Patch "perf intel-pt: Fix ip compression" has been added to the 4.4-stable tree

Patch "perf intel-pt: Fix ip compression" has been added to the 4.4-stable tree

[gregkh]

This is a note to let you know that I've just added the patch titled

    perf intel-pt: Fix ip compression

to the 4.4-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     perf-intel-pt-fix-ip-compression.patch
and it can be found in the queue-4.4 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


>From e1717e0485af4f47fc4da1e979ac817f9ad61b0f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 20 Jul 2016 12:00:06 +0300
Subject: perf intel-pt: Fix ip compression

From: Adrian Hunter <adrian.hunter@intel.com>

commit e1717e0485af4f47fc4da1e979ac817f9ad61b0f upstream.

The June 2015 Intel SDM introduced IP Compression types 4 and 6. Refer
to section 36.4.2.2 Target IP (TIP) Packet - IP Compression.

Existing Intel PT packet decoder did not support type 4, and got type 6
wrong.  Because type 3 and type 4 have the same number of bytes, the
packet 'count' has been changed from being the number of ip bytes to
being the type code.  That allows the Intel PT decoder to correctly
decide whether to sign-extend or use the last ip.  However that also
meant the code had to be adjusted in a number of places.

Currently hardware is not using the new compression types, so this fix
has no effect on existing hardware.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1469005206-3049-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c     |   44 ++++++++--------
 tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c |   24 ++++++--
 2 files changed, 40 insertions(+), 28 deletions(-)

--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -145,8 +145,6 @@ struct intel_pt_decoder {
 	bool have_calc_cyc_to_tsc;
 	int exec_mode;
 	unsigned int insn_bytes;
-	uint64_t sign_bit;
-	uint64_t sign_bits;
 	uint64_t period;
 	enum intel_pt_period_type period_type;
 	uint64_t tot_insn_cnt;
@@ -214,9 +212,6 @@ struct intel_pt_decoder *intel_pt_decode
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 
-	decoder->sign_bit           = (uint64_t)1 << 47;
-	decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
 
@@ -385,21 +380,30 @@ int intel_pt__strerror(int code, char *b
 	return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-				 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 				 uint64_t last_ip)
 {
 	uint64_t ip;
 
 	switch (packet->count) {
-	case 2:
+	case 1:
 		ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
 		     packet->payload;
 		break;
-	case 4:
+	case 2:
 		ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
 		     packet->payload;
 		break;
+	case 3:
+		ip = packet->payload;
+		/* Sign-extend 6-byte ip */
+		if (ip & (uint64_t)0x800000000000ULL)
+			ip |= (uint64_t)0xffff000000000000ULL;
+		break;
+	case 4:
+		ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+		     packet->payload;
+		break;
 	case 6:
 		ip = packet->payload;
 		break;
@@ -407,16 +411,12 @@ static uint64_t intel_pt_calc_ip(struct
 		return 0;
 	}
 
-	if (ip & decoder->sign_bit)
-		return ip | decoder->sign_bits;
-
 	return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-	decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-					    decoder->last_ip);
+	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -1718,6 +1718,12 @@ next:
 	}
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+	return decoder->last_ip || decoder->packet.count == 0 ||
+	       decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1739,8 +1745,7 @@ static int intel_pt_walk_psb(struct inte
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0) {
+			if (intel_pt_have_ip(decoder)) {
 				uint64_t current_ip = decoder->ip;
 
 				intel_pt_set_ip(decoder);
@@ -1832,8 +1837,7 @@ static int intel_pt_walk_to_ip(struct in
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0)
+			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
 			if (decoder->ip)
 				return 0;
@@ -1841,9 +1845,7 @@ static int intel_pt_walk_to_ip(struct in
 
 		case INTEL_PT_FUP:
 			if (decoder->overflow) {
-				if (decoder->last_ip ||
-				    decoder->packet.count == 6 ||
-				    decoder->packet.count == 0)
+				if (intel_pt_have_ip(decoder))
 					intel_pt_set_ip(decoder);
 				if (decoder->ip)
 					return 0;
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -293,36 +293,46 @@ static int intel_pt_get_ip(enum intel_pt
 			   const unsigned char *buf, size_t len,
 			   struct intel_pt_pkt *packet)
 {
-	switch (byte >> 5) {
+	int ip_len;
+
+	packet->count = byte >> 5;
+
+	switch (packet->count) {
 	case 0:
-		packet->count = 0;
+		ip_len = 0;
 		break;
 	case 1:
 		if (len < 3)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 2;
+		ip_len = 2;
 		packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
 		break;
 	case 2:
 		if (len < 5)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 4;
+		ip_len = 4;
 		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
 		break;
 	case 3:
-	case 6:
+	case 4:
 		if (len < 7)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 6;
+		ip_len = 6;
 		memcpy_le64(&packet->payload, buf + 1, 6);
 		break;
+	case 6:
+		if (len < 9)
+			return INTEL_PT_NEED_MORE_BYTES;
+		ip_len = 8;
+		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+		break;
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
 
 	packet->type = type;
 
-	return packet->count + 1;
+	return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,


Patches currently in stable-queue which might be from adrian.hunter@intel.com are

queue-4.4/perf-intel-pt-ensure-never-to-set-last_ip-when-packet-count-is-zero.patch
queue-4.4/perf-intel-pt-use-fup-always-when-scanning-for-an-ip.patch
queue-4.4/perf-intel-pt-fix-last_ip-usage.patch
queue-4.4/perf-intel-pt-fix-ip-compression.patch