x86/ftrace: Use text_poke()

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

This also avoids ftrace violating the (new) W^X rule and avoids
fragmenting the kernel text page-tables, due to no longer having to
toggle them RW.
Tested-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191111132457.761255803@infradead.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/ftrace.h

@@ -34,8 +34,6 @@ 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 */

arch/x86/kernel/alternative.c

@@ -949,7 +949,7 @@ static struct bp_patching_desc {
 	int nr_entries;
 } bp_patching;
 
-static int patch_cmp(const void *key, const void *elt)
+static int notrace patch_cmp(const void *key, const void *elt)
 {
 	struct text_poke_loc *tp = (struct text_poke_loc *) elt;
 
@@ -961,7 +961,7 @@ static int patch_cmp(const void *key, const void *elt)
 }
 NOKPROBE_SYMBOL(patch_cmp);
 
-int poke_int3_handler(struct pt_regs *regs)
+int notrace poke_int3_handler(struct pt_regs *regs)
 {
 	struct text_poke_loc *tp;
 	void *ip;
@@ -1209,10 +1209,15 @@ void text_poke_finish(void)
 	text_poke_flush(NULL);
 }
 
-void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
+void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
 {
 	struct text_poke_loc *tp;
 
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
 	text_poke_flush(addr);
 
 	tp = &tp_vec[tp_vec_nr++];
@@ -1230,10 +1235,15 @@ void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emu
  * 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, const void *emulate)
+void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
 {
 	struct text_poke_loc tp;
 
+	if (unlikely(system_state == SYSTEM_BOOTING)) {
+		text_poke_early(addr, opcode, len);
+		return;
+	}
+
 	text_poke_loc_init(&tp, addr, opcode, len, emulate);
 	text_poke_bp_batch(&tp, 1);
 }

arch/x86/kernel/traps.c

@@ -563,15 +563,6 @@ 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;