// SPDX-License-Identifier: GPL-2.0-only/* * crash.c - kernel crash support code. * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #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 <linux/delay.h>#include <linux/panic.h> #include <asm/page.h>#include <asm/sections.h> #include "kallsyms_internal.h"#include "kexec_internal.h" /* Per cpu memory for storing cpu states in case of system crash. */note_buf_t __percpu *crash_notes; /* time to wait for possible DMA to finish before starting the kdump kernel * when a CMA reservation is used */#define CMA_DMA_TIMEOUT_SEC 10 #ifdef CONFIG_CRASH_DUMP int kimage_crash_copy_vmcoreinfo(struct kimage *image){ struct page *vmcoreinfo_base; struct page *vmcoreinfo_pages[DIV_ROUND_UP(VMCOREINFO_BYTES, PAGE_SIZE)]; unsigned int order, nr_pages; int i; void *safecopy; nr_pages = DIV_ROUND_UP(VMCOREINFO_BYTES, PAGE_SIZE); order = get_order(VMCOREINFO_BYTES); if (!IS_ENABLED(CONFIG_CRASH_DUMP)) return 0; if (image->type != KEXEC_TYPE_CRASH) return 0; /* * 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_base = kimage_alloc_control_pages(image, order); if (!vmcoreinfo_base) { pr_warn("Could not allocate vmcoreinfo buffer\n"); return -ENOMEM; } for (i = 0; i < nr_pages; i++) vmcoreinfo_pages[i] = vmcoreinfo_base + i; safecopy = vmap(vmcoreinfo_pages, nr_pages, VM_MAP, PAGE_KERNEL); if (!safecopy) { pr_warn("Could not vmap vmcoreinfo buffer\n"); return -ENOMEM; } image->vmcoreinfo_data_copy = safecopy; crash_update_vmcoreinfo_safecopy(safecopy); return 0;} 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); static void crash_cma_clear_pending_dma(void){ if (!crashk_cma_cnt) return; mdelay(CMA_DMA_TIMEOUT_SEC * 1000);} /* * 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. */void __noclone __crash_kexec(struct pt_regs *regs){ /* 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); crash_cma_clear_pending_dma(); machine_kexec(kexec_crash_image); } kexec_unlock(); }}STACK_FRAME_NON_STANDARD(__crash_kexec); __bpf_kfunc void crash_kexec(struct pt_regs *regs){ if (panic_try_start()) { /* This is the 1st CPU which comes here, so go ahead. */ __crash_kexec(regs); /* * Reset panic_cpu to allow another panic()/crash_kexec() * call. */ panic_reset(); }} static inline resource_size_t crash_resource_size(const struct resource *res){ return !res->end ? 0 : resource_size(res);} int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, 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; 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. */ 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++; } /* 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++; } /* 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 struct crash_mem *alloc_cmem(unsigned int nr_ranges){ struct crash_mem *cmem; cmem = kvzalloc_flex(*cmem, ranges, nr_ranges); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; return cmem;} unsigned int __weak arch_get_system_nr_ranges(void) { return 0; }int __weak arch_crash_populate_cmem(struct crash_mem *cmem) { return -1; }int __weak arch_crash_exclude_ranges(struct crash_mem *cmem) { return 0; } int __weak arch_crash_exclude_mem_range(struct crash_mem **mem, unsigned long long mstart, unsigned long long mend){ return crash_exclude_mem_range(*mem, mstart, mend);} int crash_exclude_core_ranges(struct crash_mem **cmem){ int ret, i; /* Exclude crashkernel region */ ret = arch_crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) { ret = arch_crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); if (ret) return ret; } for (i = 0; i < crashk_cma_cnt; ++i) { ret = arch_crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, crashk_cma_ranges[i].end); if (ret) return ret; } return 0;} int crash_prepare_headers(int need_kernel_map, void **addr, unsigned long *sz, unsigned long *nr_mem_ranges){ unsigned int max_nr_ranges; struct crash_mem *cmem; int ret; max_nr_ranges = arch_get_system_nr_ranges(); if (!max_nr_ranges) return -ENOMEM; cmem = alloc_cmem(max_nr_ranges); if (!cmem) return -ENOMEM; ret = arch_crash_populate_cmem(cmem); if (ret) goto out; ret = crash_exclude_core_ranges(&cmem); if (ret) goto out; ret = arch_crash_exclude_ranges(cmem); if (ret) goto out; /* Return the computed number of memory ranges, for hotplug usage */ if (nr_mem_ranges) *nr_mem_ranges = cmem->nr_ranges; ret = crash_prepare_elf64_headers(cmem, need_kernel_map, addr, sz); out: kvfree(cmem); return ret;} /** * crash_exclude_mem_range - exclude a mem range for existing ranges * @mem: mem->range contains an array of ranges sorted in ascending order * @mstart: the start of to-be-excluded range * @mend: the start of to-be-excluded range * * If you are unsure if a range split will happen, to avoid function call * failure because of -ENOMEM, always make sure * mem->max_nr_ranges == mem->nr_ranges + 1 * before calling the function each time. * * returns 0 if a memory range is excluded successfully * return -ENOMEM if mem->ranges doesn't have space to hold split ranges */int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend){ 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; /* 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 0;}EXPORT_SYMBOL_GPL(crash_exclude_mem_range); ssize_t crash_get_memory_size(void){ ssize_t size = 0; if (!kexec_trylock()) return -EBUSY; size += crash_resource_size(&crashk_res); size += crash_resource_size(&crashk_low_res); kexec_unlock(); return size;} static int __crash_shrink_memory(struct resource *old_res, unsigned long new_size){ struct resource *ram_res; ram_res = kzalloc_obj(*ram_res); if (!ram_res) return -ENOMEM; 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 { old_res->end = ram_res->start - 1; } crash_free_reserved_phys_range(ram_res->start, ram_res->end); insert_resource(&iomem_resource, ram_res); return 0;} int crash_shrink_memory(unsigned long new_size){ int ret = 0; unsigned long old_size, low_size; if (!kexec_trylock()) return -EBUSY; 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 thatLines 1–500 of 783. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * crash.c - kernel crash support code. * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #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 <linux/delay.h> #include <linux/panic.h> #include <asm/page.h> #include <asm/sections.h> #include "kallsyms_internal.h" #include "kexec_internal.h" /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; /* time to wait for possible DMA to finish before starting the kdump kernel * when a CMA reservation is used */ #define CMA_DMA_TIMEOUT_SEC 10 #ifdef CONFIG_CRASH_DUMP int kimage_crash_copy_vmcoreinfo(struct kimage *image) { struct page *vmcoreinfo_base; struct page *vmcoreinfo_pages[DIV_ROUND_UP(VMCOREINFO_BYTES, PAGE_SIZE)]; unsigned int order, nr_pages; int i; void *safecopy; nr_pages = DIV_ROUND_UP(VMCOREINFO_BYTES, PAGE_SIZE); order = get_order(VMCOREINFO_BYTES); if (!IS_ENABLED(CONFIG_CRASH_DUMP)) return 0; if (image->type != KEXEC_TYPE_CRASH) return 0; /* * 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_base = kimage_alloc_control_pages(image, order); if (!vmcoreinfo_base) { pr_warn("Could not allocate vmcoreinfo buffer\n"); return -ENOMEM; } for (i = 0; i < nr_pages; i++) vmcoreinfo_pages[i] = vmcoreinfo_base + i; safecopy = vmap(vmcoreinfo_pages, nr_pages, VM_MAP, PAGE_KERNEL); if (!safecopy) { pr_warn("Could not vmap vmcoreinfo buffer\n"); return -ENOMEM; } image->vmcoreinfo_data_copy = safecopy; crash_update_vmcoreinfo_safecopy(safecopy); return 0; } 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); static void crash_cma_clear_pending_dma(void) { if (!crashk_cma_cnt) return; mdelay(CMA_DMA_TIMEOUT_SEC * 1000); } /* * 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. */ void __noclone __crash_kexec(struct pt_regs *regs) { /* 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); crash_cma_clear_pending_dma(); machine_kexec(kexec_crash_image); } kexec_unlock(); } } STACK_FRAME_NON_STANDARD(__crash_kexec); __bpf_kfunc void crash_kexec(struct pt_regs *regs) { if (panic_try_start()) { /* This is the 1st CPU which comes here, so go ahead. */ __crash_kexec(regs); /* * Reset panic_cpu to allow another panic()/crash_kexec() * call. */ panic_reset(); } } static inline resource_size_t crash_resource_size(const struct resource *res) { return !res->end ? 0 : resource_size(res); } int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, 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; 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. */ 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++; } /* 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++; } /* 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 struct crash_mem *alloc_cmem(unsigned int nr_ranges) { struct crash_mem *cmem; cmem = kvzalloc_flex(*cmem, ranges, nr_ranges); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; return cmem; } unsigned int __weak arch_get_system_nr_ranges(void) { return 0; } int __weak arch_crash_populate_cmem(struct crash_mem *cmem) { return -1; } int __weak arch_crash_exclude_ranges(struct crash_mem *cmem) { return 0; } int __weak arch_crash_exclude_mem_range(struct crash_mem **mem, unsigned long long mstart, unsigned long long mend) { return crash_exclude_mem_range(*mem, mstart, mend); } int crash_exclude_core_ranges(struct crash_mem **cmem) { int ret, i; /* Exclude crashkernel region */ ret = arch_crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) { ret = arch_crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); if (ret) return ret; } for (i = 0; i < crashk_cma_cnt; ++i) { ret = arch_crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, crashk_cma_ranges[i].end); if (ret) return ret; } return 0; } int crash_prepare_headers(int need_kernel_map, void **addr, unsigned long *sz, unsigned long *nr_mem_ranges) { unsigned int max_nr_ranges; struct crash_mem *cmem; int ret; max_nr_ranges = arch_get_system_nr_ranges(); if (!max_nr_ranges) return -ENOMEM; cmem = alloc_cmem(max_nr_ranges); if (!cmem) return -ENOMEM; ret = arch_crash_populate_cmem(cmem); if (ret) goto out; ret = crash_exclude_core_ranges(&cmem); if (ret) goto out; ret = arch_crash_exclude_ranges(cmem); if (ret) goto out; /* Return the computed number of memory ranges, for hotplug usage */ if (nr_mem_ranges) *nr_mem_ranges = cmem->nr_ranges; ret = crash_prepare_elf64_headers(cmem, need_kernel_map, addr, sz); out: kvfree(cmem); return ret; } /** * crash_exclude_mem_range - exclude a mem range for existing ranges * @mem: mem->range contains an array of ranges sorted in ascending order * @mstart: the start of to-be-excluded range * @mend: the start of to-be-excluded range * * If you are unsure if a range split will happen, to avoid function call * failure because of -ENOMEM, always make sure * mem->max_nr_ranges == mem->nr_ranges + 1 * before calling the function each time. * * returns 0 if a memory range is excluded successfully * return -ENOMEM if mem->ranges doesn't have space to hold split ranges */ int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend) { 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; /* 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 0; } EXPORT_SYMBOL_GPL(crash_exclude_mem_range); ssize_t crash_get_memory_size(void) { ssize_t size = 0; if (!kexec_trylock()) return -EBUSY; size += crash_resource_size(&crashk_res); size += crash_resource_size(&crashk_low_res); kexec_unlock(); return size; } static int __crash_shrink_memory(struct resource *old_res, unsigned long new_size) { struct resource *ram_res; ram_res = kzalloc_obj(*ram_res); if (!ram_res) return -ENOMEM; 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 { old_res->end = ram_res->start - 1; } crash_free_reserved_phys_range(ram_res->start, ram_res->end); insert_resource(&iomem_resource, ram_res); return 0; } int crash_shrink_memory(unsigned long new_size) { int ret = 0; unsigned long old_size, low_size; if (!kexec_trylock()) return -EBUSY; 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