1 files changed, 184 insertions, 35 deletions

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 77cb9f830ee4..fb0edf735483 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -23,6 +23,7 @@
 #include <linux/time.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -85,6 +86,7 @@ static const match_table_t tokens = {
         {Opt_locktable, "locktable=%s"},
         {Opt_hostdata, "hostdata=%s"},
         {Opt_spectator, "spectator"},
+        {Opt_spectator, "norecovery"},
         {Opt_ignore_local_fs, "ignore_local_fs"},
         {Opt_localflocks, "localflocks"},
         {Opt_localcaching, "localcaching"},
@@ -159,13 +161,13 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         args->ar_spectator = 1;
                         break;
                 case Opt_ignore_local_fs:
-                        args->ar_ignore_local_fs = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_localflocks:
                         args->ar_localflocks = 1;
                         break;
                 case Opt_localcaching:
-                        args->ar_localcaching = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_debug:
                         if (args->ar_errors == GFS2_ERRORS_PANIC) {
@@ -179,7 +181,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         args->ar_debug = 0;
                         break;
                 case Opt_upgrade:
-                        args->ar_upgrade = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_acl:
                         args->ar_posix_acl = 1;
@@ -342,15 +344,14 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
 {
         struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
         struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+        u64 size = i_size_read(jd->jd_inode);
 
-        if (ip->i_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
-            (ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
-                gfs2_consist_inode(ip);
+        if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30))
                 return -EIO;
-        }
-        jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
 
-        if (gfs2_write_alloc_required(ip, 0, ip->i_disksize)) {
+        jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
+
+        if (gfs2_write_alloc_required(ip, 0, size)) {
                 gfs2_consist_inode(ip);
                 return -EIO;
         }
@@ -657,7 +658,7 @@ out:
  * @sdp: the file system
  *
  * This function flushes data and meta data for all machines by
- * aquiring the transaction log exclusively.  All journals are
+ * acquiring the transaction log exclusively.  All journals are
  * ensured to be in a clean state as well.
  *
  * Returns: errno
@@ -700,11 +701,47 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
         mutex_unlock(&sdp->sd_freeze_lock);
 }
 
+void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
+{
+        struct gfs2_dinode *str = buf;
+
+        str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+        str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
+        str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
+        str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
+        str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+        str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
+        str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
+        str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+        str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
+        str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
+        str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
+        str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
+        str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
+        str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
+
+        str->di_goal_meta = cpu_to_be64(ip->i_goal);
+        str->di_goal_data = cpu_to_be64(ip->i_goal);
+        str->di_generation = cpu_to_be64(ip->i_generation);
+
+        str->di_flags = cpu_to_be32(ip->i_diskflags);
+        str->di_height = cpu_to_be16(ip->i_height);
+        str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
+                                             !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
+                                             GFS2_FORMAT_DE : 0);
+        str->di_depth = cpu_to_be16(ip->i_depth);
+        str->di_entries = cpu_to_be32(ip->i_entries);
+
+        str->di_eattr = cpu_to_be64(ip->i_eattr);
+        str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
+        str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
+        str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
+}
 
 /**
  * gfs2_write_inode - Make sure the inode is stable on the disk
  * @inode: The inode
- * @sync: synchronous write flag
+ * @wbc: The writeback control structure
  *
  * Returns: errno
  */
@@ -713,18 +750,24 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
         struct gfs2_sbd *sdp = GFS2_SB(inode);
+        struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
+        struct backing_dev_info *bdi = metamapping->backing_dev_info;
         struct gfs2_holder gh;
         struct buffer_head *bh;
         struct timespec atime;
         struct gfs2_dinode *di;
-        int ret = 0;
+        int ret = -EAGAIN;
+        int unlock_required = 0;
 
-        /* Check this is a "normal" inode, etc */
+        /* Skip timestamp update, if this is from a memalloc */
         if (current->flags & PF_MEMALLOC)
-                return 0;
-        ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-        if (ret)
                 goto do_flush;
+        if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+                ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+                if (ret)
+                        goto do_flush;
+                unlock_required = 1;
+        }
         ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
         if (ret)
                 goto do_unlock;
@@ -741,10 +784,18 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
         }
         gfs2_trans_end(sdp);
 do_unlock:
-        gfs2_glock_dq_uninit(&gh);
+        if (unlock_required)
+                gfs2_glock_dq_uninit(&gh);
 do_flush:
         if (wbc->sync_mode == WB_SYNC_ALL)
                 gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+        filemap_fdatawrite(metamapping);
+        if (bdi->dirty_exceeded)
+                gfs2_ail1_flush(sdp, wbc);
+        if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
+                ret = filemap_fdatawait(metamapping);
+        if (ret)
+                mark_inode_dirty_sync(inode);
         return ret;
 }
 
@@ -857,7 +908,6 @@ restart:
         gfs2_clear_rgrpd(sdp);
         gfs2_jindex_free(sdp);
         /*  Take apart glock structures and buffer lists  */
-        invalidate_inodes(sdp->sd_vfs);
         gfs2_gl_hash_clear(sdp);
         /*  Unmount the locking protocol  */
         gfs2_lm_unmount(sdp);
@@ -875,8 +925,9 @@ restart:
 
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
-        if (wait && sb->s_fs_info)
-                gfs2_log_flush(sb->s_fs_info, NULL);
+        struct gfs2_sbd *sdp = sb->s_fs_info;
+        if (wait && sdp)
+                gfs2_log_flush(sdp, NULL);
         return 0;
 }
 
@@ -1129,9 +1180,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 
         /* Some flags must not be changed */
         if (args_neq(&args, &sdp->sd_args, spectator) ||
-            args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
             args_neq(&args, &sdp->sd_args, localflocks) ||
-            args_neq(&args, &sdp->sd_args, localcaching) ||
             args_neq(&args, &sdp->sd_args, meta))
                 return -EINVAL;
 
@@ -1234,16 +1283,10 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
                 seq_printf(s, ",hostdata=%s", args->ar_hostdata);
         if (args->ar_spectator)
                 seq_printf(s, ",spectator");
-        if (args->ar_ignore_local_fs)
-                seq_printf(s, ",ignore_local_fs");
         if (args->ar_localflocks)
                 seq_printf(s, ",localflocks");
-        if (args->ar_localcaching)
-                seq_printf(s, ",localcaching");
         if (args->ar_debug)
                 seq_printf(s, ",debug");
-        if (args->ar_upgrade)
-                seq_printf(s, ",upgrade");
         if (args->ar_posix_acl)
                 seq_printf(s, ",acl");
         if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
@@ -1317,7 +1360,92 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
         return 0;
 }
 
-/*
+static void gfs2_final_release_pages(struct gfs2_inode *ip)
+{
+        struct inode *inode = &ip->i_inode;
+        struct gfs2_glock *gl = ip->i_gl;
+
+        truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0);
+        truncate_inode_pages(&inode->i_data, 0);
+
+        if (atomic_read(&gl->gl_revokes) == 0) {
+                clear_bit(GLF_LFLUSH, &gl->gl_flags);
+                clear_bit(GLF_DIRTY, &gl->gl_flags);
+        }
+}
+
+static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
+{
+        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+        struct gfs2_alloc *al;
+        struct gfs2_rgrpd *rgd;
+        int error;
+
+        if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
+                gfs2_consist_inode(ip);
+                return -EIO;
+        }
+
+        al = gfs2_alloc_get(ip);
+        if (!al)
+                return -ENOMEM;
+
+        error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+        if (error)
+                goto out;
+
+        error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+        if (error)
+                goto out_qs;
+
+        rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+        if (!rgd) {
+                gfs2_consist_inode(ip);
+                error = -EIO;
+                goto out_rindex_relse;
+        }
+
+        error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
+                                   &al->al_rgd_gh);
+        if (error)
+                goto out_rindex_relse;
+
+        error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
+                                 sdp->sd_jdesc->jd_blocks);
+        if (error)
+                goto out_rg_gunlock;
+
+        gfs2_free_di(rgd, ip);
+
+        gfs2_final_release_pages(ip);
+
+        gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+        gfs2_glock_dq_uninit(&al->al_rgd_gh);
+out_rindex_relse:
+        gfs2_glock_dq_uninit(&al->al_ri_gh);
+out_qs:
+        gfs2_quota_unhold(ip);
+out:
+        gfs2_alloc_put(ip);
+        return error;
+}
+
+/**
+ * gfs2_evict_inode - Remove an inode from cache
+ * @inode: The inode to evict
+ *
+ * There are three cases to consider:
+ * 1. i_nlink == 0, we are final opener (and must deallocate)
+ * 2. i_nlink == 0, we are not the final opener (and cannot deallocate)
+ * 3. i_nlink > 0
+ *
+ * If the fs is read only, then we have to treat all cases as per #3
+ * since we are unable to do any deallocation. The inode will be
+ * deallocated by the next read/write node to attempt an allocation
+ * in the same resource group
+ *
  * We have to (at the moment) hold the inodes main lock to cover
  * the gap between unlocking the shared lock on the iopen lock and
  * taking the exclusive lock. I'd rather do a shared -> exclusive
@@ -1327,15 +1455,17 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 
 static void gfs2_evict_inode(struct inode *inode)
 {
-        struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+        struct super_block *sb = inode->i_sb;
+        struct gfs2_sbd *sdp = sb->s_fs_info;
         struct gfs2_inode *ip = GFS2_I(inode);
         struct gfs2_holder gh;
         int error;
 
-        if (inode->i_nlink)
+        if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
                 goto out;
 
-        error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+        /* Must not read inode block until block type has been verified */
+        error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
         if (unlikely(error)) {
                 gfs2_glock_dq_uninit(&ip->i_iopen_gh);
                 goto out;
@@ -1345,12 +1475,21 @@ static void gfs2_evict_inode(struct inode *inode)
         if (error)
                 goto out_truncate;
 
+        if (test_bit(GIF_INVALID, &ip->i_flags)) {
+                error = gfs2_inode_refresh(ip);
+                if (error)
+                        goto out_truncate;
+        }
+
+        ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
         gfs2_glock_dq_wait(&ip->i_iopen_gh);
         gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
         error = gfs2_glock_nq(&ip->i_iopen_gh);
         if (error)
                 goto out_truncate;
 
+        /* Case 1 starts here */
+
         if (S_ISDIR(inode->i_mode) &&
             (ip->i_diskflags & GFS2_DIF_EXHASH)) {
                 error = gfs2_dir_exhash_dealloc(ip);
@@ -1371,10 +1510,10 @@ static void gfs2_evict_inode(struct inode *inode)
         }
 
         error = gfs2_dinode_dealloc(ip);
-        if (error)
-                goto out_unlock;
+        goto out_unlock;
 
 out_truncate:
+        /* Case 2 starts here */
         error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
         if (error)
                 goto out_unlock;
@@ -1383,6 +1522,7 @@ out_truncate:
         gfs2_trans_end(sdp);
 
 out_unlock:
+        /* Error path for case 1 */
         if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
                 gfs2_glock_dq(&ip->i_iopen_gh);
         gfs2_holder_uninit(&ip->i_iopen_gh);
@@ -1390,10 +1530,12 @@ out_unlock:
         if (error && error != GLR_TRYFAILED && error != -EROFS)
                 fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
+        /* Case 3 starts here */
         truncate_inode_pages(&inode->i_data, 0);
         end_writeback(inode);
 
         ip->i_gl->gl_object = NULL;
+        gfs2_glock_add_to_lru(ip->i_gl);
         gfs2_glock_put(ip->i_gl);
         ip->i_gl = NULL;
         if (ip->i_iopen_gh.gh_gl) {
@@ -1414,11 +1556,18 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
         return &ip->i_inode;
 }
 
-static void gfs2_destroy_inode(struct inode *inode)
+static void gfs2_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(gfs2_inode_cachep, inode);
 }
 
+static void gfs2_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, gfs2_i_callback);
+}
+
 const struct super_operations gfs2_super_ops = {
         .alloc_inode            = gfs2_alloc_inode,
         .destroy_inode          = gfs2_destroy_inode,