[PATCH] f2fs: call radix_tree_preload before radix_tree_insert

[Jaegeuk Kim]

This patch tries to fix:

 BUG: using smp_processor_id() in preemptible [00000000] code: f2fs_gc-254:0/384
  (radix_tree_node_alloc+0x14/0x74) from [<c033d8a0>] (radix_tree_insert+0x110/0x200)
  (radix_tree_insert+0x110/0x200) from [<c02e8264>] (gc_data_segment+0x340/0x52c)
  (gc_data_segment+0x340/0x52c) from [<c02e8658>] (f2fs_gc+0x208/0x400)
  (f2fs_gc+0x208/0x400) from [<c02e8a98>] (gc_thread_func+0x248/0x28c)
  (gc_thread_func+0x248/0x28c) from [<c0139944>] (kthread+0xa0/0xac)
  (kthread+0xa0/0xac) from [<c0105ef8>] (ret_from_fork+0x14/0x3c)

The reason is that f2fs calls radix_tree_insert under enabled preemption.
So, before calling it, we need to call radix_tree_preload.

Otherwise, we should use _GFP_WAIT for the radix tree, and use mutex or
semaphore to cover the radix tree operations.

Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
---
 fs/f2fs/checkpoint.c |  8 ++++++++
 fs/f2fs/gc.c         |  6 ++----
 fs/f2fs/node.c       | 11 +++++++++--
 3 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 20a917b..6a81b73 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -304,6 +304,11 @@ static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 	struct inode_management *im = &sbi->im[type];
 	struct ino_entry *e;
 retry:
+	if (radix_tree_preload(GFP_NOFS)) {
+		cond_resched();
+		goto retry;
+	}
+
 	spin_lock(&im->ino_lock);
 
 	e = radix_tree_lookup(&im->ino_root, ino);
@@ -311,11 +316,13 @@ retry:
 		e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
 		if (!e) {
 			spin_unlock(&im->ino_lock);
+			radix_tree_preload_end();
 			goto retry;
 		}
 		if (radix_tree_insert(&im->ino_root, ino, e)) {
 			spin_unlock(&im->ino_lock);
 			kmem_cache_free(ino_entry_slab, e);
+			radix_tree_preload_end();
 			goto retry;
 		}
 		memset(e, 0, sizeof(struct ino_entry));
@@ -326,6 +333,7 @@ retry:
 			im->ino_num++;
 	}
 	spin_unlock(&im->ino_lock);
+	radix_tree_preload_end();
 }
 
 static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index a1af74f..2c58c58 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -351,7 +351,6 @@ static struct inode *find_gc_inode(struct gc_inode_list *gc_list, nid_t ino)
 static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 {
 	struct inode_entry *new_ie;
-	int ret;
 
 	if (inode == find_gc_inode(gc_list, inode->i_ino)) {
 		iput(inode);
@@ -361,8 +360,7 @@ retry:
 	new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
 	new_ie->inode = inode;
 
-	ret = radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
-	if (ret) {
+	if (radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie)) {
 		kmem_cache_free(winode_slab, new_ie);
 		goto retry;
 	}
@@ -703,7 +701,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 	struct cp_control cpc;
 	struct gc_inode_list gc_list = {
 		.ilist = LIST_HEAD_INIT(gc_list.ilist),
-		.iroot = RADIX_TREE_INIT(GFP_ATOMIC),
+		.iroot = RADIX_TREE_INIT(GFP_NOFS),
 	};
 
 	cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b47555f..8de4f55 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1447,15 +1447,22 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 	i->nid = nid;
 	i->state = NID_NEW;
 
+	if (radix_tree_preload(GFP_NOFS)) {
+		kmem_cache_free(free_nid_slab, i);
+		return 0;
+	}
+
 	spin_lock(&nm_i->free_nid_list_lock);
 	if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
 		spin_unlock(&nm_i->free_nid_list_lock);
+		radix_tree_preload_end();
 		kmem_cache_free(free_nid_slab, i);
 		return 0;
 	}
 	list_add_tail(&i->list, &nm_i->free_nid_list);
 	nm_i->fcnt++;
 	spin_unlock(&nm_i->free_nid_list_lock);
+	radix_tree_preload_end();
 	return 1;
 }
 
@@ -1994,8 +2001,8 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
 	INIT_LIST_HEAD(&nm_i->free_nid_list);
-	INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC);
-	INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_ATOMIC);
+	INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
+	INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
 	INIT_LIST_HEAD(&nm_i->nat_entries);
 
 	mutex_init(&nm_i->build_lock);
-- 
2.1.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/