linux-stable/kernel/rcu/tiny.c
Zhen Lei 2cbc482d32 rcu: Dump memory object info if callback function is invalid
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@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
2023-09-13 22:29:12 +02:00

264 lines
7 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
*
* Copyright IBM Corporation, 2008
*
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#include <linux/completion.h>
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/rcupdate_wait.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/cpu.h>
#include <linux/prefetch.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include "rcu.h"
/* Global control variables for rcupdate callback mechanism. */
struct rcu_ctrlblk {
struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
struct rcu_head **curtail; /* ->next pointer of last CB. */
unsigned long gp_seq; /* Grace-period counter. */
};
/* Definition for rcupdate control block. */
static struct rcu_ctrlblk rcu_ctrlblk = {
.donetail = &rcu_ctrlblk.rcucblist,
.curtail = &rcu_ctrlblk.rcucblist,
.gp_seq = 0 - 300UL,
};
void rcu_barrier(void)
{
wait_rcu_gp(call_rcu_hurry);
}
EXPORT_SYMBOL(rcu_barrier);
/* Record an rcu quiescent state. */
void rcu_qs(void)
{
unsigned long flags;
local_irq_save(flags);
if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
raise_softirq_irqoff(RCU_SOFTIRQ);
}
WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
local_irq_restore(flags);
}
/*
* Check to see if the scheduling-clock interrupt came from an extended
* quiescent state, and, if so, tell RCU about it. This function must
* be called from hardirq context. It is normally called from the
* scheduling-clock interrupt.
*/
void rcu_sched_clock_irq(int user)
{
if (user) {
rcu_qs();
} else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
}
/*
* Reclaim the specified callback, either by invoking it for non-kfree cases or
* freeing it directly (for kfree). Return true if kfreeing, false otherwise.
*/
static inline bool rcu_reclaim_tiny(struct rcu_head *head)
{
rcu_callback_t f;
unsigned long offset = (unsigned long)head->func;
rcu_lock_acquire(&rcu_callback_map);
if (__is_kvfree_rcu_offset(offset)) {
trace_rcu_invoke_kvfree_callback("", head, offset);
kvfree((void *)head - offset);
rcu_lock_release(&rcu_callback_map);
return true;
}
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);
return false;
}
/* Invoke the RCU callbacks whose grace period has elapsed. */
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
struct rcu_head *next, *list;
unsigned long flags;
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
if (rcu_ctrlblk.donetail == &rcu_ctrlblk.rcucblist) {
/* No callbacks ready, so just leave. */
local_irq_restore(flags);
return;
}
list = rcu_ctrlblk.rcucblist;
rcu_ctrlblk.rcucblist = *rcu_ctrlblk.donetail;
*rcu_ctrlblk.donetail = NULL;
if (rcu_ctrlblk.curtail == rcu_ctrlblk.donetail)
rcu_ctrlblk.curtail = &rcu_ctrlblk.rcucblist;
rcu_ctrlblk.donetail = &rcu_ctrlblk.rcucblist;
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
while (list) {
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
rcu_reclaim_tiny(list);
local_bh_enable();
list = next;
}
}
/*
* Wait for a grace period to elapse. But it is illegal to invoke
* synchronize_rcu() from within an RCU read-side critical section.
* Therefore, any legal call to synchronize_rcu() is a quiescent state,
* and so on a UP system, synchronize_rcu() need do nothing, other than
* let the polled APIs know that another grace period elapsed.
*
* (But Lai Jiangshan points out the benefits of doing might_sleep()
* to reduce latency.)
*
* Cool, huh? (Due to Josh Triplett.)
*/
void synchronize_rcu(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
static void tiny_rcu_leak_callback(struct rcu_head *rhp)
{
}
/*
* Post an RCU callback to be invoked after the end of an RCU grace
* period. But since we have but one CPU, that would be after any
* quiescent state.
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
static atomic_t doublefrees;
unsigned long flags;
if (debug_rcu_head_queue(head)) {
if (atomic_inc_return(&doublefrees) < 4) {
pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func);
mem_dump_obj(head);
}
if (!__is_kvfree_rcu_offset((unsigned long)head->func))
WRITE_ONCE(head->func, tiny_rcu_leak_callback);
return;
}
head->func = func;
head->next = NULL;
local_irq_save(flags);
*rcu_ctrlblk.curtail = head;
rcu_ctrlblk.curtail = &head->next;
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
}
EXPORT_SYMBOL_GPL(call_rcu);
/*
* Store a grace-period-counter "cookie". For more information,
* see the Tree RCU header comment.
*/
void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
{
rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
}
EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
/*
* Return a grace-period-counter "cookie". For more information,
* see the Tree RCU header comment.
*/
unsigned long get_state_synchronize_rcu(void)
{
return READ_ONCE(rcu_ctrlblk.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/*
* Return a grace-period-counter "cookie" and ensure that a future grace
* period completes. For more information, see the Tree RCU header comment.
*/
unsigned long start_poll_synchronize_rcu(void)
{
unsigned long gp_seq = get_state_synchronize_rcu();
if (unlikely(is_idle_task(current))) {
/* force scheduling for rcu_qs() */
resched_cpu(0);
}
return gp_seq;
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
/*
* Return true if the grace period corresponding to oldstate has completed
* and false otherwise. For more information, see the Tree RCU header
* comment.
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
return oldstate == RCU_GET_STATE_COMPLETED || READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
#ifdef CONFIG_KASAN_GENERIC
void kvfree_call_rcu(struct rcu_head *head, void *ptr)
{
if (head)
kasan_record_aux_stack_noalloc(ptr);
__kvfree_call_rcu(head, ptr);
}
EXPORT_SYMBOL_GPL(kvfree_call_rcu);
#endif
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
rcu_early_boot_tests();
}