[PW_SID:1103915] arm64/riscv: Add support for crashkernel CMA reservation

Documentation/admin-guide/kernel-parameters.txt

@@ -1119,14 +1119,14 @@ Kernel parameters
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 	crashkernel=size[KMG],cma
-			[KNL, X86, ppc] Reserve additional crash kernel memory from
-			CMA. This reservation is usable by the first system's
-			userspace memory and kernel movable allocations (memory
-			balloon, zswap). Pages allocated from this memory range
-			will not be included in the vmcore so this should not
-			be used if dumping of userspace memory is intended and
-			it has to be expected that some movable kernel pages
-			may be missing from the dump.
+			[KNL, X86, ARM64, RISCV, PPC] Reserve additional crash
+			kernel memory from CMA. This reservation is usable by
+			the first system's userspace memory and kernel movable
+			allocations (memory balloon, zswap). Pages allocated
+			from this memory range will not be included in the vmcore
+			so this should not be used if dumping of userspace memory
+			is intended and it has to be expected that some movable
+			kernel pages may be missing from the dump.
 
 			A standard crashkernel reservation, as described above,
 			is still needed to hold the crash kernel and initrd.

arch/arm64/Kconfig

@@ -1609,6 +1609,9 @@ config ARCH_DEFAULT_CRASH_DUMP
 config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
 	def_bool CRASH_RESERVE
 
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+	def_bool y
+
 config TRANS_TABLE
 	def_bool y
 	depends on HIBERNATION || KEXEC_CORE

arch/arm64/include/asm/kexec.h

@@ -130,6 +130,19 @@ extern int load_other_segments(struct kimage *image,
 		char *cmdline);
 #endif
 
+#ifdef CONFIG_CRASH_HOTPLUG
+#define pnum_hdr_sz(pnum) ((pnum) * sizeof(Elf64_Phdr) + sizeof(Elf64_Ehdr))
+
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
+
+unsigned int arch_crash_get_elfcorehdr_size(void);
+#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
+#endif
+
 #endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/kernel/Makefile

@@ -64,7 +64,7 @@ obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o kexec_image.o
 obj-$(CONFIG_ARM64_RELOC_TEST)		+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
+obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o crash.o
 obj-$(CONFIG_VMCORE_INFO)		+= vmcore_info.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o

arch/arm64/kernel/crash.c

@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Architecture specific functions for kexec based crash dumps.
+ */
+
+#define pr_fmt(fmt)	"crash hp: " fmt
+
+#include <linux/kexec.h>
+#include <linux/elf.h>
+#include <linux/memblock.h>
+#include <linux/vmalloc.h>
+#include <linux/cacheflush.h>
+#include <linux/crash_core.h>
+
+#include <asm/kexec.h>
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
+unsigned int arch_get_system_nr_ranges(void)
+{
+	/* for exclusion of crashkernel region */
+	unsigned int nr_ranges = 2 + crashk_cma_cnt + CRASH_HOTPLUG_SAFETY_PADDING;
+	phys_addr_t start, end;
+	u64 i;
+
+	for_each_mem_range(i, &start, &end)
+		nr_ranges++;
+
+	return nr_ranges;
+}
+
+int arch_crash_populate_cmem(struct crash_mem *cmem)
+{
+	phys_addr_t start, end;
+	u64 i;
+
+	for_each_mem_range(i, &start, &end) {
+		if (unlikely(cmem->nr_ranges >= cmem->max_nr_ranges))
+			return -EAGAIN;
+
+		cmem->ranges[cmem->nr_ranges].start = start;
+		cmem->ranges[cmem->nr_ranges].end = end - 1;
+		cmem->nr_ranges++;
+	}
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_CRASH_HOTPLUG
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+#ifdef CONFIG_KEXEC_FILE
+	if (image->file_mode)
+		return 1;
+#endif
+	/*
+	 * For kexec_load syscall, crash hotplug support requires
+	 * KEXEC_CRASH_HOTPLUG_SUPPORT flag to be passed by userspace.
+	 */
+	return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT;
+}
+
+unsigned int arch_crash_get_elfcorehdr_size(void)
+{
+	unsigned int phdr_cnt;
+
+	/* A program header for possible CPUs, vmcoreinfo and kernel_map */
+	phdr_cnt = 2 + num_possible_cpus();
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES;
+
+	return pnum_hdr_sz(phdr_cnt);
+}
+
+/**
+ * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old
+ *			       elfcorehdr in the kexec segment array.
+ * @image: the active struct kimage
+ */
+static void update_crash_elfcorehdr(struct kimage *image)
+{
+	void *elfbuf = NULL, *old_elfcorehdr;
+	unsigned long mem, memsz;
+	unsigned long elfsz = 0;
+
+	/*
+	 * Create the new elfcorehdr reflecting the changes to CPU and/or
+	 * memory resources.
+	 */
+	if (crash_prepare_headers(true, &elfbuf, &elfsz, NULL)) {
+		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 = (void *)__va(mem);
+	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((void *)old_elfcorehdr, elfbuf, elfsz);
+	dcache_clean_inval_poc((unsigned long)old_elfcorehdr,
+			       (unsigned long)old_elfcorehdr + elfsz);
+	xchg(&kexec_crash_image, image);
+	pr_debug("updated elfcorehdr\n");
+
+out:
+	vfree(elfbuf);
+}
+
+/**
+ * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
+ * @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and
+ *       NULL for CPU hotplug case.
+ *
+ * Update the kdump image based on the type of hotplug event:
+ * - CPU add and remove: No action is needed.
+ * - Memory add/remove: Update the elfcorehdr to reflect the current memory layout.
+ *
+ * Prepare the new elfcorehdr and replace the existing elfcorehdr.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
+{
+	if ((image->file_mode || image->elfcorehdr_updated) &&
+		((image->hp_action == KEXEC_CRASH_HP_ADD_CPU) ||
+		(image->hp_action == KEXEC_CRASH_HP_REMOVE_CPU)))
+		return;
+
+	update_crash_elfcorehdr(image);
+}
+#endif /* CONFIG_CRASH_HOTPLUG */

arch/arm64/kernel/kexec_image.c

@@ -8,6 +8,7 @@
 
 #define pr_fmt(fmt)	"kexec_file(Image): " fmt
 
+#include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -89,6 +90,38 @@ static void *image_load(struct kimage *image,
 
 	kernel_segment_number = image->nr_segments;
 
+#ifdef CONFIG_CRASH_DUMP
+	if (image->type == KEXEC_TYPE_CRASH) {
+		/* load elf core header */
+		unsigned long headers_sz, pnum = 0;
+		void *headers;
+
+		ret = crash_prepare_headers(true, &headers, &headers_sz, &pnum);
+		if (ret) {
+			pr_err("Preparing elf core header failed\n");
+			return ERR_PTR(ret);
+		}
+		image->elf_headers = headers;
+		image->elf_headers_sz = headers_sz;
+
+#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 + num_possible_cpus() + CONFIG_CRASH_MAX_MEMORY_RANGES;
+		else
+			pnum += 2 + num_possible_cpus();
+
+		if (pnum < (unsigned long)PN_XNUM)
+			image->elf_headers_sz = max(pnum_hdr_sz(pnum), headers_sz);
+		else
+			pr_err("number of Phdrs %lu exceeds max\n", pnum);
+#endif
+	}
+#endif
+
 	/*
 	 * The location of the kernel segment may make it impossible to satisfy
 	 * the other segment requirements, so we try repeatedly to find a
@@ -107,6 +140,7 @@ static void *image_load(struct kimage *image,
 		 * We couldn't find space for the other segments; erase the
 		 * kernel segment and try the next available hole.
 		 */
+		kexec_free_segment_cma(image, kernel_segment_number);
 		image->nr_segments -= 1;
 		kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
 		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;

arch/arm64/kernel/machine_kexec_file.c

@@ -10,11 +10,11 @@
 
 #define pr_fmt(fmt) "kexec_file: " fmt
 
+#include <linux/elf.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/libfdt.h>
-#include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/slab.h>
@@ -39,50 +39,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
 	return kexec_image_post_load_cleanup_default(image);
 }
 
-#ifdef CONFIG_CRASH_DUMP
-static int prepare_elf_headers(void **addr, unsigned long *sz)
-{
-	struct crash_mem *cmem;
-	unsigned int nr_ranges;
-	int ret;
-	u64 i;
-	phys_addr_t start, end;
-
-	nr_ranges = 2; /* for exclusion of crashkernel region */
-	for_each_mem_range(i, &start, &end)
-		nr_ranges++;
-
-	cmem = kmalloc_flex(*cmem, ranges, nr_ranges);
-	if (!cmem)
-		return -ENOMEM;
-
-	cmem->max_nr_ranges = nr_ranges;
-	cmem->nr_ranges = 0;
-	for_each_mem_range(i, &start, &end) {
-		cmem->ranges[cmem->nr_ranges].start = start;
-		cmem->ranges[cmem->nr_ranges].end = end - 1;
-		cmem->nr_ranges++;
-	}
-
-	/* Exclude crashkernel region */
-	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
-	if (ret)
-		goto out;
-
-	if (crashk_low_res.end) {
-		ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
-		if (ret)
-			goto out;
-	}
-
-	ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
-
-out:
-	kfree(cmem);
-	return ret;
-}
-#endif
-
 /*
  * Tries to add the initrd and DTB to the image. If it is not possible to find
  * valid locations, this function will undo changes to the image and return non
@@ -105,32 +61,25 @@ int load_other_segments(struct kimage *image,
 	kbuf.buf_min = kernel_load_addr + kernel_size;
 
 #ifdef CONFIG_CRASH_DUMP
-	/* load elf core header */
-	void *headers;
-	unsigned long headers_sz;
 	if (image->type == KEXEC_TYPE_CRASH) {
-		ret = prepare_elf_headers(&headers, &headers_sz);
-		if (ret) {
-			pr_err("Preparing elf core header failed\n");
-			goto out_err;
-		}
-
-		kbuf.buffer = headers;
-		kbuf.bufsz = headers_sz;
+		kbuf.buffer = image->elf_headers;
+		kbuf.bufsz = image->elf_headers_sz;
 		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
-		kbuf.memsz = headers_sz;
+		kbuf.memsz = image->elf_headers_sz;
+
+#ifdef CONFIG_CRASH_HOTPLUG
+		if (image->elf_headers_sz < pnum_hdr_sz(PN_XNUM))
+			image->elfcorehdr_index = image->nr_segments;
+#endif
+
 		kbuf.buf_align = SZ_64K; /* largest supported page size */
 		kbuf.buf_max = ULONG_MAX;
 		kbuf.top_down = true;
 
 		ret = kexec_add_buffer(&kbuf);
-		if (ret) {
-			vfree(headers);
+		if (ret)
 			goto out_err;
-		}
-		image->elf_headers = headers;
 		image->elf_load_addr = kbuf.mem;
-		image->elf_headers_sz = headers_sz;
 
 		kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
 			      image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
@@ -195,7 +144,10 @@ int load_other_segments(struct kimage *image,
 	return 0;
 
 out_err:
-	image->nr_segments = orig_segments;
+	while (image->nr_segments > orig_segments) {
+		kexec_free_segment_cma(image, image->nr_segments - 1);
+		image->nr_segments--;
+	}
 	kvfree(dtb);
 	return ret;
 }