Re: [syzbot] [mm?] INFO: rcu detected stall in exit_to_user_mode_loop

Re: [syzbot] [mm?] INFO: rcu detected stall in exit_to_user_mode_loop

[syzbot]

syzbot has found a reproducer for the following issue on:

HEAD commit:    afd8c2c9e2e2 Merge branch 'ipv6-f6i-fib6_siblings-and-rt-f..
git tree:       net
console output: https://syzkaller.appspot.com/x/log.txt?x=13c71034580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=a4bcc0a11b3192be
dashboard link: https://syzkaller.appspot.com/bug?extid=2642f347f7309b4880dc
compiler:       Debian clang version 20.1.7 (++20250616065708+6146a88f6049-1~exp1~20250616065826.132), Debian LLD 20.1.7
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=17b284a2580000
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=17c71034580000

Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/6f29edec8e85/disk-afd8c2c9.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/8490ef85f5cd/vmlinux-afd8c2c9.xz
kernel image: https://storage.googleapis.com/syzbot-assets/1357e17669cb/bzImage-afd8c2c9.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+2642f347f7309b4880dc@syzkaller.appspotmail.com

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
rcu: 	0-...!: (3 ticks this GP) idle=8da4/1/0x4000000000000000 softirq=18768/18768 fqs=0
rcu: 	(detected by 1, t=10502 jiffies, g=13833, q=887 ncpus=2)
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 UID: 0 PID: 5983 Comm: syz-executor Not tainted 6.16.0-rc7-syzkaller-00100-gafd8c2c9e2e2 #0 PREEMPT(full) 
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:__lock_acquire+0x316/0xd20 kernel/locking/lockdep.c:5188
Code: 8b 54 24 0c 83 e2 01 c1 e2 12 44 09 e2 41 c1 e6 14 41 09 d6 8b 54 24 10 c1 e2 13 c1 e5 15 09 d5 09 cd 44 09 f5 41 89 6c c7 20 <45> 89 44 c7 24 4c 89 7c 24 10 4d 8d 34 c7 81 e5 ff 1f 00 00 48 0f
RSP: 0018:ffffc90000007b40 EFLAGS: 00000002
RAX: 000000000000000a RBX: ffffffff8e13f0e0 RCX: 0000000000000007
RDX: 0000000000080000 RSI: 0000000000004000 RDI: ffff88802c368000
RBP: 00000000000a4007 R08: 0000000000000000 R09: ffffffff898d70e8
R10: dffffc0000000000 R11: ffffed100fc2785e R12: 0000000000024000
R13: 0000000000000000 R14: 0000000000024000 R15: ffff88802c368af0
FS:  0000000000000000(0000) GS:ffff888125c23000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055556e2015c8 CR3: 000000000df38000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 lock_acquire+0x120/0x360 kernel/locking/lockdep.c:5871
 rcu_lock_acquire include/linux/rcupdate.h:331 [inline]
 rcu_read_lock include/linux/rcupdate.h:841 [inline]
 advance_sched+0xa14/0xc90 net/sched/sch_taprio.c:985
 __run_hrtimer kernel/time/hrtimer.c:1761 [inline]
 __hrtimer_run_queues+0x52c/0xc60 kernel/time/hrtimer.c:1825
 hrtimer_interrupt+0x45b/0xaa0 kernel/time/hrtimer.c:1887
 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1039 [inline]
 __sysvec_apic_timer_interrupt+0x108/0x410 arch/x86/kernel/apic/apic.c:1056
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline]
 sysvec_apic_timer_interrupt+0xa1/0xc0 arch/x86/kernel/apic/apic.c:1050
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
RIP: 0010:debug_lockdep_rcu_enabled+0xf/0x40 kernel/rcu/update.c:320
Code: cc cc cc cc cc cc cc cc cc cc cc 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 31 c0 83 3d 17 30 34 04 00 74 1e <83> 3d 3a 60 34 04 00 74 15 65 48 8b 0c 25 08 d0 9f 92 31 c0 83 b9
RSP: 0018:ffffc90003f0ef70 EFLAGS: 00000202
RAX: 0000000000000000 RBX: ffffffff90d8d001 RCX: ffffc90003f0ff60
RDX: ffffc90003f0f001 RSI: dffffc0000000000 RDI: ffffc90003f0f050
RBP: dffffc0000000000 R08: ffffc90003f0ff48 R09: 0000000000000000
R10: ffffc90003f0f098 R11: fffff520007e1e15 R12: ffffc90003f0ff58
R13: ffffc90003f08000 R14: ffffc90003f0f048 R15: ffffffff8172aae5
 rcu_read_unlock include/linux/rcupdate.h:869 [inline]
 class_rcu_destructor include/linux/rcupdate.h:1155 [inline]
 unwind_next_frame+0x195c/0x2390 arch/x86/kernel/unwind_orc.c:680
 arch_stack_walk+0x11c/0x150 arch/x86/kernel/stacktrace.c:25
 stack_trace_save+0x9c/0xe0 kernel/stacktrace.c:122
 save_stack+0xf5/0x1f0 mm/page_owner.c:156
 __reset_page_owner+0x71/0x1f0 mm/page_owner.c:308
 reset_page_owner include/linux/page_owner.h:25 [inline]
 free_pages_prepare mm/page_alloc.c:1248 [inline]
 free_unref_folios+0xc66/0x14d0 mm/page_alloc.c:2763
 folios_put_refs+0x559/0x640 mm/swap.c:992
 free_pages_and_swap_cache+0x277/0x520 mm/swap_state.c:264
 __tlb_batch_free_encoded_pages mm/mmu_gather.c:136 [inline]
 tlb_batch_pages_flush mm/mmu_gather.c:149 [inline]
 tlb_flush_mmu_free mm/mmu_gather.c:397 [inline]
 tlb_flush_mmu+0x3a0/0x680 mm/mmu_gather.c:404
 tlb_finish_mmu+0xc3/0x1d0 mm/mmu_gather.c:497
 exit_mmap+0x44c/0xb50 mm/mmap.c:1297
 __mmput+0x118/0x420 kernel/fork.c:1121
 exit_mm+0x1da/0x2c0 kernel/exit.c:581
 do_exit+0x648/0x22e0 kernel/exit.c:952
 do_group_exit+0x21c/0x2d0 kernel/exit.c:1105
 get_signal+0x1286/0x1340 kernel/signal.c:3034
 arch_do_signal_or_restart+0x9a/0x750 arch/x86/kernel/signal.c:337
 exit_to_user_mode_loop+0x75/0x110 kernel/entry/common.c:111
 exit_to_user_mode_prepare include/linux/entry-common.h:330 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:414 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:449 [inline]
 do_syscall_64+0x2bd/0x3b0 arch/x86/entry/syscall_64.c:100
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f730c585213
Code: Unable to access opcode bytes at 0x7f730c5851e9.
RSP: 002b:00007ffe0103af48 EFLAGS: 00000246 ORIG_RAX: 0000000000000038
RAX: fffffffffffffffc RBX: 0000000000000000 RCX: 00007f730c585213
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011
RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
R10: 000055556e1e67d0 R11: 0000000000000246 R12: 0000000000000000
R13: 00000000000927c0 R14: 000000000003604b R15: 00007ffe0103b0e0
 </TASK>
rcu: rcu_preempt kthread timer wakeup didn't happen for 10501 jiffies! g13833 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402
rcu: 	Possible timer handling issue on cpu=0 timer-softirq=10563
rcu: rcu_preempt kthread starved for 10502 jiffies! g13833 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=0
rcu: 	Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior.
rcu: RCU grace-period kthread stack dump:
task:rcu_preempt     state:I stack:26792 pid:16    tgid:16    ppid:2      task_flags:0x208040 flags:0x00004000
Call Trace:
 <TASK>
 context_switch kernel/sched/core.c:5397 [inline]
 __schedule+0x16fd/0x4cf0 kernel/sched/core.c:6786
 __schedule_loop kernel/sched/core.c:6864 [inline]
 schedule+0x165/0x360 kernel/sched/core.c:6879
 schedule_timeout+0x12b/0x270 kernel/time/sleep_timeout.c:99
 rcu_gp_fqs_loop+0x301/0x1540 kernel/rcu/tree.c:2054
 rcu_gp_kthread+0x99/0x390 kernel/rcu/tree.c:2256
 kthread+0x70e/0x8a0 kernel/kthread.c:464
 ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>


---
If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

Re: [syzbot] [mm?] INFO: rcu detected stall in exit_to_user_mode_loop

[syzbot]

Hello,

syzbot has tested the proposed patch and the reproducer did not trigger any issue:

Reported-by: syzbot+2642f347f7309b4880dc@syzkaller.appspotmail.com
Tested-by: syzbot+2642f347f7309b4880dc@syzkaller.appspotmail.com

Tested on:

commit:         24ef02f9 net: page_pool: fix UAF in __page_pool_releas..
git tree:       git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
console output: https://syzkaller.appspot.com/x/log.txt?x=15742679580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=d07fbc6821d72a61
dashboard link: https://syzkaller.appspot.com/bug?extid=2642f347f7309b4880dc
compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
patch:          https://syzkaller.appspot.com/x/patch.diff?x=16b1ea25580000

Note: testing is done by a robot and is best-effort only.

Re: [syzbot] [mm?] INFO: rcu detected stall in exit_to_user_mode_loop

[Junjie Cao]

#syz test: git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git 24ef02f934eeb48830cff6b739abc3c62b1d107b

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 299234a5f0fe..7519bc5c1aff 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -259,6 +259,26 @@ static int length_to_duration(struct taprio_sched *q, int len)
 	return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC);
 }
 
+/* Software schedules service one hrtimer expiry per entry; intervals
+ * shorter than the expiry service cost rearm the timer with an expiry
+ * already in the past and storm the CPU. 100us leaves margin above the
+ * measured cost on debug configurations.
+ */
+#define TAPRIO_MIN_SW_INTERVAL_NS	(100 * NSEC_PER_USEC)
+
+static s64 taprio_min_interval(struct taprio_sched *q)
+{
+	s64 min_interval = length_to_duration(q, ETH_ZLEN);
+
+	/* Only pure software schedules arm the per-entry hrtimer. */
+	if (!FULL_OFFLOAD_IS_ENABLED(q->flags) &&
+	    !TXTIME_ASSIST_IS_ENABLED(q->flags))
+		min_interval = max_t(s64, min_interval,
+				     TAPRIO_MIN_SW_INTERVAL_NS);
+
+	return min_interval;
+}
+
 static int duration_to_length(struct taprio_sched *q, u64 duration)
 {
 	return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte));
@@ -915,6 +935,51 @@ static bool should_change_schedules(const struct sched_gate_list *admin,
 	return false;
 }
 
+/* The operational schedule fell behind, e.g. because the timer was delayed
+ * or the reference clock stepped forward. Advancing one entry per timer
+ * expiry would replay the whole backlog from hrtimer context, so skip
+ * complete cycles arithmetically and walk the remaining entries to land on
+ * the entry covering the current time.
+ */
+static void taprio_catch_up(struct sched_gate_list *oper,
+			    struct sched_entry **next, ktime_t *next_start,
+			    ktime_t *end_time, ktime_t now)
+{
+	int budget = 2 * oper->num_entries + 1;
+	struct sched_entry *entry = *next;
+	ktime_t start = *next_start;
+	ktime_t end = *end_time;
+	s64 behind = ktime_sub(now, end);
+
+	if (oper->cycle_time > 0 && behind >= oper->cycle_time) {
+		s64 jump = div64_s64(behind, oper->cycle_time) * oper->cycle_time;
+
+		start = ktime_add_ns(start, jump);
+		end = ktime_add_ns(end, jump);
+		oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, jump);
+	}
+
+	while (ktime_before(end, now) && --budget) {
+		if (list_is_last(&entry->list, &oper->entries) ||
+		    ktime_compare(end, oper->cycle_end_time) == 0) {
+			entry = list_first_entry(&oper->entries,
+						 struct sched_entry, list);
+			oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time,
+							    oper->cycle_time);
+		} else {
+			entry = list_next_entry(entry, list);
+		}
+
+		start = end;
+		end = ktime_add_ns(end, entry->interval);
+		end = min_t(ktime_t, end, oper->cycle_end_time);
+	}
+
+	*next = entry;
+	*next_start = start;
+	*end_time = end;
+}
+
 static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 {
 	struct taprio_sched *q = container_of(timer, struct taprio_sched,
@@ -924,7 +989,7 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 	int num_tc = netdev_get_num_tc(dev);
 	struct sched_entry *entry, *next;
 	struct Qdisc *sch = q->root;
-	ktime_t end_time;
+	ktime_t end_time, next_start, now;
 	int tc;
 
 	spin_lock(&q->current_entry_lock);
@@ -960,14 +1025,19 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 		next = list_next_entry(entry, list);
 	}
 
-	end_time = ktime_add_ns(entry->end_time, next->interval);
+	next_start = entry->end_time;
+	end_time = ktime_add_ns(next_start, next->interval);
 	end_time = min_t(ktime_t, end_time, oper->cycle_end_time);
 
+	now = taprio_get_time(q);
+	if (unlikely(ktime_before(end_time, now)))
+		taprio_catch_up(oper, &next, &next_start, &end_time, now);
+
 	for (tc = 0; tc < num_tc; tc++) {
 		if (next->gate_duration[tc] == oper->cycle_time)
 			next->gate_close_time[tc] = KTIME_MAX;
 		else
-			next->gate_close_time[tc] = ktime_add_ns(entry->end_time,
+			next->gate_close_time[tc] = ktime_add_ns(next_start,
 								 next->gate_duration[tc]);
 	}
 
@@ -1038,7 +1108,7 @@ static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
 			    struct sched_entry *entry,
 			    struct netlink_ext_ack *extack)
 {
-	int min_duration = length_to_duration(q, ETH_ZLEN);
+	s64 min_duration = taprio_min_interval(q);
 	u32 interval = 0;
 
 	if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
@@ -1166,7 +1236,7 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 		new->cycle_time = cycle;
 	}
 
-	if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) {
+	if (new->cycle_time < (s64)new->num_entries * taprio_min_interval(q)) {
 		NL_SET_ERR_MSG(extack, "'cycle_time' is too small");
 		return -EINVAL;
 	}