diff options
Diffstat (limited to 'arch/x86/kernel/crash.c')
-rw-r--r-- | arch/x86/kernel/crash.c | 282 |
1 files changed, 213 insertions, 69 deletions
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9730c88530fc..c6b12bed173d 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> @@ -37,10 +38,10 @@ #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> -#include <asm/virtext.h> #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 { @@ -49,27 +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) @@ -77,24 +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 VMX or SVM if needed. - * - * We need to disable virtualization on all CPUs. - * Having VMX or SVM enabled on any CPU may break rebooting - * after the kdump kernel has finished its task. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); - - /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); + kdump_sev_callback(); + disable_local_APIC(); } @@ -143,17 +111,7 @@ 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(); - - /* Booting kdump kernel with VMX or SVM enabled won't work, - * because (among other limitations) we can't disable paging - * with the virt flags. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); + cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging @@ -170,11 +128,22 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif - crash_save_cpu(regs, safe_smp_processor_id()); -} -#ifdef CONFIG_KEXEC_FILE + /* + * 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) static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; @@ -194,10 +163,10 @@ 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. */ - nr_ranges += 2; + nr_ranges += 2 + crashk_cma_cnt; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return NULL; @@ -215,9 +184,10 @@ 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; @@ -229,8 +199,17 @@ 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) @@ -245,8 +224,8 @@ 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) +static int prepare_elf_headers(void **addr, unsigned long *sz, + unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; @@ -264,14 +243,19 @@ static int prepare_elf_headers(struct kimage *image, void **addr, if (ret) goto out; + /* Return the computed number of memory ranges, for hotplug usage */ + *nr_mem_ranges = cmem->nr_ranges; + /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); + ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); return ret; } +#endif +#ifdef CONFIG_KEXEC_FILE static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; @@ -304,6 +288,7 @@ 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; @@ -312,22 +297,43 @@ 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)); + /* + * Using random kexec_buf for passing dm crypt keys may cause a range + * split. So use two slots here. + */ + nr_ranges = 2; + cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return -ENOMEM; + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; @@ -378,6 +384,14 @@ 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; @@ -386,29 +400,159 @@ out: int crash_load_segments(struct kimage *image) { int ret; + unsigned long pnum = 0; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz); + ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; - image->elf_headers = kbuf.buffer; - image->elf_headers_sz = kbuf.bufsz; + image->elf_headers = kbuf.buffer; + image->elf_headers_sz = kbuf.bufsz; + kbuf.memsz = kbuf.bufsz; + +#ifdef CONFIG_CRASH_HOTPLUG + /* + * The elfcorehdr segment size accounts for VMCOREINFO, kernel_map, + * maximum CPUs and maximum memory ranges. + */ + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + pnum = 2 + CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES; + else + pnum += 2 + CONFIG_NR_CPUS_DEFAULT; + + if (pnum < (unsigned long)PN_XNUM) { + kbuf.memsz = pnum * sizeof(Elf64_Phdr); + kbuf.memsz += sizeof(Elf64_Ehdr); + + image->elfcorehdr_index = image->nr_segments; + + /* Mark as usable to crash kernel, else crash kernel fails on boot */ + image->elf_headers_sz = kbuf.memsz; + } else { + pr_err("number of Phdrs %lu exceeds max\n", pnum); + } +#endif - kbuf.memsz = kbuf.bufsz; kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); - if (ret) { - vfree((void *)image->elf_headers); + 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; } #endif /* CONFIG_KEXEC_FILE */ + +#ifdef CONFIG_CRASH_HOTPLUG + +#undef pr_fmt +#define pr_fmt(fmt) "crash hp: " fmt + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ + +#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) +{ + unsigned int sz; + + /* kernel_map, VMCOREINFO and maximum CPUs */ + sz = 2 + CONFIG_NR_CPUS_DEFAULT; + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + sz += CONFIG_CRASH_MAX_MEMORY_RANGES; + sz *= sizeof(Elf64_Phdr); + return sz; +} + +/** + * 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 *arg) +{ + void *elfbuf = NULL, *old_elfcorehdr; + unsigned long nr_mem_ranges; + unsigned long mem, memsz; + unsigned long elfsz = 0; + + /* + * As crash_prepare_elf64_headers() has already described all + * possible CPUs, there is no need to update the elfcorehdr + * for additional CPU changes. + */ + if ((image->file_mode || image->elfcorehdr_updated) && + ((image->hp_action == KEXEC_CRASH_HP_ADD_CPU) || + (image->hp_action == KEXEC_CRASH_HP_REMOVE_CPU))) + return; + + /* + * Create the new elfcorehdr reflecting the changes to CPU and/or + * memory resources. + */ + if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { + pr_err("unable to create new elfcorehdr"); + goto out; + } + + /* + * Obtain address and size of the elfcorehdr segment, and + * check it against the new elfcorehdr buffer. + */ + mem = image->segment[image->elfcorehdr_index].mem; + memsz = image->segment[image->elfcorehdr_index].memsz; + if (elfsz > memsz) { + pr_err("update elfcorehdr elfsz %lu > memsz %lu", + elfsz, memsz); + goto out; + } + + /* + * Copy new elfcorehdr over the old elfcorehdr at destination. + */ + old_elfcorehdr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT)); + if (!old_elfcorehdr) { + pr_err("mapping elfcorehdr segment failed\n"); + goto out; + } + + /* + * Temporarily invalidate the crash image while the + * elfcorehdr is updated. + */ + xchg(&kexec_crash_image, NULL); + memcpy_flushcache(old_elfcorehdr, elfbuf, elfsz); + xchg(&kexec_crash_image, image); + kunmap_local(old_elfcorehdr); + pr_debug("updated elfcorehdr\n"); + +out: + vfree(elfbuf); +} +#endif |