perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers

Add support for perf text poke event for text_poke_bp_batch() callers. That
includes jump labels. See comments for more details.

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>
Link: https://lkml.kernel.org/r/20200512121922.8997-3-adrian.hunter@intel.com

arch/x86/kernel/alternative.c

@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -1001,6 +1002,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1168,8 +1170,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1177,14 +1181,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {