public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-05-20 08:03:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Crash: add lock to serialize crash hotplug handling

Browse source 
Eric reported that handling corresponding crash hotplug event can be
failed easily when many memory hotplug event are notified in a short
period.  They failed because failing to take __kexec_lock.

=======
[   78.714569] Fallback order for Node 0: 0
[   78.714575] Built 1 zonelists, mobility grouping on.  Total pages: 1817886
[   78.717133] Policy zone: Normal
[   78.724423] crash hp: kexec_trylock() failed, elfcorehdr may be inaccurate
[   78.727207] crash hp: kexec_trylock() failed, elfcorehdr may be inaccurate
[   80.056643] PEFILE: Unsigned PE binary
=======

The memory hotplug events are notified very quickly and very many, while
the handling of crash hotplug is much slower relatively.  So the atomic
variable __kexec_lock and kexec_trylock() can't guarantee the
serialization of crash hotplug handling.

Here, add a new mutex lock __crash_hotplug_lock to serialize crash hotplug
handling specifically.  This doesn't impact the usage of __kexec_lock.

Link: https://lkml.kernel.org/r/20230926120905.392903-1-bhe@redhat.com
Fixes: 2472627561 ("crash: add generic infrastructure for crash hotplug support")
Signed-off-by: Baoquan He <bhe@redhat.com>
Tested-by: Eric DeVolder <eric.devolder@oracle.com>
Reviewed-by: Eric DeVolder <eric.devolder@oracle.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Cc: Sourabh Jain <sourabhjain@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Baoquan He 2023-09-26 20:09:05 +08:00 • committed by Andrew Morton
parent bbe246f875
commit e2a8f20dd8
1 changed files with 17 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
kernel/crash_core.c
View file

@ -739,6 +739,17 @@ subsys_initcall(crash_notes_memory_init);
#undef pr_fmt #undef pr_fmt
#define pr_fmt(fmt) "crash hp: " fmt #define pr_fmt(fmt) "crash hp: " fmt
/*
* Different than kexec/kdump loading/unloading/jumping/shrinking which
* usually rarely happen, there will be many crash hotplug events notified
* during one short period, e.g one memory board is hot added and memory
* regions are online. So mutex lock __crash_hotplug_lock is used to
* serialize the crash hotplug handling specifically.
*/
DEFINE_MUTEX(__crash_hotplug_lock);
#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock)
#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock)
/* /*
* This routine utilized when the crash_hotplug sysfs node is read. * This routine utilized when the crash_hotplug sysfs node is read.
* It reflects the kernel's ability/permission to update the crash * It reflects the kernel's ability/permission to update the crash
@ -748,9 +759,11 @@ int crash_check_update_elfcorehdr(void)
{ {
int rc = 0; int rc = 0;
crash_hotplug_lock();
/* Obtain lock while reading crash information */ /* Obtain lock while reading crash information */
if (!kexec_trylock()) { if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
crash_hotplug_unlock();
return 0; return 0;
} }
if (kexec_crash_image) { if (kexec_crash_image) {
@ -761,6 +774,7 @@ int crash_check_update_elfcorehdr(void)
} }
/* Release lock now that update complete */ /* Release lock now that update complete */
kexec_unlock(); kexec_unlock();
crash_hotplug_unlock();
return rc; return rc;
} }
@ -783,9 +797,11 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
{ {
struct kimage *image; struct kimage *image;
crash_hotplug_lock();
/* Obtain lock while changing crash information */ /* Obtain lock while changing crash information */
if (!kexec_trylock()) { if (!kexec_trylock()) {
pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
crash_hotplug_unlock();
return; return;
} }
@ -852,6 +868,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
out: out:
/* Release lock now that update complete */ /* Release lock now that update complete */
kexec_unlock(); kexec_unlock();
crash_hotplug_unlock();
} }
static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v) static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)