From a79f248b9b309ebb5f34ca6a8fd1eb9e18db5720 Mon Sep 17 00:00:00 2001 From: David Daney Date: Thu, 19 Apr 2012 14:59:55 -0700 Subject: scripts: Add sortextable to sort the kernel's exception table. Using this build-time sort saves time booting as we don't have to burn cycles sorting the exception table. Signed-off-by: David Daney Link: http://lkml.kernel.org/r/1334872799-14589-2-git-send-email-ddaney.cavm@gmail.com Signed-off-by: H. Peter Anvin --- scripts/sortextable.c | 271 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 scripts/sortextable.c (limited to 'scripts/sortextable.c') diff --git a/scripts/sortextable.c b/scripts/sortextable.c new file mode 100644 index 000000000000..f51f1d43da63 --- /dev/null +++ b/scripts/sortextable.c @@ -0,0 +1,271 @@ +/* + * sortextable.c: Sort the kernel's exception table + * + * Copyright 2011 Cavium, Inc. + * + * Based on code taken from recortmcount.c which is: + * + * Copyright 2009 John F. Reiser . All rights reserved. + * Licensed under the GNU General Public License, version 2 (GPLv2). + * + * Restructured to fit Linux format, as well as other updates: + * Copyright 2010 Steven Rostedt , Red Hat Inc. + */ + +/* + * Strategy: alter the vmlinux file in-place. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int fd_map; /* File descriptor for file being modified. */ +static int mmap_failed; /* Boolean flag. */ +static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */ +static struct stat sb; /* Remember .st_size, etc. */ +static jmp_buf jmpenv; /* setjmp/longjmp per-file error escape */ + +/* setjmp() return values */ +enum { + SJ_SETJMP = 0, /* hardwired first return */ + SJ_FAIL, + SJ_SUCCEED +}; + +/* Per-file resource cleanup when multiple files. */ +static void +cleanup(void) +{ + if (!mmap_failed) + munmap(ehdr_curr, sb.st_size); + close(fd_map); +} + +static void __attribute__((noreturn)) +fail_file(void) +{ + cleanup(); + longjmp(jmpenv, SJ_FAIL); +} + +static void __attribute__((noreturn)) +succeed_file(void) +{ + cleanup(); + longjmp(jmpenv, SJ_SUCCEED); +} + + +/* + * Get the whole file as a programming convenience in order to avoid + * malloc+lseek+read+free of many pieces. If successful, then mmap + * avoids copying unused pieces; else just read the whole file. + * Open for both read and write. + */ +static void *mmap_file(char const *fname) +{ + void *addr; + + fd_map = open(fname, O_RDWR); + if (fd_map < 0 || fstat(fd_map, &sb) < 0) { + perror(fname); + fail_file(); + } + if (!S_ISREG(sb.st_mode)) { + fprintf(stderr, "not a regular file: %s\n", fname); + fail_file(); + } + addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_SHARED, + fd_map, 0); + if (addr == MAP_FAILED) { + mmap_failed = 1; + fprintf(stderr, "Could not mmap file: %s\n", fname); + fail_file(); + } + return addr; +} + +/* w8rev, w8nat, ...: Handle endianness. */ + +static uint64_t w8rev(uint64_t const x) +{ + return ((0xff & (x >> (0 * 8))) << (7 * 8)) + | ((0xff & (x >> (1 * 8))) << (6 * 8)) + | ((0xff & (x >> (2 * 8))) << (5 * 8)) + | ((0xff & (x >> (3 * 8))) << (4 * 8)) + | ((0xff & (x >> (4 * 8))) << (3 * 8)) + | ((0xff & (x >> (5 * 8))) << (2 * 8)) + | ((0xff & (x >> (6 * 8))) << (1 * 8)) + | ((0xff & (x >> (7 * 8))) << (0 * 8)); +} + +static uint32_t w4rev(uint32_t const x) +{ + return ((0xff & (x >> (0 * 8))) << (3 * 8)) + | ((0xff & (x >> (1 * 8))) << (2 * 8)) + | ((0xff & (x >> (2 * 8))) << (1 * 8)) + | ((0xff & (x >> (3 * 8))) << (0 * 8)); +} + +static uint32_t w2rev(uint16_t const x) +{ + return ((0xff & (x >> (0 * 8))) << (1 * 8)) + | ((0xff & (x >> (1 * 8))) << (0 * 8)); +} + +static uint64_t w8nat(uint64_t const x) +{ + return x; +} + +static uint32_t w4nat(uint32_t const x) +{ + return x; +} + +static uint32_t w2nat(uint16_t const x) +{ + return x; +} + +static uint64_t (*w8)(uint64_t); +static uint32_t (*w)(uint32_t); +static uint32_t (*w2)(uint16_t); + + +/* 32 bit and 64 bit are very similar */ +#include "sortextable.h" +#define SORTEXTABLE_64 +#include "sortextable.h" + + +static void +do_file(char const *const fname) +{ + Elf32_Ehdr *const ehdr = mmap_file(fname); + + ehdr_curr = ehdr; + w = w4nat; + w2 = w2nat; + w8 = w8nat; + switch (ehdr->e_ident[EI_DATA]) { + static unsigned int const endian = 1; + default: + fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", + ehdr->e_ident[EI_DATA], fname); + fail_file(); + break; + case ELFDATA2LSB: + if (*(unsigned char const *)&endian != 1) { + /* main() is big endian, file.o is little endian. */ + w = w4rev; + w2 = w2rev; + w8 = w8rev; + } + break; + case ELFDATA2MSB: + if (*(unsigned char const *)&endian != 0) { + /* main() is little endian, file.o is big endian. */ + w = w4rev; + w2 = w2rev; + w8 = w8rev; + } + break; + } /* end switch */ + if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 + || w2(ehdr->e_type) != ET_EXEC + || ehdr->e_ident[EI_VERSION] != EV_CURRENT) { + fprintf(stderr, "unrecognized ET_EXEC file %s\n", fname); + fail_file(); + } + + switch (w2(ehdr->e_machine)) { + default: + fprintf(stderr, "unrecognized e_machine %d %s\n", + w2(ehdr->e_machine), fname); + fail_file(); + break; + case EM_386: + case EM_MIPS: + case EM_X86_64: + break; + } /* end switch */ + + switch (ehdr->e_ident[EI_CLASS]) { + default: + fprintf(stderr, "unrecognized ELF class %d %s\n", + ehdr->e_ident[EI_CLASS], fname); + fail_file(); + break; + case ELFCLASS32: + if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr) + || w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { + fprintf(stderr, + "unrecognized ET_EXEC file: %s\n", fname); + fail_file(); + } + do32(ehdr, fname); + break; + case ELFCLASS64: { + Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr; + if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr) + || w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { + fprintf(stderr, + "unrecognized ET_EXEC file: %s\n", fname); + fail_file(); + } + do64(ghdr, fname); + break; + } + } /* end switch */ + + cleanup(); +} + +int +main(int argc, char *argv[]) +{ + int n_error = 0; /* gcc-4.3.0 false positive complaint */ + int i; + + if (argc < 2) { + fprintf(stderr, "usage: sortextable vmlinux...\n"); + return 0; + } + + /* Process each file in turn, allowing deep failure. */ + for (i = 1; i < argc; i++) { + char *file = argv[i]; + int const sjval = setjmp(jmpenv); + + switch (sjval) { + default: + fprintf(stderr, "internal error: %s\n", file); + exit(1); + break; + case SJ_SETJMP: /* normal sequence */ + /* Avoid problems if early cleanup() */ + fd_map = -1; + ehdr_curr = NULL; + mmap_failed = 1; + do_file(file); + break; + case SJ_FAIL: /* error in do_file or below */ + ++n_error; + break; + case SJ_SUCCEED: /* premature success */ + /* do nothing */ + break; + } /* end switch */ + } + return !!n_error; +} -- cgit v1.2.3 From d59a16836d917548cf41eda3369936684d527f5f Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 24 Apr 2012 11:23:14 -0700 Subject: scripts/sortextable: Handle relative entries, and other cleanups x86 is now using relative rather than absolute addresses in its exception table, so we add a sorter for these. If there are relocations on the __ex_table section, they are redundant and probably incorrect after the sort, so they are zeroed out leaving them valid and consistent. Also use the unaligned safe accessors from tools/{be,le}_byteshift.h Signed-off-by: David Daney Link: http://lkml.kernel.org/r/1335291795-26693-2-git-send-email-ddaney.cavm@gmail.com Signed-off-by: H. Peter Anvin --- scripts/sortextable.c | 171 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 111 insertions(+), 60 deletions(-) (limited to 'scripts/sortextable.c') diff --git a/scripts/sortextable.c b/scripts/sortextable.c index f51f1d43da63..1ca9ceb95eb6 100644 --- a/scripts/sortextable.c +++ b/scripts/sortextable.c @@ -1,7 +1,7 @@ /* * sortextable.c: Sort the kernel's exception table * - * Copyright 2011 Cavium, Inc. + * Copyright 2011 - 2012 Cavium, Inc. * * Based on code taken from recortmcount.c which is: * @@ -28,6 +28,9 @@ #include #include +#include +#include + static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */ @@ -94,109 +97,157 @@ static void *mmap_file(char const *fname) return addr; } -/* w8rev, w8nat, ...: Handle endianness. */ - -static uint64_t w8rev(uint64_t const x) +static uint64_t r8be(const uint64_t *x) { - return ((0xff & (x >> (0 * 8))) << (7 * 8)) - | ((0xff & (x >> (1 * 8))) << (6 * 8)) - | ((0xff & (x >> (2 * 8))) << (5 * 8)) - | ((0xff & (x >> (3 * 8))) << (4 * 8)) - | ((0xff & (x >> (4 * 8))) << (3 * 8)) - | ((0xff & (x >> (5 * 8))) << (2 * 8)) - | ((0xff & (x >> (6 * 8))) << (1 * 8)) - | ((0xff & (x >> (7 * 8))) << (0 * 8)); + return get_unaligned_be64(x); } - -static uint32_t w4rev(uint32_t const x) +static uint32_t rbe(const uint32_t *x) { - return ((0xff & (x >> (0 * 8))) << (3 * 8)) - | ((0xff & (x >> (1 * 8))) << (2 * 8)) - | ((0xff & (x >> (2 * 8))) << (1 * 8)) - | ((0xff & (x >> (3 * 8))) << (0 * 8)); + return get_unaligned_be32(x); } - -static uint32_t w2rev(uint16_t const x) +static uint16_t r2be(const uint16_t *x) { - return ((0xff & (x >> (0 * 8))) << (1 * 8)) - | ((0xff & (x >> (1 * 8))) << (0 * 8)); + return get_unaligned_be16(x); } - -static uint64_t w8nat(uint64_t const x) +static uint64_t r8le(const uint64_t *x) { - return x; + return get_unaligned_le64(x); } - -static uint32_t w4nat(uint32_t const x) +static uint32_t rle(const uint32_t *x) +{ + return get_unaligned_le32(x); +} +static uint16_t r2le(const uint16_t *x) { - return x; + return get_unaligned_le16(x); } -static uint32_t w2nat(uint16_t const x) +static void w8be(uint64_t val, uint64_t *x) +{ + put_unaligned_be64(val, x); +} +static void wbe(uint32_t val, uint32_t *x) +{ + put_unaligned_be32(val, x); +} +static void w2be(uint16_t val, uint16_t *x) +{ + put_unaligned_be16(val, x); +} +static void w8le(uint64_t val, uint64_t *x) +{ + put_unaligned_le64(val, x); +} +static void wle(uint32_t val, uint32_t *x) +{ + put_unaligned_le32(val, x); +} +static void w2le(uint16_t val, uint16_t *x) { - return x; + put_unaligned_le16(val, x); } -static uint64_t (*w8)(uint64_t); -static uint32_t (*w)(uint32_t); -static uint32_t (*w2)(uint16_t); +static uint64_t (*r8)(const uint64_t *); +static uint32_t (*r)(const uint32_t *); +static uint16_t (*r2)(const uint16_t *); +static void (*w8)(uint64_t, uint64_t *); +static void (*w)(uint32_t, uint32_t *); +static void (*w2)(uint16_t, uint16_t *); +typedef void (*table_sort_t)(char *, int); /* 32 bit and 64 bit are very similar */ #include "sortextable.h" #define SORTEXTABLE_64 #include "sortextable.h" +static int compare_x86_table(const void *a, const void *b) +{ + int32_t av = (int32_t)r(a); + int32_t bv = (int32_t)r(b); + + if (av < bv) + return -1; + if (av > bv) + return 1; + return 0; +} + +static void sort_x86_table(char *extab_image, int image_size) +{ + int i; + + /* + * Do the same thing the runtime sort does, first normalize to + * being relative to the start of the section. + */ + i = 0; + while (i < image_size) { + uint32_t *loc = (uint32_t *)(extab_image + i); + w(r(loc) + i, loc); + i += 4; + } + + qsort(extab_image, image_size / 8, 8, compare_x86_table); + + /* Now denormalize. */ + i = 0; + while (i < image_size) { + uint32_t *loc = (uint32_t *)(extab_image + i); + w(r(loc) - i, loc); + i += 4; + } +} static void do_file(char const *const fname) { - Elf32_Ehdr *const ehdr = mmap_file(fname); + table_sort_t custom_sort; + Elf32_Ehdr *ehdr = mmap_file(fname); ehdr_curr = ehdr; - w = w4nat; - w2 = w2nat; - w8 = w8nat; switch (ehdr->e_ident[EI_DATA]) { - static unsigned int const endian = 1; default: fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", ehdr->e_ident[EI_DATA], fname); fail_file(); break; case ELFDATA2LSB: - if (*(unsigned char const *)&endian != 1) { - /* main() is big endian, file.o is little endian. */ - w = w4rev; - w2 = w2rev; - w8 = w8rev; - } + r = rle; + r2 = r2le; + r8 = r8le; + w = wle; + w2 = w2le; + w8 = w8le; break; case ELFDATA2MSB: - if (*(unsigned char const *)&endian != 0) { - /* main() is little endian, file.o is big endian. */ - w = w4rev; - w2 = w2rev; - w8 = w8rev; - } + r = rbe; + r2 = r2be; + r8 = r8be; + w = wbe; + w2 = w2be; + w8 = w8be; break; } /* end switch */ if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 - || w2(ehdr->e_type) != ET_EXEC + || r2(&ehdr->e_type) != ET_EXEC || ehdr->e_ident[EI_VERSION] != EV_CURRENT) { fprintf(stderr, "unrecognized ET_EXEC file %s\n", fname); fail_file(); } - switch (w2(ehdr->e_machine)) { + custom_sort = NULL; + switch (r2(&ehdr->e_machine)) { default: fprintf(stderr, "unrecognized e_machine %d %s\n", - w2(ehdr->e_machine), fname); + r2(&ehdr->e_machine), fname); fail_file(); break; case EM_386: - case EM_MIPS: case EM_X86_64: + custom_sort = sort_x86_table; + break; + case EM_MIPS: break; } /* end switch */ @@ -207,23 +258,23 @@ do_file(char const *const fname) fail_file(); break; case ELFCLASS32: - if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr) - || w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { + if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) + || r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC file: %s\n", fname); fail_file(); } - do32(ehdr, fname); + do32(ehdr, fname, custom_sort); break; case ELFCLASS64: { Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr; - if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr) - || w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { + if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) + || r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC file: %s\n", fname); fail_file(); } - do64(ghdr, fname); + do64(ghdr, fname, custom_sort); break; } } /* end switch */ -- cgit v1.2.3