kexec: support for kexec on panic using new system call

This patch adds support for loading a kexec on panic (kdump) kernel usning
new system call.

It prepares ELF headers for memory areas to be dumped and for saved cpu
registers.  Also prepares the memory map for second kernel and limits its
boot to reserved areas only.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: Greg Kroah-Hartman <greg@kroah.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: WANG Chao <chaowang@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/crash.h

+#ifndef _ASM_X86_CRASH_H
+#define _ASM_X86_CRASH_H
+
+int crash_load_segments(struct kimage *image);
+int crash_copy_backup_region(struct kimage *image);
+int crash_setup_memmap_entries(struct kimage *image,
+		struct boot_params *params);
+
+#endif /* _ASM_X86_CRASH_H */

arch/x86/include/asm/kexec.h

@@ -25,6 +25,8 @@
 #include <asm/ptrace.h>
 #include <asm/bootparam.h>
 
+struct kimage;
+
 /*
  * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
  * I.e. Maximum page that is mapped directly into kernel memory,
@@ -62,6 +64,10 @@
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
 #endif
 
+/* Memory to backup during crash kdump */
+#define KEXEC_BACKUP_SRC_START	(0UL)
+#define KEXEC_BACKUP_SRC_END	(640 * 1024UL)	/* 640K */
+
 /*
  * CPU does not save ss and sp on stack if execution is already
  * running in kernel mode at the time of NMI occurrence. This code
@@ -161,17 +167,35 @@ struct kimage_arch {
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
+	/* Details of backup region */
+	unsigned long backup_src_start;
+	unsigned long backup_src_sz;
+
+	/* Physical address of backup segment */
+	unsigned long backup_load_addr;
+
+	/* Core ELF header buffer */
+	void *elf_headers;
+	unsigned long elf_headers_sz;
+	unsigned long elf_load_addr;
 };
+#endif /* CONFIG_X86_32 */
 
+#ifdef CONFIG_X86_64
+/*
+ * Number of elements and order of elements in this structure should match
+ * with the ones in arch/x86/purgatory/entry64.S. If you make a change here
+ * make an appropriate change in purgatory too.
+ */
 struct kexec_entry64_regs {
 	uint64_t rax;
-	uint64_t rbx;
 	uint64_t rcx;
 	uint64_t rdx;
-	uint64_t rsi;
-	uint64_t rdi;
+	uint64_t rbx;
 	uint64_t rsp;
 	uint64_t rbp;
+	uint64_t rsi;
+	uint64_t rdi;
 	uint64_t r8;
 	uint64_t r9;
 	uint64_t r10;

arch/x86/kernel/crash.c

@@ -4,9 +4,14 @@
  * Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
  *
  * Copyright (C) IBM Corporation, 2004. All rights reserved.
+ * Copyright (C) Red Hat Inc., 2014. All rights reserved.
+ * Authors:
+ *      Vivek Goyal <vgoyal@redhat.com>
  *
  */
 
+#define pr_fmt(fmt)	"kexec: " fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/smp.h>
@@ -16,6 +21,7 @@
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -28,6 +34,45 @@
 #include <asm/reboot.h>
 #include <asm/virtext.h>
 
+/* Alignment required for elf header segment */
+#define ELF_CORE_HEADER_ALIGN   4096
+
+/* This primarily represents number of split ranges due to exclusion */
+#define CRASH_MAX_RANGES	16
+
+struct crash_mem_range {
+	u64 start, end;
+};
+
+struct crash_mem {
+	unsigned int nr_ranges;
+	struct crash_mem_range ranges[CRASH_MAX_RANGES];
+};
+
+/* Misc data about ram ranges needed to prepare elf headers */
+struct crash_elf_data {
+	struct kimage *image;
+	/*
+	 * Total number of ram ranges we have after various adjustments for
+	 * GART, crash reserved region etc.
+	 */
+	unsigned int max_nr_ranges;
+	unsigned long gart_start, gart_end;
+
+	/* Pointer to elf header */
+	void *ehdr;
+	/* Pointer to next phdr */
+	void *bufp;
+	struct crash_mem mem;
+};
+
+/* Used while preparing memory map entries for second kernel */
+struct crash_memmap_data {
+	struct boot_params *params;
+	/* Type of memory */
+	unsigned int type;
+};
+
 int in_crash_kexec;
 
 /*
@@ -39,6 +84,7 @@ int in_crash_kexec;
  */
 crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
 EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+unsigned long crash_zero_bytes;
 
 static inline void cpu_crash_vmclear_loaded_vmcss(void)
 {
@@ -135,3 +181,520 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 #endif
 	crash_save_cpu(regs, safe_smp_processor_id());
 }
+
+#ifdef CONFIG_X86_64
+
+static int get_nr_ram_ranges_callback(unsigned long start_pfn,
+				unsigned long nr_pfn, void *arg)
+{
+	int *nr_ranges = arg;
+
+	(*nr_ranges)++;
+	return 0;
+}
+
+static int get_gart_ranges_callback(u64 start, u64 end, void *arg)
+{
+	struct crash_elf_data *ced = arg;
+
+	ced->gart_start = start;
+	ced->gart_end = end;
+
+	/* Not expecting more than 1 gart aperture */
+	return 1;
+}
+
+
+/* Gather all the required information to prepare elf headers for ram regions */
+static void fill_up_crash_elf_data(struct crash_elf_data *ced,
+				   struct kimage *image)
+{
+	unsigned int nr_ranges = 0;
+
+	ced->image = image;
+
+	walk_system_ram_range(0, -1, &nr_ranges,
+				get_nr_ram_ranges_callback);
+
+	ced->max_nr_ranges = nr_ranges;
+
+	/*
+	 * We don't create ELF headers for GART aperture as an attempt
+	 * to dump this memory in second kernel leads to hang/crash.
+	 * If gart aperture is present, one needs to exclude that region
+	 * and that could lead to need of extra phdr.
+	 */
+	walk_iomem_res("GART", IORESOURCE_MEM, 0, -1,
+				ced, get_gart_ranges_callback);
+
+	/*
+	 * If we have gart region, excluding that could potentially split
+	 * a memory range, resulting in extra header. Account for  that.
+	 */
+	if (ced->gart_end)
+		ced->max_nr_ranges++;
+
+	/* Exclusion of crash region could split memory ranges */
+	ced->max_nr_ranges++;
+
+	/* If crashk_low_res is not 0, another range split possible */
+	if (crashk_low_res.end != 0)
+		ced->max_nr_ranges++;
+}
+
+static int exclude_mem_range(struct crash_mem *mem,
+		unsigned long long mstart, unsigned long long mend)
+{
+	int i, j;
+	unsigned long long start, end;
+	struct crash_mem_range temp_range = {0, 0};
+
+	for (i = 0; i < mem->nr_ranges; i++) {
+		start = mem->ranges[i].start;
+		end = mem->ranges[i].end;
+
+		if (mstart > end || mend < start)
+			continue;
+
+		/* Truncate any area outside of range */
+		if (mstart < start)
+			mstart = start;
+		if (mend > end)
+			mend = end;
+
+		/* Found completely overlapping range */
+		if (mstart == start && mend == end) {
+			mem->ranges[i].start = 0;
+			mem->ranges[i].end = 0;
+			if (i < mem->nr_ranges - 1) {
+				/* Shift rest of the ranges to left */
+				for (j = i; j < mem->nr_ranges - 1; j++) {
+					mem->ranges[j].start =
+						mem->ranges[j+1].start;
+					mem->ranges[j].end =
+							mem->ranges[j+1].end;
+				}
+			}
+			mem->nr_ranges--;
+			return 0;
+		}
+
+		if (mstart > start && mend < end) {
+			/* Split original range */
+			mem->ranges[i].end = mstart - 1;
+			temp_range.start = mend + 1;
+			temp_range.end = end;
+		} else if (mstart != start)
+			mem->ranges[i].end = mstart - 1;
+		else
+			mem->ranges[i].start = mend + 1;
+		break;
+	}
+
+	/* If a split happend, add the split to array */
+	if (!temp_range.end)
+		return 0;
+
+	/* Split happened */
+	if (i == CRASH_MAX_RANGES - 1) {
+		pr_err("Too many crash ranges after split\n");
+		return -ENOMEM;
+	}
+
+	/* Location where new range should go */
+	j = i + 1;
+	if (j < mem->nr_ranges) {
+		/* Move over all ranges one slot towards the end */
+		for (i = mem->nr_ranges - 1; i >= j; i--)
+			mem->ranges[i + 1] = mem->ranges[i];
+	}
+
+	mem->ranges[j].start = temp_range.start;
+	mem->ranges[j].end = temp_range.end;
+	mem->nr_ranges++;
+	return 0;
+}
+
+/*
+ * Look for any unwanted ranges between mstart, mend and remove them. This
+ * might lead to split and split ranges are put in ced->mem.ranges[] array
+ */
+static int elf_header_exclude_ranges(struct crash_elf_data *ced,
+		unsigned long long mstart, unsigned long long mend)
+{
+	struct crash_mem *cmem = &ced->mem;
+	int ret = 0;
+
+	memset(cmem->ranges, 0, sizeof(cmem->ranges));
+
+	cmem->ranges[0].start = mstart;
+	cmem->ranges[0].end = mend;
+	cmem->nr_ranges = 1;
+
+	/* Exclude crashkernel region */
+	ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+	if (ret)
+		return ret;
+
+	ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+	if (ret)
+		return ret;
+
+	/* Exclude GART region */
+	if (ced->gart_end) {
+		ret = exclude_mem_range(cmem, ced->gart_start, ced->gart_end);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg)
+{
+	struct crash_elf_data *ced = arg;
+	Elf64_Ehdr *ehdr;
+	Elf64_Phdr *phdr;
+	unsigned long mstart, mend;
+	struct kimage *image = ced->image;
+	struct crash_mem *cmem;
+	int ret, i;
+
+	ehdr = ced->ehdr;
+
+	/* Exclude unwanted mem ranges */
+	ret = elf_header_exclude_ranges(ced, start, end);
+	if (ret)
+		return ret;
+
+	/* Go through all the ranges in ced->mem.ranges[] and prepare phdr */
+	cmem = &ced->mem;
+
+	for (i = 0; i < cmem->nr_ranges; i++) {
+		mstart = cmem->ranges[i].start;
+		mend = cmem->ranges[i].end;
+
+		phdr = ced->bufp;
+		ced->bufp += sizeof(Elf64_Phdr);
+
+		phdr->p_type = PT_LOAD;
+		phdr->p_flags = PF_R|PF_W|PF_X;
+		phdr->p_offset  = mstart;
+
+		/*
+		 * If a range matches backup region, adjust offset to backup
+		 * segment.
+		 */
+		if (mstart == image->arch.backup_src_start &&
+		    (mend - mstart + 1) == image->arch.backup_src_sz)
+			phdr->p_offset = image->arch.backup_load_addr;
+
+		phdr->p_paddr = mstart;
+		phdr->p_vaddr = (unsigned long long) __va(mstart);
+		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
+		phdr->p_align = 0;
+		ehdr->e_phnum++;
+		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+			ehdr->e_phnum, phdr->p_offset);
+	}
+
+	return ret;
+}
+
+static int prepare_elf64_headers(struct crash_elf_data *ced,
+		void **addr, unsigned long *sz)
+{
+	Elf64_Ehdr *ehdr;
+	Elf64_Phdr *phdr;
+	unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
+	unsigned char *buf, *bufp;
+	unsigned int cpu;
+	unsigned long long notes_addr;
+	int ret;
+
+	/* extra phdr for vmcoreinfo elf note */
+	nr_phdr = nr_cpus + 1;
+	nr_phdr += ced->max_nr_ranges;
+
+	/*
+	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
+	 * area on x86_64 (ffffffff80000000 - ffffffffa0000000).
+	 * I think this is required by tools like gdb. So same physical
+	 * memory will be mapped in two elf headers. One will contain kernel
+	 * text virtual addresses and other will have __va(physical) addresses.
+	 */
+
+	nr_phdr++;
+	elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
+	elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
+
+	buf = vzalloc(elf_sz);
+	if (!buf)
+		return -ENOMEM;
+
+	bufp = buf;
+	ehdr = (Elf64_Ehdr *)bufp;
+	bufp += sizeof(Elf64_Ehdr);
+	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+	ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
+	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+	ehdr->e_ident[EI_OSABI] = ELF_OSABI;
+	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+	ehdr->e_type = ET_CORE;
+	ehdr->e_machine = ELF_ARCH;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_phoff = sizeof(Elf64_Ehdr);
+	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+	ehdr->e_phentsize = sizeof(Elf64_Phdr);
+
+	/* Prepare one phdr of type PT_NOTE for each present cpu */
+	for_each_present_cpu(cpu) {
+		phdr = (Elf64_Phdr *)bufp;
+		bufp += sizeof(Elf64_Phdr);
+		phdr->p_type = PT_NOTE;
+		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
+		phdr->p_offset = phdr->p_paddr = notes_addr;
+		phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
+		(ehdr->e_phnum)++;
+	}
+
+	/* Prepare one PT_NOTE header for vmcoreinfo */
+	phdr = (Elf64_Phdr *)bufp;
+	bufp += sizeof(Elf64_Phdr);
+	phdr->p_type = PT_NOTE;
+	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
+	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	(ehdr->e_phnum)++;
+
+#ifdef CONFIG_X86_64
+	/* Prepare PT_LOAD type program header for kernel text region */
+	phdr = (Elf64_Phdr *)bufp;
+	bufp += sizeof(Elf64_Phdr);
+	phdr->p_type = PT_LOAD;
+	phdr->p_flags = PF_R|PF_W|PF_X;
+	phdr->p_vaddr = (Elf64_Addr)_text;
+	phdr->p_filesz = phdr->p_memsz = _end - _text;
+	phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
+	(ehdr->e_phnum)++;
+#endif
+
+	/* Prepare PT_LOAD headers for system ram chunks. */
+	ced->ehdr = ehdr;
+	ced->bufp = bufp;
+	ret = walk_system_ram_res(0, -1, ced,
+			prepare_elf64_ram_headers_callback);
+	if (ret < 0)
+		return ret;
+
+	*addr = buf;
+	*sz = elf_sz;
+	return 0;
+}
+
+/* Prepare elf headers. Return addr and size */
+static int prepare_elf_headers(struct kimage *image, void **addr,
+					unsigned long *sz)
+{
+	struct crash_elf_data *ced;
+	int ret;
+
+	ced = kzalloc(sizeof(*ced), GFP_KERNEL);
+	if (!ced)
+		return -ENOMEM;
+
+	fill_up_crash_elf_data(ced, image);
+
+	/* By default prepare 64bit headers */
+	ret =  prepare_elf64_headers(ced, addr, sz);
+	kfree(ced);
+	return ret;
+}
+
+static int add_e820_entry(struct boot_params *params, struct e820entry *entry)
+{
+	unsigned int nr_e820_entries;
+
+	nr_e820_entries = params->e820_entries;
+	if (nr_e820_entries >= E820MAX)
+		return 1;
+
+	memcpy(&params->e820_map[nr_e820_entries], entry,
+			sizeof(struct e820entry));
+	params->e820_entries++;
+	return 0;
+}
+
+static int memmap_entry_callback(u64 start, u64 end, void *arg)
+{
+	struct crash_memmap_data *cmd = arg;
+	struct boot_params *params = cmd->params;
+	struct e820entry ei;
+
+	ei.addr = start;
+	ei.size = end - start + 1;
+	ei.type = cmd->type;
+	add_e820_entry(params, &ei);
+
+	return 0;
+}
+
+static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
+				 unsigned long long mstart,
+				 unsigned long long mend)
+{
+	unsigned long start, end;
+	int ret = 0;
+
+	cmem->ranges[0].start = mstart;
+	cmem->ranges[0].end = mend;
+	cmem->nr_ranges = 1;
+
+	/* Exclude Backup region */
+	start = image->arch.backup_load_addr;
+	end = start + image->arch.backup_src_sz - 1;
+	ret = exclude_mem_range(cmem, start, end);
+	if (ret)
+		return ret;
+
+	/* Exclude elf header region */
+	start = image->arch.elf_load_addr;
+	end = start + image->arch.elf_headers_sz - 1;
+	return exclude_mem_range(cmem, start, end);
+}
+
+/* Prepare memory map for crash dump kernel */
+int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
+{
+	int i, ret = 0;
+	unsigned long flags;
+	struct e820entry ei;
+	struct crash_memmap_data cmd;
+	struct crash_mem *cmem;
+
+	cmem = vzalloc(sizeof(struct crash_mem));
+	if (!cmem)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(struct crash_memmap_data));
+	cmd.params = params;
+
+	/* Add first 640K segment */
+	ei.addr = image->arch.backup_src_start;
+	ei.size = image->arch.backup_src_sz;
+	ei.type = E820_RAM;
+	add_e820_entry(params, &ei);
+
+	/* Add ACPI tables */
+	cmd.type = E820_ACPI;
+	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	walk_iomem_res("ACPI Tables", flags, 0, -1, &cmd,
+		       memmap_entry_callback);
+
+	/* Add ACPI Non-volatile Storage */
+	cmd.type = E820_NVS;
+	walk_iomem_res("ACPI Non-volatile Storage", flags, 0, -1, &cmd,
+			memmap_entry_callback);
+
+	/* Add crashk_low_res region */
+	if (crashk_low_res.end) {
+		ei.addr = crashk_low_res.start;
+		ei.size = crashk_low_res.end - crashk_low_res.start + 1;
+		ei.type = E820_RAM;
+		add_e820_entry(params, &ei);
+	}
+
+	/* Exclude some ranges from crashk_res and add rest to memmap */
+	ret = memmap_exclude_ranges(image, cmem, crashk_res.start,
+						crashk_res.end);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < cmem->nr_ranges; i++) {
+		ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1;
+
+		/* If entry is less than a page, skip it */
+		if (ei.size < PAGE_SIZE)
+			continue;
+		ei.addr = cmem->ranges[i].start;
+		ei.type = E820_RAM;
+		add_e820_entry(params, &ei);
+	}
+
+out:
+	vfree(cmem);
+	return ret;
+}
+
+static int determine_backup_region(u64 start, u64 end, void *arg)
+{
+	struct kimage *image = arg;
+
+	image->arch.backup_src_start = start;
+	image->arch.backup_src_sz = end - start + 1;
+
+	/* Expecting only one range for backup region */
+	return 1;
+}
+
+int crash_load_segments(struct kimage *image)
+{
+	unsigned long src_start, src_sz, elf_sz;
+	void *elf_addr;
+	int ret;
+
+	/*
+	 * Determine and load a segment for backup area. First 640K RAM
+	 * region is backup source
+	 */
+
+	ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END,
+				image, determine_backup_region);
+
+	/* Zero or postive return values are ok */
+	if (ret < 0)
+		return ret;
+
+	src_start = image->arch.backup_src_start;
+	src_sz = image->arch.backup_src_sz;
+
+	/* Add backup segment. */
+	if (src_sz) {
+		/*
+		 * Ideally there is no source for backup segment. This is
+		 * copied in purgatory after crash. Just add a zero filled
+		 * segment for now to make sure checksum logic works fine.
+		 */
+		ret = kexec_add_buffer(image, (char *)&crash_zero_bytes,
+				       sizeof(crash_zero_bytes), src_sz,
+				       PAGE_SIZE, 0, -1, 0,
+				       &image->arch.backup_load_addr);
+		if (ret)
+			return ret;
+		pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n",
+			 image->arch.backup_load_addr, src_start, src_sz);
+	}
+
+	/* Prepare elf headers and add a segment */
+	ret = prepare_elf_headers(image, &elf_addr, &elf_sz);
+	if (ret)
+		return ret;
+
+	image->arch.elf_headers = elf_addr;
+	image->arch.elf_headers_sz = elf_sz;
+
+	ret = kexec_add_buffer(image, (char *)elf_addr, elf_sz, elf_sz,
+			ELF_CORE_HEADER_ALIGN, 0, -1, 0,
+			&image->arch.elf_load_addr);
+	if (ret) {
+		vfree((void *)image->arch.elf_headers);
+		return ret;
+	}
+	pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		 image->arch.elf_load_addr, elf_sz, elf_sz);
+
+	return ret;
+}
+
+#endif /* CONFIG_X86_64 */

arch/x86/kernel/kexec-bzimage64.c

@@ -21,6 +21,9 @@
 
 #include <asm/bootparam.h>
 #include <asm/setup.h>
+#include <asm/crash.h>
+
+#define MAX_ELFCOREHDR_STR_LEN	30	/* elfcorehdr=0x<64bit-value> */
 
 /*
  * Defines lowest physical address for various segments. Not sure where
@@ -58,18 +61,24 @@ static int setup_initrd(struct boot_params *params,
 	return 0;
 }
 
-static int setup_cmdline(struct boot_params *params,
+static int setup_cmdline(struct kimage *image, struct boot_params *params,
 			 unsigned long bootparams_load_addr,
 			 unsigned long cmdline_offset, char *cmdline,
 			 unsigned long cmdline_len)
 {
 	char *cmdline_ptr = ((char *)params) + cmdline_offset;
-	unsigned long cmdline_ptr_phys;
+	unsigned long cmdline_ptr_phys, len;
 	uint32_t cmdline_low_32, cmdline_ext_32;
 
 	memcpy(cmdline_ptr, cmdline, cmdline_len);
+	if (image->type == KEXEC_TYPE_CRASH) {
+		len = sprintf(cmdline_ptr + cmdline_len - 1,
+			" elfcorehdr=0x%lx", image->arch.elf_load_addr);
+		cmdline_len += len;
+	}
 	cmdline_ptr[cmdline_len - 1] = '\0';
 
+	pr_debug("Final command line is: %s\n", cmdline_ptr);
 	cmdline_ptr_phys = bootparams_load_addr + cmdline_offset;
 	cmdline_low_32 = cmdline_ptr_phys & 0xffffffffUL;
 	cmdline_ext_32 = cmdline_ptr_phys >> 32;
@@ -98,11 +107,12 @@ static int setup_memory_map_entries(struct boot_params *params)
 	return 0;
 }
 
-static int setup_boot_parameters(struct boot_params *params)
+static int setup_boot_parameters(struct kimage *image,
+				 struct boot_params *params)
 {
 	unsigned int nr_e820_entries;
 	unsigned long long mem_k, start, end;
-	int i;
+	int i, ret = 0;
 
 	/* Get subarch from existing bootparams */
 	params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch;
@@ -125,7 +135,13 @@ static int setup_boot_parameters(struct boot_params *params)
 	/* Default sysdesc table */
 	params->sys_desc_table.length = 0;
 
-	setup_memory_map_entries(params);
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = crash_setup_memmap_entries(image, params);
+		if (ret)
+			return ret;
+	} else
+		setup_memory_map_entries(params);
+
 	nr_e820_entries = params->e820_entries;
 
 	for (i = 0; i < nr_e820_entries; i++) {
@@ -153,7 +169,7 @@ static int setup_boot_parameters(struct boot_params *params)
 	memcpy(params->edd_mbr_sig_buffer, boot_params.edd_mbr_sig_buffer,
 	       EDD_MBR_SIG_MAX * sizeof(unsigned int));
 
-	return 0;
+	return ret;
 }
 
 int bzImage64_probe(const char *buf, unsigned long len)
@@ -240,6 +256,22 @@ void *bzImage64_load(struct kimage *image, char *kernel,
 		return ERR_PTR(-EINVAL);
 	}
 
+	/*
+	 * In case of crash dump, we will append elfcorehdr=<addr> to
+	 * command line. Make sure it does not overflow
+	 */
+	if (cmdline_len + MAX_ELFCOREHDR_STR_LEN > header->cmdline_size) {
+		pr_debug("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Allocate and load backup region */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = crash_load_segments(image);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	/*
 	 * Load purgatory. For 64bit entry point, purgatory  code can be
 	 * anywhere.
@@ -254,7 +286,8 @@ void *bzImage64_load(struct kimage *image, char *kernel,
 	pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
 
 	/* Load Bootparams and cmdline */
-	params_cmdline_sz = sizeof(struct boot_params) + cmdline_len;
+	params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
+				MAX_ELFCOREHDR_STR_LEN;
 	params = kzalloc(params_cmdline_sz, GFP_KERNEL);
 	if (!params)
 		return ERR_PTR(-ENOMEM);
@@ -303,8 +336,8 @@ void *bzImage64_load(struct kimage *image, char *kernel,
 		setup_initrd(params, initrd_load_addr, initrd_len);
 	}
 
-	setup_cmdline(params, bootparam_load_addr, sizeof(struct boot_params),
-		      cmdline, cmdline_len);
+	setup_cmdline(image, params, bootparam_load_addr,
+		      sizeof(struct boot_params), cmdline, cmdline_len);
 
 	/* bootloader info. Do we need a separate ID for kexec kernel loader? */
 	params->hdr.type_of_loader = 0x0D << 4;
@@ -332,7 +365,9 @@ void *bzImage64_load(struct kimage *image, char *kernel,
 	if (ret)
 		goto out_free_params;
 
-	setup_boot_parameters(params);
+	ret = setup_boot_parameters(image, params);
+	if (ret)
+		goto out_free_params;
 
 	/* Allocate loader specific data */
 	ldata = kzalloc(sizeof(struct bzimage64_data), GFP_KERNEL);

arch/x86/kernel/machine_kexec_64.c

@@ -178,6 +178,38 @@ static void load_segments(void)
 		);
 }
 
+/* Update purgatory as needed after various image segments have been prepared */
+static int arch_update_purgatory(struct kimage *image)
+{
+	int ret = 0;
+
+	if (!image->file_mode)
+		return 0;
+
+	/* Setup copying of backup region */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		ret = kexec_purgatory_get_set_symbol(image, "backup_dest",
+				&image->arch.backup_load_addr,
+				sizeof(image->arch.backup_load_addr), 0);
+		if (ret)
+			return ret;
+
+		ret = kexec_purgatory_get_set_symbol(image, "backup_src",
+				&image->arch.backup_src_start,
+				sizeof(image->arch.backup_src_start), 0);
+		if (ret)
+			return ret;
+
+		ret = kexec_purgatory_get_set_symbol(image, "backup_sz",
+				&image->arch.backup_src_sz,
+				sizeof(image->arch.backup_src_sz), 0);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 int machine_kexec_prepare(struct kimage *image)
 {
 	unsigned long start_pgtable;
@@ -191,6 +223,11 @@ int machine_kexec_prepare(struct kimage *image)
 	if (result)
 		return result;
 
+	/* update purgatory as needed */
+	result = arch_update_purgatory(image);
+	if (result)
+		return result;
+
 	return 0;
 }
 
@@ -315,6 +352,9 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 
 void *arch_kexec_kernel_image_load(struct kimage *image)
 {
+	vfree(image->arch.elf_headers);
+	image->arch.elf_headers = NULL;
+
 	if (!image->fops || !image->fops->load)
 		return ERR_PTR(-ENOEXEC);
 

arch/x86/purgatory/entry64.S

@@ -61,13 +61,13 @@ new_cs_exit:
 	.balign 4
 entry64_regs:
 rax:	.quad 0x0
-rbx:	.quad 0x0
 rcx:	.quad 0x0
 rdx:	.quad 0x0
-rsi:	.quad 0x0
-rdi:	.quad 0x0
+rbx:	.quad 0x0
 rsp:	.quad 0x0
 rbp:	.quad 0x0
+rsi:	.quad 0x0
+rdi:	.quad 0x0
 r8:	.quad 0x0
 r9:	.quad 0x0
 r10:	.quad 0x0

kernel/kexec.c

@@ -548,6 +548,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 {
 	int ret;
 	struct kimage *image;
+	bool kexec_on_panic = flags & KEXEC_FILE_ON_CRASH;
 
 	image = do_kimage_alloc_init();
 	if (!image)
@@ -555,6 +556,12 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 
 	image->file_mode = 1;
 
+	if (kexec_on_panic) {
+		/* Enable special crash kernel control page alloc policy. */
+		image->control_page = crashk_res.start;
+		image->type = KEXEC_TYPE_CRASH;
+	}
+
 	ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd,
 					   cmdline_ptr, cmdline_len, flags);
 	if (ret)
@@ -572,10 +579,12 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 		goto out_free_post_load_bufs;
 	}
 
-	image->swap_page = kimage_alloc_control_pages(image, 0);
-	if (!image->swap_page) {
-		pr_err(KERN_ERR "Could not allocate swap buffer\n");
-		goto out_free_control_pages;
+	if (!kexec_on_panic) {
+		image->swap_page = kimage_alloc_control_pages(image, 0);
+		if (!image->swap_page) {
+			pr_err(KERN_ERR "Could not allocate swap buffer\n");
+			goto out_free_control_pages;
+		}
 	}
 
 	*rimage = image;
@@ -1113,10 +1122,14 @@ static int kimage_load_crash_segment(struct kimage *image,
 	unsigned long maddr;
 	size_t ubytes, mbytes;
 	int result;
-	unsigned char __user *buf;
+	unsigned char __user *buf = NULL;
+	unsigned char *kbuf = NULL;
 
 	result = 0;
-	buf = segment->buf;
+	if (image->file_mode)
+		kbuf = segment->kbuf;
+	else
+		buf = segment->buf;
 	ubytes = segment->bufsz;
 	mbytes = segment->memsz;
 	maddr = segment->mem;
@@ -1139,7 +1152,12 @@ static int kimage_load_crash_segment(struct kimage *image,
 			/* Zero the trailing part of the page */
 			memset(ptr + uchunk, 0, mchunk - uchunk);
 		}
-		result = copy_from_user(ptr, buf, uchunk);
+
+		/* For file based kexec, source pages are in kernel memory */
+		if (image->file_mode)
+			memcpy(ptr, kbuf, uchunk);
+		else
+			result = copy_from_user(ptr, buf, uchunk);
 		kexec_flush_icache_page(page);
 		kunmap(page);
 		if (result) {
@@ -1148,7 +1166,10 @@ static int kimage_load_crash_segment(struct kimage *image,
 		}
 		ubytes -= uchunk;
 		maddr  += mchunk;
-		buf += mchunk;
+		if (image->file_mode)
+			kbuf += mchunk;
+		else
+			buf += mchunk;
 		mbytes -= mchunk;
 	}
 out:
@@ -2127,7 +2148,14 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	ret = walk_system_ram_res(0, -1, kbuf, locate_mem_hole_callback);
+	if (image->type == KEXEC_TYPE_CRASH)
+		ret = walk_iomem_res("Crash kernel",
+				     IORESOURCE_MEM | IORESOURCE_BUSY,
+				     crashk_res.start, crashk_res.end, kbuf,
+				     locate_mem_hole_callback);
+	else
+		ret = walk_system_ram_res(0, -1, kbuf,
+					  locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;