[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20231013115902.1059735-8-frederic@kernel.org>
Date: Fri, 13 Oct 2023 13:58:51 +0200
From: Frederic Weisbecker <frederic@...nel.org>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Zhen Lei <thunder.leizhen@...wei.com>,
Boqun Feng <boqun.feng@...il.com>,
Joel Fernandes <joel@...lfernandes.org>,
Josh Triplett <josh@...htriplett.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Neeraj Upadhyay <neeraj.upadhyay@....com>,
"Paul E . McKenney" <paulmck@...nel.org>,
Steven Rostedt <rostedt@...dmis.org>,
Uladzislau Rezki <urezki@...il.com>, rcu <rcu@...r.kernel.org>,
Frederic Weisbecker <frederic@...nel.org>
Subject: [PATCH 07/18] rcu: Dump memory object info if callback function is invalid
From: Zhen Lei <thunder.leizhen@...wei.com>
When a structure containing an RCU callback rhp is (incorrectly) freed
and reallocated after rhp is passed to call_rcu(), it is not unusual for
rhp->func to be set to NULL. This defeats the debugging prints used by
__call_rcu_common() in kernels built with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y,
which expect to identify the offending code using the identity of this
function.
And in kernels build without CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, things
are even worse, as can be seen from this splat:
Unable to handle kernel NULL pointer dereference at virtual address 0
... ...
PC is at 0x0
LR is at rcu_do_batch+0x1c0/0x3b8
... ...
(rcu_do_batch) from (rcu_core+0x1d4/0x284)
(rcu_core) from (__do_softirq+0x24c/0x344)
(__do_softirq) from (__irq_exit_rcu+0x64/0x108)
(__irq_exit_rcu) from (irq_exit+0x8/0x10)
(irq_exit) from (__handle_domain_irq+0x74/0x9c)
(__handle_domain_irq) from (gic_handle_irq+0x8c/0x98)
(gic_handle_irq) from (__irq_svc+0x5c/0x94)
(__irq_svc) from (arch_cpu_idle+0x20/0x3c)
(arch_cpu_idle) from (default_idle_call+0x4c/0x78)
(default_idle_call) from (do_idle+0xf8/0x150)
(do_idle) from (cpu_startup_entry+0x18/0x20)
(cpu_startup_entry) from (0xc01530)
This commit therefore adds calls to mem_dump_obj(rhp) to output some
information, for example:
slab kmalloc-256 start ffff410c45019900 pointer offset 0 size 256
This provides the rough size of the memory block and the offset of the
rcu_head structure, which as least provides at least a few clues to help
locate the problem. If the problem is reproducible, additional slab
debugging can be enabled, for example, CONFIG_DEBUG_SLAB=y, which can
provide significantly more information.
Signed-off-by: Zhen Lei <thunder.leizhen@...wei.com>
Signed-off-by: Paul E. McKenney <paulmck@...nel.org>
Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
---
kernel/rcu/rcu.h | 7 +++++++
kernel/rcu/srcutiny.c | 1 +
kernel/rcu/srcutree.c | 1 +
kernel/rcu/tasks.h | 1 +
kernel/rcu/tiny.c | 1 +
kernel/rcu/tree.c | 1 +
6 files changed, 12 insertions(+)
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98e13be411af..d612731feea4 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -10,6 +10,7 @@
#ifndef __LINUX_RCU_H
#define __LINUX_RCU_H
+#include <linux/slab.h>
#include <trace/events/rcu.h>
/*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_callback(struct rcu_head *rhp)
+{
+ if (unlikely(!rhp->func))
+ kmem_dump_obj(rhp);
+}
+
extern int rcu_cpu_stall_suppress_at_boot;
static inline bool rcu_stall_is_suppressed_at_boot(void)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 336af24e0fe3..c38e5933a5d6 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)
while (lh) {
rhp = lh;
lh = lh->next;
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index f1a905200fc2..833a8f848a90 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1710,6 +1710,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
rhp = rcu_cblist_dequeue(&ready_cbs);
for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
debug_rcu_head_unqueue(rhp);
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 8d65f7d576a3..7c845532a50a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -538,6 +538,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
len = rcl.len;
for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 42f7589e51e0..fec804b79080 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
trace_rcu_invoke_callback("", head);
f = head->func;
+ debug_rcu_head_callback(head);
WRITE_ONCE(head->func, (rcu_callback_t)0L);
f(head);
rcu_lock_release(&rcu_callback_map);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3c7281fc25a7..aae515071ffd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2135,6 +2135,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
trace_rcu_invoke_callback(rcu_state.name, rhp);
f = rhp->func;
+ debug_rcu_head_callback(rhp);
WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
f(rhp);
--
2.34.1
Powered by blists - more mailing lists