crash: add generic infrastructure for crash hotplug support

To support crash hotplug, a mechanism is needed to update the crash
elfcorehdr upon CPU or memory changes (eg.  hot un/plug or off/ onlining).
The crash elfcorehdr describes the CPUs and memory to be written into the
vmcore.

To track CPU changes, callbacks are registered with the cpuhp mechanism
via cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN).  The crash hotplug
elfcorehdr update has no explicit ordering requirement (relative to other
cpuhp states), so meets the criteria for utilizing CPUHP_BP_PREPARE_DYN. 
CPUHP_BP_PREPARE_DYN is a dynamic state and avoids the need to introduce a
new state for crash hotplug.  Also, CPUHP_BP_PREPARE_DYN is the last state
in the PREPARE group, just prior to the STARTING group, which is very
close to the CPU starting up in a plug/online situation, or stopping in a
unplug/ offline situation.  This minimizes the window of time during an
actual plug/online or unplug/offline situation in which the elfcorehdr
would be inaccurate.  Note that for a CPU being unplugged or offlined, the
CPU will still be present in the list of CPUs generated by
crash_prepare_elf64_headers().  However, there is no need to explicitly
omit the CPU, see justification in 'crash: change
crash_prepare_elf64_headers() to for_each_possible_cpu()'.

To track memory changes, a notifier is registered to capture the memblock
MEM_ONLINE and MEM_OFFLINE events via register_memory_notifier().

The CPU callbacks and memory notifiers invoke crash_handle_hotplug_event()
which performs needed tasks and then dispatches the event to the
architecture specific arch_crash_handle_hotplug_event() to update the
elfcorehdr with the current state of CPUs and memory.  During the process,
the kexec_lock is held.

Link: https://lkml.kernel.org/r/20230814214446.6659-3-eric.devolder@oracle.com
Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
Reviewed-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Akhil Raj <lf32.dev@gmail.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Mimi Zohar <zohar@linux.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 197 insertions, 0 deletions

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 1e48b1d96404..0c06561bf5ff 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -104,4 +104,11 @@ extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_ma
 struct kimage;
 struct kexec_segment;
 
+#define KEXEC_CRASH_HP_NONE			0
+#define KEXEC_CRASH_HP_ADD_CPU			1
+#define KEXEC_CRASH_HP_REMOVE_CPU		2
+#define KEXEC_CRASH_HP_ADD_MEMORY		3
+#define KEXEC_CRASH_HP_REMOVE_MEMORY		4
+#define KEXEC_CRASH_HP_INVALID_CPU		-1U
+
 #endif /* LINUX_CRASH_CORE_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index fb4350db33ff..df395f888915 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -33,6 +33,7 @@ extern note_buf_t __percpu *crash_notes;
 #include <linux/compat.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/highmem.h>
 #include <asm/kexec.h>
 
 /* Verify architecture specific macros are defined */
@@ -345,6 +346,12 @@ struct kimage {
 	struct purgatory_info purgatory_info;
 #endif
 
+#ifdef CONFIG_CRASH_HOTPLUG
+	int hp_action;
+	int elfcorehdr_index;
+	bool elfcorehdr_updated;
+#endif
+
 #ifdef CONFIG_IMA_KEXEC
 	/* Virtual address of IMA measurement buffer for kexec syscall */
 	void *ima_buffer;
@@ -475,6 +482,10 @@ static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g
 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) { }
+#endif
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 701cd5336f4f..727190571544 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -112,4 +112,35 @@ config CRASH_DUMP
 	  For s390, this option also enables zfcpdump.
 	  See also <file:Documentation/s390/zfcpdump.rst>
 
+config CRASH_HOTPLUG
+	bool "Update the crash elfcorehdr on system configuration changes"
+	default y
+	depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_HOTPLUG)
+	depends on ARCH_SUPPORTS_CRASH_HOTPLUG
+	help
+	  Enable direct update to the crash elfcorehdr (which contains
+	  the list of CPUs and memory regions to be dumped upon a crash)
+	  in response to hot plug/unplug or online/offline of CPUs or
+	  memory. This is a much more advanced approach than userspace
+	  attempting that.
+
+	  If unsure, say Y.
+
+config CRASH_MAX_MEMORY_RANGES
+	int "Specify the maximum number of memory regions for the elfcorehdr"
+	default 8192
+	depends on CRASH_HOTPLUG
+	help
+	  For the kexec_file_load() syscall path, specify the maximum number of
+	  memory regions that the elfcorehdr buffer/segment can accommodate.
+	  These regions are obtained via walk_system_ram_res(); eg. the
+	  'System RAM' entries in /proc/iomem.
+	  This value is combined with NR_CPUS_DEFAULT and multiplied by
+	  sizeof(Elf64_Phdr) to determine the final elfcorehdr memory buffer/
+	  segment size.
+	  The value 8192, for example, covers a (sparsely populated) 1TiB system
+	  consisting of 128MiB memblocks, while resulting in an elfcorehdr
+	  memory buffer/segment size under 1MiB. This represents a sane choice
+	  to accommodate both baremetal and virtual machine configurations.
+
 endmenu
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 336083fba623..40388ad51034 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,6 +11,8 @@
 #include <linux/vmalloc.h>
 #include <linux/sizes.h>
 #include <linux/kexec.h>
+#include <linux/memory.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -18,6 +20,7 @@
 #include <crypto/sha1.h>
 
 #include "kallsyms_internal.h"
+#include "kexec_internal.h"
 
 /* Per cpu memory for storing cpu states in case of system crash. */
 note_buf_t __percpu *crash_notes;
@@ -733,3 +736,142 @@ static int __init crash_notes_memory_init(void)
 	return 0;
 }
 subsys_initcall(crash_notes_memory_init);
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+/*
+ * To accurately reflect hot un/plug changes of cpu and memory resources
+ * (including onling and offlining of those resources), the elfcorehdr
+ * (which is passed to the crash kernel via the elfcorehdr= parameter)
+ * must be updated with the new list of CPUs and memories.
+ *
+ * In order to make changes to elfcorehdr, two conditions are needed:
+ * First, the segment containing the elfcorehdr must be large enough
+ * to permit a growing number of resources; the elfcorehdr memory size
+ * is based on NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES.
+ * Second, purgatory must explicitly exclude the elfcorehdr from the
+ * 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)
+{
+	struct kimage *image;
+
+	/* Obtain lock while changing crash information */
+	if (!kexec_trylock()) {
+		pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n");
+		return;
+	}
+
+	/* Check kdump is not loaded */
+	if (!kexec_crash_image)
+		goto out;
+
+	image = kexec_crash_image;
+
+	if (hp_action == KEXEC_CRASH_HP_ADD_CPU ||
+		hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
+		pr_debug("hp_action %u, cpu %u\n", hp_action, cpu);
+	else
+		pr_debug("hp_action %u\n", hp_action);
+
+	/*
+	 * The elfcorehdr_index is set to -1 when the struct kimage
+	 * is allocated. Find the segment containing the elfcorehdr,
+	 * if not already found.
+	 */
+	if (image->elfcorehdr_index < 0) {
+		unsigned long mem;
+		unsigned char *ptr;
+		unsigned int n;
+
+		for (n = 0; n < image->nr_segments; n++) {
+			mem = image->segment[n].mem;
+			ptr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT));
+			if (ptr) {
+				/* The segment containing elfcorehdr */
+				if (memcmp(ptr, ELFMAG, SELFMAG) == 0)
+					image->elfcorehdr_index = (int)n;
+				kunmap_local(ptr);
+			}
+		}
+	}
+
+	if (image->elfcorehdr_index < 0) {
+		pr_err("unable to locate elfcorehdr segment");
+		goto out;
+	}
+
+	/* Needed in order for the segments to be updated */
+	arch_kexec_unprotect_crashkres();
+
+	/* Differentiate between normal load and hotplug update */
+	image->hp_action = hp_action;
+
+	/* Now invoke arch-specific update handler */
+	arch_crash_handle_hotplug_event(image);
+
+	/* No longer handling a hotplug event */
+	image->hp_action = KEXEC_CRASH_HP_NONE;
+	image->elfcorehdr_updated = true;
+
+	/* Change back to read-only */
+	arch_kexec_protect_crashkres();
+
+	/* Errors in the callback is not a reason to rollback state */
+out:
+	/* Release lock now that update complete */
+	kexec_unlock();
+}
+
+static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
+{
+	switch (val) {
+	case MEM_ONLINE:
+		crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
+			KEXEC_CRASH_HP_INVALID_CPU);
+		break;
+
+	case MEM_OFFLINE:
+		crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
+			KEXEC_CRASH_HP_INVALID_CPU);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block crash_memhp_nb = {
+	.notifier_call = crash_memhp_notifier,
+	.priority = 0
+};
+
+static int crash_cpuhp_online(unsigned int cpu)
+{
+	crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
+	return 0;
+}
+
+static int crash_cpuhp_offline(unsigned int cpu)
+{
+	crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
+	return 0;
+}
+
+static int __init crash_hotplug_init(void)
+{
+	int result = 0;
+
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		register_memory_notifier(&crash_memhp_nb);
+
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+		result = cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN,
+			"crash/cpuhp", crash_cpuhp_online, crash_cpuhp_offline);
+	}
+
+	return result;
+}
+
+subsys_initcall(crash_hotplug_init);
+#endif
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 4ff564bbd8d8..9dc728982d79 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -274,6 +274,12 @@ struct kimage *do_kimage_alloc_init(void)
 	/* Initialize the list of unusable pages */
 	INIT_LIST_HEAD(&image->unusable_pages);
 
+#ifdef CONFIG_CRASH_HOTPLUG
+	image->hp_action = KEXEC_CRASH_HP_NONE;
+	image->elfcorehdr_index = -1;
+	image->elfcorehdr_updated = false;
+#endif
+
 	return image;
 }