1
0
Fork 0
alistair23-linux/scripts/recordmcount.c

672 lines
17 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* recordmcount.c: construct a table of the locations of calls to 'mcount'
* so that ftrace can find them quickly.
* Copyright 2009 John F. Reiser <jreiser@BitWagon.com>. All rights reserved.
*
* Restructured to fit Linux format, as well as other updates:
* Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
*/
/*
* Strategy: alter the .o file in-place.
*
* Append a new STRTAB that has the new section names, followed by a new array
* ElfXX_Shdr[] that has the new section headers, followed by the section
* contents for __mcount_loc and its relocations. The old shstrtab strings,
* and the old ElfXX_Shdr[] array, remain as "garbage" (commonly, a couple
* kilobytes.) Subsequent processing by /bin/ld (or the kernel module loader)
* will ignore the garbage regions, because they are not designated by the
* new .e_shoff nor the new ElfXX_Shdr[]. [In order to remove the garbage,
* then use "ld -r" to create a new file that omits the garbage.]
*/
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <getopt.h>
#include <elf.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#ifndef EM_AARCH64
#define EM_AARCH64 183
#define R_AARCH64_NONE 0
#define R_AARCH64_ABS64 257
#endif
ARM: 8950/1: ftrace/recordmcount: filter relocation types commit 927d780ee371d7e121cea4fc7812f6ef2cea461c upstream. Scenario 1, ARMv7 ================= If code in arch/arm/kernel/ftrace.c would operate on mcount() pointer the following may be generated: 00000230 <prealloc_fixed_plts>: 230: b5f8 push {r3, r4, r5, r6, r7, lr} 232: b500 push {lr} 234: f7ff fffe bl 0 <__gnu_mcount_nc> 234: R_ARM_THM_CALL __gnu_mcount_nc 238: f240 0600 movw r6, #0 238: R_ARM_THM_MOVW_ABS_NC __gnu_mcount_nc 23c: f8d0 1180 ldr.w r1, [r0, #384] ; 0x180 FTRACE currently is not able to deal with it: WARNING: CPU: 0 PID: 0 at .../kernel/trace/ftrace.c:1979 ftrace_bug+0x1ad/0x230() ... CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.4.116-... #1 ... [<c0314e3d>] (unwind_backtrace) from [<c03115e9>] (show_stack+0x11/0x14) [<c03115e9>] (show_stack) from [<c051a7f1>] (dump_stack+0x81/0xa8) [<c051a7f1>] (dump_stack) from [<c0321c5d>] (warn_slowpath_common+0x69/0x90) [<c0321c5d>] (warn_slowpath_common) from [<c0321cf3>] (warn_slowpath_null+0x17/0x1c) [<c0321cf3>] (warn_slowpath_null) from [<c038ee9d>] (ftrace_bug+0x1ad/0x230) [<c038ee9d>] (ftrace_bug) from [<c038f1f9>] (ftrace_process_locs+0x27d/0x444) [<c038f1f9>] (ftrace_process_locs) from [<c08915bd>] (ftrace_init+0x91/0xe8) [<c08915bd>] (ftrace_init) from [<c0885a67>] (start_kernel+0x34b/0x358) [<c0885a67>] (start_kernel) from [<00308095>] (0x308095) ---[ end trace cb88537fdc8fa200 ]--- ftrace failed to modify [<c031266c>] prealloc_fixed_plts+0x8/0x60 actual: 44:f2:e1:36 ftrace record flags: 0 (0) expected tramp: c03143e9 Scenario 2, ARMv4T ================== ftrace: allocating 14435 entries in 43 pages ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2029 ftrace_bug+0x204/0x310 CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.5 #1 Hardware name: Cirrus Logic EDB9302 Evaluation Board [<c0010a24>] (unwind_backtrace) from [<c000ecb0>] (show_stack+0x20/0x2c) [<c000ecb0>] (show_stack) from [<c03c72e8>] (dump_stack+0x20/0x30) [<c03c72e8>] (dump_stack) from [<c0021c18>] (__warn+0xdc/0x104) [<c0021c18>] (__warn) from [<c0021d7c>] (warn_slowpath_null+0x4c/0x5c) [<c0021d7c>] (warn_slowpath_null) from [<c0095360>] (ftrace_bug+0x204/0x310) [<c0095360>] (ftrace_bug) from [<c04dabac>] (ftrace_init+0x3b4/0x4d4) [<c04dabac>] (ftrace_init) from [<c04cef4c>] (start_kernel+0x20c/0x410) [<c04cef4c>] (start_kernel) from [<00000000>] ( (null)) ---[ end trace 0506a2f5dae6b341 ]--- ftrace failed to modify [<c000c350>] perf_trace_sys_exit+0x5c/0xe8 actual: 1e:ff:2f:e1 Initializing ftrace call sites ftrace record flags: 0 (0) expected tramp: c000fb24 The analysis for this problem has been already performed previously, refer to the link below. Fix the above problems by allowing only selected reloc types in __mcount_loc. The list itself comes from the legacy recordmcount.pl script. Link: https://lore.kernel.org/lkml/56961010.6000806@pengutronix.de/ Cc: stable@vger.kernel.org Fixes: ed60453fa8f8 ("ARM: 6511/1: ftrace: add ARM support for C version of recordmcount") Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-01-08 07:57:47 -07:00
#define R_ARM_PC24 1
#define R_ARM_THM_CALL 10
#define R_ARM_CALL 28
#define R_AARCH64_CALL26 283
static int fd_map; /* File descriptor for file being modified. */
static int mmap_failed; /* Boolean flag. */
static char gpfx; /* prefix for global symbol name (sometimes '_') */
static struct stat sb; /* Remember .st_size, etc. */
static const char *altmcount; /* alternate mcount symbol name */
static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
static void *file_map; /* pointer of the mapped file */
static void *file_end; /* pointer to the end of the mapped file */
static int file_updated; /* flag to state file was changed */
static void *file_ptr; /* current file pointer location */
static void *file_append; /* added to the end of the file */
static size_t file_append_size; /* how much is added to end of file */
/* Per-file resource cleanup when multiple files. */
static void file_append_cleanup(void)
{
free(file_append);
file_append = NULL;
file_append_size = 0;
file_updated = 0;
}
static void mmap_cleanup(void)
{
if (!mmap_failed)
munmap(file_map, sb.st_size);
else
free(file_map);
file_map = NULL;
}
/* ulseek, uwrite, ...: Check return value for errors. */
static off_t ulseek(off_t const offset, int const whence)
{
switch (whence) {
case SEEK_SET:
file_ptr = file_map + offset;
break;
case SEEK_CUR:
file_ptr += offset;
break;
case SEEK_END:
file_ptr = file_map + (sb.st_size - offset);
break;
}
if (file_ptr < file_map) {
fprintf(stderr, "lseek: seek before file\n");
return -1;
}
return file_ptr - file_map;
}
static ssize_t uwrite(void const *const buf, size_t const count)
{
size_t cnt = count;
off_t idx = 0;
file_updated = 1;
if (file_ptr + count >= file_end) {
off_t aoffset = (file_ptr + count) - file_end;
if (aoffset > file_append_size) {
file_append = realloc(file_append, aoffset);
file_append_size = aoffset;
}
if (!file_append) {
perror("write");
file_append_cleanup();
mmap_cleanup();
return -1;
}
if (file_ptr < file_end) {
cnt = file_end - file_ptr;
} else {
cnt = 0;
idx = aoffset - count;
}
}
if (cnt)
memcpy(file_ptr, buf, cnt);
if (cnt < count)
memcpy(file_append + idx, buf + cnt, count - cnt);
file_ptr += count;
return count;
}
static void * umalloc(size_t size)
{
void *const addr = malloc(size);
if (addr == 0) {
fprintf(stderr, "malloc failed: %zu bytes\n", size);
file_append_cleanup();
mmap_cleanup();
return NULL;
}
return addr;
}
/*
* 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; new info will be appended to the file.
* Use MAP_PRIVATE so that a few changes to the in-memory ElfXX_Ehdr
* do not propagate to the file until an explicit overwrite at the last.
* This preserves most aspects of consistency (all except .st_size)
* for simultaneous readers of the file while we are appending to it.
* However, multiple writers still are bad. We choose not to use
* locking because it is expensive and the use case of kernel build
* makes multiple writers unlikely.
*/
static void *mmap_file(char const *fname)
{
/* Avoid problems if early cleanup() */
fd_map = -1;
mmap_failed = 1;
file_map = NULL;
file_ptr = NULL;
file_updated = 0;
sb.st_size = 0;
fd_map = open(fname, O_RDONLY);
if (fd_map < 0) {
perror(fname);
return NULL;
}
if (fstat(fd_map, &sb) < 0) {
perror(fname);
goto out;
}
if (!S_ISREG(sb.st_mode)) {
fprintf(stderr, "not a regular file: %s\n", fname);
goto out;
}
file_map = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
fd_map, 0);
if (file_map == MAP_FAILED) {
mmap_failed = 1;
file_map = umalloc(sb.st_size);
if (!file_map) {
perror(fname);
goto out;
}
if (read(fd_map, file_map, sb.st_size) != sb.st_size) {
perror(fname);
free(file_map);
file_map = NULL;
goto out;
}
} else
mmap_failed = 0;
out:
close(fd_map);
fd_map = -1;
file_end = file_map + sb.st_size;
return file_map;
}
static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
static unsigned char *ideal_nop;
static char rel_type_nop;
static int (*make_nop)(void *map, size_t const offset);
static int make_nop_x86(void *map, size_t const offset)
{
uint32_t *ptr;
unsigned char *op;
/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
ptr = map + offset;
if (*ptr != 0)
return -1;
op = map + offset - 1;
if (*op != 0xe8)
return -1;
/* convert to nop */
if (ulseek(offset - 1, SEEK_SET) < 0)
return -1;
if (uwrite(ideal_nop, 5) < 0)
return -1;
return 0;
}
static unsigned char ideal_nop4_arm_le[4] = { 0x00, 0x00, 0xa0, 0xe1 }; /* mov r0, r0 */
static unsigned char ideal_nop4_arm_be[4] = { 0xe1, 0xa0, 0x00, 0x00 }; /* mov r0, r0 */
static unsigned char *ideal_nop4_arm;
static unsigned char bl_mcount_arm_le[4] = { 0xfe, 0xff, 0xff, 0xeb }; /* bl */
static unsigned char bl_mcount_arm_be[4] = { 0xeb, 0xff, 0xff, 0xfe }; /* bl */
static unsigned char *bl_mcount_arm;
static unsigned char push_arm_le[4] = { 0x04, 0xe0, 0x2d, 0xe5 }; /* push {lr} */
static unsigned char push_arm_be[4] = { 0xe5, 0x2d, 0xe0, 0x04 }; /* push {lr} */
static unsigned char *push_arm;
static unsigned char ideal_nop2_thumb_le[2] = { 0x00, 0xbf }; /* nop */
static unsigned char ideal_nop2_thumb_be[2] = { 0xbf, 0x00 }; /* nop */
static unsigned char *ideal_nop2_thumb;
static unsigned char push_bl_mcount_thumb_le[6] = { 0x00, 0xb5, 0xff, 0xf7, 0xfe, 0xff }; /* push {lr}, bl */
static unsigned char push_bl_mcount_thumb_be[6] = { 0xb5, 0x00, 0xf7, 0xff, 0xff, 0xfe }; /* push {lr}, bl */
static unsigned char *push_bl_mcount_thumb;
static int make_nop_arm(void *map, size_t const offset)
{
char *ptr;
int cnt = 1;
int nop_size;
size_t off = offset;
ptr = map + offset;
if (memcmp(ptr, bl_mcount_arm, 4) == 0) {
if (memcmp(ptr - 4, push_arm, 4) == 0) {
off -= 4;
cnt = 2;
}
ideal_nop = ideal_nop4_arm;
nop_size = 4;
} else if (memcmp(ptr - 2, push_bl_mcount_thumb, 6) == 0) {
cnt = 3;
nop_size = 2;
off -= 2;
ideal_nop = ideal_nop2_thumb;
} else
return -1;
/* Convert to nop */
if (ulseek(off, SEEK_SET) < 0)
return -1;
do {
if (uwrite(ideal_nop, nop_size) < 0)
return -1;
} while (--cnt > 0);
return 0;
}
static unsigned char ideal_nop4_arm64[4] = {0x1f, 0x20, 0x03, 0xd5};
static int make_nop_arm64(void *map, size_t const offset)
{
uint32_t *ptr;
ptr = map + offset;
/* bl <_mcount> is 0x94000000 before relocation */
if (*ptr != 0x94000000)
return -1;
/* Convert to nop */
if (ulseek(offset, SEEK_SET) < 0)
return -1;
if (uwrite(ideal_nop, 4) < 0)
return -1;
return 0;
}
static int write_file(const char *fname)
{
char tmp_file[strlen(fname) + 4];
size_t n;
if (!file_updated)
return 0;
sprintf(tmp_file, "%s.rc", fname);
/*
* After reading the entire file into memory, delete it
* and write it back, to prevent weird side effects of modifying
* an object file in place.
*/
fd_map = open(tmp_file, O_WRONLY | O_TRUNC | O_CREAT, sb.st_mode);
if (fd_map < 0) {
perror(fname);
return -1;
}
n = write(fd_map, file_map, sb.st_size);
if (n != sb.st_size) {
perror("write");
close(fd_map);
return -1;
}
if (file_append_size) {
n = write(fd_map, file_append, file_append_size);
if (n != file_append_size) {
perror("write");
close(fd_map);
return -1;
}
}
close(fd_map);
if (rename(tmp_file, fname) < 0) {
perror(fname);
return -1;
}
return 0;
}
/* 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);
/* Names of the sections that could contain calls to mcount. */
static int is_mcounted_section_name(char const *const txtname)
{
return strncmp(".text", txtname, 5) == 0 ||
strcmp(".init.text", txtname) == 0 ||
strcmp(".ref.text", txtname) == 0 ||
strcmp(".sched.text", txtname) == 0 ||
strcmp(".spinlock.text", txtname) == 0 ||
strcmp(".irqentry.text", txtname) == 0 ||
strcmp(".softirqentry.text", txtname) == 0 ||
strcmp(".kprobes.text", txtname) == 0 ||
strcmp(".cpuidle.text", txtname) == 0;
}
static char const *already_has_rel_mcount = "success"; /* our work here is done! */
/* 32 bit and 64 bit are very similar */
#include "recordmcount.h"
#define RECORD_MCOUNT_64
#include "recordmcount.h"
ARM: 8950/1: ftrace/recordmcount: filter relocation types commit 927d780ee371d7e121cea4fc7812f6ef2cea461c upstream. Scenario 1, ARMv7 ================= If code in arch/arm/kernel/ftrace.c would operate on mcount() pointer the following may be generated: 00000230 <prealloc_fixed_plts>: 230: b5f8 push {r3, r4, r5, r6, r7, lr} 232: b500 push {lr} 234: f7ff fffe bl 0 <__gnu_mcount_nc> 234: R_ARM_THM_CALL __gnu_mcount_nc 238: f240 0600 movw r6, #0 238: R_ARM_THM_MOVW_ABS_NC __gnu_mcount_nc 23c: f8d0 1180 ldr.w r1, [r0, #384] ; 0x180 FTRACE currently is not able to deal with it: WARNING: CPU: 0 PID: 0 at .../kernel/trace/ftrace.c:1979 ftrace_bug+0x1ad/0x230() ... CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.4.116-... #1 ... [<c0314e3d>] (unwind_backtrace) from [<c03115e9>] (show_stack+0x11/0x14) [<c03115e9>] (show_stack) from [<c051a7f1>] (dump_stack+0x81/0xa8) [<c051a7f1>] (dump_stack) from [<c0321c5d>] (warn_slowpath_common+0x69/0x90) [<c0321c5d>] (warn_slowpath_common) from [<c0321cf3>] (warn_slowpath_null+0x17/0x1c) [<c0321cf3>] (warn_slowpath_null) from [<c038ee9d>] (ftrace_bug+0x1ad/0x230) [<c038ee9d>] (ftrace_bug) from [<c038f1f9>] (ftrace_process_locs+0x27d/0x444) [<c038f1f9>] (ftrace_process_locs) from [<c08915bd>] (ftrace_init+0x91/0xe8) [<c08915bd>] (ftrace_init) from [<c0885a67>] (start_kernel+0x34b/0x358) [<c0885a67>] (start_kernel) from [<00308095>] (0x308095) ---[ end trace cb88537fdc8fa200 ]--- ftrace failed to modify [<c031266c>] prealloc_fixed_plts+0x8/0x60 actual: 44:f2:e1:36 ftrace record flags: 0 (0) expected tramp: c03143e9 Scenario 2, ARMv4T ================== ftrace: allocating 14435 entries in 43 pages ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2029 ftrace_bug+0x204/0x310 CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.5 #1 Hardware name: Cirrus Logic EDB9302 Evaluation Board [<c0010a24>] (unwind_backtrace) from [<c000ecb0>] (show_stack+0x20/0x2c) [<c000ecb0>] (show_stack) from [<c03c72e8>] (dump_stack+0x20/0x30) [<c03c72e8>] (dump_stack) from [<c0021c18>] (__warn+0xdc/0x104) [<c0021c18>] (__warn) from [<c0021d7c>] (warn_slowpath_null+0x4c/0x5c) [<c0021d7c>] (warn_slowpath_null) from [<c0095360>] (ftrace_bug+0x204/0x310) [<c0095360>] (ftrace_bug) from [<c04dabac>] (ftrace_init+0x3b4/0x4d4) [<c04dabac>] (ftrace_init) from [<c04cef4c>] (start_kernel+0x20c/0x410) [<c04cef4c>] (start_kernel) from [<00000000>] ( (null)) ---[ end trace 0506a2f5dae6b341 ]--- ftrace failed to modify [<c000c350>] perf_trace_sys_exit+0x5c/0xe8 actual: 1e:ff:2f:e1 Initializing ftrace call sites ftrace record flags: 0 (0) expected tramp: c000fb24 The analysis for this problem has been already performed previously, refer to the link below. Fix the above problems by allowing only selected reloc types in __mcount_loc. The list itself comes from the legacy recordmcount.pl script. Link: https://lore.kernel.org/lkml/56961010.6000806@pengutronix.de/ Cc: stable@vger.kernel.org Fixes: ed60453fa8f8 ("ARM: 6511/1: ftrace: add ARM support for C version of recordmcount") Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-01-08 07:57:47 -07:00
static int arm_is_fake_mcount(Elf32_Rel const *rp)
{
switch (ELF32_R_TYPE(w(rp->r_info))) {
case R_ARM_THM_CALL:
case R_ARM_CALL:
case R_ARM_PC24:
return 0;
}
return 1;
}
recordmcount: only record relocation of type R_AARCH64_CALL26 on arm64. [ Upstream commit ea0eada45632f4807b2f49de951072283e2d781c ] Currently, if a section has a relocation to '_mcount' symbol, a new __mcount_loc entry will be added whatever the relocation type is. This is problematic when a relocation to '_mcount' is in the middle of a section and is not a call for ftrace use. Such relocation could be generated with below code for example: bool is_mcount(unsigned long addr) { return (target == (unsigned long) &_mcount); } With this snippet of code, ftrace will try to patch the mcount location generated by this code on module load and fail with: Call trace: ftrace_bug+0xa0/0x28c ftrace_process_locs+0x2f4/0x430 ftrace_module_init+0x30/0x38 load_module+0x14f0/0x1e78 __do_sys_finit_module+0x100/0x11c __arm64_sys_finit_module+0x28/0x34 el0_svc_common+0x88/0x194 el0_svc_handler+0x38/0x8c el0_svc+0x8/0xc ---[ end trace d828d06b36ad9d59 ]--- ftrace failed to modify [<ffffa2dbf3a3a41c>] 0xffffa2dbf3a3a41c actual: 66:a9:3c:90 Initializing ftrace call sites ftrace record flags: 2000000 (0) expected tramp: ffffa2dc6cf66724 So Limit the relocation type to R_AARCH64_CALL26 as in perl version of recordmcount. Fixes: af64d2aa872a ("ftrace: Add arm64 support to recordmcount") Signed-off-by: Gregory Herrero <gregory.herrero@oracle.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Link: https://lore.kernel.org/r/20200717143338.19302-1-gregory.herrero@oracle.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-07-17 08:33:38 -06:00
static int arm64_is_fake_mcount(Elf64_Rel const *rp)
{
return ELF64_R_TYPE(w(rp->r_info)) != R_AARCH64_CALL26;
}
/* 64-bit EM_MIPS has weird ELF64_Rela.r_info.
* http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf
* We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40]
* to imply the order of the members; the spec does not say so.
* typedef unsigned char Elf64_Byte;
* fails on MIPS64 because their <elf.h> already has it!
*/
typedef uint8_t myElf64_Byte; /* Type for a 8-bit quantity. */
union mips_r_info {
Elf64_Xword r_info;
struct {
Elf64_Word r_sym; /* Symbol index. */
myElf64_Byte r_ssym; /* Special symbol. */
myElf64_Byte r_type3; /* Third relocation. */
myElf64_Byte r_type2; /* Second relocation. */
myElf64_Byte r_type; /* First relocation. */
} r_mips;
};
static uint64_t MIPS64_r_sym(Elf64_Rel const *rp)
{
return w(((union mips_r_info){ .r_info = rp->r_info }).r_mips.r_sym);
}
static void MIPS64_r_info(Elf64_Rel *const rp, unsigned sym, unsigned type)
{
rp->r_info = ((union mips_r_info){
.r_mips = { .r_sym = w(sym), .r_type = type }
}).r_info;
}
static int do_file(char const *const fname)
{
unsigned int reltype = 0;
Elf32_Ehdr *ehdr;
int rc = -1;
ehdr = mmap_file(fname);
if (!ehdr)
goto out;
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);
goto out;
case ELFDATA2LSB:
if (*(unsigned char const *)&endian != 1) {
/* main() is big endian, file.o is little endian. */
w = w4rev;
w2 = w2rev;
w8 = w8rev;
}
ideal_nop4_arm = ideal_nop4_arm_le;
bl_mcount_arm = bl_mcount_arm_le;
push_arm = push_arm_le;
ideal_nop2_thumb = ideal_nop2_thumb_le;
push_bl_mcount_thumb = push_bl_mcount_thumb_le;
break;
case ELFDATA2MSB:
if (*(unsigned char const *)&endian != 0) {
/* main() is little endian, file.o is big endian. */
w = w4rev;
w2 = w2rev;
w8 = w8rev;
}
ideal_nop4_arm = ideal_nop4_arm_be;
bl_mcount_arm = bl_mcount_arm_be;
push_arm = push_arm_be;
ideal_nop2_thumb = ideal_nop2_thumb_be;
push_bl_mcount_thumb = push_bl_mcount_thumb_be;
break;
} /* end switch */
if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 ||
w2(ehdr->e_type) != ET_REL ||
ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
goto out;
}
gpfx = '_';
switch (w2(ehdr->e_machine)) {
default:
fprintf(stderr, "unrecognized e_machine %u %s\n",
w2(ehdr->e_machine), fname);
goto out;
case EM_386:
reltype = R_386_32;
rel_type_nop = R_386_NONE;
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_32;
mcount_adjust_32 = -1;
gpfx = 0;
break;
case EM_ARM:
reltype = R_ARM_ABS32;
altmcount = "__gnu_mcount_nc";
make_nop = make_nop_arm;
rel_type_nop = R_ARM_NONE;
ARM: 8950/1: ftrace/recordmcount: filter relocation types commit 927d780ee371d7e121cea4fc7812f6ef2cea461c upstream. Scenario 1, ARMv7 ================= If code in arch/arm/kernel/ftrace.c would operate on mcount() pointer the following may be generated: 00000230 <prealloc_fixed_plts>: 230: b5f8 push {r3, r4, r5, r6, r7, lr} 232: b500 push {lr} 234: f7ff fffe bl 0 <__gnu_mcount_nc> 234: R_ARM_THM_CALL __gnu_mcount_nc 238: f240 0600 movw r6, #0 238: R_ARM_THM_MOVW_ABS_NC __gnu_mcount_nc 23c: f8d0 1180 ldr.w r1, [r0, #384] ; 0x180 FTRACE currently is not able to deal with it: WARNING: CPU: 0 PID: 0 at .../kernel/trace/ftrace.c:1979 ftrace_bug+0x1ad/0x230() ... CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.4.116-... #1 ... [<c0314e3d>] (unwind_backtrace) from [<c03115e9>] (show_stack+0x11/0x14) [<c03115e9>] (show_stack) from [<c051a7f1>] (dump_stack+0x81/0xa8) [<c051a7f1>] (dump_stack) from [<c0321c5d>] (warn_slowpath_common+0x69/0x90) [<c0321c5d>] (warn_slowpath_common) from [<c0321cf3>] (warn_slowpath_null+0x17/0x1c) [<c0321cf3>] (warn_slowpath_null) from [<c038ee9d>] (ftrace_bug+0x1ad/0x230) [<c038ee9d>] (ftrace_bug) from [<c038f1f9>] (ftrace_process_locs+0x27d/0x444) [<c038f1f9>] (ftrace_process_locs) from [<c08915bd>] (ftrace_init+0x91/0xe8) [<c08915bd>] (ftrace_init) from [<c0885a67>] (start_kernel+0x34b/0x358) [<c0885a67>] (start_kernel) from [<00308095>] (0x308095) ---[ end trace cb88537fdc8fa200 ]--- ftrace failed to modify [<c031266c>] prealloc_fixed_plts+0x8/0x60 actual: 44:f2:e1:36 ftrace record flags: 0 (0) expected tramp: c03143e9 Scenario 2, ARMv4T ================== ftrace: allocating 14435 entries in 43 pages ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2029 ftrace_bug+0x204/0x310 CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.5 #1 Hardware name: Cirrus Logic EDB9302 Evaluation Board [<c0010a24>] (unwind_backtrace) from [<c000ecb0>] (show_stack+0x20/0x2c) [<c000ecb0>] (show_stack) from [<c03c72e8>] (dump_stack+0x20/0x30) [<c03c72e8>] (dump_stack) from [<c0021c18>] (__warn+0xdc/0x104) [<c0021c18>] (__warn) from [<c0021d7c>] (warn_slowpath_null+0x4c/0x5c) [<c0021d7c>] (warn_slowpath_null) from [<c0095360>] (ftrace_bug+0x204/0x310) [<c0095360>] (ftrace_bug) from [<c04dabac>] (ftrace_init+0x3b4/0x4d4) [<c04dabac>] (ftrace_init) from [<c04cef4c>] (start_kernel+0x20c/0x410) [<c04cef4c>] (start_kernel) from [<00000000>] ( (null)) ---[ end trace 0506a2f5dae6b341 ]--- ftrace failed to modify [<c000c350>] perf_trace_sys_exit+0x5c/0xe8 actual: 1e:ff:2f:e1 Initializing ftrace call sites ftrace record flags: 0 (0) expected tramp: c000fb24 The analysis for this problem has been already performed previously, refer to the link below. Fix the above problems by allowing only selected reloc types in __mcount_loc. The list itself comes from the legacy recordmcount.pl script. Link: https://lore.kernel.org/lkml/56961010.6000806@pengutronix.de/ Cc: stable@vger.kernel.org Fixes: ed60453fa8f8 ("ARM: 6511/1: ftrace: add ARM support for C version of recordmcount") Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-01-08 07:57:47 -07:00
is_fake_mcount32 = arm_is_fake_mcount;
gpfx = 0;
break;
case EM_AARCH64:
reltype = R_AARCH64_ABS64;
make_nop = make_nop_arm64;
rel_type_nop = R_AARCH64_NONE;
ideal_nop = ideal_nop4_arm64;
recordmcount: only record relocation of type R_AARCH64_CALL26 on arm64. [ Upstream commit ea0eada45632f4807b2f49de951072283e2d781c ] Currently, if a section has a relocation to '_mcount' symbol, a new __mcount_loc entry will be added whatever the relocation type is. This is problematic when a relocation to '_mcount' is in the middle of a section and is not a call for ftrace use. Such relocation could be generated with below code for example: bool is_mcount(unsigned long addr) { return (target == (unsigned long) &_mcount); } With this snippet of code, ftrace will try to patch the mcount location generated by this code on module load and fail with: Call trace: ftrace_bug+0xa0/0x28c ftrace_process_locs+0x2f4/0x430 ftrace_module_init+0x30/0x38 load_module+0x14f0/0x1e78 __do_sys_finit_module+0x100/0x11c __arm64_sys_finit_module+0x28/0x34 el0_svc_common+0x88/0x194 el0_svc_handler+0x38/0x8c el0_svc+0x8/0xc ---[ end trace d828d06b36ad9d59 ]--- ftrace failed to modify [<ffffa2dbf3a3a41c>] 0xffffa2dbf3a3a41c actual: 66:a9:3c:90 Initializing ftrace call sites ftrace record flags: 2000000 (0) expected tramp: ffffa2dc6cf66724 So Limit the relocation type to R_AARCH64_CALL26 as in perl version of recordmcount. Fixes: af64d2aa872a ("ftrace: Add arm64 support to recordmcount") Signed-off-by: Gregory Herrero <gregory.herrero@oracle.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Link: https://lore.kernel.org/r/20200717143338.19302-1-gregory.herrero@oracle.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-07-17 08:33:38 -06:00
is_fake_mcount64 = arm64_is_fake_mcount;
break;
case EM_IA_64: reltype = R_IA64_IMM64; break;
case EM_MIPS: /* reltype: e_class */ break;
case EM_PPC: reltype = R_PPC_ADDR32; break;
case EM_PPC64: reltype = R_PPC64_ADDR64; break;
case EM_S390: /* reltype: e_class */ break;
case EM_SH: reltype = R_SH_DIR32; gpfx = 0; break;
case EM_SPARCV9: reltype = R_SPARC_64; break;
case EM_X86_64:
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_64;
reltype = R_X86_64_64;
rel_type_nop = R_X86_64_NONE;
mcount_adjust_64 = -1;
gpfx = 0;
break;
} /* end switch */
switch (ehdr->e_ident[EI_CLASS]) {
default:
fprintf(stderr, "unrecognized ELF class %d %s\n",
ehdr->e_ident[EI_CLASS], fname);
goto out;
case ELFCLASS32:
if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
|| w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
fprintf(stderr,
"unrecognized ET_REL file: %s\n", fname);
goto out;
}
if (w2(ehdr->e_machine) == EM_MIPS) {
reltype = R_MIPS_32;
ftrace/MIPS: Add module support for C version of recordmcount Since MIPS modules' address space differs from the core kernel space, to access the _mcount in the core kernel, the kernel functions in modules must use long call (-mlong-calls): load the _mcount address into one register and jump to the address stored by the register: c: 3c030000 lui v1,0x0 <--------> b label c: R_MIPS_HI16 _mcount c: R_MIPS_NONE *ABS* c: R_MIPS_NONE *ABS* 10: 64630000 daddiu v1,v1,0 10: R_MIPS_LO16 _mcount 10: R_MIPS_NONE *ABS* 10: R_MIPS_NONE *ABS* 14: 03e0082d move at,ra 18: 0060f809 jalr v1 label: In the old Perl version of recordmcount, we only need to record the position of the 1st R_MIPS_HI16 type of _mcount, and later, in ftrace_make_nop(), replace the instruction in this position by a "b label" and in ftrace_make_call(), replace it back. But, the default C version of recordmcount records all of the _mcount symbols, so, we must filter the 2nd _mcount like the Perl version of recordmcount does. The C version of recordmcount copes with the symbols before they are linked, So It doesn't know the type of the symbols and therefore can not filter the symbols as the Perl version of recordmcount does. But as we can see above, the 2nd _mcount symbols of the long call alawys follows the 1st _mcount symbol of the same long call, which means the offset from the 1st to the 2nd is fixed, it is 0x10-0xc = 4 here, 4 is the length of the 1st load instruciton, for MIPS has fixed length of instructions, this offset is always 4. And as we know, the _mcount is inserted into the entry of every kernel function, the offset between the other _mcount's is expected to be always bigger than 4. So, to filter the 2ns _mcount symbol of the long call, we can simply check the offset between two _mcount symbols, If it is 4, then, filter the 2nd _mcount symbol. To avoid touching too much code, an 'empty' function fn_is_fake_mcount() is added for all of the archs, and the specific archs can override it via chaning the function pointer: is_fake_mcount in do_file() with the e_machine. e.g. This patch adds MIPS_is_fake_mcount() to override the default fn_is_fake_mcount() pointed by is_fake_mcount. This fn_is_fake_mcount() checks if the _mcount symbol is fake, e.g. the 2nd _mcount symbol of the long call is fake, for there are 2 _mcount symbols mapped to one real mcount call, so, one of them is fake and must be filtered. This fn_is_fake_mcount() is called in sift_rel_mcount() after finding the _mcount symbols and before adding the _mcount symbol into mrelp, so, it can prevent the fake mcount symbol going into the last __mcount_loc table. Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com> LKML-Reference: <b866f0138224340a132d31861fa3f9300dee30ac.1288176026.git.wuzhangjin@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-10-27 04:59:08 -06:00
is_fake_mcount32 = MIPS32_is_fake_mcount;
}
if (do32(ehdr, fname, reltype) < 0)
goto out;
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_REL file: %s\n", fname);
goto out;
}
if (w2(ghdr->e_machine) == EM_S390) {
reltype = R_390_64;
s390/ftrace,kprobes: allow to patch first instruction If the function tracer is enabled, allow to set kprobes on the first instruction of a function (which is the function trace caller): If no kprobe is set handling of enabling and disabling function tracing of a function simply patches the first instruction. Either it is a nop (right now it's an unconditional branch, which skips the mcount block), or it's a branch to the ftrace_caller() function. If a kprobe is being placed on a function tracer calling instruction we encode if we actually have a nop or branch in the remaining bytes after the breakpoint instruction (illegal opcode). This is possible, since the size of the instruction used for the nop and branch is six bytes, while the size of the breakpoint is only two bytes. Therefore the first two bytes contain the illegal opcode and the last four bytes contain either "0" for nop or "1" for branch. The kprobes code will then execute/simulate the correct instruction. Instruction patching for kprobes and function tracer is always done with stop_machine(). Therefore we don't have any races where an instruction is patched concurrently on a different cpu. Besides that also the program check handler which executes the function trace caller instruction won't be executed concurrently to any stop_machine() execution. This allows to keep full fault based kprobes handling which generates correct pt_regs contents automatically. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-10-15 04:17:38 -06:00
mcount_adjust_64 = -14;
}
if (w2(ghdr->e_machine) == EM_MIPS) {
reltype = R_MIPS_64;
Elf64_r_sym = MIPS64_r_sym;
Elf64_r_info = MIPS64_r_info;
ftrace/MIPS: Add module support for C version of recordmcount Since MIPS modules' address space differs from the core kernel space, to access the _mcount in the core kernel, the kernel functions in modules must use long call (-mlong-calls): load the _mcount address into one register and jump to the address stored by the register: c: 3c030000 lui v1,0x0 <--------> b label c: R_MIPS_HI16 _mcount c: R_MIPS_NONE *ABS* c: R_MIPS_NONE *ABS* 10: 64630000 daddiu v1,v1,0 10: R_MIPS_LO16 _mcount 10: R_MIPS_NONE *ABS* 10: R_MIPS_NONE *ABS* 14: 03e0082d move at,ra 18: 0060f809 jalr v1 label: In the old Perl version of recordmcount, we only need to record the position of the 1st R_MIPS_HI16 type of _mcount, and later, in ftrace_make_nop(), replace the instruction in this position by a "b label" and in ftrace_make_call(), replace it back. But, the default C version of recordmcount records all of the _mcount symbols, so, we must filter the 2nd _mcount like the Perl version of recordmcount does. The C version of recordmcount copes with the symbols before they are linked, So It doesn't know the type of the symbols and therefore can not filter the symbols as the Perl version of recordmcount does. But as we can see above, the 2nd _mcount symbols of the long call alawys follows the 1st _mcount symbol of the same long call, which means the offset from the 1st to the 2nd is fixed, it is 0x10-0xc = 4 here, 4 is the length of the 1st load instruciton, for MIPS has fixed length of instructions, this offset is always 4. And as we know, the _mcount is inserted into the entry of every kernel function, the offset between the other _mcount's is expected to be always bigger than 4. So, to filter the 2ns _mcount symbol of the long call, we can simply check the offset between two _mcount symbols, If it is 4, then, filter the 2nd _mcount symbol. To avoid touching too much code, an 'empty' function fn_is_fake_mcount() is added for all of the archs, and the specific archs can override it via chaning the function pointer: is_fake_mcount in do_file() with the e_machine. e.g. This patch adds MIPS_is_fake_mcount() to override the default fn_is_fake_mcount() pointed by is_fake_mcount. This fn_is_fake_mcount() checks if the _mcount symbol is fake, e.g. the 2nd _mcount symbol of the long call is fake, for there are 2 _mcount symbols mapped to one real mcount call, so, one of them is fake and must be filtered. This fn_is_fake_mcount() is called in sift_rel_mcount() after finding the _mcount symbols and before adding the _mcount symbol into mrelp, so, it can prevent the fake mcount symbol going into the last __mcount_loc table. Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com> LKML-Reference: <b866f0138224340a132d31861fa3f9300dee30ac.1288176026.git.wuzhangjin@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-10-27 04:59:08 -06:00
is_fake_mcount64 = MIPS64_is_fake_mcount;
}
if (do64(ghdr, fname, reltype) < 0)
goto out;
break;
}
} /* end switch */
rc = write_file(fname);
out:
file_append_cleanup();
mmap_cleanup();
return rc;
}
int main(int argc, char *argv[])
{
const char ftrace[] = "/ftrace.o";
int ftrace_size = sizeof(ftrace) - 1;
int n_error = 0; /* gcc-4.3.0 false positive complaint */
int c;
int i;
while ((c = getopt(argc, argv, "w")) >= 0) {
switch (c) {
case 'w':
warn_on_notrace_sect = 1;
break;
default:
fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
return 0;
}
}
if ((argc - optind) < 1) {
fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
return 0;
}
/* Process each file in turn, allowing deep failure. */
for (i = optind; i < argc; i++) {
char *file = argv[i];
int len;
/*
* The file kernel/trace/ftrace.o references the mcount
* function but does not call it. Since ftrace.o should
* not be traced anyway, we just skip it.
*/
len = strlen(file);
if (len >= ftrace_size &&
strcmp(file + (len - ftrace_size), ftrace) == 0)
continue;
if (do_file(file)) {
fprintf(stderr, "%s: failed\n", file);
++n_error;
}
}
return !!n_error;
}