Merge branch 'sched/core' into cpus4096

Conflicts:
	include/linux/ftrace.h
	kernel/sched.c

10 files changed, 52 insertions, 16 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index db831efbdbb..99e0ae1a4c7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1135,12 +1135,15 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if (res)
 		return res;
 
-	if (!(filp->f_mode & FMODE_EXCL))
-		return 0;
+	if (filp->f_mode & FMODE_EXCL) {
+		res = bd_claim(bdev, filp);
+		if (res)
+			goto out_blkdev_put;
+	}
 
-	if (!(res = bd_claim(bdev, filp)))
-		return 0;
+	return 0;
 
+ out_blkdev_put:
 	blkdev_put(bdev, filp->f_mode);
 	return res;
 }
@@ -1203,8 +1206,16 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	fmode_t mode = file->f_mode;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
 	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY_NOW;
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index 4e834f16d9d..ec5df9a3831 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1159,6 +1159,7 @@ EXPORT_SYMBOL(remove_arg_zero);
  */
 int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 {
+	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
 	struct linux_binfmt *fmt;
 #ifdef __alpha__
@@ -1219,8 +1220,15 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 				continue;
 			read_unlock(&binfmt_lock);
 			retval = fn(bprm, regs);
+			/*
+			 * Restore the depth counter to its starting value
+			 * in this call, so we don't have to rely on every
+			 * load_binary function to restore it on return.
+			 */
+			bprm->recursion_depth = depth;
 			if (retval >= 0) {
-				tracehook_report_exec(fmt, bprm, regs);
+				if (depth == 0)
+					tracehook_report_exec(fmt, bprm, regs);
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
 				if (bprm->file)
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 80246bad1b7..890e0182881 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -367,6 +367,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	 * Try to get any dentry for the given file handle from the filesystem.
 	 */
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
+	if (!result)
+		result = ERR_PTR(-ESTALE);
 	if (IS_ERR(result))
 		return result;
 
@@ -420,6 +422,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 
 		target_dir = nop->fh_to_parent(mnt->mnt_sb, fid,
 				fh_len, fileid_type);
+		if (!target_dir)
+			goto err_result;
 		err = PTR_ERR(target_dir);
 		if (IS_ERR(target_dir))
 			goto err_result;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index d2003cdc36a..db35cfdb3c8 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -609,8 +609,8 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 
 	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
 						EXT4_FREEBLOCKS_WATERMARK) {
-		free_blocks  = percpu_counter_sum(fbc);
-		dirty_blocks = percpu_counter_sum(dbc);
+		free_blocks  = percpu_counter_sum_positive(fbc);
+		dirty_blocks = percpu_counter_sum_positive(dbc);
 		if (dirty_blocks < 0) {
 			printk(KERN_CRIT "Dirty block accounting "
 					"went wrong %lld\n",
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ac4f7db9f13..549daf8005f 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -19,6 +19,7 @@
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
+#include <linux/smp_lock.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -175,6 +176,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	if (error)
 		return error;
 
+	/*
+	 * We still need a lock here for now to keep multiple FASYNC calls
+	 * from racing with each other.
+	 */
+	lock_kernel();
 	if ((arg ^ filp->f_flags) & FASYNC) {
 		if (filp->f_op && filp->f_op->fasync) {
 			error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
@@ -185,6 +191,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 
 	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
  out:
+	unlock_kernel();
 	return error;
 }
 
diff --git a/fs/inotify.c b/fs/inotify.c
index 7bbed1b8982..dae3f28f30d 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -428,11 +428,13 @@ void inotify_unmount_inodes(struct list_head *list)
 		watches = &inode->inotify_watches;
 		list_for_each_entry_safe(watch, next_w, watches, i_list) {
 			struct inotify_handle *ih= watch->ih;
+			get_inotify_watch(watch);
 			mutex_lock(&ih->mutex);
 			ih->in_ops->handle_event(watch, watch->wd, IN_UNMOUNT, 0,
 						 NULL, NULL);
 			inotify_remove_watch_locked(ih, watch);
 			mutex_unlock(&ih->mutex);
+			put_inotify_watch(watch);
 		}
 		mutex_unlock(&inode->inotify_mutex);
 		iput(inode);		
diff --git a/fs/ioctl.c b/fs/ioctl.c
index d152856c371..43e8b2c0664 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -400,11 +400,9 @@ static int ioctl_fioasync(unsigned int fd, struct file *filp,
 
 	/* Did FASYNC state change ? */
 	if ((flag ^ filp->f_flags) & FASYNC) {
-		if (filp->f_op && filp->f_op->fasync) {
-			lock_kernel();
+		if (filp->f_op && filp->f_op->fasync)
 			error = filp->f_op->fasync(fd, filp, on);
-			unlock_kernel();
-		} else
+		else
 			error = -ENOTTY;
 	}
 	if (error)
@@ -440,11 +438,17 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		break;
 
 	case FIONBIO:
+		/* BKL needed to avoid races tweaking f_flags */
+		lock_kernel();
 		error = ioctl_fionbio(filp, argp);
+		unlock_kernel();
 		break;
 
 	case FIOASYNC:
+		/* BKL needed to avoid races tweaking f_flags */
+		lock_kernel();
 		error = ioctl_fioasync(fd, filp, argp);
+		unlock_kernel();
 		break;
 
 	case FIOQSIZE:
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 486cf3fe713..d4677603c88 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -371,7 +371,7 @@ static int lstats_show_proc(struct seq_file *m, void *v)
 				task->latency_record[i].time,
 				task->latency_record[i].max);
 			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
-				char sym[KSYM_NAME_LEN];
+				char sym[KSYM_SYMBOL_LEN];
 				char *c;
 				if (!task->latency_record[i].backtrace[q])
 					break;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b770c095e45..3a8bdd7f575 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -557,9 +557,9 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
 }
 
-static unsigned long pte_to_pagemap_entry(pte_t pte)
+static u64 pte_to_pagemap_entry(pte_t pte)
 {
-	unsigned long pme = 0;
+	u64 pme = 0;
 	if (is_swap_pte(pte))
 		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
 			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index d700dacdb10..c903130be7f 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -212,7 +212,7 @@ xfs_rename(
 	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
 		     (target_dp->i_d.di_projid != src_ip->i_d.di_projid))) {
 		error = XFS_ERROR(EXDEV);
-		xfs_rename_unlock4(inodes, XFS_ILOCK_SHARED);
+		xfs_rename_unlock4(inodes, XFS_ILOCK_EXCL);
 		xfs_trans_cancel(tp, cancel_flags);
 		goto std_return;
 	}