[PATCH v8 7/8] crash: forward memory_notify args to arch crash hotplug handler

Sourabh Jain sourabhjain at linux.ibm.com
Wed Feb 1 17:38:40 AEDT 2023


The way memory hot remove is handled on PowerPC, it is hard to update
the elfcorehdr without memory_notify args.

On PowePC memblock data structure is used to prepare elfcorehdr for kdump.
Since the notifier used for memory hotplug crash handler get initiated
before the memblock data structure update happens (as depicted below),
the newly prepared elfcorehdr still holds the old memory regions. So if
the system crash with obsolete elfcorehdr, makedumpfile failed to collect
vmcore.

Sequence of actions done on PowerPC to serve the memory hot remove:

 Initiate memory hot remove
          |
          v
 offline pages
          |
          v
 initiate memory notify call chain
 for MEM_OFFLINE event.
 (same is used for crash update)
          |
          v
 prepare new elfcorehdr for kdump using
 memblock data structure
          |
          v
 update memblock data structure

How passing memory_notify to arch crash hotplug handler will help?

memory_notify holds the start PFN and page count, with that base address
and size of hot unplugged memory can calculated and same can be use to
avoid hot unplugged memory region to get added in the elfcorehdr.

Signed-off-by: Sourabh Jain <sourabhjain at linux.ibm.com>
---
 arch/powerpc/include/asm/kexec.h |  2 +-
 arch/powerpc/kexec/core_64.c     |  3 ++-
 arch/x86/include/asm/kexec.h     |  3 ++-
 arch/x86/kernel/crash.c          |  4 +++-
 include/linux/kexec.h            |  6 +++++-
 kernel/crash_core.c              | 14 +++++++-------
 6 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index c2b8debc11a61..f49eec264e545 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -108,7 +108,7 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges);
 int machine_kexec_post_load(struct kimage *image);
 #define machine_kexec_post_load machine_kexec_post_load
 
-void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action);
+void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action, void *arg);
 #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
 
 #endif
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 5fdc9fe4e7fe0..27a360120bc55 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -620,11 +620,12 @@ int update_cpus_node(void *fdt)
  * arch_crash_hotplug_handler() - Handle hotplug kexec segements changes FDT, elfcorehdr
  * @image: the active struct kimage
  * @hp_action: the hot un/plug action being handled
+ * @arg: struct memory_notify data handler
  *
  * To accurately reflect CPU hot un/plug changes, the FDT must be updated with the
  * new list of CPUs.
  */
-void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action)
+void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action, void *arg)
 {
 	void *fdt;
 
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index ec33a592a2ddd..171edb8167a12 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -213,7 +213,8 @@ extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
 extern void kdump_nmi_shootdown_cpus(void);
 
 #ifdef CONFIG_CRASH_HOTPLUG
-void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action);
+void arch_crash_handle_hotplug_event(struct kimage *image,
+				     unsigned int hp_action, void *arg);
 #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c0b5afad37565..bbe8e3cd0c61d 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -464,12 +464,14 @@ int crash_load_segments(struct kimage *image)
  * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
  * @image: the active struct kimage
  * @hp_action: the hot un/plug action being handled
+ * @arg: struct memory_notify data handler
  *
  * To accurately reflect hot un/plug changes, the new elfcorehdr
  * is prepared in a kernel buffer, and then it is written on top
  * of the existing/old elfcorehdr.
  */
-void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action)
+void arch_crash_handle_hotplug_event(struct kimage *image,
+				     unsigned int hp_action, void *arg)
 {
 	void *elfbuf = NULL, *old_elfcorehdr;
 	unsigned long nr_mem_ranges;
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 5461a4ad50e2a..fe33f6aeed843 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -509,7 +509,11 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) {
 #endif
 
 #ifndef arch_crash_handle_hotplug_event
-static inline void arch_crash_handle_hotplug_event(struct kimage *image, unsigned int hp_action) { }
+static inline void arch_crash_handle_hotplug_event(struct kimage *image,
+						   unsigned int hp_action,
+						   void *arg)
+{
+}
 #endif
 
 #else /* !CONFIG_KEXEC_CORE */
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 3aede7187c8b4..f19978dcb1e65 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -727,7 +727,7 @@ subsys_initcall(crash_save_vmcoreinfo_init);
  * list of segments it checks (since the elfcorehdr changes and thus
  * would require an update to purgatory itself to update the digest).
  */
-static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
+static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg)
 {
 	/* Obtain lock while changing crash information */
 	if (kexec_trylock()) {
@@ -789,7 +789,7 @@ static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
 					cpu : KEXEC_CRASH_HP_INVALID_CPU;
 
 			/* Now invoke arch-specific update handler */
-			arch_crash_handle_hotplug_event(image, hp_action);
+			arch_crash_handle_hotplug_event(image, hp_action, arg);
 
 			/* No longer handling a hotplug event */
 			image->hotplug_event = false;
@@ -804,17 +804,17 @@ static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
 	}
 }
 
-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 *arg)
 {
 	switch (val) {
 	case MEM_ONLINE:
 		handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
-			KEXEC_CRASH_HP_INVALID_CPU);
+			KEXEC_CRASH_HP_INVALID_CPU, arg);
 		break;
 
 	case MEM_OFFLINE:
 		handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
-			KEXEC_CRASH_HP_INVALID_CPU);
+			KEXEC_CRASH_HP_INVALID_CPU, arg);
 		break;
 	}
 	return NOTIFY_OK;
@@ -827,13 +827,13 @@ static struct notifier_block crash_memhp_nb = {
 
 static int crash_cpuhp_online(unsigned int cpu)
 {
-	handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
+	handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu, NULL);
 	return 0;
 }
 
 static int crash_cpuhp_offline(unsigned int cpu)
 {
-	handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
+	handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu, NULL);
 	return 0;
 }
 
-- 
2.39.1



More information about the Linuxppc-dev mailing list