Message-Id: <20230118213544.2128-7-eric.devolder@oracle.com>
Date:   Wed, 18 Jan 2023 16:35:44 -0500
From:   Eric DeVolder <eric.devolder@...cle.com>
To:     linux-kernel@...r.kernel.org, x86@...nel.org,
        kexec@...ts.infradead.org, ebiederm@...ssion.com,
        dyoung@...hat.com, bhe@...hat.com, vgoyal@...hat.com
Cc:     tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...ux.intel.com, hpa@...or.com,
        nramas@...ux.microsoft.com, thomas.lendacky@....com,
        robh@...nel.org, efault@....de, rppt@...nel.org, david@...hat.com,
        sourabhjain@...ux.ibm.com, konrad.wilk@...cle.com,
        boris.ostrovsky@...cle.com, eric.devolder@...cle.com
Subject: [PATCH v17 6/6] x86/crash: add x86 crash hotplug support

When CPU or memory is hot un/plugged, 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
into a buffer, and then installed over the top of the existing
elfcorehdr. The segment containing the elfcorehdr is identified
at run time in crash_core:handle_hotplug_event(), which works for
both the kexec_load() and kexec_file_load() syscalls.

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 description.

Signed-off-by: Eric DeVolder <eric.devolder@...cle.com>
---
 arch/x86/Kconfig             |  12 ++++
 arch/x86/include/asm/kexec.h |  15 +++++
 arch/x86/kernel/crash.c      | 123 +++++++++++++++++++++++++++++++++--
 3 files changed, 143 insertions(+), 7 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3604074a878b..09e9b7a091ed 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2119,6 +2119,18 @@ config CRASH_DUMP
 	  (CONFIG_RELOCATABLE=y).
 	  For more details see Documentation/admin-guide/kdump/kdump.rst
 
+config CRASH_HOTPLUG
+	bool "Update the crash elfcorehdr on system configuration changes"
+	default n
+	depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_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 of CPUs or memory. This is a much
+	  more advanced approach than userspace attempting that.
+
+	  If unsure, say Y.
+
 config KEXEC_JUMP
 	bool "kexec jump"
 	depends on KEXEC && HIBERNATION
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a3760ca796aa..1bc852ce347d 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -212,6 +212,21 @@ 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 8a9bc9807813..ba11c7e70edb 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -42,6 +42,21 @@
 #include <asm/crash.h>
 #include <asm/cmdline.h>
 
+/*
+ * 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.
+ */
+#define CRASH_MAX_MEMORY_RANGES 8192
+
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
 	struct boot_params *params;
@@ -173,8 +188,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	crash_save_cpu(regs, safe_smp_processor_id());
 }
 
-#ifdef CONFIG_KEXEC_FILE
-
 static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 {
 	unsigned int *nr_ranges = arg;
@@ -246,7 +259,7 @@ 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;
@@ -264,6 +277,9 @@ 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(image, cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
 
@@ -272,6 +288,7 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 	return ret;
 }
 
+#ifdef CONFIG_KEXEC_FILE
 static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 {
 	unsigned int nr_e820_entries;
@@ -386,18 +403,45 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 int crash_load_segments(struct kimage *image)
 {
 	int ret;
+	unsigned long nr_mem_ranges;
 	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, &nr_mem_ranges);
 	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;
+
+	if (IS_ENABLED(CONFIG_CRASH_HOTPLUG)) {
+		/*
+		 * Ensure the elfcorehdr segment large enough for hotplug changes.
+		 * Start with VMCOREINFO and kernel_map and maximum CPUs.
+		 */
+		unsigned long pnum = 2 + CONFIG_NR_CPUS_DEFAULT;
+
+		if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+			pnum += CRASH_MAX_MEMORY_RANGES;
+		else
+			pnum += nr_mem_ranges;
+
+		if (pnum < (unsigned long)PN_XNUM) {
+			kbuf.memsz = pnum * sizeof(Elf64_Phdr);
+			kbuf.memsz += sizeof(Elf64_Ehdr);
+
+			image->elfcorehdr_index = image->nr_segments;
+			image->elfcorehdr_index_valid = true;
+
+			/* 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);
+		}
+	}
 
-	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
@@ -410,3 +454,68 @@ 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: the active struct kimage
+ *
+ * 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)
+{
+	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 prepare elfcore headers");
+		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("updating elfcorehdr 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
-- 
2.31.1

Powered by blists - more mailing lists