- 09 May, 2019 8 commits
-
-
Chuck Lever authored
Restore the kref_get that matches the gss_put_auth(gss_msg->auth) done by gss_release_msg(). Fixes: ac83228a ("SUNRPC: Use namespace of listening daemon ...") Signed-off-by:
Chuck Lever <chuck.lever@oracle.com> Signed-off-by:
Anna Schumaker <Anna.Schumaker@Netapp.com>
-
Benjamin Coddington authored
Now that nfs_match_client drops the nfs_client_lock, we should be careful to always return it in the same condition: locked. Fixes: 950a578c ("NFS: make nfs_match_client killable") Reported-by: syzbot+228a82b263b5da91883d@syzkaller.appspotmail.com Signed-off-by:
Benjamin Coddington <bcodding@redhat.com> Signed-off-by:
-
Christoph Hellwig authored
Fix the callbacks NFS passes to read_cache_page to actually have the proper type expected. Casting around function pointers can easily hide typing bugs, and defeats control flow protection. Signed-off-by:
Christoph Hellwig <hch@lst.de> Signed-off-by:
-
Scott Mayhew authored
Only delegations and layouts can be recalled, so it shouldn't be necessary to recover all opens when handling the status bit SEQ4_STATUS_RECALLABLE_STATE_REVOKED. We'll still wind up calling nfs41_open_expired() when a TEST_STATEID returns NFS4ERR_DELEG_REVOKED. Signed-off-by:
Scott Mayhew <smayhew@redhat.com> Reviewed-by:
Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by:
-
Dan Carpenter authored
If kstrdup_const() then this function returns zero (success) but it should return -ENOMEM. Fixes: ac83228a ("SUNRPC: Use namespace of listening daemon in the client AUTH_GSS upcall") Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
ZhangXiaoxu authored
If the rpc.gssd always return cred success, but now the cred is expired, then the task will loop in call_refresh and call_transmit. Exit the rpc task after retry. Signed-off-by:
ZhangXiaoxu <zhangxiaoxu5@huawei.com> Signed-off-by:
-
ZhangXiaoxu authored
stat command with soft mount never return after server is stopped. When alloc a new client, the state of the client will be set to NFS4CLNT_LEASE_EXPIRED. When the server is stopped, the state manager will work, and accord the state to recover. But the state is NFS4CLNT_LEASE_EXPIRED, it will drain the slot table and lead other task to wait queue, until the client recovered. Then the stat command is hung. When discover server trunking, the client will renew the lease, but check the client state, it lead the client state corruption. So, we need to call state manager to recover it when detect server ip trunking. Signed-off-by:
-
Olga Kornievskaia authored
If we fail to find a good deviceid while trying to pnfs instead of propogating an error back fallback to doing IO to the MDS. Currently, code with fals the IO with EINVAL. Signed-off-by:
Olga Kornievskaia <kolga@netapp.com> Fixes: 8d40b0f1 ("NFS filelayout:call GETDEVICEINFO after pnfs_layout_process completes" Cc: stable@vger.kernel.org # v4.11+ Signed-off-by:
-
- 07 May, 2019 1 commit
-
-
Roberto Bergantinos Corpas authored
Actually we don't do anything with return value from nfs_wait_client_init_complete in nfs_match_client, as a consequence if we get a fatal signal and client is not fully initialised, we'll loop to "again" label This has been proven to cause soft lockups on some scenarios (no-carrier but configured network interfaces) Signed-off-by:Roberto Bergantinos Corpas <rbergant@redhat.com> Reviewed-by:
-
- 26 Apr, 2019 9 commits
-
-
Trond Myklebust authored
When we create a new lockd client, we want to be able to pass the correct credential of the process that created the struct nlm_host. Signed-off-by:
-
Trond Myklebust authored
If two different containers that share the same network namespace attempt to mount the same filesystem, we should not allow them to share the same super block if they do not share the same user namespace, since the user mappings on the wire will need to differ. Signed-off-by:
-
Trond Myklebust authored
When mapping NFS identities, we want to substitute for the uids and gids on the wire as we would for the AUTH_UNIX creds. Signed-off-by:
-
Trond Myklebust authored
When mapping NFS identities using the NFSv4 idmapper, we want to substitute for the uids and gids that would normally go on the wire as part of a NFSv3 request. So we use the same mapping in the NFSv4 upcall as we use in the NFSv3 RPC call (i.e. the mapping stored in the rpc_clnt cred). Signed-off-by:
-
Trond Myklebust authored
When mapping NFS identities, we want to substitute for the uids and gids on the wire as we would for the AUTH_UNIX creds. Signed-off-by:
-
Trond Myklebust authored
When the client needs to talk to rpc.gssd, we should ensure that the uid argument is encoded to match the user namespace of the daemon. Signed-off-by:
-
Trond Myklebust authored
When encoding AUTH_UNIX creds and AUTH_GSS upcalls, use the user namespace of the process that created the rpc client. Signed-off-by:
-
Trond Myklebust authored
Store the credential of the mount process so that we can determine information such as the user namespace. Signed-off-by:
-
Trond Myklebust authored
When converting kuids to AUTH_UNIX creds, etc we will want to use the same user namespace as the process that created the rpc client. Signed-off-by:
-
- 25 Apr, 2019 22 commits
-
-
Chuck Lever authored
The comment hasn't been accurate for several years. Signed-off-by:
-
Chuck Lever authored
Commit e1ede312 ("xprtrdma: Fix helper that drains the transport") replaced the ib_drain_qp() call, so update documenting comments to reflect current operation. Signed-off-by:
-
Chuck Lever authored
Clean up: rely on the trace points instead. Signed-off-by:
-
Chuck Lever authored
Clean up. Move the remaining field in rpcrdma_create_data_internal so the structure can be removed. Signed-off-by:
-
Chuck Lever authored
Clean up. The inline settings are actually a characteristic of the endpoint, and not related to the device. They are also modified after the transport instance is created, so they do not belong in the cdata structure either. Lastly, let's use names that are more natural to RDMA than to NFS: inline_write -> inline_send and inline_read -> inline_recv. The /proc files retain their names to avoid breaking user space. Signed-off-by:
-
Chuck Lever authored
Clean up. xprt_rdma_max_inline_{read,write} cannot be set to large values by virtue of proc_dointvec_minmax. The current maximum is RPCRDMA_MAX_INLINE, which is much smaller than RPCRDMA_MAX_SEGS * PAGE_SIZE. The .rsize and .wsize fields are otherwise unused in the current code base, and thus can be removed. Signed-off-by: -
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Clean up. Since commit 54cbd6b0 ("xprtrdma: Delay DMA mapping Send and Receive buffers"), a pointer to the device is now saved in each regbuf when it is DMA mapped. Signed-off-by:
-
Chuck Lever authored
Instead of using a fixed number, allow the amount of Send completion batching to vary based on the client's maximum credit limit. - A larger default gives a small boost to IOPS throughput - Reducing it based on max_requests gives a safe result when the max credit limit is cranked down (eg. when the device has a small max_qp_wr). Signed-off-by:
-
Chuck Lever authored
Minor clean-ups I've stumbled on since sendctx was merged last year. In particular, making Send completion processing more efficient appears to have a measurable impact on IOPS throughput. Note: test_and_clear_bit() returns a value, thus an explicit memory barrier is not necessary. Signed-off-by:
-
Chuck Lever authored
Record an event when rpcrdma_marshal_req returns a non-zero return value to help track down why an xprt close might have occurred. Signed-off-by:
-
Chuck Lever authored
Reflects the change introduced in commit 067c4696 ("NFSv4.1: Bump the default callback session slot count to 16"). Signed-off-by:
-
Chuck Lever authored
The Receive handler runs in process context, thus can use on-demand GFP_KERNEL allocations instead of pre-allocation. This makes the xprtrdma backchannel independent of the number of backchannel session slots provisioned by the Upper Layer protocol. Signed-off-by:
-
Chuck Lever authored
For code legibility, clean up the function names to be consistent with the pattern: "rpcrdma" _ object-type _ action Also rpcrdma_regbuf_alloc and rpcrdma_regbuf_free no longer have any callers outside of verbs.c, and can thus be made static. Signed-off-by:
-
Chuck Lever authored
Clean up by providing an API to do this common task. At this point, the difference between rpcrdma_get_sendbuf and rpcrdma_get_recvbuf has become tiny. These can be collapsed into a single helper. Signed-off-by:
-
Chuck Lever authored
Allocating an rpcrdma_req's regbufs at xprt create time enables a pair of micro-optimizations: First, if these regbufs are always there, we can eliminate two conditional branches from the hot xprt_rdma_allocate path. Second, by allocating a 1KB buffer, it places a lower bound on the size of these buffers, without adding yet another conditional branch. The lower bound reduces the number of hardway re- allocations. In fact, for some workloads it completely eliminates hardway allocations. Signed-off-by:
-
Chuck Lever authored
Allocate the struct rpcrdma_regbuf separately from the I/O buffer to better guarantee the alignment of the I/O buffer and eliminate the wasted space between the rpcrdma_regbuf metadata and the buffer itself. Signed-off-by:
-
Chuck Lever authored
For code legibility, clean up the function names to be consistent with the pattern: "rpcrdma" _ object-type _ action Signed-off-by:
-
Chuck Lever authored
Eventually, I'd like to invoke rpcrdma_create_req() during the call_reserve step. Memory allocation there probably needs to use GFP_NOIO. Therefore a set of GFP flags needs to be passed in. As an additional clean up, just return a pointer or NULL, because the only error return code here is -ENOMEM. Lastly, clean up the function names to be consistent with the pattern: "rpcrdma" _ object-type _ action Signed-off-by:
-
Chuck Lever authored
After a DMA map failure in frwr_map, mark the MR so that recycling won't attempt to DMA unmap it. Signed-off-by:
-
Chuck Lever authored
Page allocation requests made when the SPARSE_PAGES flag is set are allowed to fail, and are not critical. No need to spend a rare resource. Signed-off-by:
-
Xiaoli Feng authored
dedupe_file_range operations is combiled into remap_file_range. But in nfs42_remap_file_range, it's skiped for dedupe operations. Before this patch: # dd if=/dev/zero of=nfs/file bs=1M count=1 # xfs_io -c "dedupe nfs/file 4k 64k 4k" nfs/file XFS_IOC_FILE_EXTENT_SAME: Invalid argument After this patch: # dd if=/dev/zero of=nfs/file bs=1M count=1 # xfs_io -c "dedupe nfs/file 4k 64k 4k" nfs/file deduped 4096/4096 bytes at offset 65536 4 KiB, 1 ops; 0.0046 sec (865.988 KiB/sec and 216.4971 ops/sec) Signed-off-by:
Xiaoli Feng <fengxiaoli0714@gmail.com> Signed-off-by:
-
