summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* nfsd: remove include/linux/nfsd/syscall.hJ. Bruce Fields2011-08-315-120/+0
| | | | | | We don't need this any more. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: remove redundant is_open_owner checkJ. Bruce Fields2011-08-271-2/+0
| | | | | | | When called with OPEN_STATE, preprocess_seqid_op only returns an open stateid, hence only an open owner. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: get lock checks out of preprocess_seqid_opJ. Bruce Fields2011-08-271-29/+20
| | | | | | | We've got some lock-specific code here in nfs4_preprocess_seqid_op which is only used by nfsd4_lock(). Move it to the caller. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: simplify lock openmode checkJ. Bruce Fields2011-08-271-10/+5
| | | | | | | | | Note that the special handling for the lock stateid case is already done by nfs4_check_openmode() (as of 02921914170e3b7fea1cd82dac9713685d2de5e2 "nfsd4: fix openmode checking on IO using lock stateid") so we no longer need these two cases in the caller. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: cleanup and consolidate seqid_mutating_errJ. Bruce Fields2011-08-273-37/+17
| | | | Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: remove HAS_SESSIONJ. Bruce Fields2011-08-273-23/+12
| | | | | | This flag doesn't really buy us anything. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: cleanup lock/stateowner initializationJ. Bruce Fields2011-08-271-48/+52
| | | | | | | Share some common code, stop doing silly things like initializing a list head immediately before adding it to a list, etc. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: name openowner data structures more clearlyJ. Bruce Fields2011-08-271-18/+18
| | | | | | | These appear to be generic (for both open and lock owners), but they're actually just for open owners. This has confused me more than once. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: replace some macros by functionsJ. Bruce Fields2011-08-271-15/+38
| | | | | | For all the usual reasons. (Type safety, readability.) Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: stop using nfserr_resource for transitory errorsJ. Bruce Fields2011-08-273-9/+9
| | | | | | | | | | The server is returning nfserr_resource for both permanent errors and for errors (like allocation failures) that might be resolved by retrying later. Save nfserr_resource for the former and use delay/jukebox for the latter. Cc: stable@kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: fix failure to end nfsd4 grace periodBoaz Harrosh2011-08-271-7/+8
| | | | | | | | | | | | | | | | | | | Even if we fail to write a recovery record, we should still mark the client as having acquired its first state. Otherwise we leave 4.1 clients with indefinite ERR_GRACE returns. However, an inability to write stable storage records may cause failures of reboot recovery, and the problem should still be brought to the server administrator's attention. So, make sure the error is logged. These errors shouldn't normally be triggered on a corectly functioning server--this isn't a case where a misconfigured client could spam the logs. Signed-off-by: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: simplify recovery dir settingJ. Bruce Fields2011-08-273-45/+34
| | | | | | | Move around some of this code, simplify a bit. Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd: prettify NFSD_MAY_* flag definitionsJ. Bruce Fields2011-08-271-14/+14
| | | | | Acked-by: Jim Rees <rees@umich.edu> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: permit read opens of executable-only filesJ. Bruce Fields2011-08-273-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | A client that wants to execute a file must be able to read it. Read opens over nfs are therefore implicitly allowed for executable files even when those files are not readable. NFSv2/v3 get this right by using a passed-in NFSD_MAY_OWNER_OVERRIDE on read requests, but NFSv4 has gotten this wrong ever since dc730e173785e29b297aa605786c94adaffe2544 "nfsd4: fix owner-override on open", when we realized that the file owner shouldn't override permissions on non-reclaim NFSv4 opens. So we can't use NFSD_MAY_OWNER_OVERRIDE to tell nfsd_permission to allow reads of executable files. So, do the same thing we do whenever we encounter another weird NFS permission nit: define yet another NFSD_MAY_* flag. The industry's future standardization on 128-bit processors will be motivated primarily by the need for integers with enough bits for all the NFSD_MAY_* flags. Reported-by: Leonardo Borda <leonardoborda@gmail.com> Cc: stable@kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* Remove include/linux/nfsd/const.hJ. Bruce Fields2011-08-274-45/+31
| | | | | | | Userspace shouldn't have a use for these constants. Nothing here is used outside fs/nfsd. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd: remove unused definesJ. Bruce Fields2011-08-271-13/+0
| | | | | | At least one of these is actually wrong anyway. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: it's OK to return nfserr_symlinkJ. Bruce Fields2011-08-273-23/+2
| | | | | | | | | | | | | | | | | | | | | The nfsd4 code has a bunch of special exceptions for error returns which map nfserr_symlink to other errors. In fact, the spec makes it clear that nfserr_symlink is to be preferred over less specific errors where possible. The patch that introduced it back in 2.6.4 is "kNFSd: correct symlink related error returns.", which claims that these special exceptions are represent an NFSv4 break from v2/v3 tradition--when in fact the symlink error was introduced with v4. I suspect what happened was pynfs tests were written that were overly faithful to the (known-incomplete) rfc3530 error return lists, and then code was fixed up mindlessly to make the tests pass. Delete these unnecessary exceptions. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: fix incorrect comment in nfsd4_set_nfs4_aclJ. Bruce Fields2011-08-271-1/+1
| | | | | | | | | Zero means "I don't care what kind of file this is". And that's probably what we want--acls are also settable at least on directories, and if the filesystem doesn't want them on other objects, leave it to it to complain. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd: clean up nfsd_mode_check()J. Bruce Fields2011-08-271-12/+18
| | | | | | | Add some more comments, simplify logic, do & S_IFMT just once, name "type" more helpfully. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd: open-code special directory-hardlink checkJ. Bruce Fields2011-08-272-11/+4
| | | | | | | | We allow the fh_verify caller to specify that any object *except* those of a given type is allowed, by passing a negative type. But only one caller actually uses it. Open-code that check in the one caller. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: clean up S_IS -> NF4 file type mappingJ. Bruce Fields2011-08-271-7/+14
| | | | | | | A slightly unconventional approach to make the code more compact I could live with, but let's give the poor reader *some* chance. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* sunrpc: use better NUMA affinitiesEric Dumazet2011-08-194-13/+28
| | | | | | | | | | | | | | | | Use NUMA aware allocations to reduce latencies and increase throughput. sunrpc kthreads can use kthread_create_on_node() if pool_mode is "percpu" or "pernode", and svc_prepare_thread()/svc_init_buffer() can also take into account NUMA node affinity for memory allocations. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: "J. Bruce Fields" <bfields@fieldses.org> CC: Neil Brown <neilb@suse.de> CC: David Miller <davem@davemloft.net> Reviewed-by: Greg Banks <gnb@fastmail.fm> [bfields@redhat.com: fix up caller nfs41_callback_up] Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* locks: setlease cleanupJ. Bruce Fields2011-08-191-16/+17
| | | | | | | | | There's an incorrect comment here. Also clean up the logic: the "rdlease" and "wrlease" locals are confusingly named, and don't really add anything since we can make a decision as soon as we hit one of these cases. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* locks: fix tracking of inprogress lease breaksJ. Bruce Fields2011-08-192-34/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | We currently use a bit in fl_flags to record whether a lease is being broken, and set fl_type to the type (RDLCK or UNLCK) that it will eventually have. This means that once the lease break starts, we forget what the lease's type *used* to be. Breaking a read lease will then result in blocking read opens, even though there's no conflict--because the lease type is now F_UNLCK and we can no longer tell whether it was previously a read or write lease. So, instead keep fl_type as the original type (the type which we enforce), and keep track of whether we're unlocking or merely downgrading by replacing the single FL_INPROGRESS flag by FL_UNLOCK_PENDING and FL_DOWNGRADE_PENDING flags. To get this right we also need to track separate downgrade and break times, to handle the case where a write-leased file gets conflicting opens first for read, then later for write. (I first considered just eliminating the downgrade behavior completely--nfsv4 doesn't need it, and nobody as far as I can tell actually uses it currently--but Jeremy Allison tells me that Windows oplocks do behave this way, so Samba will probably use this some day.) Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* locks: move F_INPROGRESS from fl_type to fl_flags fieldJ. Bruce Fields2011-08-194-14/+10
| | | | | | | | F_INPROGRESS isn't exposed to userspace. To me it makes more sense in fl_flags.... Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* locks: minor lease cleanupJ. Bruce Fields2011-08-191-5/+10
| | | | | | | Use a helper function, to simplify upcoming changes. Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: return nfserr_symlink on v4 OPEN of non-regular fileJ. Bruce Fields2011-08-191-0/+21
| | | | | | | Without this, an attempt to open a device special file without first stat'ing it will fail. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: fix seqid_mutating_errorJ. Bruce Fields2011-08-192-6/+12
| | | | | | | | | | | The set of errors here does *not* agree with the set of errors specified in the rfc! While we're there, turn this macros into a function, for the usual reasons, and move it to the one place where it's actually used. Cc: stable@kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* nfsd4: Remove check for a 32-bit cookie in nfsd4_readdir()Bernd Schubert2011-08-161-1/+1
| | | | | | | | | | | | Fan Yong <yong.fan@whamcloud.com> noticed setting FMODE_32bithash wouldn't work with nfsd v4, as nfsd4_readdir() checks for 32 bit cookies. However, according to RFC 3530 cookies have a 64 bit type and cookies are also defined as u64 in 'struct nfsd4_readdir'. So remove the test for >32-bit values. Cc: stable@kernel.org Signed-off-by: Bernd Schubert <bernd.schubert@itwm.fraunhofer.de> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
* Linux 3.1-rc1v3.1-rc1Linus Torvalds2011-08-081-2/+2
|
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparcLinus Torvalds2011-08-081-2/+4
|\ | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc: sparc: Fix build with DEBUG_PAGEALLOC enabled.
| * sparc: Fix build with DEBUG_PAGEALLOC enabled.David S. Miller2011-08-061-2/+4
| | | | | | | | | | | | | | arch/sparc/mm/init_64.c:1622:22: error: unused variable '__swapper_4m_tsb_phys_patch_end' [-Werror=unused-variable] arch/sparc/mm/init_64.c:1621:22: error: unused variable '__swapper_4m_tsb_phys_patch' [-Werror=unused-variable] Signed-off-by: David S. Miller <davem@davemloft.net>
* | sh: Fix boot crash related to SCIRafael J. Wysocki2011-08-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | Commit d006199e72a9 ("serial: sh-sci: Regtype probing doesn't need to be fatal.") made sci_init_single() return when sci_probe_regmap() succeeds, although it should return when sci_probe_regmap() fails. This causes systems using the serial sh-sci driver to crash during boot. Fix the problem by using the right return condition. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | arm: remove stale export of 'sha_transform'Linus Torvalds2011-08-081-3/+0
| | | | | | | | | | | | | | The generic library code already exports the generic function, this was left-over from the ARM-specific version that just got removed. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | arm: remove "optimized" SHA1 routinesLinus Torvalds2011-08-072-212/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since commit 1eb19a12bd22 ("lib/sha1: use the git implementation of SHA-1"), the ARM SHA1 routines no longer work. The reason? They depended on the larger 320-byte workspace, and now the sha1 workspace is just 16 words (64 bytes). So the assembly version would overwrite the stack randomly. The optimized asm version is also probably slower than the new improved C version, so there's no reason to keep it around. At least that was the case in git, where what appears to be the same assembly language version was removed two years ago because the optimized C BLK_SHA1 code was faster. Reported-and-tested-by: Joachim Eastwood <manabian@gmail.com> Cc: Andreas Schwab <schwab@linux-m68k.org> Cc: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | fix rcu annotations noise in cred.hAl Viro2011-08-071-5/+6
| | | | | | | | | | | | | | | | | | | | | | | | task->cred is declared as __rcu, and access to other tasks' ->cred is, indeed, protected. Access to current->cred does not need rcu_dereference() at all, since only the task itself can change its ->cred. sparse, of course, has no way of knowing that... Add force-cast in current_cred(), make current_fsuid() et.al. use it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | vfs: rename 'do_follow_link' to 'should_follow_link'Linus Torvalds2011-08-071-2/+2
| | | | | | | | | | | | | | | | Al points out that the do_follow_link() helper function really is misnamed - it's about whether we should try to follow a symlink or not, not about actually doing the following. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | Fix POSIX ACL permission checkAri Savolainen2011-08-071-1/+1
| | | | | | | | | | | | | | | | | | After commit 3567866bf261: "RCUify freeing acls, let check_acl() go ahead in RCU mode if acl is cached" posix_acl_permission is being called with an unsupported flag and the permission check fails. This patch fixes the issue. Signed-off-by: Ari Savolainen <ari.m.savolainen@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* | Merge branch 'for-linus' of git://git.open-osd.org/linux-open-osdLinus Torvalds2011-08-079-504/+617
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://git.open-osd.org/linux-open-osd: ore: Make ore its own module exofs: Rename raid engine from exofs/ios.c => ore exofs: ios: Move to a per inode components & device-table exofs: Move exofs specific osd operations out of ios.c exofs: Add offset/length to exofs_get_io_state exofs: Fix truncate for the raid-groups case exofs: Small cleanup of exofs_fill_super exofs: BUG: Avoid sbi realloc exofs: Remove pnfs-osd private definitions nfs_xdr: Move nfs4_string definition out of #ifdef CONFIG_NFS_V4
| * | ore: Make ore its own moduleBoaz Harrosh2011-08-073-1/+23
| | | | | | | | | | | | | | | | | | | | | Export everything from ore need exporting. Change Kbuild and Kconfig to build ore.ko as an independent module. Import ore from exofs Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Rename raid engine from exofs/ios.c => oreBoaz Harrosh2011-08-076-255/+295
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ORE stands for "Objects Raid Engine" This patch is a mechanical rename of everything that was in ios.c and its API declaration to an ore.c and an osd_ore.h header. The ore engine will later be used by the pnfs objects layout driver. * File ios.c => ore.c * Declaration of types and API are moved from exofs.h to a new osd_ore.h * All used types are prefixed by ore_ from their exofs_ name. * Shift includes from exofs.h to osd_ore.h so osd_ore.h is independent, include it from exofs.h. Other than a pure rename there are no other changes. Next patch will move the ore into it's own module and will export the API to be used by exofs and later the layout driver Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: ios: Move to a per inode components & device-tableBoaz Harrosh2011-08-074-183/+218
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Exofs raid engine was saving on memory space by having a single layout-info, single pid, and a single device-table, global to the filesystem. Then passing a credential and object_id info at the io_state level, private for each inode. It would also devise this contraption of rotating the device table view for each inode->ino to spread out the device usage. This is not compatible with the pnfs-objects standard, demanding that each inode can have it's own layout-info, device-table, and each object component it's own pid, oid and creds. So: Bring exofs raid engine to be usable for generic pnfs-objects use by: * Define an exofs_comp structure that holds obj_id and credential info. * Break up exofs_layout struct to an exofs_components structure that holds a possible array of exofs_comp and the array of devices + the size of the arrays. * Add a "comps" parameter to get_io_state() that specifies the ids creds and device array to use for each IO. This enables to keep the layout global, but the device-table view, creds and IDs at the inode level. It only adds two 64bit to each inode, since some of these members already existed in another form. * ios raid engine now access layout-info and comps-info through the passed pointers. Everything is pre-prepared by caller for generic access of these structures and arrays. At the exofs Level: * Super block holds an exofs_components struct that holds the device array, previously in layout. The devices there are in device-table order. The device-array is twice bigger and repeats the device-table twice so now each inode's device array can point to a random device and have a round-robin view of the table, making it compatible to previous exofs versions. * Each inode has an exofs_components struct that is initialized at load time, with it's own view of the device table IDs and creds. When doing IO this gets passed to the io_state together with the layout. While preforming this change. Bugs where found where credentials with the wrong IDs where used to access the different SB objects (super.c). As well as some dead code. It was never noticed because the target we use does not check the credentials. Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Move exofs specific osd operations out of ios.cBoaz Harrosh2011-08-074-73/+79
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ios.c will be moving to an external library, for use by the objects-layout-driver. Remove from it some exofs specific functions. Also g_attr_logical_length is used both by inode.c and ios.c move definition to the later, to keep it independent Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Add offset/length to exofs_get_io_stateBoaz Harrosh2011-08-073-16/+38
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In future raid code we will need to know the IO offset/length and if it's a read or write to determine some of the array sizes we'll need. So add a new exofs_get_rw_state() API for use when writeing/reading. All other simple cases are left using the old way. The major change to this is that now we need to call exofs_get_io_state later at inode.c::read_exec and inode.c::write_exec when we actually know these things. So this patch is kept separate so I can test things apart from other changes. Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Fix truncate for the raid-groups caseBoaz Harrosh2011-08-041-20/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In the general raid-group case the truncate was wrong in that it did not also fix the object length of the neighboring groups. There are two bad cases in the old code: 1. Space that should be freed was not. 2. If a file That was big is truncated small, then made bigger again, the holes would not contain zeros but could expose old data. (If the growing of the file expands to more than a full groups cycle + group size (> S + T)) Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Small cleanup of exofs_fill_superBoaz Harrosh2011-08-041-4/+2
| | | | | | | | | | | | | | | | | | | | | Small cleanup that unifies duplicated code used in both the error and success cases Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: BUG: Avoid sbi reallocBoaz Harrosh2011-08-042-24/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since the beginning we realloced the sbi structure when a bigger then one device table was specified. (I know that was really stupid). Then much later when "register bdi" was added (By Jens) it was registering the pointer to sbi->bdi before the realloc. We never saw this problem because up till now the realloc did not do anything since the device table was small enough to fit in the original allocation. But once we starting testing with large device tables (Bigger then 28) we noticed the crash of writeback operating on a deallocated pointer. * Avoid the all mess by allocating the device-table as a second array and get rid of the variable-sized structure and the rest of this mess. * Take the chance to clean near by structures and comments. * Add a needed dprint on startup to indicate the loaded layout. * Also move the bdi registration to the very end because it will only fail in a low memory, which will probably fail before hand. There are many more likely causes to not load before that. This way the error handling is made simpler. (Just doing this would be enough to fix the BUG) Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | exofs: Remove pnfs-osd private definitionsBoaz Harrosh2011-08-042-50/+1
| | | | | | | | | | | | | | | | | | | | | Now that pnfs-osd has hit mainline we can remove exofs's private header. (And the FIXME comment) Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
| * | nfs_xdr: Move nfs4_string definition out of #ifdef CONFIG_NFS_V4Boaz Harrosh2011-08-041-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | exofs file system wants to use pnfs_osd_xdr.h file instead of redefining pnfs-objects types in it's private "pnfs.h" headr. Before we do the switch we must make sure pnfs_osd_xdr.h is compilable also under NFS versions smaller than 4.1. Since now it is needed regardless of version, by the exofs code. nfs4_string is not the only nfs4 type out in the global scope. Ack-by: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
* | | vfs: optimize inode cache access patternsLinus Torvalds2011-08-074-34/+106
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The inode structure layout is largely random, and some of the vfs paths really do care. The path lookup in particular is already quite D$ intensive, and profiles show that accessing the 'inode->i_op->xyz' fields is quite costly. We already optimized the dcache to not unnecessarily load the d_op structure for members that are often NULL using the DCACHE_OP_xyz bits in dentry->d_flags, and this does something very similar for the inode ops that are used during pathname lookup. It also re-orders the fields so that the fields accessed by 'stat' are together at the beginning of the inode structure, and roughly in the order accessed. The effect of this seems to be in the 1-2% range for an empty kernel "make -j" run (which is fairly kernel-intensive, mostly in filename lookup), so it's visible. The numbers are fairly noisy, though, and likely depend a lot on exact microarchitecture. So there's more tuning to be done. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-16 22:50:47 +0100