This is a note to let you know that I've just added the patch titled
ring-buffer: Sync IRQ works before buffer destruction
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
ring-buffer-sync-irq-works-before-buffer-destruction.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 675751bb20634f981498c7d66161584080cc061e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@xxxxxxxxx>
Date: Thu, 27 Apr 2023 17:59:20 +0200
Subject: ring-buffer: Sync IRQ works before buffer destruction
From: Johannes Berg <johannes.berg@xxxxxxxxx>
commit 675751bb20634f981498c7d66161584080cc061e upstream.
If something was written to the buffer just before destruction,
it may be possible (maybe not in a real system, but it did
happen in ARCH=um with time-travel) to destroy the ringbuffer
before the IRQ work ran, leading this KASAN report (or a crash
without KASAN):
BUG: KASAN: slab-use-after-free in irq_work_run_list+0x11a/0x13a
Read of size 8 at addr 000000006d640a48 by task swapper/0
CPU: 0 PID: 0 Comm: swapper Tainted: G W O 6.3.0-rc1 #7
Stack:
60c4f20f 0c203d48 41b58ab3 60f224fc
600477fa 60f35687 60c4f20f 601273dd
00000008 6101eb00 6101eab0 615be548
Call Trace:
[<60047a58>] show_stack+0x25e/0x282
[<60c609e0>] dump_stack_lvl+0x96/0xfd
[<60c50d4c>] print_report+0x1a7/0x5a8
[<603078d3>] kasan_report+0xc1/0xe9
[<60308950>] __asan_report_load8_noabort+0x1b/0x1d
[<60232844>] irq_work_run_list+0x11a/0x13a
[<602328b4>] irq_work_tick+0x24/0x34
[<6017f9dc>] update_process_times+0x162/0x196
[<6019f335>] tick_sched_handle+0x1a4/0x1c3
[<6019fd9e>] tick_sched_timer+0x79/0x10c
[<601812b9>] __hrtimer_run_queues.constprop.0+0x425/0x695
[<60182913>] hrtimer_interrupt+0x16c/0x2c4
[<600486a3>] um_timer+0x164/0x183
[...]
Allocated by task 411:
save_stack_trace+0x99/0xb5
stack_trace_save+0x81/0x9b
kasan_save_stack+0x2d/0x54
kasan_set_track+0x34/0x3e
kasan_save_alloc_info+0x25/0x28
____kasan_kmalloc+0x8b/0x97
__kasan_kmalloc+0x10/0x12
__kmalloc+0xb2/0xe8
load_elf_phdrs+0xee/0x182
[...]
The buggy address belongs to the object at 000000006d640800
which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 584 bytes inside of
freed 1024-byte region [000000006d640800, 000000006d640c00)
Add the appropriate irq_work_sync() so the work finishes before
the buffers are destroyed.
Prior to the commit in the Fixes tag below, there was only a
single global IRQ work, so this issue didn't exist.
Link: https://lore.kernel.org/linux-trace-kernel/20230427175920.a76159263122.I8295e405c44362a86c995e9c2c37e3e03810aa56@changeid
Cc: stable@xxxxxxxxxxxxxxx
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Fixes: 15693458c4bc ("tracing/ring-buffer: Move poll wake ups into ring buffer code")
Signed-off-by: Johannes Berg <johannes.berg@xxxxxxxxx>
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/trace/ring_buffer.c | 4 ++++
1 file changed, 4 insertions(+)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1778,6 +1778,8 @@ static void rb_free_cpu_buffer(struct ri
struct list_head *head = cpu_buffer->pages;
struct buffer_page *bpage, *tmp;
+ irq_work_sync(&cpu_buffer->irq_work.work);
+
free_buffer_page(cpu_buffer->reader_page);
if (head) {
@@ -1884,6 +1886,8 @@ ring_buffer_free(struct trace_buffer *bu
cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+ irq_work_sync(&buffer->irq_work.work);
+
for_each_buffer_cpu(buffer, cpu)
rb_free_cpu_buffer(buffer->buffers[cpu]);
Patches currently in stable-queue which might be from johannes.berg@xxxxxxxxx are
queue-6.1/ring-buffer-sync-irq-works-before-buffer-destruction.patch
