[PATCH RT 2/7] fs/dcache: disable preemption on i_dir_seqs write side

From: Steven Rostedt
Date: Thu Nov 23 2017 - 00:27:39 EST


4.9.61-rt52-rc2 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>

i_dir_seq is an opencoded seqcounter. Based on the code it looks like we
could have two writers in parallel despite the fact that the d_lock is
held. The problem is that during the write process on RT the preemption
is still enabled and if this process is interrupted by a reader with RT
priority then we lock up.
To avoid that lock up I am disabling the preemption during the update.
The rename of i_dir_seq is here to ensure to catch new write sides in
future.

Cc: stable-rt@xxxxxxxxxxxxxxx
Reported-by: Oleg.Karfich@xxxxxxxx
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
fs/dcache.c | 12 +++++++-----
fs/inode.c | 2 +-
fs/libfs.c | 6 ++++--
include/linux/fs.h | 2 +-
4 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 37948da28742..f0719b2f1be5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2409,9 +2409,10 @@ EXPORT_SYMBOL(d_rehash);
static inline unsigned start_dir_add(struct inode *dir)
{

+ preempt_disable_rt();
for (;;) {
- unsigned n = dir->i_dir_seq;
- if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+ unsigned n = dir->__i_dir_seq;
+ if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n)
return n;
cpu_relax();
}
@@ -2419,7 +2420,8 @@ static inline unsigned start_dir_add(struct inode *dir)

static inline void end_dir_add(struct inode *dir, unsigned n)
{
- smp_store_release(&dir->i_dir_seq, n + 2);
+ smp_store_release(&dir->__i_dir_seq, n + 2);
+ preempt_enable_rt();
}

static void d_wait_lookup(struct dentry *dentry)
@@ -2455,7 +2457,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,

retry:
rcu_read_lock();
- seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1;
+ seq = smp_load_acquire(&parent->d_inode->__i_dir_seq) & ~1;
r_seq = read_seqbegin(&rename_lock);
dentry = __d_lookup_rcu(parent, name, &d_seq);
if (unlikely(dentry)) {
@@ -2477,7 +2479,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
goto retry;
}
hlist_bl_lock(b);
- if (unlikely(parent->d_inode->i_dir_seq != seq)) {
+ if (unlikely(parent->d_inode->__i_dir_seq != seq)) {
hlist_bl_unlock(b);
rcu_read_unlock();
goto retry;
diff --git a/fs/inode.c b/fs/inode.c
index 920aa0b1c6b0..3d6b5fd1bf06 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -153,7 +153,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
inode->i_bdev = NULL;
inode->i_cdev = NULL;
inode->i_link = NULL;
- inode->i_dir_seq = 0;
+ inode->__i_dir_seq = 0;
inode->i_rdev = 0;
inode->dirtied_when = 0;

diff --git a/fs/libfs.c b/fs/libfs.c
index 48826d4da189..3ea54d1fc431 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -89,7 +89,7 @@ static struct dentry *next_positive(struct dentry *parent,
struct list_head *from,
int count)
{
- unsigned *seq = &parent->d_inode->i_dir_seq, n;
+ unsigned *seq = &parent->d_inode->__i_dir_seq, n;
struct dentry *res;
struct list_head *p;
bool skipped;
@@ -122,8 +122,9 @@ static struct dentry *next_positive(struct dentry *parent,
static void move_cursor(struct dentry *cursor, struct list_head *after)
{
struct dentry *parent = cursor->d_parent;
- unsigned n, *seq = &parent->d_inode->i_dir_seq;
+ unsigned n, *seq = &parent->d_inode->__i_dir_seq;
spin_lock(&parent->d_lock);
+ preempt_disable_rt();
for (;;) {
n = *seq;
if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
@@ -136,6 +137,7 @@ static void move_cursor(struct dentry *cursor, struct list_head *after)
else
list_add_tail(&cursor->d_child, &parent->d_subdirs);
smp_store_release(seq, n + 2);
+ preempt_enable_rt();
spin_unlock(&parent->d_lock);
}

diff --git a/include/linux/fs.h b/include/linux/fs.h
index d705ae084edd..ab1946f4a729 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -688,7 +688,7 @@ struct inode {
struct block_device *i_bdev;
struct cdev *i_cdev;
char *i_link;
- unsigned i_dir_seq;
+ unsigned __i_dir_seq;
};

__u32 i_generation;
--
2.13.2