mirror of
https://github.com/torvalds/linux.git
synced 2024-11-14 08:02:07 +00:00
05c6257433
Attempting to get a crash dump out of a debug PREEMPT_RT kernel via an NMI panic() doesn't work. The cause of that lies in the PREEMPT_RT definition of mutex_trylock(): if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) return 0; This prevents an nmi_panic() from executing the main body of __crash_kexec() which does the actual kexec into the kdump kernel. The warning and return are explained by:6ce47fd961("rtmutex: Warn if trylock is called from hard/softirq context") [...] The reasons for this are: 1) There is a potential deadlock in the slowpath 2) Another cpu which blocks on the rtmutex will boost the task which allegedly locked the rtmutex, but that cannot work because the hard/softirq context borrows the task context. Furthermore, grabbing the lock isn't NMI safe, so do away with kexec_mutex and replace it with an atomic variable. This is somewhat overzealous as *some* callsites could keep using a mutex (e.g. the sysfs-facing ones like crash_shrink_memory()), but this has the benefit of involving a single unified lock and preventing any future NMI-related surprises. Tested by triggering NMI panics via: $ echo 1 > /proc/sys/kernel/panic_on_unrecovered_nmi $ echo 1 > /proc/sys/kernel/unknown_nmi_panic $ echo 1 > /proc/sys/kernel/panic $ ipmitool power diag Link: https://lkml.kernel.org/r/20220630223258.4144112-3-vschneid@redhat.com Fixes:6ce47fd961("rtmutex: Warn if trylock is called from hard/softirq context") Signed-off-by: Valentin Schneider <vschneid@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Baoquan He <bhe@redhat.com> Cc: "Eric W . Biederman" <ebiederm@xmission.com> Cc: Juri Lelli <jlelli@redhat.com> Cc: Luis Claudio R. Goncalves <lgoncalv@redhat.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
40 lines
1.3 KiB
C
40 lines
1.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef LINUX_KEXEC_INTERNAL_H
|
|
#define LINUX_KEXEC_INTERNAL_H
|
|
|
|
#include <linux/kexec.h>
|
|
|
|
struct kimage *do_kimage_alloc_init(void);
|
|
int sanity_check_segment_list(struct kimage *image);
|
|
void kimage_free_page_list(struct list_head *list);
|
|
void kimage_free(struct kimage *image);
|
|
int kimage_load_segment(struct kimage *image, struct kexec_segment *segment);
|
|
void kimage_terminate(struct kimage *image);
|
|
int kimage_is_destination_range(struct kimage *image,
|
|
unsigned long start, unsigned long end);
|
|
|
|
/*
|
|
* Whatever is used to serialize accesses to the kexec_crash_image needs to be
|
|
* NMI safe, as __crash_kexec() can happen during nmi_panic(), so here we use a
|
|
* "simple" atomic variable that is acquired with a cmpxchg().
|
|
*/
|
|
extern atomic_t __kexec_lock;
|
|
static inline bool kexec_trylock(void)
|
|
{
|
|
return atomic_cmpxchg_acquire(&__kexec_lock, 0, 1) == 0;
|
|
}
|
|
static inline void kexec_unlock(void)
|
|
{
|
|
atomic_set_release(&__kexec_lock, 0);
|
|
}
|
|
|
|
#ifdef CONFIG_KEXEC_FILE
|
|
#include <linux/purgatory.h>
|
|
void kimage_file_post_load_cleanup(struct kimage *image);
|
|
extern char kexec_purgatory[];
|
|
extern size_t kexec_purgatory_size;
|
|
#else /* CONFIG_KEXEC_FILE */
|
|
static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
|
|
#endif /* CONFIG_KEXEC_FILE */
|
|
#endif /* LINUX_KEXEC_INTERNAL_H */
|