#include "xfs_rw.h"
#include "xfs_error.h"
#include "xfs_utils.h"
-#include "xfs_dir2_trace.h"
#include "xfs_quota.h"
-#include "xfs_acl.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
+#include "xfs_trace.h"
kmem_zone_t *xfs_ifork_zone;
kmem_zone_t *xfs_inode_zone;
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:
case XFS_DINODE_FMT_LOCAL:
atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
size = be16_to_cpu(atp->hdr.totsize);
+
+ if (unlikely(size < sizeof(struct xfs_attr_sf_hdr))) {
+ xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+ "corrupt inode %Lu "
+ "(bad attr fork size %Ld).",
+ (unsigned long long) ip->i_ino,
+ (long long) size);
+ XFS_CORRUPTION_ERROR("xfs_iformat(8)",
+ XFS_ERRLEVEL_LOW,
+ ip->i_mount, dip);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+
error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, size);
break;
case XFS_DINODE_FMT_EXTENTS:
return 0;
}
-void
+STATIC void
xfs_dinode_from_disk(
xfs_icdinode_t *to,
xfs_dinode_t *from)
* around for a while. This helps to keep recently accessed
* meta-data in-core longer.
*/
- XFS_BUF_SET_REF(bp, XFS_INO_REF);
+ XFS_BUF_SET_REF(bp, XFS_INO_REF);
/*
* Use xfs_trans_brelse() to release the buffer containing the
* In that case the pages will still be in memory, but the inode size
* will never have been updated.
*/
-xfs_fsize_t
+STATIC xfs_fsize_t
xfs_file_last_byte(
xfs_inode_t *ip)
{
* necessary.
*/
if (ip->i_df.if_flags & XFS_IFEXTENTS) {
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmap_last_offset(NULL, ip, &last_block,
XFS_DATA_FORK);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error) {
last_block = 0;
}
return last_byte;
}
-#if defined(XFS_RW_TRACE)
-STATIC void
-xfs_itrunc_trace(
- int tag,
- xfs_inode_t *ip,
- int flag,
- xfs_fsize_t new_size,
- xfs_off_t toss_start,
- xfs_off_t toss_finish)
-{
- if (ip->i_rwtrace == NULL) {
- return;
- }
-
- ktrace_enter(ip->i_rwtrace,
- (void*)((long)tag),
- (void*)ip,
- (void*)(unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff),
- (void*)(unsigned long)(ip->i_d.di_size & 0xffffffff),
- (void*)((long)flag),
- (void*)(unsigned long)((new_size >> 32) & 0xffffffff),
- (void*)(unsigned long)(new_size & 0xffffffff),
- (void*)(unsigned long)((toss_start >> 32) & 0xffffffff),
- (void*)(unsigned long)(toss_start & 0xffffffff),
- (void*)(unsigned long)((toss_finish >> 32) & 0xffffffff),
- (void*)(unsigned long)(toss_finish & 0xffffffff),
- (void*)(unsigned long)current_cpu(),
- (void*)(unsigned long)current_pid(),
- (void*)NULL,
- (void*)NULL,
- (void*)NULL);
-}
-#else
-#define xfs_itrunc_trace(tag, ip, flag, new_size, toss_start, toss_finish)
-#endif
-
/*
* Start the truncation of the file to new_size. The new size
* must be smaller than the current size. This routine will
* direct I/O with the truncate operation. Also, because we hold
* the IOLOCK in exclusive mode, we prevent new direct I/Os from being
* started until the truncate completes and drops the lock. Essentially,
- * the vn_iowait() call forms an I/O barrier that provides strict ordering
- * between direct I/Os and the truncate operation.
+ * the xfs_ioend_wait() call forms an I/O barrier that provides strict
+ * ordering between direct I/Os and the truncate operation.
*
* The flags parameter can have either the value XFS_ITRUNC_DEFINITE
* or XFS_ITRUNC_MAYBE. The XFS_ITRUNC_MAYBE value should be used
/* wait for the completion of any pending DIOs */
if (new_size == 0 || new_size < ip->i_size)
- vn_iowait(ip);
+ xfs_ioend_wait(ip);
/*
* Call toss_pages or flushinval_pages to get rid of pages
return 0;
}
last_byte = xfs_file_last_byte(ip);
- xfs_itrunc_trace(XFS_ITRUNC_START, ip, flags, new_size, toss_start,
- last_byte);
+ trace_xfs_itruncate_start(ip, flags, new_size, toss_start, last_byte);
if (last_byte > toss_start) {
if (flags & XFS_ITRUNC_DEFINITE) {
xfs_tosspages(ip, toss_start,
new_size = 0LL;
}
first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
- xfs_itrunc_trace(XFS_ITRUNC_FINISH1, ip, 0, new_size, 0, 0);
+ trace_xfs_itruncate_finish_start(ip, new_size);
+
/*
* The first thing we do is set the size to new_size permanently
* on disk. This way we don't have to worry about anyone ever
* in this file with garbage in them once recovery
* runs.
*/
- XFS_BMAP_INIT(&free_list, &first_block);
+ xfs_bmap_init(&free_list, &first_block);
error = xfs_bunmapi(ntp, ip,
first_unmap_block, unmap_len,
- XFS_BMAPI_AFLAG(fork) |
+ xfs_bmapi_aflag(fork) |
(sync ? 0 : XFS_BMAPI_ASYNC),
XFS_ITRUNC_MAX_EXTENTS,
&first_block, &free_list,
ASSERT((new_size != 0) ||
(fork == XFS_ATTR_FORK) ||
(ip->i_d.di_nextents == 0));
- xfs_itrunc_trace(XFS_ITRUNC_FINISH2, ip, 0, new_size, 0, 0);
+ trace_xfs_itruncate_finish_end(ip, new_size);
return 0;
}
}
/*
- * This is called free all the memory associated with an inode.
- * It must free the inode itself and any buffers allocated for
- * if_extents/if_data and if_broot. It must also free the lock
- * associated with the inode.
- *
- * Note: because we don't initialise everything on reallocation out
- * of the zone, we must ensure we nullify everything correctly before
- * freeing the structure.
- */
-void
-xfs_idestroy(
- xfs_inode_t *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);
-}
-
-
-/*
* Increment the pin count of the given buffer.
* This value is protected by ipinlock spinlock in the mount structure.
*/
for (i = 0; i < nrecs; i++) {
xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
start_block = xfs_bmbt_get_startblock(ep);
- if (ISNULLSTARTBLOCK(start_block)) {
+ if (isnullstartblock(start_block)) {
/*
* It's a delayed allocation extent, so skip it.
*/
XFS_BUF_CLR_BDSTRAT_FUNC(bp);
XFS_BUF_UNDONE(bp);
XFS_BUF_STALE(bp);
- XFS_BUF_SHUT(bp);
XFS_BUF_ERROR(bp,EIO);
xfs_biodone(bp);
} else {
mp = ip->i_mount;
/*
- * If the inode isn't dirty, then just release the inode
- * flush lock and do nothing.
+ * If the inode isn't dirty, then just release the inode flush lock and
+ * do nothing. Treat stale inodes the same; we cannot rely on the
+ * backing buffer remaining stale in cache for the remaining life of
+ * the stale inode and so xfs_itobp() below may give us a buffer that
+ * no longer contains inodes below. Doing this stale check here also
+ * avoids forcing the log on pinned, stale inodes.
*/
- if (xfs_inode_clean(ip)) {
+ if (xfs_inode_clean(ip) || xfs_iflags_test(ip, XFS_ISTALE)) {
xfs_ifunlock(ip);
return 0;
}
SYNCHRONIZE();
/*
- * Make sure to get the latest atime from the Linux inode.
+ * Make sure to get the latest timestamps from the Linux inode.
*/
- xfs_synchronize_atime(ip);
+ xfs_synchronize_times(ip);
if (XFS_TEST_ERROR(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC,
mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
return XFS_ERROR(EFSCORRUPTED);
}
-
-
-#ifdef XFS_ILOCK_TRACE
-ktrace_t *xfs_ilock_trace_buf;
-
-void
-xfs_ilock_trace(xfs_inode_t *ip, int lock, unsigned int lockflags, inst_t *ra)
-{
- ktrace_enter(ip->i_lock_trace,
- (void *)ip,
- (void *)(unsigned long)lock, /* 1 = LOCK, 3=UNLOCK, etc */
- (void *)(unsigned long)lockflags, /* XFS_ILOCK_EXCL etc */
- (void *)ra, /* caller of ilock */
- (void *)(unsigned long)current_cpu(),
- (void *)(unsigned long)current_pid(),
- NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL);
-}
-#endif
-
/*
* Return a pointer to the extent record at file index idx.
*/
*/
void
xfs_iext_insert(
- xfs_ifork_t *ifp, /* inode fork pointer */
+ xfs_inode_t *ip, /* incore inode pointer */
xfs_extnum_t idx, /* starting index of new items */
xfs_extnum_t count, /* number of inserted items */
- xfs_bmbt_irec_t *new) /* items to insert */
+ xfs_bmbt_irec_t *new, /* items to insert */
+ int state) /* type of extent conversion */
{
+ xfs_ifork_t *ifp = (state & BMAP_ATTRFORK) ? ip->i_afp : &ip->i_df;
xfs_extnum_t i; /* extent record index */
+ trace_xfs_iext_insert(ip, idx, new, state, _RET_IP_);
+
ASSERT(ifp->if_flags & XFS_IFEXTENTS);
xfs_iext_add(ifp, idx, count);
for (i = idx; i < idx + count; i++, new++)
*/
void
xfs_iext_remove(
- xfs_ifork_t *ifp, /* inode fork pointer */
+ xfs_inode_t *ip, /* incore inode pointer */
xfs_extnum_t idx, /* index to begin removing exts */
- int ext_diff) /* number of extents to remove */
+ int ext_diff, /* number of extents to remove */
+ int state) /* type of extent conversion */
{
+ xfs_ifork_t *ifp = (state & BMAP_ATTRFORK) ? ip->i_afp : &ip->i_df;
xfs_extnum_t nextents; /* number of extents in file */
int new_size; /* size of extents after removal */
+ trace_xfs_iext_remove(ip, idx, state, _RET_IP_);
+
ASSERT(ext_diff > 0);
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
new_size = (nextents - ext_diff) * sizeof(xfs_bmbt_rec_t);
/*
* Resize an extent indirection array to new_size bytes.
*/
-void
+STATIC void
xfs_iext_realloc_indirect(
xfs_ifork_t *ifp, /* inode fork pointer */
int new_size) /* new indirection array size */
/*
* Switch from indirection array to linear (direct) extent allocations.
*/
-void
+STATIC void
xfs_iext_indirect_to_direct(
xfs_ifork_t *ifp) /* inode fork pointer */
{