summaryrefslogtreecommitdiff
path: root/fs
AgeCommit message (Collapse)Author
2020-12-14NFSv4.2/pnfs: Don't use READ_PLUS with pNFS yetTrond Myklebust
We have no way of tracking server READ_PLUS support in pNFS for now, so just disable it. Reported-by: "Mkrtchyan, Tigran" <tigran.mkrtchyan@desy.de> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: Deal with potential READ_PLUS data extent buffer overflowTrond Myklebust
If the server returns more data than we have buffer space for, then we need to truncate and exit early. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: Don't error when exiting early on a READ_PLUS buffer overflowTrond Myklebust
Expanding the READ_PLUS extents can cause the read buffer to overflow. If it does, then don't error, but just exit early. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: Handle hole lengths that exceed the READ_PLUS read bufferTrond Myklebust
If a hole extends beyond the READ_PLUS read buffer, then we want to fill just the remaining buffer with zeros. Also ignore eof... Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: decode_read_plus_hole() needs to check the extent offsetTrond Myklebust
The server is allowed to return a hole extent with an offset that starts before the offset supplied in the READ_PLUS argument. Ensure that we support that case too. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: decode_read_plus_data() must skip padding after data segmentTrond Myklebust
All XDR opaque object sizes are 32-bit aligned, and a data segment is no exception. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: Ensure we always reset the result->count in decode_read_plus()Trond Myklebust
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.1: use BITS_PER_LONG macro in nfs4session.hGeliang Tang
Use the existing BITS_PER_LONG macro instead of calculating the value. Signed-off-by: Geliang Tang <geliangtang@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-14NFSv4.2: improve page handling for GETXATTRFrank van der Linden
XDRBUF_SPARSE_PAGES can cause problems for the RDMA transport, and it's easy enough to allocate enough pages for the request up front, so do that. Also, since we've allocated the pages anyway, use the full page aligned length for the receive buffer. This will allow caching of valid replies that are too large for the caller, but that still fit in the allocated pages. Signed-off-by: Frank van der Linden <fllinden@amazon.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-10NFSv4.2: Fix up the get/listxattr calls to rpc_prepare_reply_pages()Trond Myklebust
Ensure that both getxattr and listxattr page array are correctly aligned, and that getxattr correctly accounts for the page padding word. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFS: switch nfsiod to be an UNBOUND workqueue.NeilBrown
nfsiod is currently a concurrency-managed workqueue (CMWQ). This means that workitems scheduled to nfsiod on a given CPU are queued behind all other work items queued on any CMWQ on the same CPU. This can introduce unexpected latency. Occaionally nfsiod can even cause excessive latency. If the work item to complete a CLOSE request calls the final iput() on an inode, the address_space of that inode will be dismantled. This takes time proportional to the number of in-memory pages, which on a large host working on large files (e.g.. 5TB), can be a large number of pages resulting in a noticable number of seconds. We can avoid these latency problems by switching nfsiod to WQ_UNBOUND. This causes each concurrent work item to gets a dedicated thread which can be scheduled to an idle CPU. There is precedent for this as several other filesystems use WQ_UNBOUND workqueue for handling various async events. Signed-off-by: NeilBrown <neilb@suse.de> Fixes: ada609ee2ac2 ("workqueue: use WQ_MEM_RECLAIM instead of WQ_RESCUER") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02lockd: don't use interval-based rebinding over TCPCalum Mackay
NLM uses an interval-based rebinding, i.e. it clears the transport's binding under certain conditions if more than 60 seconds have elapsed since the connection was last bound. This rebinding is not necessary for an autobind RPC client over a connection-oriented protocol like TCP. It can also cause problems: it is possible for nlm_bind_host() to clear XPRT_BOUND whilst a connection worker is in the middle of trying to reconnect, after it had already been checked in xprt_connect(). When the connection worker notices that XPRT_BOUND has been cleared under it, in xs_tcp_finish_connecting(), that results in: xs_tcp_setup_socket: connect returned unhandled error -107 Worse, it's possible that the two can get into lockstep, resulting in the same behaviour repeated indefinitely, with the above error every 300 seconds, without ever recovering, and the connection never being established. This has been seen in practice, with a large number of NLM client tasks, following a server restart. The existing callers of nlm_bind_host & nlm_rebind_host should not need to force the rebind, for TCP, so restrict the interval-based rebinding to UDP only. For TCP, we will still rebind when needed, e.g. on timeout, and connection error (including closure), since connection-related errors on an existing connection, ECONNREFUSED when trying to connect, and rpc_check_timeout(), already unconditionally clear XPRT_BOUND. To avoid having to add the fix, and explanation, to both nlm_bind_host() and nlm_rebind_host(), remove the duplicate code from the former, and have it call the latter. Drop the dprintk, which adds no value over a trace. Signed-off-by: Calum Mackay <calum.mackay@oracle.com> Fixes: 35f5a422ce1a ("SUNRPC: new interface to force an RPC rebind") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4: Refactor to use user namespaces for nfs4idmapSargun Dhillon
In several patches work has been done to enable NFSv4 to use user namespaces: 58002399da65: NFSv4: Convert the NFS client idmapper to use the container user namespace 3b7eb5e35d0f: NFS: When mounting, don't share filesystems between different user namespaces Unfortunately, the userspace APIs were only such that the userspace facing side of the filesystem (superblock s_user_ns) could be set to a non init user namespace. This furthers the fs_context related refactoring, and piggybacks on top of that logic, so the superblock user namespace, and the NFS user namespace are the same. Users can still use rpc.idmapd if they choose to, but there are complexities with user namespaces and request-key that have yet to be addresssed. Eventually, we will need to at least: * Come up with an upcall mechanism that can be triggered inside of the container, or safely triggered outside, with the requisite context to do the right mapping. * Handle whatever refactoring needs to be done in net/sunrpc. Signed-off-by: Sargun Dhillon <sargun@sargun.me> Tested-by: Alban Crequy <alban.crequy@gmail.com> Fixes: 62a55d088cd8 ("NFS: Additional refactoring for fs_context conversion") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFS: NFSv2/NFSv3: Use cred from fs_context during mountSargun Dhillon
There was refactoring done to use the fs_context for mounting done in: 62a55d088cd87: NFS: Additional refactoring for fs_context conversion This made it so that the net_ns is fetched from the fs_context (the netns that fsopen is called in). This change also makes it so that the credential fetched during fsopen is used as well as the net_ns. NFS has already had a number of changes to prepare it for user namespaces: 1a58e8a0e5c1: NFS: Store the credential of the mount process in the nfs_server 264d948ce7d0: NFS: Convert NFSv3 to use the container user namespace c207db2f5da5: NFS: Convert NFSv2 to use the container user namespace Previously, different credentials could be used for creation of the fs_context versus creation of the nfs_server, as FSCONFIG_CMD_CREATE did the actual credential check, and that's where current_creds() were fetched. This meant that the user namespace which fsopen was called in could be a non-init user namespace. This still requires that the user that calls FSCONFIG_CMD_CREATE has CAP_SYS_ADMIN in the init user ns. This roughly allows a privileged user to mount on behalf of an unprivileged usernamespace, by forking off and calling fsopen in the unprivileged user namespace. It can then pass back that fsfd to the privileged process which can configure the NFS mount, and then it can call FSCONFIG_CMD_CREATE before switching back into the mount namespace of the container, and finish up the mounting process and call fsmount and move_mount. Signed-off-by: Sargun Dhillon <sargun@sargun.me> Tested-by: Alban Crequy <alban.crequy@gmail.com> Fixes: 62a55d088cd8 ("NFS: Additional refactoring for fs_context conversion") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4: Fix a pNFS layout related use-after-free race when freeing the inodeTrond Myklebust
When returning the layout in nfs4_evict_inode(), we need to ensure that the layout is actually done being freed before we can proceed to free the inode itself. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4: Fix open coded xdr_stream_remaining()Trond Myklebust
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02SUNRPC: Clean up the handling of page padding in rpc_prepare_reply_pages()Trond Myklebust
rpc_prepare_reply_pages() currently expects the 'hdrsize' argument to contain the length of the data that we expect to want placed in the head kvec plus a count of 1 word of padding that is placed after the page data. This is very confusing when trying to read the code, and sometimes leads to callers adding an arbitrary value of '1' just in order to satisfy the requirement (whether or not the page data actually needs such padding). This patch aims to clarify the code by changing the 'hdrsize' argument to remove that 1 word of padding. This means we need to subtract the padding from all the existing callers. Fixes: 02ef04e432ba ("NFS: Account for XDR pad of buf->pages") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4: Fix the alignment of page data in the getdeviceinfo replyTrond Myklebust
We can fit the device_addr4 opaque data padding in the pages. Fixes: cf500bac8fd4 ("SUNRPC: Introduce rpc_prepare_reply_pages()") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02pNFS: Clean up open coded xdr string decodingTrond Myklebust
Use the existing xdr_stream_decode_string_dup() to safely decode into kmalloced strings. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02pNFS/flexfiles: Fix up layoutstats reporting for non-TCP transportsTrond Myklebust
Ensure that we report the correct netid when using UDP or RDMA transports to the DSes. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4/pNFS: Store the transport type in struct nfs4_pnfs_ds_addrTrond Myklebust
We want to enable RDMA and UDP as valid transport methods if a GETDEVICEINFO call specifies it. Do so by adding a parser for the netid that translates it to an appropriate argument for the RPC transport layer. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02pNFS: Add helpers for allocation/free of struct nfs4_pnfs_ds_addrTrond Myklebust
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4/pNFS: Use connections to a DS that are all of the same protocol familyTrond Myklebust
If the pNFS metadata server advertises multiple addresses for the same data server, we should try to connect to just one protocol family and transport type on the assumption that homogeneity will improve performance. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFS: Switch mount code to use xprt_find_transport_ident()Trond Myklebust
Switch the mount code to use xprt_find_transport_ident() and to check the results before allowing the mount to proceed. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFS: Do uncached readdir when we're seeking a cookie in an empty page cacheTrond Myklebust
If the directory is changing, causing the page cache to get invalidated while we are listing the contents, then the NFS client is currently forced to read in the entire directory contents from scratch, because it needs to perform a linear search for the readdir cookie. While this is not an issue for small directories, it does not scale to directories with millions of entries. In order to be able to deal with large directories that are changing, add a heuristic to ensure that if the page cache is empty, and we are searching for a cookie that is not the zero cookie, we just default to performing uncached readdir. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Reduce number of RPC calls when doing uncached readdirTrond Myklebust
If we're doing uncached readdir, allocate multiple pages in order to try to avoid duplicate RPC calls for the same getdents() call. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Optimisations for monotonically increasing readdir cookiesTrond Myklebust
If the server is handing out monotonically increasing readdir cookie values, then we can optimise away searches through pages that contain cookies that lie outside our search range. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Improve handling of directory verifiersTrond Myklebust
If the server insists on using the readdir verifiers in order to allow cookies to expire, then we should ensure that we cache the verifier with the cookie, so that we can return an error if the application tries to use the expired cookie. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Handle NFS4ERR_NOT_SAME and NFSERR_BADCOOKIE from readdir callsTrond Myklebust
If the server returns NFS4ERR_NOT_SAME or tells us that the cookie is bad in response to a READDIR call, then we should empty the page cache so that we can fill it from scratch again. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Allow the NFS generic code to pass in a verifier to readdirTrond Myklebust
If we're ever going to allow support for servers that use the readdir verifier, then that use needs to be managed by the middle layers as those need to be able to reject cookies from other verifiers. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Cleanup to remove nfs_readdir_descriptor_t typedefTrond Myklebust
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Reduce readdir stack usageTrond Myklebust
The descriptor and the struct nfs_entry are both large structures, so don't allocate them from the stack. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: nfs_do_filldir() does not return a valueTrond Myklebust
Clean up nfs_do_filldir(). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: More readdir cleanupsTrond Myklebust
Remove the redundant caching of the credential in struct nfs_open_dir_context. Pass the buffer size as an argument to nfs_readdir_xdr_filler(). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Support larger readdir buffersTrond Myklebust
Support readdir buffers of up to 1MB in size so that we can read large directories using few RPC calls. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Simplify struct nfs_cache_array_entryTrond Myklebust
We don't need to store a hash, so replace struct qstr with a simple const char pointer and length. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Replace kmap() with kmap_atomic() in nfs_readdir_search_array()Trond Myklebust
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Remove unnecessary kmap in nfs_readdir_xdr_to_array()Trond Myklebust
The kmapped pointer is only used once per loop to check if we need to exit. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Don't discard readdir resultsTrond Myklebust
If a readdir call returns more data than we can fit into one page cache page, then allocate a new one for that data rather than discarding the data. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Clean up directory array handlingTrond Myklebust
Refactor to use pagecache_get_page() so that we can fill the page in multiple stages. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Clean up nfs_readdir_page_filler()Trond Myklebust
Clean up handling of the case where there are no entries in the readdir reply. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Clean up readdir struct nfs_cache_arrayTrond Myklebust
Since the 'eof_index' is only ever used as a flag, make it so. Also add a flag to detect if the page has been completely filled. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFS: Ensure contents of struct nfs_open_dir_context are consistentTrond Myklebust
Ensure that the contents of struct nfs_open_dir_context are consistent by setting them under the file->f_lock from a private copy (that is known to be consistent). Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Reviewed-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Benjamin Coddington <bcodding@redhat.com> Tested-by: Dave Wysochanski <dwysocha@redhat.com>
2020-12-02NFSv4.2: condition READDIR's mask for security label based on LSM stateOlga Kornievskaia
Currently, the client will always ask for security_labels if the server returns that it supports that feature regardless of any LSM modules (such as Selinux) enforcing security policy. This adds performance penalty to the READDIR operation. Client adjusts superblock's support of the security_label based on the server's support but also current client's configuration of the LSM modules. Thus, prior to using the default bitmask in READDIR, this patch checks the server's capabilities and then instructs READDIR to remove FATTR4_WORD2_SECURITY_LABEL from the bitmask. v5: fixing silly mistakes of the rushed v4 v4: simplifying logic v3: changing label's initialization per Ondrej's comment v2: dropping selinux hook and using the sb cap. Suggested-by: Ondrej Mosnacek <omosnace@redhat.com> Suggested-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Olga Kornievskaia <kolga@netapp.com> Fixes: 2b0143b5c986 ("VFS: normal filesystems (and lustre): d_inode() annotations") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4: Observe the NFS_MOUNT_SOFTREVAL flag in _nfs4_proc_lookuppTrond Myklebust
We need to respect the NFS_MOUNT_SOFTREVAL flag in _nfs4_proc_lookupp, by timing out if the server is unavailable. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv3: Add emulation of the lookupp() operationTrond Myklebust
In order to use the open_by_filehandle() operations on NFSv3, we need to be able to emulate lookupp() so that nfs_get_parent() can be used to convert disconnected dentries into connected ones. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv3: Refactor nfs3_proc_lookup() to split out the dentryTrond Myklebust
We want to reuse the lookup code in NFSv3 in order to emulate the NFSv4 lookupp operation. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
2020-12-02NFSv4.2: Fix 5 seconds delay when doing inter server copyDai Ngo
Since commit b4868b44c5628 ("NFSv4: Wait for stateid updates after CLOSE/OPEN_DOWNGRADE"), every inter server copy operation suffers 5 seconds delay regardless of the size of the copy. The delay is from nfs_set_open_stateid_locked when the check by nfs_stateid_is_sequential fails because the seqid in both nfs4_state and nfs4_stateid are 0. Fix __nfs42_ssc_open to delay setting of NFS_OPEN_STATE in nfs4_state, until after the call to update_open_stateid, to indicate this is the 1st open. This fix is part of a 2 patches, the other patch is the fix in the source server to return the stateid for COPY_NOTIFY request with seqid 1 instead of 0. Fixes: ce0887ac96d3 ("NFSD add nfs4 inter ssc to nfsd4_copy") Signed-off-by: Dai Ngo <dai.ngo@oracle.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2020-12-02NFS: Fix rpcrdma_inline_fixup() crash with new LISTXATTRS operationChuck Lever
By switching to an XFS-backed export, I am able to reproduce the ibcomp worker crash on my client with xfstests generic/013. For the failing LISTXATTRS operation, xdr_inline_pages() is called with page_len=12 and buflen=128. - When ->send_request() is called, rpcrdma_marshal_req() does not set up a Reply chunk because buflen is smaller than the inline threshold. Thus rpcrdma_convert_iovs() does not get invoked at all and the transport's XDRBUF_SPARSE_PAGES logic is not invoked on the receive buffer. - During reply processing, rpcrdma_inline_fixup() tries to copy received data into rq_rcv_buf->pages because page_len is positive. But there are no receive pages because rpcrdma_marshal_req() never allocated them. The result is that the ibcomp worker faults and dies. Sometimes that causes a visible crash, and sometimes it results in a transport hang without other symptoms. RPC/RDMA's XDRBUF_SPARSE_PAGES support is not entirely correct, and should eventually be fixed or replaced. However, my preference is that upper-layer operations should explicitly allocate their receive buffers (using GFP_KERNEL) when possible, rather than relying on XDRBUF_SPARSE_PAGES. Reported-by: Olga kornievskaia <kolga@netapp.com> Suggested-by: Olga kornievskaia <kolga@netapp.com> Fixes: c10a75145feb ("NFSv4.2: add the extended attribute proc functions.") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Olga kornievskaia <kolga@netapp.com> Reviewed-by: Frank van der Linden <fllinden@amazon.com> Tested-by: Olga kornievskaia <kolga@netapp.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2020-11-30pNFS/flexfiles: Fix array overflow when flexfiles mirroring is enabledTrond Myklebust
If the flexfiles mirroring is enabled, then the read code expects to be able to set pgio->pg_mirror_idx to point to the data server that is being used for this particular read. However it does not change the pg_mirror_count because we only need to send a single read. Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-28 14:01:38 +0000