From 5fc6e7d45373571d03cd04fd4c6069c0a97fa75a Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:37 +0800 Subject: [PATCH 01/13] riscv: kexec_file: Fix crashk_low_res not exclude bug As done in commit 944a45abfabc ("arm64: kdump: Reimplement crashkernel=X") and commit 4831be702b95 ("arm64/kexec: Fix missing extra range for crashkres_low.") for arm64, while implementing crashkernel=X,[high,low], riscv should have excluded the "crashk_low_res" reserved ranges from the crash kernel memory to prevent them from being exported through /proc/vmcore, and the exclusion would need an extra crash_mem range. Just simply tested on qemu with crashkernel=4G with kexec in [1] mentioned in [2]. And the second kernel can be started normally. # dmesg | grep crash [ 0.000000] crashkernel low memory reserved: 0xf8000000 - 0x100000000 (128 MB) [ 0.000000] crashkernel reserved: 0x000000017fe00000 - 0x000000027fe00000 (4096 MB) [1]: https://github.com/chenjh005/kexec-tools/tree/build-test-riscv-v2 [2]: https://lore.kernel.org/all/20230726175000.2536220-1-chenjiahao16@huawei.com/ Cc: Guo Ren Cc: Baoquan He Fixes: 5882e5acf18d ("riscv: kdump: Implement crashkernel=X,[high,low]") Reviewed-by: Guo Ren Signed-off-by: Jinjie Ruan Link: https://github.com/chenjh005/kexec-tools/tree/build-test-riscv-v2 Link: https://lore.kernel.org/all/20230726175000.2536220-1-chenjiahao16@huawei.com/ Link: https://patch.msgid.link/20260629094746.191843-2-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/riscv/kernel/machine_kexec_file.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index 59d4bbc848a8..fa2946aa9b8f 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -62,7 +62,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) unsigned int nr_ranges; int ret; - nr_ranges = 1; /* For exclusion of crashkernel region */ + nr_ranges = 2; /* For exclusion of crashkernel region */ walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); cmem = kmalloc_flex(*cmem, ranges, nr_ranges); @@ -77,8 +77,16 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) /* 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); + 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); out: kfree(cmem); From 202b5de3ec34317d6a8944239fe227ef8f6853ec Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Mon, 29 Jun 2026 17:47:38 +0800 Subject: [PATCH 02/13] powerpc/crash: sort crash memory ranges before preparing elfcorehdr During a memory hot-remove event, the elfcorehdr is rebuilt to exclude the removed memory. While updating the crash memory ranges for this operation, the crash memory ranges array can become unsorted. This happens because remove_mem_range() may split a memory range into two parts and append the higher-address part as a separate range at the end of the array. So far, no issues have been observed due to the unsorted crash memory ranges. However, this could lead to problems once crash memory range removal is handled by generic code, as introduced in the upcoming patches in this series. Currently, powerpc uses a platform-specific function, remove_mem_range(), to exclude hot-removed memory from the crash memory ranges. This function performs the same task as the generic crash_exclude_mem_range() in crash_core.c. The generic helper also ensures that the crash memory ranges remain sorted. So remove the redundant powerpc-specific implementation and instead call crash_exclude_mem_range_guarded() (which internally calls crash_exclude_mem_range()) to exclude the hot-removed memory ranges. Cc: Andrew Morton Cc: Baoquan he Cc: Jinjie Ruan Cc: Hari Bathini Cc: Madhavan Srinivasan Cc: Mahesh Salgaonkar Cc: Michael Ellerman Cc: Ritesh Harjani (IBM) Cc: Shivang Upadhyay Cc: linux-kernel@vger.kernel.org Acked-by: Baoquan He Reviewed-by: Ritesh Harjani (IBM) Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Sourabh Jain Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-3-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/powerpc/include/asm/kexec_ranges.h | 4 +- arch/powerpc/kexec/crash.c | 5 +- arch/powerpc/kexec/ranges.c | 87 +------------------------ 3 files changed, 7 insertions(+), 89 deletions(-) diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index 14055896cbcb..ad95e3792d10 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -7,7 +7,9 @@ void sort_memory_ranges(struct crash_mem *mrngs, bool merge); struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); -int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); +int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges, + unsigned long long mstart, + unsigned long long mend); int get_exclude_memory_ranges(struct crash_mem **mem_ranges); int get_reserved_memory_ranges(struct crash_mem **mem_ranges); int get_crash_memory_ranges(struct crash_mem **mem_ranges); diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index e6539f213b3d..2e88ec5c4356 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -493,7 +493,7 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * struct crash_mem *cmem = NULL; struct kexec_segment *ksegment; void *ptr, *mem, *elfbuf = NULL; - unsigned long elfsz, memsz, base_addr, size; + unsigned long elfsz, memsz, base_addr, size, end; ksegment = &image->segment[image->elfcorehdr_index]; mem = (void *) ksegment->mem; @@ -512,7 +512,8 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) { base_addr = PFN_PHYS(mn->start_pfn); size = mn->nr_pages * PAGE_SIZE; - ret = remove_mem_range(&cmem, base_addr, size); + end = base_addr + size - 1; + ret = crash_exclude_mem_range_guarded(&cmem, base_addr, end); if (ret) { pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n"); goto out; diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 867135560e5c..6c58bcc3e130 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -553,7 +553,7 @@ 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, +int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges, unsigned long long mstart, unsigned long long mend) { @@ -641,89 +641,4 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges) pr_err("Failed to setup crash memory ranges\n"); return ret; } - -/** - * remove_mem_range - Removes the given memory range from the range list. - * @mem_ranges: Range list to remove the memory range to. - * @base: Base address of the range to remove. - * @size: Size of the memory range to remove. - * - * (Re)allocates memory, if needed. - * - * Returns 0 on success, negative errno on error. - */ -int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) -{ - u64 end; - int ret = 0; - unsigned int i; - u64 mstart, mend; - struct crash_mem *mem_rngs = *mem_ranges; - - if (!size) - return 0; - - /* - * Memory range are stored as start and end address, use - * the same format to do remove operation. - */ - end = base + size - 1; - - for (i = 0; i < mem_rngs->nr_ranges; i++) { - mstart = mem_rngs->ranges[i].start; - mend = mem_rngs->ranges[i].end; - - /* - * Memory range to remove is not part of this range entry - * in the memory range list - */ - if (!(base >= mstart && end <= mend)) - continue; - - /* - * Memory range to remove is equivalent to this entry in the - * memory range list. Remove the range entry from the list. - */ - if (base == mstart && end == mend) { - for (; i < mem_rngs->nr_ranges - 1; i++) { - mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start; - mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end; - } - mem_rngs->nr_ranges--; - goto out; - } - /* - * Start address of the memory range to remove and the - * current memory range entry in the list is same. Just - * move the start address of the current memory range - * entry in the list to end + 1. - */ - else if (base == mstart) { - mem_rngs->ranges[i].start = end + 1; - goto out; - } - /* - * End address of the memory range to remove and the - * current memory range entry in the list is same. - * Just move the end address of the current memory - * range entry in the list to base - 1. - */ - else if (end == mend) { - mem_rngs->ranges[i].end = base - 1; - goto out; - } - /* - * Memory range to remove is not at the edge of current - * memory range entry. Split the current memory entry into - * two half. - */ - else { - size = mem_rngs->ranges[i].end - end + 1; - mem_rngs->ranges[i].end = base - 1; - ret = add_mem_range(mem_ranges, end + 1, size); - } - } -out: - return ret; -} #endif /* CONFIG_CRASH_DUMP */ From 5beabef0cffaa1ea6e27e85dbd526b7a28e0e7c7 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:39 +0800 Subject: [PATCH 03/13] crash: Add crash_prepare_headers() to exclude crash kernel memory The crash memory alloc, and the exclude of crashk_res, crashk_low_res and crashk_cma memory are almost identical across different architectures, handling them in the crash core would eliminate a lot of duplication, so add crash_prepare_headers() helper to handle them in the common code. To achieve the above goal, three architecture-specific functions are introduced: - arch_get_system_nr_ranges(). Pre-counts the max number of memory ranges. - arch_crash_populate_cmem(). Collects the memory ranges and fills them into cmem. - arch_crash_exclude_ranges(). Architecture's additional crash memory ranges exclusion, defaulting to empty. Reviewed-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-4-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- include/linux/crash_core.h | 5 +++ kernel/crash_core.c | 82 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 84 insertions(+), 3 deletions(-) diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index c1dee3f971a9..583ffcc703d4 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -59,6 +59,8 @@ extern int crash_exclude_mem_range(struct crash_mem *mem, 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_headers(int need_kernel_map, void **addr, + unsigned long *sz, unsigned long *nr_mem_ranges); struct kimage; struct kexec_segment; @@ -76,6 +78,9 @@ int kexec_should_crash(struct task_struct *p); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); +extern unsigned int arch_get_system_nr_ranges(void); +extern int arch_crash_populate_cmem(struct crash_mem *cmem); +extern int arch_crash_exclude_ranges(struct crash_mem *cmem); #else /* !CONFIG_CRASH_DUMP*/ struct pt_regs; diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 4f21fc3b108b..481babc29131 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -168,9 +168,6 @@ 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) { @@ -272,6 +269,85 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, 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; } + +static int crash_exclude_core_ranges(struct crash_mem *cmem) +{ + int ret, i; + + /* 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; +} + +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 From 201b561cbc6c594aa1ef718a1204dd45720d96dd Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:40 +0800 Subject: [PATCH 04/13] arm64: kexec_file: Use crash_prepare_headers() helper to simplify code Use the newly introduced crash_prepare_headers() function to replace the existing prepare_elf_headers(), allocate cmem and exclude crash kernel memory in the crash core, which reduce code duplication. Only the following two architecture functions need to be implemented: - arch_get_system_nr_ranges(). Use for_each_mem_range() to traverse and pre-count the max number of memory ranges. - arch_crash_populate_cmem(). Use for_each_mem_range to traverse and collect the memory ranges and fills them into cmem. Acked-by: Catalin Marinas Reviewed-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-5-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/arm64/kernel/machine_kexec_file.c | 40 ++++++++------------------ 1 file changed, 12 insertions(+), 28 deletions(-) diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index e31fabed378a..b019b31df48c 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -40,46 +40,30 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) } #ifdef CONFIG_CRASH_DUMP -static int prepare_elf_headers(void **addr, unsigned long *sz) +unsigned int arch_get_system_nr_ranges(void) { - struct crash_mem *cmem; - unsigned int nr_ranges; - int ret; - u64 i; + unsigned int nr_ranges = 2; /* for exclusion of crashkernel region */ phys_addr_t start, end; + u64 i; - nr_ranges = 2; /* for exclusion of crashkernel region */ for_each_mem_range(i, &start, &end) nr_ranges++; - cmem = kmalloc_flex(*cmem, ranges, nr_ranges); - if (!cmem) - return -ENOMEM; + return nr_ranges; +} + +int arch_crash_populate_cmem(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; cmem->ranges[cmem->nr_ranges].end = end - 1; 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); - -out: - kfree(cmem); - return ret; + return 0; } #endif @@ -109,7 +93,7 @@ int load_other_segments(struct kimage *image, void *headers; unsigned long headers_sz; if (image->type == KEXEC_TYPE_CRASH) { - ret = prepare_elf_headers(&headers, &headers_sz); + ret = crash_prepare_headers(true, &headers, &headers_sz, NULL); if (ret) { pr_err("Preparing elf core header failed\n"); goto out_err; From a8f09f2a7485956c3653696f6cb94faadd243645 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:41 +0800 Subject: [PATCH 05/13] x86/crash: Use crash_prepare_headers() helper to simplify code Use the newly introduced crash_prepare_headers() function to replace the existing prepare_elf_headers(), allocate cmem and exclude crash kernel memory in the crash core, which reduce code duplication. Only the following three architecture functions need to be implemented: - arch_get_system_nr_ranges(). Call get_nr_ram_ranges_callback() to pre-count the max number of memory ranges. - arch_crash_populate_cmem(). Use prepare_elf64_ram_headers_callback() to collect the memory ranges and fills them into cmem. - arch_crash_exclude_ranges(). Exclude the low 1M for x86. While at it, remove the unused "nr_mem_ranges" in arch_crash_handle_hotplug_event(). Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Andrew Morton Cc: Vivek Goyal Acked-by: Borislav Petkov (AMD) Reviewed-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-6-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/x86/kernel/crash.c | 89 +++++------------------------------------ 1 file changed, 11 insertions(+), 78 deletions(-) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 623d4474631a..e681ec9cf1dc 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -155,16 +155,8 @@ 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) +unsigned int arch_get_system_nr_ranges(void) { - unsigned int nr_ranges = 0; - struct crash_mem *cmem; - - 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. @@ -179,49 +171,16 @@ static struct crash_mem *fill_up_crash_elf_data(void) * 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; + unsigned int nr_ranges = 3 + crashk_cma_cnt; - cmem->max_nr_ranges = nr_ranges; - - return cmem; + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + return nr_ranges; } -/* - * 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 arch_crash_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; + return crash_exclude_mem_range(cmem, 0, SZ_1M - 1); } static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) @@ -235,35 +194,9 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) return 0; } -/* Prepare elf headers. Return addr and size */ -static int prepare_elf_headers(void **addr, unsigned long *sz, - unsigned long *nr_mem_ranges) +int arch_crash_populate_cmem(struct crash_mem *cmem) { - 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 walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); } #endif @@ -421,7 +354,8 @@ int crash_load_segments(struct kimage *image) .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); + ret = crash_prepare_headers(IS_ENABLED(CONFIG_X86_64), &kbuf.buffer, + &kbuf.bufsz, &pnum); if (ret) return ret; @@ -514,7 +448,6 @@ unsigned int arch_crash_get_elfcorehdr_size(void) void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; - unsigned long nr_mem_ranges; unsigned long mem, memsz; unsigned long elfsz = 0; @@ -532,7 +465,7 @@ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ - if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { + if (crash_prepare_headers(IS_ENABLED(CONFIG_X86_64), &elfbuf, &elfsz, NULL)) { pr_err("unable to create new elfcorehdr"); goto out; } From 7b078a0aa2753dcf5cae88e5349a25ac39998a9b Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:42 +0800 Subject: [PATCH 06/13] riscv: kexec_file: Use crash_prepare_headers() helper to simplify code Use the newly introduced crash_prepare_headers() function to replace the existing prepare_elf_headers(), allocate cmem and exclude crash kernel memory in the crash core, which reduce code duplication. Only the following two architecture functions need to be implemented: - arch_get_system_nr_ranges(). Call get_nr_ram_ranges_callback() to pre-counts the max number of memory ranges. - arch_crash_populate_cmem(). Use prepare_elf64_ram_headers_callback() to collects the memory ranges and fills them into cmem. Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Alexandre Ghiti Cc: Guo Ren Reviewed-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Reviewed-by: Guo Ren Link: https://patch.msgid.link/20260629094746.191843-7-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/riscv/kernel/machine_kexec_file.c | 47 +++++++------------------- 1 file changed, 12 insertions(+), 35 deletions(-) diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index fa2946aa9b8f..1dfb1d9eb691 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -45,6 +45,15 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } +unsigned int arch_get_system_nr_ranges(void) +{ + unsigned int nr_ranges = 2; /* For exclusion of crashkernel region */ + + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + + return nr_ranges; +} + static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_mem *cmem = arg; @@ -56,41 +65,9 @@ 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_crash_populate_cmem(struct crash_mem *cmem) { - struct crash_mem *cmem; - unsigned int nr_ranges; - int ret; - - nr_ranges = 2; /* For exclusion of crashkernel region */ - walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); - - cmem = kmalloc_flex(*cmem, ranges, nr_ranges); - 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) - 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); - -out: - kfree(cmem); - return ret; + return walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); } static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, @@ -282,7 +259,7 @@ int load_extra_segments(struct kimage *image, unsigned long kernel_start, if (image->type == KEXEC_TYPE_CRASH) { void *headers; unsigned long headers_sz; - ret = prepare_elf_headers(&headers, &headers_sz); + ret = crash_prepare_headers(true, &headers, &headers_sz, NULL); if (ret) { pr_err("Preparing elf core header failed\n"); goto out; From 51ed0950adf05c99e393818887a2616dd4ab3e34 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:43 +0800 Subject: [PATCH 07/13] LoongArch: kexec_file: Use crash_prepare_headers() helper to simplify code Use the newly introduced crash_prepare_headers() function to replace the existing prepare_elf_headers(), allocate cmem and exclude crash kernel memory in the crash core, which reduce code duplication. Only the following two architecture functions need to be implemented: - arch_get_system_nr_ranges(). Use for_each_mem_range to traverse and pre-count the max number of memory ranges. - arch_crash_populate_cmem(). Use for_each_mem_range to traverse and collect the memory ranges and fills them into cmem. Cc: Huacai Chen Cc: WANG Xuerui Cc: Youling Tang Cc: Baoquan He Reviewed-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-8-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/loongarch/kernel/machine_kexec_file.c | 40 +++++++--------------- 1 file changed, 12 insertions(+), 28 deletions(-) diff --git a/arch/loongarch/kernel/machine_kexec_file.c b/arch/loongarch/kernel/machine_kexec_file.c index 5584b798ba46..5412aa9f3568 100644 --- a/arch/loongarch/kernel/machine_kexec_file.c +++ b/arch/loongarch/kernel/machine_kexec_file.c @@ -56,46 +56,30 @@ 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) +unsigned int arch_get_system_nr_ranges(void) { - int ret, nr_ranges; - uint64_t i; + int nr_ranges = 2; /* for exclusion of crashkernel region */ 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++; - cmem = kmalloc_flex(*cmem, ranges, nr_ranges); - if (!cmem) - return -ENOMEM; + return nr_ranges; +} + +int arch_crash_populate_cmem(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; cmem->ranges[cmem->nr_ranges].end = end - 1; 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); - -out: - kfree(cmem); - return ret; + return 0; } /* @@ -163,7 +147,7 @@ int load_other_segments(struct kimage *image, void *headers; unsigned long headers_sz; - ret = prepare_elf_headers(&headers, &headers_sz); + ret = crash_prepare_headers(true, &headers, &headers_sz, NULL); if (ret < 0) { pr_err("Preparing elf core header failed\n"); goto out_err; From b0e06c5a30742bc6bc8523fe9c71c1a043a7661d Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:44 +0800 Subject: [PATCH 08/13] powerpc/kexec_file: Use crash_exclude_core_ranges() helper The crash memory exclude of crashk_res and crashk_cma memory on powerpc are almost identical to the generic crash_exclude_core_ranges(). By introducing the architecture-specific arch_crash_exclude_mem_range() function with a default implementation of crash_exclude_mem_range(), and using crash_exclude_mem_range_guarded as powerpc's separate implementation, the generic crash_exclude_core_ranges() helper function can be reused. Cc: Andrew Morton Cc: Hari Bathini Cc: Madhavan Srinivasan Cc: Mahesh Salgaonkar Cc: Michael Ellerman Cc: Ritesh Harjani (IBM) Cc: Shivang Upadhyay Acked-by: Breno leitao Acked-by: Baoquan He Reviewed-by: Sourabh Jain Acked-by: Mike Rapoport (Microsoft) Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-9-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- arch/powerpc/include/asm/kexec_ranges.h | 3 --- arch/powerpc/kexec/crash.c | 2 +- arch/powerpc/kexec/ranges.c | 16 ++++------------ include/linux/crash_core.h | 4 ++++ kernel/crash_core.c | 19 +++++++++++++------ 5 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index ad95e3792d10..8489e844b447 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -7,9 +7,6 @@ void sort_memory_ranges(struct crash_mem *mrngs, bool merge); struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); -int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges, - unsigned long long mstart, - unsigned long long mend); int get_exclude_memory_ranges(struct crash_mem **mem_ranges); int get_reserved_memory_ranges(struct crash_mem **mem_ranges); int get_crash_memory_ranges(struct crash_mem **mem_ranges); diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index 2e88ec5c4356..60a917a6beaa 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -513,7 +513,7 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * base_addr = PFN_PHYS(mn->start_pfn); size = mn->nr_pages * PAGE_SIZE; end = base_addr + size - 1; - ret = crash_exclude_mem_range_guarded(&cmem, base_addr, end); + ret = arch_crash_exclude_mem_range(&cmem, base_addr, end); if (ret) { pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n"); goto out; diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 6c58bcc3e130..e5fea23b191b 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 -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 +604,10 @@ 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); + ret = crash_exclude_core_ranges(mem_ranges); 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/include/linux/crash_core.h b/include/linux/crash_core.h index 583ffcc703d4..bc087124cd78 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -61,6 +61,7 @@ extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_ma void **addr, unsigned long *sz); extern int crash_prepare_headers(int need_kernel_map, void **addr, unsigned long *sz, unsigned long *nr_mem_ranges); +extern int crash_exclude_core_ranges(struct crash_mem **cmem); struct kimage; struct kexec_segment; @@ -81,6 +82,9 @@ extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern unsigned int arch_get_system_nr_ranges(void); extern int arch_crash_populate_cmem(struct crash_mem *cmem); extern int arch_crash_exclude_ranges(struct crash_mem *cmem); +extern int arch_crash_exclude_mem_range(struct crash_mem **mem, + unsigned long long mstart, + unsigned long long mend); #else /* !CONFIG_CRASH_DUMP*/ struct pt_regs; diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 481babc29131..2b36aa9fade0 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -285,24 +285,31 @@ 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; } -static int crash_exclude_core_ranges(struct crash_mem *cmem) +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 = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + ret = arch_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); + 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 = crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, - crashk_cma_ranges[i].end); + ret = arch_crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, + crashk_cma_ranges[i].end); if (ret) return ret; } @@ -329,7 +336,7 @@ int crash_prepare_headers(int need_kernel_map, void **addr, unsigned long *sz, if (ret) goto out; - ret = crash_exclude_core_ranges(cmem); + ret = crash_exclude_core_ranges(&cmem); if (ret) goto out; From c12c63d05dfe7088aa8b1b872fe261e25537c823 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:45 +0800 Subject: [PATCH 09/13] arm64: kexec_file: Add support for crashkernel CMA reservation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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. Tested-by: Breno Leitao Acked-by: Catalin Marinas Acked-by: Rob Herring (Arm) Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Acked-by: Ard Biesheuvel Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-10-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- Documentation/admin-guide/kernel-parameters.txt | 2 +- arch/arm64/kernel/machine_kexec_file.c | 2 +- arch/arm64/mm/init.c | 5 +++-- drivers/of/fdt.c | 9 +++++---- drivers/of/kexec.c | 9 +++++++++ include/linux/crash_reserve.h | 4 +++- 6 files changed, 22 insertions(+), 9 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b5493a7f8f22..6774223c53b0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1089,7 +1089,7 @@ 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 b019b31df48c..854d872dfd0f 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -42,7 +42,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) #ifdef CONFIG_CRASH_DUMP unsigned int arch_get_system_nr_ranges(void) { - unsigned int nr_ranges = 2; /* for exclusion of crashkernel region */ + unsigned int nr_ranges = 2 + crashk_cma_cnt; /* for exclusion of crashkernel region */ phys_addr_t start, end; u64 i; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 97987f850a33..227f58522dad 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) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 26f66046cc32..a64afc3ded3d 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -878,11 +878,12 @@ static unsigned long chosen_node_offset = -FDT_ERR_NOTFOUND; /* * The main usage of linux,usable-memory-range is for crash dump kernel. * Originally, the number of usable-memory regions is one. Now there may - * be two regions, low region and high region. - * To make compatibility with existing user-space and older kdump, the low - * region is always the last range of linux,usable-memory-range if exist. + * be 2 + CRASHK_CMA_RANGES_MAX regions, low region, high region and cma + * regions. To make compatibility with existing user-space and older kdump, + * the high and low region are always the first two ranges of + * linux,usable-memory-range if exist. */ -#define MAX_USABLE_RANGES 2 +#define MAX_USABLE_RANGES (2 + CRASHK_CMA_RANGES_MAX) /** * early_init_dt_check_for_usable_mem_range - Decode usable memory range diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index b6837e299e7f..029903b986cb 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -458,6 +458,15 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image, if (ret) goto out; } + + for (int i = 0; i < crashk_cma_cnt; i++) { + ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, + "linux,usable-memory-range", + crashk_cma_ranges[i].start, + crashk_cma_ranges[i].end - crashk_cma_ranges[i].start + 1); + if (ret) + goto out; + } #endif } diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index f0dc03d94ca2..30864d90d7f5 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -14,9 +14,11 @@ extern struct resource crashk_res; extern struct resource crashk_low_res; extern struct range crashk_cma_ranges[]; + +#define CRASHK_CMA_RANGES_MAX 4 #if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION) #define CRASHKERNEL_CMA -#define CRASHKERNEL_CMA_RANGES_MAX 4 +#define CRASHKERNEL_CMA_RANGES_MAX (CRASHK_CMA_RANGES_MAX) extern int crashk_cma_cnt; #else #define crashk_cma_cnt 0 From a037fe3c58ed489ca8ad8531bd7e16b90a84badc Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 29 Jun 2026 17:47:46 +0800 Subject: [PATCH 10/13] riscv: kexec_file: Add support for crashkernel CMA reservation 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, which was already done in of_kexec_alloc_and_setup_fdt(). - Exclude the CMA-reserved ranges from the crash kernel memory to prevent them from being exported through /proc/vmcore, which was already done in the crash core. Update kernel-parameters.txt to document CMA support for crashkernel on riscv architecture. Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Alexandre Ghiti Acked-by: Baoquan He Acked-by: Mike Rapoport (Microsoft) Acked-by: Paul Walmsley # arch/riscv Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20260629094746.191843-11-ruanjinjie@huawei.com Signed-off-by: Mike Rapoport (Microsoft) --- Documentation/admin-guide/kernel-parameters.txt | 16 ++++++++-------- arch/riscv/kernel/machine_kexec_file.c | 2 +- arch/riscv/mm/init.c | 5 +++-- 3 files changed, 12 insertions(+), 11 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6774223c53b0..4f65b2a37521 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1089,14 +1089,14 @@ 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 1dfb1d9eb691..26cd2a8bd0cd 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -47,7 +47,7 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) unsigned int arch_get_system_nr_ranges(void) { - unsigned int nr_ranges = 2; /* For exclusion of crashkernel region */ + unsigned int nr_ranges = 2 + crashk_cma_cnt; /* For exclusion of crashkernel region */ walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 5b1b3c88b4d1..1d0145c86c15 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1320,7 +1320,7 @@ 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; @@ -1330,11 +1330,12 @@ 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) From 94f9cef0f51c0cb14495dab315266c0a3ae4ce9a Mon Sep 17 00:00:00 2001 From: Michal Clapinski Date: Tue, 2 Jun 2026 14:33:11 +0200 Subject: [PATCH 11/13] kexec_file: skip checksum verification when safe Checksum verification is needed 1. for crash kernels. In a crash, we can't be sure the kernel is intact. 2. if we're worried about relocating the kernel into a region used by some DMA that wasn't properly cancelled. If KHO is enabled then relocations will happen to KHO scratch, which is free from DMA regions. If we used CMA to allocate segments then relocations are not going to happen at all. Therefore, we can safely disable checksum verification in both of those cases. Instead of adding a new variable to purgatory, just skip adding regions and save the default value of SHA256 hash. Saves ~250ms on my 4.0 GHz CPU. This is an important saving for the live-update project. Signed-off-by: Michal Clapinski Reviewed-by: Pratyush Yadav (Google) Reviewed-by: Pasha Tatashin Acked-by: Baoquan He Link: https://patch.msgid.link/20260602123311.1841746-1-mclapinski@google.com Signed-off-by: Pasha Tatashin Signed-off-by: Mike Rapoport (Microsoft) --- kernel/kexec_file.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 2bfbb2d144e6..59fb9d71e9d8 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "kexec_internal.h" #ifdef CONFIG_KEXEC_SIG @@ -798,6 +799,16 @@ int kexec_add_buffer(struct kexec_buf *kbuf) return 0; } +static bool kexec_only_cma_segments(struct kimage *image) +{ + for (int i = 0; i < image->nr_segments; i++) { + if (!image->segment_cma[i]) + return false; + } + + return true; +} + /* Calculate and store the digest of segments */ static int kexec_calculate_store_digests(struct kimage *image) { @@ -822,6 +833,21 @@ static int kexec_calculate_store_digests(struct kimage *image) sha256_init(&sctx); + /* + * If KHO is enabled, the destinations are located in KHO scratch. + * KHO scratch can only contain early boot allocations and movable + * allocations. That means there is no risk of memory corruption by + * uncancelled DMA. + * + * If all segments were loaded into contiguous memory, there will be no + * relocations at all, so also no risk of corruption. + */ + if (image->type != KEXEC_TYPE_CRASH && + (kho_is_enabled() || kexec_only_cma_segments(image))) { + pr_debug("disabling checksum verification in purgatory\n"); + goto skip_checksum; + } + for (j = i = 0; i < image->nr_segments; i++) { struct kexec_segment *ksegment; @@ -867,6 +893,7 @@ static int kexec_calculate_store_digests(struct kimage *image) j++; } +skip_checksum: sha256_final(&sctx, digest); ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions", From 6a673b6c419a5b5bf7457f33b80a77f842057066 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 19 Jun 2026 18:06:54 +0200 Subject: [PATCH 12/13] kexec: Replace __ASSEMBLY__ with __ASSEMBLER__ in header file While the GCC and Clang compilers already define __ASSEMBLER__ automatically when compiling assembly code, __ASSEMBLY__ is a macro that only gets defined by the Makefiles in the kernel. This can be very confusing when switching between userspace and kernelspace coding, or when dealing with uapi headers that rather should use __ASSEMBLER__ instead. So let's standardize now on the __ASSEMBLER__ macro that is provided by the compilers. Signed-off-by: Thomas Huth Acked-by: Pratyush Yadav Link: https://patch.msgid.link/20260619160654.75980-1-thuth@redhat.com Signed-off-by: Mike Rapoport (Microsoft) --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 8a22bc9b8c6c..0af8ae4fdd08 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -13,7 +13,7 @@ #define IND_SOURCE (1 << IND_SOURCE_BIT) #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE) -#if !defined(__ASSEMBLY__) +#if !defined(__ASSEMBLER__) #include #include From ada2e5a44e99113e08ad9b7b71396c6c572204da Mon Sep 17 00:00:00 2001 From: Guangshuo Li Date: Sat, 4 Jul 2026 19:25:09 +0800 Subject: [PATCH 13/13] crash_dump: release keyring reference at the correct time restore_dm_crypt_keys_to_thread_keyring() gets a reference to the user keyring before restoring the saved dm-crypt keys. The same keyring reference is then passed to add_key_to_keyring() for each saved key, but add_key_to_keyring() drops that reference on every call. This is only balanced when exactly one key is restored. With multiple keys, the keyring reference is dropped too many times and may trigger a refcount underflow or use-after-free. When more than five keys are restored, a refcount underflow/use-after-free warning can be triggered. The early error paths after lookup_user_key() also return without dropping the keyring reference. Keep ownership of the keyring reference in restore_dm_crypt_keys_to_thread_keyring(), drop it once on all exit paths, and make add_key_to_keyring() only use the reference without consuming it. Fixes: 62f17d9df692 ("crash_dump: retrieve dm crypt keys in kdump kernel") Signed-off-by: Guangshuo Li Reviewed-and-tested-by: Coiby Xu Acked-by: Baoquan He Reviewed-by: Bradley Morgan Link: https://patch.msgid.link/20260704112509.3717884-1-lgs201920130244@gmail.com Signed-off-by: Mike Rapoport (Microsoft) --- kernel/crash_dump_dm_crypt.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c index cb875ddb6ba6..c685497cd470 100644 --- a/kernel/crash_dump_dm_crypt.c +++ b/kernel/crash_dump_dm_crypt.c @@ -81,7 +81,6 @@ static int add_key_to_keyring(struct dm_crypt_key *dm_key, kexec_dprintk("Error when adding key"); } - key_ref_put(keyring_ref); return r; } @@ -104,6 +103,7 @@ static int restore_dm_crypt_keys_to_thread_keyring(void) struct dm_crypt_key *key; size_t keys_header_size; key_ref_t keyring_ref; + int ret = 0; u64 addr; /* find the target keyring (which must be writable) */ @@ -118,7 +118,8 @@ static int restore_dm_crypt_keys_to_thread_keyring(void) dm_crypt_keys_read((char *)&key_count, sizeof(key_count), &addr); if (key_count > KEY_NUM_MAX) { kexec_dprintk("Failed to read the number of dm-crypt keys\n"); - return -1; + ret = -1; + goto out; } kexec_dprintk("There are %u keys\n", key_count); @@ -126,8 +127,10 @@ static int restore_dm_crypt_keys_to_thread_keyring(void) keys_header_size = get_keys_header_size(key_count); keys_header = kzalloc(keys_header_size, GFP_KERNEL); - if (!keys_header) - return -ENOMEM; + if (!keys_header) { + ret = -ENOMEM; + goto out; + } dm_crypt_keys_read((char *)keys_header, keys_header_size, &addr); @@ -137,7 +140,9 @@ static int restore_dm_crypt_keys_to_thread_keyring(void) add_key_to_keyring(key, keyring_ref); } - return 0; +out: + key_ref_put(keyring_ref); + return ret; } static int read_key_from_user_keyring(struct dm_crypt_key *dm_key)