[PATCH v1 0/4] perf cs-etm: Add support for sample flags

[PATCH v1 0/4] perf cs-etm: Add support for sample flags

[Leo Yan]

This patch seris adds support for sample flags so can facilitate perf
to print sample flags for branch instruction.

The branch instructions also include exception taken and return
related instructions, so the first patch is used to generate branch
sample for exception packets; and the second patch is to track the
exception number.

The patch 0003 is to set branch instruction flags in packet, this
patch has the core code in this series to set flags according to the
decoding element type, and also based on the elements including
instruction type, subtype and condition flag to help making decision
to set flags value.

The patch 0004 is to support sample flags by copying the flags value
from packet structure to sample structure, and it includes two fixing
up for TRACE_ON and exception packets.

The patch series is based on OpenCSD v0.10.0 and Rob's patch 'perf:
Support for Arm A32/T32 instruction sets in CoreSight trace' also is
prerequisite to support A32/T32 ISAs.

The patches can be applied on the acme core branch [1] and tested on
Juno board with below commands for A64 and A32/T32 building:

  # perf script -F,-time,+flags,+ip,+sym,+addr -k vmlinux


Leo Yan (4):
  perf cs-etm: Generate branch sample for exception packet
  perf cs-etm: Track exception number
  perf cs-etm: Set branch instruction flags in packet
  perf cs-etm: Add support sample flags

 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 237 +++++++++++++++++++++++-
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.h |  11 +-
 tools/perf/util/cs-etm.c                        |  44 ++++-
 3 files changed, 277 insertions(+), 15 deletions(-)

-- 
2.7.4

[PATCH v1 1/4] perf cs-etm: Generate branch sample for exception packet

[Leo Yan]

The exception packet appears as one element with 'elem_type' ==
OCSD_GEN_TRC_ELEM_EXCEPTION or OCSD_GEN_TRC_ELEM_EXCEPTION_RET,
which present for exception entry and exit respectively.  The decoder
set packet fields 'packet->exc' and 'packet->exc_ret' to indicate the
exception packets; but exception packets don't have dedicated sample
type and shares the same sample type CS_ETM_RANGE with normal
instruction packets.

As result, the exception packets are taken as normal instruction packets
and this introduces confusion to mix different packet types.
Furthermore, these instruction range packets will be processed for
branch sample only when 'packet->last_instr_taken_branch' is true,
otherwise they will be omitted, this can introduce mess for exception
and exception returning due we don't have complete address range info
for context switching.

To process exception packets properly, this patch introduce two new
sample type: CS_ETM_EXCEPTION and CS_ETM_EXCEPTION_RET; for these two
kind packets, they will be handled by cs_etm__exception().  The func
cs_etm__exception() forces to set previous CS_ETM_RANGE packet flag
'prev_packet->last_instr_taken_branch' to true, this matches well with
the program flow when the exception is trapped from user space to kernel
space, no matter if the most recent flow has branch taken or not; this
is also safe for returning to user space after exception handling.

After exception packets have their own sample type, the packet fields
'packet->exc' and 'packet->exc_ret' aren't needed anymore, so remove
them.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 26 +++++++++++++++++------
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 10 ++++-----
 tools/perf/util/cs-etm.c                        | 28 +++++++++++++++++++++++++
 3 files changed, 53 insertions(+), 11 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 5efb616..0f29534 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -269,8 +269,6 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 		decoder->packet_buffer[i].instr_count = 0;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].last_instr_size = 0;
-		decoder->packet_buffer[i].exc = false;
-		decoder->packet_buffer[i].exc_ret = false;
 		decoder->packet_buffer[i].cpu = INT_MIN;
 	}
 }
@@ -298,8 +296,6 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 
 	decoder->packet_buffer[et].sample_type = sample_type;
 	decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
-	decoder->packet_buffer[et].exc = false;
-	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
 	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
 	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
@@ -376,6 +372,22 @@ cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
 					     CS_ETM_TRACE_ON);
 }
 
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder,
+				 const uint8_t trace_chan_id)
+{
+	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					     CS_ETM_EXCEPTION);
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_exception_ret(struct cs_etm_decoder *decoder,
+				     const uint8_t trace_chan_id)
+{
+	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					     CS_ETM_EXCEPTION_RET);
+}
+
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 				const void *context,
 				const ocsd_trc_index_t indx __maybe_unused,
@@ -401,10 +413,12 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
-		decoder->packet_buffer[decoder->tail].exc = true;
+		resp = cs_etm_decoder__buffer_exception(decoder,
+							trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
-		decoder->packet_buffer[decoder->tail].exc_ret = true;
+		resp = cs_etm_decoder__buffer_exception_ret(decoder,
+							    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
 	case OCSD_GEN_TRC_ELEM_EO_TRACE:
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 9351bd1..217bcc6 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,9 +23,11 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
-	CS_ETM_EMPTY = 0,
-	CS_ETM_RANGE = 1 << 0,
-	CS_ETM_TRACE_ON = 1 << 1,
+	CS_ETM_EMPTY	     = 0,
+	CS_ETM_RANGE	     = 1 << 0,
+	CS_ETM_TRACE_ON	     = 1 << 1,
+	CS_ETM_EXCEPTION     = 1 << 2,
+	CS_ETM_EXCEPTION_RET = 1 << 3,
 };
 
 enum cs_etm_isa {
@@ -43,8 +45,6 @@ struct cs_etm_packet {
 	u32 instr_count;
 	u8 last_instr_taken_branch;
 	u8 last_instr_size;
-	u8 exc;
-	u8 exc_ret;
 	int cpu;
 };
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 908bf9f..00a95d7 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -933,6 +933,25 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 	return 0;
 }
 
+static int cs_etm__exception(struct cs_etm_queue *etmq)
+{
+	/*
+	 * When the exception packet is inserted, whether the last instruction
+	 * in previous range packet is taken branch or not, we need to force
+	 * to set 'prev_packet->last_instr_taken_branch' to true.  This ensures
+	 * to generate branch sample for the instruction range before the
+	 * exception is trapped to kernel or before the exception returning.
+	 *
+	 * The exception packet includes the dummy address values, so don't
+	 * swap PACKET with PREV_PACKET.  This keeps PREV_PACKET to be useful
+	 * for generating instruction and branch samples.
+	 */
+	if (etmq->prev_packet->sample_type == CS_ETM_RANGE)
+		etmq->prev_packet->last_instr_taken_branch = true;
+
+	return 0;
+}
+
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
@@ -1048,6 +1067,15 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__sample(etmq);
 					break;
+				case CS_ETM_EXCEPTION:
+				case CS_ETM_EXCEPTION_RET:
+					/*
+					 * If the exception packet is coming,
+					 * make sure the previous instruction
+					 * range packet to be handled properly.
+					 */
+					cs_etm__exception(etmq);
+					break;
 				case CS_ETM_TRACE_ON:
 					/*
 					 * Discontinuity in trace, flush
-- 
2.7.4

[PATCH v1 2/4] perf cs-etm: Track exception number

[Leo Yan]

When an exception packet comes, it contains the info for exception
number; the exception number indicates the exception types, so from it
we can know if the exception is taken for interrupt, system call or
other traps, etc.  But because the exception return packet cannot
delivery exception number correctly by decoder thus when prepare sample
flags we cannot know what's type for exception return.

This patch adds a new 'exc_num' array in decoder structure to record
exception number per CPU, the exception number is recorded in the array
when the exception packet comes and this exception number can be used by
exception return packet.  If detect there have discontinuous trace with
TRACE_ON packet, the exception number is set to invalid value.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 51 ++++++++++++++++++++++---
 1 file changed, 45 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 0f29534..efc4332 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -43,6 +43,7 @@ struct cs_etm_decoder {
 	u32 packet_count;
 	u32 head;
 	u32 tail;
+	u32 *exc_num;
 	struct cs_etm_packet packet_buffer[MAX_BUFFER];
 };
 
@@ -368,16 +369,44 @@ static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
 				const uint8_t trace_chan_id)
 {
-	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
-					     CS_ETM_TRACE_ON);
+	int ret;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_TRACE_ON);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+
+	/* Clear execption number for discontinuous trace */
+	decoder->exc_num[packet->cpu] = UINT32_MAX;
+
+	return ret;
 }
 
 static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder,
+				 const ocsd_generic_trace_elem *elem,
 				 const uint8_t trace_chan_id)
 {
-	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
-					     CS_ETM_EXCEPTION);
+	int ret;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_EXCEPTION);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+
+	/*
+	 * Exception number is recorded per CPU and later can be used
+	 * for exception return instruction analysis.
+	 */
+	decoder->exc_num[packet->cpu] = elem->exception_number;
+
+	return ret;
 }
 
 static ocsd_datapath_resp_t
@@ -413,7 +442,7 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
-		resp = cs_etm_decoder__buffer_exception(decoder,
+		resp = cs_etm_decoder__buffer_exception(decoder, elem,
 							trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
@@ -501,6 +530,10 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
 	if (!decoder)
 		return NULL;
 
+	decoder->exc_num = zalloc(sizeof(*decoder->exc_num) * num_cpu);
+	if (!decoder->exc_num)
+		goto err_free_decoder;
+
 	decoder->data = d_params->data;
 	decoder->prev_return = OCSD_RESP_CONT;
 	cs_etm_decoder__clear_buffer(decoder);
@@ -521,7 +554,7 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
 	decoder->dcd_tree = ocsd_create_dcd_tree(format, flags);
 
 	if (decoder->dcd_tree == 0)
-		goto err_free_decoder;
+		goto err_free_decoder_exc_num;
 
 	/* init library print logging support */
 	ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder);
@@ -532,6 +565,9 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
 	cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
 
 	for (i = 0; i < num_cpu; i++) {
+		/* init expcetion number to an invalid value */
+		decoder->exc_num[i] = UINT32_MAX;
+
 		ret = cs_etm_decoder__create_etm_decoder(d_params,
 							 &t_params[i],
 							 decoder);
@@ -543,6 +579,8 @@ cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
 
 err_free_decoder_tree:
 	ocsd_destroy_dcd_tree(decoder->dcd_tree);
+err_free_decoder_exc_num:
+	free(decoder->exc_num);
 err_free_decoder:
 	free(decoder);
 	return NULL;
@@ -603,5 +641,6 @@ void cs_etm_decoder__free(struct cs_etm_decoder *decoder)
 
 	ocsd_destroy_dcd_tree(decoder->dcd_tree);
 	decoder->dcd_tree = NULL;
+	free(decoder->exc_num);
 	free(decoder);
 }
-- 
2.7.4

[PATCH v1 3/4] perf cs-etm: Set branch instruction flags in packet

[Leo Yan]

The perf sample data contains flags to indicate the hardware trace data
is belonging to which type branch instruction, thus this can be used to
print out the human readable string.  Arm CoreSight ETM sample data is
missed to set flags and it is always set to zeros, this results in perf
tool skips to print string for instruction types.

Arm CoreSight ETM supports different kinds instruction of A64, A32 and
T32; this patch is to set branch instruction flags in packet for these
ISAs.

The brief idea for patch implementation is describe as below:

- For element with OCSD_GEN_TRC_ELEM_TRACE_ON type, it is taken as trace
  beginning packet; for element with OCSD_GEN_TRC_ELEM_NO_SYNC or
  OCSD_GEN_TRC_ELEM_EO_TRACE, these two kinds elements are used to set
  for trace end;

  As Mike suggested the packet stream might have more than one two
  TRACE_ON packets, the first one TRACE_ON packet indicates trace end
  and the second one is taken as trace restarting.  We will handle this
  special case in the upper layer with packet queue handling, which has
  more context so it's more suitable fix up for it.  This will be
  accomplished in the sequential patch.

- For instruction range packet, mainly base on three factors to decide
  the branch instruction types:

  elem->last_i_type
  elem->last_i_subtype
  elem->last_instr_cond

  If the instruction is immediate branch but without link and return
  flag, we consider it as function internal branch;  in fact the
  immediate branch also can be used to invoke the function entry,
  usually this is only used in assembly code to directly call a symbol
  and don't expect to return back; after reviewing kernel normal
  functions and user space programs, both of them are very seldom to use
  immediate branch for function call.  On the other hand, if we want to
  decide the immediate branch is for function branch jumping or for
  function calling, we need to rely on the start address of next packet
  and check the symbol offset for the start address,  this will
  introduce much complexity in the implementation.  So for this version
  we simply consider immediate branch as function internal branch.
  Moreover, we rely on 'elem->last_instr_cond' to decide if the branch
  instruction is a conditional branch or not.

  If the instruction is immediate branch with link, it's instruction
  'BL' and which is used for function call.

  If the instruction is indirect branch and with subtype
  OCSD_S_INSTR_V7_IMPLIED_RET, the decoders gives the hint the function
  return for below cases related with A32/T32 instruction; set this
  branch flag as function return (Thanks for Al's suggestion).

    BX R14
    MOV PC, LR
    POP {…, PC}
    LDR PC, [SP], #offset

  If the instruction is indirect branch without link, this is
  corresponding to instruction 'BR', this instruction usually is used
  for dynamic link lib with below usage; so we think it's a return
  instruction.

    0000000000000680 <.plt>:
     680:   a9bf7bf0        stp     x16, x30, [sp, #-16]!
     684:   90000090        adrp    x16, 10000 <__FRAME_END__+0xf630>
     688:   f947fe11        ldr     x17, [x16, #4088]
     68c:   913fe210        add     x16, x16, #0xff8
     690:   d61f0220        br      x17

  If the instruction is indirect branch with link, e.g BLR, we think
  it's a function call.

  For function return, ARMv8 introduces a dedicated instruction 'ret',
  which has flag of OCSD_S_INSTR_V8_RET.

- For exception packets, this patch divides into three types:

  The first type of exception is caused by external logics like bus,
  interrupt controller, debug module or PE reset or halt; this is
  corresponding to flags "bcyi" which defined in doc perf-script.txt;

  The second type is for system call, this is set as "bcs" by following
  definition in the doc;

  The third type is for CPU trap, data and instruction prefetch abort,
  alignment abort; usually these exceptions are synchronous for CPU, so
  set them as "bci" type.

Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: Al Grant <Al.Grant@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 168 ++++++++++++++++++++++++
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.h |   1 +
 2 files changed, 169 insertions(+)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index efc4332..cbfd730 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -303,6 +303,7 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].instr_count = 0;
 	decoder->packet_buffer[et].last_instr_taken_branch = false;
 	decoder->packet_buffer[et].last_instr_size = 0;
+	decoder->packet_buffer[et].flags = 0;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -417,6 +418,171 @@ cs_etm_decoder__buffer_exception_ret(struct cs_etm_decoder *decoder,
 					     CS_ETM_EXCEPTION_RET);
 }
 
+static void cs_etm_decoder__set_sample_flags(
+				const void *context,
+				const ocsd_generic_trace_elem *elem)
+{
+	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+	struct cs_etm_packet *packet;
+	u32 exc_num;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+
+	switch (elem->elem_type) {
+	case OCSD_GEN_TRC_ELEM_TRACE_ON:
+		packet->flags = PERF_IP_FLAG_BRANCH |
+				PERF_IP_FLAG_TRACE_BEGIN;
+		break;
+
+	case OCSD_GEN_TRC_ELEM_NO_SYNC:
+	case OCSD_GEN_TRC_ELEM_EO_TRACE:
+		packet->flags = PERF_IP_FLAG_BRANCH |
+				PERF_IP_FLAG_TRACE_END;
+		break;
+
+	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
+		/*
+		 * Immediate branch instruction without neither link nor
+		 * return flag, it's normal branch instruction within
+		 * the function.
+		 */
+		if (elem->last_i_type == OCSD_INSTR_BR &&
+		    elem->last_i_subtype == OCSD_S_INSTR_NONE) {
+			packet->flags = PERF_IP_FLAG_BRANCH;
+
+			if (elem->last_instr_cond)
+				packet->flags |= PERF_IP_FLAG_CONDITIONAL;
+		}
+
+		/*
+		 * Immediate branch instruction with link (e.g. BL), this is
+		 * branch instruction for function call.
+		 */
+		if (elem->last_i_type == OCSD_INSTR_BR &&
+		    elem->last_i_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/*
+		 * Indirect branch instruction with subtype of
+		 * OCSD_S_INSTR_V7_IMPLIED_RET, this is explicit hint for
+		 * function return for A32/T32.
+		 */
+		if (elem->last_i_type == OCSD_INSTR_BR_INDIRECT &&
+		    elem->last_i_subtype == OCSD_S_INSTR_V7_IMPLIED_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Indirect branch instruction without link (e.g. BR), usually
+		 * this is used for function return, especially for functions
+		 * within dynamic link lib.
+		 */
+		if (elem->last_i_type == OCSD_INSTR_BR_INDIRECT &&
+		    elem->last_i_subtype == OCSD_S_INSTR_NONE)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Indirect branch instruction with link (e.g. BLR), this is
+		 * branch instruction for function call.
+		 */
+		if (elem->last_i_type == OCSD_INSTR_BR_INDIRECT &&
+		    elem->last_i_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/* Return instruction for function return. */
+		if (elem->last_i_type == OCSD_INSTR_BR_INDIRECT &&
+		    elem->last_i_subtype == OCSD_S_INSTR_V8_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		break;
+
+	case OCSD_GEN_TRC_ELEM_EXCEPTION:
+
+#define OCSD_EXC_RESET			0
+#define OCSD_EXC_DEBUG_HALT		1
+#define OCSD_EXC_CALL			2
+#define OCSD_EXC_TRAP			3
+#define OCSD_EXC_SYSTEM_ERROR		4
+#define OCSD_EXC_INST_DEBUG		6
+#define OCSD_EXC_DATA_DEBUG		7
+#define OCSD_EXC_ALIGNMENT		10
+#define OCSD_EXC_INST_FAULT		11
+#define OCSD_EXC_DATA_FAULT		12
+#define OCSD_EXC_IRQ			14
+#define OCSD_EXC_FIQ			15
+
+		exc_num = decoder->exc_num[packet->cpu];
+
+		/*
+		 * The exceptions are triggered by external signals
+		 * from bus, interrupt controller, debug module,
+		 * PE reset or halt.
+		 */
+		if (exc_num == OCSD_EXC_RESET ||
+		    exc_num == OCSD_EXC_DEBUG_HALT ||
+		    exc_num == OCSD_EXC_SYSTEM_ERROR ||
+		    exc_num == OCSD_EXC_INST_DEBUG ||
+		    exc_num == OCSD_EXC_DATA_DEBUG ||
+		    exc_num == OCSD_EXC_IRQ ||
+		    exc_num == OCSD_EXC_FIQ)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_ASYNC |
+					PERF_IP_FLAG_INTERRUPT;
+
+		/* The exception is for system call. */
+		if (exc_num == OCSD_EXC_CALL)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_SYSCALLRET;
+
+		/*
+		 * The exception is introduced by trap, instruction &
+		 * data fault or alignment errors.
+		 */
+		if (exc_num == OCSD_EXC_TRAP ||
+		    exc_num == OCSD_EXC_ALIGNMENT ||
+		    exc_num == OCSD_EXC_INST_FAULT ||
+		    exc_num == OCSD_EXC_DATA_FAULT)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_INTERRUPT;
+
+		break;
+
+	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
+
+		exc_num = decoder->exc_num[packet->cpu];
+
+		if (exc_num == OCSD_EXC_CALL)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN |
+					PERF_IP_FLAG_SYSCALLRET;
+		else
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN |
+					PERF_IP_FLAG_INTERRUPT;
+
+		break;
+
+	case OCSD_GEN_TRC_ELEM_UNKNOWN:
+	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
+	case OCSD_GEN_TRC_ELEM_ADDR_NACC:
+	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+	case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
+	case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
+	case OCSD_GEN_TRC_ELEM_EVENT:
+	case OCSD_GEN_TRC_ELEM_SWTRACE:
+	case OCSD_GEN_TRC_ELEM_CUSTOM:
+	default:
+		break;
+	}
+}
+
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 				const void *context,
 				const ocsd_trc_index_t indx __maybe_unused,
@@ -462,6 +628,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 		break;
 	}
 
+	cs_etm_decoder__set_sample_flags(context, elem);
+
 	return resp;
 }
 
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 217bcc6..34e093e 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -46,6 +46,7 @@ struct cs_etm_packet {
 	u8 last_instr_taken_branch;
 	u8 last_instr_size;
 	int cpu;
+	u32 flags;
 };
 
 struct cs_etm_queue;
-- 
2.7.4

[PATCH v1 4/4] perf cs-etm: Add support sample flags

[Leo Yan]

We have prepared the flags in the packet structure, so need to copy
the related value into sample structure thus perf tool can facilitate
sample flags.

The PREV_PACKET contains the branch instruction flags and PACKET
actually contains the flags for next branch instruction.  So this patch
is to set sample flags with 'etmq->prev_packet->flags'.

This patch includes two fixing up: if there has TRACE_ON packet in the
middle of instruction packets, the TRACE_ON packet indicates the trace
is discontinuous, so append the flag PERF_IP_FLAG_TRACE_END to the
previous packet; if the coming packet is exception packet or exception
return packet, also update the previous packet for exception specific
flags.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
 tools/perf/util/cs-etm.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 00a95d7..7e36dcf 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -655,7 +655,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.stream_id = etmq->etm->instructions_id;
 	sample.period = period;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.insn_len = 1;
 	sample.cpumode = event->header.misc;
 
@@ -711,7 +711,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.cpumode = PERF_RECORD_MISC_USER;
 
 	/*
@@ -945,9 +945,13 @@ static int cs_etm__exception(struct cs_etm_queue *etmq)
 	 * The exception packet includes the dummy address values, so don't
 	 * swap PACKET with PREV_PACKET.  This keeps PREV_PACKET to be useful
 	 * for generating instruction and branch samples.
+	 *
+	 * Also update flags so can tell perf it is exception related.
 	 */
-	if (etmq->prev_packet->sample_type == CS_ETM_RANGE)
+	if (etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		etmq->prev_packet->last_instr_taken_branch = true;
+		etmq->prev_packet->flags = etmq->packet->flags;
+	}
 
 	return 0;
 }
@@ -965,6 +969,14 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
 
+	/*
+	 * The start tracing packet is in the middle of instruction range
+	 * packets, this means the trace is discontinuous; so need to set
+	 * the previous packet flag to PERF_IP_FLAG_TRACE_END.
+	 */
+	if (etmq->prev_packet->sample_type == CS_ETM_RANGE)
+		etmq->prev_packet->flags |= PERF_IP_FLAG_TRACE_END;
+
 	if (etmq->etm->synth_opts.last_branch &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
-- 
2.7.4