summaryrefslogtreecommitdiffstats
path: root/fs
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'nfs-for-3.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfsLinus Torvalds2014-04-0613-189/+271
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull NFS client updates from Trond Myklebust: "Highlights include: - Stable fix for a use after free issue in the NFSv4.1 open code - Fix the SUNRPC bi-directional RPC code to account for TCP segmentation - Optimise usage of readdirplus when confronted with 'ls -l' situations - Soft mount bugfixes - NFS over RDMA bugfixes - NFSv4 close locking fixes - Various NFSv4.x client state management optimisations - Rename/unlink code cleanups" * tag 'nfs-for-3.15-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (28 commits) nfs: pass string length to pr_notice message about readdir loops NFSv4: Fix a use-after-free problem in open() SUNRPC: rpc_restart_call/rpc_restart_call_prepare should clear task->tk_status SUNRPC: Don't let rpc_delay() clobber non-timeout errors SUNRPC: Ensure call_connect_status() deals correctly with SOFTCONN tasks SUNRPC: Ensure call_status() deals correctly with SOFTCONN tasks NFSv4: Ensure we respect soft mount timeouts during trunking discovery NFSv4: Schedule recovery if nfs40_walk_client_list() is interrupted NFS: advertise only supported callback netids SUNRPC: remove KERN_INFO from dprintk() call sites SUNRPC: Fix large reads on NFS/RDMA NFS: Clean up: revert increase in READDIR RPC buffer max size SUNRPC: Ensure that call_bind times out correctly SUNRPC: Ensure that call_connect times out correctly nfs: emit a fsnotify_nameremove call in sillyrename codepath nfs: remove synchronous rename code nfs: convert nfs_rename to use async_rename infrastructure nfs: make nfs_async_rename non-static nfs: abstract out code needed to complete a sillyrename NFSv4: Clear the open state flags if the new stateid does not match ...
| * nfs: pass string length to pr_notice message about readdir loopsJeff Layton2014-04-051-4/+3
| | | | | | | | | | | | | | | | | | | | | | There is no guarantee that the strings in the nfs_cache_array will be NULL-terminated. In the event that we end up hitting a readdir loop, we need to ensure that we pass the warning message the length of the string. Reported-by: Lachlan McIlroy <lmcilroy@redhat.com> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFSv4: Fix a use-after-free problem in open()Trond Myklebust2014-03-281-9/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | If we interrupt the nfs4_wait_for_completion_rpc_task() call in nfs4_run_open_task(), then we don't prevent the RPC call from completing. So freeing up the opendata->f_attr.mdsthreshold in the error path in _nfs4_do_open() leads to a use-after-free when the XDR decoder tries to decode the mdsthreshold information from the server. Fixes: 82be417aa37c0 (NFSv4.1 cache mdsthreshold values on OPEN) Tested-by: Steve Dickson <SteveD@redhat.com> Cc: stable@vger.kernel.org # 3.5+ Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFSv4: Ensure we respect soft mount timeouts during trunking discoveryTrond Myklebust2014-03-191-1/+3
| | | | | | | | | | Tested-by: Steve Dickson <steved@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFSv4: Schedule recovery if nfs40_walk_client_list() is interruptedTrond Myklebust2014-03-191-0/+7
| | | | | | | | | | | | | | | | | | | | If a timeout or a signal interrupts the NFSv4 trunking discovery SETCLIENTID_CONFIRM call, then we don't know whether or not the server has changed the callback identifier on us. Assume that it did, and schedule a 'path down' recovery... Tested-by: Steve Dickson <steved@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFS: advertise only supported callback netidsChuck Lever2014-03-171-6/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | NFSv4.0 clients use the SETCLIENTID operation to inform NFS servers how to contact a client's callback service. If a server cannot contact a client's callback service, that server will not delegate to that client, which results in a performance loss. Our client advertises "rdma" as the callback netid when the forward channel is "rdma". But our client always starts only "tcp" and "tcp6" callback services. Instead of advertising the forward channel netid, advertise "tcp" or "tcp6" as the callback netid, based on the value of the clientaddr mount option, since those are what our client currently supports. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=69171 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * NFS: Clean up: revert increase in READDIR RPC buffer max sizeChuck Lever2014-03-171-2/+1
| | | | | | | | | | | | | | | | | | | | Security labels go with each directory entry, thus they are always stored in the page cache, not in the head buffer. The length of the reply that goes in head[0] should not have changed to support NFSv4.2 labels. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| * Merge branch 'devel' into linux-nextTrond Myklebust2014-03-1711-167/+229
| |\
| | * nfs: emit a fsnotify_nameremove call in sillyrename codepathJeff Layton2014-03-171-2/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a file is sillyrenamed, then the generic vfs_unlink code will skip emitting fsnotify events for it. This patch has the sillyrename code do that instead. In truth this is a little bit odd since we aren't actually removing the dentry per-se, but renaming it. Still, this is probably the right thing to do since it's what userland apps expect to see when an unlink() occurs or some file is renamed on top of the dentry. Signed-off-by: Jeff Layton <jlayton@redhat.com> Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * nfs: remove synchronous rename codeJeff Layton2014-03-173-105/+0
| | | | | | | | | | | | | | | | | | | | | | | | Now that nfs_rename uses the async infrastructure, we can remove this. Signed-off-by: Jeff Layton <jlayton@redhat.com> Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * nfs: convert nfs_rename to use async_rename infrastructureJeff Layton2014-03-171-2/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There isn't much sense in maintaining two separate versions of rename code. Convert nfs_rename to use the asynchronous rename infrastructure that nfs_sillyrename uses, and emulate synchronous behavior by having the task just wait on the reply. Signed-off-by: Jeff Layton <jlayton@redhat.com> Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * nfs: make nfs_async_rename non-staticJeff Layton2014-03-172-1/+8
| | | | | | | | | | | | | | | | | | | | | | | | ...and move the prototype for nfs_sillyrename to internal.h. Signed-off-by: Jeff Layton <jlayton@redhat.com> Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * nfs: abstract out code needed to complete a sillyrenameJeff Layton2014-03-171-4/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The async rename code is currently "polluted" with some parts that are really just for sillyrenames. Add a new "complete" operation vector to the nfs_renamedata to separate out the stuff that just needs to be done for a sillyrename. Signed-off-by: Jeff Layton <jlayton@redhat.com> Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4: Clear the open state flags if the new stateid does not matchTrond Myklebust2014-02-193-5/+28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | RFC3530 and RFC5661 both prescribe that the 'opaque' field of the open stateid returned by new OPEN/OPEN_DOWNGRADE/CLOSE calls for the same file and open owner should match. If this is not the case, assume that the open state has been lost, and that we need to recover it. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4: Use correct locking when updating nfs4_state in nfs4_close_doneTrond Myklebust2014-02-191-30/+35
| | | | | | | | | | | | | | | | | | | | | The stateid and state->flags should be updated atomically under protection of the state->seqlock. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4.1: Ensure that we free existing layout segments if we get a new layoutTrond Myklebust2014-02-191-0/+15
| | | | | | | | | | | | | | | | | | | | | If the server returns a completely new layout stateid in response to our LAYOUTGET, then make sure to free any existing layout segments. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4.1: Minor optimisation in get_layout_by_fh_locked()Trond Myklebust2014-02-191-2/+2
| | | | | | | | | | | | | | | | | | | | | If the filehandles match, but the igrab() fails, or the layout is freed before we can get it, then just return NULL. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4.1: Ensure that the layout recall callback matches layout stateidsTrond Myklebust2014-02-191-5/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | It is not sufficient to compare filehandles when we receive a layout recall from the server; we also need to check that the layout stateids match. Reported-by: shaobingqing <shaobingqing@bwstor.com.cn> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4: Don't update the open stateid unless it is newer than the old oneTrond Myklebust2014-02-192-4/+27
| | | | | | | | | | | | | | | | | | This patch is in preparation for the NFSv4.1 parallel open capability. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFSv4.1: Fix wraparound issues in pnfs_seqid_is_newer()Trond Myklebust2014-02-191-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | Subtraction of signed integers does not have well defined wraparound semantics in the C99 standard. In order to be wraparound-safe, we have to use unsigned subtraction, and then cast the result. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
| | * NFS: Be more aggressive in using readdirplus for 'ls -l' situationsTrond Myklebust2014-02-113-11/+66
| | | | | | | | | | | | | | | | | | | | | | | | | | | Try to detect 'ls -l' by having nfs_getattr() look at whether or not there is an opendir() file descriptor for the parent directory. If so, then assume that we want to force use of readdirplus in order to avoid the multiple GETATTR calls over the wire. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
* | | Merge tag 'modules-next-for-linus' of ↵Linus Torvalds2014-04-063-7/+7
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux Pull module updates from Rusty Russell: "Nothing major: the stricter permissions checking for sysfs broke a staging driver; fix included. Greg KH said he'd take the patch but hadn't as the merge window opened, so it's included here to avoid breaking build" * tag 'modules-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: staging: fix up speakup kobject mode Use 'E' instead of 'X' for unsigned module taint flag. VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms. kallsyms: fix percpu vars on x86-64 with relocation. kallsyms: generalize address range checking module: LLVMLinux: Remove unused function warning from __param_check macro Fix: module signature vs tracepoints: add new TAINT_UNSIGNED_MODULE module: remove MODULE_GENERIC_TABLE module: allow multiple calls to MODULE_DEVICE_TABLE() per module module: use pr_cont
| * | | VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.Rusty Russell2014-03-243-7/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary of http://lkml.org/lkml/2014/3/14/363 : Ted: module_param(queue_depth, int, 444) Joe: 0444! Rusty: User perms >= group perms >= other perms? Joe: CLASS_ATTR, DEVICE_ATTR, SENSOR_ATTR and SENSOR_ATTR_2? Side effect of stricter permissions means removing the unnecessary S_IFREG from several callers. Note that the BUILD_BUG_ON_ZERO((perm) & 2) test was removed: a fair number of drivers fail this test, so that will be the debate for a future patch. Suggested-by: Joe Perches <joe@perches.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> for drivers/pci/slot.c Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
* | | | Merge tag 'xfs-for-linus-3.15-rc1' of git://oss.sgi.com/xfs/xfsLinus Torvalds2014-04-0454-415/+1177
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull xfs update from Dave Chinner: "There are a couple of new fallocate features in this request - it was decided that it was easiest to push them through the XFS tree using topic branches and have the ext4 support be based on those branches. Hence you may see some overlap with the ext4 tree merge depending on how they including those topic branches into their tree. Other than that, there is O_TMPFILE support, some cleanups and bug fixes. The main changes in the XFS tree for 3.15-rc1 are: - O_TMPFILE support - allowing AIO+DIO writes beyond EOF - FALLOC_FL_COLLAPSE_RANGE support for fallocate syscall and XFS implementation - FALLOC_FL_ZERO_RANGE support for fallocate syscall and XFS implementation - IO verifier cleanup and rework - stack usage reduction changes - vm_map_ram NOIO context fixes to remove lockdep warings - various bug fixes and cleanups" * tag 'xfs-for-linus-3.15-rc1' of git://oss.sgi.com/xfs/xfs: (34 commits) xfs: fix directory hash ordering bug xfs: extra semi-colon breaks a condition xfs: Add support for FALLOC_FL_ZERO_RANGE fs: Introduce FALLOC_FL_ZERO_RANGE flag for fallocate xfs: inode log reservations are still too small xfs: xfs_check_page_type buffer checks need help xfs: avoid AGI/AGF deadlock scenario for inode chunk allocation xfs: use NOIO contexts for vm_map_ram xfs: don't leak EFSBADCRC to userspace xfs: fix directory inode iolock lockdep false positive xfs: allocate xfs_da_args to reduce stack footprint xfs: always do log forces via the workqueue xfs: modify verifiers to differentiate CRC from other errors xfs: print useful caller information in xfs_error_report xfs: add xfs_verifier_error() xfs: add helper for updating checksums on xfs_bufs xfs: add helper for verifying checksums on xfs_bufs xfs: Use defines for CRC offsets in all cases xfs: skip pointless CRC updates after verifier failures xfs: Add support FALLOC_FL_COLLAPSE_RANGE for fallocate ...
| * \ \ \ Merge branch 'xfs-bug-fixes-for-3.15-3' into for-nextDave Chinner2014-04-042-3/+3
| |\ \ \ \
| | * | | | xfs: fix directory hash ordering bugMark Tinguely2014-04-041-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit f5ea1100 ("xfs: add CRCs to dir2/da node blocks") introduced in 3.10 incorrectly converted the btree hash index array pointer in xfs_da3_fixhashpath(). It resulted in the the current hash always being compared against the first entry in the btree rather than the current block index into the btree block's hash entry array. As a result, it was comparing the wrong hashes, and so could misorder the entries in the btree. For most cases, this doesn't cause any problems as it requires hash collisions to expose the ordering problem. However, when there are hash collisions within a directory there is a very good probability that the entries will be ordered incorrectly and that actually matters when duplicate hashes are placed into or removed from the btree block hash entry array. This bug results in an on-disk directory corruption and that results in directory verifier functions throwing corruption warnings into the logs. While no data or directory entries are lost, access to them may be compromised, and attempts to remove entries from a directory that has suffered from this corruption may result in a filesystem shutdown. xfs_repair will fix the directory hash ordering without data loss occuring. [dchinner: wrote useful a commit message] cc: <stable@vger.kernel.org> Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Mark Tinguely <tinguely@sgi.com> Reviewed-by: Ben Myers <bpm@sgi.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | xfs: extra semi-colon breaks a conditionDan Carpenter2014-04-041-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There were some extra semi-colons here which mean that we return true unintentionally. Fixes: a49935f200e2 ('xfs: xfs_check_page_type buffer checks need help') Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| * | | | | Merge branch 'xfs-O_TMPFILE-support' into for-nextDave Chinner2014-03-137-15/+201
| |\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: fs/xfs/xfs_trans_resv.c - fix for XFS_INODE_CLUSTER_SIZE macro removal
| | * | | | | xfs: allow linkat() on O_TMPFILE filesZhi Yong Wu2014-01-062-3/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The VFS allows an anonymous temporary file to be named at a later time via a linkat() syscall. The inodes for O_TMPFILE files are are marked with a special flag I_LINKABLE and have a zero link count. To support this in XFS, xfs_link() detects if this flag I_LINKABLE is set and behaves appropriately when detected. So in this case, its transaciton reservation takes into account the additional overhead of removing the inode from the unlinked list. Then the inode is removed from the unlinked list and the directory entry is added. Finally its link count is bumped accordingly. Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
| | * | | | | xfs: add O_TMPFILE supportZhi Yong Wu2014-01-066-3/+164
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add two functions xfs_create_tmpfile() and xfs_vn_tmpfile() to support O_TMPFILE file creation. In contrast to xfs_create(), xfs_create_tmpfile() has a different log reservation to the regular file creation because there is no directory modification, and doesn't check if an entry can be added to the directory, but the reservation quotas is required appropriately, and finally its inode is added to the unlinked list. xfs_vn_tmpfile() add one O_TMPFILE method to VFS interface and directly invoke xfs_create_tmpfile(). Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
| | * | | | | xfs: factor prid related codes into xfs_get_initial_prid()Zhi Yong Wu2014-01-063-9/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It will be reused by the O_TMPFILE creation function. Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com> Signed-off-by: Ben Myers <bpm@sgi.com>
| * | | | | | Merge branch 'xfs-bug-fixes-for-3.15-2' into for-nextDave Chinner2014-03-138-39/+126
| |\ \ \ \ \ \ | | | |/ / / / | | |/| | | |
| | * | | | | xfs: inode log reservations are still too smallDave Chinner2014-03-071-7/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Back in commit 23956703 ("xfs: inode log reservations are too small"), the reservation size was increased to take into account the difference in size between the in-memory BMBT block headers and the on-disk BMDR headers. This solved a transaction overrun when logging the inode size. Recently, however, we've seen a number of these same overruns on kernels with the above fix in it. All of them have been by 4 bytes, so we must still not be accounting for something correctly. Through inspection it turns out the above commit didn't take into account everything it should have. That is, it only accounts for a single log op_hdr structure, when it can actually require up to four op_hdrs - one for each region (log iovec) that is formatted. These regions are the inode log format header, the inode core, and the two forks that can be held in the literal area of the inode. This means we are not accounting for 36 bytes of log space that the transaction can use, and hence when we get inodes in certain formats with particular fragmentation patterns we can overrun the transaction. Fix this by adding the correct accounting for log op_headers in the transaction. Tested-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | xfs: xfs_check_page_type buffer checks need helpDave Chinner2014-03-071-31/+50
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | xfs_aops_discard_page() was introduced in the following commit: xfs: truncate delalloc extents when IO fails in writeback ... to clean up left over delalloc ranges after I/O failure in ->writepage(). generic/224 tests for this scenario and occasionally reproduces panics on sub-4k blocksize filesystems. The cause of this is failure to clean up the delalloc range on a page where the first buffer does not match one of the expected states of xfs_check_page_type(). If a buffer is not unwritten, delayed or dirty&mapped, xfs_check_page_type() stops and immediately returns 0. The stress test of generic/224 creates a scenario where the first several buffers of a page with delayed buffers are mapped & uptodate and some subsequent buffer is delayed. If the ->writepage() happens to fail for this page, xfs_aops_discard_page() incorrectly skips the entire page. This then causes later failures either when direct IO maps the range and finds the stale delayed buffer, or we evict the inode and find that the inode still has a delayed block reservation accounted to it. We can easily fix this xfs_aops_discard_page() failure by making xfs_check_page_type() check all buffers, but this breaks xfs_convert_page() more than it is already broken. Indeed, xfs_convert_page() wants xfs_check_page_type() to tell it if the first buffers on the pages are of a type that can be aggregated into the contiguous IO that is already being built. xfs_convert_page() should not be writing random buffers out of a page, but the current behaviour will cause it to do so if there are buffers that don't match the current specification on the page. Hence for xfs_convert_page() we need to: a) return "not ok" if the first buffer on the page does not match the specification provided to we don't write anything; and b) abort it's buffer-add-to-io loop the moment we come across a buffer that does not match the specification. Hence we need to fix both xfs_check_page_type() and xfs_convert_page() to work correctly with pages that have mixed buffer types, whilst allowing xfs_aops_discard_page() to scan all buffers on the page for a type match. Reported-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | xfs: avoid AGI/AGF deadlock scenario for inode chunk allocationBrian Foster2014-03-071-0/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The inode chunk allocation path can lead to deadlock conditions if a transaction is dirtied with an AGF (to fix up the freelist) for an AG that cannot satisfy the actual allocation request. This code path is written to try and avoid this scenario, but it can be reproduced by running xfstests generic/270 in a loop on a 512b fs. An example situation is: - process A attempts an inode allocation on AG 3, modifies the freelist, fails the allocation and ultimately moves on to AG 0 with the AG 3 AGF held - process B is doing a free space operation (i.e., truncate) and acquires the AG 0 AGF, waits on the AG 3 AGF - process A acquires the AG 0 AGI, waits on the AG 0 AGF (deadlock) The problem here is that process A acquired the AG 3 AGF while moving on to AG 0 (and releasing the AG 3 AGI with the AG 3 AGF held). xfs_dialloc() makes one pass through each of the AGs when attempting to allocate an inode chunk. The expectation is a clean transaction if a particular AG cannot satisfy the allocation request. xfs_ialloc_ag_alloc() is written to support this through use of the minalignslop allocation args field. When using the agi->agi_newino optimization, we attempt an exact bno allocation request based on the location of the previously allocated chunk. minalignslop is set to inform the allocator that we will require alignment on this chunk, and thus to not allow the request for this AG if the extra space is not available. Suppose that the AG in question has just enough space for this request, but not at the requested bno. xfs_alloc_fix_freelist() will proceed as normal as it determines the request should succeed, and thus it is allowed to modify the agf. xfs_alloc_ag_vextent() ultimately fails because the requested bno is not available. In response, the caller moves on to a NEAR_BNO allocation request for the same AG. The alignment is set, but the minalignslop field is never reset. This increases the overall requirement of the request from the first attempt. If this delta is the difference between allocation success and failure for the AG, xfs_alloc_fix_freelist() rejects this request outright the second time around and causes the allocation request to unnecessarily fail for this AG. To address this situation, reset the minalignslop field immediately after use and prevent it from leaking into subsequent requests. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | xfs: use NOIO contexts for vm_map_ramDave Chinner2014-03-072-1/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When we map pages in the buffer cache, we can do so in GFP_NOFS contexts. However, the vmap interfaces do not provide any method of communicating this information to memory reclaim, and hence we get lockdep complaining about it regularly and occassionally see hangs that may be vmap related reclaim deadlocks. We can also see these same problems from anywhere where we use vmalloc for a large buffer (e.g. attribute code) inside a transaction context. A typical lockdep report shows up as a reclaim state warning like so: [14046.101458] ================================= [14046.102850] [ INFO: inconsistent lock state ] [14046.102850] 3.14.0-rc4+ #2 Not tainted [14046.102850] --------------------------------- [14046.102850] inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. [14046.102850] kswapd0/14 [HC0[0]:SC0[0]:HE1:SE1] takes: [14046.102850] (&xfs_dir_ilock_class){++++?+}, at: [<791a04bb>] xfs_ilock+0xff/0x16a [14046.102850] {RECLAIM_FS-ON-W} state was registered at: [14046.102850] [<7904cdb1>] mark_held_locks+0x81/0xe7 [14046.102850] [<7904d390>] lockdep_trace_alloc+0x5c/0xb4 [14046.102850] [<790c2c28>] kmem_cache_alloc_trace+0x2b/0x11e [14046.102850] [<790ba7f4>] vm_map_ram+0x119/0x3e6 [14046.102850] [<7914e124>] _xfs_buf_map_pages+0x5b/0xcf [14046.102850] [<7914ed74>] xfs_buf_get_map+0x67/0x13f [14046.102850] [<7917506f>] xfs_attr_rmtval_set+0x396/0x4d5 [14046.102850] [<7916e8bb>] xfs_attr_leaf_addname+0x18f/0x37d [14046.102850] [<7916ed9e>] xfs_attr_set_int+0x2f5/0x3e8 [14046.102850] [<7916eefc>] xfs_attr_set+0x6b/0x74 [14046.102850] [<79168355>] xfs_xattr_set+0x61/0x81 [14046.102850] [<790e5b10>] generic_setxattr+0x59/0x68 [14046.102850] [<790e4c06>] __vfs_setxattr_noperm+0x58/0xce [14046.102850] [<790e4d0a>] vfs_setxattr+0x8e/0x92 [14046.102850] [<790e4ddd>] setxattr+0xcf/0x159 [14046.102850] [<790e5423>] SyS_lsetxattr+0x88/0xbb [14046.102850] [<79268438>] sysenter_do_call+0x12/0x36 Now, we can't completely remove these traces - mainly because vm_map_ram() will do GFP_KERNEL allocation and that generates the above warning before we get into the reclaim code, but we can turn them all into false positive warnings. To do that, use the method that DM and other IO context code uses to avoid this problem: there is a process flag to tell memory reclaim not to do IO that we can set appropriately. That prevents GFP_KERNEL context reclaim being done from deep inside the vmalloc code in places we can't directly pass a GFP_NOFS context to. That interface has a pair of wrapper functions: memalloc_noio_save() and memalloc_noio_restore(). Adding them around vm_map_ram and the vzalloc call in kmem_alloc_large() will prevent deadlocks and most lockdep reports for this issue. Also, convert the vzalloc() call in kmem_alloc_large() to use __vmalloc() so that we can pass the correct gfp context to the data page allocation routine inside __vmalloc() so that it is clear that GFP_NOFS context is important to this vmalloc call. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | xfs: don't leak EFSBADCRC to userspaceDave Chinner2014-03-073-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While the verifier routines may return EFSBADCRC when a buffer has a bad CRC, we need to translate that to EFSCORRUPTED so that the higher layers treat the error appropriately and we return a consistent error to userspace. This fixes a xfs/005 regression. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| * | | | | | Merge branch 'xfs-verifier-cleanup' into for-nextDave Chinner2014-03-1325-155/+202
| |\ \ \ \ \ \
| | * | | | | | xfs: modify verifiers to differentiate CRC from other errorsEric Sandeen2014-02-2716-117/+125
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Modify all read & write verifiers to differentiate between CRC errors and other inconsistencies. This sets the appropriate error number on bp->b_error, and then calls xfs_verifier_error() if something went wrong. That function will issue the appropriate message to the user. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: print useful caller information in xfs_error_reportEric Sandeen2014-02-271-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | xfs_error_report used to just print the hex address of the caller; %pF will give us something more human-readable. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Jie Liu <jeff.liu@oracle.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: add xfs_verifier_error()Eric Sandeen2014-02-273-0/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We want to distinguish between corruption, CRC errors, etc. In addition, the full stack trace on verifier errors seems less than helpful; it looks more like an oops than corruption. Create a new function to specifically alert the user to verifier errors, which can differentiate between EFSCORRUPTED and CRC mismatches. It doesn't dump stack unless the xfs error level is turned up high. Define a new error message (EFSBADCRC) to clearly identify CRC errors. (Defined to EBADMSG, bad message) Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: add helper for updating checksums on xfs_bufsEric Sandeen2014-02-2712-15/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Many/most callers of xfs_update_cksum() pass bp->b_addr and BBTOB(bp->b_length) as the first 2 args. Add a helper which can just accept the bp and the crc offset, and work it out on its own, for brevity. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: add helper for verifying checksums on xfs_bufsEric Sandeen2014-02-2713-26/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Many/most callers of xfs_verify_cksum() pass bp->b_addr and BBTOB(bp->b_length) as the first 2 args. Add a helper which can just accept the bp and the crc offset, and work it out on its own, for brevity. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: Use defines for CRC offsets in all casesEric Sandeen2014-02-279-17/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some calls to crc functions used useful #defines, others used awkward offsetof() constructs. Switch them all to #define to make things a bit cleaner. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | xfs: skip pointless CRC updates after verifier failuresEric Sandeen2014-02-272-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Most write verifiers don't update CRCs after the verifier has failed and the buffer has been marked in error. These two didn't, but should. Add returns to the verifier failure block, since the buffer won't be written anyway. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Jie Liu <jeff.liu@oracle.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| * | | | | | | Merge branch 'xfs-stack-fixes' into for-nextDave Chinner2014-03-133-143/+265
| |\ \ \ \ \ \ \
| | * | | | | | | xfs: fix directory inode iolock lockdep false positiveDave Chinner2014-02-271-0/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The change to add the IO lock to protect the directory extent map during readdir operations has cause lockdep to have a heart attack as it now sees a different locking order on inodes w.r.t. the mmap_sem because readdir has a different ordering to write(). Add a new lockdep class for directory inodes to avoid this false positive. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | | xfs: allocate xfs_da_args to reduce stack footprintDave Chinner2014-02-271-130/+212
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The struct xfs_da_args used to pass directory/attribute operation information to the lower layers is 128 bytes in size and is allocated on the stack. Dynamically allocate them to reduce the stack footprint of directory operations. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| | * | | | | | | xfs: always do log forces via the workqueueDave Chinner2014-02-271-13/+39
| | | |/ / / / / | | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Log forces can occur deep in the call chain when we have relatively little stack free. Log forces can also happen at close to the call chain leaves (e.g. xfs_buf_lock()) and hence we can trigger IO from places where we really don't want to add more stack overhead. This stack overhead occurs because log forces do foreground CIL pushes (xlog_cil_push_foreground()) rather than waking the background push wq and waiting for the for the push to complete. This foreground push was done to avoid confusing the CFQ Io scheduler when fsync()s were issued, as it has trouble dealing with dependent IOs being issued from different process contexts. Avoiding blowing the stack is much more critical than performance optimisations for CFQ, especially as we've been recommending against the use of CFQ for XFS since 3.2 kernels were release because of it's problems with multi-threaded IO workloads. Hence convert xlog_cil_push_foreground() to move the push work to the CIL workqueue. We already do the waiting for the push to complete in xlog_cil_force_lsn(), so there's nothing else we need to modify to make this work. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
| * | | | | | | Merge branch 'xfs-collapse-range' into for-nextDave Chinner2014-03-137-8/+355
| |\ \ \ \ \ \ \
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-04 22:18:47 +0000