[PATCH v9 5/6] crash: forward memory_notify args to arch crash hotplug handler

Sourabh Jain sourabhjain at linux.ibm.com
Sun Mar 12 11:11:53 PDT 2023


On PowePC memblock regions are used to prepare elfcorehdr which
describes the memory regions of the running kernel to the kdump kernel.
Since the notifier used for the memory hotplug crash handler gets
initiated before the update of the memblock region happens (as depicted
below) for the memory remove case, the newly prepared elfcorehdr still
holds the old memory regions. If the elfcorehdr is prepared with stale
memblock regions then the newly prepared elfcorehdr will still be
holding stale memory regions. And dump collection with stale elfcorehdr
will lead to dump collection failure or incomplete dump collection.

The sequence of actions done on PowerPC when an LMB memory hot removed:

 Initiate memory hot remove
          |
          v
 offline pages
          |
          v
 initiate memory notify call
 chain for MEM_OFFLINE event.  <---> Prepare new elfcorehdr and update
                                     the kdump kernel image.
          |
          v
 update memblock regions

Such challenges only exist for memory remove case. For the memory add
case the memory regions are updated first and then memory notify calls
the arch crash hotplug handler to update the elfcorehdr.

This patch passes additional information about the hot removed LMB to
the arch crash hotplug handler in the form of memory_notify object.

How passing memory_notify to arch crash hotplug handler will help?

memory_notify holds the start PFN and page count of the hot removed
memory. With that base address and the size of the hot removed memory
can be calculated and same can be used to avoid adding hot removed
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     |  2 +-
 arch/x86/kernel/crash.c          |  3 ++-
 include/linux/kexec.h            |  2 +-
 kernel/crash_core.c              | 14 +++++++-------
 6 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 826671bd8ff97..92f7a03c4af46 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -106,7 +106,7 @@ 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
 #if defined(CONFIG_CRASH_HOTPLUG)
-void arch_crash_handle_hotplug_event(struct kimage *image);
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
 #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
 #endif
 #endif
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 35de0aa0fe375..863d9261908cd 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -582,8 +582,9 @@ int update_cpus_node(void *fdt)
  * arch_crash_hotplug_handler() - Handle crash CPU/Memory hotplug events to update the
  *                                necessary kexec segments based on the hotplug event.
  * @image: the active struct kimage
+ * @arg: struct memory_notify data handler for memory hotplug and NULL for CPU hotplug
  */
-void arch_crash_handle_hotplug_event(struct kimage *image)
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
 {
 	void *fdt;
 	int fdt_index;
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 1bc852ce347d4..70c3b23b468b6 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -213,7 +213,7 @@ 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);
+void arch_crash_handle_hotplug_event(struct kimage *image, 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 8f7b0b7fba909..a57c05b43c740 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -445,11 +445,12 @@ int crash_load_segments(struct kimage *image)
 /**
  * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
  * @image: the active struct kimage
+ * @arg: struct memory_notify data handler for memory hotplug and NULL for CPU hotplug
  *
  * 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)
+void arch_crash_handle_hotplug_event(struct kimage *image, 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 0ac41f48de0b1..69765e6a92d0d 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -506,7 +506,7 @@ 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) { }
+static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { }
 #endif
 
 #ifndef crash_hotplug_cpu_support
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index d5cd0f67e8567..e3c2e791aed87 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -718,7 +718,7 @@ 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 crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
+static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg)
 {
 	/* Obtain lock while changing crash information */
 	if (kexec_trylock()) {
@@ -769,7 +769,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
 			image->hp_action = hp_action;
 
 			/* Now invoke arch-specific update handler */
-			arch_crash_handle_hotplug_event(image);
+			arch_crash_handle_hotplug_event(image, arg);
 
 			/* No longer handling a hotplug event */
 			image->hp_action = KEXEC_CRASH_HP_NONE;
@@ -785,17 +785,17 @@ static void crash_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:
 		crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
-			KEXEC_CRASH_HP_INVALID_CPU);
+			KEXEC_CRASH_HP_INVALID_CPU, arg);
 		break;
 
 	case MEM_OFFLINE:
 		crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
-			KEXEC_CRASH_HP_INVALID_CPU);
+			KEXEC_CRASH_HP_INVALID_CPU, arg);
 		break;
 	}
 	return NOTIFY_OK;
@@ -808,13 +808,13 @@ static struct notifier_block crash_memhp_nb = {
 
 static int crash_cpuhp_online(unsigned int cpu)
 {
-	crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
+	crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu, NULL);
 	return 0;
 }
 
 static int crash_cpuhp_offline(unsigned int cpu)
 {
-	crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
+	crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu, NULL);
 	return 0;
 }
 
-- 
2.39.1




More information about the kexec mailing list