[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <38a5029cd2590e04209117740f8912db36eff58f.1682673543.git.houwenlong.hwl@antgroup.com>
Date: Fri, 28 Apr 2023 17:51:02 +0800
From: "Hou Wenlong" <houwenlong.hwl@...group.com>
To: linux-kernel@...r.kernel.org
Cc: "Thomas Garnier" <thgarnie@...omium.org>,
"Lai Jiangshan" <jiangshan.ljs@...group.com>,
"Kees Cook" <keescook@...omium.org>,
"Hou Wenlong" <houwenlong.hwl@...group.com>,
"Steven Rostedt" <rostedt@...dmis.org>,
"Masami Hiramatsu" <mhiramat@...nel.org>,
"Mark Rutland" <mark.rutland@....com>,
"Thomas Gleixner" <tglx@...utronix.de>,
"Ingo Molnar" <mingo@...hat.com>, "Borislav Petkov" <bp@...en8.de>,
"Dave Hansen" <dave.hansen@...ux.intel.com>, <x86@...nel.org>,
"H. Peter Anvin" <hpa@...or.com>,
"Huacai Chen" <chenhuacai@...nel.org>,
"Qing Zhang" <zhangqing@...ngson.cn>,
<linux-trace-kernel@...r.kernel.org>
Subject: [PATCH RFC 22/43] x86/ftrace: Adapt ftrace nop patching for PIE support
From: Thomas Garnier <thgarnie@...omium.org>
From: Thomas Garnier <thgarnie@...omium.org>
When using PIE with function tracing, the compiler generates a
call through the GOT (call *__fentry__@...PCREL). This instruction
takes 6-bytes instead of 5-bytes with a relative call. And -mnop-mcount
option is not implemented for -fPIE now.
If PIE is enabled, replace the 6th byte of the GOT call by a 1-byte nop
so ftrace can handle the previous 5-bytes as before.
[Hou Wenlong: Adapt code change and fix wrong offset calculation in
make_nop_x86()]
Signed-off-by: Thomas Garnier <thgarnie@...omium.org>
Co-developed-by: Hou Wenlong <houwenlong.hwl@...group.com>
Signed-off-by: Hou Wenlong <houwenlong.hwl@...group.com>
Cc: Lai Jiangshan <jiangshan.ljs@...group.com>
Cc: Kees Cook <keescook@...omium.org>
---
arch/x86/kernel/ftrace.c | 46 ++++++++++++++++++++++-
scripts/recordmcount.c | 81 ++++++++++++++++++++++++++--------------
2 files changed, 98 insertions(+), 29 deletions(-)
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 5e7ead52cfdb..b795f9dde561 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -124,6 +124,50 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
return 0;
}
+/* Bytes before call GOT offset */
+static const unsigned char got_call_preinsn[] = { 0xff, 0x15 };
+
+static int __ref
+ftrace_modify_initial_code(unsigned long ip, unsigned const char *old_code,
+ unsigned const char *new_code)
+{
+ unsigned char replaced[MCOUNT_INSN_SIZE + 1];
+
+ /*
+ * If PIE is not enabled default to the original approach to code
+ * modification.
+ */
+ if (!IS_ENABLED(CONFIG_X86_PIE))
+ return ftrace_modify_code_direct(ip, old_code, new_code);
+
+ ftrace_expected = old_code;
+
+ /* Ensure the instructions point to a call to the GOT */
+ if (copy_from_kernel_nofault(replaced, (void *)ip, sizeof(replaced))) {
+ WARN_ONCE(1, "invalid function");
+ return -EFAULT;
+ }
+
+ if (memcmp(replaced, got_call_preinsn, sizeof(got_call_preinsn))) {
+ WARN_ONCE(1, "invalid function call");
+ return -EINVAL;
+ }
+
+ /*
+ * Build a nop slide with a 5-byte nop and 1-byte nop to keep the ftrace
+ * hooking algorithm working with the expected 5 bytes instruction.
+ */
+ memset(replaced, x86_nops[1][0], sizeof(replaced));
+ memcpy(replaced, new_code, MCOUNT_INSN_SIZE);
+
+ /* replace the text with the new text */
+ if (ftrace_poke_late)
+ text_poke_queue((void *)ip, replaced, MCOUNT_INSN_SIZE + 1, NULL);
+ else
+ text_poke_early((void *)ip, replaced, MCOUNT_INSN_SIZE + 1);
+ return 0;
+}
+
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
@@ -141,7 +185,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long ad
* just modify the code directly.
*/
if (addr == MCOUNT_ADDR)
- return ftrace_modify_code_direct(ip, old, new);
+ return ftrace_modify_initial_code(ip, old, new);
/*
* x86 overrides ftrace_replace_code -- this function will never be used
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index e30216525325..02783a29d428 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -218,36 +218,10 @@ static void *mmap_file(char const *fname)
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_nop;
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 */
@@ -504,6 +478,50 @@ static void MIPS64_r_info(Elf64_Rel *const rp, unsigned sym, unsigned type)
}).r_info;
}
+static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop6_x86_64[6] = { 0x66, 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+static size_t ideal_nop_x86_size;
+
+static unsigned char stub_default_x86[2] = { 0xe8, 0x00 }; /* call relative */
+static unsigned char stub_got_x86[3] = { 0xff, 0x15, 0x00 }; /* call .got */
+static unsigned char *stub_x86;
+static size_t stub_x86_size;
+
+static int make_nop_x86(void *map, size_t const offset)
+{
+ uint32_t *ptr;
+ size_t stub_offset = offset + 1 - stub_x86_size;
+
+ /* Confirm we have the expected stub */
+ ptr = map + stub_offset;
+ if (memcmp(ptr, stub_x86, stub_x86_size))
+ return -1;
+
+ /* convert to nop */
+ if (ulseek(stub_offset, SEEK_SET) < 0)
+ return -1;
+ if (uwrite(ideal_nop, ideal_nop_x86_size) < 0)
+ return -1;
+ return 0;
+}
+
+/* Swap the stub and nop for a got call if the binary is built with PIE */
+static int is_fake_mcount_x86_x64(Elf64_Rel const *rp)
+{
+ if (ELF64_R_TYPE(rp->r_info) == R_X86_64_GOTPCREL) {
+ ideal_nop = ideal_nop6_x86_64;
+ ideal_nop_x86_size = sizeof(ideal_nop6_x86_64);
+ stub_x86 = stub_got_x86;
+ stub_x86_size = sizeof(stub_got_x86);
+ mcount_adjust_64 = 1 - stub_x86_size;
+ }
+
+ /* Once the relocation was checked, rollback to default */
+ is_fake_mcount64 = fn_is_fake_mcount64;
+ return is_fake_mcount64(rp);
+}
+
static int do_file(char const *const fname)
{
unsigned int reltype = 0;
@@ -568,6 +586,9 @@ static int do_file(char const *const fname)
rel_type_nop = R_386_NONE;
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_32;
+ ideal_nop_x86_size = sizeof(ideal_nop5_x86_32);
+ stub_x86 = stub_default_x86;
+ stub_x86_size = sizeof(stub_default_x86);
mcount_adjust_32 = -1;
gpfx = 0;
break;
@@ -597,9 +618,13 @@ static int do_file(char const *const fname)
case EM_X86_64:
make_nop = make_nop_x86;
ideal_nop = ideal_nop5_x86_64;
+ ideal_nop_x86_size = sizeof(ideal_nop5_x86_64);
+ stub_x86 = stub_default_x86;
+ stub_x86_size = sizeof(stub_default_x86);
reltype = R_X86_64_64;
rel_type_nop = R_X86_64_NONE;
- mcount_adjust_64 = -1;
+ is_fake_mcount64 = is_fake_mcount_x86_x64;
+ mcount_adjust_64 = 1 - stub_x86_size;
gpfx = 0;
break;
} /* end switch */
--
2.31.1
Powered by blists - more mailing lists