[PATCH 1/2] uprobes/x86: Add support to emulate nop5 instruction

[Jiri Olsa]

Adding support to emulate nop5 as the original uprobe instruction.

This change speeds up uprobe on top of nop5 and is a preparation for
usdt probe optimization, that will be done on top of nop5 instruction.

With this change the usdt probe on top of nop5 won't take the performance
hit compared to usdt probe on top of standard nop instruction.

Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
 arch/x86/kernel/uprobes.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9194695662b2..63cc68e19da6 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -608,6 +608,16 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		*sr = utask->autask.saved_scratch_register;
 	}
 }
+
+static int is_nop5_insn(uprobe_opcode_t *insn)
+{
+	return !memcmp(insn, x86_nops[5], 5);
+}
+
+static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
+{
+	return is_nop5_insn((uprobe_opcode_t *) &auprobe->insn);
+}
 #else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit
@@ -621,6 +631,10 @@ static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 }
+static bool emulate_nop5_insn(struct arch_uprobe *auprobe)
+{
+	return false;
+}
 #endif /* CONFIG_X86_64 */
 
 struct uprobe_xol_ops {
@@ -852,6 +866,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 		break;
 
 	case 0x0f:
+		if (emulate_nop5_insn(auprobe))
+			goto setup;
 		if (insn->opcode.nbytes != 2)
 			return -ENOSYS;
 		/*
-- 
2.49.0