From 118005713e35a1893c6ee47ab2926cca277737de Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:08 +0530 Subject: [PATCH 1/7] crash: forward memory_notify arg to arch crash hotplug handler In the event of memory hotplug or online/offline events, the crash memory hotplug notifier `crash_memhp_notifier()` receives a `memory_notify` object but doesn't forward that object to the generic and architecture-specific crash hotplug handler. The `memory_notify` object contains the starting PFN (Page Frame Number) and the number of pages in the hot-removed memory. This information is necessary for architectures like PowerPC to update/recreate the kdump image, specifically `elfcorehdr`. So update the function signature of `crash_handle_hotplug_event()` and `arch_crash_handle_hotplug_event()` to accept the `memory_notify` object as an argument from crash memory hotplug notifier. Since no such object is available in the case of CPU hotplug event, the crash CPU hotplug notifier `crash_cpuhp_online()` passes NULL to the crash hotplug handler. Signed-off-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-2-sourabhjain@linux.ibm.com --- arch/x86/include/asm/kexec.h | 2 +- arch/x86/kernel/crash.c | 4 +++- include/linux/crash_core.h | 2 +- kernel/crash_core.c | 14 +++++++------- 4 files changed, 12 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 91ca9a9ee3a2b..cb1320ebbc235 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -207,7 +207,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image); extern void kdump_nmi_shootdown_cpus(void); #ifdef CONFIG_CRASH_HOTPLUG -void arch_crash_handle_hotplug_event(struct kimage *image); +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e74d0c4286c14..2a682fe863528 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -432,10 +432,12 @@ unsigned int arch_crash_get_elfcorehdr_size(void) /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image + * @arg: struct memory_notify handler for memory hotplug case and + * NULL for CPU hotplug case. * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ -void arch_crash_handle_hotplug_event(struct kimage *image) +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index d33352c2e3865..647e928efee82 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -37,7 +37,7 @@ static inline void arch_kexec_unprotect_crashkres(void) { } #ifndef arch_crash_handle_hotplug_event -static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } +static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { } #endif int crash_check_update_elfcorehdr(void); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 78b5dc7cee3ab..70fa8111a9d6f 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -534,7 +534,7 @@ int crash_check_update_elfcorehdr(void) * list of segments it checks (since the elfcorehdr changes and thus * would require an update to purgatory itself to update the digest). */ -static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) +static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, void *arg) { struct kimage *image; @@ -596,7 +596,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) image->hp_action = hp_action; /* Now invoke arch-specific update handler */ - arch_crash_handle_hotplug_event(image); + arch_crash_handle_hotplug_event(image, arg); /* No longer handling a hotplug event */ image->hp_action = KEXEC_CRASH_HP_NONE; @@ -612,17 +612,17 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) crash_hotplug_unlock(); } -static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v) +static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *arg) { switch (val) { case MEM_ONLINE: crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY, - KEXEC_CRASH_HP_INVALID_CPU); + KEXEC_CRASH_HP_INVALID_CPU, arg); break; case MEM_OFFLINE: crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY, - KEXEC_CRASH_HP_INVALID_CPU); + KEXEC_CRASH_HP_INVALID_CPU, arg); break; } return NOTIFY_OK; @@ -635,13 +635,13 @@ static struct notifier_block crash_memhp_nb = { static int crash_cpuhp_online(unsigned int cpu) { - crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu); + crash_handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu, NULL); return 0; } static int crash_cpuhp_offline(unsigned int cpu) { - crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu); + crash_handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu, NULL); return 0; } From 79365026f86948b52c3cb7bf099dded92c559b4c Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:09 +0530 Subject: [PATCH 2/7] crash: add a new kexec flag for hotplug support Commit a72bbec70da2 ("crash: hotplug support for kexec_load()") introduced a new kexec flag, `KEXEC_UPDATE_ELFCOREHDR`. Kexec tool uses this flag to indicate to the kernel that it is safe to modify the elfcorehdr of the kdump image loaded using the kexec_load system call. However, it is possible that architectures may need to update kexec segments other then elfcorehdr. For example, FDT (Flatten Device Tree) on PowerPC. Introducing a new kexec flag for every new kexec segment may not be a good solution. Hence, a generic kexec flag bit, `KEXEC_CRASH_HOTPLUG_SUPPORT`, is introduced to share the CPU/Memory hotplug support intent between the kexec tool and the kernel for the kexec_load system call. Now we have two kexec flags that enables crash hotplug support for kexec_load system call. First is KEXEC_UPDATE_ELFCOREHDR (only used in x86), and second is KEXEC_CRASH_HOTPLUG_SUPPORT (for all architectures). To simplify the process of finding and reporting the crash hotplug support the following changes are introduced. 1. Define arch specific function to process the kexec flags and determine crash hotplug support 2. Rename the @update_elfcorehdr member of struct kimage to @hotplug_support and populate it for both kexec_load and kexec_file_load syscalls, because architecture can update more than one kexec segment 3. Let generic function crash_check_hotplug_support report hotplug support for loaded kdump image based on value of @hotplug_support To bring the x86 crash hotplug support in line with the above points, the following changes have been made: - Introduce the arch_crash_hotplug_support function to process kexec flags and determine crash hotplug support - Remove the arch_crash_hotplug_[cpu|memory]_support functions Signed-off-by: Sourabh Jain Acked-by: Baoquan He Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-3-sourabhjain@linux.ibm.com --- arch/x86/include/asm/kexec.h | 11 ++--------- arch/x86/kernel/crash.c | 28 +++++++++++++++++----------- drivers/base/cpu.c | 2 +- drivers/base/memory.c | 2 +- include/linux/crash_core.h | 13 ++++++------- include/linux/kexec.h | 11 +++++++---- include/uapi/linux/kexec.h | 1 + kernel/crash_core.c | 15 ++++++--------- kernel/kexec.c | 4 ++-- kernel/kexec_file.c | 5 +++++ 10 files changed, 48 insertions(+), 44 deletions(-) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index cb1320ebbc235..ae5482a2f0ca0 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -210,15 +210,8 @@ extern void kdump_nmi_shootdown_cpus(void); void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); #define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void); -#define crash_hotplug_cpu_support arch_crash_hotplug_cpu_support -#endif - -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void); -#define crash_hotplug_memory_support arch_crash_hotplug_memory_support -#endif +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support unsigned int arch_crash_get_elfcorehdr_size(void); #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2a682fe863528..f06501445cd98 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -402,20 +402,26 @@ int crash_load_segments(struct kimage *image) #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt -/* These functions provide the value for the sysfs crash_hotplug nodes */ -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void) +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { - return crash_check_update_elfcorehdr(); -} -#endif -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void) -{ - return crash_check_update_elfcorehdr(); -} +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; #endif + /* + * Initially, crash hotplug support for kexec_load was added + * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this + * functionality was expanded to accommodate multiple kexec + * segment updates, leading to the introduction of the + * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, + * when the kexec tool sends either of these flags, it indicates + * that the required kexec segment (elfcorehdr) is excluded from + * the SHA calculation. + */ + return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || + kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); +} unsigned int arch_crash_get_elfcorehdr_size(void) { diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 56fba44ba391a..c61ecb0c2ae29 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -306,7 +306,7 @@ static ssize_t crash_hotplug_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", crash_hotplug_cpu_support()); + return sysfs_emit(buf, "%d\n", crash_check_hotplug_support()); } static DEVICE_ATTR_ADMIN_RO(crash_hotplug); #endif diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c0436f46cfb70..67858eeb92ed2 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -535,7 +535,7 @@ static DEVICE_ATTR_RW(auto_online_blocks); static ssize_t crash_hotplug_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", crash_hotplug_memory_support()); + return sysfs_emit(buf, "%d\n", crash_check_hotplug_support()); } static DEVICE_ATTR_RO(crash_hotplug); #endif diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 647e928efee82..44305336314eb 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -40,14 +40,13 @@ static inline void arch_kexec_unprotect_crashkres(void) { } static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { } #endif -int crash_check_update_elfcorehdr(void); +int crash_check_hotplug_support(void); -#ifndef crash_hotplug_cpu_support -static inline int crash_hotplug_cpu_support(void) { return 0; } -#endif - -#ifndef crash_hotplug_memory_support -static inline int crash_hotplug_memory_support(void) { return 0; } +#ifndef arch_crash_hotplug_support +static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ + return 0; +} #endif #ifndef crash_get_elfcorehdr_size diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 060835bb82d52..5b93a5767413a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -319,8 +319,10 @@ struct kimage { /* If set, we are using file mode kexec syscall */ unsigned int file_mode:1; #ifdef CONFIG_CRASH_HOTPLUG - /* If set, allow changes to elfcorehdr of kexec_load'd image */ - unsigned int update_elfcorehdr:1; + /* If set, it is safe to update kexec segments that are + * excluded from SHA calculation. + */ + unsigned int hotplug_support:1; #endif #ifdef ARCH_HAS_KIMAGE_ARCH @@ -391,9 +393,10 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec flags */ #ifndef CONFIG_KEXEC_JUMP -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR | KEXEC_CRASH_HOTPLUG_SUPPORT) #else -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR | \ + KEXEC_CRASH_HOTPLUG_SUPPORT) #endif /* List of defined/legal kexec file flags */ diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index c17bb096ea685..5ae1741ea8ea0 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -13,6 +13,7 @@ #define KEXEC_ON_CRASH 0x00000001 #define KEXEC_PRESERVE_CONTEXT 0x00000002 #define KEXEC_UPDATE_ELFCOREHDR 0x00000004 +#define KEXEC_CRASH_HOTPLUG_SUPPORT 0x00000008 #define KEXEC_ARCH_MASK 0xffff0000 /* diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 70fa8111a9d6f..394db3ebe8353 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -493,10 +493,10 @@ static DEFINE_MUTEX(__crash_hotplug_lock); /* * This routine utilized when the crash_hotplug sysfs node is read. - * It reflects the kernel's ability/permission to update the crash - * elfcorehdr directly. + * It reflects the kernel's ability/permission to update the kdump + * image directly. */ -int crash_check_update_elfcorehdr(void) +int crash_check_hotplug_support(void) { int rc = 0; @@ -508,10 +508,7 @@ int crash_check_update_elfcorehdr(void) return 0; } if (kexec_crash_image) { - if (kexec_crash_image->file_mode) - rc = 1; - else - rc = kexec_crash_image->update_elfcorehdr; + rc = kexec_crash_image->hotplug_support; } /* Release lock now that update complete */ kexec_unlock(); @@ -552,8 +549,8 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu, image = kexec_crash_image; - /* Check that updating elfcorehdr is permitted */ - if (!(image->file_mode || image->update_elfcorehdr)) + /* Check that kexec segments update is permitted */ + if (!image->hotplug_support) goto out; if (hp_action == KEXEC_CRASH_HP_ADD_CPU || diff --git a/kernel/kexec.c b/kernel/kexec.c index bab542fc1463d..a6b3f96bb50c8 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -135,8 +135,8 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, image->preserve_context = 1; #ifdef CONFIG_CRASH_HOTPLUG - if (flags & KEXEC_UPDATE_ELFCOREHDR) - image->update_elfcorehdr = 1; + if ((flags & KEXEC_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; #endif ret = machine_kexec_prepare(image); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 2d1db05fbf04f..3d64290d24c9a 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -376,6 +376,11 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; +#ifdef CONFIG_CRASH_HOTPLUG + if ((flags & KEXEC_FILE_ON_CRASH) && arch_crash_hotplug_support(image, flags)) + image->hotplug_support = 1; +#endif + ret = machine_kexec_prepare(image); if (ret) goto out; From f5f0da5a7b18fab383bac92044fd8f4f288c9d38 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:10 +0530 Subject: [PATCH 3/7] powerpc/kexec: move *_memory_ranges functions to ranges.c Move the following functions form kexec/{file_load_64.c => ranges.c} and make them public so that components other than KEXEC_FILE can also use these functions. 1. get_exclude_memory_ranges 2. get_reserved_memory_ranges 3. get_crash_memory_ranges 4. get_usable_memory_ranges Later in the series get_crash_memory_ranges function is utilized for in-kernel updates to kdump image during CPU/Memory hotplug or online/offline events for both kexec_load and kexec_file_load syscalls. Since the above functions are moved to ranges.c, some of the helper functions in ranges.c are no longer required to be public. Mark them as static and removed them from kexec_ranges.h header file. Finally, remove the CONFIG_KEXEC_FILE build dependency for range.c because it is required for other config, such as CONFIG_CRASH_DUMP. No functional changes are intended. Signed-off-by: Sourabh Jain Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-4-sourabhjain@linux.ibm.com --- arch/powerpc/include/asm/kexec_ranges.h | 19 +- arch/powerpc/kexec/Makefile | 4 +- arch/powerpc/kexec/file_load_64.c | 190 -------------------- arch/powerpc/kexec/ranges.c | 227 +++++++++++++++++++++++- 4 files changed, 224 insertions(+), 216 deletions(-) diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index f83866a19e870..8489e844b4475 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -7,19 +7,8 @@ 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 add_tce_mem_ranges(struct crash_mem **mem_ranges); -int add_initrd_mem_range(struct crash_mem **mem_ranges); -#ifdef CONFIG_PPC_64S_HASH_MMU -int add_htab_mem_range(struct crash_mem **mem_ranges); -#else -static inline int add_htab_mem_range(struct crash_mem **mem_ranges) -{ - return 0; -} -#endif -int add_kernel_mem_range(struct crash_mem **mem_ranges); -int add_rtas_mem_range(struct crash_mem **mem_ranges); -int add_opal_mem_range(struct crash_mem **mem_ranges); -int add_reserved_mem_ranges(struct crash_mem **mem_ranges); - +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); +int get_usable_memory_ranges(struct crash_mem **mem_ranges); #endif /* _ASM_POWERPC_KEXEC_RANGES_H */ diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile index 8e469c4da3f88..470eb0453e17f 100644 --- a/arch/powerpc/kexec/Makefile +++ b/arch/powerpc/kexec/Makefile @@ -3,11 +3,11 @@ # Makefile for the linux kernel. # -obj-y += core.o core_$(BITS).o +obj-y += core.o core_$(BITS).o ranges.o obj-$(CONFIG_PPC32) += relocate_32.o -obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o +obj-$(CONFIG_KEXEC_FILE) += file_load.o file_load_$(BITS).o elf_$(BITS).o obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_CRASH_DUMP) += crash.o diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 1bc65de6174f3..6a01f62b8fcfc 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -47,83 +47,6 @@ const struct kexec_file_ops * const kexec_file_loaders[] = { NULL }; -/** - * get_exclude_memory_ranges - Get exclude memory ranges. This list includes - * regions like opal/rtas, tce-table, initrd, - * kernel, htab which should be avoided while - * setting up kexec load segments. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_exclude_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - ret = add_tce_mem_ranges(mem_ranges); - if (ret) - goto out; - - ret = add_initrd_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_htab_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_kernel_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_reserved_mem_ranges(mem_ranges); - if (ret) - goto out; - - /* exclude memory ranges should be sorted for easy lookup */ - sort_memory_ranges(*mem_ranges, true); -out: - if (ret) - pr_err("Failed to setup exclude memory ranges\n"); - return ret; -} - -/** - * get_reserved_memory_ranges - Get reserve memory ranges. This list includes - * memory regions that should be added to the - * memory reserve map to ensure the region is - * protected from any mischief. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_reserved_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_tce_mem_ranges(mem_ranges); - if (ret) - goto out; - - ret = add_reserved_mem_ranges(mem_ranges); -out: - if (ret) - pr_err("Failed to setup reserved memory ranges\n"); - return ret; -} - /** * __locate_mem_hole_top_down - Looks top down for a large enough memory hole * in the memory regions between buf_min & buf_max @@ -322,119 +245,6 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf, } #ifdef CONFIG_CRASH_DUMP -/** - * get_usable_memory_ranges - Get usable memory ranges. This list includes - * regions like crashkernel, opal/rtas & tce-table, - * that kdump kernel could use. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_usable_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - /* - * Early boot failure observed on guests when low memory (first memory - * block?) is not added to usable memory. So, add [0, crashk_res.end] - * instead of [crashk_res.start, crashk_res.end] to workaround it. - * Also, crashed kernel's memory must be added to reserve map to - * avoid kdump kernel from using it. - */ - ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); - if (ret) - goto out; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_tce_mem_ranges(mem_ranges); -out: - if (ret) - pr_err("Failed to setup usable memory ranges\n"); - return ret; -} - -/** - * get_crash_memory_ranges - Get crash memory ranges. This list includes - * first/crashing kernel's memory regions that - * would be exported via an elfcore. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_crash_memory_ranges(struct crash_mem **mem_ranges) -{ - phys_addr_t base, end; - struct crash_mem *tmem; - u64 i; - int ret; - - for_each_mem_range(i, &base, &end) { - u64 size = end - base; - - /* Skip backup memory region, which needs a separate entry */ - if (base == BACKUP_SRC_START) { - if (size > BACKUP_SRC_SIZE) { - base = BACKUP_SRC_END + 1; - size -= BACKUP_SRC_SIZE; - } else - continue; - } - - ret = add_mem_range(mem_ranges, base, size); - if (ret) - goto out; - - /* Try merging adjacent ranges before reallocation attempt */ - if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) - sort_memory_ranges(*mem_ranges, true); - } - - /* Reallocate memory ranges if there is no space to split ranges */ - tmem = *mem_ranges; - if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { - tmem = realloc_mem_ranges(mem_ranges); - if (!tmem) - goto out; - } - - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.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 - * crash, they should actually be backed up just like the - * first 64K bytes of memory. - */ - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - /* create a separate program header for the backup region */ - ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); - if (ret) - goto out; - - sort_memory_ranges(*mem_ranges, false); -out: - if (ret) - pr_err("Failed to setup crash memory ranges\n"); - return ret; -} - /** * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries * @um_info: Usable memory buffer and ranges info. diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 33b780049aaf9..b1f4267d9b171 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -20,9 +20,13 @@ #include #include #include +#include +#include #include #include +#include +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) /** * get_max_nr_ranges - Get the max no. of ranges crash_mem structure * could hold, given the size allocated for it. @@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) return __add_mem_range(mem_ranges, base, size); } +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ + +#ifdef CONFIG_KEXEC_FILE /** * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list. * @mem_ranges: Range list to add the memory range(s) to. * * Returns 0 on success, negative errno on error. */ -int add_tce_mem_ranges(struct crash_mem **mem_ranges) +static int add_tce_mem_ranges(struct crash_mem **mem_ranges) { struct device_node *dn = NULL; int ret = 0; @@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_initrd_mem_range(struct crash_mem **mem_ranges) +static int add_initrd_mem_range(struct crash_mem **mem_ranges) { u64 base, end; int ret; @@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges) return ret; } -#ifdef CONFIG_PPC_64S_HASH_MMU /** * add_htab_mem_range - Adds htab range to the given memory ranges list, * if it exists @@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_htab_mem_range(struct crash_mem **mem_ranges) +static int add_htab_mem_range(struct crash_mem **mem_ranges) { + +#ifdef CONFIG_PPC_64S_HASH_MMU if (!htab_address) return 0; return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes); -} +#else + return 0; #endif +} /** * add_kernel_mem_range - Adds kernel text region to the given @@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_kernel_mem_range(struct crash_mem **mem_ranges) +static int add_kernel_mem_range(struct crash_mem **mem_ranges) { return add_mem_range(mem_ranges, 0, __pa(_end)); } +#endif /* CONFIG_KEXEC_FILE */ +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) /** * add_rtas_mem_range - Adds RTAS region to the given memory ranges list. * @mem_ranges: Range list to add the memory range to. * * Returns 0 on success, negative errno on error. */ -int add_rtas_mem_range(struct crash_mem **mem_ranges) +static int add_rtas_mem_range(struct crash_mem **mem_ranges) { struct device_node *dn; u32 base, size; @@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_opal_mem_range(struct crash_mem **mem_ranges) +static int add_opal_mem_range(struct crash_mem **mem_ranges) { struct device_node *dn; u64 base, size; @@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges) of_node_put(dn); return ret; } +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ +#ifdef CONFIG_KEXEC_FILE /** * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w * to the given memory ranges list. @@ -382,7 +396,7 @@ int add_opal_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_reserved_mem_ranges(struct crash_mem **mem_ranges) +static int add_reserved_mem_ranges(struct crash_mem **mem_ranges) { int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0; struct device_node *root = of_find_node_by_path("/"); @@ -412,3 +426,198 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges) return ret; } + +/** + * get_reserved_memory_ranges - Get reserve memory ranges. This list includes + * memory regions that should be added to the + * memory reserve map to ensure the region is + * protected from any mischief. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_reserved_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup reserved memory ranges\n"); + return ret; +} + +/** + * get_exclude_memory_ranges - Get exclude memory ranges. This list includes + * regions like opal/rtas, tce-table, initrd, + * kernel, htab which should be avoided while + * setting up kexec load segments. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_exclude_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_initrd_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_htab_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_kernel_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); + if (ret) + goto out; + + /* exclude memory ranges should be sorted for easy lookup */ + sort_memory_ranges(*mem_ranges, true); +out: + if (ret) + pr_err("Failed to setup exclude memory ranges\n"); + return ret; +} + +#ifdef CONFIG_CRASH_DUMP +/** + * get_usable_memory_ranges - Get usable memory ranges. This list includes + * regions like crashkernel, opal/rtas & tce-table, + * that kdump kernel could use. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_usable_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + /* + * Early boot failure observed on guests when low memory (first memory + * block?) is not added to usable memory. So, add [0, crashk_res.end] + * instead of [crashk_res.start, crashk_res.end] to workaround it. + * Also, crashed kernel's memory must be added to reserve map to + * avoid kdump kernel from using it. + */ + ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup usable memory ranges\n"); + return ret; +} +#endif /* CONFIG_CRASH_DUMP */ +#endif /* CONFIG_KEXEC_FILE */ + +#ifdef CONFIG_CRASH_DUMP +/** + * get_crash_memory_ranges - Get crash memory ranges. This list includes + * first/crashing kernel's memory regions that + * would be exported via an elfcore. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_crash_memory_ranges(struct crash_mem **mem_ranges) +{ + phys_addr_t base, end; + struct crash_mem *tmem; + u64 i; + int ret; + + for_each_mem_range(i, &base, &end) { + u64 size = end - base; + + /* Skip backup memory region, which needs a separate entry */ + if (base == BACKUP_SRC_START) { + if (size > BACKUP_SRC_SIZE) { + base = BACKUP_SRC_END + 1; + size -= BACKUP_SRC_SIZE; + } else + continue; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + goto out; + + /* Try merging adjacent ranges before reallocation attempt */ + if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) + sort_memory_ranges(*mem_ranges, true); + } + + /* Reallocate memory ranges if there is no space to split ranges */ + tmem = *mem_ranges; + if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { + tmem = realloc_mem_ranges(mem_ranges); + if (!tmem) + goto out; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.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 + * crash, they should actually be backed up just like the + * first 64K bytes of memory. + */ + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + /* create a separate program header for the backup region */ + ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); + if (ret) + goto out; + + sort_memory_ranges(*mem_ranges, false); +out: + if (ret) + pr_err("Failed to setup crash memory ranges\n"); + return ret; +} +#endif /* CONFIG_CRASH_DUMP */ From 0857beff9c1ec8bb421a8b7a721da0f34cc886c0 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:11 +0530 Subject: [PATCH 4/7] powerpc/kexec: make the update_cpus_node() function public Move the update_cpus_node() from kexec/{file_load_64.c => core_64.c} to allow other kexec components to use it. Later in the series, this function is used for in-kernel updates to the kdump image during CPU/memory hotplug or online/offline events for both kexec_load and kexec_file_load syscalls. No functional changes are intended. Signed-off-by: Sourabh Jain Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-5-sourabhjain@linux.ibm.com --- arch/powerpc/include/asm/kexec.h | 4 ++ arch/powerpc/kexec/core_64.c | 91 +++++++++++++++++++++++++++++++ arch/powerpc/kexec/file_load_64.c | 87 ----------------------------- 3 files changed, 95 insertions(+), 87 deletions(-) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index fdb90e24dc74d..d9ff4d0e392dc 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -185,6 +185,10 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) #endif /* CONFIG_CRASH_DUMP */ +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +int update_cpus_node(void *fdt); +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #include #endif diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 762e4d09aacfa..85050be08a23d 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -30,6 +31,7 @@ #include #include #include +#include int machine_kexec_prepare(struct kimage *image) { @@ -419,3 +421,92 @@ static int __init export_htab_values(void) } late_initcall(export_htab_values); #endif /* CONFIG_PPC_64S_HASH_MMU */ + +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +/** + * add_node_props - Reads node properties from device node structure and add + * them to fdt. + * @fdt: Flattened device tree of the kernel + * @node_offset: offset of the node to add a property at + * @dn: device node pointer + * + * Returns 0 on success, negative errno on error. + */ +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) +{ + int ret = 0; + struct property *pp; + + if (!dn) + return -EINVAL; + + for_each_property_of_node(dn, pp) { + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); + if (ret < 0) { + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); + return ret; + } + } + return ret; +} + +/** + * update_cpus_node - Update cpus node of flattened device tree using of_root + * device node. + * @fdt: Flattened device tree of the kernel. + * + * Returns 0 on success, negative errno on error. + */ +int update_cpus_node(void *fdt) +{ + struct device_node *cpus_node, *dn; + int cpus_offset, cpus_subnode_offset, ret = 0; + + cpus_offset = fdt_path_offset(fdt, "/cpus"); + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { + pr_err("Malformed device tree: error reading /cpus node: %s\n", + fdt_strerror(cpus_offset)); + return cpus_offset; + } + + if (cpus_offset > 0) { + ret = fdt_del_node(fdt, cpus_offset); + if (ret < 0) { + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); + return -EINVAL; + } + } + + /* Add cpus node to fdt */ + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); + if (cpus_offset < 0) { + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); + return -EINVAL; + } + + /* Add cpus node properties */ + cpus_node = of_find_node_by_path("/cpus"); + ret = add_node_props(fdt, cpus_offset, cpus_node); + of_node_put(cpus_node); + if (ret < 0) + return ret; + + /* Loop through all subnodes of cpus and add them to fdt */ + for_each_node_by_type(dn, "cpu") { + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); + if (cpus_subnode_offset < 0) { + pr_err("Unable to add %s subnode: %s\n", dn->full_name, + fdt_strerror(cpus_subnode_offset)); + ret = cpus_subnode_offset; + goto out; + } + + ret = add_node_props(fdt, cpus_subnode_offset, dn); + if (ret < 0) + goto out; + } +out: + of_node_put(dn); + return ret; +} +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 6a01f62b8fcfc..4b94c31e31728 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -838,93 +838,6 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) return extra_size + kdump_extra_fdt_size_ppc64(image); } -/** - * add_node_props - Reads node properties from device node structure and add - * them to fdt. - * @fdt: Flattened device tree of the kernel - * @node_offset: offset of the node to add a property at - * @dn: device node pointer - * - * Returns 0 on success, negative errno on error. - */ -static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) -{ - int ret = 0; - struct property *pp; - - if (!dn) - return -EINVAL; - - for_each_property_of_node(dn, pp) { - ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); - if (ret < 0) { - pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); - return ret; - } - } - return ret; -} - -/** - * update_cpus_node - Update cpus node of flattened device tree using of_root - * device node. - * @fdt: Flattened device tree of the kernel. - * - * Returns 0 on success, negative errno on error. - */ -static int update_cpus_node(void *fdt) -{ - struct device_node *cpus_node, *dn; - int cpus_offset, cpus_subnode_offset, ret = 0; - - cpus_offset = fdt_path_offset(fdt, "/cpus"); - if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { - pr_err("Malformed device tree: error reading /cpus node: %s\n", - fdt_strerror(cpus_offset)); - return cpus_offset; - } - - if (cpus_offset > 0) { - ret = fdt_del_node(fdt, cpus_offset); - if (ret < 0) { - pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); - return -EINVAL; - } - } - - /* Add cpus node to fdt */ - cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); - if (cpus_offset < 0) { - pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); - return -EINVAL; - } - - /* Add cpus node properties */ - cpus_node = of_find_node_by_path("/cpus"); - ret = add_node_props(fdt, cpus_offset, cpus_node); - of_node_put(cpus_node); - if (ret < 0) - return ret; - - /* Loop through all subnodes of cpus and add them to fdt */ - for_each_node_by_type(dn, "cpu") { - cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); - if (cpus_subnode_offset < 0) { - pr_err("Unable to add %s subnode: %s\n", dn->full_name, - fdt_strerror(cpus_subnode_offset)); - ret = cpus_subnode_offset; - goto out; - } - - ret = add_node_props(fdt, cpus_subnode_offset, dn); - if (ret < 0) - goto out; - } -out: - of_node_put(dn); - return ret; -} - static int copy_property(void *fdt, int node_offset, const struct device_node *dn, const char *propname) { From b741092d59761b98781fcb4f3f521312ed8d5006 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:12 +0530 Subject: [PATCH 5/7] powerpc/crash: add crash CPU hotplug support Due to CPU/Memory hotplug or online/offline events, the elfcorehdr (which describes the CPUs and memory of the crashed kernel) and FDT (Flattened Device Tree) of kdump image becomes outdated. Consequently, attempting dump collection with an outdated elfcorehdr or FDT can lead to failed or inaccurate dump collection. Going forward, CPU hotplug or online/offline events are referred as CPU/Memory add/remove events. The current solution to address the above issue involves monitoring the CPU/Memory add/remove events in userspace using udev rules and whenever there are changes in CPU and memory resources, the entire kdump image is loaded again. The kdump image includes kernel, initrd, elfcorehdr, FDT, purgatory. Given that only elfcorehdr and FDT get outdated due to CPU/Memory add/remove events, reloading the entire kdump image is inefficient. More importantly, kdump remains inactive for a substantial amount of time until the kdump reload completes. To address the aforementioned issue, commit 247262756121 ("crash: add generic infrastructure for crash hotplug support") added a generic infrastructure that allows architectures to selectively update the kdump image component during CPU or memory add/remove events within the kernel itself. In the event of a CPU or memory add/remove events, the generic crash hotplug event handler, `crash_handle_hotplug_event()`, is triggered. It then acquires the necessary locks to update the kdump image and invokes the architecture-specific crash hotplug handler, `arch_crash_handle_hotplug_event()`, to update the required kdump image components. This patch adds crash hotplug handler for PowerPC and enable support to update the kdump image on CPU add/remove events. Support for memory add/remove events is added in a subsequent patch with the title "powerpc: add crash memory hotplug support" As mentioned earlier, only the elfcorehdr and FDT kdump image components need to be updated in the event of CPU or memory add/remove events. However, on PowerPC architecture crash hotplug handler only updates the FDT to enable crash hotplug support for CPU add/remove events. Here's why. The elfcorehdr on PowerPC is built with possible CPUs, and thus, it does not need an update on CPU add/remove events. On the other hand, the FDT needs to be updated on CPU add events to include the newly added CPU. If the FDT is not updated and the kernel crashes on a newly added CPU, the kdump kernel will fail to boot due to the unavailability of the crashing CPU in the FDT. During the early boot, it is expected that the boot CPU must be a part of the FDT; otherwise, the kernel will raise a BUG and fail to boot. For more information, refer to commit 36ae37e3436b0 ("powerpc: Make boot_cpuid common between 32 and 64-bit"). Since it is okay to have an offline CPU in the kdump FDT, no action is taken in case of CPU removal. There are two system calls, `kexec_file_load` and `kexec_load`, used to load the kdump image. Few changes have been made to ensure kernel can safely update the FDT of kdump image loaded using both system calls. For kexec_file_load syscall the kdump image is prepared in kernel. So to support an increasing number of CPUs, the FDT is constructed with extra buffer space to ensure it can accommodate a possible number of CPU nodes. Additionally, a call to fdt_pack (which trims the unused space once the FDT is prepared) is avoided if this feature is enabled. For the kexec_load syscall, the FDT is updated only if the KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag is passed to the kernel by userspace (kexec tools). When userspace passes this flag to the kernel, it indicates that the FDT is built to accommodate possible CPUs, and the FDT segment is excluded from SHA calculation, making it safe to update. The changes related to this feature are kept under the CRASH_HOTPLUG config, and it is enabled by default. Signed-off-by: Sourabh Jain Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-6-sourabhjain@linux.ibm.com --- arch/powerpc/Kconfig | 4 ++ arch/powerpc/include/asm/kexec.h | 8 +++ arch/powerpc/kexec/crash.c | 103 ++++++++++++++++++++++++++++++ arch/powerpc/kexec/elf_64.c | 3 +- arch/powerpc/kexec/file_load_64.c | 17 +++++ 5 files changed, 134 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1c4be33736860..a1a3b33630080 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -686,6 +686,10 @@ config ARCH_SELECTS_CRASH_DUMP depends on CRASH_DUMP select RELOCATABLE if PPC64 || 44x || PPC_85xx +config ARCH_SUPPORTS_CRASH_HOTPLUG + def_bool y + depends on PPC64 + config FA_DUMP bool "Firmware-assisted dump" depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index d9ff4d0e392dc..e75970351bcd2 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -135,6 +135,14 @@ static inline void crash_setup_regs(struct pt_regs *newregs, ppc_save_regs(newregs); } +#ifdef CONFIG_CRASH_HOTPLUG +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); +#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support +#endif /* CONFIG_CRASH_HOTPLUG */ + 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 ef5c2d25ec397..8938a19af12fd 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -392,3 +393,105 @@ void default_machine_crash_shutdown(struct pt_regs *regs) if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); } + +#ifdef CONFIG_CRASH_HOTPLUG +#undef pr_fmt +#define pr_fmt(fmt) "crash hp: " fmt + +/** + * get_fdt_index - Loop through the kexec segment array and find + * the index of the FDT segment. + * @image: a pointer to kexec_crash_image + * + * Returns the index of FDT segment in the kexec segment array + * if found; otherwise -1. + */ +static int get_fdt_index(struct kimage *image) +{ + void *ptr; + unsigned long mem; + int i, fdt_index = -1; + + /* Find the FDT segment index in kexec segment array. */ + for (i = 0; i < image->nr_segments; i++) { + mem = image->segment[i].mem; + ptr = __va(mem); + + if (ptr && fdt_magic(ptr) == FDT_MAGIC) { + fdt_index = i; + break; + } + } + + return fdt_index; +} + +/** + * update_crash_fdt - updates the cpus node of the crash FDT. + * + * @image: a pointer to kexec_crash_image + */ +static void update_crash_fdt(struct kimage *image) +{ + void *fdt; + int fdt_index; + + fdt_index = get_fdt_index(image); + if (fdt_index < 0) { + pr_err("Unable to locate FDT segment.\n"); + return; + } + + fdt = __va((void *)image->segment[fdt_index].mem); + + /* Temporarily invalidate the crash image while it is replaced */ + xchg(&kexec_crash_image, NULL); + + /* update FDT to reflect changes in CPU resources */ + if (update_cpus_node(fdt)) + pr_err("Failed to update crash FDT"); + + /* The crash image is now valid once again */ + xchg(&kexec_crash_image, image); +} + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; +#endif + return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT; +} + +/** + * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the + * necessary kexec segments based on the hotplug event. + * @image: a pointer to kexec_crash_image + * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case. + * + * Update the kdump image based on the type of hotplug event, represented by image->hp_action. + * CPU add: Update the FDT segment to include the newly added CPU. + * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs + * part of the FDT. + * Memory add/remove: No action is taken as this is not yet supported. + */ +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) +{ + switch (image->hp_action) { + case KEXEC_CRASH_HP_REMOVE_CPU: + return; + + case KEXEC_CRASH_HP_ADD_CPU: + update_crash_fdt(image); + break; + + case KEXEC_CRASH_HP_REMOVE_MEMORY: + case KEXEC_CRASH_HP_ADD_MEMORY: + pr_info_once("Crash update is not supported for memory hotplug\n"); + return; + default: + pr_warn_once("Unknown hotplug action\n"); + } +} +#endif /* CONFIG_CRASH_HOTPLUG */ diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c index 6d8951e8e9666..214c071c58edf 100644 --- a/arch/powerpc/kexec/elf_64.c +++ b/arch/powerpc/kexec/elf_64.c @@ -116,7 +116,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, if (ret) goto out_free_fdt; - fdt_pack(fdt); + if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH) + fdt_pack(fdt); kbuf.buffer = fdt; kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 4b94c31e31728..2640a804fcdfe 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -30,6 +30,7 @@ #include #include #include +#include struct umem_info { __be64 *buf; /* data buffer for usable-memory property */ @@ -789,6 +790,9 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image) unsigned int cpu_nodes, extra_size = 0; struct device_node *dn; u64 usm_entries; +#ifdef CONFIG_CRASH_HOTPLUG + unsigned int possible_cpu_nodes; +#endif if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH) return 0; @@ -816,6 +820,19 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image) if (cpu_nodes > boot_cpu_node_count) extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size(); +#ifdef CONFIG_CRASH_HOTPLUG + /* + * Make sure enough space is reserved to accommodate possible CPU nodes + * in the crash FDT. This allows packing possible CPU nodes which are + * not yet present in the system without regenerating the entire FDT. + */ + if (image->type == KEXEC_TYPE_CRASH) { + possible_cpu_nodes = num_possible_cpus() / threads_per_core; + if (possible_cpu_nodes > cpu_nodes) + extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size(); + } +#endif + return extra_size; } From 849599b702ef8977fcd5b2f27c61ef773c42bb88 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 26 Mar 2024 11:24:13 +0530 Subject: [PATCH 6/7] powerpc/crash: add crash memory hotplug support Extend the arch crash hotplug handler, as introduced by the patch title ("powerpc: add crash CPU hotplug support"), to also support memory add/remove events. Elfcorehdr describes the memory of the crash kernel to capture the kernel; hence, it needs to be updated if memory resources change due to memory add/remove events. Therefore, arch_crash_handle_hotplug_event() is updated to recreate the elfcorehdr and replace it with the previous one on memory add/remove events. The memblock list is used to prepare the elfcorehdr. In the case of memory hot remove, the memblock list is updated after the arch crash hotplug handler is triggered, as depicted in Figure 1. Thus, the hot-removed memory is explicitly removed from the crash memory ranges to ensure that the memory ranges added to elfcorehdr do not include the hot-removed memory. Memory remove | v Offline pages | v Initiate memory notify call <----> crash hotplug handler chain for MEM_OFFLINE event | v Update memblock list Figure 1 There are two system calls, `kexec_file_load` and `kexec_load`, used to load the kdump image. A few changes have been made to ensure that the kernel can safely update the elfcorehdr component of the kdump image for both system calls. For the kexec_file_load syscall, kdump image is prepared in the kernel. To support an increasing number of memory regions, the elfcorehdr is built with extra buffer space to ensure that it can accommodate additional memory ranges in future. For the kexec_load syscall, the elfcorehdr is updated only if the KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag is passed to the kernel by the kexec tool. Passing this flag to the kernel indicates that the elfcorehdr is built to accommodate additional memory ranges and the elfcorehdr segment is not considered for SHA calculation, making it safe to update. The changes related to this feature are kept under the CRASH_HOTPLUG config, and it is enabled by default. Signed-off-by: Sourabh Jain Acked-by: Hari Bathini Signed-off-by: Michael Ellerman Link: https://msgid.link/20240326055413.186534-7-sourabhjain@linux.ibm.com --- arch/powerpc/include/asm/kexec.h | 3 + arch/powerpc/include/asm/kexec_ranges.h | 1 + arch/powerpc/kexec/crash.c | 95 ++++++++++++++++++++++++- arch/powerpc/kexec/file_load_64.c | 20 +++++- arch/powerpc/kexec/ranges.c | 85 ++++++++++++++++++++++ 5 files changed, 202 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index e75970351bcd2..95a98b390d62d 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -141,6 +141,9 @@ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); #define arch_crash_hotplug_support arch_crash_hotplug_support + +unsigned int arch_crash_get_elfcorehdr_size(void); +#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size #endif /* CONFIG_CRASH_HOTPLUG */ extern int crashing_cpu; diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index 8489e844b4475..14055896cbcbc 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -7,6 +7,7 @@ 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 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 8938a19af12fd..21b193e938a37 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -25,6 +26,7 @@ #include #include #include +#include /* * The primary CPU waits a while for all secondary CPUs to enter. This is to @@ -398,6 +400,94 @@ void default_machine_crash_shutdown(struct pt_regs *regs) #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt +/* + * Advertise preferred elfcorehdr size to userspace via + * /sys/kernel/crash_elfcorehdr_size sysfs interface. + */ +unsigned int arch_crash_get_elfcorehdr_size(void) +{ + unsigned long phdr_cnt; + + /* A program header for possible CPUs + vmcoreinfo */ + phdr_cnt = num_possible_cpus() + 1; + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES; + + 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 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; + } + + /* + * The hot unplugged memory is part of crash memory ranges, + * remove it here. + */ + 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); + if (ret) { + pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n"); + goto out; + } + } + + ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz); + if (ret) { + pr_err("Failed to prepare elf header\n"); + goto out; + } + + /* + * It is unlikely that kernel hit this because elfcorehdr kexec + * segment (memsz) is built with addition space to accommodate growing + * number of crash memory ranges while loading the kdump kernel. It is + * Just to avoid any unforeseen case. + */ + if (elfsz > memsz) { + pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz); + goto out; + } + + ptr = __va(mem); + if (ptr) { + /* Temporarily invalidate the crash image while it is replaced */ + xchg(&kexec_crash_image, NULL); + + /* Replace the old elfcorehdr with newly prepared elfcorehdr */ + memcpy((void *)ptr, elfbuf, elfsz); + + /* The crash image is now valid once again */ + xchg(&kexec_crash_image, image); + } +out: + kvfree(cmem); + if (elfbuf) + kvfree(elfbuf); +} + /** * get_fdt_index - Loop through the kexec segment array and find * the index of the FDT segment. @@ -478,6 +568,8 @@ int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) */ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { + struct memory_notify *mn; + switch (image->hp_action) { case KEXEC_CRASH_HP_REMOVE_CPU: return; @@ -488,7 +580,8 @@ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) case KEXEC_CRASH_HP_REMOVE_MEMORY: case KEXEC_CRASH_HP_ADD_MEMORY: - pr_info_once("Crash update is not supported for memory hotplug\n"); + mn = (struct memory_notify *)arg; + update_crash_elfcorehdr(image, mn); return; default: pr_warn_once("Unknown hotplug action\n"); diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 2640a804fcdfe..925a69ad24689 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -595,6 +595,23 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) } } +static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) +{ +#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) + 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); + + return extra_sz; +#endif + return 0; +} + /** * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr * segment needed to load kdump kernel. @@ -626,7 +643,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; - kbuf->bufsz = kbuf->memsz = headers_sz; + kbuf->bufsz = headers_sz; + kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem); kbuf->top_down = false; ret = kexec_add_buffer(kbuf); diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index b1f4267d9b171..3702b0bdab141 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -620,4 +620,89 @@ 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 { + mem_rngs->ranges[i].end = base - 1; + size = mem_rngs->ranges[i].end - end; + ret = add_mem_range(mem_ranges, end + 1, size); + } + } +out: + return ret; +} #endif /* CONFIG_CRASH_DUMP */ From 9803af291162dbca4b9773586a3f5c392f0dd974 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Thu, 2 May 2024 23:50:40 +0530 Subject: [PATCH 7/7] powerpc/crash: remove unnecessary NULL check before kvfree() Fix the following coccicheck build warning: arch/powerpc/kexec/crash.c:488:2-8: WARNING: NULL check before some freeing functions is not needed. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202404261048.skfV5DDB-lkp@intel.com/ Signed-off-by: Sourabh Jain Signed-off-by: Michael Ellerman Link: https://msgid.link/20240502182040.774759-1-sourabhjain@linux.ibm.com --- arch/powerpc/kexec/crash.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index 21b193e938a37..9ac3266e49652 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -484,8 +484,7 @@ static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify * } out: kvfree(cmem); - if (elfbuf) - kvfree(elfbuf); + kvfree(elfbuf); } /**