[PATCH 6/6] kexec: Support for Kexec on panic using new system call
Baoquan He
bhe at redhat.com
Thu Nov 28 06:28:16 EST 2013
On 11/20/13 at 12:50pm, Vivek Goyal wrote:
> This patch adds support for loading a kexec on panic (kdump) kernel usning
> new system call.
>
> Signed-off-by: Vivek Goyal <vgoyal at redhat.com>
> ---
> arch/x86/include/asm/crash.h | 9 +
> arch/x86/include/asm/kexec.h | 17 +
> arch/x86/kernel/crash.c | 585 ++++++++++++++++++++++++++++++++++++
> arch/x86/kernel/kexec-bzimage.c | 63 ++++-
> arch/x86/kernel/machine_kexec_64.c | 1 +
> kernel/kexec.c | 69 ++++-
> 6 files changed, 731 insertions(+), 13 deletions(-)
> create mode 100644 arch/x86/include/asm/crash.h
>
> diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h
> new file mode 100644
> index 0000000..2dd2eb8
> --- /dev/null
> +++ b/arch/x86/include/asm/crash.h
> @@ -0,0 +1,9 @@
> +#ifndef _ASM_X86_CRASH_H
> +#define _ASM_X86_CRASH_H
> +
> +int load_crashdump_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 */
> diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
> index 94f1257..9dc19fe 100644
> --- a/arch/x86/include/asm/kexec.h
> +++ b/arch/x86/include/asm/kexec.h
> @@ -64,6 +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 (655360UL) /* 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
> @@ -166,8 +170,21 @@ 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 */
> + unsigned long elf_headers;
> + unsigned long elf_headers_sz;
> + unsigned long elf_load_addr;
> };
> +#endif /* CONFIG_X86_32 */
>
> +#ifdef CONFIG_X86_64
> struct kexec_entry64_regs {
> uint64_t rax;
> uint64_t rbx;
> diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
> index 18677a9..d5d3118 100644
> --- a/arch/x86/kernel/crash.c
> +++ b/arch/x86/kernel/crash.c
> @@ -4,6 +4,9 @@
> * Created by: Hariprasad Nellitheertha (hari at in.ibm.com)
> *
> * Copyright (C) IBM Corporation, 2004. All rights reserved.
> + * Copyright (C) Red Hat Inc., 2013. All rights reserved.
> + * Authors:
> + * Vivek Goyal <vgoyal at redhat.com>
> *
> */
>
> @@ -17,6 +20,7 @@
> #include <linux/elf.h>
> #include <linux/elfcore.h>
> #include <linux/module.h>
> +#include <linux/slab.h>
>
> #include <asm/processor.h>
> #include <asm/hardirq.h>
> @@ -29,6 +33,45 @@
> #include <asm/reboot.h>
> #include <asm/virtext.h>
>
> +/* Alignment required for elf header segment */
> +#define ELF_CORE_HEADER_ALIGN 4096
> +
> +/* This primarily reprsents number of split ranges due to exclusion */
> +#define CRASH_MAX_RANGES 16
> +
> +struct crash_mem_range {
> + unsigned long long 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 ajustments 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 prepareing memory map entries for second kernel */
> +struct crash_memmap_data {
> + struct boot_params *params;
> + /* Type of memory */
> + unsigned int type;
> +};
> +
> int in_crash_kexec;
>
> /*
> @@ -138,3 +181,545 @@ 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 int fill_up_ced(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_ram_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 there, another range split possible */
> + if (crashk_low_res.end != 0)
> + ced->max_nr_ranges++;
> +
> + return 0;
> +}
> +
> +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 in array */
> + if (!temp_range.end)
> + return 0;
> +
> + /* Split happened */
> + if (i == CRASH_MAX_RANGES - 1) {
> + printk("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 place */
> + 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,
> + unsigned long *addr, unsigned long *sz)
> +{
> + Elf64_Ehdr *ehdr;
> + Elf64_Phdr *phdr;
> + unsigned long nr_cpus = NR_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_entry = 0;
> + ehdr->e_phoff = sizeof(Elf64_Ehdr);
> + ehdr->e_shoff = 0;
> + ehdr->e_flags = 0;
> + ehdr->e_ehsize = sizeof(Elf64_Ehdr);
> + ehdr->e_phentsize = sizeof(Elf64_Phdr);
> + ehdr->e_phnum = 0;
> + ehdr->e_shentsize = 0;
> + ehdr->e_shnum = 0;
> + ehdr->e_shstrndx = 0;
> +
> + /* 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;
> + phdr->p_flags = 0;
> + notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
> + phdr->p_offset = phdr->p_paddr = notes_addr;
> + phdr->p_vaddr = 0;
> + phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
> + phdr->p_align = 0;
> + (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_flags = 0;
> + phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
> + phdr->p_vaddr = 0;
> + phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
> + phdr->p_align = 0;
> + (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);
> + phdr->p_align = 0;
> + (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 = (unsigned long)buf;
> + *sz = elf_sz;
> + return 0;
> +}
> +
> +/* Prepare elf headers. Return addr and size */
> +static int prepare_elf_headers(struct kimage *image, unsigned long *addr,
> + unsigned long *sz)
> +{
> + struct crash_elf_data *ced;
> + int ret;
> +
> + ced = kzalloc(sizeof(*ced), GFP_KERNEL);
> + if (!ced)
> + return -ENOMEM;
> +
> + ret = fill_up_ced(ced, image);
> + if (ret)
> + goto out;
> +
> + /* By default prepare 64bit headers */
> + ret = prepare_elf64_headers(ced, addr, sz);
> +out:
> + 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(¶ms->e820_map[nr_e820_entries], entry,
> + sizeof(struct e820entry));
> + params->e820_entries++;
> +
> + pr_debug("Add e820 entry to bootparams. addr=0x%llx size=0x%llx"
> + " type=%d\n", entry->addr, entry->size, entry->type);
> + 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;
> +
> + memset(cmem->ranges, 0, sizeof(cmem->ranges));
> +
> + 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;
> + ret = exclude_mem_range(cmem, start, end);
> + return ret;
> +}
> +
> +/* 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_ram_res("ACPI Tables", flags, 0, -1, &cmd, memmap_entry_callback);
> +
> + /* Add ACPI Non-volatile Storage */
> + cmd.type = E820_NVS;
> + walk_ram_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.addr = cmem->ranges[i].start;
> + ei.size = cmem->ranges[i].end - ei.addr + 1;
> + ei.type = E820_RAM;
> +
> + /* If entry is less than a page, skip it */
> + if (ei.size < PAGE_SIZE) {
> + continue;
> + }
> + 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 load_crashdump_segments(struct kimage *image)
> +{
> + unsigned long src_start, src_sz;
> + unsigned long elf_addr, elf_sz;
> + 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 of 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) {
> + ret = kexec_add_buffer(image, __va(src_start), src_sz, src_sz,
> + PAGE_SIZE, 0, -1, 0,
> + &image->arch.backup_load_addr);
> + if (ret)
> + return ret;
> + }
> +
> + /* 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)
> + kfree((void *)image->arch.elf_headers);
> +
> + return ret;
> +}
> +
> +int crash_copy_backup_region(struct kimage *image)
> +{
Why need this func be called, backup region has been added into crash
segment by kexec_add_buffer, and then buffer copy is done in
kimage_load_crash_segment. I think this copy is handled twice. Please
correct me if I am wrong.
> + unsigned long dest_start, src_start, src_sz;
> +
> + dest_start = image->arch.backup_load_addr;
> + src_start = image->arch.backup_src_start;
> + src_sz = image->arch.backup_src_sz;
> +
> + memcpy(__va(dest_start), __va(src_start), src_sz);
> +
> + return 0;
> +}
> +#endif /* CONFIG_X86_64 */
> diff --git a/arch/x86/kernel/kexec-bzimage.c b/arch/x86/kernel/kexec-bzimage.c
> index a1032d4..606942c 100644
> --- a/arch/x86/kernel/kexec-bzimage.c
> +++ b/arch/x86/kernel/kexec-bzimage.c
> @@ -8,6 +8,9 @@
>
> #include <asm/bootparam.h>
> #include <asm/setup.h>
> +#include <asm/crash.h>
> +
> +#define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */
>
> #ifdef CONFIG_X86_64
>
> @@ -86,7 +89,8 @@ static int setup_memory_map_entries(struct boot_params *params)
> return 0;
> }
>
> -static void setup_linux_system_parameters(struct boot_params *params)
> +static void setup_linux_system_parameters(struct kimage *image,
> + struct boot_params *params)
> {
> unsigned int nr_e820_entries;
> unsigned long long mem_k, start, end;
> @@ -113,7 +117,10 @@ static void setup_linux_system_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)
> + crash_setup_memmap_entries(image, params);
> + else
> + setup_memory_map_entries(params);
> nr_e820_entries = params->e820_entries;
>
> for(i = 0; i < nr_e820_entries; i++) {
> @@ -151,18 +158,23 @@ static void setup_initrd(struct boot_params *boot_params, unsigned long initrd_l
> boot_params->ext_ramdisk_size = initrd_len >> 32;
> }
>
> -static void setup_cmdline(struct boot_params *boot_params,
> +static void setup_cmdline(struct kimage *image, struct boot_params *boot_params,
> unsigned long bootparams_load_addr,
> unsigned long cmdline_offset, char *cmdline,
> unsigned long cmdline_len)
> {
> char *cmdline_ptr = ((char *)boot_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;
> @@ -203,17 +215,34 @@ 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) {
> + ret = -EINVAL;
> + pr_debug("Kernel command line too long\n");
> + return ERR_PTR(-EINVAL);
> + }
> +
> /* Allocate loader specific data */
> ldata = kzalloc(sizeof(struct bzimage64_data), GFP_KERNEL);
> if (!ldata)
> return ERR_PTR(-ENOMEM);
>
> + /* Allocate and load backup region */
> + if (image->type == KEXEC_TYPE_CRASH) {
> + ret = load_crashdump_segments(image);
> + if (ret)
> + goto out_free_loader_data;
> + }
> +
> /* Argument/parameter segment */
> kern16_size_needed = kern16_size;
> if (kern16_size_needed < 4096)
> kern16_size_needed = 4096;
>
> - setup_size = kern16_size_needed + cmdline_len;
> + setup_size = kern16_size_needed + cmdline_len + MAX_ELFCOREHDR_STR_LEN;
> params = kzalloc(setup_size, GFP_KERNEL);
> if (!params) {
> ret = -ENOMEM;
> @@ -259,14 +288,14 @@ void *bzImage64_load(struct kimage *image, char *kernel,
> setup_initrd(params, initrd_load_addr, initrd_len);
> }
>
> - setup_cmdline(params, bootparam_load_addr, kern16_size_needed,
> + setup_cmdline(image, params, bootparam_load_addr, kern16_size_needed,
> cmdline, cmdline_len);
>
> /* bootloader info. Do we need a separate ID for kexec kernel loader? */
> params->hdr.type_of_loader = 0x0D << 4;
> params->hdr.loadflags = 0;
>
> - setup_linux_system_parameters(params);
> + setup_linux_system_parameters(image, params);
>
> /*
> * Allocate a purgatory page. For 64bit entry point, purgatory
> @@ -302,7 +331,7 @@ out_free_loader_data:
> return ERR_PTR(ret);
> }
>
> -int bzImage64_prep_entry(struct kimage *image)
> +static int prepare_purgatory(struct kimage *image)
> {
> struct bzimage64_data *ldata;
> char *purgatory_page;
> @@ -362,6 +391,22 @@ int bzImage64_prep_entry(struct kimage *image)
> return 0;
> }
>
> +int bzImage64_prep_entry(struct kimage *image)
> +{
> + if (!image->file_mode)
> + return 0;
> +
> + if (!image->image_loader_data)
> + return -EINVAL;
> +
> + prepare_purgatory(image);
> +
> + if (image->type == KEXEC_TYPE_CRASH)
> + crash_copy_backup_region(image);
> +
> + return 0;
> +}
> +
> /* This cleanup function is called after various segments have been loaded */
> int bzImage64_cleanup(struct kimage *image)
> {
> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> index a66ce1d..9d7a42d 100644
> --- a/arch/x86/kernel/machine_kexec_64.c
> +++ b/arch/x86/kernel/machine_kexec_64.c
> @@ -334,6 +334,7 @@ int arch_image_file_post_load_cleanup(struct kimage *image)
> {
> int idx = image->file_handler_idx;
>
> + vfree((void *)image->arch.elf_headers);
> if (kexec_file_type[idx].cleanup)
> return kexec_file_type[idx].cleanup(image);
> return 0;
> diff --git a/kernel/kexec.c b/kernel/kexec.c
> index 50bcaa8..64184a7 100644
> --- a/kernel/kexec.c
> +++ b/kernel/kexec.c
> @@ -524,7 +524,6 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
> *rimage = image;
> return 0;
>
> -
> out_free_control_pages:
> kimage_free_page_list(&image->control_pages);
> out_free_image:
> @@ -532,6 +531,54 @@ out_free_image:
> return result;
> }
>
> +static int kimage_file_crash_alloc(struct kimage **rimage, int kernel_fd,
> + int initrd_fd, const char __user *cmdline_ptr,
> + unsigned long cmdline_len)
> +{
> + int result;
> + struct kimage *image;
> +
> + /* Allocate and initialize a controlling structure */
> + image = do_kimage_alloc_init();
> + if (!image)
> + return -ENOMEM;
> +
> + image->file_mode = 1;
> + image->file_handler_idx = -1;
> +
> + /* Enable the special crash kernel control page allocation policy. */
> + image->control_page = crashk_res.start;
> + image->type = KEXEC_TYPE_CRASH;
> +
> + result = kimage_file_prepare_segments(image, kernel_fd, initrd_fd,
> + cmdline_ptr, cmdline_len);
> + if (result)
> + goto out_free_image;
> +
> + result = sanity_check_segment_list(image);
> + if (result)
> + goto out_free_post_load_bufs;
> +
> + result = -ENOMEM;
> + image->control_code_page = kimage_alloc_control_pages(image,
> + get_order(KEXEC_CONTROL_PAGE_SIZE));
> + if (!image->control_code_page) {
> + printk(KERN_ERR "Could not allocate control_code_buffer\n");
> + goto out_free_post_load_bufs;
> + }
> +
> + *rimage = image;
> + return 0;
> +
> +out_free_post_load_bufs:
> + kimage_file_post_load_cleanup(image);
> + kfree(image->image_loader_data);
> +out_free_image:
> + kfree(image);
> + return result;
> +}
> +
> +
> static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
> unsigned long nr_segments,
> struct kexec_segment __user *segments)
> @@ -1130,7 +1177,12 @@ 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, buf, uchunk);
> + else
> + result = copy_from_user(ptr, buf, uchunk);
> kexec_flush_icache_page(page);
> kunmap(page);
> if (result) {
> @@ -1358,7 +1410,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, const char __us
> if (flags & KEXEC_FILE_UNLOAD)
> goto exchange;
>
> - ret = kimage_file_normal_alloc(&image, kernel_fd, initrd_fd,
> + if (flags & KEXEC_FILE_ON_CRASH)
> + ret = kimage_file_crash_alloc(&image, kernel_fd, initrd_fd,
> + cmdline_ptr, cmdline_len);
> + else
> + ret = kimage_file_normal_alloc(&image, kernel_fd, initrd_fd,
> cmdline_ptr, cmdline_len);
> if (ret)
> goto out;
> @@ -2108,7 +2164,12 @@ int kexec_add_buffer(struct kimage *image, char *buffer,
> kbuf->top_down = top_down;
>
> /* Walk the RAM ranges and allocate a suitable range for the buffer */
> - walk_system_ram_res(0, -1, kbuf, walk_ram_range_callback);
> + if (image->type == KEXEC_TYPE_CRASH)
> + walk_ram_res("Crash kernel", IORESOURCE_MEM | IORESOURCE_BUSY,
> + crashk_res.start, crashk_res.end, kbuf,
> + walk_ram_range_callback);
> + else
> + walk_system_ram_res(0, -1, kbuf, walk_ram_range_callback);
>
> kbuf->image = NULL;
> kfree(kbuf);
> --
> 1.7.7.6
>
>
> _______________________________________________
> kexec mailing list
> kexec at lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec
More information about the kexec
mailing list