* [PATCH v7 01/20] nfs: pass nfs_client to nfs_initiate_pgio
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 02/20] nfs: pass descriptor thru nfs_initiate_pgio path Mike Snitzer
` (19 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Weston Andros Adamson <dros@primarydata.com>
The nfs_client is needed for localio support. Otherwise it won't be
possible to disable localio if it is attempted but fails.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/filelayout/filelayout.c | 4 ++--
fs/nfs/flexfilelayout/flexfilelayout.c | 6 ++++--
fs/nfs/internal.h | 5 +++--
fs/nfs/pagelist.c | 10 ++++++----
4 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 29d84dc66ca3..43e16e9e0176 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -486,7 +486,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->mds_offset = offset;
/* Perform an asynchronous read to ds */
- nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+ nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
0, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
@@ -528,7 +528,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
/* Perform an asynchronous write */
- nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+ nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
sync, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 24188af56d5b..327f1a5c9fbe 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1803,7 +1803,8 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->mds_offset = offset;
/* Perform an asynchronous read to ds */
- nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
+ nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, ds_cred,
+ ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
0, RPC_TASK_SOFTCONN);
@@ -1871,7 +1872,8 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
hdr->args.offset = offset;
/* Perform an asynchronous write */
- nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
+ nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, ds_cred,
+ ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
sync, RPC_TASK_SOFTCONN);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9f0f4534744b..a9c0c29f7804 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -306,8 +306,9 @@ extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
void nfs_pgio_header_free(struct nfs_pgio_header *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
- const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
+int nfs_initiate_pgio(struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
+ struct nfs_pgio_header *hdr, const struct cred *cred,
+ const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6efb5068c116..d9b795c538cd 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -844,8 +844,9 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
rpc_exit(task, err);
}
-int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
- const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
+int nfs_initiate_pgio(struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
+ struct nfs_pgio_header *hdr, const struct cred *cred,
+ const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags)
{
struct rpc_task *task;
@@ -855,7 +856,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
.rpc_cred = cred,
};
struct rpc_task_setup task_setup_data = {
- .rpc_client = clnt,
+ .rpc_client = rpc_clnt,
.task = &hdr->task,
.rpc_message = &msg,
.callback_ops = call_ops,
@@ -1070,7 +1071,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
if (ret == 0) {
if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
- ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
+ ret = nfs_initiate_pgio(NFS_SERVER(hdr->inode)->nfs_client,
+ NFS_CLIENT(hdr->inode),
hdr,
hdr->cred,
NFS_PROTO(hdr->inode),
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 02/20] nfs: pass descriptor thru nfs_initiate_pgio path
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 01/20] nfs: pass nfs_client to nfs_initiate_pgio Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 03/20] nfs: pass struct file to nfs_init_pgio and nfs_init_commit Mike Snitzer
` (18 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Weston Andros Adamson <dros@primarydata.com>
This is needed for localio support.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/blocklayout/blocklayout.c | 6 ++++--
fs/nfs/filelayout/filelayout.c | 10 ++++++----
fs/nfs/flexfilelayout/flexfilelayout.c | 10 ++++++----
fs/nfs/internal.h | 6 +++---
fs/nfs/pagelist.c | 6 ++++--
fs/nfs/pnfs.c | 24 +++++++++++++-----------
fs/nfs/pnfs.h | 6 ++++--
7 files changed, 40 insertions(+), 28 deletions(-)
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 6be13e0ec170..6a61ddd1835f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -227,7 +227,8 @@ bl_end_par_io_read(void *data)
}
static enum pnfs_try_status
-bl_read_pagelist(struct nfs_pgio_header *header)
+bl_read_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *header)
{
struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
@@ -372,7 +373,8 @@ static void bl_end_par_io_write(void *data)
}
static enum pnfs_try_status
-bl_write_pagelist(struct nfs_pgio_header *header, int sync)
+bl_write_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *header, int sync)
{
struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 43e16e9e0176..f9b600c4a2b5 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -447,7 +447,8 @@ static const struct rpc_call_ops filelayout_commit_call_ops = {
};
static enum pnfs_try_status
-filelayout_read_pagelist(struct nfs_pgio_header *hdr)
+filelayout_read_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr)
{
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
@@ -486,7 +487,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->mds_offset = offset;
/* Perform an asynchronous read to ds */
- nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, hdr->cred,
+ nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
0, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
@@ -494,7 +495,8 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
/* Perform async writes. */
static enum pnfs_try_status
-filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
+filelayout_write_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr, int sync)
{
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
@@ -528,7 +530,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
/* Perform an asynchronous write */
- nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, hdr->cred,
+ nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
sync, RPC_TASK_SOFTCONN);
return PNFS_ATTEMPTED;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 327f1a5c9fbe..22c0e8014afb 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1751,7 +1751,8 @@ static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = {
};
static enum pnfs_try_status
-ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
+ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr)
{
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
@@ -1803,7 +1804,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->mds_offset = offset;
/* Perform an asynchronous read to ds */
- nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, ds_cred,
+ nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
@@ -1822,7 +1823,8 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
/* Perform async writes. */
static enum pnfs_try_status
-ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
+ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr, int sync)
{
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
@@ -1872,7 +1874,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
hdr->args.offset = offset;
/* Perform an asynchronous write */
- nfs_initiate_pgio(ds->ds_clp, ds_clnt, hdr, ds_cred,
+ nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index a9c0c29f7804..f6e56fdd8bc2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -306,9 +306,9 @@ extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
void nfs_pgio_header_free(struct nfs_pgio_header *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
- struct nfs_pgio_header *hdr, const struct cred *cred,
- const struct nfs_rpc_ops *rpc_ops,
+int nfs_initiate_pgio(struct nfs_pageio_descriptor *, struct nfs_client *clp,
+ struct rpc_clnt *rpc_clnt, struct nfs_pgio_header *hdr,
+ const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index d9b795c538cd..3786d767e2ff 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -844,7 +844,8 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
rpc_exit(task, err);
}
-int nfs_initiate_pgio(struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
+int nfs_initiate_pgio(struct nfs_pageio_descriptor *desc,
+ struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
struct nfs_pgio_header *hdr, const struct cred *cred,
const struct nfs_rpc_ops *rpc_ops,
const struct rpc_call_ops *call_ops, int how, int flags)
@@ -1071,7 +1072,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
if (ret == 0) {
if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
- ret = nfs_initiate_pgio(NFS_SERVER(hdr->inode)->nfs_client,
+ ret = nfs_initiate_pgio(desc,
+ NFS_SERVER(hdr->inode)->nfs_client,
NFS_CLIENT(hdr->inode),
hdr,
hdr->cred,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index b5834728f31b..c9015179b72c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2885,10 +2885,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
}
static enum pnfs_try_status
-pnfs_try_to_write_data(struct nfs_pgio_header *hdr,
- const struct rpc_call_ops *call_ops,
- struct pnfs_layout_segment *lseg,
- int how)
+pnfs_try_to_write_data(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops,
+ struct pnfs_layout_segment *lseg,
+ int how)
{
struct inode *inode = hdr->inode;
enum pnfs_try_status trypnfs;
@@ -2898,7 +2899,7 @@ pnfs_try_to_write_data(struct nfs_pgio_header *hdr,
dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
inode->i_ino, hdr->args.count, hdr->args.offset, how);
- trypnfs = nfss->pnfs_curr_ld->write_pagelist(hdr, how);
+ trypnfs = nfss->pnfs_curr_ld->write_pagelist(desc, hdr, how);
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_WRITE);
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
@@ -2913,7 +2914,7 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
- trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
+ trypnfs = pnfs_try_to_write_data(desc, hdr, call_ops, lseg, how);
switch (trypnfs) {
case PNFS_NOT_ATTEMPTED:
pnfs_write_through_mds(desc, hdr);
@@ -3012,9 +3013,10 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
* Call the appropriate parallel I/O subsystem read function.
*/
static enum pnfs_try_status
-pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
- const struct rpc_call_ops *call_ops,
- struct pnfs_layout_segment *lseg)
+pnfs_try_to_read_data(struct nfs_pageio_descriptor *desc,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops,
+ struct pnfs_layout_segment *lseg)
{
struct inode *inode = hdr->inode;
struct nfs_server *nfss = NFS_SERVER(inode);
@@ -3025,7 +3027,7 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
dprintk("%s: Reading ino:%lu %u@%llu\n",
__func__, inode->i_ino, hdr->args.count, hdr->args.offset);
- trypnfs = nfss->pnfs_curr_ld->read_pagelist(hdr);
+ trypnfs = nfss->pnfs_curr_ld->read_pagelist(desc, hdr);
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_READ);
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
@@ -3058,7 +3060,7 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
- trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
+ trypnfs = pnfs_try_to_read_data(desc, hdr, call_ops, lseg);
switch (trypnfs) {
case PNFS_NOT_ATTEMPTED:
pnfs_read_through_mds(desc, hdr);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index fa5beeaaf5da..92acb837cfa6 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -157,8 +157,10 @@ struct pnfs_layoutdriver_type {
* Return PNFS_ATTEMPTED to indicate the layout code has attempted
* I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
*/
- enum pnfs_try_status (*read_pagelist)(struct nfs_pgio_header *);
- enum pnfs_try_status (*write_pagelist)(struct nfs_pgio_header *, int);
+ enum pnfs_try_status (*read_pagelist)(struct nfs_pageio_descriptor *,
+ struct nfs_pgio_header *);
+ enum pnfs_try_status (*write_pagelist)(struct nfs_pageio_descriptor *,
+ struct nfs_pgio_header *, int);
void (*free_deviceid_node) (struct nfs4_deviceid_node *);
struct nfs4_deviceid_node * (*alloc_deviceid_node)
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 03/20] nfs: pass struct file to nfs_init_pgio and nfs_init_commit
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 01/20] nfs: pass nfs_client to nfs_initiate_pgio Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 02/20] nfs: pass descriptor thru nfs_initiate_pgio path Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 04/20] sunrpc: add rpcauth_map_to_svc_cred_local Mike Snitzer
` (17 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Weston Andros Adamson <dros@primarydata.com>
This is needed for localio support.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/filelayout/filelayout.c | 6 +++---
fs/nfs/flexfilelayout/flexfilelayout.c | 6 +++---
fs/nfs/internal.h | 6 ++++--
fs/nfs/pagelist.c | 6 ++++--
fs/nfs/pnfs_nfs.c | 2 +-
fs/nfs/write.c | 5 +++--
6 files changed, 18 insertions(+), 13 deletions(-)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index f9b600c4a2b5..b9e5e7bd15ca 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -489,7 +489,7 @@ filelayout_read_pagelist(struct nfs_pageio_descriptor *desc,
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
- 0, RPC_TASK_SOFTCONN);
+ 0, RPC_TASK_SOFTCONN, NULL);
return PNFS_ATTEMPTED;
}
@@ -532,7 +532,7 @@ filelayout_write_pagelist(struct nfs_pageio_descriptor *desc,
/* Perform an asynchronous write */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, hdr->cred,
NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
- sync, RPC_TASK_SOFTCONN);
+ sync, RPC_TASK_SOFTCONN, NULL);
return PNFS_ATTEMPTED;
}
@@ -1013,7 +1013,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
data->args.fh = fh;
return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
&filelayout_commit_call_ops, how,
- RPC_TASK_SOFTCONN);
+ RPC_TASK_SOFTCONN, NULL);
out_err:
pnfs_generic_prepare_to_resend_writes(data);
pnfs_generic_commit_release(data);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 22c0e8014afb..3ea07446f05a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1808,7 +1808,7 @@ ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
- 0, RPC_TASK_SOFTCONN);
+ 0, RPC_TASK_SOFTCONN, NULL);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1878,7 +1878,7 @@ ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
- sync, RPC_TASK_SOFTCONN);
+ sync, RPC_TASK_SOFTCONN, NULL);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1953,7 +1953,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
- how, RPC_TASK_SOFTCONN);
+ how, RPC_TASK_SOFTCONN, NULL);
put_cred(ds_cred);
return ret;
out_err:
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f6e56fdd8bc2..958c8de072e2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -309,7 +309,8 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
int nfs_initiate_pgio(struct nfs_pageio_descriptor *, struct nfs_client *clp,
struct rpc_clnt *rpc_clnt, struct nfs_pgio_header *hdr,
const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
- const struct rpc_call_ops *call_ops, int how, int flags);
+ const struct rpc_call_ops *call_ops, int how, int flags,
+ struct file *localio);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
@@ -529,7 +530,8 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt,
struct nfs_commit_data *data,
const struct nfs_rpc_ops *nfs_ops,
const struct rpc_call_ops *call_ops,
- int how, int flags);
+ int how, int flags,
+ struct file *localio);
extern void nfs_init_commit(struct nfs_commit_data *data,
struct list_head *head,
struct pnfs_layout_segment *lseg,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 3786d767e2ff..57d62db3be5b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -848,7 +848,8 @@ int nfs_initiate_pgio(struct nfs_pageio_descriptor *desc,
struct nfs_client *clp, struct rpc_clnt *rpc_clnt,
struct nfs_pgio_header *hdr, const struct cred *cred,
const struct nfs_rpc_ops *rpc_ops,
- const struct rpc_call_ops *call_ops, int how, int flags)
+ const struct rpc_call_ops *call_ops, int how, int flags,
+ struct file *localio)
{
struct rpc_task *task;
struct rpc_message msg = {
@@ -1080,7 +1081,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
NFS_PROTO(hdr->inode),
desc->pg_rpc_callops,
desc->pg_ioflags,
- RPC_TASK_CRED_NOREF | task_flags);
+ RPC_TASK_CRED_NOREF | task_flags,
+ NULL);
}
return ret;
}
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 88e061bd711b..ecfde2649cf3 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -537,7 +537,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
nfs_initiate_commit(NFS_CLIENT(inode), data,
NFS_PROTO(data->inode),
data->mds_ops, how,
- RPC_TASK_CRED_NOREF);
+ RPC_TASK_CRED_NOREF, NULL);
} else {
nfs_init_commit(data, NULL, data->lseg, cinfo);
initiate_commit(data, how);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2329cbb0e446..267bed2a4ceb 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1670,7 +1670,8 @@ EXPORT_SYMBOL_GPL(nfs_commitdata_release);
int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
const struct nfs_rpc_ops *nfs_ops,
const struct rpc_call_ops *call_ops,
- int how, int flags)
+ int how, int flags,
+ struct file *localio)
{
struct rpc_task *task;
int priority = flush_task_priority(how);
@@ -1816,7 +1817,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
task_flags = RPC_TASK_MOVEABLE;
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
data->mds_ops, how,
- RPC_TASK_CRED_NOREF | task_flags);
+ RPC_TASK_CRED_NOREF | task_flags, NULL);
}
/*
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 04/20] sunrpc: add rpcauth_map_to_svc_cred_local
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (2 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 03/20] nfs: pass struct file to nfs_init_pgio and nfs_init_commit Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement Mike Snitzer
` (16 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Weston Andros Adamson <dros@primarydata.com>
Add new funtion rpcauth_map_to_svc_cred_local which maps a generic
cred to a svc_cred suitable for use in nfsd.
This is needed by the localio code to map nfs client creds to nfs
server credentials.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
include/linux/sunrpc/auth.h | 4 ++++
net/sunrpc/auth.c | 15 +++++++++++++++
2 files changed, 19 insertions(+)
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 61e58327b1aa..872f594a924c 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -11,6 +11,7 @@
#define _LINUX_SUNRPC_AUTH_H
#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/svcauth.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/xdr.h>
@@ -184,6 +185,9 @@ int rpcauth_uptodatecred(struct rpc_task *);
int rpcauth_init_credcache(struct rpc_auth *);
void rpcauth_destroy_credcache(struct rpc_auth *);
void rpcauth_clear_credcache(struct rpc_cred_cache *);
+void rpcauth_map_to_svc_cred_local(struct rpc_auth *,
+ const struct cred *,
+ struct svc_cred *);
char * rpcauth_stringify_acceptor(struct rpc_cred *);
static inline
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 04534ea537c8..00f12ca779c5 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -308,6 +308,21 @@ rpcauth_init_credcache(struct rpc_auth *auth)
}
EXPORT_SYMBOL_GPL(rpcauth_init_credcache);
+void
+rpcauth_map_to_svc_cred_local(struct rpc_auth *auth, const struct cred *cred,
+ struct svc_cred *svc)
+{
+ svc->cr_uid = cred->uid;
+ svc->cr_gid = cred->gid;
+ svc->cr_flavor = auth->au_flavor;
+ if (cred->group_info)
+ svc->cr_group_info = get_group_info(cred->group_info);
+ /* These aren't relevant for local (network is bypassed) */
+ svc->cr_principal = NULL;
+ svc->cr_gss_mech = NULL;
+}
+EXPORT_SYMBOL_GPL(rpcauth_map_to_svc_cred_local);
+
char *
rpcauth_stringify_acceptor(struct rpc_cred *cred)
{
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (3 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 04/20] sunrpc: add rpcauth_map_to_svc_cred_local Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 23:33 ` NeilBrown
2024-06-24 16:27 ` [PATCH v7 06/20] nfs/nfsd: add "localio" support Mike Snitzer
` (15 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
First use is in nfsd, to add access to a global nfsd_uuids list that
will be used to identify local nfsd instances.
nfsd_uuids is protected by nfsd_mutex or RCU read lock. List is
composed of nfsd_uuid_t instances that are managed as nfsd creates
them (per network namespace).
nfsd_uuid_is_local() will be used to search all local nfsd for the
client specified nfsd uuid.
This commit also adds all the nfs_client members required to implement
the entire localio feature (which depends on the LOCALIO protocol).
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/client.c | 8 +++++
fs/nfs_common/Makefile | 3 ++
fs/nfs_common/nfslocalio.c | 72 ++++++++++++++++++++++++++++++++++++++
fs/nfsd/netns.h | 4 +++
fs/nfsd/nfssvc.c | 12 ++++++-
include/linux/nfs_fs_sb.h | 9 +++++
include/linux/nfslocalio.h | 39 +++++++++++++++++++++
7 files changed, 146 insertions(+), 1 deletion(-)
create mode 100644 fs/nfs_common/nfslocalio.c
create mode 100644 include/linux/nfslocalio.h
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index de77848ae654..bcdf8d42cbc7 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
clp->cl_net = get_net(cl_init->net);
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ seqlock_init(&clp->cl_boot_lock);
+ ktime_get_real_ts64(&clp->cl_nfssvc_boot);
+ clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
+ clp->nfsd_open_local_fh = NULL;
+ clp->cl_nfssvc_net = NULL;
+#endif /* CONFIG_NFS_LOCALIO */
+
clp->cl_principal = "*";
clp->cl_xprtsec = cl_init->xprtsec;
return clp;
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index 119c75ab9fd0..d81623b76aba 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -6,5 +6,8 @@
obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
nfs_acl-objs := nfsacl.o
+obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o
+nfs_localio-objs := nfslocalio.o
+
obj-$(CONFIG_GRACE_PERIOD) += grace.o
obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o
diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
new file mode 100644
index 000000000000..755b84b742a6
--- /dev/null
+++ b/fs/nfs_common/nfslocalio.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+
+#include <linux/module.h>
+#include <linux/rculist.h>
+#include <linux/nfslocalio.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("NFS localio protocol bypass support");
+
+/*
+ * Global list of nfsd_uuid_t instances, add/remove
+ * is protected by fs/nfsd/nfssvc.c:nfsd_mutex.
+ * Reads are protected by RCU read lock (see below).
+ */
+LIST_HEAD(nfsd_uuids);
+EXPORT_SYMBOL(nfsd_uuids);
+
+/* Must be called with RCU read lock held. */
+static const uuid_t * nfsd_uuid_lookup(const uuid_t *uuid,
+ struct net **netp)
+{
+ nfsd_uuid_t *nfsd_uuid;
+
+ list_for_each_entry_rcu(nfsd_uuid, &nfsd_uuids, list)
+ if (uuid_equal(&nfsd_uuid->uuid, uuid)) {
+ *netp = nfsd_uuid->net;
+ return &nfsd_uuid->uuid;
+ }
+
+ return &uuid_null;
+}
+
+bool nfsd_uuid_is_local(const uuid_t *uuid, struct net **netp)
+{
+ const uuid_t *nfsd_uuid;
+
+ rcu_read_lock();
+ nfsd_uuid = nfsd_uuid_lookup(uuid, netp);
+ rcu_read_unlock();
+
+ return !uuid_is_null(nfsd_uuid);
+}
+EXPORT_SYMBOL_GPL(nfsd_uuid_is_local);
+
+/*
+ * The nfs localio code needs to call into nfsd to do the filehandle -> struct path
+ * mapping, but cannot be statically linked, because that will make the nfs module
+ * depend on the nfsd module.
+ *
+ * Instead, do dynamic linking to the nfsd module (via nfs_common module). The
+ * nfs_common module will only hold a reference on nfsd when localio is in use.
+ * This allows some sanity checking, like giving up on localio if nfsd isn't loaded.
+ */
+
+extern int nfsd_open_local_fh(struct net *, struct rpc_clnt *rpc_clnt,
+ const struct cred *cred, const struct nfs_fh *nfs_fh,
+ const fmode_t fmode, struct file **pfilp);
+
+nfs_to_nfsd_open_t get_nfsd_open_local_fh(void)
+{
+ return symbol_request(nfsd_open_local_fh);
+}
+EXPORT_SYMBOL_GPL(get_nfsd_open_local_fh);
+
+void put_nfsd_open_local_fh(void)
+{
+ symbol_put(nfsd_open_local_fh);
+}
+EXPORT_SYMBOL_GPL(put_nfsd_open_local_fh);
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 14ec15656320..0c5a1d97e4ac 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -15,6 +15,7 @@
#include <linux/percpu_counter.h>
#include <linux/siphash.h>
#include <linux/sunrpc/stats.h>
+#include <linux/nfslocalio.h>
/* Hash tables for nfs4_clientid state */
#define CLIENT_HASH_BITS 4
@@ -213,6 +214,9 @@ struct nfsd_net {
/* last time an admin-revoke happened for NFSv4.0 */
time64_t nfs40_last_revoke;
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ nfsd_uuid_t nfsd_uuid;
+#endif
};
/* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9edb4f7c4cc2..1222a0a33fe1 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -19,6 +19,7 @@
#include <linux/sunrpc/svc_xprt.h>
#include <linux/lockd/bind.h>
#include <linux/nfsacl.h>
+#include <linux/nfslocalio.h>
#include <linux/seq_file.h>
#include <linux/inetdevice.h>
#include <net/addrconf.h>
@@ -427,6 +428,10 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred)
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
nfsd4_ssc_init_umount_work(nn);
+#endif
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ INIT_LIST_HEAD(&nn->nfsd_uuid.list);
+ list_add_tail_rcu(&nn->nfsd_uuid.list, &nfsd_uuids);
#endif
nn->nfsd_net_up = true;
return 0;
@@ -456,6 +461,9 @@ static void nfsd_shutdown_net(struct net *net)
lockd_down(net);
nn->lockd_up = false;
}
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ list_del_rcu(&nn->nfsd_uuid.list);
+#endif
nn->nfsd_net_up = false;
nfsd_shutdown_generic();
}
@@ -802,7 +810,9 @@ nfsd_svc(int n, int *nthreads, struct net *net, const struct cred *cred, const c
strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename,
sizeof(nn->nfsd_name));
-
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ uuid_gen(&nn->nfsd_uuid.uuid);
+#endif
error = nfsd_create_serv(net);
if (error)
goto out;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 92de074e63b9..e58e706a6503 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -8,6 +8,7 @@
#include <linux/wait.h>
#include <linux/nfs_xdr.h>
#include <linux/sunrpc/xprt.h>
+#include <linux/nfslocalio.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
@@ -125,6 +126,14 @@ struct nfs_client {
struct net *cl_net;
struct list_head pending_cb_stateids;
struct rcu_head rcu;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ struct timespec64 cl_nfssvc_boot;
+ seqlock_t cl_boot_lock;
+ struct rpc_clnt * cl_rpcclient_localio;
+ struct net * cl_nfssvc_net;
+ nfs_to_nfsd_open_t nfsd_open_local_fh;
+#endif /* CONFIG_NFS_LOCALIO */
};
/*
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
new file mode 100644
index 000000000000..c9592ad0afe2
--- /dev/null
+++ b/include/linux/nfslocalio.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+#ifndef __LINUX_NFSLOCALIO_H
+#define __LINUX_NFSLOCALIO_H
+
+#include <linux/list.h>
+#include <linux/uuid.h>
+#include <linux/nfs.h>
+#include <net/net_namespace.h>
+
+/*
+ * Global list of nfsd_uuid_t instances, add/remove
+ * is protected by fs/nfsd/nfssvc.c:nfsd_mutex.
+ */
+extern struct list_head nfsd_uuids;
+
+/*
+ * Each nfsd instance has an nfsd_uuid_t that is accessible through the
+ * global nfsd_uuids list. Useful to allow a client to negotiate if localio
+ * possible with its server.
+ */
+typedef struct {
+ uuid_t uuid;
+ struct list_head list;
+ struct net *net; /* nfsd's network namespace */
+} nfsd_uuid_t;
+
+bool nfsd_uuid_is_local(const uuid_t *uuid, struct net **netp);
+
+typedef int (*nfs_to_nfsd_open_t)(struct net *, struct rpc_clnt *,
+ const struct cred *, const struct nfs_fh *,
+ const fmode_t, struct file **);
+
+nfs_to_nfsd_open_t get_nfsd_open_local_fh(void);
+void put_nfsd_open_local_fh(void);
+
+#endif /* __LINUX_NFSLOCALIO_H */
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement
2024-06-24 16:27 ` [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement Mike Snitzer
@ 2024-06-25 23:33 ` NeilBrown
2024-06-26 16:50 ` Mike Snitzer
0 siblings, 1 reply; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:33 UTC (permalink / raw)
To: Mike Snitzer
Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Mike Snitzer wrote:
> First use is in nfsd, to add access to a global nfsd_uuids list that
> will be used to identify local nfsd instances.
>
> nfsd_uuids is protected by nfsd_mutex or RCU read lock. List is
> composed of nfsd_uuid_t instances that are managed as nfsd creates
> them (per network namespace).
>
> nfsd_uuid_is_local() will be used to search all local nfsd for the
> client specified nfsd uuid.
>
> This commit also adds all the nfs_client members required to implement
> the entire localio feature (which depends on the LOCALIO protocol).
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> fs/nfs/client.c | 8 +++++
> fs/nfs_common/Makefile | 3 ++
> fs/nfs_common/nfslocalio.c | 72 ++++++++++++++++++++++++++++++++++++++
> fs/nfsd/netns.h | 4 +++
> fs/nfsd/nfssvc.c | 12 ++++++-
> include/linux/nfs_fs_sb.h | 9 +++++
> include/linux/nfslocalio.h | 39 +++++++++++++++++++++
> 7 files changed, 146 insertions(+), 1 deletion(-)
> create mode 100644 fs/nfs_common/nfslocalio.c
> create mode 100644 include/linux/nfslocalio.h
>
> diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> index de77848ae654..bcdf8d42cbc7 100644
> --- a/fs/nfs/client.c
> +++ b/fs/nfs/client.c
> @@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
> clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
> clp->cl_net = get_net(cl_init->net);
>
> +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> + seqlock_init(&clp->cl_boot_lock);
> + ktime_get_real_ts64(&clp->cl_nfssvc_boot);
> + clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
> + clp->nfsd_open_local_fh = NULL;
> + clp->cl_nfssvc_net = NULL;
> +#endif /* CONFIG_NFS_LOCALIO */
> +
> clp->cl_principal = "*";
> clp->cl_xprtsec = cl_init->xprtsec;
> return clp;
> diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
> index 119c75ab9fd0..d81623b76aba 100644
> --- a/fs/nfs_common/Makefile
> +++ b/fs/nfs_common/Makefile
> @@ -6,5 +6,8 @@
> obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
> nfs_acl-objs := nfsacl.o
>
> +obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o
> +nfs_localio-objs := nfslocalio.o
> +
> obj-$(CONFIG_GRACE_PERIOD) += grace.o
> obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o
> diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
> new file mode 100644
> index 000000000000..755b84b742a6
> --- /dev/null
> +++ b/fs/nfs_common/nfslocalio.c
> @@ -0,0 +1,72 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> + */
> +
> +#include <linux/module.h>
> +#include <linux/rculist.h>
> +#include <linux/nfslocalio.h>
> +
> +MODULE_LICENSE("GPL");
> +MODULE_DESCRIPTION("NFS localio protocol bypass support");
> +
> +/*
> + * Global list of nfsd_uuid_t instances, add/remove
> + * is protected by fs/nfsd/nfssvc.c:nfsd_mutex.
> + * Reads are protected by RCU read lock (see below).
> + */
> +LIST_HEAD(nfsd_uuids);
> +EXPORT_SYMBOL(nfsd_uuids);
> +
> +/* Must be called with RCU read lock held. */
> +static const uuid_t * nfsd_uuid_lookup(const uuid_t *uuid,
> + struct net **netp)
> +{
> + nfsd_uuid_t *nfsd_uuid;
> +
> + list_for_each_entry_rcu(nfsd_uuid, &nfsd_uuids, list)
> + if (uuid_equal(&nfsd_uuid->uuid, uuid)) {
> + *netp = nfsd_uuid->net;
> + return &nfsd_uuid->uuid;
> + }
> +
> + return &uuid_null;
> +}
> +
> +bool nfsd_uuid_is_local(const uuid_t *uuid, struct net **netp)
> +{
> + const uuid_t *nfsd_uuid;
> +
> + rcu_read_lock();
> + nfsd_uuid = nfsd_uuid_lookup(uuid, netp);
> + rcu_read_unlock();
> +
> + return !uuid_is_null(nfsd_uuid);
This is still unsafe. You can only safely dereference nfsd_uuid while
still holding the rcu_read_lock.
NeilBrown
> +}
> +EXPORT_SYMBOL_GPL(nfsd_uuid_is_local);
> +
> +/*
> + * The nfs localio code needs to call into nfsd to do the filehandle -> struct path
> + * mapping, but cannot be statically linked, because that will make the nfs module
> + * depend on the nfsd module.
> + *
> + * Instead, do dynamic linking to the nfsd module (via nfs_common module). The
> + * nfs_common module will only hold a reference on nfsd when localio is in use.
> + * This allows some sanity checking, like giving up on localio if nfsd isn't loaded.
> + */
> +
> +extern int nfsd_open_local_fh(struct net *, struct rpc_clnt *rpc_clnt,
> + const struct cred *cred, const struct nfs_fh *nfs_fh,
> + const fmode_t fmode, struct file **pfilp);
> +
> +nfs_to_nfsd_open_t get_nfsd_open_local_fh(void)
> +{
> + return symbol_request(nfsd_open_local_fh);
> +}
> +EXPORT_SYMBOL_GPL(get_nfsd_open_local_fh);
> +
> +void put_nfsd_open_local_fh(void)
> +{
> + symbol_put(nfsd_open_local_fh);
> +}
> +EXPORT_SYMBOL_GPL(put_nfsd_open_local_fh);
> diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
> index 14ec15656320..0c5a1d97e4ac 100644
> --- a/fs/nfsd/netns.h
> +++ b/fs/nfsd/netns.h
> @@ -15,6 +15,7 @@
> #include <linux/percpu_counter.h>
> #include <linux/siphash.h>
> #include <linux/sunrpc/stats.h>
> +#include <linux/nfslocalio.h>
>
> /* Hash tables for nfs4_clientid state */
> #define CLIENT_HASH_BITS 4
> @@ -213,6 +214,9 @@ struct nfsd_net {
> /* last time an admin-revoke happened for NFSv4.0 */
> time64_t nfs40_last_revoke;
>
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + nfsd_uuid_t nfsd_uuid;
> +#endif
> };
>
> /* Simple check to find out if a given net was properly initialized */
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index 9edb4f7c4cc2..1222a0a33fe1 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -19,6 +19,7 @@
> #include <linux/sunrpc/svc_xprt.h>
> #include <linux/lockd/bind.h>
> #include <linux/nfsacl.h>
> +#include <linux/nfslocalio.h>
> #include <linux/seq_file.h>
> #include <linux/inetdevice.h>
> #include <net/addrconf.h>
> @@ -427,6 +428,10 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred)
>
> #ifdef CONFIG_NFSD_V4_2_INTER_SSC
> nfsd4_ssc_init_umount_work(nn);
> +#endif
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + INIT_LIST_HEAD(&nn->nfsd_uuid.list);
> + list_add_tail_rcu(&nn->nfsd_uuid.list, &nfsd_uuids);
> #endif
> nn->nfsd_net_up = true;
> return 0;
> @@ -456,6 +461,9 @@ static void nfsd_shutdown_net(struct net *net)
> lockd_down(net);
> nn->lockd_up = false;
> }
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + list_del_rcu(&nn->nfsd_uuid.list);
> +#endif
> nn->nfsd_net_up = false;
> nfsd_shutdown_generic();
> }
> @@ -802,7 +810,9 @@ nfsd_svc(int n, int *nthreads, struct net *net, const struct cred *cred, const c
>
> strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename,
> sizeof(nn->nfsd_name));
> -
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + uuid_gen(&nn->nfsd_uuid.uuid);
> +#endif
> error = nfsd_create_serv(net);
> if (error)
> goto out;
> diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
> index 92de074e63b9..e58e706a6503 100644
> --- a/include/linux/nfs_fs_sb.h
> +++ b/include/linux/nfs_fs_sb.h
> @@ -8,6 +8,7 @@
> #include <linux/wait.h>
> #include <linux/nfs_xdr.h>
> #include <linux/sunrpc/xprt.h>
> +#include <linux/nfslocalio.h>
>
> #include <linux/atomic.h>
> #include <linux/refcount.h>
> @@ -125,6 +126,14 @@ struct nfs_client {
> struct net *cl_net;
> struct list_head pending_cb_stateids;
> struct rcu_head rcu;
> +
> +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> + struct timespec64 cl_nfssvc_boot;
> + seqlock_t cl_boot_lock;
> + struct rpc_clnt * cl_rpcclient_localio;
> + struct net * cl_nfssvc_net;
> + nfs_to_nfsd_open_t nfsd_open_local_fh;
> +#endif /* CONFIG_NFS_LOCALIO */
> };
>
> /*
> diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
> new file mode 100644
> index 000000000000..c9592ad0afe2
> --- /dev/null
> +++ b/include/linux/nfslocalio.h
> @@ -0,0 +1,39 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> + */
> +#ifndef __LINUX_NFSLOCALIO_H
> +#define __LINUX_NFSLOCALIO_H
> +
> +#include <linux/list.h>
> +#include <linux/uuid.h>
> +#include <linux/nfs.h>
> +#include <net/net_namespace.h>
> +
> +/*
> + * Global list of nfsd_uuid_t instances, add/remove
> + * is protected by fs/nfsd/nfssvc.c:nfsd_mutex.
> + */
> +extern struct list_head nfsd_uuids;
> +
> +/*
> + * Each nfsd instance has an nfsd_uuid_t that is accessible through the
> + * global nfsd_uuids list. Useful to allow a client to negotiate if localio
> + * possible with its server.
> + */
> +typedef struct {
> + uuid_t uuid;
> + struct list_head list;
> + struct net *net; /* nfsd's network namespace */
> +} nfsd_uuid_t;
> +
> +bool nfsd_uuid_is_local(const uuid_t *uuid, struct net **netp);
> +
> +typedef int (*nfs_to_nfsd_open_t)(struct net *, struct rpc_clnt *,
> + const struct cred *, const struct nfs_fh *,
> + const fmode_t, struct file **);
> +
> +nfs_to_nfsd_open_t get_nfsd_open_local_fh(void);
> +void put_nfsd_open_local_fh(void);
> +
> +#endif /* __LINUX_NFSLOCALIO_H */
> --
> 2.44.0
>
>
>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement
2024-06-25 23:33 ` NeilBrown
@ 2024-06-26 16:50 ` Mike Snitzer
0 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-26 16:50 UTC (permalink / raw)
To: NeilBrown; +Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Wed, Jun 26, 2024 at 09:33:03AM +1000, NeilBrown wrote:
> On Tue, 25 Jun 2024, Mike Snitzer wrote:
> > First use is in nfsd, to add access to a global nfsd_uuids list that
> > will be used to identify local nfsd instances.
> >
> > nfsd_uuids is protected by nfsd_mutex or RCU read lock. List is
> > composed of nfsd_uuid_t instances that are managed as nfsd creates
> > them (per network namespace).
> >
> > nfsd_uuid_is_local() will be used to search all local nfsd for the
> > client specified nfsd uuid.
> >
> > This commit also adds all the nfs_client members required to implement
> > the entire localio feature (which depends on the LOCALIO protocol).
> >
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > ---
> > fs/nfs/client.c | 8 +++++
> > fs/nfs_common/Makefile | 3 ++
> > fs/nfs_common/nfslocalio.c | 72 ++++++++++++++++++++++++++++++++++++++
> > fs/nfsd/netns.h | 4 +++
> > fs/nfsd/nfssvc.c | 12 ++++++-
> > include/linux/nfs_fs_sb.h | 9 +++++
> > include/linux/nfslocalio.h | 39 +++++++++++++++++++++
> > 7 files changed, 146 insertions(+), 1 deletion(-)
> > create mode 100644 fs/nfs_common/nfslocalio.c
> > create mode 100644 include/linux/nfslocalio.h
> >
> > diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> > index de77848ae654..bcdf8d42cbc7 100644
> > --- a/fs/nfs/client.c
> > +++ b/fs/nfs/client.c
> > @@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
> > clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
> > clp->cl_net = get_net(cl_init->net);
> >
> > +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> > + seqlock_init(&clp->cl_boot_lock);
> > + ktime_get_real_ts64(&clp->cl_nfssvc_boot);
> > + clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
> > + clp->nfsd_open_local_fh = NULL;
> > + clp->cl_nfssvc_net = NULL;
> > +#endif /* CONFIG_NFS_LOCALIO */
> > +
> > clp->cl_principal = "*";
> > clp->cl_xprtsec = cl_init->xprtsec;
> > return clp;
> > diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
> > index 119c75ab9fd0..d81623b76aba 100644
> > --- a/fs/nfs_common/Makefile
> > +++ b/fs/nfs_common/Makefile
> > @@ -6,5 +6,8 @@
> > obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
> > nfs_acl-objs := nfsacl.o
> >
> > +obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o
> > +nfs_localio-objs := nfslocalio.o
> > +
> > obj-$(CONFIG_GRACE_PERIOD) += grace.o
> > obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o
> > diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
> > new file mode 100644
> > index 000000000000..755b84b742a6
> > --- /dev/null
> > +++ b/fs/nfs_common/nfslocalio.c
> > @@ -0,0 +1,72 @@
> > +// SPDX-License-Identifier: GPL-2.0-only
> > +/*
> > + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> > + */
> > +
> > +#include <linux/module.h>
> > +#include <linux/rculist.h>
> > +#include <linux/nfslocalio.h>
> > +
> > +MODULE_LICENSE("GPL");
> > +MODULE_DESCRIPTION("NFS localio protocol bypass support");
> > +
> > +/*
> > + * Global list of nfsd_uuid_t instances, add/remove
> > + * is protected by fs/nfsd/nfssvc.c:nfsd_mutex.
> > + * Reads are protected by RCU read lock (see below).
> > + */
> > +LIST_HEAD(nfsd_uuids);
> > +EXPORT_SYMBOL(nfsd_uuids);
> > +
> > +/* Must be called with RCU read lock held. */
> > +static const uuid_t * nfsd_uuid_lookup(const uuid_t *uuid,
> > + struct net **netp)
> > +{
> > + nfsd_uuid_t *nfsd_uuid;
> > +
> > + list_for_each_entry_rcu(nfsd_uuid, &nfsd_uuids, list)
> > + if (uuid_equal(&nfsd_uuid->uuid, uuid)) {
> > + *netp = nfsd_uuid->net;
> > + return &nfsd_uuid->uuid;
> > + }
> > +
> > + return &uuid_null;
> > +}
> > +
> > +bool nfsd_uuid_is_local(const uuid_t *uuid, struct net **netp)
> > +{
> > + const uuid_t *nfsd_uuid;
> > +
> > + rcu_read_lock();
> > + nfsd_uuid = nfsd_uuid_lookup(uuid, netp);
> > + rcu_read_unlock();
> > +
> > + return !uuid_is_null(nfsd_uuid);
>
> This is still unsafe. You can only safely dereference nfsd_uuid while
> still holding the rcu_read_lock.
Fixed, thanks.
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 06/20] nfs/nfsd: add "localio" support
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (4 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 05/20] nfs_common: add NFS LOCALIO auxiliary protocol enablement Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 18:26 ` Chuck Lever
2024-06-24 16:27 ` [PATCH v7 07/20] nfsd/localio: manage netns reference in nfsd_open_local_fh Mike Snitzer
` (14 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Weston Andros Adamson <dros@primarydata.com>
Add client support for bypassing NFS for localhost reads, writes, and
commits. This is only useful when the client and the server are
running on the same host.
nfs_local_probe() is stubbed out, later commits will enable client and
server handshake via a Linux-only LOCALIO auxiliary RPC protocol.
This has dynamic binding with the nfsd module (via nfs_localio module
which is part of nfs_common). Localio will only work if nfsd is
already loaded.
The "localio_enabled" nfs kernel module parameter can be used to
disable and enable the ability to use localio support.
Tracepoints were added for nfs_local_open_fh, nfs_local_enable and
nfs_local_disable.
Also, pass the stored cl_nfssvc_net from the client to the server as
first argument to nfsd_open_local_fh() to ensure the proper network
namespace is used for localio.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/Makefile | 1 +
fs/nfs/client.c | 3 +
fs/nfs/inode.c | 4 +
fs/nfs/internal.h | 51 +++
fs/nfs/localio.c | 654 ++++++++++++++++++++++++++++++++++++++
fs/nfs/nfstrace.h | 61 ++++
fs/nfs/pagelist.c | 3 +
fs/nfs/write.c | 3 +
fs/nfsd/Makefile | 1 +
fs/nfsd/filecache.c | 2 +-
fs/nfsd/localio.c | 244 ++++++++++++++
fs/nfsd/nfssvc.c | 1 +
fs/nfsd/trace.h | 3 +-
fs/nfsd/vfs.h | 9 +
include/linux/nfs.h | 2 +
include/linux/nfs_fs.h | 2 +
include/linux/nfs_fs_sb.h | 1 +
17 files changed, 1043 insertions(+), 2 deletions(-)
create mode 100644 fs/nfs/localio.c
create mode 100644 fs/nfsd/localio.c
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 5f6db37f461e..9fb2f2cac87e 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -13,6 +13,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \
nfs-$(CONFIG_ROOT_NFS) += nfsroot.o
nfs-$(CONFIG_SYSCTL) += sysctl.o
nfs-$(CONFIG_NFS_FSCACHE) += fscache.o
+nfs-$(CONFIG_NFS_LOCALIO) += localio.o
obj-$(CONFIG_NFS_V2) += nfsv2.o
nfsv2-y := nfs2super.o proc.o nfs2xdr.o
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index bcdf8d42cbc7..1300c388f971 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -241,6 +241,8 @@ static void pnfs_init_server(struct nfs_server *server)
*/
void nfs_free_client(struct nfs_client *clp)
{
+ nfs_local_disable(clp);
+
/* -EIO all pending I/O */
if (!IS_ERR(clp->cl_rpcclient))
rpc_shutdown_client(clp->cl_rpcclient);
@@ -432,6 +434,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
list_add_tail(&new->cl_share_link,
&nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
+ nfs_local_probe(new);
return rpc_ops->init_client(new, cl_init);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index acef52ecb1bb..f9923cbf6058 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -39,6 +39,7 @@
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/freezer.h>
+#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
@@ -1053,6 +1054,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
ctx->lock_context.open_context = ctx;
INIT_LIST_HEAD(&ctx->list);
ctx->mdsthreshold = NULL;
+ ctx->local_filp = NULL;
return ctx;
}
EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
@@ -1084,6 +1086,8 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
nfs_sb_deactive(sb);
put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
kfree(ctx->mdsthreshold);
+ if (!IS_ERR_OR_NULL(ctx->local_filp))
+ fput(ctx->local_filp);
kfree_rcu(ctx, rcu_head);
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 958c8de072e2..d352040e3232 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -451,6 +451,57 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+/* localio.c */
+extern void nfs_local_disable(struct nfs_client *);
+extern void nfs_local_probe(struct nfs_client *);
+extern struct file *nfs_local_open_fh(struct nfs_client *, const struct cred *,
+ struct nfs_fh *, const fmode_t);
+extern struct file *nfs_local_file_open(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ struct nfs_open_context *ctx);
+extern int nfs_local_doio(struct nfs_client *, struct file *,
+ struct nfs_pgio_header *,
+ const struct rpc_call_ops *);
+extern int nfs_local_commit(struct file *, struct nfs_commit_data *,
+ const struct rpc_call_ops *, int);
+extern bool nfs_server_is_local(const struct nfs_client *clp);
+
+#else
+static inline void nfs_local_disable(struct nfs_client *clp) {}
+static inline void nfs_local_probe(struct nfs_client *clp) {}
+static inline struct file *nfs_local_open_fh(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ const fmode_t mode)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline struct file *nfs_local_file_open(struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ struct nfs_open_context *ctx)
+{
+ return NULL;
+}
+static inline int nfs_local_doio(struct nfs_client *clp, struct file *filep,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ return -EINVAL;
+}
+static inline int nfs_local_commit(struct file *filep, struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops, int how)
+{
+ return -EINVAL;
+}
+static inline bool nfs_server_is_local(const struct nfs_client *clp)
+{
+ return false;
+}
+#endif /* CONFIG_NFS_LOCALIO */
+
/* super.c */
extern const struct super_operations nfs_sops;
bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
new file mode 100644
index 000000000000..724e81716b16
--- /dev/null
+++ b/fs/nfs/localio.c
@@ -0,0 +1,654 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS client support for local clients to bypass network stack
+ *
+ * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
+ * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/vfs.h>
+#include <linux/file.h>
+#include <linux/inet.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#include <linux/module.h>
+#include <linux/bvec.h>
+
+#include <linux/nfs.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+
+#include "internal.h"
+#include "pnfs.h"
+#include "nfstrace.h"
+
+#define NFSDBG_FACILITY NFSDBG_VFS
+
+struct nfs_local_kiocb {
+ struct kiocb kiocb;
+ struct bio_vec *bvec;
+ struct nfs_pgio_header *hdr;
+ struct work_struct work;
+};
+
+struct nfs_local_fsync_ctx {
+ struct file *filp;
+ struct nfs_commit_data *data;
+ struct work_struct work;
+ struct kref kref;
+ struct completion *done;
+};
+static void nfs_local_fsync_work(struct work_struct *work);
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ */
+static struct {
+ __u32 stat;
+ int errno;
+} nfs_errtbl[] = {
+ { NFS4_OK, 0 },
+ { NFS4ERR_PERM, -EPERM },
+ { NFS4ERR_NOENT, -ENOENT },
+ { NFS4ERR_IO, -EIO },
+ { NFS4ERR_NXIO, -ENXIO },
+ { NFS4ERR_FBIG, -E2BIG },
+ { NFS4ERR_STALE, -EBADF },
+ { NFS4ERR_ACCESS, -EACCES },
+ { NFS4ERR_EXIST, -EEXIST },
+ { NFS4ERR_XDEV, -EXDEV },
+ { NFS4ERR_MLINK, -EMLINK },
+ { NFS4ERR_NOTDIR, -ENOTDIR },
+ { NFS4ERR_ISDIR, -EISDIR },
+ { NFS4ERR_INVAL, -EINVAL },
+ { NFS4ERR_FBIG, -EFBIG },
+ { NFS4ERR_NOSPC, -ENOSPC },
+ { NFS4ERR_ROFS, -EROFS },
+ { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG },
+ { NFS4ERR_NOTEMPTY, -ENOTEMPTY },
+ { NFS4ERR_DQUOT, -EDQUOT },
+ { NFS4ERR_STALE, -ESTALE },
+ { NFS4ERR_STALE, -EOPENSTALE },
+ { NFS4ERR_DELAY, -ETIMEDOUT },
+ { NFS4ERR_DELAY, -ERESTARTSYS },
+ { NFS4ERR_DELAY, -EAGAIN },
+ { NFS4ERR_DELAY, -ENOMEM },
+ { NFS4ERR_IO, -ETXTBSY },
+ { NFS4ERR_IO, -EBUSY },
+ { NFS4ERR_BADHANDLE, -EBADHANDLE },
+ { NFS4ERR_BAD_COOKIE, -EBADCOOKIE },
+ { NFS4ERR_NOTSUPP, -EOPNOTSUPP },
+ { NFS4ERR_TOOSMALL, -ETOOSMALL },
+ { NFS4ERR_SERVERFAULT, -ESERVERFAULT },
+ { NFS4ERR_SERVERFAULT, -ENFILE },
+ { NFS4ERR_IO, -EREMOTEIO },
+ { NFS4ERR_IO, -EUCLEAN },
+ { NFS4ERR_PERM, -ENOKEY },
+ { NFS4ERR_BADTYPE, -EBADTYPE },
+ { NFS4ERR_SYMLINK, -ELOOP },
+ { NFS4ERR_DEADLOCK, -EDEADLK },
+};
+
+/*
+ * Convert an NFS error code to a local one.
+ * This one is used jointly by NFSv2 and NFSv3.
+ */
+static __u32
+nfs4errno(int errno)
+{
+ unsigned int i;
+ for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
+ if (nfs_errtbl[i].errno == errno)
+ return nfs_errtbl[i].stat;
+ }
+ /* If we cannot translate the error, the recovery routines should
+ * handle it.
+ * Note: remaining NFSv4 error codes have values > 10000, so should
+ * not conflict with native Linux error codes.
+ */
+ return NFS4ERR_SERVERFAULT;
+}
+
+static bool localio_enabled __read_mostly = true;
+module_param(localio_enabled, bool, 0644);
+
+bool nfs_server_is_local(const struct nfs_client *clp)
+{
+ return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 &&
+ localio_enabled;
+}
+EXPORT_SYMBOL_GPL(nfs_server_is_local);
+
+/*
+ * nfs_local_enable - attempt to enable local i/o for an nfs_client
+ */
+static void nfs_local_enable(struct nfs_client *clp, struct net *net)
+{
+ if (READ_ONCE(clp->nfsd_open_local_fh)) {
+ set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+ clp->cl_nfssvc_net = net;
+ trace_nfs_local_enable(clp);
+ }
+}
+
+/*
+ * nfs_local_disable - disable local i/o for an nfs_client
+ */
+void nfs_local_disable(struct nfs_client *clp)
+{
+ if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
+ trace_nfs_local_disable(clp);
+ clp->cl_nfssvc_net = NULL;
+ }
+}
+
+/*
+ * nfs_local_probe - probe local i/o support for an nfs_client
+ */
+void
+nfs_local_probe(struct nfs_client *clp)
+{
+ bool enable = false;
+
+ if (enable)
+ nfs_local_enable(clp);
+}
+EXPORT_SYMBOL_GPL(nfs_local_probe);
+
+/*
+ * nfs_local_open_fh - open a local filehandle
+ *
+ * Returns a pointer to a struct file or an ERR_PTR
+ */
+struct file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, const fmode_t mode)
+{
+ struct file *filp;
+ int status;
+
+ if (mode & ~(FMODE_READ | FMODE_WRITE))
+ return ERR_PTR(-EINVAL);
+
+ status = clp->nfsd_open_local_fh(clp->cl_nfssvc_net, clp->cl_rpcclient,
+ cred, fh, mode, &filp);
+ if (status < 0) {
+ dprintk("%s: open local file failed error=%d\n",
+ __func__, status);
+ trace_nfs_local_open_fh(fh, mode, status);
+ switch (status) {
+ case -ENXIO:
+ nfs_local_disable(clp);
+ fallthrough;
+ case -ETIMEDOUT:
+ status = -EAGAIN;
+ }
+ filp = ERR_PTR(status);
+ }
+ return filp;
+}
+EXPORT_SYMBOL_GPL(nfs_local_open_fh);
+
+static struct bio_vec *
+nfs_bvec_alloc_and_import_pagevec(struct page **pagevec,
+ unsigned int npages, gfp_t flags)
+{
+ struct bio_vec *bvec, *p;
+
+ bvec = kmalloc_array(npages, sizeof(*bvec), flags);
+ if (bvec != NULL) {
+ for (p = bvec; npages > 0; p++, pagevec++, npages--) {
+ p->bv_page = *pagevec;
+ p->bv_len = PAGE_SIZE;
+ p->bv_offset = 0;
+ }
+ }
+ return bvec;
+}
+
+static void
+nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
+{
+ kfree(iocb->bvec);
+ kfree(iocb);
+}
+
+static struct nfs_local_kiocb *
+nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, struct file *filp,
+ gfp_t flags)
+{
+ struct nfs_local_kiocb *iocb;
+
+ iocb = kmalloc(sizeof(*iocb), flags);
+ if (iocb == NULL)
+ return NULL;
+ iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec,
+ hdr->page_array.npages, flags);
+ if (iocb->bvec == NULL) {
+ kfree(iocb);
+ return NULL;
+ }
+ init_sync_kiocb(&iocb->kiocb, filp);
+ iocb->kiocb.ki_pos = hdr->args.offset;
+ iocb->hdr = hdr;
+ iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+ return iocb;
+}
+
+static void
+nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ iov_iter_bvec(i, dir, iocb->bvec, hdr->page_array.npages,
+ hdr->args.count + hdr->args.pgbase);
+ if (hdr->args.pgbase != 0)
+ iov_iter_advance(i, hdr->args.pgbase);
+}
+
+static void
+nfs_local_hdr_release(struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ call_ops->rpc_call_done(&hdr->task, hdr);
+ call_ops->rpc_release(hdr);
+}
+
+static void
+nfs_local_pgio_init(struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ hdr->task.tk_ops = call_ops;
+ if (!hdr->task.tk_start)
+ hdr->task.tk_start = ktime_get();
+}
+
+static void
+nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
+{
+ if (status >= 0) {
+ hdr->res.count = status;
+ hdr->res.op_status = NFS4_OK;
+ hdr->task.tk_status = 0;
+ } else {
+ hdr->res.op_status = nfs4errno(status);
+ hdr->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ fput(iocb->kiocb.ki_filp);
+ nfs_local_iocb_free(iocb);
+ nfs_local_hdr_release(hdr, hdr->task.tk_ops);
+}
+
+static void
+nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+ struct file *filp = iocb->kiocb.ki_filp;
+
+ nfs_local_pgio_done(hdr, status);
+
+ if (hdr->res.count != hdr->args.count ||
+ hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
+ hdr->res.eof = true;
+
+ dprintk("%s: read %ld bytes eof %d.\n", __func__,
+ status > 0 ? status : 0, hdr->res.eof);
+}
+
+static int
+nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_kiocb *iocb;
+ struct iov_iter iter;
+ ssize_t status;
+
+ dprintk("%s: vfs_read count=%u pos=%llu\n",
+ __func__, hdr->args.count, hdr->args.offset);
+
+ iocb = nfs_local_iocb_alloc(hdr, filp, GFP_KERNEL);
+ if (iocb == NULL)
+ return -ENOMEM;
+ nfs_local_iter_init(&iter, iocb, READ);
+
+ nfs_local_pgio_init(hdr, call_ops);
+ hdr->res.eof = false;
+
+ status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_read_done(iocb, status);
+ nfs_local_pgio_release(iocb);
+ }
+ return 0;
+}
+
+static void
+nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode)
+{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+ u32 *verf = (u32 *)verifier->data;
+ int seq = 0;
+
+ do {
+ read_seqbegin_or_lock(&clp->cl_boot_lock, &seq);
+ verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec;
+ verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec;
+ } while (need_seqretry(&clp->cl_boot_lock, seq));
+ done_seqretry(&clp->cl_boot_lock, seq);
+}
+
+static void
+nfs_reset_boot_verifier(struct inode *inode)
+{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+
+ write_seqlock(&clp->cl_boot_lock);
+ ktime_get_real_ts64(&clp->cl_nfssvc_boot);
+ write_sequnlock(&clp->cl_boot_lock);
+}
+
+static void
+nfs_set_local_verifier(struct inode *inode,
+ struct nfs_writeverf *verf,
+ enum nfs3_stable_how how)
+{
+
+ nfs_copy_boot_verifier(&verf->verifier, inode);
+ verf->committed = how;
+}
+
+static void
+nfs_get_vfs_attr(struct file *filp, struct nfs_fattr *fattr)
+{
+ struct kstat stat;
+
+ if (fattr != NULL && vfs_getattr(&filp->f_path, &stat,
+ STATX_INO |
+ STATX_ATIME |
+ STATX_MTIME |
+ STATX_CTIME |
+ STATX_SIZE |
+ STATX_BLOCKS,
+ AT_STATX_SYNC_AS_STAT) == 0) {
+ fattr->valid = NFS_ATTR_FATTR_FILEID |
+ NFS_ATTR_FATTR_CHANGE |
+ NFS_ATTR_FATTR_SIZE |
+ NFS_ATTR_FATTR_ATIME |
+ NFS_ATTR_FATTR_MTIME |
+ NFS_ATTR_FATTR_CTIME |
+ NFS_ATTR_FATTR_SPACE_USED;
+ fattr->fileid = stat.ino;
+ fattr->size = stat.size;
+ fattr->atime = stat.atime;
+ fattr->mtime = stat.mtime;
+ fattr->ctime = stat.ctime;
+ fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
+ fattr->du.nfs3.used = stat.blocks << 9;
+ }
+}
+
+static void
+nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
+
+ /* Handle short writes as if they are ENOSPC */
+ if (status > 0 && status < hdr->args.count) {
+ hdr->mds_offset += status;
+ hdr->args.offset += status;
+ hdr->args.pgbase += status;
+ hdr->args.count -= status;
+ nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
+ status = -ENOSPC;
+ }
+ if (status < 0)
+ nfs_reset_boot_verifier(hdr->inode);
+ nfs_local_pgio_done(hdr, status);
+}
+
+static int
+nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_kiocb *iocb;
+ struct iov_iter iter;
+ ssize_t status;
+
+ dprintk("%s: vfs_write count=%u pos=%llu %s\n",
+ __func__, hdr->args.count, hdr->args.offset,
+ (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable");
+
+ iocb = nfs_local_iocb_alloc(hdr, filp, GFP_NOIO);
+ if (iocb == NULL)
+ return -ENOMEM;
+ nfs_local_iter_init(&iter, iocb, WRITE);
+
+ switch (hdr->args.stable) {
+ default:
+ break;
+ case NFS_DATA_SYNC:
+ iocb->kiocb.ki_flags |= IOCB_DSYNC;
+ break;
+ case NFS_FILE_SYNC:
+ iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
+ }
+ nfs_local_pgio_init(hdr, call_ops);
+
+ nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
+
+ file_start_write(filp);
+ status = filp->f_op->write_iter(&iocb->kiocb, &iter);
+ file_end_write(filp);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_write_done(iocb, status);
+ nfs_get_vfs_attr(filp, hdr->res.fattr);
+ nfs_local_pgio_release(iocb);
+ }
+ return 0;
+}
+
+static struct file *
+nfs_local_file_open_cached(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, struct nfs_open_context *ctx)
+{
+ struct file *filp = ctx->local_filp;
+
+ if (!filp) {
+ struct file *new = nfs_local_open_fh(clp, cred, fh, ctx->mode);
+ if (IS_ERR_OR_NULL(new))
+ return NULL;
+ /* try to put this one in the slot */
+ filp = cmpxchg(&ctx->local_filp, NULL, new);
+ if (filp != NULL)
+ fput(new);
+ else
+ filp = new;
+ }
+ return get_file(filp);
+}
+
+struct file *
+nfs_local_file_open(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, struct nfs_open_context *ctx)
+{
+ if (!nfs_server_is_local(clp))
+ return NULL;
+ return nfs_local_file_open_cached(clp, cred, fh, ctx);
+}
+
+int
+nfs_local_doio(struct nfs_client *clp, struct file *filp,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ int status = 0;
+
+ if (!hdr->args.count)
+ goto out_fput;
+ /* Don't support filesystems without read_iter/write_iter */
+ if (!filp->f_op->read_iter || !filp->f_op->write_iter) {
+ nfs_local_disable(clp);
+ status = -EAGAIN;
+ goto out_fput;
+ }
+
+ switch (hdr->rw_mode) {
+ case FMODE_READ:
+ status = nfs_do_local_read(hdr, filp, call_ops);
+ break;
+ case FMODE_WRITE:
+ status = nfs_do_local_write(hdr, filp, call_ops);
+ break;
+ default:
+ dprintk("%s: invalid mode: %d\n", __func__,
+ hdr->rw_mode);
+ status = -EINVAL;
+ }
+out_fput:
+ if (status != 0) {
+ fput(filp);
+ hdr->task.tk_status = status;
+ nfs_local_hdr_release(hdr, call_ops);
+ }
+ return status;
+}
+
+static void
+nfs_local_init_commit(struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops)
+{
+ data->task.tk_ops = call_ops;
+}
+
+static int
+nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data)
+{
+ loff_t start = data->args.offset;
+ loff_t end = LLONG_MAX;
+
+ if (data->args.count > 0) {
+ end = start + data->args.count - 1;
+ if (end < start)
+ end = LLONG_MAX;
+ }
+
+ dprintk("%s: commit %llu - %llu\n", __func__, start, end);
+ return vfs_fsync_range(filp, start, end, 0);
+}
+
+static void
+nfs_local_commit_done(struct nfs_commit_data *data, int status)
+{
+ if (status >= 0) {
+ nfs_set_local_verifier(data->inode,
+ data->res.verf,
+ NFS_FILE_SYNC);
+ data->res.op_status = NFS4_OK;
+ data->task.tk_status = 0;
+ } else {
+ nfs_reset_boot_verifier(data->inode);
+ data->res.op_status = nfs4errno(status);
+ data->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_release_commit_data(struct file *filp,
+ struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops)
+{
+ fput(filp);
+ call_ops->rpc_call_done(&data->task, data);
+ call_ops->rpc_release(data);
+}
+
+static struct nfs_local_fsync_ctx *
+nfs_local_fsync_ctx_alloc(struct nfs_commit_data *data, struct file *filp,
+ gfp_t flags)
+{
+ struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags);
+
+ if (ctx != NULL) {
+ ctx->filp = filp;
+ ctx->data = data;
+ INIT_WORK(&ctx->work, nfs_local_fsync_work);
+ kref_init(&ctx->kref);
+ ctx->done = NULL;
+ }
+ return ctx;
+}
+
+static void
+nfs_local_fsync_ctx_kref_free(struct kref *kref)
+{
+ kfree(container_of(kref, struct nfs_local_fsync_ctx, kref));
+}
+
+static void
+nfs_local_fsync_ctx_put(struct nfs_local_fsync_ctx *ctx)
+{
+ kref_put(&ctx->kref, nfs_local_fsync_ctx_kref_free);
+}
+
+static void
+nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx)
+{
+ nfs_local_release_commit_data(ctx->filp, ctx->data,
+ ctx->data->task.tk_ops);
+ nfs_local_fsync_ctx_put(ctx);
+}
+
+static void
+nfs_local_fsync_work(struct work_struct *work)
+{
+ struct nfs_local_fsync_ctx *ctx;
+ int status;
+
+ ctx = container_of(work, struct nfs_local_fsync_ctx, work);
+
+ status = nfs_local_run_commit(ctx->filp, ctx->data);
+ nfs_local_commit_done(ctx->data, status);
+ if (ctx->done != NULL)
+ complete(ctx->done);
+ nfs_local_fsync_ctx_free(ctx);
+}
+
+int
+nfs_local_commit(struct file *filp, struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops, int how)
+{
+ struct nfs_local_fsync_ctx *ctx;
+
+ ctx = nfs_local_fsync_ctx_alloc(data, filp, GFP_KERNEL);
+ if (!ctx) {
+ nfs_local_commit_done(data, -ENOMEM);
+ nfs_local_release_commit_data(filp, data, call_ops);
+ return -ENOMEM;
+ }
+
+ nfs_local_init_commit(data, call_ops);
+ kref_get(&ctx->kref);
+ if (how & FLUSH_SYNC) {
+ DECLARE_COMPLETION_ONSTACK(done);
+ ctx->done = &done;
+ queue_work(nfsiod_workqueue, &ctx->work);
+ wait_for_completion(&done);
+ } else
+ queue_work(nfsiod_workqueue, &ctx->work);
+ nfs_local_fsync_ctx_put(ctx);
+ return 0;
+}
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 1e710654af11..95a2c19a9172 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -1681,6 +1681,67 @@ TRACE_EVENT(nfs_mount_path,
TP_printk("path='%s'", __get_str(path))
);
+TRACE_EVENT(nfs_local_open_fh,
+ TP_PROTO(
+ const struct nfs_fh *fh,
+ fmode_t fmode,
+ int error
+ ),
+
+ TP_ARGS(fh, fmode, error),
+
+ TP_STRUCT__entry(
+ __field(int, error)
+ __field(u32, fhandle)
+ __field(unsigned int, fmode)
+ ),
+
+ TP_fast_assign(
+ __entry->error = error;
+ __entry->fhandle = nfs_fhandle_hash(fh);
+ __entry->fmode = (__force unsigned int)fmode;
+ ),
+
+ TP_printk(
+ "error=%d fhandle=0x%08x mode=%s",
+ __entry->error,
+ __entry->fhandle,
+ show_fs_fmode_flags(__entry->fmode)
+ )
+);
+
+DECLARE_EVENT_CLASS(nfs_local_client_event,
+ TP_PROTO(
+ const struct nfs_client *clp
+ ),
+
+ TP_ARGS(clp),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, protocol)
+ __string(server, clp->cl_hostname)
+ ),
+
+ TP_fast_assign(
+ __entry->protocol = clp->rpc_ops->version;
+ __assign_str(server);
+ ),
+
+ TP_printk(
+ "server=%s NFSv%u", __get_str(server), __entry->protocol
+ )
+);
+
+#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \
+ DEFINE_EVENT(nfs_local_client_event, name, \
+ TP_PROTO( \
+ const struct nfs_client *clp \
+ ), \
+ TP_ARGS(clp))
+
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable);
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable);
+
DECLARE_EVENT_CLASS(nfs_xdr_event,
TP_PROTO(
const struct xdr_stream *xdr,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 57d62db3be5b..b08420b8e664 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -879,6 +879,9 @@ int nfs_initiate_pgio(struct nfs_pageio_descriptor *desc,
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ if (localio)
+ return nfs_local_doio(clp, localio, hdr, call_ops);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 267bed2a4ceb..b29b0fd5431f 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1700,6 +1700,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
dprintk("NFS: initiated commit call\n");
+ if (localio)
+ return nfs_local_commit(localio, data, call_ops, how);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index b8736a82e57c..78b421778a79 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -23,3 +23,4 @@ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
+nfsd-$(CONFIG_NFSD_LOCALIO) += localio.o
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ad9083ca144b..99631fa56662 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -52,7 +52,7 @@
#define NFSD_FILE_CACHE_UP (0)
/* We only care about NFSD_MAY_READ/WRITE for this cache */
-#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE)
+#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO)
static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
new file mode 100644
index 000000000000..e9aa0997f898
--- /dev/null
+++ b/fs/nfsd/localio.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS server support for local clients to bypass network stack
+ *
+ * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
+ * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+
+#include <linux/exportfs.h>
+#include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
+#include <linux/string.h>
+
+#include "nfsd.h"
+#include "vfs.h"
+#include "netns.h"
+#include "filecache.h"
+
+#define NFSDDBG_FACILITY NFSDDBG_FH
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ * - duplicated from fs/nfs/nfs2xdr.c to avoid needless bloat of
+ * all compiled nfs objects if it were in include/linux/nfs.h
+ */
+static const struct {
+ int stat;
+ int errno;
+} nfs_common_errtbl[] = {
+ { NFS_OK, 0 },
+ { NFSERR_PERM, -EPERM },
+ { NFSERR_NOENT, -ENOENT },
+ { NFSERR_IO, -EIO },
+ { NFSERR_NXIO, -ENXIO },
+/* { NFSERR_EAGAIN, -EAGAIN }, */
+ { NFSERR_ACCES, -EACCES },
+ { NFSERR_EXIST, -EEXIST },
+ { NFSERR_XDEV, -EXDEV },
+ { NFSERR_NODEV, -ENODEV },
+ { NFSERR_NOTDIR, -ENOTDIR },
+ { NFSERR_ISDIR, -EISDIR },
+ { NFSERR_INVAL, -EINVAL },
+ { NFSERR_FBIG, -EFBIG },
+ { NFSERR_NOSPC, -ENOSPC },
+ { NFSERR_ROFS, -EROFS },
+ { NFSERR_MLINK, -EMLINK },
+ { NFSERR_NAMETOOLONG, -ENAMETOOLONG },
+ { NFSERR_NOTEMPTY, -ENOTEMPTY },
+ { NFSERR_DQUOT, -EDQUOT },
+ { NFSERR_STALE, -ESTALE },
+ { NFSERR_REMOTE, -EREMOTE },
+#ifdef EWFLUSH
+ { NFSERR_WFLUSH, -EWFLUSH },
+#endif
+ { NFSERR_BADHANDLE, -EBADHANDLE },
+ { NFSERR_NOT_SYNC, -ENOTSYNC },
+ { NFSERR_BAD_COOKIE, -EBADCOOKIE },
+ { NFSERR_NOTSUPP, -ENOTSUPP },
+ { NFSERR_TOOSMALL, -ETOOSMALL },
+ { NFSERR_SERVERFAULT, -EREMOTEIO },
+ { NFSERR_BADTYPE, -EBADTYPE },
+ { NFSERR_JUKEBOX, -EJUKEBOX },
+ { -1, -EIO }
+};
+
+/**
+ * nfs_stat_to_errno - convert an NFS status code to a local errno
+ * @status: NFS status code to convert
+ *
+ * Returns a local errno value, or -EIO if the NFS status code is
+ * not recognized. This function is used jointly by NFSv2 and NFSv3.
+ */
+static int nfs_stat_to_errno(enum nfs_stat status)
+{
+ int i;
+
+ for (i = 0; nfs_common_errtbl[i].stat != -1; i++) {
+ if (nfs_common_errtbl[i].stat == (int)status)
+ return nfs_common_errtbl[i].errno;
+ }
+ return nfs_common_errtbl[i].errno;
+}
+
+static void
+nfsd_local_fakerqst_destroy(struct svc_rqst *rqstp)
+{
+ if (rqstp->rq_client)
+ auth_domain_put(rqstp->rq_client);
+ if (rqstp->rq_cred.cr_group_info)
+ put_group_info(rqstp->rq_cred.cr_group_info);
+ /* rpcauth_map_to_svc_cred_local() clears cr_principal */
+ WARN_ON_ONCE(rqstp->rq_cred.cr_principal != NULL);
+ kfree(rqstp->rq_xprt);
+ kfree(rqstp);
+}
+
+static struct svc_rqst *
+nfsd_local_fakerqst_create(struct net *net, struct rpc_clnt *rpc_clnt,
+ const struct cred *cred)
+{
+ struct svc_rqst *rqstp;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ int status;
+
+ /* FIXME: not running in nfsd context, must get reference on nfsd_serv */
+ if (unlikely(!READ_ONCE(nn->nfsd_serv))) {
+ dprintk("%s: localio denied. Server not running\n", __func__);
+ return ERR_PTR(-ENXIO);
+ }
+
+ rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
+ if (!rqstp)
+ return ERR_PTR(-ENOMEM);
+
+ rqstp->rq_xprt = kzalloc(sizeof(*rqstp->rq_xprt), GFP_KERNEL);
+ if (!rqstp->rq_xprt) {
+ status = -ENOMEM;
+ goto out_err;
+ }
+
+ rqstp->rq_xprt->xpt_net = net;
+ __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ rqstp->rq_proc = 1;
+ rqstp->rq_vers = 3;
+ rqstp->rq_prot = IPPROTO_TCP;
+ rqstp->rq_server = nn->nfsd_serv;
+
+ /* Note: we're connecting to ourself, so source addr == peer addr */
+ rqstp->rq_addrlen = rpc_peeraddr(rpc_clnt,
+ (struct sockaddr *)&rqstp->rq_addr,
+ sizeof(rqstp->rq_addr));
+
+ rpcauth_map_to_svc_cred_local(rpc_clnt->cl_auth, cred, &rqstp->rq_cred);
+
+ /*
+ * set up enough for svcauth_unix_set_client to be able to wait
+ * for the cache downcall. Note that we do _not_ want to allow the
+ * request to be deferred for later revisit since this rqst and xprt
+ * are not set up to run inside of the normal svc_rqst engine.
+ */
+ INIT_LIST_HEAD(&rqstp->rq_xprt->xpt_deferred);
+ kref_init(&rqstp->rq_xprt->xpt_ref);
+ spin_lock_init(&rqstp->rq_xprt->xpt_lock);
+ rqstp->rq_chandle.thread_wait = 5 * HZ;
+
+ status = svcauth_unix_set_client(rqstp);
+ switch (status) {
+ case SVC_OK:
+ break;
+ case SVC_DENIED:
+ status = -ENXIO;
+ dprintk("%s: client %pISpc denied localio access\n",
+ __func__, (struct sockaddr *)&rqstp->rq_addr);
+ goto out_err;
+ default:
+ status = -ETIMEDOUT;
+ dprintk("%s: client %pISpc temporarily denied localio access\n",
+ __func__, (struct sockaddr *)&rqstp->rq_addr);
+ goto out_err;
+ }
+
+ return rqstp;
+
+out_err:
+ nfsd_local_fakerqst_destroy(rqstp);
+ return ERR_PTR(status);
+}
+
+/*
+ * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to @file
+ *
+ * This function maps a local fh to a path on a local filesystem.
+ * This is useful when the nfs client has the local server mounted - it can
+ * avoid all the NFS overhead with reads, writes and commits.
+ *
+ * on successful return, caller is responsible for calling path_put. Also
+ * note that this is called from nfs.ko via find_symbol() to avoid an explicit
+ * dependency on knfsd. So, there is no forward declaration in a header file
+ * for it.
+ */
+int nfsd_open_local_fh(struct net *net,
+ struct rpc_clnt *rpc_clnt,
+ const struct cred *cred,
+ const struct nfs_fh *nfs_fh,
+ const fmode_t fmode,
+ struct file **pfilp)
+{
+ const struct cred *save_cred;
+ struct svc_rqst *rqstp;
+ struct svc_fh fh;
+ struct nfsd_file *nf;
+ int status = 0;
+ int mayflags = NFSD_MAY_LOCALIO;
+ __be32 beres;
+
+ /* Save creds before calling into nfsd */
+ save_cred = get_current_cred();
+
+ rqstp = nfsd_local_fakerqst_create(net, rpc_clnt, cred);
+ if (IS_ERR(rqstp)) {
+ status = PTR_ERR(rqstp);
+ goto out_revertcred;
+ }
+
+ /* nfs_fh -> svc_fh */
+ if (nfs_fh->size > NFS4_FHSIZE) {
+ status = -EINVAL;
+ goto out;
+ }
+ fh_init(&fh, NFS4_FHSIZE);
+ fh.fh_handle.fh_size = nfs_fh->size;
+ memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size);
+
+ if (fmode & FMODE_READ)
+ mayflags |= NFSD_MAY_READ;
+ if (fmode & FMODE_WRITE)
+ mayflags |= NFSD_MAY_WRITE;
+
+ beres = nfsd_file_acquire(rqstp, &fh, mayflags, &nf);
+ if (beres) {
+ status = nfs_stat_to_errno(be32_to_cpu(beres));
+ dprintk("%s: fh_verify failed %d\n", __func__, status);
+ goto out_fh_put;
+ }
+
+ *pfilp = get_file(nf->nf_file);
+
+ nfsd_file_put(nf);
+out_fh_put:
+ fh_put(&fh);
+
+out:
+ nfsd_local_fakerqst_destroy(rqstp);
+out_revertcred:
+ revert_creds(save_cred);
+ return status;
+}
+EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
+
+/* Compile time type checking, not used by anything */
+static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 1222a0a33fe1..a477d2c5088a 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -431,6 +431,7 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred)
#endif
#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
INIT_LIST_HEAD(&nn->nfsd_uuid.list);
+ nn->nfsd_uuid.net = net;
list_add_tail_rcu(&nn->nfsd_uuid.list, &nfsd_uuids);
#endif
nn->nfsd_net_up = true;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 77bbd23aa150..9c0610fdd11c 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -86,7 +86,8 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
{ NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \
{ NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \
{ NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \
- { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" })
+ { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }, \
+ { NFSD_MAY_LOCALIO, "LOCALIO" })
TRACE_EVENT(nfsd_compound,
TP_PROTO(
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 57cd70062048..af07bb146e81 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -36,6 +36,8 @@
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+#define NFSD_MAY_LOCALIO 0x800000
+
struct nfsd_file;
/*
@@ -158,6 +160,13 @@ __be32 nfsd_permission(struct svc_rqst *, struct svc_export *,
void nfsd_filp_close(struct file *fp);
+int nfsd_open_local_fh(struct net *net,
+ struct rpc_clnt *rpc_clnt,
+ const struct cred *cred,
+ const struct nfs_fh *nfs_fh,
+ const fmode_t fmode,
+ struct file **pfilp);
+
static inline int fh_want_write(struct svc_fh *fh)
{
int ret;
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index ceb70a926b95..64ed672a0b34 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -8,6 +8,8 @@
#ifndef _LINUX_NFS_H
#define _LINUX_NFS_H
+#include <linux/cred.h>
+#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/string.h>
#include <linux/crc32.h>
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 039898d70954..a0bb947fdd1d 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -96,6 +96,8 @@ struct nfs_open_context {
struct list_head list;
struct nfs4_threshold *mdsthreshold;
struct rcu_head rcu_head;
+
+ struct file *local_filp;
};
struct nfs_open_dir_context {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index e58e706a6503..4290c550a049 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -50,6 +50,7 @@ struct nfs_client {
#define NFS_CS_DS 7 /* - Server is a DS */
#define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */
#define NFS_CS_PNFS 9 /* - Server used for pnfs */
+#define NFS_CS_LOCAL_IO 10 /* - client is local */
struct sockaddr_storage cl_addr; /* server identifier */
size_t cl_addrlen;
char * cl_hostname; /* hostname of server */
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 06/20] nfs/nfsd: add "localio" support
2024-06-24 16:27 ` [PATCH v7 06/20] nfs/nfsd: add "localio" support Mike Snitzer
@ 2024-06-24 18:26 ` Chuck Lever
2024-06-25 4:57 ` Mike Snitzer
0 siblings, 1 reply; 40+ messages in thread
From: Chuck Lever @ 2024-06-24 18:26 UTC (permalink / raw)
To: Mike Snitzer; +Cc: linux-nfs, Jeff Layton, Trond Myklebust, NeilBrown, snitzer
On Mon, Jun 24, 2024 at 12:27:27PM -0400, Mike Snitzer wrote:
> From: Weston Andros Adamson <dros@primarydata.com>
>
> Add client support for bypassing NFS for localhost reads, writes, and
> commits. This is only useful when the client and the server are
> running on the same host.
>
> nfs_local_probe() is stubbed out, later commits will enable client and
> server handshake via a Linux-only LOCALIO auxiliary RPC protocol.
>
> This has dynamic binding with the nfsd module (via nfs_localio module
> which is part of nfs_common). Localio will only work if nfsd is
> already loaded.
>
> The "localio_enabled" nfs kernel module parameter can be used to
> disable and enable the ability to use localio support.
>
> Tracepoints were added for nfs_local_open_fh, nfs_local_enable and
> nfs_local_disable.
>
> Also, pass the stored cl_nfssvc_net from the client to the server as
> first argument to nfsd_open_local_fh() to ensure the proper network
> namespace is used for localio.
>
> Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
> Signed-off-by: Peng Tao <tao.peng@primarydata.com>
> Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> fs/nfs/Makefile | 1 +
> fs/nfs/client.c | 3 +
> fs/nfs/inode.c | 4 +
> fs/nfs/internal.h | 51 +++
> fs/nfs/localio.c | 654 ++++++++++++++++++++++++++++++++++++++
> fs/nfs/nfstrace.h | 61 ++++
> fs/nfs/pagelist.c | 3 +
> fs/nfs/write.c | 3 +
Hi Mike -
I'd prefer to see this patch split into two patches, one for the
NFS client, and one for the NFS server. The other patches in this
series seem to have a clear line between server and client
changes.
One or two more remarks below.
> fs/nfsd/Makefile | 1 +
> fs/nfsd/filecache.c | 2 +-
> fs/nfsd/localio.c | 244 ++++++++++++++
> fs/nfsd/nfssvc.c | 1 +
> fs/nfsd/trace.h | 3 +-
> fs/nfsd/vfs.h | 9 +
> include/linux/nfs.h | 2 +
> include/linux/nfs_fs.h | 2 +
> include/linux/nfs_fs_sb.h | 1 +
> 17 files changed, 1043 insertions(+), 2 deletions(-)
> create mode 100644 fs/nfs/localio.c
> create mode 100644 fs/nfsd/localio.c
>
> diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
> index 5f6db37f461e..9fb2f2cac87e 100644
> --- a/fs/nfs/Makefile
> +++ b/fs/nfs/Makefile
> @@ -13,6 +13,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \
> nfs-$(CONFIG_ROOT_NFS) += nfsroot.o
> nfs-$(CONFIG_SYSCTL) += sysctl.o
> nfs-$(CONFIG_NFS_FSCACHE) += fscache.o
> +nfs-$(CONFIG_NFS_LOCALIO) += localio.o
>
> obj-$(CONFIG_NFS_V2) += nfsv2.o
> nfsv2-y := nfs2super.o proc.o nfs2xdr.o
> diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> index bcdf8d42cbc7..1300c388f971 100644
> --- a/fs/nfs/client.c
> +++ b/fs/nfs/client.c
> @@ -241,6 +241,8 @@ static void pnfs_init_server(struct nfs_server *server)
> */
> void nfs_free_client(struct nfs_client *clp)
> {
> + nfs_local_disable(clp);
> +
> /* -EIO all pending I/O */
> if (!IS_ERR(clp->cl_rpcclient))
> rpc_shutdown_client(clp->cl_rpcclient);
> @@ -432,6 +434,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
> list_add_tail(&new->cl_share_link,
> &nn->nfs_client_list);
> spin_unlock(&nn->nfs_client_lock);
> + nfs_local_probe(new);
> return rpc_ops->init_client(new, cl_init);
> }
>
> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
> index acef52ecb1bb..f9923cbf6058 100644
> --- a/fs/nfs/inode.c
> +++ b/fs/nfs/inode.c
> @@ -39,6 +39,7 @@
> #include <linux/slab.h>
> #include <linux/compat.h>
> #include <linux/freezer.h>
> +#include <linux/file.h>
> #include <linux/uaccess.h>
> #include <linux/iversion.h>
>
> @@ -1053,6 +1054,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
> ctx->lock_context.open_context = ctx;
> INIT_LIST_HEAD(&ctx->list);
> ctx->mdsthreshold = NULL;
> + ctx->local_filp = NULL;
> return ctx;
> }
> EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
> @@ -1084,6 +1086,8 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
> nfs_sb_deactive(sb);
> put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
> kfree(ctx->mdsthreshold);
> + if (!IS_ERR_OR_NULL(ctx->local_filp))
> + fput(ctx->local_filp);
> kfree_rcu(ctx, rcu_head);
> }
>
> diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
> index 958c8de072e2..d352040e3232 100644
> --- a/fs/nfs/internal.h
> +++ b/fs/nfs/internal.h
> @@ -451,6 +451,57 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
> extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
> extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
>
> +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> +/* localio.c */
> +extern void nfs_local_disable(struct nfs_client *);
> +extern void nfs_local_probe(struct nfs_client *);
> +extern struct file *nfs_local_open_fh(struct nfs_client *, const struct cred *,
> + struct nfs_fh *, const fmode_t);
> +extern struct file *nfs_local_file_open(struct nfs_client *clp,
> + const struct cred *cred,
> + struct nfs_fh *fh,
> + struct nfs_open_context *ctx);
> +extern int nfs_local_doio(struct nfs_client *, struct file *,
> + struct nfs_pgio_header *,
> + const struct rpc_call_ops *);
> +extern int nfs_local_commit(struct file *, struct nfs_commit_data *,
> + const struct rpc_call_ops *, int);
> +extern bool nfs_server_is_local(const struct nfs_client *clp);
> +
> +#else
> +static inline void nfs_local_disable(struct nfs_client *clp) {}
> +static inline void nfs_local_probe(struct nfs_client *clp) {}
> +static inline struct file *nfs_local_open_fh(struct nfs_client *clp,
> + const struct cred *cred,
> + struct nfs_fh *fh,
> + const fmode_t mode)
> +{
> + return ERR_PTR(-EINVAL);
> +}
> +static inline struct file *nfs_local_file_open(struct nfs_client *clp,
> + const struct cred *cred,
> + struct nfs_fh *fh,
> + struct nfs_open_context *ctx)
> +{
> + return NULL;
> +}
> +static inline int nfs_local_doio(struct nfs_client *clp, struct file *filep,
> + struct nfs_pgio_header *hdr,
> + const struct rpc_call_ops *call_ops)
> +{
> + return -EINVAL;
> +}
> +static inline int nfs_local_commit(struct file *filep, struct nfs_commit_data *data,
> + const struct rpc_call_ops *call_ops, int how)
> +{
> + return -EINVAL;
> +}
> +static inline bool nfs_server_is_local(const struct nfs_client *clp)
> +{
> + return false;
> +}
> +#endif /* CONFIG_NFS_LOCALIO */
> +
> /* super.c */
> extern const struct super_operations nfs_sops;
> bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
> diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
> new file mode 100644
> index 000000000000..724e81716b16
> --- /dev/null
> +++ b/fs/nfs/localio.c
> @@ -0,0 +1,654 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * NFS client support for local clients to bypass network stack
> + *
> + * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
> + * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> + */
> +
> +#include <linux/module.h>
> +#include <linux/errno.h>
> +#include <linux/vfs.h>
> +#include <linux/file.h>
> +#include <linux/inet.h>
> +#include <linux/sunrpc/addr.h>
> +#include <linux/inetdevice.h>
> +#include <net/addrconf.h>
> +#include <linux/module.h>
> +#include <linux/bvec.h>
> +
> +#include <linux/nfs.h>
> +#include <linux/nfs_fs.h>
> +#include <linux/nfs_xdr.h>
> +
> +#include "internal.h"
> +#include "pnfs.h"
> +#include "nfstrace.h"
> +
> +#define NFSDBG_FACILITY NFSDBG_VFS
> +
> +struct nfs_local_kiocb {
> + struct kiocb kiocb;
> + struct bio_vec *bvec;
> + struct nfs_pgio_header *hdr;
> + struct work_struct work;
> +};
> +
> +struct nfs_local_fsync_ctx {
> + struct file *filp;
> + struct nfs_commit_data *data;
> + struct work_struct work;
> + struct kref kref;
> + struct completion *done;
> +};
> +static void nfs_local_fsync_work(struct work_struct *work);
> +
> +/*
> + * We need to translate between nfs status return values and
> + * the local errno values which may not be the same.
> + */
> +static struct {
> + __u32 stat;
> + int errno;
> +} nfs_errtbl[] = {
> + { NFS4_OK, 0 },
> + { NFS4ERR_PERM, -EPERM },
> + { NFS4ERR_NOENT, -ENOENT },
> + { NFS4ERR_IO, -EIO },
> + { NFS4ERR_NXIO, -ENXIO },
> + { NFS4ERR_FBIG, -E2BIG },
> + { NFS4ERR_STALE, -EBADF },
> + { NFS4ERR_ACCESS, -EACCES },
> + { NFS4ERR_EXIST, -EEXIST },
> + { NFS4ERR_XDEV, -EXDEV },
> + { NFS4ERR_MLINK, -EMLINK },
> + { NFS4ERR_NOTDIR, -ENOTDIR },
> + { NFS4ERR_ISDIR, -EISDIR },
> + { NFS4ERR_INVAL, -EINVAL },
> + { NFS4ERR_FBIG, -EFBIG },
> + { NFS4ERR_NOSPC, -ENOSPC },
> + { NFS4ERR_ROFS, -EROFS },
> + { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG },
> + { NFS4ERR_NOTEMPTY, -ENOTEMPTY },
> + { NFS4ERR_DQUOT, -EDQUOT },
> + { NFS4ERR_STALE, -ESTALE },
> + { NFS4ERR_STALE, -EOPENSTALE },
> + { NFS4ERR_DELAY, -ETIMEDOUT },
> + { NFS4ERR_DELAY, -ERESTARTSYS },
> + { NFS4ERR_DELAY, -EAGAIN },
> + { NFS4ERR_DELAY, -ENOMEM },
> + { NFS4ERR_IO, -ETXTBSY },
> + { NFS4ERR_IO, -EBUSY },
> + { NFS4ERR_BADHANDLE, -EBADHANDLE },
> + { NFS4ERR_BAD_COOKIE, -EBADCOOKIE },
> + { NFS4ERR_NOTSUPP, -EOPNOTSUPP },
> + { NFS4ERR_TOOSMALL, -ETOOSMALL },
> + { NFS4ERR_SERVERFAULT, -ESERVERFAULT },
> + { NFS4ERR_SERVERFAULT, -ENFILE },
> + { NFS4ERR_IO, -EREMOTEIO },
> + { NFS4ERR_IO, -EUCLEAN },
> + { NFS4ERR_PERM, -ENOKEY },
> + { NFS4ERR_BADTYPE, -EBADTYPE },
> + { NFS4ERR_SYMLINK, -ELOOP },
> + { NFS4ERR_DEADLOCK, -EDEADLK },
> +};
> +
> +/*
> + * Convert an NFS error code to a local one.
> + * This one is used jointly by NFSv2 and NFSv3.
> + */
> +static __u32
> +nfs4errno(int errno)
> +{
> + unsigned int i;
> + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
> + if (nfs_errtbl[i].errno == errno)
> + return nfs_errtbl[i].stat;
> + }
> + /* If we cannot translate the error, the recovery routines should
> + * handle it.
> + * Note: remaining NFSv4 error codes have values > 10000, so should
> + * not conflict with native Linux error codes.
> + */
> + return NFS4ERR_SERVERFAULT;
> +}
> +
> +static bool localio_enabled __read_mostly = true;
> +module_param(localio_enabled, bool, 0644);
> +
> +bool nfs_server_is_local(const struct nfs_client *clp)
> +{
> + return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 &&
> + localio_enabled;
> +}
> +EXPORT_SYMBOL_GPL(nfs_server_is_local);
> +
> +/*
> + * nfs_local_enable - attempt to enable local i/o for an nfs_client
> + */
> +static void nfs_local_enable(struct nfs_client *clp, struct net *net)
> +{
> + if (READ_ONCE(clp->nfsd_open_local_fh)) {
> + set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
> + clp->cl_nfssvc_net = net;
> + trace_nfs_local_enable(clp);
> + }
> +}
> +
> +/*
> + * nfs_local_disable - disable local i/o for an nfs_client
> + */
> +void nfs_local_disable(struct nfs_client *clp)
> +{
> + if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
> + trace_nfs_local_disable(clp);
> + clp->cl_nfssvc_net = NULL;
> + }
> +}
> +
> +/*
> + * nfs_local_probe - probe local i/o support for an nfs_client
> + */
> +void
> +nfs_local_probe(struct nfs_client *clp)
> +{
> + bool enable = false;
> +
> + if (enable)
> + nfs_local_enable(clp);
> +}
> +EXPORT_SYMBOL_GPL(nfs_local_probe);
> +
> +/*
> + * nfs_local_open_fh - open a local filehandle
> + *
> + * Returns a pointer to a struct file or an ERR_PTR
> + */
> +struct file *
> +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
> + struct nfs_fh *fh, const fmode_t mode)
> +{
> + struct file *filp;
> + int status;
> +
> + if (mode & ~(FMODE_READ | FMODE_WRITE))
> + return ERR_PTR(-EINVAL);
> +
> + status = clp->nfsd_open_local_fh(clp->cl_nfssvc_net, clp->cl_rpcclient,
> + cred, fh, mode, &filp);
> + if (status < 0) {
> + dprintk("%s: open local file failed error=%d\n",
> + __func__, status);
> + trace_nfs_local_open_fh(fh, mode, status);
> + switch (status) {
> + case -ENXIO:
> + nfs_local_disable(clp);
> + fallthrough;
> + case -ETIMEDOUT:
> + status = -EAGAIN;
> + }
> + filp = ERR_PTR(status);
> + }
> + return filp;
> +}
> +EXPORT_SYMBOL_GPL(nfs_local_open_fh);
> +
> +static struct bio_vec *
> +nfs_bvec_alloc_and_import_pagevec(struct page **pagevec,
> + unsigned int npages, gfp_t flags)
> +{
> + struct bio_vec *bvec, *p;
> +
> + bvec = kmalloc_array(npages, sizeof(*bvec), flags);
> + if (bvec != NULL) {
> + for (p = bvec; npages > 0; p++, pagevec++, npages--) {
> + p->bv_page = *pagevec;
> + p->bv_len = PAGE_SIZE;
> + p->bv_offset = 0;
> + }
> + }
> + return bvec;
> +}
> +
> +static void
> +nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
> +{
> + kfree(iocb->bvec);
> + kfree(iocb);
> +}
> +
> +static struct nfs_local_kiocb *
> +nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, struct file *filp,
> + gfp_t flags)
> +{
> + struct nfs_local_kiocb *iocb;
> +
> + iocb = kmalloc(sizeof(*iocb), flags);
> + if (iocb == NULL)
> + return NULL;
> + iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec,
> + hdr->page_array.npages, flags);
> + if (iocb->bvec == NULL) {
> + kfree(iocb);
> + return NULL;
> + }
> + init_sync_kiocb(&iocb->kiocb, filp);
> + iocb->kiocb.ki_pos = hdr->args.offset;
> + iocb->hdr = hdr;
> + iocb->kiocb.ki_flags &= ~IOCB_APPEND;
> + return iocb;
> +}
> +
> +static void
> +nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir)
> +{
> + struct nfs_pgio_header *hdr = iocb->hdr;
> +
> + iov_iter_bvec(i, dir, iocb->bvec, hdr->page_array.npages,
> + hdr->args.count + hdr->args.pgbase);
> + if (hdr->args.pgbase != 0)
> + iov_iter_advance(i, hdr->args.pgbase);
> +}
> +
> +static void
> +nfs_local_hdr_release(struct nfs_pgio_header *hdr,
> + const struct rpc_call_ops *call_ops)
> +{
> + call_ops->rpc_call_done(&hdr->task, hdr);
> + call_ops->rpc_release(hdr);
> +}
> +
> +static void
> +nfs_local_pgio_init(struct nfs_pgio_header *hdr,
> + const struct rpc_call_ops *call_ops)
> +{
> + hdr->task.tk_ops = call_ops;
> + if (!hdr->task.tk_start)
> + hdr->task.tk_start = ktime_get();
> +}
> +
> +static void
> +nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
> +{
> + if (status >= 0) {
> + hdr->res.count = status;
> + hdr->res.op_status = NFS4_OK;
> + hdr->task.tk_status = 0;
> + } else {
> + hdr->res.op_status = nfs4errno(status);
> + hdr->task.tk_status = status;
> + }
> +}
> +
> +static void
> +nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
> +{
> + struct nfs_pgio_header *hdr = iocb->hdr;
> +
> + fput(iocb->kiocb.ki_filp);
> + nfs_local_iocb_free(iocb);
> + nfs_local_hdr_release(hdr, hdr->task.tk_ops);
> +}
> +
> +static void
> +nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
> +{
> + struct nfs_pgio_header *hdr = iocb->hdr;
> + struct file *filp = iocb->kiocb.ki_filp;
> +
> + nfs_local_pgio_done(hdr, status);
> +
> + if (hdr->res.count != hdr->args.count ||
> + hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
> + hdr->res.eof = true;
> +
> + dprintk("%s: read %ld bytes eof %d.\n", __func__,
> + status > 0 ? status : 0, hdr->res.eof);
> +}
> +
> +static int
> +nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
> + const struct rpc_call_ops *call_ops)
> +{
> + struct nfs_local_kiocb *iocb;
> + struct iov_iter iter;
> + ssize_t status;
> +
> + dprintk("%s: vfs_read count=%u pos=%llu\n",
> + __func__, hdr->args.count, hdr->args.offset);
> +
> + iocb = nfs_local_iocb_alloc(hdr, filp, GFP_KERNEL);
> + if (iocb == NULL)
> + return -ENOMEM;
> + nfs_local_iter_init(&iter, iocb, READ);
> +
> + nfs_local_pgio_init(hdr, call_ops);
> + hdr->res.eof = false;
> +
> + status = filp->f_op->read_iter(&iocb->kiocb, &iter);
> + if (status != -EIOCBQUEUED) {
> + nfs_local_read_done(iocb, status);
> + nfs_local_pgio_release(iocb);
> + }
> + return 0;
> +}
> +
> +static void
> +nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode)
> +{
> + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
> + u32 *verf = (u32 *)verifier->data;
> + int seq = 0;
> +
> + do {
> + read_seqbegin_or_lock(&clp->cl_boot_lock, &seq);
> + verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec;
> + verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec;
> + } while (need_seqretry(&clp->cl_boot_lock, seq));
> + done_seqretry(&clp->cl_boot_lock, seq);
> +}
> +
> +static void
> +nfs_reset_boot_verifier(struct inode *inode)
> +{
> + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
> +
> + write_seqlock(&clp->cl_boot_lock);
> + ktime_get_real_ts64(&clp->cl_nfssvc_boot);
> + write_sequnlock(&clp->cl_boot_lock);
> +}
> +
> +static void
> +nfs_set_local_verifier(struct inode *inode,
> + struct nfs_writeverf *verf,
> + enum nfs3_stable_how how)
> +{
> +
> + nfs_copy_boot_verifier(&verf->verifier, inode);
> + verf->committed = how;
> +}
> +
> +static void
> +nfs_get_vfs_attr(struct file *filp, struct nfs_fattr *fattr)
> +{
> + struct kstat stat;
> +
> + if (fattr != NULL && vfs_getattr(&filp->f_path, &stat,
> + STATX_INO |
> + STATX_ATIME |
> + STATX_MTIME |
> + STATX_CTIME |
> + STATX_SIZE |
> + STATX_BLOCKS,
> + AT_STATX_SYNC_AS_STAT) == 0) {
> + fattr->valid = NFS_ATTR_FATTR_FILEID |
> + NFS_ATTR_FATTR_CHANGE |
> + NFS_ATTR_FATTR_SIZE |
> + NFS_ATTR_FATTR_ATIME |
> + NFS_ATTR_FATTR_MTIME |
> + NFS_ATTR_FATTR_CTIME |
> + NFS_ATTR_FATTR_SPACE_USED;
> + fattr->fileid = stat.ino;
> + fattr->size = stat.size;
> + fattr->atime = stat.atime;
> + fattr->mtime = stat.mtime;
> + fattr->ctime = stat.ctime;
> + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
> + fattr->du.nfs3.used = stat.blocks << 9;
> + }
> +}
> +
> +static void
> +nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
> +{
> + struct nfs_pgio_header *hdr = iocb->hdr;
> +
> + dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
> +
> + /* Handle short writes as if they are ENOSPC */
> + if (status > 0 && status < hdr->args.count) {
> + hdr->mds_offset += status;
> + hdr->args.offset += status;
> + hdr->args.pgbase += status;
> + hdr->args.count -= status;
> + nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
> + status = -ENOSPC;
> + }
> + if (status < 0)
> + nfs_reset_boot_verifier(hdr->inode);
> + nfs_local_pgio_done(hdr, status);
> +}
> +
> +static int
> +nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
> + const struct rpc_call_ops *call_ops)
> +{
> + struct nfs_local_kiocb *iocb;
> + struct iov_iter iter;
> + ssize_t status;
> +
> + dprintk("%s: vfs_write count=%u pos=%llu %s\n",
> + __func__, hdr->args.count, hdr->args.offset,
> + (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable");
> +
> + iocb = nfs_local_iocb_alloc(hdr, filp, GFP_NOIO);
> + if (iocb == NULL)
> + return -ENOMEM;
> + nfs_local_iter_init(&iter, iocb, WRITE);
> +
> + switch (hdr->args.stable) {
> + default:
> + break;
> + case NFS_DATA_SYNC:
> + iocb->kiocb.ki_flags |= IOCB_DSYNC;
> + break;
> + case NFS_FILE_SYNC:
> + iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
> + }
> + nfs_local_pgio_init(hdr, call_ops);
> +
> + nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
> +
> + file_start_write(filp);
> + status = filp->f_op->write_iter(&iocb->kiocb, &iter);
> + file_end_write(filp);
> + if (status != -EIOCBQUEUED) {
> + nfs_local_write_done(iocb, status);
> + nfs_get_vfs_attr(filp, hdr->res.fattr);
> + nfs_local_pgio_release(iocb);
> + }
> + return 0;
> +}
> +
> +static struct file *
> +nfs_local_file_open_cached(struct nfs_client *clp, const struct cred *cred,
> + struct nfs_fh *fh, struct nfs_open_context *ctx)
> +{
> + struct file *filp = ctx->local_filp;
> +
> + if (!filp) {
> + struct file *new = nfs_local_open_fh(clp, cred, fh, ctx->mode);
> + if (IS_ERR_OR_NULL(new))
> + return NULL;
> + /* try to put this one in the slot */
> + filp = cmpxchg(&ctx->local_filp, NULL, new);
> + if (filp != NULL)
> + fput(new);
> + else
> + filp = new;
> + }
> + return get_file(filp);
> +}
> +
> +struct file *
> +nfs_local_file_open(struct nfs_client *clp, const struct cred *cred,
> + struct nfs_fh *fh, struct nfs_open_context *ctx)
> +{
> + if (!nfs_server_is_local(clp))
> + return NULL;
> + return nfs_local_file_open_cached(clp, cred, fh, ctx);
> +}
> +
> +int
> +nfs_local_doio(struct nfs_client *clp, struct file *filp,
> + struct nfs_pgio_header *hdr,
> + const struct rpc_call_ops *call_ops)
> +{
> + int status = 0;
> +
> + if (!hdr->args.count)
> + goto out_fput;
> + /* Don't support filesystems without read_iter/write_iter */
> + if (!filp->f_op->read_iter || !filp->f_op->write_iter) {
> + nfs_local_disable(clp);
> + status = -EAGAIN;
> + goto out_fput;
> + }
> +
> + switch (hdr->rw_mode) {
> + case FMODE_READ:
> + status = nfs_do_local_read(hdr, filp, call_ops);
> + break;
> + case FMODE_WRITE:
> + status = nfs_do_local_write(hdr, filp, call_ops);
> + break;
> + default:
> + dprintk("%s: invalid mode: %d\n", __func__,
> + hdr->rw_mode);
> + status = -EINVAL;
> + }
> +out_fput:
> + if (status != 0) {
> + fput(filp);
> + hdr->task.tk_status = status;
> + nfs_local_hdr_release(hdr, call_ops);
> + }
> + return status;
> +}
> +
> +static void
> +nfs_local_init_commit(struct nfs_commit_data *data,
> + const struct rpc_call_ops *call_ops)
> +{
> + data->task.tk_ops = call_ops;
> +}
> +
> +static int
> +nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data)
> +{
> + loff_t start = data->args.offset;
> + loff_t end = LLONG_MAX;
> +
> + if (data->args.count > 0) {
> + end = start + data->args.count - 1;
> + if (end < start)
> + end = LLONG_MAX;
> + }
> +
> + dprintk("%s: commit %llu - %llu\n", __func__, start, end);
> + return vfs_fsync_range(filp, start, end, 0);
> +}
> +
> +static void
> +nfs_local_commit_done(struct nfs_commit_data *data, int status)
> +{
> + if (status >= 0) {
> + nfs_set_local_verifier(data->inode,
> + data->res.verf,
> + NFS_FILE_SYNC);
> + data->res.op_status = NFS4_OK;
> + data->task.tk_status = 0;
> + } else {
> + nfs_reset_boot_verifier(data->inode);
> + data->res.op_status = nfs4errno(status);
> + data->task.tk_status = status;
> + }
> +}
> +
> +static void
> +nfs_local_release_commit_data(struct file *filp,
> + struct nfs_commit_data *data,
> + const struct rpc_call_ops *call_ops)
> +{
> + fput(filp);
> + call_ops->rpc_call_done(&data->task, data);
> + call_ops->rpc_release(data);
> +}
> +
> +static struct nfs_local_fsync_ctx *
> +nfs_local_fsync_ctx_alloc(struct nfs_commit_data *data, struct file *filp,
> + gfp_t flags)
> +{
> + struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags);
> +
> + if (ctx != NULL) {
> + ctx->filp = filp;
> + ctx->data = data;
> + INIT_WORK(&ctx->work, nfs_local_fsync_work);
> + kref_init(&ctx->kref);
> + ctx->done = NULL;
> + }
> + return ctx;
> +}
> +
> +static void
> +nfs_local_fsync_ctx_kref_free(struct kref *kref)
> +{
> + kfree(container_of(kref, struct nfs_local_fsync_ctx, kref));
> +}
> +
> +static void
> +nfs_local_fsync_ctx_put(struct nfs_local_fsync_ctx *ctx)
> +{
> + kref_put(&ctx->kref, nfs_local_fsync_ctx_kref_free);
> +}
> +
> +static void
> +nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx)
> +{
> + nfs_local_release_commit_data(ctx->filp, ctx->data,
> + ctx->data->task.tk_ops);
> + nfs_local_fsync_ctx_put(ctx);
> +}
> +
> +static void
> +nfs_local_fsync_work(struct work_struct *work)
> +{
> + struct nfs_local_fsync_ctx *ctx;
> + int status;
> +
> + ctx = container_of(work, struct nfs_local_fsync_ctx, work);
> +
> + status = nfs_local_run_commit(ctx->filp, ctx->data);
> + nfs_local_commit_done(ctx->data, status);
> + if (ctx->done != NULL)
> + complete(ctx->done);
> + nfs_local_fsync_ctx_free(ctx);
> +}
> +
> +int
> +nfs_local_commit(struct file *filp, struct nfs_commit_data *data,
> + const struct rpc_call_ops *call_ops, int how)
> +{
> + struct nfs_local_fsync_ctx *ctx;
> +
> + ctx = nfs_local_fsync_ctx_alloc(data, filp, GFP_KERNEL);
> + if (!ctx) {
> + nfs_local_commit_done(data, -ENOMEM);
> + nfs_local_release_commit_data(filp, data, call_ops);
> + return -ENOMEM;
> + }
> +
> + nfs_local_init_commit(data, call_ops);
> + kref_get(&ctx->kref);
> + if (how & FLUSH_SYNC) {
> + DECLARE_COMPLETION_ONSTACK(done);
> + ctx->done = &done;
> + queue_work(nfsiod_workqueue, &ctx->work);
> + wait_for_completion(&done);
> + } else
> + queue_work(nfsiod_workqueue, &ctx->work);
> + nfs_local_fsync_ctx_put(ctx);
> + return 0;
> +}
> diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
> index 1e710654af11..95a2c19a9172 100644
> --- a/fs/nfs/nfstrace.h
> +++ b/fs/nfs/nfstrace.h
> @@ -1681,6 +1681,67 @@ TRACE_EVENT(nfs_mount_path,
> TP_printk("path='%s'", __get_str(path))
> );
>
> +TRACE_EVENT(nfs_local_open_fh,
> + TP_PROTO(
> + const struct nfs_fh *fh,
> + fmode_t fmode,
> + int error
> + ),
> +
> + TP_ARGS(fh, fmode, error),
> +
> + TP_STRUCT__entry(
> + __field(int, error)
> + __field(u32, fhandle)
> + __field(unsigned int, fmode)
> + ),
> +
> + TP_fast_assign(
> + __entry->error = error;
> + __entry->fhandle = nfs_fhandle_hash(fh);
> + __entry->fmode = (__force unsigned int)fmode;
> + ),
> +
> + TP_printk(
> + "error=%d fhandle=0x%08x mode=%s",
> + __entry->error,
> + __entry->fhandle,
> + show_fs_fmode_flags(__entry->fmode)
> + )
> +);
> +
> +DECLARE_EVENT_CLASS(nfs_local_client_event,
> + TP_PROTO(
> + const struct nfs_client *clp
> + ),
> +
> + TP_ARGS(clp),
> +
> + TP_STRUCT__entry(
> + __field(unsigned int, protocol)
> + __string(server, clp->cl_hostname)
> + ),
> +
> + TP_fast_assign(
> + __entry->protocol = clp->rpc_ops->version;
> + __assign_str(server);
> + ),
> +
> + TP_printk(
> + "server=%s NFSv%u", __get_str(server), __entry->protocol
> + )
> +);
> +
> +#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \
> + DEFINE_EVENT(nfs_local_client_event, name, \
> + TP_PROTO( \
> + const struct nfs_client *clp \
> + ), \
> + TP_ARGS(clp))
> +
> +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable);
> +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable);
> +
> DECLARE_EVENT_CLASS(nfs_xdr_event,
> TP_PROTO(
> const struct xdr_stream *xdr,
> diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
> index 57d62db3be5b..b08420b8e664 100644
> --- a/fs/nfs/pagelist.c
> +++ b/fs/nfs/pagelist.c
> @@ -879,6 +879,9 @@ int nfs_initiate_pgio(struct nfs_pageio_descriptor *desc,
> hdr->args.count,
> (unsigned long long)hdr->args.offset);
>
> + if (localio)
> + return nfs_local_doio(clp, localio, hdr, call_ops);
> +
> task = rpc_run_task(&task_setup_data);
> if (IS_ERR(task))
> return PTR_ERR(task);
> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> index 267bed2a4ceb..b29b0fd5431f 100644
> --- a/fs/nfs/write.c
> +++ b/fs/nfs/write.c
> @@ -1700,6 +1700,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
>
> dprintk("NFS: initiated commit call\n");
>
> + if (localio)
> + return nfs_local_commit(localio, data, call_ops, how);
> +
> task = rpc_run_task(&task_setup_data);
> if (IS_ERR(task))
> return PTR_ERR(task);
> diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
> index b8736a82e57c..78b421778a79 100644
> --- a/fs/nfsd/Makefile
> +++ b/fs/nfsd/Makefile
> @@ -23,3 +23,4 @@ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
> nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
> nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
> nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
> +nfsd-$(CONFIG_NFSD_LOCALIO) += localio.o
> diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
> index ad9083ca144b..99631fa56662 100644
> --- a/fs/nfsd/filecache.c
> +++ b/fs/nfsd/filecache.c
> @@ -52,7 +52,7 @@
> #define NFSD_FILE_CACHE_UP (0)
>
> /* We only care about NFSD_MAY_READ/WRITE for this cache */
> -#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE)
> +#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO)
>
> static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
> static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
> diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> new file mode 100644
> index 000000000000..e9aa0997f898
> --- /dev/null
> +++ b/fs/nfsd/localio.c
> @@ -0,0 +1,244 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * NFS server support for local clients to bypass network stack
> + *
> + * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
> + * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
> + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> + */
> +
> +#include <linux/exportfs.h>
> +#include <linux/sunrpc/svcauth_gss.h>
> +#include <linux/sunrpc/clnt.h>
> +#include <linux/nfs.h>
> +#include <linux/string.h>
> +
> +#include "nfsd.h"
> +#include "vfs.h"
> +#include "netns.h"
> +#include "filecache.h"
> +
> +#define NFSDDBG_FACILITY NFSDDBG_FH
I think I'd rather prefer to see trace points in here rather than
new dprintk call sites. In any event, perhaps NFSDDBG_FH is not
especially appropriate?
> +
> +/*
> + * We need to translate between nfs status return values and
> + * the local errno values which may not be the same.
> + * - duplicated from fs/nfs/nfs2xdr.c to avoid needless bloat of
> + * all compiled nfs objects if it were in include/linux/nfs.h
> + */
> +static const struct {
> + int stat;
> + int errno;
> +} nfs_common_errtbl[] = {
> + { NFS_OK, 0 },
> + { NFSERR_PERM, -EPERM },
> + { NFSERR_NOENT, -ENOENT },
> + { NFSERR_IO, -EIO },
> + { NFSERR_NXIO, -ENXIO },
> +/* { NFSERR_EAGAIN, -EAGAIN }, */
> + { NFSERR_ACCES, -EACCES },
> + { NFSERR_EXIST, -EEXIST },
> + { NFSERR_XDEV, -EXDEV },
> + { NFSERR_NODEV, -ENODEV },
> + { NFSERR_NOTDIR, -ENOTDIR },
> + { NFSERR_ISDIR, -EISDIR },
> + { NFSERR_INVAL, -EINVAL },
> + { NFSERR_FBIG, -EFBIG },
> + { NFSERR_NOSPC, -ENOSPC },
> + { NFSERR_ROFS, -EROFS },
> + { NFSERR_MLINK, -EMLINK },
> + { NFSERR_NAMETOOLONG, -ENAMETOOLONG },
> + { NFSERR_NOTEMPTY, -ENOTEMPTY },
> + { NFSERR_DQUOT, -EDQUOT },
> + { NFSERR_STALE, -ESTALE },
> + { NFSERR_REMOTE, -EREMOTE },
> +#ifdef EWFLUSH
> + { NFSERR_WFLUSH, -EWFLUSH },
> +#endif
> + { NFSERR_BADHANDLE, -EBADHANDLE },
> + { NFSERR_NOT_SYNC, -ENOTSYNC },
> + { NFSERR_BAD_COOKIE, -EBADCOOKIE },
> + { NFSERR_NOTSUPP, -ENOTSUPP },
> + { NFSERR_TOOSMALL, -ETOOSMALL },
> + { NFSERR_SERVERFAULT, -EREMOTEIO },
> + { NFSERR_BADTYPE, -EBADTYPE },
> + { NFSERR_JUKEBOX, -EJUKEBOX },
> + { -1, -EIO }
> +};
> +
> +/**
> + * nfs_stat_to_errno - convert an NFS status code to a local errno
> + * @status: NFS status code to convert
> + *
> + * Returns a local errno value, or -EIO if the NFS status code is
> + * not recognized. This function is used jointly by NFSv2 and NFSv3.
> + */
> +static int nfs_stat_to_errno(enum nfs_stat status)
> +{
> + int i;
> +
> + for (i = 0; nfs_common_errtbl[i].stat != -1; i++) {
> + if (nfs_common_errtbl[i].stat == (int)status)
> + return nfs_common_errtbl[i].errno;
> + }
> + return nfs_common_errtbl[i].errno;
> +}
I get it: The existing nfserrno() function on the server is the
reverse mapping from this one, and you need to undo the nfsstat
returned from nfsd_file_acquire().
The documenting comments here confusing in the context of why this
function is necessary on the server. For example, "This function is
used jointly by NFSv2 and NFSv3"... Maybe instead, explain that
nfsd_file_acquire() returns an nfsstat that needs to be translated
to an errno before being returned to a local client application.
> +static void
> +nfsd_local_fakerqst_destroy(struct svc_rqst *rqstp)
> +{
> + if (rqstp->rq_client)
> + auth_domain_put(rqstp->rq_client);
> + if (rqstp->rq_cred.cr_group_info)
> + put_group_info(rqstp->rq_cred.cr_group_info);
> + /* rpcauth_map_to_svc_cred_local() clears cr_principal */
> + WARN_ON_ONCE(rqstp->rq_cred.cr_principal != NULL);
> + kfree(rqstp->rq_xprt);
> + kfree(rqstp);
> +}
> +
> +static struct svc_rqst *
> +nfsd_local_fakerqst_create(struct net *net, struct rpc_clnt *rpc_clnt,
> + const struct cred *cred)
> +{
> + struct svc_rqst *rqstp;
> + struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> + int status;
> +
> + /* FIXME: not running in nfsd context, must get reference on nfsd_serv */
What's your plan for addressing this FIXME?
> + if (unlikely(!READ_ONCE(nn->nfsd_serv))) {
> + dprintk("%s: localio denied. Server not running\n", __func__);
> + return ERR_PTR(-ENXIO);
> + }
> +
> + rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
> + if (!rqstp)
> + return ERR_PTR(-ENOMEM);
> +
> + rqstp->rq_xprt = kzalloc(sizeof(*rqstp->rq_xprt), GFP_KERNEL);
> + if (!rqstp->rq_xprt) {
> + status = -ENOMEM;
> + goto out_err;
> + }
> +
> + rqstp->rq_xprt->xpt_net = net;
> + __set_bit(RQ_SECURE, &rqstp->rq_flags);
> + rqstp->rq_proc = 1;
> + rqstp->rq_vers = 3;
> + rqstp->rq_prot = IPPROTO_TCP;
> + rqstp->rq_server = nn->nfsd_serv;
> +
> + /* Note: we're connecting to ourself, so source addr == peer addr */
> + rqstp->rq_addrlen = rpc_peeraddr(rpc_clnt,
> + (struct sockaddr *)&rqstp->rq_addr,
> + sizeof(rqstp->rq_addr));
> +
> + rpcauth_map_to_svc_cred_local(rpc_clnt->cl_auth, cred, &rqstp->rq_cred);
> +
> + /*
> + * set up enough for svcauth_unix_set_client to be able to wait
> + * for the cache downcall. Note that we do _not_ want to allow the
> + * request to be deferred for later revisit since this rqst and xprt
> + * are not set up to run inside of the normal svc_rqst engine.
> + */
> + INIT_LIST_HEAD(&rqstp->rq_xprt->xpt_deferred);
> + kref_init(&rqstp->rq_xprt->xpt_ref);
> + spin_lock_init(&rqstp->rq_xprt->xpt_lock);
> + rqstp->rq_chandle.thread_wait = 5 * HZ;
> +
> + status = svcauth_unix_set_client(rqstp);
> + switch (status) {
> + case SVC_OK:
> + break;
> + case SVC_DENIED:
> + status = -ENXIO;
> + dprintk("%s: client %pISpc denied localio access\n",
> + __func__, (struct sockaddr *)&rqstp->rq_addr);
> + goto out_err;
> + default:
> + status = -ETIMEDOUT;
> + dprintk("%s: client %pISpc temporarily denied localio access\n",
> + __func__, (struct sockaddr *)&rqstp->rq_addr);
> + goto out_err;
> + }
> +
> + return rqstp;
> +
> +out_err:
> + nfsd_local_fakerqst_destroy(rqstp);
> + return ERR_PTR(status);
> +}
> +
> +/*
> + * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to @file
> + *
> + * This function maps a local fh to a path on a local filesystem.
> + * This is useful when the nfs client has the local server mounted - it can
> + * avoid all the NFS overhead with reads, writes and commits.
> + *
> + * on successful return, caller is responsible for calling path_put. Also
> + * note that this is called from nfs.ko via find_symbol() to avoid an explicit
> + * dependency on knfsd. So, there is no forward declaration in a header file
> + * for it.
> + */
> +int nfsd_open_local_fh(struct net *net,
> + struct rpc_clnt *rpc_clnt,
> + const struct cred *cred,
> + const struct nfs_fh *nfs_fh,
> + const fmode_t fmode,
> + struct file **pfilp)
> +{
> + const struct cred *save_cred;
> + struct svc_rqst *rqstp;
> + struct svc_fh fh;
> + struct nfsd_file *nf;
> + int status = 0;
> + int mayflags = NFSD_MAY_LOCALIO;
> + __be32 beres;
> +
> + /* Save creds before calling into nfsd */
> + save_cred = get_current_cred();
> +
> + rqstp = nfsd_local_fakerqst_create(net, rpc_clnt, cred);
> + if (IS_ERR(rqstp)) {
> + status = PTR_ERR(rqstp);
> + goto out_revertcred;
> + }
> +
> + /* nfs_fh -> svc_fh */
> + if (nfs_fh->size > NFS4_FHSIZE) {
> + status = -EINVAL;
> + goto out;
> + }
> + fh_init(&fh, NFS4_FHSIZE);
> + fh.fh_handle.fh_size = nfs_fh->size;
> + memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size);
> +
> + if (fmode & FMODE_READ)
> + mayflags |= NFSD_MAY_READ;
> + if (fmode & FMODE_WRITE)
> + mayflags |= NFSD_MAY_WRITE;
> +
> + beres = nfsd_file_acquire(rqstp, &fh, mayflags, &nf);
> + if (beres) {
> + status = nfs_stat_to_errno(be32_to_cpu(beres));
> + dprintk("%s: fh_verify failed %d\n", __func__, status);
> + goto out_fh_put;
> + }
> +
> + *pfilp = get_file(nf->nf_file);
> +
> + nfsd_file_put(nf);
> +out_fh_put:
> + fh_put(&fh);
> +
> +out:
> + nfsd_local_fakerqst_destroy(rqstp);
> +out_revertcred:
> + revert_creds(save_cred);
> + return status;
> +}
> +EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
> +
> +/* Compile time type checking, not used by anything */
> +static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index 1222a0a33fe1..a477d2c5088a 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -431,6 +431,7 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred)
> #endif
> #if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> INIT_LIST_HEAD(&nn->nfsd_uuid.list);
> + nn->nfsd_uuid.net = net;
> list_add_tail_rcu(&nn->nfsd_uuid.list, &nfsd_uuids);
> #endif
> nn->nfsd_net_up = true;
> diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
> index 77bbd23aa150..9c0610fdd11c 100644
> --- a/fs/nfsd/trace.h
> +++ b/fs/nfsd/trace.h
> @@ -86,7 +86,8 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
> { NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \
> { NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \
> { NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \
> - { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" })
> + { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }, \
> + { NFSD_MAY_LOCALIO, "LOCALIO" })
>
> TRACE_EVENT(nfsd_compound,
> TP_PROTO(
> diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
> index 57cd70062048..af07bb146e81 100644
> --- a/fs/nfsd/vfs.h
> +++ b/fs/nfsd/vfs.h
> @@ -36,6 +36,8 @@
> #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
> #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
>
> +#define NFSD_MAY_LOCALIO 0x800000
> +
Nit: I'd prefer to see NFSD_MAY_LOCALIO inserted just after
NFSD_MAY_64BIT_COOKIE. Is there a reason the value of the new flag
should not be 0x2000 ?
> struct nfsd_file;
>
> /*
> @@ -158,6 +160,13 @@ __be32 nfsd_permission(struct svc_rqst *, struct svc_export *,
>
> void nfsd_filp_close(struct file *fp);
>
> +int nfsd_open_local_fh(struct net *net,
> + struct rpc_clnt *rpc_clnt,
> + const struct cred *cred,
> + const struct nfs_fh *nfs_fh,
> + const fmode_t fmode,
> + struct file **pfilp);
> +
> static inline int fh_want_write(struct svc_fh *fh)
> {
> int ret;
> diff --git a/include/linux/nfs.h b/include/linux/nfs.h
> index ceb70a926b95..64ed672a0b34 100644
> --- a/include/linux/nfs.h
> +++ b/include/linux/nfs.h
> @@ -8,6 +8,8 @@
> #ifndef _LINUX_NFS_H
> #define _LINUX_NFS_H
>
> +#include <linux/cred.h>
> +#include <linux/sunrpc/auth.h>
> #include <linux/sunrpc/msg_prot.h>
> #include <linux/string.h>
> #include <linux/crc32.h>
> diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
> index 039898d70954..a0bb947fdd1d 100644
> --- a/include/linux/nfs_fs.h
> +++ b/include/linux/nfs_fs.h
> @@ -96,6 +96,8 @@ struct nfs_open_context {
> struct list_head list;
> struct nfs4_threshold *mdsthreshold;
> struct rcu_head rcu_head;
> +
> + struct file *local_filp;
> };
>
> struct nfs_open_dir_context {
> diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
> index e58e706a6503..4290c550a049 100644
> --- a/include/linux/nfs_fs_sb.h
> +++ b/include/linux/nfs_fs_sb.h
> @@ -50,6 +50,7 @@ struct nfs_client {
> #define NFS_CS_DS 7 /* - Server is a DS */
> #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */
> #define NFS_CS_PNFS 9 /* - Server used for pnfs */
> +#define NFS_CS_LOCAL_IO 10 /* - client is local */
> struct sockaddr_storage cl_addr; /* server identifier */
> size_t cl_addrlen;
> char * cl_hostname; /* hostname of server */
> --
> 2.44.0
>
--
Chuck Lever
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 06/20] nfs/nfsd: add "localio" support
2024-06-24 18:26 ` Chuck Lever
@ 2024-06-25 4:57 ` Mike Snitzer
2024-06-25 13:59 ` Chuck Lever
0 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-25 4:57 UTC (permalink / raw)
To: Chuck Lever; +Cc: linux-nfs, Jeff Layton, Trond Myklebust, NeilBrown, snitzer
On Mon, Jun 24, 2024 at 02:26:42PM -0400, Chuck Lever wrote:
> On Mon, Jun 24, 2024 at 12:27:27PM -0400, Mike Snitzer wrote:
> > From: Weston Andros Adamson <dros@primarydata.com>
> >
> > Add client support for bypassing NFS for localhost reads, writes, and
> > commits. This is only useful when the client and the server are
> > running on the same host.
> >
> > nfs_local_probe() is stubbed out, later commits will enable client and
> > server handshake via a Linux-only LOCALIO auxiliary RPC protocol.
> >
> > This has dynamic binding with the nfsd module (via nfs_localio module
> > which is part of nfs_common). Localio will only work if nfsd is
> > already loaded.
> >
> > The "localio_enabled" nfs kernel module parameter can be used to
> > disable and enable the ability to use localio support.
> >
> > Tracepoints were added for nfs_local_open_fh, nfs_local_enable and
> > nfs_local_disable.
> >
> > Also, pass the stored cl_nfssvc_net from the client to the server as
> > first argument to nfsd_open_local_fh() to ensure the proper network
> > namespace is used for localio.
> >
> > Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
> > Signed-off-by: Peng Tao <tao.peng@primarydata.com>
> > Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
> > Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > ---
> > fs/nfs/Makefile | 1 +
> > fs/nfs/client.c | 3 +
> > fs/nfs/inode.c | 4 +
> > fs/nfs/internal.h | 51 +++
> > fs/nfs/localio.c | 654 ++++++++++++++++++++++++++++++++++++++
> > fs/nfs/nfstrace.h | 61 ++++
> > fs/nfs/pagelist.c | 3 +
> > fs/nfs/write.c | 3 +
>
> Hi Mike -
>
> I'd prefer to see this patch split into two patches, one for the
> NFS client, and one for the NFS server. The other patches in this
> series seem to have a clear line between server and client
> changes.
Will do.
> > diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> > new file mode 100644
> > index 000000000000..e9aa0997f898
> > --- /dev/null
> > +++ b/fs/nfsd/localio.c
> > @@ -0,0 +1,244 @@
> > +// SPDX-License-Identifier: GPL-2.0-only
> > +/*
> > + * NFS server support for local clients to bypass network stack
> > + *
> > + * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
> > + * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
> > + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> > + */
> > +
> > +#include <linux/exportfs.h>
> > +#include <linux/sunrpc/svcauth_gss.h>
> > +#include <linux/sunrpc/clnt.h>
> > +#include <linux/nfs.h>
> > +#include <linux/string.h>
> > +
> > +#include "nfsd.h"
> > +#include "vfs.h"
> > +#include "netns.h"
> > +#include "filecache.h"
> > +
> > +#define NFSDDBG_FACILITY NFSDDBG_FH
>
> I think I'd rather prefer to see trace points in here rather than
> new dprintk call sites. In any event, perhaps NFSDDBG_FH is not
> especially appropriate?
I think NFSDDBG_FH is most appropriate given this localio is most
focused on opening a file handle. (The getuuid not so much)
I'm not loving how overdone the trace points interface is. in my
experience, trace points are also a serious source of conflicts when
backporting changes to older kernels.
But if you were inclined to switch this code over to trace points once
it is merged, who am I to stop you! ;)
> > +
> > +/**
> > + * nfs_stat_to_errno - convert an NFS status code to a local errno
> > + * @status: NFS status code to convert
> > + *
> > + * Returns a local errno value, or -EIO if the NFS status code is
> > + * not recognized. This function is used jointly by NFSv2 and NFSv3.
> > + */
> > +static int nfs_stat_to_errno(enum nfs_stat status)
> > +{
> > + int i;
> > +
> > + for (i = 0; nfs_common_errtbl[i].stat != -1; i++) {
> > + if (nfs_common_errtbl[i].stat == (int)status)
> > + return nfs_common_errtbl[i].errno;
> > + }
> > + return nfs_common_errtbl[i].errno;
> > +}
>
> I get it: The existing nfserrno() function on the server is the
> reverse mapping from this one, and you need to undo the nfsstat
> returned from nfsd_file_acquire().
>
> The documenting comments here confusing in the context of why this
> function is necessary on the server. For example, "This function is
> used jointly by NFSv2 and NFSv3"... Maybe instead, explain that
> nfsd_file_acquire() returns an nfsstat that needs to be translated
> to an errno before being returned to a local client application.
Thanks, fixed.
> > +static void
> > +nfsd_local_fakerqst_destroy(struct svc_rqst *rqstp)
> > +{
> > + if (rqstp->rq_client)
> > + auth_domain_put(rqstp->rq_client);
> > + if (rqstp->rq_cred.cr_group_info)
> > + put_group_info(rqstp->rq_cred.cr_group_info);
> > + /* rpcauth_map_to_svc_cred_local() clears cr_principal */
> > + WARN_ON_ONCE(rqstp->rq_cred.cr_principal != NULL);
> > + kfree(rqstp->rq_xprt);
> > + kfree(rqstp);
> > +}
> > +
> > +static struct svc_rqst *
> > +nfsd_local_fakerqst_create(struct net *net, struct rpc_clnt *rpc_clnt,
> > + const struct cred *cred)
> > +{
> > + struct svc_rqst *rqstp;
> > + struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> > + int status;
> > +
> > + /* FIXME: not running in nfsd context, must get reference on nfsd_serv */
>
> What's your plan for addressing this FIXME?
The SRCU (and nfsd_serv_get, nfsd_serv_put and nfsd_serv_sync) in
later patches addresses it.
FYI: And now that I looked closer at Neil's earlier suggestion (to
have a single SRCU for all of nfsd_net -- rather than having one
embedded in each): I'll try to include that change for v8.
> > diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
> > index 57cd70062048..af07bb146e81 100644
> > --- a/fs/nfsd/vfs.h
> > +++ b/fs/nfsd/vfs.h
> > @@ -36,6 +36,8 @@
> > #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
> > #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
> >
> > +#define NFSD_MAY_LOCALIO 0x800000
> > +
>
> Nit: I'd prefer to see NFSD_MAY_LOCALIO inserted just after
> NFSD_MAY_64BIT_COOKIE. Is there a reason the value of the new flag
> should not be 0x2000 ?
Fixed.
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 06/20] nfs/nfsd: add "localio" support
2024-06-25 4:57 ` Mike Snitzer
@ 2024-06-25 13:59 ` Chuck Lever
0 siblings, 0 replies; 40+ messages in thread
From: Chuck Lever @ 2024-06-25 13:59 UTC (permalink / raw)
To: Mike Snitzer; +Cc: linux-nfs, Jeff Layton, Trond Myklebust, NeilBrown, snitzer
On Tue, Jun 25, 2024 at 12:57:54AM -0400, Mike Snitzer wrote:
> On Mon, Jun 24, 2024 at 02:26:42PM -0400, Chuck Lever wrote:
> > On Mon, Jun 24, 2024 at 12:27:27PM -0400, Mike Snitzer wrote:
> > > From: Weston Andros Adamson <dros@primarydata.com>
> > > diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> > > new file mode 100644
> > > index 000000000000..e9aa0997f898
> > > --- /dev/null
> > > +++ b/fs/nfsd/localio.c
> > > @@ -0,0 +1,244 @@
> > > +// SPDX-License-Identifier: GPL-2.0-only
> > > +/*
> > > + * NFS server support for local clients to bypass network stack
> > > + *
> > > + * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
> > > + * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
> > > + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
> > > + */
> > > +
> > > +#include <linux/exportfs.h>
> > > +#include <linux/sunrpc/svcauth_gss.h>
> > > +#include <linux/sunrpc/clnt.h>
> > > +#include <linux/nfs.h>
> > > +#include <linux/string.h>
> > > +
> > > +#include "nfsd.h"
> > > +#include "vfs.h"
> > > +#include "netns.h"
> > > +#include "filecache.h"
> > > +
> > > +#define NFSDDBG_FACILITY NFSDDBG_FH
> >
> > I think I'd rather prefer to see trace points in here rather than
> > new dprintk call sites. In any event, perhaps NFSDDBG_FH is not
> > especially appropriate?
>
> I think NFSDDBG_FH is most appropriate given this localio is most
> focused on opening a file handle. (The getuuid not so much)
If more than one debugging facility is appropriate, consider using
dfprintk() instead so each call site can specify its preferred
facility.
> I'm not loving how overdone the trace points interface is. in my
> experience, trace points are also a serious source of conflicts when
> backporting changes to older kernels.
>
> But if you were inclined to switch this code over to trace points once
> it is merged, who am I to stop you! ;)
Have a heartfelt conversation with yourself about whether all of
these dprintk's need to stay, then.
Anything you've been using strictly as a development tool can be
considered disposable. Anything an admin or support engineer might
want to enable to diagnose a local configuration or deployment issue
is a candidate for staying in the code. And so on and so forth.
--
Chuck Lever
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 07/20] nfsd/localio: manage netns reference in nfsd_open_local_fh
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (5 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 06/20] nfs/nfsd: add "localio" support Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 08/20] NFS: Enable localio for non-pNFS I/O Mike Snitzer
` (13 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
Use maybe_get_net() and put_net() in nfsd_open_local_fh().
Also refactor nfsd_open_local_fh() slightly.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfsd/localio.c | 45 ++++++++++++++++++++++++++-------------------
1 file changed, 26 insertions(+), 19 deletions(-)
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index e9aa0997f898..f6df66b1d523 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -99,18 +99,11 @@ nfsd_local_fakerqst_destroy(struct svc_rqst *rqstp)
static struct svc_rqst *
nfsd_local_fakerqst_create(struct net *net, struct rpc_clnt *rpc_clnt,
- const struct cred *cred)
+ const struct cred *cred, struct svc_serv *serv)
{
struct svc_rqst *rqstp;
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int status;
- /* FIXME: not running in nfsd context, must get reference on nfsd_serv */
- if (unlikely(!READ_ONCE(nn->nfsd_serv))) {
- dprintk("%s: localio denied. Server not running\n", __func__);
- return ERR_PTR(-ENXIO);
- }
-
rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
return ERR_PTR(-ENOMEM);
@@ -120,13 +113,13 @@ nfsd_local_fakerqst_create(struct net *net, struct rpc_clnt *rpc_clnt,
status = -ENOMEM;
goto out_err;
}
-
rqstp->rq_xprt->xpt_net = net;
+
__set_bit(RQ_SECURE, &rqstp->rq_flags);
rqstp->rq_proc = 1;
rqstp->rq_vers = 3;
rqstp->rq_prot = IPPROTO_TCP;
- rqstp->rq_server = nn->nfsd_serv;
+ rqstp->rq_server = serv;
/* Note: we're connecting to ourself, so source addr == peer addr */
rqstp->rq_addrlen = rpc_peeraddr(rpc_clnt,
@@ -188,28 +181,44 @@ int nfsd_open_local_fh(struct net *net,
const fmode_t fmode,
struct file **pfilp)
{
+ struct nfsd_net *nn;
const struct cred *save_cred;
struct svc_rqst *rqstp;
struct svc_fh fh;
struct nfsd_file *nf;
int status = 0;
int mayflags = NFSD_MAY_LOCALIO;
+ struct svc_serv *serv;
__be32 beres;
+ if (nfs_fh->size > NFS4_FHSIZE)
+ return -EINVAL;
+
+ /* Not running in nfsd context, must safely get reference on nfsd_serv */
+ net = maybe_get_net(net);
+ if (!net) {
+ dprintk("%s: localio denied. Server netns not available\n", __func__);
+ return -ENXIO;
+ }
+ nn = net_generic(net, nfsd_net_id);
+
+ serv = READ_ONCE(nn->nfsd_serv);
+ if (unlikely(!serv)) {
+ dprintk("%s: localio denied. Server not running\n", __func__);
+ status = -ENXIO;
+ goto out_net;
+ }
+
/* Save creds before calling into nfsd */
save_cred = get_current_cred();
- rqstp = nfsd_local_fakerqst_create(net, rpc_clnt, cred);
+ rqstp = nfsd_local_fakerqst_create(net, rpc_clnt, cred, serv);
if (IS_ERR(rqstp)) {
status = PTR_ERR(rqstp);
goto out_revertcred;
}
/* nfs_fh -> svc_fh */
- if (nfs_fh->size > NFS4_FHSIZE) {
- status = -EINVAL;
- goto out;
- }
fh_init(&fh, NFS4_FHSIZE);
fh.fh_handle.fh_size = nfs_fh->size;
memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size);
@@ -225,17 +234,15 @@ int nfsd_open_local_fh(struct net *net,
dprintk("%s: fh_verify failed %d\n", __func__, status);
goto out_fh_put;
}
-
*pfilp = get_file(nf->nf_file);
-
nfsd_file_put(nf);
out_fh_put:
fh_put(&fh);
-
-out:
nfsd_local_fakerqst_destroy(rqstp);
out_revertcred:
revert_creds(save_cred);
+out_net:
+ put_net(net);
return status;
}
EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 08/20] NFS: Enable localio for non-pNFS I/O
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (6 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 07/20] nfsd/localio: manage netns reference in nfsd_open_local_fh Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 09/20] pnfs/flexfiles: Enable localio for flexfiles I/O Mike Snitzer
` (12 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Try a local open of the file we're writing to, and if it succeeds, then
do local I/O.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/pagelist.c | 19 ++++++++++---------
fs/nfs/write.c | 7 ++++++-
2 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index b08420b8e664..3ee78da5ebc4 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1063,6 +1063,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio);
static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
{
struct nfs_pgio_header *hdr;
+ struct file *filp;
int ret;
unsigned short task_flags = 0;
@@ -1074,18 +1075,18 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
nfs_pgheader_init(desc, hdr, nfs_pgio_header_free);
ret = nfs_generic_pgio(desc, hdr);
if (ret == 0) {
+ struct nfs_client *clp = NFS_SERVER(hdr->inode)->nfs_client;
+
+ filp = nfs_local_file_open(clp, hdr->cred, hdr->args.fh,
+ hdr->args.context);
+
if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
- ret = nfs_initiate_pgio(desc,
- NFS_SERVER(hdr->inode)->nfs_client,
- NFS_CLIENT(hdr->inode),
- hdr,
- hdr->cred,
- NFS_PROTO(hdr->inode),
- desc->pg_rpc_callops,
- desc->pg_ioflags,
+ ret = nfs_initiate_pgio(desc, clp, NFS_CLIENT(hdr->inode),
+ hdr, hdr->cred, NFS_PROTO(hdr->inode),
+ desc->pg_rpc_callops, desc->pg_ioflags,
RPC_TASK_CRED_NOREF | task_flags,
- NULL);
+ filp);
}
return ret;
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b29b0fd5431f..b2c06b8b88cd 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1802,6 +1802,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
struct nfs_commit_info *cinfo)
{
struct nfs_commit_data *data;
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+ struct file *filp;
unsigned short task_flags = 0;
/* another commit raced with us */
@@ -1818,9 +1820,12 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
nfs_init_commit(data, head, NULL, cinfo);
if (NFS_SERVER(inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
+
+ filp = nfs_local_file_open(clp, data->cred, data->args.fh,
+ data->context);
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
data->mds_ops, how,
- RPC_TASK_CRED_NOREF | task_flags, NULL);
+ RPC_TASK_CRED_NOREF | task_flags, filp);
}
/*
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 09/20] pnfs/flexfiles: Enable localio for flexfiles I/O
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (7 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 08/20] NFS: Enable localio for non-pNFS I/O Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 10/20] nfs/localio: use dedicated workqueues for filesystem read and write Mike Snitzer
` (11 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Trond Myklebust <trond.myklebust@hammerspace.com>
If the DS is local to this client, then we should be able to use local
I/O to write the data.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 113 ++++++++++++++++++++--
fs/nfs/flexfilelayout/flexfilelayout.h | 2 +
fs/nfs/flexfilelayout/flexfilelayoutdev.c | 6 ++
3 files changed, 112 insertions(+), 9 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 3ea07446f05a..ec6aaa110a7b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,6 +11,7 @@
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/file.h>
#include <linux/sched/mm.h>
#include <linux/sunrpc/metrics.h>
@@ -162,6 +163,52 @@ decode_name(struct xdr_stream *xdr, u32 *id)
return 0;
}
+static struct file *
+ff_local_open_fh(struct pnfs_layout_segment *lseg,
+ u32 ds_idx,
+ struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ fmode_t mode)
+{
+ struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+ struct file *filp, *new, __rcu **pfile;
+
+ if (!nfs_server_is_local(clp))
+ return NULL;
+ if (mode & FMODE_WRITE) {
+ /*
+ * Always request read and write access since this corresponds
+ * to a rw layout.
+ */
+ mode |= FMODE_READ;
+ pfile = &mirror->rw_file;
+ } else
+ pfile = &mirror->ro_file;
+
+ new = NULL;
+ rcu_read_lock();
+ filp = rcu_dereference(*pfile);
+ if (!filp) {
+ rcu_read_unlock();
+ new = nfs_local_open_fh(clp, cred, fh, mode);
+ if (IS_ERR(new))
+ return NULL;
+ rcu_read_lock();
+ /* try to swap in the pointer */
+ filp = cmpxchg(pfile, NULL, new);
+ if (!filp) {
+ filp = new;
+ new = NULL;
+ }
+ }
+ filp = get_file_rcu(&filp);
+ rcu_read_unlock();
+ if (new)
+ fput(new);
+ return filp;
+}
+
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
const struct nfs4_ff_layout_mirror *m2)
{
@@ -237,8 +284,15 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
+ struct file *filp;
const struct cred *cred;
+ filp = rcu_access_pointer(mirror->ro_file);
+ if (filp)
+ fput(filp);
+ filp = rcu_access_pointer(mirror->rw_file);
+ if (filp)
+ fput(filp);
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
cred = rcu_access_pointer(mirror->ro_cred);
@@ -414,6 +468,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
struct nfs4_ff_layout_mirror *mirror;
struct cred *kcred;
const struct cred __rcu *cred;
+ const struct cred __rcu *old;
kuid_t uid;
kgid_t gid;
u32 ds_count, fh_count, id;
@@ -513,13 +568,26 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
if (mirror != fls->mirror_array[i]) {
+ struct file *filp;
+
/* swap cred ptrs so free_mirror will clean up old */
if (lgr->range.iomode == IOMODE_READ) {
- cred = xchg(&mirror->ro_cred, cred);
- rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ old = xchg(&mirror->ro_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, old);
+ /* drop file if creds changed */
+ if (old != cred) {
+ filp = rcu_dereference_protected(xchg(&mirror->ro_file, NULL), 1);
+ if (filp)
+ fput(filp);
+ }
} else {
- cred = xchg(&mirror->rw_cred, cred);
- rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+ old = xchg(&mirror->rw_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, old);
+ if (old != cred) {
+ filp = rcu_dereference_protected(xchg(&mirror->rw_file, NULL), 1);
+ if (filp)
+ fput(filp);
+ }
}
ff_layout_free_mirror(fls->mirror_array[i]);
fls->mirror_array[i] = mirror;
@@ -1757,6 +1825,7 @@ ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1803,12 +1872,20 @@ ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
hdr->args.offset = offset;
hdr->mds_offset = offset;
+ /* Start IO accounting for local read */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ);
+ if (filp) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
- 0, RPC_TASK_SOFTCONN, NULL);
+ 0, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1829,6 +1906,7 @@ ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1873,12 +1951,20 @@ ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
*/
hdr->args.offset = offset;
+ /* Start IO accounting for local write */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (filp) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous write */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
- sync, RPC_TASK_SOFTCONN, NULL);
+ sync, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1912,6 +1998,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
u32 idx;
@@ -1950,10 +2037,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
if (fh)
data->args.fh = fh;
+ /* Start IO accounting for local commit */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (filp) {
+ data->task.tk_start = ktime_get();
+ ff_layout_commit_record_layoutstats_start(&data->task, data);
+ }
+
ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
- vers == 3 ? &ff_layout_commit_call_ops_v3 :
- &ff_layout_commit_call_ops_v4,
- how, RPC_TASK_SOFTCONN, NULL);
+ vers == 3 ? &ff_layout_commit_call_ops_v3 :
+ &ff_layout_commit_call_ops_v4,
+ how, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return ret;
out_err:
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f84b3fb0dddd..8e042df5a2c9 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -82,7 +82,9 @@ struct nfs4_ff_layout_mirror {
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
const struct cred __rcu *ro_cred;
+ struct file __rcu *ro_file;
const struct cred __rcu *rw_cred;
+ struct file __rcu *rw_file;
refcount_t ref;
spinlock_t lock;
unsigned long flags;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e028f5a0ef5f..e58bedfb1dcc 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -395,6 +395,12 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
/* connect success, check rsize/wsize limit */
if (!status) {
+ /*
+ * ds_clp is put in destroy_ds().
+ * keep ds_clp even if DS is local, so that if local IO cannot
+ * proceed somehow, we can fall back to NFS whenever we want.
+ */
+ nfs_local_probe(ds->ds_clp);
max_payload =
nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
NULL);
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 10/20] nfs/localio: use dedicated workqueues for filesystem read and write
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (8 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 09/20] pnfs/flexfiles: Enable localio for flexfiles I/O Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 23:15 ` NeilBrown
2024-06-24 16:27 ` [PATCH v7 11/20] nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h Mike Snitzer
` (10 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: Trond Myklebust <trond.myklebust@hammerspace.com>
For localio access, don't call filesystem read() and write() routines
directly.
Some filesystem writeback routines can end up taking up a lot of stack
space (particularly xfs). Instead of risking running over due to the
extra overhead from the NFS stack, we should just call these routines
from a workqueue job.
Use of dedicated workqueues improves performance over using the
system_unbound_wq. Localio is motivated by the promise of improved
performance, it makes little sense to yield it back.
But further analysis of the latest stack depth requirements would be
useful. It'd be nice to root cause and fix the latest stack hogs,
because using workqueues at all can cause a loss in performance due to
context switches.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/inode.c | 57 +++++++++++++++++---------
fs/nfs/internal.h | 1 +
fs/nfs/localio.c | 102 +++++++++++++++++++++++++++++++++++-----------
3 files changed, 118 insertions(+), 42 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f9923cbf6058..aac8c5302503 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2394,35 +2394,54 @@ static void nfs_destroy_inodecache(void)
kmem_cache_destroy(nfs_inode_cachep);
}
+struct workqueue_struct *nfslocaliod_workqueue;
struct workqueue_struct *nfsiod_workqueue;
EXPORT_SYMBOL_GPL(nfsiod_workqueue);
/*
- * start up the nfsiod workqueue
- */
-static int nfsiod_start(void)
-{
- struct workqueue_struct *wq;
- dprintk("RPC: creating workqueue nfsiod\n");
- wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
- if (wq == NULL)
- return -ENOMEM;
- nfsiod_workqueue = wq;
- return 0;
-}
-
-/*
- * Destroy the nfsiod workqueue
+ * Destroy the nfsiod workqueues
*/
static void nfsiod_stop(void)
{
struct workqueue_struct *wq;
wq = nfsiod_workqueue;
- if (wq == NULL)
- return;
- nfsiod_workqueue = NULL;
- destroy_workqueue(wq);
+ if (wq != NULL) {
+ nfsiod_workqueue = NULL;
+ destroy_workqueue(wq);
+ }
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ wq = nfslocaliod_workqueue;
+ if (wq != NULL) {
+ nfslocaliod_workqueue = NULL;
+ destroy_workqueue(wq);
+ }
+#endif /* CONFIG_NFS_LOCALIO */
+}
+
+/*
+ * Start the nfsiod workqueues
+ */
+static int nfsiod_start(void)
+{
+ dprintk("RPC: creating workqueue nfsiod\n");
+ nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+ if (nfsiod_workqueue == NULL)
+ return -ENOMEM;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ /*
+ * localio writes need to use a normal (non-memreclaim) workqueue.
+ * When we start getting low on space, XFS goes and calls flush_work() on
+ * a non-memreclaim work queue, which causes a priority inversion problem.
+ */
+ dprintk("RPC: creating workqueue nfslocaliod\n");
+ nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0);
+ if (unlikely(nfslocaliod_workqueue == NULL)) {
+ nfsiod_stop();
+ return -ENOMEM;
+ }
+#endif /* CONFIG_NFS_LOCALIO */
+ return 0;
}
unsigned int nfs_net_id;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d352040e3232..9251a357d097 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -440,6 +440,7 @@ int nfs_check_flags(int);
/* inode.c */
extern struct workqueue_struct *nfsiod_workqueue;
+extern struct workqueue_struct *nfslocaliod_workqueue;
extern struct inode *nfs_alloc_inode(struct super_block *sb);
extern void nfs_free_inode(struct inode *);
extern int nfs_write_inode(struct inode *, struct writeback_control *);
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 724e81716b16..418b8d76692b 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -44,6 +44,12 @@ struct nfs_local_fsync_ctx {
};
static void nfs_local_fsync_work(struct work_struct *work);
+struct nfs_local_io_args {
+ struct nfs_local_kiocb *iocb;
+ struct work_struct work;
+ struct completion *done;
+};
+
/*
* We need to translate between nfs status return values and
* the local errno values which may not be the same.
@@ -307,30 +313,54 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
status > 0 ? status : 0, hdr->res.eof);
}
-static int
-nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
- const struct rpc_call_ops *call_ops)
+static void nfs_local_call_read(struct work_struct *work)
{
- struct nfs_local_kiocb *iocb;
+ struct nfs_local_io_args *args =
+ container_of(work, struct nfs_local_io_args, work);
+ struct nfs_local_kiocb *iocb = args->iocb;
+ struct file *filp = iocb->kiocb.ki_filp;
struct iov_iter iter;
ssize_t status;
+ nfs_local_iter_init(&iter, iocb, READ);
+
+ status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_read_done(iocb, status);
+ nfs_local_pgio_release(iocb);
+ }
+ complete(args->done);
+}
+
+static int nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_io_args args;
+ DECLARE_COMPLETION_ONSTACK(done);
+ struct nfs_local_kiocb *iocb;
+
dprintk("%s: vfs_read count=%u pos=%llu\n",
__func__, hdr->args.count, hdr->args.offset);
iocb = nfs_local_iocb_alloc(hdr, filp, GFP_KERNEL);
if (iocb == NULL)
return -ENOMEM;
- nfs_local_iter_init(&iter, iocb, READ);
nfs_local_pgio_init(hdr, call_ops);
hdr->res.eof = false;
- status = filp->f_op->read_iter(&iocb->kiocb, &iter);
- if (status != -EIOCBQUEUED) {
- nfs_local_read_done(iocb, status);
- nfs_local_pgio_release(iocb);
- }
+ /*
+ * Don't call filesystem read() routines directly.
+ * In order to avoid issues with stack overflow,
+ * call the read routines from a workqueue job.
+ */
+ args.iocb = iocb;
+ args.done = &done;
+ INIT_WORK_ONSTACK(&args.work, nfs_local_call_read);
+ queue_work(nfslocaliod_workqueue, &args.work);
+ wait_for_completion(&done);
+ destroy_work_on_stack(&args.work);
+
return 0;
}
@@ -420,14 +450,35 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
nfs_local_pgio_done(hdr, status);
}
-static int
-nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
- const struct rpc_call_ops *call_ops)
+static void nfs_local_call_write(struct work_struct *work)
{
- struct nfs_local_kiocb *iocb;
+ struct nfs_local_io_args *args =
+ container_of(work, struct nfs_local_io_args, work);
+ struct nfs_local_kiocb *iocb = args->iocb;
+ struct file *filp = iocb->kiocb.ki_filp;
struct iov_iter iter;
ssize_t status;
+ nfs_local_iter_init(&iter, iocb, WRITE);
+
+ file_start_write(filp);
+ status = filp->f_op->write_iter(&iocb->kiocb, &iter);
+ file_end_write(filp);
+ if (status != -EIOCBQUEUED) {
+ nfs_local_write_done(iocb, status);
+ nfs_get_vfs_attr(filp, iocb->hdr->res.fattr);
+ nfs_local_pgio_release(iocb);
+ }
+ complete(args->done);
+}
+
+static int nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
+ const struct rpc_call_ops *call_ops)
+{
+ struct nfs_local_io_args args;
+ DECLARE_COMPLETION_ONSTACK(done);
+ struct nfs_local_kiocb *iocb;
+
dprintk("%s: vfs_write count=%u pos=%llu %s\n",
__func__, hdr->args.count, hdr->args.offset,
(hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable");
@@ -435,7 +486,6 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
iocb = nfs_local_iocb_alloc(hdr, filp, GFP_NOIO);
if (iocb == NULL)
return -ENOMEM;
- nfs_local_iter_init(&iter, iocb, WRITE);
switch (hdr->args.stable) {
default:
@@ -450,14 +500,20 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
- file_start_write(filp);
- status = filp->f_op->write_iter(&iocb->kiocb, &iter);
- file_end_write(filp);
- if (status != -EIOCBQUEUED) {
- nfs_local_write_done(iocb, status);
- nfs_get_vfs_attr(filp, hdr->res.fattr);
- nfs_local_pgio_release(iocb);
- }
+ /*
+ * Don't call filesystem write() routines directly.
+ * Some filesystem writeback routines can end up taking up a lot of
+ * stack (particularly xfs). Instead of risking running over due to
+ * the extra overhead from the NFS stack, call these write routines
+ * from a workqueue job.
+ */
+ args.iocb = iocb;
+ args.done = &done;
+ INIT_WORK_ONSTACK(&args.work, nfs_local_call_write);
+ queue_work(nfslocaliod_workqueue, &args.work);
+ wait_for_completion(&done);
+ destroy_work_on_stack(&args.work);
+
return 0;
}
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 10/20] nfs/localio: use dedicated workqueues for filesystem read and write
2024-06-24 16:27 ` [PATCH v7 10/20] nfs/localio: use dedicated workqueues for filesystem read and write Mike Snitzer
@ 2024-06-25 23:15 ` NeilBrown
0 siblings, 0 replies; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:15 UTC (permalink / raw)
To: Mike Snitzer
Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Mike Snitzer wrote:
> From: Trond Myklebust <trond.myklebust@hammerspace.com>
>
> For localio access, don't call filesystem read() and write() routines
> directly.
>
> Some filesystem writeback routines can end up taking up a lot of stack
> space (particularly xfs). Instead of risking running over due to the
> extra overhead from the NFS stack, we should just call these routines
> from a workqueue job.
>
> Use of dedicated workqueues improves performance over using the
> system_unbound_wq. Localio is motivated by the promise of improved
> performance, it makes little sense to yield it back.
>
> But further analysis of the latest stack depth requirements would be
> useful. It'd be nice to root cause and fix the latest stack hogs,
> because using workqueues at all can cause a loss in performance due to
> context switches.
>
I would rather this patch were left out of the final submission, and
only added if/when we have documented evidence that it helps.
Thanks,
NeilBrown
> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> fs/nfs/inode.c | 57 +++++++++++++++++---------
> fs/nfs/internal.h | 1 +
> fs/nfs/localio.c | 102 +++++++++++++++++++++++++++++++++++-----------
> 3 files changed, 118 insertions(+), 42 deletions(-)
>
> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
> index f9923cbf6058..aac8c5302503 100644
> --- a/fs/nfs/inode.c
> +++ b/fs/nfs/inode.c
> @@ -2394,35 +2394,54 @@ static void nfs_destroy_inodecache(void)
> kmem_cache_destroy(nfs_inode_cachep);
> }
>
> +struct workqueue_struct *nfslocaliod_workqueue;
> struct workqueue_struct *nfsiod_workqueue;
> EXPORT_SYMBOL_GPL(nfsiod_workqueue);
>
> /*
> - * start up the nfsiod workqueue
> - */
> -static int nfsiod_start(void)
> -{
> - struct workqueue_struct *wq;
> - dprintk("RPC: creating workqueue nfsiod\n");
> - wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
> - if (wq == NULL)
> - return -ENOMEM;
> - nfsiod_workqueue = wq;
> - return 0;
> -}
> -
> -/*
> - * Destroy the nfsiod workqueue
> + * Destroy the nfsiod workqueues
> */
> static void nfsiod_stop(void)
> {
> struct workqueue_struct *wq;
>
> wq = nfsiod_workqueue;
> - if (wq == NULL)
> - return;
> - nfsiod_workqueue = NULL;
> - destroy_workqueue(wq);
> + if (wq != NULL) {
> + nfsiod_workqueue = NULL;
> + destroy_workqueue(wq);
> + }
> +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> + wq = nfslocaliod_workqueue;
> + if (wq != NULL) {
> + nfslocaliod_workqueue = NULL;
> + destroy_workqueue(wq);
> + }
> +#endif /* CONFIG_NFS_LOCALIO */
> +}
> +
> +/*
> + * Start the nfsiod workqueues
> + */
> +static int nfsiod_start(void)
> +{
> + dprintk("RPC: creating workqueue nfsiod\n");
> + nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
> + if (nfsiod_workqueue == NULL)
> + return -ENOMEM;
> +#if IS_ENABLED(CONFIG_NFS_LOCALIO)
> + /*
> + * localio writes need to use a normal (non-memreclaim) workqueue.
> + * When we start getting low on space, XFS goes and calls flush_work() on
> + * a non-memreclaim work queue, which causes a priority inversion problem.
> + */
> + dprintk("RPC: creating workqueue nfslocaliod\n");
> + nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0);
> + if (unlikely(nfslocaliod_workqueue == NULL)) {
> + nfsiod_stop();
> + return -ENOMEM;
> + }
> +#endif /* CONFIG_NFS_LOCALIO */
> + return 0;
> }
>
> unsigned int nfs_net_id;
> diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
> index d352040e3232..9251a357d097 100644
> --- a/fs/nfs/internal.h
> +++ b/fs/nfs/internal.h
> @@ -440,6 +440,7 @@ int nfs_check_flags(int);
>
> /* inode.c */
> extern struct workqueue_struct *nfsiod_workqueue;
> +extern struct workqueue_struct *nfslocaliod_workqueue;
> extern struct inode *nfs_alloc_inode(struct super_block *sb);
> extern void nfs_free_inode(struct inode *);
> extern int nfs_write_inode(struct inode *, struct writeback_control *);
> diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
> index 724e81716b16..418b8d76692b 100644
> --- a/fs/nfs/localio.c
> +++ b/fs/nfs/localio.c
> @@ -44,6 +44,12 @@ struct nfs_local_fsync_ctx {
> };
> static void nfs_local_fsync_work(struct work_struct *work);
>
> +struct nfs_local_io_args {
> + struct nfs_local_kiocb *iocb;
> + struct work_struct work;
> + struct completion *done;
> +};
> +
> /*
> * We need to translate between nfs status return values and
> * the local errno values which may not be the same.
> @@ -307,30 +313,54 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
> status > 0 ? status : 0, hdr->res.eof);
> }
>
> -static int
> -nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
> - const struct rpc_call_ops *call_ops)
> +static void nfs_local_call_read(struct work_struct *work)
> {
> - struct nfs_local_kiocb *iocb;
> + struct nfs_local_io_args *args =
> + container_of(work, struct nfs_local_io_args, work);
> + struct nfs_local_kiocb *iocb = args->iocb;
> + struct file *filp = iocb->kiocb.ki_filp;
> struct iov_iter iter;
> ssize_t status;
>
> + nfs_local_iter_init(&iter, iocb, READ);
> +
> + status = filp->f_op->read_iter(&iocb->kiocb, &iter);
> + if (status != -EIOCBQUEUED) {
> + nfs_local_read_done(iocb, status);
> + nfs_local_pgio_release(iocb);
> + }
> + complete(args->done);
> +}
> +
> +static int nfs_do_local_read(struct nfs_pgio_header *hdr, struct file *filp,
> + const struct rpc_call_ops *call_ops)
> +{
> + struct nfs_local_io_args args;
> + DECLARE_COMPLETION_ONSTACK(done);
> + struct nfs_local_kiocb *iocb;
> +
> dprintk("%s: vfs_read count=%u pos=%llu\n",
> __func__, hdr->args.count, hdr->args.offset);
>
> iocb = nfs_local_iocb_alloc(hdr, filp, GFP_KERNEL);
> if (iocb == NULL)
> return -ENOMEM;
> - nfs_local_iter_init(&iter, iocb, READ);
>
> nfs_local_pgio_init(hdr, call_ops);
> hdr->res.eof = false;
>
> - status = filp->f_op->read_iter(&iocb->kiocb, &iter);
> - if (status != -EIOCBQUEUED) {
> - nfs_local_read_done(iocb, status);
> - nfs_local_pgio_release(iocb);
> - }
> + /*
> + * Don't call filesystem read() routines directly.
> + * In order to avoid issues with stack overflow,
> + * call the read routines from a workqueue job.
> + */
> + args.iocb = iocb;
> + args.done = &done;
> + INIT_WORK_ONSTACK(&args.work, nfs_local_call_read);
> + queue_work(nfslocaliod_workqueue, &args.work);
> + wait_for_completion(&done);
> + destroy_work_on_stack(&args.work);
> +
> return 0;
> }
>
> @@ -420,14 +450,35 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
> nfs_local_pgio_done(hdr, status);
> }
>
> -static int
> -nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
> - const struct rpc_call_ops *call_ops)
> +static void nfs_local_call_write(struct work_struct *work)
> {
> - struct nfs_local_kiocb *iocb;
> + struct nfs_local_io_args *args =
> + container_of(work, struct nfs_local_io_args, work);
> + struct nfs_local_kiocb *iocb = args->iocb;
> + struct file *filp = iocb->kiocb.ki_filp;
> struct iov_iter iter;
> ssize_t status;
>
> + nfs_local_iter_init(&iter, iocb, WRITE);
> +
> + file_start_write(filp);
> + status = filp->f_op->write_iter(&iocb->kiocb, &iter);
> + file_end_write(filp);
> + if (status != -EIOCBQUEUED) {
> + nfs_local_write_done(iocb, status);
> + nfs_get_vfs_attr(filp, iocb->hdr->res.fattr);
> + nfs_local_pgio_release(iocb);
> + }
> + complete(args->done);
> +}
> +
> +static int nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
> + const struct rpc_call_ops *call_ops)
> +{
> + struct nfs_local_io_args args;
> + DECLARE_COMPLETION_ONSTACK(done);
> + struct nfs_local_kiocb *iocb;
> +
> dprintk("%s: vfs_write count=%u pos=%llu %s\n",
> __func__, hdr->args.count, hdr->args.offset,
> (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable");
> @@ -435,7 +486,6 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
> iocb = nfs_local_iocb_alloc(hdr, filp, GFP_NOIO);
> if (iocb == NULL)
> return -ENOMEM;
> - nfs_local_iter_init(&iter, iocb, WRITE);
>
> switch (hdr->args.stable) {
> default:
> @@ -450,14 +500,20 @@ nfs_do_local_write(struct nfs_pgio_header *hdr, struct file *filp,
>
> nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
>
> - file_start_write(filp);
> - status = filp->f_op->write_iter(&iocb->kiocb, &iter);
> - file_end_write(filp);
> - if (status != -EIOCBQUEUED) {
> - nfs_local_write_done(iocb, status);
> - nfs_get_vfs_attr(filp, hdr->res.fattr);
> - nfs_local_pgio_release(iocb);
> - }
> + /*
> + * Don't call filesystem write() routines directly.
> + * Some filesystem writeback routines can end up taking up a lot of
> + * stack (particularly xfs). Instead of risking running over due to
> + * the extra overhead from the NFS stack, call these write routines
> + * from a workqueue job.
> + */
> + args.iocb = iocb;
> + args.done = &done;
> + INIT_WORK_ONSTACK(&args.work, nfs_local_call_write);
> + queue_work(nfslocaliod_workqueue, &args.work);
> + wait_for_completion(&done);
> + destroy_work_on_stack(&args.work);
> +
> return 0;
> }
>
> --
> 2.44.0
>
>
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 11/20] nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (9 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 10/20] nfs/localio: use dedicated workqueues for filesystem read and write Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 18:28 ` Chuck Lever
2024-06-24 16:27 ` [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg Mike Snitzer
` (9 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
Eliminates duplicate functions in various files to allow for
additional callers.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 6 ------
fs/nfs/nfs4xdr.c | 13 -------------
include/linux/nfs_xdr.h | 20 +++++++++++++++++++-
3 files changed, 19 insertions(+), 20 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index ec6aaa110a7b..8b9096ad0663 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -2185,12 +2185,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
return ff_layout_encode_ds_ioerr(xdr, &ff_args->errors);
}
-static void
-encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
-{
- WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
-}
-
static void
ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr,
const nfs4_stateid *stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1416099dfcd1..ede431ee0ef0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -968,11 +968,6 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
return p;
}
-static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
-{
- WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
-}
-
static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
{
WARN_ON_ONCE(xdr_stream_encode_opaque(xdr, str, len) < 0);
@@ -4352,14 +4347,6 @@ static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access)
return 0;
}
-static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
-{
- ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
- if (unlikely(ret < 0))
- return -EIO;
- return 0;
-}
-
static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index d09b9773b20c..bb460af0ea1f 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1820,6 +1820,24 @@ struct nfs_rpc_ops {
void (*disable_swap)(struct inode *inode);
};
+/*
+ * Helper functions used by NFS client and/or server
+ */
+static inline void encode_opaque_fixed(struct xdr_stream *xdr,
+ const void *buf, size_t len)
+{
+ WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
+}
+
+static inline int decode_opaque_fixed(struct xdr_stream *xdr,
+ void *buf, size_t len)
+{
+ ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
+ if (unlikely(ret < 0))
+ return -EIO;
+ return 0;
+}
+
/*
* Function vectors etc. for the NFS client
*/
@@ -1833,4 +1851,4 @@ extern const struct rpc_version nfs_version4;
extern const struct rpc_version nfsacl_version3;
extern const struct rpc_program nfsacl_program;
-#endif
+#endif /* _LINUX_NFS_XDR_H */
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 11/20] nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h
2024-06-24 16:27 ` [PATCH v7 11/20] nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h Mike Snitzer
@ 2024-06-24 18:28 ` Chuck Lever
0 siblings, 0 replies; 40+ messages in thread
From: Chuck Lever @ 2024-06-24 18:28 UTC (permalink / raw)
To: Mike Snitzer; +Cc: linux-nfs, Jeff Layton, Trond Myklebust, NeilBrown, snitzer
On Mon, Jun 24, 2024 at 12:27:32PM -0400, Mike Snitzer wrote:
> Eliminates duplicate functions in various files to allow for
> additional callers.
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> fs/nfs/flexfilelayout/flexfilelayout.c | 6 ------
> fs/nfs/nfs4xdr.c | 13 -------------
> include/linux/nfs_xdr.h | 20 +++++++++++++++++++-
> 3 files changed, 19 insertions(+), 20 deletions(-)
Nit: The "nfsd" can be removed from the Subject line since there are
no NFSD changes in this patch.
> diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
> index ec6aaa110a7b..8b9096ad0663 100644
> --- a/fs/nfs/flexfilelayout/flexfilelayout.c
> +++ b/fs/nfs/flexfilelayout/flexfilelayout.c
> @@ -2185,12 +2185,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
> return ff_layout_encode_ds_ioerr(xdr, &ff_args->errors);
> }
>
> -static void
> -encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
> -{
> - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
> -}
> -
> static void
> ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr,
> const nfs4_stateid *stateid,
> diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
> index 1416099dfcd1..ede431ee0ef0 100644
> --- a/fs/nfs/nfs4xdr.c
> +++ b/fs/nfs/nfs4xdr.c
> @@ -968,11 +968,6 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
> return p;
> }
>
> -static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
> -{
> - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
> -}
> -
> static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
> {
> WARN_ON_ONCE(xdr_stream_encode_opaque(xdr, str, len) < 0);
> @@ -4352,14 +4347,6 @@ static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access)
> return 0;
> }
>
> -static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
> -{
> - ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
> - if (unlikely(ret < 0))
> - return -EIO;
> - return 0;
> -}
> -
> static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
> {
> return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> index d09b9773b20c..bb460af0ea1f 100644
> --- a/include/linux/nfs_xdr.h
> +++ b/include/linux/nfs_xdr.h
> @@ -1820,6 +1820,24 @@ struct nfs_rpc_ops {
> void (*disable_swap)(struct inode *inode);
> };
>
> +/*
> + * Helper functions used by NFS client and/or server
> + */
> +static inline void encode_opaque_fixed(struct xdr_stream *xdr,
> + const void *buf, size_t len)
> +{
> + WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
> +}
> +
> +static inline int decode_opaque_fixed(struct xdr_stream *xdr,
> + void *buf, size_t len)
> +{
> + ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
> + if (unlikely(ret < 0))
> + return -EIO;
> + return 0;
> +}
> +
> /*
> * Function vectors etc. for the NFS client
> */
> @@ -1833,4 +1851,4 @@ extern const struct rpc_version nfs_version4;
> extern const struct rpc_version nfsacl_version3;
> extern const struct rpc_program nfsacl_program;
>
> -#endif
> +#endif /* _LINUX_NFS_XDR_H */
> --
> 2.44.0
>
--
Chuck Lever
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (10 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 11/20] nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 23:19 ` NeilBrown
2024-06-24 16:27 ` [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM Mike Snitzer
` (8 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
This is needed for the LOCALIO protocol's GETUUID RPC which takes a
void arg. The LOCALIO protocol spec in rpcgen syntax is:
/* raw RFC 9562 UUID */
typedef u8 uuid_t<UUID_SIZE>;
program NFS_LOCALIO_PROGRAM {
version LOCALIO_V1 {
void
NULL(void) = 0;
uuid_t
GETUUID(void) = 1;
} = 1;
} = 400122;
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
net/sunrpc/clnt.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index cfd1b1bf7e35..2d7f96103f08 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1894,7 +1894,6 @@ call_allocate(struct rpc_task *task)
return;
if (proc->p_proc != 0) {
- BUG_ON(proc->p_arglen == 0);
if (proc->p_decode != NULL)
BUG_ON(proc->p_replen == 0);
}
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg
2024-06-24 16:27 ` [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg Mike Snitzer
@ 2024-06-25 23:19 ` NeilBrown
2024-06-26 16:53 ` Mike Snitzer
0 siblings, 1 reply; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:19 UTC (permalink / raw)
To: Mike Snitzer
Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Mike Snitzer wrote:
> This is needed for the LOCALIO protocol's GETUUID RPC which takes a
> void arg. The LOCALIO protocol spec in rpcgen syntax is:
>
> /* raw RFC 9562 UUID */
> typedef u8 uuid_t<UUID_SIZE>;
>
> program NFS_LOCALIO_PROGRAM {
> version LOCALIO_V1 {
> void
> NULL(void) = 0;
>
> uuid_t
> GETUUID(void) = 1;
> } = 1;
> } = 400122;
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> net/sunrpc/clnt.c | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
> index cfd1b1bf7e35..2d7f96103f08 100644
> --- a/net/sunrpc/clnt.c
> +++ b/net/sunrpc/clnt.c
> @@ -1894,7 +1894,6 @@ call_allocate(struct rpc_task *task)
> return;
>
> if (proc->p_proc != 0) {
> - BUG_ON(proc->p_arglen == 0);
> if (proc->p_decode != NULL)
> BUG_ON(proc->p_replen == 0);
> }
I would be in favour get rid of all 5 lines.
I wonder if p_decode is ever NULL. It would cause
rpcauth_unwrap_resp_decode() problems.
NeilBrown
> --
> 2.44.0
>
>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg
2024-06-25 23:19 ` NeilBrown
@ 2024-06-26 16:53 ` Mike Snitzer
0 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-26 16:53 UTC (permalink / raw)
To: NeilBrown; +Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Wed, Jun 26, 2024 at 09:19:43AM +1000, NeilBrown wrote:
> On Tue, 25 Jun 2024, Mike Snitzer wrote:
> > This is needed for the LOCALIO protocol's GETUUID RPC which takes a
> > void arg. The LOCALIO protocol spec in rpcgen syntax is:
> >
> > /* raw RFC 9562 UUID */
> > typedef u8 uuid_t<UUID_SIZE>;
> >
> > program NFS_LOCALIO_PROGRAM {
> > version LOCALIO_V1 {
> > void
> > NULL(void) = 0;
> >
> > uuid_t
> > GETUUID(void) = 1;
> > } = 1;
> > } = 400122;
> >
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > ---
> > net/sunrpc/clnt.c | 1 -
> > 1 file changed, 1 deletion(-)
> >
> > diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
> > index cfd1b1bf7e35..2d7f96103f08 100644
> > --- a/net/sunrpc/clnt.c
> > +++ b/net/sunrpc/clnt.c
> > @@ -1894,7 +1894,6 @@ call_allocate(struct rpc_task *task)
> > return;
> >
> > if (proc->p_proc != 0) {
> > - BUG_ON(proc->p_arglen == 0);
> > if (proc->p_decode != NULL)
> > BUG_ON(proc->p_replen == 0);
> > }
>
> I would be in favour get rid of all 5 lines.
> I wonder if p_decode is ever NULL. It would cause
> rpcauth_unwrap_resp_decode() problems.
OK, but that broader cleanup can happen with an incremental follow-up
patch.
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (11 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 12/20] SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC with void arg Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 23:21 ` NeilBrown
2024-06-24 16:27 ` [PATCH v7 14/20] nfsd: implement server " Mike Snitzer
` (7 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
LOCALIOPROC_GETUUID allows a client to discover the server's uuid.
nfs_local_probe() will retrieve server's uuid via LOCALIO protocol and
verify the server with that uuid it is known to be local. This ensures
client and server 1: support localio 2: are local to each other.
All the knowledge of the LOCALIO RPC protocol is in fs/nfs/localio.c
which implements just a single version (1) that is used independently
of what NFS version is used.
Get nfsd_open_local_fh and store it in rpc_client during client
creation, put the symbol during nfs_local_disable -- which is also
called during client destruction.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
[neilb: factored out and simplified single localio protocol]
Co-developed-by: NeilBrown <neilb@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
---
fs/nfs/client.c | 6 +-
fs/nfs/localio.c | 159 +++++++++++++++++++++++++++++++++++++++++---
include/linux/nfs.h | 7 ++
3 files changed, 161 insertions(+), 11 deletions(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 1300c388f971..6faa9fdc444d 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -434,8 +434,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
list_add_tail(&new->cl_share_link,
&nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
- nfs_local_probe(new);
- return rpc_ops->init_client(new, cl_init);
+ new = rpc_ops->init_client(new, cl_init);
+ if (!IS_ERR(new))
+ nfs_local_probe(new);
+ return new;
}
spin_unlock(&nn->nfs_client_lock);
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 418b8d76692b..e4f860a51170 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -15,6 +15,7 @@
#include <linux/sunrpc/addr.h>
#include <linux/inetdevice.h>
#include <net/addrconf.h>
+#include <linux/nfslocalio.h>
#include <linux/module.h>
#include <linux/bvec.h>
@@ -123,13 +124,72 @@ nfs4errno(int errno)
static bool localio_enabled __read_mostly = true;
module_param(localio_enabled, bool, 0644);
+static inline bool nfs_client_is_local(const struct nfs_client *clp)
+{
+ return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+}
+
bool nfs_server_is_local(const struct nfs_client *clp)
{
- return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 &&
- localio_enabled;
+ return nfs_client_is_local(clp) && localio_enabled;
}
EXPORT_SYMBOL_GPL(nfs_server_is_local);
+/*
+ * GETUUID XDR functions
+ */
+
+static void localio_xdr_enc_getuuidargs(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ /* void function */
+}
+
+static int localio_xdr_dec_getuuidres(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ void *result)
+{
+ u8 *uuid = result;
+
+ return decode_opaque_fixed(xdr, uuid, UUID_SIZE);
+}
+
+static const struct rpc_procinfo nfs_localio_procedures[] = {
+ [LOCALIOPROC_GETUUID] = {
+ .p_proc = LOCALIOPROC_GETUUID,
+ .p_encode = localio_xdr_enc_getuuidargs,
+ .p_decode = localio_xdr_dec_getuuidres,
+ .p_arglen = 0,
+ .p_replen = XDR_QUADLEN(UUID_SIZE),
+ .p_statidx = LOCALIOPROC_GETUUID,
+ .p_name = "GETUUID",
+ },
+};
+
+static unsigned int nfs_localio_counts[ARRAY_SIZE(nfs_localio_procedures)];
+const struct rpc_version nfslocalio_version1 = {
+ .number = 1,
+ .nrprocs = ARRAY_SIZE(nfs_localio_procedures),
+ .procs = nfs_localio_procedures,
+ .counts = nfs_localio_counts,
+};
+
+static const struct rpc_version *nfslocalio_version[] = {
+ [1] = &nfslocalio_version1,
+};
+
+extern const struct rpc_program nfslocalio_program;
+static struct rpc_stat nfslocalio_rpcstat = { &nfslocalio_program };
+
+const struct rpc_program nfslocalio_program = {
+ .name = "nfslocalio",
+ .number = NFS_LOCALIO_PROGRAM,
+ .nrvers = ARRAY_SIZE(nfslocalio_version),
+ .version = nfslocalio_version,
+ .stats = &nfslocalio_rpcstat,
+};
+
/*
* nfs_local_enable - attempt to enable local i/o for an nfs_client
*/
@@ -149,20 +209,100 @@ void nfs_local_disable(struct nfs_client *clp)
{
if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
trace_nfs_local_disable(clp);
+ put_nfsd_open_local_fh();
+ clp->nfsd_open_local_fh = NULL;
+ if (!IS_ERR(clp->cl_rpcclient_localio)) {
+ rpc_shutdown_client(clp->cl_rpcclient_localio);
+ clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
+ }
clp->cl_nfssvc_net = NULL;
}
}
/*
- * nfs_local_probe - probe local i/o support for an nfs_client
+ * nfs_init_localioclient - Initialise an NFS localio client connection
*/
-void
-nfs_local_probe(struct nfs_client *clp)
+static void nfs_init_localioclient(struct nfs_client *clp)
{
- bool enable = false;
+ if (unlikely(!IS_ERR(clp->cl_rpcclient_localio)))
+ goto out;
+ clp->cl_rpcclient_localio = rpc_bind_new_program(clp->cl_rpcclient,
+ &nfslocalio_program, 1);
+ if (IS_ERR(clp->cl_rpcclient_localio))
+ goto out;
+ /* No errors! Assume that localio is supported */
+ clp->nfsd_open_local_fh = get_nfsd_open_local_fh();
+ if (!clp->nfsd_open_local_fh) {
+ rpc_shutdown_client(clp->cl_rpcclient_localio);
+ clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
+ }
+out:
+ dprintk_rcu("%s: server (%s) %s NFS LOCALIO, nfsd_open_local_fh is %s.\n",
+ __func__, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
+ (IS_ERR(clp->cl_rpcclient_localio) ? "does not support" : "supports"),
+ (clp->nfsd_open_local_fh ? "set" : "not set"));
+}
- if (enable)
- nfs_local_enable(clp);
+static bool nfs_local_server_getuuid(struct nfs_client *clp, uuid_t *nfsd_uuid)
+{
+ u8 uuid[UUID_SIZE];
+ struct rpc_message msg = {
+ .rpc_resp = &uuid,
+ };
+ int status;
+
+ nfs_init_localioclient(clp);
+ if (IS_ERR(clp->cl_rpcclient_localio))
+ return false;
+
+ dprintk("%s: NFS issuing getuuid\n", __func__);
+ msg.rpc_proc = &nfs_localio_procedures[LOCALIOPROC_GETUUID];
+ status = rpc_call_sync(clp->cl_rpcclient_localio, &msg, 0);
+ dprintk("%s: NFS reply getuuid: status=%d uuid=%pU\n",
+ __func__, status, uuid);
+ if (status)
+ return false;
+
+ import_uuid(nfsd_uuid, uuid);
+
+ return true;
+}
+
+/*
+ * nfs_local_probe - probe local i/o support for an nfs_server and nfs_client
+ * - called after alloc_client and init_client (so cl_rpcclient exists)
+ * - this function is idempotent, it can be called for old or new clients
+ */
+void nfs_local_probe(struct nfs_client *clp)
+{
+ uuid_t uuid;
+ struct net *net = NULL;
+
+ if (!localio_enabled || clp->cl_rpcclient->cl_vers == 2)
+ goto unsupported;
+
+ if (nfs_client_is_local(clp)) {
+ /* If already enabled, disable and re-enable */
+ nfs_local_disable(clp);
+ }
+
+ /*
+ * Retrieve server's uuid via LOCALIO protocol and verify the
+ * server with that uuid is known to be local. This ensures
+ * client and server 1: support localio 2: are local to each other
+ * by verifying client's nfsd, with specified uuid, is local.
+ */
+ if (!nfs_local_server_getuuid(clp, &uuid) ||
+ !nfsd_uuid_is_local(&uuid, &net))
+ goto unsupported;
+
+ dprintk("%s: detected local server.\n", __func__);
+ nfs_local_enable(clp, net);
+ return;
+
+unsupported:
+ /* localio not supported */
+ nfs_local_disable(clp);
}
EXPORT_SYMBOL_GPL(nfs_local_probe);
@@ -189,7 +329,8 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
trace_nfs_local_open_fh(fh, mode, status);
switch (status) {
case -ENXIO:
- nfs_local_disable(clp);
+ /* Revalidate localio, will disable if unsupported */
+ nfs_local_probe(clp);
fallthrough;
case -ETIMEDOUT:
status = -EAGAIN;
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index 64ed672a0b34..036f6b0ed94d 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -15,6 +15,13 @@
#include <linux/crc32.h>
#include <uapi/linux/nfs.h>
+/* The localio program is entirely private to Linux and is
+ * NOT part of the uapi.
+ */
+#define NFS_LOCALIO_PROGRAM 400122
+#define LOCALIOPROC_NULL 0
+#define LOCALIOPROC_GETUUID 1
+
/*
* This is the kernel NFS client file handle representation
*/
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM
2024-06-24 16:27 ` [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM Mike Snitzer
@ 2024-06-25 23:21 ` NeilBrown
2024-06-26 16:45 ` Mike Snitzer
0 siblings, 1 reply; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:21 UTC (permalink / raw)
To: Mike Snitzer
Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Mike Snitzer wrote:
> LOCALIOPROC_GETUUID allows a client to discover the server's uuid.
>
> nfs_local_probe() will retrieve server's uuid via LOCALIO protocol and
> verify the server with that uuid it is known to be local. This ensures
> client and server 1: support localio 2: are local to each other.
>
> All the knowledge of the LOCALIO RPC protocol is in fs/nfs/localio.c
> which implements just a single version (1) that is used independently
> of what NFS version is used.
>
> Get nfsd_open_local_fh and store it in rpc_client during client
> creation, put the symbol during nfs_local_disable -- which is also
> called during client destruction.
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> [neilb: factored out and simplified single localio protocol]
> Co-developed-by: NeilBrown <neilb@suse.de>
> Signed-off-by: NeilBrown <neilb@suse.de>
> ---
> fs/nfs/client.c | 6 +-
> fs/nfs/localio.c | 159 +++++++++++++++++++++++++++++++++++++++++---
> include/linux/nfs.h | 7 ++
> 3 files changed, 161 insertions(+), 11 deletions(-)
>
> diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> index 1300c388f971..6faa9fdc444d 100644
> --- a/fs/nfs/client.c
> +++ b/fs/nfs/client.c
> @@ -434,8 +434,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
> list_add_tail(&new->cl_share_link,
> &nn->nfs_client_list);
> spin_unlock(&nn->nfs_client_lock);
> - nfs_local_probe(new);
> - return rpc_ops->init_client(new, cl_init);
> + new = rpc_ops->init_client(new, cl_init);
> + if (!IS_ERR(new))
> + nfs_local_probe(new);
> + return new;
I would fold this back into the earlier patch that introduced
nfs_local_probe(). It makes this patch ugly.
But I won't insist.
NeilBrown
> }
>
> spin_unlock(&nn->nfs_client_lock);
> diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
> index 418b8d76692b..e4f860a51170 100644
> --- a/fs/nfs/localio.c
> +++ b/fs/nfs/localio.c
> @@ -15,6 +15,7 @@
> #include <linux/sunrpc/addr.h>
> #include <linux/inetdevice.h>
> #include <net/addrconf.h>
> +#include <linux/nfslocalio.h>
> #include <linux/module.h>
> #include <linux/bvec.h>
>
> @@ -123,13 +124,72 @@ nfs4errno(int errno)
> static bool localio_enabled __read_mostly = true;
> module_param(localio_enabled, bool, 0644);
>
> +static inline bool nfs_client_is_local(const struct nfs_client *clp)
> +{
> + return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
> +}
> +
> bool nfs_server_is_local(const struct nfs_client *clp)
> {
> - return test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags) != 0 &&
> - localio_enabled;
> + return nfs_client_is_local(clp) && localio_enabled;
> }
> EXPORT_SYMBOL_GPL(nfs_server_is_local);
>
> +/*
> + * GETUUID XDR functions
> + */
> +
> +static void localio_xdr_enc_getuuidargs(struct rpc_rqst *req,
> + struct xdr_stream *xdr,
> + const void *data)
> +{
> + /* void function */
> +}
> +
> +static int localio_xdr_dec_getuuidres(struct rpc_rqst *req,
> + struct xdr_stream *xdr,
> + void *result)
> +{
> + u8 *uuid = result;
> +
> + return decode_opaque_fixed(xdr, uuid, UUID_SIZE);
> +}
> +
> +static const struct rpc_procinfo nfs_localio_procedures[] = {
> + [LOCALIOPROC_GETUUID] = {
> + .p_proc = LOCALIOPROC_GETUUID,
> + .p_encode = localio_xdr_enc_getuuidargs,
> + .p_decode = localio_xdr_dec_getuuidres,
> + .p_arglen = 0,
> + .p_replen = XDR_QUADLEN(UUID_SIZE),
> + .p_statidx = LOCALIOPROC_GETUUID,
> + .p_name = "GETUUID",
> + },
> +};
> +
> +static unsigned int nfs_localio_counts[ARRAY_SIZE(nfs_localio_procedures)];
> +const struct rpc_version nfslocalio_version1 = {
> + .number = 1,
> + .nrprocs = ARRAY_SIZE(nfs_localio_procedures),
> + .procs = nfs_localio_procedures,
> + .counts = nfs_localio_counts,
> +};
> +
> +static const struct rpc_version *nfslocalio_version[] = {
> + [1] = &nfslocalio_version1,
> +};
> +
> +extern const struct rpc_program nfslocalio_program;
> +static struct rpc_stat nfslocalio_rpcstat = { &nfslocalio_program };
> +
> +const struct rpc_program nfslocalio_program = {
> + .name = "nfslocalio",
> + .number = NFS_LOCALIO_PROGRAM,
> + .nrvers = ARRAY_SIZE(nfslocalio_version),
> + .version = nfslocalio_version,
> + .stats = &nfslocalio_rpcstat,
> +};
> +
> /*
> * nfs_local_enable - attempt to enable local i/o for an nfs_client
> */
> @@ -149,20 +209,100 @@ void nfs_local_disable(struct nfs_client *clp)
> {
> if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
> trace_nfs_local_disable(clp);
> + put_nfsd_open_local_fh();
> + clp->nfsd_open_local_fh = NULL;
> + if (!IS_ERR(clp->cl_rpcclient_localio)) {
> + rpc_shutdown_client(clp->cl_rpcclient_localio);
> + clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
> + }
> clp->cl_nfssvc_net = NULL;
> }
> }
>
> /*
> - * nfs_local_probe - probe local i/o support for an nfs_client
> + * nfs_init_localioclient - Initialise an NFS localio client connection
> */
> -void
> -nfs_local_probe(struct nfs_client *clp)
> +static void nfs_init_localioclient(struct nfs_client *clp)
> {
> - bool enable = false;
> + if (unlikely(!IS_ERR(clp->cl_rpcclient_localio)))
> + goto out;
> + clp->cl_rpcclient_localio = rpc_bind_new_program(clp->cl_rpcclient,
> + &nfslocalio_program, 1);
> + if (IS_ERR(clp->cl_rpcclient_localio))
> + goto out;
> + /* No errors! Assume that localio is supported */
> + clp->nfsd_open_local_fh = get_nfsd_open_local_fh();
> + if (!clp->nfsd_open_local_fh) {
> + rpc_shutdown_client(clp->cl_rpcclient_localio);
> + clp->cl_rpcclient_localio = ERR_PTR(-EINVAL);
> + }
> +out:
> + dprintk_rcu("%s: server (%s) %s NFS LOCALIO, nfsd_open_local_fh is %s.\n",
> + __func__, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
> + (IS_ERR(clp->cl_rpcclient_localio) ? "does not support" : "supports"),
> + (clp->nfsd_open_local_fh ? "set" : "not set"));
> +}
>
> - if (enable)
> - nfs_local_enable(clp);
> +static bool nfs_local_server_getuuid(struct nfs_client *clp, uuid_t *nfsd_uuid)
> +{
> + u8 uuid[UUID_SIZE];
> + struct rpc_message msg = {
> + .rpc_resp = &uuid,
> + };
> + int status;
> +
> + nfs_init_localioclient(clp);
> + if (IS_ERR(clp->cl_rpcclient_localio))
> + return false;
> +
> + dprintk("%s: NFS issuing getuuid\n", __func__);
> + msg.rpc_proc = &nfs_localio_procedures[LOCALIOPROC_GETUUID];
> + status = rpc_call_sync(clp->cl_rpcclient_localio, &msg, 0);
> + dprintk("%s: NFS reply getuuid: status=%d uuid=%pU\n",
> + __func__, status, uuid);
> + if (status)
> + return false;
> +
> + import_uuid(nfsd_uuid, uuid);
> +
> + return true;
> +}
> +
> +/*
> + * nfs_local_probe - probe local i/o support for an nfs_server and nfs_client
> + * - called after alloc_client and init_client (so cl_rpcclient exists)
> + * - this function is idempotent, it can be called for old or new clients
> + */
> +void nfs_local_probe(struct nfs_client *clp)
> +{
> + uuid_t uuid;
> + struct net *net = NULL;
> +
> + if (!localio_enabled || clp->cl_rpcclient->cl_vers == 2)
> + goto unsupported;
> +
> + if (nfs_client_is_local(clp)) {
> + /* If already enabled, disable and re-enable */
> + nfs_local_disable(clp);
> + }
> +
> + /*
> + * Retrieve server's uuid via LOCALIO protocol and verify the
> + * server with that uuid is known to be local. This ensures
> + * client and server 1: support localio 2: are local to each other
> + * by verifying client's nfsd, with specified uuid, is local.
> + */
> + if (!nfs_local_server_getuuid(clp, &uuid) ||
> + !nfsd_uuid_is_local(&uuid, &net))
> + goto unsupported;
> +
> + dprintk("%s: detected local server.\n", __func__);
> + nfs_local_enable(clp, net);
> + return;
> +
> +unsupported:
> + /* localio not supported */
> + nfs_local_disable(clp);
> }
> EXPORT_SYMBOL_GPL(nfs_local_probe);
>
> @@ -189,7 +329,8 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
> trace_nfs_local_open_fh(fh, mode, status);
> switch (status) {
> case -ENXIO:
> - nfs_local_disable(clp);
> + /* Revalidate localio, will disable if unsupported */
> + nfs_local_probe(clp);
> fallthrough;
> case -ETIMEDOUT:
> status = -EAGAIN;
> diff --git a/include/linux/nfs.h b/include/linux/nfs.h
> index 64ed672a0b34..036f6b0ed94d 100644
> --- a/include/linux/nfs.h
> +++ b/include/linux/nfs.h
> @@ -15,6 +15,13 @@
> #include <linux/crc32.h>
> #include <uapi/linux/nfs.h>
>
> +/* The localio program is entirely private to Linux and is
> + * NOT part of the uapi.
> + */
> +#define NFS_LOCALIO_PROGRAM 400122
> +#define LOCALIOPROC_NULL 0
> +#define LOCALIOPROC_GETUUID 1
> +
> /*
> * This is the kernel NFS client file handle representation
> */
> --
> 2.44.0
>
>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM
2024-06-25 23:21 ` NeilBrown
@ 2024-06-26 16:45 ` Mike Snitzer
0 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-26 16:45 UTC (permalink / raw)
To: NeilBrown; +Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Wed, Jun 26, 2024 at 09:21:00AM +1000, NeilBrown wrote:
> On Tue, 25 Jun 2024, Mike Snitzer wrote:
> > LOCALIOPROC_GETUUID allows a client to discover the server's uuid.
> >
> > nfs_local_probe() will retrieve server's uuid via LOCALIO protocol and
> > verify the server with that uuid it is known to be local. This ensures
> > client and server 1: support localio 2: are local to each other.
> >
> > All the knowledge of the LOCALIO RPC protocol is in fs/nfs/localio.c
> > which implements just a single version (1) that is used independently
> > of what NFS version is used.
> >
> > Get nfsd_open_local_fh and store it in rpc_client during client
> > creation, put the symbol during nfs_local_disable -- which is also
> > called during client destruction.
> >
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > [neilb: factored out and simplified single localio protocol]
> > Co-developed-by: NeilBrown <neilb@suse.de>
> > Signed-off-by: NeilBrown <neilb@suse.de>
> > ---
> > fs/nfs/client.c | 6 +-
> > fs/nfs/localio.c | 159 +++++++++++++++++++++++++++++++++++++++++---
> > include/linux/nfs.h | 7 ++
> > 3 files changed, 161 insertions(+), 11 deletions(-)
> >
> > diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> > index 1300c388f971..6faa9fdc444d 100644
> > --- a/fs/nfs/client.c
> > +++ b/fs/nfs/client.c
> > @@ -434,8 +434,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
> > list_add_tail(&new->cl_share_link,
> > &nn->nfs_client_list);
> > spin_unlock(&nn->nfs_client_lock);
> > - nfs_local_probe(new);
> > - return rpc_ops->init_client(new, cl_init);
> > + new = rpc_ops->init_client(new, cl_init);
> > + if (!IS_ERR(new))
> > + nfs_local_probe(new);
> > + return new;
>
> I would fold this back into the earlier patch that introduced
> nfs_local_probe(). It makes this patch ugly.
> But I won't insist.
I cleaned it up a bit so that this patch is cleaner, but I'd prefer to
leave it split out.
Thanks.
Mike
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 14/20] nfsd: implement server support for NFS_LOCALIO_PROGRAM
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (12 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 13/20] nfs: implement client support for NFS_LOCALIO_PROGRAM Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 18:45 ` Chuck Lever
2024-06-25 23:23 ` NeilBrown
2024-06-24 16:27 ` [PATCH v7 15/20] SUNRPC: replace program list with program array Mike Snitzer
` (6 subsequent siblings)
20 siblings, 2 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
LOCALIOPROC_GETUUID encodes the server's uuid_t in terms of the fixed
UUID_SIZE (16). The fixed size opaque encode and decode XDR methods
are used instead of the less efficient variable sized methods.
Aside from a bit of code in nfssvc.c, all the knowledge of the LOCALIO
RPC protocol is in fs/nfsd/localio.c which implements just a single
version (1) that is used independently of what NFS version is used.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
[neilb: factored out and simplified single localio protocol]
Co-developed-by: NeilBrown <neilb@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
---
fs/nfsd/localio.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++
fs/nfsd/nfssvc.c | 29 ++++++++++++++++++-
2 files changed, 102 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index f6df66b1d523..aaa5293eb352 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -11,12 +11,15 @@
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
#include <linux/string.h>
#include "nfsd.h"
#include "vfs.h"
#include "netns.h"
#include "filecache.h"
+#include "cache.h"
#define NFSDDBG_FACILITY NFSDDBG_FH
@@ -249,3 +252,74 @@ EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
/* Compile time type checking, not used by anything */
static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
+
+/*
+ * GETUUID XDR encode functions
+ */
+
+static __be32 nfsd_proc_null(struct svc_rqst *rqstp)
+{
+ return rpc_success;
+}
+
+struct nfsd_getuuidres {
+ uuid_t uuid;
+};
+
+static __be32 nfsd_proc_getuuid(struct svc_rqst *rqstp)
+{
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfsd_getuuidres *resp = rqstp->rq_resp;
+
+ uuid_copy(&resp->uuid, &nn->nfsd_uuid.uuid);
+
+ return rpc_success;
+}
+
+static bool nfslocalio_encode_getuuidres(struct svc_rqst *rqstp,
+ struct xdr_stream *xdr)
+{
+ struct nfsd_getuuidres *resp = rqstp->rq_resp;
+ u8 uuid[UUID_SIZE];
+
+ export_uuid(uuid, &resp->uuid);
+ encode_opaque_fixed(xdr, uuid, UUID_SIZE);
+ dprintk("%s: uuid=%pU\n", __func__, uuid);
+
+ return true;
+}
+
+static const struct svc_procedure nfsd_localio_procedures[2] = {
+ [LOCALIOPROC_NULL] = {
+ .pc_func = nfsd_proc_null,
+ .pc_decode = nfssvc_decode_voidarg,
+ .pc_encode = nfssvc_encode_voidres,
+ .pc_argsize = sizeof(struct nfsd_voidargs),
+ .pc_ressize = sizeof(struct nfsd_voidres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = 0,
+ .pc_name = "NULL",
+ },
+ [LOCALIOPROC_GETUUID] = {
+ .pc_func = nfsd_proc_getuuid,
+ .pc_decode = nfssvc_decode_voidarg,
+ .pc_encode = nfslocalio_encode_getuuidres,
+ .pc_argsize = sizeof(struct nfsd_voidargs),
+ .pc_ressize = sizeof(struct nfsd_getuuidres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_xdrressize = XDR_QUADLEN(UUID_SIZE),
+ .pc_name = "GETUUID",
+ },
+};
+
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+ nfsd_localio_count[ARRAY_SIZE(nfsd_localio_procedures)]);
+const struct svc_version nfsd_localio_version1 = {
+ .vs_vers = 1,
+ .vs_nproc = 2,
+ .vs_proc = nfsd_localio_procedures,
+ .vs_dispatch = nfsd_dispatch,
+ .vs_count = nfsd_localio_count,
+ .vs_xdrsize = XDR_QUADLEN(UUID_SIZE),
+ .vs_hidden = true,
+};
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index a477d2c5088a..bc69a2c90077 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -81,6 +81,26 @@ DEFINE_SPINLOCK(nfsd_drc_lock);
unsigned long nfsd_drc_max_mem;
unsigned long nfsd_drc_mem_used;
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+extern const struct svc_version nfsd_localio_version1;
+static const struct svc_version *nfsd_localio_version[] = {
+ [1] = &nfsd_localio_version1,
+};
+
+#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(nfsd_localio_version)
+
+static struct svc_program nfsd_localio_program = {
+ .pg_prog = NFS_LOCALIO_PROGRAM,
+ .pg_nvers = NFSD_LOCALIO_NRVERS,
+ .pg_vers = nfsd_localio_version,
+ .pg_name = "nfslocalio",
+ .pg_class = "nfsd",
+ .pg_authenticate = &svc_set_client,
+ .pg_init_request = svc_generic_init_request,
+ .pg_rpcbind_set = svc_generic_rpcbind_set,
+};
+#endif /* CONFIG_NFSD_LOCALIO */
+
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
static const struct svc_version *nfsd_acl_version[] = {
# if defined(CONFIG_NFSD_V2_ACL)
@@ -95,6 +115,9 @@ static const struct svc_version *nfsd_acl_version[] = {
#define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version)
static struct svc_program nfsd_acl_program = {
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ .pg_next = &nfsd_localio_program,
+#endif /* CONFIG_NFSD_LOCALIO */
.pg_prog = NFS_ACL_PROGRAM,
.pg_nvers = NFSD_ACL_NRVERS,
.pg_vers = nfsd_acl_version,
@@ -123,6 +146,10 @@ static const struct svc_version *nfsd_version[] = {
struct svc_program nfsd_program = {
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
.pg_next = &nfsd_acl_program,
+#else
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ .pg_next = &nfsd_localio_program,
+#endif /* CONFIG_NFSD_LOCALIO */
#endif
.pg_prog = NFS_PROGRAM, /* program number */
.pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */
@@ -975,7 +1002,7 @@ nfsd(void *vrqstp)
}
/**
- * nfsd_dispatch - Process an NFS or NFSACL Request
+ * nfsd_dispatch - Process an NFS or NFSACL or NFSLOCALIO Request
* @rqstp: incoming request
*
* This RPC dispatcher integrates the NFS server's duplicate reply cache.
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 14/20] nfsd: implement server support for NFS_LOCALIO_PROGRAM
2024-06-24 16:27 ` [PATCH v7 14/20] nfsd: implement server " Mike Snitzer
@ 2024-06-24 18:45 ` Chuck Lever
2024-06-25 23:23 ` NeilBrown
1 sibling, 0 replies; 40+ messages in thread
From: Chuck Lever @ 2024-06-24 18:45 UTC (permalink / raw)
To: Mike Snitzer; +Cc: linux-nfs, Jeff Layton, Trond Myklebust, NeilBrown, snitzer
On Mon, Jun 24, 2024 at 12:27:35PM -0400, Mike Snitzer wrote:
> LOCALIOPROC_GETUUID encodes the server's uuid_t in terms of the fixed
> UUID_SIZE (16). The fixed size opaque encode and decode XDR methods
> are used instead of the less efficient variable sized methods.
>
> Aside from a bit of code in nfssvc.c, all the knowledge of the LOCALIO
> RPC protocol is in fs/nfsd/localio.c which implements just a single
> version (1) that is used independently of what NFS version is used.
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> [neilb: factored out and simplified single localio protocol]
> Co-developed-by: NeilBrown <neilb@suse.de>
> Signed-off-by: NeilBrown <neilb@suse.de>
> ---
> fs/nfsd/localio.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++
> fs/nfsd/nfssvc.c | 29 ++++++++++++++++++-
> 2 files changed, 102 insertions(+), 1 deletion(-)
>
> diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> index f6df66b1d523..aaa5293eb352 100644
> --- a/fs/nfsd/localio.c
> +++ b/fs/nfsd/localio.c
> @@ -11,12 +11,15 @@
> #include <linux/sunrpc/svcauth_gss.h>
> #include <linux/sunrpc/clnt.h>
> #include <linux/nfs.h>
> +#include <linux/nfs_fs.h>
> +#include <linux/nfs_xdr.h>
> #include <linux/string.h>
>
> #include "nfsd.h"
> #include "vfs.h"
> #include "netns.h"
> #include "filecache.h"
> +#include "cache.h"
>
> #define NFSDDBG_FACILITY NFSDDBG_FH
>
> @@ -249,3 +252,74 @@ EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
>
> /* Compile time type checking, not used by anything */
> static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
> +
> +/*
> + * GETUUID XDR encode functions
> + */
> +
> +static __be32 nfsd_proc_null(struct svc_rqst *rqstp)
> +{
> + return rpc_success;
> +}
We already have an nfsd_proc_null() (for NFSv2). Let's use
localio_proc_null()
instead.
> +struct nfsd_getuuidres {
> + uuid_t uuid;
> +};
> +
> +static __be32 nfsd_proc_getuuid(struct svc_rqst *rqstp)
And here, please use
localio_proc_getuuid()
instead.
> +{
> + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
> + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> +
> + uuid_copy(&resp->uuid, &nn->nfsd_uuid.uuid);
> +
> + return rpc_success;
> +}
> +
> +static bool nfslocalio_encode_getuuidres(struct svc_rqst *rqstp,
> + struct xdr_stream *xdr)
Please use
localio_encode_getuuidres()
instead.
> +{
> + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> + u8 uuid[UUID_SIZE];
> +
> + export_uuid(uuid, &resp->uuid);
> + encode_opaque_fixed(xdr, uuid, UUID_SIZE);
> + dprintk("%s: uuid=%pU\n", __func__, uuid);
> +
> + return true;
> +}
> +
> +static const struct svc_procedure nfsd_localio_procedures[2] = {
I think I prefer:
localio_procedures1
> + [LOCALIOPROC_NULL] = {
> + .pc_func = nfsd_proc_null,
> + .pc_decode = nfssvc_decode_voidarg,
> + .pc_encode = nfssvc_encode_voidres,
> + .pc_argsize = sizeof(struct nfsd_voidargs),
> + .pc_ressize = sizeof(struct nfsd_voidres),
> + .pc_cachetype = RC_NOCACHE,
> + .pc_xdrressize = 0,
> + .pc_name = "NULL",
> + },
> + [LOCALIOPROC_GETUUID] = {
> + .pc_func = nfsd_proc_getuuid,
> + .pc_decode = nfssvc_decode_voidarg,
> + .pc_encode = nfslocalio_encode_getuuidres,
> + .pc_argsize = sizeof(struct nfsd_voidargs),
> + .pc_ressize = sizeof(struct nfsd_getuuidres),
> + .pc_cachetype = RC_NOCACHE,
> + .pc_xdrressize = XDR_QUADLEN(UUID_SIZE),
> + .pc_name = "GETUUID",
> + },
> +};
> +
> +static DEFINE_PER_CPU_ALIGNED(unsigned long,
> + nfsd_localio_count[ARRAY_SIZE(nfsd_localio_procedures)]);
> +const struct svc_version nfsd_localio_version1 = {
I'd prefer:
localiosvc_version1
> + .vs_vers = 1,
> + .vs_nproc = 2,
> + .vs_proc = nfsd_localio_procedures,
> + .vs_dispatch = nfsd_dispatch,
> + .vs_count = nfsd_localio_count,
> + .vs_xdrsize = XDR_QUADLEN(UUID_SIZE),
> + .vs_hidden = true,
> +};
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index a477d2c5088a..bc69a2c90077 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -81,6 +81,26 @@ DEFINE_SPINLOCK(nfsd_drc_lock);
> unsigned long nfsd_drc_max_mem;
> unsigned long nfsd_drc_mem_used;
>
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> +extern const struct svc_version nfsd_localio_version1;
> +static const struct svc_version *nfsd_localio_version[] = {
Instead:
localio_versions[]
> + [1] = &nfsd_localio_version1,
> +};
> +
> +#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(nfsd_localio_version)
> +
> +static struct svc_program nfsd_localio_program = {
> + .pg_prog = NFS_LOCALIO_PROGRAM,
> + .pg_nvers = NFSD_LOCALIO_NRVERS,
> + .pg_vers = nfsd_localio_version,
> + .pg_name = "nfslocalio",
> + .pg_class = "nfsd",
> + .pg_authenticate = &svc_set_client,
> + .pg_init_request = svc_generic_init_request,
> + .pg_rpcbind_set = svc_generic_rpcbind_set,
> +};
> +#endif /* CONFIG_NFSD_LOCALIO */
> +
> #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
> static const struct svc_version *nfsd_acl_version[] = {
> # if defined(CONFIG_NFSD_V2_ACL)
> @@ -95,6 +115,9 @@ static const struct svc_version *nfsd_acl_version[] = {
> #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version)
>
> static struct svc_program nfsd_acl_program = {
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + .pg_next = &nfsd_localio_program,
> +#endif /* CONFIG_NFSD_LOCALIO */
> .pg_prog = NFS_ACL_PROGRAM,
> .pg_nvers = NFSD_ACL_NRVERS,
> .pg_vers = nfsd_acl_version,
> @@ -123,6 +146,10 @@ static const struct svc_version *nfsd_version[] = {
> struct svc_program nfsd_program = {
> #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
> .pg_next = &nfsd_acl_program,
> +#else
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + .pg_next = &nfsd_localio_program,
> +#endif /* CONFIG_NFSD_LOCALIO */
> #endif
> .pg_prog = NFS_PROGRAM, /* program number */
> .pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */
> @@ -975,7 +1002,7 @@ nfsd(void *vrqstp)
> }
>
> /**
> - * nfsd_dispatch - Process an NFS or NFSACL Request
> + * nfsd_dispatch - Process an NFS or NFSACL or NFSLOCALIO Request
Nit: "nfsd_dispatch - Process an NFS, NFSACL, or LOCALIO request"
> * @rqstp: incoming request
> *
> * This RPC dispatcher integrates the NFS server's duplicate reply cache.
> --
> 2.44.0
>
--
Chuck Lever
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 14/20] nfsd: implement server support for NFS_LOCALIO_PROGRAM
2024-06-24 16:27 ` [PATCH v7 14/20] nfsd: implement server " Mike Snitzer
2024-06-24 18:45 ` Chuck Lever
@ 2024-06-25 23:23 ` NeilBrown
2024-06-26 16:27 ` Mike Snitzer
1 sibling, 1 reply; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:23 UTC (permalink / raw)
To: Mike Snitzer
Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Mike Snitzer wrote:
> LOCALIOPROC_GETUUID encodes the server's uuid_t in terms of the fixed
> UUID_SIZE (16). The fixed size opaque encode and decode XDR methods
> are used instead of the less efficient variable sized methods.
>
> Aside from a bit of code in nfssvc.c, all the knowledge of the LOCALIO
> RPC protocol is in fs/nfsd/localio.c which implements just a single
> version (1) that is used independently of what NFS version is used.
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> [neilb: factored out and simplified single localio protocol]
> Co-developed-by: NeilBrown <neilb@suse.de>
> Signed-off-by: NeilBrown <neilb@suse.de>
> ---
> fs/nfsd/localio.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++
> fs/nfsd/nfssvc.c | 29 ++++++++++++++++++-
> 2 files changed, 102 insertions(+), 1 deletion(-)
>
> diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> index f6df66b1d523..aaa5293eb352 100644
> --- a/fs/nfsd/localio.c
> +++ b/fs/nfsd/localio.c
> @@ -11,12 +11,15 @@
> #include <linux/sunrpc/svcauth_gss.h>
> #include <linux/sunrpc/clnt.h>
> #include <linux/nfs.h>
> +#include <linux/nfs_fs.h>
> +#include <linux/nfs_xdr.h>
> #include <linux/string.h>
>
> #include "nfsd.h"
> #include "vfs.h"
> #include "netns.h"
> #include "filecache.h"
> +#include "cache.h"
>
> #define NFSDDBG_FACILITY NFSDDBG_FH
>
> @@ -249,3 +252,74 @@ EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
>
> /* Compile time type checking, not used by anything */
> static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
> +
> +/*
> + * GETUUID XDR encode functions
> + */
> +
> +static __be32 nfsd_proc_null(struct svc_rqst *rqstp)
> +{
> + return rpc_success;
> +}
> +
> +struct nfsd_getuuidres {
> + uuid_t uuid;
> +};
> +
> +static __be32 nfsd_proc_getuuid(struct svc_rqst *rqstp)
> +{
> + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
> + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> +
> + uuid_copy(&resp->uuid, &nn->nfsd_uuid.uuid);
> +
> + return rpc_success;
> +}
> +
> +static bool nfslocalio_encode_getuuidres(struct svc_rqst *rqstp,
> + struct xdr_stream *xdr)
> +{
> + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> + u8 uuid[UUID_SIZE];
> +
> + export_uuid(uuid, &resp->uuid);
> + encode_opaque_fixed(xdr, uuid, UUID_SIZE);
> + dprintk("%s: uuid=%pU\n", __func__, uuid);
> +
> + return true;
> +}
> +
> +static const struct svc_procedure nfsd_localio_procedures[2] = {
Including a '2' here is unnecessary.
> + [LOCALIOPROC_NULL] = {
> + .pc_func = nfsd_proc_null,
> + .pc_decode = nfssvc_decode_voidarg,
> + .pc_encode = nfssvc_encode_voidres,
> + .pc_argsize = sizeof(struct nfsd_voidargs),
> + .pc_ressize = sizeof(struct nfsd_voidres),
> + .pc_cachetype = RC_NOCACHE,
> + .pc_xdrressize = 0,
> + .pc_name = "NULL",
> + },
> + [LOCALIOPROC_GETUUID] = {
> + .pc_func = nfsd_proc_getuuid,
> + .pc_decode = nfssvc_decode_voidarg,
> + .pc_encode = nfslocalio_encode_getuuidres,
> + .pc_argsize = sizeof(struct nfsd_voidargs),
> + .pc_ressize = sizeof(struct nfsd_getuuidres),
> + .pc_cachetype = RC_NOCACHE,
> + .pc_xdrressize = XDR_QUADLEN(UUID_SIZE),
> + .pc_name = "GETUUID",
> + },
> +};
> +
> +static DEFINE_PER_CPU_ALIGNED(unsigned long,
> + nfsd_localio_count[ARRAY_SIZE(nfsd_localio_procedures)]);
We have ARRAY_SIZE above and "= 2" below, both referring to the same
value.
Maybe #define LOCALIO_NR_PROCEEDURES ARRAY_SIZE(nfsd_localio_procedures)
??
NeilBrown
> +const struct svc_version nfsd_localio_version1 = {
> + .vs_vers = 1,
> + .vs_nproc = 2,
> + .vs_proc = nfsd_localio_procedures,
> + .vs_dispatch = nfsd_dispatch,
> + .vs_count = nfsd_localio_count,
> + .vs_xdrsize = XDR_QUADLEN(UUID_SIZE),
> + .vs_hidden = true,
> +};
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index a477d2c5088a..bc69a2c90077 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -81,6 +81,26 @@ DEFINE_SPINLOCK(nfsd_drc_lock);
> unsigned long nfsd_drc_max_mem;
> unsigned long nfsd_drc_mem_used;
>
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> +extern const struct svc_version nfsd_localio_version1;
> +static const struct svc_version *nfsd_localio_version[] = {
> + [1] = &nfsd_localio_version1,
> +};
> +
> +#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(nfsd_localio_version)
> +
> +static struct svc_program nfsd_localio_program = {
> + .pg_prog = NFS_LOCALIO_PROGRAM,
> + .pg_nvers = NFSD_LOCALIO_NRVERS,
> + .pg_vers = nfsd_localio_version,
> + .pg_name = "nfslocalio",
> + .pg_class = "nfsd",
> + .pg_authenticate = &svc_set_client,
> + .pg_init_request = svc_generic_init_request,
> + .pg_rpcbind_set = svc_generic_rpcbind_set,
> +};
> +#endif /* CONFIG_NFSD_LOCALIO */
> +
> #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
> static const struct svc_version *nfsd_acl_version[] = {
> # if defined(CONFIG_NFSD_V2_ACL)
> @@ -95,6 +115,9 @@ static const struct svc_version *nfsd_acl_version[] = {
> #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version)
>
> static struct svc_program nfsd_acl_program = {
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + .pg_next = &nfsd_localio_program,
> +#endif /* CONFIG_NFSD_LOCALIO */
> .pg_prog = NFS_ACL_PROGRAM,
> .pg_nvers = NFSD_ACL_NRVERS,
> .pg_vers = nfsd_acl_version,
> @@ -123,6 +146,10 @@ static const struct svc_version *nfsd_version[] = {
> struct svc_program nfsd_program = {
> #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
> .pg_next = &nfsd_acl_program,
> +#else
> +#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> + .pg_next = &nfsd_localio_program,
> +#endif /* CONFIG_NFSD_LOCALIO */
> #endif
> .pg_prog = NFS_PROGRAM, /* program number */
> .pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */
> @@ -975,7 +1002,7 @@ nfsd(void *vrqstp)
> }
>
> /**
> - * nfsd_dispatch - Process an NFS or NFSACL Request
> + * nfsd_dispatch - Process an NFS or NFSACL or NFSLOCALIO Request
> * @rqstp: incoming request
> *
> * This RPC dispatcher integrates the NFS server's duplicate reply cache.
> --
> 2.44.0
>
>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 14/20] nfsd: implement server support for NFS_LOCALIO_PROGRAM
2024-06-25 23:23 ` NeilBrown
@ 2024-06-26 16:27 ` Mike Snitzer
0 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-26 16:27 UTC (permalink / raw)
To: NeilBrown; +Cc: linux-nfs, Jeff Layton, Chuck Lever, Trond Myklebust, snitzer
On Wed, Jun 26, 2024 at 09:23:30AM +1000, NeilBrown wrote:
> On Tue, 25 Jun 2024, Mike Snitzer wrote:
> > LOCALIOPROC_GETUUID encodes the server's uuid_t in terms of the fixed
> > UUID_SIZE (16). The fixed size opaque encode and decode XDR methods
> > are used instead of the less efficient variable sized methods.
> >
> > Aside from a bit of code in nfssvc.c, all the knowledge of the LOCALIO
> > RPC protocol is in fs/nfsd/localio.c which implements just a single
> > version (1) that is used independently of what NFS version is used.
> >
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > [neilb: factored out and simplified single localio protocol]
> > Co-developed-by: NeilBrown <neilb@suse.de>
> > Signed-off-by: NeilBrown <neilb@suse.de>
> > ---
> > fs/nfsd/localio.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++
> > fs/nfsd/nfssvc.c | 29 ++++++++++++++++++-
> > 2 files changed, 102 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
> > index f6df66b1d523..aaa5293eb352 100644
> > --- a/fs/nfsd/localio.c
> > +++ b/fs/nfsd/localio.c
> > @@ -11,12 +11,15 @@
> > #include <linux/sunrpc/svcauth_gss.h>
> > #include <linux/sunrpc/clnt.h>
> > #include <linux/nfs.h>
> > +#include <linux/nfs_fs.h>
> > +#include <linux/nfs_xdr.h>
> > #include <linux/string.h>
> >
> > #include "nfsd.h"
> > #include "vfs.h"
> > #include "netns.h"
> > #include "filecache.h"
> > +#include "cache.h"
> >
> > #define NFSDDBG_FACILITY NFSDDBG_FH
> >
> > @@ -249,3 +252,74 @@ EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
> >
> > /* Compile time type checking, not used by anything */
> > static nfs_to_nfsd_open_t __maybe_unused nfsd_open_local_fh_typecheck = nfsd_open_local_fh;
> > +
> > +/*
> > + * GETUUID XDR encode functions
> > + */
> > +
> > +static __be32 nfsd_proc_null(struct svc_rqst *rqstp)
> > +{
> > + return rpc_success;
> > +}
> > +
> > +struct nfsd_getuuidres {
> > + uuid_t uuid;
> > +};
> > +
> > +static __be32 nfsd_proc_getuuid(struct svc_rqst *rqstp)
> > +{
> > + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
> > + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> > +
> > + uuid_copy(&resp->uuid, &nn->nfsd_uuid.uuid);
> > +
> > + return rpc_success;
> > +}
> > +
> > +static bool nfslocalio_encode_getuuidres(struct svc_rqst *rqstp,
> > + struct xdr_stream *xdr)
> > +{
> > + struct nfsd_getuuidres *resp = rqstp->rq_resp;
> > + u8 uuid[UUID_SIZE];
> > +
> > + export_uuid(uuid, &resp->uuid);
> > + encode_opaque_fixed(xdr, uuid, UUID_SIZE);
> > + dprintk("%s: uuid=%pU\n", __func__, uuid);
> > +
> > + return true;
> > +}
> > +
> > +static const struct svc_procedure nfsd_localio_procedures[2] = {
>
> Including a '2' here is unnecessary.
>
> > + [LOCALIOPROC_NULL] = {
> > + .pc_func = nfsd_proc_null,
> > + .pc_decode = nfssvc_decode_voidarg,
> > + .pc_encode = nfssvc_encode_voidres,
> > + .pc_argsize = sizeof(struct nfsd_voidargs),
> > + .pc_ressize = sizeof(struct nfsd_voidres),
> > + .pc_cachetype = RC_NOCACHE,
> > + .pc_xdrressize = 0,
> > + .pc_name = "NULL",
> > + },
> > + [LOCALIOPROC_GETUUID] = {
> > + .pc_func = nfsd_proc_getuuid,
> > + .pc_decode = nfssvc_decode_voidarg,
> > + .pc_encode = nfslocalio_encode_getuuidres,
> > + .pc_argsize = sizeof(struct nfsd_voidargs),
> > + .pc_ressize = sizeof(struct nfsd_getuuidres),
> > + .pc_cachetype = RC_NOCACHE,
> > + .pc_xdrressize = XDR_QUADLEN(UUID_SIZE),
> > + .pc_name = "GETUUID",
> > + },
> > +};
> > +
> > +static DEFINE_PER_CPU_ALIGNED(unsigned long,
> > + nfsd_localio_count[ARRAY_SIZE(nfsd_localio_procedures)]);
>
> We have ARRAY_SIZE above and "= 2" below, both referring to the same
> value.
>
> Maybe #define LOCALIO_NR_PROCEEDURES ARRAY_SIZE(nfsd_localio_procedures)
> ??
Yeap, sounds good, fixed for v8.
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 15/20] SUNRPC: replace program list with program array
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (13 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 14/20] nfsd: implement server " Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 16/20] nfsd: prepare to use SRCU to dereference nn->nfsd_serv Mike Snitzer
` (5 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
From: NeilBrown <neil@brown.name>
A service created with svc_create_pooled() can be given a linked list of
programs and all of these will be served.
Using a linked list makes it cumbersome when there are several programs
that can be optionally selected with CONFIG settings.
So change to use an array with explicit size. svc_create() is always
passed a single program. svc_create_pooled() now must be used for
multiple programs.
Signed-off-by: NeilBrown <neil@brown.name>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfsd/nfsctl.c | 2 +-
fs/nfsd/nfsd.h | 2 +-
fs/nfsd/nfssvc.c | 69 ++++++++++++++++++--------------------
include/linux/sunrpc/svc.h | 7 ++--
net/sunrpc/svc.c | 68 +++++++++++++++++++++----------------
net/sunrpc/svc_xprt.c | 2 +-
net/sunrpc/svcauth_unix.c | 3 +-
7 files changed, 80 insertions(+), 73 deletions(-)
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index e5d2cc74ef77..6fb92bb61c6d 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2265,7 +2265,7 @@ static __net_init int nfsd_net_init(struct net *net)
if (retval)
goto out_repcache_error;
memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats));
- nn->nfsd_svcstats.program = &nfsd_program;
+ nn->nfsd_svcstats.program = &nfsd_programs[0];
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
nfsd4_init_leases_net(nn);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index cec8697b1cd6..c3f7c5957950 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -80,7 +80,7 @@ struct nfsd_genl_rqstp {
u32 rq_opnum[NFSD_MAX_OPS_PER_COMPOUND];
};
-extern struct svc_program nfsd_program;
+extern struct svc_program nfsd_programs[];
extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4;
extern struct mutex nfsd_mutex;
extern spinlock_t nfsd_drc_lock;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index bc69a2c90077..1df9e18c510b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -36,7 +36,6 @@
#define NFSDDBG_FACILITY NFSDDBG_SVC
atomic_t nfsd_th_cnt = ATOMIC_INIT(0);
-extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
static int nfsd_acl_rpcbind_set(struct net *,
@@ -89,16 +88,6 @@ static const struct svc_version *nfsd_localio_version[] = {
#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(nfsd_localio_version)
-static struct svc_program nfsd_localio_program = {
- .pg_prog = NFS_LOCALIO_PROGRAM,
- .pg_nvers = NFSD_LOCALIO_NRVERS,
- .pg_vers = nfsd_localio_version,
- .pg_name = "nfslocalio",
- .pg_class = "nfsd",
- .pg_authenticate = &svc_set_client,
- .pg_init_request = svc_generic_init_request,
- .pg_rpcbind_set = svc_generic_rpcbind_set,
-};
#endif /* CONFIG_NFSD_LOCALIO */
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
@@ -111,23 +100,9 @@ static const struct svc_version *nfsd_acl_version[] = {
# endif
};
-#define NFSD_ACL_MINVERS 2
+#define NFSD_ACL_MINVERS 2
#define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version)
-static struct svc_program nfsd_acl_program = {
-#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
- .pg_next = &nfsd_localio_program,
-#endif /* CONFIG_NFSD_LOCALIO */
- .pg_prog = NFS_ACL_PROGRAM,
- .pg_nvers = NFSD_ACL_NRVERS,
- .pg_vers = nfsd_acl_version,
- .pg_name = "nfsacl",
- .pg_class = "nfsd",
- .pg_authenticate = &svc_set_client,
- .pg_init_request = nfsd_acl_init_request,
- .pg_rpcbind_set = nfsd_acl_rpcbind_set,
-};
-
#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
static const struct svc_version *nfsd_version[] = {
@@ -140,25 +115,44 @@ static const struct svc_version *nfsd_version[] = {
#endif
};
-#define NFSD_MINVERS 2
+#define NFSD_MINVERS 2
#define NFSD_NRVERS ARRAY_SIZE(nfsd_version)
-struct svc_program nfsd_program = {
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
- .pg_next = &nfsd_acl_program,
-#else
-#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
- .pg_next = &nfsd_localio_program,
-#endif /* CONFIG_NFSD_LOCALIO */
-#endif
+struct svc_program nfsd_programs[] = {
+ {
.pg_prog = NFS_PROGRAM, /* program number */
.pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */
.pg_vers = nfsd_version, /* version table */
.pg_name = "nfsd", /* program name */
.pg_class = "nfsd", /* authentication class */
- .pg_authenticate = &svc_set_client, /* export authentication */
+ .pg_authenticate = svc_set_client, /* export authentication */
.pg_init_request = nfsd_init_request,
.pg_rpcbind_set = nfsd_rpcbind_set,
+ },
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+ {
+ .pg_prog = NFS_ACL_PROGRAM,
+ .pg_nvers = NFSD_ACL_NRVERS,
+ .pg_vers = nfsd_acl_version,
+ .pg_name = "nfsacl",
+ .pg_class = "nfsd",
+ .pg_authenticate = svc_set_client,
+ .pg_init_request = nfsd_acl_init_request,
+ .pg_rpcbind_set = nfsd_acl_rpcbind_set,
+ },
+#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
+#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
+ {
+ .pg_prog = NFS_LOCALIO_PROGRAM,
+ .pg_nvers = NFSD_LOCALIO_NRVERS,
+ .pg_vers = nfsd_localio_version,
+ .pg_name = "nfslocalio",
+ .pg_class = "nfsd",
+ .pg_authenticate = svc_set_client,
+ .pg_init_request = svc_generic_init_request,
+ .pg_rpcbind_set = svc_generic_rpcbind_set,
+ }
+#endif /* IS_ENABLED(CONFIG_NFSD_LOCALIO) */
};
bool nfsd_support_version(int vers)
@@ -696,7 +690,8 @@ int nfsd_create_serv(struct net *net)
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions(nn);
- serv = svc_create_pooled(&nfsd_program, &nn->nfsd_svcstats,
+ serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs),
+ &nn->nfsd_svcstats,
nfsd_max_blksize, nfsd);
if (serv == NULL)
return -ENOMEM;
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index a7d0406b9ef5..7c86b1696398 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -66,9 +66,10 @@ enum {
* We currently do not support more than one RPC program per daemon.
*/
struct svc_serv {
- struct svc_program * sv_program; /* RPC program */
+ struct svc_program * sv_programs; /* RPC programs */
struct svc_stat * sv_stats; /* RPC statistics */
spinlock_t sv_lock;
+ unsigned int sv_nprogs; /* Number of sv_programs */
unsigned int sv_nrthreads; /* # of server threads */
unsigned int sv_maxconn; /* max connections allowed or
* '0' causing max to be based
@@ -329,10 +330,9 @@ struct svc_process_info {
};
/*
- * List of RPC programs on the same transport endpoint
+ * RPC program - an array of these can use the same transport endpoint
*/
struct svc_program {
- struct svc_program * pg_next; /* other programs (same xprt) */
u32 pg_prog; /* program number */
unsigned int pg_lovers; /* lowest version */
unsigned int pg_hivers; /* highest version */
@@ -414,6 +414,7 @@ void svc_rqst_release_pages(struct svc_rqst *rqstp);
void svc_rqst_free(struct svc_rqst *);
void svc_exit_thread(struct svc_rqst *);
struct svc_serv * svc_create_pooled(struct svc_program *prog,
+ unsigned int nprog,
struct svc_stat *stats,
unsigned int bufsize,
int (*threadfn)(void *data));
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 965a27806bfd..d9f348aa0672 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -440,10 +440,11 @@ EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
static int svc_uses_rpcbind(struct svc_serv *serv)
{
- struct svc_program *progp;
- unsigned int i;
+ unsigned int p, i;
+
+ for (p = 0; p < serv->sv_nprogs; p++) {
+ struct svc_program *progp = &serv->sv_programs[p];
- for (progp = serv->sv_program; progp; progp = progp->pg_next) {
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
@@ -480,7 +481,7 @@ __svc_init_bc(struct svc_serv *serv)
* Create an RPC service
*/
static struct svc_serv *
-__svc_create(struct svc_program *prog, struct svc_stat *stats,
+__svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats,
unsigned int bufsize, int npools, int (*threadfn)(void *data))
{
struct svc_serv *serv;
@@ -491,7 +492,8 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats,
if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
return NULL;
serv->sv_name = prog->pg_name;
- serv->sv_program = prog;
+ serv->sv_programs = prog;
+ serv->sv_nprogs = nprogs;
serv->sv_stats = stats;
if (bufsize > RPCSVC_MAXPAYLOAD)
bufsize = RPCSVC_MAXPAYLOAD;
@@ -499,17 +501,18 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats,
serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE);
serv->sv_threadfn = threadfn;
xdrsize = 0;
- while (prog) {
- prog->pg_lovers = prog->pg_nvers-1;
- for (vers=0; vers<prog->pg_nvers ; vers++)
- if (prog->pg_vers[vers]) {
- prog->pg_hivers = vers;
- if (prog->pg_lovers > vers)
- prog->pg_lovers = vers;
- if (prog->pg_vers[vers]->vs_xdrsize > xdrsize)
- xdrsize = prog->pg_vers[vers]->vs_xdrsize;
+ for (i = 0; i < nprogs; i++) {
+ struct svc_program *progp = &prog[i];
+
+ progp->pg_lovers = progp->pg_nvers-1;
+ for (vers = 0; vers < progp->pg_nvers ; vers++)
+ if (progp->pg_vers[vers]) {
+ progp->pg_hivers = vers;
+ if (progp->pg_lovers > vers)
+ progp->pg_lovers = vers;
+ if (progp->pg_vers[vers]->vs_xdrsize > xdrsize)
+ xdrsize = progp->pg_vers[vers]->vs_xdrsize;
}
- prog = prog->pg_next;
}
serv->sv_xdrsize = xdrsize;
INIT_LIST_HEAD(&serv->sv_tempsocks);
@@ -558,13 +561,14 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats,
struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize,
int (*threadfn)(void *data))
{
- return __svc_create(prog, NULL, bufsize, 1, threadfn);
+ return __svc_create(prog, 1, NULL, bufsize, 1, threadfn);
}
EXPORT_SYMBOL_GPL(svc_create);
/**
* svc_create_pooled - Create an RPC service with pooled threads
- * @prog: the RPC program the new service will handle
+ * @prog: Array of RPC programs the new service will handle
+ * @nprogs: Number of programs in the array
* @stats: the stats struct if desired
* @bufsize: maximum message size for @prog
* @threadfn: a function to service RPC requests for @prog
@@ -572,6 +576,7 @@ EXPORT_SYMBOL_GPL(svc_create);
* Returns an instantiated struct svc_serv object or NULL.
*/
struct svc_serv *svc_create_pooled(struct svc_program *prog,
+ unsigned int nprogs,
struct svc_stat *stats,
unsigned int bufsize,
int (*threadfn)(void *data))
@@ -579,7 +584,7 @@ struct svc_serv *svc_create_pooled(struct svc_program *prog,
struct svc_serv *serv;
unsigned int npools = svc_pool_map_get();
- serv = __svc_create(prog, stats, bufsize, npools, threadfn);
+ serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn);
if (!serv)
goto out_err;
serv->sv_is_pooled = true;
@@ -602,16 +607,16 @@ svc_destroy(struct svc_serv **servp)
*servp = NULL;
- dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name);
+ dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name);
timer_shutdown_sync(&serv->sv_temptimer);
/*
* Remaining transports at this point are not expected.
*/
WARN_ONCE(!list_empty(&serv->sv_permsocks),
- "SVC: permsocks remain for %s\n", serv->sv_program->pg_name);
+ "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name);
WARN_ONCE(!list_empty(&serv->sv_tempsocks),
- "SVC: tempsocks remain for %s\n", serv->sv_program->pg_name);
+ "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name);
cache_clean_deferred(serv);
@@ -1156,15 +1161,16 @@ int svc_register(const struct svc_serv *serv, struct net *net,
const int family, const unsigned short proto,
const unsigned short port)
{
- struct svc_program *progp;
- unsigned int i;
+ unsigned int p, i;
int error = 0;
WARN_ON_ONCE(proto == 0 && port == 0);
if (proto == 0 && port == 0)
return -EINVAL;
- for (progp = serv->sv_program; progp; progp = progp->pg_next) {
+ for (p = 0; p < serv->sv_nprogs; p++) {
+ struct svc_program *progp = &serv->sv_programs[p];
+
for (i = 0; i < progp->pg_nvers; i++) {
error = progp->pg_rpcbind_set(net, progp, i,
@@ -1216,13 +1222,14 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi
static void svc_unregister(const struct svc_serv *serv, struct net *net)
{
struct sighand_struct *sighand;
- struct svc_program *progp;
unsigned long flags;
- unsigned int i;
+ unsigned int p, i;
clear_thread_flag(TIF_SIGPENDING);
- for (progp = serv->sv_program; progp; progp = progp->pg_next) {
+ for (p = 0; p < serv->sv_nprogs; p++) {
+ struct svc_program *progp = &serv->sv_programs[p];
+
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
@@ -1328,7 +1335,7 @@ svc_process_common(struct svc_rqst *rqstp)
struct svc_process_info process;
enum svc_auth_status auth_res;
unsigned int aoffset;
- int rc;
+ int pr, rc;
__be32 *p;
/* Will be turned off only when NFSv4 Sessions are used */
@@ -1352,9 +1359,12 @@ svc_process_common(struct svc_rqst *rqstp)
rqstp->rq_vers = be32_to_cpup(p++);
rqstp->rq_proc = be32_to_cpup(p);
- for (progp = serv->sv_program; progp; progp = progp->pg_next)
+ for (pr = 0; pr < serv->sv_nprogs; pr++) {
+ progp = &serv->sv_programs[pr];
+
if (rqstp->rq_prog == progp->pg_prog)
break;
+ }
/*
* Decode auth data, and add verifier to reply buffer.
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index d3735ab3e6d1..16634afdf253 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -268,7 +268,7 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
spin_unlock(&svc_xprt_class_lock);
newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
if (IS_ERR(newxprt)) {
- trace_svc_xprt_create_err(serv->sv_program->pg_name,
+ trace_svc_xprt_create_err(serv->sv_programs->pg_name,
xcl->xcl_name, sap, len,
newxprt);
module_put(xcl->xcl_owner);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 04b45588ae6f..8ca98b146ec8 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -697,7 +697,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
rqstp->rq_auth_stat = rpc_autherr_badcred;
ipm = ip_map_cached_get(xprt);
if (ipm == NULL)
- ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class,
+ ipm = __ip_map_lookup(sn->ip_map_cache,
+ rqstp->rq_server->sv_programs->pg_class,
&sin6->sin6_addr);
if (ipm == NULL)
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 16/20] nfsd: prepare to use SRCU to dereference nn->nfsd_serv
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (14 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 15/20] SUNRPC: replace program list with program array Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 17/20] nfsd: " Mike Snitzer
` (4 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
The next commit switches the nfsd_serv member for struct nfsd_net over
to a void pointer (void __rcu *). Prepare for this by assigning
nn->nfsd_serv to an struct svc_serv pointer that is then happily
dereferenced. This eliminates what would otherwise be numerous void
pointer dereferences after the next commit.
All nfsd code what audited so that methods that hold nfsd_mutex will
continue to directly dereference nn->nfsd_serv.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfsd/nfsctl.c | 21 +++++++++++++--------
fs/nfsd/nfssvc.c | 34 ++++++++++++++++++----------------
2 files changed, 31 insertions(+), 24 deletions(-)
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 6fb92bb61c6d..075ada559e18 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -687,10 +687,11 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size)
static ssize_t __write_ports_names(char *buf, struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv = nn->nfsd_serv;
- if (nn->nfsd_serv == NULL)
+ if (serv == NULL)
return 0;
- return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
+ return svc_xprt_names(serv, buf, SIMPLE_TRANSACTION_LIMIT);
}
/*
@@ -717,7 +718,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
serv = nn->nfsd_serv;
err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
- if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ if (!serv->sv_nrthreads && list_empty(&serv->sv_permsocks))
nfsd_destroy_serv(net);
return err;
@@ -765,7 +766,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
svc_xprt_put(xprt);
}
out_err:
- if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ if (!serv->sv_nrthreads && list_empty(&serv->sv_permsocks))
nfsd_destroy_serv(net);
return err;
@@ -1674,6 +1675,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
int *nthreads, count = 0, nrpools, i, ret = -EOPNOTSUPP, rem;
struct net *net = genl_info_net(info);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
const struct nlattr *attr;
const char *scope = NULL;
@@ -1708,7 +1710,8 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
info->attrs[NFSD_A_SERVER_LEASETIME] ||
info->attrs[NFSD_A_SERVER_SCOPE]) {
ret = -EBUSY;
- if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads)
+ serv = nn->nfsd_serv;
+ if (serv && serv->sv_nrthreads)
goto out_unlock;
ret = -EINVAL;
@@ -1757,6 +1760,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
void *hdr;
int err;
@@ -1781,11 +1785,12 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
if (err)
goto err_unlock;
- if (nn->nfsd_serv) {
+ serv = nn->nfsd_serv;
+ if (serv) {
int i;
for (i = 0; i < nfsd_nrpools(net); ++i) {
- struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
+ struct svc_pool *sp = &serv->sv_pools[i];
err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
atomic_read(&sp->sp_nrthreads));
@@ -2103,7 +2108,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
err = ret;
}
- if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ if (!serv->sv_nrthreads && list_empty(&serv->sv_permsocks))
nfsd_destroy_serv(net);
out_unlock_mtx:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 1df9e18c510b..c16c7d630859 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -288,10 +288,12 @@ int nfsd_nrthreads(struct net *net)
{
int rv = 0;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv)
- rv = nn->nfsd_serv->sv_nrthreads;
+ serv = nn->nfsd_serv;
+ if (serv)
+ rv = serv->sv_nrthreads;
mutex_unlock(&nfsd_mutex);
return rv;
}
@@ -300,16 +302,17 @@ static int nfsd_init_socks(struct net *net, const struct cred *cred)
{
int error;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv = nn->nfsd_serv;
- if (!list_empty(&nn->nfsd_serv->sv_permsocks))
+ if (!list_empty(&serv->sv_permsocks))
return 0;
- error = svc_xprt_create(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT,
+ error = svc_xprt_create(serv, "udp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS, cred);
if (error < 0)
return error;
- error = svc_xprt_create(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT,
+ error = svc_xprt_create(serv, "tcp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS, cred);
if (error < 0)
return error;
@@ -722,11 +725,12 @@ int nfsd_create_serv(struct net *net)
int nfsd_nrpools(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv = nn->nfsd_serv;
- if (nn->nfsd_serv == NULL)
+ if (serv == NULL)
return 0;
else
- return nn->nfsd_serv->sv_nrpools;
+ return serv->sv_nrpools;
}
int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
@@ -760,14 +764,15 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
int tot = 0;
int err = 0;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv = nn->nfsd_serv;
lockdep_assert_held(&nfsd_mutex);
- if (nn->nfsd_serv == NULL || n <= 0)
+ if (serv == NULL || n <= 0)
return 0;
- if (n > nn->nfsd_serv->sv_nrpools)
- n = nn->nfsd_serv->sv_nrpools;
+ if (n > serv->sv_nrpools)
+ n = serv->sv_nrpools;
/* enforce a global maximum number of threads */
tot = 0;
@@ -790,18 +795,15 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
/* apply the new numbers */
for (i = 0; i < n; i++) {
- err = svc_set_num_threads(nn->nfsd_serv,
- &nn->nfsd_serv->sv_pools[i],
+ err = svc_set_num_threads(serv, &serv->sv_pools[i],
nthreads[i]);
if (err)
goto out;
}
/* Anything undefined in array is considered to be 0 */
- for (i = n; i < nn->nfsd_serv->sv_nrpools; ++i) {
- err = svc_set_num_threads(nn->nfsd_serv,
- &nn->nfsd_serv->sv_pools[i],
- 0);
+ for (i = n; i < serv->sv_nrpools; ++i) {
+ err = svc_set_num_threads(serv, &serv->sv_pools[i], 0);
if (err)
goto out;
}
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 17/20] nfsd: use SRCU to dereference nn->nfsd_serv
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (15 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 16/20] nfsd: prepare to use SRCU to dereference nn->nfsd_serv Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 12:43 ` Jeff Layton
2024-06-24 16:27 ` [PATCH v7 18/20] nfsd/localio: use SRCU to dereference nn->nfsd_serv in nfsd_open_local_fh Mike Snitzer
` (3 subsequent siblings)
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
Introduce nfsd_serv_get, nfsd_serv_put and nfsd_serv_sync and update
the nfsd code to prevent nfsd_destroy_serv from destroying
nn->nfsd_serv until all nfsd code is done with it (particularly the
localio code that doesn't run in the context of nfsd's svc threads,
nor does it take the nfsd_mutex).
Commit 83d5e5b0af90 ("dm: optimize use SRCU and RCU") provided a
familiar well-worn pattern for how implement.
Suggested-by: NeilBrown <neilb@suse.de>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfsd/filecache.c | 13 ++++++++---
fs/nfsd/netns.h | 14 ++++++++++--
fs/nfsd/nfs4state.c | 25 ++++++++++++++-------
fs/nfsd/nfsctl.c | 7 ++++--
fs/nfsd/nfssvc.c | 54 ++++++++++++++++++++++++++++++++++++---------
5 files changed, 88 insertions(+), 25 deletions(-)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 99631fa56662..474b3a3af3fb 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -413,12 +413,15 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
struct nfsd_file *nf = list_first_entry(dispose,
struct nfsd_file, nf_lru);
struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
struct nfsd_fcache_disposal *l = nn->fcache_disposal;
spin_lock(&l->lock);
list_move_tail(&nf->nf_lru, &l->freeme);
spin_unlock(&l->lock);
- svc_wake_up(nn->nfsd_serv);
+ svc_wake_up(serv);
+ nfsd_serv_put(nn, srcu_idx);
}
}
@@ -443,11 +446,15 @@ void nfsd_file_net_dispose(struct nfsd_net *nn)
for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
list_move(l->freeme.next, &dispose);
spin_unlock(&l->lock);
- if (!list_empty(&l->freeme))
+ if (!list_empty(&l->freeme)) {
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
/* Wake up another thread to share the work
* *before* doing any actual disposing.
*/
- svc_wake_up(nn->nfsd_serv);
+ svc_wake_up(serv);
+ nfsd_serv_put(nn, srcu_idx);
+ }
nfsd_file_dispose_list(&dispose);
}
}
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 0c5a1d97e4ac..92d0d0883f17 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -139,8 +139,14 @@ struct nfsd_net {
u32 clverifier_counter;
struct svc_info nfsd_info;
-#define nfsd_serv nfsd_info.serv
-
+ /*
+ * The current 'nfsd_serv' at nfsd_info.serv. Using 'void' rather than
+ * 'struct svc_serv' to guard against new code dereferencing nfsd_serv
+ * without using proper synchronization.
+ * Use nfsd_serv_get() or take nfsd_mutex to dereference.
+ */
+ void __rcu *nfsd_serv;
+ struct srcu_struct nfsd_serv_srcu;
/*
* clientid and stateid data for construction of net unique COPY
@@ -225,6 +231,10 @@ struct nfsd_net {
extern bool nfsd_support_version(int vers);
extern void nfsd_netns_free_versions(struct nfsd_net *nn);
+extern struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx);
+extern void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx);
+extern void nfsd_serv_sync(struct nfsd_net *nn);
+
extern unsigned int nfsd_net_id;
void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a20c2c9d7d45..8876810e569d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1919,6 +1919,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
u32 num = ca->maxreqs;
unsigned long avail, total_avail;
unsigned int scale_factor;
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
spin_lock(&nfsd_drc_lock);
if (nfsd_drc_max_mem > nfsd_drc_mem_used)
@@ -1940,7 +1942,7 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
* Give the client one slot even if that would require
* over-allocation--it is better than failure.
*/
- scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads);
+ scale_factor = max_t(unsigned int, 8, serv->sv_nrthreads);
avail = clamp_t(unsigned long, avail, slotsize,
total_avail/scale_factor);
@@ -1949,6 +1951,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
nfsd_drc_mem_used += num * slotsize;
spin_unlock(&nfsd_drc_lock);
+ nfsd_serv_put(nn, srcu_idx);
+
return num;
}
@@ -3702,12 +3706,16 @@ nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
{
- u32 maxrpc = nn->nfsd_serv->sv_max_mesg;
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
+ u32 maxrpc = serv->sv_max_mesg;
+ __be32 status = nfs_ok;
- if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ)
- return nfserr_toosmall;
- if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ)
- return nfserr_toosmall;
+ if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ ||
+ ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ) {
+ status = nfserr_toosmall;
+ goto out;
+ }
ca->headerpadsz = 0;
ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
@@ -3726,8 +3734,9 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
* accounting is soft and provides no guarantees either way.
*/
ca->maxreqs = nfsd4_get_drc_mem(ca, nn);
-
- return nfs_ok;
+out:
+ nfsd_serv_put(nn, srcu_idx);
+ return status;
}
/*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 075ada559e18..d3eeb829bc9b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1569,10 +1569,12 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
{
struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id);
int i, ret, rqstp_index = 0;
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
rcu_read_lock();
- for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
+ for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_rqst *rqstp;
if (i < cb->args[0]) /* already consumed */
@@ -1580,7 +1582,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
rqstp_index = 0;
list_for_each_entry_rcu(rqstp,
- &nn->nfsd_serv->sv_pools[i].sp_all_threads,
+ &serv->sv_pools[i].sp_all_threads,
rq_all) {
struct nfsd_genl_rqstp genl_rqstp;
unsigned int status_counter;
@@ -1645,6 +1647,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
ret = skb->len;
out:
rcu_read_unlock();
+ nfsd_serv_put(nn, srcu_idx);
return ret;
}
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index c16c7d630859..6f41fb832484 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -279,6 +279,26 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
return 0;
}
+struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx)
+ __acquires(nn->nfsd_serv_srcu)
+{
+ *srcu_idx = srcu_read_lock(&nn->nfsd_serv_srcu);
+
+ return srcu_dereference(nn->nfsd_serv, &nn->nfsd_serv_srcu);
+}
+
+void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx)
+ __releases(nn->nfsd_serv_srcu)
+{
+ srcu_read_unlock(&nn->nfsd_serv_srcu, srcu_idx);
+}
+
+void nfsd_serv_sync(struct nfsd_net *nn)
+{
+ synchronize_srcu(&nn->nfsd_serv_srcu);
+ synchronize_rcu_expedited();
+}
+
/*
* Maximum number of nfsd processes
*/
@@ -486,6 +506,7 @@ static void nfsd_shutdown_net(struct net *net)
lockd_down(net);
nn->lockd_up = false;
}
+ cleanup_srcu_struct(&nn->nfsd_serv_srcu);
#if IS_ENABLED(CONFIG_NFSD_LOCALIO)
list_del_rcu(&nn->nfsd_uuid.list);
#endif
@@ -493,6 +514,7 @@ static void nfsd_shutdown_net(struct net *net)
nfsd_shutdown_generic();
}
+// FIXME: nfsd_serv_{get,put} should make it safe to eliminate nfsd_notifier_lock
static DEFINE_SPINLOCK(nfsd_notifier_lock);
static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
void *ptr)
@@ -502,20 +524,22 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
struct net *net = dev_net(dev);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct sockaddr_in sin;
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
- if (event != NETDEV_DOWN || !nn->nfsd_serv)
+ if (event != NETDEV_DOWN || !serv)
goto out;
spin_lock(&nfsd_notifier_lock);
- if (nn->nfsd_serv) {
+ if (serv) {
dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local);
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = ifa->ifa_local;
- svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
+ svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin);
}
spin_unlock(&nfsd_notifier_lock);
-
out:
+ nfsd_serv_put(nn, srcu_idx);
return NOTIFY_DONE;
}
@@ -532,22 +556,24 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
struct net *net = dev_net(dev);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct sockaddr_in6 sin6;
+ int srcu_idx;
+ struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
- if (event != NETDEV_DOWN || !nn->nfsd_serv)
+ if (event != NETDEV_DOWN || !serv)
goto out;
spin_lock(&nfsd_notifier_lock);
- if (nn->nfsd_serv) {
+ if (serv) {
dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ifa->addr;
if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin6.sin6_scope_id = ifa->idev->dev->ifindex;
- svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
+ svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin6);
}
spin_unlock(&nfsd_notifier_lock);
-
out:
+ nfsd_serv_put(nn, srcu_idx);
return NOTIFY_DONE;
}
@@ -568,9 +594,12 @@ void nfsd_destroy_serv(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct svc_serv *serv = nn->nfsd_serv;
+ lockdep_assert_held(&nfsd_mutex);
+
spin_lock(&nfsd_notifier_lock);
- nn->nfsd_serv = NULL;
+ rcu_assign_pointer(nn->nfsd_serv, NULL);
spin_unlock(&nfsd_notifier_lock);
+ nfsd_serv_sync(nn);
/* check if the notifier still has clients */
if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
@@ -690,6 +719,10 @@ int nfsd_create_serv(struct net *net)
if (nn->nfsd_serv)
return 0;
+ error = init_srcu_struct(&nn->nfsd_serv_srcu);
+ if (error)
+ return error;
+
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions(nn);
@@ -707,7 +740,8 @@ int nfsd_create_serv(struct net *net)
}
spin_lock(&nfsd_notifier_lock);
nn->nfsd_info.mutex = &nfsd_mutex;
- nn->nfsd_serv = serv;
+ nn->nfsd_info.serv = serv;
+ rcu_assign_pointer(nn->nfsd_serv, nn->nfsd_info.serv);
spin_unlock(&nfsd_notifier_lock);
set_max_drc();
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 17/20] nfsd: use SRCU to dereference nn->nfsd_serv
2024-06-24 16:27 ` [PATCH v7 17/20] nfsd: " Mike Snitzer
@ 2024-06-25 12:43 ` Jeff Layton
2024-06-25 23:29 ` NeilBrown
0 siblings, 1 reply; 40+ messages in thread
From: Jeff Layton @ 2024-06-25 12:43 UTC (permalink / raw)
To: Mike Snitzer, linux-nfs; +Cc: Chuck Lever, Trond Myklebust, NeilBrown, snitzer
On Mon, 2024-06-24 at 12:27 -0400, Mike Snitzer wrote:
> Introduce nfsd_serv_get, nfsd_serv_put and nfsd_serv_sync and update
> the nfsd code to prevent nfsd_destroy_serv from destroying
> nn->nfsd_serv until all nfsd code is done with it (particularly the
> localio code that doesn't run in the context of nfsd's svc threads,
> nor does it take the nfsd_mutex).
>
> Commit 83d5e5b0af90 ("dm: optimize use SRCU and RCU") provided a
> familiar well-worn pattern for how implement.
>
> Suggested-by: NeilBrown <neilb@suse.de>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> fs/nfsd/filecache.c | 13 ++++++++---
> fs/nfsd/netns.h | 14 ++++++++++--
> fs/nfsd/nfs4state.c | 25 ++++++++++++++-------
> fs/nfsd/nfsctl.c | 7 ++++--
> fs/nfsd/nfssvc.c | 54 ++++++++++++++++++++++++++++++++++++---------
> 5 files changed, 88 insertions(+), 25 deletions(-)
>
> diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
> index 99631fa56662..474b3a3af3fb 100644
> --- a/fs/nfsd/filecache.c
> +++ b/fs/nfsd/filecache.c
> @@ -413,12 +413,15 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
> struct nfsd_file *nf = list_first_entry(dispose,
> struct nfsd_file, nf_lru);
> struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> struct nfsd_fcache_disposal *l = nn->fcache_disposal;
>
> spin_lock(&l->lock);
> list_move_tail(&nf->nf_lru, &l->freeme);
> spin_unlock(&l->lock);
> - svc_wake_up(nn->nfsd_serv);
> + svc_wake_up(serv);
> + nfsd_serv_put(nn, srcu_idx);
> }
> }
>
> @@ -443,11 +446,15 @@ void nfsd_file_net_dispose(struct nfsd_net *nn)
> for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
> list_move(l->freeme.next, &dispose);
> spin_unlock(&l->lock);
> - if (!list_empty(&l->freeme))
> + if (!list_empty(&l->freeme)) {
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> /* Wake up another thread to share the work
> * *before* doing any actual disposing.
> */
> - svc_wake_up(nn->nfsd_serv);
> + svc_wake_up(serv);
> + nfsd_serv_put(nn, srcu_idx);
> + }
> nfsd_file_dispose_list(&dispose);
> }
> }
> diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
> index 0c5a1d97e4ac..92d0d0883f17 100644
> --- a/fs/nfsd/netns.h
> +++ b/fs/nfsd/netns.h
> @@ -139,8 +139,14 @@ struct nfsd_net {
> u32 clverifier_counter;
>
> struct svc_info nfsd_info;
> -#define nfsd_serv nfsd_info.serv
> -
> + /*
> + * The current 'nfsd_serv' at nfsd_info.serv. Using 'void' rather than
> + * 'struct svc_serv' to guard against new code dereferencing nfsd_serv
> + * without using proper synchronization.
> + * Use nfsd_serv_get() or take nfsd_mutex to dereference.
> + */
> + void __rcu *nfsd_serv;
> + struct srcu_struct nfsd_serv_srcu;
I'm still not sold on the use of a void pointer here. It might protect
you from using nn->nfsd_serv directly, but if you do:
struct svc_serv *serv = nn->nfsd_serv;
...that will still work. If you really want to guard against direct
dereferencing, maybe it should be an unsigned long? Then you really
will have to cast to use it.
>
> /*
> * clientid and stateid data for construction of net unique COPY
> @@ -225,6 +231,10 @@ struct nfsd_net {
> extern bool nfsd_support_version(int vers);
> extern void nfsd_netns_free_versions(struct nfsd_net *nn);
>
> +extern struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx);
> +extern void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx);
> +extern void nfsd_serv_sync(struct nfsd_net *nn);
> +
> extern unsigned int nfsd_net_id;
>
> void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index a20c2c9d7d45..8876810e569d 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -1919,6 +1919,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> u32 num = ca->maxreqs;
> unsigned long avail, total_avail;
> unsigned int scale_factor;
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
>
> spin_lock(&nfsd_drc_lock);
> if (nfsd_drc_max_mem > nfsd_drc_mem_used)
> @@ -1940,7 +1942,7 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> * Give the client one slot even if that would require
> * over-allocation--it is better than failure.
> */
> - scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads);
> + scale_factor = max_t(unsigned int, 8, serv->sv_nrthreads);
>
> avail = clamp_t(unsigned long, avail, slotsize,
> total_avail/scale_factor);
> @@ -1949,6 +1951,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> nfsd_drc_mem_used += num * slotsize;
> spin_unlock(&nfsd_drc_lock);
>
> + nfsd_serv_put(nn, srcu_idx);
> +
> return num;
> }
>
> @@ -3702,12 +3706,16 @@ nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
>
> static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
> {
> - u32 maxrpc = nn->nfsd_serv->sv_max_mesg;
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> + u32 maxrpc = serv->sv_max_mesg;
> + __be32 status = nfs_ok;
>
> - if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ)
> - return nfserr_toosmall;
> - if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ)
> - return nfserr_toosmall;
> + if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ ||
> + ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ) {
> + status = nfserr_toosmall;
> + goto out;
> + }
> ca->headerpadsz = 0;
> ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
> ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
> @@ -3726,8 +3734,9 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
> * accounting is soft and provides no guarantees either way.
> */
> ca->maxreqs = nfsd4_get_drc_mem(ca, nn);
> -
> - return nfs_ok;
> +out:
> + nfsd_serv_put(nn, srcu_idx);
> + return status;
> }
>
> /*
> diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
> index 075ada559e18..d3eeb829bc9b 100644
> --- a/fs/nfsd/nfsctl.c
> +++ b/fs/nfsd/nfsctl.c
> @@ -1569,10 +1569,12 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> {
> struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id);
> int i, ret, rqstp_index = 0;
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
>
> rcu_read_lock();
>
> - for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
> + for (i = 0; i < serv->sv_nrpools; i++) {
> struct svc_rqst *rqstp;
>
> if (i < cb->args[0]) /* already consumed */
> @@ -1580,7 +1582,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
>
> rqstp_index = 0;
> list_for_each_entry_rcu(rqstp,
> - &nn->nfsd_serv->sv_pools[i].sp_all_threads,
> + &serv->sv_pools[i].sp_all_threads,
> rq_all) {
> struct nfsd_genl_rqstp genl_rqstp;
> unsigned int status_counter;
> @@ -1645,6 +1647,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> ret = skb->len;
> out:
> rcu_read_unlock();
> + nfsd_serv_put(nn, srcu_idx);
>
> return ret;
> }
> diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> index c16c7d630859..6f41fb832484 100644
> --- a/fs/nfsd/nfssvc.c
> +++ b/fs/nfsd/nfssvc.c
> @@ -279,6 +279,26 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
> return 0;
> }
>
> +struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx)
> + __acquires(nn->nfsd_serv_srcu)
> +{
> + *srcu_idx = srcu_read_lock(&nn->nfsd_serv_srcu);
> +
> + return srcu_dereference(nn->nfsd_serv, &nn->nfsd_serv_srcu);
> +}
> +
> +void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx)
> + __releases(nn->nfsd_serv_srcu)
> +{
> + srcu_read_unlock(&nn->nfsd_serv_srcu, srcu_idx);
> +}
> +
> +void nfsd_serv_sync(struct nfsd_net *nn)
> +{
> + synchronize_srcu(&nn->nfsd_serv_srcu);
> + synchronize_rcu_expedited();
> +}
> +
> /*
> * Maximum number of nfsd processes
> */
> @@ -486,6 +506,7 @@ static void nfsd_shutdown_net(struct net *net)
> lockd_down(net);
> nn->lockd_up = false;
> }
> + cleanup_srcu_struct(&nn->nfsd_serv_srcu);
> #if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> list_del_rcu(&nn->nfsd_uuid.list);
> #endif
> @@ -493,6 +514,7 @@ static void nfsd_shutdown_net(struct net *net)
> nfsd_shutdown_generic();
> }
>
> +// FIXME: nfsd_serv_{get,put} should make it safe to eliminate nfsd_notifier_lock
> static DEFINE_SPINLOCK(nfsd_notifier_lock);
> static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
> void *ptr)
> @@ -502,20 +524,22 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
> struct net *net = dev_net(dev);
> struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> struct sockaddr_in sin;
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
>
> - if (event != NETDEV_DOWN || !nn->nfsd_serv)
> + if (event != NETDEV_DOWN || !serv)
> goto out;
>
> spin_lock(&nfsd_notifier_lock);
> - if (nn->nfsd_serv) {
> + if (serv) {
> dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local);
> sin.sin_family = AF_INET;
> sin.sin_addr.s_addr = ifa->ifa_local;
> - svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
> + svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin);
> }
> spin_unlock(&nfsd_notifier_lock);
> -
> out:
> + nfsd_serv_put(nn, srcu_idx);
> return NOTIFY_DONE;
> }
>
> @@ -532,22 +556,24 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
> struct net *net = dev_net(dev);
> struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> struct sockaddr_in6 sin6;
> + int srcu_idx;
> + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
>
> - if (event != NETDEV_DOWN || !nn->nfsd_serv)
> + if (event != NETDEV_DOWN || !serv)
> goto out;
>
> spin_lock(&nfsd_notifier_lock);
> - if (nn->nfsd_serv) {
> + if (serv) {
> dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
> sin6.sin6_family = AF_INET6;
> sin6.sin6_addr = ifa->addr;
> if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
> sin6.sin6_scope_id = ifa->idev->dev->ifindex;
> - svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
> + svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin6);
> }
> spin_unlock(&nfsd_notifier_lock);
> -
> out:
> + nfsd_serv_put(nn, srcu_idx);
> return NOTIFY_DONE;
> }
>
> @@ -568,9 +594,12 @@ void nfsd_destroy_serv(struct net *net)
> struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> struct svc_serv *serv = nn->nfsd_serv;
>
> + lockdep_assert_held(&nfsd_mutex);
> +
> spin_lock(&nfsd_notifier_lock);
> - nn->nfsd_serv = NULL;
> + rcu_assign_pointer(nn->nfsd_serv, NULL);
> spin_unlock(&nfsd_notifier_lock);
> + nfsd_serv_sync(nn);
>
> /* check if the notifier still has clients */
> if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
> @@ -690,6 +719,10 @@ int nfsd_create_serv(struct net *net)
> if (nn->nfsd_serv)
> return 0;
>
> + error = init_srcu_struct(&nn->nfsd_serv_srcu);
> + if (error)
> + return error;
> +
> if (nfsd_max_blksize == 0)
> nfsd_max_blksize = nfsd_get_default_max_blksize();
> nfsd_reset_versions(nn);
> @@ -707,7 +740,8 @@ int nfsd_create_serv(struct net *net)
> }
> spin_lock(&nfsd_notifier_lock);
> nn->nfsd_info.mutex = &nfsd_mutex;
> - nn->nfsd_serv = serv;
> + nn->nfsd_info.serv = serv;
> + rcu_assign_pointer(nn->nfsd_serv, nn->nfsd_info.serv);
> spin_unlock(&nfsd_notifier_lock);
>
> set_max_drc();
--
Jeff Layton <jlayton@kernel.org>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 17/20] nfsd: use SRCU to dereference nn->nfsd_serv
2024-06-25 12:43 ` Jeff Layton
@ 2024-06-25 23:29 ` NeilBrown
2024-06-26 16:49 ` Mike Snitzer
0 siblings, 1 reply; 40+ messages in thread
From: NeilBrown @ 2024-06-25 23:29 UTC (permalink / raw)
To: Jeff Layton
Cc: Mike Snitzer, linux-nfs, Chuck Lever, Trond Myklebust, snitzer
On Tue, 25 Jun 2024, Jeff Layton wrote:
> On Mon, 2024-06-24 at 12:27 -0400, Mike Snitzer wrote:
> > Introduce nfsd_serv_get, nfsd_serv_put and nfsd_serv_sync and update
> > the nfsd code to prevent nfsd_destroy_serv from destroying
> > nn->nfsd_serv until all nfsd code is done with it (particularly the
> > localio code that doesn't run in the context of nfsd's svc threads,
> > nor does it take the nfsd_mutex).
> >
> > Commit 83d5e5b0af90 ("dm: optimize use SRCU and RCU") provided a
> > familiar well-worn pattern for how implement.
> >
> > Suggested-by: NeilBrown <neilb@suse.de>
> > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > ---
> > fs/nfsd/filecache.c | 13 ++++++++---
> > fs/nfsd/netns.h | 14 ++++++++++--
> > fs/nfsd/nfs4state.c | 25 ++++++++++++++-------
> > fs/nfsd/nfsctl.c | 7 ++++--
> > fs/nfsd/nfssvc.c | 54 ++++++++++++++++++++++++++++++++++++---------
> > 5 files changed, 88 insertions(+), 25 deletions(-)
> >
> > diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
> > index 99631fa56662..474b3a3af3fb 100644
> > --- a/fs/nfsd/filecache.c
> > +++ b/fs/nfsd/filecache.c
> > @@ -413,12 +413,15 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
> > struct nfsd_file *nf = list_first_entry(dispose,
> > struct nfsd_file, nf_lru);
> > struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> > struct nfsd_fcache_disposal *l = nn->fcache_disposal;
> >
> > spin_lock(&l->lock);
> > list_move_tail(&nf->nf_lru, &l->freeme);
> > spin_unlock(&l->lock);
> > - svc_wake_up(nn->nfsd_serv);
> > + svc_wake_up(serv);
> > + nfsd_serv_put(nn, srcu_idx);
> > }
> > }
> >
> > @@ -443,11 +446,15 @@ void nfsd_file_net_dispose(struct nfsd_net *nn)
> > for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
> > list_move(l->freeme.next, &dispose);
> > spin_unlock(&l->lock);
> > - if (!list_empty(&l->freeme))
> > + if (!list_empty(&l->freeme)) {
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> > /* Wake up another thread to share the work
> > * *before* doing any actual disposing.
> > */
> > - svc_wake_up(nn->nfsd_serv);
> > + svc_wake_up(serv);
> > + nfsd_serv_put(nn, srcu_idx);
> > + }
> > nfsd_file_dispose_list(&dispose);
> > }
> > }
> > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
> > index 0c5a1d97e4ac..92d0d0883f17 100644
> > --- a/fs/nfsd/netns.h
> > +++ b/fs/nfsd/netns.h
> > @@ -139,8 +139,14 @@ struct nfsd_net {
> > u32 clverifier_counter;
> >
> > struct svc_info nfsd_info;
> > -#define nfsd_serv nfsd_info.serv
> > -
> > + /*
> > + * The current 'nfsd_serv' at nfsd_info.serv. Using 'void' rather than
> > + * 'struct svc_serv' to guard against new code dereferencing nfsd_serv
> > + * without using proper synchronization.
> > + * Use nfsd_serv_get() or take nfsd_mutex to dereference.
> > + */
> > + void __rcu *nfsd_serv;
> > + struct srcu_struct nfsd_serv_srcu;
>
> I'm still not sold on the use of a void pointer here. It might protect
> you from using nn->nfsd_serv directly, but if you do:
>
> struct svc_serv *serv = nn->nfsd_serv;
>
> ...that will still work. If you really want to guard against direct
> dereferencing, maybe it should be an unsigned long? Then you really
> will have to cast to use it.
I agree. The point of the "__rcu" attribute is that sparse will
complain if you use the pointer without using srcu_dereference().
And CONFIG_PROVE_RCU gives you run-time splats.
We should use the tools we already have.
Thanks,
NeilBrown
>
> >
> > /*
> > * clientid and stateid data for construction of net unique COPY
> > @@ -225,6 +231,10 @@ struct nfsd_net {
> > extern bool nfsd_support_version(int vers);
> > extern void nfsd_netns_free_versions(struct nfsd_net *nn);
> >
> > +extern struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx);
> > +extern void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx);
> > +extern void nfsd_serv_sync(struct nfsd_net *nn);
> > +
> > extern unsigned int nfsd_net_id;
> >
> > void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
> > diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> > index a20c2c9d7d45..8876810e569d 100644
> > --- a/fs/nfsd/nfs4state.c
> > +++ b/fs/nfsd/nfs4state.c
> > @@ -1919,6 +1919,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> > u32 num = ca->maxreqs;
> > unsigned long avail, total_avail;
> > unsigned int scale_factor;
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> >
> > spin_lock(&nfsd_drc_lock);
> > if (nfsd_drc_max_mem > nfsd_drc_mem_used)
> > @@ -1940,7 +1942,7 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> > * Give the client one slot even if that would require
> > * over-allocation--it is better than failure.
> > */
> > - scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads);
> > + scale_factor = max_t(unsigned int, 8, serv->sv_nrthreads);
> >
> > avail = clamp_t(unsigned long, avail, slotsize,
> > total_avail/scale_factor);
> > @@ -1949,6 +1951,8 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn
> > nfsd_drc_mem_used += num * slotsize;
> > spin_unlock(&nfsd_drc_lock);
> >
> > + nfsd_serv_put(nn, srcu_idx);
> > +
> > return num;
> > }
> >
> > @@ -3702,12 +3706,16 @@ nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
> >
> > static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
> > {
> > - u32 maxrpc = nn->nfsd_serv->sv_max_mesg;
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> > + u32 maxrpc = serv->sv_max_mesg;
> > + __be32 status = nfs_ok;
> >
> > - if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ)
> > - return nfserr_toosmall;
> > - if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ)
> > - return nfserr_toosmall;
> > + if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ ||
> > + ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ) {
> > + status = nfserr_toosmall;
> > + goto out;
> > + }
> > ca->headerpadsz = 0;
> > ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
> > ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
> > @@ -3726,8 +3734,9 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
> > * accounting is soft and provides no guarantees either way.
> > */
> > ca->maxreqs = nfsd4_get_drc_mem(ca, nn);
> > -
> > - return nfs_ok;
> > +out:
> > + nfsd_serv_put(nn, srcu_idx);
> > + return status;
> > }
> >
> > /*
> > diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
> > index 075ada559e18..d3eeb829bc9b 100644
> > --- a/fs/nfsd/nfsctl.c
> > +++ b/fs/nfsd/nfsctl.c
> > @@ -1569,10 +1569,12 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> > {
> > struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id);
> > int i, ret, rqstp_index = 0;
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> >
> > rcu_read_lock();
> >
> > - for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
> > + for (i = 0; i < serv->sv_nrpools; i++) {
> > struct svc_rqst *rqstp;
> >
> > if (i < cb->args[0]) /* already consumed */
> > @@ -1580,7 +1582,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> >
> > rqstp_index = 0;
> > list_for_each_entry_rcu(rqstp,
> > - &nn->nfsd_serv->sv_pools[i].sp_all_threads,
> > + &serv->sv_pools[i].sp_all_threads,
> > rq_all) {
> > struct nfsd_genl_rqstp genl_rqstp;
> > unsigned int status_counter;
> > @@ -1645,6 +1647,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
> > ret = skb->len;
> > out:
> > rcu_read_unlock();
> > + nfsd_serv_put(nn, srcu_idx);
> >
> > return ret;
> > }
> > diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
> > index c16c7d630859..6f41fb832484 100644
> > --- a/fs/nfsd/nfssvc.c
> > +++ b/fs/nfsd/nfssvc.c
> > @@ -279,6 +279,26 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
> > return 0;
> > }
> >
> > +struct svc_serv *nfsd_serv_get(struct nfsd_net *nn, int *srcu_idx)
> > + __acquires(nn->nfsd_serv_srcu)
> > +{
> > + *srcu_idx = srcu_read_lock(&nn->nfsd_serv_srcu);
> > +
> > + return srcu_dereference(nn->nfsd_serv, &nn->nfsd_serv_srcu);
> > +}
> > +
> > +void nfsd_serv_put(struct nfsd_net *nn, int srcu_idx)
> > + __releases(nn->nfsd_serv_srcu)
> > +{
> > + srcu_read_unlock(&nn->nfsd_serv_srcu, srcu_idx);
> > +}
> > +
> > +void nfsd_serv_sync(struct nfsd_net *nn)
> > +{
> > + synchronize_srcu(&nn->nfsd_serv_srcu);
> > + synchronize_rcu_expedited();
> > +}
> > +
> > /*
> > * Maximum number of nfsd processes
> > */
> > @@ -486,6 +506,7 @@ static void nfsd_shutdown_net(struct net *net)
> > lockd_down(net);
> > nn->lockd_up = false;
> > }
> > + cleanup_srcu_struct(&nn->nfsd_serv_srcu);
> > #if IS_ENABLED(CONFIG_NFSD_LOCALIO)
> > list_del_rcu(&nn->nfsd_uuid.list);
> > #endif
> > @@ -493,6 +514,7 @@ static void nfsd_shutdown_net(struct net *net)
> > nfsd_shutdown_generic();
> > }
> >
> > +// FIXME: nfsd_serv_{get,put} should make it safe to eliminate nfsd_notifier_lock
> > static DEFINE_SPINLOCK(nfsd_notifier_lock);
> > static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
> > void *ptr)
> > @@ -502,20 +524,22 @@ static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event,
> > struct net *net = dev_net(dev);
> > struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> > struct sockaddr_in sin;
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> >
> > - if (event != NETDEV_DOWN || !nn->nfsd_serv)
> > + if (event != NETDEV_DOWN || !serv)
> > goto out;
> >
> > spin_lock(&nfsd_notifier_lock);
> > - if (nn->nfsd_serv) {
> > + if (serv) {
> > dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local);
> > sin.sin_family = AF_INET;
> > sin.sin_addr.s_addr = ifa->ifa_local;
> > - svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin);
> > + svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin);
> > }
> > spin_unlock(&nfsd_notifier_lock);
> > -
> > out:
> > + nfsd_serv_put(nn, srcu_idx);
> > return NOTIFY_DONE;
> > }
> >
> > @@ -532,22 +556,24 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
> > struct net *net = dev_net(dev);
> > struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> > struct sockaddr_in6 sin6;
> > + int srcu_idx;
> > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> >
> > - if (event != NETDEV_DOWN || !nn->nfsd_serv)
> > + if (event != NETDEV_DOWN || !serv)
> > goto out;
> >
> > spin_lock(&nfsd_notifier_lock);
> > - if (nn->nfsd_serv) {
> > + if (serv) {
> > dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
> > sin6.sin6_family = AF_INET6;
> > sin6.sin6_addr = ifa->addr;
> > if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
> > sin6.sin6_scope_id = ifa->idev->dev->ifindex;
> > - svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
> > + svc_age_temp_xprts_now(serv, (struct sockaddr *)&sin6);
> > }
> > spin_unlock(&nfsd_notifier_lock);
> > -
> > out:
> > + nfsd_serv_put(nn, srcu_idx);
> > return NOTIFY_DONE;
> > }
> >
> > @@ -568,9 +594,12 @@ void nfsd_destroy_serv(struct net *net)
> > struct nfsd_net *nn = net_generic(net, nfsd_net_id);
> > struct svc_serv *serv = nn->nfsd_serv;
> >
> > + lockdep_assert_held(&nfsd_mutex);
> > +
> > spin_lock(&nfsd_notifier_lock);
> > - nn->nfsd_serv = NULL;
> > + rcu_assign_pointer(nn->nfsd_serv, NULL);
> > spin_unlock(&nfsd_notifier_lock);
> > + nfsd_serv_sync(nn);
> >
> > /* check if the notifier still has clients */
> > if (atomic_dec_return(&nfsd_notifier_refcount) == 0) {
> > @@ -690,6 +719,10 @@ int nfsd_create_serv(struct net *net)
> > if (nn->nfsd_serv)
> > return 0;
> >
> > + error = init_srcu_struct(&nn->nfsd_serv_srcu);
> > + if (error)
> > + return error;
> > +
> > if (nfsd_max_blksize == 0)
> > nfsd_max_blksize = nfsd_get_default_max_blksize();
> > nfsd_reset_versions(nn);
> > @@ -707,7 +740,8 @@ int nfsd_create_serv(struct net *net)
> > }
> > spin_lock(&nfsd_notifier_lock);
> > nn->nfsd_info.mutex = &nfsd_mutex;
> > - nn->nfsd_serv = serv;
> > + nn->nfsd_info.serv = serv;
> > + rcu_assign_pointer(nn->nfsd_serv, nn->nfsd_info.serv);
> > spin_unlock(&nfsd_notifier_lock);
> >
> > set_max_drc();
>
> --
> Jeff Layton <jlayton@kernel.org>
>
^ permalink raw reply [flat|nested] 40+ messages in thread* Re: [PATCH v7 17/20] nfsd: use SRCU to dereference nn->nfsd_serv
2024-06-25 23:29 ` NeilBrown
@ 2024-06-26 16:49 ` Mike Snitzer
0 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-26 16:49 UTC (permalink / raw)
To: NeilBrown; +Cc: Jeff Layton, linux-nfs, Chuck Lever, Trond Myklebust, snitzer
On Wed, Jun 26, 2024 at 09:29:13AM +1000, NeilBrown wrote:
> On Tue, 25 Jun 2024, Jeff Layton wrote:
> > On Mon, 2024-06-24 at 12:27 -0400, Mike Snitzer wrote:
> > > Introduce nfsd_serv_get, nfsd_serv_put and nfsd_serv_sync and update
> > > the nfsd code to prevent nfsd_destroy_serv from destroying
> > > nn->nfsd_serv until all nfsd code is done with it (particularly the
> > > localio code that doesn't run in the context of nfsd's svc threads,
> > > nor does it take the nfsd_mutex).
> > >
> > > Commit 83d5e5b0af90 ("dm: optimize use SRCU and RCU") provided a
> > > familiar well-worn pattern for how implement.
> > >
> > > Suggested-by: NeilBrown <neilb@suse.de>
> > > Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> > > ---
> > > fs/nfsd/filecache.c | 13 ++++++++---
> > > fs/nfsd/netns.h | 14 ++++++++++--
> > > fs/nfsd/nfs4state.c | 25 ++++++++++++++-------
> > > fs/nfsd/nfsctl.c | 7 ++++--
> > > fs/nfsd/nfssvc.c | 54 ++++++++++++++++++++++++++++++++++++---------
> > > 5 files changed, 88 insertions(+), 25 deletions(-)
> > >
> > > diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
> > > index 99631fa56662..474b3a3af3fb 100644
> > > --- a/fs/nfsd/filecache.c
> > > +++ b/fs/nfsd/filecache.c
> > > @@ -413,12 +413,15 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
> > > struct nfsd_file *nf = list_first_entry(dispose,
> > > struct nfsd_file, nf_lru);
> > > struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
> > > + int srcu_idx;
> > > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> > > struct nfsd_fcache_disposal *l = nn->fcache_disposal;
> > >
> > > spin_lock(&l->lock);
> > > list_move_tail(&nf->nf_lru, &l->freeme);
> > > spin_unlock(&l->lock);
> > > - svc_wake_up(nn->nfsd_serv);
> > > + svc_wake_up(serv);
> > > + nfsd_serv_put(nn, srcu_idx);
> > > }
> > > }
> > >
> > > @@ -443,11 +446,15 @@ void nfsd_file_net_dispose(struct nfsd_net *nn)
> > > for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
> > > list_move(l->freeme.next, &dispose);
> > > spin_unlock(&l->lock);
> > > - if (!list_empty(&l->freeme))
> > > + if (!list_empty(&l->freeme)) {
> > > + int srcu_idx;
> > > + struct svc_serv *serv = nfsd_serv_get(nn, &srcu_idx);
> > > /* Wake up another thread to share the work
> > > * *before* doing any actual disposing.
> > > */
> > > - svc_wake_up(nn->nfsd_serv);
> > > + svc_wake_up(serv);
> > > + nfsd_serv_put(nn, srcu_idx);
> > > + }
> > > nfsd_file_dispose_list(&dispose);
> > > }
> > > }
> > > diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
> > > index 0c5a1d97e4ac..92d0d0883f17 100644
> > > --- a/fs/nfsd/netns.h
> > > +++ b/fs/nfsd/netns.h
> > > @@ -139,8 +139,14 @@ struct nfsd_net {
> > > u32 clverifier_counter;
> > >
> > > struct svc_info nfsd_info;
> > > -#define nfsd_serv nfsd_info.serv
> > > -
> > > + /*
> > > + * The current 'nfsd_serv' at nfsd_info.serv. Using 'void' rather than
> > > + * 'struct svc_serv' to guard against new code dereferencing nfsd_serv
> > > + * without using proper synchronization.
> > > + * Use nfsd_serv_get() or take nfsd_mutex to dereference.
> > > + */
> > > + void __rcu *nfsd_serv;
> > > + struct srcu_struct nfsd_serv_srcu;
> >
> > I'm still not sold on the use of a void pointer here. It might protect
> > you from using nn->nfsd_serv directly, but if you do:
> >
> > struct svc_serv *serv = nn->nfsd_serv;
> >
> > ...that will still work. If you really want to guard against direct
> > dereferencing, maybe it should be an unsigned long? Then you really
> > will have to cast to use it.
>
> I agree. The point of the "__rcu" attribute is that sparse will
> complain if you use the pointer without using srcu_dereference().
> And CONFIG_PROVE_RCU gives you run-time splats.
> We should use the tools we already have.
Good news, I've switched from using SRCU to a percpu-refcount. So v8
will be considerably cleaner (less shotgun blast due to dropping the
excessive churn from SRCU prep and implementation).
SRCU would've enabled us to drop the client notifier spinlock, and
maybe more but certianly best to avoid all the SRCU changes.
Mike
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 18/20] nfsd/localio: use SRCU to dereference nn->nfsd_serv in nfsd_open_local_fh
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (16 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 17/20] nfsd: " Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-24 16:27 ` [PATCH v7 19/20] nfs: add Documentation/filesystems/nfs/localio.rst Mike Snitzer
` (2 subsequent siblings)
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
Use nfsd_serv_get to SRCU deference nn->nfsd_serv and pass the
resulting svc_serv to nfsd_local_fakerqst_create, open the file handle
and then drop the reference using nfsd_serv_put at the end of
nfsd_open_local_fh.
Verified to fix an easy to hit crash that would occur if an nfsd
instance running in a container, with a localio client mounted, is
shutdown. Upon restart of the container and associated nfsd the client
would go on to crash due to NULL pointer dereference that occuured due
to the nfs client's localio attempting to nfsd_open_local_fh(), using
nn->nfsd_serv, without having a proper reference on nn->nfsd_serv.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfsd/localio.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index aaa5293eb352..4c54905dca14 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -191,6 +191,7 @@ int nfsd_open_local_fh(struct net *net,
struct nfsd_file *nf;
int status = 0;
int mayflags = NFSD_MAY_LOCALIO;
+ int srcu_idx;
struct svc_serv *serv;
__be32 beres;
@@ -205,7 +206,7 @@ int nfsd_open_local_fh(struct net *net,
}
nn = net_generic(net, nfsd_net_id);
- serv = READ_ONCE(nn->nfsd_serv);
+ serv = nfsd_serv_get(nn, &srcu_idx);
if (unlikely(!serv)) {
dprintk("%s: localio denied. Server not running\n", __func__);
status = -ENXIO;
@@ -245,6 +246,7 @@ int nfsd_open_local_fh(struct net *net,
out_revertcred:
revert_creds(save_cred);
out_net:
+ nfsd_serv_put(nn, srcu_idx);
put_net(net);
return status;
}
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* [PATCH v7 19/20] nfs: add Documentation/filesystems/nfs/localio.rst
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (17 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 18/20] nfsd/localio: use SRCU to dereference nn->nfsd_serv in nfsd_open_local_fh Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 11:59 ` Jeff Layton
2024-06-24 16:27 ` [PATCH v7 20/20] nfs/nfsd: add Kconfig options to allow localio to be enabled Mike Snitzer
2024-06-25 12:49 ` [PATCH v7 00/20] nfs/nfsd: add support for localio Jeff Layton
20 siblings, 1 reply; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
This document gives an overview of the LOCALIO auxiliary RPC protocol
added to the Linux NFS client and server (both v3 and v4) to allow a
client and server to reliably handshake to determine if they are on the
same host. The LOCALIO auxiliary protocol's implementation, which uses
the same connection as NFS traffic, follows the pattern established by
the NFS ACL protocol extension.
The robust handshake between local client and server is just the
beginning, the ultimate usecase this locality makes possible is the
client is able to issue reads, writes and commits directly to the server
without having to go over the network. This is particularly useful for
container usecases (e.g. kubernetes) where it is possible to run an IO
job local to the server.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
Documentation/filesystems/nfs/localio.rst | 134 ++++++++++++++++++++++
include/linux/nfslocalio.h | 2 +
2 files changed, 136 insertions(+)
create mode 100644 Documentation/filesystems/nfs/localio.rst
diff --git a/Documentation/filesystems/nfs/localio.rst b/Documentation/filesystems/nfs/localio.rst
new file mode 100644
index 000000000000..e856b6273e78
--- /dev/null
+++ b/Documentation/filesystems/nfs/localio.rst
@@ -0,0 +1,134 @@
+===========
+NFS localio
+===========
+
+This document gives an overview of the LOCALIO auxiliary RPC protocol
+added to the Linux NFS client and server (both v3 and v4) to allow a
+client and server to reliably handshake to determine if they are on the
+same host. The LOCALIO auxiliary protocol's implementation, which uses
+the same connection as NFS traffic, follows the pattern established by
+the NFS ACL protocol extension.
+
+The LOCALIO auxiliary protocol is needed to allow robust discovery of
+clients local to their servers. Prior to this LOCALIO protocol a
+fragile sockaddr network address based match against all local network
+interfaces was attempted. But unlike the LOCALIO protocol, the
+sockaddr-based matching didn't handle use of iptables or containers.
+
+The robust handshake between local client and server is just the
+beginning, the ultimate usecase this locality makes possible is the
+client is able to issue reads, writes and commits directly to the server
+without having to go over the network. This is particularly useful for
+container usecases (e.g. kubernetes) where it is possible to run an IO
+job local to the server.
+
+The performance advantage realized from localio's ability to bypass
+using XDR and RPC for reads, writes and commits can be extreme, e.g.:
+fio for 20 secs with 24 libaio threads, 64k directio reads, qd of 8,
+- With localio:
+ read: IOPS=691k, BW=42.2GiB/s (45.3GB/s)(843GiB/20002msec)
+- Without localio:
+ read: IOPS=15.7k, BW=984MiB/s (1032MB/s)(19.2GiB/20013msec)
+
+RPC
+---
+
+The LOCALIO auxiliary RPC protocol consists of a single "GETUUID" RPC
+method that allows the Linux NFS client to retrieve a Linux NFS server's
+uuid. This protocol isn't part of an IETF standard, nor does it need to
+be considering it is Linux-to-Linux auxiliary RPC protocol that amounts
+to an implementation detail.
+
+The GETUUID method encodes the server's uuid_t in terms of the fixed
+UUID_SIZE (16 bytes). The fixed size opaque encode and decode XDR
+methods are used instead of the less efficient variable sized methods.
+
+The RPC program number for the NFS_LOCALIO_PROGRAM is 400122 (as assigned
+by IANA, see https://www.iana.org/assignments/rpc-program-numbers/ ):
+Linux Kernel Organization 400122 nfslocalio
+
+The LOCALIO protocol spec in rpcgen syntax is:
+
+/* raw RFC 9562 UUID */
+#define UUID_SIZE 16
+typedef u8 uuid_t<UUID_SIZE>;
+
+program NFS_LOCALIO_PROGRAM {
+ version LOCALIO_V1 {
+ void
+ NULL(void) = 0;
+
+ uuid_t
+ GETUUID(void) = 1;
+ } = 1;
+} = 400122;
+
+LOCALIO uses the same transport connection as NFS traffic. As such,
+LOCALIO is not registered with rpcbind.
+
+Once an NFS client and server handshake as "local", the client will
+bypass the network RPC protocol for read, write and commit operations.
+Due to this XDR and RPC bypass, these operations will operate faster.
+
+NFS Common and Server
+---------------------
+
+First use is in nfsd, to add access to a global nfsd_uuids list in
+nfs_common that is used to register and then identify local nfsd
+instances.
+
+nfsd_uuids is protected by the nfsd_mutex or RCU read lock and is
+composed of nfsd_uuid_t instances that are managed as nfsd creates them
+(per network namespace).
+
+nfsd_uuid_is_local() and nfsd_uuid_lookup() are used to search all local
+nfsd for the client specified nfsd uuid.
+
+The nfsd_uuids list is the basis for localio enablement, as such it has
+members that point to nfsd memory for direct use by the client
+(e.g. 'net' is the server's network namespace, through it the client can
+access nn->nfsd_serv with proper rcu read access). It is this client
+and server synchronization that enables advanced usage and lifetime of
+objects to span from the host kernel's nfsd to per-container knfsd
+instances that are connected to nfs client's running on the same local
+host.
+
+NFS Client
+----------
+
+fs/nfs/localio.c:nfs_local_probe() will retrieve a server's uuid via
+LOCALIO protocol and check if the server with that uuid is known to be
+local. This ensures client and server 1: support localio 2: are local
+to each other.
+
+See fs/nfs/localio.c:nfs_local_open_fh() and
+fs/nfsd/localio.c:nfsd_open_local_fh() for the interface that makes
+focused use of nfsd_uuid_t struct to allow a client local to a server to
+open a file pointer without needing to go over the network.
+
+The client's fs/nfs/localio.c:nfs_local_open_fh() will call into the
+server's fs/nfsd/localio.c:nfsd_open_local_fh() and carefully access
+both the nfsd network namespace and the associated nn->nfsd_serv in
+terms of RCU. If nfsd_open_local_fh() finds that client no longer sees
+valid nfsd objects (be it struct net or nn->nfsd_serv) it returns ENXIO
+to nfs_local_open_fh() and the client will try to reestablish the
+LOCALIO resources needed by calling nfs_local_probe() again. This
+recovery is needed if/when an nfsd instance running in a container were
+to reboot while a localio client is connected to it.
+
+Testing
+-------
+
+The LOCALIO auxiliary protocol and associated NFS localio read, write
+and commit access have proven stable against various test scenarios but
+these have not yet been formalized in any testsuite:
+
+- Client and server both on localhost (for both v3 and v4.2).
+
+- Various permutations of client and server support enablement for
+ both local and remote client and server. Testing against NFS storage
+ products that don't support the LOCALIO protocol was also performed.
+
+- Client on host, server within a container (for both v3 and v4.2)
+ The container testing was in terms of podman managed containers and
+ includes container stop/restart scenario.
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index c9592ad0afe2..a9722e18b527 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -20,6 +20,8 @@ extern struct list_head nfsd_uuids;
* Each nfsd instance has an nfsd_uuid_t that is accessible through the
* global nfsd_uuids list. Useful to allow a client to negotiate if localio
* possible with its server.
+ *
+ * See Documentation/filesystems/nfs/localio.rst for more detail.
*/
typedef struct {
uuid_t uuid;
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 19/20] nfs: add Documentation/filesystems/nfs/localio.rst
2024-06-24 16:27 ` [PATCH v7 19/20] nfs: add Documentation/filesystems/nfs/localio.rst Mike Snitzer
@ 2024-06-25 11:59 ` Jeff Layton
0 siblings, 0 replies; 40+ messages in thread
From: Jeff Layton @ 2024-06-25 11:59 UTC (permalink / raw)
To: Mike Snitzer, linux-nfs; +Cc: Chuck Lever, Trond Myklebust, NeilBrown, snitzer
On Mon, 2024-06-24 at 12:27 -0400, Mike Snitzer wrote:
> This document gives an overview of the LOCALIO auxiliary RPC protocol
> added to the Linux NFS client and server (both v3 and v4) to allow a
> client and server to reliably handshake to determine if they are on the
> same host. The LOCALIO auxiliary protocol's implementation, which uses
> the same connection as NFS traffic, follows the pattern established by
> the NFS ACL protocol extension.
>
> The robust handshake between local client and server is just the
> beginning, the ultimate usecase this locality makes possible is the
> client is able to issue reads, writes and commits directly to the server
> without having to go over the network. This is particularly useful for
> container usecases (e.g. kubernetes) where it is possible to run an IO
> job local to the server.
>
> Signed-off-by: Mike Snitzer <snitzer@kernel.org>
> ---
> Documentation/filesystems/nfs/localio.rst | 134 ++++++++++++++++++++++
> include/linux/nfslocalio.h | 2 +
> 2 files changed, 136 insertions(+)
> create mode 100644 Documentation/filesystems/nfs/localio.rst
>
> diff --git a/Documentation/filesystems/nfs/localio.rst b/Documentation/filesystems/nfs/localio.rst
> new file mode 100644
> index 000000000000..e856b6273e78
> --- /dev/null
> +++ b/Documentation/filesystems/nfs/localio.rst
> @@ -0,0 +1,134 @@
> +===========
> +NFS localio
> +===========
> +
> +This document gives an overview of the LOCALIO auxiliary RPC protocol
> +added to the Linux NFS client and server (both v3 and v4) to allow a
> +client and server to reliably handshake to determine if they are on the
> +same host. The LOCALIO auxiliary protocol's implementation, which uses
> +the same connection as NFS traffic, follows the pattern established by
> +the NFS ACL protocol extension.
> +
> +The LOCALIO auxiliary protocol is needed to allow robust discovery of
> +clients local to their servers. Prior to this LOCALIO protocol a
> +fragile sockaddr network address based match against all local network
> +interfaces was attempted. But unlike the LOCALIO protocol, the
> +sockaddr-based matching didn't handle use of iptables or containers.
> +
The above paragraph sounds like there was an earlier implementation in
mainline kernels that used address matching. It might be good to point
out that that was a private implementation.
> +The robust handshake between local client and server is just the
> +beginning, the ultimate usecase this locality makes possible is the
> +client is able to issue reads, writes and commits directly to the server
> +without having to go over the network. This is particularly useful for
> +container usecases (e.g. kubernetes) where it is possible to run an IO
> +job local to the server.
> +
> +The performance advantage realized from localio's ability to bypass
> +using XDR and RPC for reads, writes and commits can be extreme, e.g.:
> +fio for 20 secs with 24 libaio threads, 64k directio reads, qd of 8,
> +- With localio:
> + read: IOPS=691k, BW=42.2GiB/s (45.3GB/s)(843GiB/20002msec)
> +- Without localio:
> + read: IOPS=15.7k, BW=984MiB/s (1032MB/s)(19.2GiB/20013msec)
> +
> +RPC
> +---
> +
> +The LOCALIO auxiliary RPC protocol consists of a single "GETUUID" RPC
> +method that allows the Linux NFS client to retrieve a Linux NFS server's
> +uuid. This protocol isn't part of an IETF standard, nor does it need to
> +be considering it is Linux-to-Linux auxiliary RPC protocol that amounts
> +to an implementation detail.
> +
> +The GETUUID method encodes the server's uuid_t in terms of the fixed
> +UUID_SIZE (16 bytes). The fixed size opaque encode and decode XDR
> +methods are used instead of the less efficient variable sized methods.
> +
> +The RPC program number for the NFS_LOCALIO_PROGRAM is 400122 (as assigned
> +by IANA, see https://www.iana.org/assignments/rpc-program-numbers/ ):
> +Linux Kernel Organization 400122 nfslocalio
> +
Nice! Glad this got officially registered fast.
> +The LOCALIO protocol spec in rpcgen syntax is:
> +
> +/* raw RFC 9562 UUID */
> +#define UUID_SIZE 16
> +typedef u8 uuid_t<UUID_SIZE>;
> +
> +program NFS_LOCALIO_PROGRAM {
> + version LOCALIO_V1 {
> + void
> + NULL(void) = 0;
> +
> + uuid_t
> + GETUUID(void) = 1;
> + } = 1;
> +} = 400122;
> +
> +LOCALIO uses the same transport connection as NFS traffic. As such,
> +LOCALIO is not registered with rpcbind.
> +
> +Once an NFS client and server handshake as "local", the client will
> +bypass the network RPC protocol for read, write and commit operations.
> +Due to this XDR and RPC bypass, these operations will operate faster.
> +
> +NFS Common and Server
> +---------------------
> +
> +First use is in nfsd, to add access to a global nfsd_uuids list in
> +nfs_common that is used to register and then identify local nfsd
> +instances.
> +
First use of what? This sentence doesn't parse well.
> +nfsd_uuids is protected by the nfsd_mutex or RCU read lock and is
> +composed of nfsd_uuid_t instances that are managed as nfsd creates them
> +(per network namespace).
> +
> +nfsd_uuid_is_local() and nfsd_uuid_lookup() are used to search all local
> +nfsd for the client specified nfsd uuid.
> +
> +The nfsd_uuids list is the basis for localio enablement, as such it has
> +members that point to nfsd memory for direct use by the client
> +(e.g. 'net' is the server's network namespace, through it the client can
> +access nn->nfsd_serv with proper rcu read access). It is this client
> +and server synchronization that enables advanced usage and lifetime of
> +objects to span from the host kernel's nfsd to per-container knfsd
> +instances that are connected to nfs client's running on the same local
> +host.
> +
> +NFS Client
> +----------
> +
> +fs/nfs/localio.c:nfs_local_probe() will retrieve a server's uuid via
> +LOCALIO protocol and check if the server with that uuid is known to be
> +local. This ensures client and server 1: support localio 2: are local
> +to each other.
> +
> +See fs/nfs/localio.c:nfs_local_open_fh() and
> +fs/nfsd/localio.c:nfsd_open_local_fh() for the interface that makes
> +focused use of nfsd_uuid_t struct to allow a client local to a server to
> +open a file pointer without needing to go over the network.
> +
> +The client's fs/nfs/localio.c:nfs_local_open_fh() will call into the
> +server's fs/nfsd/localio.c:nfsd_open_local_fh() and carefully access
> +both the nfsd network namespace and the associated nn->nfsd_serv in
> +terms of RCU. If nfsd_open_local_fh() finds that client no longer sees
> +valid nfsd objects (be it struct net or nn->nfsd_serv) it returns ENXIO
> +to nfs_local_open_fh() and the client will try to reestablish the
> +LOCALIO resources needed by calling nfs_local_probe() again. This
> +recovery is needed if/when an nfsd instance running in a container were
> +to reboot while a localio client is connected to it.
> +
> +Testing
> +-------
> +
> +The LOCALIO auxiliary protocol and associated NFS localio read, write
> +and commit access have proven stable against various test scenarios but
> +these have not yet been formalized in any testsuite:
> +
> +- Client and server both on localhost (for both v3 and v4.2).
> +
> +- Various permutations of client and server support enablement for
> + both local and remote client and server. Testing against NFS storage
> + products that don't support the LOCALIO protocol was also performed.
> +
> +- Client on host, server within a container (for both v3 and v4.2)
> + The container testing was in terms of podman managed containers and
> + includes container stop/restart scenario.
> diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
> index c9592ad0afe2..a9722e18b527 100644
> --- a/include/linux/nfslocalio.h
> +++ b/include/linux/nfslocalio.h
> @@ -20,6 +20,8 @@ extern struct list_head nfsd_uuids;
> * Each nfsd instance has an nfsd_uuid_t that is accessible through the
> * global nfsd_uuids list. Useful to allow a client to negotiate if localio
> * possible with its server.
> + *
> + * See Documentation/filesystems/nfs/localio.rst for more detail.
> */
> typedef struct {
> uuid_t uuid;
--
Jeff Layton <jlayton@kernel.org>
^ permalink raw reply [flat|nested] 40+ messages in thread
* [PATCH v7 20/20] nfs/nfsd: add Kconfig options to allow localio to be enabled
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (18 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 19/20] nfs: add Documentation/filesystems/nfs/localio.rst Mike Snitzer
@ 2024-06-24 16:27 ` Mike Snitzer
2024-06-25 12:49 ` [PATCH v7 00/20] nfs/nfsd: add support for localio Jeff Layton
20 siblings, 0 replies; 40+ messages in thread
From: Mike Snitzer @ 2024-06-24 16:27 UTC (permalink / raw)
To: linux-nfs; +Cc: Jeff Layton, Chuck Lever, Trond Myklebust, NeilBrown, snitzer
Now that all the localio code is complete, allow users to enable it.
CONFIG_NFS_LOCALIO controls the client enablement and
CONFIG_NFSD_LOCALIO the server enablement.
While it is true that it doesn't make sense, on a using LOCALIO level,
to have one without the other: it is useful to allow a mix be
configured for testing purposes. It could be that the same control
could be achieved by exposing a discrete "localio_enabled"
module_param in the server (nfsd.ko) like is already available in the
client (nfs.ko).
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/Kconfig | 3 +++
fs/nfs/Kconfig | 14 ++++++++++++++
fs/nfsd/Kconfig | 14 ++++++++++++++
3 files changed, 31 insertions(+)
diff --git a/fs/Kconfig b/fs/Kconfig
index a46b0cbc4d8f..170083ff2a51 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -377,6 +377,9 @@ config NFS_ACL_SUPPORT
tristate
select FS_POSIX_ACL
+config NFS_COMMON_LOCALIO_SUPPORT
+ tristate
+
config NFS_COMMON
bool
depends on NFSD || NFS_FS || LOCKD
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 57249f040dfc..311ae8bc587f 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -86,6 +86,20 @@ config NFS_V4
If unsure, say Y.
+config NFS_LOCALIO
+ tristate "NFS client support for the LOCALIO auxiliary protocol"
+ depends on NFS_V3 || NFS_V4
+ select NFS_COMMON_LOCALIO_SUPPORT
+ help
+ Some NFS servers support an auxiliary NFS LOCALIO protocol
+ that is not an official part of the NFS version 3 or 4 protocol.
+
+ This option enables support for the LOCALIO protocol in the
+ kernel's NFS client. Enable this to bypass using the NFS
+ protocol when issuing reads, writes and commits to the server.
+
+ If unsure, say N.
+
config NFS_SWAP
bool "Provide swap over NFS support"
default n
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index ec2ab6429e00..a36ff66c7430 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -89,6 +89,20 @@ config NFSD_V4
If unsure, say N.
+config NFSD_LOCALIO
+ tristate "NFS server support for the LOCALIO auxiliary protocol"
+ depends on NFSD || NFSD_V4
+ select NFS_COMMON_LOCALIO_SUPPORT
+ help
+ Some NFS servers support an auxiliary NFS LOCALIO protocol
+ that is not an official part of the NFS version 3 or 4 protocol.
+
+ This option enables support for the LOCALIO protocol in the
+ kernel's NFS server. Enable this to bypass using the NFS
+ protocol when issuing reads, writes and commits to the server.
+
+ If unsure, say N.
+
config NFSD_PNFS
bool
--
2.44.0
^ permalink raw reply related [flat|nested] 40+ messages in thread* Re: [PATCH v7 00/20] nfs/nfsd: add support for localio
2024-06-24 16:27 [PATCH v7 00/20] nfs/nfsd: add support for localio Mike Snitzer
` (19 preceding siblings ...)
2024-06-24 16:27 ` [PATCH v7 20/20] nfs/nfsd: add Kconfig options to allow localio to be enabled Mike Snitzer
@ 2024-06-25 12:49 ` Jeff Layton
20 siblings, 0 replies; 40+ messages in thread
From: Jeff Layton @ 2024-06-25 12:49 UTC (permalink / raw)
To: Mike Snitzer, linux-nfs; +Cc: Chuck Lever, Trond Myklebust, NeilBrown, snitzer
On Mon, 2024-06-24 at 12:27 -0400, Mike Snitzer wrote:
> Hi,
>
> IANA has assigned the RPC program number 400122 for localio!
>
> Tested with xfstests, all is passing agsint NFS v3 and v4.2 (localio
> ontop of XFS) except generic/355 (which tests if suid bit gets
> cleared
> with directio).
>
> My git tree is here:
> https://git.kernel.org/pub/scm/linux/kernel/git/snitzer/linux.git/
>
> This v7 is both branch nfs-localio-for-6.11 (always tracks latest)
> and nfs-localio-for-6.11.v7
>
> Quite a bit has changed since v6:
> - Updated to use IANA assigned RPC program number 400122.
> - Thanks to Neil the localio protocol stands on its own and is
> simplified, all of Neil's changes were included. But a patch is
> needed to sunrpc to remove the BUG_ON if p_arglen is 0 (otherwise
> the NULL rpc used during connection triggers the BUG_ON.
> - Reduced Kconfig knobs down to NFS_LOCALIO and NFSD_LOCALIO. Left
> them piece-wise for reason detailed in the last patch.
> - Added MODULE_DESCRIPTION to nfs_localio module.
> - Removed all the AIO directio code from fs/nfs/localio.c because it
> wasn't used (since nothing ever set NFS_IOHDR_ODIRECT). But even
> if
> enabled the async kiocb completion wasn't ever used in practice.
>
> TODO:
> - For directio, fix kiocb so that it conveys IOCB_DIRECT to
> underlying
> filesystem.
> - Must fix xfstests generic/355.
> - Look closer at implementing standlone SRCU to avoid bloating
> nfsd_net -- idea of shared SRCU is very unintuitive to me...
>
> FYI:
> - Really rather not play games with 'localio_enabled' to get all of
> localio code to build but be disabled by default.. just too
> fiddley.
>
> All review and comments are welcome!
>
> Thanks,
> Mike
>
> Mike Snitzer (11):
> nfs_common: add NFS LOCALIO auxiliary protocol enablement
> nfsd/localio: manage netns reference in nfsd_open_local_fh
> nfs/nfsd: factor out {encode,decode}_opaque_fixed to nfs_xdr.h
> SUNRPC: remove call_allocate() BUG_ON if p_arglen=0 to allow RPC
> with void arg
> nfs: implement client support for NFS_LOCALIO_PROGRAM
> nfsd: implement server support for NFS_LOCALIO_PROGRAM
> nfsd: prepare to use SRCU to dereference nn->nfsd_serv
> nfsd: use SRCU to dereference nn->nfsd_serv
> nfsd/localio: use SRCU to dereference nn->nfsd_serv in
> nfsd_open_local_fh
> nfs: add Documentation/filesystems/nfs/localio.rst
> nfs/nfsd: add Kconfig options to allow localio to be enabled
>
> NeilBrown (1):
> SUNRPC: replace program list with program array
>
> Trond Myklebust (3):
> NFS: Enable localio for non-pNFS I/O
> pnfs/flexfiles: Enable localio for flexfiles I/O
> nfs/localio: use dedicated workqueues for filesystem read and write
>
> Weston Andros Adamson (5):
> nfs: pass nfs_client to nfs_initiate_pgio
> nfs: pass descriptor thru nfs_initiate_pgio path
> nfs: pass struct file to nfs_init_pgio and nfs_init_commit
> sunrpc: add rpcauth_map_to_svc_cred_local
> nfs/nfsd: add "localio" support
>
> Documentation/filesystems/nfs/localio.rst | 134 ++++
> fs/Kconfig | 3 +
> fs/nfs/Kconfig | 14 +
> fs/nfs/Makefile | 1 +
> fs/nfs/blocklayout/blocklayout.c | 6 +-
> fs/nfs/client.c | 15 +-
> fs/nfs/filelayout/filelayout.c | 16 +-
> fs/nfs/flexfilelayout/flexfilelayout.c | 131 +++-
> fs/nfs/flexfilelayout/flexfilelayout.h | 2 +
> fs/nfs/flexfilelayout/flexfilelayoutdev.c | 6 +
> fs/nfs/inode.c | 61 +-
> fs/nfs/internal.h | 61 +-
> fs/nfs/localio.c | 851
> ++++++++++++++++++++++
> fs/nfs/nfs4xdr.c | 13 -
> fs/nfs/nfstrace.h | 61 ++
> fs/nfs/pagelist.c | 32 +-
> fs/nfs/pnfs.c | 24 +-
> fs/nfs/pnfs.h | 6 +-
> fs/nfs/pnfs_nfs.c | 2 +-
> fs/nfs/write.c | 13 +-
> fs/nfs_common/Makefile | 3 +
> fs/nfs_common/nfslocalio.c | 72 ++
> fs/nfsd/Kconfig | 14 +
> fs/nfsd/Makefile | 1 +
> fs/nfsd/filecache.c | 15 +-
> fs/nfsd/localio.c | 327 +++++++++
> fs/nfsd/netns.h | 18 +-
> fs/nfsd/nfs4state.c | 25 +-
> fs/nfsd/nfsctl.c | 30 +-
> fs/nfsd/nfsd.h | 2 +-
> fs/nfsd/nfssvc.c | 165 +++--
> fs/nfsd/trace.h | 3 +-
> fs/nfsd/vfs.h | 9 +
> include/linux/nfs.h | 9 +
> include/linux/nfs_fs.h | 2 +
> include/linux/nfs_fs_sb.h | 10 +
> include/linux/nfs_xdr.h | 20 +-
> include/linux/nfslocalio.h | 41 ++
> include/linux/sunrpc/auth.h | 4 +
> include/linux/sunrpc/svc.h | 7 +-
> net/sunrpc/auth.c | 15 +
> net/sunrpc/clnt.c | 1 -
> net/sunrpc/svc.c | 68 +-
> net/sunrpc/svc_xprt.c | 2 +-
> net/sunrpc/svcauth_unix.c | 3 +-
> 45 files changed, 2116 insertions(+), 202 deletions(-)
> create mode 100644 Documentation/filesystems/nfs/localio.rst
> create mode 100644 fs/nfs/localio.c
> create mode 100644 fs/nfs_common/nfslocalio.c
> create mode 100644 fs/nfsd/localio.c
> create mode 100644 include/linux/nfslocalio.h
>
This is looking pretty good now! I know Chuck noted some nits and I'm
still hung up on the making nfsd_serv a void *, but I don't see it as a
show stopper and we can always fix that later. You can add:
Reviewed-by: Jeff Layton <jlayton@kernel.org>
^ permalink raw reply [flat|nested] 40+ messages in thread