[PATCH v9 7/7] x86/crash: Add x86 crash hotplug support

[Eric DeVolder]

For x86_64, when CPU or memory is hot un/plugged, the crash
elfcorehdr, which describes the CPUs and memory in the system,
must also be updated.

When loading the crash kernel via kexec_load or kexec_file_load,
the elfcorehdr is identified at run time in
crash_core:handle_hotplug_event().

To update the elfcorehdr for x86_64, a new elfcorehdr must be
generated from the available CPUs and memory. The new elfcorehdr
is prepared into a buffer, and then installed over the top of
the existing elfcorehdr.

In the patch 'kexec: exclude elfcorehdr from the segment digest'
the need to update purgatory due to the change in elfcorehdr was
eliminated.  As a result, no changes to purgatory or boot_params
(as the elfcorehdr= kernel command line parameter pointer
remains unchanged and correct) are needed, just elfcorehdr.

To accommodate a growing number of resources via hotplug, the
elfcorehdr segment must be sufficiently large enough to accommodate
changes, see the CRASH_MAX_MEMORY_RANGES configure item.

With this change, crash hotplug for kexec_file_load syscall
is supported. The kexec_load is also supported, but also
requires a corresponding change to userspace kexec-tools.

Signed-off-by: Eric DeVolder <eric.devolder at oracle.com>
---
 arch/x86/Kconfig        |  11 ++++
 arch/x86/kernel/crash.c | 116 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 127 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 762a0b6ab8b6..e9eecff3b97d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2082,6 +2082,17 @@ config CRASH_DUMP
 	  (CONFIG_RELOCATABLE=y).
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config CRASH_MAX_MEMORY_RANGES
+	depends on CRASH_DUMP && KEXEC_FILE && (HOTPLUG_CPU || MEMORY_HOTPLUG)
+	int
+	default 32768
+	help
+	  For the kexec_file_load path, specify the maximum number of
+	  memory regions, eg. as represented by the 'System RAM' entries
+	  in /proc/iomem, that the elfcorehdr buffer/segment can accommodate.
+	  This value is combined with NR_CPUS and multiplied by Elf64_Phdr
+	  size to determine the final buffer size.
+
 config KEXEC_JUMP
 	bool "kexec jump"
 	depends on KEXEC && HIBERNATION
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 9db41cce8d97..b9cdf7a0d868 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/memblock.h>
+#include <linux/highmem.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -398,7 +399,17 @@ int crash_load_segments(struct kimage *image)
 	image->elf_headers = kbuf.buffer;
 	image->elf_headers_sz = kbuf.bufsz;
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
+	/* Ensure elfcorehdr segment large enough for hotplug changes */
+	kbuf.memsz = (CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES) * sizeof(Elf64_Phdr);
+	/* For marking as usable to crash kernel */
+	image->elf_headers_sz = kbuf.memsz;
+	/* Record the index of the elfcorehdr segment */
+	image->elfcorehdr_index = image->nr_segments;
+	image->elfcorehdr_index_valid = true;
+#else
 	kbuf.memsz = kbuf.bufsz;
+#endif
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
@@ -413,3 +424,108 @@ int crash_load_segments(struct kimage *image)
 	return ret;
 }
 #endif /* CONFIG_KEXEC_FILE */
+
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
+int crash_hotplug_support(void) { return 1; }
+void *arch_map_crash_pages(unsigned long paddr, unsigned long size)
+{
+	/*
+	 * NOTE: The addresses and sizes passed to this routine have
+	 * already been fully aligned on page boundaries. There is no
+	 * need for massaging the address or size.
+	 */
+	void *ptr = NULL;
+
+	/* NOTE: requires arch_kexec_[un]protect_crashkres() for write access */
+	if (size > 0) {
+		struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+
+		ptr = kmap(page);
+	}
+
+	return ptr;
+}
+
+void arch_unmap_crash_pages(void **ptr)
+{
+	if (ptr) {
+		if (*ptr)
+			kunmap(*ptr);
+		*ptr = NULL;
+	}
+}
+
+/**
+ * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
+ * @image: the active struct kimage
+ * @hp_action: the hot un/plug action being handled
+ * @cpu: when KEXEC_CRASH_HP_ADD/REMOVE_CPU, the cpu affected
+ *
+ * To accurately reflect hot un/plug changes, the elfcorehdr (which
+ * is passed to the crash kernel via the elfcorehdr= parameter)
+ * must be updated with the new list of CPUs and memories. The new
+ * elfcorehdr is prepared in a kernel buffer, and then it is
+ * written on top of the existing/old elfcorehdr.
+ *
+ * For hotplug changes to elfcorehdr to work, two conditions are
+ * needed:
+ * First, the segment containing the elfcorehdr must be large enough
+ * to permit a growing number of resources. See the
+ * CONFIG_CRASH_MAX_MEMORY_RANGES description.
+ * 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).
+ *
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image,
+	unsigned int hp_action, unsigned int cpu)
+{
+	struct kexec_segment *ksegment;
+	unsigned char *ptr = NULL;
+	unsigned long elfsz = 0;
+	void *elfbuf = NULL;
+	unsigned long mem, memsz;
+
+	/*
+	 * Elfcorehdr_index_valid checked in crash_core:handle_hotplug_event()
+	 */
+	ksegment = &image->segment[image->elfcorehdr_index];
+	mem = ksegment->mem;
+	memsz = ksegment->memsz;
+
+	/*
+	 * Create the new elfcorehdr reflecting the changes to CPU and/or
+	 * memory resources.
+	 */
+	if (prepare_elf_headers(image, &elfbuf, &elfsz)) {
+		pr_err("crash hp: unable to prepare elfcore headers");
+		goto out;
+	}
+	if (elfsz > memsz) {
+		pr_err("crash hp: update elfcorehdr elfsz %lu > memsz %lu",
+			elfsz, memsz);
+		goto out;
+	}
+
+	/*
+	 * At this point, we are all but assured of success.
+	 * Copy new elfcorehdr into destination.
+	 */
+	ptr = arch_map_crash_pages(mem, memsz);
+	if (ptr) {
+		/*
+		 * Temporarily invalidate the crash image while the
+		 * elfcorehdr is updated.
+		 */
+		xchg(&kexec_crash_image, NULL);
+		memcpy_flushcache((void *)ptr, elfbuf, elfsz);
+		xchg(&kexec_crash_image, image);
+	}
+	arch_unmap_crash_pages((void **)&ptr);
+	pr_debug("crash hp: re-loaded elfcorehdr at 0x%lx\n", mem);
+
+out:
+	if (elfbuf)
+		vfree(elfbuf);
+}
+#endif
-- 
2.31.1