x86/crash: add x86 crash hotplug support

When CPU or memory is hot un/plugged, or off/onlined, the crash
elfcorehdr, which describes the CPUs and memory in the system, must also
be updated.

A new elfcorehdr is generated from the available CPUs and memory and
replaces the existing elfcorehdr.  The segment containing the elfcorehdr
is identified at run-time in crash_core:crash_handle_hotplug_event().

No modifications to purgatory (see 'kexec: exclude elfcorehdr from the
segment digest') or boot_params (as the elfcorehdr= capture kernel command
line parameter pointer remains unchanged and correct) are needed, just
elfcorehdr.

For kexec_file_load(), the elfcorehdr segment size is based on NR_CPUS and
CRASH_MAX_MEMORY_RANGES in order to accommodate a growing number of CPU
and memory resources.

For kexec_load(), the userspace kexec utility needs to size the elfcorehdr
segment in the same/similar manner.

To accommodate kexec_load() syscall in the absence of kexec_file_load()
syscall support, prepare_elf_headers() and dependents are moved outside of
CONFIG_KEXEC_FILE.

[eric.devolder@oracle.com: correct unused function build error]
  Link: https://lkml.kernel.org/r/20230821182644.2143-1-eric.devolder@oracle.com
Link: https://lkml.kernel.org/r/20230814214446.6659-6-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>

3 files changed, 116 insertions, 7 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fedc6dddd743..d9fc80b9ef84 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2069,6 +2069,9 @@ config ARCH_SUPPORTS_KEXEC_JUMP
 config ARCH_SUPPORTS_CRASH_DUMP
 	def_bool X86_64 || (X86_32 && HIGHMEM)
 
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+	def_bool y
+
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP)
 	default "0x1000000"
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5b77bbc28f96..9143100ea3ea 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -209,6 +209,21 @@ typedef void crash_vmclear_fn(void);
 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);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+#ifdef CONFIG_HOTPLUG_CPU
+static inline int crash_hotplug_cpu_support(void) { return 1; }
+#define crash_hotplug_cpu_support crash_hotplug_cpu_support
+#endif
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static inline int crash_hotplug_memory_support(void) { return 1; }
+#define crash_hotplug_memory_support crash_hotplug_memory_support
+#endif
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index cdd92ab43cda..d755c41a50a7 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -158,8 +158,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	crash_save_cpu(regs, safe_smp_processor_id());
 }
 
-#ifdef CONFIG_KEXEC_FILE
-
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
 static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 {
 	unsigned int *nr_ranges = arg;
@@ -231,7 +230,7 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
 
 /* Prepare elf headers. Return addr and size */
 static int prepare_elf_headers(struct kimage *image, void **addr,
-					unsigned long *sz)
+					unsigned long *sz, unsigned long *nr_mem_ranges)
 {
 	struct crash_mem *cmem;
 	int ret;
@@ -249,6 +248,9 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 	if (ret)
 		goto out;
 
+	/* Return the computed number of memory ranges, for hotplug usage */
+	*nr_mem_ranges = cmem->nr_ranges;
+
 	/* By default prepare 64bit headers */
 	ret =  crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
 
@@ -256,7 +258,9 @@ out:
 	vfree(cmem);
 	return ret;
 }
+#endif
 
+#ifdef CONFIG_KEXEC_FILE
 static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 {
 	unsigned int nr_e820_entries;
@@ -371,18 +375,42 @@ out:
 int crash_load_segments(struct kimage *image)
 {
 	int ret;
+	unsigned long pnum = 0;
 	struct kexec_buf kbuf = { .image = image, .buf_min = 0,
 				  .buf_max = ULONG_MAX, .top_down = false };
 
 	/* Prepare elf headers and add a segment */
-	ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz);
+	ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum);
 	if (ret)
 		return ret;
 
-	image->elf_headers = kbuf.buffer;
-	image->elf_headers_sz = kbuf.bufsz;
+	image->elf_headers	= kbuf.buffer;
+	image->elf_headers_sz	= kbuf.bufsz;
+	kbuf.memsz		= kbuf.bufsz;
+
+#ifdef CONFIG_CRASH_HOTPLUG
+	/*
+	 * The elfcorehdr segment size accounts for VMCOREINFO, kernel_map,
+	 * maximum CPUs and maximum memory ranges.
+	 */
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		pnum = 2 + CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES;
+	else
+		pnum += 2 + CONFIG_NR_CPUS_DEFAULT;
+
+	if (pnum < (unsigned long)PN_XNUM) {
+		kbuf.memsz = pnum * sizeof(Elf64_Phdr);
+		kbuf.memsz += sizeof(Elf64_Ehdr);
+
+		image->elfcorehdr_index = image->nr_segments;
+
+		/* Mark as usable to crash kernel, else crash kernel fails on boot */
+		image->elf_headers_sz = kbuf.memsz;
+	} else {
+		pr_err("number of Phdrs %lu exceeds max\n", pnum);
+	}
+#endif
 
-	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
@@ -395,3 +423,66 @@ int crash_load_segments(struct kimage *image)
 	return ret;
 }
 #endif /* CONFIG_KEXEC_FILE */
+
+#ifdef CONFIG_CRASH_HOTPLUG
+
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/**
+ * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
+ * @image: a pointer to kexec_crash_image
+ *
+ * Prepare the new elfcorehdr and replace the existing elfcorehdr.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image)
+{
+	void *elfbuf = NULL, *old_elfcorehdr;
+	unsigned long nr_mem_ranges;
+	unsigned long mem, memsz;
+	unsigned long elfsz = 0;
+
+	/*
+	 * Create the new elfcorehdr reflecting the changes to CPU and/or
+	 * memory resources.
+	 */
+	if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) {
+		pr_err("unable to create new elfcorehdr");
+		goto out;
+	}
+
+	/*
+	 * Obtain address and size of the elfcorehdr segment, and
+	 * check it against the new elfcorehdr buffer.
+	 */
+	mem = image->segment[image->elfcorehdr_index].mem;
+	memsz = image->segment[image->elfcorehdr_index].memsz;
+	if (elfsz > memsz) {
+		pr_err("update elfcorehdr elfsz %lu > memsz %lu",
+			elfsz, memsz);
+		goto out;
+	}
+
+	/*
+	 * Copy new elfcorehdr over the old elfcorehdr at destination.
+	 */
+	old_elfcorehdr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT));
+	if (!old_elfcorehdr) {
+		pr_err("mapping elfcorehdr segment failed\n");
+		goto out;
+	}
+
+	/*
+	 * Temporarily invalidate the crash image while the
+	 * elfcorehdr is updated.
+	 */
+	xchg(&kexec_crash_image, NULL);
+	memcpy_flushcache(old_elfcorehdr, elfbuf, elfsz);
+	xchg(&kexec_crash_image, image);
+	kunmap_local(old_elfcorehdr);
+	pr_debug("updated elfcorehdr\n");
+
+out:
+	vfree(elfbuf);
+}
+#endif