_unlock_and_release_request(req);
}
@@ -662,6 +685,7 @@ static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq)
while (!list_empty(&reqs)) {
req = nfs_list_entry(reqs.next);
nfs_list_remove_request(req);
+ nfs_direct_truncate_request(dreq, req);
nfs_release_request(req);
nfs_unlock_and_release_request(req);
}
@@ -711,7 +735,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
}
nfs_direct_count_bytes(dreq, hdr);
- if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags)) {
+ if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags) &&
+ !test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (!dreq->flags)
dreq->flags = NFS_ODIRECT_DO_COMMIT;
flags = dreq->flags;
@@ -755,18 +780,23 @@ static void nfs_write_sync_pgio_error(struct list_head *head, int error)
static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr)
{
struct nfs_direct_req *dreq = hdr->dreq;
+ struct nfs_page *req;
+ struct nfs_commit_info cinfo;
trace_nfs_direct_write_reschedule_io(dreq);
+ nfs_init_cinfo_from_dreq(&cinfo, dreq);
spin_lock(&dreq->lock);
- if (dreq->error == 0) {
+ if (dreq->error == 0)
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
- /* fake unstable write to let common nfs resend pages */
- hdr->verf.committed = NFS_UNSTABLE;
- hdr->good_bytes = hdr->args.offset + hdr->args.count -
- hdr->io_start;
- }
+ set_bit(NFS_IOHDR_REDO, &hdr->flags);
spin_unlock(&dreq->lock);
+ while (!list_empty(&hdr->pages)) {
+ req = nfs_list_entry(hdr->pages.next);
+ nfs_list_remove_request(req);
+ nfs_unlock_request(req);
+ nfs_mark_request_commit(req, NULL, &cinfo, 0);
+ }
}
static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
@@ -794,9 +824,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
{
struct nfs_pageio_descriptor desc;
struct inode *inode = dreq->inode;
+ struct nfs_commit_info cinfo;
ssize_t result = 0;
size_t requested_bytes = 0;
size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
+ bool defer = false;
trace_nfs_direct_write_schedule_iovec(dreq);
@@ -837,17 +869,37 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
break;
}
- nfs_lock_request(req);
- if (!nfs_pageio_add_request(&desc, req)) {
- result = desc.pg_error;
- nfs_unlock_and_release_request(req);
- break;
- }
pgbase = 0;
bytes -= req_len;
requested_bytes += req_len;
pos += req_len;
dreq->bytes_left -= req_len;
+
+ if (defer) {
+ nfs_mark_request_commit(req, NULL, &cinfo, 0);
+ continue;
+ }
+
+ nfs_lock_request(req);
+ if (nfs_pageio_add_request(&desc, req))
+ continue;
+
+ /* Exit on hard errors */
+ if (desc.pg_error < 0 && desc.pg_error != -EAGAIN) {
+ result = desc.pg_error;
+ nfs_unlock_and_release_request(req);
+ break;
+ }
+
+ /* If the error is soft, defer remaining requests */
+ nfs_init_cinfo_from_dreq(&cinfo, dreq);
+ spin_lock(&dreq->lock);
+ dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+ spin_unlock(&dreq->lock);
+ nfs_unlock_request(req);
+ nfs_mark_request_commit(req, NULL, &cinfo, 0);
+ desc.pg_error = 0;
+ defer = true;
}
nfs_direct_release_pages(pagevec, npages);
kvfree(pagevec);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 7deb3cd76abe..ef817a0475ff 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1235,6 +1235,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
case -EOPNOTSUPP:
+ case -EINVAL:
case -ECONNREFUSED:
case -ECONNRESET:
case -EHOSTDOWN:
@@ -2519,9 +2520,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
return i;
}
-static int
-ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
+static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
{
+ struct pnfs_layout_hdr *lo;
struct nfs4_flexfile_layout *ff_layout;
const int dev_count = PNFS_LAYOUTSTATS_MAXDEV;
@@ -2532,11 +2533,14 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
return -ENOMEM;
spin_lock(&args->inode->i_lock);
- ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout);
- args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr,
- &args->devinfo[0],
- dev_count,
- NFS4_FF_OP_LAYOUTSTATS);
+ lo = NFS_I(args->inode)->layout;
+ if (lo && pnfs_layout_is_valid(lo)) {
+ ff_layout = FF_LAYOUT_FROM_HDR(lo);
+ args->num_dev = ff_layout_mirror_prepare_stats(
+ &ff_layout->generic_hdr, &args->devinfo[0], dev_count,
+ NFS4_FF_OP_LAYOUTSTATS);
+ } else
+ args->num_dev = 0;
spin_unlock(&args->inode->i_lock);
if (!args->num_dev) {
kfree(args->devinfo);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 063e00aff87e..28704f924612 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -81,7 +81,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
if (status == 0) {
if (nfs_should_remove_suid(inode)) {
spin_lock(&inode->i_lock);
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+ nfs_set_cache_invalid(inode,
+ NFS_INO_REVAL_FORCED | NFS_INO_INVALID_MODE);
spin_unlock(&inode->i_lock);
}
status = nfs_post_op_update_inode_force_wcc(inode,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 27fb25567ce7..11e3a285594c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -417,6 +417,8 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old)
.net = old->cl_net,
.servername = old->cl_hostname,
};
+ int max_connect = test_bit(NFS_CS_PNFS, &clp->cl_flags) ?
+ clp->cl_max_connect : old->cl_max_connect;
if (clp->cl_proto != old->cl_proto)
return;
@@ -430,7 +432,7 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old)
xprt_args.addrlen = clp_salen;
rpc_clnt_add_xprt(old->cl_rpcclient, &xprt_args,
- rpc_clnt_test_and_add_xprt, NULL);
+ rpc_clnt_test_and_add_xprt, &max_connect);
}
/**
@@ -1010,6 +1012,8 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
__set_bit(NFS_CS_DS, &cl_init.init_flags);
+ __set_bit(NFS_CS_PNFS, &cl_init.init_flags);
+ cl_init.max_connect = NFS_MAX_TRANSPORTS;
/*
* Set an authflavor equual to the MDS value. Use the MDS nfs_client
* cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 794343790ea8..5ee283eb9660 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2703,8 +2703,12 @@ static int _nfs4_proc_open(struct nfs4_opendata *data,
return status;
}
if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) {
+ struct nfs_fh *fh = &o_res->fh;
+
nfs4_sequence_free_slot(&o_res->seq_res);
- nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL);
+ if (o_arg->claim == NFS4_OPEN_CLAIM_FH)
+ fh = NFS_FH(d_inode(data->dentry));
+ nfs4_proc_getattr(server, fh, o_res->f_attr, NULL);
}
return 0;
}
@@ -8866,8 +8870,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
/* Save the EXCHANGE_ID verifier session trunk tests */
memcpy(clp->cl_confirm.data, argp->verifier.data,
sizeof(clp->cl_confirm.data));
- if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS)
- set_bit(NFS_CS_DS, &clp->cl_flags);
out:
trace_nfs4_exchange_id(clp, status);
rpc_put_task(task);
@@ -10618,7 +10620,9 @@ static void nfs4_disable_swap(struct inode *inode)
*/
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
- nfs4_schedule_state_manager(clp);
+ set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+ wake_up_var(&clp->cl_state);
}
static const struct inode_operations nfs4_dir_inode_operations = {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e079987af4a3..9a5d911a7edc 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
{
struct task_struct *task;
char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
+ struct rpc_clnt *clnt = clp->cl_rpcclient;
+ bool swapon = false;
- if (clp->cl_rpcclient->cl_shutdown)
+ if (clnt->cl_shutdown)
return;
set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
- if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) {
- wake_up_var(&clp->cl_state);
- return;
+
+ if (atomic_read(&clnt->cl_swapper)) {
+ swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE,
+ &clp->cl_state);
+ if (!swapon) {
+ wake_up_var(&clp->cl_state);
+ return;
+ }
}
- set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
+
+ if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
+ return;
+
__module_get(THIS_MODULE);
refcount_inc(&clp->cl_count);
@@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
__func__, PTR_ERR(task));
if (!nfs_client_init_is_complete(clp))
nfs_mark_client_ready(clp, PTR_ERR(task));
+ if (swapon)
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
nfs4_clear_state_manager_bit(clp);
- clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
nfs_put_client(clp);
module_put(THIS_MODULE);
}
@@ -2703,6 +2714,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
+ if (test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING,
+ &clp->cl_state)) {
+ memflags = memalloc_nofs_save();
+ continue;
+ }
+
if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) {
if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
nfs_client_return_marked_delegations(clp);
@@ -2741,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr)
allow_signal(SIGKILL);
again:
- set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
nfs4_state_manager(clp);
- if (atomic_read(&cl->cl_swapper)) {
+
+ if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) &&
+ !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) {
wait_var_event_interruptible(&clp->cl_state,
test_bit(NFS4CLNT_RUN_MANAGER,
&clp->cl_state));
- if (atomic_read(&cl->cl_swapper) &&
- test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
+ if (!atomic_read(&cl->cl_swapper))
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+ if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
goto again;
/* Either no longer a swapper, or were signalled */
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
}
- clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
- !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state))
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
goto again;
nfs_put_client(clp);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 306cba0b9e69..84343aefbbd6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2634,31 +2634,44 @@ pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo,
return mode == 0;
}
-static int
-pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data)
+static int pnfs_layout_return_unused_byserver(struct nfs_server *server,
+ void *data)
{
const struct pnfs_layout_range *range = data;
+ const struct cred *cred;
struct pnfs_layout_hdr *lo;
struct inode *inode;
+ nfs4_stateid stateid;
+ enum pnfs_iomode iomode;
+
restart:
rcu_read_lock();
list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) {
- if (!pnfs_layout_can_be_returned(lo) ||
+ inode = lo->plh_inode;
+ if (!inode || !pnfs_layout_can_be_returned(lo) ||
test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
continue;
- inode = lo->plh_inode;
spin_lock(&inode->i_lock);
- if (!pnfs_should_return_unused_layout(lo, range)) {
+ if (!lo->plh_inode ||
+ !pnfs_should_return_unused_layout(lo, range)) {
spin_unlock(&inode->i_lock);
continue;
}
+ pnfs_get_layout_hdr(lo);
+ pnfs_set_plh_return_info(lo, range->iomode, 0);
+ if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ range, 0) != 0 ||
+ !pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode)) {
+ spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
+ pnfs_put_layout_hdr(lo);
+ cond_resched();
+ goto restart;
+ }
spin_unlock(&inode->i_lock);
- inode = pnfs_grab_inode_layout_hdr(lo);
- if (!inode)
- continue;
rcu_read_unlock();
- pnfs_mark_layout_for_return(inode, range);
- iput(inode);
+ pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false);
+ pnfs_put_layout_hdr(lo);
cond_resched();
goto restart;
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f4cca8f00c0c..9d82d50ce0b1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -59,7 +59,8 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
static const struct nfs_rw_ops nfs_rw_write_ops;
static void nfs_inode_remove_request(struct nfs_page *req);
-static void nfs_clear_request_commit(struct nfs_page *req);
+static void nfs_clear_request_commit(struct nfs_commit_info *cinfo,
+ struct nfs_page *req);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode);
static struct nfs_page *
@@ -502,8 +503,8 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
* the (former) group. All subrequests are removed from any write or commit
* lists, unlinked from the group and destroyed.
*/
-void
-nfs_join_page_group(struct nfs_page *head, struct inode *inode)
+void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo,
+ struct inode *inode)
{
struct nfs_page *subreq;
struct nfs_page *destroy_list = NULL;
@@ -533,7 +534,7 @@ nfs_join_page_group(struct nfs_page *head, struct inode *inode)
* Commit list removal accounting is done after locks are dropped */
subreq = head;
do {
- nfs_clear_request_commit(subreq);
+ nfs_clear_request_commit(cinfo, subreq);
subreq = subreq->wb_this_page;
} while (subreq != head);
@@ -566,8 +567,10 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
{
struct inode *inode = folio_file_mapping(folio)->host;
struct nfs_page *head;
+ struct nfs_commit_info cinfo;
int ret;
+ nfs_init_cinfo_from_inode(&cinfo, inode);
/*
* A reference is taken only on the head request which acts as a
* reference to the whole page group - the group will not be destroyed
@@ -584,7 +587,7 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
return ERR_PTR(ret);
}
- nfs_join_page_group(head, inode);
+ nfs_join_page_group(head, &cinfo, inode);
return head;
}
@@ -785,6 +788,8 @@ static void nfs_inode_add_request(struct nfs_page *req)
*/
static void nfs_inode_remove_request(struct nfs_page *req)
{
+ struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req));
+
if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
struct folio *folio = nfs_page_to_folio(req->wb_head);
struct address_space *mapping = folio_file_mapping(folio);
@@ -799,8 +804,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
}
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
+ atomic_long_dec(&nfsi->nrequests);
nfs_release_request(req);
- atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests);
}
}
@@ -955,18 +960,16 @@ static void nfs_folio_clear_commit(struct folio *folio)
}
/* Called holding the request lock on @req */
-static void
-nfs_clear_request_commit(struct nfs_page *req)
+static void nfs_clear_request_commit(struct nfs_commit_info *cinfo,
+ struct nfs_page *req)
{
if (test_bit(PG_CLEAN, &req->wb_flags)) {
struct nfs_open_context *ctx = nfs_req_openctx(req);
struct inode *inode = d_inode(ctx->dentry);
- struct nfs_commit_info cinfo;
- nfs_init_cinfo_from_inode(&cinfo, inode);
mutex_lock(&NFS_I(inode)->commit_mutex);
- if (!pnfs_clear_request_commit(req, &cinfo)) {
- nfs_request_remove_commit_list(req, &cinfo);
+ if (!pnfs_clear_request_commit(req, cinfo)) {
+ nfs_request_remove_commit_list(req, cinfo);
}
mutex_unlock(&NFS_I(inode)->commit_mutex);
nfs_folio_clear_commit(nfs_page_to_folio(req));
generated by cgit (git 2.34.1) at 2024-05-27 13:28:54 +0000