[PATCH 0/3] Rewrite x86/ftrace to use text_poke()

[PATCH 0/3] Rewrite x86/ftrace to use text_poke()

[Peter Zijlstra]

Ftrace was one of the last W^X violators; these patches move it over to the
generic text_poke() interface and thereby get rid of this oddity.

Very lightly tested...

[PATCH 1/3] x86/alternatives: Teach text_poke_bp() to emulate instructions

[Peter Zijlstra]

In preparation for static_call and variable size jump_label support,
teach text_poke_bp() to emulate instructions, namely:

  JMP32, JMP8, CALL, NOP2, NOP_ATOMIC5

The current text_poke_bp() takes a @handler argument which is used as
a jump target when the temporary INT3 is hit by a different CPU.

When patching CALL instructions, this doesn't work because we'd miss
the PUSH of the return address. Instead, teach poke_int3_handler() to
emulate an instruction, typically the instruction we're patching in.

This fits almost all text_poke_bp() users, except
arch_unoptimize_kprobe() which restores random text, and for that site
we have to build an explicit emulate instruction.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/text-patching.h |   24 ++++++--
 arch/x86/kernel/alternative.c        |   98 ++++++++++++++++++++++++++---------
 arch/x86/kernel/jump_label.c         |    9 +--
 arch/x86/kernel/kprobes/opt.c        |   11 ++-
 4 files changed, 103 insertions(+), 39 deletions(-)

--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -26,10 +26,11 @@ static inline void apply_paravirt(struct
 #define POKE_MAX_OPCODE_SIZE	5
 
 struct text_poke_loc {
-	void *detour;
 	void *addr;
-	size_t len;
-	const char opcode[POKE_MAX_OPCODE_SIZE];
+	int len;
+	s32 rel32;
+	u8 opcode;
+	const char text[POKE_MAX_OPCODE_SIZE];
 };
 
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -51,8 +52,10 @@ extern void text_poke_early(void *addr,
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
 extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
+extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			       const void *opcode, size_t len, const void *emulate);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
@@ -63,8 +66,17 @@ static inline void int3_emulate_jmp(stru
 	regs->ip = ip;
 }
 
-#define INT3_INSN_SIZE 1
-#define CALL_INSN_SIZE 5
+#define INT3_INSN_SIZE		1
+#define INT3_INSN_OPCODE	0xCC
+
+#define CALL_INSN_SIZE		5
+#define CALL_INSN_OPCODE	0xE8
+
+#define JMP32_INSN_SIZE		5
+#define JMP32_INSN_OPCODE	0xE9
+
+#define JMP8_INSN_SIZE		2
+#define JMP8_INSN_OPCODE	0xEB
 
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -956,16 +956,15 @@ NOKPROBE_SYMBOL(patch_cmp);
 int poke_int3_handler(struct pt_regs *regs)
 {
 	struct text_poke_loc *tp;
-	unsigned char int3 = 0xcc;
 	void *ip;
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
 	 * bp_patching.nr_entries.
 	 *
-	 * 	nr_entries != 0			INT3
-	 * 	WMB				RMB
-	 * 	write INT3			if (nr_entries)
+	 *	nr_entries != 0			INT3
+	 *	WMB				RMB
+	 *	write INT3			if (nr_entries)
 	 *
 	 * Idem for other elements in bp_patching.
 	 */
@@ -978,9 +977,9 @@ int poke_int3_handler(struct pt_regs *re
 		return 0;
 
 	/*
-	 * Discount the sizeof(int3). See text_poke_bp_batch().
+	 * Discount the INT3. See text_poke_bp_batch().
 	 */
-	ip = (void *) regs->ip - sizeof(int3);
+	ip = (void *) regs->ip - INT3_INSN_SIZE;
 
 	/*
 	 * Skip the binary search if there is a single member in the vector.
@@ -997,8 +996,22 @@ int poke_int3_handler(struct pt_regs *re
 			return 0;
 	}
 
-	/* set up the specified breakpoint detour */
-	regs->ip = (unsigned long) tp->detour;
+	ip += tp->len;
+
+	switch (tp->opcode) {
+	case CALL_INSN_OPCODE:
+		int3_emulate_call(regs, (long)ip + tp->rel32);
+		break;
+
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		break;
+
+	default: /* nop */
+		int3_emulate_jmp(regs, (long)ip);
+		break;
+	}
 
 	return 1;
 }
@@ -1027,8 +1040,8 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  */
 void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
+	unsigned char int3 = INT3_INSN_OPCODE;
 	int patched_all_but_first = 0;
-	unsigned char int3 = 0xcc;
 	unsigned int i;
 
 	lockdep_assert_held(&text_mutex);
@@ -1056,7 +1069,7 @@ void text_poke_bp_batch(struct text_poke
 	for (i = 0; i < nr_entries; i++) {
 		if (tp[i].len - sizeof(int3) > 0) {
 			text_poke((char *)tp[i].addr + sizeof(int3),
-				  (const char *)tp[i].opcode + sizeof(int3),
+				  (const char *)tp[i].text + sizeof(int3),
 				  tp[i].len - sizeof(int3));
 			patched_all_but_first++;
 		}
@@ -1076,7 +1089,7 @@ void text_poke_bp_batch(struct text_poke
 	 * replacing opcode.
 	 */
 	for (i = 0; i < nr_entries; i++)
-		text_poke(tp[i].addr, tp[i].opcode, sizeof(int3));
+		text_poke(tp[i].addr, tp[i].text, sizeof(int3));
 
 	on_each_cpu(do_sync_core, NULL, 1);
 	/*
@@ -1087,6 +1100,53 @@ void text_poke_bp_batch(struct text_poke
 	bp_patching.nr_entries = 0;
 }
 
+void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+			const void *opcode, size_t len, const void *emulate)
+{
+	struct insn insn;
+
+	if (!opcode)
+		opcode = (void *)tp->text;
+	else
+		memcpy((void *)tp->text, opcode, len);
+
+	if (!emulate)
+		emulate = opcode;
+
+	kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
+	insn_get_length(&insn);
+
+	BUG_ON(!insn_complete(&insn));
+	BUG_ON(len != insn.length);
+
+	tp->addr = addr;
+	tp->len = len;
+	tp->opcode = insn.opcode.bytes[0];
+
+	switch (tp->opcode) {
+	case CALL_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		tp->rel32 = insn.immediate.value;
+		break;
+
+	default: /* assume NOP */
+		switch (len) {
+		case 2:
+			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			break;
+
+		case 5:
+			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			break;
+
+		default:
+			BUG();
+		}
+		break;
+	}
+}
+
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
  * @addr:	address to patch
@@ -1098,20 +1158,10 @@ void text_poke_bp_batch(struct text_poke
  * dynamically allocated memory. This function should be used when it is
  * not possible to allocate memory.
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	struct text_poke_loc tp = {
-		.detour = handler,
-		.addr = addr,
-		.len = len,
-	};
-
-	if (len > POKE_MAX_OPCODE_SIZE) {
-		WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE);
-		return;
-	}
-
-	memcpy((void *)tp.opcode, opcode, len);
+	struct text_poke_loc tp;
 
+	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -89,8 +89,7 @@ static void __ref __jump_label_transform
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE,
-		     (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
@@ -147,11 +146,9 @@ bool arch_jump_label_transform_queue(str
 	}
 
 	__jump_label_set_jump_code(entry, type,
-				   (union jump_code_union *) &tp->opcode, 0);
+				   (union jump_code_union *)&tp->text, 0);
 
-	tp->addr = entry_code;
-	tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
-	tp->len = JUMP_LABEL_NOP_SIZE;
+	text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
 
 	tp_vec_nr++;
 
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -437,8 +437,7 @@ void arch_optimize_kprobes(struct list_h
 		insn_buff[0] = RELATIVEJUMP_OPCODE;
 		*(s32 *)(&insn_buff[1]) = rel;
 
-		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-			     op->optinsn.insn);
+		text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL);
 
 		list_del_init(&op->list);
 	}
@@ -448,12 +447,18 @@ void arch_optimize_kprobes(struct list_h
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	u8 insn_buff[RELATIVEJUMP_SIZE];
+	u8 emulate_buff[RELATIVEJUMP_SIZE];
 
 	/* Set int3 to first byte for kprobes */
 	insn_buff[0] = BREAKPOINT_INSTRUCTION;
 	memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	emulate_buff[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
 	text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-		     op->optinsn.insn);
+		     emulate_buff);
 }
 
 /*

[PATCH 2/3] x86/alternatives: Move tp_vec

[Peter Zijlstra]

In order to allow other users to make use of the tp_vec; move it near
the text_poke_bp_batch() code, instead of keeping it in the jump_label
code.

Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/text-patching.h |    4 ++++
 arch/x86/kernel/alternative.c        |    3 +++
 arch/x86/kernel/jump_label.c         |   25 ++++++++++++-------------
 3 files changed, 19 insertions(+), 13 deletions(-)

--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -60,6 +60,10 @@ extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
 
+#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
+extern struct text_poke_loc tp_vec[TP_VEC_MAX];
+extern int tp_vec_nr;
+
 #ifndef CONFIG_UML_X86
 static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
 {
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1017,6 +1017,9 @@ int poke_int3_handler(struct pt_regs *re
 }
 NOKPROBE_SYMBOL(poke_int3_handler);
 
+struct text_poke_loc tp_vec[TP_VEC_MAX];
+int tp_vec_nr;
+
 /**
  * text_poke_bp_batch() -- update instructions on live kernel on SMP
  * @tp:			vector of instructions to patch
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -100,15 +100,12 @@ void arch_jump_label_transform(struct ju
 	mutex_unlock(&text_mutex);
 }
 
-#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
-static struct text_poke_loc tp_vec[TP_VEC_MAX];
-static int tp_vec_nr;
-
 bool arch_jump_label_transform_queue(struct jump_entry *entry,
 				     enum jump_label_type type)
 {
 	struct text_poke_loc *tp;
 	void *entry_code;
+	bool ret = true;
 
 	if (system_state == SYSTEM_BOOTING) {
 		/*
@@ -118,12 +115,15 @@ bool arch_jump_label_transform_queue(str
 		return true;
 	}
 
+	mutex_lock(&text_mutex);
 	/*
 	 * No more space in the vector, tell upper layer to apply
 	 * the queue before continuing.
 	 */
-	if (tp_vec_nr == TP_VEC_MAX)
-		return false;
+	if (tp_vec_nr == TP_VEC_MAX) {
+		ret = false;
+		goto unlock;
+	}
 
 	tp = &tp_vec[tp_vec_nr];
 
@@ -151,20 +151,19 @@ bool arch_jump_label_transform_queue(str
 	text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
 
 	tp_vec_nr++;
+unlock:
+	mutex_unlock(&text_mutex);
 
-	return true;
+	return ret;
 }
 
 void arch_jump_label_transform_apply(void)
 {
-	if (!tp_vec_nr)
-		return;
-
 	mutex_lock(&text_mutex);
-	text_poke_bp_batch(tp_vec, tp_vec_nr);
-	mutex_unlock(&text_mutex);
-
+	if (tp_vec_nr)
+		text_poke_bp_batch(tp_vec, tp_vec_nr);
 	tp_vec_nr = 0;
+	mutex_unlock(&text_mutex);
 }
 
 static enum {

[RFC][PATCH 3/3] x86/ftrace: Use text_poke()

[Peter Zijlstra]

Move ftrace over to using the generic x86 text_poke functions; this
avoids having a second/different copy of that code around.

Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/ftrace.h |    2 
 arch/x86/kernel/ftrace.c      |  571 +++---------------------------------------
 arch/x86/kernel/traps.c       |    9 
 3 files changed, 51 insertions(+), 531 deletions(-)

--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -35,8 +35,6 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-int ftrace_int3_handler(struct pt_regs *regs);
-
 #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -43,16 +43,17 @@ int ftrace_arch_code_modify_prepare(void
 	 * ftrace has it set to "read/write".
 	 */
 	mutex_lock(&text_mutex);
-	set_kernel_text_rw();
-	set_all_modules_text_rw();
+	WARN_ON_ONCE(tp_vec_nr);
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
     __releases(&text_mutex)
 {
-	set_all_modules_text_ro();
-	set_kernel_text_ro();
+	if (tp_vec_nr) {
+		text_poke_bp_batch(tp_vec, tp_vec_nr);
+		tp_vec_nr = 0;
+	}
 	mutex_unlock(&text_mutex);
 	return 0;
 }
@@ -60,67 +61,36 @@ int ftrace_arch_code_modify_post_process
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
-		unsigned char op;
+		char op;
 		int offset;
 	} __attribute__((packed));
 };
 
-static int ftrace_calc_offset(long ip, long addr)
-{
-	return (int)(addr - ip);
-}
-
-static unsigned char *
-ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr)
+static char *ftrace_text_replace(char op, unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
-	calc.op		= op;
-	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
+	calc.op = op;
+	calc.offset = (int)(addr - (ip + MCOUNT_INSN_SIZE));
 
 	return calc.code;
 }
 
-static unsigned char *
-ftrace_call_replace(unsigned long ip, unsigned long addr)
-{
-	return ftrace_text_replace(0xe8, ip, addr);
-}
-
-static inline int
-within(unsigned long addr, unsigned long start, unsigned long end)
+static char *ftrace_nop_replace(void)
 {
-	return addr >= start && addr < end;
-}
-
-static unsigned long text_ip_addr(unsigned long ip)
-{
-	/*
-	 * On x86_64, kernel text mappings are mapped read-only, so we use
-	 * the kernel identity mapping instead of the kernel text mapping
-	 * to modify the kernel text.
-	 *
-	 * For 32bit kernels, these mappings are same and we can use
-	 * kernel identity mapping to modify code.
-	 */
-	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
-		ip = (unsigned long)__va(__pa_symbol(ip));
-
-	return ip;
+	return ideal_nops[NOP_ATOMIC5];
 }
 
-static const unsigned char *ftrace_nop_replace(void)
+static char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
-	return ideal_nops[NOP_ATOMIC5];
+	return ftrace_text_replace(CALL_INSN_OPCODE, ip, addr);
 }
 
-static int
-ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code)
+static int;
+ftrace_modify_code_direct(unsigned long ip, const char *old_code,
+			  const char *new_code)
 {
-	unsigned char replaced[MCOUNT_INSN_SIZE];
-
-	ftrace_expected = old_code;
+	char cur_code[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note:
@@ -129,31 +99,23 @@ ftrace_modify_code_direct(unsigned long
 	 * Carefully read and modify the code with probe_kernel_*(), and make
 	 * sure what we read is what we expected it to be before modifying it.
 	 */
-
 	/* read the text we want to modify */
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+	if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
-	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+	if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
-	ip = text_ip_addr(ip);
-
 	/* replace the text with the new text */
-	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
-		return -EPERM;
-
-	sync_core();
-
+	text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
-int ftrace_make_nop(struct module *mod,
-		    struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
+	const char *new, *old;
 
 	old = ftrace_call_replace(ip, addr);
 	new = ftrace_nop_replace();
@@ -166,20 +128,21 @@ int ftrace_make_nop(struct module *mod,
 	 * We do not want to use the breakpoint version in this case,
 	 * just modify the code directly.
 	 */
-	if (addr == MCOUNT_ADDR)
-		return ftrace_modify_code_direct(rec->ip, old, new);
+	if (addr == MCOUNT)
+		return ftrace_modify_code_direct(ip, old, new);
 
-	ftrace_expected = NULL;
-
-	/* Normal cases use add_brk_on_nop */
+	/*
+	 * x86 overrides ftrace_replace_code -- this function will never be used
+	 * in this case.
+	 */
 	WARN_ONCE(1, "invalid use of ftrace_make_nop");
 	return -EINVAL;
 }
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
+	const char *new, *old;
 
 	old = ftrace_nop_replace();
 	new = ftrace_call_replace(ip, addr);
@@ -189,43 +152,6 @@ int ftrace_make_call(struct dyn_ftrace *
 }
 
 /*
- * The modifying_ftrace_code is used to tell the breakpoint
- * handler to call ftrace_int3_handler(). If it fails to
- * call this handler for a breakpoint added by ftrace, then
- * the kernel may crash.
- *
- * As atomic_writes on x86 do not need a barrier, we do not
- * need to add smp_mb()s for this to work. It is also considered
- * that we can not read the modifying_ftrace_code before
- * executing the breakpoint. That would be quite remarkable if
- * it could do that. Here's the flow that is required:
- *
- *   CPU-0                          CPU-1
- *
- * atomic_inc(mfc);
- * write int3s
- *				<trap-int3> // implicit (r)mb
- *				if (atomic_read(mfc))
- *					call ftrace_int3_handler()
- *
- * Then when we are finished:
- *
- * atomic_dec(mfc);
- *
- * If we hit a breakpoint that was not set by ftrace, it does not
- * matter if ftrace_int3_handler() is called or not. It will
- * simply be ignored. But it is crucial that a ftrace nop/caller
- * breakpoint is handled. No other user should ever place a
- * breakpoint on an ftrace nop/caller location. It must only
- * be done by this code.
- */
-atomic_t modifying_ftrace_code __read_mostly;
-
-static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code);
-
-/*
  * Should never be called:
  *  As it is only called by __ftrace_replace_code() which is called by
  *  ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
@@ -237,452 +163,57 @@ int ftrace_modify_call(struct dyn_ftrace
 				 unsigned long addr)
 {
 	WARN_ON(1);
-	ftrace_expected = NULL;
 	return -EINVAL;
 }
 
-static unsigned long ftrace_update_func;
-static unsigned long ftrace_update_func_call;
-
-static int update_ftrace_func(unsigned long ip, void *new)
-{
-	unsigned char old[MCOUNT_INSN_SIZE];
-	int ret;
-
-	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
-
-	ftrace_update_func = ip;
-	/* Make sure the breakpoints see the ftrace_update_func update */
-	smp_wmb();
-
-	/* See comment above by declaration of modifying_ftrace_code */
-	atomic_inc(&modifying_ftrace_code);
-
-	ret = ftrace_modify_code(ip, old, new);
-
-	atomic_dec(&modifying_ftrace_code);
-
-	return ret;
-}
-
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
 	unsigned char *new;
-	int ret;
-
-	ftrace_update_func_call = (unsigned long)func;
 
 	new = ftrace_call_replace(ip, (unsigned long)func);
-	ret = update_ftrace_func(ip, new);
-
-	/* Also update the regs callback function */
-	if (!ret) {
-		ip = (unsigned long)(&ftrace_regs_call);
-		new = ftrace_call_replace(ip, (unsigned long)func);
-		ret = update_ftrace_func(ip, new);
-	}
-
-	return ret;
-}
-
-static nokprobe_inline int is_ftrace_caller(unsigned long ip)
-{
-	if (ip == ftrace_update_func)
-		return 1;
-
-	return 0;
-}
-
-/*
- * A breakpoint was added to the code address we are about to
- * modify, and this is the handle that will just skip over it.
- * We are either changing a nop into a trace call, or a trace
- * call to a nop. While the change is taking place, we treat
- * it just like it was a nop.
- */
-int ftrace_int3_handler(struct pt_regs *regs)
-{
-	unsigned long ip;
-
-	if (WARN_ON_ONCE(!regs))
-		return 0;
-
-	ip = regs->ip - INT3_INSN_SIZE;
-
-	if (ftrace_location(ip)) {
-		int3_emulate_call(regs, (unsigned long)ftrace_regs_caller);
-		return 1;
-	} else if (is_ftrace_caller(ip)) {
-		if (!ftrace_update_func_call) {
-			int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
-			return 1;
-		}
-		int3_emulate_call(regs, ftrace_update_func_call);
-		return 1;
-	}
-
-	return 0;
-}
-NOKPROBE_SYMBOL(ftrace_int3_handler);
-
-static int ftrace_write(unsigned long ip, const char *val, int size)
-{
-	ip = text_ip_addr(ip);
-
-	if (probe_kernel_write((void *)ip, val, size))
-		return -EPERM;
-
-	return 0;
-}
-
-static int add_break(unsigned long ip, const char *old)
-{
-	unsigned char replaced[MCOUNT_INSN_SIZE];
-	unsigned char brk = BREAKPOINT_INSTRUCTION;
-
-	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	ftrace_expected = old;
-
-	/* Make sure it is what we expect it to be */
-	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
-		return -EINVAL;
-
-	return ftrace_write(ip, &brk, 1);
-}
-
-static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned const char *old;
-	unsigned long ip = rec->ip;
-
-	old = ftrace_call_replace(ip, addr);
-
-	return add_break(rec->ip, old);
-}
-
-
-static int add_brk_on_nop(struct dyn_ftrace *rec)
-{
-	unsigned const char *old;
-
-	old = ftrace_nop_replace();
-
-	return add_break(rec->ip, old);
-}
-
-static int add_breakpoints(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ftrace_addr = ftrace_get_addr_curr(rec);
-
-	ret = ftrace_test_record(rec, enable);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return add_brk_on_nop(rec);
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return add_brk_on_call(rec, ftrace_addr);
-	}
-	return 0;
-}
-
-/*
- * On error, we need to remove breakpoints. This needs to
- * be done caefully. If the address does not currently have a
- * breakpoint, we know we are done. Otherwise, we look at the
- * remaining 4 bytes of the instruction. If it matches a nop
- * we replace the breakpoint with the nop. Otherwise we replace
- * it with the call instruction.
- */
-static int remove_breakpoint(struct dyn_ftrace *rec)
-{
-	unsigned char ins[MCOUNT_INSN_SIZE];
-	unsigned char brk = BREAKPOINT_INSTRUCTION;
-	const unsigned char *nop;
-	unsigned long ftrace_addr;
-	unsigned long ip = rec->ip;
-
-	/* If we fail the read, just give up */
-	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	/* If this does not have a breakpoint, we are done */
-	if (ins[0] != brk)
-		return 0;
-
-	nop = ftrace_nop_replace();
-
-	/*
-	 * If the last 4 bytes of the instruction do not match
-	 * a nop, then we assume that this is a call to ftrace_addr.
-	 */
-	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
-		/*
-		 * For extra paranoidism, we check if the breakpoint is on
-		 * a call that would actually jump to the ftrace_addr.
-		 * If not, don't touch the breakpoint, we make just create
-		 * a disaster.
-		 */
-		ftrace_addr = ftrace_get_addr_new(rec);
-		nop = ftrace_call_replace(ip, ftrace_addr);
-
-		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
-			goto update;
-
-		/* Check both ftrace_addr and ftrace_old_addr */
-		ftrace_addr = ftrace_get_addr_curr(rec);
-		nop = ftrace_call_replace(ip, ftrace_addr);
-
-		ftrace_expected = nop;
-
-		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
-			return -EINVAL;
-	}
-
- update:
-	return ftrace_write(ip, nop, 1);
-}
-
-static int add_update_code(unsigned long ip, unsigned const char *new)
-{
-	/* skip breakpoint */
-	ip++;
-	new++;
-	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
-}
-
-static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_call_replace(ip, addr);
-	return add_update_code(ip, new);
-}
-
-static int add_update_nop(struct dyn_ftrace *rec)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_nop_replace();
-	return add_update_code(ip, new);
-}
-
-static int add_update(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ret = ftrace_test_record(rec, enable);
-
-	ftrace_addr  = ftrace_get_addr_new(rec);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return add_update_call(rec, ftrace_addr);
-
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return add_update_nop(rec);
-	}
-
-	return 0;
-}
-
-static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_call_replace(ip, addr);
-
-	return ftrace_write(ip, new, 1);
-}
-
-static int finish_update_nop(struct dyn_ftrace *rec)
-{
-	unsigned long ip = rec->ip;
-	unsigned const char *new;
-
-	new = ftrace_nop_replace();
-
-	return ftrace_write(ip, new, 1);
-}
-
-static int finish_update(struct dyn_ftrace *rec, bool enable)
-{
-	unsigned long ftrace_addr;
-	int ret;
-
-	ret = ftrace_update_record(rec, enable);
-
-	ftrace_addr = ftrace_get_addr_new(rec);
-
-	switch (ret) {
-	case FTRACE_UPDATE_IGNORE:
-		return 0;
-
-	case FTRACE_UPDATE_MODIFY_CALL:
-	case FTRACE_UPDATE_MAKE_CALL:
-		/* converting nop to call */
-		return finish_update_call(rec, ftrace_addr);
-
-	case FTRACE_UPDATE_MAKE_NOP:
-		/* converting a call to a nop */
-		return finish_update_nop(rec);
-	}
+	text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
 
 	return 0;
 }
 
-static void do_sync_core(void *data)
-{
-	sync_core();
-}
-
-static void run_sync(void)
-{
-	int enable_irqs;
-
-	/* No need to sync if there's only one CPU */
-	if (num_online_cpus() == 1)
-		return;
-
-	enable_irqs = irqs_disabled();
-
-	/* We may be called with interrupts disabled (on bootup). */
-	if (enable_irqs)
-		local_irq_enable();
-	on_each_cpu(do_sync_core, NULL, 1);
-	if (enable_irqs)
-		local_irq_disable();
-}
-
 void ftrace_replace_code(int enable)
 {
 	struct ftrace_rec_iter *iter;
+	struct text_poke_loc *tp;
 	struct dyn_ftrace *rec;
-	const char *report = "adding breakpoints";
-	int count = 0;
-	int ret;
+	const char *new;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 
-		ret = add_breakpoints(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
-	}
-
-	run_sync();
-
-	report = "updating code";
-	count = 0;
-
-	for_ftrace_rec_iter(iter) {
-		rec = ftrace_rec_iter_record(iter);
-
-		ret = add_update(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
-	}
-
-	run_sync();
-
-	report = "removing breakpoints";
-	count = 0;
-
-	for_ftrace_rec_iter(iter) {
-		rec = ftrace_rec_iter_record(iter);
-
-		ret = finish_update(rec, enable);
-		if (ret)
-			goto remove_breakpoints;
-		count++;
-	}
-
-	run_sync();
+		if (tp_vec_nr == TP_VEC_MAX) {
+			text_poke_bp_batch(tp_vec, tp_vec_nr);
+			tp_vec_nr = 0;
+		}
 
-	return;
+		switch (ftrace_test_record(rec, enable)) {
+		case FTRACE_UPDATE_IGNORE:
+			continue;
+
+		case FTRACE_UPDATE_MODIFY_CALL:
+		case FTRACE_UPDATE_MAKE_CALL:
+			new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec));
+			break;
+
+		case FTRACE_UPDATE_MAKE_NOP:
+			new = ftrace_nop_replace();
+			break;
+		};
 
- remove_breakpoints:
-	pr_warn("Failed on %s (%d):\n", report, count);
-	ftrace_bug(ret, rec);
-	for_ftrace_rec_iter(iter) {
-		rec = ftrace_rec_iter_record(iter);
-		/*
-		 * Breakpoints are handled only when this function is in
-		 * progress. The system could not work with them.
-		 */
-		if (remove_breakpoint(rec))
-			BUG();
+		tp = &tp_vec[tp_vec_nr++];
+		text_poke_loc_init(tp, (void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
 	}
-	run_sync();
-}
-
-static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
-		   unsigned const char *new_code)
-{
-	int ret;
-
-	ret = add_break(ip, old_code);
-	if (ret)
-		goto out;
-
-	run_sync();
-
-	ret = add_update_code(ip, new_code);
-	if (ret)
-		goto fail_update;
-
-	run_sync();
-
-	ret = ftrace_write(ip, new_code, 1);
-	/*
-	 * The breakpoint is handled only when this function is in progress.
-	 * The system could not work if we could not remove it.
-	 */
-	BUG_ON(ret);
- out:
-	run_sync();
-	return ret;
-
- fail_update:
-	/* Also here the system could not work with the breakpoint */
-	if (ftrace_write(ip, old_code, 1))
-		BUG();
-	goto out;
 }
 
 void arch_ftrace_update_code(int command)
 {
-	/* See comment above by declaration of modifying_ftrace_code */
-	atomic_inc(&modifying_ftrace_code);
-
 	ftrace_modify_all_code(command);
-
-	atomic_dec(&modifying_ftrace_code);
 }
 
 int __init ftrace_dyn_arch_init(void)
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -568,15 +568,6 @@ NOKPROBE_SYMBOL(do_general_protection);
 
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/*
-	 * ftrace must be first, everything else may cause a recursive crash.
-	 * See note by declaration of modifying_ftrace_code in ftrace.c
-	 */
-	if (unlikely(atomic_read(&modifying_ftrace_code)) &&
-	    ftrace_int3_handler(regs))
-		return;
-#endif
 	if (poke_int3_handler(regs))
 		return;
 

Re: [PATCH 0/3] Rewrite x86/ftrace to use text_poke()

[Peter Zijlstra]

On Mon, Aug 26, 2019 at 02:51:38PM +0200, Peter Zijlstra wrote:
> Ftrace was one of the last W^X violators; these patches move it over to the
> generic text_poke() interface and thereby get rid of this oddity.
> 
> Very lightly tested...

I'm thinking there's more cleanup to be had; set_kernel_text_*() can go
away now, and I'm thinking the whole batching thing can be further
simplified/shared between this and jump_label.

Re: [PATCH 2/3] x86/alternatives: Move tp_vec

[Peter Zijlstra]

On Mon, Aug 26, 2019 at 02:51:40PM +0200, Peter Zijlstra wrote:

> +#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
> +extern struct text_poke_loc tp_vec[TP_VEC_MAX];
> +extern int tp_vec_nr;

FWIW, that currently results in a batch size of 128, but I've not
noticed any delay in flipping ftrace on and off on the commandline.

Growing that buffer really shouldn't be a problem, but I'm thinking we'd
want solid performance numbers to justify it.

Re: [RFC][PATCH 3/3] x86/ftrace: Use text_poke()

[Peter Zijlstra]

On Mon, Aug 26, 2019 at 02:51:41PM +0200, Peter Zijlstra wrote:
> Move ftrace over to using the generic x86 text_poke functions; this
> avoids having a second/different copy of that code around.
> 
> Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

*sigh*.. one of those days again. I seem to have tested without this
patch applied.

Let me go fix this.

Re: [PATCH 0/3] Rewrite x86/ftrace to use text_poke()

[Song Liu]

Hi Peter,

> On Aug 27, 2019, at 11:06 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> 
> Ftrace was one of the last W^X violators; these patches move it over to the
> generic text_poke() interface and thereby get rid of this oddity.
> 
> The first patch has been posted before and was/is part of my (in-progress)
> static_call and jump_label/jmp8 patch series; but is equally needed here.
> 
> The second patch cleans up the text_poke batching code, and the third converts
> ftrace.

Thanks for the patch. It solves the kernel-text-PMD-split issue. 

The only problem I found is, it is not easy to back port these patches to 5.2 
based kernel.  

Thanks,
Song

Tested-by: Song Liu <songliubraving@fb.com>

 

[PATCH 0/3] Rewrite x86/ftrace to use text_poke()

[Peter Zijlstra]

Ftrace was one of the last W^X violators; these patches move it over to the
generic text_poke() interface and thereby get rid of this oddity.

The first patch has been posted before and was/is part of my (in-progress)
static_call and jump_label/jmp8 patch series; but is equally needed here.

The second patch cleans up the text_poke batching code, and the third converts
ftrace.

---
 arch/x86/include/asm/ftrace.h        |   2 -
 arch/x86/include/asm/text-patching.h |  28 +-
 arch/x86/kernel/alternative.c        | 156 +++++++--
 arch/x86/kernel/ftrace.c             | 620 +++++------------------------------
 arch/x86/kernel/jump_label.c         |  83 ++---
 arch/x86/kernel/kprobes/opt.c        |  11 +-
 arch/x86/kernel/traps.c              |   9 -
 7 files changed, 261 insertions(+), 648 deletions(-)