diff options
Diffstat (limited to 'kernel/crash_core.c')
| -rw-r--r-- | kernel/crash_core.c | 983 |
1 files changed, 564 insertions, 419 deletions
diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 825284baaf46..078fe5bc5a74 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -4,524 +4,669 @@ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ -#include <linux/crash_core.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/buildid.h> +#include <linux/init.h> #include <linux/utsname.h> #include <linux/vmalloc.h> +#include <linux/sizes.h> +#include <linux/kexec.h> +#include <linux/memory.h> +#include <linux/mm.h> +#include <linux/cpuhotplug.h> +#include <linux/memblock.h> +#include <linux/kmemleak.h> +#include <linux/crash_core.h> +#include <linux/reboot.h> +#include <linux/btf.h> +#include <linux/objtool.h> #include <asm/page.h> #include <asm/sections.h> #include <crypto/sha1.h> -/* vmcoreinfo stuff */ -unsigned char *vmcoreinfo_data; -size_t vmcoreinfo_size; -u32 *vmcoreinfo_note; +#include "kallsyms_internal.h" +#include "kexec_internal.h" -/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ -static unsigned char *vmcoreinfo_data_safecopy; +/* Per cpu memory for storing cpu states in case of system crash. */ +note_buf_t __percpu *crash_notes; -/* - * parsing the "crashkernel" commandline - * - * this code is intended to be called from architecture specific code - */ +#ifdef CONFIG_CRASH_DUMP - -/* - * This function parses command lines in the format - * - * crashkernel=ramsize-range:size[,...][@offset] - * - * The function returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_mem(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) +int kimage_crash_copy_vmcoreinfo(struct kimage *image) { - char *cur = cmdline, *tmp; + struct page *vmcoreinfo_page; + void *safecopy; - /* for each entry of the comma-separated list */ - do { - unsigned long long start, end = ULLONG_MAX, size; + if (!IS_ENABLED(CONFIG_CRASH_DUMP)) + return 0; + if (image->type != KEXEC_TYPE_CRASH) + return 0; - /* get the start of the range */ - start = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (*cur != '-') { - pr_warn("crashkernel: '-' expected\n"); - return -EINVAL; - } - cur++; - - /* if no ':' is here, than we read the end */ - if (*cur != ':') { - end = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (end <= start) { - pr_warn("crashkernel: end <= start\n"); - return -EINVAL; - } - } + /* + * For kdump, allocate one vmcoreinfo safe copy from the + * crash memory. as we have arch_kexec_protect_crashkres() + * after kexec syscall, we naturally protect it from write + * (even read) access under kernel direct mapping. But on + * the other hand, we still need to operate it when crash + * happens to generate vmcoreinfo note, hereby we rely on + * vmap for this purpose. + */ + vmcoreinfo_page = kimage_alloc_control_pages(image, 0); + if (!vmcoreinfo_page) { + pr_warn("Could not allocate vmcoreinfo buffer\n"); + return -ENOMEM; + } + safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); + if (!safecopy) { + pr_warn("Could not vmap vmcoreinfo buffer\n"); + return -ENOMEM; + } - if (*cur != ':') { - pr_warn("crashkernel: ':' expected\n"); - return -EINVAL; - } - cur++; + image->vmcoreinfo_data_copy = safecopy; + crash_update_vmcoreinfo_safecopy(safecopy); + + return 0; +} - size = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (size >= system_ram) { - pr_warn("crashkernel: invalid size\n"); - return -EINVAL; - } - /* match ? */ - if (system_ram >= start && system_ram < end) { - *crash_size = size; - break; - } - } while (*cur++ == ','); - - if (*crash_size > 0) { - while (*cur && *cur != ' ' && *cur != '@') - cur++; - if (*cur == '@') { - cur++; - *crash_base = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); - return -EINVAL; - } - } - } else - pr_info("crashkernel size resulted in zero bytes\n"); +int kexec_should_crash(struct task_struct *p) +{ + /* + * If crash_kexec_post_notifiers is enabled, don't run + * crash_kexec() here yet, which must be run after panic + * notifiers in panic(). + */ + if (crash_kexec_post_notifiers) + return 0; + /* + * There are 4 panic() calls in make_task_dead() path, each of which + * corresponds to each of these 4 conditions. + */ + if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) + return 1; return 0; } +int kexec_crash_loaded(void) +{ + return !!kexec_crash_image; +} +EXPORT_SYMBOL_GPL(kexec_crash_loaded); + /* - * That function parses "simple" (old) crashkernel command lines like - * - * crashkernel=size[@offset] - * - * It returns 0 on success and -EINVAL on failure. + * No panic_cpu check version of crash_kexec(). This function is called + * only when panic_cpu holds the current CPU number; this is the only CPU + * which processes crash_kexec routines. */ -static int __init parse_crashkernel_simple(char *cmdline, - unsigned long long *crash_size, - unsigned long long *crash_base) +void __noclone __crash_kexec(struct pt_regs *regs) { - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; + /* Take the kexec_lock here to prevent sys_kexec_load + * running on one cpu from replacing the crash kernel + * we are using after a panic on a different cpu. + * + * If the crash kernel was not located in a fixed area + * of memory the xchg(&kexec_crash_image) would be + * sufficient. But since I reuse the memory... + */ + if (kexec_trylock()) { + if (kexec_crash_image) { + struct pt_regs fixed_regs; + + crash_setup_regs(&fixed_regs, regs); + crash_save_vmcoreinfo(); + machine_crash_shutdown(&fixed_regs); + machine_kexec(kexec_crash_image); + } + kexec_unlock(); } +} +STACK_FRAME_NON_STANDARD(__crash_kexec); + +__bpf_kfunc void crash_kexec(struct pt_regs *regs) +{ + int old_cpu, this_cpu; - if (*cur == '@') - *crash_base = memparse(cur+1, &cur); - else if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; + /* + * Only one CPU is allowed to execute the crash_kexec() code as with + * panic(). Otherwise parallel calls of panic() and crash_kexec() + * may stop each other. To exclude them, we use panic_cpu here too. + */ + old_cpu = PANIC_CPU_INVALID; + this_cpu = raw_smp_processor_id(); + + if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { + /* This is the 1st CPU which comes here, so go ahead. */ + __crash_kexec(regs); + + /* + * Reset panic_cpu to allow another panic()/crash_kexec() + * call. + */ + atomic_set(&panic_cpu, PANIC_CPU_INVALID); } +} - return 0; +static inline resource_size_t crash_resource_size(const struct resource *res) +{ + return !res->end ? 0 : resource_size(res); } -#define SUFFIX_HIGH 0 -#define SUFFIX_LOW 1 -#define SUFFIX_NULL 2 -static __initdata char *suffix_tbl[] = { - [SUFFIX_HIGH] = ",high", - [SUFFIX_LOW] = ",low", - [SUFFIX_NULL] = NULL, -}; -/* - * That function parses "suffix" crashkernel command lines like - * - * crashkernel=size,[high|low] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, - const char *suffix) + + +int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, + void **addr, unsigned long *sz) { - char *cur = cmdline; + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz; + unsigned char *buf; + unsigned int cpu, i; + unsigned long long notes_addr; + unsigned long mstart, mend; + + /* extra phdr for vmcoreinfo ELF note */ + nr_phdr = nr_cpus + 1; + nr_phdr += mem->nr_ranges; + + /* + * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping + * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64). + * 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. + */ - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; + 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; + + ehdr = (Elf64_Ehdr *)buf; + phdr = (Elf64_Phdr *)(ehdr + 1); + 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 possible CPU */ + for_each_possible_cpu(cpu) { + 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)++; + phdr++; } - /* check with suffix */ - if (strncmp(cur, suffix, strlen(suffix))) { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; + /* Prepare one PT_NOTE header for vmcoreinfo */ + phdr->p_type = PT_NOTE; + phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); + phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; + (ehdr->e_phnum)++; + phdr++; + + /* Prepare PT_LOAD type program header for kernel text region */ + if (need_kernel_map) { + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_vaddr = (unsigned long) _text; + phdr->p_filesz = phdr->p_memsz = _end - _text; + phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); + ehdr->e_phnum++; + phdr++; } - cur += strlen(suffix); - if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; + + /* Go through all the ranges in mem->ranges[] and prepare phdr */ + for (i = 0; i < mem->nr_ranges; i++) { + mstart = mem->ranges[i].start; + mend = mem->ranges[i].end; + + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_offset = mstart; + + phdr->p_paddr = mstart; + phdr->p_vaddr = (unsigned long) __va(mstart); + phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; + phdr->p_align = 0; + ehdr->e_phnum++; +#ifdef CONFIG_KEXEC_FILE + kexec_dprintk("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); +#endif + phdr++; } + *addr = buf; + *sz = elf_sz; return 0; } -static __init char *get_last_crashkernel(char *cmdline, - const char *name, - const char *suffix) +int crash_exclude_mem_range(struct crash_mem *mem, + unsigned long long mstart, unsigned long long mend) { - char *p = cmdline, *ck_cmdline = NULL; - - /* find crashkernel and use the last one if there are more */ - p = strstr(p, name); - while (p) { - char *end_p = strchr(p, ' '); - char *q; - - if (!end_p) - end_p = p + strlen(p); - - if (!suffix) { - int i; - - /* skip the one with any known suffix */ - for (i = 0; suffix_tbl[i]; i++) { - q = end_p - strlen(suffix_tbl[i]); - if (!strncmp(q, suffix_tbl[i], - strlen(suffix_tbl[i]))) - goto next; - } - ck_cmdline = p; - } else { - q = end_p - strlen(suffix); - if (!strncmp(q, suffix, strlen(suffix))) - ck_cmdline = p; - } -next: - p = strstr(p+1, name); - } + int i; + unsigned long long start, end, p_start, p_end; + + for (i = 0; i < mem->nr_ranges; i++) { + start = mem->ranges[i].start; + end = mem->ranges[i].end; + p_start = mstart; + p_end = mend; + + if (p_start > end) + continue; + + /* + * Because the memory ranges in mem->ranges are stored in + * ascending order, when we detect `p_end < start`, we can + * immediately exit the for loop, as the subsequent memory + * ranges will definitely be outside the range we are looking + * for. + */ + if (p_end < start) + break; - if (!ck_cmdline) - return NULL; + /* Truncate any area outside of range */ + if (p_start < start) + p_start = start; + if (p_end > end) + p_end = end; + + /* Found completely overlapping range */ + if (p_start == start && p_end == end) { + memmove(&mem->ranges[i], &mem->ranges[i + 1], + (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i])); + i--; + mem->nr_ranges--; + } else if (p_start > start && p_end < end) { + /* Split original range */ + if (mem->nr_ranges >= mem->max_nr_ranges) + return -ENOMEM; + + memmove(&mem->ranges[i + 2], &mem->ranges[i + 1], + (mem->nr_ranges - (i + 1)) * sizeof(mem->ranges[i])); + + mem->ranges[i].end = p_start - 1; + mem->ranges[i + 1].start = p_end + 1; + mem->ranges[i + 1].end = end; + + i++; + mem->nr_ranges++; + } else if (p_start != start) + mem->ranges[i].end = p_start - 1; + else + mem->ranges[i].start = p_end + 1; + } - return ck_cmdline; + return 0; } -static int __init __parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - const char *name, - const char *suffix) +ssize_t crash_get_memory_size(void) { - char *first_colon, *first_space; - char *ck_cmdline; + ssize_t size = 0; - BUG_ON(!crash_size || !crash_base); - *crash_size = 0; - *crash_base = 0; + if (!kexec_trylock()) + return -EBUSY; - ck_cmdline = get_last_crashkernel(cmdline, name, suffix); + size += crash_resource_size(&crashk_res); + size += crash_resource_size(&crashk_low_res); - if (!ck_cmdline) - return -EINVAL; + kexec_unlock(); + return size; +} - ck_cmdline += strlen(name); +static int __crash_shrink_memory(struct resource *old_res, + unsigned long new_size) +{ + struct resource *ram_res; - if (suffix) - return parse_crashkernel_suffix(ck_cmdline, crash_size, - suffix); - /* - * if the commandline contains a ':', then that's the extended - * syntax -- if not, it must be the classic syntax - */ - first_colon = strchr(ck_cmdline, ':'); - first_space = strchr(ck_cmdline, ' '); - if (first_colon && (!first_space || first_colon < first_space)) - return parse_crashkernel_mem(ck_cmdline, system_ram, - crash_size, crash_base); + ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); + if (!ram_res) + return -ENOMEM; - return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); -} + ram_res->start = old_res->start + new_size; + ram_res->end = old_res->end; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; + ram_res->name = "System RAM"; + + if (!new_size) { + release_resource(old_res); + old_res->start = 0; + old_res->end = 0; + } else { + crashk_res.end = ram_res->start - 1; + } -/* - * That function is the entry point for command line parsing and should be - * called from the arch-specific code. - */ -int __init parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", NULL); -} + crash_free_reserved_phys_range(ram_res->start, ram_res->end); + insert_resource(&iomem_resource, ram_res); -int __init parse_crashkernel_high(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", suffix_tbl[SUFFIX_HIGH]); + return 0; } -int __init parse_crashkernel_low(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) +int crash_shrink_memory(unsigned long new_size) { - return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel=", suffix_tbl[SUFFIX_LOW]); -} + int ret = 0; + unsigned long old_size, low_size; -Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, - void *data, size_t data_len) -{ - struct elf_note *note = (struct elf_note *)buf; - - note->n_namesz = strlen(name) + 1; - note->n_descsz = data_len; - note->n_type = type; - buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); - memcpy(buf, name, note->n_namesz); - buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); - memcpy(buf, data, data_len); - buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); - - return buf; -} + if (!kexec_trylock()) + return -EBUSY; -void final_note(Elf_Word *buf) -{ - memset(buf, 0, sizeof(struct elf_note)); + if (kexec_crash_image) { + ret = -ENOENT; + goto unlock; + } + + low_size = crash_resource_size(&crashk_low_res); + old_size = crash_resource_size(&crashk_res) + low_size; + new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); + if (new_size >= old_size) { + ret = (new_size == old_size) ? 0 : -EINVAL; + goto unlock; + } + + /* + * (low_size > new_size) implies that low_size is greater than zero. + * This also means that if low_size is zero, the else branch is taken. + * + * If low_size is greater than 0, (low_size > new_size) indicates that + * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res + * needs to be shrunken. + */ + if (low_size > new_size) { + ret = __crash_shrink_memory(&crashk_res, 0); + if (ret) + goto unlock; + + ret = __crash_shrink_memory(&crashk_low_res, new_size); + } else { + ret = __crash_shrink_memory(&crashk_res, new_size - low_size); + } + + /* Swap crashk_res and crashk_low_res if needed */ + if (!crashk_res.end && crashk_low_res.end) { + crashk_res.start = crashk_low_res.start; + crashk_res.end = crashk_low_res.end; + release_resource(&crashk_low_res); + crashk_low_res.start = 0; + crashk_low_res.end = 0; + insert_resource(&iomem_resource, &crashk_res); + } + +unlock: + kexec_unlock(); + return ret; } -static void update_vmcoreinfo_note(void) +void crash_save_cpu(struct pt_regs *regs, int cpu) { - u32 *buf = vmcoreinfo_note; + struct elf_prstatus prstatus; + u32 *buf; - if (!vmcoreinfo_size) + if ((cpu < 0) || (cpu >= nr_cpu_ids)) return; - buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - vmcoreinfo_size); + + /* Using ELF notes here is opportunistic. + * I need a well defined structure format + * for the data I pass, and I need tags + * on the data to indicate what information I have + * squirrelled away. ELF notes happen to provide + * all of that, so there is no need to invent something new. + */ + buf = (u32 *)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); + prstatus.common.pr_pid = current->pid; + elf_core_copy_regs(&prstatus.pr_reg, regs); + buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); final_note(buf); } -void crash_update_vmcoreinfo_safecopy(void *ptr) -{ - if (ptr) - memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); - vmcoreinfo_data_safecopy = ptr; -} -void crash_save_vmcoreinfo(void) +static int __init crash_notes_memory_init(void) { - if (!vmcoreinfo_note) - return; + /* Allocate memory for saving cpu registers. */ + size_t size, align; - /* Use the safe copy to generate vmcoreinfo note if have */ - if (vmcoreinfo_data_safecopy) - vmcoreinfo_data = vmcoreinfo_data_safecopy; + /* + * crash_notes could be allocated across 2 vmalloc pages when percpu + * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc + * pages are also on 2 continuous physical pages. In this case the + * 2nd part of crash_notes in 2nd page could be lost since only the + * starting address and size of crash_notes are exported through sysfs. + * Here round up the size of crash_notes to the nearest power of two + * and pass it to __alloc_percpu as align value. This can make sure + * crash_notes is allocated inside one physical page. + */ + size = sizeof(note_buf_t); + align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE); - vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds()); - update_vmcoreinfo_note(); + /* + * Break compile if size is bigger than PAGE_SIZE since crash_notes + * definitely will be in 2 pages with that. + */ + BUILD_BUG_ON(size > PAGE_SIZE); + + crash_notes = __alloc_percpu(size, align); + if (!crash_notes) { + pr_warn("Memory allocation for saving cpu register states failed\n"); + return -ENOMEM; + } + return 0; } +subsys_initcall(crash_notes_memory_init); -void vmcoreinfo_append_str(const char *fmt, ...) -{ - va_list args; - char buf[0x50]; - size_t r; +#endif /*CONFIG_CRASH_DUMP*/ - va_start(args, fmt); - r = vscnprintf(buf, sizeof(buf), fmt, args); - va_end(args); +#ifdef CONFIG_CRASH_HOTPLUG +#undef pr_fmt +#define pr_fmt(fmt) "crash hp: " fmt - r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); +/* + * Different than kexec/kdump loading/unloading/jumping/shrinking which + * usually rarely happen, there will be many crash hotplug events notified + * during one short period, e.g one memory board is hot added and memory + * regions are online. So mutex lock __crash_hotplug_lock is used to + * serialize the crash hotplug handling specifically. + */ +static DEFINE_MUTEX(__crash_hotplug_lock); +#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock) +#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock) - memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); +/* + * This routine utilized when the crash_hotplug sysfs node is read. + * It reflects the kernel's ability/permission to update the kdump + * image directly. + */ +int crash_check_hotplug_support(void) +{ + int rc = 0; + + crash_hotplug_lock(); + /* Obtain lock while reading crash information */ + if (!kexec_trylock()) { + if (!kexec_in_progress) + pr_info("kexec_trylock() failed, kdump image may be inaccurate\n"); + crash_hotplug_unlock(); + return 0; + } + if (kexec_crash_image) { + rc = kexec_crash_image->hotplug_support; + } + /* Release lock now that update complete */ + kexec_unlock(); + crash_hotplug_unlock(); - vmcoreinfo_size += r; + return rc; } /* - * provide an empty default implementation here -- architecture - * code may override this + * To accurately reflect hot un/plug changes of CPU and Memory resources + * (including onling and offlining of those resources), the relevant + * kexec segments must be updated with latest CPU and Memory resources. + * + * Architectures must ensure two things for all segments that need + * updating during hotplug events: + * + * 1. Segments must be large enough to accommodate a growing number of + * resources. + * 2. Exclude the segments from SHA verification. + * + * For example, on most architectures, the elfcorehdr (which is passed + * to the crash kernel via the elfcorehdr= parameter) must include the + * new list of CPUs and memory. To make changes to the elfcorehdr, it + * should be large enough to permit a growing number of CPU and Memory + * resources. One can estimate the elfcorehdr memory size based on + * NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES. The elfcorehdr is + * excluded from SHA verification by default if the architecture + * supports crash hotplug. */ -void __weak arch_crash_save_vmcoreinfo(void) -{} - -phys_addr_t __weak paddr_vmcoreinfo_note(void) +static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg) { - return __pa(vmcoreinfo_note); -} -EXPORT_SYMBOL(paddr_vmcoreinfo_note); + struct kimage *image; + + crash_hotplug_lock(); + /* Obtain lock while changing crash information */ + if (!kexec_trylock()) { + if (!kexec_in_progress) + pr_info("kexec_trylock() failed, kdump image may be inaccurate\n"); + crash_hotplug_unlock(); + return; + } -#define NOTES_SIZE (&__stop_notes - &__start_notes) -#define BUILD_ID_MAX SHA1_DIGEST_SIZE -#define NT_GNU_BUILD_ID 3 + /* Check kdump is not loaded */ + if (!kexec_crash_image) + goto out; -struct elf_note_section { - struct elf_note n_hdr; - u8 n_data[]; -}; + image = kexec_crash_image; -/* - * Add build ID from .notes section as generated by the GNU ld(1) - * or LLVM lld(1) --build-id option. - */ -static void add_build_id_vmcoreinfo(void) -{ - char build_id[BUILD_ID_MAX * 2 + 1]; - int n_remain = NOTES_SIZE; - - while (n_remain >= sizeof(struct elf_note)) { - const struct elf_note_section *note_sec = - &__start_notes + NOTES_SIZE - n_remain; - const u32 n_namesz = note_sec->n_hdr.n_namesz; - - if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID && - n_namesz != 0 && - !strcmp((char *)¬e_sec->n_data[0], "GNU")) { - if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) { - const u32 n_descsz = note_sec->n_hdr.n_descsz; - const u8 *s = ¬e_sec->n_data[n_namesz]; - - s = PTR_ALIGN(s, 4); - bin2hex(build_id, s, n_descsz); - build_id[2 * n_descsz] = '\0'; - VMCOREINFO_BUILD_ID(build_id); - return; + /* Check that kexec segments update is permitted */ + if (!image->hotplug_support) + goto out; + + if (hp_action == KEXEC_CRASH_HP_ADD_CPU || + hp_action == KEXEC_CRASH_HP_REMOVE_CPU) + pr_debug("hp_action %u, cpu %u\n", hp_action, cpu); + else + pr_debug("hp_action %u\n", hp_action); + + /* + * The elfcorehdr_index is set to -1 when the struct kimage + * is allocated. Find the segment containing the elfcorehdr, + * if not already found. + */ + if (image->elfcorehdr_index < 0) { + unsigned long mem; + unsigned char *ptr; + unsigned int n; + + for (n = 0; n < image->nr_segments; n++) { + mem = image->segment[n].mem; + ptr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT)); + if (ptr) { + /* The segment containing elfcorehdr */ + if (memcmp(ptr, ELFMAG, SELFMAG) == 0) + image->elfcorehdr_index = (int)n; + kunmap_local(ptr); } - pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n", - note_sec->n_hdr.n_descsz, - BUILD_ID_MAX); - return; } - n_remain -= sizeof(struct elf_note) + - ALIGN(note_sec->n_hdr.n_namesz, 4) + - ALIGN(note_sec->n_hdr.n_descsz, 4); } + + if (image->elfcorehdr_index < 0) { + pr_err("unable to locate elfcorehdr segment"); + goto out; + } + + /* Needed in order for the segments to be updated */ + arch_kexec_unprotect_crashkres(); + + /* Differentiate between normal load and hotplug update */ + image->hp_action = hp_action; + + /* Now invoke arch-specific update handler */ + arch_crash_handle_hotplug_event(image, arg); + + /* No longer handling a hotplug event */ + image->hp_action = KEXEC_CRASH_HP_NONE; + image->elfcorehdr_updated = true; + + /* Change back to read-only */ + arch_kexec_protect_crashkres(); + + /* Errors in the callback is not a reason to rollback state */ +out: + /* Release lock now that update complete */ + kexec_unlock(); + crash_hotplug_unlock(); } -static int __init crash_save_vmcoreinfo_init(void) +static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *arg) { - vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); - if (!vmcoreinfo_data) { - pr_warn("Memory allocation for vmcoreinfo_data failed\n"); - return -ENOMEM; + switch (val) { + case MEM_ONLINE: + crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY, + KEXEC_CRASH_HP_INVALID_CPU, arg); + break; + + case MEM_OFFLINE: + crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY, + KEXEC_CRASH_HP_INVALID_CPU, arg); + break; } + return NOTIFY_OK; +} - vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, - GFP_KERNEL | __GFP_ZERO); - if (!vmcoreinfo_note) { - free_page((unsigned long)vmcoreinfo_data); - vmcoreinfo_data = NULL; - pr_warn("Memory allocation for vmcoreinfo_note failed\n"); - return -ENOMEM; - } +static struct notifier_block crash_memhp_nb = { + .notifier_call = crash_memhp_notifier, + .priority = 0 +}; - VMCOREINFO_OSRELEASE(init_uts_ns.name.release); - add_build_id_vmcoreinfo(); - VMCOREINFO_PAGESIZE(PAGE_SIZE); +static int crash_cpuhp_online(unsigned int cpu) +{ + crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu, NULL); + return 0; +} - VMCOREINFO_SYMBOL(init_uts_ns); - VMCOREINFO_OFFSET(uts_namespace, name); - VMCOREINFO_SYMBOL(node_online_map); -#ifdef CONFIG_MMU - VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); -#endif - VMCOREINFO_SYMBOL(_stext); - VMCOREINFO_SYMBOL(vmap_area_list); +static int crash_cpuhp_offline(unsigned int cpu) +{ + crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu, NULL); + return 0; +} -#ifndef CONFIG_NEED_MULTIPLE_NODES - VMCOREINFO_SYMBOL(mem_map); - VMCOREINFO_SYMBOL(contig_page_data); -#endif -#ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL_ARRAY(mem_section); - VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); - VMCOREINFO_STRUCT_SIZE(mem_section); - VMCOREINFO_OFFSET(mem_section, section_mem_map); - VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); -#endif - VMCOREINFO_STRUCT_SIZE(page); - VMCOREINFO_STRUCT_SIZE(pglist_data); - VMCOREINFO_STRUCT_SIZE(zone); - VMCOREINFO_STRUCT_SIZE(free_area); - VMCOREINFO_STRUCT_SIZE(list_head); - VMCOREINFO_SIZE(nodemask_t); - VMCOREINFO_OFFSET(page, flags); - VMCOREINFO_OFFSET(page, _refcount); - VMCOREINFO_OFFSET(page, mapping); - VMCOREINFO_OFFSET(page, lru); - VMCOREINFO_OFFSET(page, _mapcount); - VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_dtor); - VMCOREINFO_OFFSET(page, compound_order); - VMCOREINFO_OFFSET(page, compound_head); - VMCOREINFO_OFFSET(pglist_data, node_zones); - VMCOREINFO_OFFSET(pglist_data, nr_zones); -#ifdef CONFIG_FLAT_NODE_MEM_MAP - VMCOREINFO_OFFSET(pglist_data, node_mem_map); -#endif - VMCOREINFO_OFFSET(pglist_data, node_start_pfn); - VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); - VMCOREINFO_OFFSET(pglist_data, node_id); - VMCOREINFO_OFFSET(zone, free_area); - VMCOREINFO_OFFSET(zone, vm_stat); - VMCOREINFO_OFFSET(zone, spanned_pages); - VMCOREINFO_OFFSET(free_area, free_list); - VMCOREINFO_OFFSET(list_head, next); - VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_OFFSET(vmap_area, va_start); - VMCOREINFO_OFFSET(vmap_area, list); - VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); - log_buf_vmcoreinfo_setup(); - VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); - VMCOREINFO_NUMBER(NR_FREE_PAGES); - VMCOREINFO_NUMBER(PG_lru); - VMCOREINFO_NUMBER(PG_private); - VMCOREINFO_NUMBER(PG_swapcache); - VMCOREINFO_NUMBER(PG_swapbacked); - VMCOREINFO_NUMBER(PG_slab); -#ifdef CONFIG_MEMORY_FAILURE - VMCOREINFO_NUMBER(PG_hwpoison); -#endif - VMCOREINFO_NUMBER(PG_head_mask); -#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) - VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); -#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) - VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif +static int __init crash_hotplug_init(void) +{ + int result = 0; - arch_crash_save_vmcoreinfo(); - update_vmcoreinfo_note(); + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + register_memory_notifier(&crash_memhp_nb); - return 0; + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + result = cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN, + "crash/cpuhp", crash_cpuhp_online, crash_cpuhp_offline); + } + + return result; } -subsys_initcall(crash_save_vmcoreinfo_init); +subsys_initcall(crash_hotplug_init); +#endif |