11 files changed, 222 insertions, 42 deletions

diff --git a/fs/file.c b/fs/file.c
index 708d997a7748..7cb71b992603 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -685,7 +685,6 @@ void do_close_on_exec(struct files_struct *files)
         struct fdtable *fdt;
 
         /* exec unshares first */
-        BUG_ON(atomic_read(&files->count) != 1);
         spin_lock(&files->file_lock);
         for (i = 0; ; i++) {
                 unsigned long set;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 60ef3fb707ff..1506673c087e 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
         struct page *pg;
         struct inode *inode = mapping->host;
         struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
+        struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+        struct jffs2_raw_inode ri;
+        uint32_t alloc_len = 0;
         pgoff_t index = pos >> PAGE_CACHE_SHIFT;
         uint32_t pageofs = index << PAGE_CACHE_SHIFT;
         int ret = 0;
 
+        jffs2_dbg(1, "%s()\n", __func__);
+
+        if (pageofs > inode->i_size) {
+                ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+                                          ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+                if (ret)
+                        return ret;
+        }
+
+        mutex_lock(&f->sem);
         pg = grab_cache_page_write_begin(mapping, index, flags);
-        if (!pg)
+        if (!pg) {
+                if (alloc_len)
+                        jffs2_complete_reservation(c);
+                mutex_unlock(&f->sem);
                 return -ENOMEM;
+        }
         *pagep = pg;
 
-        jffs2_dbg(1, "%s()\n", __func__);
-
-        if (pageofs > inode->i_size) {
+        if (alloc_len) {
                 /* Make new hole frag from old EOF to new page */
-                struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-                struct jffs2_raw_inode ri;
                 struct jffs2_full_dnode *fn;
-                uint32_t alloc_len;
 
                 jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
                           (unsigned int)inode->i_size, pageofs);
 
-                ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-                                          ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-                if (ret)
-                        goto out_page;
-
-                mutex_lock(&f->sem);
                 memset(&ri, 0, sizeof(ri));
 
                 ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
                 if (IS_ERR(fn)) {
                         ret = PTR_ERR(fn);
                         jffs2_complete_reservation(c);
-                        mutex_unlock(&f->sem);
                         goto out_page;
                 }
                 ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
                         jffs2_mark_node_obsolete(c, fn->raw);
                         jffs2_free_full_dnode(fn);
                         jffs2_complete_reservation(c);
-                        mutex_unlock(&f->sem);
                         goto out_page;
                 }
                 jffs2_complete_reservation(c);
                 inode->i_size = pageofs;
-                mutex_unlock(&f->sem);
         }
 
         /*
@@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
          * case of a short-copy.
          */
         if (!PageUptodate(pg)) {
-                mutex_lock(&f->sem);
                 ret = jffs2_do_readpage_nolock(inode, pg);
-                mutex_unlock(&f->sem);
                 if (ret)
                         goto out_page;
         }
+        mutex_unlock(&f->sem);
         jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
         return ret;
 
 out_page:
         unlock_page(pg);
         page_cache_release(pg);
+        mutex_unlock(&f->sem);
         return ret;
 }
 
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 721d692fa8d4..6fcaeb8c902e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -258,7 +258,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
         if (ret)
                 goto out_close_fd;
 
-        fd_install(fd, f);
+        if (fd != FAN_NOFD)
+                fd_install(fd, f);
         return fanotify_event_metadata.event_len;
 
 out_close_fd:
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 144a96732dd7..3c231adf8450 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = {
         .release        = mem_release,
 };
 
+static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
+                            loff_t *ppos)
+{
+        struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+        char buffer[PROC_NUMBUF];
+        int oom_adj = OOM_ADJUST_MIN;
+        size_t len;
+        unsigned long flags;
+
+        if (!task)
+                return -ESRCH;
+        if (lock_task_sighand(task, &flags)) {
+                if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+                        oom_adj = OOM_ADJUST_MAX;
+                else
+                        oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+                                  OOM_SCORE_ADJ_MAX;
+                unlock_task_sighand(task, &flags);
+        }
+        put_task_struct(task);
+        len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
+        return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_adj_write(struct file *file, const char __user *buf,
+                             size_t count, loff_t *ppos)
+{
+        struct task_struct *task;
+        char buffer[PROC_NUMBUF];
+        int oom_adj;
+        unsigned long flags;
+        int err;
+
+        memset(buffer, 0, sizeof(buffer));
+        if (count > sizeof(buffer) - 1)
+                count = sizeof(buffer) - 1;
+        if (copy_from_user(buffer, buf, count)) {
+                err = -EFAULT;
+                goto out;
+        }
+
+        err = kstrtoint(strstrip(buffer), 0, &oom_adj);
+        if (err)
+                goto out;
+        if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
+             oom_adj != OOM_DISABLE) {
+                err = -EINVAL;
+                goto out;
+        }
+
+        task = get_proc_task(file->f_path.dentry->d_inode);
+        if (!task) {
+                err = -ESRCH;
+                goto out;
+        }
+
+        task_lock(task);
+        if (!task->mm) {
+                err = -EINVAL;
+                goto err_task_lock;
+        }
+
+        if (!lock_task_sighand(task, &flags)) {
+                err = -ESRCH;
+                goto err_task_lock;
+        }
+
+        /*
+         * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+         * value is always attainable.
+         */
+        if (oom_adj == OOM_ADJUST_MAX)
+                oom_adj = OOM_SCORE_ADJ_MAX;
+        else
+                oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+
+        if (oom_adj < task->signal->oom_score_adj &&
+            !capable(CAP_SYS_RESOURCE)) {
+                err = -EACCES;
+                goto err_sighand;
+        }
+
+        /*
+         * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+         * /proc/pid/oom_score_adj instead.
+         */
+        printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+                  current->comm, task_pid_nr(current), task_pid_nr(task),
+                  task_pid_nr(task));
+
+        task->signal->oom_score_adj = oom_adj;
+        trace_oom_score_adj_update(task);
+err_sighand:
+        unlock_task_sighand(task, &flags);
+err_task_lock:
+        task_unlock(task);
+        put_task_struct(task);
+out:
+        return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_adj_operations = {
+        .read           = oom_adj_read,
+        .write          = oom_adj_write,
+        .llseek         = generic_file_llseek,
+};
+
 static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
                                         size_t count, loff_t *ppos)
 {
@@ -2598,6 +2705,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
         INF("oom_score",  S_IRUGO, proc_oom_score),
+        REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
         REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
@@ -2964,6 +3072,7 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
         INF("oom_score", S_IRUGO, proc_oom_score),
+        REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
         REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index a40da07e93d6..947fbe06c3b1 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -161,6 +161,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 
         while (s < e) {
                 unsigned long flags;
+                u64 id;
 
                 if (c > psinfo->bufsize)
                         c = psinfo->bufsize;
@@ -172,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
                         spin_lock_irqsave(&psinfo->buf_lock, flags);
                 }
                 memcpy(psinfo->buf, s, c);
-                psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo);
+                psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo);
                 spin_unlock_irqrestore(&psinfo->buf_lock, flags);
                 s += c;
                 c = e - s;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 28ec13af28d9..2dcf3d473fec 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c)
         if (!lprops) {
                 lprops = ubifs_fast_find_freeable(c);
                 if (!lprops) {
-                        ubifs_assert(c->freeable_cnt == 0);
-                        if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+                        /*
+                         * The first condition means the following: go scan the
+                         * LPT if there are uncategorized lprops, which means
+                         * there may be freeable LEBs there (UBIFS does not
+                         * store the information about freeable LEBs in the
+                         * master node).
+                         */
+                        if (c->in_a_category_cnt != c->main_lebs ||
+                            c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+                                ubifs_assert(c->freeable_cnt == 0);
                                 lprops = scan_for_leb_for_idx(c);
                                 if (IS_ERR(lprops)) {
                                         err = PTR_ERR(lprops);
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index e5a2a35a46dc..46190a7c42a6 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
         default:
                 ubifs_assert(0);
         }
+
         lprops->flags &= ~LPROPS_CAT_MASK;
         lprops->flags |= cat;
+        c->in_a_category_cnt += 1;
+        ubifs_assert(c->in_a_category_cnt <= c->main_lebs);
 }
 
 /**
@@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
         default:
                 ubifs_assert(0);
         }
+
+        c->in_a_category_cnt -= 1;
+        ubifs_assert(c->in_a_category_cnt >= 0);
 }
 
 /**
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 5486346d0a3f..d133c276fe05 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1183,6 +1183,8 @@ struct ubifs_debug_info;
  * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size)
  * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size)
  * @freeable_cnt: number of freeable LEBs in @freeable_list
+ * @in_a_category_cnt: count of lprops which are in a certain category, which
+ *                     basically meants that they were loaded from the flash
  *
  * @ltab_lnum: LEB number of LPT's own lprops table
  * @ltab_offs: offset of LPT's own lprops table
@@ -1412,6 +1414,7 @@ struct ubifs_info {
         struct list_head freeable_list;
         struct list_head frdi_idx_list;
         int freeable_cnt;
+        int in_a_category_cnt;
 
         int ltab_lnum;
         int ltab_offs;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index e562dd43f41f..e57e2daa357c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -481,11 +481,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
  *
  * The fix is two passes across the ioend list - one to start writeback on the
  * buffer_heads, and then submit them for I/O on the second pass.
+ *
+ * If @fail is non-zero, it means that we have a situation where some part of
+ * the submission process has failed after we have marked paged for writeback
+ * and unlocked them. In this situation, we need to fail the ioend chain rather
+ * than submit it to IO. This typically only happens on a filesystem shutdown.
  */
 STATIC void
 xfs_submit_ioend(
         struct writeback_control *wbc,
-        xfs_ioend_t             *ioend)
+        xfs_ioend_t             *ioend,
+        int                     fail)
 {
         xfs_ioend_t             *head = ioend;
         xfs_ioend_t             *next;
@@ -506,6 +512,18 @@ xfs_submit_ioend(
                 next = ioend->io_list;
                 bio = NULL;
 
+                /*
+                 * If we are failing the IO now, just mark the ioend with an
+                 * error and finish it. This will run IO completion immediately
+                 * as there is only one reference to the ioend at this point in
+                 * time.
+                 */
+                if (fail) {
+                        ioend->io_error = -fail;
+                        xfs_finish_ioend(ioend);
+                        continue;
+                }
+
                 for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
 
                         if (!bio) {
@@ -1060,7 +1078,18 @@ xfs_vm_writepage(
 
         xfs_start_page_writeback(page, 1, count);
 
-        if (ioend && imap_valid) {
+        /* if there is no IO to be submitted for this page, we are done */
+        if (!ioend)
+                return 0;
+
+        ASSERT(iohead);
+
+        /*
+         * Any errors from this point onwards need tobe reported through the IO
+         * completion path as we have marked the initial page as under writeback
+         * and unlocked it.
+         */
+        if (imap_valid) {
                 xfs_off_t               end_index;
 
                 end_index = imap.br_startoff + imap.br_blockcount;
@@ -1079,20 +1108,15 @@ xfs_vm_writepage(
                                   wbc, end_index);
         }
 
-        if (iohead) {
-                /*
-                 * Reserve log space if we might write beyond the on-disk
-                 * inode size.
-                 */
-                if (ioend->io_type != XFS_IO_UNWRITTEN &&
-                    xfs_ioend_is_append(ioend)) {
-                        err = xfs_setfilesize_trans_alloc(ioend);
-                        if (err)
-                                goto error;
-                }
 
-                xfs_submit_ioend(wbc, iohead);
-        }
+        /*
+         * Reserve log space if we might write beyond the on-disk inode size.
+         */
+        err = 0;
+        if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+                err = xfs_setfilesize_trans_alloc(ioend);
+
+        xfs_submit_ioend(wbc, iohead, err);
 
         return 0;
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d330111ca738..70eec1829776 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -1291,6 +1291,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
         leaf2 = blk2->bp->b_addr;
         ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
         ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+        ASSERT(leaf2->hdr.count == 0);
         args = state->args;
 
         trace_xfs_attr_leaf_rebalance(args);
@@ -1361,6 +1362,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
                  * I assert that since all callers pass in an empty
                  * second buffer, this code should never execute.
                  */
+                ASSERT(0);
 
                 /*
                  * Figure the total bytes to be added to the destination leaf.
@@ -1422,10 +1424,24 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
                         args->index2 = 0;
                         args->blkno2 = blk2->blkno;
                 } else {
+                        /*
+                         * On a double leaf split, the original attr location
+                         * is already stored in blkno2/index2, so don't
+                         * overwrite it overwise we corrupt the tree.
+                         */
                         blk2->index = blk1->index
                                     - be16_to_cpu(leaf1->hdr.count);
-                        args->index = args->index2 = blk2->index;
-                        args->blkno = args->blkno2 = blk2->blkno;
+                        args->index = blk2->index;
+                        args->blkno = blk2->blkno;
+                        if (!state->extravalid) {
+                                /*
+                                 * set the new attr location to match the old
+                                 * one and let the higher level split code
+                                 * decide where in the leaf to place it.
+                                 */
+                                args->index2 = blk2->index;
+                                args->blkno2 = blk2->blkno;
+                        }
                 }
         } else {
                 ASSERT(state->inleaf == 1);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 933b7930b863..4b0b8dd1b7b0 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1197,9 +1197,14 @@ xfs_buf_bio_end_io(
 {
         xfs_buf_t               *bp = (xfs_buf_t *)bio->bi_private;
 
-        xfs_buf_ioerror(bp, -error);
+        /*
+         * don't overwrite existing errors - otherwise we can lose errors on
+         * buffers that require multiple bios to complete.
+         */
+        if (!bp->b_error)
+                xfs_buf_ioerror(bp, -error);
 
-        if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+        if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
                 invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
 
         _xfs_buf_ioend(bp, 1);
@@ -1279,6 +1284,11 @@ next_chunk:
                 if (size)
                         goto next_chunk;
         } else {
+                /*
+                 * This is guaranteed not to be the last io reference count
+                 * because the caller (xfs_buf_iorequest) holds a count itself.
+                 */
+                atomic_dec(&bp->b_io_remaining);
                 xfs_buf_ioerror(bp, EIO);
                 bio_put(bio);
         }