From 2df173d9e85d9e2c6a8933c63f0c034accff7e0f Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Thu, 16 Feb 2012 01:14:37 +0000 Subject: [PATCH] fadump: Initialize elfcore header and add PT_LOAD program headers. Build the crash memory range list by traversing through system memory during the first kernel before we register for firmware-assisted dump. After the successful dump registration, initialize the elfcore header and populate PT_LOAD program headers with crash memory ranges. The elfcore header is saved in the scratch area within the reserved memory. The scratch area starts at the end of the memory reserved for saving RMR region contents. The scratch area contains fadump crash info structure that contains magic number for fadump validation and physical address where the eflcore header can be found. This structure will also be used to pass some important crash info data to the second kernel which will help second kernel to populate ELF core header with correct data before it gets exported through /proc/vmcore. Since the firmware preserves the entire partition memory at the time of crash the contents of the scratch area will be preserved till second kernel boot. Since the memory dump exported through /proc/vmcore is in ELF format similar to kdump, it will help us to reuse the kdump infrastructure for dump capture and filtering. Unlike phyp dump, userspace tool does not need to refer any sysfs interface while reading /proc/vmcore. NOTE: The current design implementation does not address a possibility of introducing additional fields (in future) to this structure without affecting compatibility. It's on TODO list to come up with better approach to address this. Reserved dump area start => +-------------------------------------+ | CPU state dump data | +-------------------------------------+ | HPTE region data | +-------------------------------------+ | RMR region data | Scratch area start => +-------------------------------------+ | fadump crash info structure { | | magic nummber | +------|---- elfcorehdr_addr | | | } | +----> +-------------------------------------+ | ELF core header | Reserved dump area end => +-------------------------------------+ Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/fadump.h | 43 ++++++ arch/powerpc/kernel/fadump.c | 233 +++++++++++++++++++++++++++++- 2 files changed, 275 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index bbaf278bdccc..9e172a5d53c7 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -43,6 +43,12 @@ #define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \ + (0x1UL << 26)) +#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) + +#ifndef ELF_CORE_EFLAGS +#define ELF_CORE_EFLAGS 0 +#endif + /* Firmware provided dump sections */ #define FADUMP_CPU_STATE_DATA 0x0001 #define FADUMP_HPTE_REGION 0x0002 @@ -56,6 +62,9 @@ #define FADUMP_UNREGISTER 2 #define FADUMP_INVALIDATE 3 +/* Dump status flag */ +#define FADUMP_ERROR_FLAG 0x2000 + /* Kernel Dump section info */ struct fadump_section { u32 request_flag; @@ -109,6 +118,7 @@ struct fw_dump { /* cmd line option during boot */ unsigned long reserve_bootvar; + unsigned long fadumphdr_addr; int ibm_configure_kernel_dump; unsigned long fadump_enabled:1; @@ -117,6 +127,39 @@ struct fw_dump { unsigned long dump_registered:1; }; +/* + * Copy the ascii values for first 8 characters from a string into u64 + * variable at their respective indexes. + * e.g. + * The string "FADMPINF" will be converted into 0x4641444d50494e46 + */ +static inline u64 str_to_u64(const char *str) +{ + u64 val = 0; + int i; + + for (i = 0; i < sizeof(val); i++) + val = (*str) ? (val << 8) | *str++ : val << 8; + return val; +} +#define STR_TO_HEX(x) str_to_u64(x) + +#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF") + +/* fadump crash info structure */ +struct fadump_crash_info_header { + u64 magic_number; + u64 elfcorehdr_addr; +}; + +/* Crash memory ranges */ +#define INIT_CRASHMEM_RANGES (INIT_MEMBLOCK_REGIONS + 2) + +struct fad_crash_memory_ranges { + unsigned long long base; + unsigned long long size; +}; + extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data); extern int fadump_reserve_mem(void); diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index eb8f782afade..63857e183de5 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -43,6 +44,8 @@ static struct fadump_mem_struct fdm; static const struct fadump_mem_struct *fdm_active; static DEFINE_MUTEX(fadump_mutex); +struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES]; +int crash_mem_ranges; /* Scan the Firmware Assisted dump configuration details. */ int __init early_init_dt_scan_fw_dump(unsigned long node, @@ -235,6 +238,10 @@ static unsigned long get_fadump_area_size(void) size += fw_dump.cpu_state_data_size; size += fw_dump.hpte_region_size; size += fw_dump.boot_memory_size; + size += sizeof(struct fadump_crash_info_header); + size += sizeof(struct elfhdr); /* ELF core header.*/ + /* Program headers for crash memory regions. */ + size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2); size = PAGE_ALIGN(size); return size; @@ -300,6 +307,12 @@ int __init fadump_reserve_mem(void) "for saving crash dump\n", (unsigned long)(size >> 20), (unsigned long)(base >> 20)); + + fw_dump.fadumphdr_addr = + fdm_active->rmr_region.destination_address + + fdm_active->rmr_region.source_len; + pr_debug("fadumphdr_addr = %p\n", + (void *) fw_dump.fadumphdr_addr); } else { /* Reserve the memory at the top of memory. */ size = get_fadump_area_size(); @@ -380,8 +393,210 @@ static void register_fw_dump(struct fadump_mem_struct *fdm) } } +/* + * Validate and process the dump data stored by firmware before exporting + * it through '/proc/vmcore'. + */ +static int __init process_fadump(const struct fadump_mem_struct *fdm_active) +{ + struct fadump_crash_info_header *fdh; + + if (!fdm_active || !fw_dump.fadumphdr_addr) + return -EINVAL; + + /* Check if the dump data is valid. */ + if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) || + (fdm_active->rmr_region.error_flags != 0)) { + printk(KERN_ERR "Dump taken by platform is not valid\n"); + return -EINVAL; + } + if (fdm_active->rmr_region.bytes_dumped != + fdm_active->rmr_region.source_len) { + printk(KERN_ERR "Dump taken by platform is incomplete\n"); + return -EINVAL; + } + + /* Validate the fadump crash info header */ + fdh = __va(fw_dump.fadumphdr_addr); + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { + printk(KERN_ERR "Crash info header is not valid.\n"); + return -EINVAL; + } + + /* + * We are done validating dump info and elfcore header is now ready + * to be exported. set elfcorehdr_addr so that vmcore module will + * export the elfcore header through '/proc/vmcore'. + */ + elfcorehdr_addr = fdh->elfcorehdr_addr; + + return 0; +} + +static inline void fadump_add_crash_memory(unsigned long long base, + unsigned long long end) +{ + if (base == end) + return; + + pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n", + crash_mem_ranges, base, end - 1, (end - base)); + crash_memory_ranges[crash_mem_ranges].base = base; + crash_memory_ranges[crash_mem_ranges].size = end - base; + crash_mem_ranges++; +} + +static void fadump_exclude_reserved_area(unsigned long long start, + unsigned long long end) +{ + unsigned long long ra_start, ra_end; + + ra_start = fw_dump.reserve_dump_area_start; + ra_end = ra_start + fw_dump.reserve_dump_area_size; + + if ((ra_start < end) && (ra_end > start)) { + if ((start < ra_start) && (end > ra_end)) { + fadump_add_crash_memory(start, ra_start); + fadump_add_crash_memory(ra_end, end); + } else if (start < ra_start) { + fadump_add_crash_memory(start, ra_start); + } else if (ra_end < end) { + fadump_add_crash_memory(ra_end, end); + } + } else + fadump_add_crash_memory(start, end); +} + +static int fadump_init_elfcore_header(char *bufp) +{ + struct elfhdr *elf; + + elf = (struct elfhdr *) bufp; + bufp += sizeof(struct elfhdr); + memcpy(elf->e_ident, ELFMAG, SELFMAG); + elf->e_ident[EI_CLASS] = ELF_CLASS; + elf->e_ident[EI_DATA] = ELF_DATA; + elf->e_ident[EI_VERSION] = EV_CURRENT; + elf->e_ident[EI_OSABI] = ELF_OSABI; + memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD); + elf->e_type = ET_CORE; + elf->e_machine = ELF_ARCH; + elf->e_version = EV_CURRENT; + elf->e_entry = 0; + elf->e_phoff = sizeof(struct elfhdr); + elf->e_shoff = 0; + elf->e_flags = ELF_CORE_EFLAGS; + elf->e_ehsize = sizeof(struct elfhdr); + elf->e_phentsize = sizeof(struct elf_phdr); + elf->e_phnum = 0; + elf->e_shentsize = 0; + elf->e_shnum = 0; + elf->e_shstrndx = 0; + + return 0; +} + +/* + * Traverse through memblock structure and setup crash memory ranges. These + * ranges will be used create PT_LOAD program headers in elfcore header. + */ +static void fadump_setup_crash_memory_ranges(void) +{ + struct memblock_region *reg; + unsigned long long start, end; + + pr_debug("Setup crash memory ranges.\n"); + crash_mem_ranges = 0; + /* + * add the first memory chunk (RMA_START through boot_memory_size) as + * a separate memory chunk. The reason is, at the time crash firmware + * will move the content of this memory chunk to different location + * specified during fadump registration. We need to create a separate + * program header for this chunk with the correct offset. + */ + fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size); + + for_each_memblock(memory, reg) { + start = (unsigned long long)reg->base; + end = start + (unsigned long long)reg->size; + if (start == RMA_START && end >= fw_dump.boot_memory_size) + start = fw_dump.boot_memory_size; + + /* add this range excluding the reserved dump area. */ + fadump_exclude_reserved_area(start, end); + } +} + +static int fadump_create_elfcore_headers(char *bufp) +{ + struct elfhdr *elf; + struct elf_phdr *phdr; + int i; + + fadump_init_elfcore_header(bufp); + elf = (struct elfhdr *)bufp; + bufp += sizeof(struct elfhdr); + + /* setup PT_LOAD sections. */ + + for (i = 0; i < crash_mem_ranges; i++) { + unsigned long long mbase, msize; + mbase = crash_memory_ranges[i].base; + msize = crash_memory_ranges[i].size; + + if (!msize) + continue; + + phdr = (struct elf_phdr *)bufp; + bufp += sizeof(struct elf_phdr); + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_offset = mbase; + + if (mbase == RMA_START) { + /* + * The entire RMA region will be moved by firmware + * to the specified destination_address. Hence set + * the correct offset. + */ + phdr->p_offset = fdm.rmr_region.destination_address; + } + + phdr->p_paddr = mbase; + phdr->p_vaddr = (unsigned long)__va(mbase); + phdr->p_filesz = msize; + phdr->p_memsz = msize; + phdr->p_align = 0; + + /* Increment number of program headers. */ + (elf->e_phnum)++; + } + return 0; +} + +static unsigned long init_fadump_header(unsigned long addr) +{ + struct fadump_crash_info_header *fdh; + + if (!addr) + return 0; + + fw_dump.fadumphdr_addr = addr; + fdh = __va(addr); + addr += sizeof(struct fadump_crash_info_header); + + memset(fdh, 0, sizeof(struct fadump_crash_info_header)); + fdh->magic_number = FADUMP_CRASH_INFO_MAGIC; + fdh->elfcorehdr_addr = addr; + + return addr; +} + static void register_fadump(void) { + unsigned long addr; + void *vaddr; + /* * If no memory is reserved then we can not register for firmware- * assisted dump. @@ -389,6 +604,16 @@ static void register_fadump(void) if (!fw_dump.reserve_dump_area_size) return; + fadump_setup_crash_memory_ranges(); + + addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len; + /* Initialize fadump crash info header. */ + addr = init_fadump_header(addr); + vaddr = __va(addr); + + pr_debug("Creating ELF core headers at %#016lx\n", addr); + fadump_create_elfcore_headers(vaddr); + /* register the future kernel dump with firmware. */ register_fw_dump(&fdm); } @@ -585,8 +810,14 @@ int __init setup_fadump(void) } fadump_show_config(); + /* + * If dump data is available then see if it is valid and prepare for + * saving it to the disk. + */ + if (fw_dump.dump_active) + process_fadump(fdm_active); /* Initialize the kernel dump memory structure for FAD registration. */ - if (fw_dump.reserve_dump_area_size) + else if (fw_dump.reserve_dump_area_size) init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); fadump_init_files();