summaryrefslogtreecommitdiffstats
path: root/fs/xfs/linux-2.6
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/linux-2.6')
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_cred.h10
-rw-r--r--fs/xfs/linux-2.6/xfs_globals.c8
-rw-r--r--fs/xfs/linux-2.6/xfs_globals.h1
-rw-r--r--fs/xfs/linux-2.6/xfs_ioctl.c9
-rw-r--r--fs/xfs/linux-2.6/xfs_iops.c25
-rw-r--r--fs/xfs/linux-2.6/xfs_linux.h2
-rw-r--r--fs/xfs/linux-2.6/xfs_stats.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_stats.h65
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c840
-rw-r--r--fs/xfs/linux-2.6/xfs_super.h3
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c763
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.h55
-rw-r--r--fs/xfs/linux-2.6/xfs_sysctl.c11
-rw-r--r--fs/xfs/linux-2.6/xfs_sysctl.h3
-rw-r--r--fs/xfs/linux-2.6/xfs_vfs.h31
-rw-r--r--fs/xfs/linux-2.6/xfs_vnode.c15
-rw-r--r--fs/xfs/linux-2.6/xfs_vnode.h5
18 files changed, 1205 insertions, 647 deletions
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index a44d68eb50b..8fbc97df360 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -191,7 +191,7 @@ xfs_setfilesize(
ip->i_d.di_size = isize;
ip->i_update_core = 1;
ip->i_update_size = 1;
- mark_inode_dirty_sync(ioend->io_inode);
+ xfs_mark_inode_dirty_sync(ip);
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/linux-2.6/xfs_cred.h b/fs/xfs/linux-2.6/xfs_cred.h
index 652721ce0ea..e279d00779f 100644
--- a/fs/xfs/linux-2.6/xfs_cred.h
+++ b/fs/xfs/linux-2.6/xfs_cred.h
@@ -24,15 +24,7 @@
* Credentials
*/
typedef struct cred {
- /* EMPTY */
+ /* EMPTY */
} cred_t;
-extern struct cred *sys_cred;
-
-/* this is a hack.. (assumes sys_cred is the only cred_t in the system) */
-static inline int capable_cred(cred_t *cr, int cid)
-{
- return (cr == sys_cred) ? 1 : capable(cid);
-}
-
#endif /* __XFS_CRED_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/linux-2.6/xfs_globals.c
index ef90e64641e..2ae8b1ccb02 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/fs/xfs/linux-2.6/xfs_globals.c
@@ -26,7 +26,6 @@
*/
xfs_param_t xfs_params = {
/* MIN DFLT MAX */
- .restrict_chown = { 0, 1, 1 },
.sgid_inherit = { 0, 0, 1 },
.symlink_mode = { 0, 0, 1 },
.panic_mask = { 0, 0, 255 },
@@ -43,10 +42,3 @@ xfs_param_t xfs_params = {
.inherit_nodfrg = { 0, 1, 1 },
.fstrm_timer = { 1, 30*100, 3600*100},
};
-
-/*
- * Global system credential structure.
- */
-static cred_t sys_cred_val;
-cred_t *sys_cred = &sys_cred_val;
-
diff --git a/fs/xfs/linux-2.6/xfs_globals.h b/fs/xfs/linux-2.6/xfs_globals.h
index 2770b0085ee..69f71caf061 100644
--- a/fs/xfs/linux-2.6/xfs_globals.h
+++ b/fs/xfs/linux-2.6/xfs_globals.h
@@ -19,6 +19,5 @@
#define __XFS_GLOBALS_H__
extern uint64_t xfs_panic_mask; /* set to cause more panics */
-extern struct cred *sys_cred;
#endif /* __XFS_GLOBALS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index d3438c72dca..f1bd6c36e6f 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -691,8 +691,7 @@ xfs_ioc_space(
if (ioflags & IO_INVIS)
attr_flags |= XFS_ATTR_DMI;
- error = xfs_change_file_space(ip, cmd, &bf, filp->f_pos,
- NULL, attr_flags);
+ error = xfs_change_file_space(ip, cmd, &bf, filp->f_pos, attr_flags);
return -error;
}
@@ -1007,7 +1006,7 @@ xfs_ioctl_setattr(
* to the file owner ID, except in cases where the
* CAP_FSETID capability is applicable.
*/
- if (current->fsuid != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
+ if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
@@ -1104,10 +1103,6 @@ xfs_ioctl_setattr(
/*
* Change file ownership. Must be the owner or privileged.
- * If the system was configured with the "restricted_chown"
- * option, the owner is not permitted to give away the file,
- * and can change the group id only to a group of which he
- * or she is a member.
*/
if (mask & FSX_PROJID) {
/*
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 095d271f343..f78bc221576 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -64,14 +64,14 @@ xfs_synchronize_atime(
{
struct inode *inode = VFS_I(ip);
- if (inode) {
+ if (!(inode->i_state & I_CLEAR)) {
ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
}
}
/*
- * If the linux inode exists, mark it dirty.
+ * If the linux inode is valid, mark it dirty.
* Used when commiting a dirty inode into a transaction so that
* the inode will get written back by the linux code
*/
@@ -81,7 +81,7 @@ xfs_mark_inode_dirty_sync(
{
struct inode *inode = VFS_I(ip);
- if (inode)
+ if (!(inode->i_state & (I_WILL_FREE|I_FREEING|I_CLEAR)))
mark_inode_dirty_sync(inode);
}
@@ -128,7 +128,7 @@ xfs_ichgtime(
if (sync_it) {
SYNCHRONIZE();
ip->i_update_core = 1;
- mark_inode_dirty_sync(inode);
+ xfs_mark_inode_dirty_sync(ip);
}
}
@@ -601,7 +601,7 @@ xfs_vn_setattr(
struct dentry *dentry,
struct iattr *iattr)
{
- return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0, NULL);
+ return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0);
}
/*
@@ -642,7 +642,7 @@ xfs_vn_fallocate(
xfs_ilock(ip, XFS_IOLOCK_EXCL);
error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
- 0, NULL, XFS_ATTR_NOLOCK);
+ 0, XFS_ATTR_NOLOCK);
if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode))
new_size = offset + len;
@@ -653,7 +653,7 @@ xfs_vn_fallocate(
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
- error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK, NULL);
+ error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
@@ -766,12 +766,21 @@ xfs_diflags_to_iflags(
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
+ *
+ * We are always called with an uninitialised linux inode here.
+ * We need to initialise the necessary fields and take a reference
+ * on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
- struct inode *inode = ip->i_vnode;
+ struct inode *inode = &ip->i_vnode;
+
+ inode->i_ino = ip->i_ino;
+ inode->i_state = I_NEW|I_LOCK;
+ inode_add_to_lists(ip->i_mount->m_super, inode);
+ ASSERT(atomic_read(&inode->i_count) == 1);
inode->i_mode = ip->i_d.di_mode;
inode->i_nlink = ip->i_d.di_nlink;
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index cc0f7b3a979..77d6ddcaf54 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -77,6 +77,7 @@
#include <linux/spinlock.h>
#include <linux/random.h>
#include <linux/ctype.h>
+#include <linux/writeback.h>
#include <asm/page.h>
#include <asm/div64.h>
@@ -107,7 +108,6 @@
#undef HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */
#endif
-#define restricted_chown xfs_params.restrict_chown.val
#define irix_sgid_inherit xfs_params.sgid_inherit.val
#define irix_symlink_mode xfs_params.symlink_mode.val
#define xfs_panic_mask xfs_params.panic_mask.val
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/linux-2.6/xfs_stats.c
index 3d5b67c075c..64f4ec90b8b 100644
--- a/fs/xfs/linux-2.6/xfs_stats.c
+++ b/fs/xfs/linux-2.6/xfs_stats.c
@@ -53,6 +53,10 @@ xfs_read_xfsstats(
{ "icluster", XFSSTAT_END_INODE_CLUSTER },
{ "vnodes", XFSSTAT_END_VNODE_OPS },
{ "buf", XFSSTAT_END_BUF },
+ { "abtb2", XFSSTAT_END_ABTB_V2 },
+ { "abtc2", XFSSTAT_END_ABTC_V2 },
+ { "bmbt2", XFSSTAT_END_BMBT_V2 },
+ { "ibt2", XFSSTAT_END_IBT_V2 },
};
/* Loop over all stats groups */
diff --git a/fs/xfs/linux-2.6/xfs_stats.h b/fs/xfs/linux-2.6/xfs_stats.h
index e83820febc9..736854b1ca1 100644
--- a/fs/xfs/linux-2.6/xfs_stats.h
+++ b/fs/xfs/linux-2.6/xfs_stats.h
@@ -118,6 +118,71 @@ struct xfsstats {
__uint32_t xb_page_retries;
__uint32_t xb_page_found;
__uint32_t xb_get_read;
+/* Version 2 btree counters */
+#define XFSSTAT_END_ABTB_V2 (XFSSTAT_END_BUF+15)
+ __uint32_t xs_abtb_2_lookup;
+ __uint32_t xs_abtb_2_compare;
+ __uint32_t xs_abtb_2_insrec;
+ __uint32_t xs_abtb_2_delrec;
+ __uint32_t xs_abtb_2_newroot;
+ __uint32_t xs_abtb_2_killroot;
+ __uint32_t xs_abtb_2_increment;
+ __uint32_t xs_abtb_2_decrement;
+ __uint32_t xs_abtb_2_lshift;
+ __uint32_t xs_abtb_2_rshift;
+ __uint32_t xs_abtb_2_split;
+ __uint32_t xs_abtb_2_join;
+ __uint32_t xs_abtb_2_alloc;
+ __uint32_t xs_abtb_2_free;
+ __uint32_t xs_abtb_2_moves;
+#define XFSSTAT_END_ABTC_V2 (XFSSTAT_END_ABTB_V2+15)
+ __uint32_t xs_abtc_2_lookup;
+ __uint32_t xs_abtc_2_compare;
+ __uint32_t xs_abtc_2_insrec;
+ __uint32_t xs_abtc_2_delrec;
+ __uint32_t xs_abtc_2_newroot;
+ __uint32_t xs_abtc_2_killroot;
+ __uint32_t xs_abtc_2_increment;
+ __uint32_t xs_abtc_2_decrement;
+ __uint32_t xs_abtc_2_lshift;
+ __uint32_t xs_abtc_2_rshift;
+ __uint32_t xs_abtc_2_split;
+ __uint32_t xs_abtc_2_join;
+ __uint32_t xs_abtc_2_alloc;
+ __uint32_t xs_abtc_2_free;
+ __uint32_t xs_abtc_2_moves;
+#define XFSSTAT_END_BMBT_V2 (XFSSTAT_END_ABTC_V2+15)
+ __uint32_t xs_bmbt_2_lookup;
+ __uint32_t xs_bmbt_2_compare;
+ __uint32_t xs_bmbt_2_insrec;
+ __uint32_t xs_bmbt_2_delrec;
+ __uint32_t xs_bmbt_2_newroot;
+ __uint32_t xs_bmbt_2_killroot;
+ __uint32_t xs_bmbt_2_increment;
+ __uint32_t xs_bmbt_2_decrement;
+ __uint32_t xs_bmbt_2_lshift;
+ __uint32_t xs_bmbt_2_rshift;
+ __uint32_t xs_bmbt_2_split;
+ __uint32_t xs_bmbt_2_join;
+ __uint32_t xs_bmbt_2_alloc;
+ __uint32_t xs_bmbt_2_free;
+ __uint32_t xs_bmbt_2_moves;
+#define XFSSTAT_END_IBT_V2 (XFSSTAT_END_BMBT_V2+15)
+ __uint32_t xs_ibt_2_lookup;
+ __uint32_t xs_ibt_2_compare;
+ __uint32_t xs_ibt_2_insrec;
+ __uint32_t xs_ibt_2_delrec;
+ __uint32_t xs_ibt_2_newroot;
+ __uint32_t xs_ibt_2_killroot;
+ __uint32_t xs_ibt_2_increment;
+ __uint32_t xs_ibt_2_decrement;
+ __uint32_t xs_ibt_2_lshift;
+ __uint32_t xs_ibt_2_rshift;
+ __uint32_t xs_ibt_2_split;
+ __uint32_t xs_ibt_2_join;
+ __uint32_t xs_ibt_2_alloc;
+ __uint32_t xs_ibt_2_free;
+ __uint32_t xs_ibt_2_moves;
/* Extra precision counters */
__uint64_t xs_xstrat_bytes;
__uint64_t xs_write_bytes;
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 37ebe36056e..c3d004bc462 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_bit.h"
#include "xfs_log.h"
-#include "xfs_clnt.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
@@ -36,6 +35,7 @@
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
+#include "xfs_btree_trace.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
@@ -58,6 +58,7 @@
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
#include "xfs_inode_item.h"
+#include "xfs_sync.h"
#include <linux/namei.h>
#include <linux/init.h>
@@ -70,36 +71,9 @@
static struct quotactl_ops xfs_quotactl_operations;
static struct super_operations xfs_super_operations;
-static kmem_zone_t *xfs_vnode_zone;
static kmem_zone_t *xfs_ioend_zone;
mempool_t *xfs_ioend_pool;
-STATIC struct xfs_mount_args *
-xfs_args_allocate(
- struct super_block *sb,
- int silent)
-{
- struct xfs_mount_args *args;
-
- args = kzalloc(sizeof(struct xfs_mount_args), GFP_KERNEL);
- if (!args)
- return NULL;
-
- args->logbufs = args->logbufsize = -1;
- strncpy(args->fsname, sb->s_id, MAXNAMELEN);
-
- /* Copy the already-parsed mount(2) flags we're interested in */
- if (sb->s_flags & MS_DIRSYNC)
- args->flags |= XFSMNT_DIRSYNC;
- if (sb->s_flags & MS_SYNCHRONOUS)
- args->flags |= XFSMNT_WSYNC;
- if (silent)
- args->flags |= XFSMNT_QUIET;
- args->flags |= XFSMNT_32BITINODES;
-
- return args;
-}
-
#define MNTOPT_LOGBUFS "logbufs" /* number of XFS log buffers */
#define MNTOPT_LOGBSIZE "logbsize" /* size of XFS log buffers */
#define MNTOPT_LOGDEV "logdev" /* log device */
@@ -188,26 +162,54 @@ suffix_strtoul(char *s, char **endp, unsigned int base)
return simple_strtoul((const char *)s, endp, base) << shift_left_factor;
}
+/*
+ * 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 xfs_mount_args *args,
- int update)
+ char **mtpt)
{
+ struct super_block *sb = mp->m_super;
char *this_char, *value, *eov;
- int dsunit, dswidth, vol_dsunit, vol_dswidth;
- int iosize;
+ int dsunit = 0;
+ int dswidth = 0;
+ int iosize = 0;
int dmapi_implies_ikeep = 1;
+ uchar_t iosizelog = 0;
- args->flags |= XFSMNT_BARRIER;
- args->flags2 |= XFSMNT2_COMPAT_IOSIZE;
+ /*
+ * 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;
+ mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+
+ /*
+ * These can be overridden by the mount option parsing.
+ */
+ mp->m_logbufs = -1;
+ mp->m_logbsize = -1;
if (!options)
goto done;
- iosize = dsunit = dswidth = vol_dsunit = vol_dswidth = 0;
-
while ((this_char = strsep(&options, ",")) != NULL) {
if (!*this_char)
continue;
@@ -221,7 +223,7 @@ xfs_parseargs(
this_char);
return EINVAL;
}
- args->logbufs = simple_strtoul(value, &eov, 10);
+ mp->m_logbufs = simple_strtoul(value, &eov, 10);
} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -229,7 +231,7 @@ xfs_parseargs(
this_char);
return EINVAL;
}
- args->logbufsize = suffix_strtoul(value, &eov, 10);
+ mp->m_logbsize = suffix_strtoul(value, &eov, 10);
} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -237,7 +239,9 @@ xfs_parseargs(
this_char);
return EINVAL;
}
- strncpy(args->logname, value, MAXNAMELEN);
+ mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+ if (!mp->m_logname)
+ return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_MTPT)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -245,7 +249,9 @@ xfs_parseargs(
this_char);
return EINVAL;
}
- strncpy(args->mtpt, value, MAXNAMELEN);
+ *mtpt = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+ if (!*mtpt)
+ return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -253,7 +259,9 @@ xfs_parseargs(
this_char);
return EINVAL;
}
- strncpy(args->rtname, value, MAXNAMELEN);
+ mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+ if (!mp->m_rtname)
+ return ENOMEM;
} else if (!strcmp(this_char, MNTOPT_BIOSIZE)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -262,8 +270,7 @@ xfs_parseargs(
return EINVAL;
}
iosize = simple_strtoul(value, &eov, 10);
- args->flags |= XFSMNT_IOSIZE;
- args->iosizelog = (uint8_t) iosize;
+ iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -272,8 +279,7 @@ xfs_parseargs(
return EINVAL;
}
iosize = suffix_strtoul(value, &eov, 10);
- args->flags |= XFSMNT_IOSIZE;
- args->iosizelog = ffs(iosize) - 1;
+ iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_GRPID) ||
!strcmp(this_char, MNTOPT_BSDGROUPS)) {
mp->m_flags |= XFS_MOUNT_GRPID;
@@ -281,23 +287,25 @@ xfs_parseargs(
!strcmp(this_char, MNTOPT_SYSVGROUPS)) {
mp->m_flags &= ~XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
- args->flags |= XFSMNT_WSYNC;
+ mp->m_flags |= XFS_MOUNT_WSYNC;
} else if (!strcmp(this_char, MNTOPT_OSYNCISOSYNC)) {
- args->flags |= XFSMNT_OSYNCISOSYNC;
+ mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
- args->flags |= XFSMNT_NORECOVERY;
+ mp->m_flags |= XFS_MOUNT_NORECOVERY;
} else if (!strcmp(this_char, MNTOPT_INO64)) {
- args->flags |= XFSMNT_INO64;
-#if !XFS_BIG_INUMS
+#if XFS_BIG_INUMS
+ mp->m_flags |= XFS_MOUNT_INO64;
+ mp->m_inoadd = XFS_INO64_OFFSET;
+#else
cmn_err(CE_WARN,
"XFS: %s option not allowed on this system",
this_char);
return EINVAL;
#endif
} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
- args->flags |= XFSMNT_NOALIGN;
+ mp->m_flags |= XFS_MOUNT_NOALIGN;
} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
- args->flags |= XFSMNT_SWALLOC;
+ mp->m_flags |= XFS_MOUNT_SWALLOC;
} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
if (!value || !*value) {
cmn_err(CE_WARN,
@@ -315,7 +323,7 @@ xfs_parseargs(
}
dswidth = simple_strtoul(value, &eov, 10);
} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
- args->flags &= ~XFSMNT_32BITINODES;
+ mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
#if !XFS_BIG_INUMS
cmn_err(CE_WARN,
"XFS: %s option not allowed on this system",
@@ -323,56 +331,61 @@ xfs_parseargs(
return EINVAL;
#endif
} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
- args->flags |= XFSMNT_NOUUID;
+ mp->m_flags |= XFS_MOUNT_NOUUID;
} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
- args->flags |= XFSMNT_BARRIER;
+ mp->m_flags |= XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
- args->flags &= ~XFSMNT_BARRIER;
+ mp->m_flags &= ~XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
- args->flags |= XFSMNT_IKEEP;
+ mp->m_flags |= XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
dmapi_implies_ikeep = 0;
- args->flags &= ~XFSMNT_IKEEP;
+ mp->m_flags &= ~XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
- args->flags2 &= ~XFSMNT2_COMPAT_IOSIZE;
+ mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
- args->flags2 |= XFSMNT2_COMPAT_IOSIZE;
+ mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
- args->flags |= XFSMNT_ATTR2;
+ mp->m_flags |= XFS_MOUNT_ATTR2;
} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
- args->flags &= ~XFSMNT_ATTR2;
- args->flags |= XFSMNT_NOATTR2;
+ mp->m_flags &= ~XFS_MOUNT_ATTR2;
+ mp->m_flags |= XFS_MOUNT_NOATTR2;
} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
- args->flags2 |= XFSMNT2_FILESTREAMS;
+ mp->m_flags |= XFS_MOUNT_FILESTREAMS;
} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
- args->flags &= ~(XFSMNT_UQUOTAENF|XFSMNT_UQUOTA);
- args->flags &= ~(XFSMNT_GQUOTAENF|XFSMNT_GQUOTA);
+ mp->m_qflags &= ~(XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+ XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+ XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+ XFS_UQUOTA_ENFD | XFS_OQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
!strcmp(this_char, MNTOPT_UQUOTA) ||
!strcmp(this_char, MNTOPT_USRQUOTA)) {
- args->flags |= XFSMNT_UQUOTA | XFSMNT_UQUOTAENF;
+ mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+ XFS_UQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
!strcmp(this_char, MNTOPT_UQUOTANOENF)) {
- args->flags |= XFSMNT_UQUOTA;
- args->flags &= ~XFSMNT_UQUOTAENF;
+ 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)) {
- args->flags |= XFSMNT_PQUOTA | XFSMNT_PQUOTAENF;
+ mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+ XFS_OQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
- args->flags |= XFSMNT_PQUOTA;
- args->flags &= ~XFSMNT_PQUOTAENF;
+ mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+ mp->m_qflags &= ~XFS_OQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
!strcmp(this_char, MNTOPT_GRPQUOTA)) {
- args->flags |= XFSMNT_GQUOTA | XFSMNT_GQUOTAENF;
+ mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+ XFS_OQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
- args->flags |= XFSMNT_GQUOTA;
- args->flags &= ~XFSMNT_GQUOTAENF;
+ mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+ mp->m_qflags &= ~XFS_OQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_DMAPI)) {
- args->flags |= XFSMNT_DMAPI;
+ mp->m_flags |= XFS_MOUNT_DMAPI;
} else if (!strcmp(this_char, MNTOPT_XDSM)) {
- args->flags |= XFSMNT_DMAPI;
+ mp->m_flags |= XFS_MOUNT_DMAPI;
} else if (!strcmp(this_char, MNTOPT_DMI)) {
- args->flags |= XFSMNT_DMAPI;
+ mp->m_flags |= XFS_MOUNT_DMAPI;
} else if (!strcmp(this_char, "ihashsize")) {
cmn_err(CE_WARN,
"XFS: ihashsize no longer used, option is deprecated.");
@@ -390,27 +403,29 @@ xfs_parseargs(
}
}
- if (args->flags & XFSMNT_NORECOVERY) {
- if ((mp->m_flags & XFS_MOUNT_RDONLY) == 0) {
- cmn_err(CE_WARN,
- "XFS: no-recovery mounts must be read-only.");
- return EINVAL;
- }
+ /*
+ * no recovery flag requires a read-only mount
+ */
+ if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
+ !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+ cmn_err(CE_WARN, "XFS: no-recovery mounts must be read-only.");
+ return EINVAL;
}
- if ((args->flags & XFSMNT_NOALIGN) && (dsunit || dswidth)) {
+ if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
cmn_err(CE_WARN,
"XFS: sunit and swidth options incompatible with the noalign option");
return EINVAL;
}
- if ((args->flags & XFSMNT_GQUOTA) && (args->flags & XFSMNT_PQUOTA)) {
+ if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
+ (mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE))) {
cmn_err(CE_WARN,
"XFS: cannot mount with both project and group quota");
return EINVAL;
}
- if ((args->flags & XFSMNT_DMAPI) && *args->mtpt == '\0') {
+ if ((mp->m_flags & XFS_MOUNT_DMAPI) && (!*mtpt || *mtpt[0] == '\0')) {
printk("XFS: %s option needs the mount point option as well\n",
MNTOPT_DMAPI);
return EINVAL;
@@ -438,27 +453,66 @@ xfs_parseargs(
* Note that if "ikeep" or "noikeep" mount options are
* supplied, then they are honored.
*/
- if ((args->flags & XFSMNT_DMAPI) && dmapi_implies_ikeep)
- args->flags |= XFSMNT_IKEEP;
+ if ((mp->m_flags & XFS_MOUNT_DMAPI) && dmapi_implies_ikeep)
+ mp->m_flags |= XFS_MOUNT_IKEEP;
- if ((args->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) {
+done:
+ if (!(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.
+ */
if (dsunit) {
- args->sunit = dsunit;
- args->flags |= XFSMNT_RETERR;
- } else {
- args->sunit = vol_dsunit;
+ mp->m_dalign = dsunit;
+ mp->m_flags |= XFS_MOUNT_RETERR;
}
- dswidth ? (args->swidth = dswidth) :
- (args->swidth = vol_dswidth);
- } else {
- args->sunit = args->swidth = 0;
+
+ if (dswidth)
+ 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)) {
+ cmn_err(CE_WARN,
+ "XFS: 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))) {
+ cmn_err(CE_WARN,
+ "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
+ mp->m_logbsize);
+ return XFS_ERROR(EINVAL);
+ }
+
+ 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;
+
+ if (iosizelog) {
+ if (iosizelog > XFS_MAX_IO_LOG ||
+ iosizelog < XFS_MIN_IO_LOG) {
+ cmn_err(CE_WARN,
+ "XFS: 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;
}
-done:
- if (args->flags & XFSMNT_32BITINODES)
- mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
- if (args->flags2)
- args->flags |= XFSMNT_FLAGS2;
return 0;
}
@@ -704,8 +758,7 @@ xfs_close_devices(
*/
STATIC int
xfs_open_devices(
- struct xfs_mount *mp,
- struct xfs_mount_args *args)
+ struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
struct block_device *logdev = NULL, *rtdev = NULL;
@@ -714,14 +767,14 @@ xfs_open_devices(
/*
* Open real time and log devices - order is important.
*/
- if (args->logname[0]) {
- error = xfs_blkdev_get(mp, args->logname, &logdev);
+ if (mp->m_logname) {
+ error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
}
- if (args->rtname[0]) {
- error = xfs_blkdev_get(mp, args->rtname, &rtdev);
+ if (mp->m_rtname) {
+ error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev);
if (error)
goto out_close_logdev;
@@ -813,18 +866,18 @@ xfs_setup_devices(
*/
void
xfsaild_wakeup(
- xfs_mount_t *mp,
+ struct xfs_ail *ailp,
xfs_lsn_t threshold_lsn)
{
- mp->m_ail.xa_target = threshold_lsn;
- wake_up_process(mp->m_ail.xa_task);
+ ailp->xa_target = threshold_lsn;
+ wake_up_process(ailp->xa_task);
}
int
xfsaild(
void *data)
{
- xfs_mount_t *mp = (xfs_mount_t *)data;
+ struct xfs_ail *ailp = data;
xfs_lsn_t last_pushed_lsn = 0;
long tout = 0;
@@ -836,11 +889,11 @@ xfsaild(
/* swsusp */
try_to_freeze();
- ASSERT(mp->m_log);
- if (XFS_FORCED_SHUTDOWN(mp))
+ ASSERT(ailp->xa_mount->m_log);
+ if (XFS_FORCED_SHUTDOWN(ailp->xa_mount))
continue;
- tout = xfsaild_push(mp, &last_pushed_lsn);
+ tout = xfsaild_push(ailp, &last_pushed_lsn);
}
return 0;
@@ -848,43 +901,82 @@ xfsaild(
int
xfsaild_start(
- xfs_mount_t *mp)
+ struct xfs_ail *ailp)
{
- mp->m_ail.xa_target = 0;
- mp->m_ail.xa_task = kthread_run(xfsaild, mp, "xfsaild");
- if (IS_ERR(mp->m_ail.xa_task))
- return -PTR_ERR(mp->m_ail.xa_task);
+ ailp->xa_target = 0;
+ ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild");
+ if (IS_ERR(ailp->xa_task))
+ return -PTR_ERR(ailp->xa_task);
return 0;
}
void
xfsaild_stop(
- xfs_mount_t *mp)
+ struct xfs_ail *ailp)
{
- kthread_stop(mp->m_ail.xa_task);
+ kthread_stop(ailp->xa_task);
}
-
+/* Catch misguided souls that try to use this interface on XFS */
STATIC struct inode *
xfs_fs_alloc_inode(
struct super_block *sb)
{
- return kmem_zone_alloc(xfs_vnode_zone, KM_SLEEP);
+ 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 inode *inode)
{
- kmem_zone_free(xfs_vnode_zone, inode);
+ xfs_inode_t *ip = XFS_I(inode);
+
+ XFS_STATS_INC(vn_reclaim);
+ if (xfs_reclaim(ip))
+ panic("%s: cannot reclaim 0x%p\n", __func__, inode);
}
+/*
+ * 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 intialise
+ * fields in the xfs inode that left in the initialise state
+ * when freeing the inode.
+ */
STATIC void
xfs_fs_inode_init_once(
- void *vnode)
+ void *inode)
{
- inode_init_once((struct inode *)vnode);
+ 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_iocount, 0);
+ atomic_set(&ip->i_pincount, 0);
+ spin_lock_init(&ip->i_flags_lock);
+ init_waitqueue_head(&ip->i_ipin_wait);
+ /*
+ * Because we want to use a counting completion, complete
+ * the flush completion once to allow a single access to
+ * the flush completion without blocking.
+ */
+ init_completion(&ip->i_flush);
+ complete(&ip->i_flush);
+
+ mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
+ "xfsino", ip->i_ino);
+ mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
}
/*
@@ -912,7 +1004,7 @@ xfs_fs_write_inode(
* it dirty again so we'll try again later.
*/
if (error)
- mark_inode_dirty_sync(inode);
+ xfs_mark_inode_dirty_sync(XFS_I(inode));
return -error;
}
@@ -923,164 +1015,13 @@ xfs_fs_clear_inode(
{
xfs_inode_t *ip = XFS_I(inode);
- /*
- * ip can be null when xfs_iget_core calls xfs_idestroy if we
- * find an inode with di_mode == 0 but without IGET_CREATE set.
- */
- if (ip) {
- xfs_itrace_entry(ip);
- XFS_STATS_INC(vn_rele);
- XFS_STATS_INC(vn_remove);
- XFS_STATS_INC(vn_reclaim);
- XFS_STATS_DEC(vn_active);
-
- xfs_inactive(ip);
- xfs_iflags_clear(ip, XFS_IMODIFIED);
- if (xfs_reclaim(ip))
- panic("%s: cannot reclaim 0x%p\n", __func__, inode);
- }
+ xfs_itrace_entry(ip);
+ XFS_STATS_INC(vn_rele);
+ XFS_STATS_INC(vn_remove);
+ XFS_STATS_DEC(vn_active);
- ASSERT(XFS_I(inode) == NULL);
-}
-
-/*
- * Enqueue a work item to be picked up by the vfs xfssyncd thread.
- * Doing this has two advantages:
- * - It saves on stack space, which is tight in certain situations
- * - It can be used (with care) as a mechanism to avoid deadlocks.
- * Flushing while allocating in a full filesystem requires both.
- */
-STATIC void
-xfs_syncd_queue_work(
- struct xfs_mount *mp,
- void *data,
- void (*syncer)(struct xfs_mount *, void *))
-{
- struct bhv_vfs_sync_work *work;
-
- work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
- INIT_LIST_HEAD(&work->w_list);
- work->w_syncer = syncer;
- work->w_data = data;
- work->w_mount = mp;
- spin_lock(&mp->m_sync_lock);
- list_add_tail(&work->w_list, &mp->m_sync_list);
- spin_unlock(&mp->m_sync_lock);
- wake_up_process(mp->m_sync_task);
-}
-
-/*
- * Flush delayed allocate data, attempting to free up reserved space
- * from existing allocations. At this point a new allocation attempt
- * has failed with ENOSPC and we are in the process of scratching our
- * heads, looking about for more room...
- */
-STATIC void
-xfs_flush_inode_work(
- struct xfs_mount *mp,
- void *arg)
-{
- struct inode *inode = arg;
- filemap_flush(inode->i_mapping);
- iput(inode);
-}
-
-void
-xfs_flush_inode(
- xfs_inode_t *ip)
-{
- struct inode *inode = VFS_I(ip);
-
- igrab(inode);
- xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
- delay(msecs_to_jiffies(500));
-}
-
-/*
- * This is the "bigger hammer" version of xfs_flush_inode_work...
- * (IOW, "If at first you don't succeed, use a Bigger Hammer").
- */
-STATIC void
-xfs_flush_device_work(
- struct xfs_mount *mp,
- void *arg)
-{
- struct inode *inode = arg;
- sync_blockdev(mp->m_super->s_bdev);
- iput(inode);
-}
-
-void
-xfs_flush_device(
- xfs_inode_t *ip)
-{
- struct inode *inode = VFS_I(ip);
-
- igrab(inode);
- xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
- delay(msecs_to_jiffies(500));
- xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
-}
-
-STATIC void
-xfs_sync_worker(
- struct xfs_mount *mp,
- void *unused)
-{
- int error;
-
- if (!(mp->m_flags & XFS_MOUNT_RDONLY))
- error = xfs_sync(mp, SYNC_FSDATA | SYNC_BDFLUSH | SYNC_ATTR);
- mp->m_sync_seq++;
- wake_up(&mp->m_wait_single_sync_task);
-}
-
-STATIC int
-xfssyncd(
- void *arg)
-{
- struct xfs_mount *mp = arg;
- long timeleft;
- bhv_vfs_sync_work_t *work, *n;
- LIST_HEAD (tmp);
-
- set_freezable();
- timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
- for (;;) {
- timeleft = schedule_timeout_interruptible(timeleft);
- /* swsusp */
- try_to_freeze();
- if (kthread_should_stop() && list_empty(&mp->m_sync_list))
- break;
-
- spin_lock(&mp->m_sync_lock);
- /*
- * We can get woken by laptop mode, to do a sync -
- * that's the (only!) case where the list would be
- * empty with time remaining.
- */
- if (!timeleft || list_empty(&mp->m_sync_list)) {
- if (!timeleft)
- timeleft = xfs_syncd_centisecs *
- msecs_to_jiffies(10);
- INIT_LIST_HEAD(&mp->m_sync_work.w_list);
- list_add_tail(&mp->m_sync_work.w_list,
- &mp->m_sync_list);
- }
- list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
- list_move(&work->w_list, &tmp);
- spin_unlock(&mp->m_sync_lock);
-
- list_for_each_entry_safe(work, n, &tmp, w_list) {
- (*work->w_syncer)(mp, work->w_data);
- list_del(&work->w_list);
- if (work == &mp->m_sync_work)
- continue;
- kmem_free(work);
- }
- }
-
- return 0;
+ xfs_inactive(ip);
+ xfs_iflags_clear(ip, XFS_IMODIFIED);
}
STATIC void
@@ -1101,9 +1042,8 @@ xfs_fs_put_super(
int unmount_event_flags = 0;
int error;
- kthread_stop(mp->m_sync_task);
-
- xfs_sync(mp, SYNC_ATTR | SYNC_DELWRI);
+ xfs_syncd_stop(mp);
+ xfs_sync_inodes(mp, SYNC_ATTR|SYNC_DELWRI);
#ifdef HAVE_DMAPI
if (mp->m_flags & XFS_MOUNT_DMAPI) {
@@ -1131,16 +1071,6 @@ xfs_fs_put_super(
error = xfs_unmount_flush(mp, 0);
WARN_ON(error);
- /*
- * If we're forcing a shutdown, typically because of a media error,
- * we want to make sure we invalidate dirty pages that belong to
- * referenced vnodes as well.
- */
- if (XFS_FORCED_SHUTDOWN(mp)) {
- error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE);
- ASSERT(error != EFSCORRUPTED);
- }
-
if (mp->m_flags & XFS_MOUNT_DMAPI) {
XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
unmount_event_flags);
@@ -1161,7 +1091,7 @@ xfs_fs_write_super(
struct super_block *sb)
{
if (!(sb->s_flags & MS_RDONLY))
- xfs_sync(XFS_M(sb), SYNC_FSDATA);
+ xfs_sync_fsdata(XFS_M(sb), 0);
sb->s_dirt = 0;
}
@@ -1172,7 +1102,6 @@ xfs_fs_sync_super(
{
struct xfs_mount *mp = XFS_M(sb);
int error;
- int flags;
/*
* Treat a sync operation like a freeze. This is to work
@@ -1186,20 +1115,10 @@ xfs_fs_sync_super(
* dirty the Linux inode until after the transaction I/O
* completes.
*/
- if (wait || unlikely(sb->s_frozen == SB_FREEZE_WRITE)) {
- /*
- * First stage of freeze - no more writers will make progress
- * now we are here, so we flush delwri and delalloc buffers
- * here, then wait for all I/O to complete. Data is frozen at
- * that point. Metadata is not frozen, transactions can still
- * occur here so don't bother flushing the buftarg (i.e
- * SYNC_QUIESCE) because it'll just get dirty again.
- */
- flags = SYNC_DATA_QUIESCE;
- } else
- flags = SYNC_FSDATA;
-
- error = xfs_sync(mp, flags);
+ if (wait || unlikely(sb->s_frozen == SB_FREEZE_WRITE))
+ error = xfs_quiesce_data(mp);
+ else
+ error = xfs_sync_fsdata(mp, 0);
sb->s_dirt = 0;
if (unlikely(laptop_mode)) {
@@ -1337,9 +1256,8 @@ xfs_fs_remount(
/* rw -> ro */
if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
- xfs_filestream_flush(mp);
- xfs_sync(mp, SYNC_DATA_QUIESCE);
- xfs_attr_quiesce(mp);
+ xfs_quiesce_data(mp);
+ xfs_quiesce_attr(mp);
mp->m_flags |= XFS_MOUNT_RDONLY;
}
@@ -1348,7 +1266,7 @@ xfs_fs_remount(
/*
* Second stage of a freeze. The data is already frozen so we only
- * need to take care of themetadata. Once that's done write a dummy
+ * 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.
*/
STATIC void
@@ -1357,7 +1275,7 @@ xfs_fs_lockfs(
{
struct xfs_mount *mp = XFS_M(sb);
- xfs_attr_quiesce(mp);
+ xfs_quiesce_attr(mp);
xfs_fs_log_dummy(mp);
}
@@ -1422,175 +1340,28 @@ xfs_fs_setxquota(
/*
* This function fills in xfs_mount_t fields based on mount args.
- * Note: the superblock has _not_ yet been read in.
- */
-STATIC int
-xfs_start_flags(
- struct xfs_mount_args *ap,
- struct xfs_mount *mp)
-{
- int error;
-
- /* Values are in BBs */
- if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_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 = ap->sunit;
- mp->m_swidth = ap->swidth;
- }
-
- if (ap->logbufs != -1 &&
- ap->logbufs != 0 &&
- (ap->logbufs < XLOG_MIN_ICLOGS ||
- ap->logbufs > XLOG_MAX_ICLOGS)) {
- cmn_err(CE_WARN,
- "XFS: invalid logbufs value: %d [not %d-%d]",
- ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
- return XFS_ERROR(EINVAL);
- }
- mp->m_logbufs = ap->logbufs;
- if (ap->logbufsize != -1 &&
- ap->logbufsize != 0 &&
- (ap->logbufsize < XLOG_MIN_RECORD_BSIZE ||
- ap->logbufsize > XLOG_MAX_RECORD_BSIZE ||
- !is_power_of_2(ap->logbufsize))) {
- cmn_err(CE_WARN,
- "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
- ap->logbufsize);
- return XFS_ERROR(EINVAL);
- }
-
- error = ENOMEM;
-
- mp->m_logbsize = ap->logbufsize;
- mp->m_fsname_len = strlen(ap->fsname) + 1;
-
- mp->m_fsname = kstrdup(ap->fsname, GFP_KERNEL);
- if (!mp->m_fsname)
- goto out;
-
- if (ap->rtname[0]) {
- mp->m_rtname = kstrdup(ap->rtname, GFP_KERNEL);
- if (!mp->m_rtname)
- goto out_free_fsname;
-
- }
-
- if (ap->logname[0]) {
- mp->m_logname = kstrdup(ap->logname, GFP_KERNEL);
- if (!mp->m_logname)
- goto out_free_rtname;
- }
-
- if (ap->flags & XFSMNT_WSYNC)
- mp->m_flags |= XFS_MOUNT_WSYNC;
-#if XFS_BIG_INUMS
- if (ap->flags & XFSMNT_INO64) {
- mp->m_flags |= XFS_MOUNT_INO64;
- mp->m_inoadd = XFS_INO64_OFFSET;
- }
-#endif
- if (ap->flags & XFSMNT_RETERR)
- mp->m_flags |= XFS_MOUNT_RETERR;
- if (ap->flags & XFSMNT_NOALIGN)
- mp->m_flags |= XFS_MOUNT_NOALIGN;
- if (ap->flags & XFSMNT_SWALLOC)
- mp->m_flags |= XFS_MOUNT_SWALLOC;
- if (ap->flags & XFSMNT_OSYNCISOSYNC)
- mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
- if (ap->flags & XFSMNT_32BITINODES)
- mp->m_flags |= XFS_MOUNT_32BITINODES;
-
- if (ap->flags & XFSMNT_IOSIZE) {
- if (ap->iosizelog > XFS_MAX_IO_LOG ||
- ap->iosizelog < XFS_MIN_IO_LOG) {
- cmn_err(CE_WARN,
- "XFS: invalid log iosize: %d [not %d-%d]",
- ap->iosizelog, XFS_MIN_IO_LOG,
- XFS_MAX_IO_LOG);
- return XFS_ERROR(EINVAL);
- }
-
- mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
- mp->m_readio_log = mp->m_writeio_log = ap->iosizelog;
- }
-
- if (ap->flags & XFSMNT_IKEEP)
- mp->m_flags |= XFS_MOUNT_IKEEP;
- if (ap->flags & XFSMNT_DIRSYNC)
- mp->m_flags |= XFS_MOUNT_DIRSYNC;
- if (ap->flags & XFSMNT_ATTR2)
- mp->m_flags |= XFS_MOUNT_ATTR2;
- if (ap->flags & XFSMNT_NOATTR2)
- mp->m_flags |= XFS_MOUNT_NOATTR2;
-
- if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE)
- mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-
- /*
- * no recovery flag requires a read-only mount
- */
- if (ap->flags & XFSMNT_NORECOVERY) {
- if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
- cmn_err(CE_WARN,
- "XFS: tried to mount a FS read-write without recovery!");
- return XFS_ERROR(EINVAL);
- }
- mp->m_flags |= XFS_MOUNT_NORECOVERY;
- }
-
- if (ap->flags & XFSMNT_NOUUID)
- mp->m_flags |= XFS_MOUNT_NOUUID;
- if (ap->flags & XFSMNT_BARRIER)
- mp->m_flags |= XFS_MOUNT_BARRIER;
- else
- mp->m_flags &= ~XFS_MOUNT_BARRIER;
-
- if (ap->flags2 & XFSMNT2_FILESTREAMS)
- mp->m_flags |= XFS_MOUNT_FILESTREAMS;
-
- if (ap->flags & XFSMNT_DMAPI)
- mp->m_flags |= XFS_MOUNT_DMAPI;
- return 0;
-
-
- out_free_rtname:
- kfree(mp->m_rtname);
- out_free_fsname:
- kfree(mp->m_fsname);
- out:
- return error;
-}
-
-/*
- * 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_args *ap,
struct xfs_mount *mp)
{
int ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
/* Fail a mount where the logbuf is smaller then the log stripe */
if (xfs_sb_version_haslogv2(&mp->m_sb)) {
- if ((ap->logbufsize <= 0) &&
- (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) {
+ if (mp->m_logbsize <= 0 &&
+ mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
mp->m_logbsize = mp->m_sb.sb_logsunit;
- } else if (ap->logbufsize > 0 &&
- ap->logbufsize < mp->m_sb.sb_logsunit) {
+ } else if (mp->m_logbsize > 0 &&
+ mp->m_logbsize < mp->m_sb.sb_logsunit) {
cmn_err(CE_WARN,
"XFS: 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 (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) {
+ if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
cmn_err(CE_WARN,
"XFS: logbuf size for version 1 logs must be 16K or 32K");
return XFS_ERROR(EINVAL);
@@ -1602,7 +1373,7 @@ xfs_finish_flags(
* told by noattr2 to turn it off
*/
if (xfs_sb_version_hasattr2(&mp->m_sb) &&
- !(ap->flags & XFSMNT_NOATTR2))
+ !(mp->m_flags & XFS_MOUNT_NOATTR2))
mp->m_flags |= XFS_MOUNT_ATTR2;
/*
@@ -1614,6 +1385,7 @@ xfs_finish_flags(
return XFS_ERROR(EROFS);
}
+#if 0 /* shared mounts were never supported on Linux */
/*
* check for shared mount.
*/
@@ -1636,25 +1408,11 @@ xfs_finish_flags(
/*
* Shared XFS V0 can't deal with DMI. Return EINVAL.
*/
- if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI))
+ if (mp->m_sb.sb_shared_vn == 0 &&
+ (mp->m_flags & XFS_MOUNT_DMAPI))
return XFS_ERROR(EINVAL);
}
-
- if (ap->flags & XFSMNT_UQUOTA) {
- mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
- if (ap->flags & XFSMNT_UQUOTAENF)
- mp->m_qflags |= XFS_UQUOTA_ENFD;
- }
-
- if (ap->flags & XFSMNT_GQUOTA) {
- mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
- if (ap->flags & XFSMNT_GQUOTAENF)
- mp->m_qflags |= XFS_OQUOTA_ENFD;
- } else if (ap->flags & XFSMNT_PQUOTA) {
- mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
- if (ap->flags & XFSMNT_PQUOTAENF)
- mp->m_qflags |= XFS_OQUOTA_ENFD;
- }
+#endif
return 0;
}
@@ -1667,19 +1425,14 @@ xfs_fs_fill_super(
{
struct inode *root;
struct xfs_mount *mp = NULL;
- struct xfs_mount_args *args;
int flags = 0, error = ENOMEM;
-
- args = xfs_args_allocate(sb, silent);
- if (!args)
- return -ENOMEM;
+ char *mtpt = NULL;
mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
if (!mp)
- goto out_free_args;
+ goto out;
spin_lock_init(&mp->m_sb_lock);
- mutex_init(&mp->m_ilock);
mutex_init(&mp->m_growlock);
atomic_set(&mp->m_active_trans, 0);
INIT_LIST_HEAD(&mp->m_sync_list);
@@ -1689,12 +1442,9 @@ xfs_fs_fill_super(
mp->m_super = sb;
sb->s_fs_info = mp;
- if (sb->s_flags & MS_RDONLY)
- mp->m_flags |= XFS_MOUNT_RDONLY;
-
- error = xfs_parseargs(mp, (char *)data, args, 0);
+ error = xfs_parseargs(mp, (char *)data, &mtpt);
if (error)
- goto out_free_mp;
+ goto out_free_fsname;
sb_min_blocksize(sb, BBSIZE);
sb->s_xattr = xfs_xattr_handlers;
@@ -1702,33 +1452,28 @@ xfs_fs_fill_super(
sb->s_qcop = &xfs_quotactl_operations;
sb->s_op = &xfs_super_operations;
- error = xfs_dmops_get(mp, args);
+ error = xfs_dmops_get(mp);
if (error)
- goto out_free_mp;
- error = xfs_qmops_get(mp, args);
+ goto out_free_fsname;
+ error = xfs_qmops_get(mp);
if (error)
goto out_put_dmops;
- if (args->flags & XFSMNT_QUIET)
+ if (silent)
flags |= XFS_MFSI_QUIET;
- error = xfs_open_devices(mp, args);
+ error = xfs_open_devices(mp);
if (error)
goto out_put_qmops;
if (xfs_icsb_init_counters(mp))
mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
- /*
- * Setup flags based on mount(2) options and then the superblock
- */
- error = xfs_start_flags(args, mp);
- if (error)
- goto out_free_fsname;
error = xfs_readsb(mp, flags);
if (error)
- goto out_free_fsname;
- error = xfs_finish_flags(args, mp);
+ goto out_destroy_counters;
+
+ error = xfs_finish_flags(mp);
if (error)
goto out_free_sb;
@@ -1747,7 +1492,7 @@ xfs_fs_fill_super(
if (error)
goto out_filestream_unmount;
- XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname);
+ XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, mtpt, mp->m_fsname);
sb->s_dirt = 1;
sb->s_magic = XFS_SB_MAGIC;
@@ -1772,35 +1517,31 @@ xfs_fs_fill_super(
goto fail_vnrele;
}
- mp->m_sync_work.w_syncer = xfs_sync_worker;
- mp->m_sync_work.w_mount = mp;
- mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
- if (IS_ERR(mp->m_sync_task)) {
- error = -PTR_ERR(mp->m_sync_task);
+ error = xfs_syncd_init(mp);
+ if (error)
goto fail_vnrele;
- }
- xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
+ kfree(mtpt);
- kfree(args);
+ xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
return 0;
out_filestream_unmount:
xfs_filestream_unmount(mp);
out_free_sb:
xfs_freesb(mp);
- out_free_fsname:
- xfs_free_fsname(mp);
+ out_destroy_counters:
xfs_icsb_destroy_counters(mp);
xfs_close_devices(mp);
out_put_qmops:
xfs_qmops_put(mp);
out_put_dmops:
xfs_dmops_put(mp);
- out_free_mp:
+ out_free_fsname:
+ xfs_free_fsname(mp);
+ kfree(mtpt);
kfree(mp);
- out_free_args:
- kfree(args);
+ out:
return -error;
fail_vnrele:
@@ -1882,10 +1623,19 @@ xfs_alloc_trace_bufs(void)
if (!xfs_bmap_trace_buf)
goto out_free_alloc_trace;
#endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
+ xfs_allocbt_trace_buf = ktrace_alloc(XFS_ALLOCBT_TRACE_SIZE,
+ KM_MAYFAIL);
+ if (!xfs_allocbt_trace_buf)
+ goto out_free_bmap_trace;
+
+ xfs_inobt_trace_buf = ktrace_alloc(XFS_INOBT_TRACE_SIZE, KM_MAYFAIL);
+ if (!xfs_inobt_trace_buf)
+ goto out_free_allocbt_trace;
+
xfs_bmbt_trace_buf = ktrace_alloc(XFS_BMBT_TRACE_SIZE, KM_MAYFAIL);
if (!xfs_bmbt_trace_buf)
- goto out_free_bmap_trace;
+ goto out_free_inobt_trace;
#endif
#ifdef XFS_ATTR_TRACE
xfs_attr_trace_buf = ktrace_alloc(XFS_ATTR_TRACE_SIZE, KM_MAYFAIL);
@@ -1907,8 +1657,12 @@ xfs_alloc_trace_bufs(void)
ktrace_free(xfs_attr_trace_buf);
out_free_bmbt_trace:
#endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
ktrace_free(xfs_bmbt_trace_buf);
+ out_free_inobt_trace:
+ ktrace_free(xfs_inobt_trace_buf);
+ out_free_allocbt_trace:
+ ktrace_free(xfs_allocbt_trace_buf);
out_free_bmap_trace:
#endif
#ifdef XFS_BMAP_TRACE
@@ -1931,8 +1685,10 @@ xfs_free_trace_bufs(void)
#ifdef XFS_ATTR_TRACE
ktrace_free(xfs_attr_trace_buf);
#endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
ktrace_free(xfs_bmbt_trace_buf);
+ ktrace_free(xfs_inobt_trace_buf);
+ ktrace_free(xfs_allocbt_trace_buf);
#endif
#ifdef XFS_BMAP_TRACE
ktrace_free(xfs_bmap_trace_buf);
@@ -1945,16 +1701,10 @@ xfs_free_trace_bufs(void)
STATIC int __init
xfs_init_zones(void)
{
- xfs_vnode_zone = kmem_zone_init_flags(sizeof(struct inode), "xfs_vnode",
- KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
- KM_ZONE_SPREAD,
- xfs_fs_inode_init_once);
- if (!xfs_vnode_zone)
- goto out;
xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
if (!xfs_ioend_zone)
- goto out_destroy_vnode_zone;
+ goto out;
xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
xfs_ioend_zone);
@@ -1970,6 +1720,7 @@ xfs_init_zones(void)
"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)
@@ -2017,8 +1768,8 @@ xfs_init_zones(void)
xfs_inode_zone =
kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
- KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
- KM_ZONE_SPREAD, NULL);
+ KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD,
+ xfs_fs_inode_init_once);
if (!xfs_inode_zone)
goto out_destroy_efi_zone;
@@ -2066,8 +1817,6 @@ xfs_init_zones(void)
mempool_destroy(xfs_ioend_pool);
out_destroy_ioend_zone:
kmem_zone_destroy(xfs_ioend_zone);
- out_destroy_vnode_zone:
- kmem_zone_destroy(xfs_vnode_zone);
out:
return -ENOMEM;
}
@@ -2092,7 +1841,6 @@ xfs_destroy_zones(void)
kmem_zone_destroy(xfs_log_ticket_zone);
mempool_destroy(xfs_ioend_pool);
kmem_zone_destroy(xfs_ioend_zone);
- kmem_zone_destroy(xfs_vnode_zone);
}
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index fe2ef4e6a0f..56dc48a76fa 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -101,9 +101,6 @@ struct block_device;
extern __uint64_t xfs_max_file_offset(unsigned int);
-extern void xfs_flush_inode(struct xfs_inode *);
-extern void xfs_flush_device(struct xfs_inode *);
-
extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
extern const struct export_operations xfs_export_operations;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
new file mode 100644
index 00000000000..fb5cca3df84
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -0,0 +1,763 @@
+/*
+ * Copyright (c) 2000-2005 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
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_types.h"
+#include "xfs_bit.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_dmapi.h"
+#include "xfs_mount.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_btree.h"
+#include "xfs_dir2_sf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_inode.h"
+#include "xfs_dinode.h"
+#include "xfs_error.h"
+#include "xfs_mru_cache.h"
+#include "xfs_filestream.h"
+#include "xfs_vnodeops.h"
+#include "xfs_utils.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode_item.h"
+#include "xfs_rw.h"
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+/*
+ * Sync all the inodes in the given AG according to the
+ * direction given by the flags.
+ */
+STATIC int
+xfs_sync_inodes_ag(
+ xfs_mount_t *mp,
+ int ag,
+ int flags)
+{
+ xfs_perag_t *pag = &mp->m_perag[ag];
+ int nr_found;
+ uint32_t first_index = 0;
+ int error = 0;
+ int last_error = 0;
+ int fflag = XFS_B_ASYNC;
+
+ if (flags & SYNC_DELWRI)
+ fflag = XFS_B_DELWRI;
+ if (flags & SYNC_WAIT)
+ fflag = 0; /* synchronous overrides all */
+
+ do {
+ struct inode *inode;
+ xfs_inode_t *ip = NULL;
+ int lock_flags = XFS_ILOCK_SHARED;
+
+ /*
+ * use a gang lookup to find the next inode in the tree
+ * as the tree is sparse and a gang lookup walks to find
+ * the number of objects requested.
+ */
+ read_lock(&pag->pag_ici_lock);
+ nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+ (void**)&ip, first_index, 1);
+
+ if (!nr_found) {
+ read_unlock(&pag->pag_ici_lock);
+ break;
+ }
+
+ /*
+ * Update the index for the next lookup. Catch overflows
+ * into the next AG range which can occur if we have inodes
+ * in the last block of the AG and we are currently
+ * pointing to the last inode.
+ */
+ first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+ if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
+ read_unlock(&pag->pag_ici_lock);
+ break;
+ }
+
+ /* nothing to sync during shutdown */
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ read_unlock(&pag->pag_ici_lock);
+ return 0;
+ }
+
+ /*
+ * If we can't get a reference on the inode, it must be
+ * in reclaim. Leave it for the reclaim code to flush.
+ */
+ inode = VFS_I(ip);
+ if (!igrab(inode)) {
+ read_unlock(&pag->pag_ici_lock);
+ continue;
+ }
+ read_unlock(&pag->pag_ici_lock);
+
+ /* bad inodes are dealt with elsewhere */
+ if (is_bad_inode(inode)) {
+ IRELE(ip);
+ continue;
+ }
+
+ /*
+ * If we have to flush data or wait for I/O completion
+ * we need to hold the iolock.
+ */
+ if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
+ xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ lock_flags |= XFS_IOLOCK_SHARED;
+ error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
+ if (flags & SYNC_IOWAIT)
+ vn_iowait(ip);
+ }
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+
+ if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
+ if (flags & SYNC_WAIT) {
+ xfs_iflock(ip);
+ if (!xfs_inode_clean(ip))
+ error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+ else
+ xfs_ifunlock(ip);
+ } else if (xfs_iflock_nowait(ip)) {
+ if (!xfs_inode_clean(ip))
+ error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
+ else
+ xfs_ifunlock(ip);
+ }
+ }
+ xfs_iput(ip, lock_flags);
+
+ if (error)
+ last_error = error;
+ /*
+ * bail out if the filesystem is corrupted.
+ */
+ if (error == EFSCORRUPTED)
+ return XFS_ERROR(error);
+
+ } while (nr_found);
+
+ return last_error;
+}
+
+int
+xfs_sync_inodes(
+ xfs_mount_t *mp,
+ int flags)
+{
+ int error;
+ int last_error;
+ int i;
+ int lflags = XFS_LOG_FORCE;
+
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ return 0;
+ error = 0;
+ last_error = 0;
+
+ if (flags & SYNC_WAIT)
+ lflags |= XFS_LOG_SYNC;
+
+ for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+ if (!mp->m_perag[i].pag_ici_init)
+ continue;
+ error = xfs_sync_inodes_ag(mp, i, flags);
+ if (error)
+ last_error = error;
+ if (error == EFSCORRUPTED)
+ break;
+ }
+ if (flags & SYNC_DELWRI)
+ xfs_log_force(mp, 0, lflags);
+
+ return XFS_ERROR(last_error);
+}
+
+STATIC int
+xfs_commit_dummy_trans(
+ struct xfs_mount *mp,
+ uint log_flags)
+{
+ struct xfs_inode *ip = mp->m_rootip;
+ struct xfs_trans *tp;
+ int error;
+
+ /*
+ * Put a dummy transaction in the log to tell recovery
+ * that all others are OK.
+ */
+ tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
+ error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ xfs_trans_ihold(tp, ip);
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ /* XXX(hch): ignoring the error here.. */
+ error = xfs_trans_commit(tp, 0);
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+ xfs_log_force(mp, 0, log_flags);
+ return 0;
+}
+
+int
+xfs_sync_fsdata(
+ struct xfs_mount *mp,
+ int flags)
+{
+ struct xfs_buf *bp;
+ struct xfs_buf_log_item *bip;
+ int error = 0;
+
+ /*
+ * If this is xfssyncd() then only sync the superblock if we can
+ * lock it without sleeping and it is not pinned.
+ */
+ if (flags & SYNC_BDFLUSH) {
+ ASSERT(!(flags & SYNC_WAIT));
+
+ bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
+ if (!bp)
+ goto out;
+
+ bip = XFS_BUF_FSPRIVATE(bp, struct xfs_buf_log_item *);
+ if (!bip || !xfs_buf_item_dirty(bip) || XFS_BUF_ISPINNED(bp))
+ goto out_brelse;
+ } else {
+ bp = xfs_getsb(mp, 0);
+
+ /*
+ * If the buffer is pinned then push on the log so we won't
+ * get stuck waiting in the write for someone, maybe
+ * ourselves, to flush the log.
+ *
+ * Even though we just pushed the log above, we did not have
+ * the superblock buffer locked at that point so it can
+ * become pinned in between there and here.
+ */
+ if (XFS_BUF_ISPINNED(bp))
+ xfs_log_force(mp, 0, XFS_LOG_FORCE);
+ }
+
+
+ if (flags & SYNC_WAIT)
+ XFS_BUF_UNASYNC(bp);
+ else
+ XFS_BUF_ASYNC(bp);
+
+ return xfs_bwrite(mp, bp);
+
+ out_brelse:
+ xfs_buf_relse(bp);
+ out:
+ return error;
+}
+
+/*
+ * When remounting a filesystem read-only or freezing the filesystem, we have
+ * two phases to execute. This first phase is syncing the data before we
+ * quiesce the filesystem, and the second is flushing all the inodes out after
+ * we've waited for all the transactions created by the first phase to
+ * complete. The second phase ensures that the inodes are 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 main difference between a sync and a quiesce).
+ */
+/*
+ * First stage of freeze - no writers will make progress now we are here,
+ * so we flush delwri and delalloc buffers here, then wait for all I/O to
+ * complete. Data is frozen at that point. Metadata is not frozen,
+ * transactions can still occur here so don't bother flushing the buftarg
+ * because it'll just get dirty again.
+ */
+int
+xfs_quiesce_data(
+ struct xfs_mount *mp)
+{
+ int error;
+
+ /* push non-blocking */
+ xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_BDFLUSH);
+ XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
+ xfs_filestream_flush(mp);
+
+ /* push and block */
+ xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_WAIT|SYNC_IOWAIT);
+ XFS_QM_DQSYNC(mp, SYNC_WAIT);
+
+ /* write superblock and hoover up shutdown errors */
+ error = xfs_sync_fsdata(mp, 0);
+
+ /* flush data-only devices */
+ if (mp->m_rtdev_targp)
+ XFS_bflush(mp->m_rtdev_targp);
+
+ return error;
+}
+
+STATIC void
+xfs_quiesce_fs(
+ struct xfs_mount *mp)
+{
+ int count = 0, pincount;
+
+ xfs_flush_buftarg(mp->m_ddev_targp, 0);
+ xfs_reclaim_inodes(mp, 0, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+
+ /*
+ * This loop must run at least twice. The first instance of the loop
+ * will flush most meta data but that will generate more meta data
+ * (typically directory updates). Which then must be flushed and
+ * logged before we can write the unmount record.
+ */
+ do {
+ xfs_sync_inodes(mp, SYNC_ATTR|SYNC_WAIT);
+ pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
+ if (!pincount) {
+ delay(50);
+ count++;
+ }
+ } while (count < 2);
+}
+
+/*
+ * Second stage of a quiesce. The data is already synced, now we have to take
+ * care of the metadata. New transactions are already blocked, so we need to
+ * wait for any remaining transactions to drain out before proceding.
+ */
+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);
+
+ /* flush inodes and push all remaining buffers out to disk */
+ xfs_quiesce_fs(mp);
+
+ ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
+
+ /* Push the superblock and write an unmount record */
+ error = xfs_log_sbcount(mp, 1);
+ if (error)
+ xfs_fs_cmn_err(CE_WARN, mp,
+ "xfs_attr_quiesce: failed to log sb changes. "
+ "Frozen image may not be consistent.");
+ xfs_log_unmount_write(mp);
+ xfs_unmountfs_writesb(mp);
+}
+
+/*
+ * Enqueue a work item to be picked up by the vfs xfssyncd thread.
+ * Doing this has two advantages:
+ * - It saves on stack space, which is tight in certain situations
+ * - It can be used (with care) as a mechanism to avoid deadlocks.
+ * Flushing while allocating in a full filesystem requires both.
+ */
+STATIC void
+xfs_syncd_queue_work(
+ struct xfs_mount *mp,
+ void *data,
+ void (*syncer)(struct xfs_mount *, void *))
+{
+ struct bhv_vfs_sync_work *work;
+
+ work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
+ INIT_LIST_HEAD(&work->w_list);
+ work->w_syncer = syncer;
+ work->w_data = data;
+ work->w_mount = mp;
+ spin_lock(&mp->m_sync_lock);
+ list_add_tail(&work->w_list, &mp->m_sync_list);
+ spin_unlock(&mp->m_sync_lock);
+ wake_up_process(mp->m_sync_task);
+}
+
+/*
+ * Flush delayed allocate data, attempting to free up reserved space
+ * from existing allocations. At this point a new allocation attempt
+ * has failed with ENOSPC and we are in the process of scratching our
+ * heads, looking about for more room...
+ */
+STATIC void
+xfs_flush_inode_work(
+ struct xfs_mount *mp,
+ void *arg)
+{
+ struct inode *inode = arg;
+ filemap_flush(inode->i_mapping);
+ iput(inode);
+}
+
+void
+xfs_flush_inode(
+ xfs_inode_t *ip)
+{
+ struct inode *inode = VFS_I(ip);
+
+ igrab(inode);
+ xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
+ delay(msecs_to_jiffies(500));
+}
+
+/*
+ * This is the "bigger hammer" version of xfs_flush_inode_work...
+ * (IOW, "If at first you don't succeed, use a Bigger Hammer").
+ */
+STATIC void
+xfs_flush_device_work(
+ struct xfs_mount *mp,
+ void *arg)
+{
+ struct inode *inode = arg;
+ sync_blockdev(mp->m_super->s_bdev);
+ iput(inode);
+}
+
+void
+xfs_flush_device(
+ xfs_inode_t *ip)
+{
+ struct inode *inode = VFS_I(ip);
+
+ igrab(inode);
+ xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
+ delay(msecs_to_jiffies(500));
+ xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
+}
+
+/*
+ * Every sync period we need to unpin all items, reclaim inodes, sync
+ * quota and write out the superblock. We might need to cover the log
+ * to indicate it is idle.
+ */
+STATIC void
+xfs_sync_worker(
+ struct xfs_mount *mp,
+ void *unused)
+{
+ int error;
+
+ if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+ xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+ xfs_reclaim_inodes(mp, 0, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+ /* dgc: errors ignored here */
+ error = XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
+ error = xfs_sync_fsdata(mp, SYNC_BDFLUSH);
+ if (xfs_log_need_covered(mp))
+ error = xfs_commit_dummy_trans(mp, XFS_LOG_FORCE);
+ }
+ mp->m_sync_seq++;
+ wake_up(&mp->m_wait_single_sync_task);
+}
+
+STATIC int
+xfssyncd(
+ void *arg)
+{
+ struct xfs_mount *mp = arg;
+ long timeleft;
+ bhv_vfs_sync_work_t *work, *n;
+ LIST_HEAD (tmp);
+
+ set_freezable();
+ timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
+ for (;;) {
+ timeleft = schedule_timeout_interruptible(timeleft);
+ /* swsusp */
+ try_to_freeze();
+ if (kthread_should_stop() && list_empty(&mp->m_sync_list))
+ break;
+
+ spin_lock(&mp->m_sync_lock);
+ /*
+ * We can get woken by laptop mode, to do a sync -
+ * that's the (only!) case where the list would be
+ * empty with time remaining.
+ */
+ if (!timeleft || list_empty(&mp->m_sync_list)) {
+ if (!timeleft)
+ timeleft = xfs_syncd_centisecs *
+ msecs_to_jiffies(10);
+ INIT_LIST_HEAD(&mp->m_sync_work.w_list);
+ list_add_tail(&mp->m_sync_work.w_list,
+ &mp->m_sync_list);
+ }
+ list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
+ list_move(&work->w_list, &tmp);
+ spin_unlock(&mp->m_sync_lock);
+
+ list_for_each_entry_safe(work, n, &tmp, w_list) {
+ (*work->w_syncer)(mp, work->w_data);
+ list_del(&work->w_list);
+ if (work == &mp->m_sync_work)
+ continue;
+ kmem_free(work);
+ }
+ }
+
+ return 0;
+}
+
+int
+xfs_syncd_init(
+ struct xfs_mount *mp)
+{
+ mp->m_sync_work.w_syncer = xfs_sync_worker;
+ mp->m_sync_work.w_mount = mp;
+ mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
+ if (IS_ERR(mp->m_sync_task))
+ return -PTR_ERR(mp->m_sync_task);
+ return 0;
+}
+
+void
+xfs_syncd_stop(
+ struct xfs_mount *mp)
+{
+ kthread_stop(mp->m_sync_task);
+}
+
+int
+xfs_reclaim_inode(
+ xfs_inode_t *ip,
+ int locked,
+ int sync_mode)
+{
+ xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
+
+ /* The hash lock here protects a thread in xfs_iget_core from
+ * racing with us on linking the inode back with a vnode.
+ * Once we have the XFS_IRECLAIM flag set it will not touch
+ * us.
+ */
+ write_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
+ !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
+ if (locked) {
+ xfs_ifunlock(ip);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ }
+ return 1;
+ }
+ __xfs_iflags_set(ip, XFS_IRECLAIM);
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
+ xfs_put_perag(ip->i_mount, pag);
+
+ /*
+ * If the inode is still dirty, then flush it out. If the inode
+ * is not in the AIL, then it will be OK to flush it delwri as
+ * long as xfs_iflush() does not keep any references to the inode.
+ * We leave that decision up to xfs_iflush() since it has the
+ * knowledge of whether it's OK to simply do a delwri flush of
+ * the inode or whether we need to wait until the inode is
+ * pulled from the AIL.
+ * We get the flush lock regardless, though, just to make sure
+ * we don't free it while it is being flushed.
+ */
+ if (!locked) {
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_iflock(ip);
+ }
+
+ /*
+ * In the case of a forced shutdown we rely on xfs_iflush() to
+ * wait for the inode to be unpinned before returning an error.
+ */
+ if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
+ /* synchronize with xfs_iflush_done */
+ xfs_iflock(ip);
+ xfs_ifunlock(ip);
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_ireclaim(ip);
+ return 0;
+}
+
+/*
+ * We set the inode flag atomically with the radix tree tag.
+ * Once we get tag lookups on the radix tree, this inode flag
+ * can go away.
+ */
+void
+xfs_inode_set_reclaim_tag(
+ xfs_inode_t *ip)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino);
+
+ read_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+ radix_tree_tag_set(&pag->pag_ici_root,
+ XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+ __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
+ spin_unlock(&ip->i_flags_lock);
+ read_unlock(&pag->pag_ici_lock);
+ xfs_put_perag(mp, pag);
+}
+
+void
+__xfs_inode_clear_reclaim_tag(
+ xfs_mount_t *mp,
+ xfs_perag_t *pag,
+ xfs_inode_t *ip)
+{
+ radix_tree_tag_clear(&pag->pag_ici_root,
+ XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+}
+
+void
+xfs_inode_clear_reclaim_tag(
+ xfs_inode_t *ip)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino);
+
+ read_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+ __xfs_inode_clear_reclaim_tag(mp, pag, ip);
+ spin_unlock(&ip->i_flags_lock);
+ read_unlock(&pag->pag_ici_lock);
+ xfs_put_perag(mp, pag);
+}
+
+
+STATIC void
+xfs_reclaim_inodes_ag(
+ xfs_mount_t *mp,
+ int ag,
+ int noblock,
+ int mode)
+{
+ xfs_inode_t *ip = NULL;
+ xfs_perag_t *pag = &mp->m_perag[ag];
+ int nr_found;
+ uint32_t first_index;
+ int skipped;
+
+restart:
+ first_index = 0;
+ skipped = 0;
+ do {
+ /*
+ * use a gang lookup to find the next inode in the tree
+ * as the tree is sparse and a gang lookup walks to find
+ * the number of objects requested.
+ */
+ read_lock(&pag->pag_ici_lock);
+ nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root,
+ (void**)&ip, first_index, 1,
+ XFS_ICI_RECLAIM_TAG);
+
+ if (!nr_found) {
+ read_unlock(&pag->pag_ici_lock);
+ break;
+ }
+
+ /*
+ * Update the index for the next lookup. Catch overflows
+ * into the next AG range which can occur if we have inodes
+ * in the last block of the AG and we are currently
+ * pointing to the last inode.
+ */
+ first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+ if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
+ read_unlock(&pag->pag_ici_lock);
+ break;
+ }
+
+ ASSERT(xfs_iflags_test(ip, (XFS_IRECLAIMABLE|XFS_IRECLAIM)));
+
+ /* ignore if already under reclaim */
+ if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
+ read_unlock(&pag->pag_ici_lock);
+ continue;
+ }
+
+ if (noblock) {
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+ read_unlock(&pag->pag_ici_lock);
+ continue;
+ }
+ if (xfs_ipincount(ip) ||
+ !xfs_iflock_nowait(ip)) {
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ read_unlock(&pag->pag_ici_lock);
+ continue;
+ }
+ }
+ read_unlock(&pag->pag_ici_lock);
+
+ /*
+ * hmmm - this is an inode already in reclaim. Do
+ * we even bother catching it here?
+ */
+ if (xfs_reclaim_inode(ip, noblock, mode))
+ skipped++;
+ } while (nr_found);
+
+ if (skipped) {
+ delay(1);
+ goto restart;
+ }
+ return;
+
+}
+
+int
+xfs_reclaim_inodes(
+ xfs_mount_t *mp,
+ int noblock,
+ int mode)
+{
+ int i;
+
+ for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+ if (!mp->m_perag[i].pag_ici_init)
+ continue;
+ xfs_reclaim_inodes_ag(mp, i, noblock, mode);
+ }
+ return 0;
+}
+
+
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
new file mode 100644
index 00000000000..5f6de1efe1f
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -0,0 +1,55 @@
+/*
+ * 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
+ */
+#ifndef XFS_SYNC_H
+#define XFS_SYNC_H 1
+
+struct xfs_mount;
+
+typedef struct bhv_vfs_sync_work {
+ struct list_head w_list;
+ struct xfs_mount *w_mount;
+ void *w_data; /* syncer routine argument */
+ void (*w_syncer)(struct xfs_mount *, void *);
+} bhv_vfs_sync_work_t;
+
+#define SYNC_ATTR 0x0001 /* sync attributes */
+#define SYNC_DELWRI 0x0002 /* look at delayed writes */
+#define SYNC_WAIT 0x0004 /* wait for i/o to complete */
+#define SYNC_BDFLUSH 0x0008 /* BDFLUSH is calling -- don't block */
+#define SYNC_IOWAIT 0x0010 /* wait for all I/O to complete */
+
+int xfs_syncd_init(struct xfs_mount *mp);
+void xfs_syncd_stop(struct xfs_mount *mp);
+
+int xfs_sync_inodes(struct xfs_mount *mp, int flags);
+int xfs_sync_fsdata(struct xfs_mount *mp, int flags);
+
+int xfs_quiesce_data(struct xfs_mount *mp);
+void xfs_quiesce_attr(struct xfs_mount *mp);
+
+void xfs_flush_inode(struct xfs_inode *ip);
+void xfs_flush_device(struct xfs_inode *ip);
+
+int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
+int xfs_reclaim_inodes(struct xfs_mount *mp, int noblock, int mode);
+
+void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void xfs_inode_clear_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
+ struct xfs_inode *ip);
+#endif
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index 7dacb5bbde3..916c0ffb608 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -56,17 +56,6 @@ xfs_stats_clear_proc_handler(
static ctl_table xfs_table[] = {
{
- .ctl_name = XFS_RESTRICT_CHOWN,
- .procname = "restrict_chown",
- .data = &xfs_params.restrict_chown.val,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
- .extra1 = &xfs_params.restrict_chown.min,
- .extra2 = &xfs_params.restrict_chown.max
- },
- {
.ctl_name = XFS_SGID_INHERIT,
.procname = "irix_sgid_inherit",
.data = &xfs_params.sgid_inherit.val,
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.h b/fs/xfs/linux-2.6/xfs_sysctl.h
index 4aadb8056c3..b9937d450f8 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.h
+++ b/fs/xfs/linux-2.6/xfs_sysctl.h
@@ -31,7 +31,6 @@ typedef struct xfs_sysctl_val {
} xfs_sysctl_val_t;
typedef struct xfs_param {
- xfs_sysctl_val_t restrict_chown;/* Root/non-root can give away files.*/
xfs_sysctl_val_t sgid_inherit; /* Inherit S_ISGID if process' GID is
* not a member of parent dir GID. */
xfs_sysctl_val_t symlink_mode; /* Link creat mode affected by umask */
@@ -68,7 +67,7 @@ typedef struct xfs_param {
enum {
/* XFS_REFCACHE_SIZE = 1 */
/* XFS_REFCACHE_PURGE = 2 */
- XFS_RESTRICT_CHOWN = 3,
+ /* XFS_RESTRICT_CHOWN = 3 */
XFS_SGID_INHERIT = 4,
XFS_SYMLINK_MODE = 5,
XFS_PANIC_MASK = 6,
diff --git a/fs/xfs/linux-2.6/xfs_vfs.h b/fs/xfs/linux-2.6/xfs_vfs.h
index 7e60c7776b1..0ab60bc2e76 100644
--- a/fs/xfs/linux-2.6/xfs_vfs.h
+++ b/fs/xfs/linux-2.6/xfs_vfs.h
@@ -33,37 +33,6 @@ struct xfs_mount_args;
typedef struct kstatfs bhv_statvfs_t;
-typedef struct bhv_vfs_sync_work {
- struct list_head w_list;
- struct xfs_mount *w_mount;
- void *w_data; /* syncer routine argument */
- void (*w_syncer)(struct xfs_mount *, void *);
-} bhv_vfs_sync_work_t;
-
-#define SYNC_ATTR 0x0001 /* sync attributes */
-#define SYNC_CLOSE 0x0002 /* close file system down */
-#define SYNC_DELWRI 0x0004 /* look at delayed writes */
-#define SYNC_WAIT 0x0008 /* wait for i/o to complete */
-#define SYNC_BDFLUSH 0x0010 /* BDFLUSH is calling -- don't block */
-#define SYNC_FSDATA 0x0020 /* flush fs data (e.g. superblocks) */
-#define SYNC_REFCACHE 0x0040 /* prune some of the nfs ref cache */
-#define SYNC_REMOUNT 0x0080 /* remount readonly, no dummy LRs */
-#define SYNC_IOWAIT 0x0100 /* wait for all I/O to complete */
-
-/*
- * When remounting a filesystem read-only or freezing the filesystem,
- * we have two phases to execute. This first phase is syncing the data
- * before we quiesce the fielsystem, and the second is flushing all the
- * inodes out after we've waited for all the transactions created by
- * the first phase to complete. The second phase uses SYNC_INODE_QUIESCE
- * to ensure that the inodes are 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 main difference between a sync and a quiesce).
- */
-#define SYNC_DATA_QUIESCE (SYNC_DELWRI|SYNC_FSDATA|SYNC_WAIT|SYNC_IOWAIT)
-#define SYNC_INODE_QUIESCE (SYNC_REMOUNT|SYNC_ATTR|SYNC_WAIT)
-
#define SHUTDOWN_META_IO_ERROR 0x0001 /* write attempt to metadata failed */
#define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */
#define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */
diff --git a/fs/xfs/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c
index b52528bbbff..ad18262d651 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.c
+++ b/fs/xfs/linux-2.6/xfs_vnode.c
@@ -84,25 +84,12 @@ vn_ioerror(
#ifdef XFS_INODE_TRACE
-/*
- * Reference count of Linux inode if present, -1 if the xfs_inode
- * has no associated Linux inode.
- */
-static inline int xfs_icount(struct xfs_inode *ip)
-{
- struct inode *vp = VFS_I(ip);
-
- if (vp)
- return vn_count(vp);
- return -1;
-}
-
#define KTRACE_ENTER(ip, vk, s, line, ra) \
ktrace_enter( (ip)->i_trace, \
/* 0 */ (void *)(__psint_t)(vk), \
/* 1 */ (void *)(s), \
/* 2 */ (void *)(__psint_t) line, \
-/* 3 */ (void *)(__psint_t)xfs_icount(ip), \
+/* 3 */ (void *)(__psint_t)atomic_read(&VFS_I(ip)->i_count), \
/* 4 */ (void *)(ra), \
/* 5 */ NULL, \
/* 6 */ (void *)(__psint_t)current_cpu(), \
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 683ce16210f..bf89e41c3b8 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -80,11 +80,6 @@ do { \
iput(VFS_I(ip)); \
} while (0)
-static inline struct inode *vn_grab(struct inode *vp)
-{
- return igrab(vp);
-}
-
/*
* Dealing with bad inodes
*/
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-26 23:12:11 +0000