Re: [Crash-utility] [Patch 4/4][crash] Recognise elf-note of type NT_NOCOREDUMP before vmcore analysis

The kernel might have added a new elf-note of type NT_NOCOREDUMP for various reasons. This patch teaches crash tool to look for the same inside a vmcore before further analysis. If present, display the error description and exit early. Signed-off-by: K.Prasad <prasad(a)linux.vnet.ibm.com&gt;

--- netdump.c | 136 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 files changed, 131 insertions(+), 5 deletions(-) diff --git a/netdump.c b/netdump.c index 1e9960c..3b4edec 100644 --- a/netdump.c +++ b/netdump.c @@ -95,6 +95,74 @@ map_cpus_to_prstatus(void) } /* + * Temporary definition of new elf-note type for compilation purposes. + * Not required when run on a new kernel containing this definition. + */ +#define NT_NOCOREDUMP 21 + +/* + * Function to verify if the vmcore contains and elf-note of type NT_NOCOREDUMP. + * The kernel adds such an elf-note when it is known that the crash is + * triggered due to a reason that does not need analysis of the entire kernel + * memory dump (e.g. crash triggered due to a faulty memory DIMM). + */ +static void +has_nt_nocoredump(void *note_ptr, unsigned long size_note) +{ + Elf32_Nhdr *note32 = NULL; + Elf64_Nhdr *note64 = NULL; + size_t tot, len = 0; + int num = 0; + + for (tot = 0; tot < size_note; tot += len) { + if (machine_type("X86_64")) { + note64 = note_ptr + tot; + /* + * If vmcore is generated due to fatal hardware + * errors (such as Machine Check Exception, we only have + * a 'slim' crashdump. Don't analyse further, inform the + * user about it and exit. + */ + if (note64->n_type == NT_NOCOREDUMP) { + fprintf(fp, "\"System crashed due to a hardware" + " memory error. No coredump" + " available.\"\n"); + + /* Do we have an accompanying error message? */ + if (note64->n_descsz == 0) + goto exit; + fprintf(fp,"Nocoredump Reason: %s", + (char *)note64 + sizeof(Elf64_Nhdr)); + } + + len = sizeof(Elf64_Nhdr); + len = roundup(len + note64->n_namesz, 4); + len = roundup(len + note64->n_descsz, 4); + } else if (machine_type("X86")) { + note32 = note_ptr + tot; + if (note32->n_type == NT_NOCOREDUMP) { + fprintf(fp, "\"System crashed due to a hardware" + " memory error. No coredump" + " available.\"\n"); + + /* Do we have an accompanying error message? */ + if (note32->n_descsz == 0) + goto exit; + + fprintf(fp,"Nocoredump Reason: %s", + (char *)note32 + sizeof(Elf32_Nhdr)); +exit: + clean_exit(0); + } + + len = sizeof(Elf32_Nhdr); + len = roundup(len + note32->n_namesz, 4); + len = roundup(len + note32->n_descsz, 4); + } + } +} + +/* * Determine whether a file is a netdump/diskdump/kdump creation, * and if TRUE, initialize the vmcore_data structure. */ @@ -103,12 +171,12 @@ is_netdump(char *file, ulong source_query) { int i, fd, swap; Elf32_Ehdr *elf32; - Elf32_Phdr *load32; + Elf32_Phdr *load32, *myload32; Elf64_Ehdr *elf64; - Elf64_Phdr *load64; + Elf64_Phdr *load64, *myload64; char eheader[MIN_NETDUMP_ELF_HEADER_SIZE]; char buf[BUFSIZE]; - size_t size, len, tot; + size_t size, mysize, len, tot; Elf32_Off offset32; Elf64_Off offset64; ulong tmp_flags; @@ -195,7 +263,10 @@ is_netdump(char *file, ulong source_query) load32 = (Elf32_Phdr *) &eheader[sizeof(Elf32_Ehdr)+sizeof(Elf32_Phdr)]; - size = (size_t)load32->p_offset; + myload32 = (Elf32_Phdr *) + &eheader[sizeof(Elf32_Ehdr)]; + + size = (size_t)myload32->p_offset; if ((load32->p_offset & (MIN_PAGE_SIZE-1)) && (load32->p_align == 0)) @@ -249,7 +320,10 @@ is_netdump(char *file, ulong source_query) load64 = (Elf64_Phdr *) &eheader[sizeof(Elf64_Ehdr)+sizeof(Elf64_Phdr)]; - size = (size_t)load64->p_offset; + myload64 = (Elf64_Phdr *) + &eheader[sizeof(Elf64_Ehdr)]; + + size = (size_t)myload64->p_offset; if ((load64->p_offset & (MIN_PAGE_SIZE-1)) && (load64->p_align == 0)) tmp_flags |= KDUMP_ELF64; @@ -362,6 +436,58 @@ is_netdump(char *file, ulong source_query) &nd->elf_header[sizeof(Elf64_Ehdr)]; nd->load64 = (Elf64_Phdr *) &nd->elf_header[sizeof(Elf64_Ehdr)+sizeof(Elf64_Phdr)]; + /* + * Find out if there exists an elf-note of type NT_NOCOREDUMP. + * If so, exit early from crash analysis after displaying the + * description string. + * + * Allocate a temporary buffer to store the PT_NOTE section and + * loop through them to look for NT_NOCOREDUMP. + */ + for (i = 0; i < elf64->e_phnum; i++, myload64++) { + mysize += myload64->p_memsz; + if (myload64->p_type == PT_NOTE) { + break; + } + } + + if (mysize == 0) { + fprintf(stderr, "No PT_NOTE section found\n"); + clean_exit(1); + } + + /* + * Size of the buffer should accommodate the Elf_Ehdr, Elf_Phdr + * and all sections upto the first PT_NOTE. + */ + mysize += size; + tmp_elf_header = realloc(tmp_elf_header, mysize); + if (tmp_elf_header == NULL) { + fprintf(stderr, "cannot malloc notes buffer\n"); + clean_exit(1); + } + if (FLAT_FORMAT()) { + if (!read_flattened_format(fd, 0, tmp_elf_header, mysize)) { + free(tmp_elf_header); + goto bailout; + } + } else { + if (lseek(fd, 0, SEEK_SET) != 0) { + sprintf(buf, "%s: lseek", file); + perror(buf); + goto bailout; + } + if (read(fd, tmp_elf_header, mysize) != mysize) { + sprintf(buf, "%s: read", file); + perror(buf); + free(tmp_elf_header); + goto bailout; + } + } + + has_nt_nocoredump((char *)tmp_elf_header + myload64->p_offset, + myload64->p_memsz); + if (DUMPFILE_FORMAT(nd->flags) == NETDUMP_ELF64) nd->page_size = (uint)nd->load64->p_align; dump_Elf64_Ehdr(nd->elf64); -- 1.7.4.1