perf/x86: Add perf text poke events for kprobes

Add perf text poke events for kprobes. That includes:

 - the replaced instruction(s) which are executed out-of-line
   i.e. arch_copy_kprobe() and arch_remove_kprobe()

 - the INT3 that activates the kprobe
   i.e. arch_arm_kprobe() and arch_disarm_kprobe()

 - optimised kprobe function
   i.e. arch_prepare_optimized_kprobe() and
      __arch_remove_optimized_kprobe()

 - optimised kprobe
   i.e. arch_optimize_kprobes() and arch_unoptimize_kprobe()

Resulting in 8 possible text_poke events:

 0:  NULL -> probe.ainsn.insn (if ainsn.boostable && !kp.post_handler)
					arch_copy_kprobe()

 1:  old0 -> INT3			arch_arm_kprobe()

 // boosted kprobe active

 2:  NULL -> optprobe_trampoline	arch_prepare_optimized_kprobe()

 3:  INT3,old1,old2,old3,old4 -> JMP32	arch_optimize_kprobes()

 // optprobe active

 4:  JMP32 -> INT3,old1,old2,old3,old4

 // optprobe disabled and kprobe active (this sometimes goes back to 3)
					arch_unoptimize_kprobe()

 5:  optprobe_trampoline -> NULL	arch_remove_optimized_kprobe()

 // boosted kprobe active

 6:  INT3 -> old0			arch_disarm_kprobe()

 7:  probe.ainsn.insn -> NULL (if ainsn.boostable && !kp.post_handler)
					arch_remove_kprobe()

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lkml.kernel.org/r/20200512121922.8997-6-adrian.hunter@intel.com

1 files changed, 33 insertions, 5 deletions

diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 321c19950285..3239b6a80bce 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -352,8 +353,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -424,8 +432,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -477,10 +492,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*