Prev: [tip:perf/core] perf, x86: Call x86_setup_perfctr() from .hw_config()
Next: [tip:perf/core] perf, x86: Pass enable bit mask to __x86_pmu_enable_event()
From: tip-bot for Yong Zhang on 7 May 2010 14:50
Commit-ID: 4726f2a617ebd868a4fdeb5679613b897e5f1676
Gitweb: http://git.kernel.org/tip/4726f2a617ebd868a4fdeb5679613b897e5f1676
Author: Yong Zhang <yong.zhang(a)windriver.com>
AuthorDate: Tue, 4 May 2010 14:16:48 +0800
Committer: Ingo Molnar <mingo(a)elte.hu>
CommitDate: Fri, 7 May 2010 11:27:26 +0200

lockdep: Reduce stack_trace usage

When calling check_prevs_add(), if all validations passed
add_lock_to_list() will add new lock to dependency tree and
alloc stack_trace for each list_entry.

But at this time, we are always on the same stack, so stack_trace
for each list_entry has the same value. This is redundant and eats
up lots of memory which could lead to warning on low
MAX_STACK_TRACE_ENTRIES.

Use one copy of stack_trace instead.

V2: As suggested by Peter Zijlstra, move save_trace() from
check_prevs_add() to check_prev_add().
Add tracking for trylock dependence which is also redundant.

Signed-off-by: Yong Zhang <yong.zhang0(a)windriver.com>
Cc: David S. Miller <davem(a)davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl>
LKML-Reference: <20100504065711.GC10784(a)windriver.com>
Signed-off-by: Ingo Molnar <mingo(a)elte.hu>
---
kernel/lockdep.c | 29 +++++++++++++++++++++--------
1 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 9cf7985..5108080 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -805,7 +805,8 @@ static struct lock_list *alloc_list_entry(void)
* Add a new dependency to the head of the list:
*/
static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
- struct list_head *head, unsigned long ip, int distance)
+ struct list_head *head, unsigned long ip,
+ int distance, struct stack_trace *trace)
{
struct lock_list *entry;
/*
@@ -816,11 +817,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
if (!entry)
return 0;

- if (!save_trace(&entry->trace))
- return 0;
-
entry->class = this;
entry->distance = distance;
+ entry->trace = *trace;
/*
* Since we never remove from the dependency list, the list can
* be walked lockless by other CPUs, it's only allocation
@@ -1622,12 +1621,20 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
*/
static int
check_prev_add(struct task_struct *curr, struct held_lock *prev,
- struct held_lock *next, int distance)
+ struct held_lock *next, int distance, int trylock_loop)
{
struct lock_list *entry;
int ret;
struct lock_list this;
struct lock_list *uninitialized_var(target_entry);
+ /*
+ * Static variable, serialized by the graph_lock().
+ *
+ * We use this static variable to save the stack trace in case
+ * we call into this function multiple times due to encountering
+ * trylocks in the held lock stack.
+ */
+ static struct stack_trace trace;

/*
* Prove that the new <prev> -> <next> dependency would not
@@ -1675,20 +1682,23 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
}
}

+ if (!trylock_loop && !save_trace(&trace))
+ return 0;
+
/*
* Ok, all validations passed, add the new lock
* to the previous lock's dependency list:
*/
ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
&hlock_class(prev)->locks_after,
- next->acquire_ip, distance);
+ next->acquire_ip, distance, &trace);

if (!ret)
return 0;

ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
&hlock_class(next)->locks_before,
- next->acquire_ip, distance);
+ next->acquire_ip, distance, &trace);
if (!ret)
return 0;

@@ -1718,6 +1728,7 @@ static int
check_prevs_add(struct task_struct *curr, struct held_lock *next)
{
int depth = curr->lockdep_depth;
+ int trylock_loop = 0;
struct held_lock *hlock;

/*
@@ -1743,7 +1754,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
* added:
*/
if (hlock->read != 2) {
- if (!check_prev_add(curr, hlock, next, distance))
+ if (!check_prev_add(curr, hlock, next,
+ distance, trylock_loop))
return 0;
/*
* Stop after the first non-trylock entry,
@@ -1766,6 +1778,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
if (curr->held_locks[depth].irq_context !=
curr->held_locks[depth-1].irq_context)
break;
+ trylock_loop = 1;
}
return 1;
out_bug:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
 | 
Pages: 1
Prev: [tip:perf/core] perf, x86: Call x86_setup_perfctr() from .hw_config()
Next: [tip:perf/core] perf, x86: Pass enable bit mask to __x86_pmu_enable_event()