github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-09-14 16:10:02 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

rcu: Reduce stack usage in show_rcu_gp_kthreads()

Browse Source 
When CONFIG_KASAN=y and CONFIG_KASAN_STACK=y builds, the
show_rcu_gp_kthreads() exceeds the 1024-byte frame-size limit:

make kernel/rcu/tree.o KCFLAGS="-fstack-usage"
  DESCEND objtool
  DESCEND bpf/resolve_btfids
  INSTALL libsubcmd_headers
  CC      kernel/rcu/tree.o
In file included from kernel/rcu/tree.c:4998:
kernel/rcu/tree_stall.h: In function 'show_rcu_gp_kthreads':
kernel/rcu/tree_stall.h:994:1: warning: the frame size of 1656 bytes is larger than 1024 bytes [-Wframe-larger-than=]

grep show_rcu kernel/rcu/tree.su
tree_nocb.h:1622:13:show_rcu_nocb_state 896     dynamic,bounded
tree_stall.h:933:6:show_rcu_gp_kthreads 1784    dynamic,bounded
tree_stall.h:1102:13:sysrq_show_rcu     16      static

Wrap the pr_info() into two noinline_for_stack helpers function:
show_rcu_state() print rcu_state status, and show_rcu_node()
print single rcu_node status.

After apply this change:

grep show_rcu kernel/rcu/tree.su
tree_stall.h:955:22:show_rcu_node	696	dynamic,bounded
tree_stall.h:930:22:show_rcu_state	872	dynamic,bounded
tree_nocb.h:1622:13:show_rcu_nocb_state	896	dynamic,bounded
tree_stall.h:972:6:show_rcu_gp_kthreads	544	static
tree_stall.h:1113:13:sysrq_show_rcu	16	static

Signed-off-by: Zqiang <qiang.zhang@linux.dev>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit is contained in:
Zqiang 2026-07-23 18:04:30 +08:00 committed by Paul E. McKenney
parent 27d73e8119
commit df0ecbc497
1 changed files with 29 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
kernel/rcu/tree_stall.h
View File

@ -927,20 +927,13 @@ bool rcu_check_boost_fail(unsigned long gp_state, int *cpup)
}
EXPORT_SYMBOL_GPL(rcu_check_boost_fail);
/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
static noinline_for_stack void show_rcu_state(void)
{
unsigned long cbs = 0;
int cpu;
unsigned long j;
unsigned long ja;
unsigned long jr;
unsigned long js;
unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
j = jiffies;
@ -957,21 +950,39 @@ void show_rcu_gp_kthreads(void)
(long)data_race(READ_ONCE(rcu_get_root()->gp_seq_needed)),
data_race(READ_ONCE(rcu_state.gp_max)),
data_race(READ_ONCE(rcu_state.gp_flags)));
}
static noinline_for_stack void show_rcu_node(struct rcu_node *rnp)
{
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld ->qsmask %#lx %c%c%c%c ->n_boosts %ld\n",
rnp->grplo, rnp->grphi,
(long)data_race(READ_ONCE(rnp->gp_seq)),
(long)data_race(READ_ONCE(rnp->gp_seq_needed)),
data_race(READ_ONCE(rnp->qsmask)),
".b"[!!data_race(READ_ONCE(rnp->boost_kthread_task))],
".B"[!!data_race(READ_ONCE(rnp->boost_tasks))],
".E"[!!data_race(READ_ONCE(rnp->exp_tasks))],
".G"[!!data_race(READ_ONCE(rnp->gp_tasks))],
data_race(READ_ONCE(rnp->n_boosts)));
}
/*
* Show the state of the grace-period kthreads.
*/
void show_rcu_gp_kthreads(void)
{
unsigned long cbs = 0;
int cpu;
struct rcu_data *rdp;
struct rcu_node *rnp;
show_rcu_state();
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq), READ_ONCE(rnp->gp_seq_needed)) &&
!data_race(READ_ONCE(rnp->qsmask)) && !data_race(READ_ONCE(rnp->boost_tasks)) &&
!data_race(READ_ONCE(rnp->exp_tasks)) && !data_race(READ_ONCE(rnp->gp_tasks)))
continue;
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld ->qsmask %#lx %c%c%c%c ->n_boosts %ld\n",
rnp->grplo, rnp->grphi,
(long)data_race(READ_ONCE(rnp->gp_seq)),
(long)data_race(READ_ONCE(rnp->gp_seq_needed)),
data_race(READ_ONCE(rnp->qsmask)),
".b"[!!data_race(READ_ONCE(rnp->boost_kthread_task))],
".B"[!!data_race(READ_ONCE(rnp->boost_tasks))],
".E"[!!data_race(READ_ONCE(rnp->exp_tasks))],
".G"[!!data_race(READ_ONCE(rnp->gp_tasks))],
data_race(READ_ONCE(rnp->n_boosts)));
show_rcu_node(rnp);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {