summaryrefslogtreecommitdiff
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/callback_proc.c9
-rw-r--r--fs/nfs/delegation.c9
-rw-r--r--fs/nfs/filelayout/filelayout.c2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c29
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.h16
-rw-r--r--fs/nfs/fs_context.c8
-rw-r--r--fs/nfs/internal.h12
-rw-r--r--fs/nfs/nfs4proc.c22
-rw-r--r--fs/nfs/pnfs.c4
-rw-r--r--fs/nfs/pnfs_nfs.c2
-rw-r--r--fs/nfs/read.c25
-rw-r--r--fs/nfs/write.c14
12 files changed, 119 insertions, 33 deletions
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 4ea9221ded42..10f2354ba304 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -257,6 +257,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
struct pnfs_layout_hdr *lo;
u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
LIST_HEAD(free_me_list);
+ bool return_range = false;
ino = nfs_layout_find_inode(clp, &args->cbl_fh, &args->cbl_stateid);
if (IS_ERR(ino)) {
@@ -301,13 +302,13 @@ static u32 initiate_file_draining(struct nfs_client *clp,
/* Embrace your forgetfulness! */
rv = NFS4ERR_NOMATCHING_LAYOUT;
- if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
- NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
- &args->cbl_range);
- }
+ return_range = true;
}
unlock:
spin_unlock(&ino->i_lock);
+ if (return_range && NFS_SERVER(ino)->pnfs_curr_ld->return_range)
+ NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
+ &args->cbl_range);
pnfs_free_lseg_list(&free_me_list);
/* Free all lsegs that are attached to commit buckets */
nfs_commit_inode(ino, 0);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 122fb3f14ffb..9546d2195c25 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -173,6 +173,7 @@ int nfs4_check_delegation(struct inode *inode, fmode_t type)
static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct inode *inode = state->inode;
+ struct nfs_inode *nfsi = NFS_I(inode);
struct file_lock *fl;
struct file_lock_context *flctx = locks_inode_context(inode);
struct list_head *list;
@@ -182,6 +183,9 @@ static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_state
goto out;
list = &flctx->flc_posix;
+
+ /* Guard against reclaim and new lock/unlock calls */
+ down_write(&nfsi->rwsem);
spin_lock(&flctx->flc_lock);
restart:
for_each_file_lock(fl, list) {
@@ -189,8 +193,10 @@ restart:
continue;
spin_unlock(&flctx->flc_lock);
status = nfs4_lock_delegation_recall(fl, state, stateid);
- if (status < 0)
+ if (status < 0) {
+ up_write(&nfsi->rwsem);
goto out;
+ }
spin_lock(&flctx->flc_lock);
}
if (list == &flctx->flc_posix) {
@@ -198,6 +204,7 @@ restart:
goto restart;
}
spin_unlock(&flctx->flc_lock);
+ up_write(&nfsi->rwsem);
out:
return status;
}
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index e85380e3b11d..70f2cbd46960 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -778,6 +778,8 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
static bool
filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
{
+ if (flseg->dsaddr)
+ return flseg->dsaddr->stripe_count > 1;
return flseg->num_fh > 1;
}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index e22a8e0daf2c..2e7f857d5a8c 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -636,6 +636,9 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
if (!p)
goto out_sort_mirrors;
fls->flags = be32_to_cpup(p);
+ if (fls->flags & FF_FLAGS_NO_IO_THRU_MDS)
+ set_bit(NFS4_FF_HDR_NO_IO_THRU_MDS,
+ &FF_LAYOUT_FROM_HDR(lh)->flags);
p = xdr_inline_decode(&stream, 4);
if (!p)
@@ -1185,6 +1188,16 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
0, NFS4_MAX_UINT64, IOMODE_RW,
NFS_I(pgio->pg_inode)->layout,
pgio->pg_lseg);
+ if (NFS_I(pgio->pg_inode)->layout &&
+ ff_layout_hdr_no_fallback_to_mds(NFS_I(pgio->pg_inode)->layout)) {
+ /*
+ * FF_FLAGS_NO_IO_THRU_MDS: no current lseg but the server's
+ * policy forbids MDS fallback. Surface -EAGAIN so writeback
+ * retries rather than silently issuing the WRITE via MDS.
+ */
+ pgio->pg_error = -EAGAIN;
+ goto out;
+ }
/* no lseg means that pnfs is not in use, so no mirroring here */
nfs_pageio_reset_write_mds(pgio);
out:
@@ -2204,6 +2217,14 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
return PNFS_TRY_AGAIN;
+ if (ff_layout_no_fallback_to_mds(lseg)) {
+ /*
+ * FF_FLAGS_NO_IO_THRU_MDS: force fresh LAYOUTGET,
+ * never fall through to MDS I/O.
+ */
+ pnfs_error_mark_layout_for_return(hdr->inode, lseg);
+ return PNFS_TRY_AGAIN;
+ }
trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
hdr->args.offset, hdr->args.count,
IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);
@@ -2289,6 +2310,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
return PNFS_TRY_AGAIN;
+ if (ff_layout_no_fallback_to_mds(lseg)) {
+ /*
+ * FF_FLAGS_NO_IO_THRU_MDS: force fresh LAYOUTGET,
+ * never fall through to MDS I/O.
+ */
+ pnfs_error_mark_layout_for_return(hdr->inode, lseg);
+ return PNFS_TRY_AGAIN;
+ }
trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
hdr->args.offset, hdr->args.count,
IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 17a008c8e97c..a5bd00f69e82 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -112,12 +112,16 @@ struct nfs4_ff_layout_segment {
struct nfs4_ff_layout_mirror *mirror_array[] __counted_by(mirror_array_cnt);
};
+/* nfs4_flexfile_layout::flags bit indices */
+#define NFS4_FF_HDR_NO_IO_THRU_MDS 0 /* any lseg has had FF_FLAGS_NO_IO_THRU_MDS */
+
struct nfs4_flexfile_layout {
struct pnfs_layout_hdr generic_hdr;
struct pnfs_ds_commit_info commit_info;
struct list_head mirrors;
struct list_head error_list; /* nfs4_ff_layout_ds_err */
ktime_t last_report_time; /* Layoutstat report times */
+ unsigned long flags;
};
struct nfs4_flexfile_layoutreturn_args {
@@ -184,6 +188,18 @@ ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg)
return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_IO_THRU_MDS;
}
+/*
+ * Sticky hdr-level mirror of FF_FLAGS_NO_IO_THRU_MDS so callers that have
+ * no current lseg (e.g. between LAYOUTRETURN and the next LAYOUTGET) can
+ * still honor the no-MDS-fallback policy.
+ */
+static inline bool
+ff_layout_hdr_no_fallback_to_mds(struct pnfs_layout_hdr *lo)
+{
+ return test_bit(NFS4_FF_HDR_NO_IO_THRU_MDS,
+ &FF_LAYOUT_FROM_HDR(lo)->flags);
+}
+
static inline bool
ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
{
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index c105882edd16..1967de7d1dff 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -1769,7 +1769,9 @@ struct file_system_type nfs_fs_type = {
.init_fs_context = nfs_init_fs_context,
.parameters = nfs_fs_parameters,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE |
+ FS_BINARY_MOUNTDATA |
+ FS_USERNS_DELEGATABLE,
};
MODULE_ALIAS_FS("nfs");
EXPORT_SYMBOL_GPL(nfs_fs_type);
@@ -1781,7 +1783,9 @@ struct file_system_type nfs4_fs_type = {
.init_fs_context = nfs_init_fs_context,
.parameters = nfs_fs_parameters,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE |
+ FS_BINARY_MOUNTDATA |
+ FS_USERNS_DELEGATABLE,
};
MODULE_ALIAS_FS("nfs4");
MODULE_ALIAS("nfs4");
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 18d46b0e71dd..1d5d62f88dde 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -847,17 +847,19 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
}
/*
- * Record the page as unstable (an extra writeback period) and mark its
- * inode as dirty.
+ * Record the request's range as unstable (an extra writeback period) and
+ * mark its inode as dirty.
*/
-static inline void nfs_folio_mark_unstable(struct folio *folio,
+static inline void nfs_folio_mark_unstable(struct nfs_page *req,
struct nfs_commit_info *cinfo)
{
+ struct folio *folio = nfs_page_to_folio(req);
+
if (folio && !cinfo->dreq) {
struct inode *inode = folio->mapping->host;
- long nr = folio_nr_pages(folio);
+ long nr = DIV_ROUND_UP(req->wb_bytes, PAGE_SIZE);
- /* This page is really still in write-back - just that the
+ /* This range is really still in write-back - just that the
* writeback is happening on the server now.
*/
node_stat_mod_folio(folio, NR_WRITEBACK, nr);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c354b7b90293..4db27f4eb01e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7084,7 +7084,6 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
switch (task->tk_status) {
case 0:
renew_lease(calldata->server, calldata->timestamp);
- locks_lock_inode_wait(calldata->lsp->ls_state->inode, &calldata->fl);
if (nfs4_update_lock_stateid(calldata->lsp,
&calldata->res.stateid))
break;
@@ -7352,11 +7351,6 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
case 0:
renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)),
data->timestamp);
- if (data->arg.new_lock && !data->cancelled) {
- data->fl.c.flc_flags &= ~(FL_SLEEP | FL_ACCESS);
- if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
- goto out_restart;
- }
if (data->arg.new_lock_owner != 0) {
nfs_confirm_seqid(&lsp->ls_seqid, 0);
nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid);
@@ -7467,11 +7461,10 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
msg.rpc_argp = &data->arg;
msg.rpc_resp = &data->res;
task_setup_data.callback_data = data;
- if (recovery_type > NFS_LOCK_NEW) {
- if (recovery_type == NFS_LOCK_RECLAIM)
- data->arg.reclaim = NFS_LOCK_RECLAIM;
- } else
- data->arg.new_lock = 1;
+
+ if (recovery_type == NFS_LOCK_RECLAIM)
+ data->arg.reclaim = NFS_LOCK_RECLAIM;
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -7581,6 +7574,13 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
up_read(&nfsi->rwsem);
mutex_unlock(&sp->so_delegreturn_mutex);
status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
+ if (status)
+ goto out;
+
+ down_read(&nfsi->rwsem);
+ request->c.flc_flags &= ~(FL_SLEEP | FL_ACCESS);
+ status = locks_lock_inode_wait(state->inode, request);
+ up_read(&nfsi->rwsem);
out:
request->c.flc_flags = flags;
return status;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index aee523134c0f..b7dcf58f21c3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1463,8 +1463,6 @@ _pnfs_return_layout(struct inode *ino)
pnfs_clear_layoutcommit(ino, &tmp_list);
pnfs_mark_matching_lsegs_return(lo, &tmp_list, &range, 0);
- if (NFS_SERVER(ino)->pnfs_curr_ld->return_range)
- NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
/* Don't send a LAYOUTRETURN if list was initially empty */
if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) ||
@@ -1476,6 +1474,8 @@ _pnfs_return_layout(struct inode *ino)
send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
spin_unlock(&ino->i_lock);
+ if (NFS_SERVER(ino)->pnfs_curr_ld->return_range)
+ NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
if (send)
status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY,
0);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 0ff43dbcb7cd..648c95b78eea 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -1199,7 +1199,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
nfs_request_add_commit_list_locked(req, list, cinfo);
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
- nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo);
+ nfs_folio_mark_unstable(req, cinfo);
return;
out_resched:
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index e1fe78d7b8d0..2b70bd2b934b 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -132,10 +132,32 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
static void nfs_page_group_set_uptodate(struct nfs_page *req)
{
- if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
+ bool uptodate = false;
+
+ nfs_page_group_lock(req);
+ if (!test_bit(PG_READ_FAILED, &req->wb_head->wb_flags) &&
+ nfs_page_group_sync_on_bit_locked(req, PG_UPTODATE))
+ uptodate = true;
+ nfs_page_group_unlock(req);
+
+ if (uptodate)
folio_mark_uptodate(nfs_page_to_folio(req));
}
+static void nfs_page_group_mark_read_failed(struct nfs_page *req)
+{
+ struct nfs_page *tmp;
+
+ nfs_page_group_lock(req);
+ set_bit(PG_READ_FAILED, &req->wb_head->wb_flags);
+ tmp = req;
+ do {
+ clear_bit(PG_UPTODATE, &tmp->wb_flags);
+ tmp = tmp->wb_this_page;
+ } while (tmp != req);
+ nfs_page_group_unlock(req);
+}
+
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
@@ -172,6 +194,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
if (bytes <= hdr->good_bytes)
nfs_page_group_set_uptodate(req);
else {
+ nfs_page_group_mark_read_failed(req);
error = hdr->error;
xchg(&nfs_req_openctx(req)->error, error);
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d7c399763ad9..f7a5fb8140c4 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -807,7 +807,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo)
mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo);
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
- nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo);
+ nfs_folio_mark_unstable(req, cinfo);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
@@ -866,10 +866,12 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
nfs_request_add_commit_list(req, cinfo);
}
-static void nfs_folio_clear_commit(struct folio *folio)
+static void nfs_folio_clear_commit(struct nfs_page *req)
{
+ struct folio *folio = nfs_page_to_folio(req);
+
if (folio) {
- long nr = folio_nr_pages(folio);
+ long nr = DIV_ROUND_UP(req->wb_bytes, PAGE_SIZE);
node_stat_mod_folio(folio, NR_WRITEBACK, -nr);
bdi_wb_stat_mod(folio->mapping->host, WB_WRITEBACK, -nr);
@@ -889,7 +891,7 @@ static void nfs_clear_request_commit(struct nfs_commit_info *cinfo,
nfs_request_remove_commit_list(req, cinfo);
}
mutex_unlock(&NFS_I(inode)->commit_mutex);
- nfs_folio_clear_commit(nfs_page_to_folio(req));
+ nfs_folio_clear_commit(req);
}
}
@@ -1741,7 +1743,7 @@ void nfs_retry_commit(struct list_head *page_list,
req = nfs_list_entry(page_list->next);
nfs_list_remove_request(req);
nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
- nfs_folio_clear_commit(nfs_page_to_folio(req));
+ nfs_folio_clear_commit(req);
nfs_unlock_and_release_request(req);
}
}
@@ -1813,7 +1815,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
folio = nfs_page_to_folio(req);
- nfs_folio_clear_commit(folio);
+ nfs_folio_clear_commit(req);
dprintk("NFS: commit (%s/%llu %d@%lld)",
nfs_req_openctx(req)->dentry->d_sb->s_id,
generated by cgit v1.2.3 (git 2.25.1) at 2026-07-25 15:22:16 +0000