kprobes/x86: Use text_poke_bp() instead of text_poke_smp*()

Use text_poke_bp() for optimizing kprobes instead of
text_poke_smp*(). Since the number of kprobes is usually not so
large (<100) and text_poke_bp() is much lighter than
text_poke_smp() [which uses stop_machine()], this just stops
using batch processing.
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Reviewed-by: Jiri Kosina <jkosina@suse.cz>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: yrl.pp-manager.tt@hitachi.com
Cc: Borislav Petkov <bpetkov@suse.de>
Link: http://lkml.kernel.org/r/20130718114750.26675.9174.stgit@mhiramat-M0-7522Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/kprobes/common.h

@@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to);
 extern void synthesize_relcall(void *from, void *to);
 
 #ifdef	CONFIG_OPTPROBES
-extern int arch_init_optprobes(void);
 extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
 extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
 #else	/* !CONFIG_OPTPROBES */
-static inline int arch_init_optprobes(void)
-{
-	return 0;
-}
 static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 {
 	return 0;

arch/x86/kernel/kprobes/core.c

@@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 
 int __init arch_init_kprobes(void)
 {
-	return arch_init_optprobes();
+	return 0;
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)

arch/x86/kernel/kprobes/opt.c

@@ -371,19 +371,21 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 	return 0;
 }
 
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-	u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-					    u8 *insn_buf,
-					    struct optimized_kprobe *op)
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
 {
+	struct optimized_kprobe *op, *tmp;
+	u8 insn_buf[RELATIVEJUMP_SIZE];
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
 		s32 rel = (s32)((long)op->optinsn.insn -
 			((long)op->kp.addr + RELATIVEJUMP_SIZE));
 
+		WARN_ON(kprobe_disabled(&op->kp));
+
 		/* Backup instructions which will be replaced by jump address */
 		memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
 		       RELATIVE_ADDR_SIZE);
@@ -391,44 +393,23 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
 		insn_buf[0] = RELATIVEJUMP_OPCODE;
 		*(s32 *)(&insn_buf[1]) = rel;
 
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
+		text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+			     op->optinsn.insn);
 
-/*
- * Replace breakpoints (int3) with relative jumps.
- * Caller must call with locking kprobe_mutex and text_mutex.
- */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
-{
-	struct optimized_kprobe *op, *tmp;
-	int c = 0;
-
-	list_for_each_entry_safe(op, tmp, oplist, list) {
-		WARN_ON(kprobe_disabled(&op->kp));
-		/* Setup param */
-		setup_optimize_kprobe(&jump_poke_params[c],
-				      jump_poke_bufs[c].buf, op);
 		list_del_init(&op->list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
 	}
-
-	text_poke_smp_batch(jump_poke_params, c);
 }
 
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-					      u8 *insn_buf,
-					      struct optimized_kprobe *op)
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
+	u8 insn_buf[RELATIVEJUMP_SIZE];
+
 	/* Set int3 to first byte for kprobes */
 	insn_buf[0] = BREAKPOINT_INSTRUCTION;
 	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
+	text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+		     op->optinsn.insn);
 }
 
 /*
@@ -439,29 +420,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
 				    struct list_head *done_list)
 {
 	struct optimized_kprobe *op, *tmp;
-	int c = 0;
 
 	list_for_each_entry_safe(op, tmp, oplist, list) {
-		/* Setup param */
-		setup_unoptimize_kprobe(&jump_poke_params[c],
-					jump_poke_bufs[c].buf, op);
+		arch_unoptimize_kprobe(op);
 		list_move(&op->list, done_list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
 	}
-
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-	u8 buf[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
 }
 
 int  __kprobes
@@ -481,22 +444,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 	}
 	return 0;
 }
-
-int __kprobes arch_init_optprobes(void)
-{
-	/* Allocate code buffer and parameter array */
-	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_bufs)
-		return -ENOMEM;
-
-	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_params) {
-		kfree(jump_poke_bufs);
-		jump_poke_bufs = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}