442f04c34a
This adds a host tool named objtool which has a "check" subcommand which analyzes .o files to ensure the validity of stack metadata. It enforces a set of rules on asm code and C inline assembly code so that stack traces can be reliable. For each function, it recursively follows all possible code paths and validates the correct frame pointer state at each instruction. It also follows code paths involving kernel special sections, like .altinstructions, __jump_table, and __ex_table, which can add alternative execution paths to a given instruction (or set of instructions). Similarly, it knows how to follow switch statements, for which gcc sometimes uses jump tables. Here are some of the benefits of validating stack metadata: a) More reliable stack traces for frame pointer enabled kernels Frame pointers are used for debugging purposes. They allow runtime code and debug tools to be able to walk the stack to determine the chain of function call sites that led to the currently executing code. For some architectures, frame pointers are enabled by CONFIG_FRAME_POINTER. For some other architectures they may be required by the ABI (sometimes referred to as "backchain pointers"). For C code, gcc automatically generates instructions for setting up frame pointers when the -fno-omit-frame-pointer option is used. But for asm code, the frame setup instructions have to be written by hand, which most people don't do. So the end result is that CONFIG_FRAME_POINTER is honored for C code but not for most asm code. For stack traces based on frame pointers to be reliable, all functions which call other functions must first create a stack frame and update the frame pointer. If a first function doesn't properly create a stack frame before calling a second function, the *caller* of the first function will be skipped on the stack trace. For example, consider the following example backtrace with frame pointers enabled: [<ffffffff81812584>] dump_stack+0x4b/0x63 [<ffffffff812d6dc2>] cmdline_proc_show+0x12/0x30 [<ffffffff8127f568>] seq_read+0x108/0x3e0 [<ffffffff812cce62>] proc_reg_read+0x42/0x70 [<ffffffff81256197>] __vfs_read+0x37/0x100 [<ffffffff81256b16>] vfs_read+0x86/0x130 [<ffffffff81257898>] SyS_read+0x58/0xd0 [<ffffffff8181c1f2>] entry_SYSCALL_64_fastpath+0x12/0x76 It correctly shows that the caller of cmdline_proc_show() is seq_read(). If we remove the frame pointer logic from cmdline_proc_show() by replacing the frame pointer related instructions with nops, here's what it looks like instead: [<ffffffff81812584>] dump_stack+0x4b/0x63 [<ffffffff812d6dc2>] cmdline_proc_show+0x12/0x30 [<ffffffff812cce62>] proc_reg_read+0x42/0x70 [<ffffffff81256197>] __vfs_read+0x37/0x100 [<ffffffff81256b16>] vfs_read+0x86/0x130 [<ffffffff81257898>] SyS_read+0x58/0xd0 [<ffffffff8181c1f2>] entry_SYSCALL_64_fastpath+0x12/0x76 Notice that cmdline_proc_show()'s caller, seq_read(), has been skipped. Instead the stack trace seems to show that cmdline_proc_show() was called by proc_reg_read(). The benefit of "objtool check" here is that because it ensures that *all* functions honor CONFIG_FRAME_POINTER, no functions will ever[*] be skipped on a stack trace. [*] unless an interrupt or exception has occurred at the very beginning of a function before the stack frame has been created, or at the very end of the function after the stack frame has been destroyed. This is an inherent limitation of frame pointers. b) 100% reliable stack traces for DWARF enabled kernels This is not yet implemented. For more details about what is planned, see tools/objtool/Documentation/stack-validation.txt. c) Higher live patching compatibility rate This is not yet implemented. For more details about what is planned, see tools/objtool/Documentation/stack-validation.txt. To achieve the validation, "objtool check" enforces the following rules: 1. Each callable function must be annotated as such with the ELF function type. In asm code, this is typically done using the ENTRY/ENDPROC macros. If objtool finds a return instruction outside of a function, it flags an error since that usually indicates callable code which should be annotated accordingly. This rule is needed so that objtool can properly identify each callable function in order to analyze its stack metadata. 2. Conversely, each section of code which is *not* callable should *not* be annotated as an ELF function. The ENDPROC macro shouldn't be used in this case. This rule is needed so that objtool can ignore non-callable code. Such code doesn't have to follow any of the other rules. 3. Each callable function which calls another function must have the correct frame pointer logic, if required by CONFIG_FRAME_POINTER or the architecture's back chain rules. This can by done in asm code with the FRAME_BEGIN/FRAME_END macros. This rule ensures that frame pointer based stack traces will work as designed. If function A doesn't create a stack frame before calling function B, the _caller_ of function A will be skipped on the stack trace. 4. Dynamic jumps and jumps to undefined symbols are only allowed if: a) the jump is part of a switch statement; or b) the jump matches sibling call semantics and the frame pointer has the same value it had on function entry. This rule is needed so that objtool can reliably analyze all of a function's code paths. If a function jumps to code in another file, and it's not a sibling call, objtool has no way to follow the jump because it only analyzes a single file at a time. 5. A callable function may not execute kernel entry/exit instructions. The only code which needs such instructions is kernel entry code, which shouldn't be be in callable functions anyway. This rule is just a sanity check to ensure that callable functions return normally. It currently only supports x86_64. I tried to make the code generic so that support for other architectures can hopefully be plugged in relatively easily. On my Lenovo laptop with a i7-4810MQ 4-core/8-thread CPU, building the kernel with objtool checking every .o file adds about three seconds of total build time. It hasn't been optimized for performance yet, so there are probably some opportunities for better build performance. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Bernd Petrovitsch <bernd@petrovitsch.priv.at> Cc: Borislav Petkov <bp@alien8.de> Cc: Chris J Arges <chris.j.arges@canonical.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Pedro Alves <palves@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: live-patching@vger.kernel.org Link: http://lkml.kernel.org/r/f3efb173de43bd067b060de73f856567c0fa1174.1456719558.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
404 lines
8.1 KiB
C
404 lines
8.1 KiB
C
/*
|
|
* elf.c - ELF access library
|
|
*
|
|
* Adapted from kpatch (https://github.com/dynup/kpatch):
|
|
* Copyright (C) 2013-2015 Josh Poimboeuf <jpoimboe@redhat.com>
|
|
* Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version 2
|
|
* of the License, or (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#include <sys/types.h>
|
|
#include <sys/stat.h>
|
|
#include <fcntl.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <unistd.h>
|
|
|
|
#include "elf.h"
|
|
#include "warn.h"
|
|
|
|
struct section *find_section_by_name(struct elf *elf, const char *name)
|
|
{
|
|
struct section *sec;
|
|
|
|
list_for_each_entry(sec, &elf->sections, list)
|
|
if (!strcmp(sec->name, name))
|
|
return sec;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static struct section *find_section_by_index(struct elf *elf,
|
|
unsigned int idx)
|
|
{
|
|
struct section *sec;
|
|
|
|
list_for_each_entry(sec, &elf->sections, list)
|
|
if (sec->idx == idx)
|
|
return sec;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
|
|
{
|
|
struct section *sec;
|
|
struct symbol *sym;
|
|
|
|
list_for_each_entry(sec, &elf->sections, list)
|
|
list_for_each_entry(sym, &sec->symbols, list)
|
|
if (sym->idx == idx)
|
|
return sym;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
|
|
{
|
|
struct symbol *sym;
|
|
|
|
list_for_each_entry(sym, &sec->symbols, list)
|
|
if (sym->type != STT_SECTION &&
|
|
sym->offset == offset)
|
|
return sym;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
|
|
unsigned int len)
|
|
{
|
|
struct rela *rela;
|
|
|
|
if (!sec->rela)
|
|
return NULL;
|
|
|
|
list_for_each_entry(rela, &sec->rela->relas, list)
|
|
if (rela->offset >= offset && rela->offset < offset + len)
|
|
return rela;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset)
|
|
{
|
|
return find_rela_by_dest_range(sec, offset, 1);
|
|
}
|
|
|
|
struct symbol *find_containing_func(struct section *sec, unsigned long offset)
|
|
{
|
|
struct symbol *func;
|
|
|
|
list_for_each_entry(func, &sec->symbols, list)
|
|
if (func->type == STT_FUNC && offset >= func->offset &&
|
|
offset < func->offset + func->len)
|
|
return func;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static int read_sections(struct elf *elf)
|
|
{
|
|
Elf_Scn *s = NULL;
|
|
struct section *sec;
|
|
size_t shstrndx, sections_nr;
|
|
int i;
|
|
|
|
if (elf_getshdrnum(elf->elf, §ions_nr)) {
|
|
perror("elf_getshdrnum");
|
|
return -1;
|
|
}
|
|
|
|
if (elf_getshdrstrndx(elf->elf, &shstrndx)) {
|
|
perror("elf_getshdrstrndx");
|
|
return -1;
|
|
}
|
|
|
|
for (i = 0; i < sections_nr; i++) {
|
|
sec = malloc(sizeof(*sec));
|
|
if (!sec) {
|
|
perror("malloc");
|
|
return -1;
|
|
}
|
|
memset(sec, 0, sizeof(*sec));
|
|
|
|
INIT_LIST_HEAD(&sec->symbols);
|
|
INIT_LIST_HEAD(&sec->relas);
|
|
|
|
list_add_tail(&sec->list, &elf->sections);
|
|
|
|
s = elf_getscn(elf->elf, i);
|
|
if (!s) {
|
|
perror("elf_getscn");
|
|
return -1;
|
|
}
|
|
|
|
sec->idx = elf_ndxscn(s);
|
|
|
|
if (!gelf_getshdr(s, &sec->sh)) {
|
|
perror("gelf_getshdr");
|
|
return -1;
|
|
}
|
|
|
|
sec->name = elf_strptr(elf->elf, shstrndx, sec->sh.sh_name);
|
|
if (!sec->name) {
|
|
perror("elf_strptr");
|
|
return -1;
|
|
}
|
|
|
|
sec->elf_data = elf_getdata(s, NULL);
|
|
if (!sec->elf_data) {
|
|
perror("elf_getdata");
|
|
return -1;
|
|
}
|
|
|
|
if (sec->elf_data->d_off != 0 ||
|
|
sec->elf_data->d_size != sec->sh.sh_size) {
|
|
WARN("unexpected data attributes for %s", sec->name);
|
|
return -1;
|
|
}
|
|
|
|
sec->data = (unsigned long)sec->elf_data->d_buf;
|
|
sec->len = sec->elf_data->d_size;
|
|
}
|
|
|
|
/* sanity check, one more call to elf_nextscn() should return NULL */
|
|
if (elf_nextscn(elf->elf, s)) {
|
|
WARN("section entry mismatch");
|
|
return -1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int read_symbols(struct elf *elf)
|
|
{
|
|
struct section *symtab;
|
|
struct symbol *sym;
|
|
struct list_head *entry, *tmp;
|
|
int symbols_nr, i;
|
|
|
|
symtab = find_section_by_name(elf, ".symtab");
|
|
if (!symtab) {
|
|
WARN("missing symbol table");
|
|
return -1;
|
|
}
|
|
|
|
symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
|
|
|
|
for (i = 0; i < symbols_nr; i++) {
|
|
sym = malloc(sizeof(*sym));
|
|
if (!sym) {
|
|
perror("malloc");
|
|
return -1;
|
|
}
|
|
memset(sym, 0, sizeof(*sym));
|
|
|
|
sym->idx = i;
|
|
|
|
if (!gelf_getsym(symtab->elf_data, i, &sym->sym)) {
|
|
perror("gelf_getsym");
|
|
goto err;
|
|
}
|
|
|
|
sym->name = elf_strptr(elf->elf, symtab->sh.sh_link,
|
|
sym->sym.st_name);
|
|
if (!sym->name) {
|
|
perror("elf_strptr");
|
|
goto err;
|
|
}
|
|
|
|
sym->type = GELF_ST_TYPE(sym->sym.st_info);
|
|
sym->bind = GELF_ST_BIND(sym->sym.st_info);
|
|
|
|
if (sym->sym.st_shndx > SHN_UNDEF &&
|
|
sym->sym.st_shndx < SHN_LORESERVE) {
|
|
sym->sec = find_section_by_index(elf,
|
|
sym->sym.st_shndx);
|
|
if (!sym->sec) {
|
|
WARN("couldn't find section for symbol %s",
|
|
sym->name);
|
|
goto err;
|
|
}
|
|
if (sym->type == STT_SECTION) {
|
|
sym->name = sym->sec->name;
|
|
sym->sec->sym = sym;
|
|
}
|
|
} else
|
|
sym->sec = find_section_by_index(elf, 0);
|
|
|
|
sym->offset = sym->sym.st_value;
|
|
sym->len = sym->sym.st_size;
|
|
|
|
/* sorted insert into a per-section list */
|
|
entry = &sym->sec->symbols;
|
|
list_for_each_prev(tmp, &sym->sec->symbols) {
|
|
struct symbol *s;
|
|
|
|
s = list_entry(tmp, struct symbol, list);
|
|
|
|
if (sym->offset > s->offset) {
|
|
entry = tmp;
|
|
break;
|
|
}
|
|
|
|
if (sym->offset == s->offset && sym->len >= s->len) {
|
|
entry = tmp;
|
|
break;
|
|
}
|
|
}
|
|
list_add(&sym->list, entry);
|
|
}
|
|
|
|
return 0;
|
|
|
|
err:
|
|
free(sym);
|
|
return -1;
|
|
}
|
|
|
|
static int read_relas(struct elf *elf)
|
|
{
|
|
struct section *sec;
|
|
struct rela *rela;
|
|
int i;
|
|
unsigned int symndx;
|
|
|
|
list_for_each_entry(sec, &elf->sections, list) {
|
|
if (sec->sh.sh_type != SHT_RELA)
|
|
continue;
|
|
|
|
sec->base = find_section_by_name(elf, sec->name + 5);
|
|
if (!sec->base) {
|
|
WARN("can't find base section for rela section %s",
|
|
sec->name);
|
|
return -1;
|
|
}
|
|
|
|
sec->base->rela = sec;
|
|
|
|
for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) {
|
|
rela = malloc(sizeof(*rela));
|
|
if (!rela) {
|
|
perror("malloc");
|
|
return -1;
|
|
}
|
|
memset(rela, 0, sizeof(*rela));
|
|
|
|
list_add_tail(&rela->list, &sec->relas);
|
|
|
|
if (!gelf_getrela(sec->elf_data, i, &rela->rela)) {
|
|
perror("gelf_getrela");
|
|
return -1;
|
|
}
|
|
|
|
rela->type = GELF_R_TYPE(rela->rela.r_info);
|
|
rela->addend = rela->rela.r_addend;
|
|
rela->offset = rela->rela.r_offset;
|
|
symndx = GELF_R_SYM(rela->rela.r_info);
|
|
rela->sym = find_symbol_by_index(elf, symndx);
|
|
if (!rela->sym) {
|
|
WARN("can't find rela entry symbol %d for %s",
|
|
symndx, sec->name);
|
|
return -1;
|
|
}
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct elf *elf_open(const char *name)
|
|
{
|
|
struct elf *elf;
|
|
|
|
elf_version(EV_CURRENT);
|
|
|
|
elf = malloc(sizeof(*elf));
|
|
if (!elf) {
|
|
perror("malloc");
|
|
return NULL;
|
|
}
|
|
memset(elf, 0, sizeof(*elf));
|
|
|
|
INIT_LIST_HEAD(&elf->sections);
|
|
|
|
elf->name = strdup(name);
|
|
if (!elf->name) {
|
|
perror("strdup");
|
|
goto err;
|
|
}
|
|
|
|
elf->fd = open(name, O_RDONLY);
|
|
if (elf->fd == -1) {
|
|
perror("open");
|
|
goto err;
|
|
}
|
|
|
|
elf->elf = elf_begin(elf->fd, ELF_C_READ_MMAP, NULL);
|
|
if (!elf->elf) {
|
|
perror("elf_begin");
|
|
goto err;
|
|
}
|
|
|
|
if (!gelf_getehdr(elf->elf, &elf->ehdr)) {
|
|
perror("gelf_getehdr");
|
|
goto err;
|
|
}
|
|
|
|
if (read_sections(elf))
|
|
goto err;
|
|
|
|
if (read_symbols(elf))
|
|
goto err;
|
|
|
|
if (read_relas(elf))
|
|
goto err;
|
|
|
|
return elf;
|
|
|
|
err:
|
|
elf_close(elf);
|
|
return NULL;
|
|
}
|
|
|
|
void elf_close(struct elf *elf)
|
|
{
|
|
struct section *sec, *tmpsec;
|
|
struct symbol *sym, *tmpsym;
|
|
struct rela *rela, *tmprela;
|
|
|
|
list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) {
|
|
list_for_each_entry_safe(sym, tmpsym, &sec->symbols, list) {
|
|
list_del(&sym->list);
|
|
free(sym);
|
|
}
|
|
list_for_each_entry_safe(rela, tmprela, &sec->relas, list) {
|
|
list_del(&rela->list);
|
|
free(rela);
|
|
}
|
|
list_del(&sec->list);
|
|
free(sec);
|
|
}
|
|
if (elf->name)
|
|
free(elf->name);
|
|
if (elf->fd > 0)
|
|
close(elf->fd);
|
|
if (elf->elf)
|
|
elf_end(elf->elf);
|
|
free(elf);
|
|
}
|