37 files changed, 330 insertions, 214 deletions
diff --git a/fs/bio.c b/fs/bio.c
index 9298c65ad9c7..b96fc6ce4855 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -75,6 +75,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
        unsigned int sz = sizeof(struct bio) + extra_size;
        struct kmem_cache *slab = NULL;
        struct bio_slab *bslab, *new_bio_slabs;
+        unsigned int new_bio_slab_max;
        unsigned int i, entry = -1;
        mutex_lock(&bio_slab_lock);
@@ -97,12 +98,13 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
                goto out_unlock;
        if (bio_slab_nr == bio_slab_max && entry == -1) {
-                bio_slab_max <<= 1;
+                new_bio_slab_max = bio_slab_max << 1;
                new_bio_slabs = krealloc(bio_slabs,
-                                         bio_slab_max * sizeof(struct bio_slab),
+                                         new_bio_slab_max * sizeof(struct bio_slab),
                                         GFP_KERNEL);
                if (!new_bio_slabs)
                        goto out_unlock;
+                bio_slab_max = new_bio_slab_max;
                bio_slabs = new_bio_slabs;
        }
        if (entry == -1)
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 02ce90972d81..9349bb37a2fe 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -90,6 +90,8 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
                *max_len = handle_length;
                type = 255;
        }
+        if (dentry)
+                dput(dentry);
        return type;
 }
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index fc783e264420..0fb15bbbe43c 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -225,6 +225,13 @@ sid_to_str(struct cifs_sid *sidptr, char *sidstr)
 }
 static void
+cifs_copy_sid(struct cifs_sid *dst, const struct cifs_sid *src)
+{
+        memcpy(dst, src, sizeof(*dst));
+        dst->num_subauth = min_t(u8, src->num_subauth, NUM_SUBAUTHS);
+}
+static void
 id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr,
                struct cifs_sid_id **psidid, char *typestr)
 {
@@ -248,7 +255,7 @@ id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr,
                }
        }
-        memcpy(&(*psidid)->sid, sidptr, sizeof(struct cifs_sid));
+        cifs_copy_sid(&(*psidid)->sid, sidptr);
        (*psidid)->time = jiffies - (SID_MAP_RETRY + 1);
        (*psidid)->refcount = 0;
@@ -354,7 +361,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
         * any fields of the node after a reference is put .
         */
        if (test_bit(SID_ID_MAPPED, &psidid->state)) {
-                memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
+                cifs_copy_sid(ssid, &psidid->sid);
                psidid->time = jiffies; /* update ts for accessing */
                goto id_sid_out;
        }
@@ -370,14 +377,14 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
                if (IS_ERR(sidkey)) {
                        rc = -EINVAL;
                        cFYI(1, "%s: Can't map and id to a SID", __func__);
+                } else if (sidkey->datalen < sizeof(struct cifs_sid)) {
+                        rc = -EIO;
+                        cFYI(1, "%s: Downcall contained malformed key "
+                                "(datalen=%hu)", __func__, sidkey->datalen);
                } else {
                        lsid = (struct cifs_sid *)sidkey->payload.data;
-                        memcpy(&psidid->sid, lsid,
+                        cifs_copy_sid(&psidid->sid, lsid);
-                                sidkey->datalen < sizeof(struct cifs_sid) ?
+                        cifs_copy_sid(ssid, &psidid->sid);
-                                sidkey->datalen : sizeof(struct cifs_sid));
-                        memcpy(ssid, &psidid->sid,
-                                sidkey->datalen < sizeof(struct cifs_sid) ?
-                                sidkey->datalen : sizeof(struct cifs_sid));
                        set_bit(SID_ID_MAPPED, &psidid->state);
                        key_put(sidkey);
                        kfree(psidid->sidstr);
@@ -396,7 +403,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
                        return rc;
                }
                if (test_bit(SID_ID_MAPPED, &psidid->state))
-                        memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
+                        cifs_copy_sid(ssid, &psidid->sid);
                else
                        rc = -EINVAL;
        }
@@ -675,8 +682,6 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
 static void copy_sec_desc(const struct cifs_ntsd *pntsd,
                                struct cifs_ntsd *pnntsd, __u32 sidsoffset)
 {
-        int i;
        struct cifs_sid *owner_sid_ptr, *group_sid_ptr;
        struct cifs_sid *nowner_sid_ptr, *ngroup_sid_ptr;
@@ -692,26 +697,14 @@ static void copy_sec_desc(const struct cifs_ntsd *pntsd,
        owner_sid_ptr = (struct cifs_sid *)((char *)pntsd +
                                le32_to_cpu(pntsd->osidoffset));
        nowner_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset);
+        cifs_copy_sid(nowner_sid_ptr, owner_sid_ptr);
-        nowner_sid_ptr->revision = owner_sid_ptr->revision;
-        nowner_sid_ptr->num_subauth = owner_sid_ptr->num_subauth;
-        for (i = 0; i < 6; i++)
-                nowner_sid_ptr->authority[i] = owner_sid_ptr->authority[i];
-        for (i = 0; i < 5; i++)
-                nowner_sid_ptr->sub_auth[i] = owner_sid_ptr->sub_auth[i];
        /* copy group sid */
        group_sid_ptr = (struct cifs_sid *)((char *)pntsd +
                                le32_to_cpu(pntsd->gsidoffset));
        ngroup_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset +
                                        sizeof(struct cifs_sid));
+        cifs_copy_sid(ngroup_sid_ptr, group_sid_ptr);
-        ngroup_sid_ptr->revision = group_sid_ptr->revision;
-        ngroup_sid_ptr->num_subauth = group_sid_ptr->num_subauth;
-        for (i = 0; i < 6; i++)
-                ngroup_sid_ptr->authority[i] = group_sid_ptr->authority[i];
-        for (i = 0; i < 5; i++)
-                ngroup_sid_ptr->sub_auth[i] = group_sid_ptr->sub_auth[i];
        return;
 }
@@ -1120,8 +1113,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
                                kfree(nowner_sid_ptr);
                                return rc;
                        }
-                        memcpy(owner_sid_ptr, nowner_sid_ptr,
+                        cifs_copy_sid(owner_sid_ptr, nowner_sid_ptr);
-                                        sizeof(struct cifs_sid));
                        kfree(nowner_sid_ptr);
                        *aclflag = CIFS_ACL_OWNER;
                }
@@ -1139,8 +1131,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
                                kfree(ngroup_sid_ptr);
                                return rc;
                        }
-                        memcpy(group_sid_ptr, ngroup_sid_ptr,
+                        cifs_copy_sid(group_sid_ptr, ngroup_sid_ptr);
-                                        sizeof(struct cifs_sid));
                        kfree(ngroup_sid_ptr);
                        *aclflag = CIFS_ACL_GROUP;
                }
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 7c0a81283645..d3671f2acb29 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -398,7 +398,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
         * in network traffic in the other paths.
         */
        if (!(oflags & O_CREAT)) {
-                struct dentry *res = cifs_lookup(inode, direntry, 0);
+                struct dentry *res;
+                /*
+                 * Check for hashed negative dentry. We have already revalidated
+                 * the dentry and it is fine. No need to perform another lookup.
+                 */
+                if (!d_unhashed(direntry))
+                        return -ENOENT;
+                res = cifs_lookup(inode, direntry, 0);
                if (IS_ERR(res))
                        return PTR_ERR(res);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index da72250ddc1c..cd96649bfe62 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -346,7 +346,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p)
 /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
 static inline int ep_op_has_event(int op)
 {
-        return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD;
+        return op != EPOLL_CTL_DEL;
 }
 /* Initialize the poll safe wake up structure */
@@ -676,34 +676,6 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
        return 0;
 }
-/*
- * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item
- * had no event flags set, indicating that another thread may be currently
- * handling that item's events (in the case that EPOLLONESHOT was being
- * used). Otherwise a zero result indicates that the item has been disabled
- * from receiving events. A disabled item may be re-enabled via
- * EPOLL_CTL_MOD. Must be called with "mtx" held.
- */
-static int ep_disable(struct eventpoll *ep, struct epitem *epi)
-{
-        int result = 0;
-        unsigned long flags;
-        spin_lock_irqsave(&ep->lock, flags);
-        if (epi->event.events & ~EP_PRIVATE_BITS) {
-                if (ep_is_linked(&epi->rdllink))
-                        list_del_init(&epi->rdllink);
-                /* Ensure ep_poll_callback will not add epi back onto ready
-                   list: */
-                epi->event.events &= EP_PRIVATE_BITS;
-                }
-        else
-                result = -EBUSY;
-        spin_unlock_irqrestore(&ep->lock, flags);
-        return result;
-}
 static void ep_free(struct eventpoll *ep)
 {
        struct rb_node *rbp;
@@ -1048,6 +1020,8 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
        rb_insert_color(&epi->rbn, &ep->rbr);
 }
 #define PATH_ARR_SIZE 5
 /*
 * These are the number paths of length 1 to 5, that we are allowing to emanate
@@ -1813,12 +1787,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
                } else
                        error = -ENOENT;
                break;
-        case EPOLL_CTL_DISABLE:
-                if (epi)
-                        error = ep_disable(ep, epi);
-                else
-                        error = -ENOENT;
-                break;
        }
        mutex_unlock(&ep->mtx);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 4facdd29a350..3a100e7a62a8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -725,6 +725,10 @@ repeat_in_this_group:
                                   "inode=%lu", ino + 1);
                        continue;
                }
+                BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+                err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+                if (err)
+                        goto fail;
                ext4_lock_group(sb, group);
                ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
                ext4_unlock_group(sb, group);
@@ -738,6 +742,11 @@ repeat_in_this_group:
        goto out;
 got:
+        BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+        err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
+        if (err)
+                goto fail;
        /* We may have to initialize the block bitmap if it isn't already */
        if (ext4_has_group_desc_csum(sb) &&
            gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -771,11 +780,6 @@ got:
                        goto fail;
        }
-        BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-        err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
-        if (err)
-                goto fail;
        BUFFER_TRACE(group_desc_bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, group_desc_bh);
        if (err)
@@ -823,11 +827,6 @@ got:
        }
        ext4_unlock_group(sb, group);
-        BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
-        err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
-        if (err)
-                goto fail;
        BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
        err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
        if (err)
diff --git a/fs/file.c b/fs/file.c
index d3b5fa80b71b..708d997a7748 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -900,7 +900,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
                return __close_fd(files, fd);
        if (fd >= rlimit(RLIMIT_NOFILE))
-                return -EMFILE;
+                return -EBADF;
        spin_lock(&files->file_lock);
        err = expand_files(files, fd);
@@ -926,7 +926,7 @@ SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
                return -EINVAL;
        if (newfd >= rlimit(RLIMIT_NOFILE))
-                return -EMFILE;
+                return -EBADF;
        spin_lock(&files->file_lock);
        err = expand_files(files, newfd);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 0def0504afc1..e056b4ce4877 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -516,15 +516,13 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
                struct gfs2_holder i_gh;
                int error;
-                gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+                error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
-                error = gfs2_glock_nq(&i_gh);
+                                           &i_gh);
-                if (error == 0) {
-                        file_accessed(file);
-                        gfs2_glock_dq(&i_gh);
-                }
-                gfs2_holder_uninit(&i_gh);
                if (error)
                        return error;
+                /* grab lock to update inode */
+                gfs2_glock_dq_uninit(&i_gh);
+                file_accessed(file);
        }
        vma->vm_ops = &gfs2_vm_ops;
@@ -677,10 +675,8 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
        size_t writesize = iov_length(iov, nr_segs);
        struct dentry *dentry = file->f_dentry;
        struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
-        struct gfs2_sbd *sdp;
        int ret;
-        sdp = GFS2_SB(file->f_mapping->host);
        ret = gfs2_rs_alloc(ip);
        if (ret)
                return ret;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 8ff95a2d54ee..9ceccb1595a3 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -393,12 +393,10 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
        struct gfs2_meta_header *mh;
        struct gfs2_trans *tr;
-        lock_buffer(bd->bd_bh);
-        gfs2_log_lock(sdp);
        tr = current->journal_info;
        tr->tr_touched = 1;
        if (!list_empty(&bd->bd_list))
-                goto out;
+                return;
        set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
        set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
        mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
@@ -414,9 +412,6 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
        sdp->sd_log_num_buf++;
        list_add(&bd->bd_list, &sdp->sd_log_le_buf);
        tr->tr_num_buf_new++;
-out:
-        gfs2_log_unlock(sdp);
-        unlock_buffer(bd->bd_bh);
 }
 static void gfs2_check_magic(struct buffer_head *bh)
@@ -621,7 +616,6 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 {
-        struct gfs2_log_descriptor *ld;
        struct gfs2_meta_header *mh;
        unsigned int offset;
        struct list_head *head = &sdp->sd_log_le_revoke;
@@ -634,7 +628,6 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
        length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
        page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
-        ld = page_address(page);
        offset = sizeof(struct gfs2_log_descriptor);
        list_for_each_entry(bd, head, bd_list) {
@@ -777,12 +770,10 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
        struct address_space *mapping = bd->bd_bh->b_page->mapping;
        struct gfs2_inode *ip = GFS2_I(mapping->host);
-        lock_buffer(bd->bd_bh);
-        gfs2_log_lock(sdp);
        if (tr)
                tr->tr_touched = 1;
        if (!list_empty(&bd->bd_list))
-                goto out;
+                return;
        set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
        set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
        if (gfs2_is_jdata(ip)) {
@@ -793,9 +784,6 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
        } else {
                list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered);
        }
-out:
-        gfs2_log_unlock(sdp);
-        unlock_buffer(bd->bd_bh);
 }
 /**
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 40c4b0d42fa8..c5af8e18f27a 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -497,8 +497,11 @@ int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid)
        struct gfs2_quota_data **qd;
        int error;
-        if (ip->i_res == NULL)
+        if (ip->i_res == NULL) {
-                gfs2_rs_alloc(ip);
+                error = gfs2_rs_alloc(ip);
+                if (error)
+                        return error;
+        }
        qd = ip->i_res->rs_qa_qd;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 3cc402ce6fea..38fe18f2f055 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -553,7 +553,6 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd)
 */
 int gfs2_rs_alloc(struct gfs2_inode *ip)
 {
-        int error = 0;
        struct gfs2_blkreserv *res;
        if (ip->i_res)
@@ -561,7 +560,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip)
        res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
        if (!res)
-                error = -ENOMEM;
+                return -ENOMEM;
        RB_CLEAR_NODE(&res->rs_node);
@@ -571,7 +570,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip)
        else
                ip->i_res = res;
        up_write(&ip->i_rw_mutex);
-        return error;
+        return 0;
 }
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
@@ -1263,7 +1262,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
        int ret = 0;
        u64 amt;
        u64 trimmed = 0;
+        u64 start, end, minlen;
        unsigned int x;
+        unsigned bs_shift = sdp->sd_sb.sb_bsize_shift;
        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;
@@ -1271,19 +1272,25 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
        if (!blk_queue_discard(q))
                return -EOPNOTSUPP;
-        if (argp == NULL) {
+        if (copy_from_user(&r, argp, sizeof(r)))
-                r.start = 0;
-                r.len = ULLONG_MAX;
-                r.minlen = 0;
-        } else if (copy_from_user(&r, argp, sizeof(r)))
                return -EFAULT;
        ret = gfs2_rindex_update(sdp);
        if (ret)
                return ret;
-        rgd = gfs2_blk2rgrpd(sdp, r.start, 0);
+        start = r.start >> bs_shift;
-        rgd_end = gfs2_blk2rgrpd(sdp, r.start + r.len, 0);
+        end = start + (r.len >> bs_shift);
+        minlen = max_t(u64, r.minlen,
+                       q->limits.discard_granularity) >> bs_shift;
+        rgd = gfs2_blk2rgrpd(sdp, start, 0);
+        rgd_end = gfs2_blk2rgrpd(sdp, end - 1, 0);
+        if (end <= start ||
+            minlen > sdp->sd_max_rg_data ||
+            start > rgd_end->rd_data0 + rgd_end->rd_data)
+                return -EINVAL;
        while (1) {
@@ -1295,7 +1302,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
                        /* Trim each bitmap in the rgrp */
                        for (x = 0; x < rgd->rd_length; x++) {
                                struct gfs2_bitmap *bi = rgd->rd_bits + x;
-                                ret = gfs2_rgrp_send_discards(sdp, rgd->rd_data0, NULL, bi, r.minlen, &amt);
+                                ret = gfs2_rgrp_send_discards(sdp,
+                                                rgd->rd_data0, NULL, bi, minlen,
+                                                &amt);
                                if (ret) {
                                        gfs2_glock_dq_uninit(&gh);
                                        goto out;
@@ -1324,7 +1333,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 out:
        r.len = trimmed << 9;
-        if (argp && copy_to_user(argp, &r, sizeof(r)))
+        if (copy_to_user(argp, &r, sizeof(r)))
                return -EFAULT;
        return ret;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index bc737261f234..d6488674d916 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -810,7 +810,8 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
                        return;
                }
                need_unlock = 1;
-        }
+        } else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE))
+                return;
        if (current->journal_info == NULL) {
                ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index adbd27875ef9..413627072f36 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -155,14 +155,22 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
        struct gfs2_sbd *sdp = gl->gl_sbd;
        struct gfs2_bufdata *bd;
+        lock_buffer(bh);
+        gfs2_log_lock(sdp);
        bd = bh->b_private;
        if (bd)
                gfs2_assert(sdp, bd->bd_gl == gl);
        else {
+                gfs2_log_unlock(sdp);
+                unlock_buffer(bh);
                gfs2_attach_bufdata(gl, bh, meta);
                bd = bh->b_private;
+                lock_buffer(bh);
+                gfs2_log_lock(sdp);
        }
        lops_add(sdp, bd);
+        gfs2_log_unlock(sdp);
+        unlock_buffer(bh);
 }
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index 31c26c4dcc23..ca4b11ec87a2 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -217,7 +217,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 {
        char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
        struct nfs_dns_ent key, *item;
-        unsigned long ttl;
+        unsigned int ttl;
        ssize_t len;
        int ret = -EINVAL;
@@ -240,7 +240,8 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
        key.namelen = len;
        memset(&key.h, 0, sizeof(key.h));
-        ttl = get_expiry(&buf);
+        if (get_uint(&buf, &ttl) < 0)
+                goto out;
        if (ttl == 0)
                goto out;
        key.h.expiry_time = ttl + seconds_since_boot();
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5c7325c5c5e6..6fa01aea2488 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -685,7 +685,10 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
        if (ctx->cred != NULL)
                put_rpccred(ctx->cred);
        dput(ctx->dentry);
-        nfs_sb_deactive(sb);
+        if (is_sync)
+                nfs_sb_deactive(sb);
+        else
+                nfs_sb_deactive_async(sb);
        kfree(ctx->mdsthreshold);
        kfree(ctx);
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 59b133c5d652..05521cadac2e 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -351,10 +351,12 @@ extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 extern void nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
+extern void nfs_sb_deactive_async(struct super_block *sb);
 /* namespace.c */
+#define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
-                      char *buffer, ssize_t buflen);
+                      char *buffer, ssize_t buflen, unsigned flags);
 extern struct vfsmount *nfs_d_automount(struct path *path);
 struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *,
                              struct nfs_fh *, struct nfs_fattr *);
@@ -498,7 +500,7 @@ static inline char *nfs_devname(struct dentry *dentry,
                                char *buffer, ssize_t buflen)
 {
        char *dummy;
-        return nfs_path(&dummy, dentry, buffer, buflen);
+        return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL);
 }
 /*
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 8e65c7f1f87c..015f71f8f62c 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -181,7 +181,7 @@ int nfs_mount(struct nfs_mount_request *info)
        else
                msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT];
-        status = rpc_call_sync(mnt_clnt, &msg, 0);
+        status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT);
        rpc_shutdown_client(mnt_clnt);
        if (status < 0)
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 655925373b91..dd057bc6b65b 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -33,6 +33,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 * @dentry - pointer to dentry
 * @buffer - result buffer
 * @buflen - length of buffer
+ * @flags - options (see below)
 *
 * Helper function for constructing the server pathname
 * by arbitrary hashed dentry.
@@ -40,8 +41,14 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 * This is mainly for use in figuring out the path on the
 * server side when automounting on top of an existing partition
 * and in generating /proc/mounts and friends.
+ *
+ * Supported flags:
+ * NFS_PATH_CANONICAL: ensure there is exactly one slash after
+ *                     the original device (export) name
+ *                     (if unset, the original name is returned verbatim)
 */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen)
+char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
+               unsigned flags)
 {
        char *end;
        int namelen;
@@ -74,7 +81,7 @@ rename_retry:
                rcu_read_unlock();
                goto rename_retry;
        }
-        if (*end != '/') {
+        if ((flags & NFS_PATH_CANONICAL) && *end != '/') {
                if (--buflen < 0) {
                        spin_unlock(&dentry->d_lock);
                        rcu_read_unlock();
@@ -91,9 +98,11 @@ rename_retry:
                return end;
        }
        namelen = strlen(base);
-        /* Strip off excess slashes in base string */
+        if (flags & NFS_PATH_CANONICAL) {
-        while (namelen > 0 && base[namelen - 1] == '/')
+                /* Strip off excess slashes in base string */
-                namelen--;
+                while (namelen > 0 && base[namelen - 1] == '/')
+                        namelen--;
+        }
        buflen -= namelen;
        if (buflen < 0) {
                spin_unlock(&dentry->d_lock);
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 79fbb61ce202..1e09eb78543b 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -81,7 +81,8 @@ static char *nfs_path_component(const char *nfspath, const char *end)
 static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
 {
        char *limit;
-        char *path = nfs_path(&limit, dentry, buffer, buflen);
+        char *path = nfs_path(&limit, dentry, buffer, buflen,
+                              NFS_PATH_CANONICAL);
        if (!IS_ERR(path)) {
                char *path_component = nfs_path_component(path, limit);
                if (path_component)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 68b21d81b7ac..5eec4429970c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -339,8 +339,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
                        dprintk("%s ERROR: %d Reset session\n", __func__,
                                errorcode);
                        nfs4_schedule_session_recovery(clp->cl_session, errorcode);
-                        exception->retry = 1;
+                        goto wait_on_recovery;
-                        break;
 #endif /* defined(CONFIG_NFS_V4_1) */
                case -NFS4ERR_FILE_OPEN:
                        if (exception->timeout > HZ) {
@@ -1572,9 +1571,11 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
        data->timestamp = jiffies;
        if (nfs4_setup_sequence(data->o_arg.server,
                                &data->o_arg.seq_args,
-                                &data->o_res.seq_res, task))
+                                &data->o_res.seq_res,
-                return;
+                                task) != 0)
-        rpc_call_start(task);
+                nfs_release_seqid(data->o_arg.seqid);
+        else
+                rpc_call_start(task);
        return;
 unlock_no_action:
        rcu_read_unlock();
@@ -1748,7 +1749,7 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
        /* even though OPEN succeeded, access is denied. Close the file */
        nfs4_close_state(state, fmode);
-        return -NFS4ERR_ACCESS;
+        return -EACCES;
 }
 /*
@@ -2196,7 +2197,7 @@ static void nfs4_free_closedata(void *data)
        nfs4_put_open_state(calldata->state);
        nfs_free_seqid(calldata->arg.seqid);
        nfs4_put_state_owner(sp);
-        nfs_sb_deactive(sb);
+        nfs_sb_deactive_async(sb);
        kfree(calldata);
 }
@@ -2296,9 +2297,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
        if (nfs4_setup_sequence(NFS_SERVER(inode),
                                &calldata->arg.seq_args,
                                &calldata->res.seq_res,
-                                task))
+                                task) != 0)
-                goto out;
+                nfs_release_seqid(calldata->arg.seqid);
-        rpc_call_start(task);
+        else
+                rpc_call_start(task);
 out:
        dprintk("%s: done!\n", __func__);
 }
@@ -4529,6 +4531,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
                        if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
                                rpc_restart_call_prepare(task);
        }
+        nfs_release_seqid(calldata->arg.seqid);
 }
 static void nfs4_locku_prepare(struct rpc_task *task, void *data)
@@ -4545,9 +4548,11 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
        calldata->timestamp = jiffies;
        if (nfs4_setup_sequence(calldata->server,
                                &calldata->arg.seq_args,
-                                &calldata->res.seq_res, task))
+                                &calldata->res.seq_res,
-                return;
+                                task) != 0)
-        rpc_call_start(task);
+                nfs_release_seqid(calldata->arg.seqid);
+        else
+                rpc_call_start(task);
 }
 static const struct rpc_call_ops nfs4_locku_ops = {
@@ -4692,7 +4697,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
        /* Do we need to do an open_to_lock_owner? */
        if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
                if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0)
-                        return;
+                        goto out_release_lock_seqid;
                data->arg.open_stateid = &state->stateid;
                data->arg.new_lock_owner = 1;
                data->res.open_seqid = data->arg.open_seqid;
@@ -4701,10 +4706,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
        data->timestamp = jiffies;
        if (nfs4_setup_sequence(data->server,
                                &data->arg.seq_args,
-                                &data->res.seq_res, task))
+                                &data->res.seq_res,
+                                task) == 0) {
+                rpc_call_start(task);
                return;
-        rpc_call_start(task);
+        }
-        dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
+        nfs_release_seqid(data->arg.open_seqid);
+out_release_lock_seqid:
+        nfs_release_seqid(data->arg.lock_seqid);
+        dprintk("%s: done!, ret = %d\n", __func__, task->tk_status);
 }
 static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
@@ -5667,7 +5677,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
                tbl->slots = new;
                tbl->max_slots = max_slots;
        }
-        tbl->highest_used_slotid = -1;  /* no slot is currently used */
+        tbl->highest_used_slotid = NFS4_NO_SLOT;
        for (i = 0; i < tbl->max_slots; i++)
                tbl->slots[i].seq_nr = ivalue;
        spin_unlock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index fe624c91bd00..2878f97bd78d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -925,8 +925,8 @@ pnfs_find_alloc_layout(struct inode *ino,
        if (likely(nfsi->layout == NULL)) {     /* Won the race? */
                nfsi->layout = new;
                return new;
-        }
+        } else if (new != NULL)
-        pnfs_free_layout_hdr(new);
+                pnfs_free_layout_hdr(new);
 out_existing:
        pnfs_get_layout_hdr(nfsi->layout);
        return nfsi->layout;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e831bce49766..652d3f7176a9 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -54,6 +54,7 @@
 #include <linux/parser.h>
 #include <linux/nsproxy.h>
 #include <linux/rcupdate.h>
+#include <linux/kthread.h>
 #include <asm/uaccess.h>
@@ -415,6 +416,54 @@ void nfs_sb_deactive(struct super_block *sb)
 }
 EXPORT_SYMBOL_GPL(nfs_sb_deactive);
+static int nfs_deactivate_super_async_work(void *ptr)
+{
+        struct super_block *sb = ptr;
+        deactivate_super(sb);
+        module_put_and_exit(0);
+        return 0;
+}
+/*
+ * same effect as deactivate_super, but will do final unmount in kthread
+ * context
+ */
+static void nfs_deactivate_super_async(struct super_block *sb)
+{
+        struct task_struct *task;
+        char buf[INET6_ADDRSTRLEN + 1];
+        struct nfs_server *server = NFS_SB(sb);
+        struct nfs_client *clp = server->nfs_client;
+        if (!atomic_add_unless(&sb->s_active, -1, 1)) {
+                rcu_read_lock();
+                snprintf(buf, sizeof(buf),
+                        rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+                rcu_read_unlock();
+                __module_get(THIS_MODULE);
+                task = kthread_run(nfs_deactivate_super_async_work, sb,
+                                "%s-deactivate-super", buf);
+                if (IS_ERR(task)) {
+                        pr_err("%s: kthread_run: %ld\n",
+                                __func__, PTR_ERR(task));
+                        /* make synchronous call and hope for the best */
+                        deactivate_super(sb);
+                        module_put(THIS_MODULE);
+                }
+        }
+}
+void nfs_sb_deactive_async(struct super_block *sb)
+{
+        struct nfs_server *server = NFS_SB(sb);
+        if (atomic_dec_and_test(&server->active))
+                nfs_deactivate_super_async(sb);
+}
+EXPORT_SYMBOL_GPL(nfs_sb_deactive_async);
 /*
 * Deliver file system statistics to userspace
 */
@@ -771,7 +820,7 @@ int nfs_show_devname(struct seq_file *m, struct dentry *root)
        int err = 0;
        if (!page)
                return -ENOMEM;
-        devname = nfs_path(&dummy, root, page, PAGE_SIZE);
+        devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0);
        if (IS_ERR(devname))
                err = PTR_ERR(devname);
        else
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 13cea637eff8..3f79c77153b8 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -95,7 +95,7 @@ static void nfs_async_unlink_release(void *calldata)
        nfs_dec_sillycount(data->dir);
        nfs_free_unlinkdata(data);
-        nfs_sb_deactive(sb);
+        nfs_sb_deactive_async(sb);
 }
 static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index f35794b97e8e..a50636025364 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -21,6 +21,7 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new)
                        if ((old->path.mnt == new->path.mnt) &&
                            (old->path.dentry == new->path.dentry))
                                return true;
+                        break;
                case (FSNOTIFY_EVENT_NONE):
                        return true;
                default:
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 4f33c32affe3..335206a9c698 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1866,6 +1866,7 @@ xfs_alloc_fix_freelist(
        /*
         * Initialize the args structure.
         */
+        memset(&targs, 0, sizeof(targs));
        targs.tp = tp;
        targs.mp = mp;
        targs.agbp = agbp;
@@ -2207,7 +2208,7 @@ xfs_alloc_read_agf(
 * group or loop over the allocation groups to find the result.
 */
 int                             /* error */
-__xfs_alloc_vextent(
+xfs_alloc_vextent(
        xfs_alloc_arg_t *args)  /* allocation argument structure */
 {
        xfs_agblock_t   agsize; /* allocation group size */
@@ -2417,46 +2418,6 @@ error0:
        return error;
 }
-static void
-xfs_alloc_vextent_worker(
-        struct work_struct      *work)
-{
-        struct xfs_alloc_arg    *args = container_of(work,
-                                                struct xfs_alloc_arg, work);
-        unsigned long           pflags;
-        /* we are in a transaction context here */
-        current_set_flags_nested(&pflags, PF_FSTRANS);
-        args->result = __xfs_alloc_vextent(args);
-        complete(args->done);
-        current_restore_flags_nested(&pflags, PF_FSTRANS);
-}
-/*
- * Data allocation requests often come in with little stack to work on. Push
- * them off to a worker thread so there is lots of stack to use. Metadata
- * requests, OTOH, are generally from low stack usage paths, so avoid the
- * context switch overhead here.
- */
-int
-xfs_alloc_vextent(
-        struct xfs_alloc_arg    *args)
-{
-        DECLARE_COMPLETION_ONSTACK(done);
-        if (!args->userdata)
-                return __xfs_alloc_vextent(args);
-        args->done = &done;
-        INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);
-        queue_work(xfs_alloc_wq, &args->work);
-        wait_for_completion(&done);
-        return args->result;
-}
 /*
 * Free an extent.
 * Just break up the extent address and hand off to xfs_free_ag_extent
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 93be4a667ca1..feacb061bab7 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -120,9 +120,6 @@ typedef struct xfs_alloc_arg {
        char            isfl;           /* set if is freelist blocks - !acctg */
        char            userdata;       /* set if this is user data */
        xfs_fsblock_t   firstblock;     /* io first block allocated */
-        struct completion *done;
-        struct work_struct work;
-        int             result;
 } xfs_alloc_arg_t;
 /*
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index f1647caace8f..f7876c6d6165 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -121,6 +121,8 @@ xfs_allocbt_free_block(
        xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
                              XFS_EXTENT_BUSY_SKIP_DISCARD);
        xfs_trans_agbtree_delta(cur->bc_tp, -1);
+        xfs_trans_binval(cur->bc_tp, bp);
        return 0;
 }
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 848ffa77707b..83d0cf3df930 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2437,6 +2437,7 @@ xfs_bmap_btalloc(
         * Normal allocation, done through xfs_alloc_vextent.
         */
        tryagain = isaligned = 0;
+        memset(&args, 0, sizeof(args));
        args.tp = ap->tp;
        args.mp = mp;
        args.fsbno = ap->blkno;
@@ -3082,6 +3083,7 @@ xfs_bmap_extents_to_btree(
         * Convert to a btree with two levels, one record in root.
         */
        XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
+        memset(&args, 0, sizeof(args));
        args.tp = tp;
        args.mp = mp;
        args.firstblock = *firstblock;
@@ -3237,6 +3239,7 @@ xfs_bmap_local_to_extents(
                xfs_buf_t       *bp;    /* buffer for extent block */
                xfs_bmbt_rec_host_t *ep;/* extent record pointer */
+                memset(&args, 0, sizeof(args));
                args.tp = tp;
                args.mp = ip->i_mount;
                args.firstblock = *firstblock;
@@ -4616,12 +4619,11 @@ xfs_bmapi_delay(
 STATIC int
-xfs_bmapi_allocate(
+__xfs_bmapi_allocate(
-        struct xfs_bmalloca     *bma,
+        struct xfs_bmalloca     *bma)
-        int                     flags)
 {
        struct xfs_mount        *mp = bma->ip->i_mount;
-        int                     whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
+        int                     whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ?
                                                XFS_ATTR_FORK : XFS_DATA_FORK;
        struct xfs_ifork        *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
        int                     tmp_logflags = 0;
@@ -4654,24 +4656,27 @@ xfs_bmapi_allocate(
         * Indicate if this is the first user data in the file, or just any
         * user data.
         */
-        if (!(flags & XFS_BMAPI_METADATA)) {
+        if (!(bma->flags & XFS_BMAPI_METADATA)) {
                bma->userdata = (bma->offset == 0) ?
                        XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
        }
-        bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
+        bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
        /*
         * Only want to do the alignment at the eof if it is userdata and
         * allocation length is larger than a stripe unit.
         */
        if (mp->m_dalign && bma->length >= mp->m_dalign &&
-            !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
+            !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
                error = xfs_bmap_isaeof(bma, whichfork);
                if (error)
                        return error;
        }
+        if (bma->flags & XFS_BMAPI_STACK_SWITCH)
+                bma->stack_switch = 1;
        error = xfs_bmap_alloc(bma);
        if (error)
                return error;
@@ -4706,7 +4711,7 @@ xfs_bmapi_allocate(
         * A wasdelay extent has been initialized, so shouldn't be flagged
         * as unwritten.
         */
-        if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) &&
+        if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) &&
            xfs_sb_version_hasextflgbit(&mp->m_sb))
                bma->got.br_state = XFS_EXT_UNWRITTEN;
@@ -4734,6 +4739,45 @@ xfs_bmapi_allocate(
        return 0;
 }
+static void
+xfs_bmapi_allocate_worker(
+        struct work_struct      *work)
+{
+        struct xfs_bmalloca     *args = container_of(work,
+                                                struct xfs_bmalloca, work);
+        unsigned long           pflags;
+        /* we are in a transaction context here */
+        current_set_flags_nested(&pflags, PF_FSTRANS);
+        args->result = __xfs_bmapi_allocate(args);
+        complete(args->done);
+        current_restore_flags_nested(&pflags, PF_FSTRANS);
+}
+/*
+ * Some allocation requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. Otherwise just
+ * call directly to avoid the context switch overhead here.
+ */
+int
+xfs_bmapi_allocate(
+        struct xfs_bmalloca     *args)
+{
+        DECLARE_COMPLETION_ONSTACK(done);
+        if (!args->stack_switch)
+                return __xfs_bmapi_allocate(args);
+        args->done = &done;
+        INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
+        queue_work(xfs_alloc_wq, &args->work);
+        wait_for_completion(&done);
+        return args->result;
+}
 STATIC int
 xfs_bmapi_convert_unwritten(
        struct xfs_bmalloca     *bma,
@@ -4919,6 +4963,7 @@ xfs_bmapi_write(
                        bma.conv = !!(flags & XFS_BMAPI_CONVERT);
                        bma.wasdel = wasdelay;
                        bma.offset = bno;
+                        bma.flags = flags;
                        /*
                         * There's a 32/64 bit type mismatch between the
@@ -4934,7 +4979,7 @@ xfs_bmapi_write(
                        ASSERT(len > 0);
                        ASSERT(bma.length > 0);
-                        error = xfs_bmapi_allocate(&bma, flags);
+                        error = xfs_bmapi_allocate(&bma);
                        if (error)
                                goto error0;
                        if (bma.blkno == NULLFSBLOCK)
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 803b56d7ce16..5f469c3516eb 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -77,6 +77,7 @@ typedef	struct xfs_bmap_free
 * from written to unwritten, otherwise convert from unwritten to written.
 */
 #define XFS_BMAPI_CONVERT       0x040
+#define XFS_BMAPI_STACK_SWITCH  0x080
 #define XFS_BMAPI_FLAGS \
        { XFS_BMAPI_ENTIRE,     "ENTIRE" }, \
@@ -85,7 +86,8 @@ typedef	struct xfs_bmap_free
        { XFS_BMAPI_PREALLOC,   "PREALLOC" }, \
        { XFS_BMAPI_IGSTATE,    "IGSTATE" }, \
        { XFS_BMAPI_CONTIG,     "CONTIG" }, \
-        { XFS_BMAPI_CONVERT,    "CONVERT" }
+        { XFS_BMAPI_CONVERT,    "CONVERT" }, \
+        { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }
 static inline int xfs_bmapi_aflag(int w)
@@ -133,6 +135,11 @@ typedef struct xfs_bmalloca {
        char                    userdata;/* set if is user data */
        char                    aeof;   /* allocated space at eof */
        char                    conv;   /* overwriting unwritten extents */
+        char                    stack_switch;
+        int                     flags;
+        struct completion       *done;
+        struct work_struct      work;
+        int                     result;
 } xfs_bmalloca_t;
 /*
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a8d0ed911196..becf4a97efc6 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -526,7 +526,25 @@ xfs_buf_item_unpin(
                }
                xfs_buf_relse(bp);
        } else if (freed && remove) {
+                /*
+                 * There are currently two references to the buffer - the active
+                 * LRU reference and the buf log item. What we are about to do
+                 * here - simulate a failed IO completion - requires 3
+                 * references.
+                 *
+                 * The LRU reference is removed by the xfs_buf_stale() call. The
+                 * buf item reference is removed by the xfs_buf_iodone()
+                 * callback that is run by xfs_buf_do_callbacks() during ioend
+                 * processing (via the bp->b_iodone callback), and then finally
+                 * the ioend processing will drop the IO reference if the buffer
+                 * is marked XBF_ASYNC.
+                 *
+                 * Hence we need to take an additional reference here so that IO
+                 * completion processing doesn't free the buffer prematurely.
+                 */
                xfs_buf_lock(bp);
+                xfs_buf_hold(bp);
+                bp->b_flags |= XBF_ASYNC;
                xfs_buf_ioerror(bp, EIO);
                XFS_BUF_UNDONE(bp);
                xfs_buf_stale(bp);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index c25b094efbf7..4beaede43277 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -399,9 +399,26 @@ xfs_growfs_data_private(
        /* update secondary superblocks. */
        for (agno = 1; agno < nagcount; agno++) {
-                error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
+                error = 0;
+                /*
+                 * new secondary superblocks need to be zeroed, not read from
+                 * disk as the contents of the new area we are growing into is
+                 * completely unknown.
+                 */
+                if (agno < oagcount) {
+                        error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
                                  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
                                  XFS_FSS_TO_BB(mp, 1), 0, &bp);
+                } else {
+                        bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp,
+                                  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
+                                  XFS_FSS_TO_BB(mp, 1), 0);
+                        if (bp)
+                                xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+                        else
+                                error = ENOMEM;
+                }
                if (error) {
                        xfs_warn(mp,
                "error %d reading secondary superblock for ag %d",
@@ -423,7 +440,7 @@ xfs_growfs_data_private(
                        break; /* no point in continuing */
                }
        }
-        return 0;
+        return error;
 error0:
        xfs_trans_cancel(tp, XFS_TRANS_ABORT);
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 445bf1aef31c..c5c4ef4f2bdb 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -250,6 +250,7 @@ xfs_ialloc_ag_alloc(
                                        /* boundary */
        struct xfs_perag *pag;
+        memset(&args, 0, sizeof(args));
        args.tp = tp;
        args.mp = tp->t_mountp;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2778258fcfa2..1938b41ee9f5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1509,7 +1509,8 @@ xfs_ifree_cluster(
                 * to mark all the active inodes on the buffer stale.
                 */
                bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-                                        mp->m_bsize * blks_per_cluster, 0);
+                                        mp->m_bsize * blks_per_cluster,
+                                        XBF_UNMAPPED);
                if (!bp)
                        return ENOMEM;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 8305f2ac6773..c1df3c623de2 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -70,7 +70,7 @@ xfs_find_handle(
        int                     hsize;
        xfs_handle_t            handle;
        struct inode            *inode;
-        struct fd               f;
+        struct fd               f = {0};
        struct path             path;
        int                     error;
        struct xfs_inode        *ip;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 973dff6ad935..7f537663365b 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -584,7 +584,9 @@ xfs_iomap_write_allocate(
                         * pointer that the caller gave to us.
                         */
                        error = xfs_bmapi_write(tp, ip, map_start_fsb,
-                                                count_fsb, 0, &first_block, 1,
+                                                count_fsb,
+                                                XFS_BMAPI_STACK_SWITCH,
+                                                &first_block, 1,
                                                imap, &nimaps, &free_list);
                        if (error)
                                goto trans_cancel;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 7f4f9370d0e7..4dad756962d0 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2387,14 +2387,27 @@ xlog_state_do_callback(
                                /*
-                                 * update the last_sync_lsn before we drop the
+                                 * Completion of a iclog IO does not imply that
+                                 * a transaction has completed, as transactions
+                                 * can be large enough to span many iclogs. We
+                                 * cannot change the tail of the log half way
+                                 * through a transaction as this may be the only
+                                 * transaction in the log and moving th etail to
+                                 * point to the middle of it will prevent
+                                 * recovery from finding the start of the
+                                 * transaction. Hence we should only update the
+                                 * last_sync_lsn if this iclog contains
+                                 * transaction completion callbacks on it.
+                                 *
+                                 * We have to do this before we drop the
                                 * icloglock to ensure we are the only one that
                                 * can update it.
                                 */
                                ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn),
                                        be64_to_cpu(iclog->ic_header.h_lsn)) <= 0);
-                                atomic64_set(&log->l_last_sync_lsn,
+                                if (iclog->ic_callback)
-                                        be64_to_cpu(iclog->ic_header.h_lsn));
+                                        atomic64_set(&log->l_last_sync_lsn,
+                                                be64_to_cpu(iclog->ic_header.h_lsn));
                        } else
                                ioerrors++;
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 5da3ace352bf..d308749fabf1 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3541,7 +3541,7 @@ xlog_do_recovery_pass(
                                 *   - order is important.
                                 */
                                error = xlog_bread_offset(log, 0,
-                                                bblks - split_bblks, hbp,
+                                                bblks - split_bblks, dbp,
                                                offset + BBTOB(split_bblks));
                                if (error)
                                        goto bread_err2;