aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/linux-2.6/kmem.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_acl.c73
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c8
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_file.c1
-rw-r--r--fs/xfs/linux-2.6/xfs_ioctl32.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_iops.c4
-rw-r--r--fs/xfs/linux-2.6/xfs_linux.h2
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c13
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.h1
-rw-r--r--fs/xfs/xfs_acl.h4
-rw-r--r--fs/xfs/xfs_attr.c8
-rw-r--r--fs/xfs/xfs_bmap.c2
-rw-r--r--fs/xfs/xfs_btree.c4
-rw-r--r--fs/xfs/xfs_da_btree.c6
-rw-r--r--fs/xfs/xfs_dir2.c2
-rw-r--r--fs/xfs/xfs_fsops.c20
-rw-r--r--fs/xfs/xfs_iget.c255
-rw-r--r--fs/xfs/xfs_inode.c10
-rw-r--r--fs/xfs/xfs_inode.h22
-rw-r--r--fs/xfs/xfs_log.c2
-rw-r--r--fs/xfs/xfs_vnodeops.c4
23 files changed, 208 insertions, 245 deletions
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 1cd3b55ee3d..2d3f90afe5f 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__func__, lflags);
- congestion_wait(WRITE, HZ/50);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
} while (1);
}
@@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__func__, lflags);
- congestion_wait(WRITE, HZ/50);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
} while (1);
}
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 1e9d1246eeb..b23a5450644 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -25,14 +25,10 @@
#include <linux/posix_acl_xattr.h>
-#define XFS_ACL_NOT_CACHED ((void *)-1)
-
/*
* Locking scheme:
* - all ACL updates are protected by inode->i_mutex, which is taken before
* calling into this file.
- * - access and updates to the ip->i_acl and ip->i_default_acl pointers are
- * protected by inode->i_lock.
*/
STATIC struct posix_acl *
@@ -102,59 +98,35 @@ xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
}
}
-/*
- * Update the cached ACL pointer in the inode.
- *
- * Because we don't hold any locks while reading/writing the attribute
- * from/to disk another thread could have raced and updated the cached
- * ACL value before us. In that case we release the previous cached value
- * and update it with our new value.
- */
-STATIC void
-xfs_update_cached_acl(struct inode *inode, struct posix_acl **p_acl,
- struct posix_acl *acl)
-{
- spin_lock(&inode->i_lock);
- if (*p_acl && *p_acl != XFS_ACL_NOT_CACHED)
- posix_acl_release(*p_acl);
- *p_acl = posix_acl_dup(acl);
- spin_unlock(&inode->i_lock);
-}
-
struct posix_acl *
xfs_get_acl(struct inode *inode, int type)
{
struct xfs_inode *ip = XFS_I(inode);
- struct posix_acl *acl = NULL, **p_acl;
+ struct posix_acl *acl;
struct xfs_acl *xfs_acl;
int len = sizeof(struct xfs_acl);
char *ea_name;
int error;
+ acl = get_cached_acl(inode, type);
+ if (acl != ACL_NOT_CACHED)
+ return acl;
+
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
- p_acl = &ip->i_acl;
break;
case ACL_TYPE_DEFAULT:
ea_name = SGI_ACL_DEFAULT;
- p_acl = &ip->i_default_acl;
break;
default:
- return ERR_PTR(-EINVAL);
+ BUG();
}
- spin_lock(&inode->i_lock);
- if (*p_acl != XFS_ACL_NOT_CACHED)
- acl = posix_acl_dup(*p_acl);
- spin_unlock(&inode->i_lock);
-
/*
* If we have a cached ACLs value just return it, not need to
* go out to the disk.
*/
- if (acl)
- return acl;
xfs_acl = kzalloc(sizeof(struct xfs_acl), GFP_KERNEL);
if (!xfs_acl)
@@ -165,7 +137,7 @@ xfs_get_acl(struct inode *inode, int type)
/*
* If the attribute doesn't exist make sure we have a negative
* cache entry, for any other error assume it is transient and
- * leave the cache entry as XFS_ACL_NOT_CACHED.
+ * leave the cache entry as ACL_NOT_CACHED.
*/
if (error == -ENOATTR) {
acl = NULL;
@@ -179,7 +151,7 @@ xfs_get_acl(struct inode *inode, int type)
goto out;
out_update_cache:
- xfs_update_cached_acl(inode, p_acl, acl);
+ set_cached_acl(inode, type, acl);
out:
kfree(xfs_acl);
return acl;
@@ -189,7 +161,6 @@ STATIC int
xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
{
struct xfs_inode *ip = XFS_I(inode);
- struct posix_acl **p_acl;
char *ea_name;
int error;
@@ -199,13 +170,11 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
- p_acl = &ip->i_acl;
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
ea_name = SGI_ACL_DEFAULT;
- p_acl = &ip->i_default_acl;
break;
default:
return -EINVAL;
@@ -242,7 +211,7 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
}
if (!error)
- xfs_update_cached_acl(inode, p_acl, acl);
+ set_cached_acl(inode, type, acl);
return error;
}
@@ -384,30 +353,6 @@ xfs_acl_chmod(struct inode *inode)
return error;
}
-void
-xfs_inode_init_acls(struct xfs_inode *ip)
-{
- /*
- * No need for locking, inode is not live yet.
- */
- ip->i_acl = XFS_ACL_NOT_CACHED;
- ip->i_default_acl = XFS_ACL_NOT_CACHED;
-}
-
-void
-xfs_inode_clear_acls(struct xfs_inode *ip)
-{
- /*
- * No need for locking here, the inode is not live anymore
- * and just about to be freed.
- */
- if (ip->i_acl != XFS_ACL_NOT_CACHED)
- posix_acl_release(ip->i_acl);
- if (ip->i_default_acl != XFS_ACL_NOT_CACHED)
- posix_acl_release(ip->i_default_acl);
-}
-
-
/*
* System xattr handlers.
*
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 7ec89fc05b2..aecf2519db7 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1268,6 +1268,14 @@ xfs_vm_writepage(
if (!page_has_buffers(page))
create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+
+ /*
+ * VM calculation for nr_to_write seems off. Bump it way
+ * up, this gets simple streaming writes zippy again.
+ * To be reviewed again after Jens' writeback changes.
+ */
+ wbc->nr_to_write *= 4;
+
/*
* Convert delayed allocate, unwritten or unmapped space
* to real space and flush out to disk.
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 1418b916fc2..965df1227d6 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -412,7 +412,7 @@ _xfs_buf_lookup_pages(
XFS_STATS_INC(xb_page_retries);
xfsbufd_wakeup(0, gfp_mask);
- congestion_wait(WRITE, HZ/50);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
@@ -770,7 +770,7 @@ xfs_buf_associate_memory(
bp->b_pages = NULL;
bp->b_addr = mem;
- rval = _xfs_buf_get_pages(bp, page_count, 0);
+ rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK);
if (rval)
return rval;
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index f4e25544157..0542fd50764 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -41,7 +41,6 @@
#include "xfs_ioctl.h"
#include <linux/dcache.h>
-#include <linux/smp_lock.h>
static struct vm_operations_struct xfs_file_vm_ops;
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 0882d166239..eafcc7c1870 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -619,7 +619,7 @@ xfs_file_compat_ioctl(
case XFS_IOC_GETVERSION_32:
cmd = _NATIVE_IOC(cmd, long);
return xfs_file_ioctl(filp, cmd, p);
- case XFS_IOC_SWAPEXT: {
+ case XFS_IOC_SWAPEXT_32: {
struct xfs_swapext sxp;
struct compat_xfs_swapext __user *sxu = arg;
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 58973bb4603..8070b34cc28 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -680,8 +680,8 @@ xfs_vn_fiemap(
else
bm.bmv_length = BTOBB(length);
- /* our formatter will tell xfs_getbmap when to stop. */
- bm.bmv_count = MAXEXTNUM;
+ /* We add one because in getbmap world count includes the header */
+ bm.bmv_count = fieinfo->fi_extents_max + 1;
bm.bmv_iflags = BMV_IF_PREALLOC;
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
bm.bmv_iflags |= BMV_IF_ATTRFORK;
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index f65a53f8752..6127e24062d 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -24,7 +24,7 @@
* XFS_BIG_BLKNOS needs block layer disk addresses to be 64 bits.
* XFS_BIG_INUMS requires XFS_BIG_BLKNOS to be set.
*/
-#if defined(CONFIG_LBD) || (BITS_PER_LONG == 64)
+#if defined(CONFIG_LBDAF) || (BITS_PER_LONG == 64)
# define XFS_BIG_BLKNOS 1
# define XFS_BIG_INUMS 1
#else
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 2e09efbca8d..a220d36f789 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -616,7 +616,7 @@ xfs_max_file_offset(
*/
#if BITS_PER_LONG == 32
-# if defined(CONFIG_LBD)
+# if defined(CONFIG_LBDAF)
ASSERT(sizeof(sector_t) == 8);
pagefactor = PAGE_CACHE_SIZE;
bitshift = BITS_PER_LONG;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index b619d6b8ca4..98ef624d9ba 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -708,6 +708,16 @@ xfs_reclaim_inode(
return 0;
}
+void
+__xfs_inode_set_reclaim_tag(
+ struct xfs_perag *pag,
+ struct xfs_inode *ip)
+{
+ radix_tree_tag_set(&pag->pag_ici_root,
+ XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+ XFS_ICI_RECLAIM_TAG);
+}
+
/*
* We set the inode flag atomically with the radix tree tag.
* Once we get tag lookups on the radix tree, this inode flag
@@ -722,8 +732,7 @@ xfs_inode_set_reclaim_tag(
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_inode_set_reclaim_tag(pag, ip);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
read_unlock(&pag->pag_ici_lock);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 2a10301c99c..59120602588 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -48,6 +48,7 @@ int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, 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);
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 63dc1f2efad..947b150df8e 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -46,8 +46,6 @@ extern int xfs_check_acl(struct inode *inode, int mask);
extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
extern int xfs_inherit_acl(struct inode *inode, struct posix_acl *default_acl);
extern int xfs_acl_chmod(struct inode *inode);
-extern void xfs_inode_init_acls(struct xfs_inode *ip);
-extern void xfs_inode_clear_acls(struct xfs_inode *ip);
extern int posix_acl_access_exists(struct inode *inode);
extern int posix_acl_default_exists(struct inode *inode);
@@ -57,8 +55,6 @@ extern struct xattr_handler xfs_xattr_system_handler;
# define xfs_get_acl(inode, type) NULL
# define xfs_inherit_acl(inode, default_acl) 0
# define xfs_acl_chmod(inode) 0
-# define xfs_inode_init_acls(ip)
-# define xfs_inode_clear_acls(ip)
# define posix_acl_access_exists(inode) 0
# define posix_acl_default_exists(inode) 0
#endif /* CONFIG_XFS_POSIX_ACL */
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index db15feb906f..4ece1906bd4 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -2010,7 +2010,9 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno,
- blkcnt, XFS_BUF_LOCK, &bp);
+ blkcnt,
+ XFS_BUF_LOCK | XBF_DONT_BLOCK,
+ &bp);
if (error)
return(error);
@@ -2141,8 +2143,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
- bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno,
- blkcnt, XFS_BUF_LOCK);
+ bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, blkcnt,
+ XFS_BUF_LOCK | XBF_DONT_BLOCK);
ASSERT(bp);
ASSERT(!XFS_BUF_GETERROR(bp));
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 7928b9983c1..8ee5b5a76a2 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -6009,7 +6009,7 @@ xfs_getbmap(
*/
error = ENOMEM;
subnex = 16;
- map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL);
+ map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
if (!map)
goto out_unlock_ilock;
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e9df9957482..26717388acf 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -120,8 +120,8 @@ xfs_btree_check_sblock(
XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
if (bp)
xfs_buftrace("SBTREE ERROR", bp);
- XFS_ERROR_REPORT("xfs_btree_check_sblock", XFS_ERRLEVEL_LOW,
- cur->bc_mp);
+ XFS_CORRUPTION_ERROR("xfs_btree_check_sblock",
+ XFS_ERRLEVEL_LOW, cur->bc_mp, block);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 9ff6e57a507..2847bbc1c53 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -2201,7 +2201,7 @@ kmem_zone_t *xfs_dabuf_zone; /* dabuf zone */
xfs_da_state_t *
xfs_da_state_alloc(void)
{
- return kmem_zone_zalloc(xfs_da_state_zone, KM_SLEEP);
+ return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
}
/*
@@ -2261,9 +2261,9 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra)
int off;
if (nbuf == 1)
- dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_SLEEP);
+ dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
else
- dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_SLEEP);
+ dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
dabuf->dirty = 0;
#ifdef XFS_DABUF_DEBUG
dabuf->ra = ra;
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index c657bec6d95..bb1d58eb398 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -256,7 +256,7 @@ xfs_dir_cilookup_result(
!(args->op_flags & XFS_DA_OP_CILOOKUP))
return EEXIST;
- args->value = kmem_alloc(len, KM_MAYFAIL);
+ args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL);
if (!args->value)
return ENOMEM;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index cbd451bb484..2d0b3e1da9e 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -167,17 +167,25 @@ xfs_growfs_data_private(
new = nb - mp->m_sb.sb_dblocks;
oagcount = mp->m_sb.sb_agcount;
if (nagcount > oagcount) {
+ void *new_perag, *old_perag;
+
xfs_filestream_flush(mp);
+
+ new_perag = kmem_zalloc(sizeof(xfs_perag_t) * nagcount,
+ KM_MAYFAIL);
+ if (!new_perag)
+ return XFS_ERROR(ENOMEM);
+
down_write(&mp->m_peraglock);
- mp->m_perag = kmem_realloc(mp->m_perag,
- sizeof(xfs_perag_t) * nagcount,
- sizeof(xfs_perag_t) * oagcount,
- KM_SLEEP);
- memset(&mp->m_perag[oagcount], 0,
- (nagcount - oagcount) * sizeof(xfs_perag_t));
+ memcpy(new_perag, mp->m_perag, sizeof(xfs_perag_t) * oagcount);
+ old_perag = mp->m_perag;
+ mp->m_perag = new_perag;
+
mp->m_flags |= XFS_MOUNT_32BITINODES;
nagimax = xfs_initialize_perag(mp, nagcount);
up_write(&mp->m_peraglock);
+
+ kmem_free(old_perag);
}
tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS);
tp->t_flags |= XFS_TRANS_RESERVE;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 76c540f719e..ecbf8b4d2e2 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -64,6 +64,10 @@ xfs_inode_alloc(
ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
if (!ip)
return NULL;
+ if (inode_init_always(mp->m_super, VFS_I(ip))) {
+ kmem_zone_free(xfs_inode_zone, ip);
+ return NULL;
+ }
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -83,7 +87,6 @@ xfs_inode_alloc(
memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
ip->i_size = 0;
ip->i_new_size = 0;
- xfs_inode_init_acls(ip);
/*
* Initialize inode's trace buffers.
@@ -106,17 +109,6 @@ xfs_inode_alloc(
#ifdef XFS_DIR2_TRACE
ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
#endif
- /*
- * Now initialise the VFS inode. We do this after the xfs_inode
- * initialisation as internal failures will result in ->destroy_inode
- * being called and that will pass down through the reclaim path and
- * free the XFS inode. This path requires the XFS inode to already be
- * initialised. Hence if this call fails, the xfs_inode has already
- * been freed and we should not reference it at all in the error
- * handling.
- */
- if (!inode_init_always(mp->m_super, VFS_I(ip)))
- return NULL;
/* prevent anyone from using this yet */
VFS_I(ip)->i_state = I_NEW|I_LOCK;
@@ -124,6 +116,71 @@ xfs_inode_alloc(
return ip;
}
+STATIC void
+xfs_inode_free(
+ struct xfs_inode *ip)
+{
+ switch (ip->i_d.di_mode & S_IFMT) {
+ case S_IFREG:
+ case S_IFDIR:
+ case S_IFLNK:
+ xfs_idestroy_fork(ip, XFS_DATA_FORK);
+ break;
+ }
+
+ if (ip->i_afp)
+ xfs_idestroy_fork(ip, XFS_ATTR_FORK);
+
+#ifdef XFS_INODE_TRACE
+ ktrace_free(ip->i_trace);
+#endif
+#ifdef XFS_BMAP_TRACE
+ ktrace_free(ip->i_xtrace);
+#endif
+#ifdef XFS_BTREE_TRACE
+ ktrace_free(ip->i_btrace);
+#endif
+#ifdef XFS_RW_TRACE
+ ktrace_free(ip->i_rwtrace);
+#endif
+#ifdef XFS_ILOCK_TRACE
+ ktrace_free(ip->i_lock_trace);
+#endif
+#ifdef XFS_DIR2_TRACE
+ ktrace_free(ip->i_dir_trace);
+#endif
+
+ if (ip->i_itemp) {
+ /*
+ * Only if we are shutting down the fs will we see an
+ * inode still in the AIL. If it is there, we should remove
+ * it to prevent a use-after-free from occurring.
+ */
+ xfs_log_item_t *lip = &ip->i_itemp->ili_item;
+ struct xfs_ail *ailp = lip->li_ailp;
+
+ ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
+ XFS_FORCED_SHUTDOWN(ip->i_mount));
+ if (lip->li_flags & XFS_LI_IN_AIL) {
+ spin_lock(&ailp->xa_lock);
+ if (lip->li_flags & XFS_LI_IN_AIL)
+ xfs_trans_ail_delete(ailp, lip);
+ else
+ spin_unlock(&ailp->xa_lock);
+ }
+ xfs_inode_item_destroy(ip);
+ ip->i_itemp = NULL;
+ }
+
+ /* asserts to verify all state is correct here */
+ ASSERT(atomic_read(&ip->i_iocount) == 0);
+ ASSERT(atomic_read(&ip->i_pincount) == 0);
+ ASSERT(!spin_is_locked(&ip->i_flags_lock));
+ ASSERT(completion_done(&ip->i_flush));
+
+ kmem_zone_free(xfs_inode_zone, ip);
+}
+
/*
* Check the validity of the inode we just found it the cache
*/
@@ -134,80 +191,82 @@ xfs_iget_cache_hit(
int flags,
int lock_flags) __releases(pag->pag_ici_lock)
{
+ struct inode *inode = VFS_I(ip);
struct xfs_mount *mp = ip->i_mount;
- int error = EAGAIN;
+ int error;
+
+ spin_lock(&ip->i_flags_lock);
/*
- * If INEW is set this inode is being set up
- * If IRECLAIM is set this inode is being torn down
- * Pause and try again.
+ * If we are racing with another cache hit that is currently
+ * instantiating this inode or currently recycling it out of
+ * reclaimabe state, wait for the initialisation to complete
+ * before continuing.
+ *
+ * XXX(hch): eventually we should do something equivalent to
+ * wait_on_inode to wait for these flags to be cleared
+ * instead of polling for it.
*/
- if (xfs_iflags_test(ip, (XFS_INEW|XFS_IRECLAIM))) {
+ if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
XFS_STATS_INC(xs_ig_frecycle);
+ error = EAGAIN;
goto out_error;
}
- /* If IRECLAIMABLE is set, we've torn down the vfs inode part */
- if (xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
-
- /*
- * If lookup is racing with unlink, then we should return an
- * error immediately so we don't remove it from the reclaim
- * list and potentially leak the inode.
- */
- if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
- error = ENOENT;
- goto out_error;
- }
+ /*
+ * If lookup is racing with unlink return an error immediately.
+ */
+ if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+ error = ENOENT;
+ goto out_error;
+ }
+ /*
+ * If IRECLAIMABLE is set, we've torn down the VFS inode already.
+ * Need to carefully get it back into useable state.
+ */
+ if (ip->i_flags & XFS_IRECLAIMABLE) {
xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
/*
- * We need to re-initialise the VFS inode as it has been
- * 'freed' by the VFS. Do this here so we can deal with
- * errors cleanly, then tag it so it can be set up correctly
- * later.
+ * We need to set XFS_INEW atomically with clearing the
+ * reclaimable tag so that we do have an indicator of the
+ * inode still being initialized.
*/
- if (!inode_init_always(mp->m_super, VFS_I(ip))) {
- error = ENOMEM;
- goto out_error;
- }
+ ip->i_flags |= XFS_INEW;
+ ip->i_flags &= ~XFS_IRECLAIMABLE;
+ __xfs_inode_clear_reclaim_tag(mp, pag, ip);
- /*
- * We must set the XFS_INEW flag before clearing the
- * XFS_IRECLAIMABLE flag so that if a racing lookup does
- * not find the XFS_IRECLAIMABLE above but has the igrab()
- * below succeed we can safely check XFS_INEW to detect
- * that this inode is still being initialised.
- */
- xfs_iflags_set(ip, XFS_INEW);
- xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
+ spin_unlock(&ip->i_flags_lock);
+ read_unlock(&pag->pag_ici_lock);
- /* clear the radix tree reclaim flag as well. */
- __xfs_inode_clear_reclaim_tag(mp, pag, ip);
- } else if (!igrab(VFS_I(ip))) {
+ error = -inode_init_always(mp->m_super, inode);
+ if (error) {
+ /*
+ * Re-initializing the inode failed, and we are in deep
+ * trouble. Try to re-add it to the reclaim list.
+ */
+ read_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+
+ ip->i_flags &= ~XFS_INEW;
+ ip->i_flags |= XFS_IRECLAIMABLE;
+ __xfs_inode_set_reclaim_tag(pag, ip);
+ goto out_error;
+ }
+ inode->i_state = I_LOCK|I_NEW;
+ } else {
/* If the VFS inode is being torn down, pause and try again. */
- XFS_STATS_INC(xs_ig_frecycle);
- goto out_error;
- } else if (xfs_iflags_test(ip, XFS_INEW)) {
- /*
- * We are racing with another cache hit that is
- * currently recycling this inode out of the XFS_IRECLAIMABLE
- * state. Wait for the initialisation to complete before
- * continuing.
- */
- wait_on_inode(VFS_I(ip));
- }
+ if (!igrab(inode)) {
+ error = EAGAIN;
+ goto out_error;
+ }
- if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
- error = ENOENT;
- iput(VFS_I(ip));
- goto out_error;
+ /* We've got a live one. */
+ spin_unlock(&ip->i_flags_lock);
+ read_unlock(&pag->pag_ici_lock);
}
- /* We've got a live one. */
- read_unlock(&pag->pag_ici_lock);
-
if (lock_flags != 0)
xfs_ilock(ip, lock_flags);
@@ -217,6 +276,7 @@ xfs_iget_cache_hit(
return 0;
out_error:
+ spin_unlock(&ip->i_flags_lock);
read_unlock(&pag->pag_ici_lock);
return error;
}
@@ -300,7 +360,8 @@ out_preload_end:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
- xfs_destroy_inode(ip);
+ __destroy_inode(VFS_I(ip));
+ xfs_inode_free(ip);
return error;
}
@@ -505,63 +566,7 @@ xfs_ireclaim(
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- switch (ip->i_d.di_mode & S_IFMT) {
- case S_IFREG:
- case S_IFDIR:
- case S_IFLNK:
- xfs_idestroy_fork(ip, XFS_DATA_FORK);
- break;
- }
-
- if (ip->i_afp)
- xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
-#ifdef XFS_INODE_TRACE
- ktrace_free(ip->i_trace);
-#endif
-#ifdef XFS_BMAP_TRACE
- ktrace_free(ip->i_xtrace);
-#endif
-#ifdef XFS_BTREE_TRACE
- ktrace_free(ip->i_btrace);
-#endif
-#ifdef XFS_RW_TRACE
- ktrace_free(ip->i_rwtrace);
-#endif
-#ifdef XFS_ILOCK_TRACE
- ktrace_free(ip->i_lock_trace);
-#endif
-#ifdef XFS_DIR2_TRACE
- ktrace_free(ip->i_dir_trace);
-#endif
- if (ip->i_itemp) {
- /*
- * Only if we are shutting down the fs will we see an
- * inode still in the AIL. If it is there, we should remove
- * it to prevent a use-after-free from occurring.
- */
- xfs_log_item_t *lip = &ip->i_itemp->ili_item;
- struct xfs_ail *ailp = lip->li_ailp;
-
- ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
- XFS_FORCED_SHUTDOWN(ip->i_mount));
- if (lip->li_flags & XFS_LI_IN_AIL) {
- spin_lock(&ailp->xa_lock);
- if (lip->li_flags & XFS_LI_IN_AIL)
- xfs_trans_ail_delete(ailp, lip);
- else
- spin_unlock(&ailp->xa_lock);
- }
- xfs_inode_item_destroy(ip);
- ip->i_itemp = NULL;
- }
- /* asserts to verify all state is correct here */
- ASSERT(atomic_read(&ip->i_iocount) == 0);
- ASSERT(atomic_read(&ip->i_pincount) == 0);
- ASSERT(!spin_is_locked(&ip->i_flags_lock));
- ASSERT(completion_done(&ip->i_flush));
- xfs_inode_clear_acls(ip);
- kmem_zone_free(xfs_inode_zone, ip);
+ xfs_inode_free(ip);
}
/*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1f22d65fed0..da428b3fe0f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -343,6 +343,16 @@ xfs_iformat(
return XFS_ERROR(EFSCORRUPTED);
}
+ if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
+ !ip->i_mount->m_rtdev_targp)) {
+ xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+ "corrupt dinode %Lu, has realtime flag set.",
+ ip->i_ino);
+ XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
+ XFS_ERRLEVEL_LOW, ip->i_mount, dip);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 77016702938..65f24a3cc99 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -273,11 +273,6 @@ typedef struct xfs_inode {
/* VFS inode */
struct inode i_vnode; /* embedded VFS inode */
-#ifdef CONFIG_XFS_POSIX_ACL
- struct posix_acl *i_acl;
- struct posix_acl *i_default_acl;
-#endif
-
/* Trace buffers per inode. */
#ifdef XFS_INODE_TRACE
struct ktrace *i_trace; /* general inode trace */
@@ -315,23 +310,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
}
/*
- * Get rid of a partially initialized inode.
- *
- * We have to go through destroy_inode to make sure allocations
- * from init_inode_always like the security data are undone.
- *
- * We mark the inode bad so that it takes the short cut in
- * the reclaim path instead of going through the flush path
- * which doesn't make sense for an inode that has never seen the
- * light of day.
- */
-static inline void xfs_destroy_inode(struct xfs_inode *ip)
-{
- make_bad_inode(VFS_I(ip));
- return destroy_inode(VFS_I(ip));
-}
-
-/*
* i_flags helper functions
*/
static inline void
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3750f04ede0..9dbdff3ea48 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3180,7 +3180,7 @@ try_again:
STATIC void
xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
{
- ASSERT(spin_is_locked(&log->l_icloglock));
+ assert_spin_locked(&log->l_icloglock);
if (iclog->ic_state == XLOG_STATE_ACTIVE) {
xlog_state_switch_iclogs(log, iclog, 0);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index c4eca5ed5da..492d75bae2b 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -538,7 +538,9 @@ xfs_readlink_bmap(
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
- bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0);
+ bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt),
+ XBF_LOCK | XBF_MAPPED |
+ XBF_DONT_BLOCK);
error = XFS_BUF_GETERROR(bp);
if (error) {
xfs_ioerror_alert("xfs_readlink",
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2024-11-27 10:15:34 +0000