| Age | Commit message (Collapse) | Author |
|---|
|
# Conflicts:
# drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
# net/ceph/osd_client.c
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
|
|
The xpt_reserved counter exists for UDP socket-buffer back-pressure.
svc_udp_has_wspace() is the only has_wspace implementation that
consults it, so on TCP and RDMA the counter is maintained and never
read. svc_handle_xprt() adds to it once per RPC. svc_reserve()
shrinks it again on each call from svc_process_common(), from
svc_xprt_release(), and from each proc function that calls
svc_reserve_auth(). Every shrinking call also runs
svc_xprt_resource_released(), which issues an smp_mb() and can
enqueue the transport.
Add an xcl_flags field to svc_xprt_class and set
SVC_XPRT_FLAG_WSPACE_RESERVE on the UDP class. Gate the xpt_reserved
accounting on that flag.
After the change, svc_reserve() no longer calls
svc_xprt_resource_released() on TCP and RDMA. Two paths still cover
that enqueue. svc_xprt_release() reaches the helper through
svc_xprt_release_slot(), and svc_xprt_received() enqueues a transport
whose XPT_DATA remains set.
Link: https://patch.msgid.link/20260828135036.796842-4-cel@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_rdma_wc_receive() and svc_rdma_wc_read_done() set XPT_DATA after
adding a completed context to sc_rq_dto_q or sc_read_complete_q.
svc_rdma_recvfrom() dequeues one context and leaves XPT_DATA set, so
the svc_xprt_received() that follows re-enqueues the transport and
svc_xprt_enqueue() dispatches a second thread. That thread finds both
queues empty and returns zero.
Recheck the receive queues after each dequeue and clear XPT_DATA when
the last context is taken, rather than only when a dequeue finds
nothing. svc_xprt_received()'s kernel-doc no longer describes every
transport, so relax its note about when XPT_DATA is cleared.
Measured on one NFSv4.2 connection over 100GbE RoCE. A 4KB random read
at queue depth 1 falls from 2.997 transport dequeues per RPC to 1.998,
and from 96,629 to 82,398 server cycles per RPC. A 256KB random write
falls from 3.270 dequeues to 2.004, and from 259,936 to 246,059 cycles.
Each dispatch removed is worth about 10,000 cycles.
The gain shrinks as the receive queues fill, since a leftover XPT_DATA
then dispatches a thread that finds real work. An 8KB random write at
queue depth 512 already runs at the two dequeues an RPC with a Read
chunk requires, and shows no change. Throughput moves only where the
server has no idle CPU to absorb the saving, so only the queue depth 1
read gains, by 1.8%.
One dispatch per RPC remains. svc_rdma_send_ctxt_put() sets XPT_DATA to
schedule a drain of sc_send_release_list, and svc_rdma_recvfrom() does
not service that list.
Link: https://patch.msgid.link/20260828135036.796842-3-cel@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_rdma_accept() computes sc_fc_credits from sc_max_requests before
the Receive Queue depth is checked against the device's max_qp_wr.
When that check lowers sc_max_requests, the credit grant keeps the
original value, so the server advertises more credits than it has
Receives posted. A client that uses the full grant overruns the
Receive Queue, and the connection is lost with an RNR error.
Set sc_fc_credits after the clamp so the grant matches the number
of Receives the server posts.
Fixes: fc2e69db82c1 ("svcrdma: Clean up comment in svc_rdma_accept()")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260828135036.796842-2-cel@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_recvfrom() parses the RPC record stream with ->read_sock,
which calls neither security_socket_recvmsg() nor the
sock:sock_recv_length tracepoint. svc_tcp_recv_cmsg() still goes
through sock_recvmsg(), so an LSM mediates only the TLS control
records on a server socket, and sock:sock_recv_length reports only
those. Partial coverage is worse than none. It makes the RPC stream
look mediated and observed when it is not.
Until the record stream moved to ->read_sock, an LSM saw every octet
NFSD read from a TCP socket. An SELinux policy that denies
SOCKET__READ to NFSD blocked the receive. After this change no call
on the server's TCP receive path consults an LSM, so that denial has
no effect.
Dispatch ->recvmsg directly so the whole receive path behaves one
way. sock_recvmsg_nosec() reaches ->recvmsg through
INDIRECT_CALL_INET(), so on a retpoline build the direct dispatch
costs one indirect call per control record. Control records are rare
on an established connection.
Link: https://patch.msgid.link/20260821-tls-read-sock-2-v1-5-7ffce164eb45@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_recvfrom() reads an RPC record with two recvmsg() calls, one
for the four-octet fragment marker and one for the body. Neither
supplies a control-message buffer, so kTLS reports a TLS control
record on either one by raising MSG_CTRUNC and delivering nothing.
Both receives have to recognize that outcome and hand off to a
recovery path that re-reads the record. Commit bee47cb026e7 ("sunrpc:
fix handling of server side tls alerts") built that recovery path. It
stays on both receives for as long as one recvmsg() serves data and
control alike.
Instead, parse the record stream in a ->read_sock actor. The data
path then carries no control-message buffer at all. A control record
at the head stops ->read_sock short, so svc_tcp_recv_ctrl_record()
classifies the head of the receive queue with MSG_PEEK before
consuming anything.
skb_copy_bits() walks an skb from its head to reach the copy offset,
so an actor that copies a page at a time rewalks a large GRO or kTLS
skb once per page. Copy each callback's share of the record into
rq_bvec with one skb_copy_datagram_iter() instead.
A non-final fragment carries four octets of marker and may carry no
payload. sk_datalen advances only by the payload, so neither a run
of empty fragments nor a run of one-octet fragments trips the
sv_max_mesg check before desc->count runs out. Only desc->count
bounds such a run, four or five octets at a time. Cap the fragments
per socket-lock hold.
recvmsg() skips an urgent octet and clears the condition, so the old
receive path advanced past it. ->read_sock consumes what precedes
the urgent octet and then stops there for good. The data path calls
no recvmsg() now, so the record stream cannot advance again. An RPC
stream carries no urgent data, so close the connection. The read
that first reaches the mark returns a positive count, so a
zero-length read does not mark the stop. Key the close on an
incomplete record.
Link: https://patch.msgid.link/20260821-tls-read-sock-2-v1-4-7ffce164eb45@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_read_msg() flushes the destination pages after every
receive. A record that arrives in several pieces is therefore
flushed once per piece. A page spanning two pieces is flushed
twice. Nothing reads the message body before the record is
complete, so no reader needs the intermediate flushes.
Flush every page of the record in one pass from svc_tcp_recvfrom(),
once the last fragment has arrived. Remove svc_flush_bvec() and its
ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE guard. The guard avoided setting
up a bvec iterator, and a plain walk of rq_pages compiles away on
its own where flush_dcache_page() is an empty inline.
Link: https://patch.msgid.link/20260821-tls-read-sock-2-v1-3-7ffce164eb45@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_sock_recv_cmsg() drains a TLS record that is neither an alert
nor application data, then returns -EAGAIN so the receive loop retries.
It runs only on an established TLS session. A handshake record there
carries a post-handshake message, and the server has no handler for
one. Draining a KeyUpdate only delays the close. kTLS sets
key_update_pending when it decrypts that record, and a later receive
returns -EKEYEXPIRED. kTLS flags only a KeyUpdate, so any other
post-handshake message disappears and the connection keeps running.
Return -EPROTO for an unhandled record type. Any error but -EAGAIN
closes the transport. An application data record keeps its -EAGAIN
return. No NFS client is known to send a handshake record on an
established connection.
Link: https://patch.msgid.link/20260821-tls-read-sock-2-v1-2-7ffce164eb45@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_sock_recv_cmsg() receives the record at the head of the kTLS
receive queue and decides what its content type means for the
transport. The receive and the decision are one step, so a caller
cannot learn a record's type without also acting on it. A later
caller classifies the head of the queue with MSG_PEEK before it
decides whether to consume the record. It needs the receive without
the decision.
Move the receive into svc_tcp_recv_cmsg(), which takes the recvmsg()
flags and reports the octet count, the record type, and the message
flags. The alert policy stays in svc_tcp_sock_recv_cmsg(), the
helper's only caller in this patch.
The zeroed control buffer replaces the msg_controllen check. An
unfilled buffer reports record type zero, so a positive octet count
with no record type now returns -EBADMSG instead of a count. The
alert parse runs on a second msghdr over the alert buffer, so the
copy and the parse share no iterator state. The rewind that commit
bee47cb026e7 ("sunrpc: fix handling of server side tls alerts")
added by hand is no longer needed.
Link: https://patch.msgid.link/20260821-tls-read-sock-2-v1-1-7ffce164eb45@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
xs_sock_process_cmsg() switches on the TLS record type, and every arm
but TLS_RECORD_TYPE_ALERT returns the -EAGAIN its caller passed in.
The DATA arm clears MSG_EOR in the caller's msghdr, but
xs_sock_recvmsg() has already cleared that flag before the call.
Deriving the record type a second time inside the helper also fires
trace_tls_contenttype() twice for every alert.
Move the alert handling into xs_sock_recv_cmsg() and delete the
helper. Every other record type still returns -EAGAIN. The DATA arm's
account of MSG_EOR moves to xs_sock_recvmsg(), where the flag is
cleared.
Signed-off-by: Chuck Lever <cel@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@hammerspace.com>
|
|
xs_sock_process_cmsg() decides whether an alert ends the session by
reading the alert's level octet. RFC 8446 Section 6 retired that
field. The severity is implicit in the description, and a receiver
treats every alert listed in Section 6.2 as an error alert
"regardless of the AlertLevel in the message". A peer that aborts
with unexpected_message but leaves the legacy octet set to warning
makes the client return -EAGAIN. xs_stream_data_receive() wakes no
pending task for that error, so RPC Calls queued on a dead TLS
session wait for their timeouts to expire.
Decide from the alert description instead. close_notify and
user_canceled are the closure alerts (RFC 8446 Section 6.1). Every
other description ends the session, including one this kernel does
not recognize.
Fixes: 39067dda1d86 ("SUNRPC: Use new helpers to handle TLS Alerts")
Signed-off-by: Chuck Lever <cel@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@hammerspace.com>
|
|
tls_alert_recv() reads two octets from the kvec it is handed and does
not check the length (net/handshake/alert.c). xs_sock_process_cmsg()
calls it for any alert record, and the alert[] buffer that
xs_sock_recv_cmsg() supplies carries no initializer. A one-octet alert
body leaves the description read from uninitialized stack and reported
through trace_tls_alert_recv().
The peer controls that length. Neither tls_rx_msg_size() nor
tls_rx_one_record() enforces the two-octet Alert payload. A TLS 1.3
record carrying only the inner content-type octet decrypts to a
zero-length payload. RFC 8446 Section 5.1 requires a record with an
Alert type to carry exactly one message, so any other length is
malformed. RFC 9289 Section 5 bars RPC-with-TLS from negotiating a
version below TLS 1.3, so no other alert framing applies.
Require exactly two octets before parsing and return -EACCES
otherwise. xs_stream_data_receive() already treats -EACCES as a fatal
alert and reports it to the pending tasks. Gate the path on a control
message rather than a positive count so that a zero-length record
reaches the check.
Fixes: cc5d59081fa2 ("sunrpc: fix client side handling of tls alerts")
Signed-off-by: Chuck Lever <cel@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@hammerspace.com>
|
|
Writing the same socket descriptor to /proc/fs/nfsd/portlist twice
attaches a second svc_sock to one socket. svc_setup_socket() saves
the socket's callbacks before installing its own, so the second
attach records svc_write_space() as the old write_space callback.
svc_udp_init() invokes that callback by way of svc_sock_setbufsize(),
and svc_write_space() then calls itself until the kernel stack is
exhausted:
BUG: TASK stack guard page was hit at ffffc900037d7ff8
svc_write_space+0x90/0x2b0 net/sunrpc/svcsock.c:429
svc_write_space+0xe6/0x2b0 net/sunrpc/svcsock.c:430
... 700 more ...
svc_sock_setbufsize+0x18d/0x220 net/sunrpc/svcsock.c:386
svc_udp_init net/sunrpc/svcsock.c:854 [inline]
svc_setup_socket+0xb2f/0x1090 net/sunrpc/svcsock.c:1498
svc_addsock+0x2fd/0x760 net/sunrpc/svcsock.c:1547
__write_ports_addfd fs/nfsd/nfsctl.c:742 [inline]
write_ports+0xa5b/0xcc0 fs/nfsd/nfsctl.c:861
nfsctl_transaction_write+0x106/0x1a0 fs/nfsd/nfsctl.c:112
svc_data_ready() and svc_tcp_state_change() chain through their saved
callbacks the same way, so a TCP descriptor added twice recurses on
the next incoming segment instead. Reaching any of this takes a
writer on portlist, and the nfsd filesystem sets no FS_USERNS_MOUNT,
so the reproducer needs CAP_SYS_ADMIN in the initial user namespace.
Reject a socket that already carries sk_user_data. svc_setup_socket()
overwrites that field unconditionally, so a socket some other
consumer has claimed is one NFSD would corrupt whether or not the
callbacks recurse.
Fixes: b41b66d63c73 ("[PATCH] knfsd: allow sockets to be passed to nfsd via 'portlist'")
Cc: stable@vger.kernel.org
Reported-by: syzbot+54cdc566f64abf51b7f1@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=54cdc566f64abf51b7f1
Link: https://patch.msgid.link/20260815162844.8219-1-cel@kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
The unix_gid netlink upcall protocol has an explicit
SUNRPC_A_UNIX_GID_NEGATIVE attribute for failed group lookups, and
mountd sends it, but sunrpc_nl_parse_one_unix_gid() only allocates
an empty group list for a flagged reply without propagating the
flag into the entry, so it installs a valid positive entry with
zero groups. Such an entry strips the uid of all supplementary
groups until it is refreshed or expires: the same defect the
previous patch fixes on the classic channel, on a transport that
can say "lookup failed" explicitly.
Set CACHE_NEGATIVE for flagged replies, as the netlink ip_map
path already does for its negative flag. An empty GIDS list
without the flag remains a positive entry.
Fixes: 0850e8603cd7 ("sunrpc: add netlink upcall for the auth.unix.gid cache")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-fable-5
Signed-off-by: Ameer Hamza <ameer.hamza@truenas.com>
Link: https://patch.msgid.link/20260814221953.108837-3-ameer.hamza@truenas.com
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
When rpc.mountd cannot resolve a uid (getpwuid() or getgrouplist()
failure, e.g. while winbind or sssd is briefly unreachable), it
answers the auth.unix.gid upcall with zero groups. unix_gid_parse()
installs that as a valid positive entry, and svcauth_unix_set_client()
then replaces the credential's group list with the empty one on
every request, RPCSEC_GSS included via svcauth_gss_set_client().
One failed lookup strips that uid of all supplementary groups on
every export for up to mountd's configured TTL (30 minutes by
default), long after the NSS backend has recovered.
mountd cannot send an empty list for a successful lookup, since
getgrouplist(3) always includes at least the user's primary group,
so a zero-group reply can only mean the lookup failed. Record it as
a negative entry: unix_gid_find() then returns -ENOENT and
svcauth_unix_set_client() keeps the groups the RPC credential
already carries. This is the fallback that
commit 3fc605a2aa38 ("[PATCH] knfsd: allow the server to provide a
gid list when using AUTH_UNIX authentication") promised when no
answer is available, and the same state try_to_negate_entry()
already creates when no listener holds the channel open.
Fixes: 3fc605a2aa38 ("[PATCH] knfsd: allow the server to provide a gid list when using AUTH_UNIX authentication")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-fable-5
Signed-off-by: Ameer Hamza <ameer.hamza@truenas.com>
Link: https://patch.msgid.link/20260814221953.108837-2-ameer.hamza@truenas.com
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
A TLS control record delivers no payload to the RPC layer.
svc_tcp_recvfrom() clears XPT_DATA before the receive, and
svc_tcp_sock_recv_cmsg() returns -EAGAIN for the record it consumed.
Nothing marks the transport ready again. kTLS raises data_ready for
arriving TCP segments, not for records it has already decrypted. An
RPC Call queued behind an alert or a KeyUpdate waits until the client
sends more. The client blocks until its RPC timeout expires.
The receive takes only the first two octets of the record. kTLS holds
the remainder on its receive list, where each later receive takes two
octets more.
Drain a record that is not an alert, then mark the transport ready
once a control record has been consumed.
Fixes: 5e052dda121e ("SUNRPC: Recognize control messages in server-side TCP socket code")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260808-svcsock-cmsg-fixes-v3-4-62d9a631c880@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_sock_process_cmsg() decides whether an alert ends the session
by reading the alert's level octet. RFC 8446 Section 6 retired that
field. The severity is implicit in the description, and a receiver
treats every alert listed in Section 6.2 as an error alert
"regardless of the AlertLevel in the message". A peer that aborts
with unexpected_message but leaves the legacy octet set to warning
makes the server return -EAGAIN. svc_tcp_recvfrom() then leaves a
dead TLS session attached to an open transport. NFSD keeps polling
it.
Decide from the alert description instead. close_notify and
user_canceled are the closure alerts (RFC 8446 Section 6.1). Every
other description ends the session, including one this kernel does
not recognize.
Fixes: 39067dda1d86 ("SUNRPC: Use new helpers to handle TLS Alerts")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260808-svcsock-cmsg-fixes-v3-3-62d9a631c880@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
tls_alert_recv() reads two octets from the kvec it is handed and does
not check the length (net/handshake/alert.c). svc_tcp_sock_recv_cmsg()
calls it for any positive receive, and the alert[] buffer it supplies
carries no initializer. A one-octet alert body leaves the description
read from uninitialized stack and reported through
trace_tls_alert_recv().
The peer controls that length. Neither tls_rx_msg_size() nor
tls_rx_one_record() enforces the two-octet Alert payload. A TLS 1.3
record carrying only the inner content-type octet decrypts to a
zero-length payload. RFC 8446 Section 5.1 requires a record with an
Alert type to carry exactly one message, so any other length is
malformed.
Require exactly two octets before parsing and return -EBADMSG
otherwise. That closes the transport rather than acting on a partly
uninitialized alert. Gate the path on a control message rather than a
positive count so that a zero-length record reaches the check.
Fixes: bee47cb026e7 ("sunrpc: fix handling of server side tls alerts")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260808-svcsock-cmsg-fixes-v3-2-62d9a631c880@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_tcp_sock_recv_cmsg() receives up to two octets into a local
buffer, and returns that count for any record type other than
TLS_RECORD_TYPE_ALERT. Nothing reached the caller's buffer, but
svc_tcp_read_marker() adds the count to sk_tcplen and
svc_tcp_read_msg()'s caller adds it to sk_datalen. The RPC stream
advances over octets it never received. The fragment marker is
assembled from stale sk_marker octets. The message body comes from
pages nothing wrote.
A conforming client reaches this. RFC 8446 Section 4.6.3 lets either
peer send KeyUpdate once it has sent its Finished, and svcsock has no
rekey path. kTLS leaves the partially consumed record on ctx->rx_list,
so the body drains two octets per svc_tcp_recvfrom() call. Each pair
is credited the same way.
Return -EAGAIN for a record that is not an alert. That is what
svc_tcp_sock_process_cmsg()'s default arm returned before the receive
moved into a local buffer.
Fixes: bee47cb026e7 ("sunrpc: fix handling of server side tls alerts")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260808-svcsock-cmsg-fixes-v3-1-62d9a631c880@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
This is another run of the Coccinelle script for converting kmalloc()
family of allocations to kmalloc_obj() via the existing rules in
scripts/coccinelle/api/kmalloc_objs.cocci
This catches both the set of kmalloc() uses added since the first
kmalloc_obj() conversions in v7.0 and adds a large group missed in the
first pass due to Coccinelle not interacting well with the cleanup.h
scoped_...() family of macros[1]. I worked around this with spatch's
"--macro-file" argument to a file with all the scoped_...() macros mapped
to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control
flow indicator I could find.
Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc,
riscv, and s390 with no new warnings.
Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1]
Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2]
Signed-off-by: Kees Cook <kees+treewide@kernel.org>
|
|
Pull NFS client updates from Trond Myklebust:
"Highlights include:
Stable fixes:
- Use-after-free fixes for the sunrpc client code
- Delegation hash table leak
- NULL dereference on lockowner allocation failure
- Fix a handshake completion race in the TLS code
- Fix an error sign checking issue when deciding whether the pNFS
layout is still in use, or can be returned
- Fix a layout segment leak in pnfs_layout_process()
Other bugfixes:
- Fix a missing NULL check in the rpcbind client
- annotate shared socket callbacks with READ_ONCE/WRITE_ONCE
- nfs_inode_set_delegation() error paths should return the delegation
- Use clear_and_wake_up_bit() in nfs_clear_invalid_mapping() and the
pNFS code.
- Fix the nfs4_alloc_client() error paths to free the IDR allocation
- fix folio dereference before NULL check in
nfs_inode_remove_request()
- Fix delayed delegation return
- Fix another state manager race with umount
- Fix device leaks on parse failure
- Avoid cancelling in-flight I/O during a layout recall if the server
doesn't require it
- flexfiles: report cancelled I/O as a layout error
- flexfiles: fix NULL dereference for NFSv4.0 data servers
- Fix incorrect argument passed to nfs4_delete_lease()
- Fix several symlink issues resulting from nfs_atomic_open_v23()
- Fix an uninitialised variable issue in the NFSv4.1 callback code
- fix LAYOUTSTATS send buffer exhaustion
Features and cleanups:
- NFSv4.2: Allow the server to specify that file data may not be cached
- localio: optimise I/O submission when when not doing memory reclaim
- localio: Remove duplicate wait code in nfs_local_commit
- flexfiles: support loosely coupled NFSv4.x data servers
- pNFS: key the data server cache on the NFS version"
* tag 'nfs-for-7.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (33 commits)
NFSv4.1: fix layout segment leak on the pnfs_layout_process() forget path
NFSv4/pnfs: key the data server cache on the NFS version
NFSv4.2: fix LAYOUTSTATS send buffer exhaustion
pNFS: Fix EBUSY check in pnfs_layout_need_return
NFSv4.1: zero referring call lists before decoding
nfs: fix ENXIO on O_CREAT open of existing symlink over NFSv3
SUNRPC: wait for in-flight client TLS handshake callback
NFSv4: Fix incorrect argument passed to nfs4_delete_lease() in nfs4_add_lease()
lockd: fix NULL dereference on lockowner allocation failure
NFS: fix delegation_hash_table leak when nfs4_server_common_setup() fails
NFSv4/flexfiles: support loosely coupled data servers
NFSv4/flexfiles: fix NULL dereference for NFSv4.0 data servers
NFSv4: pin the superblock for active state owners
sunrpc: fix use-after-free in __rpc_clnt_handle_event and __rpc_clnt_remove_pipedir
NFS/localio: issue commit inline when not in a memory-reclaim context
NFS/localio: remove dead FLUSH_SYNC handling from nfs_local_commit
NFS/localio: issue IO inline when not in a memory-reclaim context
NFS: Fix delayed delegation return list handling
NFS: Verify symlink inode before caching target
NFS: fix folio dereference before NULL check in nfs_inode_remove_request()
...
|
|
No file in net/sunrpc needs pagemap.h, nor depends on it bringing in any
of its dependencies. After this patch, no file in net/sunrpc depends on
pagemap.h, even transitively.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
|
|
Pull RDMA updates from Jason Gunthorpe:
"About the normal size, still a lot of AI bug fixes and so on, but some
interesting new functionality too:
- Assorted locking, bounds-checking, cleanup, and error-path fixes
across UCMA/CMA, bng_re, bnxt_re, cxgb4, EFA, ERDMA, HFI1, HNS,
ionic, iRDMA, mlx4/mlx5, RXE, SIW, SRP/SRPT, and iSER target.
- netlink report for max # of supported resources
- get_zeroed_page()/etc removal
- Robust udata for ionic
- Allow unique RDMA device names per network namespace
- Completion counters and v2 admit queue support for EFA
- UC QP support for MANA
- Completion timestamps for ionic
- Harden uverbs data validation and resource lifetime handling,
fixing several core use-after-free conditions.
- bnxt_re toggle-page ownership and lifetime bug fixes
- dmabuf SRQ support for mlx5"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (160 commits)
RDMA/ucma: Allow path records to exactly fit the output buffer
RDMA/uverbs: Guard legacy bundles without method_elm
RDMA/efa: Add support for 128B admin v2 SQ entry
RDMA/efa: Generalize the admin SQ
RDMA/efa: Decouple admin command payload from admin header
RDMA/rxe: Fix OOB in free_rd_atomic_resources()
RDMA/cma: Fix WARNING in res_to_rt
RDMA/cxgb4: Free debugfs on registration failure
RDMA/cxgb4: Cancel reg_work before freeing device on remove
RDMA/ucma: Lock the handler in ucma_set_ib_path()
RDMA/ucma: Lock the handler in ucma_write_cm_event()
RDMA/erdma: restrict the driver to little-endian systems
RDMA/ionic: Embed counter driver data in rdma_counter allocation
RDMA/ionic: Cap eq_count to the eth driver's interrupt vector budget
RDMA/siw: Fix use-after-free in siw_accept()
IB/isert: post the full-feature receive buffers after session registration
IB/isert: delay the final Login Response until the session is registered
RDMA/srp: fix heap information leak on a truncated SRP_CRED_REQ
RDMA/erdma: Hold QP references for AE and CM processing
RDMA/erdma: Hold CQ references when processing EQ events
...
|
|
xs_tls_handshake_sync() gives xs_tls_handshake_done() a reference to the
lower transport before submitting the handshake request. On timeout or
signal, the synchronous waiter drops that reference after calling
tls_handshake_cancel().
handshake_req_cancel() returns false when handshake_complete() has
already marked the request complete. In that case the completion callback
can still be running, so dropping the callback-owned reference in the
waiter can free the lower transport before xs_tls_handshake_done() stores
xprt_err or drops its own reference.
If cancellation loses to completion, wait until xs_tls_handshake_done()
signals handshake_done and let the callback release its reference. This
mirrors the server-side handshake lifetime handling and keeps the timeout
or signal return value unchanged.
Fixes: 75eb6af7acdf ("SUNRPC: Add a TCP-with-TLS RPC transport class")
Cc: stable@vger.kernel.org
Assisted-by: Codex:gpt-5
Signed-off-by: Jérémy Jean <Jeremy.Jean@oss.cyber.gouv.fr>
Reviewed-by: Chuck Lever <cel@kernel.org>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
|
|
__rpc_clnt_remove_pipedir
Normal client creation goes through rpc_setup_pipedir(), which records
clnt->pipefs_sb, but the mount-event path in __rpc_clnt_handle_event()
calls rpc_setup_pipedir_sb() directly and never refreshes that field.
The umount path also removes the directory without clearing
clnt->pipefs_sb.
After a late pipefs mount or any remount, rpc_clnt_remove_pipedir()
compares the current superblock against a stale pipefs_sb pointer and
skips cleanup, leaving pipefs dentries whose inode private data still
points at a freed rpc_clnt, leading to a potential use-after-free during
subsequent rpc_info_open() or rpc_show_info() calls.
Fix this by properly updating clnt->pipefs_sb upon mount events and
clearing it during unmount or failure paths.
Fixes: bfca5fb4e97c ("SUNRPC: Fix RPC client cleaned up the freed pipefs dentries")
Cc: stable@vger.kernel.org
Reported-by: Yuan Tan <yuantan098@gmail.com>
Reported-by: Xin Liu <dstsmallbird@foxmail.com>
Reviewed-by: Ren Wei <enjou1224z@gmail.com>
Assisted-by: Codex:gpt-5.4
Signed-off-by: Luxiao Xu <rakukuip@gmail.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
|
|
xprtsock replaces and restores sk->sk_data_ready and
sk->sk_write_space on live sockets with plain stores, and
xs_udp_do_set_buffer_size() invokes sk->sk_write_space via a plain
load. These callback pointers are shared with generic socket and
protocol paths that may read or invoke them concurrently, so xprtsock
needs the same READ_ONCE()/WRITE_ONCE() callback visibility contract
that the validated 4022 family applied elsewhere.
When SUNRPC takes over an AF_LOCAL, UDP, or TCP socket and later
restores the lower-socket callbacks during teardown, another CPU may
still hold an earlier callback snapshot. The plain replace/restore
pattern leaves the same visibility hole as the validated 4022 family,
so a stale snapshot can still invoke xs_data_ready() or
xs_udp_write_space() after the live callback fields have already been
restored to the lower-socket handlers.
Use WRITE_ONCE() for the shared sk_data_ready and sk_write_space
stores in xs_local_finish_connecting(), xs_udp_finish_connecting(),
xs_tcp_finish_connecting(), and xs_restore_old_callbacks(). Use
READ_ONCE() for the direct sk_write_space invocation in
xs_udp_do_set_buffer_size(). This matches the required callback
visibility contract while leaving adjacent sk_state_change and
sk_error_report handling unchanged.
Fixes: a246b0105bbd ("[PATCH] RPC: introduce client-side transport switch")
Signed-off-by: Runyu Xiao <runyu.xiao@seu.edu.cn>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
|
|
rpcb_register_inet4() and rpcb_register_inet6() store the result of
rpc_sockaddr2uaddr() into map->r_addr without checking it for NULL.
rpc_sockaddr2uaddr() returns NULL when its final kstrdup() fails, and
the unchecked NULL is then carried into the synchronous RPCBPROC_SET
encode path: rpcb_register_call() -> rpc_call_sync() ->
rpcb_enc_getaddr() -> encode_rpcb_string(), whose first statement is
strlen(string), dereferencing NULL and oopsing the kernel.
The crash reproduces under failslab on v6.12; with KASAN the NULL
dereference surfaces as a fault on the shadow of address zero:
Oops: general protection fault, probably for non-canonical address
0xdffffc0000000000 [#1] PREEMPT SMP KASAN
RIP: 0010:strlen (lib/string.c:409)
Call Trace:
encode_rpcb_string (net/sunrpc/rpcb_clnt.c:890)
rpcb_enc_getaddr (net/sunrpc/rpcb_clnt.c:910)
rpcauth_wrap_req_encode (net/sunrpc/auth.c:745)
call_encode (net/sunrpc/clnt.c:1966)
__rpc_execute (net/sunrpc/sched.c:952)
rpc_run_task (net/sunrpc/clnt.c:1243)
rpc_call_sync (net/sunrpc/clnt.c:1272)
rpcb_v4_register (net/sunrpc/rpcb_clnt.c:500)
svc_generic_rpcbind_set
nfsd_rpcbind_set
svc_register
svc_setup_socket
svc_addsock
write_ports
nfsctl_transaction_write
vfs_write
The crash is reachable when an in-kernel RPC service (nfsd, lockd,
nfs-callback) registers with the local rpcbind under enough memory
pressure for the small GFP_KERNEL kstrdup() in rpc_sockaddr2uaddr() to
fail. The asynchronous getport path already handles this exact failure
mode by returning -ENOMEM; only the two register helpers omit the check.
Mirror that handling: bail out with -ENOMEM when rpc_sockaddr2uaddr()
returns NULL, before the address is fed into the encoder.
Fixes: d77385f23830 ("SUNRPC: Fix rpc_sockaddr2uaddr")
Reported-by: Xiang Mei <xmei5@asu.edu>
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
|
|
Now that svc_seq_show() and the nfsd netlink stats handler both use
the per-netns svc_stat vs_count arrays, the global per-version
vs_count percpu counters are no longer read by anything. Remove the
vs_count field from struct svc_version and all the associated
DEFINE_PER_CPU_ALIGNED arrays and initializers across nfsd, lockd,
and the NFS client callback service.
Assisted-by: LLM
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260717-exportd-netlink-v7-4-b7ce17b83b60@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
Update svc_seq_show() to read from the per-netns
statp->vs_count[] arrays instead of the global
svc_version->vs_count[].
The only caller is nfsd, which always allocates vs_count via
svc_stat_alloc_counts() in nfsd_net_init(), so the per-netns
arrays are always available.
This makes /proc/net/rpc/nfsd report per-network-namespace
procedure call counts.
Assisted-by: LLM
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260717-exportd-netlink-v7-2-b7ce17b83b60@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
The existing per-procedure call counts live in global
svc_version->vs_count[] arrays which are not network-namespace-aware.
Add per-netns equivalents in struct svc_stat so the upcoming netlink
stats interface can return namespace-scoped statistics.
Add a vs_count pointer array to struct svc_stat, along with
svc_stat_alloc_counts() and svc_stat_free_counts() helpers to manage
per-version percpu call count arrays.
Increment the per-net counter alongside the global one in
svc_generic_init_request(). Call the alloc/free helpers from
nfsd_net_init() and nfsd_net_exit().
Assisted-by: LLM
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260717-exportd-netlink-v7-1-b7ce17b83b60@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
Now that the pool mode is always pernode, svc_serv.sv_nrpools is
redundant with sv_is_pooled: an unpooled service always has a single
pool, and a pooled service has svc_pool_map.npools pools (which is one on
a single-node host). sv_nrpools cannot distinguish an unpooled service
from a pooled service that happens to have one pool, so it is sv_nrpools,
not sv_is_pooled, that carries no unique information.
Replace the cached field with a svc_serv_nrpools() helper that derives
the count from sv_is_pooled and the pool map, and convert all readers to
it. svc_pool_map is file-local to svc.c, so export the helper for the
svc_xprt.c and nfsd callers.
Reading svc_pool_map.npools without svc_pool_map_mutex is safe: the
mutex protects only svc_pool_map.count, and npools is already read
locklessly in svc_pool_for_cpu().
A pooled service holds a map reference for its whole lifetime, so npools
is stable while any reader could observe it. The hot path
(svc_pool_for_cpu()) already dereferences svc_pool_map for to_pool, and
npools shares that cacheline, so there is no new locking or coherence
cost.
__svc_create() keeps using its local npools argument for the sv_pools[]
allocation, since sv_is_pooled is not set until svc_create_pooled() has
returned from it.
Doing this also removes a modulus operation from svc_pool_for_cpu(),
which should make for more efficient RPC queueing.
Assisted-by: Claude:claude-opus-4-8
Suggested-by: NeilBrown <neilb@ownmail.net>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260706-sunrpc-pool-mode-v5-5-6c4ee7cd89aa@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_destroy() drops the service's reference to the global svc_pool_map
before iterating serv->sv_pools[] to destroy each pool's percpu counters.
That ordering happens to be fine today because the loop is bounded by the
per-service sv_nrpools field.
A following patch removes sv_nrpools and derives the pool count from the
pool map instead. svc_pool_map_put() zeroes svc_pool_map.npools when the
last reference is dropped, so a derived loop bound would read as zero for
the last pooled service and skip svc_pool_destroy_counters() entirely,
leaking the percpu counters (which remain linked on the global
percpu_counters list while the svc_serv is freed).
Reorder svc_destroy() to destroy the pool counters while the map is still
referenced, then drop the reference. No functional change.
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260706-sunrpc-pool-mode-v5-4-6c4ee7cd89aa@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_set_num_threads() spreads the requested thread count evenly across
the service's pools. In pernode mode each pool maps to a NUMA node, and
svc_pool_for_cpu() steers an incoming transport to the pool for the node
it arrived on. When fewer threads than pools are requested, even
distribution leaves some pools empty, and a transport steered to an
empty pool has no thread to service it.
Floor each pool at one thread when auto-distributing a non-zero count,
so no pool is left empty. Every pool maps to a node that had CPUs when
the pool map was built (svc_pool_map_init_pernode() only creates pools
for nodes returned by for_each_node_with_cpus()), so there is no pool
that should be left threadless. The resulting total may exceed the
requested count. This only affects the auto-distribute path (a
single-value array, i.e. svc_set_num_threads()); callers that set
per-pool counts explicitly via svc_set_pool_threads() are unchanged and
may still set a pool to zero.
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/20260706-sunrpc-pool-mode-v5-3-6c4ee7cd89aa@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
The SVC_POOL_AUTO/GLOBAL/PERCPU/PERNODE pool mode selection machinery
was added when NUMA was new and the right default was unclear. The
default has always been "global" (a single pool for the whole service);
the other modes were only used when an admin explicitly set the
pool_mode parameter or asked for "auto", which then picked a mode from
the host topology. Today, pernode is the right choice everywhere:
- On multi-NUMA hosts, it gives one pool per node with proper thread
affinity and NUMA-local memory allocation.
- On single-node hosts, pernode degenerates to exactly one pool,
identical to the old "global" mode -- svc_pool_for_cpu() short-
circuits when sv_nrpools <= 1, no CPU affinity is set, and memory
is allocated from the single node.
The percpu mode (one pool per CPU) created excessive pools relative to
the number of threads most deployments run, and was only auto-selected
in a narrow case (single node, >2 CPUs).
Note that this changes the default behaviour on multi-NUMA hosts: a
service that previously ran with a single global pool now gets one pool
per NUMA node by default. This in turn means a host running fewer
threads than it has NUMA nodes can end up with pools that have no
threads. svc_pool_for_cpu() already falls back to a populated pool in
that case, so transports are still serviced.
Remove the SVC_POOL_* enum, mode selection heuristic,
svc_pool_map_init_percpu(), and all mode-based switch statements.
Simplify pool map functions to always use the pernode path. If pool
map allocation fails, svc_pool_map_get() now returns 0 and service
creation fails, rather than silently falling back to a single global
pool.
With the mode check gone, svc_pool_map_get_node() would dereference the
shared pool_to[] for every service that starts a thread. Only services
created via svc_create_pooled() hold a map reference that keeps that
array allocated, so gate the lookup in svc_new_thread() on sv_is_pooled:
unpooled services (e.g. lockd, the NFS callback) use NUMA_NO_NODE and
never consult the map. The kmalloc_node() callers in
svc_prepare_thread() already accept NUMA_NO_NODE, but __folio_alloc_node()
requires a valid node id, so resolve NUMA_NO_NODE to numa_mem_id() for
the scratch folio allocation.
The module parameter and netlink interfaces are preserved for backward
compatibility:
- Writing any of the four documented mode names still succeeds silently
- Reading always returns "pernode"
- Writing to the module parameter emits a deprecation notice
Update Documentation/admin-guide/kernel-parameters.txt to mark the
pool_mode parameter deprecated and describe the new behaviour.
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260706-sunrpc-pool-mode-v5-2-6c4ee7cd89aa@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_set_num_threads() spreads the requested threads evenly across the
service's pools (base = nrservs / sv_nrpools). When a service runs
fewer threads than it has pools -- e.g. an nfsd configured with fewer
threads than the host has NUMA nodes while running in "pernode" or
"percpu" mode -- the trailing pools are left with no threads at all.
svc_xprt_enqueue() selects a pool from the CPU servicing the transport,
queues the transport on that pool's sp_xprts, and only wakes a thread
from the same pool. Each thread services exclusively its own pool, so a
transport that lands on a threadless pool is enqueued on sp_xprts and
never picked up: the connection hangs indefinitely.
Have svc_pool_for_cpu() skip pools that currently have no threads,
falling back to the next populated pool. This trades NUMA locality for
a guarantee that the work is actually serviced. sp_nrthreads is only
updated under the service mutex; the lockless read here is a best-effort
routing hint, so annotate it with data_race().
Fixes: bfd241600a3b ("[PATCH] knfsd: make rpc threads pools numa aware")
Cc: stable@vger.kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260706-sunrpc-pool-mode-v5-1-6c4ee7cd89aa@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
Commit d57e43b72bf2 ("SUNRPC: Update svcxdr_init_decode() to call
xdr_set_scratch_folio()") changed svc_pool_map_get_node() to return
numa_mem_id() instead of NUMA_NO_NODE, because __folio_alloc_node()
cannot accept NUMA_NO_NODE. That return value is not equivalent: it
is evaluated in the context of the task creating the nfsd threads,
once per thread created, and it is passed to kthread_create_on_node()
and to the per-thread allocations in svc_prepare_thread().
Since commit d1a89197589c ("kthread: Default affine kthread to its
preferred NUMA node"), the node argument of kthread_create_on_node()
no longer only places the task structure and stack: a kthread created
with a real node id normally affines itself to that node's CPUs when
it is first woken to run its thread function. All nfsd threads are
typically started together, by one task writing to
/proc/fs/nfsd/threads, so under the default pool_mode=global each
nfsd thread is now affined to the local-memory node of the CPU its
creating iteration happened to run on - typically the same node for
every thread. The CPUs of the other nodes are then unable to run
nfsd at all, and the threads' allocations - svc_rqst structures,
page pointer arrays, newly allocated task stacks, and the per-RPC
pages allocated at run time - all prefer that one node.
Restore the NUMA_NO_NODE behaviour that global mode has had since
commit 11fd165c68b7 ("sunrpc: use better NUMA affinities"), and
handle NUMA_NO_NODE at the one call site that cannot take it by
resolving it to numa_mem_id() there, exactly as alloc_pages_node()
did for the scratch page before the conversion. The mapped percpu
and pernode branches are unchanged. Unpooled services such as lockd
and the NFS client callback service also take this fallback when no
percpu or pernode map is active, restoring their thread placement in
that case.
A bisect of a 2x NFS READ throughput regression between v6.17 and
v6.18 converged on d57e43b72bf2. On the affected 4-node server every
nfsd thread comes up with its CPU affinity restricted to the CPUs of
a single node; with this change the threads are runnable on all CPUs
again and the observed regression is resolved.
Fixes: d57e43b72bf2 ("SUNRPC: Update svcxdr_init_decode() to call xdr_set_scratch_folio()")
Cc: stable@vger.kernel.org
Signed-off-by: Ameer Hamza <ameer.hamza@truenas.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260722182012.2063936-1-ameer.hamza@truenas.com
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
An RPC-over-RDMA client can request a reply, such as an NFS READ
payload, without providing a Write list or a Reply chunk to carry
it. When such a reply needs more scatter/gather entries than the
device's Send Queue supports, svc_rdma_pull_up_needed() selects
pull-up and svc_rdma_pull_up_reply_msg() linearizes the whole
reply into sctxt->sc_xprt_buf. That buffer is only sc_max_req_size
bytes, while the reply on this path is bounded only by the client's
request, so svc_rdma_xb_linearize() copies past the end of the
buffer and corrupts adjacent slab memory. The oversized length is
then stored in sc_sges[0].length and posted, so the device also
reads beyond the mapped region.
The SGE-exhaustion branch is the only pull-up path that can exceed
the buffer: the threshold branch pulls up only replies smaller
than RPCRDMA_PULLUP_THRESH, and replies that fit the device's SGE
budget are sent directly without linearization. Make
svc_rdma_pull_up_needed() report -E2BIG when the reply it would
pull up cannot fit sc_max_req_size, and fail the request with
ERR_CHUNK as RFC 8166 Section 4.5.3 directs rather than dropping
the connection.
The helper no longer answers a simple yes/no question: it now
reports pull-up, no pull-up, or -E2BIG for a reply too large to
linearize. Rename svc_rdma_pull_up_needed() to
svc_rdma_check_pull_up() so its name no longer implies a boolean
predicate.
Fixes: e248aa7be86e ("svcrdma: Remove max_sge check at connect time")
Cc: stable@vger.kernel.org
Reported-by: Chris Mason <clm@meta.com>
Assisted-by: kres:claude-opus-4-7
Link: https://patch.msgid.link/20260623014728.826032-1-cel@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
svc_rqst_free() frees rqstp->rq_argp and rqstp->rq_resp synchronously
via kfree(), but defers the rqstp struct free via kfree_rcu(). After
svc_exit_thread() calls list_del_rcu() and svc_rqst_free(), there is
a window where RCU readers that started before list_del_rcu() can still
traverse the thread list and find the rqstp. These readers (e.g.
nfsd_nl_rpc_status_get_dumpit()) dereference rqstp->rq_argp, which has
already been freed — a use-after-free.
Fix this by moving the kfree of rq_argp and rq_resp into an explicit
call_rcu() callback alongside the struct free. Resources not accessed
by RCU readers (bvec, buffer pages, scratch folio, auth_data) remain
synchronously freed.
Fixes: 812443865c5f ("sunrpc: add a rcu_head to svc_rqst and use kfree_rcu to free it")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260611-nfsd-testing-v2-4-5b90e276f2d9@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
A pooled RPC service sizes its threads dynamically, growing and
shrinking each pool between its minimum and maximum bounds as load
varies. The count of running threads therefore reflects recent
demand, not the service's capacity. A consumer that sizes a data
structure against the concurrency the service can sustain -- NFSD's
NFSv4 session slot tables, for one -- needs that stable ceiling, and
computing it means summing sp_nrthrmax across every pool.
Add svc_serv_maxthreads() so the summation, and its dependence
on the layout of struct svc_serv and struct svc_pool, stays within
sunrpc. The read is lock-free: pool maxima change only when a service
is reconfigured, a path callers already serialize against startup and
shutdown, so a racing reader observes at worst a transient value. This
is acceptable for the sizing heuristics that will consume it.
nfsd_nrthreads() already sums sp_nrthrmax across pools by hand; convert
it to svc_serv_maxthreads(), giving the new export an in-tree consumer
and removing a copy of the dependence on svc_serv internals.
Reviewed-by: NeilBrown <neil@brown.name>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Benjamin Coddington <bcodding@hammerspace.com>
Link: https://patch.msgid.link/20260610-nfsd-slot-growth-clamp-v1-1-7b966700df0b@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>
|
|
Replacing strcpy() with strscpy() ensures that overflow of the target
buffer cannot happen.
Signed-off-by: David Laight <david.laight.linux@gmail.com>
Link: https://patch.msgid.link/20260608095523.2606-16-david.laight.linux@gmail.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
rpcrdma_rn_register() inserts @rn into rd_xa with xa_alloc() before
storing the caller's callback in rn->rn_done. The xarray makes @rn
reachable to rpcrdma_remove_one(), which walks rd_xa and invokes
rn->rn_done(rn) for every registered notification. A device removal
that races a fresh registration can therefore observe @rn with
rn_done still NULL, because the notification objects are zero
allocated by their owners, and call through a NULL function pointer.
Store rn->rn_done before xa_alloc() publishes @rn. The xarray's
store-side and load-side ordering then guarantees that any CPU which
finds @rn in rd_xa also observes the armed callback.
rpcrdma_rn_unregister() treats a non-NULL rn_done as the sentinel
for a completed registration, so the early store must not survive a
failed registration. Clear rn_done again when xa_alloc() fails.
Were it left set, the failed-accept cleanup path would call
rpcrdma_rn_unregister() on an @rn that was never inserted, erasing
an unrelated rd_xa slot and underflowing rd_kref.
Fixes: 7e86845a0346 ("rpcrdma: Implement generic device removal")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260601201703.46078-1-cel@kernel.org
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
__svc_create() initializes three per-pool percpu_counter stats and
ignores every return value. On SMP, percpu_counter_init() fails when
__alloc_percpu_gfp() cannot satisfy the allocation, leaving the failed
counter with fbc->counters == NULL and its embedded raw_spinlock_t,
list_head, and count never initialized. __svc_create() returns the
half-constructed svc_serv to nfsd, lockd, or the NFS callback service
anyway.
Once that service is live, the hot-path increments in
svc_xprt_enqueue(), svc_handle_xprt(), and
svc_pool_wake_idle_thread() reach a counter whose backing pointer is
NULL. The pointer is a per-cpu offset, so the access does not fault:
it resolves to offset zero of the current CPU's per-cpu area and
silently corrupts whatever variable lives there. A
/proc/fs/nfsd/pool_stats read walks the same NULL per-cpu storage and
returns garbage, and on CONFIG_DEBUG_SPINLOCK or lockdep it splats on
the never-initialized lock.
Creating the broken service requires a percpu allocation failure during
RPC server startup, so it is reachable only by a local administrator
under memory pressure or fault injection; a remote peer cannot induce
the bad state on its own.
Check each percpu_counter_init() return value in __svc_create() and
fail when an allocation fails, unwinding the counters already set up
in the current pool and in every pool initialized before it. A
discrete percpu_counter_destroy() per counter at teardown frees each
per-cpu allocation exactly once.
Fixes: ccf08bed6e7a ("SUNRPC: Replace pool stats with per-CPU variables")
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260530-tier2-local-v2-2-5a0fd532db57@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
create_use_gss_proxy_proc_entry() publishes /proc/net/rpc/use-gss-proxy
via proc_create_data() before init_gssp_clnt() runs mutex_init() on
sn->gssp_lock. Once the dentry is linked under proc_subdir_lock it is
immediately reachable from userspace, so a write that lands in the
window drives set_gssp_clnt() into mutex_lock() on a zero-initialized
struct mutex.
create_use_gss_proxy_proc_entry(net)
proc_create_data("use-gss-proxy", ...) /* dentry live */
init_gssp_clnt(sn)
mutex_init(&sn->gssp_lock) /* too late */
write_gssp()
set_gssp_clnt(net)
mutex_lock(&sn->gssp_lock) /* uninitialized */
gssp_rpc_create(...)
sn->gssp_clnt = clnt
mutex_unlock(&sn->gssp_lock)
The window spans only the two statements between proc_create_data()
returning and init_gssp_clnt(), so a writer reaches it only if the
registering thread is preempted there while another task is already
opening the freshly published file. register_pernet_subsys() runs in
preemptible context under pernet_ops_rwsem, so that preemption is
possible, and the window widens on auth_rpcgss module load, when the
proc entry is created for every live net namespace whose tasks are
already running. A writer that wins the race locks a zero-filled
struct mutex. On CONFIG_DEBUG_MUTEXES the missing magic value trips a
"lock used without init" splat; on a production kernel the fast path
acquires the lock via CMPXCHG(owner, 0, current). In the latter case
a second writer that arrives before init_gssp_clnt() re-zeroes owner
can enter set_gssp_clnt() concurrently, shut down the first writer's
clnt while it is still in use, and leak the loser's clnt.
Fix by initializing sn->gssp_lock in sunrpc_init_net() so its lifetime
matches the sunrpc_net it lives in. sn->gssp_clnt is already NULL from
the kzalloc that backs net_generic storage, so the lazy helper is no
longer needed; drop init_gssp_clnt(), its prototype, and the call from
create_use_gss_proxy_proc_entry(). sunrpc.ko is a build-time
dependency of auth_rpcgss.ko, so sunrpc_init_net() has always run on
every netns before any auth_gss pernet init can publish the proc
entry.
Fixes: 030d794bf498 ("SUNRPC: Use gssproxy upcall for server RPCGSS authentication.")
Cc: stable@vger.kernel.org
Assisted-by: kres:claude-opus-4-7
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260530-tier2-local-v2-1-5a0fd532db57@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
A backchannel receive can complete a request while the NFS callback
service is being torn down. xprt_complete_bc_request() removes the
request from bc_pa_list, drops bc_alloc_count, marks the request in use,
and then asks xprt_enqueue_bc_request() to hand it to the callback
service.
If teardown has already cleared xprt->bc_serv, xprt_enqueue_bc_request()
currently returns without enqueueing or freeing the committed request.
The xprt_get() taken on entry is leaked as well. If the producer wins
the race before bc_serv is cleared, it can also enqueue onto sv_cb_list
after nfs_callback_down() has stopped the callback threads, leaving the
request linked to a svc_serv that is about to be freed.
Close the producer side before callback threads are stopped. Add
xprt_svc_shutdown_bc() to clear xprt->bc_serv under bc_pa_lock, and call
it on callback shutdown and callback-start failure before stopping the
service threads. Requests that lose the NULL transition in
xprt_enqueue_bc_request() are released through the normal backchannel
free path after balancing bc_slot_count. Finally, drain any remaining
sv_cb_list requests after the callback threads have stopped and before
svc_destroy() frees the service.
Fixes: 441244d4273a ("SUNRPC: cleanup common code in backchannel request")
Fixes: 9e9fdd0ad0fb ("NFSv4.1: protect destroying and nullifying bc_serv structure")
Cc: stable@vger.kernel.org
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-6-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
svcauth_gss_decode_credbody() writes the caller's
rpc_gss_wire_cred field by field and assigns gc_ctx.len only on
the success tail. The caller storage is svcdata->clcred, which
lives in the per-svc_rqst gss_svc_data and is reused across
requests. Early decode failures leave partially decoded state
mixed with residue from the prior request.
The trailing body_len tightness check is the sharpest case:
xdr_stream_decode_opaque_inline() has already written gc_ctx.data
with a borrowed inline pointer into the current request's XDR
pages, but gc_ctx.len retains its prior value. Once the request
pages are released the pooled clcred carries a dangling pointer
paired with a stale length.
Zero the caller's rpc_gss_wire_cred at function entry so that
every early-return path leaves a deterministic all-zero cred.
On the trailing tightness-check path, gc_ctx.len is now zero
instead of stale, which neuters length-driven consumers such as
gss_svc_searchbyctx() that would otherwise walk the dangling
data pointer.
Fixes: b0bc53470d1a ("SUNRPC: Convert the svcauth_gss_accept() pre-amble to use xdr_stream")
Cc: stable@vger.kernel.org
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-5-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
svcauth_gss_release() reads gc_proc and switches on gc_svc before
consulting rq_auth_stat. On the SVC_DENIED path after a failed
svcauth_gss_accept(), those fields may hold stale values from a
prior request or uninitialized slab residue: svcauth_gss_accept()
allocates gss_svc_data with non-zeroing kmalloc and clears only
gsd_databody_offset and rsci per request, not clcred.
Because RPC_GSS_PROC_DATA is zero, a zeroed or stale-zero gc_proc
passes the existing guard and falls through into the gc_svc switch,
which can dispatch to svcauth_gss_wrap_integ() or
svcauth_gss_wrap_priv(). Both wrap helpers call
svcauth_gss_prepare_to_wrap() before any rsci->mechctx dereference,
and that helper already returns early when rq_auth_stat is not
rpc_auth_ok, so the downstream NULL dereference is blocked. The
dispatch itself remains structurally wrong: it reads scalars that
the caller has no contract to have initialized after a failed
authentication.
Mirror the existing rq_auth_stat gate in
svcauth_gss_prepare_to_wrap() one frame up, so
svcauth_gss_release() skips the clcred dispatch entirely when
authentication has not succeeded. The cleanup tail that releases
rq_client, rq_gssclient, cr_group_info, and rsci still runs.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-4-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
gssx_dec_option_array() walks the wire-supplied option array and, for
every entry whose name matches CREDS_VALUE, calls
gssx_dec_linux_creds() on the same struct svc_cred. That helper
unconditionally installs a fresh groups_alloc() result into
creds->cr_group_info without releasing whatever pointer was already
there:
for (i = 0; i < count; i++) {
... decode name ...
if (length == sizeof(CREDS_VALUE) &&
memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) {
err = gssx_dec_linux_creds(xdr, creds);
...
}
}
A reply that carries two CREDS_VALUE entries therefore overwrites
cr_group_info on the second iteration and orphans the group_info
allocated by the first call. The earlier free_creds path only
releases the last cr_group_info via free_svc_cred(), so the first
allocation's refcount stays at one and its kvmalloc-backed storage
is leaked. No in-tree caller of gssp_accept_sec_context_upcall()
expects more than one CREDS_VALUE per reply.
Fix by tracking whether a CREDS_VALUE option has already been
decoded and returning -EINVAL on any subsequent match, so the
free_creds path releases the single group_info that was installed.
Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth")
Cc: stable@vger.kernel.org
Assisted-by: kres (claude-opus-4-7)
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-3-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
Four coupled defects in the gssx XDR option-array decoder make the
error paths unsafe: a NULL deref in the caller, a refcount leak on
the decoded group_info, and a latent use-after-free that the leak
fix would otherwise expose.
gssx_dec_option_array() sets oa->count = 1 before allocating
oa->data. If that allocation fails, -ENOMEM is returned with
oa->count == 1 and oa->data == NULL. All other error paths jump
to free_oa: which frees oa->data and NULLs it but also leaves
oa->count == 1. The caller trusts the count:
gssp_accept_sec_context_upcall()
gssx_dec_accept_sec_context()
gssx_dec_option_array() /* fails, count=1 data=NULL */
data = res.options.data[0].value /* NULL deref */
Independently, free_creds: releases the partially decoded svc_cred
with a bare kfree(creds). gssx_dec_linux_creds() installs a
groups_alloc() result into creds->cr_group_info; that object is
kvmalloc-backed and refcounted, and only put_group_info() reaches
kvfree(). A plain kfree(creds) drops the wrapper and leaks the
group_info allocation.
The natural fix for the leak is to call free_svc_cred(creds) before
kfree(creds), but free_svc_cred() invokes put_group_info() on
creds->cr_group_info unconditionally when non-NULL. The existing
out_free_groups: path in gssx_dec_linux_creds() already called
groups_free() on that pointer without clearing it, so once
free_svc_cred() is wired in, the subsequent put_group_info() would
touch freed memory.
Fix all four together:
- Move the oa->count = 1 assignment below the oa->data allocation
so it is never set when oa->data is NULL.
- Reset oa->count to 0 at free_oa: so count and data stay
coherent and the caller sees an empty option array.
- Call free_svc_cred(creds) before kfree(creds) at free_creds:
so the refcounted cr_group_info is released. free_svc_cred()
either NULL-guards each field explicitly (cr_group_info has
an if() check) or delegates to a helper that is NULL-safe
itself (kfree for the string fields, gss_mech_put() which
guards with if(gm) at gss_mech_switch.c:342), so it is safe
to call on a partially decoded svc_cred where only
cr_uid/cr_gid/cr_group_info have been written and everything
else is zero from kzalloc.
- In gssx_dec_linux_creds()'s out_free_groups: path, release
cr_group_info with put_group_info() rather than groups_free()
so the teardown matches free_svc_cred()'s refcount-aware path,
and clear the pointer so a later free_svc_cred() on the same
creds does not release it a second time.
Fixes: 3cfcfc102a5e ("SUNRPC: fix some memleaks in gssx_dec_option_array")
Cc: stable@vger.kernel.org
Assisted-by: kres (claude-opus-4-7)
Signed-off-by: Chris Mason <clm@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-2-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
|
gss_krb5_unwrap_v2() sets buf->len to a logical
length, which can be much smaller than head[0].iov_len
(the allocated receive-page capacity). It then calls
xdr_buf_trim() with a trim length derived from the 16-bit
"extra count" (ec) field in the Kerberos v2 token header.
The ec field is authenticated by the post-decrypt memcmp()
against the encrypted header copy, so a randomly-mutated
value is rejected. However, any peer holding a valid GSS
context can legitimately encrypt a token whose ec exceeds
the plaintext length. Per RFC 4121, such a token is
structurally malformed.
Although xdr_buf_trim() now clamps the buf->len subtraction
to avoid unsigned underflow, the buffer is still left in a
semantically invalid state (zero length, inconsistent iov
lengths) when ec is oversized.
Reject these tokens before calling xdr_buf_trim(), giving
callers a well-defined GSS_S_DEFECTIVE_TOKEN error and
keeping the xdr_buf internally consistent. The wrapped blob
begins at a nonzero offset -- both callers pass len as
offset + opaque_len -- so buf->len still counts the offset
bytes that precede the blob. Compare the trim length
against the remaining wrapped segment, buf->len - offset,
rather than the whole buffer; comparing against buf->len
alone leaves an offset-wide window in which an oversized ec
passes the test and xdr_buf_trim() cuts into the bytes ahead
of the blob.
Fixes: cf4c024b9083 ("sunrpc: trim off EC bytes in GSSAPI v2 unwrap")
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260528-tier2-v1-1-d026a1415e0b@oracle.com
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
|
