Merge branch 'perf/urgent' into perf/core

Conflicts:
	tools/perf/builtin-record.c
	tools/perf/builtin-top.c
	tools/perf/perf.h
	tools/perf/util/top.h

Merge reason: resolve these cherry-picking conflicts.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

66 files changed, 779 insertions, 643 deletions

diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index d8d8e7ba6a1..eb1cc92cd67 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -110,6 +110,7 @@ struct autofs_sb_info {
 	int sub_version;
 	int min_proto;
 	int max_proto;
+	int compat_daemon;
 	unsigned long exp_timeout;
 	unsigned int type;
 	int reghost_enabled;
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 76741d8d778..85f1fcdb30e 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -385,6 +385,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		sbi->pipefd = pipefd;
 		sbi->pipe = pipe;
 		sbi->catatonic = 0;
+		sbi->compat_daemon = is_compat_task();
 	}
 out:
 	mutex_unlock(&sbi->wq_mutex);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 450f529a4ea..1feb68ecef9 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -124,6 +124,7 @@ start:
 	/* Negative dentry - try next */
 	if (!simple_positive(q)) {
 		spin_unlock(&p->d_lock);
+		lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_);
 		p = q;
 		goto again;
 	}
@@ -186,6 +187,7 @@ again:
 	/* Negative dentry - try next */
 	if (!simple_positive(ret)) {
 		spin_unlock(&p->d_lock);
+		lock_set_subclass(&ret->d_lock.dep_map, 0, _RET_IP_);
 		p = ret;
 		goto again;
 	}
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index e16980b00b8..06858d95512 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -19,6 +19,7 @@
 #include <linux/parser.h>
 #include <linux/bitops.h>
 #include <linux/magic.h>
+#include <linux/compat.h>
 #include "autofs_i.h"
 #include <linux/module.h>
 
@@ -224,6 +225,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	set_autofs_type_indirect(&sbi->type);
 	sbi->min_proto = 0;
 	sbi->max_proto = 0;
+	sbi->compat_daemon = is_compat_task();
 	mutex_init(&sbi->wq_mutex);
 	mutex_init(&sbi->pipe_mutex);
 	spin_lock_init(&sbi->fs_lock);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index da8876d38a7..9c098db4334 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -91,7 +91,24 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 
 	return (bytes > 0);
 }
-	
+
+/*
+ * The autofs_v5 packet was misdesigned.
+ *
+ * The packets are identical on x86-32 and x86-64, but have different
+ * alignment. Which means that 'sizeof()' will give different results.
+ * Fix it up for the case of running 32-bit user mode on a 64-bit kernel.
+ */
+static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi)
+{
+	size_t pktsz = sizeof(struct autofs_v5_packet);
+#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT)
+	if (sbi->compat_daemon > 0)
+		pktsz -= 4;
+#endif
+	return pktsz;
+}
+
 static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 				 struct autofs_wait_queue *wq,
 				 int type)
@@ -155,8 +172,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	{
 		struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet;
 
-		pktsz = sizeof(*packet);
-
+		pktsz = autofs_v5_packet_size(sbi);
 		packet->wait_queue_token = wq->wait_queue_token;
 		packet->len = wq->name.len;
 		memcpy(packet->name, wq->name.name, wq->name.len);
diff --git a/fs/bio.c b/fs/bio.c
index b1fe82cf88c..b980ecde026 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -505,13 +505,9 @@ EXPORT_SYMBOL(bio_clone);
 int bio_get_nr_vecs(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	int nr_pages;
-
-	nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (nr_pages > queue_max_segments(q))
-		nr_pages = queue_max_segments(q);
-
-	return nr_pages;
+	return min_t(unsigned,
+		     queue_max_segments(q),
+		     queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
 }
 EXPORT_SYMBOL(bio_get_nr_vecs);
 
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 633c701a287..98f6bf10bbd 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -892,6 +892,8 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		if (eb != eb_in)
 			free_extent_buffer(eb);
 		ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
+		if (ret > 0)
+			ret = -ENOENT;
 		if (ret)
 			break;
 		next_inum = found_key.offset;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b669a7d8e49..d986824bb2b 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -644,7 +644,7 @@ static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(
 static int btrfsic_process_superblock(struct btrfsic_state *state,
 				      struct btrfs_fs_devices *fs_devices)
 {
-	int ret;
+	int ret = 0;
 	struct btrfs_super_block *selected_super;
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 14f1c5a0b2d..d02c27cd14c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -588,6 +588,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				   page_offset(bio->bi_io_vec->bv_page),
 				   PAGE_CACHE_SIZE);
 	read_unlock(&em_tree->lock);
+	if (!em)
+		return -EIO;
 
 	compressed_len = em->block_len;
 	cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 27ebe61d3cc..80b6486fd5e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -886,7 +886,7 @@ struct btrfs_block_rsv {
 	u64 reserved;
 	struct btrfs_space_info *space_info;
 	spinlock_t lock;
-	unsigned int full:1;
+	unsigned int full;
 };
 
 /*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 811d9f918b1..534266fe505 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2260,6 +2260,12 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
+	if (sectorsize < PAGE_SIZE) {
+		printk(KERN_WARNING "btrfs: Incompatible sector size "
+		       "found on %s\n", sb->s_id);
+		goto fail_sb_buffer;
+	}
+
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);
@@ -2301,6 +2307,12 @@ int open_ctree(struct super_block *sb,
 
 	btrfs_close_extra_devices(fs_devices);
 
+	if (!fs_devices->latest_bdev) {
+		printk(KERN_CRIT "btrfs: failed to read devices on %s\n",
+		       sb->s_id);
+		goto fail_tree_roots;
+	}
+
 retry_root_backup:
 	blocksize = btrfs_level_size(tree_root,
 				     btrfs_super_root_level(disk_super));
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 283af7a676a..37e0a800d34 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3312,7 +3312,8 @@ commit_trans:
 	}
 	data_sinfo->bytes_may_use += bytes;
 	trace_btrfs_space_reservation(root->fs_info, "space_info",
-				      (u64)data_sinfo, bytes, 1);
+				      (u64)(unsigned long)data_sinfo,
+				      bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
 	return 0;
@@ -3333,7 +3334,8 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
 	spin_lock(&data_sinfo->lock);
 	data_sinfo->bytes_may_use -= bytes;
 	trace_btrfs_space_reservation(root->fs_info, "space_info",
-				      (u64)data_sinfo, bytes, 0);
+				      (u64)(unsigned long)data_sinfo,
+				      bytes, 0);
 	spin_unlock(&data_sinfo->lock);
 }
 
@@ -3611,12 +3613,15 @@ static int may_commit_transaction(struct btrfs_root *root,
 	if (space_info != delayed_rsv->space_info)
 		return -ENOSPC;
 
+	spin_lock(&space_info->lock);
 	spin_lock(&delayed_rsv->lock);
-	if (delayed_rsv->size < bytes) {
+	if (space_info->bytes_pinned + delayed_rsv->size < bytes) {
 		spin_unlock(&delayed_rsv->lock);
+		spin_unlock(&space_info->lock);
 		return -ENOSPC;
 	}
 	spin_unlock(&delayed_rsv->lock);
+	spin_unlock(&space_info->lock);
 
 commit:
 	trans = btrfs_join_transaction(root);
@@ -3695,9 +3700,9 @@ again:
 		if (used + orig_bytes <= space_info->total_bytes) {
 			space_info->bytes_may_use += orig_bytes;
 			trace_btrfs_space_reservation(root->fs_info,
-						      "space_info",
-						      (u64)space_info,
-						      orig_bytes, 1);
+					      "space_info",
+					      (u64)(unsigned long)space_info,
+					      orig_bytes, 1);
 			ret = 0;
 		} else {
 			/*
@@ -3766,9 +3771,9 @@ again:
 		if (used + num_bytes < space_info->total_bytes + avail) {
 			space_info->bytes_may_use += orig_bytes;
 			trace_btrfs_space_reservation(root->fs_info,
-						      "space_info",
-						      (u64)space_info,
-						      orig_bytes, 1);
+					      "space_info",
+					      (u64)(unsigned long)space_info,
+					      orig_bytes, 1);
 			ret = 0;
 		} else {
 			wait_ordered = true;
@@ -3913,8 +3918,8 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			spin_lock(&space_info->lock);
 			space_info->bytes_may_use -= num_bytes;
 			trace_btrfs_space_reservation(fs_info, "space_info",
-						      (u64)space_info,
-						      num_bytes, 0);
+					      (u64)(unsigned long)space_info,
+					      num_bytes, 0);
 			space_info->reservation_progress++;
 			spin_unlock(&space_info->lock);
 		}
@@ -4105,7 +4110,7 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
 	num_bytes += div64_u64(data_used + meta_used, 50);
 
 	if (num_bytes * 3 > meta_used)
-		num_bytes = div64_u64(meta_used, 3);
+		num_bytes = div64_u64(meta_used, 3) * 2;
 
 	return ALIGN(num_bytes, fs_info->extent_root->leafsize << 10);
 }
@@ -4132,14 +4137,14 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 		block_rsv->reserved += num_bytes;
 		sinfo->bytes_may_use += num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
-					      (u64)sinfo, num_bytes, 1);
+				      (u64)(unsigned long)sinfo, num_bytes, 1);
 	}
 
 	if (block_rsv->reserved >= block_rsv->size) {
 		num_bytes = block_rsv->reserved - block_rsv->size;
 		sinfo->bytes_may_use -= num_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
-					      (u64)sinfo, num_bytes, 0);
+				      (u64)(unsigned long)sinfo, num_bytes, 0);
 		sinfo->reservation_progress++;
 		block_rsv->reserved = block_rsv->size;
 		block_rsv->full = 1;
@@ -4192,7 +4197,8 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 	if (!trans->bytes_reserved)
 		return;
 
-	trace_btrfs_space_reservation(root->fs_info, "transaction", (u64)trans,
+	trace_btrfs_space_reservation(root->fs_info, "transaction",
+				      (u64)(unsigned long)trans,
 				      trans->bytes_reserved, 0);
 	btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
 	trans->bytes_reserved = 0;
@@ -4710,9 +4716,9 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 			space_info->bytes_reserved += num_bytes;
 			if (reserve == RESERVE_ALLOC) {
 				trace_btrfs_space_reservation(cache->fs_info,
-							      "space_info",
-							      (u64)space_info,
-							      num_bytes, 0);
+					      "space_info",
+					      (u64)(unsigned long)space_info,
+					      num_bytes, 0);
 				space_info->bytes_may_use -= num_bytes;
 			}
 		}
@@ -7886,9 +7892,16 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
 	u64 start;
 	u64 end;
 	u64 trimmed = 0;
+	u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	int ret = 0;
 
-	cache = btrfs_lookup_block_group(fs_info, range->start);
+	/*
+	 * try to trim all FS space, our block group may start from non-zero.
+	 */
+	if (range->len == total_bytes)
+		cache = btrfs_lookup_first_block_group(fs_info, range->start);
+	else
+		cache = btrfs_lookup_block_group(fs_info, range->start);
 
 	while (cache) {
 		if (cache->key.objectid >= (range->start + range->len)) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fcf77e1ded4..a55fbe6252d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -513,6 +513,15 @@ hit_next:
 	WARN_ON(state->end < start);
 	last_end = state->end;
 
+	if (state->end < end && !need_resched())
+		next_node = rb_next(&state->rb_node);
+	else
+		next_node = NULL;
+
+	/* the state doesn't have the wanted bits, go ahead */
+	if (!(state->state & bits))
+		goto next;
+
 	/*
 	 *     | ---- desired range ---- |
 	 *  | state | or
@@ -565,20 +574,15 @@ hit_next:
 		goto out;
 	}
 
-	if (state->end < end && prealloc && !need_resched())
-		next_node = rb_next(&state->rb_node);
-	else
-		next_node = NULL;
-
 	set |= clear_state_bit(tree, state, &bits, wake);
+next:
 	if (last_end == (u64)-1)
 		goto out;
 	start = last_end + 1;
 	if (start <= end && next_node) {
 		state = rb_entry(next_node, struct extent_state,
 				 rb_node);
-		if (state->start == start)
-			goto hit_next;
+		goto hit_next;
 	}
 	goto search_again;
 
@@ -961,8 +965,6 @@ hit_next:
 
 		set_state_bits(tree, state, &bits);
 		clear_state_bit(tree, state, &clear_bits, 0);
-
-		merge_state(tree, state);
 		if (last_end == (u64)-1)
 			goto out;
 
@@ -1007,7 +1009,6 @@ hit_next:
 		if (state->end <= end) {
 			set_state_bits(tree, state, &bits);
 			clear_state_bit(tree, state, &clear_bits, 0);
-			merge_state(tree, state);
 			if (last_end == (u64)-1)
 				goto out;
 			start = last_end + 1;
@@ -1068,8 +1069,6 @@ hit_next:
 
 		set_state_bits(tree, prealloc, &bits);
 		clear_state_bit(tree, prealloc, &clear_bits, 0);
-
-		merge_state(tree, prealloc);
 		prealloc = NULL;
 		goto out;
 	}
@@ -2154,13 +2153,46 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page,
 		 "this_mirror=%d, num_copies=%d, in_validation=%d\n", read_mode,
 		 failrec->this_mirror, num_copies, failrec->in_validation);
 
-	tree->ops->submit_bio_hook(inode, read_mode, bio, failrec->this_mirror,
-					failrec->bio_flags, 0);
-	return 0;
+	ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
+					 failrec->this_mirror,
+					 failrec->bio_flags, 0);
+	return ret;
 }
 
 /* lots and lots of room for performance fixes in the end_bio funcs */
 
+int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
+{
+	int uptodate = (err == 0);
+	struct extent_io_tree *tree;
+	int ret;
+
+	tree = &BTRFS_I(page->mapping->host)->io_tree;
+
+	if (tree->ops && tree->ops->writepage_end_io_hook) {
+		ret = tree->ops->writepage_end_io_hook(page, start,
+					       end, NULL, uptodate);
+		if (ret)
+			uptodate = 0;
+	}
+
+	if (!uptodate && tree->ops &&
+	    tree->ops->writepage_io_failed_hook) {
+		ret = tree->ops->writepage_io_failed_hook(NULL, page,
+						 start, end, NULL);
+		/* Writeback already completed */
+		if (ret == 0)
+			return 1;
+	}
+
+	if (!uptodate) {
+		clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS);
+		ClearPageUptodate(page);
+		SetPageError(page);
+	}
+	return 0;
+}
+
 /*
  * after a writepage IO is done, we need to:
  * clear the uptodate bits on error
@@ -2172,13 +2204,11 @@ static int bio_readpage_error(struct bio *failed_bio, struct page *page,
  */
 static void end_bio_extent_writepage(struct bio *bio, int err)
 {
-	int uptodate = err == 0;
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
 	struct extent_io_tree *tree;
 	u64 start;
 	u64 end;
 	int whole_page;
-	int ret;
 
 	do {
 		struct page *page = bvec->bv_page;
@@ -2195,28 +2225,9 @@ static void end_bio_extent_writepage(struct bio *bio, int err)
 
 		if (--bvec >= bio->bi_io_vec)
 			prefetchw(&bvec->bv_page->flags);
-		if (tree->ops && tree->ops->writepage_end_io_hook) {
-			ret = tree->ops->writepage_end_io_hook(page, start,
-						       end, NULL, uptodate);
-			if (ret)
-				uptodate = 0;
-		}
-
-		if (!uptodate && tree->ops &&
-		    tree->ops->writepage_io_failed_hook) {
-			ret = tree->ops->writepage_io_failed_hook(bio, page,
-							 start, end, NULL);
-			if (ret == 0) {
-				uptodate = (err == 0);
-				continue;
-			}
-		}
 
-		if (!uptodate) {
-			clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS);
-			ClearPageUptodate(page);
-			SetPageError(page);
-		}
+		if (end_extent_writepage(page, err, start, end))
+			continue;
 
 		if (whole_page)
 			end_page_writeback(page);
@@ -2779,9 +2790,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 				delalloc_start = delalloc_end + 1;
 				continue;
 			}
-			tree->ops->fill_delalloc(inode, page, delalloc_start,
-						 delalloc_end, &page_started,
-						 &nr_written);
+			ret = tree->ops->fill_delalloc(inode, page,
+						       delalloc_start,
+						       delalloc_end,
+						       &page_started,
+						       &nr_written);
+			BUG_ON(ret);
 			/*
 			 * delalloc_end is already one less than the total
 			 * length, so we don't subtract one from
@@ -2818,8 +2832,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	if (tree->ops && tree->ops->writepage_start_hook) {
 		ret = tree->ops->writepage_start_hook(page, start,
 						      page_end);
-		if (ret == -EAGAIN) {
-			redirty_page_for_writepage(wbc, page);
+		if (ret) {
+			/* Fixup worker will requeue */
+			if (ret == -EBUSY)
+				wbc->pages_skipped++;
+			else
+				redirty_page_for_writepage(wbc, page);
 			update_nr_written(page, wbc, nr_written);
 			unlock_page(page);
 			ret = 0;
@@ -3289,7 +3307,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 			len = end - start + 1;
 			write_lock(&map->lock);
 			em = lookup_extent_mapping(map, start, len);
-			if (IS_ERR_OR_NULL(em)) {
+			if (!em) {
 				write_unlock(&am