From 6b27cc6c66abf0f0b091a95ca1ad4e0fc68c11fd Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 11 Jan 2024 15:24:29 +0000 Subject: mm: convert mm_counter_file() to take a folio Now all callers of mm_counter_file() have a folio, convert mm_counter_file() to take a folio. Saves a call to compound_head() hidden inside PageSwapBacked(). Link: https://lkml.kernel.org/r/20240111152429.3374566-11-willy@infradead.org Signed-off-by: Kefeng Wang Signed-off-by: Matthew Wilcox (Oracle) Cc: David Hildenbrand Signed-off-by: Andrew Morton --- kernel/events/uprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 929e98c62965..e4834d23e1d1 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, dec_mm_counter(mm, MM_ANONPAGES); if (!folio_test_anon(old_folio)) { - dec_mm_counter(mm, mm_counter_file(old_page)); + dec_mm_counter(mm, mm_counter_file(old_folio)); inc_mm_counter(mm, MM_ANONPAGES); } -- cgit v1.2.3 From fe58582c0e362d5e52b97985142b0dcef920b745 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 5 Feb 2024 08:46:47 +0530 Subject: mm/cma: drop CONFIG_CMA_DEBUG All pr_debug() prints in (mm/cma.c) could be enabled via standard Makefile based method. Besides cma_debug_show_areas() should always be called during cma_alloc() failure path. This seemingly redundant config, CONFIG_CMA_DEBUG can be dropped without any problem. [lukas.bulwahn@gmail.com: remove debug code to removed CONFIG_CMA_DEBUG] Link: https://lkml.kernel.org/r/20240207143825.986-1-lukas.bulwahn@gmail.com Link: https://lkml.kernel.org/r/20240205031647.283510-1-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Signed-off-by: Lukas Bulwahn Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: Robin Murphy Signed-off-by: Andrew Morton --- kernel/dma/contiguous.c | 6 ------ mm/Kconfig | 9 --------- mm/cma.c | 9 --------- 3 files changed, 24 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index f005c66f378c..055da410ac71 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -37,12 +37,6 @@ #define pr_fmt(fmt) "cma: " fmt -#ifdef CONFIG_CMA_DEBUG -#ifndef DEBUG -# define DEBUG -#endif -#endif - #include #include diff --git a/mm/Kconfig b/mm/Kconfig index ffc3a2ba3a8c..35fa9940e61f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -901,15 +901,6 @@ config CMA If unsure, say "n". -config CMA_DEBUG - bool "CMA debug messages (DEVELOPMENT)" - depends on DEBUG_KERNEL && CMA - help - Turns on debug messages in CMA. This produces KERN_DEBUG - messages for every CMA call as well as various messages while - processing calls such as dma_alloc_from_contiguous(). - This option does not affect warning and error messages. - config CMA_DEBUGFS bool "CMA debugfs interface" depends on CMA && DEBUG_FS diff --git a/mm/cma.c b/mm/cma.c index b6720930312d..4902bbfe24f1 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -14,11 +14,6 @@ #define pr_fmt(fmt) "cma: " fmt -#ifdef CONFIG_CMA_DEBUG -#ifndef DEBUG -# define DEBUG -#endif -#endif #define CREATE_TRACE_POINTS #include @@ -387,7 +382,6 @@ err: return ret; } -#ifdef CONFIG_CMA_DEBUG static void cma_debug_show_areas(struct cma *cma) { unsigned long next_zero_bit, next_set_bit, nr_zero; @@ -412,9 +406,6 @@ static void cma_debug_show_areas(struct cma *cma) pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count); spin_unlock_irq(&cma->lock); } -#else -static inline void cma_debug_show_areas(struct cma *cma) { } -#endif /** * cma_alloc() - allocate pages from contiguous area -- cgit v1.2.3 From 55c49fee57af99f3c663e69dedc5b85e691bbe50 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 2 Jan 2024 19:46:27 +0100 Subject: mm/vmalloc: remove vmap_area_list Earlier, vmap_area_list is exported to vmcoreinfo so that makedumpfile get the base address of vmalloc area. Now, vmap_area_list is empty, so export VMALLOC_START to vmcoreinfo instead, and remove vmap_area_list. [urezki@gmail.com: fix a warning in the crash_save_vmcoreinfo_init()] Link: https://lkml.kernel.org/r/20240111192329.449189-1-urezki@gmail.com Link: https://lkml.kernel.org/r/20240102184633.748113-6-urezki@gmail.com Signed-off-by: Baoquan He Signed-off-by: Uladzislau Rezki (Sony) Acked-by: Lorenzo Stoakes Cc: Christoph Hellwig Cc: Dave Chinner Cc: Joel Fernandes (Google) Cc: Kazuhito Hagio Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Oleksiy Avramchenko Cc: Paul E. McKenney Signed-off-by: Andrew Morton --- Documentation/admin-guide/kdump/vmcoreinfo.rst | 8 ++++---- arch/arm64/kernel/crash_core.c | 1 - arch/riscv/kernel/crash_core.c | 1 - include/linux/vmalloc.h | 1 - kernel/crash_core.c | 4 +--- kernel/kallsyms_selftest.c | 1 - mm/nommu.c | 2 -- mm/vmalloc.c | 2 -- 8 files changed, 5 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index bced9e4b6e08..0f714fc945ac 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -65,11 +65,11 @@ Defines the beginning of the text section. In general, _stext indicates the kernel start address. Used to convert a virtual address from the direct kernel map to a physical address. -vmap_area_list --------------- +VMALLOC_START +------------- -Stores the virtual area list. makedumpfile gets the vmalloc start value -from this variable and its value is necessary for vmalloc translation. +Stores the base address of vmalloc area. makedumpfile gets this value +since is necessary for vmalloc translation. mem_map ------- diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c index 66cde752cd74..2a24199a9b81 100644 --- a/arch/arm64/kernel/crash_core.c +++ b/arch/arm64/kernel/crash_core.c @@ -23,7 +23,6 @@ void arch_crash_save_vmcoreinfo(void) /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); - vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index 8706736fd4e2..d18d529fd9b9 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -8,7 +8,6 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_NUMBER(phys_ram_base); vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); - vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); #ifdef CONFIG_MMU VMCOREINFO_NUMBER(VA_BITS); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index c720be70c8dd..91810b4e9510 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -253,7 +253,6 @@ extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ -extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 75cd6a736d03..49b31e59d3cc 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -748,7 +748,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); #endif VMCOREINFO_SYMBOL(_stext); - VMCOREINFO_SYMBOL(vmap_area_list); + vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", (unsigned long) VMALLOC_START); #ifndef CONFIG_NUMA VMCOREINFO_SYMBOL(mem_map); @@ -789,8 +789,6 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(free_area, free_list); VMCOREINFO_OFFSET(list_head, next); VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_OFFSET(vmap_area, va_start); - VMCOREINFO_OFFSET(vmap_area, list); VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); log_buf_vmcoreinfo_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index b4cac76ea5e9..8a689b4ff4f9 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -89,7 +89,6 @@ static struct test_item test_items[] = { ITEM_DATA(kallsyms_test_var_data_static), ITEM_DATA(kallsyms_test_var_bss), ITEM_DATA(kallsyms_test_var_data), - ITEM_DATA(vmap_area_list), #endif }; diff --git a/mm/nommu.c b/mm/nommu.c index b6dc558d3144..5ec8f44e7ce9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -131,8 +131,6 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL(follow_pfn); -LIST_HEAD(vmap_area_list); - void vfree(const void *addr) { kfree(addr); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 86efebf0e0c8..b5882790da00 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -729,8 +729,6 @@ EXPORT_SYMBOL(vmalloc_to_pfn); static DEFINE_SPINLOCK(free_vmap_area_lock); -/* Export for kexec only */ -LIST_HEAD(vmap_area_list); static bool vmap_initialized __read_mostly; static struct rb_root purge_vmap_area_root = RB_ROOT; -- cgit v1.2.3 From 85fcde402db191b5f222ebfecda653777d7d084e Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:41 +0800 Subject: kexec: split crashkernel reservation code out from crash_core.c Patch series "Split crash out from kexec and clean up related config items", v3. Motivation: ============= Previously, LKP reported a building error. When investigating, it can't be resolved reasonablly with the present messy kdump config items. https://lore.kernel.org/oe-kbuild-all/202312182200.Ka7MzifQ-lkp@intel.com/ The kdump (crash dumping) related config items could causes confusions: Firstly, CRASH_CORE enables codes including - crashkernel reservation; - elfcorehdr updating; - vmcoreinfo exporting; - crash hotplug handling; Now fadump of powerpc, kcore dynamic debugging and kdump all selects CRASH_CORE, while fadump - fadump needs crashkernel parsing, vmcoreinfo exporting, and accessing global variable 'elfcorehdr_addr'; - kcore only needs vmcoreinfo exporting; - kdump needs all of the current kernel/crash_core.c. So only enabling PROC_CORE or FA_DUMP will enable CRASH_CORE, this mislead people that we enable crash dumping, actual it's not. Secondly, It's not reasonable to allow KEXEC_CORE select CRASH_CORE. Because KEXEC_CORE enables codes which allocate control pages, copy kexec/kdump segments, and prepare for switching. These codes are shared by both kexec reboot and kdump. We could want kexec reboot, but disable kdump. In that case, CRASH_CORE should not be selected. -------------------- CONFIG_CRASH_CORE=y CONFIG_KEXEC_CORE=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y --------------------- Thirdly, It's not reasonable to allow CRASH_DUMP select KEXEC_CORE. That could make KEXEC_CORE, CRASH_DUMP are enabled independently from KEXEC or KEXEC_FILE. However, w/o KEXEC or KEXEC_FILE, the KEXEC_CORE code built in doesn't make any sense because no kernel loading or switching will happen to utilize the KEXEC_CORE code. --------------------- CONFIG_CRASH_CORE=y CONFIG_KEXEC_CORE=y CONFIG_CRASH_DUMP=y --------------------- In this case, what is worse, on arch sh and arm, KEXEC relies on MMU, while CRASH_DUMP can still be enabled when !MMU, then compiling error is seen as the lkp test robot reported in above link. ------arch/sh/Kconfig------ config ARCH_SUPPORTS_KEXEC def_bool MMU config ARCH_SUPPORTS_CRASH_DUMP def_bool BROKEN_ON_SMP --------------------------- Changes: =========== 1, split out crash_reserve.c from crash_core.c; 2, split out vmcore_infoc. from crash_core.c; 3, move crash related codes in kexec_core.c into crash_core.c; 4, remove dependency of FA_DUMP on CRASH_DUMP; 5, clean up kdump related config items; 6, wrap up crash codes in crash related ifdefs on all 8 arch-es which support crash dumping, except of ppc; Achievement: =========== With above changes, I can rearrange the config item logic as below (the right item depends on or is selected by the left item): PROC_KCORE -----------> VMCORE_INFO |----------> VMCORE_INFO FA_DUMP----| |----------> CRASH_RESERVE ---->VMCORE_INFO / |---->CRASH_RESERVE KEXEC --| /| |--> KEXEC_CORE--> CRASH_DUMP-->/-|---->PROC_VMCORE KEXEC_FILE --| \ | \---->CRASH_HOTPLUG KEXEC --| |--> KEXEC_CORE (for kexec reboot only) KEXEC_FILE --| Test ======== On all 8 architectures, including x86_64, arm64, s390x, sh, arm, mips, riscv, loongarch, I did below three cases of config item setting and building all passed. Take configs on x86_64 as exampmle here: (1) Both CONFIG_KEXEC and KEXEC_FILE is unset, then all kexec/kdump items are unset automatically: # Kexec and crash features # CONFIG_KEXEC is not set # CONFIG_KEXEC_FILE is not set # end of Kexec and crash features (2) set CONFIG_KEXEC_FILE and 'make olddefconfig': --------------- # Kexec and crash features CONFIG_CRASH_RESERVE=y CONFIG_VMCORE_INFO=y CONFIG_KEXEC_CORE=y CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_CRASH_HOTPLUG=y CONFIG_CRASH_MAX_MEMORY_RANGES=8192 # end of Kexec and crash features --------------- (3) unset CONFIG_CRASH_DUMP in case 2 and execute 'make olddefconfig': ------------------------ # Kexec and crash features CONFIG_KEXEC_CORE=y CONFIG_KEXEC_FILE=y # end of Kexec and crash features ------------------------ Note: For ppc, it needs investigation to make clear how to split out crash code in arch folder. Hope Hari and Pingfan can help have a look, see if it's doable. Now, I make it either have both kexec and crash enabled, or disable both of them altogether. This patch (of 14): Both kdump and fa_dump of ppc rely on crashkernel reservation. Move the relevant codes into separate files: crash_reserve.c, include/linux/crash_reserve.h. And also add config item CRASH_RESERVE to control its enabling of the codes. And update config items which has relationship with crashkernel reservation. And also change ifdeffery from CONFIG_CRASH_CORE to CONFIG_CRASH_RESERVE when those scopes are only crashkernel reservation related. And also rename arch/XXX/include/asm/{crash_core.h => crash_reserve.h} on arm64, x86 and risc-v because those architectures' crash_core.h is only related to crashkernel reservation. [akpm@linux-foundation.org: s/CRASH_RESEERVE/CRASH_RESERVE/, per Klara Modin] Link: https://lkml.kernel.org/r/20240124051254.67105-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20240124051254.67105-2-bhe@redhat.com Signed-off-by: Baoquan He Acked-by: Hari Bathini Cc: Al Viro Cc: Eric W. Biederman Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 2 +- arch/arm64/include/asm/crash_core.h | 10 - arch/arm64/include/asm/crash_reserve.h | 10 + arch/powerpc/Kconfig | 1 + arch/powerpc/mm/nohash/kaslr_booke.c | 4 +- arch/riscv/Kconfig | 2 +- arch/riscv/include/asm/crash_core.h | 11 - arch/riscv/include/asm/crash_reserve.h | 11 + arch/x86/Kconfig | 2 +- arch/x86/include/asm/crash_core.h | 42 --- arch/x86/include/asm/crash_reserve.h | 42 +++ include/linux/crash_core.h | 40 --- include/linux/crash_reserve.h | 48 ++++ include/linux/kexec.h | 1 + kernel/Kconfig.kexec | 5 +- kernel/Makefile | 1 + kernel/crash_core.c | 438 ------------------------------- kernel/crash_reserve.c | 464 +++++++++++++++++++++++++++++++++ 18 files changed, 587 insertions(+), 547 deletions(-) delete mode 100644 arch/arm64/include/asm/crash_core.h create mode 100644 arch/arm64/include/asm/crash_reserve.h delete mode 100644 arch/riscv/include/asm/crash_core.h create mode 100644 arch/riscv/include/asm/crash_reserve.h delete mode 100644 arch/x86/include/asm/crash_core.h create mode 100644 arch/x86/include/asm/crash_reserve.h create mode 100644 include/linux/crash_reserve.h create mode 100644 kernel/crash_reserve.c (limited to 'kernel') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 386566138620..5a7ac1f37bdc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1519,7 +1519,7 @@ config ARCH_SUPPORTS_CRASH_DUMP def_bool y config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config TRANS_TABLE def_bool y diff --git a/arch/arm64/include/asm/crash_core.h b/arch/arm64/include/asm/crash_core.h deleted file mode 100644 index 9f5c8d339f44..000000000000 --- a/arch/arm64/include/asm/crash_core.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _ARM64_CRASH_CORE_H -#define _ARM64_CRASH_CORE_H - -/* Current arm64 boot protocol requires 2MB alignment */ -#define CRASH_ALIGN SZ_2M - -#define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit -#define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) -#endif diff --git a/arch/arm64/include/asm/crash_reserve.h b/arch/arm64/include/asm/crash_reserve.h new file mode 100644 index 000000000000..4afe027a4e7b --- /dev/null +++ b/arch/arm64/include/asm/crash_reserve.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ARM64_CRASH_RESERVE_H +#define _ARM64_CRASH_RESERVE_H + +/* Current arm64 boot protocol requires 2MB alignment */ +#define CRASH_ALIGN SZ_2M + +#define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit +#define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) +#endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b9fc064d38d2..7f704ae5c5ef 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -691,6 +691,7 @@ config FA_DUMP bool "Firmware-assisted dump" depends on PPC64 && (PPC_RTAS || PPC_POWERNV) select CRASH_CORE + select CRASH_RESERVE select CRASH_DUMP help A robust mechanism to get reliable kernel crash dump with diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index b4f2786a7d2b..cdff129abb14 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include @@ -173,7 +173,7 @@ static __init bool overlaps_region(const void *fdt, u32 start, static void __init get_crash_kernel(void *fdt, unsigned long size) { -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_CRASH_RESERVE unsigned long long crash_size, crash_base; int ret; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..bd06ad1bb97c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -767,7 +767,7 @@ config ARCH_SUPPORTS_CRASH_DUMP def_bool y config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config COMPAT bool "Kernel support for 32-bit U-mode" diff --git a/arch/riscv/include/asm/crash_core.h b/arch/riscv/include/asm/crash_core.h deleted file mode 100644 index e1874b23feaf..000000000000 --- a/arch/riscv/include/asm/crash_core.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _RISCV_CRASH_CORE_H -#define _RISCV_CRASH_CORE_H - -#define CRASH_ALIGN PMD_SIZE - -#define CRASH_ADDR_LOW_MAX dma32_phys_limit -#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() - -extern phys_addr_t memblock_end_of_DRAM(void); -#endif diff --git a/arch/riscv/include/asm/crash_reserve.h b/arch/riscv/include/asm/crash_reserve.h new file mode 100644 index 000000000000..013962e63587 --- /dev/null +++ b/arch/riscv/include/asm/crash_reserve.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _RISCV_CRASH_RESERVE_H +#define _RISCV_CRASH_RESERVE_H + +#define CRASH_ALIGN PMD_SIZE + +#define CRASH_ADDR_LOW_MAX dma32_phys_limit +#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() + +extern phys_addr_t memblock_end_of_DRAM(void); +#endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5edec175b9bf..5bd925815154 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2106,7 +2106,7 @@ config ARCH_SUPPORTS_CRASH_HOTPLUG def_bool y config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP) diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_core.h deleted file mode 100644 index 76af98f4e801..000000000000 --- a/arch/x86/include/asm/crash_core.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _X86_CRASH_CORE_H -#define _X86_CRASH_CORE_H - -/* 16M alignment for crash kernel regions */ -#define CRASH_ALIGN SZ_16M - -/* - * Keep the crash kernel below this limit. - * - * Earlier 32-bits kernels would limit the kernel to the low 512 MB range - * due to mapping restrictions. - * - * 64-bit kdump kernels need to be restricted to be under 64 TB, which is - * the upper limit of system RAM in 4-level paging mode. Since the kdump - * jump could be from 5-level paging to 4-level paging, the jump will fail if - * the kernel is put above 64 TB, and during the 1st kernel bootup there's - * no good way to detect the paging mode of the target kernel which will be - * loaded for dumping. - */ -extern unsigned long swiotlb_size_or_default(void); - -#ifdef CONFIG_X86_32 -# define CRASH_ADDR_LOW_MAX SZ_512M -# define CRASH_ADDR_HIGH_MAX SZ_512M -#else -# define CRASH_ADDR_LOW_MAX SZ_4G -# define CRASH_ADDR_HIGH_MAX SZ_64T -#endif - -# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default() - -static inline unsigned long crash_low_size_default(void) -{ -#ifdef CONFIG_X86_64 - return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); -#else - return 0; -#endif -} - -#endif /* _X86_CRASH_CORE_H */ diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h new file mode 100644 index 000000000000..152239f95541 --- /dev/null +++ b/arch/x86/include/asm/crash_reserve.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_CRASH_RESERVE_H +#define _X86_CRASH_RESERVE_H + +/* 16M alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_16M + +/* + * Keep the crash kernel below this limit. + * + * Earlier 32-bits kernels would limit the kernel to the low 512 MB range + * due to mapping restrictions. + * + * 64-bit kdump kernels need to be restricted to be under 64 TB, which is + * the upper limit of system RAM in 4-level paging mode. Since the kdump + * jump could be from 5-level paging to 4-level paging, the jump will fail if + * the kernel is put above 64 TB, and during the 1st kernel bootup there's + * no good way to detect the paging mode of the target kernel which will be + * loaded for dumping. + */ +extern unsigned long swiotlb_size_or_default(void); + +#ifdef CONFIG_X86_32 +# define CRASH_ADDR_LOW_MAX SZ_512M +# define CRASH_ADDR_HIGH_MAX SZ_512M +#else +# define CRASH_ADDR_LOW_MAX SZ_4G +# define CRASH_ADDR_HIGH_MAX SZ_64T +#endif + +# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default() + +static inline unsigned long crash_low_size_default(void) +{ +#ifdef CONFIG_X86_64 + return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); +#else + return 0; +#endif +} + +#endif /* _X86_CRASH_RESERVE_H */ diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 9eaeaafe0cad..1fde49246fa6 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -5,14 +5,6 @@ #include #include #include -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -#include -#endif - -/* Location of a reserved region to hold the crash kernel. - */ -extern struct resource crashk_res; -extern struct resource crashk_low_res; #define CRASH_CORE_NOTE_NAME "CORE" #define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) @@ -87,38 +79,6 @@ Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); void final_note(Elf_Word *buf); -int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, - unsigned long long *crash_size, unsigned long long *crash_base, - unsigned long long *low_size, bool *high); - -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE -#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) -#endif -#ifndef CRASH_ALIGN -#define CRASH_ALIGN SZ_2M -#endif -#ifndef CRASH_ADDR_LOW_MAX -#define CRASH_ADDR_LOW_MAX SZ_4G -#endif -#ifndef CRASH_ADDR_HIGH_MAX -#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() -#endif - -void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high); -#else -static inline void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high) -{} -#endif - /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h new file mode 100644 index 000000000000..5a9df944fb80 --- /dev/null +++ b/include/linux/crash_reserve.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_CRASH_RESERVE_H +#define LINUX_CRASH_RESERVE_H + +#include +#include +#include +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#include +#endif + +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; +extern struct resource crashk_low_res; + +int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base, + unsigned long long *low_size, bool *high); + +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) +#endif +#ifndef CRASH_ALIGN +#define CRASH_ALIGN SZ_2M +#endif +#ifndef CRASH_ADDR_LOW_MAX +#define CRASH_ADDR_LOW_MAX SZ_4G +#endif +#ifndef CRASH_ADDR_HIGH_MAX +#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() +#endif + +void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high); +#else +static inline void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high) +{} +#endif +#endif /* LINUX_CRASH_RESERVE_H */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 400cb6c02176..6d79bfb52e5b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -16,6 +16,7 @@ #if !defined(__ASSEMBLY__) #include +#include #include #include diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 946dffa048b7..8b7be71edd85 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -2,11 +2,15 @@ menu "Kexec and crash features" +config CRASH_RESERVE + bool + config CRASH_CORE bool config KEXEC_CORE select CRASH_CORE + select CRASH_RESERVE bool config KEXEC_ELF @@ -96,7 +100,6 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" depends on ARCH_SUPPORTS_CRASH_DUMP - select CRASH_CORE select KEXEC_CORE help Generate crash dump after being started by kexec. diff --git a/kernel/Makefile b/kernel/Makefile index ce105a5558fc..05fa88b3ab74 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 49b31e59d3cc..ae0d1ce89b46 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -34,444 +34,6 @@ u32 *vmcoreinfo_note; /* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ static unsigned char *vmcoreinfo_data_safecopy; -/* Location of the reserved area for the crash kernel */ -struct resource crashk_res = { - .name = "Crash kernel", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, - .desc = IORES_DESC_CRASH_KERNEL -}; -struct resource crashk_low_res = { - .name = "Crash kernel", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, - .desc = IORES_DESC_CRASH_KERNEL -}; - -/* - * parsing the "crashkernel" commandline - * - * this code is intended to be called from architecture specific code - */ - - -/* - * This function parses command lines in the format - * - * crashkernel=ramsize-range:size[,...][@offset] - * - * The function returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_mem(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - char *cur = cmdline, *tmp; - unsigned long long total_mem = system_ram; - - /* - * Firmware sometimes reserves some memory regions for its own use, - * so the system memory size is less than the actual physical memory - * size. Work around this by rounding up the total size to 128M, - * which is enough for most test cases. - */ - total_mem = roundup(total_mem, SZ_128M); - - /* for each entry of the comma-separated list */ - do { - unsigned long long start, end = ULLONG_MAX, size; - - /* get the start of the range */ - start = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (*cur != '-') { - pr_warn("crashkernel: '-' expected\n"); - return -EINVAL; - } - cur++; - - /* if no ':' is here, than we read the end */ - if (*cur != ':') { - end = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (end <= start) { - pr_warn("crashkernel: end <= start\n"); - return -EINVAL; - } - } - - if (*cur != ':') { - pr_warn("crashkernel: ':' expected\n"); - return -EINVAL; - } - cur++; - - size = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (size >= total_mem) { - pr_warn("crashkernel: invalid size\n"); - return -EINVAL; - } - - /* match ? */ - if (total_mem >= start && total_mem < end) { - *crash_size = size; - break; - } - } while (*cur++ == ','); - - if (*crash_size > 0) { - while (*cur && *cur != ' ' && *cur != '@') - cur++; - if (*cur == '@') { - cur++; - *crash_base = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); - return -EINVAL; - } - } - } else - pr_info("crashkernel size resulted in zero bytes\n"); - - return 0; -} - -/* - * That function parses "simple" (old) crashkernel command lines like - * - * crashkernel=size[@offset] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_simple(char *cmdline, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; - } - - if (*cur == '@') - *crash_base = memparse(cur+1, &cur); - else if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - - return 0; -} - -#define SUFFIX_HIGH 0 -#define SUFFIX_LOW 1 -#define SUFFIX_NULL 2 -static __initdata char *suffix_tbl[] = { - [SUFFIX_HIGH] = ",high", - [SUFFIX_LOW] = ",low", - [SUFFIX_NULL] = NULL, -}; - -/* - * That function parses "suffix" crashkernel command lines like - * - * crashkernel=size,[high|low] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, - const char *suffix) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; - } - - /* check with suffix */ - if (strncmp(cur, suffix, strlen(suffix))) { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - cur += strlen(suffix); - if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - - return 0; -} - -static __init char *get_last_crashkernel(char *cmdline, - const char *name, - const char *suffix) -{ - char *p = cmdline, *ck_cmdline = NULL; - - /* find crashkernel and use the last one if there are more */ - p = strstr(p, name); - while (p) { - char *end_p = strchr(p, ' '); - char *q; - - if (!end_p) - end_p = p + strlen(p); - - if (!suffix) { - int i; - - /* skip the one with any known suffix */ - for (i = 0; suffix_tbl[i]; i++) { - q = end_p - strlen(suffix_tbl[i]); - if (!strncmp(q, suffix_tbl[i], - strlen(suffix_tbl[i]))) - goto next; - } - ck_cmdline = p; - } else { - q = end_p - strlen(suffix); - if (!strncmp(q, suffix, strlen(suffix))) - ck_cmdline = p; - } -next: - p = strstr(p+1, name); - } - - return ck_cmdline; -} - -static int __init __parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - const char *suffix) -{ - char *first_colon, *first_space; - char *ck_cmdline; - char *name = "crashkernel="; - - BUG_ON(!crash_size || !crash_base); - *crash_size = 0; - *crash_base = 0; - - ck_cmdline = get_last_crashkernel(cmdline, name, suffix); - if (!ck_cmdline) - return -ENOENT; - - ck_cmdline += strlen(name); - - if (suffix) - return parse_crashkernel_suffix(ck_cmdline, crash_size, - suffix); - /* - * if the commandline contains a ':', then that's the extended - * syntax -- if not, it must be the classic syntax - */ - first_colon = strchr(ck_cmdline, ':'); - first_space = strchr(ck_cmdline, ' '); - if (first_colon && (!first_space || first_colon < first_space)) - return parse_crashkernel_mem(ck_cmdline, system_ram, - crash_size, crash_base); - - return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); -} - -/* - * That function is the entry point for command line parsing and should be - * called from the arch-specific code. - * - * If crashkernel=,high|low is supported on architecture, non-NULL values - * should be passed to parameters 'low_size' and 'high'. - */ -int __init parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - unsigned long long *low_size, - bool *high) -{ - int ret; - - /* crashkernel=X[@offset] */ - ret = __parse_crashkernel(cmdline, system_ram, crash_size, - crash_base, NULL); -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - /* - * If non-NULL 'high' passed in and no normal crashkernel - * setting detected, try parsing crashkernel=,high|low. - */ - if (high && ret == -ENOENT) { - ret = __parse_crashkernel(cmdline, 0, crash_size, - crash_base, suffix_tbl[SUFFIX_HIGH]); - if (ret || !*crash_size) - return -EINVAL; - - /* - * crashkernel=Y,low can be specified or not, but invalid value - * is not allowed. - */ - ret = __parse_crashkernel(cmdline, 0, low_size, - crash_base, suffix_tbl[SUFFIX_LOW]); - if (ret == -ENOENT) { - *low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - ret = 0; - } else if (ret) { - return ret; - } - - *high = true; - } -#endif - if (!*crash_size) - ret = -EINVAL; - - return ret; -} - -/* - * Add a dummy early_param handler to mark crashkernel= as a known command line - * parameter and suppress incorrect warnings in init/main.c. - */ -static int __init parse_crashkernel_dummy(char *arg) -{ - return 0; -} -early_param("crashkernel", parse_crashkernel_dummy); - -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -static int __init reserve_crashkernel_low(unsigned long long low_size) -{ -#ifdef CONFIG_64BIT - unsigned long long low_base; - - low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); - if (!low_base) { - pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); - return -ENOMEM; - } - - pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", - low_base, low_base + low_size, low_size >> 20); - - crashk_low_res.start = low_base; - crashk_low_res.end = low_base + low_size - 1; -#endif - return 0; -} - -void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high) -{ - unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0; - bool fixed_base = false; - - /* User specifies base address explicitly. */ - if (crash_base) { - fixed_base = true; - search_base = crash_base; - search_end = crash_base + crash_size; - } else if (high) { - search_base = CRASH_ADDR_LOW_MAX; - search_end = CRASH_ADDR_HIGH_MAX; - } - -retry: - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, - search_base, search_end); - if (!crash_base) { - /* - * For crashkernel=size[KMG]@offset[KMG], print out failure - * message if can't reserve the specified region. - */ - if (fixed_base) { - pr_warn("crashkernel reservation failed - memory is in use.\n"); - return; - } - - /* - * For crashkernel=size[KMG], if the first attempt was for - * low memory, fall back to high memory, the minimum required - * low memory will be reserved later. - */ - if (!high && search_end == CRASH_ADDR_LOW_MAX) { - search_end = CRASH_ADDR_HIGH_MAX; - search_base = CRASH_ADDR_LOW_MAX; - crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - goto retry; - } - - /* - * For crashkernel=size[KMG],high, if the first attempt was - * for high memory, fall back to low memory. - */ - if (high && search_end == CRASH_ADDR_HIGH_MAX) { - search_end = CRASH_ADDR_LOW_MAX; - search_base = 0; - goto retry; - } - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - - if ((crash_base >= CRASH_ADDR_LOW_MAX) && - crash_low_size && reserve_crashkernel_low(crash_low_size)) { - memblock_phys_free(crash_base, crash_size); - return; - } - - pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - crash_base, crash_base + crash_size, crash_size >> 20); - - /* - * The crashkernel memory will be removed from the kernel linear - * map. Inform kmemleak so that it won't try to access it. - */ - kmemleak_ignore_phys(crash_base); - if (crashk_low_res.end) - kmemleak_ignore_phys(crashk_low_res.start); - - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; -} - -static __init int insert_crashkernel_resources(void) -{ - if (crashk_res.start < crashk_res.end) - insert_resource(&iomem_resource, &crashk_res); - - if (crashk_low_res.start < crashk_low_res.end) - insert_resource(&iomem_resource, &crashk_low_res); - - return 0; -} -early_initcall(insert_crashkernel_resources); -#endif - int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz) { diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c new file mode 100644 index 000000000000..bbb6c3cb00e4 --- /dev/null +++ b/kernel/crash_reserve.c @@ -0,0 +1,464 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * crash.c - kernel crash support code. + * Copyright (C) 2002-2004 Eric Biederman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include + +#include "kallsyms_internal.h" +#include "kexec_internal.h" + +/* Location of the reserved area for the crash kernel */ +struct resource crashk_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL +}; +struct resource crashk_low_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL +}; + +/* + * parsing the "crashkernel" commandline + * + * this code is intended to be called from architecture specific code + */ + + +/* + * This function parses command lines in the format + * + * crashkernel=ramsize-range:size[,...][@offset] + * + * The function returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_mem(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline, *tmp; + unsigned long long total_mem = system_ram; + + /* + * Firmware sometimes reserves some memory regions for its own use, + * so the system memory size is less than the actual physical memory + * size. Work around this by rounding up the total size to 128M, + * which is enough for most test cases. + */ + total_mem = roundup(total_mem, SZ_128M); + + /* for each entry of the comma-separated list */ + do { + unsigned long long start, end = ULLONG_MAX, size; + + /* get the start of the range */ + start = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (*cur != '-') { + pr_warn("crashkernel: '-' expected\n"); + return -EINVAL; + } + cur++; + + /* if no ':' is here, than we read the end */ + if (*cur != ':') { + end = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (end <= start) { + pr_warn("crashkernel: end <= start\n"); + return -EINVAL; + } + } + + if (*cur != ':') { + pr_warn("crashkernel: ':' expected\n"); + return -EINVAL; + } + cur++; + + size = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (size >= total_mem) { + pr_warn("crashkernel: invalid size\n"); + return -EINVAL; + } + + /* match ? */ + if (total_mem >= start && total_mem < end) { + *crash_size = size; + break; + } + } while (*cur++ == ','); + + if (*crash_size > 0) { + while (*cur && *cur != ' ' && *cur != '@') + cur++; + if (*cur == '@') { + cur++; + *crash_base = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected after '@'\n"); + return -EINVAL; + } + } + } else + pr_info("crashkernel size resulted in zero bytes\n"); + + return 0; +} + +/* + * That function parses "simple" (old) crashkernel command lines like + * + * crashkernel=size[@offset] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_simple(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + if (*cur == '@') + *crash_base = memparse(cur+1, &cur); + else if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +#define SUFFIX_HIGH 0 +#define SUFFIX_LOW 1 +#define SUFFIX_NULL 2 +static __initdata char *suffix_tbl[] = { + [SUFFIX_HIGH] = ",high", + [SUFFIX_LOW] = ",low", + [SUFFIX_NULL] = NULL, +}; + +/* + * That function parses "suffix" crashkernel command lines like + * + * crashkernel=size,[high|low] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_suffix(char *cmdline, + unsigned long long *crash_size, + const char *suffix) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + /* check with suffix */ + if (strncmp(cur, suffix, strlen(suffix))) { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + cur += strlen(suffix); + if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +static __init char *get_last_crashkernel(char *cmdline, + const char *name, + const char *suffix) +{ + char *p = cmdline, *ck_cmdline = NULL; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, name); + while (p) { + char *end_p = strchr(p, ' '); + char *q; + + if (!end_p) + end_p = p + strlen(p); + + if (!suffix) { + int i; + + /* skip the one with any known suffix */ + for (i = 0; suffix_tbl[i]; i++) { + q = end_p - strlen(suffix_tbl[i]); + if (!strncmp(q, suffix_tbl[i], + strlen(suffix_tbl[i]))) + goto next; + } + ck_cmdline = p; + } else { + q = end_p - strlen(suffix); + if (!strncmp(q, suffix, strlen(suffix))) + ck_cmdline = p; + } +next: + p = strstr(p+1, name); + } + + return ck_cmdline; +} + +static int __init __parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + const char *suffix) +{ + char *first_colon, *first_space; + char *ck_cmdline; + char *name = "crashkernel="; + + BUG_ON(!crash_size || !crash_base); + *crash_size = 0; + *crash_base = 0; + + ck_cmdline = get_last_crashkernel(cmdline, name, suffix); + if (!ck_cmdline) + return -ENOENT; + + ck_cmdline += strlen(name); + + if (suffix) + return parse_crashkernel_suffix(ck_cmdline, crash_size, + suffix); + /* + * if the commandline contains a ':', then that's the extended + * syntax -- if not, it must be the classic syntax + */ + first_colon = strchr(ck_cmdline, ':'); + first_space = strchr(ck_cmdline, ' '); + if (first_colon && (!first_space || first_colon < first_space)) + return parse_crashkernel_mem(ck_cmdline, system_ram, + crash_size, crash_base); + + return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); +} + +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + * + * If crashkernel=,high|low is supported on architecture, non-NULL values + * should be passed to parameters 'low_size' and 'high'. + */ +int __init parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + unsigned long long *low_size, + bool *high) +{ + int ret; + + /* crashkernel=X[@offset] */ + ret = __parse_crashkernel(cmdline, system_ram, crash_size, + crash_base, NULL); +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + /* + * If non-NULL 'high' passed in and no normal crashkernel + * setting detected, try parsing crashkernel=,high|low. + */ + if (high && ret == -ENOENT) { + ret = __parse_crashkernel(cmdline, 0, crash_size, + crash_base, suffix_tbl[SUFFIX_HIGH]); + if (ret || !*crash_size) + return -EINVAL; + + /* + * crashkernel=Y,low can be specified or not, but invalid value + * is not allowed. + */ + ret = __parse_crashkernel(cmdline, 0, low_size, + crash_base, suffix_tbl[SUFFIX_LOW]); + if (ret == -ENOENT) { + *low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + ret = 0; + } else if (ret) { + return ret; + } + + *high = true; + } +#endif + if (!*crash_size) + ret = -EINVAL; + + return ret; +} + +/* + * Add a dummy early_param handler to mark crashkernel= as a known command line + * parameter and suppress incorrect warnings in init/main.c. + */ +static int __init parse_crashkernel_dummy(char *arg) +{ + return 0; +} +early_param("crashkernel", parse_crashkernel_dummy); + +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +static int __init reserve_crashkernel_low(unsigned long long low_size) +{ +#ifdef CONFIG_64BIT + unsigned long long low_base; + + low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); + if (!low_base) { + pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); + return -ENOMEM; + } + + pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", + low_base, low_base + low_size, low_size >> 20); + + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + insert_resource(&iomem_resource, &crashk_low_res); +#endif + return 0; +} + +void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high) +{ + unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0; + bool fixed_base = false; + + /* User specifies base address explicitly. */ + if (crash_base) { + fixed_base = true; + search_base = crash_base; + search_end = crash_base + crash_size; + } else if (high) { + search_base = CRASH_ADDR_LOW_MAX; + search_end = CRASH_ADDR_HIGH_MAX; + } + +retry: + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + search_base, search_end); + if (!crash_base) { + /* + * For crashkernel=size[KMG]@offset[KMG], print out failure + * message if can't reserve the specified region. + */ + if (fixed_base) { + pr_warn("crashkernel reservation failed - memory is in use.\n"); + return; + } + + /* + * For crashkernel=size[KMG], if the first attempt was for + * low memory, fall back to high memory, the minimum required + * low memory will be reserved later. + */ + if (!high && search_end == CRASH_ADDR_LOW_MAX) { + search_end = CRASH_ADDR_HIGH_MAX; + search_base = CRASH_ADDR_LOW_MAX; + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + goto retry; + } + + /* + * For crashkernel=size[KMG],high, if the first attempt was + * for high memory, fall back to low memory. + */ + if (high && search_end == CRASH_ADDR_HIGH_MAX) { + search_end = CRASH_ADDR_LOW_MAX; + search_base = 0; + goto retry; + } + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; + } + + if ((crash_base >= CRASH_ADDR_LOW_MAX) && + crash_low_size && reserve_crashkernel_low(crash_low_size)) { + memblock_phys_free(crash_base, crash_size); + return; + } + + pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + crash_base, crash_base + crash_size, crash_size >> 20); + + /* + * The crashkernel memory will be removed from the kernel linear + * map. Inform kmemleak so that it won't try to access it. + */ + kmemleak_ignore_phys(crash_base); + if (crashk_low_res.end) + kmemleak_ignore_phys(crashk_low_res.start); + + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; +} + +static __init int insert_crashkernel_resources(void) +{ + if (crashk_res.start < crashk_res.end) + insert_resource(&iomem_resource, &crashk_res); + + if (crashk_low_res.start < crashk_low_res.end) + insert_resource(&iomem_resource, &crashk_low_res); + + return 0; +} +early_initcall(insert_crashkernel_resources); +#endif -- cgit v1.2.3 From 443cbaf9e2fdbef7d7cae457434a6cb8a679441b Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:42 +0800 Subject: crash: split vmcoreinfo exporting code out from crash_core.c Now move the relevant codes into separate files: kernel/crash_reserve.c, include/linux/crash_reserve.h. And add config item CRASH_RESERVE to control its enabling. And also update the old ifdeffery of CONFIG_CRASH_CORE, including of and config item dependency on CRASH_CORE accordingly. And also do renaming as follows: - arch/xxx/kernel/{crash_core.c => vmcore_info.c} because they are only related to vmcoreinfo exporting on x86, arm64, riscv. And also Remove config item CRASH_CORE, and rely on CONFIG_KEXEC_CORE to decide if build in crash_core.c. [yang.lee@linux.alibaba.com: remove duplicated include in vmcore_info.c] Link: https://lkml.kernel.org/r/20240126005744.16561-1-yang.lee@linux.alibaba.com Link: https://lkml.kernel.org/r/20240124051254.67105-3-bhe@redhat.com Signed-off-by: Baoquan He Signed-off-by: Yang Li Acked-by: Hari Bathini Cc: Al Viro Cc: Eric W. Biederman Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- arch/arm64/kernel/Makefile | 2 +- arch/arm64/kernel/crash_core.c | 39 ----- arch/arm64/kernel/vmcore_info.c | 39 +++++ arch/powerpc/Kconfig | 2 +- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/platforms/powernv/opal-core.c | 2 +- arch/riscv/kernel/Makefile | 2 +- arch/riscv/kernel/crash_core.c | 24 --- arch/riscv/kernel/vmcore_info.c | 24 +++ arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/crash_core_32.c | 17 --- arch/x86/kernel/crash_core_64.c | 24 --- arch/x86/kernel/vmcore_info_32.c | 17 +++ arch/x86/kernel/vmcore_info_64.c | 24 +++ drivers/firmware/qemu_fw_cfg.c | 14 +- fs/proc/Kconfig | 2 +- fs/proc/kcore.c | 2 +- include/linux/buildid.h | 2 +- include/linux/crash_core.h | 73 --------- include/linux/kexec.h | 1 + include/linux/vmcore_info.h | 81 ++++++++++ kernel/Kconfig.kexec | 4 +- kernel/Makefile | 4 +- kernel/crash_core.c | 206 -------------------------- kernel/ksysfs.c | 6 +- kernel/printk/printk.c | 4 +- kernel/vmcore_info.c | 230 +++++++++++++++++++++++++++++ lib/buildid.c | 2 +- 28 files changed, 442 insertions(+), 409 deletions(-) delete mode 100644 arch/arm64/kernel/crash_core.c create mode 100644 arch/arm64/kernel/vmcore_info.c delete mode 100644 arch/riscv/kernel/crash_core.c create mode 100644 arch/riscv/kernel/vmcore_info.c delete mode 100644 arch/x86/kernel/crash_core_32.c delete mode 100644 arch/x86/kernel/crash_core_64.c create mode 100644 arch/x86/kernel/vmcore_info_32.c create mode 100644 arch/x86/kernel/vmcore_info_64.c create mode 100644 include/linux/vmcore_info.h create mode 100644 kernel/vmcore_info.c (limited to 'kernel') diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 467cb7117273..a3882cccf049 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -66,7 +66,7 @@ obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_ARM64_MTE) += mte.o diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c deleted file mode 100644 index 2a24199a9b81..000000000000 --- a/arch/arm64/kernel/crash_core.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) Linaro. - * Copyright (C) Huawei Futurewei Technologies. - */ - -#include -#include -#include -#include -#include - -static inline u64 get_tcr_el1_t1sz(void); - -static inline u64 get_tcr_el1_t1sz(void) -{ - return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET; -} - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(VA_BITS); - /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ - vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); - vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); - vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); - vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); - vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); - vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", - kimage_voffset); - vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", - PHYS_OFFSET); - vmcoreinfo_append_str("NUMBER(TCR_EL1_T1SZ)=0x%llx\n", - get_tcr_el1_t1sz()); - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n", - system_supports_address_auth() ? - ptrauth_kernel_pac_mask() : 0); -} diff --git a/arch/arm64/kernel/vmcore_info.c b/arch/arm64/kernel/vmcore_info.c new file mode 100644 index 000000000000..b19d5d6cb8b3 --- /dev/null +++ b/arch/arm64/kernel/vmcore_info.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + */ + +#include +#include +#include +#include +#include + +static inline u64 get_tcr_el1_t1sz(void); + +static inline u64 get_tcr_el1_t1sz(void) +{ + return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET; +} + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); + vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); + vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); + vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); + vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); + vmcoreinfo_append_str("NUMBER(TCR_EL1_T1SZ)=0x%llx\n", + get_tcr_el1_t1sz()); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n", + system_supports_address_auth() ? + ptrauth_kernel_pac_mask() : 0); +} diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7f704ae5c5ef..495d197c9b27 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -690,7 +690,7 @@ config ARCH_SELECTS_CRASH_DUMP config FA_DUMP bool "Firmware-assisted dump" depends on PPC64 && (PPC_RTAS || PPC_POWERNV) - select CRASH_CORE + select VMCORE_INFO select CRASH_RESERVE select CRASH_DUMP help diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9b142b9d5187..733f210ffda1 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -109,7 +109,7 @@ int ppc_do_canonicalize_irqs; EXPORT_SYMBOL(ppc_do_canonicalize_irqs); #endif -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO /* This keeps a track of which one is the crashing cpu. */ int crashing_cpu = -1; #endif diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index bb7657115f1d..c9a9b759cc92 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..d6fd8dcfceb5 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -92,7 +92,7 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c deleted file mode 100644 index d18d529fd9b9..000000000000 --- a/arch/riscv/kernel/crash_core.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include -#include - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(phys_ram_base); - - vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); - vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); -#ifdef CONFIG_MMU - VMCOREINFO_NUMBER(VA_BITS); - vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); - vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); -#ifdef CONFIG_64BIT - vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); - vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); -#endif -#endif - vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); - vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", - kernel_map.va_kernel_pa_offset); -} diff --git a/arch/riscv/kernel/vmcore_info.c b/arch/riscv/kernel/vmcore_info.c new file mode 100644 index 000000000000..6d7a22522d63 --- /dev/null +++ b/arch/riscv/kernel/vmcore_info.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(phys_ram_base); + + vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); + vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); + vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); + vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); +#ifdef CONFIG_64BIT + vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); + vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); +#endif +#endif + vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); + vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", + kernel_map.va_kernel_pa_offset); +} diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0000325ab98f..913d4022131e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -98,7 +98,7 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_RETHOOK) += rethook.o -obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/crash_core_32.c deleted file mode 100644 index 8a89c109e20a..000000000000 --- a/arch/x86/kernel/crash_core_32.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include -#include - -#include - -void arch_crash_save_vmcoreinfo(void) -{ -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif -#ifdef CONFIG_X86_PAE - VMCOREINFO_CONFIG(X86_PAE); -#endif -} diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/crash_core_64.c deleted file mode 100644 index 7d255f882afe..000000000000 --- a/arch/x86/kernel/crash_core_64.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include -#include - -#include - -void arch_crash_save_vmcoreinfo(void) -{ - u64 sme_mask = sme_me_mask; - - VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_top_pgt); - vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", - pgtable_l5_enabled()); - -#ifdef CONFIG_NUMA - VMCOREINFO_SYMBOL(node_data); - VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); -#endif - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); - VMCOREINFO_NUMBER(sme_mask); -} diff --git a/arch/x86/kernel/vmcore_info_32.c b/arch/x86/kernel/vmcore_info_32.c new file mode 100644 index 000000000000..5995a749288a --- /dev/null +++ b/arch/x86/kernel/vmcore_info_32.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif +#ifdef CONFIG_X86_PAE + VMCOREINFO_CONFIG(X86_PAE); +#endif +} diff --git a/arch/x86/kernel/vmcore_info_64.c b/arch/x86/kernel/vmcore_info_64.c new file mode 100644 index 000000000000..0dec7d868754 --- /dev/null +++ b/arch/x86/kernel/vmcore_info_64.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include + +void arch_crash_save_vmcoreinfo(void) +{ + u64 sme_mask = sme_me_mask; + + VMCOREINFO_NUMBER(phys_base); + VMCOREINFO_SYMBOL(init_top_pgt); + vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", + pgtable_l5_enabled()); + +#ifdef CONFIG_NUMA + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); + VMCOREINFO_NUMBER(sme_mask); +} diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 03da9a4354f8..5f43dfa22f79 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include MODULE_AUTHOR("Gabriel L. Somlo "); MODULE_DESCRIPTION("QEMU fw_cfg sysfs support"); @@ -67,7 +67,7 @@ static void fw_cfg_sel_endianness(u16 key) iowrite16(key, fw_cfg_reg_ctrl); } -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO static inline bool fw_cfg_dma_enabled(void) { return (fw_cfg_rev & FW_CFG_VERSION_DMA) && fw_cfg_reg_dma; @@ -156,7 +156,7 @@ static ssize_t fw_cfg_read_blob(u16 key, return count; } -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO /* write chunk of given fw_cfg blob (caller responsible for sanity-check) */ static ssize_t fw_cfg_write_blob(u16 key, void *buf, loff_t pos, size_t count) @@ -195,7 +195,7 @@ end: return ret; } -#endif /* CONFIG_CRASH_CORE */ +#endif /* CONFIG_VMCORE_INFO */ /* clean up fw_cfg device i/o */ static void fw_cfg_io_cleanup(void) @@ -319,7 +319,7 @@ struct fw_cfg_sysfs_entry { struct list_head list; }; -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO static ssize_t fw_cfg_write_vmcoreinfo(const struct fw_cfg_file *f) { static struct fw_cfg_vmcoreinfo *data; @@ -343,7 +343,7 @@ static ssize_t fw_cfg_write_vmcoreinfo(const struct fw_cfg_file *f) kfree(data); return ret; } -#endif /* CONFIG_CRASH_CORE */ +#endif /* CONFIG_VMCORE_INFO */ /* get fw_cfg_sysfs_entry from kobject member */ static inline struct fw_cfg_sysfs_entry *to_entry(struct kobject *kobj) @@ -583,7 +583,7 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) int err; struct fw_cfg_sysfs_entry *entry; -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO if (fw_cfg_dma_enabled() && strcmp(f->name, FW_CFG_VMCOREINFO_FILENAME) == 0 && !is_kdump_kernel()) { diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 32b1116ae137..d80a1431ef7b 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -32,7 +32,7 @@ config PROC_FS config PROC_KCORE bool "/proc/kcore support" if !ARM depends on PROC_FS && MMU - select CRASH_CORE + select VMCORE_INFO help Provides a virtual ELF core file of the live kernel. This can be read with gdb and other ELF tools. No modifications can be diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 6422e569b080..8e08a9a1b7ed 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -10,7 +10,7 @@ * Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar */ -#include +#include #include #include #include diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 8a582d242f06..20aa3c2d89f7 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -11,7 +11,7 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE) +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX]; void init_vmlinux_build_id(void); #else diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 1fde49246fa6..7f19f62018ef 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -6,79 +6,6 @@ #include #include -#define CRASH_CORE_NOTE_NAME "CORE" -#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) -#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) -#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) - -/* - * The per-cpu notes area is a list of notes terminated by a "NULL" - * note header. For kdump, the code in vmcore.c runs in the context - * of the second kernel to combine them into one note. - */ -#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ - CRASH_CORE_NOTE_NAME_BYTES + \ - CRASH_CORE_NOTE_DESC_BYTES) - -#define VMCOREINFO_BYTES PAGE_SIZE -#define VMCOREINFO_NOTE_NAME "VMCOREINFO" -#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) -#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ - VMCOREINFO_NOTE_NAME_BYTES + \ - VMCOREINFO_BYTES) - -typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; -/* Per cpu memory for storing cpu states in case of system crash. */ -extern note_buf_t __percpu *crash_notes; - -void crash_update_vmcoreinfo_safecopy(void *ptr); -void crash_save_vmcoreinfo(void); -void arch_crash_save_vmcoreinfo(void); -__printf(1, 2) -void vmcoreinfo_append_str(const char *fmt, ...); -phys_addr_t paddr_vmcoreinfo_note(void); - -#define VMCOREINFO_OSRELEASE(value) \ - vmcoreinfo_append_str("OSRELEASE=%s\n", value) -#define VMCOREINFO_BUILD_ID() \ - ({ \ - static_assert(sizeof(vmlinux_build_id) == 20); \ - vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \ - }) - -#define VMCOREINFO_PAGESIZE(value) \ - vmcoreinfo_append_str("PAGESIZE=%ld\n", value) -#define VMCOREINFO_SYMBOL(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) -#define VMCOREINFO_SYMBOL_ARRAY(name) \ - vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) -#define VMCOREINFO_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(name)) -#define VMCOREINFO_STRUCT_SIZE(name) \ - vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ - (unsigned long)sizeof(struct name)) -#define VMCOREINFO_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(struct name, field)) -#define VMCOREINFO_TYPE_OFFSET(name, field) \ - vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ - (unsigned long)offsetof(name, field)) -#define VMCOREINFO_LENGTH(name, value) \ - vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) -#define VMCOREINFO_NUMBER(name) \ - vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) -#define VMCOREINFO_CONFIG(name) \ - vmcoreinfo_append_str("CONFIG_%s=y\n", #name) - -extern unsigned char *vmcoreinfo_data; -extern size_t vmcoreinfo_size; -extern u32 *vmcoreinfo_note; - -Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, - void *data, size_t data_len); -void final_note(Elf_Word *buf); - /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6d79bfb52e5b..9c7bb8b56ed6 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -16,6 +16,7 @@ #if !defined(__ASSEMBLY__) #include +#include #include #include #include diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h new file mode 100644 index 000000000000..e1dec1a6a749 --- /dev/null +++ b/include/linux/vmcore_info.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_VMCORE_INFO_H +#define LINUX_VMCORE_INFO_H + +#include +#include +#include + +#define CRASH_CORE_NOTE_NAME "CORE" +#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) +#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) + +/* + * The per-cpu notes area is a list of notes terminated by a "NULL" + * note header. For kdump, the code in vmcore.c runs in the context + * of the second kernel to combine them into one note. + */ +#define CRASH_CORE_NOTE_BYTES ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + CRASH_CORE_NOTE_NAME_BYTES + \ + CRASH_CORE_NOTE_DESC_BYTES) + +#define VMCOREINFO_BYTES PAGE_SIZE +#define VMCOREINFO_NOTE_NAME "VMCOREINFO" +#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) +#define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ + VMCOREINFO_NOTE_NAME_BYTES + \ + VMCOREINFO_BYTES) + +typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +/* Per cpu memory for storing cpu states in case of system crash. */ +extern note_buf_t __percpu *crash_notes; + +void crash_update_vmcoreinfo_safecopy(void *ptr); +void crash_save_vmcoreinfo(void); +void arch_crash_save_vmcoreinfo(void); +__printf(1, 2) +void vmcoreinfo_append_str(const char *fmt, ...); +phys_addr_t paddr_vmcoreinfo_note(void); + +#define VMCOREINFO_OSRELEASE(value) \ + vmcoreinfo_append_str("OSRELEASE=%s\n", value) +#define VMCOREINFO_BUILD_ID() \ + ({ \ + static_assert(sizeof(vmlinux_build_id) == 20); \ + vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \ + }) + +#define VMCOREINFO_PAGESIZE(value) \ + vmcoreinfo_append_str("PAGESIZE=%ld\n", value) +#define VMCOREINFO_SYMBOL(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SYMBOL_ARRAY(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) +#define VMCOREINFO_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(name)) +#define VMCOREINFO_STRUCT_SIZE(name) \ + vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ + (unsigned long)sizeof(struct name)) +#define VMCOREINFO_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_TYPE_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(name, field)) +#define VMCOREINFO_LENGTH(name, value) \ + vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) +#define VMCOREINFO_NUMBER(name) \ + vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) +#define VMCOREINFO_CONFIG(name) \ + vmcoreinfo_append_str("CONFIG_%s=y\n", #name) + +extern unsigned char *vmcoreinfo_data; +extern size_t vmcoreinfo_size; +extern u32 *vmcoreinfo_note; + +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len); +void final_note(Elf_Word *buf); +#endif /* LINUX_VMCORE_INFO_H */ diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 8b7be71edd85..8faf27043432 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -5,11 +5,11 @@ menu "Kexec and crash features" config CRASH_RESERVE bool -config CRASH_CORE +config VMCORE_INFO bool config KEXEC_CORE - select CRASH_CORE + select VMCORE_INFO select CRASH_RESERVE bool diff --git a/kernel/Makefile b/kernel/Makefile index 05fa88b3ab74..649272a1d6b9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -68,9 +68,9 @@ obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o -obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o -obj-$(CONFIG_KEXEC_CORE) += kexec_core.o +obj-$(CONFIG_KEXEC_CORE) += kexec_core.o crash_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o diff --git a/kernel/crash_core.c b/kernel/crash_core.c index ae0d1ce89b46..2f4df1fe6f7a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -26,14 +26,6 @@ /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; -/* vmcoreinfo stuff */ -unsigned char *vmcoreinfo_data; -size_t vmcoreinfo_size; -u32 *vmcoreinfo_note; - -/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ -static unsigned char *vmcoreinfo_data_safecopy; - int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz) { @@ -195,204 +187,6 @@ int crash_exclude_mem_range(struct crash_mem *mem, return 0; } -Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, - void *data, size_t data_len) -{ - struct elf_note *note = (struct elf_note *)buf; - - note->n_namesz = strlen(name) + 1; - note->n_descsz = data_len; - note->n_type = type; - buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); - memcpy(buf, name, note->n_namesz); - buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); - memcpy(buf, data, data_len); - buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); - - return buf; -} - -void final_note(Elf_Word *buf) -{ - memset(buf, 0, sizeof(struct elf_note)); -} - -static void update_vmcoreinfo_note(void) -{ - u32 *buf = vmcoreinfo_note; - - if (!vmcoreinfo_size) - return; - buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - vmcoreinfo_size); - final_note(buf); -} - -void crash_update_vmcoreinfo_safecopy(void *ptr) -{ - if (ptr) - memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); - - vmcoreinfo_data_safecopy = ptr; -} - -void crash_save_vmcoreinfo(void) -{ - if (!vmcoreinfo_note) - return; - - /* Use the safe copy to generate vmcoreinfo note if have */ - if (vmcoreinfo_data_safecopy) - vmcoreinfo_data = vmcoreinfo_data_safecopy; - - vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds()); - update_vmcoreinfo_note(); -} - -void vmcoreinfo_append_str(const char *fmt, ...) -{ - va_list args; - char buf[0x50]; - size_t r; - - va_start(args, fmt); - r = vscnprintf(buf, sizeof(buf), fmt, args); - va_end(args); - - r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); - - memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); - - vmcoreinfo_size += r; - - WARN_ONCE(vmcoreinfo_size == VMCOREINFO_BYTES, - "vmcoreinfo data exceeds allocated size, truncating"); -} - -/* - * provide an empty default implementation here -- architecture - * code may override this - */ -void __weak arch_crash_save_vmcoreinfo(void) -{} - -phys_addr_t __weak paddr_vmcoreinfo_note(void) -{ - return __pa(vmcoreinfo_note); -} -EXPORT_SYMBOL(paddr_vmcoreinfo_note); - -static int __init crash_save_vmcoreinfo_init(void) -{ - vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); - if (!vmcoreinfo_data) { - pr_warn("Memory allocation for vmcoreinfo_data failed\n"); - return -ENOMEM; - } - - vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, - GFP_KERNEL | __GFP_ZERO); - if (!vmcoreinfo_note) { - free_page((unsigned long)vmcoreinfo_data); - vmcoreinfo_data = NULL; - pr_warn("Memory allocation for vmcoreinfo_note failed\n"); - return -ENOMEM; - } - - VMCOREINFO_OSRELEASE(init_uts_ns.name.release); - VMCOREINFO_BUILD_ID(); - VMCOREINFO_PAGESIZE(PAGE_SIZE); - - VMCOREINFO_SYMBOL(init_uts_ns); - VMCOREINFO_OFFSET(uts_namespace, name); - VMCOREINFO_SYMBOL(node_online_map); -#ifdef CONFIG_MMU - VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); -#endif - VMCOREINFO_SYMBOL(_stext); - vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", (unsigned long) VMALLOC_START); - -#ifndef CONFIG_NUMA - VMCOREINFO_SYMBOL(mem_map); - VMCOREINFO_SYMBOL(contig_page_data); -#endif -#ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL_ARRAY(mem_section); - VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); - VMCOREINFO_STRUCT_SIZE(mem_section); - VMCOREINFO_OFFSET(mem_section, section_mem_map); - VMCOREINFO_NUMBER(SECTION_SIZE_BITS); - VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); -#endif - VMCOREINFO_STRUCT_SIZE(page); - VMCOREINFO_STRUCT_SIZE(pglist_data); - VMCOREINFO_STRUCT_SIZE(zone); - VMCOREINFO_STRUCT_SIZE(free_area); - VMCOREINFO_STRUCT_SIZE(list_head); - VMCOREINFO_SIZE(nodemask_t); - VMCOREINFO_OFFSET(page, flags); - VMCOREINFO_OFFSET(page, _refcount); - VMCOREINFO_OFFSET(page, mapping); - VMCOREINFO_OFFSET(page, lru); - VMCOREINFO_OFFSET(page, _mapcount); - VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_head); - VMCOREINFO_OFFSET(pglist_data, node_zones); - VMCOREINFO_OFFSET(pglist_data, nr_zones); -#ifdef CONFIG_FLATMEM - VMCOREINFO_OFFSET(pglist_data, node_mem_map); -#endif - VMCOREINFO_OFFSET(pglist_data, node_start_pfn); - VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); - VMCOREINFO_OFFSET(pglist_data, node_id); - VMCOREINFO_OFFSET(zone, free_area); - VMCOREINFO_OFFSET(zone, vm_stat); - VMCOREINFO_OFFSET(zone, spanned_pages); - VMCOREINFO_OFFSET(free_area, free_list); - VMCOREINFO_OFFSET(list_head, next); - VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); - log_buf_vmcoreinfo_setup(); - VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); - VMCOREINFO_NUMBER(NR_FREE_PAGES); - VMCOREINFO_NUMBER(PG_lru); - VMCOREINFO_NUMBER(PG_private); - VMCOREINFO_NUMBER(PG_swapcache); - VMCOREINFO_NUMBER(PG_swapbacked); - VMCOREINFO_NUMBER(PG_slab); -#ifdef CONFIG_MEMORY_FAILURE - VMCOREINFO_NUMBER(PG_hwpoison); -#endif - VMCOREINFO_NUMBER(PG_head_mask); -#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) - VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); -#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) - VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif - -#ifdef CONFIG_KALLSYMS - VMCOREINFO_SYMBOL(kallsyms_names); - VMCOREINFO_SYMBOL(kallsyms_num_syms); - VMCOREINFO_SYMBOL(kallsyms_token_table); - VMCOREINFO_SYMBOL(kallsyms_token_index); -#ifdef CONFIG_KALLSYMS_BASE_RELATIVE - VMCOREINFO_SYMBOL(kallsyms_offsets); - VMCOREINFO_SYMBOL(kallsyms_relative_base); -#else - VMCOREINFO_SYMBOL(kallsyms_addresses); -#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ -#endif /* CONFIG_KALLSYMS */ - - arch_crash_save_vmcoreinfo(); - update_vmcoreinfo_note(); - - return 0; -} - -subsys_initcall(crash_save_vmcoreinfo_init); - static int __init crash_notes_memory_init(void) { /* Allocate memory for saving cpu registers. */ diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 1d4bc493b2f4..11526fc42bc2 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -154,7 +154,7 @@ KERNEL_ATTR_RW(kexec_crash_size); #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO static ssize_t vmcoreinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -177,7 +177,7 @@ KERNEL_ATTR_RO(crash_elfcorehdr_size); #endif -#endif /* CONFIG_CRASH_CORE */ +#endif /* CONFIG_VMCORE_INFO */ /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, @@ -265,7 +265,7 @@ static struct attribute * kernel_attrs[] = { &kexec_crash_loaded_attr.attr, &kexec_crash_size_attr.attr, #endif -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO &vmcoreinfo_attr.attr, #ifdef CONFIG_CRASH_HOTPLUG &crash_elfcorehdr_size_attr.attr, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..7d74b000b43a 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include #include @@ -951,7 +951,7 @@ const struct file_operations kmsg_fops = { .release = devkmsg_release, }; -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c new file mode 100644 index 000000000000..8f77e238a54f --- /dev/null +++ b/kernel/vmcore_info.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * crash.c - kernel crash support code. + * Copyright (C) 2002-2004 Eric Biederman + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include + +#include "kallsyms_internal.h" +#include "kexec_internal.h" + +/* vmcoreinfo stuff */ +unsigned char *vmcoreinfo_data; +size_t vmcoreinfo_size; +u32 *vmcoreinfo_note; + +/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ +static unsigned char *vmcoreinfo_data_safecopy; + +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len) +{ + struct elf_note *note = (struct elf_note *)buf; + + note->n_namesz = strlen(name) + 1; + note->n_descsz = data_len; + note->n_type = type; + buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); + memcpy(buf, name, note->n_namesz); + buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); + memcpy(buf, data, data_len); + buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); + + return buf; +} + +void final_note(Elf_Word *buf) +{ + memset(buf, 0, sizeof(struct elf_note)); +} + +static void update_vmcoreinfo_note(void) +{ + u32 *buf = vmcoreinfo_note; + + if (!vmcoreinfo_size) + return; + buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, + vmcoreinfo_size); + final_note(buf); +} + +void crash_update_vmcoreinfo_safecopy(void *ptr) +{ + if (ptr) + memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); + + vmcoreinfo_data_safecopy = ptr; +} + +void crash_save_vmcoreinfo(void) +{ + if (!vmcoreinfo_note) + return; + + /* Use the safe copy to generate vmcoreinfo note if have */ + if (vmcoreinfo_data_safecopy) + vmcoreinfo_data = vmcoreinfo_data_safecopy; + + vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds()); + update_vmcoreinfo_note(); +} + +void vmcoreinfo_append_str(const char *fmt, ...) +{ + va_list args; + char buf[0x50]; + size_t r; + + va_start(args, fmt); + r = vscnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); + + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); + + vmcoreinfo_size += r; + + WARN_ONCE(vmcoreinfo_size == VMCOREINFO_BYTES, + "vmcoreinfo data exceeds allocated size, truncating"); +} + +/* + * provide an empty default implementation here -- architecture + * code may override this + */ +void __weak arch_crash_save_vmcoreinfo(void) +{} + +phys_addr_t __weak paddr_vmcoreinfo_note(void) +{ + return __pa(vmcoreinfo_note); +} +EXPORT_SYMBOL(paddr_vmcoreinfo_note); + +static int __init crash_save_vmcoreinfo_init(void) +{ + vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); + if (!vmcoreinfo_data) { + pr_warn("Memory allocation for vmcoreinfo_data failed\n"); + return -ENOMEM; + } + + vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, + GFP_KERNEL | __GFP_ZERO); + if (!vmcoreinfo_note) { + free_page((unsigned long)vmcoreinfo_data); + vmcoreinfo_data = NULL; + pr_warn("Memory allocation for vmcoreinfo_note failed\n"); + return -ENOMEM; + } + + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_BUILD_ID(); + VMCOREINFO_PAGESIZE(PAGE_SIZE); + + VMCOREINFO_SYMBOL(init_uts_ns); + VMCOREINFO_OFFSET(uts_namespace, name); + VMCOREINFO_SYMBOL(node_online_map); +#ifdef CONFIG_MMU + VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); +#endif + VMCOREINFO_SYMBOL(_stext); + vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", (unsigned long) VMALLOC_START); + +#ifndef CONFIG_NUMA + VMCOREINFO_SYMBOL(mem_map); + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#ifdef CONFIG_SPARSEMEM + VMCOREINFO_SYMBOL_ARRAY(mem_section); + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); + VMCOREINFO_STRUCT_SIZE(mem_section); + VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(SECTION_SIZE_BITS); + VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); +#endif + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); + VMCOREINFO_OFFSET(page, flags); + VMCOREINFO_OFFSET(page, _refcount); + VMCOREINFO_OFFSET(page, mapping); + VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(page, _mapcount); + VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(page, compound_head); + VMCOREINFO_OFFSET(pglist_data, node_zones); + VMCOREINFO_OFFSET(pglist_data, nr_zones); +#ifdef CONFIG_FLATMEM + VMCOREINFO_OFFSET(pglist_data, node_mem_map); +#endif + VMCOREINFO_OFFSET(pglist_data, node_start_pfn); + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); + VMCOREINFO_OFFSET(pglist_data, node_id); + VMCOREINFO_OFFSET(zone, free_area); + VMCOREINFO_OFFSET(zone, vm_stat); + VMCOREINFO_OFFSET(zone, spanned_pages); + VMCOREINFO_OFFSET(free_area, free_list); + VMCOREINFO_OFFSET(list_head, next); + VMCOREINFO_OFFSET(list_head, prev); + VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); + log_buf_vmcoreinfo_setup(); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); + VMCOREINFO_NUMBER(NR_FREE_PAGES); + VMCOREINFO_NUMBER(PG_lru); + VMCOREINFO_NUMBER(PG_private); + VMCOREINFO_NUMBER(PG_swapcache); + VMCOREINFO_NUMBER(PG_swapbacked); + VMCOREINFO_NUMBER(PG_slab); +#ifdef CONFIG_MEMORY_FAILURE + VMCOREINFO_NUMBER(PG_hwpoison); +#endif + VMCOREINFO_NUMBER(PG_head_mask); +#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) + VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); +#ifdef CONFIG_HUGETLB_PAGE + VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) + VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); +#endif + +#ifdef CONFIG_KALLSYMS + VMCOREINFO_SYMBOL(kallsyms_names); + VMCOREINFO_SYMBOL(kallsyms_num_syms); + VMCOREINFO_SYMBOL(kallsyms_token_table); + VMCOREINFO_SYMBOL(kallsyms_token_index); +#ifdef CONFIG_KALLSYMS_BASE_RELATIVE + VMCOREINFO_SYMBOL(kallsyms_offsets); + VMCOREINFO_SYMBOL(kallsyms_relative_base); +#else + VMCOREINFO_SYMBOL(kallsyms_addresses); +#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ +#endif /* CONFIG_KALLSYMS */ + + arch_crash_save_vmcoreinfo(); + update_vmcoreinfo_note(); + + return 0; +} + +subsys_initcall(crash_save_vmcoreinfo_init); diff --git a/lib/buildid.c b/lib/buildid.c index e3a7acdeef0e..3e6868c86b45 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -174,7 +174,7 @@ int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size) return parse_build_id_buf(build_id, NULL, buf, buf_size); } -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE) +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX] __ro_after_init; /** -- cgit v1.2.3 From 2c44b67e2ef345c44095d241530c10cfdd610960 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:43 +0800 Subject: crash: remove dependency of FA_DUMP on CRASH_DUMP In kdump kernel, /proc/vmcore is an elf file mapping the crashed kernel's old memory content. Its elf header is constructed in 1st kernel and passed to kdump kernel via elfcorehdr_addr. Config CRASH_DUMP enables the code of 1st kernel's old memory accessing in different architectures. Currently, config FA_DUMP has dependency on CRASH_DUMP because fadump needs access global variable 'elfcorehdr_addr' to judge if it's in kdump kernel within function is_kdump_kernel(). In the current kernel/crash_dump.c, variable 'elfcorehdr_addr' is defined, and function setup_elfcorehdr() used to parse kernel parameter to fetch the passed value of elfcorehdr_addr. Only for accessing elfcorehdr_addr, FA_DUMP really doesn't have to depends on CRASH_DUMP. To remove the dependency of FA_DUMP on CRASH_DUMP to avoid confusion, rename kernel/crash_dump.c to kernel/elfcorehdr.c, and build it when CONFIG_VMCORE_INFO is ebabled. With this, FA_DUMP doesn't need to depend on CRASH_DUMP. [bhe@redhat.com: power/fadump: make FA_DUMP select CRASH_DUMP] Link: https://lkml.kernel.org/r/Zb8D1ASrgX0qVm9z@MiWiFi-R3L-srv Link: https://lkml.kernel.org/r/20240124051254.67105-4-bhe@redhat.com Signed-off-by: Baoquan He Acked-by: Hari Bathini Cc: Al Viro Cc: Eric W. Biederman Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- arch/powerpc/Kconfig | 2 -- kernel/Makefile | 3 +-- kernel/crash_dump.c | 41 ----------------------------------------- kernel/elfcorehdr.c | 41 +++++++++++++++++++++++++++++++++++++++++ kernel/kexec_internal.h | 2 ++ 5 files changed, 44 insertions(+), 45 deletions(-) delete mode 100644 kernel/crash_dump.c create mode 100644 kernel/elfcorehdr.c (limited to 'kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 495d197c9b27..a9efaf87966d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -690,8 +690,6 @@ config ARCH_SELECTS_CRASH_DUMP config FA_DUMP bool "Firmware-assisted dump" depends on PPC64 && (PPC_RTAS || PPC_POWERNV) - select VMCORE_INFO - select CRASH_RESERVE select CRASH_DUMP help A robust mechanism to get reliable kernel crash dump with diff --git a/kernel/Makefile b/kernel/Makefile index 649272a1d6b9..35abc65e1f1a 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -68,7 +68,7 @@ obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o -obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o elfcorehdr.o obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o crash_core.o obj-$(CONFIG_KEXEC) += kexec.o @@ -121,7 +121,6 @@ obj-$(CONFIG_PERF_EVENTS) += events/ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o obj-$(CONFIG_PADATA) += padata.o -obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c deleted file mode 100644 index 92da32275af5..000000000000 --- a/kernel/crash_dump.c +++ /dev/null @@ -1,41 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include -#include -#include -#include -#include - -/* - * stores the physical address of elf header of crash image - * - * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by - * is_kdump_kernel() to determine if we are booting after a panic. Hence put - * it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. - */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; -EXPORT_SYMBOL_GPL(elfcorehdr_addr); - -/* - * stores the size of elf header of crash image - */ -unsigned long long elfcorehdr_size; - -/* - * elfcorehdr= specifies the location of elf core header stored by the crashed - * kernel. This option will be passed by kexec loader to the capture kernel. - * - * Syntax: elfcorehdr=[size[KMG]@]offset[KMG] - */ -static int __init setup_elfcorehdr(char *arg) -{ - char *end; - if (!arg) - return -EINVAL; - elfcorehdr_addr = memparse(arg, &end); - if (*end == '@') { - elfcorehdr_size = elfcorehdr_addr; - elfcorehdr_addr = memparse(end + 1, &end); - } - return end > arg ? 0 : -EINVAL; -} -early_param("elfcorehdr", setup_elfcorehdr); diff --git a/kernel/elfcorehdr.c b/kernel/elfcorehdr.c new file mode 100644 index 000000000000..92da32275af5 --- /dev/null +++ b/kernel/elfcorehdr.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include + +/* + * stores the physical address of elf header of crash image + * + * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by + * is_kdump_kernel() to determine if we are booting after a panic. Hence put + * it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. + */ +unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +EXPORT_SYMBOL_GPL(elfcorehdr_addr); + +/* + * stores the size of elf header of crash image + */ +unsigned long long elfcorehdr_size; + +/* + * elfcorehdr= specifies the location of elf core header stored by the crashed + * kernel. This option will be passed by kexec loader to the capture kernel. + * + * Syntax: elfcorehdr=[size[KMG]@]offset[KMG] + */ +static int __init setup_elfcorehdr(char *arg) +{ + char *end; + if (!arg) + return -EINVAL; + elfcorehdr_addr = memparse(arg, &end); + if (*end == '@') { + elfcorehdr_size = elfcorehdr_addr; + elfcorehdr_addr = memparse(end + 1, &end); + } + return end > arg ? 0 : -EINVAL; +} +early_param("elfcorehdr", setup_elfcorehdr); diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 74da1409cd14..2595defe8c0d 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -4,6 +4,8 @@ #include +struct kexec_segment; + struct kimage *do_kimage_alloc_init(void); int sanity_check_segment_list(struct kimage *image); void kimage_free_page_list(struct list_head *list); -- cgit v1.2.3 From 02aff8480533817a29e820729360866441d7403d Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:44 +0800 Subject: crash: split crash dumping code out from kexec_core.c Currently, KEXEC_CORE select CRASH_CORE automatically because crash codes need be built in to avoid compiling error when building kexec code even though the crash dumping functionality is not enabled. E.g -------------------- CONFIG_CRASH_CORE=y CONFIG_KEXEC_CORE=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y --------------------- After splitting out crashkernel reservation code and vmcoreinfo exporting code, there's only crash related code left in kernel/crash_core.c. Now move crash related codes from kexec_core.c to crash_core.c and only build it in when CONFIG_CRASH_DUMP=y. And also wrap up crash codes inside CONFIG_CRASH_DUMP ifdeffery scope, or replace inappropriate CONFIG_KEXEC_CORE ifdef with CONFIG_CRASH_DUMP ifdef in generic kernel files. With these changes, crash_core codes are abstracted from kexec codes and can be disabled at all if only kexec reboot feature is wanted. Link: https://lkml.kernel.org/r/20240124051254.67105-5-bhe@redhat.com Signed-off-by: Baoquan He Cc: Al Viro Cc: Eric W. Biederman Cc: Hari Bathini Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- drivers/base/cpu.c | 6 +- include/linux/crash_core.h | 61 +++++++++++ include/linux/kexec.h | 45 +------- init/initramfs.c | 2 +- kernel/Makefile | 3 +- kernel/crash_core.c | 256 +++++++++++++++++++++++++++++++++++++++++++++ kernel/kexec.c | 11 +- kernel/kexec_core.c | 250 +++---------------------------------------- kernel/kexec_file.c | 13 ++- kernel/ksysfs.c | 4 + 10 files changed, 359 insertions(+), 292 deletions(-) (limited to 'kernel') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 47de0f140ba6..b621a0fc75e1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ #endif /* CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP #include static ssize_t crash_notes_show(struct device *dev, @@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = { #endif static const struct attribute_group *common_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP &crash_note_cpu_attr_group, #endif NULL }; static const struct attribute_group *hotplugable_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP &crash_note_cpu_attr_group, #endif NULL diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 7f19f62018ef..23270b16e1db 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -6,6 +6,48 @@ #include #include +struct kimage; + +#ifdef CONFIG_CRASH_DUMP + +int crash_shrink_memory(unsigned long new_size); +ssize_t crash_get_memory_size(void); + +#ifndef arch_kexec_protect_crashkres +/* + * Protection mechanism for crashkernel reserved memory after + * the kdump kernel is loaded. + * + * Provide an empty default implementation here -- architecture + * code may override this + */ +static inline void arch_kexec_protect_crashkres(void) { } +#endif + +#ifndef arch_kexec_unprotect_crashkres +static inline void arch_kexec_unprotect_crashkres(void) { } +#endif + + + +#ifndef arch_crash_handle_hotplug_event +static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } +#endif + +int crash_check_update_elfcorehdr(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; } +#endif + +#ifndef crash_get_elfcorehdr_size +static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } +#endif + /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -31,4 +73,23 @@ struct kexec_segment; #define KEXEC_CRASH_HP_REMOVE_MEMORY 4 #define KEXEC_CRASH_HP_INVALID_CPU -1U +extern void __crash_kexec(struct pt_regs *regs); +extern void crash_kexec(struct pt_regs *regs); +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); + +#else /* !CONFIG_CRASH_DUMP*/ +struct pt_regs; +struct task_struct; +struct kimage; +static inline void __crash_kexec(struct pt_regs *regs) { } +static inline void crash_kexec(struct pt_regs *regs) { } +static inline int kexec_should_crash(struct task_struct *p) { return 0; } +static inline int kexec_crash_loaded(void) { return 0; } +static inline void crash_save_cpu(struct pt_regs *regs, int cpu) {}; +static inline int kimage_crash_copy_vmcoreinfo(struct kimage *image) { return 0; }; +#endif /* CONFIG_CRASH_DUMP*/ + #endif /* LINUX_CRASH_CORE_H */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9c7bb8b56ed6..060835bb82d5 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -15,7 +15,6 @@ #if !defined(__ASSEMBLY__) -#include #include #include #include @@ -33,6 +32,7 @@ extern note_buf_t __percpu *crash_notes; #include #include #include +#include /* Verify architecture specific macros are defined */ @@ -380,13 +380,6 @@ extern struct page *kimage_alloc_control_pages(struct kimage *image, static inline int machine_kexec_post_load(struct kimage *image) { return 0; } #endif -extern void __crash_kexec(struct pt_regs *); -extern void crash_kexec(struct pt_regs *); -int kexec_should_crash(struct task_struct *); -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 struct kimage *kexec_image; extern struct kimage *kexec_crash_image; @@ -410,24 +403,6 @@ bool kexec_load_permitted(int kexec_image_type); /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; -int crash_shrink_memory(unsigned long new_size); -ssize_t crash_get_memory_size(void); - -#ifndef arch_kexec_protect_crashkres -/* - * Protection mechanism for crashkernel reserved memory after - * the kdump kernel is loaded. - * - * Provide an empty default implementation here -- architecture - * code may override this - */ -static inline void arch_kexec_protect_crashkres(void) { } -#endif - -#ifndef arch_kexec_unprotect_crashkres -static inline void arch_kexec_unprotect_crashkres(void) { } -#endif - #ifndef page_to_boot_pfn static inline unsigned long page_to_boot_pfn(struct page *page) { @@ -484,24 +459,6 @@ static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { } #endif -#ifndef arch_crash_handle_hotplug_event -static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } -#endif - -int crash_check_update_elfcorehdr(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; } -#endif - -#ifndef crash_get_elfcorehdr_size -static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } -#endif - extern bool kexec_file_dbg_print; #define kexec_dprintk(fmt, ...) \ diff --git a/init/initramfs.c b/init/initramfs.c index 76deb48c38cb..6f095f54eec9 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -642,7 +642,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) "initrd"); } -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_RESERVE static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); diff --git a/kernel/Makefile b/kernel/Makefile index 35abc65e1f1a..3c13240dfc9f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -70,7 +70,8 @@ obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o elfcorehdr.o obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o -obj-$(CONFIG_KEXEC_CORE) += kexec_core.o crash_core.o +obj-$(CONFIG_KEXEC_CORE) += kexec_core.o +obj-$(CONFIG_CRASH_DUMP) += crash_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 2f4df1fe6f7a..78b5dc7cee3a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -11,9 +11,14 @@ #include #include #include +#include #include #include #include +#include +#include +#include +#include #include #include @@ -26,6 +31,131 @@ /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; +#ifdef CONFIG_CRASH_DUMP + +int kimage_crash_copy_vmcoreinfo(struct kimage *image) +{ + struct page *vmcoreinfo_page; + void *safecopy; + + if (!IS_ENABLED(CONFIG_CRASH_DUMP)) + return 0; + if (image->type != KEXEC_TYPE_CRASH) + return 0; + + /* + * For kdump, allocate one vmcoreinfo safe copy from the + * crash memory. as we have arch_kexec_protect_crashkres() + * after kexec syscall, we naturally protect it from write + * (even read) access under kernel direct mapping. But on + * the other hand, we still need to operate it when crash + * happens to generate vmcoreinfo note, hereby we rely on + * vmap for this purpose. + */ + vmcoreinfo_page = kimage_alloc_control_pages(image, 0); + if (!vmcoreinfo_page) { + pr_warn("Could not allocate vmcoreinfo buffer\n"); + return -ENOMEM; + } + safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); + if (!safecopy) { + pr_warn("Could not vmap vmcoreinfo buffer\n"); + return -ENOMEM; + } + + image->vmcoreinfo_data_copy = safecopy; + crash_update_vmcoreinfo_safecopy(safecopy); + + return 0; +} + + + +int kexec_should_crash(struct task_struct *p) +{ + /* + * If crash_kexec_post_notifiers is enabled, don't run + * crash_kexec() here yet, which must be run after panic + * notifiers in panic(). + */ + if (crash_kexec_post_notifiers) + return 0; + /* + * There are 4 panic() calls in make_task_dead() path, each of which + * corresponds to each of these 4 conditions. + */ + if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) + return 1; + return 0; +} + +int kexec_crash_loaded(void) +{ + return !!kexec_crash_image; +} +EXPORT_SYMBOL_GPL(kexec_crash_loaded); + +/* + * No panic_cpu check version of crash_kexec(). This function is called + * only when panic_cpu holds the current CPU number; this is the only CPU + * which processes crash_kexec routines. + */ +void __noclone __crash_kexec(struct pt_regs *regs) +{ + /* Take the kexec_lock here to prevent sys_kexec_load + * running on one cpu from replacing the crash kernel + * we are using after a panic on a different cpu. + * + * If the crash kernel was not located in a fixed area + * of memory the xchg(&kexec_crash_image) would be + * sufficient. But since I reuse the memory... + */ + if (kexec_trylock()) { + if (kexec_crash_image) { + struct pt_regs fixed_regs; + + crash_setup_regs(&fixed_regs, regs); + crash_save_vmcoreinfo(); + machine_crash_shutdown(&fixed_regs); + machine_kexec(kexec_crash_image); + } + kexec_unlock(); + } +} +STACK_FRAME_NON_STANDARD(__crash_kexec); + +__bpf_kfunc void crash_kexec(struct pt_regs *regs) +{ + int old_cpu, this_cpu; + + /* + * Only one CPU is allowed to execute the crash_kexec() code as with + * panic(). Otherwise parallel calls of panic() and crash_kexec() + * may stop each other. To exclude them, we use panic_cpu here too. + */ + old_cpu = PANIC_CPU_INVALID; + this_cpu = raw_smp_processor_id(); + + if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { + /* This is the 1st CPU which comes here, so go ahead. */ + __crash_kexec(regs); + + /* + * Reset panic_cpu to allow another panic()/crash_kexec() + * call. + */ + atomic_set(&panic_cpu, PANIC_CPU_INVALID); + } +} + +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) { @@ -187,6 +317,130 @@ int crash_exclude_mem_range(struct crash_mem *mem, return 0; } +ssize_t crash_get_memory_size(void) +{ + ssize_t size = 0; + + if (!kexec_trylock()) + return -EBUSY; + + size += crash_resource_size(&crashk_res); + size += crash_resource_size(&crashk_low_res); + + kexec_unlock(); + return size; +} + +static int __crash_shrink_memory(struct resource *old_res, + unsigned long new_size) +{ + struct resource *ram_res; + + ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); + if (!ram_res) + return -ENOMEM; + + ram_res->start = old_res->start + new_size; + ram_res->end = old_res->end; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; + ram_res->name = "System RAM"; + + if (!new_size) { + release_resource(old_res); + old_res->start = 0; + old_res->end = 0; + } else { + crashk_res.end = ram_res->start - 1; + } + + crash_free_reserved_phys_range(ram_res->start, ram_res->end); + insert_resource(&iomem_resource, ram_res); + + return 0; +} + +int crash_shrink_memory(unsigned long new_size) +{ + int ret = 0; + unsigned long old_size, low_size; + + if (!kexec_trylock()) + return -EBUSY; + + if (kexec_crash_image) { + ret = -ENOENT; + goto unlock; + } + + low_size = crash_resource_size(&crashk_low_res); + old_size = crash_resource_size(&crashk_res) + low_size; + new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); + if (new_size >= old_size) { + ret = (new_size == old_size) ? 0 : -EINVAL; + goto unlock; + } + + /* + * (low_size > new_size) implies that low_size is greater than zero. + * This also means that if low_size is zero, the else branch is taken. + * + * If low_size is greater than 0, (low_size > new_size) indicates that + * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res + * needs to be shrunken. + */ + if (low_size > new_size) { + ret = __crash_shrink_memory(&crashk_res, 0); + if (ret) + goto unlock; + + ret = __crash_shrink_memory(&crashk_low_res, new_size); + } else { + ret = __crash_shrink_memory(&crashk_res, new_size - low_size); + } + + /* Swap crashk_res and crashk_low_res if needed */ + if (!crashk_res.end && crashk_low_res.end) { + crashk_res.start = crashk_low_res.start; + crashk_res.end = crashk_low_res.end; + release_resource(&crashk_low_res); + crashk_low_res.start = 0; + crashk_low_res.end = 0; + insert_resource(&iomem_resource, &crashk_res); + } + +unlock: + kexec_unlock(); + return ret; +} + +void crash_save_cpu(struct pt_regs *regs, int cpu) +{ + struct elf_prstatus prstatus; + u32 *buf; + + if ((cpu < 0) || (cpu >= nr_cpu_ids)) + return; + + /* Using ELF notes here is opportunistic. + * I need a well defined structure format + * for the data I pass, and I need tags + * on the data to indicate what information I have + * squirrelled away. ELF notes happen to provide + * all of that, so there is no need to invent something new. + */ + buf = (u32 *)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); + prstatus.common.pr_pid = current->pid; + elf_core_copy_regs(&prstatus.pr_reg, regs); + buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); + final_note(buf); +} + + + static int __init crash_notes_memory_init(void) { /* Allocate memory for saving cpu registers. */ @@ -220,6 +474,8 @@ static int __init crash_notes_memory_init(void) } subsys_initcall(crash_notes_memory_init); +#endif /*CONFIG_CRASH_DUMP*/ + #ifdef CONFIG_CRASH_HOTPLUG #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt diff --git a/kernel/kexec.c b/kernel/kexec.c index 8f35a5a42af8..bab542fc1463 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -28,12 +28,14 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, struct kimage *image; bool kexec_on_panic = flags & KEXEC_ON_CRASH; +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Verify we have a valid entry point */ if ((entry < phys_to_boot_phys(crashk_res.start)) || (entry > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } +#endif /* Allocate and initialize a controlling structure */ image = do_kimage_alloc_init(); @@ -44,11 +46,13 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, image->nr_segments = nr_segments; memcpy(image->segment, segments, nr_segments * sizeof(*segments)); +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } +#endif ret = sanity_check_segment_list(image); if (ret) @@ -99,13 +103,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (!kexec_trylock()) return -EBUSY; +#ifdef CONFIG_CRASH_DUMP if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); - } else { + } else +#endif dest_image = &kexec_image; - } if (nr_segments == 0) { /* Uninstall image */ @@ -162,8 +167,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, image = xchg(dest_image, image); out: +#ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); +#endif kimage_free(image); out_unlock: diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d08fc7b5db97..ce3429e7972c 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -54,30 +54,6 @@ bool kexec_in_progress = false; bool kexec_file_dbg_print; -int kexec_should_crash(struct task_struct *p) -{ - /* - * If crash_kexec_post_notifiers is enabled, don't run - * crash_kexec() here yet, which must be run after panic - * notifiers in panic(). - */ - if (crash_kexec_post_notifiers) - return 0; - /* - * There are 4 panic() calls in make_task_dead() path, each of which - * corresponds to each of these 4 conditions. - */ - if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) - return 1; - return 0; -} - -int kexec_crash_loaded(void) -{ - return !!kexec_crash_image; -} -EXPORT_SYMBOL_GPL(kexec_crash_loaded); - /* * When kexec transitions to the new kernel there is a one-to-one * mapping between physical and virtual addresses. On processors @@ -209,6 +185,7 @@ int sanity_check_segment_list(struct kimage *image) if (total_pages > nr_pages / 2) return -EINVAL; +#ifdef CONFIG_CRASH_DUMP /* * Verify we have good destination addresses. Normally * the caller is responsible for making certain we don't @@ -231,6 +208,7 @@ int sanity_check_segment_list(struct kimage *image) return -EADDRNOTAVAIL; } } +#endif return 0; } @@ -403,6 +381,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, return pages; } +#ifdef CONFIG_CRASH_DUMP static struct page *kimage_alloc_crash_control_pages(struct kimage *image, unsigned int order) { @@ -468,6 +447,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, return pages; } +#endif struct page *kimage_alloc_control_pages(struct kimage *image, @@ -479,48 +459,16 @@ struct page *kimage_alloc_control_pages(struct kimage *image, case KEXEC_TYPE_DEFAULT: pages = kimage_alloc_normal_control_pages(image, order); break; +#ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: pages = kimage_alloc_crash_control_pages(image, order); break; +#endif } return pages; } -int kimage_crash_copy_vmcoreinfo(struct kimage *image) -{ - struct page *vmcoreinfo_page; - void *safecopy; - - if (image->type != KEXEC_TYPE_CRASH) - return 0; - - /* - * For kdump, allocate one vmcoreinfo safe copy from the - * crash memory. as we have arch_kexec_protect_crashkres() - * after kexec syscall, we naturally protect it from write - * (even read) access under kernel direct mapping. But on - * the other hand, we still need to operate it when crash - * happens to generate vmcoreinfo note, hereby we rely on - * vmap for this purpose. - */ - vmcoreinfo_page = kimage_alloc_control_pages(image, 0); - if (!vmcoreinfo_page) { - pr_warn("Could not allocate vmcoreinfo buffer\n"); - return -ENOMEM; - } - safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); - if (!safecopy) { - pr_warn("Could not vmap vmcoreinfo buffer\n"); - return -ENOMEM; - } - - image->vmcoreinfo_data_copy = safecopy; - crash_update_vmcoreinfo_safecopy(safecopy); - - return 0; -} - static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) @@ -603,10 +551,12 @@ void kimage_free(struct kimage *image) if (!image) return; +#ifdef CONFIG_CRASH_DUMP if (image->vmcoreinfo_data_copy) { crash_update_vmcoreinfo_safecopy(NULL); vunmap(image->vmcoreinfo_data_copy); } +#endif kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { @@ -824,6 +774,7 @@ out: return result; } +#ifdef CONFIG_CRASH_DUMP static int kimage_load_crash_segment(struct kimage *image, struct kexec_segment *segment) { @@ -891,6 +842,7 @@ static int kimage_load_crash_segment(struct kimage *image, out: return result; } +#endif int kimage_load_segment(struct kimage *image, struct kexec_segment *segment) @@ -901,9 +853,11 @@ int kimage_load_segment(struct kimage *image, case KEXEC_TYPE_DEFAULT: result = kimage_load_normal_segment(image, segment); break; +#ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: result = kimage_load_crash_segment(image, segment); break; +#endif } return result; @@ -1027,186 +981,6 @@ bool kexec_load_permitted(int kexec_image_type) return true; } -/* - * No panic_cpu check version of crash_kexec(). This function is called - * only when panic_cpu holds the current CPU number; this is the only CPU - * which processes crash_kexec routines. - */ -void __noclone __crash_kexec(struct pt_regs *regs) -{ - /* Take the kexec_lock here to prevent sys_kexec_load - * running on one cpu from replacing the crash kernel - * we are using after a panic on a different cpu. - * - * If the crash kernel was not located in a fixed area - * of memory the xchg(&kexec_crash_image) would be - * sufficient. But since I reuse the memory... - */ - if (kexec_trylock()) { - if (kexec_crash_image) { - struct pt_regs fixed_regs; - - crash_setup_regs(&fixed_regs, regs); - crash_save_vmcoreinfo(); - machine_crash_shutdown(&fixed_regs); - machine_kexec(kexec_crash_image); - } - kexec_unlock(); - } -} -STACK_FRAME_NON_STANDARD(__crash_kexec); - -__bpf_kfunc void crash_kexec(struct pt_regs *regs) -{ - int old_cpu, this_cpu; - - /* - * Only one CPU is allowed to execute the crash_kexec() code as with - * panic(). Otherwise parallel calls of panic() and crash_kexec() - * may stop each other. To exclude them, we use panic_cpu here too. - */ - old_cpu = PANIC_CPU_INVALID; - this_cpu = raw_smp_processor_id(); - - if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { - /* This is the 1st CPU which comes here, so go ahead. */ - __crash_kexec(regs); - - /* - * Reset panic_cpu to allow another panic()/crash_kexec() - * call. - */ - atomic_set(&panic_cpu, PANIC_CPU_INVALID); - } -} - -static inline resource_size_t crash_resource_size(const struct resource *res) -{ - return !res->end ? 0 : resource_size(res); -} - -ssize_t crash_get_memory_size(void) -{ - ssize_t size = 0; - - if (!kexec_trylock()) - return -EBUSY; - - size += crash_resource_size(&crashk_res); - size += crash_resource_size(&crashk_low_res); - - kexec_unlock(); - return size; -} - -static int __crash_shrink_memory(struct resource *old_res, - unsigned long new_size) -{ - struct resource *ram_res; - - ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); - if (!ram_res) - return -ENOMEM; - - ram_res->start = old_res->start + new_size; - ram_res->end = old_res->end; - ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; - ram_res->name = "System RAM"; - - if (!new_size) { - release_resource(old_res); - old_res->start = 0; - old_res->end = 0; - } else { - crashk_res.end = ram_res->start - 1; - } - - crash_free_reserved_phys_range(ram_res->start, ram_res->end); - insert_resource(&iomem_resource, ram_res); - - return 0; -} - -int crash_shrink_memory(unsigned long new_size) -{ - int ret = 0; - unsigned long old_size, low_size; - - if (!kexec_trylock()) - return -EBUSY; - - if (kexec_crash_image) { - ret = -ENOENT; - goto unlock; - } - - low_size = crash_resource_size(&crashk_low_res); - old_size = crash_resource_size(&crashk_res) + low_size; - new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); - if (new_size >= old_size) { - ret = (new_size == old_size) ? 0 : -EINVAL; - goto unlock; - } - - /* - * (low_size > new_size) implies that low_size is greater than zero. - * This also means that if low_size is zero, the else branch is taken. - * - * If low_size is greater than 0, (low_size > new_size) indicates that - * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res - * needs to be shrunken. - */ - if (low_size > new_size) { - ret = __crash_shrink_memory(&crashk_res, 0); - if (ret) - goto unlock; - - ret = __crash_shrink_memory(&crashk_low_res, new_size); - } else { - ret = __crash_shrink_memory(&crashk_res, new_size - low_size); - } - - /* Swap crashk_res and crashk_low_res if needed */ - if (!crashk_res.end && crashk_low_res.end) { - crashk_res.start = crashk_low_res.start; - crashk_res.end = crashk_low_res.end; - release_resource(&crashk_low_res); - crashk_low_res.start = 0; - crashk_low_res.end = 0; - insert_resource(&iomem_resource, &crashk_res); - } - -unlock: - kexec_unlock(); - return ret; -} - -void crash_save_cpu(struct pt_regs *regs, int cpu) -{ - struct elf_prstatus prstatus; - u32 *buf; - - if ((cpu < 0) || (cpu >= nr_cpu_ids)) - return; - - /* Using ELF notes here is opportunistic. - * I need a well defined structure format - * for the data I pass, and I need tags - * on the data to indicate what information I have - * squirrelled away. ELF notes happen to provide - * all of that, so there is no need to invent something new. - */ - buf = (u32 *)per_cpu_ptr(crash_notes, cpu); - if (!buf) - return; - memset(&prstatus, 0, sizeof(prstatus)); - prstatus.common.pr_pid = current->pid; - elf_core_copy_regs(&prstatus.pr_reg, regs); - buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, - &prstatus, sizeof(prstatus)); - final_note(buf); -} - /* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index bef2f6f2571b..ce7ce2ae27cd 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -285,11 +285,13 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG); image->file_mode = 1; +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } +#endif ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd, cmdline_ptr, cmdline_len, flags); @@ -349,13 +351,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (!kexec_trylock()) return -EBUSY; +#ifdef CONFIG_CRASH_DUMP if (image_type == KEXEC_TYPE_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); - } else { + } else +#endif dest_image = &kexec_image; - } if (flags & KEXEC_FILE_UNLOAD) goto exchange; @@ -419,8 +422,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, exchange: image = xchg(dest_image, image); out: +#ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); +#endif kexec_unlock(); kimage_free(image); @@ -595,12 +600,14 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, static int kexec_walk_resources(struct kexec_buf *kbuf, int (*func)(struct resource *, void *)) { +#ifdef CONFIG_CRASH_DUMP if (kbuf->image->type == KEXEC_TYPE_CRASH) return walk_iomem_res_desc(crashk_res.desc, IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, crashk_res.start, crashk_res.end, kbuf, func); - else if (kbuf->top_down) +#endif + if (kbuf->top_down) return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func); else return walk_system_ram_res(0, ULONG_MAX, kbuf, func); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 11526fc42bc2..fe7a517fc4ab 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -120,6 +120,7 @@ static ssize_t kexec_loaded_show(struct kobject *kobj, } KERNEL_ATTR_RO(kexec_loaded); +#ifdef CONFIG_CRASH_DUMP static ssize_t kexec_crash_loaded_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -152,6 +153,7 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj, } KERNEL_ATTR_RW(kexec_crash_size); +#endif /* CONFIG_CRASH_DUMP*/ #endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_VMCORE_INFO @@ -262,9 +264,11 @@ static struct attribute * kernel_attrs[] = { #endif #ifdef CONFIG_KEXEC_CORE &kexec_loaded_attr.attr, +#ifdef CONFIG_CRASH_DUMP &kexec_crash_loaded_attr.attr, &kexec_crash_size_attr.attr, #endif +#endif #ifdef CONFIG_VMCORE_INFO &vmcoreinfo_attr.attr, #ifdef CONFIG_CRASH_HOTPLUG -- cgit v1.2.3 From 75bc255a7444801d64c7a7bd09e3f452f86b3585 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:45 +0800 Subject: crash: clean up kdump related config items By splitting CRASH_RESERVE and VMCORE_INFO out from CRASH_CORE, cleaning up the dependency of FA_DMUMP on CRASH_DUMP, and moving crash codes from kexec_core.c to crash_core.c, now we can rearrange CRASH_DUMP to depend on KEXEC_CORE, and make CRASH_DUMP select CRASH_RESERVE and VMCORE_INFO. KEXEC_CORE won't select CRASH_RESERVE and VMCORE_INFO any more because KEXEC_CORE enables codes which allocate control pages, copy kexec/kdump segments, and prepare for switching. These codes are shared by both kexec reboot and crash dumping. Doing this makes codes and the corresponding config items more logical (the right item depends on or is selected by the left item). PROC_KCORE -----------> VMCORE_INFO |----------> VMCORE_INFO FA_DUMP----| |----------> CRASH_RESERVE ---->VMCORE_INFO / |---->CRASH_RESERVE KEXEC --| /| |--> KEXEC_CORE--> CRASH_DUMP-->/-|---->PROC_VMCORE KEXEC_FILE --| \ | \---->CRASH_HOTPLUG KEXEC --| |--> KEXEC_CORE--> kexec reboot KEXEC_FILE --| Link: https://lkml.kernel.org/r/20240124051254.67105-6-bhe@redhat.com Signed-off-by: Baoquan He Cc: Al Viro Cc: Eric W. Biederman Cc: Hari Bathini Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- kernel/Kconfig.kexec | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 8faf27043432..6c34e63c88ff 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -9,8 +9,6 @@ config VMCORE_INFO bool config KEXEC_CORE - select VMCORE_INFO - select CRASH_RESERVE bool config KEXEC_ELF @@ -99,8 +97,11 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" + default y depends on ARCH_SUPPORTS_CRASH_DUMP - select KEXEC_CORE + depends on KEXEC_CORE + select VMCORE_INFO + select CRASH_RESERVE help Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels -- cgit v1.2.3 From 40254101d87870b2e5ac3ddc28af40aa04c48486 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Jan 2024 13:12:47 +0800 Subject: arm64, crash: wrap crash dumping code into crash related ifdefs Now crash codes under kernel/ folder has been split out from kexec code, crash dumping can be separated from kexec reboot in config items on arm64 with some adjustments. Here wrap up crash dumping codes with CONFIG_CRASH_DUMP ifdeffery. [bhe@redhat.com: fix building error in generic codes] Link: https://lkml.kernel.org/r/20240129135033.157195-2-bhe@redhat.com Link: https://lkml.kernel.org/r/20240124051254.67105-8-bhe@redhat.com Signed-off-by: Baoquan He Cc: Al Viro Cc: Eric W. Biederman Cc: Hari Bathini Cc: Pingfan Liu Cc: Klara Modin Cc: Michael Kelley Cc: Nathan Chancellor Cc: Stephen Rothwell Cc: Yang Li Signed-off-by: Andrew Morton --- arch/arm64/include/asm/kexec.h | 2 +- arch/arm64/kernel/machine_kexec.c | 2 +- arch/arm64/kernel/machine_kexec_file.c | 10 ++++++++-- arch/arm64/mm/init.c | 2 +- drivers/of/kexec.c | 2 ++ kernel/kexec_file.c | 2 ++ 6 files changed, 15 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 9ac9572a3bbe..4d9cc7a76d9c 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -80,7 +80,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, } } -#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION) +#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_HIBERNATION) extern bool crash_is_nosave(unsigned long pfn); extern void crash_prepare_suspend(void); extern void crash_post_resume(void); diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index b38aae5b488d..82e2203d86a3 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -255,7 +255,7 @@ void machine_crash_shutdown(struct pt_regs *regs) pr_info("Starting crashdump kernel...\n"); } -#ifdef CONFIG_HIBERNATION +#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_HIBERNATION) /* * To preserve the crash dump kernel image, the relevant memory segments * should be mapped again around the hibernation. diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 0e017358f4ba..af1ca875c52c 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -39,6 +39,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) return kexec_image_post_load_cleanup_default(image); } +#ifdef CONFIG_CRASH_DUMP static int prepare_elf_headers(void **addr, unsigned long *sz) { struct crash_mem *cmem; @@ -80,6 +81,7 @@ out: kfree(cmem); return ret; } +#endif /* * Tries to add the initrd and DTB to the image. If it is not possible to find @@ -93,8 +95,8 @@ int load_other_segments(struct kimage *image, char *cmdline) { struct kexec_buf kbuf; - void *headers, *dtb = NULL; - unsigned long headers_sz, initrd_load_addr = 0, dtb_len, + void *dtb = NULL; + unsigned long initrd_load_addr = 0, dtb_len, orig_segments = image->nr_segments; int ret = 0; @@ -102,7 +104,10 @@ int load_other_segments(struct kimage *image, /* not allocate anything below the kernel */ kbuf.buf_min = kernel_load_addr + kernel_size; +#ifdef CONFIG_CRASH_DUMP /* load elf core header */ + void *headers; + unsigned long headers_sz; if (image->type == KEXEC_TYPE_CRASH) { ret = prepare_elf_headers(&headers, &headers_sz); if (ret) { @@ -130,6 +135,7 @@ int load_other_segments(struct kimage *image, kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); } +#endif /* load initrd */ if (initrd) { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 74c1db8ce271..c1f6213e77f3 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -100,7 +100,7 @@ static void __init arch_reserve_crashkernel(void) bool high = false; int ret; - if (!IS_ENABLED(CONFIG_KEXEC_CORE)) + if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index 68278340cecf..9ccde2fd77cb 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -395,6 +395,7 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image, if (ret) goto out; +#ifdef CONFIG_CRASH_DUMP /* add linux,usable-memory-range */ ret = fdt_appendprop_addrrange(fdt, 0, chosen_node, "linux,usable-memory-range", crashk_res.start, @@ -410,6 +411,7 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image, if (ret) goto out; } +#endif } /* add bootargs */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index ce7ce2ae27cd..2d1db05fbf04 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -540,8 +540,10 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, phys_addr_t mstart, mend; struct resource res = { }; +#ifdef CONFIG_CRASH_DUMP if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); +#endif /* * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See -- cgit v1.2.3 From 3fb43636876d98ed995e331782e4b06a00d24aee Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 19 Feb 2024 13:10:47 +0900 Subject: sched/numa, mm: do not try to migrate memory to memoryless nodes Memoryless nodes do not have any memory to migrate to, so, as an optimization, stop trying it. Link: https://lkml.kernel.org/r/20240219041920.1183-1-byungchul@sk.com Link: https://lkml.kernel.org/r/20240216111502.79759-1-byungchul@sk.com Fixes: c574bbe91703 ("NUMA balancing: optimize page placement for memory tiering system") Signed-off-by: Byungchul Park Reviewed-by: Oscar Salvador Reviewed-by: "Huang, Ying" Reviewed-by: Phil Auld Reviewed-by: Davidlohr Bueso Acked-by: David Hildenbrand Cc: Benjamin Segall Cc: Daniel Bristot de Oliveira Cc: Dietmar Eggemann Cc: Ingo Molnar Cc: Juri Lelli Cc: Mel Gorman Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Valentin Schneider Cc: Vincent Guittot Signed-off-by: Andrew Morton --- kernel/sched/fair.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 533547e3c90a..d8d71ad7f9f8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1830,6 +1830,12 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; + /* + * Cannot migrate to memoryless nodes. + */ + if (!node_state(dst_nid, N_MEMORY)) + return false; + /* * The pages in slow memory node should be migrated according * to hot/cold instead of private/shared. -- cgit v1.2.3 From 8f8cd6c0a43ed637e620bbe45a8d0e0c2f4d5130 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 27 Feb 2024 10:35:46 +0800 Subject: modules: wait do_free_init correctly The synchronization here is to ensure the ordering of freeing of a module init so that it happens before W+X checking. It is worth noting it is not that the freeing was not happening, it is just that our sanity checkers raced against the permission checkers which assume init memory is already gone. Commit 1a7b7d922081 ("modules: Use vmalloc special flag") moved calling do_free_init() into a global workqueue instead of relying on it being called through call_rcu(..., do_free_init), which used to allowed us call do_free_init() asynchronously after the end of a subsequent grace period. The move to a global workqueue broke the gaurantees for code which needed to be sure the do_free_init() would complete with rcu_barrier(). To fix this callers which used to rely on rcu_barrier() must now instead use flush_work(&init_free_wq). Without this fix, we still could encounter false positive reports in W+X checking since the rcu_barrier() here can not ensure the ordering now. Even worse, the rcu_barrier() can introduce significant delay. Eric Chanudet reported that the rcu_barrier introduces ~0.1s delay on a PREEMPT_RT kernel. [ 0.291444] Freeing unused kernel memory: 5568K [ 0.402442] Run /sbin/init as init process With this fix, the above delay can be eliminated. Link: https://lkml.kernel.org/r/20240227023546.2490667-1-changbin.du@huawei.com Fixes: 1a7b7d922081 ("modules: Use vmalloc special flag") Signed-off-by: Changbin Du Tested-by: Eric Chanudet Acked-by: Luis Chamberlain Cc: Xiaoyi Su Signed-off-by: Andrew Morton --- include/linux/moduleloader.h | 8 ++++++++ init/main.c | 5 +++-- kernel/module/main.c | 9 +++++++-- 3 files changed, 18 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 001b2ce83832..89b1e0ed9811 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -115,6 +115,14 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +#ifdef CONFIG_MODULES +void flush_module_init_free_work(void); +#else +static inline void flush_module_init_free_work(void) +{ +} +#endif + /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); diff --git a/init/main.c b/init/main.c index 749a9f8d2c9b..5ecd4e8cf6d3 100644 --- a/init/main.c +++ b/init/main.c @@ -88,6 +88,7 @@ #include #include #include +#include #include #include #include @@ -1403,11 +1404,11 @@ static void mark_readonly(void) if (rodata_enabled) { /* * load_module() results in W+X mappings, which are cleaned - * up with call_rcu(). Let's make sure that queued work is + * up with init_free_wq. Let's make sure that queued work is * flushed so that we don't hit false positives looking for * insecure pages which are W+X. */ - rcu_barrier(); + flush_module_init_free_work(); mark_rodata_ro(); debug_checkwx(); rodata_test(); diff --git a/kernel/module/main.c b/kernel/module/main.c index 36681911c05a..b0b99348e1a8 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2489,6 +2489,11 @@ static void do_free_init(struct work_struct *w) } } +void flush_module_init_free_work(void) +{ + flush_work(&init_free_wq); +} + #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." /* Default value for module->async_probe_requested */ @@ -2593,8 +2598,8 @@ static noinline int do_init_module(struct module *mod) * Note that module_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to - * be cleaned up needs to sync with the queued work - ie - * rcu_barrier() + * be cleaned up needs to sync with the queued work by invoking + * flush_module_init_free_work(). */ if (llist_add(&freeinit->node, &init_free_list)) schedule_work(&init_free_wq); -- cgit v1.2.3 From d3246b6ee42a155ab57e936841028fff3d7d98b4 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Tue, 27 Feb 2024 09:49:52 +0800 Subject: crash_core: export vmemmap when CONFIG_SPARSEMEM_VMEMMAP is enabled In memory_model.h, if CONFIG_SPARSEMEM_VMEMMAP is configed, kernel will use vmemmap to do the __pfn_to_page/page_to_pfn, and kernel will not use the "classic sparse" to do the __pfn_to_page/page_to_pfn. So export the vmemmap when CONFIG_SPARSEMEM_VMEMMAP is configed. This makes the user applications (crash, etc) get faster pfn_to_page/page_to_pfn operations too. Link: https://lkml.kernel.org/r/20240227014952.3184-1-shijie@os.amperecomputing.com Signed-off-by: Huang Shijie Acked-by: Baoquan He Cc: Dave Young Cc: Kazuhito Hagio Cc: Lianbo Jiang Cc: Vivek Goyal Signed-off-by: Andrew Morton --- kernel/vmcore_info.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index 8f77e238a54f..f95516cd45bb 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -152,6 +152,9 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(mem_map); VMCOREINFO_SYMBOL(contig_page_data); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP + VMCOREINFO_SYMBOL_ARRAY(vmemmap); +#endif #ifdef CONFIG_SPARSEMEM VMCOREINFO_SYMBOL_ARRAY(mem_section); VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); -- cgit v1.2.3 From eb52286634f042432ec775077a73334603a1c6e4 Mon Sep 17 00:00:00 2001 From: "Gang Li Subject: padata: dispatch works on" Date: Wed, 6 Mar 2024 13:04:17 -0800 Subject: Author: Gang Li padata: dispatch works on different nodes Date: Thu, 22 Feb 2024 22:04:17 +0800 When a group of tasks that access different nodes are scheduled on the same node, they may encounter bandwidth bottlenecks and access latency. Thus, numa_aware flag is introduced here, allowing tasks to be distributed across different nodes to fully utilize the advantage of multi-node systems. Link: https://lkml.kernel.org/r/20240222140422.393911-5-gang.li@linux.dev Signed-off-by: Gang Li Tested-by: David Rientjes Reviewed-by: Muchun Song Reviewed-by: Tim Chen Cc: Alexey Dobriyan Cc: Daniel Jordan Cc: David Hildenbrand Cc: Jane Chu Cc: Mike Kravetz Cc: Paul E. McKenney Cc: Randy Dunlap Cc: Steffen Klassert Signed-off-by: Andrew Morton --- include/linux/padata.h | 2 ++ kernel/padata.c | 14 ++++++++++++-- mm/mm_init.c | 1 + 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/padata.h b/include/linux/padata.h index 495b16b6b4d7..8f418711351b 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -137,6 +137,7 @@ struct padata_shell { * appropriate for one worker thread to do at once. * @max_threads: Max threads to use for the job, actual number may be less * depending on task size and minimum chunk size. + * @numa_aware: Distribute jobs to different nodes with CPU in a round robin fashion. */ struct padata_mt_job { void (*thread_fn)(unsigned long start, unsigned long end, void *arg); @@ -146,6 +147,7 @@ struct padata_mt_job { unsigned long align; unsigned long min_chunk; int max_threads; + bool numa_aware; }; /** diff --git a/kernel/padata.c b/kernel/padata.c index 179fb1518070..e3f639ff1670 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -485,7 +485,8 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) struct padata_work my_work, *pw; struct padata_mt_job_state ps; LIST_HEAD(works); - int nworks; + int nworks, nid; + static atomic_t last_used_nid __initdata; if (job->size == 0) return; @@ -517,7 +518,16 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) ps.chunk_size = roundup(ps.chunk_size, job->align); list_for_each_entry(pw, &works, pw_list) - queue_work(system_unbound_wq, &pw->pw_work); + if (job->numa_aware) { + int old_node = atomic_read(&last_used_nid); + + do { + nid = next_node_in(old_node, node_states[N_CPU]); + } while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid)); + queue_work_node(nid, system_unbound_wq, &pw->pw_work); + } else { + queue_work(system_unbound_wq, &pw->pw_work); + } /* Use the current thread, which saves starting a workqueue worker. */ padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK); diff --git a/mm/mm_init.c b/mm/mm_init.c index 2c19f5515e36..549e76af8f82 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2231,6 +2231,7 @@ static int __init deferred_init_memmap(void *data) .align = PAGES_PER_SECTION, .min_chunk = PAGES_PER_SECTION, .max_threads = max_threads, + .numa_aware = false, }; padata_do_multithreaded(&job); -- cgit v1.2.3