linux/fs/xfs/xfs_super.c

1833 lines
48 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_alloc.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_fsops.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
#include "xfs_vnodeops.h"
#include "xfs_log_priv.h"
[XFS] Move AIL pushing into it's own thread When many hundreds to thousands of threads all try to do simultaneous transactions and the log is in a tail-pushing situation (i.e. full), we can get multiple threads walking the AIL list and contending on the AIL lock. The AIL push is, in effect, a simple I/O dispatch algorithm complicated by the ordering constraints placed on it by the transaction subsystem. It really does not need multiple threads to push on it - even when only a single CPU is pushing the AIL, it can push the I/O out far faster that pretty much any disk subsystem can handle. So, to avoid contention problems stemming from multiple list walkers, move the list walk off into another thread and simply provide a "target" to push to. When a thread requires a push, it sets the target and wakes the push thread, then goes to sleep waiting for the required amount of space to become available in the log. This mechanism should also be a lot fairer under heavy load as the waiters will queue in arrival order, rather than queuing in "who completed a push first" order. Also, by moving the pushing to a separate thread we can do more effectively overload detection and prevention as we can keep context from loop iteration to loop iteration. That is, we can push only part of the list each loop and not have to loop back to the start of the list every time we run. This should also help by reducing the number of items we try to lock and/or push items that we cannot move. Note that this patch is not intended to solve the inefficiencies in the AIL structure and the associated issues with extremely large list contents. That needs to be addresses separately; parallel access would cause problems to any new structure as well, so I'm only aiming to isolate the structure from unbounded parallelism here. SGI-PV: 972759 SGI-Modid: xfs-linux-melb:xfs-kern:30371a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
2008-02-05 09:13:32 +08:00
#include "xfs_trans_priv.h"
#include "xfs_filestream.h"
#include "xfs_da_btree.h"
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
#include "xfs_inode_item.h"
#include "xfs_icache.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
#include "xfs_trace.h"
#include "xfs_icreate_item.h"
#include <linux/namei.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/mempool.h>
#include <linux/writeback.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
static kmem_zone_t *xfs_ioend_zone;
mempool_t *xfs_ioend_pool;
#define MNTOPT_LOGBUFS "logbufs" /* number of XFS log buffers */
#define MNTOPT_LOGBSIZE "logbsize" /* size of XFS log buffers */
#define MNTOPT_LOGDEV "logdev" /* log device */
#define MNTOPT_RTDEV "rtdev" /* realtime I/O device */
#define MNTOPT_BIOSIZE "biosize" /* log2 of preferred buffered io size */
#define MNTOPT_WSYNC "wsync" /* safe-mode nfs compatible mount */
#define MNTOPT_NOALIGN "noalign" /* turn off stripe alignment */
#define MNTOPT_SWALLOC "swalloc" /* turn on stripe width allocation */
#define MNTOPT_SUNIT "sunit" /* data volume stripe unit */
#define MNTOPT_SWIDTH "swidth" /* data volume stripe width */
#define MNTOPT_NOUUID "nouuid" /* ignore filesystem UUID */
#define MNTOPT_MTPT "mtpt" /* filesystem mount point */
#define MNTOPT_GRPID "grpid" /* group-ID from parent directory */
#define MNTOPT_NOGRPID "nogrpid" /* group-ID from current process */
#define MNTOPT_BSDGROUPS "bsdgroups" /* group-ID from parent directory */
#define MNTOPT_SYSVGROUPS "sysvgroups" /* group-ID from current process */
#define MNTOPT_ALLOCSIZE "allocsize" /* preferred allocation size */
#define MNTOPT_NORECOVERY "norecovery" /* don't run XFS recovery */
#define MNTOPT_BARRIER "barrier" /* use writer barriers for log write and
* unwritten extent conversion */
#define MNTOPT_NOBARRIER "nobarrier" /* .. disable */
#define MNTOPT_64BITINODE "inode64" /* inodes can be allocated anywhere */
#define MNTOPT_32BITINODE "inode32" /* inode allocation limited to
* XFS_MAXINUMBER_32 */
#define MNTOPT_IKEEP "ikeep" /* do not free empty inode clusters */
#define MNTOPT_NOIKEEP "noikeep" /* free empty inode clusters */
#define MNTOPT_LARGEIO "largeio" /* report large I/O sizes in stat() */
#define MNTOPT_NOLARGEIO "nolargeio" /* do not report large I/O sizes
* in stat(). */
#define MNTOPT_ATTR2 "attr2" /* do use attr2 attribute format */
#define MNTOPT_NOATTR2 "noattr2" /* do not use attr2 attribute format */
#define MNTOPT_FILESTREAM "filestreams" /* use filestreams allocator */
#define MNTOPT_QUOTA "quota" /* disk quotas (user) */
#define MNTOPT_NOQUOTA "noquota" /* no quotas */
#define MNTOPT_USRQUOTA "usrquota" /* user quota enabled */
#define MNTOPT_GRPQUOTA "grpquota" /* group quota enabled */
#define MNTOPT_PRJQUOTA "prjquota" /* project quota enabled */
#define MNTOPT_UQUOTA "uquota" /* user quota (IRIX variant) */
#define MNTOPT_GQUOTA "gquota" /* group quota (IRIX variant) */
#define MNTOPT_PQUOTA "pquota" /* project quota (IRIX variant) */
#define MNTOPT_UQUOTANOENF "uqnoenforce"/* user quota limit enforcement */
#define MNTOPT_GQUOTANOENF "gqnoenforce"/* group quota limit enforcement */
#define MNTOPT_PQUOTANOENF "pqnoenforce"/* project quota limit enforcement */
#define MNTOPT_QUOTANOENF "qnoenforce" /* same as uqnoenforce */
#define MNTOPT_DELAYLOG "delaylog" /* Delayed logging enabled */
#define MNTOPT_NODELAYLOG "nodelaylog" /* Delayed logging disabled */
#define MNTOPT_DISCARD "discard" /* Discard unused blocks */
#define MNTOPT_NODISCARD "nodiscard" /* Do not discard unused blocks */
/*
* Table driven mount option parser.
*
* Currently only used for remount, but it will be used for mount
* in the future, too.
*/
enum {
Opt_barrier,
Opt_nobarrier,
Opt_inode64,
Opt_inode32,
Opt_err
};
static const match_table_t tokens = {
{Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
{Opt_inode64, "inode64"},
{Opt_inode32, "inode32"},
{Opt_err, NULL}
};
STATIC unsigned long
suffix_kstrtoint(char *s, unsigned int base, int *res)
{
int last, shift_left_factor = 0, _res;
char *value = s;
last = strlen(value) - 1;
if (value[last] == 'K' || value[last] == 'k') {
shift_left_factor = 10;
value[last] = '\0';
}
if (value[last] == 'M' || value[last] == 'm') {
shift_left_factor = 20;
value[last] = '\0';
}
if (value[last] == 'G' || value[last] == 'g') {
shift_left_factor = 30;
value[last] = '\0';
}
if (kstrtoint(s, base, &_res))
return -EINVAL;
*res = _res << shift_left_factor;
return 0;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock has _not_ yet been read in.
*
* Note that this function leaks the various device name allocations on
* failure. The caller takes care of them.
*/
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
char *options)
{
struct super_block *sb = mp->m_super;
char *this_char, *value;
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
__uint8_t iosizelog = 0;
/*
* set up the mount name first so all the errors will refer to the
* correct device.
*/
mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_fsname)
return ENOMEM;
mp->m_fsname_len = strlen(mp->m_fsname) + 1;
/*
* Copy binary VFS mount flags we are interested in.
*/
if (sb->s_flags & MS_RDONLY)
mp->m_flags |= XFS_MOUNT_RDONLY;
if (sb->s_flags & MS_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
if (sb->s_flags & MS_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
* Set some default flags that could be cleared by the mount option
* parsing.
*/
mp->m_flags |= XFS_MOUNT_BARRIER;
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
#if !XFS_BIG_INUMS
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
#endif
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
if (!options)
goto done;
while ((this_char = strsep(&options, ",")) != NULL) {
if (!*this_char)
continue;
if ((value = strchr(this_char, '=')) != NULL)
*value++ = 0;
if (!strcmp(this_char, MNTOPT_LOGBUFS)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (kstrtoint(value, 10, &mp->m_logbufs))
return EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (suffix_kstrtoint(value, 10, &mp->m_logbsize))
return EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_logname)
return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_MTPT)) {
xfs_warn(mp, "%s option not allowed on this system",
this_char);
return EINVAL;
} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_rtname)
return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_BIOSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (kstrtoint(value, 10, &iosize))
return EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (suffix_kstrtoint(value, 10, &iosize))
return EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_GRPID) ||
!strcmp(this_char, MNTOPT_BSDGROUPS)) {
mp->m_flags |= XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_NOGRPID) ||
!strcmp(this_char, MNTOPT_SYSVGROUPS)) {
mp->m_flags &= ~XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
mp->m_flags |= XFS_MOUNT_WSYNC;
} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
mp->m_flags |= XFS_MOUNT_NORECOVERY;
} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
mp->m_flags |= XFS_MOUNT_NOALIGN;
} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
mp->m_flags |= XFS_MOUNT_SWALLOC;
} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (kstrtoint(value, 10, &dsunit))
return EINVAL;
} else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
if (kstrtoint(value, 10, &dswidth))
return EINVAL;
} else if (!strcmp(this_char, MNTOPT_32BITINODE)) {
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
#if !XFS_BIG_INUMS
xfs_warn(mp, "%s option not allowed on this system",
this_char);
return EINVAL;
#endif
} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
mp->m_flags |= XFS_MOUNT_NOUUID;
} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
mp->m_flags |= XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
mp->m_flags &= ~XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
mp->m_flags |= XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
mp->m_flags &= ~XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
mp->m_flags |= XFS_MOUNT_ATTR2;
} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
mp->m_flags &= ~XFS_MOUNT_ATTR2;
mp->m_flags |= XFS_MOUNT_NOATTR2;
} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
mp->m_flags |= XFS_MOUNT_FILESTREAMS;
} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
!strcmp(this_char, MNTOPT_UQUOTA) ||
!strcmp(this_char, MNTOPT_USRQUOTA)) {
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
!strcmp(this_char, MNTOPT_UQUOTANOENF)) {
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_UQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_PQUOTA) ||
!strcmp(this_char, MNTOPT_PRJQUOTA)) {
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
!strcmp(this_char, MNTOPT_GRPQUOTA)) {
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_GQUOTA_ENFD;
xfs: Introduce delayed logging core code The delayed logging code only changes in-memory structures and as such can be enabled and disabled with a mount option. Add the mount option and emit a warning that this is an experimental feature that should not be used in production yet. We also need infrastructure to track committed items that have not yet been written to the log. This is what the Committed Item List (CIL) is for. The log item also needs to be extended to track the current log vector, the associated memory buffer and it's location in the Commit Item List. Extend the log item and log vector structures to enable this tracking. To maintain the current log format for transactions with delayed logging, we need to introduce a checkpoint transaction and a context for tracking each checkpoint from initiation to transaction completion. This includes adding a log ticket for tracking space log required/used by the context checkpoint. To track all the changes we need an io vector array per log item, rather than a single array for the entire transaction. Using the new log vector structure for this requires two passes - the first to allocate the log vector structures and chain them together, and the second to fill them out. This log vector chain can then be passed to the CIL for formatting, pinning and insertion into the CIL. Formatting of the log vector chain is relatively simple - it's just a loop over the iovecs on each log vector, but it is made slightly more complex because we re-write the iovec after the copy to point back at the memory buffer we just copied into. This code also needs to pin log items. If the log item is not already tracked in this checkpoint context, then it needs to be pinned. Otherwise it is already pinned and we don't need to pin it again. The only other complexity is calculating the amount of new log space the formatting has consumed. This needs to be accounted to the transaction in progress, and the accounting is made more complex becase we need also to steal space from it for log metadata in the checkpoint transaction. Calculate all this at insert time and update all the tickets, counters, etc correctly. Once we've formatted all the log items in the transaction, attach the busy extents to the checkpoint context so the busy extents live until checkpoint completion and can be processed at that point in time. Transactions can then be freed at this point in time. Now we need to issue checkpoints - we are tracking the amount of log space used by the items in the CIL, so we can trigger background checkpoints when the space usage gets to a certain threshold. Otherwise, checkpoints need ot be triggered when a log synchronisation point is reached - a log force event. Because the log write code already handles chained log vectors, writing the transaction is trivial, too. Construct a transaction header, add it to the head of the chain and write it into the log, then issue a commit record write. Then we can release the checkpoint log ticket and attach the context to the log buffer so it can be called during Io completion to complete the checkpoint. We also need to allow for synchronising multiple in-flight checkpoints. This is needed for two things - the first is to ensure that checkpoint commit records appear in the log in the correct sequence order (so they are replayed in the correct order). The second is so that xfs_log_force_lsn() operates correctly and only flushes and/or waits for the specific sequence it was provided with. To do this we need a wait variable and a list tracking the checkpoint commits in progress. We can walk this list and wait for the checkpoints to change state or complete easily, an this provides the necessary synchronisation for correct operation in both cases. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-21 12:37:18 +08:00
} else if (!strcmp(this_char, MNTOPT_DELAYLOG)) {
xfs_warn(mp,
"delaylog is the default now, option is deprecated.");
xfs: Introduce delayed logging core code The delayed logging code only changes in-memory structures and as such can be enabled and disabled with a mount option. Add the mount option and emit a warning that this is an experimental feature that should not be used in production yet. We also need infrastructure to track committed items that have not yet been written to the log. This is what the Committed Item List (CIL) is for. The log item also needs to be extended to track the current log vector, the associated memory buffer and it's location in the Commit Item List. Extend the log item and log vector structures to enable this tracking. To maintain the current log format for transactions with delayed logging, we need to introduce a checkpoint transaction and a context for tracking each checkpoint from initiation to transaction completion. This includes adding a log ticket for tracking space log required/used by the context checkpoint. To track all the changes we need an io vector array per log item, rather than a single array for the entire transaction. Using the new log vector structure for this requires two passes - the first to allocate the log vector structures and chain them together, and the second to fill them out. This log vector chain can then be passed to the CIL for formatting, pinning and insertion into the CIL. Formatting of the log vector chain is relatively simple - it's just a loop over the iovecs on each log vector, but it is made slightly more complex because we re-write the iovec after the copy to point back at the memory buffer we just copied into. This code also needs to pin log items. If the log item is not already tracked in this checkpoint context, then it needs to be pinned. Otherwise it is already pinned and we don't need to pin it again. The only other complexity is calculating the amount of new log space the formatting has consumed. This needs to be accounted to the transaction in progress, and the accounting is made more complex becase we need also to steal space from it for log metadata in the checkpoint transaction. Calculate all this at insert time and update all the tickets, counters, etc correctly. Once we've formatted all the log items in the transaction, attach the busy extents to the checkpoint context so the busy extents live until checkpoint completion and can be processed at that point in time. Transactions can then be freed at this point in time. Now we need to issue checkpoints - we are tracking the amount of log space used by the items in the CIL, so we can trigger background checkpoints when the space usage gets to a certain threshold. Otherwise, checkpoints need ot be triggered when a log synchronisation point is reached - a log force event. Because the log write code already handles chained log vectors, writing the transaction is trivial, too. Construct a transaction header, add it to the head of the chain and write it into the log, then issue a commit record write. Then we can release the checkpoint log ticket and attach the context to the log buffer so it can be called during Io completion to complete the checkpoint. We also need to allow for synchronising multiple in-flight checkpoints. This is needed for two things - the first is to ensure that checkpoint commit records appear in the log in the correct sequence order (so they are replayed in the correct order). The second is so that xfs_log_force_lsn() operates correctly and only flushes and/or waits for the specific sequence it was provided with. To do this we need a wait variable and a list tracking the checkpoint commits in progress. We can walk this list and wait for the checkpoints to change state or complete easily, an this provides the necessary synchronisation for correct operation in both cases. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2010-05-21 12:37:18 +08:00
} else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
xfs_warn(mp,
"nodelaylog support has been removed, option is deprecated.");
} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
mp->m_flags |= XFS_MOUNT_DISCARD;
} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
mp->m_flags &= ~XFS_MOUNT_DISCARD;
} else if (!strcmp(this_char, "ihashsize")) {
xfs_warn(mp,
"ihashsize no longer used, option is deprecated.");
} else if (!strcmp(this_char, "osyncisdsync")) {
xfs_warn(mp,
"osyncisdsync has no effect, option is deprecated.");
} else if (!strcmp(this_char, "osyncisosync")) {
xfs_warn(mp,
"osyncisosync has no effect, option is deprecated.");
} else if (!strcmp(this_char, "irixsgid")) {
xfs_warn(mp,
"irixsgid is now a sysctl(2) variable, option is deprecated.");
} else {
xfs_warn(mp, "unknown mount option [%s].", this_char);
return EINVAL;
}
}
/*
* no recovery flag requires a read-only mount
*/
if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return EINVAL;
}
if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return EINVAL;
}
#ifndef CONFIG_XFS_QUOTA
if (XFS_IS_QUOTA_RUNNING(mp)) {
xfs_warn(mp, "quota support not available in this kernel.");
return EINVAL;
}
#endif
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return EINVAL;
}
if (dsunit && (dswidth % dsunit != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
dswidth, dsunit);
return EINVAL;
}
done:
if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
* At this point the superblock has not been read
* in, therefore we do not know the block size.
* Before the mount call ends we will convert
* these to FSBs.
*/
mp->m_dalign = dsunit;
mp->m_swidth = dswidth;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return XFS_ERROR(EINVAL);
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return XFS_ERROR(EINVAL);
}
if (iosizelog) {
if (iosizelog > XFS_MAX_IO_LOG ||
iosizelog < XFS_MIN_IO_LOG) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
iosizelog, XFS_MIN_IO_LOG,
XFS_MAX_IO_LOG);
return XFS_ERROR(EINVAL);
}
mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
mp->m_readio_log = iosizelog;
mp->m_writeio_log = iosizelog;
}
return 0;
}
struct proc_xfs_info {
int flag;
char *str;
};
STATIC int
xfs_showargs(
struct xfs_mount *mp,
struct seq_file *m)
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_IKEEP, "," MNTOPT_IKEEP },
{ XFS_MOUNT_WSYNC, "," MNTOPT_WSYNC },
{ XFS_MOUNT_NOALIGN, "," MNTOPT_NOALIGN },
{ XFS_MOUNT_SWALLOC, "," MNTOPT_SWALLOC },
{ XFS_MOUNT_NOUUID, "," MNTOPT_NOUUID },
{ XFS_MOUNT_NORECOVERY, "," MNTOPT_NORECOVERY },
{ XFS_MOUNT_ATTR2, "," MNTOPT_ATTR2 },
{ XFS_MOUNT_FILESTREAMS, "," MNTOPT_FILESTREAM },
{ XFS_MOUNT_GRPID, "," MNTOPT_GRPID },
{ XFS_MOUNT_DISCARD, "," MNTOPT_DISCARD },
{ XFS_MOUNT_SMALL_INUMS, "," MNTOPT_32BITINODE },
{ 0, NULL }
};
static struct proc_xfs_info xfs_info_unset[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_COMPAT_IOSIZE, "," MNTOPT_LARGEIO },
{ XFS_MOUNT_BARRIER, "," MNTOPT_NOBARRIER },
{ XFS_MOUNT_SMALL_INUMS, "," MNTOPT_64BITINODE },
{ 0, NULL }
};
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
if (mp->m_flags & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
for (xfs_infop = xfs_info_unset; xfs_infop->flag; xfs_infop++) {
if (!(mp->m_flags & xfs_infop->flag))
seq_puts(m, xfs_infop->str);
}
if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
seq_printf(m, "," MNTOPT_ALLOCSIZE "=%dk",
(int)(1 << mp->m_writeio_log) >> 10);
if (mp->m_logbufs > 0)
seq_printf(m, "," MNTOPT_LOGBUFS "=%d", mp->m_logbufs);
if (mp->m_logbsize > 0)
seq_printf(m, "," MNTOPT_LOGBSIZE "=%dk", mp->m_logbsize >> 10);
if (mp->m_logname)
seq_printf(m, "," MNTOPT_LOGDEV "=%s", mp->m_logname);
if (mp->m_rtname)
seq_printf(m, "," MNTOPT_RTDEV "=%s", mp->m_rtname);
if (mp->m_dalign > 0)
seq_printf(m, "," MNTOPT_SUNIT "=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
if (mp->m_swidth > 0)
seq_printf(m, "," MNTOPT_SWIDTH "=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
seq_puts(m, "," MNTOPT_USRQUOTA);
else if (mp->m_qflags & XFS_UQUOTA_ACCT)
seq_puts(m, "," MNTOPT_UQUOTANOENF);
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
if (mp->m_qflags & XFS_PQUOTA_ACCT) {
if (mp->m_qflags & XFS_PQUOTA_ENFD)
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
seq_puts(m, "," MNTOPT_PRJQUOTA);
else
seq_puts(m, "," MNTOPT_PQUOTANOENF);
}
if (mp->m_qflags & XFS_GQUOTA_ACCT) {
if (mp->m_qflags & XFS_GQUOTA_ENFD)
xfs: xfs_showargs() reports group *and* project quotas enabled If you enable group or project quotas on an XFS file system, then the mount table presented through /proc/self/mounts erroneously shows that both options are in effect for the file system. The root of the problem is some bad logic in the xfs_showargs() function, which is used to format the file system type-specific options in effect for a file system. The problem originated in this GIT commit: Move platform specific mount option parse out of core XFS code Date: 11/22/07 Author: Dave Chinner SHA1 ID: a67d7c5f5d25d0b13a4dfb182697135b014fa478 For XFS quotas, project and group quota management are mutually exclusive--only one can be in effect at a time. There are two parts to managing quotas: aggregating usage information; and enforcing limits. It is possible to have a quota in effect (aggregating usage) but not enforced. These features are recorded on an XFS mount point using these flags: XFS_PQUOTA_ACCT - Project quotas are aggregated XFS_GQUOTA_ACCT - Group quotas are aggregated XFS_OQUOTA_ENFD - Project/group quotas are enforced The code in error is in fs/xfs/linux-2.6/xfs_super.c: if (mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_PRJQUOTA); else if (mp->m_qflags & XFS_PQUOTA_ACCT) seq_puts(m, "," MNTOPT_PQUOTANOENF); if (mp->m_qflags & (XFS_GQUOTA_ACCT|XFS_OQUOTA_ENFD)) seq_puts(m, "," MNTOPT_GRPQUOTA); else if (mp->m_qflags & XFS_GQUOTA_ACCT) seq_puts(m, "," MNTOPT_GQUOTANOENF); The problem is that XFS_OQUOTA_ENFD will be set in mp->m_qflags if either group or project quotas are enforced, and as a result both MNTOPT_PRJQUOTA and MNTOPT_GRPQUOTA will be shown as mount options. Signed-off-by: Alex Elder <aelder@sgi.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Felix Blyakher <felixb@sgi.com>
2009-09-03 06:02:24 +08:00
seq_puts(m, "," MNTOPT_GRPQUOTA);
else
seq_puts(m, "," MNTOPT_GQUOTANOENF);
}
if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
seq_puts(m, "," MNTOPT_NOQUOTA);
return 0;
}
__uint64_t
xfs_max_file_offset(
unsigned int blockshift)
{
unsigned int pagefactor = 1;
unsigned int bitshift = BITS_PER_LONG - 1;
/* Figure out maximum filesize, on Linux this can depend on
* the filesystem blocksize (on 32 bit platforms).
* __block_write_begin does this in an [unsigned] long...
* page->index << (PAGE_CACHE_SHIFT - bbits)
* So, for page sized blocks (4K on 32 bit platforms),
* this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
* (((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
* but for smaller blocksizes it is less (bbits = log2 bsize).
* Note1: get_block_t takes a long (implicit cast from above)
* Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
* can optionally convert the [unsigned] long from above into
* an [unsigned] long long.
*/
#if BITS_PER_LONG == 32
# if defined(CONFIG_LBDAF)
ASSERT(sizeof(sector_t) == 8);
pagefactor = PAGE_CACHE_SIZE;
bitshift = BITS_PER_LONG;
# else
pagefactor = PAGE_CACHE_SIZE >> (PAGE_CACHE_SHIFT - blockshift);
# endif
#endif
return (((__uint64_t)pagefactor) << bitshift) - 1;
}
xfs_agnumber_t
xfs_set_inode32(struct xfs_mount *mp)
{
xfs_agnumber_t index = 0;
xfs_agnumber_t maxagi = 0;
xfs_sb_t *sbp = &mp->m_sb;
xfs_agnumber_t max_metadata;
xfs_agino_t agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks -1, 0);
xfs_ino_t ino = XFS_AGINO_TO_INO(mp, sbp->sb_agcount -1, agino);
xfs_perag_t *pag;
/* Calculate how much should be reserved for inodes to meet
* the max inode percentage.
*/
if (mp->m_maxicount) {
__uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
icount += sbp->sb_agblocks - 1;
do_div(icount, sbp->sb_agblocks);
max_metadata = icount;
} else {
max_metadata = sbp->sb_agcount;
}
for (index = 0; index < sbp->sb_agcount; index++) {
ino = XFS_AGINO_TO_INO(mp, index, agino);
if (ino > XFS_MAXINUMBER_32) {
pag = xfs_perag_get(mp, index);
pag->pagi_inodeok = 0;
pag->pagf_metadata = 0;
xfs_perag_put(pag);
continue;
}
pag = xfs_perag_get(mp, index);
pag->pagi_inodeok = 1;
maxagi++;
if (index < max_metadata)
pag->pagf_metadata = 1;
xfs_perag_put(pag);
}
mp->m_flags |= (XFS_MOUNT_32BITINODES |
XFS_MOUNT_SMALL_INUMS);
return maxagi;
}
xfs_agnumber_t
xfs_set_inode64(struct xfs_mount *mp)
{
xfs_agnumber_t index = 0;
for (index = 0; index < mp->m_sb.sb_agcount; index++) {
struct xfs_perag *pag;
pag = xfs_perag_get(mp, index);
pag->pagi_inodeok = 1;
pag->pagf_metadata = 0;
xfs_perag_put(pag);
}
/* There is no need for lock protection on m_flags,
* the rw_semaphore of the VFS superblock is locked
* during mount/umount/remount operations, so this is
* enough to avoid concurency on the m_flags field
*/
mp->m_flags &= ~(XFS_MOUNT_32BITINODES |
XFS_MOUNT_SMALL_INUMS);
return index;
}
STATIC int
xfs_blkdev_get(
xfs_mount_t *mp,
const char *name,
struct block_device **bdevp)
{
int error = 0;
*bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
mp);
if (IS_ERR(*bdevp)) {
error = PTR_ERR(*bdevp);
xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error);
}
return -error;
}
STATIC void
xfs_blkdev_put(
struct block_device *bdev)
{
if (bdev)
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
void
xfs_blkdev_issue_flush(
xfs_buftarg_t *buftarg)
{
blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL);
}
STATIC void
xfs_close_devices(
struct xfs_mount *mp)
{
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
}
xfs_free_buftarg(mp, mp->m_ddev_targp);
}
/*
* The file system configurations are:
* (1) device (partition) with data and internal log
* (2) logical volume with data and log subvolumes.
* (3) logical volume with data, log, and realtime subvolumes.
*
* We only have to handle opening the log and realtime volumes here if
* they are present. The data subvolume has already been opened by
* get_sb_bdev() and is stored in sb->s_bdev.
*/
STATIC int
xfs_open_devices(
struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
struct block_device *logdev = NULL, *rtdev = NULL;
int error;
/*
* Open real time and log devices - order is important.
*/
if (mp->m_logname) {
error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
}
if (mp->m_rtname) {
error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev);
if (error)
goto out_close_logdev;
if (rtdev == ddev || rtdev == logdev) {
xfs_warn(mp,
"Cannot mount filesystem with identical rtdev and ddev/logdev.");
error = EINVAL;
goto out_close_rtdev;
}
}
/*
* Setup xfs_mount buffer target pointers
*/
error = ENOMEM;
mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, 0, mp->m_fsname);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev) {
mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, 1,
mp->m_fsname);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev && logdev != ddev) {
mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, 1,
mp->m_fsname);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
mp->m_logdev_targp = mp->m_ddev_targp;
}
return 0;
out_free_rtdev_targ:
if (mp->m_rtdev_targp)
xfs_free_buftarg(mp, mp->m_rtdev_targp);
out_free_ddev_targ:
xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
if (rtdev)
xfs_blkdev_put(rtdev);
out_close_logdev:
if (logdev && logdev != ddev)
xfs_blkdev_put(logdev);
out:
return error;
}
/*
* Setup xfs_mount buffer target pointers based on superblock
*/
STATIC int
xfs_setup_devices(
struct xfs_mount *mp)
{
int error;
error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize,
mp->m_sb.sb_sectsize);
if (error)
return error;
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
unsigned int log_sector_size = BBSIZE;
if (xfs_sb_version_hassector(&mp->m_sb))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
mp->m_sb.sb_blocksize,
log_sector_size);
if (error)
return error;
}
if (mp->m_rtdev_targp) {
error = xfs_setsize_buftarg(mp->m_rtdev_targp,
mp->m_sb.sb_blocksize,
mp->m_sb.sb_sectsize);
if (error)
return error;
}
return 0;
}
STATIC int
xfs_init_mount_workqueues(
struct xfs_mount *mp)
{
mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
WQ_MEM_RECLAIM, 0, mp->m_fsname);
if (!mp->m_data_workqueue)
goto out;
mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
WQ_MEM_RECLAIM, 0, mp->m_fsname);
if (!mp->m_unwritten_workqueue)
goto out_destroy_data_iodone_queue;
mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
WQ_MEM_RECLAIM, 0, mp->m_fsname);
if (!mp->m_cil_workqueue)
goto out_destroy_unwritten;
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
WQ_NON_REENTRANT, 0, mp->m_fsname);
if (!mp->m_reclaim_workqueue)
goto out_destroy_cil;
mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
WQ_NON_REENTRANT, 0, mp->m_fsname);
if (!mp->m_log_workqueue)
goto out_destroy_reclaim;
mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
WQ_NON_REENTRANT, 0, mp->m_fsname);
if (!mp->m_eofblocks_workqueue)
goto out_destroy_log;
return 0;
out_destroy_log:
destroy_workqueue(mp->m_log_workqueue);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_cil:
destroy_workqueue(mp->m_cil_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
out_destroy_data_iodone_queue:
destroy_workqueue(mp->m_data_workqueue);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_eofblocks_workqueue);
destroy_workqueue(mp->m_log_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_cil_workqueue);
destroy_workqueue(mp->m_data_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
}
xfs: xfs_sync_data is redundant. We don't do any data writeback from XFS any more - the VFS is completely responsible for that, including for freeze. We can replace the remaining caller with a VFS level function that achieves the same thing, but without conflicting with current writeback work. This means we can remove the flush_work and xfs_flush_inodes() - the VFS functionality completely replaces the internal flush queue for doing this writeback work in a separate context to avoid stack overruns. This does have one complication - it cannot be called with page locks held. Hence move the flushing of delalloc space when ENOSPC occurs back up into xfs_file_aio_buffered_write when we don't hold any locks that will stall writeback. Unfortunately, writeback_inodes_sb_if_idle() is not sufficient to trigger delalloc conversion fast enough to prevent spurious ENOSPC whent here are hundreds of writers, thousands of small files and GBs of free RAM. Hence we need to use sync_sb_inodes() to block callers while we wait for writeback like the previous xfs_flush_inodes implementation did. That means we have to hold the s_umount lock here, but because this call can nest inside i_mutex (the parent directory in the create case, held by the VFS), we have to use down_read_trylock() to avoid potential deadlocks. In practice, this trylock will succeed on almost every attempt as unmount/remount type operations are exceedingly rare. Note: we always need to pass a count of zero to generic_file_buffered_write() as the previously written byte count. We only do this by accident before this patch by the virtue of ret always being zero when there are no errors. Make this explicit rather than needing to specifically zero ret in the ENOSPC retry case. Signed-off-by: Dave Chinner <dchinner@redhat.com> Tested-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2012-10-08 18:56:04 +08:00
/*
* Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
* or a page lock. We use sync_inodes_sb() here to ensure we block while waiting
* for IO to complete so that we effectively throttle multiple callers to the
* rate at which IO is completing.
*/
void
xfs_flush_inodes(
struct xfs_mount *mp)
{
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}
/* Catch misguided souls that try to use this interface on XFS */
STATIC struct inode *
xfs_fs_alloc_inode(
struct super_block *sb)
{
BUG();
return NULL;
}
/*
* Now that the generic code is guaranteed not to be accessing
* the linux inode, we can reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
trace_xfs_destroy_inode(ip);
XFS_STATS_INC(vn_reclaim);
/* bad inode, get out here ASAP */
if (is_bad_inode(inode))
goto out_reclaim;
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
/*
* We should never get here with one of the reclaim flags already set.
*/
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
/*
* We always use background reclaim here because even if the
* inode is clean, it still may be under IO and hence we have
* to take the flush lock. The background reclaim path handles
* this more efficiently than we can here, so simply let background
* reclaim tear down all inodes.
*/
out_reclaim:
xfs_inode_set_reclaim_tag(ip);
}
/*
* Slab object creation initialisation for the XFS inode.
* This covers only the idempotent fields in the XFS inode;
* all other fields need to be initialised on allocation
* from the slab. This avoids the need to repeatedly initialise
* fields in the xfs inode that left in the initialise state
* when freeing the inode.
*/
STATIC void
xfs_fs_inode_init_once(
void *inode)
{
struct xfs_inode *ip = inode;
memset(ip, 0, sizeof(struct xfs_inode));
/* vfs inode */
inode_init_once(VFS_I(ip));
/* xfs inode */
atomic_set(&ip->i_pincount, 0);
spin_lock_init(&ip->i_flags_lock);
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
}
STATIC void
xfs_fs_evict_inode(
struct inode *inode)
{
xfs_inode_t *ip = XFS_I(inode);
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
trace_xfs_evict_inode(ip);
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
XFS_STATS_INC(vn_rele);
XFS_STATS_INC(vn_remove);
XFS_STATS_DEC(vn_active);
xfs_inactive(ip);
}
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
* xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
* racing with us, and it avoids needing to grab a spinlock here for every inode
* we drop the final reference on.
*/
STATIC int
xfs_fs_drop_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
return generic_drop_inode(inode) || (ip->i_flags & XFS_IDONTCACHE);
}
STATIC void
xfs_free_fsname(
struct xfs_mount *mp)
{
kfree(mp->m_fsname);
kfree(mp->m_rtname);
kfree(mp->m_logname);
}
STATIC void
xfs_fs_put_super(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
xfs_freesb(mp);
xfs_icsb_destroy_counters(mp);
xfs_destroy_mount_workqueues(mp);
xfs_close_devices(mp);
xfs_free_fsname(mp);
kfree(mp);
}
STATIC int
xfs_fs_sync_fs(
struct super_block *sb,
int wait)
{
struct xfs_mount *mp = XFS_M(sb);
/*
* Doing anything during the async pass would be counterproductive.
*/
if (!wait)
return 0;
xfs_log_force(mp, XFS_LOG_SYNC);
if (laptop_mode) {
/*
* The disk must be active because we're syncing.
* We schedule log work now (now that the disk is
* active) instead of later (when it might not be).
*/
flush_delayed_work(&mp->m_log->l_work);
}
return 0;
}
STATIC int
xfs_fs_statfs(
struct dentry *dentry,
struct kstatfs *statp)
{
struct xfs_mount *mp = XFS_M(dentry->d_sb);
xfs_sb_t *sbp = &mp->m_sb;
struct xfs_inode *ip = XFS_I(dentry->d_inode);
__uint64_t fakeinos, id;
xfs_extlen_t lsize;
__int64_t ffree;
statp->f_type = XFS_SB_MAGIC;
statp->f_namelen = MAXNAMELEN - 1;
id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
statp->f_fsid.val[0] = (u32)id;
statp->f_fsid.val[1] = (u32)(id >> 32);
xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
spin_lock(&mp->m_sb_lock);
statp->f_bsize = sbp->sb_blocksize;
lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
statp->f_blocks = sbp->sb_dblocks - lsize;
statp->f_bfree = statp->f_bavail =
sbp->sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
fakeinos = statp->f_bfree << sbp->sb_inopblog;
statp->f_files =
MIN(sbp->sb_icount + fakeinos, (__uint64_t)XFS_MAXINUMBER);
if (mp->m_maxicount)
statp->f_files = min_t(typeof(statp->f_files),
statp->f_files,
mp->m_maxicount);
/* make sure statp->f_ffree does not underflow */
ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
statp->f_ffree = max_t(__int64_t, ffree, 0);
spin_unlock(&mp->m_sb_lock);
if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
(XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
xfs_qm_statvfs(ip, statp);
return 0;
}
STATIC void
xfs_save_resvblks(struct xfs_mount *mp)
{
__uint64_t resblks = 0;
mp->m_resblks_save = mp->m_resblks;
xfs_reserve_blocks(mp, &resblks, NULL);
}
STATIC void
xfs_restore_resvblks(struct xfs_mount *mp)
{
__uint64_t resblks;
if (mp->m_resblks_save) {
resblks = mp->m_resblks_save;
mp->m_resblks_save = 0;
} else
resblks = xfs_default_resblks(mp);
xfs_reserve_blocks(mp, &resblks, NULL);
}
/*
* Trigger writeback of all the dirty metadata in the file system.
*
* This ensures that the metadata is written to their location on disk rather
* than just existing in transactions in the log. This means after a quiesce
* there is no log replay required to write the inodes to disk - this is the
* primary difference between a sync and a quiesce.
*
* Note: xfs_log_quiesce() stops background log work - the callers must ensure
* it is started again when appropriate.
*/
void
xfs_quiesce_attr(
struct xfs_mount *mp)
{
int error = 0;
/* wait for all modifications to complete */
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
/* force the log to unpin objects from the now complete transactions */
xfs_log_force(mp, XFS_LOG_SYNC);
/* reclaim inodes to do any IO before the freeze completes */
xfs_reclaim_inodes(mp, 0);
xfs_reclaim_inodes(mp, SYNC_WAIT);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
/*
* Just warn here till VFS can correctly support
* read-only remount without racing.
*/
WARN_ON(atomic_read(&mp->m_active_trans) != 0);
xfs_log_quiesce(mp);
}
STATIC int
xfs_fs_remount(
struct super_block *sb,
int *flags,
char *options)
{
struct xfs_mount *mp = XFS_M(sb);
substring_t args[MAX_OPT_ARGS];
char *p;
int error;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_barrier:
mp->m_flags |= XFS_MOUNT_BARRIER;
break;
case Opt_nobarrier:
mp->m_flags &= ~XFS_MOUNT_BARRIER;
break;
case Opt_inode64:
mp->m_maxagi = xfs_set_inode64(mp);
break;
case Opt_inode32:
mp->m_maxagi = xfs_set_inode32(mp);
break;
default:
/*
* Logically we would return an error here to prevent
* users from believing they might have changed
* mount options using remount which can't be changed.
*
* But unfortunately mount(8) adds all options from
* mtab and fstab to the mount arguments in some cases
* so we can't blindly reject options, but have to
* check for each specified option if it actually
* differs from the currently set option and only
* reject it if that's the case.
*
* Until that is implemented we return success for
* every remount request, and silently ignore all
* options that we can't actually change.
*/
#if 0
xfs_info(mp,
"mount option \"%s\" not supported for remount\n", p);
return -EINVAL;
#else
break;
#endif
}
}
/* ro -> rw */
if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) {
mp->m_flags &= ~XFS_MOUNT_RDONLY;
/*
* If this is the first remount to writeable state we
* might have some superblock changes to update.
*/
if (mp->m_update_flags) {
error = xfs_mount_log_sb(mp, mp->m_update_flags);
if (error) {
xfs_warn(mp, "failed to write sb changes");
return error;
}
mp->m_update_flags = 0;
}
/*
* Fill out the reserve pool if it is empty. Use the stashed
* value if it is non-zero, otherwise go with the default.
*/
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
}
/* rw -> ro */
if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
/*
* Before we sync the metadata, we need to free up the reserve
* block pool so that the used block count in the superblock on
* disk is correct at the end of the remount. Stash the current
* reserve pool size so that if we get remounted rw, we can
* return it to the same size.
*/
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
mp->m_flags |= XFS_MOUNT_RDONLY;
}
return 0;
}
/*
* Second stage of a freeze. The data is already frozen so we only
* need to take care of the metadata. Once that's done write a dummy
* record to dirty the log in case of a crash while frozen.
*/
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
STATIC int
xfs_fs_freeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
return -xfs_fs_log_dummy(mp);
}
STATIC int
xfs_fs_unfreeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
return 0;
}
STATIC int
xfs_fs_show_options(
struct seq_file *m,
struct dentry *root)
{
return -xfs_showargs(XFS_M(root->d_sb), m);
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock _has_ now been read in.
*/
STATIC int
xfs_finish_flags(
struct xfs_mount *mp)
{
int ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
/* Fail a mount where the logbuf is smaller than the log stripe */
if (xfs_sb_version_haslogv2(&mp->m_sb)) {
if (mp->m_logbsize <= 0 &&
mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
mp->m_logbsize = mp->m_sb.sb_logsunit;
} else if (mp->m_logbsize > 0 &&
mp->m_logbsize < mp->m_sb.sb_logsunit) {
xfs_warn(mp,
"logbuf size must be greater than or equal to log stripe size");
return XFS_ERROR(EINVAL);
}
} else {
/* Fail a mount if the logbuf is larger than 32K */
if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
xfs_warn(mp,
"logbuf size for version 1 logs must be 16K or 32K");
return XFS_ERROR(EINVAL);
}
}
/*
* V5 filesystems always use attr2 format for attributes.
*/
if (xfs_sb_version_hascrc(&mp->m_sb) &&
(mp->m_flags & XFS_MOUNT_NOATTR2)) {
xfs_warn(mp,
"Cannot mount a V5 filesystem as %s. %s is always enabled for V5 filesystems.",
MNTOPT_NOATTR2, MNTOPT_ATTR2);
return XFS_ERROR(EINVAL);
}
/*
* mkfs'ed attr2 will turn on attr2 mount unless explicitly
* told by noattr2 to turn it off
*/
if (xfs_sb_version_hasattr2(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_NOATTR2))
mp->m_flags |= XFS_MOUNT_ATTR2;
/*
* prohibit r/w mounts of read-only filesystems
*/
if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) {
xfs_warn(mp,
"cannot mount a read-only filesystem as read-write");
return XFS_ERROR(EROFS);
}
if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
(mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE)) &&
!xfs_sb_version_has_pquotino(&mp->m_sb)) {
xfs_warn(mp,
"Super block does not support project and group quota together");
return XFS_ERROR(EINVAL);
}
return 0;
}
STATIC int
xfs_fs_fill_super(
struct super_block *sb,
void *data,
int silent)
{
struct inode *root;
struct xfs_mount *mp = NULL;
int flags = 0, error = ENOMEM;
mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
if (!mp)
goto out;
spin_lock_init(&mp->m_sb_lock);
mutex_init(&mp->m_growlock);
atomic_set(&mp->m_active_trans, 0);
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
mp->m_super = sb;
sb->s_fs_info = mp;
error = xfs_parseargs(mp, (char *)data);
if (error)
goto out_free_fsname;
sb_min_blocksize(sb, BBSIZE);
sb->s_xattr = xfs_xattr_handlers;
sb->s_export_op = &xfs_export_operations;
#ifdef CONFIG_XFS_QUOTA
sb->s_qcop = &xfs_quotactl_operations;
#endif
sb->s_op = &xfs_super_operations;
if (silent)
flags |= XFS_MFSI_QUIET;
error = xfs_open_devices(mp);
if (error)
goto out_free_fsname;
error = xfs_init_mount_workqueues(mp);
if (error)
goto out_close_devices;
error = xfs_icsb_init_counters(mp);
if (error)
goto out_destroy_workqueues;
error = xfs_readsb(mp, flags);
if (error)
goto out_destroy_counters;
error = xfs_finish_flags(mp);
if (error)
goto out_free_sb;
error = xfs_setup_devices(mp);
if (error)
goto out_free_sb;
error = xfs_filestream_mount(mp);
if (error)
goto out_free_sb;
/*
* we must configure the block size in the superblock before we run the
* full mount process as the mount process can lookup and cache inodes.
*/
sb->s_magic = XFS_SB_MAGIC;
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
set_posix_acl_flag(sb);
/* version 5 superblocks support inode version counters. */
if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
sb->s_flags |= MS_I_VERSION;
error = xfs_mountfs(mp);
if (error)
goto out_filestream_unmount;
root = igrab(VFS_I(mp->m_rootip));
if (!root) {
error = ENOENT;
goto out_unmount;
}
if (is_bad_inode(root)) {
error = EINVAL;
goto out_unmount;
}
sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = ENOMEM;
goto out_unmount;
}
return 0;
out_filestream_unmount:
xfs_filestream_unmount(mp);
out_free_sb:
xfs_freesb(mp);
out_destroy_counters:
xfs_icsb_destroy_counters(mp);
out_destroy_workqueues:
xfs_destroy_mount_workqueues(mp);
out_close_devices:
xfs_close_devices(mp);
out_free_fsname:
xfs_free_fsname(mp);
kfree(mp);
out:
return -error;
out_unmount:
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
goto out_free_sb;
}
STATIC struct dentry *
xfs_fs_mount(
struct file_system_type *fs_type,
int flags,
const char *dev_name,
void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
}
static int
xfs_fs_nr_cached_objects(
struct super_block *sb)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
static void
xfs_fs_free_cached_objects(
struct super_block *sb,
int nr_to_scan)
{
xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
}
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
.evict_inode = xfs_fs_evict_inode,
.drop_inode = xfs_fs_drop_inode,
.put_super = xfs_fs_put_super,
.sync_fs = xfs_fs_sync_fs,
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
.freeze_fs = xfs_fs_freeze,
.unfreeze_fs = xfs_fs_unfreeze,
.statfs = xfs_fs_statfs,
.remount_fs = xfs_fs_remount,
.show_options = xfs_fs_show_options,
.nr_cached_objects = xfs_fs_nr_cached_objects,
.free_cached_objects = xfs_fs_free_cached_objects,
};
static struct file_system_type xfs_fs_type = {
.owner = THIS_MODULE,
.name = "xfs",
.mount = xfs_fs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
{
xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
if (!xfs_ioend_zone)
goto out;
xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
xfs_ioend_zone);
if (!xfs_ioend_pool)
goto out_destroy_ioend_zone;
xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
"xfs_log_ticket");
if (!xfs_log_ticket_zone)
goto out_destroy_ioend_pool;
xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
"xfs_bmap_free_item");
if (!xfs_bmap_free_item_zone)
goto out_destroy_log_ticket_zone;
xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
"xfs_btree_cur");
if (!xfs_btree_cur_zone)
goto out_destroy_bmap_free_item_zone;
xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
"xfs_da_state");
if (!xfs_da_state_zone)
goto out_destroy_btree_cur_zone;
xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
if (!xfs_ifork_zone)
goto out_destroy_da_state_zone;
xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
if (!xfs_trans_zone)
goto out_destroy_ifork_zone;
xfs_log_item_desc_zone =
kmem_zone_init(sizeof(struct xfs_log_item_desc),
"xfs_log_item_desc");
if (!xfs_log_item_desc_zone)
goto out_destroy_trans_zone;
/*
* The size of the zone allocated buf log item is the maximum
* size possible under XFS. This wastes a little bit of memory,
* but it is much faster.
*/
xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
"xfs_buf_item");
if (!xfs_buf_item_zone)
goto out_destroy_log_item_desc_zone;
xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
((XFS_EFD_MAX_FAST_EXTENTS - 1) *
sizeof(xfs_extent_t))), "xfs_efd_item");
if (!xfs_efd_zone)
goto out_destroy_buf_item_zone;
xfs_efi_zone = kmem_zone_init((sizeof(xfs_efi_log_item_t) +
((XFS_EFI_MAX_FAST_EXTENTS - 1) *
sizeof(xfs_extent_t))), "xfs_efi_item");
if (!xfs_efi_zone)
goto out_destroy_efd_zone;
xfs_inode_zone =
kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD,
xfs_fs_inode_init_once);
if (!xfs_inode_zone)
goto out_destroy_efi_zone;
xfs_ili_zone =
kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
KM_ZONE_SPREAD, NULL);
if (!xfs_ili_zone)
goto out_destroy_inode_zone;
xfs_icreate_zone = kmem_zone_init(sizeof(struct xfs_icreate_item),
"xfs_icr");
if (!xfs_icreate_zone)
goto out_destroy_ili_zone;
return 0;
out_destroy_ili_zone:
kmem_zone_destroy(xfs_ili_zone);
out_destroy_inode_zone:
kmem_zone_destroy(xfs_inode_zone);
out_destroy_efi_zone:
kmem_zone_destroy(xfs_efi_zone);
out_destroy_efd_zone:
kmem_zone_destroy(xfs_efd_zone);
out_destroy_buf_item_zone:
kmem_zone_destroy(xfs_buf_item_zone);
out_destroy_log_item_desc_zone:
kmem_zone_destroy(xfs_log_item_desc_zone);
out_destroy_trans_zone:
kmem_zone_destroy(xfs_trans_zone);
out_destroy_ifork_zone:
kmem_zone_destroy(xfs_ifork_zone);
out_destroy_da_state_zone:
kmem_zone_destroy(xfs_da_state_zone);
out_destroy_btree_cur_zone:
kmem_zone_destroy(xfs_btree_cur_zone);
out_destroy_bmap_free_item_zone:
kmem_zone_destroy(xfs_bmap_free_item_zone);
out_destroy_log_ticket_zone:
kmem_zone_destroy(xfs_log_ticket_zone);
out_destroy_ioend_pool:
mempool_destroy(xfs_ioend_pool);
out_destroy_ioend_zone:
kmem_zone_destroy(xfs_ioend_zone);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_zones(void)
{
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
kmem_zone_destroy(xfs_icreate_zone);
kmem_zone_destroy(xfs_ili_zone);
kmem_zone_destroy(xfs_inode_zone);
kmem_zone_destroy(xfs_efi_zone);
kmem_zone_destroy(xfs_efd_zone);
kmem_zone_destroy(xfs_buf_item_zone);
kmem_zone_destroy(xfs_log_item_desc_zone);
kmem_zone_destroy(xfs_trans_zone);
kmem_zone_destroy(xfs_ifork_zone);
kmem_zone_destroy(xfs_da_state_zone);
kmem_zone_destroy(xfs_btree_cur_zone);
kmem_zone_destroy(xfs_bmap_free_item_zone);
kmem_zone_destroy(xfs_log_ticket_zone);
mempool_destroy(xfs_ioend_pool);
kmem_zone_destroy(xfs_ioend_zone);
}
STATIC int __init
xfs_init_workqueues(void)
{
/*
* The allocation workqueue can be used in memory reclaim situations
* (writepage path), and parallelism is only limited by the number of
* AGs in all the filesystems mounted. Hence use the default large
* max_active value for this workqueue.
*/
xfs_alloc_wq = alloc_workqueue("xfsalloc", WQ_MEM_RECLAIM, 0);
if (!xfs_alloc_wq)
return -ENOMEM;
return 0;
}
STATIC void
xfs_destroy_workqueues(void)
{
destroy_workqueue(xfs_alloc_wq);
}
STATIC int __init
init_xfs_fs(void)
{
int error;
printk(KERN_INFO XFS_VERSION_STRING " with "
XFS_BUILD_OPTIONS " enabled\n");
xfs_dir_startup();
error = xfs_init_zones();
if (error)
goto out;
error = xfs_init_workqueues();
if (error)
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 07:14:59 +08:00
goto out_destroy_zones;
error = xfs_mru_cache_init();
if (error)
goto out_destroy_wq;
error = xfs_filestream_init();
if (error)
goto out_mru_cache_uninit;
error = xfs_buf_init();
if (error)
goto out_filestream_uninit;
error = xfs_init_procfs();
if (error)
goto out_buf_terminate;
error = xfs_sysctl_register();
if (error)
goto out_cleanup_procfs;
error = xfs_qm_init();
if (error)
goto out_sysctl_unregister;
error = register_filesystem(&xfs_fs_type);
if (error)
goto out_qm_exit;
return 0;
out_qm_exit:
xfs_qm_exit();
out_sysctl_unregister:
xfs_sysctl_unregister();
out_cleanup_procfs:
xfs_cleanup_procfs();
out_buf_terminate:
xfs_buf_terminate();
out_filestream_uninit:
xfs_filestream_uninit();
out_mru_cache_uninit:
xfs_mru_cache_uninit();
out_destroy_wq:
xfs_destroy_workqueues();
out_destroy_zones:
xfs_destroy_zones();
out:
return error;
}
STATIC void __exit
exit_xfs_fs(void)
{
xfs_qm_exit();
unregister_filesystem(&xfs_fs_type);
xfs_sysctl_unregister();
xfs_cleanup_procfs();
xfs_buf_terminate();
xfs_filestream_uninit();
xfs_mru_cache_uninit();
xfs_destroy_workqueues();
xfs_destroy_zones();
}
module_init(init_xfs_fs);
module_exit(exit_xfs_fs);
MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled");
MODULE_LICENSE("GPL");