Re: [PATCH 1/2] tracing: fgraph: Raise FTRACE_RETSTACK_ALLOC_SIZE to 1024

[Peter Zijlstra <peterz@infradead.org>]

On Tue, Sep 22, 2026 at 03:55:25PM -0700, Vineet Gupta wrote:
> When ftrace graphing is turned on, all tasks in the system missing
> return stack page are assigned one. This is done in a simplistic
> multi-sweep loop of FTRACE_RETSTACK_ALLOC_SIZE (currently 32) tasks
> at a time as follows:
> 
>    start_graph_tracing()
> 	do {
> 		alloc_retstack_tasklist
> 	} while (-EAGAIN);
> 
>    alloc_retstack_tasklist()
> 	alloc x32           # GFP_KERNEL, may sleep
> 	rcu_read_lock()     # preempt off
> 		for_each_process_thread    walk N_total, no cond_resched
>                      t->ret_stack = new_page
> 	rcu_read_unlock()   # preempt enable but no explicit yield
> 
> Each successive iteration of loop invokes for_each_process_thread()
> which doesn't support cursor based resume and always restarts from the
> init_task. Thus each successive loop needs to skip the tasks assigned
> ret_stack in prior sweeps and thus take longer and longer to find the
> candidate 32 tasks. 

Does this work?

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index ed455b53513b..155dafad474d 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1036,10 +1036,9 @@ trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 {
-	int i;
-	int ret = 0;
 	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
 	struct task_struct *g, *t;
+	int i, ret = 0;
 
 	if (WARN_ON_ONCE(!fgraph_stack_cachep))
 		return -ENOMEM;
@@ -1054,26 +1053,29 @@ static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 		}
 	}
 
-	rcu_read_lock();
-	for_each_process_thread(g, t) {
-		if (start == end) {
-			ret = -EAGAIN;
-			goto unlock;
-		}
+	scoped_guard (rcu) {
+		for_each_process_thread(g, t) {
+			unsigned long *rs;
+
+			if (t->ret_stack)
+				continue;
+
+			rs = kmem_cache_alloc(fgraph_stack_cachep, GFP_NOWAIT);
+			if (!rs) {
+				if (start == end)
+					return -EAGAIN;
+				rs = ret_stack_list[start++];
+			}
 
-		if (t->ret_stack == NULL) {
 			atomic_set(&t->trace_overrun, 0);
-			ret_stack_init_task_vars(ret_stack_list[start]);
+			ret_stack_init_task_vars(rs);
 			t->curr_ret_stack = 0;
 			t->curr_ret_depth = -1;
 			/* Make sure the tasks see the 0 first: */
-			smp_wmb();
-			t->ret_stack = ret_stack_list[start++];
+			smp_store_release(&t->ret_stack, rs);
 		}
 	}
 
-unlock:
-	rcu_read_unlock();
 free:
 	for (i = start; i < end; i++)
 		kmem_cache_free(fgraph_stack_cachep, ret_stack_list[i]);