summaryrefslogtreecommitdiffstats
path: root/fs/orangefs
Commit message (Collapse)AuthorAgeFilesLines
...
* get rid of bufmap argument of orangefs_bufmap_put()Al Viro2016-02-123-5/+6
| | | | | | | | it's always equal to __orangefs_bufmap and the latter can't change until we are done Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: get rid of handle_io_error()Al Viro2016-02-121-51/+14
| | | | | | | the second caller never needs to cancel, actually Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: wait_for_direct_io(): restore the position in iter when restartingAl Viro2016-02-121-0/+3
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: avoid freeing a slot twice in wait_for_direct_io()Al Viro2016-02-121-0/+1
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: added a couple of WARN_ONs, perhaps just temporarily.Mike Marshall2016-02-042-0/+2
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Do not retrieve size from servers unless it it necessary.Martin Brandenburg2016-02-041-2/+4
| | | | | Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Implement inode_operations->permission().Martin Brandenburg2016-02-046-1/+34
| | | | | | | | Thus d_revalidate is not obliged to check on as much, which will eventually lead the way to hammering the filesystem servers much less. Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Only compare attributes specified in orangefs_inode_getattr.Martin Brandenburg2016-02-041-19/+43
| | | | | Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: clean up slab allocation.Mike Marshall2016-02-044-124/+6
| | | | | | | | | | | | | | | A couple of caches were no longer needed: - iov_iter improvements to orangefs_devreq_write_iter eliminated the need for the dev_req_cache. - removal (months ago) of the old AIO code eliminated the need for the kiocb_cache. Also, deobfuscation of use of GFP_KERNEL when calling kmem_cache_(z)alloc for remaining caches. Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: improve gossip statementMike Marshall2016-02-041-2/+5
| | | | | | | | There were two just alike, making it hard maybe to tell which one you were looking at in syslog... so I changed it a little by adding some extra interesting tidbits to it... Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Fix revalidate.Martin Brandenburg2016-01-285-64/+187
| | | | | | | | | | | | | | | | Previously, it would update a live inode. This was fixed, but it did not ever check that the inode attributes in the dcache are correct. This checks all inode attributes and rejects any that are not correct, which causes a lookup and thus a new getattr. Perhaps inode_operations->permission should replace or augment some of this. There is no actual caching, and this does a rather excessive amount of network operations back to the filesystem server. Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Util functions shouldn't operate on inode where it can be avoided.Martin Brandenburg2016-01-281-39/+43
| | | | | Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: clean up op_alloc()Al Viro2016-01-233-22/+9
| | | | | | | | | fold orangefs_op_initialize() in there, don't bother locking something nobody else could've seen yet, use kmem_cache_zalloc() instead of explicit memset()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: move handle_io_error() to file.cAl Viro2016-01-232-46/+41
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: don't reinvent completion.h...Al Viro2016-01-235-62/+24
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* if ORANGEFS_VFS_OP_FILE_IO request had been given up, don't bother waitingAl Viro2016-01-231-16/+16
| | | | | | | | ... we are not going to get woken up anyway, so it's just going to time out and whine. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: get rid of MSECS_TO_JIFFIESAl Viro2016-01-234-17/+6
| | | | | | | | | All timeouts are in _seconds_, so all calls are of form MSECS_TO_JIFFIES(n * 1000), which is a convoluted way to spell n * HZ. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs_clean_up_interrupted_operation: call with op->lock heldAl Viro2016-01-231-32/+4
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: reduce nesting in wait_for_matching_downcall()Al Viro2016-01-231-60/+58
| | | | | | | reorder if branches... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: remove cargo-culting spin_lock_irqsave() in service_operation()Al Viro2016-01-231-7/+0
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: hopefully saner op refcounting and lockingAl Viro2016-01-238-143/+107
| | | | | | | | | | | | | | | | | | * create with refcount 1 * make op_release() decrement and free if zero (i.e. old put_op() has become that). * mark when submitter has given up waiting; from that point nobody else can move between the lists, change state, etc. * have daemon read/write_iter grab a reference when picking op and *always* give it up in the end * don't put into hash until we know it's been successfully passed to daemon * move op->lock _lower_ than htab_in_progress_lock (and make sure to take it in purge_inprogress_ops()) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: make sure that reopening pvfs2-req won't overlap with the end of closeAl Viro2016-01-231-3/+4
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: nothing should remain in request list and in hashAl Viro2016-01-231-22/+2
| | | | | | | | ... otherwise some thread is running in .text that is about to be freed. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: move wakeups into set_op_state_{serviced,purged}()Al Viro2016-01-231-18/+18
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: make wait_for_...downcall() staticAl Viro2016-01-231-0/+3
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: move wakeups into set_op_state_{serviced,purged}()Al Viro2016-01-234-13/+14
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: make wait_for_...downcall() staticAl Viro2016-01-232-4/+2
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* make orangefs_clean_up_interrupted_operation() staticAl Viro2016-01-232-2/+1
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: kill orangefs_inode_s ->listAl Viro2016-01-231-3/+0
| | | | | | | no users... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: get rid of <censored> macrosAl Viro2016-01-232-41/+44
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: ->poll() doesn't need spinlockAl Viro2016-01-231-2/+0
| | | | | | | not just for list_empty()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: kill ioctl32 rudimentsAl Viro2016-01-231-27/+0
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: ->poll() is only called between successful ->open() and ->release()Al Viro2016-01-231-7/+5
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: generic_file_open() is pointless for character devicesAl Viro2016-01-231-3/+2
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: use DEFINE_MUTEX (and mutex_init() had been too late)Al Viro2016-01-231-5/+2
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: make gossip statement more palatable to xtensaMike Marshall2016-01-192-4/+4
| | | | | | Thanks to Intel's kbuild test robot Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: add verification to decode_direntsMike Marshall2016-01-151-25/+93
| | | | | | Also add comments to decode_dirents and make it more readable. Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: make .statfs gossip_debug more complete.Mike Marshall2016-01-131-3/+7
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: define a minimum compatible userspace version.Mike Marshall2016-01-131-0/+1
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: change ORANGEFS_VERSION from "Unknown" to "upstream"Mike Marshall2016-01-131-1/+1
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: rename orangefs_kernel_op_s.aio_ref_count to just ref_count.Mike Marshall2016-01-132-7/+6
| | | | | | | The op structure's ref_count member hasn't got anything to do with asynchronous I/O. Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: implement .write_iterMike Marshall2016-01-131-263/+199
| | | | | | | | | | | | | | Until now, orangefs_devreq_write_iter has just been a wrapper for the old-fashioned orangefs_devreq_writev... linux would call .write_iter with "struct kiocb *iocb" and "struct iov_iter *iter" and .write_iter would just: return pvfs2_devreq_writev(iocb->ki_filp, iter->iov, iter->nr_segs, &iocb->ki_pos); Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Fix some more global namespace pollution.Martin Brandenburg2016-01-046-50/+33
| | | | | | | This only changes the names of things, so there is no functional change. Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: Don't pollute global namespaceRichard Weinberger2016-01-043-7/+7
| | | | | | | | | | | Prefix public functions with "orangefs_" do don't pollute the global namespace. This fixes a build issue on UML which also has block_signals(). Signed-off-by: Richard Weinberger <richard@nod.at> Signed-off-by: Martin Brandenburg <martin@omnibond.com> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* OrangeFS: constify export_operations structuresJulia Lawall2016-01-041-1/+1
| | | | | | | | | | This export_operations structure is never modified, so declare it as const. Most other structures of this type are already const. Done with the help of Coccinelle. Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: don't trigger copy_attributes_to_inode from d_revalidate.Mike Marshall2015-12-301-36/+14
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* orangefs: fix typo in ornagefs_inode_lockArnd Bergmann2015-12-281-1/+1
| | | | | | | | | Orangefs fails to build on 32-bit SMP configurations due to a simple misspelling, this does the obvious fix. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Fixes: 575e946125f7 ("Orangefs: change pvfs2 filenames to orangefs") Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: use kzalloc for kmalloc + memset 0Nicholas Mc Guire2015-12-281-2/+1
| | | | | | | | This is an API consolidation only. The use of kmalloc + memset to 0 should be equivalent to kzalloc in this case. Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org> Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: validate resp.listxattr.returned_countMike Marshall2015-12-171-1/+11
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
* Orangefs: don't use deprecated xattr defines.Mike Marshall2015-12-171-11/+2
| | | | Signed-off-by: Mike Marshall <hubcap@omnibond.com>
OpenPOWER on IntegriCloud