[PATCH v4 21/27] x86/ftrace: Adapt function tracing for PIE support

[Thomas Garnier]

When using -fPIE/PIC with function tracing, the compiler generates a
call through the GOT (call *__fentry__@GOTPCREL). This instruction
takes 6 bytes instead of 5 on the usual relative call.

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.

Position Independent Executable (PIE) support will allow to extend the
KASLR randomization range 0xffffffff80000000.

Signed-off-by: Thomas Garnier <thgarnie@xxxxxxxxxx>
---
 arch/x86/include/asm/ftrace.h   |  4 --
 arch/x86/include/asm/sections.h |  4 ++
 arch/x86/kernel/ftrace.c        | 42 +++++++++++++++++-
 scripts/recordmcount.c          | 79 ++++++++++++++++++++++-----------
 4 files changed, 97 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index c18ed65287d5..b1eb3f6735fc 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -24,10 +24,6 @@ extern void __fentry__(void);
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
-	/*
-	 * addr is the address of the mcount call instruction.
-	 * recordmcount does the necessary offset calculation.
-	 */
 	return addr;
 }
 
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 5c019d23d06b..da3d98bb2bcb 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -13,4 +13,8 @@ extern char __end_rodata_hpage_align[];
 extern char __entry_trampoline_start[], __entry_trampoline_end[];
 #endif
 
+#if defined(CONFIG_X86_PIE)
+extern char __start_got[], __end_got[];
+#endif
+
 #endif	/* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 01ebcb6f263e..73b3c30cb7a3 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -102,7 +102,7 @@ static const unsigned char *ftrace_nop_replace(void)
 
 static int
 ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code)
+			  unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -135,6 +135,44 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 	return 0;
 }
 
+/* Bytes before call GOT offset */
+const unsigned char got_call_preinsn[] = { 0xff, 0x15 };
+
+static int
+ftrace_modify_initial_code(unsigned long ip, unsigned const char *old_code,
+			   unsigned const char *new_code)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE + 1];
+
+	ftrace_expected = old_code;
+
+	/*
+	 * If PIE is not enabled or no GOT call was found, default to the
+	 * original approach to code modification.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_PIE) ||
+	    probe_kernel_read(replaced, (void *)ip, sizeof(replaced)) ||
+	    memcmp(replaced, got_call_preinsn, sizeof(got_call_preinsn)))
+		return ftrace_modify_code_direct(ip, old_code, new_code);
+
+	/*
+	 * 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.
+	 */
+	memcpy(replaced, new_code, MCOUNT_INSN_SIZE);
+	replaced[MCOUNT_INSN_SIZE] = ideal_nops[1][0];
+
+	ip = text_ip_addr(ip);
+
+	if (probe_kernel_write((void *)ip, replaced, sizeof(replaced)))
+		return -EPERM;
+
+	sync_core();
+
+	return 0;
+
+}
+
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
@@ -153,7 +191,7 @@ int ftrace_make_nop(struct module *mod,
 	 * just modify the code directly.
 	 */
 	if (addr == MCOUNT_ADDR)
-		return ftrace_modify_code_direct(rec->ip, old, new);
+		return ftrace_modify_initial_code(rec->ip, old, new);
 
 	ftrace_expected = NULL;
 
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 895c40e8679f..aa71b912958d 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -171,33 +171,9 @@ umalloc(size_t size)
 	return addr;
 }
 
-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 */
-	ulseek(fd_map, offset - 1, SEEK_SET);
-	uwrite(fd_map, ideal_nop, 5);
-	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 */
@@ -447,6 +423,50 @@ 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 - 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 */
+	ulseek(fd_map, stub_offset, SEEK_SET);
+	uwrite(fd_map, ideal_nop, ideal_nop_x86_size);
+	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 void
 do_file(char const *const fname)
 {
@@ -509,6 +529,9 @@ 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;
 		break;
 	case EM_ARM:	 reltype = R_ARM_ABS32;
@@ -533,9 +556,13 @@ 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;
 		break;
 	}  /* end switch */
 
-- 
2.17.0.921.gf22659ad46-goog