[PATCH v4 0/3] arm64/riscv: Add support for crashkernel CMA reservation
Add support for crashkernel CMA reservation for arm64 and riscv. By the way, exclude crash kernel memory in crash core to avoid duplication. Changes in v4: - Move the size calculation (and the realloc if needed) into the generic crash. Changs in v3: - Exclude crash kernel memory in crash core as Mike suggested. - Add acked-by. Jinjie Ruan (3): crash: Exclude crash kernel memory in crash core arm64: kexec: Add support for crashkernel CMA reservation riscv: kexec: Add support for crashkernel CMA reservation .../admin-guide/kernel-parameters.txt | 16 ++-- arch/arm64/include/asm/kexec.h | 9 ++ arch/arm64/kernel/machine_kexec_file.c | 43 ++++----- arch/arm64/mm/init.c | 5 +- arch/loongarch/include/asm/kexec.h | 9 +- arch/loongarch/kernel/machine_kexec_file.c | 41 +++----- arch/powerpc/include/asm/kexec.h | 13 +++ arch/powerpc/kexec/crash.c | 48 ++++++---- arch/powerpc/kexec/file_load_64.c | 17 ++-- arch/powerpc/kexec/ranges.c | 18 +--- arch/riscv/include/asm/kexec.h | 8 ++ arch/riscv/kernel/machine_kexec_file.c | 39 ++++---- arch/riscv/mm/init.c | 5 +- arch/x86/include/asm/kexec.h | 7 ++ arch/x86/kernel/crash.c | 95 ++----------------- include/linux/crash_core.h | 89 ++++++++++++++++- kernel/crash_core.c | 71 ++++++++++++-- 17 files changed, 307 insertions(+), 226 deletions(-) -- 2.34.1
The exclude of crashk_res, crashk_low_res and crashk_cma memory are almost identical across different architectures, so handling them in the crash core would eliminate a lot of duplication, so do them in the common code. And move the size calculation (and the realloc if needed) into the generic crash core so that: - New CMA regions or future crash-memory types are automatically accounted for; - Each architecture no longer has to play whack-a-mole with its private array size. This patch is tested ok on arm64 and riscv with QEMU. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> --- arch/arm64/include/asm/kexec.h | 9 ++ arch/arm64/kernel/machine_kexec_file.c | 41 ++++------ arch/loongarch/include/asm/kexec.h | 9 +- arch/loongarch/kernel/machine_kexec_file.c | 41 ++++------ arch/powerpc/include/asm/kexec.h | 13 +++ arch/powerpc/kexec/crash.c | 48 ++++++----- arch/powerpc/kexec/file_load_64.c | 17 ++-- arch/powerpc/kexec/ranges.c | 18 +--- arch/riscv/include/asm/kexec.h | 8 ++ arch/riscv/kernel/machine_kexec_file.c | 37 +++------ arch/x86/include/asm/kexec.h | 7 ++ arch/x86/kernel/crash.c | 95 +++------------------- include/linux/crash_core.h | 89 ++++++++++++++++++-- kernel/crash_core.c | 71 ++++++++++++++-- 14 files changed, 282 insertions(+), 221 deletions(-) diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 892e5bebda95..a6c58dd1cf6e 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -93,6 +93,7 @@ static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +struct crash_mem; struct kimage; #if defined(CONFIG_KEXEC_CORE) @@ -130,6 +131,14 @@ extern int load_other_segments(struct kimage *image, char *cmdline); #endif +#ifdef CONFIG_CRASH_DUMP +int arch_get_system_nr_ranges(unsigned int *nr_ranges); +#define arch_get_system_nr_ranges arch_get_system_nr_ranges + +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem); +#define arch_prepare_elf64_ram_headers arch_prepare_elf64_ram_headers +#endif + #endif /* __ASSEMBLER__ */ #endif diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 410060ebd86d..377980c282be 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -40,23 +40,22 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) } #ifdef CONFIG_CRASH_DUMP -static int prepare_elf_headers(void **addr, unsigned long *sz) +int arch_get_system_nr_ranges(unsigned int *nr_ranges) { - struct crash_mem *cmem; - unsigned int nr_ranges; - int ret; - u64 i; phys_addr_t start, end; + u64 i; - nr_ranges = 2; /* for exclusion of crashkernel region */ for_each_mem_range(i, &start, &end) - nr_ranges++; + (*nr_ranges)++; + + return 0; +} - cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); - if (!cmem) - return -ENOMEM; +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) +{ + phys_addr_t start, end; + u64 i; - cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; for_each_mem_range(i, &start, &end) { cmem->ranges[cmem->nr_ranges].start = start; @@ -64,22 +63,12 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) cmem->nr_ranges++; } - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); - if (ret) - goto out; - - if (crashk_low_res.end) { - ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); - if (ret) - goto out; - } - - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + return 0; +} -out: - kfree(cmem); - return ret; +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + return crash_prepare_elf64_headers(true, addr, sz, NULL, NULL, NULL); } #endif diff --git a/arch/loongarch/include/asm/kexec.h b/arch/loongarch/include/asm/kexec.h index 209fa43222e1..a3f0119e2382 100644 --- a/arch/loongarch/include/asm/kexec.h +++ b/arch/loongarch/include/asm/kexec.h @@ -34,7 +34,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } #define ARCH_HAS_KIMAGE_ARCH - struct kimage_arch { unsigned long efi_boot; unsigned long cmdline_ptr; @@ -42,12 +41,20 @@ struct kimage_arch { }; #ifdef CONFIG_KEXEC_FILE +struct crash_mem; + extern const struct kexec_file_ops kexec_efi_ops; extern const struct kexec_file_ops kexec_elf_ops; int arch_kimage_file_post_load_cleanup(struct kimage *image); #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup +int arch_get_system_nr_ranges(unsigned int *nr_ranges); +#define arch_get_system_nr_ranges arch_get_system_nr_ranges + +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem); +#define arch_prepare_elf64_ram_headers arch_prepare_elf64_ram_headers + extern int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, char *initrd, unsigned long initrd_len, char *cmdline, unsigned long cmdline_len); diff --git a/arch/loongarch/kernel/machine_kexec_file.c b/arch/loongarch/kernel/machine_kexec_file.c index fb57026f5f25..eac8544c5cc9 100644 --- a/arch/loongarch/kernel/machine_kexec_file.c +++ b/arch/loongarch/kernel/machine_kexec_file.c @@ -56,23 +56,22 @@ static void cmdline_add_initrd(struct kimage *image, unsigned long *cmdline_tmpl } #ifdef CONFIG_CRASH_DUMP - -static int prepare_elf_headers(void **addr, unsigned long *sz) +int arch_get_system_nr_ranges(unsigned int *nr_ranges) { - int ret, nr_ranges; - uint64_t i; phys_addr_t start, end; - struct crash_mem *cmem; + uint64_t i; - nr_ranges = 2; /* for exclusion of crashkernel region */ for_each_mem_range(i, &start, &end) - nr_ranges++; + (*nr_ranges)++; + + return 0; +} - cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); - if (!cmem) - return -ENOMEM; +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) +{ + phys_addr_t start, end; + uint64_t i; - cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; for_each_mem_range(i, &start, &end) { cmem->ranges[cmem->nr_ranges].start = start; @@ -80,22 +79,12 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) cmem->nr_ranges++; } - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); - if (ret < 0) - goto out; - - if (crashk_low_res.end) { - ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); - if (ret < 0) - goto out; - } - - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + return 0; +} -out: - kfree(cmem); - return ret; +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + return crash_prepare_elf64_headers(true, addr, sz, NULL, NULL, NULL); } /* diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index bd4a6c42a5f3..42a76779ccf2 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -123,6 +123,11 @@ static inline void kdump_cma_reserve(void) { } #endif #if defined(CONFIG_CRASH_DUMP) +#include <asm/kexec_ranges.h> + +struct crash_mem; +struct memory_notify; + /* * This function is responsible for capturing register states if coming * via panic or invoking dump using sysrq-trigger. @@ -147,6 +152,14 @@ unsigned int arch_crash_get_elfcorehdr_size(void); #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size #endif /* CONFIG_CRASH_HOTPLUG */ +int arch_crash_exclude_mem_range(struct crash_mem **mem, unsigned long long mstart, + unsigned long long mend); +#define arch_crash_exclude_mem_range arch_crash_exclude_mem_range + +int arch_crash_prepare_cmem(struct crash_mem *cmem, unsigned long *nr_mem_ranges, + struct kimage *image, struct memory_notify *mn); +#define arch_crash_prepare_cmem arch_crash_prepare_cmem + extern int crashing_cpu; extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)); extern void crash_ipi_callback(struct pt_regs *regs); diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index a325c1c02f96..ff798e3144fa 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -419,30 +419,21 @@ unsigned int arch_crash_get_elfcorehdr_size(void) return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr)); } -/** - * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old - * elfcorehdr in the kexec segment array. - * @image: the active struct kimage - * @mn: struct memory_notify data handler - */ -static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn) +int arch_crash_prepare_cmem(struct crash_mem *cmem, unsigned long *nr_mem_ranges, + struct kimage *image, struct memory_notify *mn) { + unsigned long base_addr, size; int ret; - struct crash_mem *cmem = NULL; - struct kexec_segment *ksegment; - void *ptr, *mem, *elfbuf = NULL; - unsigned long elfsz, memsz, base_addr, size; - - ksegment = &image->segment[image->elfcorehdr_index]; - mem = (void *) ksegment->mem; - memsz = ksegment->memsz; ret = get_crash_memory_ranges(&cmem); if (ret) { pr_err("Failed to get crash mem range\n"); - return; + return ret; } + if (!image || !mn) + return 0; + /* * The hot unplugged memory is part of crash memory ranges, * remove it here. @@ -453,11 +444,31 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * ret = remove_mem_range(&cmem, base_addr, size); if (ret) { pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n"); - goto out; + return ret; } } - ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz); + return 0; +} + +/** + * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old + * elfcorehdr in the kexec segment array. + * @image: the active struct kimage + * @mn: struct memory_notify data handler + */ +static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn) +{ + void *ptr, *mem, *elfbuf = NULL; + struct kexec_segment *ksegment; + unsigned long elfsz, memsz; + int ret; + + ksegment = &image->segment[image->elfcorehdr_index]; + mem = (void *) ksegment->mem; + memsz = ksegment->memsz; + + ret = crash_prepare_elf64_headers(false, &elfbuf, &elfsz, NULL, image, mn); if (ret) { pr_err("Failed to prepare elf header\n"); goto out; @@ -486,7 +497,6 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * xchg(&kexec_crash_image, image); } out: - kvfree(cmem); kvfree(elfbuf); } diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index e7ef8b2a2554..6fe13031236c 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -401,17 +401,17 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) } } -static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) +static unsigned int kdump_extra_elfcorehdr_size(unsigned long nr_mem_ranges) { #if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG) unsigned int extra_sz = 0; if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM) pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES); - else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES) + else if (nr_mem_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES) pr_warn("Configured crash mem ranges may not be enough\n"); else - extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr); + extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - nr_mem_ranges) * sizeof(Elf64_Phdr); return extra_sz; #endif @@ -428,17 +428,13 @@ static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) */ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) { - struct crash_mem *cmem = NULL; + unsigned long nr_mem_ranges; unsigned long headers_sz; void *headers = NULL; int ret; - ret = get_crash_memory_ranges(&cmem); - if (ret) - goto out; - /* Setup elfcorehdr segment */ - ret = crash_prepare_elf64_headers(cmem, false, &headers, &headers_sz); + ret = crash_prepare_elf64_headers(false, &headers, &headers_sz, &nr_mem_ranges, NULL, NULL); if (ret) { pr_err("Failed to prepare elf headers for the core\n"); goto out; @@ -450,7 +446,7 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; kbuf->bufsz = headers_sz; - kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem); + kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(nr_mem_ranges); kbuf->top_down = false; ret = kexec_add_buffer(kbuf); @@ -463,7 +459,6 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) image->elf_headers_sz = headers_sz; image->elf_headers = headers; out: - kfree(cmem); return ret; } diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 867135560e5c..34e3058ff1d5 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -553,9 +553,9 @@ int get_usable_memory_ranges(struct crash_mem **mem_ranges) #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_CRASH_DUMP -static int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges, - unsigned long long mstart, - unsigned long long mend) +int arch_crash_exclude_mem_range(struct crash_mem **mem_ranges, + unsigned long long mstart, + unsigned long long mend) { struct crash_mem *tmem = *mem_ranges; @@ -604,18 +604,6 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges) sort_memory_ranges(*mem_ranges, true); } - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_res.start, crashk_res.end); - if (ret) - goto out; - - for (i = 0; i < crashk_cma_cnt; ++i) { - ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_cma_ranges[i].start, - crashk_cma_ranges[i].end); - if (ret) - goto out; - } - /* * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL * regions are exported to save their context at the time of diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h index b9ee8346cc8c..87307026084e 100644 --- a/arch/riscv/include/asm/kexec.h +++ b/arch/riscv/include/asm/kexec.h @@ -55,6 +55,8 @@ typedef void (*riscv_kexec_method)(unsigned long first_ind_entry, extern riscv_kexec_method riscv_kexec_norelocate; #ifdef CONFIG_KEXEC_FILE +struct crash_mem; + extern const struct kexec_file_ops elf_kexec_ops; extern const struct kexec_file_ops image_kexec_ops; @@ -69,6 +71,12 @@ struct kimage; int arch_kimage_file_post_load_cleanup(struct kimage *image); #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup +int arch_get_system_nr_ranges(unsigned int *nr_ranges); +#define arch_get_system_nr_ranges arch_get_system_nr_ranges + +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem); +#define arch_prepare_elf64_ram_headers arch_prepare_elf64_ram_headers + int load_extra_segments(struct kimage *image, unsigned long kernel_start, unsigned long kernel_len, char *initrd, unsigned long initrd_len, char *cmdline, diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index dd9d92a96517..b3faf0dfac9b 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -44,6 +44,13 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } +int arch_get_system_nr_ranges(unsigned int *nr_ranges) +{ + walk_system_ram_res(0, -1, nr_ranges, get_nr_ram_ranges_callback); + + return 0; +} + static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_mem *cmem = arg; @@ -55,33 +62,15 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) return 0; } -static int prepare_elf_headers(void **addr, unsigned long *sz) +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) { - struct crash_mem *cmem; - unsigned int nr_ranges; - int ret; - - nr_ranges = 1; /* For exclusion of crashkernel region */ - walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); - - cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); - if (!cmem) - return -ENOMEM; - - cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; - ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); - if (ret) - goto out; - - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); - if (!ret) - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + return walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); +} -out: - kfree(cmem); - return ret; +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + return crash_prepare_elf64_headers(true, addr, sz, NULL, NULL, NULL); } static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 5cfb27f26583..d527de588aaa 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -34,6 +34,7 @@ #include <asm/page.h> #include <asm/ptrace.h> +struct crash_mem; struct kimage; /* @@ -219,6 +220,12 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image); #endif #endif +int arch_get_system_nr_ranges(unsigned int *nr_ranges); +#define arch_get_system_nr_ranges arch_get_system_nr_ranges + +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem); +#define arch_prepare_elf64_ram_headers arch_prepare_elf64_ram_headers + extern void kdump_nmi_shootdown_cpus(void); #ifdef CONFIG_CRASH_HOTPLUG diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 335fd2ee9766..ece2764506e9 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -152,72 +152,14 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } -/* Gather all the required information to prepare elf headers for ram regions */ -static struct crash_mem *fill_up_crash_elf_data(void) +int arch_get_system_nr_ranges(unsigned int *nr_ranges) { - unsigned int nr_ranges = 0; - struct crash_mem *cmem; + int ret; - walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + ret = walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); if (!nr_ranges) - return NULL; - - /* - * Exclusion of crash region, crashk_low_res and/or crashk_cma_ranges - * may cause range splits. So add extra slots here. - * - * Exclusion of low 1M may not cause another range split, because the - * range of exclude is [0, 1M] and the condition for splitting a new - * region is that the start, end parameters are both in a certain - * existing region in cmem and cannot be equal to existing region's - * start or end. Obviously, the start of [0, 1M] cannot meet this - * condition. - * - * But in order to lest the low 1M could be changed in the future, - * (e.g. [start, 1M]), add a extra slot. - */ - nr_ranges += 3 + crashk_cma_cnt; - cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); - if (!cmem) - return NULL; - - cmem->max_nr_ranges = nr_ranges; - - return cmem; -} - -/* - * Look for any unwanted ranges between mstart, mend and remove them. This - * might lead to split and split ranges are put in cmem->ranges[] array - */ -static int elf_header_exclude_ranges(struct crash_mem *cmem) -{ - int ret = 0; - int i; - - /* Exclude the low 1M because it is always reserved */ - ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); - if (ret) - return ret; - - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); - if (ret) return ret; - if (crashk_low_res.end) - ret = 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 = crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, - crashk_cma_ranges[i].end); - if (ret) - return ret; - } - return 0; } @@ -232,35 +174,18 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) return 0; } +int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) +{ + return walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); +} + /* Prepare elf headers. Return addr and size */ static int prepare_elf_headers(void **addr, unsigned long *sz, unsigned long *nr_mem_ranges) { - struct crash_mem *cmem; - int ret; - - cmem = fill_up_crash_elf_data(); - if (!cmem) - return -ENOMEM; - - ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); - if (ret) - goto out; - - /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(cmem); - if (ret) - goto out; - - /* Return the computed number of memory ranges, for hotplug usage */ - *nr_mem_ranges = cmem->nr_ranges; - /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); - -out: - vfree(cmem); - return ret; + return crash_prepare_elf64_headers(IS_ENABLED(CONFIG_X86_64), addr, sz, + nr_mem_ranges, NULL, NULL); } #endif diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index d35726d6a415..d2ea5b1a071d 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -2,11 +2,14 @@ #ifndef LINUX_CRASH_CORE_H #define LINUX_CRASH_CORE_H +#include <linux/kexec.h> #include <linux/linkage.h> #include <linux/elfcore.h> #include <linux/elf.h> +#include <linux/vmalloc.h> struct kimage; +struct memory_notify; struct crash_mem { unsigned int max_nr_ranges; @@ -54,6 +57,82 @@ static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long } #endif +#ifndef arch_get_system_nr_ranges +static inline int arch_get_system_nr_ranges(unsigned int *nr_ranges) +{ + return -EINVAL; +} +#endif + +#ifndef arch_prepare_elf64_ram_headers +static inline int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) +{ + return -EINVAL; +} +#endif + +extern int crash_exclude_mem_range(struct crash_mem *mem, + unsigned long long mstart, + unsigned long long mend); + +#ifndef arch_crash_exclude_mem_range +static __always_inline int arch_crash_exclude_mem_range(struct crash_mem **mem_ranges, + unsigned long long mstart, + unsigned long long mend) +{ + return crash_exclude_mem_range(*mem_ranges, mstart, mend); +} +#endif + +#ifndef arch_crash_prepare_cmem +static inline int arch_crash_prepare_cmem(struct crash_mem **cmem, + unsigned long *nr_mem_ranges, + struct kimage *image, + struct memory_notify *mn) +{ + unsigned int nr_ranges; + int ret; + +#ifdef CONFIG_X86_64 + /* + * Exclusion of crash region, crashk_low_res and/or crashk_cma_ranges + * may cause range splits. So add extra slots here. + * + * Exclusion of low 1M may not cause another range split, because the + * range of exclude is [0, 1M] and the condition for splitting a new + * region is that the start, end parameters are both in a certain + * existing region in cmem and cannot be equal to existing region's + * start or end. Obviously, the start of [0, 1M] cannot meet this + * condition. + * + * But in order to lest the low 1M could be changed in the future, + * (e.g. [start, 1M]), add a extra slot. + */ + nr_ranges = 3 + crashk_cma_cnt; +#else + /* For exclusion of crashkernel region*/ + nr_ranges = 1 + (crashk_low_res.end != 0) + crashk_cma_cnt; +#endif + + ret = arch_get_system_nr_ranges(&nr_ranges); + if (ret) + return ret; + + *cmem = kvzalloc(struct_size(*cmem, ranges, nr_ranges), GFP_KERNEL); + if (!(*cmem)) + return -ENOMEM; + + (*cmem)->max_nr_ranges = nr_ranges; + ret = arch_prepare_elf64_ram_headers(*cmem); + if (ret) { + kvfree(*cmem); + return ret; + } + + return 0; +} +#endif + #ifndef crash_get_elfcorehdr_size static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } #endif @@ -61,11 +140,11 @@ static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 -extern int crash_exclude_mem_range(struct crash_mem *mem, - unsigned long long mstart, - unsigned long long mend); -extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, - void **addr, unsigned long *sz); +extern int crash_prepare_elf64_headers(int need_kernel_map, + void **addr, unsigned long *sz, + unsigned long *nr_mem_ranges, + struct kimage *image, + struct memory_notify *mn); struct kimage; struct kexec_segment; diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 99dac1aa972a..71a1dba7b96f 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -18,6 +18,7 @@ #include <linux/memblock.h> #include <linux/kmemleak.h> #include <linux/crash_core.h> +#include <linux/crash_reserve.h> #include <linux/reboot.h> #include <linux/btf.h> #include <linux/objtool.h> @@ -161,19 +162,66 @@ static inline resource_size_t crash_resource_size(const struct resource *res) return !res->end ? 0 : resource_size(res); } +static int crash_exclude_mem_ranges(struct crash_mem *cmem, + unsigned long *nr_mem_ranges) +{ + int ret, i; + +#ifdef CONFIG_X86_64 + /* Exclude the low 1M because it is always reserved */ + ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); + if (ret) + return ret; +#endif + /* 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 the computed number of memory ranges, for hotplug usage */ + if (nr_mem_ranges) + *nr_mem_ranges = cmem->nr_ranges; -int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, - void **addr, unsigned long *sz) + return 0; +} + +int crash_prepare_elf64_headers(int need_kernel_map, void **addr, + unsigned long *sz, unsigned long *nr_mem_ranges, + struct kimage *image, struct memory_notify *mn) { - 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; + struct crash_mem *mem = NULL; unsigned long mstart, mend; + unsigned int cpu, i; + unsigned char *buf; + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + int ret = 0; + + ret = arch_crash_prepare_cmem(&mem, nr_mem_ranges, image, mn); + if (ret) + return ret; + + if (mem) { + ret = crash_exclude_mem_ranges(mem, nr_mem_ranges); + if (ret) + goto out; + } /* extra phdr for vmcoreinfo ELF note */ nr_phdr = nr_cpus + 1; @@ -192,8 +240,10 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN); buf = vzalloc(elf_sz); - if (!buf) - return -ENOMEM; + if (!buf) { + ret = -ENOMEM; + goto out; + } ehdr = (Elf64_Ehdr *)buf; phdr = (Elf64_Phdr *)(ehdr + 1); @@ -262,7 +312,10 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, *addr = buf; *sz = elf_sz; - return 0; + +out: + kvfree(mem); + return ret; } /** -- 2.34.1
Commit 35c18f2933c5 ("Add a new optional ",cma" suffix to the crashkernel= command line option") and commit ab475510e042 ("kdump: implement reserve_crashkernel_cma") added CMA support for kdump crashkernel reservation. Crash kernel memory reservation wastes production resources if too large, risks kdump failure if too small, and faces allocation difficulties on fragmented systems due to contiguous block constraints. The new CMA-based crashkernel reservation scheme splits the "large fixed reservation" into a "small fixed region + large CMA dynamic region": the CMA memory is available to userspace during normal operation to avoid waste, and is reclaimed for kdump upon crash—saving memory while improving reliability. So extend crashkernel CMA reservation support to arm64. The following changes are made to enable CMA reservation: - Parse and obtain the CMA reservation size along with other crashkernel parameters. - Call reserve_crashkernel_cma() to allocate the CMA region for kdump. - Include the CMA-reserved ranges for kdump kernel to use. - Exclude the CMA-reserved ranges from the crash kernel memory to prevent them from being exported through /proc/vmcore, which is already done in the crash core. Update kernel-parameters.txt to document CMA support for crashkernel on arm64 architecture. Acked-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> --- v3: - Add Acked-by. v2: - Free cmem in prepare_elf_headers() - Add the mtivation. --- Documentation/admin-guide/kernel-parameters.txt | 2 +- arch/arm64/kernel/machine_kexec_file.c | 6 ++++++ arch/arm64/mm/init.c | 5 +++-- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1058f2a6d6a8..36bb642a7edd 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1119,7 +1119,7 @@ Kernel parameters It will be ignored when crashkernel=X,high is not used or memory reserved is below 4G. crashkernel=size[KMG],cma - [KNL, X86, ppc] Reserve additional crash kernel memory from + [KNL, X86, ARM64, ppc] Reserve additional crash kernel memory from CMA. This reservation is usable by the first system's userspace memory and kernel movable allocations (memory balloon, zswap). Pages allocated from this memory range diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 377980c282be..8cc51511fa5e 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -63,6 +63,12 @@ int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) cmem->nr_ranges++; } + for (i = 0; i < crashk_cma_cnt; i++) { + cmem->ranges[cmem->nr_ranges].start = crashk_cma_ranges[i].start; + cmem->ranges[cmem->nr_ranges].end = crashk_cma_ranges[i].end; + cmem->nr_ranges++; + } + return 0; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 524d34a0e921..28165d94af08 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -96,8 +96,8 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit; static void __init arch_reserve_crashkernel(void) { + unsigned long long crash_base, crash_size, cma_size = 0; unsigned long long low_size = 0; - unsigned long long crash_base, crash_size; bool high = false; int ret; @@ -106,11 +106,12 @@ static void __init arch_reserve_crashkernel(void) ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, - &low_size, NULL, &high); + &low_size, &cma_size, &high); if (ret) return; reserve_crashkernel_generic(crash_size, crash_base, low_size, high); + reserve_crashkernel_cma(cma_size); } static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit) -- 2.34.1
Commit 35c18f2933c5 ("Add a new optional ",cma" suffix to the crashkernel= command line option") and commit ab475510e042 ("kdump: implement reserve_crashkernel_cma") added CMA support for kdump crashkernel reservation. This allows the kernel to dynamically allocate contiguous memory for crash dumping when needed, rather than permanently reserving a fixed region at boot time. So extend crashkernel CMA reservation support to riscv. The following changes are made to enable CMA reservation: - Parse and obtain the CMA reservation size along with other crashkernel parameters. - Call reserve_crashkernel_cma() to allocate the CMA region for kdump. - Include the CMA-reserved ranges for kdump kernel to use. - Exclude the CMA-reserved ranges from the crash kernel memory to prevent them from being exported through /proc/vmcore, which is already done in the crash core. Update kernel-parameters.txt to document CMA support for crashkernel on riscv architecture. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> --- Documentation/admin-guide/kernel-parameters.txt | 16 ++++++++-------- arch/riscv/kernel/machine_kexec_file.c | 14 +++++++++++++- arch/riscv/mm/init.c | 5 +++-- 3 files changed, 24 insertions(+), 11 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 36bb642a7edd..3b92324d3a03 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1119,14 +1119,14 @@ Kernel parameters It will be ignored when crashkernel=X,high is not used or memory reserved is below 4G. crashkernel=size[KMG],cma - [KNL, X86, ARM64, ppc] Reserve additional crash kernel memory from - CMA. This reservation is usable by the first system's - userspace memory and kernel movable allocations (memory - balloon, zswap). Pages allocated from this memory range - will not be included in the vmcore so this should not - be used if dumping of userspace memory is intended and - it has to be expected that some movable kernel pages - may be missing from the dump. + [KNL, X86, ARM64, RISCV, ppc] Reserve additional crash + kernel memory from CMA. This reservation is usable by + the first system's userspace memory and kernel movable + allocations (memory balloon, zswap). Pages allocated + from this memory range will not be included in the vmcore + so this should not be used if dumping of userspace memory + is intended and it has to be expected that some movable + kernel pages may be missing from the dump. A standard crashkernel reservation, as described above, is still needed to hold the crash kernel and initrd. diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index b3faf0dfac9b..cb78ab227d47 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -64,8 +64,20 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) int arch_prepare_elf64_ram_headers(struct crash_mem *cmem) { + int ret; + cmem->nr_ranges = 0; - return walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); + ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); + if (ret) + return ret; + + for (i = 0; i < crashk_cma_cnt; i++) { + cmem->ranges[cmem->nr_ranges].start = crashk_cma_ranges[i].start; + cmem->ranges[cmem->nr_ranges].end = crashk_cma_ranges[i].end; + cmem->nr_ranges++; + } + + return 0; } static int prepare_elf_headers(void **addr, unsigned long *sz) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index addb8a9305be..074d2d5f79ee 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1404,7 +1404,7 @@ static inline void setup_vm_final(void) */ static void __init arch_reserve_crashkernel(void) { - unsigned long long low_size = 0; + unsigned long long low_size = 0, cma_size = 0; unsigned long long crash_base, crash_size; bool high = false; int ret; @@ -1414,11 +1414,12 @@ static void __init arch_reserve_crashkernel(void) ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, - &low_size, NULL, &high); + &low_size, &cma_size, &high); if (ret) return; reserve_crashkernel_generic(crash_size, crash_base, low_size, high); + reserve_crashkernel_cma(cma_size); } void __init paging_init(void) -- 2.34.1
participants (1)
-
Jinjie Ruan