diff options
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/Makefile | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/intel_cacheinfo.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_amd.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/crash.c | 563 | ||||
| -rw-r--r-- | arch/x86/kernel/kexec-bzimage64.c | 532 | ||||
| -rw-r--r-- | arch/x86/kernel/machine_kexec_64.c | 228 |
7 files changed, 1331 insertions, 7 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 047f9ff2e36c..ece67cbe139d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -117,4 +117,5 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o obj-y += vsmp_64.o + obj-$(CONFIG_KEXEC) += kexec-bzimage64.o endif diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 9c8f7394c612..c7035073dfc1 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -461,7 +461,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - if (strict_strtoul(buf, 10, &val) < 0) + if (kstrtoul(buf, 10, &val) < 0) return -EINVAL; err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val); @@ -511,7 +511,7 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return -EINVAL; - if (strict_strtoul(buf, 16, &val) < 0) + if (kstrtoul(buf, 16, &val) < 0) return -EINVAL; if (amd_set_subcaches(cpu, val)) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 4fc57975acc1..bd9ccda8087f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2136,7 +2136,7 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; attr_to_bank(attr)->ctl = new; @@ -2174,7 +2174,7 @@ static ssize_t set_ignore_ce(struct device *s, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; if (mca_cfg.ignore_ce ^ !!new) { @@ -2198,7 +2198,7 @@ static ssize_t set_cmci_disabled(struct device *s, { u64 new; - if (strict_strtoull(buf, 0, &new) < 0) + if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; if (mca_cfg.cmci_disabled ^ !!new) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 603df4f74640..1e49f8f41276 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -353,7 +353,7 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) if (!b->interrupt_capable) return -EINVAL; - if (strict_strtoul(buf, 0, &new) < 0) + if (kstrtoul(buf, 0, &new) < 0) return -EINVAL; b->interrupt_enable = !!new; @@ -372,7 +372,7 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) struct thresh_restart tr; unsigned long new; - if (strict_strtoul(buf, 0, &new) < 0) + if (kstrtoul(buf, 0, &new) < 0) return -EINVAL; if (new > THRESHOLD_MAX) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 507de8066594..0553a34fa0df 100644 --- a/arch/x86/kernel/crash.c +++ b/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(¶ms->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 */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c new file mode 100644 index 000000000000..623e6c58081f --- /dev/null +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -0,0 +1,532 @@ +/* + * Kexec bzImage loader + * + * Copyright (C) 2014 Red Hat Inc. + * Authors: + * Vivek Goyal <vgoyal@redhat.com> + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#define pr_fmt(fmt) "kexec-bzImage64: " fmt + +#include <linux/string.h> +#include <linux/printk.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/efi.h> + +#include <asm/bootparam.h> +#include <asm/setup.h> +#include <asm/crash.h> +#include <asm/efi.h> + +#define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ + +/* + * Defines lowest physical address for various segments. Not sure where + * exactly these limits came from. Current bzimage64 loader in kexec-tools + * uses these so I am retaining it. It can be changed over time as we gain + * more insight. + */ +#define MIN_PURGATORY_ADDR 0x3000 +#define MIN_BOOTPARAM_ADDR 0x3000 +#define MIN_KERNEL_LOAD_ADDR 0x100000 +#define MIN_INITRD_LOAD_ADDR 0x1000000 + +/* + * This is a place holder for all boot loader specific data structure which + * gets allocated in one call but gets freed much later during cleanup + * time. Right now there is only one field but it can grow as need be. + */ +struct bzimage64_data { + /* + * Temporary buffer to hold bootparams buffer. This should be + * freed once the bootparam segment has been loaded. + */ + void *bootparams_buf; +}; + +static int setup_initrd(struct boot_params *params, + unsigned long initrd_load_addr, unsigned long initrd_len) +{ + params->hdr.ramdisk_image = initrd_load_addr & 0xffffffffUL; + params->hdr.ramdisk_size = initrd_len & 0xffffffffUL; + + params->ext_ramdisk_image = initrd_load_addr >> 32; + params->ext_ramdisk_size = initrd_len >> 32; + + return 0; +} + +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, 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; + + params->hdr.cmd_line_ptr = cmdline_low_32; + if (cmdline_ext_32) + params->ext_cmd_line_ptr = cmdline_ext_32; + + return 0; +} + +static int setup_e820_entries(struct boot_params *params) +{ + unsigned int nr_e820_entries; + + nr_e820_entries = e820_saved.nr_map; + + /* TODO: Pass entries more than E820MAX in bootparams setup data */ + if (nr_e820_entries > E820MAX) + nr_e820_entries = E820MAX; + + params->e820_entries = nr_e820_entries; + memcpy(¶ms->e820_map, &e820_saved.map, + nr_e820_entries * sizeof(struct e820entry)); + + return 0; +} + +#ifdef CONFIG_EFI +static int setup_efi_info_memmap(struct boot_params *params, + unsigned long params_load_addr, + unsigned int efi_map_offset, + unsigned int efi_map_sz) +{ + void *efi_map = (void *)params + efi_map_offset; + unsigned long efi_map_phys_addr = params_load_addr + efi_map_offset; + struct efi_info *ei = ¶ms->efi_info; + + if (!efi_map_sz) + return 0; + + efi_runtime_map_copy(efi_map, efi_map_sz); + + ei->efi_memmap = efi_map_phys_addr & 0xffffffff; + ei->efi_memmap_hi = efi_map_phys_addr >> 32; + ei->efi_memmap_size = efi_map_sz; + + return 0; +} + +static int +prepare_add_efi_setup_data(struct boot_params *params, + unsigned long params_load_addr, + unsigned int efi_setup_data_offset) +{ + unsigned long setup_data_phys; + struct setup_data *sd = (void *)params + efi_setup_data_offset; + struct efi_setup_data *esd = (void *)sd + sizeof(struct setup_data); + + esd->fw_vendor = efi.fw_vendor; + esd->runtime = efi.runtime; + esd->tables = efi.config_table; + esd->smbios = efi.smbios; + + sd->type = SETUP_EFI; + sd->len = sizeof(struct efi_setup_data); + + /* Add setup data */ + setup_data_phys = params_load_addr + efi_setup_data_offset; + sd->next = params->hdr.setup_data; + params->hdr.setup_data = setup_data_phys; + + return 0; +} + +static int +setup_efi_state(struct boot_params *params, unsigned long params_load_addr, + unsigned int efi_map_offset, unsigned int efi_map_sz, + unsigned int efi_setup_data_offset) +{ + struct efi_info *current_ei = &boot_params.efi_info; + struct efi_info *ei = ¶ms->efi_info; + + if (!current_ei->efi_memmap_size) + return 0; + + /* + * If 1:1 mapping is not enabled, second kernel can not setup EFI + * and use EFI run time services. User space will have to pass + * acpi_rsdp=<addr> on kernel command line to make second kernel boot + * without efi. + */ + if (efi_enabled(EFI_OLD_MEMMAP)) + return 0; + + ei->efi_loader_signature = current_ei->efi_loader_signature; + ei->efi_systab = current_ei->efi_systab; + ei->efi_systab_hi = current_ei->efi_systab_hi; + + ei->efi_memdesc_version = current_ei->efi_memdesc_version; + ei->efi_memdesc_size = efi_get_runtime_map_desc_size(); + + setup_efi_info_memmap(params, params_load_addr, efi_map_offset, + efi_map_sz); + prepare_add_efi_setup_data(params, params_load_addr, + efi_setup_data_offset); + return 0; +} +#endif /* CONFIG_EFI */ + +static int +setup_boot_parameters(struct kimage *image, struct boot_params *params, + unsigned long params_load_addr, + unsigned int efi_map_offset, unsigned int efi_map_sz, + unsigned int efi_setup_data_offset) +{ + unsigned int nr_e820_entries; + unsigned long long mem_k, start, end; + int i, ret = 0; + + /* Get subarch from existing bootparams */ + params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; + + /* Copying screen_info will do? */ + memcpy(¶ms->screen_info, &boot_params.screen_info, + sizeof(struct screen_info)); + + /* Fill in memsize later */ + params->screen_info.ext_mem_k = 0; + params->alt_mem_k = 0; + + /* Default APM info */ + memset(¶ms->apm_bios_info, 0, sizeof(params->apm_bios_info)); + + /* Default drive info */ + memset(¶ms->hd0_info, 0, sizeof(params->hd0_info)); + memset(¶ms->hd1_info, 0, sizeof(params->hd1_info)); + + /* Default sysdesc table */ + params->sys_desc_table.length = 0; + + if (image->type == KEXEC_TYPE_CRASH) { + ret = crash_setup_memmap_entries(image, params); + if (ret) + return ret; + } else + setup_e820_entries(params); + + nr_e820_entries = params->e820_entries; + + for (i = 0; i < nr_e820_entries; i++) { + if (params->e820_map[i].type != E820_RAM) + continue; + start = params->e820_map[i].addr; + end = params->e820_map[i].addr + params->e820_map[i].size - 1; + + if ((start <= 0x100000) && end > 0x100000) { + mem_k = (end >> 10) - (0x100000 >> 10); + params->screen_info.ext_mem_k = mem_k; + params->alt_mem_k = mem_k; + if (mem_k > 0xfc00) + params->screen_info.ext_mem_k = 0xfc00; /* 64M*/ + if (mem_k > 0xffffffff) + params->alt_mem_k = 0xffffffff; + } + } + +#ifdef CONFIG_EFI + /* Setup EFI state */ + setup_efi_state(params, params_load_addr, efi_map_offset, efi_map_sz, + efi_setup_data_offset); +#endif + + /* Setup EDD info */ + memcpy(params->eddbuf, boot_params.eddbuf, + EDDMAXNR * sizeof(struct edd_info)); + params->eddbuf_entries = boot_params.eddbuf_entries; + + memcpy(params->edd_mbr_sig_buffer, boot_params.edd_mbr_sig_buffer, + EDD_MBR_SIG_MAX * sizeof(unsigned int)); + + return ret; +} + +int bzImage64_probe(const char *buf, unsigned long len) +{ + int ret = -ENOEXEC; + struct setup_header *header; + + /* kernel should be atleast two sectors long */ + if (len < 2 * 512) { + pr_err("File is too short to be a bzImage\n"); + return ret; + } + + header = (struct setup_header *)(buf + offsetof(struct boot_params, hdr)); + if (memcmp((char *)&header->header, "HdrS", 4) != 0) { + pr_err("Not a bzImage\n"); + return ret; + } + + if (header->boot_flag != 0xAA55) { + pr_err("No x86 boot sector present\n"); + return ret; + } + + if (header->version < 0x020C) { + pr_err("Must be at least protocol version 2.12\n"); + return ret; + } + + if (!(header->loadflags & LOADED_HIGH)) { + pr_err("zImage not a bzImage\n"); + return ret; + } + + if (!(header->xloadflags & XLF_KERNEL_64)) { + pr_err("Not a bzImage64. XLF_KERNEL_64 is not set.\n"); + return ret; + } + + if (!(header->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G)) { + pr_err("XLF_CAN_BE_LOADED_ABOVE_4G is not set.\n"); + return ret; + } + + /* + * Can't handle 32bit EFI as it does not allow loading kernel + * above 4G. This should be handled by 32bit bzImage loader + */ + if (efi_enabled(EFI_RUNTIME_SERVICES) && !efi_enabled(EFI_64BIT)) { + pr_debug("EFI is 32 bit. Can't load kernel above 4G.\n"); + return ret; + } + + /* I've got a bzImage */ + pr_debug("It's a relocatable bzImage64\n"); + ret = 0; + + return ret; +} + +void *bzImage64_load(struct kimage *image, char *kernel, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + + struct setup_header *header; + int setup_sects, kern16_size, ret = 0; + unsigned long setup_header_size, params_cmdline_sz, params_misc_sz; + struct boot_params *params; + unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr; + unsigned long purgatory_load_addr; + unsigned long kernel_bufsz, kernel_memsz, kernel_align; + char *kernel_buf; + struct bzimage64_data *ldata; + struct kexec_entry64_regs regs64; + void *stack; + unsigned int setup_hdr_offset = offsetof(struct boot_params, hdr); + unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset; + + header = (struct setup_header *)(kernel + setup_hdr_offset); + setup_sects = header->setup_sects; + if (setup_sects == 0) + setup_sects = 4; + + kern16_size = (setup_sects + 1) * 512; + if (kernel_len < kern16_size) { + pr_err("bzImage truncated\n"); + return ERR_PTR(-ENOEXEC); + } + + if (cmdline_len > header->cmdline_size) { + pr_err("Kernel command line too long\n"); + 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. + */ + ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1, + &purgatory_load_addr); + if (ret) { + pr_err("Loading purgatory failed\n"); + return ERR_PTR(ret); + } + + pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + + + /* + * Load Bootparams and cmdline and space for efi stuff. + * + * Allocate memory together for multiple data structures so + * that they all can go in single area/segment and we don't + * have to create separate segment for each. Keeps things + * little bit simple + */ + efi_map_sz = efi_get_runtime_map_size(); + efi_map_sz = ALIGN(efi_map_sz, 16); + params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + + MAX_ELFCOREHDR_STR_LEN; + params_cmdline_sz = ALIGN(params_cmdline_sz, 16); + params_misc_sz = params_cmdline_sz + efi_map_sz + + sizeof(struct setup_data) + + sizeof(struct efi_setup_data); + + params = kzalloc(params_misc_sz, GFP_KERNEL); + if (!params) + return ERR_PTR(-ENOMEM); + efi_map_offset = params_cmdline_sz; + efi_setup_data_offset = efi_map_offset + efi_map_sz; + + /* Copy setup header onto bootparams. Documentation/x86/boot.txt */ + setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset; + + /* Is there a limit on setup header size? */ + memcpy(¶ms->hdr, (kernel + setup_hdr_offset), setup_header_size); + + ret = kexec_add_buffer(image, (char *)params, params_misc_sz, + params_misc_sz, 16, MIN_BOOTPARAM_ADDR, + ULONG_MAX, 1, &bootparam_load_addr); + if (ret) + goto out_free_params; + pr_debug("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + bootparam_load_addr, params_misc_sz, params_misc_sz); + + /* Load kernel */ + kernel_buf = kernel + kern16_size; + kernel_bufsz = kernel_len - kern16_size; + kernel_memsz = PAGE_ALIGN(header->init_size); + kernel_align = header->kernel_alignment; + + ret = kexec_add_buffer(image, kernel_buf, + kernel_bufsz, kernel_memsz, kernel_align, + MIN_KERNEL_LOAD_ADDR, ULONG_MAX, 1, + &kernel_load_addr); + if (ret) + goto out_free_params; + + pr_debug("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_load_addr, kernel_memsz, kernel_memsz); + + /* Load initrd high */ + if (initrd) { + ret = kexec_add_buffer(image, initrd, initrd_len, initrd_len, + PAGE_SIZE, MIN_INITRD_LOAD_ADDR, + ULONG_MAX, 1, &initrd_load_addr); + if (ret) + goto out_free_params; + + pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); + + setup_initrd(params, initrd_load_addr, initrd_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; + params->hdr.loadflags = 0; + + /* Setup purgatory regs for entry */ + ret = kexec_purgatory_get_set_symbol(image, "entry64_regs", ®s64, + sizeof(regs64), 1); + if (ret) + goto out_free_params; + + regs64.rbx = 0; /* Bootstrap Processor */ + regs64.rsi = bootparam_load_addr; + regs64.rip = kernel_load_addr + 0x200; + stack = kexec_purgatory_get_symbol_addr(image, "stack_end"); + if (IS_ERR(stack)) { + pr_err("Could not find address of symbol stack_end\n"); + ret = -EINVAL; + goto out_free_params; + } + + regs64.rsp = (unsigned long)stack; + ret = kexec_purgatory_get_set_symbol(image, "entry64_regs", ®s64, + sizeof(regs64), 0); + if (ret) + goto out_free_params; + + ret = setup_boot_parameters(image, params, bootparam_load_addr, + efi_map_offset, efi_map_sz, + efi_setup_data_offset); + if (ret) + goto out_free_params; + + /* Allocate loader specific data */ + ldata = kzalloc(sizeof(struct bzimage64_data), GFP_KERNEL); + if (!ldata) { + ret = -ENOMEM; + goto out_free_params; + } + + /* + * Store pointer to params so that it could be freed after loading + * params segment has been loaded and contents have been copied + * somewhere else. + */ + ldata->bootparams_buf = params; + return ldata; + +out_free_params: + kfree(params); + return ERR_PTR(ret); +} + +/* This cleanup function is called after various segments have been loaded */ +int bzImage64_cleanup(void *loader_data) +{ + struct bzimage64_data *ldata = loader_data; + + if (!ldata) + return 0; + + kfree(ldata->bootparams_buf); + ldata->bootparams_buf = NULL; + + return 0; +} + +struct kexec_file_ops kexec_bzImage64_ops = { + .probe = bzImage64_probe, + .load = bzImage64_load, + .cleanup = bzImage64_cleanup, +}; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 679cef0791cd..9330434da777 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -6,6 +6,8 @@ * Version 2. See the file COPYING for more details. */ +#define pr_fmt(fmt) "kexec: " fmt + #include <linux/mm.h> #include <linux/kexec.h> #include <linux/string.h> @@ -21,6 +23,11 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/debugreg.h> +#include <asm/kexec-bzimage64.h> + +static struct kexec_file_ops *kexec_file_loaders[] = { + &kexec_bzImage64_ops, +}; static void free_transition_pgtable(struct kimage *image) { @@ -171,6 +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; @@ -184,6 +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; } @@ -283,3 +327,187 @@ void arch_crash_save_vmcoreinfo(void) (unsigned long)&_text - __START_KERNEL); } +/* arch-dependent functionality related to kexec file-based syscall */ + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int i, ret = -ENOEXEC; + struct kexec_file_ops *fops; + + for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { + fops = kexec_file_loaders[i]; + if (!fops || !fops->probe) + continue; + + ret = fops->probe(buf, buf_len); + if (!ret) { + image->fops = fops; + return ret; + } + } + + return ret; +} + +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); + + return image->fops->load(image, image->kernel_buf, + image->kernel_buf_len, image->initrd_buf, + image->initrd_buf_len, image->cmdline_buf, + image->cmdline_buf_len); +} + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + if (!image->fops || !image->fops->cleanup) + return 0; + + return image->fops->cleanup(image->image_loader_data); +} + +/* + * Apply purgatory relocations. + * + * ehdr: Pointer to elf headers + * sechdrs: Pointer to section headers. + * relsec: section index of SHT_RELA section. + * + * TODO: Some of the code belongs to generic code. Move that in kexec.c. + */ +int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, + Elf64_Shdr *sechdrs, unsigned int relsec) +{ + unsigned int i; + Elf64_Rela *rel; + Elf64_Sym *sym; + void *location; + Elf64_Shdr *section, *symtabsec; + unsigned long address, sec_base, value; + const char *strtab, *name, *shstrtab; + + /* + * ->sh_offset has been modified to keep the pointer to section + * contents in memory + */ + rel = (void *)sechdrs[relsec].sh_offset; + + /* Section to which relocations apply */ + section = &sechdrs[sechdrs[relsec].sh_info]; + + pr_debug("Applying relocate section %u to %u\n", relsec, + sechdrs[relsec].sh_info); + + /* Associated symbol table */ + symtabsec = &sechdrs[sechdrs[relsec].sh_link]; + + /* String table */ + if (symtabsec->sh_link >= ehdr->e_shnum) { + /* Invalid strtab section number */ + pr_err("Invalid string table section index %d\n", + symtabsec->sh_link); + return -ENOEXEC; + } + + strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset; + + /* section header string table */ + shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset; + + for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + + /* + * rel[i].r_offset contains byte offset from beginning + * of section to the storage unit affected. + * + * This is location to update (->sh_offset). This is temporary + * buffer where section is currently loaded. This will finally + * be loaded to a different address later, pointed to by + * ->sh_addr. kexec takes care of moving it + * (kexec_load_segment()). + */ + location = (void *)(section->sh_offset + rel[i].r_offset); + + /* Final address of the location */ + address = section->sh_addr + rel[i].r_offset; + + /* + * rel[i].r_info contains information about symbol table index + * w.r.t which relocation must be made and type of relocation + * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get + * these respectively. + */ + sym = (Elf64_Sym *)symtabsec->sh_offset + + ELF64_R_SYM(rel[i].r_info); + + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + pr_debug("Symbol: %s info: %02x shndx: %02x value=%llx size: %llx\n", + name, sym->st_info, sym->st_shndx, sym->st_value, + sym->st_size); + + if (sym->st_shndx == SHN_UNDEF) { + pr_err("Undefined symbol: %s\n", name); + return -ENOEXEC; + } + + if (sym->st_shndx == SHN_COMMON) { + pr_err("symbol '%s' in common section\n", name); + return -ENOEXEC; + } + + if (sym->st_shndx == SHN_ABS) + sec_base = 0; + else if (sym->st_shndx >= ehdr->e_shnum) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); + return -ENOEXEC; + } else + sec_base = sechdrs[sym->st_shndx].sh_addr; + + value = sym->st_value; + value += sec_base; + value += rel[i].r_addend; + + switch (ELF64_R_TYPE(rel[i].r_info)) { + case R_X86_64_NONE: + break; + case R_X86_64_64: + *(u64 *)location = value; + break; + case R_X86_64_32: + *(u32 *)location = value; + if (value != *(u32 *)location) + goto overflow; + break; + case R_X86_64_32S: + *(s32 *)location = value; + if ((s64)value != *(s32 *)location) + goto overflow; + break; + case R_X86_64_PC32: + value -= (u64)address; + *(u32 *)location = value; + break; + default: + pr_err("Unknown rela relocation: %llu\n", + ELF64_R_TYPE(rel[i].r_info)); + return -ENOEXEC; + } + } + return 0; + +overflow: + pr_err("Overflow in relocation type %d value 0x%lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), value); + return -ENOEXEC; +} |