diff options
Diffstat (limited to 'arch/x86/kernel/crash.c')
| -rw-r--r-- | arch/x86/kernel/crash.c | 164 |
1 files changed, 105 insertions, 59 deletions
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 587c7743fd21..335fd2ee9766 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -26,6 +26,7 @@ #include <linux/vmalloc.h> #include <linux/memblock.h> +#include <asm/bootparam.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> @@ -40,6 +41,7 @@ #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> +#include <asm/sev.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -48,27 +50,6 @@ struct crash_memmap_data { unsigned int type; }; -/* - * This is used to VMCLEAR all VMCSs loaded on the - * processor. And when loading kvm_intel module, the - * callback function pointer will be assigned. - * - * protected by rcu. - */ -crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; -EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); - -static inline void cpu_crash_vmclear_loaded_vmcss(void) -{ - crash_vmclear_fn *do_vmclear_operation = NULL; - - rcu_read_lock(); - do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); - if (do_vmclear_operation) - do_vmclear_operation(); - rcu_read_unlock(); -} - #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) @@ -76,15 +57,12 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) crash_save_cpu(regs, cpu); /* - * VMCLEAR VMCSs loaded on all cpus if needed. - */ - cpu_crash_vmclear_loaded_vmcss(); - - /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); + kdump_sev_callback(); + disable_local_APIC(); } @@ -133,11 +111,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs) crash_smp_send_stop(); - /* - * VMCLEAR VMCSs loaded on this cpu if needed. - */ - cpu_crash_vmclear_loaded_vmcss(); - cpu_emergency_disable_virtualization(); /* @@ -155,7 +128,19 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif - crash_save_cpu(regs, safe_smp_processor_id()); + + /* + * Non-crash kexec calls enc_kexec_begin() while scheduling is still + * active. This allows the callback to wait until all in-flight + * shared<->private conversions are complete. In a crash scenario, + * enc_kexec_begin() gets called after all but one CPU have been shut + * down and interrupts have been disabled. This allows the callback to + * detect a race with the conversion and report it. + */ + x86_platform.guest.enc_kexec_begin(); + x86_platform.guest.enc_kexec_finish(); + + crash_save_cpu(regs, smp_processor_id()); } #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG) @@ -178,16 +163,25 @@ static struct crash_mem *fill_up_crash_elf_data(void) return NULL; /* - * Exclusion of crash region and/or crashk_low_res may cause - * another range split. So add extra two slots here. + * Exclusion of crash region, crashk_low_res and/or crashk_cma_ranges + * may cause range splits. So add extra slots here. + * + * Exclusion of low 1M may not cause another range split, because the + * range of exclude is [0, 1M] and the condition for splitting a new + * region is that the start, end parameters are both in a certain + * existing region in cmem and cannot be equal to existing region's + * start or end. Obviously, the start of [0, 1M] cannot meet this + * condition. + * + * But in order to lest the low 1M could be changed in the future, + * (e.g. [start, 1M]), add a extra slot. */ - nr_ranges += 2; + nr_ranges += 3 + crashk_cma_cnt; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; - cmem->nr_ranges = 0; return cmem; } @@ -199,9 +193,10 @@ static struct crash_mem *fill_up_crash_elf_data(void) static int elf_header_exclude_ranges(struct crash_mem *cmem) { int ret = 0; + int i; /* Exclude the low 1M because it is always reserved */ - ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1); + ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); if (ret) return ret; @@ -213,8 +208,17 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem) if (crashk_low_res.end) ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret) + return ret; - return ret; + for (i = 0; i < crashk_cma_cnt; ++i) { + ret = crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, + crashk_cma_ranges[i].end); + if (ret) + return ret; + } + + return 0; } static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) @@ -229,8 +233,8 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) } /* Prepare elf headers. Return addr and size */ -static int prepare_elf_headers(struct kimage *image, void **addr, - unsigned long *sz, unsigned long *nr_mem_ranges) +static int prepare_elf_headers(void **addr, unsigned long *sz, + unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; @@ -252,7 +256,7 @@ static int prepare_elf_headers(struct kimage *image, void **addr, *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); + ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); @@ -293,6 +297,7 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mend) { unsigned long start, end; + int ret; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; @@ -301,22 +306,47 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, /* Exclude elf header region */ start = image->elf_load_addr; end = start + image->elf_headers_sz - 1; - return crash_exclude_mem_range(cmem, start, end); + ret = crash_exclude_mem_range(cmem, start, end); + + if (ret) + return ret; + + /* Exclude dm crypt keys region */ + if (image->dm_crypt_keys_addr) { + start = image->dm_crypt_keys_addr; + end = start + image->dm_crypt_keys_sz - 1; + return crash_exclude_mem_range(cmem, start, end); + } + + return ret; } /* Prepare memory map for crash dump kernel */ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { + unsigned int nr_ranges = 0; int i, ret = 0; unsigned long flags; struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; - cmem = vzalloc(struct_size(cmem, ranges, 1)); + /* + * In the current x86 architecture code, the elfheader is always + * allocated at crashk_res.start. But it depends on the allocation + * position of elfheader in crashk_res. To avoid potential out of + * bounds in future, add an extra slot. + * + * And using random kexec_buf for passing dm crypt keys may cause a + * range split too, add another extra slot here. + */ + nr_ranges = 3; + cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return -ENOMEM; + cmem->max_nr_ranges = nr_ranges; + memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; @@ -367,6 +397,14 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) add_e820_entry(params, &ei); } + for (i = 0; i < crashk_cma_cnt; ++i) { + ei.addr = crashk_cma_ranges[i].start; + ei.size = crashk_cma_ranges[i].end - + crashk_cma_ranges[i].start + 1; + ei.type = E820_TYPE_RAM; + add_e820_entry(params, &ei); + } + out: vfree(cmem); return ret; @@ -380,7 +418,7 @@ int crash_load_segments(struct kimage *image) .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum); + ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; @@ -417,8 +455,8 @@ int crash_load_segments(struct kimage *image) if (ret) return ret; image->elf_load_addr = kbuf.mem; - pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } @@ -429,20 +467,26 @@ int crash_load_segments(struct kimage *image) #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt -/* These functions provide the value for the sysfs crash_hotplug nodes */ -#ifdef CONFIG_HOTPLUG_CPU -int arch_crash_hotplug_cpu_support(void) +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { - return crash_check_update_elfcorehdr(); -} -#endif -#ifdef CONFIG_MEMORY_HOTPLUG -int arch_crash_hotplug_memory_support(void) -{ - return crash_check_update_elfcorehdr(); -} +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; #endif + /* + * Initially, crash hotplug support for kexec_load was added + * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this + * functionality was expanded to accommodate multiple kexec + * segment updates, leading to the introduction of the + * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, + * when the kexec tool sends either of these flags, it indicates + * that the required kexec segment (elfcorehdr) is excluded from + * the SHA calculation. + */ + return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || + kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); +} unsigned int arch_crash_get_elfcorehdr_size(void) { @@ -459,10 +503,12 @@ unsigned int arch_crash_get_elfcorehdr_size(void) /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image + * @arg: struct memory_notify handler for memory hotplug case and + * NULL for CPU hotplug case. * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ -void arch_crash_handle_hotplug_event(struct kimage *image) +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; @@ -483,7 +529,7 @@ void arch_crash_handle_hotplug_event(struct kimage *image) * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ - if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) { + if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } |