summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/filesystems/nfs/index.rst1
-rw-r--r--Documentation/filesystems/nfs/localio.rst357
-rw-r--r--fs/Kconfig23
-rw-r--r--fs/nfs/Kconfig1
-rw-r--r--fs/nfs/Makefile1
-rw-r--r--fs/nfs/client.c21
-rw-r--r--fs/nfs/dir.c6
-rw-r--r--fs/nfs/filelayout/filelayout.c6
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c56
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c6
-rw-r--r--fs/nfs/fs_context.c8
-rw-r--r--fs/nfs/getroot.c2
-rw-r--r--fs/nfs/inode.c53
-rw-r--r--fs/nfs/internal.h54
-rw-r--r--fs/nfs/localio.c757
-rw-r--r--fs/nfs/nfs2xdr.c70
-rw-r--r--fs/nfs/nfs3xdr.c108
-rw-r--r--fs/nfs/nfs4_fs.h2
-rw-r--r--fs/nfs/nfs4proc.c16
-rw-r--r--fs/nfs/nfs4state.c22
-rw-r--r--fs/nfs/nfs4xdr.c90
-rw-r--r--fs/nfs/nfstrace.h61
-rw-r--r--fs/nfs/pagelist.c16
-rw-r--r--fs/nfs/pnfs_nfs.c2
-rw-r--r--fs/nfs/read.c3
-rw-r--r--fs/nfs/super.c3
-rw-r--r--fs/nfs/write.c21
-rw-r--r--fs/nfs_common/Makefile5
-rw-r--r--fs/nfs_common/common.c134
-rw-r--r--fs/nfs_common/nfslocalio.c172
-rw-r--r--fs/nfsd/Kconfig1
-rw-r--r--fs/nfsd/Makefile1
-rw-r--r--fs/nfsd/export.c30
-rw-r--r--fs/nfsd/filecache.c101
-rw-r--r--fs/nfsd/filecache.h5
-rw-r--r--fs/nfsd/localio.c169
-rw-r--r--fs/nfsd/netns.h12
-rw-r--r--fs/nfsd/nfsctl.c27
-rw-r--r--fs/nfsd/nfsd.h6
-rw-r--r--fs/nfsd/nfsfh.c137
-rw-r--r--fs/nfsd/nfsfh.h2
-rw-r--r--fs/nfsd/nfssvc.c105
-rw-r--r--fs/nfsd/trace.h21
-rw-r--r--fs/nfsd/vfs.h2
-rw-r--r--include/linux/nfs.h9
-rw-r--r--include/linux/nfs_common.h17
-rw-r--r--include/linux/nfs_fs_sb.h13
-rw-r--r--include/linux/nfs_xdr.h22
-rw-r--r--include/linux/nfslocalio.h74
-rw-r--r--include/linux/sunrpc/sched.h16
-rw-r--r--include/linux/sunrpc/svc.h7
-rw-r--r--include/linux/sunrpc/svcauth.h5
-rw-r--r--net/sunrpc/cache.c10
-rw-r--r--net/sunrpc/clnt.c13
-rw-r--r--net/sunrpc/svc.c68
-rw-r--r--net/sunrpc/svc_xprt.c2
-rw-r--r--net/sunrpc/svcauth.c28
-rw-r--r--net/sunrpc/svcauth_unix.c3
58 files changed, 2519 insertions, 464 deletions
diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst
index 8536134f31fd..95c2c009874c 100644
--- a/Documentation/filesystems/nfs/index.rst
+++ b/Documentation/filesystems/nfs/index.rst
@@ -8,6 +8,7 @@ NFS
client-identifier
exporting
+ localio
pnfs
rpc-cache
rpc-server-gss
diff --git a/Documentation/filesystems/nfs/localio.rst b/Documentation/filesystems/nfs/localio.rst
new file mode 100644
index 000000000000..bd1967e2eab3
--- /dev/null
+++ b/Documentation/filesystems/nfs/localio.rst
@@ -0,0 +1,357 @@
+===========
+NFS LOCALIO
+===========
+
+Overview
+========
+
+The LOCALIO auxiliary RPC protocol allows the Linux NFS client and
+server to reliably handshake to determine if they are on the same
+host. Select "NFS client and server support for LOCALIO auxiliary
+protocol" in menuconfig to enable CONFIG_NFS_LOCALIO in the kernel
+config (both CONFIG_NFS_FS and CONFIG_NFSD must also be enabled).
+
+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.
+
+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. In a private implementation that
+preceded use of 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 use case this locality makes possible is the
+client is able to open files and issue reads, writes and commits
+directly to the server without having to go over the network. The
+requirement is to perform these loopback NFS operations as efficiently
+as possible, this is particularly useful for container use cases
+(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 directio, qd of 8, 16 libaio threads:
+ - With LOCALIO:
+ 4K read: IOPS=979k, BW=3825MiB/s (4011MB/s)(74.7GiB/20002msec)
+ 4K write: IOPS=165k, BW=646MiB/s (678MB/s)(12.6GiB/20002msec)
+ 128K read: IOPS=402k, BW=49.1GiB/s (52.7GB/s)(982GiB/20002msec)
+ 128K write: IOPS=11.5k, BW=1433MiB/s (1503MB/s)(28.0GiB/20004msec)
+
+ - Without LOCALIO:
+ 4K read: IOPS=79.2k, BW=309MiB/s (324MB/s)(6188MiB/20003msec)
+ 4K write: IOPS=59.8k, BW=234MiB/s (245MB/s)(4671MiB/20002msec)
+ 128K read: IOPS=33.9k, BW=4234MiB/s (4440MB/s)(82.7GiB/20004msec)
+ 128K write: IOPS=11.5k, BW=1434MiB/s (1504MB/s)(28.0GiB/20011msec)
+
+fio for 20 secs with directio, qd of 8, 1 libaio thread:
+ - With LOCALIO:
+ 4K read: IOPS=230k, BW=898MiB/s (941MB/s)(17.5GiB/20001msec)
+ 4K write: IOPS=22.6k, BW=88.3MiB/s (92.6MB/s)(1766MiB/20001msec)
+ 128K read: IOPS=38.8k, BW=4855MiB/s (5091MB/s)(94.8GiB/20001msec)
+ 128K write: IOPS=11.4k, BW=1428MiB/s (1497MB/s)(27.9GiB/20001msec)
+
+ - Without LOCALIO:
+ 4K read: IOPS=77.1k, BW=301MiB/s (316MB/s)(6022MiB/20001msec)
+ 4K write: IOPS=32.8k, BW=128MiB/s (135MB/s)(2566MiB/20001msec)
+ 128K read: IOPS=24.4k, BW=3050MiB/s (3198MB/s)(59.6GiB/20001msec)
+ 128K write: IOPS=11.4k, BW=1430MiB/s (1500MB/s)(27.9GiB/20001msec)
+
+FAQ
+===
+
+1. What are the use cases for LOCALIO?
+
+ a. Workloads where the NFS client and server are on the same host
+ realize improved IO performance. In particular, it is common when
+ running containerised workloads for jobs to find themselves
+ running on the same host as the knfsd server being used for
+ storage.
+
+2. What are the requirements for LOCALIO?
+
+ a. Bypass use of the network RPC protocol as much as possible. This
+ includes bypassing XDR and RPC for open, read, write and commit
+ operations.
+ b. Allow client and server to autonomously discover if they are
+ running local to each other without making any assumptions about
+ the local network topology.
+ c. Support the use of containers by being compatible with relevant
+ namespaces (e.g. network, user, mount).
+ d. Support all versions of NFS. NFSv3 is of particular importance
+ because it has wide enterprise usage and pNFS flexfiles makes use
+ of it for the data path.
+
+3. Why doesn’t LOCALIO just compare IP addresses or hostnames when
+ deciding if the NFS client and server are co-located on the same
+ host?
+
+ Since one of the main use cases is containerised workloads, we cannot
+ assume that IP addresses will be shared between the client and
+ server. This sets up a requirement for a handshake protocol that
+ needs to go over the same connection as the NFS traffic in order to
+ identify that the client and the server really are running on the
+ same host. The handshake uses a secret that is sent over the wire,
+ and can be verified by both parties by comparing with a value stored
+ in shared kernel memory if they are truly co-located.
+
+4. Does LOCALIO improve pNFS flexfiles?
+
+ Yes, LOCALIO complements pNFS flexfiles by allowing it to take
+ advantage of NFS client and server locality. Policy that initiates
+ client IO as closely to the server where the data is stored naturally
+ benefits from the data path optimization LOCALIO provides.
+
+5. Why not develop a new pNFS layout to enable LOCALIO?
+
+ A new pNFS layout could be developed, but doing so would put the
+ onus on the server to somehow discover that the client is co-located
+ when deciding to hand out the layout.
+ There is value in a simpler approach (as provided by LOCALIO) that
+ allows the NFS client to negotiate and leverage locality without
+ requiring more elaborate modeling and discovery of such locality in a
+ more centralized manner.
+
+6. Why is having the client perform a server-side file OPEN, without
+ using RPC, beneficial? Is the benefit pNFS specific?
+
+ Avoiding the use of XDR and RPC for file opens is beneficial to
+ performance regardless of whether pNFS is used. Especially when
+ dealing with small files its best to avoid going over the wire
+ whenever possible, otherwise it could reduce or even negate the
+ benefits of avoiding the wire for doing the small file I/O itself.
+ Given LOCALIO's requirements the current approach of having the
+ client perform a server-side file open, without using RPC, is ideal.
+ If in the future requirements change then we can adapt accordingly.
+
+7. Why is LOCALIO only supported with UNIX Authentication (AUTH_UNIX)?
+
+ Strong authentication is usually tied to the connection itself. It
+ works by establishing a context that is cached by the server, and
+ that acts as the key for discovering the authorisation token, which
+ can then be passed to rpc.mountd to complete the authentication
+ process. On the other hand, in the case of AUTH_UNIX, the credential
+ that was passed over the wire is used directly as the key in the
+ upcall to rpc.mountd. This simplifies the authentication process, and
+ so makes AUTH_UNIX easier to support.
+
+8. How do export options that translate RPC user IDs behave for LOCALIO
+ operations (eg. root_squash, all_squash)?
+
+ Export options that translate user IDs are managed by nfsd_setuser()
+ which is called by nfsd_setuser_and_check_port() which is called by
+ __fh_verify(). So they get handled exactly the same way for LOCALIO
+ as they do for non-LOCALIO.
+
+9. How does LOCALIO make certain that object lifetimes are managed
+ properly given NFSD and NFS operate in different contexts?
+
+ See the detailed "NFS Client and Server Interlock" section below.
+
+RPC
+===
+
+The LOCALIO auxiliary RPC protocol consists of a single "UUID_IS_LOCAL"
+RPC method that allows the Linux NFS client to verify the local Linux
+NFS server can see the nonce (single-use UUID) the client generated and
+made available in nfs_common. 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 UUID_IS_LOCAL method encodes the client generated 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;
+
+ void
+ UUID_IS_LOCAL(uuid_t) = 1;
+ } = 1;
+ } = 400122;
+
+LOCALIO uses the same transport connection as NFS traffic. As such,
+LOCALIO is not registered with rpcbind.
+
+NFS Common and Client/Server Handshake
+======================================
+
+fs/nfs_common/nfslocalio.c provides interfaces that enable an NFS client
+to generate a nonce (single-use UUID) and associated short-lived
+nfs_uuid_t struct, register it with nfs_common for subsequent lookup and
+verification by the NFS server and if matched the NFS server populates
+members in the nfs_uuid_t struct. The NFS client then uses nfs_common to
+transfer the nfs_uuid_t from its nfs_uuids to the nn->nfsd_serv
+clients_list from the nfs_common's uuids_list. See:
+fs/nfs/localio.c:nfs_local_probe()
+
+nfs_common's nfs_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 and Server Interlock
+===============================
+
+LOCALIO provides the nfs_uuid_t object and associated interfaces to
+allow proper network namespace (net-ns) and NFSD object refcounting:
+
+ We don't want to keep a long-term counted reference on each NFSD's
+ net-ns in the client because that prevents a server container from
+ completely shutting down.
+
+ So we avoid taking a reference at all and rely on the per-cpu
+ reference to the server (detailed below) being sufficient to keep
+ the net-ns active. This involves allowing the NFSD's net-ns exit
+ code to iterate all active clients and clear their ->net pointers
+ (which are needed to find the per-cpu-refcount for the nfsd_serv).
+
+ Details:
+
+ - Embed nfs_uuid_t in nfs_client. nfs_uuid_t provides a list_head
+ that can be used to find the client. It does add the 16-byte
+ uuid_t to nfs_client so it is bigger than needed (given that
+ uuid_t is only used during the initial NFS client and server
+ LOCALIO handshake to determine if they are local to each other).
+ If that is really a problem we can find a fix.
+
+ - When the nfs server confirms that the uuid_t is local, it moves
+ the nfs_uuid_t onto a per-net-ns list in NFSD's nfsd_net.
+
+ - When each server's net-ns is shutting down - in a "pre_exit"
+ handler, all these nfs_uuid_t have their ->net cleared. There is
+ an rcu_synchronize() call between pre_exit() handlers and exit()
+ handlers so any caller that sees nfs_uuid_t ->net as not NULL can
+ safely manage the per-cpu-refcount for nfsd_serv.
+
+ - The client's nfs_uuid_t is passed to nfsd_open_local_fh() so it
+ can safely dereference ->net in a private rcu_read_lock() section
+ to allow safe access to the associated nfsd_net and nfsd_serv.
+
+So LOCALIO required the introduction and use of NFSD's percpu_ref to
+interlock nfsd_destroy_serv() and nfsd_open_local_fh(), to ensure each
+nn->nfsd_serv is not destroyed while in use by nfsd_open_local_fh(), and
+warrants a more detailed explanation:
+
+ nfsd_open_local_fh() uses nfsd_serv_try_get() before opening its
+ nfsd_file handle and then the caller (NFS client) must drop the
+ reference for the nfsd_file and associated nn->nfsd_serv using
+ nfs_file_put_local() once it has completed its IO.
+
+ This interlock working relies heavily on nfsd_open_local_fh() being
+ afforded the ability to safely deal with the possibility that the
+ NFSD's net-ns (and nfsd_net by association) may have been destroyed
+ by nfsd_destroy_serv() via nfsd_shutdown_net() -- which is only
+ possible given the nfs_uuid_t ->net pointer managemenet detailed
+ above.
+
+All told, this elaborate interlock of the NFS client and server has been
+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 occurred due
+to the LOCALIO client's attempting to nfsd_open_local_fh(), using
+nn->nfsd_serv, without having a proper reference on nn->nfsd_serv.
+
+NFS Client issues IO instead of Server
+======================================
+
+Because LOCALIO is focused on protocol bypass to achieve improved IO
+performance, alternatives to the traditional NFS wire protocol (SUNRPC
+with XDR) must be provided to access the backing filesystem.
+
+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 select nfs server objects 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 associated nfsd network namespace and nn->nfsd_serv in terms of
+RCU. If nfsd_open_local_fh() finds that the 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.
+
+Once the client has an open nfsd_file pointer it will issue reads,
+writes and commits directly to the underlying local filesystem (normally
+done by the nfs server). As such, for these operations, the NFS client
+is issuing IO to the underlying local filesystem that it is sharing with
+the NFS server. See: fs/nfs/localio.c:nfs_local_doio() and
+fs/nfs/localio.c:nfs_local_commit().
+
+Security
+========
+
+Localio is only supported when UNIX-style authentication (AUTH_UNIX, aka
+AUTH_SYS) is used.
+
+Care is taken to ensure the same NFS security mechanisms are used
+(authentication, etc) regardless of whether LOCALIO or regular NFS
+access is used. The auth_domain established as part of the traditional
+NFS client access to the NFS server is also used for LOCALIO.
+
+Relative to containers, LOCALIO gives the client access to the network
+namespace the server has. This is required to allow the client to access
+the server's per-namespace nfsd_net struct. With traditional NFS, the
+client is afforded this same level of access (albeit in terms of the NFS
+protocol via SUNRPC). No other namespaces (user, mount, etc) have been
+altered or purposely extended from the server to the client.
+
+Testing
+=======
+
+The LOCALIO auxiliary protocol and associated NFS LOCALIO read, write
+and commit access have proven stable against various test scenarios:
+
+- Client and server both on the same host.
+
+- All 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 successful container stop/restart scenario.
+
+- Formalizing these test scenarios in terms of existing test
+ infrastructure is on-going. Initial regular coverage is provided in
+ terms of ktest running xfstests against a LOCALIO-enabled NFS loopback
+ mount configuration, and includes lockdep and KASAN coverage, see:
+ https://evilpiepirate.org/~testdashboard/ci?user=snitzer&branch=snitm-nfs-next
+ https://github.com/koverstreet/ktest
+
+- Various kdevops testing (in terms of "Chuck's BuildBot") has been
+ performed to regularly verify the LOCALIO changes haven't caused any
+ regressions to non-LOCALIO NFS use cases.
+
+- All of Hammerspace's various sanity tests pass with LOCALIO enabled
+ (this includes numerous pNFS and flexfiles tests).
diff --git a/fs/Kconfig b/fs/Kconfig
index 0e4efec1d92e..949895cff872 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -386,6 +386,29 @@ config NFS_COMMON
depends on NFSD || NFS_FS || LOCKD
default y
+config NFS_COMMON_LOCALIO_SUPPORT
+ tristate
+ default n
+ default y if NFSD=y || NFS_FS=y
+ default m if NFSD=m && NFS_FS=m
+ select SUNRPC
+
+config NFS_LOCALIO
+ bool "NFS client and server support for LOCALIO auxiliary protocol"
+ depends on NFSD && NFS_FS
+ select NFS_COMMON_LOCALIO_SUPPORT
+ default n
+ help
+ Some NFS servers support an auxiliary NFS LOCALIO protocol
+ that is not an official part of the NFS protocol.
+
+ This option enables support for the LOCALIO protocol in the
+ kernel's NFS server and client. Enable this to permit local
+ NFS clients to bypass the network when issuing reads and
+ writes to the local NFS server.
+
+ If unsure, say N.
+
config NFS_V4_2_SSC_HELPER
bool
default y if NFS_V4_2
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 57249f040dfc..0eb20012792f 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -4,6 +4,7 @@ config NFS_FS
depends on INET && FILE_LOCKING && MULTIUSER
select LOCKD
select SUNRPC
+ select NFS_COMMON
select NFS_ACL_SUPPORT if NFS_V3_ACL
help
Choose Y here if you want to access files residing on other
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 8286edd6062d..a1d21c4be0ac 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_uuid.net = NULL;
+ clp->cl_uuid.dom = NULL;
+ spin_lock_init(&clp->cl_localio_lock);
+#endif /* CONFIG_NFS_LOCALIO */
+
clp->cl_principal = "*";
clp->cl_xprtsec = cl_init->xprtsec;
return clp;
@@ -233,6 +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);
@@ -424,7 +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);
- 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);
@@ -997,8 +1010,8 @@ struct nfs_server *nfs_alloc_server(void)
init_waitqueue_head(&server->write_congestion_wait);
atomic_long_set(&server->writeback, 0);
- ida_init(&server->openowner_id);
- ida_init(&server->lockowner_id);
+ atomic64_set(&server->owner_ctr, 0);
+
pnfs_init_server(server);
rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
@@ -1037,8 +1050,6 @@ void nfs_free_server(struct nfs_server *server)
}
ida_free(&s_sysfs_ids, server->s_sysfs_id);
- ida_destroy(&server->lockowner_id);
- ida_destroy(&server->openowner_id);
put_cred(server->cred);
nfs_release_automount_timer();
call_rcu(&server->rcu, delayed_free);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4cb97ef41350..492cffd9d3d8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -151,7 +151,7 @@ struct nfs_cache_array {
unsigned char folio_full : 1,
folio_is_eof : 1,
cookies_are_ordered : 1;
- struct nfs_cache_array_entry array[];
+ struct nfs_cache_array_entry array[] __counted_by(size);
};
struct nfs_readdir_descriptor {
@@ -328,7 +328,8 @@ static int nfs_readdir_folio_array_append(struct folio *folio,
goto out;
}
- cache_entry = &array->array[array->size];
+ array->size++;
+ cache_entry = &array->array[array->size - 1];
cache_entry->cookie = array->last_cookie;
cache_entry->ino = entry->ino;
cache_entry->d_type = entry->d_type;
@@ -337,7 +338,6 @@ static int nfs_readdir_folio_array_append(struct folio *folio,
array->last_cookie = entry->cookie;
if (array->last_cookie <= cache_entry->cookie)
array->cookies_are_ordered = 0;
- array->size++;
if (entry->eof != 0)
nfs_readdir_array_set_eof(array);
out:
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index b6e9aeaf4ce2..d39a1f58e18d 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -488,7 +488,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(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;
}
@@ -530,7 +530,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
/* Perform an asynchronous write */
nfs_initiate_pgio(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;
}
@@ -1011,7 +1011,7 @@ 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 39ba9f4208aa..f78115c6c2c1 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 +163,21 @@ decode_name(struct xdr_stream *xdr, u32 *id)
return 0;
}
+static struct nfsd_file *
+ff_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, fmode_t mode)
+{
+ if (mode & FMODE_WRITE) {
+ /*
+ * Always request read and write access since this corresponds
+ * to a rw layout.
+ */
+ mode |= FMODE_READ;
+ }
+
+ return nfs_local_open_fh(clp, cred, fh, mode);
+}
+
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
const struct nfs4_ff_layout_mirror *m2)
{
@@ -237,7 +253,7 @@ 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)
{
- const struct cred *cred;
+ const struct cred *cred;
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
@@ -1756,6 +1772,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1802,11 +1819,18 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
hdr->args.offset = offset;
hdr->mds_offset = offset;
+ /* Start IO accounting for local read */
+ localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ);
+ if (localio) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(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);
+ 0, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1826,6 +1850,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1870,11 +1895,19 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
*/
hdr->args.offset = offset;
+ /* Start IO accounting for local write */
+ localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (localio) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous write */
nfs_initiate_pgio(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);
+ sync, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1908,6 +1941,7 @@ 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 nfsd_file *localio;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
u32 idx;
@@ -1946,10 +1980,18 @@ 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 */
+ localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (localio) {
+ 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);
+ how, RPC_TASK_SOFTCONN, localio);
put_cred(ds_cred);
return ret;
out_err:
@@ -2087,12 +2129,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
}
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,
const struct nfs42_layoutstat_devinfo *devinfo)
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);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 6c9f3f6645dd..7e000d782e28 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -49,6 +49,7 @@ enum nfs_param {
Opt_bsize,
Opt_clientaddr,
Opt_cto,
+ Opt_alignwrite,
Opt_fg,
Opt_fscache,
Opt_fscache_flag,
@@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
fsparam_u32 ("bsize", Opt_bsize),
fsparam_string("clientaddr", Opt_clientaddr),
fsparam_flag_no("cto", Opt_cto),
+ fsparam_flag_no("alignwrite", Opt_alignwrite),
fsparam_flag ("fg", Opt_fg),
fsparam_flag_no("fsc", Opt_fscache_flag),
fsparam_string("fsc", Opt_fscache),
@@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
else
ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY;
break;
+ case Opt_alignwrite:
+ if (result.negated)
+ ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE;
+ else
+ ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE;
+ break;
case Opt_ac:
if (result.negated)
ctx->flags |= NFS_MOUNT_NOAC;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 11ff2b2e060f..f13d25d95b85 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -62,7 +62,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
}
/*
- * get an NFS2/NFS3 root dentry from the root filehandle
+ * get a root dentry from the root filehandle
*/
int nfs_get_root(struct super_block *s, struct fs_context *fc)
{
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b4914a11c3c2..542c7d97b235 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2461,35 +2461,54 @@ 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
+ * Destroy the nfsiod workqueues
*/
-static int nfsiod_start(void)
+static void nfsiod_stop(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;
+
+ wq = nfsiod_workqueue;
+ 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 */
}
/*
- * Destroy the nfsiod workqueue
+ * Start the nfsiod workqueues
*/
-static void nfsiod_stop(void)
+static int nfsiod_start(void)
{
- struct workqueue_struct *wq;
-
- wq = nfsiod_workqueue;
- if (wq == NULL)
- return;
- nfsiod_workqueue = NULL;
- destroy_workqueue(wq);
+ 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 5902a9beca1f..430733e3eff2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -9,6 +9,7 @@
#include <linux/crc32.h>
#include <linux/sunrpc/addr.h>
#include <linux/nfs_page.h>
+#include <linux/nfslocalio.h>
#include <linux/wait_bit.h>
#define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS)
@@ -308,7 +309,8 @@ 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,
- const struct rpc_call_ops *call_ops, int how, int flags);
+ const struct rpc_call_ops *call_ops, int how, int flags,
+ struct nfsd_file *localio);
void nfs_free_request(struct nfs_page *req);
struct nfs_pgio_mirror *
nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
@@ -438,6 +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 *);
@@ -449,6 +452,51 @@ 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 nfsd_file *nfs_local_open_fh(struct nfs_client *,
+ const struct cred *,
+ struct nfs_fh *,
+ const fmode_t);
+extern int nfs_local_doio(struct nfs_client *,
+ struct nfsd_file *,
+ struct nfs_pgio_header *,
+ const struct rpc_call_ops *);
+extern int nfs_local_commit(struct nfsd_file *,
+ struct nfs_commit_data *,
+ const struct rpc_call_ops *, int);
+extern bool nfs_server_is_local(const struct nfs_client *clp);
+
+#else /* CONFIG_NFS_LOCALIO */
+static inline void nfs_local_disable(struct nfs_client *clp) {}
+static inline void nfs_local_probe(struct nfs_client *clp) {}
+static inline struct nfsd_file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, const fmode_t mode)
+{
+ return NULL;
+}
+static inline int nfs_local_doio(struct nfs_client *clp,
+ struct nfsd_file *localio,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ return -EINVAL;
+}
+static inline int nfs_local_commit(struct nfsd_file *localio,
+ 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);
@@ -505,7 +553,6 @@ extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
struct nfs_open_context *ctx,
struct folio *folio);
extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio);
-extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
/* super.c */
@@ -528,7 +575,8 @@ 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 nfsd_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/localio.c b/fs/nfs/localio.c
new file mode 100644
index 000000000000..c29cdf51c458
--- /dev/null
+++ b/fs/nfs/localio.c
@@ -0,0 +1,757 @@
+// 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>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+
+#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/nfs_common.h>
+#include <linux/nfslocalio.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 nfsd_file *localio;
+};
+
+struct nfs_local_fsync_ctx {
+ struct nfsd_file *localio;
+ 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);
+
+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 nfs_client_is_local(clp) && localio_enabled;
+}
+EXPORT_SYMBOL_GPL(nfs_server_is_local);
+
+/*
+ * UUID_IS_LOCAL XDR functions
+ */
+
+static void localio_xdr_enc_uuidargs(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ const void *data)
+{
+ const u8 *uuid = data;
+
+ encode_opaque_fixed(xdr, uuid, UUID_SIZE);
+}
+
+static int localio_xdr_dec_uuidres(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ void *result)
+{
+ /* void return */
+ return 0;
+}
+
+static const struct rpc_procinfo nfs_localio_procedures[] = {
+ [LOCALIOPROC_UUID_IS_LOCAL] = {
+ .p_proc = LOCALIOPROC_UUID_IS_LOCAL,
+ .p_encode = localio_xdr_enc_uuidargs,
+ .p_decode = localio_xdr_dec_uuidres,
+ .p_arglen = XDR_QUADLEN(UUID_SIZE),
+ .p_replen = 0,
+ .p_statidx = LOCALIOPROC_UUID_IS_LOCAL,
+ .p_name = "UUID_IS_LOCAL",
+ },
+};
+
+static unsigned int nfs_localio_counts[ARRAY_SIZE(nfs_localio_procedures)];
+static 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 - enable local i/o for an nfs_client
+ */
+static void nfs_local_enable(struct nfs_client *clp)
+{
+ spin_lock(&clp->cl_localio_lock);
+ set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+ trace_nfs_local_enable(clp);
+ spin_unlock(&clp->cl_localio_lock);
+}
+
+/*
+ * nfs_local_disable - disable local i/o for an nfs_client
+ */
+void nfs_local_disable(struct nfs_client *clp)
+{
+ spin_lock(&clp->cl_localio_lock);
+ if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
+ trace_nfs_local_disable(clp);
+ nfs_uuid_invalidate_one_client(&clp->cl_uuid);
+ }
+ spin_unlock(&clp->cl_localio_lock);
+}
+
+/*
+ * nfs_init_localioclient - Initialise an NFS localio client connection
+ */
+static struct rpc_clnt *nfs_init_localioclient(struct nfs_client *clp)
+{
+ struct rpc_clnt *rpcclient_localio;
+
+ rpcclient_localio = rpc_bind_new_program(clp->cl_rpcclient,
+ &nfslocalio_program, 1);
+
+ dprintk_rcu("%s: server (%s) %s NFS LOCALIO.\n",
+ __func__, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
+ (IS_ERR(rpcclient_localio) ? "does not support" : "supports"));
+
+ return rpcclient_localio;
+}
+
+static bool nfs_server_uuid_is_local(struct nfs_client *clp)
+{
+ u8 uuid[UUID_SIZE];
+ struct rpc_message msg = {
+ .rpc_argp = &uuid,
+ };
+ struct rpc_clnt *rpcclient_localio;
+ int status;
+
+ rpcclient_localio = nfs_init_localioclient(clp);
+ if (IS_ERR(rpcclient_localio))
+ return false;
+
+ export_uuid(uuid, &clp->cl_uuid.uuid);
+
+ msg.rpc_proc = &nfs_localio_procedures[LOCALIOPROC_UUID_IS_LOCAL];
+ status = rpc_call_sync(rpcclient_localio, &msg, 0);
+ dprintk("%s: NFS reply UUID_IS_LOCAL: status=%d\n",
+ __func__, status);
+ rpc_shutdown_client(rpcclient_localio);
+
+ /* Server is only local if it initialized required struct members */
+ if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom)
+ return false;
+
+ 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)
+{
+ /* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */
+ if (!localio_enabled ||
+ clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) {
+ nfs_local_disable(clp);
+ return;
+ }
+
+ if (nfs_client_is_local(clp)) {
+ /* If already enabled, disable and re-enable */
+ nfs_local_disable(clp);
+ }
+
+ nfs_uuid_begin(&clp->cl_uuid);
+ if (nfs_server_uuid_is_local(clp))
+ nfs_local_enable(clp);
+ nfs_uuid_end(&clp->cl_uuid);
+}
+EXPORT_SYMBOL_GPL(nfs_local_probe);
+
+/*
+ * nfs_local_open_fh - open a local filehandle in terms of nfsd_file
+ *
+ * Returns a pointer to a struct nfsd_file or NULL
+ */
+struct nfsd_file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ struct nfs_fh *fh, const fmode_t mode)
+{
+ struct nfsd_file *localio;
+ int status;
+
+ if (!nfs_server_is_local(clp))
+ return NULL;
+ if (mode & ~(FMODE_READ | FMODE_WRITE))
+ return NULL;
+
+ localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
+ cred, fh, mode);
+ if (IS_ERR(localio)) {
+ status = PTR_ERR(localio);
+ trace_nfs_local_open_fh(fh, mode, status);
+ switch (status) {
+ case -ENOMEM:
+ case -ENXIO:
+ case -ENOENT:
+ /* Revalidate localio, will disable if unsupported */
+ nfs_local_probe(clp);
+ }
+ return NULL;
+ }
+ return localio;
+}
+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 nfsd_file *localio, 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, nfs_to->nfsd_file_file(localio));
+ iocb->kiocb.ki_pos = hdr->args.offset;
+ iocb->localio = localio;
+ 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 = nfs4_stat_to_errno(status);
+ hdr->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
+{
+ struct nfs_pgio_header *hdr = iocb->hdr;
+
+ nfs_to->nfsd_file_put_local(iocb->localio);
+ 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 void nfs_local_call_read(struct work_struct *work)
+{
+ struct nfs_local_kiocb *iocb =
+ container_of(work, struct nfs_local_kiocb, work);
+ struct file *filp = iocb->kiocb.ki_filp;
+ const struct cred *save_cred;
+ struct iov_iter iter;
+ ssize_t status;
+
+ save_cred = override_creds(filp->f_cred);
+
+ nfs_local_iter_init(&iter, iocb, READ);
+
+ status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+ WARN_ON_ONCE(status == -EIOCBQUEUED);
+
+ nfs_local_read_done(iocb, status);
+ nfs_local_pgio_release(iocb);
+
+ revert_creds(save_cred);
+}
+
+static int
+nfs_do_local_read(struct nfs_pgio_header *hdr,
+ struct nfsd_file *localio,
+ const struct rpc_call_ops *call_ops)
+{
+ 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, localio, GFP_KERNEL);
+ if (iocb == NULL)
+ return -ENOMEM;
+
+ nfs_local_pgio_init(hdr, call_ops);
+ hdr->res.eof = false;
+
+ INIT_WORK(&iocb->work, nfs_local_call_read);
+ queue_work(nfslocaliod_workqueue, &iocb->work);
+
+ 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;
+}
+
+/* Factored out from fs/nfsd/vfs.h:fh_getattr() */
+static int __vfs_getattr(struct path *p, struct kstat *stat, int version)
+{
+ u32 request_mask = STATX_BASIC_STATS;
+
+ if (version == 4)
+ request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
+ return vfs_getattr(p, stat, request_mask, AT_STATX_SYNC_AS_STAT);
+}
+
+/* Copied from fs/nfsd/nfsfh.c:nfsd4_change_attribute() */
+static u64 __nfsd4_change_attribute(const struct kstat *stat,
+ const struct inode *inode)
+{
+ u64 chattr;
+
+ if (stat->result_mask & STATX_CHANGE_COOKIE) {
+ chattr = stat->change_cookie;
+ if (S_ISREG(inode->i_mode) &&
+ !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) {
+ chattr += (u64)stat->ctime.tv_sec << 30;
+ chattr += stat->ctime.tv_nsec;
+ }
+ } else {
+ chattr = time_to_chattr(&stat->ctime);
+ }
+ return chattr;
+}
+
+static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb)
+{
+ struct kstat stat;
+ struct file *filp = iocb->kiocb.ki_filp;
+ struct nfs_pgio_header *hdr = iocb->hdr;
+ struct nfs_fattr *fattr = hdr->res.fattr;
+ int version = NFS_PROTO(hdr->inode)->version;
+
+ if (unlikely(!fattr) || __vfs_getattr(&filp->f_path, &stat, version))
+ return;
+
+ 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;
+ if (version == 4) {
+ fattr->change_attr =
+ __nfsd4_change_attribute(&stat, file_inode(filp));
+ } else
+ 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;
+ struct inode *inode = hdr->inode;
+
+ 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(inode);
+ else if (nfs_should_remove_suid(inode)) {
+ /* Deal with the suid/sgid bit corner case */
+ spin_lock(&inode->i_lock);
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+ spin_unlock(&inode->i_lock);
+ }
+ nfs_local_pgio_done(hdr, status);
+}
+
+static void nfs_local_call_write(struct work_struct *work)
+{
+ struct nfs_local_kiocb *iocb =
+ container_of(work, struct nfs_local_kiocb, work);
+ struct file *filp = iocb->kiocb.ki_filp;
+ unsigned long old_flags = current->flags;
+ const struct cred *save_cred;
+ struct iov_iter iter;
+ ssize_t status;
+
+ current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
+ save_cred = override_creds(filp->f_cred);
+
+ nfs_local_iter_init(&iter, iocb, WRITE);
+
+ file_start_write(filp);
+ status = filp->f_op->write_iter(&iocb->kiocb, &iter);
+ file_end_write(filp);
+ WARN_ON_ONCE(status == -EIOCBQUEUED);
+
+ nfs_local_write_done(iocb, status);
+ nfs_local_vfs_getattr(iocb);
+ nfs_local_pgio_release(iocb);
+
+ revert_creds(save_cred);
+ current->flags = old_flags;
+}
+
+static int
+nfs_do_local_write(struct nfs_pgio_header *hdr,
+ struct nfsd_file *localio,
+ const struct rpc_call_ops *call_ops)
+{
+ 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");
+
+ iocb = nfs_local_iocb_alloc(hdr, localio, GFP_NOIO);
+ if (iocb == NULL)
+ return -ENOMEM;
+
+ 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);
+
+ INIT_WORK(&iocb->work, nfs_local_call_write);
+ queue_work(nfslocaliod_workqueue, &iocb->work);
+
+ return 0;
+}
+
+int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
+ struct nfs_pgio_header *hdr,
+ const struct rpc_call_ops *call_ops)
+{
+ int status = 0;
+ struct file *filp = nfs_to->nfsd_file_file(localio);
+
+ if (!hdr->args.count)
+ return 0;
+ /* 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;
+ }
+
+ switch (hdr->rw_mode) {
+ case FMODE_READ:
+ status = nfs_do_local_read(hdr, localio, call_ops);
+ break;
+ case FMODE_WRITE:
+ status = nfs_do_local_write(hdr, localio, call_ops);
+ break;
+ default:
+ dprintk("%s: invalid mode: %d\n", __func__,
+ hdr->rw_mode);
+ status = -EINVAL;
+ }
+out:
+ if (status != 0) {
+ nfs_to->nfsd_file_put_local(localio);
+ 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 = nfs4_stat_to_errno(status);
+ data->task.tk_status = status;
+ }
+}
+
+static void
+nfs_local_release_commit_data(struct nfsd_file *localio,
+ struct nfs_commit_data *data,
+ const struct rpc_call_ops *call_ops)
+{
+ nfs_to->nfsd_file_put_local(localio);
+ 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 nfsd_file *localio, gfp_t flags)
+{
+ struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags);
+
+ if (ctx != NULL) {
+ ctx->localio = localio;
+ 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->localio, 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(nfs_to->nfsd_file_file(ctx->localio),
+ 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 nfsd_file *localio,
+ 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, localio, GFP_KERNEL);
+ if (!ctx) {
+ nfs_local_commit_done(data, -ENOMEM);
+ nfs_local_release_commit_data(localio, 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/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index c19093814296..6e75c6c2d234 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -22,14 +22,12 @@
#include <linux/nfs.h>
#include <linux/nfs2.h>
#include <linux/nfs_fs.h>
+#include <linux/nfs_common.h>
#include "nfstrace.h"
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_XDR
-/* Mapping from NFS error code to "errno" error code. */
-#define errno_NFSERR_IO EIO
-
/*
* Declare the space requirements for NFS arguments and replies as
* number of 32bit-words
@@ -64,8 +62,6 @@
#define NFS_readdirres_sz (1+NFS_pagepad_sz)
#define NFS_statfsres_sz (1+NFS_info_sz)
-static int nfs_stat_to_errno(enum nfs_stat);
-
/*
* Encode/decode NFSv2 basic data types
*
@@ -1054,70 +1050,6 @@ out_default:
return nfs_stat_to_errno(status);
}
-
-/*
- * We need to translate between nfs status return values and
- * the local errno values which may not be the same.
- */
-static const struct {
- int stat;
- int errno;
-} nfs_errtbl[] = {
- { NFS_OK, 0 },
- { NFSERR_PERM, -EPERM },
- { NFSERR_NOENT, -ENOENT },
- { NFSERR_IO, -errno_NFSERR_IO},
- { 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_errtbl[i].stat != -1; i++) {
- if (nfs_errtbl[i].stat == (int)status)
- return nfs_errtbl[i].errno;
- }
- dprintk("NFS: Unrecognized nfs status value: %u\n", status);
- return nfs_errtbl[i].errno;
-}
-
#define PROC(proc, argtype, restype, timer) \
[NFSPROC_##proc] = { \
.p_proc = NFSPROC_##proc, \
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 60f032be805a..4ae01c10b7e2 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -21,14 +21,13 @@
#include <linux/nfs3.h>
#include <linux/nfs_fs.h>
#include <linux/nfsacl.h>
+#include <linux/nfs_common.h>
+
#include "nfstrace.h"
#include "internal.h"
#define NFSDBG_FACILITY NFSDBG_XDR
-/* Mapping from NFS error code to "errno" error code. */
-#define errno_NFSERR_IO EIO
-
/*
* Declare the space requirements for NFS arguments and replies as
* number of 32bit-words
@@ -91,8 +90,6 @@
NFS3_pagepad_sz)
#define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz)
-static int nfs3_stat_to_errno(enum nfs_stat);
-
/*
* Map file type to S_IFMT bits
*/
@@ -1406,7 +1403,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req,
out:
return error;
out_default:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1445,7 +1442,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1495,7 +1492,7 @@ out_default:
error = decode_post_op_attr(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1537,7 +1534,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req,
out:
return error;
out_default:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1578,7 +1575,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req,
out:
return error;
out_default:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1658,7 +1655,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1728,7 +1725,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1795,7 +1792,7 @@ out_default:
error = decode_wcc_data(xdr, result->dir_attr, userns);
if (unlikely(error))
goto out;
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1835,7 +1832,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1881,7 +1878,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -1926,7 +1923,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/**
@@ -2101,7 +2098,7 @@ out_default:
error = decode_post_op_attr(xdr, result->dir_attr, rpc_rqst_userns(req));
if (unlikely(error))
goto out;
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -2167,7 +2164,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -2243,7 +2240,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -2304,7 +2301,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
/*
@@ -2350,7 +2347,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
out:
return error;
out_status:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
#ifdef CONFIG_NFS_V3_ACL
@@ -2416,7 +2413,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req,
out:
return error;
out_default:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
@@ -2435,76 +2432,11 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
out:
return error;
out_default:
- return nfs3_stat_to_errno(status);
+ return nfs_stat_to_errno(status);
}
#endif /* CONFIG_NFS_V3_ACL */
-
-/*
- * We need to translate between nfs status return values and
- * the local errno values which may not be the same.
- */
-static const struct {
- int stat;
- int errno;
-} nfs_errtbl[] = {
- { NFS_OK, 0 },
- { NFSERR_PERM, -EPERM },
- { NFSERR_NOENT, -ENOENT },
- { NFSERR_IO, -errno_NFSERR_IO},
- { 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 }
-};
-
-/**
- * nfs3_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 nfs3_stat_to_errno(enum nfs_stat status)
-{
- int i;
-
- for (i = 0; nfs_errtbl[i].stat != -1; i++) {
- if (nfs_errtbl[i].stat == (int)status)
- return nfs_errtbl[i].errno;
- }
- dprintk("NFS: Unrecognized nfs status value: %u\n", status);
- return nfs_errtbl[i].errno;
-}
-
-
#define PROC(proc, argtype, restype, timer) \
[NFS3PROC_##proc] = { \
.p_proc = NFS3PROC_##proc, \
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index c2045a2a9d0f..7d383d29a995 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -83,7 +83,7 @@ struct nfs4_minor_version_ops {
#define NFS_SEQID_CONFIRMED 1
struct nfs_seqid_counter {
ktime_t create_time;
- int owner_id;
+ u64 owner_id;
int flags;
u32 counter;
spinlock_t lock; /* Protects the list */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b8ffbe52ba15..cd2fbde2e6d7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3904,6 +3904,18 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_OPEN_ARGUMENTS - 1UL)
+#define FATTR4_WORD2_NFS42_TIME_DELEG_MASK \
+ (FATTR4_WORD2_TIME_DELEG_MODIFY|FATTR4_WORD2_TIME_DELEG_ACCESS)
+static bool nfs4_server_delegtime_capable(struct nfs4_server_caps_res *res)
+{
+ u32 share_access_want = res->open_caps.oa_share_access_want[0];
+ u32 attr_bitmask = res->attr_bitmask[2];
+
+ return (share_access_want & NFS4_SHARE_WANT_DELEG_TIMESTAMPS) &&
+ ((attr_bitmask & FATTR4_WORD2_NFS42_TIME_DELEG_MASK) ==
+ FATTR4_WORD2_NFS42_TIME_DELEG_MASK);
+}
+
static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
u32 minorversion = server->nfs_client->cl_minorversion;
@@ -3982,8 +3994,6 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
#endif
if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS)
server->caps |= NFS_CAP_FS_LOCATIONS;
- if (res.attr_bitmask[2] & FATTR4_WORD2_TIME_DELEG_MODIFY)
- server->caps |= NFS_CAP_DELEGTIME;
if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID))
server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID;
if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE))
@@ -4011,6 +4021,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
if (res.open_caps.oa_share_access_want[0] &
NFS4_SHARE_WANT_OPEN_XOR_DELEGATION)
server->caps |= NFS_CAP_OPEN_XOR;
+ if (nfs4_server_delegtime_capable(&res))
+ server->caps |= NFS_CAP_DELEGTIME;
memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 877f682b45f2..581864a15888 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -501,11 +501,7 @@ nfs4_alloc_state_owner(struct nfs_server *server,
sp = kzalloc(sizeof(*sp), gfp_flags);
if (!sp)
return NULL;
- sp->so_seqid.owner_id = ida_alloc(&server->openowner_id, gfp_flags);
- if (sp->so_seqid.owner_id < 0) {
- kfree(sp);
- return NULL;
- }
+ sp->so_seqid.owner_id = atomic64_inc_return(&server->owner_ctr);
sp->so_server = server;
sp->so_cred = get_cred(cred);
spin_lock_init(&sp->so_lock);
@@ -536,7 +532,6 @@ static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
{
nfs4_destroy_seqid_counter(&sp->so_seqid);
put_cred(sp->so_cred);
- ida_free(&sp->so_server->openowner_id, sp->so_seqid.owner_id);
kfree(sp);
}
@@ -879,19 +874,13 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
refcount_set(&lsp->ls_count, 1);
lsp->ls_state = state;
lsp->ls_owner = owner;
- lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT);
- if (lsp->ls_seqid.owner_id < 0)
- goto out_free;
+ lsp->ls_seqid.owner_id = atomic64_inc_return(&server->owner_ctr);
INIT_LIST_HEAD(&lsp->ls_locks);
return lsp;
-out_free:
- kfree(lsp);
- return NULL;
}
void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
{
- ida_free(&server->lockowner_id, lsp->ls_seqid.owner_id);
nfs4_destroy_seqid_counter(&lsp->ls_seqid);
kfree(lsp);
}
@@ -1957,6 +1946,7 @@ restart:
set_bit(ops->owner_flag_bit, &sp->so_flags);
nfs4_put_state_owner(sp);
status = nfs4_recovery_handle_error(clp, status);
+ nfs4_free_state_owners(&freeme);
return (status != 0) ? status : -EAGAIN;
}
@@ -2023,6 +2013,12 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
nfs_mark_client_ready(clp, -EPERM);
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
return -EPERM;
+ case -ETIMEDOUT:
+ if (clp->cl_cons_state == NFS_CS_SESSION_INITING) {
+ nfs_mark_client_ready(clp, -EIO);
+ return -EIO;
+ }
+ fallthrough;
case -EACCES:
case -NFS4ERR_DELAY:
case -EAGAIN:
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 61190d6a5a77..e8ac3f615f93 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -52,6 +52,7 @@
#include <linux/nfs.h>
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
+#include <linux/nfs_common.h>
#include "nfs4_fs.h"
#include "nfs4trace.h"
@@ -63,11 +64,7 @@
#define NFSDBG_FACILITY NFSDBG_XDR
-/* Mapping from NFS error code to "errno" error code. */
-#define errno_NFSERR_IO EIO
-
struct compound_hdr;
-static int nfs4_stat_to_errno(int);
static void encode_layoutget(struct xdr_stream *xdr,
const struct nfs4_layoutget_args *args,
struct compound_hdr *hdr);
@@ -975,11 +972,6 @@ 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);
@@ -1424,12 +1416,12 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
*/
encode_nfs4_seqid(xdr, arg->seqid);
encode_share_access(xdr, arg->share_access);
- p = reserve_space(xdr, 36);
+ p = reserve_space(xdr, 40);
p = xdr_encode_hyper(p, arg->clientid);
- *p++ = cpu_to_be32(24);
+ *p++ = cpu_to_be32(28);
p = xdr_encode_opaque_fixed(p, "open id:", 8);
*p++ = cpu_to_be32(arg->server->s_dev);
- *p++ = cpu_to_be32(arg->id.uniquifier);
+ p = xdr_encode_hyper(p, arg->id.uniquifier);
xdr_encode_hyper(p, arg->id.create_time);
}
@@ -4408,14 +4400,6 @@ 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);
@@ -7620,72 +7604,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
return 0;
}
-/*
- * We need to translate between nfs status return values and
- * the local errno values which may not be the same.
- */
-static struct {
- int stat;
- int errno;
-} nfs_errtbl[] = {
- { NFS4_OK, 0 },
- { NFS4ERR_PERM, -EPERM },
- { NFS4ERR_NOENT, -ENOENT },
- { NFS4ERR_IO, -errno_NFSERR_IO},
- { NFS4ERR_NXIO, -ENXIO },
- { NFS4ERR_ACCESS, -EACCES },
- { NFS4ERR_EXIST, -EEXIST },
- { NFS4ERR_XDEV, -EXDEV },
- { NFS4ERR_NOTDIR, -ENOTDIR },
- { NFS4ERR_ISDIR, -EISDIR },
- { NFS4ERR_INVAL, -EINVAL },
- { NFS4ERR_FBIG, -EFBIG },
- { NFS4ERR_NOSPC, -ENOSPC },
- { NFS4ERR_ROFS, -EROFS },
- { NFS4ERR_MLINK, -EMLINK },
- { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG },
- { NFS4ERR_NOTEMPTY, -ENOTEMPTY },
- { NFS4ERR_DQUOT, -EDQUOT },
- { NFS4ERR_STALE, -ESTALE },
- { NFS4ERR_BADHANDLE, -EBADHANDLE },
- { NFS4ERR_BAD_COOKIE, -EBADCOOKIE },
- { NFS4ERR_NOTSUPP, -ENOTSUPP },
- { NFS4ERR_TOOSMALL, -ETOOSMALL },
- { NFS4ERR_SERVERFAULT, -EREMOTEIO },
- { NFS4ERR_BADTYPE, -EBADTYPE },
- { NFS4ERR_LOCKED, -EAGAIN },
- { NFS4ERR_SYMLINK, -ELOOP },
- { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP },
- { NFS4ERR_DEADLOCK, -EDEADLK },
- { NFS4ERR_NOXATTR, -ENODATA },
- { NFS4ERR_XATTR2BIG, -E2BIG },
- { -1, -EIO }
-};
-
-/*
- * Convert an NFS error code to a local one.
- * This one is used jointly by NFSv2 and NFSv3.
- */
-static int
-nfs4_stat_to_errno(int stat)
-{
- int i;
- for (i = 0; nfs_errtbl[i].stat != -1; i++) {
- if (nfs_errtbl[i].stat == stat)
- return nfs_errtbl[i].errno;
- }
- if (stat <= 10000 || stat > 10100) {
- /* The server is looney tunes. */
- return -EREMOTEIO;
- }
- /* 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 -stat;
-}
-
#ifdef CONFIG_NFS_V4_2
#include "nfs42xdr.c"
#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 352fdaed4075..1eab98c277fa 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -1685,6 +1685,67 @@ 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 04124f226665..e27c07bd8929 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -731,7 +731,8 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
int nfs_initiate_pgio(struct rpc_clnt *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 nfsd_file *localio)
{
struct rpc_task *task;
struct rpc_message msg = {
@@ -761,6 +762,10 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ if (localio)
+ return nfs_local_doio(NFS_SERVER(hdr->inode)->nfs_client,
+ localio, hdr, call_ops);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -953,6 +958,12 @@ 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;
+
+ struct nfsd_file *localio =
+ nfs_local_open_fh(clp, hdr->cred,
+ hdr->args.fh, hdr->args.context->mode);
+
if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
task_flags = RPC_TASK_MOVEABLE;
ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
@@ -961,7 +972,8 @@ 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,
+ localio);
}
return ret;
}
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index a74ee69a2fa6..dbef837e871a 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -490,7 +490,7 @@ 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/read.c b/fs/nfs/read.c
index a6103333b666..81bd1b9aba17 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -48,8 +48,7 @@ static struct nfs_pgio_header *nfs_readhdr_alloc(void)
static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
{
- if (rhdr->res.scratch != NULL)
- kfree(rhdr->res.scratch);
+ kfree(rhdr->res.scratch);
kmem_cache_free(nfs_rdata_cachep, rhdr);
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 97b386032b71..9723b6c53397 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -551,6 +551,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
else
seq_puts(m, ",local_lock=posix");
+ if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE)
+ seq_puts(m, ",noalignwrite");
+
if (nfss->flags & NFS_MOUNT_WRITE_EAGER) {
if (nfss->flags & NFS_MOUNT_WRITE_WAIT)
seq_puts(m, ",write=wait");
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d074d0ceb4f0..ead2dc55952d 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -772,8 +772,7 @@ static void nfs_inode_add_request(struct nfs_page *req)
nfs_lock_request(req);
spin_lock(&mapping->i_private_lock);
set_bit(PG_MAPPED, &req->wb_flags);
- folio_set_private(folio);
- folio->private = req;
+ folio_attach_private(folio, req);
spin_unlock(&mapping->i_private_lock);
atomic_long_inc(&nfsi->nrequests);
/* this a head request for a page group - mark it as having an
@@ -797,8 +796,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
spin_lock(&mapping->i_private_lock);
if (likely(folio)) {
- folio->private = NULL;
- folio_clear_private(folio);
+ folio_detach_private(folio);
clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
}
spin_unlock(&mapping->i_private_lock);
@@ -1297,7 +1295,10 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
struct file_lock_context *flctx = locks_inode_context(inode);
struct file_lock *fl;
int ret;
+ unsigned int mntflags = NFS_SERVER(inode)->flags;
+ if (mntflags & NFS_MOUNT_NO_ALIGNWRITE)
+ return 0;
if (file->f_flags & O_DSYNC)
return 0;
if (!nfs_folio_write_uptodate(folio, pagelen))
@@ -1663,7 +1664,8 @@ 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 nfsd_file *localio)
{
struct rpc_task *task;
int priority = flush_task_priority(how);
@@ -1692,6 +1694,9 @@ 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);
@@ -1791,6 +1796,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
struct nfs_commit_info *cinfo)
{
struct nfs_commit_data *data;
+ struct nfsd_file *localio;
unsigned short task_flags = 0;
/* another commit raced with us */
@@ -1807,9 +1813,12 @@ 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;
+
+ localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred,
+ data->args.fh, data->context->mode);
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, localio);
}
/*
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index 119c75ab9fd0..a5e54809701e 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -6,5 +6,10 @@
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-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o
+
+obj-$(CONFIG_NFS_COMMON) += common.o
diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c
new file mode 100644
index 000000000000..34a115176f97
--- /dev/null
+++ b/fs/nfs_common/common.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/module.h>
+#include <linux/nfs_common.h>
+#include <linux/nfs4.h>
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ */
+static const struct {
+ int stat;
+ int errno;
+} nfs_errtbl[] = {
+ { NFS_OK, 0 },
+ { NFSERR_PERM, -EPERM },
+ { NFSERR_NOENT, -ENOENT },
+ { NFSERR_IO, -errno_NFSERR_IO},
+ { 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.
+ */
+int nfs_stat_to_errno(enum nfs_stat status)
+{
+ int i;
+
+ for (i = 0; nfs_errtbl[i].stat != -1; i++) {
+ if (nfs_errtbl[i].stat == (int)status)
+ return nfs_errtbl[i].errno;
+ }
+ return nfs_errtbl[i].errno;
+}
+EXPORT_SYMBOL_GPL(nfs_stat_to_errno);
+
+/*
+ * We need to translate between nfs v4 status return values and
+ * the local errno values which may not be the same.
+ */
+static const struct {
+ int stat;
+ int errno;
+} nfs4_errtbl[] = {
+ { NFS4_OK, 0 },
+ { NFS4ERR_PERM, -EPERM },
+ { NFS4ERR_NOENT, -ENOENT },
+ { NFS4ERR_IO, -errno_NFSERR_IO},
+ { NFS4ERR_NXIO, -ENXIO },
+ { NFS4ERR_ACCESS, -EACCES },
+ { NFS4ERR_EXIST, -EEXIST },
+ { NFS4ERR_XDEV, -EXDEV },
+ { NFS4ERR_NOTDIR, -ENOTDIR },
+ { NFS4ERR_ISDIR, -EISDIR },
+ { NFS4ERR_INVAL, -EINVAL },
+ { NFS4ERR_FBIG, -EFBIG },
+ { NFS4ERR_NOSPC, -ENOSPC },
+ { NFS4ERR_ROFS, -EROFS },
+ { NFS4ERR_MLINK, -EMLINK },
+ { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG },
+ { NFS4ERR_NOTEMPTY, -ENOTEMPTY },
+ { NFS4ERR_DQUOT, -EDQUOT },
+ { NFS4ERR_STALE, -ESTALE },
+ { NFS4ERR_BADHANDLE, -EBADHANDLE },
+ { NFS4ERR_BAD_COOKIE, -EBADCOOKIE },
+ { NFS4ERR_NOTSUPP, -ENOTSUPP },
+ { NFS4ERR_TOOSMALL, -ETOOSMALL },
+ { NFS4ERR_SERVERFAULT, -EREMOTEIO },
+ { NFS4ERR_BADTYPE, -EBADTYPE },
+ { NFS4ERR_LOCKED, -EAGAIN },
+ { NFS4ERR_SYMLINK, -ELOOP },
+ { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP },
+ { NFS4ERR_DEADLOCK, -EDEADLK },
+ { NFS4ERR_NOXATTR, -ENODATA },
+ { NFS4ERR_XATTR2BIG, -E2BIG },
+ { -1, -EIO }
+};
+
+/*
+ * Convert an NFS error code to a local one.
+ * This one is used by NFSv4.
+ */
+int nfs4_stat_to_errno(int stat)
+{
+ int i;
+ for (i = 0; nfs4_errtbl[i].stat != -1; i++) {
+ if (nfs4_errtbl[i].stat == stat)
+ return nfs4_errtbl[i].errno;
+ }
+ if (stat <= 10000 || stat > 10100) {
+ /* The server is looney tunes. */
+ return -EREMOTEIO;
+ }
+ /* 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 -stat;
+}
+EXPORT_SYMBOL_GPL(nfs4_stat_to_errno);
diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
new file mode 100644
index 000000000000..42b479b9191f
--- /dev/null
+++ b/fs/nfs_common/nfslocalio.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+
+#include <linux/module.h>
+#include <linux/rculist.h>
+#include <linux/nfslocalio.h>
+#include <net/netns/generic.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("NFS localio protocol bypass support");
+
+static DEFINE_SPINLOCK(nfs_uuid_lock);
+
+/*
+ * Global list of nfs_uuid_t instances
+ * that is protected by nfs_uuid_lock.
+ */
+static LIST_HEAD(nfs_uuids);
+
+void nfs_uuid_begin(nfs_uuid_t *nfs_uuid)
+{
+ nfs_uuid->net = NULL;
+ nfs_uuid->dom = NULL;
+ uuid_gen(&nfs_uuid->uuid);
+
+ spin_lock(&nfs_uuid_lock);
+ list_add_tail_rcu(&nfs_uuid->list, &nfs_uuids);
+ spin_unlock(&nfs_uuid_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_uuid_begin);
+
+void nfs_uuid_end(nfs_uuid_t *nfs_uuid)
+{
+ if (nfs_uuid->net == NULL) {
+ spin_lock(&nfs_uuid_lock);
+ list_del_init(&nfs_uuid->list);
+ spin_unlock(&nfs_uuid_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(nfs_uuid_end);
+
+static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid)
+{
+ nfs_uuid_t *nfs_uuid;
+
+ list_for_each_entry(nfs_uuid, &nfs_uuids, list)
+ if (uuid_equal(&nfs_uuid->uuid, uuid))
+ return nfs_uuid;
+
+ return NULL;
+}
+
+static struct module *nfsd_mod;
+
+void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list,
+ struct net *net, struct auth_domain *dom,
+ struct module *mod)
+{
+ nfs_uuid_t *nfs_uuid;
+
+ spin_lock(&nfs_uuid_lock);
+ nfs_uuid = nfs_uuid_lookup_locked(uuid);
+ if (nfs_uuid) {
+ kref_get(&dom->ref);
+ nfs_uuid->dom = dom;
+ /*
+ * We don't hold a ref on the net, but instead put
+ * ourselves on a list so the net pointer can be
+ * invalidated.
+ */
+ list_move(&nfs_uuid->list, list);
+ rcu_assign_pointer(nfs_uuid->net, net);
+
+ __module_get(mod);
+ nfsd_mod = mod;
+ }
+ spin_unlock(&nfs_uuid_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_uuid_is_local);
+
+static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid)
+{
+ if (nfs_uuid->net) {
+ module_put(nfsd_mod);
+ nfs_uuid->net = NULL;
+ }
+ if (nfs_uuid->dom) {
+ auth_domain_put(nfs_uuid->dom);
+ nfs_uuid->dom = NULL;
+ }
+ list_del_init(&nfs_uuid->list);
+}
+
+void nfs_uuid_invalidate_clients(struct list_head *list)
+{
+ nfs_uuid_t *nfs_uuid, *tmp;
+
+ spin_lock(&nfs_uuid_lock);
+ list_for_each_entry_safe(nfs_uuid, tmp, list, list)
+ nfs_uuid_put_locked(nfs_uuid);
+ spin_unlock(&nfs_uuid_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients);
+
+void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid)
+{
+ if (nfs_uuid->net) {
+ spin_lock(&nfs_uuid_lock);
+ nfs_uuid_put_locked(nfs_uuid);
+ spin_unlock(&nfs_uuid_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client);
+
+struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
+ struct rpc_clnt *rpc_clnt, const struct cred *cred,
+ const struct nfs_fh *nfs_fh, const fmode_t fmode)
+{
+ struct net *net;
+ struct nfsd_file *localio;
+
+ /*
+ * Not running in nfsd context, so must safely get reference on nfsd_serv.
+ * But the server may already be shutting down, if so disallow new localio.
+ * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that
+ * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe
+ * and if it succeeds we will have an implied reference to the net.
+ *
+ * Otherwise NFS may not have ref on NFSD and therefore cannot safely
+ * make 'nfs_to' calls.
+ */
+ rcu_read_lock();
+ net = rcu_dereference(uuid->net);
+ if (!net || !nfs_to->nfsd_serv_try_get(net)) {
+ rcu_read_unlock();
+ return ERR_PTR(-ENXIO);
+ }
+ rcu_read_unlock();
+ /* We have an implied reference to net thanks to nfsd_serv_try_get */
+ localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
+ cred, nfs_fh, fmode);
+ if (IS_ERR(localio))
+ nfs_to->nfsd_serv_put(net);
+ return localio;
+}
+EXPORT_SYMBOL_GPL(nfs_open_local_fh);
+
+/*
+ * The NFS LOCALIO code needs to call into NFSD using various symbols,
+ * but cannot be statically linked, because that will make the NFS
+ * module always depend on the NFSD module.
+ *
+ * 'nfs_to' provides NFS access to NFSD functions needed for LOCALIO,
+ * its lifetime is tightly coupled to the NFSD module and will always
+ * be available to NFS LOCALIO because any successful client<->server
+ * LOCALIO handshake results in a reference on the NFSD module (above),
+ * so NFS implicitly holds a reference to the NFSD module and its
+ * functions in the 'nfs_to' nfsd_localio_operations cannot disappear.
+ *
+ * If the last NFS client using LOCALIO disconnects (and its reference
+ * on NFSD dropped) then NFSD could be unloaded, resulting in 'nfs_to'
+ * functions being invalid pointers. But if NFSD isn't loaded then NFS
+ * will not be able to handshake with NFSD and will have no cause to
+ * try to call 'nfs_to' function pointers. If/when NFSD is reloaded it
+ * will reinitialize the 'nfs_to' function pointers and make LOCALIO
+ * possible.
+ */
+const struct nfsd_localio_operations *nfs_to;
+EXPORT_SYMBOL_GPL(nfs_to);
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index ec2ab6429e00..c0bd1509ccd4 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -7,6 +7,7 @@ config NFSD
select LOCKD
select SUNRPC
select EXPORTFS
+ select NFS_COMMON
select NFS_ACL_SUPPORT if NFSD_V2_ACL
select NFS_ACL_SUPPORT if NFSD_V3_ACL
depends on MULTIUSER
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index b8736a82e57c..18cbd3fa7691 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_NFS_LOCALIO) += localio.o
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 7bb4f2075ac5..c82d8e3e0d4f 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1074,10 +1074,30 @@ static struct svc_export *exp_find(struct cache_detail *cd,
return exp;
}
+/**
+ * check_nfsd_access - check if access to export is allowed.
+ * @exp: svc_export that is being accessed.
+ * @rqstp: svc_rqst attempting to access @exp (will be NULL for LOCALIO).
+ *
+ * Return values:
+ * %nfs_ok if access is granted, or
+ * %nfserr_wrongsec if access is denied
+ */
__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
{
struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors;
- struct svc_xprt *xprt = rqstp->rq_xprt;
+ struct svc_xprt *xprt;
+
+ /*
+ * If rqstp is NULL, this is a LOCALIO request which will only
+ * ever use a filehandle/credential pair for which access has
+ * been affirmed (by ACCESS or OPEN NFS requests) over the
+ * wire. So there is no need for further checks here.
+ */
+ if (!rqstp)
+ return nfs_ok;
+
+ xprt = rqstp->rq_xprt;
if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) {
if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags))
@@ -1098,17 +1118,17 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
ok:
/* legacy gss-only clients are always OK: */
if (exp->ex_client == rqstp->rq_gssclient)
- return 0;
+ return nfs_ok;
/* ip-address based client; check sec= export option: */
for (f = exp->ex_flavors; f < end; f++) {
if (f->pseudoflavor == rqstp->rq_cred.cr_flavor)
- return 0;
+ return nfs_ok;
}
/* defaults in absence of sec= options: */
if (exp->ex_nflavors == 0) {
if (rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL ||
rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX)
- return 0;
+ return nfs_ok;
}
/* If the compound op contains a spo_must_allowed op,
@@ -1118,7 +1138,7 @@ ok:
*/
if (nfsd4_spo_must_allow(rqstp))
- return 0;
+ return nfs_ok;
denied:
return nfserr_wrongsec;
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 24e8f1fbcebb..19bb88c7eebd 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);
@@ -390,6 +390,34 @@ nfsd_file_put(struct nfsd_file *nf)
nfsd_file_free(nf);
}
+/**
+ * nfsd_file_put_local - put the reference to nfsd_file and local nfsd_serv
+ * @nf: nfsd_file of which to put the references
+ *
+ * First put the reference of the nfsd_file and then put the
+ * reference to the associated nn->nfsd_serv.
+ */
+void
+nfsd_file_put_local(struct nfsd_file *nf)
+{
+ struct net *net = nf->nf_net;
+
+ nfsd_file_put(nf);
+ nfsd_serv_put(net);
+}
+
+/**
+ * nfsd_file_file - get the backing file of an nfsd_file
+ * @nf: nfsd_file of which to access the backing file.
+ *
+ * Return backing file for @nf.
+ */
+struct file *
+nfsd_file_file(struct nfsd_file *nf)
+{
+ return nf->nf_file;
+}
+
static void
nfsd_file_dispose_list(struct list_head *dispose)
{
@@ -982,12 +1010,14 @@ nfsd_file_is_cached(struct inode *inode)
}
static __be32
-nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
+ struct svc_cred *cred,
+ struct auth_domain *client,
+ struct svc_fh *fhp,
unsigned int may_flags, struct file *file,
struct nfsd_file **pnf, bool want_gc)
{
unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
- struct net *net = SVC_NET(rqstp);
struct nfsd_file *new, *nf;
bool stale_retry = true;
bool open_retry = true;
@@ -996,8 +1026,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
int ret;
retry:
- status = fh_verify(rqstp, fhp, S_IFREG,
- may_flags|NFSD_MAY_OWNER_OVERRIDE);
+ if (rqstp) {
+ status = fh_verify(rqstp, fhp, S_IFREG,
+ may_flags|NFSD_MAY_OWNER_OVERRIDE);
+ } else {
+ status = fh_verify_local(net, cred, client, fhp, S_IFREG,
+ may_flags|NFSD_MAY_OWNER_OVERRIDE);
+ }
if (status != nfs_ok)
return status;
inode = d_inode(fhp->fh_dentry);
@@ -1143,7 +1178,8 @@ __be32
nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
+ return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+ fhp, may_flags, NULL, pnf, true);
}
/**
@@ -1167,7 +1203,55 @@ __be32
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
+ return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+ fhp, may_flags, NULL, pnf, false);
+}
+
+/**
+ * nfsd_file_acquire_local - Get a struct nfsd_file with an open file for localio
+ * @net: The network namespace in which to perform a lookup
+ * @cred: the user credential with which to validate access
+ * @client: the auth_domain for LOCALIO lookup
+ * @fhp: the NFS filehandle of the file to be opened
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * This file lookup interface provide access to a file given the
+ * filehandle and credential. No connection-based authorisation
+ * is performed and in that way it is quite different to other
+ * file access mediated by nfsd. It allows a kernel module such as the NFS
+ * client to reach across network and filesystem namespaces to access
+ * a file. The security implications of this should be carefully
+ * considered before use.
+ *
+ * The nfsd_file object returned by this API is reference-counted
+ * and garbage-collected. The object is retained for a few
+ * seconds after the final nfsd_file_put() in case the caller
+ * wants to re-use it.
+ *
+ * Return values:
+ * %nfs_ok - @pnf points to an nfsd_file with its reference
+ * count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
+ */
+__be32
+nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
+ struct auth_domain *client, struct svc_fh *fhp,
+ unsigned int may_flags, struct nfsd_file **pnf)
+{
+ /*
+ * Save creds before calling nfsd_file_do_acquire() (which calls
+ * nfsd_setuser). Important because caller (LOCALIO) is from
+ * client context.
+ */
+ const struct cred *save_cred = get_current_cred();
+ __be32 beres;
+
+ beres = nfsd_file_do_acquire(NULL, net, cred, client,
+ fhp, may_flags, NULL, pnf, true);
+ revert_creds(save_cred);
+ return beres;
}
/**
@@ -1193,7 +1277,8 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct file *file,
struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
+ return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+ fhp, may_flags, file, pnf, false);
}
/*
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 3fbec24eea6c..cadf3c2689c4 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -55,7 +55,9 @@ void nfsd_file_cache_shutdown(void);
int nfsd_file_cache_start_net(struct net *net);
void nfsd_file_cache_shutdown_net(struct net *net);
void nfsd_file_put(struct nfsd_file *nf);
+void nfsd_file_put_local(struct nfsd_file *nf);
struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
+struct file *nfsd_file_file(struct nfsd_file *nf);
void nfsd_file_close_inode_sync(struct inode *inode);
void nfsd_file_net_dispose(struct nfsd_net *nn);
bool nfsd_file_is_cached(struct inode *inode);
@@ -66,5 +68,8 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct file *file,
struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
+ struct auth_domain *client, struct svc_fh *fhp,
+ unsigned int may_flags, struct nfsd_file **pnf);
int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
#endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
new file mode 100644
index 000000000000..291e9c69cae4
--- /dev/null
+++ b/fs/nfsd/localio.c
@@ -0,0 +1,169 @@
+// 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>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+
+#include <linux/exportfs.h>
+#include <linux/sunrpc/svcauth.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
+#include <linux/nfs_common.h>
+#include <linux/nfslocalio.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"
+
+static const struct nfsd_localio_operations nfsd_localio_ops = {
+ .nfsd_serv_try_get = nfsd_serv_try_get,
+ .nfsd_serv_put = nfsd_serv_put,
+ .nfsd_open_local_fh = nfsd_open_local_fh,
+ .nfsd_file_put_local = nfsd_file_put_local,
+ .nfsd_file_file = nfsd_file_file,
+};
+
+void nfsd_localio_ops_init(void)
+{
+ nfs_to = &nfsd_localio_ops;
+}
+
+/**
+ * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file
+ *
+ * @net: 'struct net' to get the proper nfsd_net required for LOCALIO access
+ * @dom: 'struct auth_domain' required for LOCALIO access
+ * @rpc_clnt: rpc_clnt that the client established
+ * @cred: cred that the client established
+ * @nfs_fh: filehandle to lookup
+ * @fmode: fmode_t to use for open
+ *
+ * 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, returned nfsd_file will have its nf_net member
+ * set. Caller (NFS client) is responsible for calling nfsd_serv_put and
+ * nfsd_file_put (via nfs_to->nfsd_file_put_local).
+ */
+struct nfsd_file *
+nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
+ struct rpc_clnt *rpc_clnt, const struct cred *cred,
+ const struct nfs_fh *nfs_fh, const fmode_t fmode)
+{
+ int mayflags = NFSD_MAY_LOCALIO;
+ struct svc_cred rq_cred;
+ struct svc_fh fh;
+ struct nfsd_file *localio;
+ __be32 beres;
+
+ if (nfs_fh->size > NFS4_FHSIZE)
+ return ERR_PTR(-EINVAL);
+
+ /* nfs_fh -> svc_fh */
+ 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;
+
+ svcauth_map_clnt_to_svc_cred_local(rpc_clnt, cred, &rq_cred);
+
+ beres = nfsd_file_acquire_local(net, &rq_cred, dom,
+ &fh, mayflags, &localio);
+ if (beres)
+ localio = ERR_PTR(nfs_stat_to_errno(be32_to_cpu(beres)));
+
+ fh_put(&fh);
+ if (rq_cred.cr_group_info)
+ put_group_info(rq_cred.cr_group_info);
+
+ return localio;
+}
+EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
+
+/*
+ * UUID_IS_LOCAL XDR functions
+ */
+
+static __be32 localio_proc_null(struct svc_rqst *rqstp)
+{
+ return rpc_success;
+}
+
+struct localio_uuidarg {
+ uuid_t uuid;
+};
+
+static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp)
+{
+ struct localio_uuidarg *argp = rqstp->rq_argp;
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ nfs_uuid_is_local(&argp->uuid, &nn->local_clients,
+ net, rqstp->rq_client, THIS_MODULE);
+
+ return rpc_success;
+}
+
+static bool localio_decode_uuidarg(struct svc_rqst *rqstp,
+ struct xdr_stream *xdr)
+{
+ struct localio_uuidarg *argp = rqstp->rq_argp;
+ u8 uuid[UUID_SIZE];
+
+ if (decode_opaque_fixed(xdr, uuid, UUID_SIZE))
+ return false;
+ import_uuid(&argp->uuid, uuid);
+
+ return true;
+}
+
+static const struct svc_procedure localio_procedures1[] = {
+ [LOCALIOPROC_NULL] = {
+ .pc_func = localio_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_UUID_IS_LOCAL] = {
+ .pc_func = localio_proc_uuid_is_local,
+ .pc_decode = localio_decode_uuidarg,
+ .pc_encode = nfssvc_encode_voidres,
+ .pc_argsize = sizeof(struct localio_uuidarg),
+ .pc_argzero = sizeof(struct localio_uuidarg),
+ .pc_ressize = sizeof(struct nfsd_voidres),
+ .pc_cachetype = RC_NOCACHE,
+ .pc_name = "UUID_IS_LOCAL",
+ },
+};
+
+#define LOCALIO_NR_PROCEDURES ARRAY_SIZE(localio_procedures1)
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+ localio_count[LOCALIO_NR_PROCEDURES]);
+const struct svc_version localio_version1 = {
+ .vs_vers = 1,
+ .vs_nproc = LOCALIO_NR_PROCEDURES,
+ .vs_proc = localio_procedures1,
+ .vs_dispatch = nfsd_dispatch,
+ .vs_count = localio_count,
+ .vs_xdrsize = XDR_QUADLEN(UUID_SIZE),
+ .vs_hidden = true,
+};
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 37b8bfdcfeea..26f7b34d1a03 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -13,6 +13,7 @@
#include <linux/filelock.h>
#include <linux/nfs4.h>
#include <linux/percpu_counter.h>
+#include <linux/percpu-refcount.h>
#include <linux/siphash.h>
#include <linux/sunrpc/stats.h>
@@ -139,7 +140,9 @@ struct nfsd_net {
struct svc_info nfsd_info;
#define nfsd_serv nfsd_info.serv
-
+ struct percpu_ref nfsd_serv_ref;
+ struct completion nfsd_serv_confirm_done;
+ struct completion nfsd_serv_free_done;
/*
* clientid and stateid data for construction of net unique COPY
@@ -214,6 +217,10 @@ struct nfsd_net {
/* last time an admin-revoke happened for NFSv4.0 */
time64_t nfs40_last_revoke;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ /* Local clients to be invalidated when net is shut down */
+ struct list_head local_clients;
+#endif
};
/* Simple check to find out if a given net was properly initialized */
@@ -222,6 +229,9 @@ struct nfsd_net {
extern bool nfsd_support_version(int vers);
extern unsigned int nfsd_net_id;
+bool nfsd_serv_try_get(struct net *net);
+void nfsd_serv_put(struct net *net);
+
void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
void nfsd_reset_write_verifier(struct nfsd_net *nn);
#endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 1c9e5b4bcb0a..3adbc05ebaac 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -18,6 +18,7 @@
#include <linux/sunrpc/svc.h>
#include <linux/module.h>
#include <linux/fsnotify.h>
+#include <linux/nfslocalio.h>
#include "idmap.h"
#include "nfsd.h"
@@ -2246,7 +2247,7 @@ 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];
for (i = 0; i < sizeof(nn->nfsd_versions); i++)
nn->nfsd_versions[i] = nfsd_support_version(i);
for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++)
@@ -2257,7 +2258,9 @@ static __net_init int nfsd_net_init(struct net *net)
get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
seqlock_init(&nn->writeverf_lock);
nfsd_proc_stat_init(net);
-
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ INIT_LIST_HEAD(&nn->local_clients);
+#endif
return 0;
out_repcache_error:
@@ -2268,6 +2271,22 @@ out_export_error:
return retval;
}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+/**
+ * nfsd_net_pre_exit - Disconnect localio clients from net namespace
+ * @net: a network namespace that is about to be destroyed
+ *
+ * This invalidated ->net pointers held by localio clients
+ * while they can still safely access nn->counter.
+ */
+static __net_exit void nfsd_net_pre_exit(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ nfs_uuid_invalidate_clients(&nn->local_clients);
+}
+#endif
+
/**
* nfsd_net_exit - Release the nfsd_net portion of a net namespace
* @net: a network namespace that is about to be destroyed
@@ -2285,6 +2304,9 @@ static __net_exit void nfsd_net_exit(struct net *net)
static struct pernet_operations nfsd_net_ops = {
.init = nfsd_net_init,
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+ .pre_exit = nfsd_net_pre_exit,
+#endif
.exit = nfsd_net_exit,
.id = &nfsd_net_id,
.size = sizeof(struct nfsd_net),
@@ -2322,6 +2344,7 @@ static int __init init_nfsd(void)
retval = genl_register_family(&nfsd_nl_family);
if (retval)
goto out_free_all;
+ nfsd_localio_ops_init();
return 0;
out_free_all:
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 4ccbf014a2c7..4b56ba1e8e48 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -85,7 +85,7 @@ 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;
@@ -146,6 +146,10 @@ extern const struct svc_version nfsd_acl_version3;
#endif
#endif
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+extern const struct svc_version localio_version1;
+#endif
+
struct nfsd_net;
enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 50d23d56f403..40ad58a6a036 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -87,23 +87,24 @@ nfsd_mode_check(struct dentry *dentry, umode_t requested)
return nfserr_wrong_type;
}
-static bool nfsd_originating_port_ok(struct svc_rqst *rqstp, int flags)
+static bool nfsd_originating_port_ok(struct svc_rqst *rqstp,
+ struct svc_cred *cred,
+ struct svc_export *exp)
{
- if (flags & NFSEXP_INSECURE_PORT)
+ if (nfsexp_flags(cred, exp) & NFSEXP_INSECURE_PORT)
return true;
/* We don't require gss requests to use low ports: */
- if (rqstp->rq_cred.cr_flavor >= RPC_AUTH_GSS)
+ if (cred->cr_flavor >= RPC_AUTH_GSS)
return true;
return test_bit(RQ_SECURE, &rqstp->rq_flags);
}
static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
+ struct svc_cred *cred,
struct svc_export *exp)
{
- int flags = nfsexp_flags(&rqstp->rq_cred, exp);
-
/* Check if the request originated from a secure port. */
- if (!nfsd_originating_port_ok(rqstp, flags)) {
+ if (rqstp && !nfsd_originating_port_ok(rqstp, cred, exp)) {
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
dprintk("nfsd: request from insecure port %s!\n",
svc_print_addr(rqstp, buf, sizeof(buf)));
@@ -111,7 +112,7 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
}
/* Set user creds for this exportpoint */
- return nfserrno(nfsd_setuser(&rqstp->rq_cred, exp));
+ return nfserrno(nfsd_setuser(cred, exp));
}
static inline __be32 check_pseudo_root(struct dentry *dentry,
@@ -141,7 +142,11 @@ static inline __be32 check_pseudo_root(struct dentry *dentry,
* dentry. On success, the results are used to set fh_export and
* fh_dentry.
*/
-static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
+static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net,
+ struct svc_cred *cred,
+ struct auth_domain *client,
+ struct auth_domain *gssclient,
+ struct svc_fh *fhp)
{
struct knfsd_fh *fh = &fhp->fh_handle;
struct fid *fid = NULL;
@@ -183,8 +188,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
data_left -= len;
if (data_left < 0)
return error;
- exp = rqst_exp_find(&rqstp->rq_chandle, SVC_NET(rqstp),
- rqstp->rq_client, rqstp->rq_gssclient,
+ exp = rqst_exp_find(rqstp ? &rqstp->rq_chandle : NULL,
+ net, client, gssclient,
fh->fh_fsid_type, fh->fh_fsid);
fid = (struct fid *)(fh->fh_fsid + len);
@@ -219,7 +224,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
put_cred(override_creds(new));
put_cred(new);
} else {
- error = nfsd_setuser_and_check_port(rqstp, exp);
+ error = nfsd_setuser_and_check_port(rqstp, cred, exp);
if (error)
goto out;
}
@@ -266,20 +271,20 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
fhp->fh_dentry = dentry;
fhp->fh_export = exp;
- switch (rqstp->rq_vers) {
- case 4:
+ switch (fhp->fh_maxsize) {
+ case NFS4_FHSIZE:
if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
fhp->fh_no_atomic_attr = true;
fhp->fh_64bit_cookies = true;
break;
- case 3:
+ case NFS3_FHSIZE:
if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
fhp->fh_no_wcc = true;
fhp->fh_64bit_cookies = true;
if (exp->ex_flags & NFSEXP_V4ROOT)
goto out;
break;
- case 2:
+ case NFS_FHSIZE:
fhp->fh_no_wcc = true;
if (EX_WGATHER(exp))
fhp->fh_use_wgather = true;
@@ -294,42 +299,33 @@ out:
}
/**
- * fh_verify - filehandle lookup and access checking
- * @rqstp: pointer to current rpc request
+ * __fh_verify - filehandle lookup and access checking
+ * @rqstp: RPC transaction context, or NULL
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @gssclient: RPC GSS auth domain, or NULL
* @fhp: filehandle to be verified
* @type: expected type of object pointed to by filehandle
* @access: type of access needed to object
*
- * Look up a dentry from the on-the-wire filehandle, check the client's
- * access to the export, and set the current task's credentials.
- *
- * Regardless of success or failure of fh_verify(), fh_put() should be
- * called on @fhp when the caller is finished with the filehandle.
- *
- * fh_verify() may be called multiple times on a given filehandle, for
- * example, when processing an NFSv4 compound. The first call will look
- * up a dentry using the on-the-wire filehandle. Subsequent calls will
- * skip the lookup and just perform the other checks and possibly change
- * the current task's credentials.
- *
- * @type specifies the type of object expected using one of the S_IF*
- * constants defined in include/linux/stat.h. The caller may use zero
- * to indicate that it doesn't care, or a negative integer to indicate
- * that it expects something not of the given type.
- *
- * @access is formed from the NFSD_MAY_* constants defined in
- * fs/nfsd/vfs.h.
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
*/
-__be32
-fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+static __be32
+__fh_verify(struct svc_rqst *rqstp,
+ struct net *net, struct svc_cred *cred,
+ struct auth_domain *client,
+ struct auth_domain *gssclient,
+ struct svc_fh *fhp, umode_t type, int access)
{
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct svc_export *exp = NULL;
struct dentry *dentry;
__be32 error;
if (!fhp->fh_dentry) {
- error = nfsd_set_fh_dentry(rqstp, fhp);
+ error = nfsd_set_fh_dentry(rqstp, net, cred, client,
+ gssclient, fhp);
if (error)
goto out;
}
@@ -358,7 +354,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
if (error)
goto out;
- error = nfsd_setuser_and_check_port(rqstp, exp);
+ error = nfsd_setuser_and_check_port(rqstp, cred, exp);
if (error)
goto out;
@@ -388,7 +384,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
skip_pseudoflavor_check:
/* Finally, check access permissions. */
- error = nfsd_permission(&rqstp->rq_cred, exp, dentry, access);
+ error = nfsd_permission(cred, exp, dentry, access);
out:
trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error);
if (error == nfserr_stale)
@@ -396,6 +392,63 @@ out:
return error;
}
+/**
+ * fh_verify_local - filehandle lookup and access checking
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * This API can be used by callers who do not have an RPC
+ * transaction context (ie are not running in an nfsd thread).
+ *
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
+ */
+__be32
+fh_verify_local(struct net *net, struct svc_cred *cred,
+ struct auth_domain *client, struct svc_fh *fhp,
+ umode_t type, int access)
+{
+ return __fh_verify(NULL, net, cred, client, NULL,
+ fhp, type, access);
+}
+
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
+ *
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound. The first call will look
+ * up a dentry using the on-the-wire filehandle. Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
+ *
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h. The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
+ *
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * fs/nfsd/vfs.h.
+ */
+__be32
+fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+{
+ return __fh_verify(rqstp, SVC_NET(rqstp), &rqstp->rq_cred,
+ rqstp->rq_client, rqstp->rq_gssclient,
+ fhp, type, access);
+}
/*
* Compose a file handle for an NFS reply.
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 8d46e203d139..5b7394801dc4 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -217,6 +217,8 @@ extern char * SVCFH_fmt(struct svc_fh *fhp);
* Function prototypes
*/
__be32 fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int);
+__be32 fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *,
+ struct svc_fh *, umode_t, int);
__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
__be32 fh_update(struct svc_fh *);
void fh_put(struct svc_fh *);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index defc430f912f..e236135ddc63 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>
@@ -35,7 +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 *,
@@ -80,6 +80,15 @@ DEFINE_SPINLOCK(nfsd_drc_lock);
unsigned long nfsd_drc_max_mem;
unsigned long nfsd_drc_mem_used;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+static const struct svc_version *localio_versions[] = {
+ [1] = &localio_version1,
+};
+
+#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions)
+
+#endif /* CONFIG_NFS_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)
@@ -90,20 +99,9 @@ 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 = {
- .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[NFSD_MAXVERS+1] = {
@@ -116,18 +114,41 @@ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = {
#endif
};
-struct svc_program nfsd_program = {
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
- .pg_next = &nfsd_acl_program,
-#endif
+struct svc_program nfsd_programs[] = {
+ {
.pg_prog = NFS_PROGRAM, /* program number */
.pg_nvers = NFSD_MAXVERS+1, /* 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_NFS_LOCALIO)
+ {
+ .pg_prog = NFS_LOCALIO_PROGRAM,
+ .pg_nvers = NFSD_LOCALIO_NRVERS,
+ .pg_vers = localio_versions,
+ .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_NFS_LOCALIO */
};
bool nfsd_support_version(int vers)
@@ -193,6 +214,34 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
return 0;
}
+bool nfsd_serv_try_get(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref));
+}
+
+void nfsd_serv_put(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ percpu_ref_put(&nn->nfsd_serv_ref);
+}
+
+static void nfsd_serv_done(struct percpu_ref *ref)
+{
+ struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
+
+ complete(&nn->nfsd_serv_confirm_done);
+}
+
+static void nfsd_serv_free(struct percpu_ref *ref)
+{
+ struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
+
+ complete(&nn->nfsd_serv_free_done);
+}
+
/*
* Maximum number of nfsd processes
*/
@@ -392,6 +441,7 @@ static void nfsd_shutdown_net(struct net *net)
lockd_down(net);
nn->lockd_up = false;
}
+ percpu_ref_exit(&nn->nfsd_serv_ref);
nn->nfsd_net_up = false;
nfsd_shutdown_generic();
}
@@ -471,6 +521,13 @@ 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);
+
+ percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done);
+ wait_for_completion(&nn->nfsd_serv_confirm_done);
+ wait_for_completion(&nn->nfsd_serv_free_done);
+ /* percpu_ref_exit is called in nfsd_shutdown_net */
+
spin_lock(&nfsd_notifier_lock);
nn->nfsd_serv = NULL;
spin_unlock(&nfsd_notifier_lock);
@@ -595,10 +652,18 @@ int nfsd_create_serv(struct net *net)
if (nn->nfsd_serv)
return 0;
+ error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free,
+ 0, GFP_KERNEL);
+ if (error)
+ return error;
+ init_completion(&nn->nfsd_serv_free_done);
+ init_completion(&nn->nfsd_serv_confirm_done);
+
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;
@@ -905,7 +970,7 @@ nfsd(void *vrqstp)
}
/**
- * nfsd_dispatch - Process an NFS or NFSACL Request
+ * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request
* @rqstp: incoming request
*
* This RPC dispatcher integrates the NFS server's duplicate reply cache.
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 7ab66497e261..c625966cfcf3 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(
@@ -193,7 +194,7 @@ TRACE_EVENT(nfsd_compound_encode_err,
{ S_IFIFO, "FIFO" }, \
{ S_IFSOCK, "SOCK" })
-TRACE_EVENT(nfsd_fh_verify,
+TRACE_EVENT_CONDITION(nfsd_fh_verify,
TP_PROTO(
const struct svc_rqst *rqstp,
const struct svc_fh *fhp,
@@ -201,6 +202,7 @@ TRACE_EVENT(nfsd_fh_verify,
int access
),
TP_ARGS(rqstp, fhp, type, access),
+ TP_CONDITION(rqstp != NULL),
TP_STRUCT__entry(
__field(unsigned int, netns_ino)
__sockaddr(server, rqstp->rq_xprt->xpt_remotelen)
@@ -239,7 +241,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify_err,
__be32 error
),
TP_ARGS(rqstp, fhp, type, access, error),
- TP_CONDITION(error),
+ TP_CONDITION(rqstp != NULL && error),
TP_STRUCT__entry(
__field(unsigned int, netns_ino)
__sockaddr(server, rqstp->rq_xprt->xpt_remotelen)
@@ -295,12 +297,13 @@ DECLARE_EVENT_CLASS(nfsd_fh_err_class,
__entry->status)
)
-#define DEFINE_NFSD_FH_ERR_EVENT(name) \
-DEFINE_EVENT(nfsd_fh_err_class, nfsd_##name, \
- TP_PROTO(struct svc_rqst *rqstp, \
- struct svc_fh *fhp, \
- int status), \
- TP_ARGS(rqstp, fhp, status))
+#define DEFINE_NFSD_FH_ERR_EVENT(name) \
+DEFINE_EVENT_CONDITION(nfsd_fh_err_class, nfsd_##name, \
+ TP_PROTO(struct svc_rqst *rqstp, \
+ struct svc_fh *fhp, \
+ int status), \
+ TP_ARGS(rqstp, fhp, status), \
+ TP_CONDITION(rqstp != NULL))
DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badexport);
DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badhandle);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 01947561d375..3ff146522556 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -33,6 +33,8 @@
#define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+#define NFSD_MAY_LOCALIO 0x2000 /* for tracing, reflects when localio used */
+
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index ceb70a926b95..9ad727ddfedb 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -8,11 +8,20 @@
#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>
#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_UUID_IS_LOCAL 1
+
/*
* This is the kernel NFS client file handle representation
*/
diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h
new file mode 100644
index 000000000000..5fc02df88252
--- /dev/null
+++ b/include/linux/nfs_common.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains constants and methods used by both NFS client and server.
+ */
+#ifndef _LINUX_NFS_COMMON_H
+#define _LINUX_NFS_COMMON_H
+
+#include <linux/errno.h>
+#include <uapi/linux/nfs.h>
+
+/* Mapping from NFS error code to "errno" error code. */
+#define errno_NFSERR_IO EIO
+
+int nfs_stat_to_errno(enum nfs_stat status);
+int nfs4_stat_to_errno(int stat);
+
+#endif /* _LINUX_NFS_COMMON_H */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 1df86ab98c77..853df3fcd4c2 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>
@@ -49,6 +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 */
@@ -125,6 +127,13 @@ 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;
+ nfs_uuid_t cl_uuid;
+ spinlock_t cl_localio_lock;
+#endif /* CONFIG_NFS_LOCALIO */
};
/*
@@ -158,6 +167,7 @@ struct nfs_server {
#define NFS_MOUNT_WRITE_WAIT 0x02000000
#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000
#define NFS_MOUNT_SHUTDOWN 0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE 0x10000000
unsigned int fattr_valid; /* Valid attributes */
unsigned int caps; /* server capabilities */
@@ -234,8 +244,7 @@ struct nfs_server {
/* the following fields are protected by nfs_client->cl_lock */
struct rb_root state_owners;
#endif
- struct ida openowner_id;
- struct ida lockowner_id;
+ atomic64_t owner_ctr;
struct list_head state_owners_lru;
struct list_head layouts;
struct list_head delegations;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 45623af3e7b8..12d8e47bc5a3 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -446,7 +446,7 @@ struct nfs42_clone_res {
struct stateowner_id {
__u64 create_time;
- __u32 uniquifier;
+ __u64 uniquifier;
};
struct nfs4_open_delegation {
@@ -1854,6 +1854,24 @@ struct nfs_rpc_ops {
};
/*
+ * 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
*/
extern const struct nfs_rpc_ops nfs_v2_clientops;
@@ -1866,4 +1884,4 @@ 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 */
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
new file mode 100644
index 000000000000..b353abe00357
--- /dev/null
+++ b/include/linux/nfslocalio.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+#ifndef __LINUX_NFSLOCALIO_H
+#define __LINUX_NFSLOCALIO_H
+
+/* nfsd_file structure is purposely kept opaque to NFS client */
+struct nfsd_file;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/uuid.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svcauth.h>
+#include <linux/nfs.h>
+#include <net/net_namespace.h>
+
+/*
+ * 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;
+ struct list_head list;
+ struct net __rcu *net; /* nfsd's network namespace */
+ struct auth_domain *dom; /* auth_domain for localio */
+} nfs_uuid_t;
+
+void nfs_uuid_begin(nfs_uuid_t *);
+void nfs_uuid_end(nfs_uuid_t *);
+void nfs_uuid_is_local(const uuid_t *, struct list_head *,
+ struct net *, struct auth_domain *, struct module *);
+void nfs_uuid_invalidate_clients(struct list_head *list);
+void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid);
+
+/* localio needs to map filehandle -> struct nfsd_file */
+extern struct nfsd_file *
+nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *,
+ const struct cred *, const struct nfs_fh *,
+ const fmode_t) __must_hold(rcu);
+
+struct nfsd_localio_operations {
+ bool (*nfsd_serv_try_get)(struct net *);
+ void (*nfsd_serv_put)(struct net *);
+ struct nfsd_file *(*nfsd_open_local_fh)(struct net *,
+ struct auth_domain *,
+ struct rpc_clnt *,
+ const struct cred *,
+ const struct nfs_fh *,
+ const fmode_t);
+ void (*nfsd_file_put_local)(struct nfsd_file *);
+ struct file *(*nfsd_file_file)(struct nfsd_file *);
+} ____cacheline_aligned;
+
+extern void nfsd_localio_ops_init(void);
+extern const struct nfsd_localio_operations *nfs_to;
+
+struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
+ struct rpc_clnt *, const struct cred *,
+ const struct nfs_fh *, const fmode_t);
+
+#else /* CONFIG_NFS_LOCALIO */
+static inline void nfsd_localio_ops_init(void)
+{
+}
+#endif /* CONFIG_NFS_LOCALIO */
+
+#endif /* __LINUX_NFSLOCALIO_H */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 0c77ba488bba..fec1e8a1570c 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -151,13 +151,15 @@ struct rpc_task_setup {
#define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT)
#define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE)
-#define RPC_TASK_RUNNING 0
-#define RPC_TASK_QUEUED 1
-#define RPC_TASK_ACTIVE 2
-#define RPC_TASK_NEED_XMIT 3
-#define RPC_TASK_NEED_RECV 4
-#define RPC_TASK_MSG_PIN_WAIT 5
-#define RPC_TASK_SIGNALLED 6
+enum {
+ RPC_TASK_RUNNING,
+ RPC_TASK_QUEUED,
+ RPC_TASK_ACTIVE,
+ RPC_TASK_NEED_XMIT,
+ RPC_TASK_NEED_RECV,
+ RPC_TASK_MSG_PIN_WAIT,
+ RPC_TASK_SIGNALLED,
+};
#define rpc_test_and_set_running(t) \
test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index c419a61f60e5..e68fecf6eab5 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -67,9 +67,10 @@ 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
@@ -360,10 +361,9 @@ 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 */
@@ -441,6 +441,7 @@ bool svc_rqst_replace_page(struct svc_rqst *rqstp,
void svc_rqst_release_pages(struct svc_rqst *rqstp);
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/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 63cf6fb26dcc..2e111153f7cd 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -14,6 +14,7 @@
#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/gss_api.h>
+#include <linux/sunrpc/clnt.h>
#include <linux/hash.h>
#include <linux/stringhash.h>
#include <linux/cred.h>
@@ -157,6 +158,10 @@ extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp);
extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops);
extern void svc_auth_unregister(rpc_authflavor_t flavor);
+extern void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt,
+ const struct cred *,
+ struct svc_cred *);
+
extern struct auth_domain *unix_domain_find(char *name);
extern void auth_domain_put(struct auth_domain *item);
extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 95ff74706104..4f31e73dc34d 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -731,11 +731,10 @@ static bool cache_defer_req(struct cache_req *req, struct cache_head *item)
static void cache_revisit_request(struct cache_head *item)
{
struct cache_deferred_req *dreq;
- struct list_head pending;
struct hlist_node *tmp;
int hash = DFR_HASH(item);
+ LIST_HEAD(pending);
- INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash)
@@ -756,10 +755,8 @@ static void cache_revisit_request(struct cache_head *item)
void cache_clean_deferred(void *owner)
{
struct cache_deferred_req *dreq, *tmp;
- struct list_head pending;
+ LIST_HEAD(pending);
-
- INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) {
@@ -1085,9 +1082,8 @@ static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch)
{
struct cache_queue *cq, *tmp;
struct cache_request *cr;
- struct list_head dequeued;
+ LIST_HEAD(dequeued);
- INIT_LIST_HEAD(&dequeued);
spin_lock(&queue_lock);
list_for_each_entry_safe(cq, tmp, &detail->queue, list)
if (!cq->reader) {
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 09f29a95f2bc..0090162ee8c3 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -48,13 +48,8 @@
# define RPCDBG_FACILITY RPCDBG_CALL
#endif
-/*
- * All RPC clients are linked into this list
- */
-
static DECLARE_WAIT_QUEUE_HEAD(destroy_wait);
-
static void call_start(struct rpc_task *task);
static void call_reserve(struct rpc_task *task);
static void call_reserveresult(struct rpc_task *task);
@@ -546,7 +541,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
.connect_timeout = args->connect_timeout,
.reconnect_timeout = args->reconnect_timeout,
};
- char servername[48];
+ char servername[RPC_MAXNETNAMELEN];
struct rpc_clnt *clnt;
int i;
@@ -1893,12 +1888,6 @@ call_allocate(struct rpc_task *task)
if (req->rq_buffer)
return;
- if (proc->p_proc != 0) {
- BUG_ON(proc->p_arglen == 0);
- if (proc->p_decode != NULL)
- BUG_ON(proc->p_replen == 0);
- }
-
/*
* Calculate the size (in quads) of the RPC call
* and reply headers, and convert both values
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9aff845196ce..7e7f4e0390c7 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);
@@ -1148,15 +1153,16 @@ 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,
@@ -1208,13 +1214,14 @@ 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;
@@ -1320,7 +1327,7 @@ 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 */
@@ -1344,9 +1351,12 @@ 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 53ebc719ff5a..43c57124de52 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.c b/net/sunrpc/svcauth.c
index 93d9e949e265..55b4d2874188 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -18,6 +18,7 @@
#include <linux/sunrpc/svcauth.h>
#include <linux/err.h>
#include <linux/hash.h>
+#include <linux/user_namespace.h>
#include <trace/events/sunrpc.h>
@@ -175,6 +176,33 @@ rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp)
}
EXPORT_SYMBOL_GPL(svc_auth_flavor);
+/**
+ * svcauth_map_clnt_to_svc_cred_local - maps a generic cred
+ * to a svc_cred suitable for use in nfsd.
+ * @clnt: rpc_clnt associated with nfs client
+ * @cred: generic cred associated with nfs client
+ * @svc: returned svc_cred that is suitable for use in nfsd
+ */
+void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt,
+ const struct cred *cred,
+ struct svc_cred *svc)
+{
+ struct user_namespace *userns = clnt->cl_cred ?
+ clnt->cl_cred->user_ns : &init_user_ns;
+
+ memset(svc, 0, sizeof(struct svc_cred));
+
+ svc->cr_uid = KUIDT_INIT(from_kuid_munged(userns, cred->fsuid));
+ svc->cr_gid = KGIDT_INIT(from_kgid_munged(userns, cred->fsgid));
+ svc->cr_flavor = clnt->cl_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(svcauth_map_clnt_to_svc_cred_local);
+
/**************************************************
* 'auth_domains' are stored in a hash table indexed by name.
* When the last reference to an 'auth_domain' is dropped,
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)