diff options
Diffstat (limited to 'fs/xfs/linux-2.6')
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_acl.c | 4 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_buf.h | 1 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_discard.c | 4 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_export.c | 8 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_file.c | 34 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_iops.c | 16 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_super.c | 54 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_sync.c | 48 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_sync.h | 2 |
9 files changed, 108 insertions, 63 deletions
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 39f4f80..f86e034 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -39,9 +39,11 @@ xfs_acl_from_disk(struct xfs_acl *aclp) struct posix_acl_entry *acl_e; struct posix_acl *acl; struct xfs_acl_entry *ace; - int count, i; + unsigned int count, i; count = be32_to_cpu(aclp->acl_cnt); + if (count > XFS_ACL_MAX_ENTRIES) + return ERR_PTR(-EFSCORRUPTED); acl = posix_acl_alloc(count, GFP_KERNEL); if (!acl) diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index 50a7d5f..36d6ee4 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -346,7 +346,6 @@ extern struct list_head *xfs_get_buftarg_list(void); #define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) -#define xfs_binval(buftarg) xfs_flush_buftarg(buftarg, 1) #define XFS_bflush(buftarg) xfs_flush_buftarg(buftarg, 1) #endif /* __XFS_BUF_H__ */ diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c index 244e797..572494f 100644 --- a/fs/xfs/linux-2.6/xfs_discard.c +++ b/fs/xfs/linux-2.6/xfs_discard.c @@ -68,7 +68,7 @@ xfs_trim_extents( * Look up the longest btree in the AGF and start with it. */ error = xfs_alloc_lookup_le(cur, 0, - XFS_BUF_TO_AGF(agbp)->agf_longest, &i); + be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i); if (error) goto out_del_cursor; @@ -84,7 +84,7 @@ xfs_trim_extents( if (error) goto out_del_cursor; XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor); - ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest); + ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest)); /* * Too small? Give up. diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index f4f878f..fed3f3c 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -98,22 +98,22 @@ xfs_fs_encode_fh( switch (fileid_type) { case FILEID_INO32_GEN_PARENT: spin_lock(&dentry->d_lock); - fid->i32.parent_ino = dentry->d_parent->d_inode->i_ino; + fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino; fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation; spin_unlock(&dentry->d_lock); /*FALLTHRU*/ case FILEID_INO32_GEN: - fid->i32.ino = inode->i_ino; + fid->i32.ino = XFS_I(inode)->i_ino; fid->i32.gen = inode->i_generation; break; case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG: spin_lock(&dentry->d_lock); - fid64->parent_ino = dentry->d_parent->d_inode->i_ino; + fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino; fid64->parent_gen = dentry->d_parent->d_inode->i_generation; spin_unlock(&dentry->d_lock); /*FALLTHRU*/ case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG: - fid64->ino = inode->i_ino; + fid64->ino = XFS_I(inode)->i_ino; fid64->gen = inode->i_generation; break; } diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 7f782af..b679198 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -309,7 +309,19 @@ xfs_file_aio_read( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if (unlikely(ioflags & IO_ISDIRECT)) { + /* + * Locking is a bit tricky here. If we take an exclusive lock + * for direct IO, we effectively serialise all new concurrent + * read IO to this file and block it behind IO that is currently in + * progress because IO in progress holds the IO lock shared. We only + * need to hold the lock exclusive to blow away the page cache, so + * only take lock exclusively if the page cache needs invalidation. + * This allows the normal direct IO case of no page cache pages to + * proceeed concurrently without serialisation. + */ + xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); + if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) { + xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); if (inode->i_mapping->nrpages) { @@ -322,8 +334,7 @@ xfs_file_aio_read( } } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); - } else - xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); + } trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags); @@ -658,6 +669,7 @@ xfs_file_aio_write_checks( xfs_fsize_t new_size; int error = 0; + xfs_rw_ilock(ip, XFS_ILOCK_EXCL); error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode)); if (error) { xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock); @@ -749,14 +761,24 @@ xfs_file_dio_aio_write( *iolock = XFS_IOLOCK_EXCL; else *iolock = XFS_IOLOCK_SHARED; - xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock); + xfs_rw_ilock(ip, *iolock); ret = xfs_file_aio_write_checks(file, &pos, &count, iolock); if (ret) return ret; + /* + * Recheck if there are cached pages that need invalidate after we got + * the iolock to protect against other threads adding new pages while + * we were waiting for the iolock. + */ + if (mapping->nrpages && *iolock == XFS_IOLOCK_SHARED) { + xfs_rw_iunlock(ip, *iolock); + *iolock = XFS_IOLOCK_EXCL; + xfs_rw_ilock(ip, *iolock); + } + if (mapping->nrpages) { - WARN_ON(*iolock != XFS_IOLOCK_EXCL); ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1, FI_REMAPF_LOCKED); if (ret) @@ -801,7 +823,7 @@ xfs_file_buffered_aio_write( size_t count = ocount; *iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock); + xfs_rw_ilock(ip, *iolock); ret = xfs_file_aio_write_checks(file, &pos, &count, iolock); if (ret) diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index d44d92c..f5b697b 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -69,9 +69,8 @@ xfs_synchronize_times( } /* - * If the linux inode is valid, mark it dirty. - * Used when committing a dirty inode into a transaction so that - * the inode will get written back by the linux code + * If the linux inode is valid, mark it dirty, else mark the dirty state + * in the XFS inode to make sure we pick it up when reclaiming the inode. */ void xfs_mark_inode_dirty_sync( @@ -81,6 +80,10 @@ xfs_mark_inode_dirty_sync( if (!(inode->i_state & (I_WILL_FREE|I_FREEING))) mark_inode_dirty_sync(inode); + else { + barrier(); + ip->i_update_core = 1; + } } void @@ -91,6 +94,11 @@ xfs_mark_inode_dirty( if (!(inode->i_state & (I_WILL_FREE|I_FREEING))) mark_inode_dirty(inode); + else { + barrier(); + ip->i_update_core = 1; + } + } /* @@ -456,7 +464,7 @@ xfs_vn_getattr( trace_xfs_getattr(ip); if (XFS_FORCED_SHUTDOWN(mp)) - return XFS_ERROR(EIO); + return -XFS_ERROR(EIO); stat->size = XFS_ISIZE(ip); stat->dev = inode->i_sb->s_dev; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 347cae9..e6ac98c 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -871,43 +871,6 @@ xfs_fs_dirty_inode( } STATIC int -xfs_log_inode( - struct xfs_inode *ip) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_trans *tp; - int error; - - xfs_iunlock(ip, XFS_ILOCK_SHARED); - tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); - error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0); - - if (error) { - xfs_trans_cancel(tp, 0); - /* we need to return with the lock hold shared */ - xfs_ilock(ip, XFS_ILOCK_SHARED); - return error; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - - /* - * Note - it's possible that we might have pushed ourselves out of the - * way during trans_reserve which would flush the inode. But there's - * no guarantee that the inode buffer has actually gone out yet (it's - * delwri). Plus the buffer could be pinned anyway if it's part of - * an inode in another recent transaction. So we play it safe and - * fire off the transaction anyway. - */ - xfs_trans_ijoin(tp, ip); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - error = xfs_trans_commit(tp, 0); - xfs_ilock_demote(ip, XFS_ILOCK_EXCL); - - return error; -} - -STATIC int xfs_fs_write_inode( struct inode *inode, struct writeback_control *wbc) @@ -919,9 +882,9 @@ xfs_fs_write_inode( trace_xfs_write_inode(ip); if (XFS_FORCED_SHUTDOWN(mp)) - return XFS_ERROR(EIO); + return -XFS_ERROR(EIO); - if (wbc->sync_mode == WB_SYNC_ALL) { + if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) { /* * Make sure the inode has made it it into the log. Instead * of forcing it all the way to stable storage using a @@ -930,13 +893,14 @@ xfs_fs_write_inode( * of synchronous log foces dramatically. */ xfs_ioend_wait(ip); - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (ip->i_update_core) { - error = xfs_log_inode(ip); - if (error) - goto out_unlock; - } + error = xfs_log_dirty_inode(ip, NULL, 0); + if (error) + goto out; + return 0; } else { + if (!ip->i_update_core) + return 0; + /* * We make this non-blocking if the inode is contended, return * EAGAIN to indicate to the caller that they did not succeed. diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 8ecad5f..2f277a0 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -336,6 +336,32 @@ xfs_sync_fsdata( return xfs_bwrite(mp, bp); } +int +xfs_log_dirty_inode( + struct xfs_inode *ip, + struct xfs_perag *pag, + int flags) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + + if (!ip->i_update_core) + return 0; + + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return xfs_trans_commit(tp, 0); +} + /* * 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 @@ -365,6 +391,17 @@ xfs_quiesce_data( /* push and block till complete */ xfs_sync_data(mp, SYNC_WAIT); + + /* + * Log all pending size and timestamp updates. The vfs writeback + * code is supposed to do this, but due to its overagressive + * livelock detection it will skip inodes where appending writes + * were written out in the first non-blocking sync phase if their + * completion took long enough that it happened after taking the + * timestamp for the cut-off in the blocking phase. + */ + xfs_inode_ag_iterator(mp, xfs_log_dirty_inode, 0); + xfs_qm_sync(mp, SYNC_WAIT); /* write superblock and hoover up shutdown errors */ @@ -772,6 +809,17 @@ restart: if (!xfs_iflock_nowait(ip)) { if (!(sync_mode & SYNC_WAIT)) goto out; + + /* + * If we only have a single dirty inode in a cluster there is + * a fair chance that the AIL push may have pushed it into + * the buffer, but xfsbufd won't touch it until 30 seconds + * from now, and thus we will lock up here. + * + * Promote the inode buffer to the front of the delwri list + * and wake up xfsbufd now. + */ + xfs_promote_inode(ip); xfs_iflock(ip); } diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index e3a6ad2..ef5b2ce 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -42,6 +42,8 @@ void xfs_quiesce_attr(struct xfs_mount *mp); void xfs_flush_inodes(struct xfs_inode *ip); +int xfs_log_dirty_inode(struct xfs_inode *ip, struct xfs_perag *pag, int flags); + int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); |