In addition to binding to a local privileged port the NFS client should
allow binding to a specific local address. This is used by the server
for callbacks. The patch adds the necessary interface.
Signed-off-by: Frank van Maarseveen <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Save the destination address of an incoming request over TCP like is
done already for UDP. It is necessary later for callbacks by the server.
Signed-off-by: Frank van Maarseveen <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Cleanup argument passing to functions for creating an RPC transport.
Signed-off-by: Frank van Maarseveen <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Clean up, for consistency. Rename rpcb_getport as rpcb_getport_async, to
match the naming scheme of rpcb_getport_sync.
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
In preparation for handling NFS mount option parsing in the kernel,
rename rpcb_getport_external as rpcb_get_port_sync, and make it available
always (instead of only when CONFIG_ROOT_NFS is enabled).
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
We should almost always be deferencing the rpc_auth struct by means of the
credential's cr_auth field instead of the rpc_clnt->cl_auth anyway. Fix up
that historical mistake, and remove the macro that propagated it.
Signed-off-by: Trond Myklebust <[email protected]>
Does a NULL RPC call and returns a pointer to the resulting rpc_task. The
call may be either synchronous or asynchronous.
Signed-off-by: Trond Myklebust <[email protected]>
The leak only affects the RPCSEC_GSS caches, since they are the only ones
that are dynamically allocated...
Rename the existing rpcauth_free_credcache() to rpcauth_clear_credcache()
in order to better describe its role, then add a new function
rpcauth_destroy_credcache() that actually frees the cache in addition to
clearing it out.
Also move the call to destroy the credcache in gss_destroy() to come before
the rpc upcall pipe is unlinked.
Signed-off-by: Trond Myklebust <[email protected]>
Currently, the downcall queue is tied to the struct gss_auth, which means
that different RPCSEC_GSS pseudoflavours must use different upcall pipes.
Add a list to struct rpc_inode that can be used instead.
Signed-off-by: Trond Myklebust <[email protected]>
Cleans up an issue whereby rpcsec_gss uses the rpc_clnt->cl_auth. If we want
to be able to add several rpc_auths to a single rpc_clnt, then this abuse
must go.
Signed-off-by: Trond Myklebust <[email protected]>
The kref now does most of what cl_count + cl_user used to do. The only
remaining role for cl_count is to tell us if we are in a 'shutdown'
phase. We can provide that information using a single bit field instead
of a full atomic counter.
Also rename rpc_destroy_client() to rpc_close_client(), which reflects
better what its role is these days.
Signed-off-by: Trond Myklebust <[email protected]>
Replace it with explicit calls to rpc_shutdown_client() or
rpc_destroy_client() (for the case of asynchronous calls).
Signed-off-by: Trond Myklebust <[email protected]>
Its use is at best racy, and there is only one user (lockd), which has
additional locking that makes the whole thing redundant.
Signed-off-by: Trond Myklebust <[email protected]>
- net/sunrpc/xprtsock.c:1635:5: warning: symbol 'init_socket_xprt' was not
declared. Should it be static?
- net/sunrpc/xprtsock.c:1649:6: warning: symbol 'cleanup_socket_xprt' was
not declared. Should it be static?
Signed-off-by: Trond Myklebust <[email protected]>
When the kernel calls svc_reserve to downsize the expected size of an RPC
reply, it fails to account for the possibility of a checksum at the end of
the packet. If a client mounts a NFSv2/3 with sec=krb5i/p, and does I/O
then you'll generally see messages similar to this in the server's ring
buffer:
RPC request reserved 164 but used 208
While I was never able to verify it, I suspect that this problem is also
the root cause of some oopses I've seen under these conditions:
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=227726
This is probably also a problem for other sec= types and for NFSv4. The
large reserved size for NFSv4 compound packets seems to generally paper
over the problem, however.
This patch adds a wrapper for svc_reserve that accounts for the possibility
of a checksum. It also fixes up the appropriate callers of svc_reserve to
call the wrapper. For now, it just uses a hardcoded value that I
determined via testing. That value may need to be revised upward as things
change, or we may want to eventually add a new auth_op that attempts to
calculate this somehow.
Unfortunately, there doesn't seem to be a good way to reliably determine
the expected checksum length prior to actually calculating it, particularly
with schemes like spkm3.
Signed-off-by: Jeff Layton <[email protected]>
Acked-by: Neil Brown <[email protected]>
Cc: Trond Myklebust <[email protected]>
Acked-by: J. Bruce Fields <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Now that sk_defer_lock protects two different things, make the name more
generic.
Also don't bother with disabling _bh as the lock is only ever taken from
process context.
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
net/sunrpc/pmap_clnt.c has been replaced by net/sunrpc/rpcb_clnt.c.
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Introduce a replacement for the in-kernel portmapper client that supports
all 3 versions of the rpcbind protocol. This code is not used yet.
Original code by Groupe Bull updated for the latest kernel, with multiple
bug fixes.
Note that rpcb_clnt.c does not yet support registering via versions 3 and
4 of the rpcbind protocol. That is planned for a later patch.
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Currently rpc_malloc sets req->rq_buffer internally. Make this a more
generic interface: return a pointer to the new buffer (or NULL) and
make the caller set req->rq_buffer and req->rq_bufsize. This looks much
more like kmalloc and eliminates the side effects.
To fix a potential deadlock, this patch also replaces GFP_NOFS with
GFP_NOWAIT in rpc_malloc. This prevents async RPCs from sleeping outside
the RPC's task scheduler while allocating their buffer.
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
The RPC buffer size estimation logic in net/sunrpc/clnt.c always
significantly overestimates the requirements for the buffer size.
A little instrumentation demonstrated that in fact rpc_malloc was never
allocating the buffer from the mempool, but almost always called kmalloc.
To compute the size of the RPC buffer more precisely, split p_bufsiz into
two fields; one for the argument size, and one for the result size.
Then, compute the sum of the exact call and reply header sizes, and split
the RPC buffer precisely between the two. That should keep almost all RPC
buffers within the 2KiB buffer mempool limit.
And, we can finally be rid of RPC_SLACK_SPACE!
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
When the last thread of nfsd exits, it shuts down all related sockets. It
currently uses svc_close_socket to do this, but that only is immediately
effective if the socket is not SK_BUSY.
If the socket is busy - i.e. if a request has arrived that has not yet been
processes - svc_close_socket is not effective and the shutdown process spins.
So create a new svc_force_close_socket which removes the SK_BUSY flag is set
and then calls svc_close_socket.
Also change some open-codes loops in svc_destroy to use
list_for_each_entry_safe.
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
They don't really save that much, and aren't worth the hassle.
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
If one of clear_bit, change_bit or set_bit is defined as a do { } while (0)
function usage of these functions in parenthesis like
(foo_bit(23, &var))
while be expaned to something like
(do { ... } while (0)}).
resulting in a build error. This patch removes the useless parenthesis.
Signed-off-by: Ralf Baechle <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
RFC3530 section 3.1.1 states an NFSv4 client MUST NOT send a request
twice on the same connection unless it is the NULL procedure. Section
3.1.1 suggests that the client should disconnect and reconnect if it
wants to retry a request.
Implement this by adding an rpc_clnt flag that an ULP can use to
specify that the underlying transport should be disconnected on a
major timeout. The NFSv4 client asserts this new flag, and requests
no retries after a minor retransmit timeout.
Note that disconnecting on a retransmit is in general not safe to do
if the RPC client does not reuse the TCP port number when reconnecting.
See http://bugzilla.linux-nfs.org/show_bug.cgi?id=6
Signed-off-by: Chuck Lever <[email protected]>
Signed-off-by: Trond Myklebust <[email protected]>
Expand the rq_addr field to allow it to contain larger addresses.
Specifically, we replace a 'sockaddr_in' with a 'sockaddr_storage', then
everywhere the 'sockaddr_in' was referenced, we use instead an accessor
function (svc_addr_in) which safely casts the _storage to _in.
Signed-off-by: Chuck Lever <[email protected]>
Cc: Aurelien Charbon <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
There are loads of places where the RPC server assumes that the rq_addr fields
contains an IPv4 address. Top among these are error and debugging messages
that display the server's IP address.
Let's refactor the address printing into a separate function that's smart
enough to figure out the difference between IPv4 and IPv6 addresses.
Signed-off-by: Chuck Lever <[email protected]>
Cc: Aurelien Charbon <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The remote peer's address won't change after the socket has been accepted. We
don't need to call ->getname on every incoming request.
Signed-off-by: Chuck Lever <[email protected]>
Cc: Aurelien Charbon <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Sometimes we need to create an RPC service but not register it with the local
portmapper. NFSv4 delegation callback, for example.
Change the svc_makesock() API to allow optionally creating temporary or
permanent sockets, optionally registering with the local portmapper, and make
it return the ephemeral port of the new socket.
Signed-off-by: Chuck Lever <[email protected]>
Cc: Aurelien Charbon <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Currently in the RPC server, registering with the local portmapper and
creating "permanent" sockets are tied together. Expand the internal APIs to
allow these two socket characteristics to be separately specified.
This will be externalized in the next patch.
Signed-off-by: Chuck Lever <[email protected]>
Cc: Aurelien Charbon <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Frank van Maarseveen