From: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
As per changes in include/linux/jbd_common.h for avoiding the
bit_spin_locks on RT ("fs: jbd/jbd2: Make state lock and journal
head lock rt safe") we do the same thing here.
We use the non atomic __set_bit and __clear_bit inside the scope of
the lock to preserve the ability of the existing LIST_DEBUG code to
use the zero'th bit in the sanity checks.
As a bit spinlock, we had no lockdep visibility into the usage
of the list head locking. Now, if we were to implement it as a
standard non-raw spinlock, we would see:
BUG: sleeping function called from invalid context at kernel/rtmutex.c:658
in_atomic(): 1, irqs_disabled(): 0, pid: 122, name: udevd
5 locks held by udevd/122:
#0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [<ffffffff811967e8>] lock_rename+0xe8/0xf0
#1: (rename_lock){+.+...}, at: [<ffffffff811a277c>] d_move+0x2c/0x60
#2: (&dentry->d_lock){+.+...}, at: [<ffffffff811a0763>] dentry_lock_for_move+0xf3/0x130
#3: (&dentry->d_lock/2){+.+...}, at: [<ffffffff811a0734>] dentry_lock_for_move+0xc4/0x130
#4: (&dentry->d_lock/3){+.+...}, at: [<ffffffff811a0747>] dentry_lock_for_move+0xd7/0x130
Pid: 122, comm: udevd Not tainted 3.4.47-rt62 #7
Call Trace:
[<ffffffff810b9624>] __might_sleep+0x134/0x1f0
[<ffffffff817a24d4>] rt_spin_lock+0x24/0x60
[<ffffffff811a0c4c>] __d_shrink+0x5c/0xa0
[<ffffffff811a1b2d>] __d_drop+0x1d/0x40
[<ffffffff811a24be>] __d_move+0x8e/0x320
[<ffffffff811a278e>] d_move+0x3e/0x60
[<ffffffff81199598>] vfs_rename+0x198/0x4c0
[<ffffffff8119b093>] sys_renameat+0x213/0x240
[<ffffffff817a2de5>] ? _raw_spin_unlock+0x35/0x60
[<ffffffff8107781c>] ? do_page_fault+0x1ec/0x4b0
[<ffffffff817a32ca>] ? retint_swapgs+0xe/0x13
[<ffffffff813eb0e6>] ? trace_hardirqs_on_thunk+0x3a/0x3f
[<ffffffff8119b0db>] sys_rename+0x1b/0x20
[<ffffffff817a3b96>] system_call_fastpath+0x1a/0x1f
Since we are only taking the lock during short lived list operations,
lets assume for now that it being raw won't be a significant latency
concern.
Cc: stable-rt@xxxxxxxxxxxxxxx
Signed-off-by: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
include/linux/list_bl.h | 24 ++++++++++++++++++++++--
1 file changed, 22 insertions(+), 2 deletions(-)
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 31f9d75..ddfd46a 100644
--- a/include/linux/list_bl.h
+++ b/include/linux/list_bl.h
@@ -2,6 +2,7 @@
#define _LINUX_LIST_BL_H
#include <linux/list.h>
+#include <linux/spinlock.h>
#include <linux/bit_spinlock.h>
/*
@@ -32,13 +33,22 @@
struct hlist_bl_head {
struct hlist_bl_node *first;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ raw_spinlock_t lock;
+#endif
};
struct hlist_bl_node {
struct hlist_bl_node *next, **pprev;
};
-#define INIT_HLIST_BL_HEAD(ptr) \
- ((ptr)->first = NULL)
+
+static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h)
+{
+ h->first = NULL;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ raw_spin_lock_init(&h->lock);
+#endif
+}
static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
{
@@ -117,12 +127,22 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n)
static inline void hlist_bl_lock(struct hlist_bl_head *b)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(0, (unsigned long *)b);
+#else
+ raw_spin_lock(&b->lock);
+ __set_bit(0, (unsigned long *)b);
+#endif
}
static inline void hlist_bl_unlock(struct hlist_bl_head *b)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
__bit_spin_unlock(0, (unsigned long *)b);
+#else
+ __clear_bit(0, (unsigned long *)b);
+ raw_spin_unlock(&b->lock);
+#endif
}
/**
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe stable-rt" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
