coresight: next v4.13-rc3

index d5b96423e1a5..d9c233135d6d 100644
@@ -353,6 +353,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 			      struct perf_output_handle *handle,
 			      void *sink_config)
 {
+	bool lost = false;
 	int i, cur;
 	u8 *buf_ptr;
 	u32 read_ptr, write_ptr, capacity;

@@ -384,7 +385,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 			(unsigned long)write_ptr);
 
 		write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
-		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+		lost = true;
 	}
 
 	/*

@@ -395,7 +396,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
 	if (status & ETB_STATUS_RAM_FULL) {
-		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+		lost = true;
 		to_read = capacity;
 		read_ptr = write_ptr;
 	} else {

@@ -428,9 +429,12 @@ static void etb_update_buffer(struct coresight_device *csdev,
 		if (read_ptr > (drvdata->buffer_depth - 1))
 			read_ptr -= drvdata->buffer_depth;
 		/* let the decoder know we've skipped ahead */
-		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+		lost = true;
 	}
 
+	if (lost)
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+
 	/* finally tell HW where we want to start reading from */
 	writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
 

index e3b9fb82eb8d..2e0fb5b9372c 100644
@@ -369,6 +369,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 				  struct perf_output_handle *handle,
 				  void *sink_config)
 {
+	bool lost = false;
 	int i, cur;
 	u32 *buf_ptr;
 	u32 read_ptr, write_ptr;

@@ -397,7 +398,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 	 */
 	status = readl_relaxed(drvdata->base + TMC_STS);
 	if (status & TMC_STS_FULL) {
-		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+		lost = true;
 		to_read = drvdata->size;
 	} else {
 		to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);

@@ -442,9 +443,12 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 			read_ptr -= drvdata->size;
 		/* Tell the HW */
 		writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
-		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+		lost = true;
 	}
 
+	if (lost)
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+
 	cur = buf->cur;
 	offset = buf->offset;
 

index d9c233135d6d..50f4846e6271 100644
@@ -233,10 +233,8 @@ static void etb_dump_hw(struct etb_drvdata *drvdata)
 	for (i = 0; i < depth; i++) {
 		read_data = readl_relaxed(drvdata->base +
 					  ETB_RAM_READ_DATA_REG);
-		*buf_ptr++ = read_data >> 0;
-		*buf_ptr++ = read_data >> 8;
-		*buf_ptr++ = read_data >> 16;
-		*buf_ptr++ = read_data >> 24;
+		*(u32 *)buf_ptr = read_data;
+		buf_ptr += 4;
 	}
 
 	if (frame_off) {

@@ -444,10 +442,8 @@ static void etb_update_buffer(struct coresight_device *csdev,
 		buf_ptr = buf->data_pages[cur] + offset;
 		read_data = readl_relaxed(drvdata->base +
 					  ETB_RAM_READ_DATA_REG);
-		*buf_ptr++ = read_data >> 0;
-		*buf_ptr++ = read_data >> 8;
-		*buf_ptr++ = read_data >> 16;
-		*buf_ptr++ = read_data >> 24;
+		*(u32 *)buf_ptr = read_data;
+		buf_ptr += 4;
 
 		offset += 4;
 		if (offset >= PAGE_SIZE) {

index 50f4846e6271..42360306f049 100644
@@ -200,8 +200,10 @@ static void etb_disable_hw(struct etb_drvdata *drvdata)
 
 static void etb_dump_hw(struct etb_drvdata *drvdata)
 {
+	bool lost = false;
 	int i;
 	u8 *buf_ptr;
+	const u32 *barrier;
 	u32 read_data, depth;
 	u32 read_ptr, write_ptr;
 	u32 frame_off, frame_endoff;

@@ -223,16 +225,24 @@ static void etb_dump_hw(struct etb_drvdata *drvdata)
 	}
 
 	if ((readl_relaxed(drvdata->base + ETB_STATUS_REG)
-		      & ETB_STATUS_RAM_FULL) == 0)
+		      & ETB_STATUS_RAM_FULL) == 0) {
 		writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
-	else
+	} else {
 		writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+		lost = true;
+	}
 
 	depth = drvdata->buffer_depth;
 	buf_ptr = drvdata->buf;
+	barrier = barrier_pkt;
 	for (i = 0; i < depth; i++) {
 		read_data = readl_relaxed(drvdata->base +
 					  ETB_RAM_READ_DATA_REG);
+		if (lost && *barrier) {
+			read_data = *barrier;
+			barrier++;
+		}
+
 		*(u32 *)buf_ptr = read_data;
 		buf_ptr += 4;
 	}

@@ -354,6 +364,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	bool lost = false;
 	int i, cur;
 	u8 *buf_ptr;
+	const u32 *barrier;
 	u32 read_ptr, write_ptr, capacity;
 	u32 status, read_data, to_read;
 	unsigned long offset;

@@ -438,10 +449,17 @@ static void etb_update_buffer(struct coresight_device *csdev,
 
 	cur = buf->cur;
 	offset = buf->offset;
+	barrier = barrier_pkt;
+
 	for (i = 0; i < to_read; i += 4) {
 		buf_ptr = buf->data_pages[cur] + offset;
 		read_data = readl_relaxed(drvdata->base +
 					  ETB_RAM_READ_DATA_REG);
+		if (lost && *barrier) {
+			read_data = *barrier;
+			barrier++;
+		}
+
 		*(u32 *)buf_ptr = read_data;
 		buf_ptr += 4;
 

index 5f662d82052c..3e25b1dd1a1a 100644
@@ -56,6 +56,8 @@ static ssize_t name##_show(struct device *_dev,				\
 }									\
 static DEVICE_ATTR_RO(name)
 
+extern const u32 barrier_pkt[5];
+
 enum etm_addr_type {
 	ETM_ADDR_TYPE_NONE,
 	ETM_ADDR_TYPE_SINGLE,

index 2e0fb5b9372c..d189b28bd5c4 100644
@@ -43,17 +43,34 @@ static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
 
 static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
 {
+	bool lost = false;
 	char *bufp;
-	u32 read_data;
+	const u32 *barrier;
+	u32 read_data, status;
 	int i;
 
+	/*
+	 * Get a hold of the status register and see if a wrap around
+	 * has occurred.
+	 */
+	status = readl_relaxed(drvdata->base + TMC_STS);
+	if (status & TMC_STS_FULL)
+		lost = true;
+
 	bufp = drvdata->buf;
 	drvdata->len = 0;
+	barrier = barrier_pkt;
 	while (1) {
 		for (i = 0; i < drvdata->memwidth; i++) {
 			read_data = readl_relaxed(drvdata->base + TMC_RRD);
 			if (read_data == 0xFFFFFFFF)
 				return;
+
+			if (lost && *barrier) {
+				read_data = *barrier;
+				barrier++;
+			}
+
 			memcpy(bufp, &read_data, 4);
 			bufp += 4;
 			drvdata->len += 4;

@@ -371,6 +388,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 {
 	bool lost = false;
 	int i, cur;
+	const u32 *barrier;
 	u32 *buf_ptr;
 	u32 read_ptr, write_ptr;
 	u32 status, to_read;

@@ -451,12 +469,18 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 
 	cur = buf->cur;
 	offset = buf->offset;
+	barrier = barrier_pkt;
 
 	/* for every byte to read */
 	for (i = 0; i < to_read; i += 4) {
 		buf_ptr = buf->data_pages[cur] + offset;
 		*buf_ptr = readl_relaxed(drvdata->base + TMC_RRD);
 
+		if (lost && *barrier) {
+			*buf_ptr = *barrier;
+			barrier++;
+		}
+
 		offset += 4;
 		if (offset >= PAGE_SIZE) {
 			offset = 0;

index 5d312699b3b9..b8fb981de7b6 100644
@@ -59,6 +59,8 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 
 static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
 {
+	const u32 *barrier;
+	u32 *temp;
 	u32 rwp, val;
 
 	rwp = readl_relaxed(drvdata->base + TMC_RWP);

@@ -71,6 +73,16 @@ static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
 	if (val & TMC_STS_FULL) {
 		drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr;
 		drvdata->len = drvdata->size;
+
+		barrier = barrier_pkt;
+		temp = (u32 *)drvdata->buf;
+
+		while (*barrier) {
+			*temp = *barrier;
+			temp++;
+			barrier++;
+		}
+
 	} else {
 		drvdata->buf = drvdata->vaddr;
 		drvdata->len = rwp - drvdata->paddr;

index 6a0202b7384f..b8091bef21dc 100644
@@ -53,6 +53,14 @@ static DEFINE_PER_CPU(struct list_head *, tracer_path);
  */
 static struct list_head *stm_path;
 
+/*
+ * When losing synchronisation a new barrier packet needs to be inserted at the
+ * beginning of the data collected in a buffer.  That way the decoder knows that
+ * it needs to look for another sync sequence.
+ */
+const u32 barrier_pkt[5] = {0x7fffffff, 0x7fffffff,
+			    0x7fffffff, 0x7fffffff, 0x0};
+
 static int coresight_id_match(struct device *dev, void *data)
 {
 	int trace_id, i_trace_id;

index 42360306f049..d0d186575c5d 100644
@@ -376,8 +376,8 @@ static void etb_update_buffer(struct coresight_device *csdev,
 
 	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
 
-	CS_UNLOCK(drvdata->base);
 	etb_disable_hw(drvdata);
+	CS_UNLOCK(drvdata->base);
 
 	/* unit is in words, not bytes */
 	read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);

index 93ee8fc539be..9d8bd4e36b32 100644
@@ -243,6 +243,8 @@ void etm_set_default(struct etm_config *config)
 	}
 
 	config->ctxid_mask = 0x0;
+	/* Setting default to 1024 as per TRM recommendation */
+	config->sync_freq = 0x400;
 }
 
 void etm_config_trace_mode(struct etm_config *config)

index 8f546f59a3fd..ad01dfeb2d68 100644
@@ -60,7 +60,7 @@ static struct attribute *etm_config_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group etm_pmu_format_group = {
+static const struct attribute_group etm_pmu_format_group = {
 	.name   = "format",
 	.attrs  = etm_config_formats_attr,
 };

index ad01dfeb2d68..8a0ad77574e7 100644
@@ -53,10 +53,12 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src);
 /* ETMv3.5/PTM's ETMCR is 'config' */
 PMU_FORMAT_ATTR(cycacc,		"config:" __stringify(ETM_OPT_CYCACC));
 PMU_FORMAT_ATTR(timestamp,	"config:" __stringify(ETM_OPT_TS));
+PMU_FORMAT_ATTR(retstack,	"config:" __stringify(ETM_OPT_RETSTK));
 
 static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_cycacc.attr,
 	&format_attr_timestamp.attr,
+	&format_attr_retstack.attr,
 	NULL,
 };
 

index 7d410260661b..45852c2cd096 100644
@@ -24,6 +24,7 @@
 /* ETMv3.5/PTM's ETMCR config bit */
 #define ETM_OPT_CYCACC  12
 #define ETM_OPT_TS      28
+#define ETM_OPT_RETSTK	29
 
 static inline int coresight_get_trace_id(int cpu)
 {

index 7d410260661b..45852c2cd096 100644
@@ -24,6 +24,7 @@
 /* ETMv3.5/PTM's ETMCR config bit */
 #define ETM_OPT_CYCACC  12
 #define ETM_OPT_TS      28
+#define ETM_OPT_RETSTK	29
 
 static inline int coresight_get_trace_id(int cpu)
 {

index ad063d7444e1..70b0a248c321 100644
@@ -106,6 +106,7 @@
 #define ETMTECR1_START_STOP	BIT(25)
 /* ETMCCER - 0x1E8 */
 #define ETMCCER_TIMESTAMP	BIT(22)
+#define ETMCCER_RETSTACK	BIT(23)
 
 #define ETM_MODE_EXCLUDE	BIT(0)
 #define ETM_MODE_CYCACC		BIT(1)

index 9d8bd4e36b32..9c010eb9497f 100644
@@ -310,7 +310,9 @@ void etm_config_trace_mode(struct etm_config *config)
 	config->addr_type[1] = ETM_ADDR_TYPE_RANGE;
 }
 
-#define ETM3X_SUPPORTED_OPTIONS (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN)
+#define ETM3X_SUPPORTED_OPTIONS (ETMCR_CYC_ACC | \
+				 ETMCR_TIMESTAMP_EN | \
+				 ETMCR_RETURN_STACK)
 
 static int etm_parse_event_config(struct etm_drvdata *drvdata,
 				  struct perf_event *event)

@@ -341,14 +343,24 @@ static int etm_parse_event_config(struct etm_drvdata *drvdata,
 		etm_config_trace_mode(config);
 
 	/*
-	 * At this time only cycle accurate and timestamp options are
-	 * available.
+	 * At this time only cycle accurate, return stack  and timestamp
+	 * options are available.
 	 */
 	if (attr->config & ~ETM3X_SUPPORTED_OPTIONS)
 		return -EINVAL;
 
 	config->ctrl = attr->config;
 
+	/*
+	 * Possible to have cores with PTM (supports ret stack) and ETM
+	 * (never has ret stack) on the same SoC. So if we have a request
+	 * for return stack that can't be honoured on this core then
+	 * clear the bit - trace will still continue normally
+	 */
+	if ((config->ctrl & ETMCR_RETURN_STACK) &&
+	    !(drvdata->etmccer & ETMCCER_RETSTACK))
+		config->ctrl &= ~ETMCR_RETURN_STACK;
+
 	return 0;
 }
 

index 532adc9dd32a..ac77b4c973d8 100644
@@ -224,6 +224,10 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata,
 	if (attr->config & BIT(ETM_OPT_TS))
 		/* bit[11], Global timestamp tracing bit */
 		config->cfg |= BIT(11);
+	/* return stack - enable if selected and supported */
+	if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack)
+		/* bit[12], Return stack enable bit */
+		config->cfg |= BIT(12);
 
 out:
 	return ret;

similarity index 97%
rename from drivers/hwtracing/coresight/coresight-replicator-qcom.c
rename to drivers/hwtracing/coresight/coresight-dynamic-replicator.c
index 0a3d15f0b009..c6900f2301de 100644
@@ -143,7 +143,6 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id)
 	if (IS_ERR(drvdata->csdev))
 		return PTR_ERR(drvdata->csdev);
 
-	dev_info(dev, "%s initialized\n", (char *)id->data);
 	return 0;
 }
 

@@ -179,14 +178,13 @@ static struct amba_id replicator_ids[] = {
 	{
 		.id     = 0x0003b909,
 		.mask   = 0x0003ffff,
-		.data	= "REPLICATOR 1.0",
 	},
 	{ 0, 0 },
 };
 
 static struct amba_driver replicator_driver = {
 	.drv = {
-		.name	= "coresight-replicator-qcom",
+		.name	= "coresight-dynamic-replicator",
 		.pm	= &replicator_dev_pm_ops,
 		.suppress_bind_attrs = true,
 	},

index 3e25b1dd1a1a..9fdebb773e71 100644
@@ -39,23 +39,31 @@
 #define ETM_MODE_EXCL_USER	BIT(31)
 
 typedef u32 (*coresight_read_fn)(const struct device *, u32 offset);
-#define coresight_simple_func(type, func, name, offset)			\
+#define __coresight_simple_func(type, func, name, lo_off, hi_off)	\
 static ssize_t name##_show(struct device *_dev,				\
 			   struct device_attribute *attr, char *buf)	\
 {									\
 	type *drvdata = dev_get_drvdata(_dev->parent);			\
 	coresight_read_fn fn = func;					\
-	u32 val;							\
+	u64 val;							\
 	pm_runtime_get_sync(_dev->parent);				\
 	if (fn)								\
-		val = fn(_dev->parent, offset);				\
+		val = (u64)fn(_dev->parent, lo_off);			\
 	else								\
-		val = readl_relaxed(drvdata->base + offset);		\
+		val = coresight_read_reg_pair(drvdata->base,		\
+						 lo_off, hi_off);	\
 	pm_runtime_put_sync(_dev->parent);				\
-	return scnprintf(buf, PAGE_SIZE, "0x%x\n", val);		\
+	return scnprintf(buf, PAGE_SIZE, "0x%llx\n", val);		\
 }									\
 static DEVICE_ATTR_RO(name)
 
+#define coresight_simple_func(type, func, name, offset)			\
+	__coresight_simple_func(type, func, name, offset, -1)
+#define coresight_simple_reg32(type, name, offset)			\
+	__coresight_simple_func(type, NULL, name, offset, -1)
+#define coresight_simple_reg64(type, name, lo_off, hi_off)		\
+	__coresight_simple_func(type, NULL, name, lo_off, hi_off)
+
 extern const u32 barrier_pkt[5];
 
 enum etm_addr_type {

@@ -108,6 +116,17 @@ static inline void CS_UNLOCK(void __iomem *addr)
 	} while (0);
 }
 
+static inline u64
+coresight_read_reg_pair(void __iomem *addr, s32 lo_offset, s32 hi_offset)
+{
+	u64 val;
+
+	val = readl_relaxed(addr + lo_offset);
+	val |= (hi_offset < 0) ? 0 :
+	       (u64)readl_relaxed(addr + hi_offset) << 32;
+	return val;
+}
+
 void coresight_disable_path(struct list_head *path);
 int coresight_enable_path(struct list_head *path, u32 mode);
 struct coresight_device *coresight_get_sink(struct list_head *path);

index d0d186575c5d..05625e3a584e 100644
@@ -575,17 +575,17 @@ static const struct file_operations etb_fops = {
 	.llseek		= no_llseek,
 };
 
-#define coresight_etb10_simple_func(name, offset)                       \
-	coresight_simple_func(struct etb_drvdata, NULL, name, offset)
-
-coresight_etb10_simple_func(rdp, ETB_RAM_DEPTH_REG);
-coresight_etb10_simple_func(sts, ETB_STATUS_REG);
-coresight_etb10_simple_func(rrp, ETB_RAM_READ_POINTER);
-coresight_etb10_simple_func(rwp, ETB_RAM_WRITE_POINTER);
-coresight_etb10_simple_func(trg, ETB_TRG);
-coresight_etb10_simple_func(ctl, ETB_CTL_REG);
-coresight_etb10_simple_func(ffsr, ETB_FFSR);
-coresight_etb10_simple_func(ffcr, ETB_FFCR);
+#define coresight_etb10_reg(name, offset)		\
+	coresight_simple_reg32(struct etb_drvdata, name, offset)
+
+coresight_etb10_reg(rdp, ETB_RAM_DEPTH_REG);
+coresight_etb10_reg(sts, ETB_STATUS_REG);
+coresight_etb10_reg(rrp, ETB_RAM_READ_POINTER);
+coresight_etb10_reg(rwp, ETB_RAM_WRITE_POINTER);
+coresight_etb10_reg(trg, ETB_TRG);
+coresight_etb10_reg(ctl, ETB_CTL_REG);
+coresight_etb10_reg(ffsr, ETB_FFSR);
+coresight_etb10_reg(ffcr, ETB_FFCR);
 
 static struct attribute *coresight_etb_mgmt_attrs[] = {
 	&dev_attr_rdp.attr,

index ca98ad13bb8c..6e547ec6fead 100644
@@ -1232,19 +1232,19 @@ static struct attribute *coresight_etm_attrs[] = {
 	NULL,
 };
 
-#define coresight_etm3x_simple_func(name, offset)			\
-	coresight_simple_func(struct etm_drvdata, NULL, name, offset)
-
-coresight_etm3x_simple_func(etmccr, ETMCCR);
-coresight_etm3x_simple_func(etmccer, ETMCCER);
-coresight_etm3x_simple_func(etmscr, ETMSCR);
-coresight_etm3x_simple_func(etmidr, ETMIDR);
-coresight_etm3x_simple_func(etmcr, ETMCR);
-coresight_etm3x_simple_func(etmtraceidr, ETMTRACEIDR);
-coresight_etm3x_simple_func(etmteevr, ETMTEEVR);
-coresight_etm3x_simple_func(etmtssvr, ETMTSSCR);
-coresight_etm3x_simple_func(etmtecr1, ETMTECR1);
-coresight_etm3x_simple_func(etmtecr2, ETMTECR2);
+#define coresight_etm3x_reg(name, offset)			\
+	coresight_simple_reg32(struct etm_drvdata, name, offset)
+
+coresight_etm3x_reg(etmccr, ETMCCR);
+coresight_etm3x_reg(etmccer, ETMCCER);
+coresight_etm3x_reg(etmscr, ETMSCR);
+coresight_etm3x_reg(etmidr, ETMIDR);
+coresight_etm3x_reg(etmcr, ETMCR);
+coresight_etm3x_reg(etmtraceidr, ETMTRACEIDR);
+coresight_etm3x_reg(etmteevr, ETMTEEVR);
+coresight_etm3x_reg(etmtssvr, ETMTSSCR);
+coresight_etm3x_reg(etmtecr1, ETMTECR1);
+coresight_etm3x_reg(etmtecr2, ETMTECR2);
 
 static struct attribute *coresight_etm_mgmt_attrs[] = {
 	&dev_attr_etmccr.attr,

index b9b1e9c8f4c4..4e6eab53e34e 100644
@@ -2066,23 +2066,23 @@ static u32 etmv4_cross_read(const struct device *dev, u32 offset)
 	return reg.data;
 }
 
-#define coresight_etm4x_simple_func(name, offset)			\
-	coresight_simple_func(struct etmv4_drvdata, NULL, name, offset)
+#define coresight_etm4x_reg(name, offset)			\
+	coresight_simple_reg32(struct etmv4_drvdata, name, offset)
 
 #define coresight_etm4x_cross_read(name, offset)			\
 	coresight_simple_func(struct etmv4_drvdata, etmv4_cross_read,	\
 			      name, offset)
 
-coresight_etm4x_simple_func(trcpdcr, TRCPDCR);
-coresight_etm4x_simple_func(trcpdsr, TRCPDSR);
-coresight_etm4x_simple_func(trclsr, TRCLSR);
-coresight_etm4x_simple_func(trcauthstatus, TRCAUTHSTATUS);
-coresight_etm4x_simple_func(trcdevid, TRCDEVID);
-coresight_etm4x_simple_func(trcdevtype, TRCDEVTYPE);
-coresight_etm4x_simple_func(trcpidr0, TRCPIDR0);
-coresight_etm4x_simple_func(trcpidr1, TRCPIDR1);
-coresight_etm4x_simple_func(trcpidr2, TRCPIDR2);
-coresight_etm4x_simple_func(trcpidr3, TRCPIDR3);
+coresight_etm4x_reg(trcpdcr, TRCPDCR);
+coresight_etm4x_reg(trcpdsr, TRCPDSR);
+coresight_etm4x_reg(trclsr, TRCLSR);
+coresight_etm4x_reg(trcauthstatus, TRCAUTHSTATUS);
+coresight_etm4x_reg(trcdevid, TRCDEVID);
+coresight_etm4x_reg(trcdevtype, TRCDEVTYPE);
+coresight_etm4x_reg(trcpidr0, TRCPIDR0);
+coresight_etm4x_reg(trcpidr1, TRCPIDR1);
+coresight_etm4x_reg(trcpidr2, TRCPIDR2);
+coresight_etm4x_reg(trcpidr3, TRCPIDR3);
 coresight_etm4x_cross_read(trcoslsr, TRCOSLSR);
 coresight_etm4x_cross_read(trcconfig, TRCCONFIGR);
 coresight_etm4x_cross_read(trctraceid, TRCTRACEIDR);

index 93fc26f01bab..202ed7a909e1 100644
@@ -635,21 +635,21 @@ static ssize_t traceid_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(traceid);
 
-#define coresight_stm_simple_func(name, offset)	\
-	coresight_simple_func(struct stm_drvdata, NULL, name, offset)
-
-coresight_stm_simple_func(tcsr, STMTCSR);
-coresight_stm_simple_func(tsfreqr, STMTSFREQR);
-coresight_stm_simple_func(syncr, STMSYNCR);
-coresight_stm_simple_func(sper, STMSPER);
-coresight_stm_simple_func(spter, STMSPTER);
-coresight_stm_simple_func(privmaskr, STMPRIVMASKR);
-coresight_stm_simple_func(spscr, STMSPSCR);
-coresight_stm_simple_func(spmscr, STMSPMSCR);
-coresight_stm_simple_func(spfeat1r, STMSPFEAT1R);
-coresight_stm_simple_func(spfeat2r, STMSPFEAT2R);
-coresight_stm_simple_func(spfeat3r, STMSPFEAT3R);
-coresight_stm_simple_func(devid, CORESIGHT_DEVID);
+#define coresight_stm_reg(name, offset)	\
+	coresight_simple_reg32(struct stm_drvdata, name, offset)
+
+coresight_stm_reg(tcsr, STMTCSR);
+coresight_stm_reg(tsfreqr, STMTSFREQR);
+coresight_stm_reg(syncr, STMSYNCR);
+coresight_stm_reg(sper, STMSPER);
+coresight_stm_reg(spter, STMSPTER);
+coresight_stm_reg(privmaskr, STMPRIVMASKR);
+coresight_stm_reg(spscr, STMSPSCR);
+coresight_stm_reg(spmscr, STMSPMSCR);
+coresight_stm_reg(spfeat1r, STMSPFEAT1R);
+coresight_stm_reg(spfeat2r, STMSPFEAT2R);
+coresight_stm_reg(spfeat3r, STMSPFEAT3R);
+coresight_stm_reg(devid, CORESIGHT_DEVID);
 
 static struct attribute *coresight_stm_attrs[] = {
 	&dev_attr_hwevent_enable.attr,

index 864488793f09..5abf711320f6 100644
@@ -217,20 +217,22 @@ static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid)
 	return memwidth;
 }
 
-#define coresight_tmc_simple_func(name, offset)			\
-	coresight_simple_func(struct tmc_drvdata, NULL, name, offset)
-
-coresight_tmc_simple_func(rsz, TMC_RSZ);
-coresight_tmc_simple_func(sts, TMC_STS);
-coresight_tmc_simple_func(rrp, TMC_RRP);
-coresight_tmc_simple_func(rwp, TMC_RWP);
-coresight_tmc_simple_func(trg, TMC_TRG);
-coresight_tmc_simple_func(ctl, TMC_CTL);
-coresight_tmc_simple_func(ffsr, TMC_FFSR);
-coresight_tmc_simple_func(ffcr, TMC_FFCR);
-coresight_tmc_simple_func(mode, TMC_MODE);
-coresight_tmc_simple_func(pscr, TMC_PSCR);
-coresight_tmc_simple_func(devid, CORESIGHT_DEVID);
+#define coresight_tmc_reg(name, offset)			\
+	coresight_simple_reg32(struct tmc_drvdata, name, offset)
+#define coresight_tmc_reg64(name, lo_off, hi_off)	\
+	coresight_simple_reg64(struct tmc_drvdata, name, lo_off, hi_off)
+
+coresight_tmc_reg(rsz, TMC_RSZ);
+coresight_tmc_reg(sts, TMC_STS);
+coresight_tmc_reg(trg, TMC_TRG);
+coresight_tmc_reg(ctl, TMC_CTL);
+coresight_tmc_reg(ffsr, TMC_FFSR);
+coresight_tmc_reg(ffcr, TMC_FFCR);
+coresight_tmc_reg(mode, TMC_MODE);
+coresight_tmc_reg(pscr, TMC_PSCR);
+coresight_tmc_reg(devid, CORESIGHT_DEVID);
+coresight_tmc_reg64(rrp, TMC_RRP, TMC_RRPHI);
+coresight_tmc_reg64(rwp, TMC_RWP, TMC_RWPHI);
 
 static struct attribute *coresight_tmc_mgmt_attrs[] = {
 	&dev_attr_rsz.attr,

index 9fdebb773e71..f1d0e21d8cab 100644
@@ -127,6 +127,14 @@ coresight_read_reg_pair(void __iomem *addr, s32 lo_offset, s32 hi_offset)
 	return val;
 }
 
+static inline void coresight_write_reg_pair(void __iomem *addr, u64 val,
+						 s32 lo_offset, s32 hi_offset)
+{
+	writel_relaxed((u32)val, addr + lo_offset);
+	if (hi_offset >= 0)
+		writel_relaxed((u32)(val >> 32), addr + hi_offset);
+}
+
 void coresight_disable_path(struct list_head *path);
 int coresight_enable_path(struct list_head *path, u32 mode);
 struct coresight_device *coresight_get_sink(struct list_head *path);

index d189b28bd5c4..e2513b786242 100644
@@ -390,7 +390,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 	int i, cur;
 	const u32 *barrier;
 	u32 *buf_ptr;
-	u32 read_ptr, write_ptr;
+	u64 read_ptr, write_ptr;
 	u32 status, to_read;
 	unsigned long offset;
 	struct cs_buffers *buf = sink_config;

@@ -407,8 +407,8 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 
 	tmc_flush_and_stop(drvdata);
 
-	read_ptr = readl_relaxed(drvdata->base + TMC_RRP);
-	write_ptr = readl_relaxed(drvdata->base + TMC_RWP);
+	read_ptr = tmc_read_rrp(drvdata);
+	write_ptr = tmc_read_rwp(drvdata);
 
 	/*
 	 * Get a hold of the status register and see if a wrap around

@@ -460,7 +460,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 		if (read_ptr > (drvdata->size - 1))
 			read_ptr -= drvdata->size;
 		/* Tell the HW */
-		writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
+		tmc_write_rrp(drvdata, read_ptr);
 		lost = true;
 	}
 

index b8fb981de7b6..9c39c899ebd5 100644
@@ -44,9 +44,8 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 		  ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
 		  TMC_AXICTL_PROT_CTL_B1;
 	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	tmc_write_dba(drvdata, drvdata->paddr);
 
-	writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO);
-	writel_relaxed(0x0, drvdata->base + TMC_DBAHI);
 	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
 		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
 		       TMC_FFCR_TRIGON_TRIGIN,

@@ -60,10 +59,11 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
 {
 	const u32 *barrier;
+	u32 val;
 	u32 *temp;
-	u32 rwp, val;
+	u64 rwp;
 
-	rwp = readl_relaxed(drvdata->base + TMC_RWP);
+	rwp = tmc_read_rwp(drvdata);
 	val = readl_relaxed(drvdata->base + TMC_STS);
 
 	/*

index 51c01851533e..c4ff23336e76 100644
@@ -139,4 +139,22 @@ extern const struct coresight_ops tmc_etf_cs_ops;
 int tmc_read_prepare_etr(struct tmc_drvdata *drvdata);
 int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata);
 extern const struct coresight_ops tmc_etr_cs_ops;
+
+
+#define TMC_REG_PAIR(name, lo_off, hi_off)				\
+static inline u64							\
+tmc_read_##name(struct tmc_drvdata *drvdata)				\
+{									\
+	return coresight_read_reg_pair(drvdata->base, lo_off, hi_off);	\
+}									\
+static inline void							\
+tmc_write_##name(struct tmc_drvdata *drvdata, u64 val)			\
+{									\
+	coresight_write_reg_pair(drvdata->base, val, lo_off, hi_off);	\
+}
+
+TMC_REG_PAIR(rrp, TMC_RRP, TMC_RRPHI)
+TMC_REG_PAIR(rwp, TMC_RWP, TMC_RWPHI)
+TMC_REG_PAIR(dba, TMC_DBALO, TMC_DBAHI)
+
 #endif

index 5abf711320f6..bd98b5101528 100644
@@ -230,9 +230,11 @@ coresight_tmc_reg(ffsr, TMC_FFSR);
 coresight_tmc_reg(ffcr, TMC_FFCR);
 coresight_tmc_reg(mode, TMC_MODE);
 coresight_tmc_reg(pscr, TMC_PSCR);
+coresight_tmc_reg(axictl, TMC_AXICTL);
 coresight_tmc_reg(devid, CORESIGHT_DEVID);
 coresight_tmc_reg64(rrp, TMC_RRP, TMC_RRPHI);
 coresight_tmc_reg64(rwp, TMC_RWP, TMC_RWPHI);
+coresight_tmc_reg64(dba, TMC_DBALO, TMC_DBAHI);
 
 static struct attribute *coresight_tmc_mgmt_attrs[] = {
 	&dev_attr_rsz.attr,

@@ -246,6 +248,8 @@ static struct attribute *coresight_tmc_mgmt_attrs[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_pscr.attr,
 	&dev_attr_devid.attr,
+	&dev_attr_dba.attr,
+	&dev_attr_axictl.attr,
 	NULL,
 };
 

index c6900f2301de..b00ea2d7d13f 100644
@@ -95,6 +95,28 @@ static const struct coresight_ops replicator_cs_ops = {
 	.link_ops	= &replicator_link_ops,
 };
 
+#define coresight_replicator_reg(name, offset) \
+	coresight_simple_reg32(struct replicator_state, name, offset)
+
+coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0);
+coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1);
+
+static struct attribute *replicator_mgmt_attrs[] = {
+	&dev_attr_idfilter0.attr,
+	&dev_attr_idfilter1.attr,
+	NULL,
+};
+
+static const struct attribute_group replicator_mgmt_group = {
+	.attrs = replicator_mgmt_attrs,
+	.name = "mgmt",
+};
+
+static const struct attribute_group *replicator_groups[] = {
+	&replicator_mgmt_group,
+	NULL,
+};
+
 static int replicator_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret;

@@ -139,6 +161,7 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id)
 	desc.ops = &replicator_cs_ops;
 	desc.pdata = adev->dev.platform_data;
 	desc.dev = &adev->dev;
+	desc.groups = replicator_groups;
 	drvdata->csdev = coresight_register(&desc);
 	if (IS_ERR(drvdata->csdev))
 		return PTR_ERR(drvdata->csdev);

index bd98b5101528..6adf74689a85 100644
@@ -360,11 +360,13 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	desc.dev = dev;
 	desc.groups = coresight_tmc_groups;
 
-	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+	switch (drvdata->config_type) {
+	case TMC_CONFIG_TYPE_ETB:
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etb_cs_ops;
-	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		break;
+	case TMC_CONFIG_TYPE_ETR:
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etr_cs_ops;

@@ -375,10 +377,16 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
 		if (ret)
 			goto out;
-	} else {
+		break;
+	case TMC_CONFIG_TYPE_ETF:
 		desc.type = CORESIGHT_DEV_TYPE_LINKSINK;
 		desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
 		desc.ops = &tmc_etf_cs_ops;
+		break;
+	default:
+		pr_err("%s: Unsupported TMC config\n", pdata->name);
+		ret = -EINVAL;
+		goto out;
 	}
 
 	drvdata->csdev = coresight_register(&desc);

index 6adf74689a85..0c99ef7b9b2b 100644
@@ -299,6 +299,20 @@ const struct attribute_group *coresight_tmc_groups[] = {
 	NULL,
 };
 
+/* Detect and initialise the capabilities of a TMC ETR */
+static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
+			     u32 devid, void *dev_caps)
+{
+	/* Set the unadvertised capabilities */
+	tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps);
+
+	/*
+	 * ETR configuration uses a 40-bit AXI master in place of
+	 * the embedded SRAM of ETB/ETF.
+	 */
+	return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(40));
+}
+
 static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret = 0;

@@ -370,11 +384,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etr_cs_ops;
-		/*
-		 * ETR configuration uses a 40-bit AXI master in place of
-		 * the embedded SRAM of ETB/ETF.
-		 */
-		ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
+		ret = tmc_etr_setup_caps(drvdata, devid, id->data);
 		if (ret)
 			goto out;
 		break;

index c4ff23336e76..13ab1008f110 100644
@@ -104,6 +104,8 @@ enum tmc_mem_intf_width {
  * @config_type: TMC variant, must be of type @tmc_config_type.
  * @memwidth:	width of the memory interface databus, in bytes.
  * @trigger_cntr: amount of words to store after a trigger.
+ * @etr_caps:	Bitmask of capabilities of the TMC ETR, inferred from the
+ *		device configuration register (DEVID)
  */
 struct tmc_drvdata {
 	void __iomem		*base;

@@ -121,6 +123,7 @@ struct tmc_drvdata {
 	enum tmc_config_type	config_type;
 	enum tmc_mem_intf_width	memwidth;
 	u32			trigger_cntr;
+	u32			etr_caps;
 };
 
 /* Generic functions */

@@ -157,4 +160,21 @@ TMC_REG_PAIR(rrp, TMC_RRP, TMC_RRPHI)
 TMC_REG_PAIR(rwp, TMC_RWP, TMC_RWPHI)
 TMC_REG_PAIR(dba, TMC_DBALO, TMC_DBAHI)
 
+/* Initialise the caps from unadvertised static capabilities of the device */
+static inline void tmc_etr_init_caps(struct tmc_drvdata *drvdata, u32 dev_caps)
+{
+	WARN_ON(drvdata->etr_caps);
+	drvdata->etr_caps = dev_caps;
+}
+
+static inline void tmc_etr_set_cap(struct tmc_drvdata *drvdata, u32 cap)
+{
+	drvdata->etr_caps |= cap;
+}
+
+static inline bool tmc_etr_has_cap(struct tmc_drvdata *drvdata, u32 cap)
+{
+	return !!(drvdata->etr_caps & cap);
+}
+
 #endif

index 0c99ef7b9b2b..bb409c485d05 100644
@@ -306,6 +306,8 @@ static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
 	/* Set the unadvertised capabilities */
 	tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps);
 
+	if (!(devid & TMC_DEVID_NOSCAT))
+		tmc_etr_set_cap(drvdata, TMC_ETR_SG);
 	/*
 	 * ETR configuration uses a 40-bit AXI master in place of
 	 * the embedded SRAM of ETB/ETF.

index 13ab1008f110..bb6a3e3314b8 100644
@@ -69,6 +69,8 @@
 #define TMC_FFCR_STOP_ON_FLUSH	BIT(12)
 
 
+#define TMC_DEVID_NOSCAT	BIT(24)
+
 enum tmc_config_type {
 	TMC_CONFIG_TYPE_ETB,
 	TMC_CONFIG_TYPE_ETR,

@@ -88,6 +90,9 @@ enum tmc_mem_intf_width {
 	TMC_MEM_INTF_WIDTH_256BITS	= 8,
 };
 
+/* TMC ETR Capability bit definitions */
+#define TMC_ETR_SG			(0x1U << 0)
+
 /**
  * struct tmc_drvdata - specifics associated to an TMC component
  * @base:	memory mapped base address for this component.

index bb409c485d05..5bfc1b3ab80c 100644
@@ -303,16 +303,36 @@ const struct attribute_group *coresight_tmc_groups[] = {
 static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
 			     u32 devid, void *dev_caps)
 {
+	u32 dma_mask = 0;
+
 	/* Set the unadvertised capabilities */
 	tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps);
 
 	if (!(devid & TMC_DEVID_NOSCAT))
 		tmc_etr_set_cap(drvdata, TMC_ETR_SG);
+
+	/* Check if the AXI address width is available */
+	if (devid & TMC_DEVID_AXIAW_VALID)
+		dma_mask = ((devid >> TMC_DEVID_AXIAW_SHIFT) &
+				TMC_DEVID_AXIAW_MASK);
+
 	/*
-	 * ETR configuration uses a 40-bit AXI master in place of
-	 * the embedded SRAM of ETB/ETF.
+	 * Unless specified in the device configuration, ETR uses a 40-bit
+	 * AXI master in place of the embedded SRAM of ETB/ETF.
 	 */
-	return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(40));
+	switch (dma_mask) {
+	case 32:
+	case 40:
+	case 44:
+	case 48:
+	case 52:
+		dev_info(drvdata->dev, "Detected dma mask %dbits\n", dma_mask);
+		break;
+	default:
+		dma_mask = 40;
+	}
+
+	return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask));
 }
 
 static int tmc_probe(struct amba_device *adev, const struct amba_id *id)

index bb6a3e3314b8..f55203d48673 100644
@@ -71,6 +71,10 @@
 
 #define TMC_DEVID_NOSCAT	BIT(24)
 
+#define TMC_DEVID_AXIAW_VALID	BIT(16)
+#define TMC_DEVID_AXIAW_SHIFT	17
+#define TMC_DEVID_AXIAW_MASK	0x7f
+
 enum tmc_config_type {
 	TMC_CONFIG_TYPE_ETB,
 	TMC_CONFIG_TYPE_ETR,

index 9c39c899ebd5..880b53527599 100644
@@ -36,13 +36,9 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
 
 	axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
-	axictl |= TMC_AXICTL_WR_BURST_16;
-	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
-	axictl &= ~TMC_AXICTL_SCT_GAT_MODE;
-	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
-	axictl = (axictl &
-		  ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
-		  TMC_AXICTL_PROT_CTL_B1;
+	axictl &= ~TMC_AXICTL_CLEAR_MASK;
+	axictl |= (TMC_AXICTL_PROT_CTL_B1 | TMC_AXICTL_WR_BURST_16);
+	axictl |= TMC_AXICTL_AXCACHE_OS;
 	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
 	tmc_write_dba(drvdata, drvdata->paddr);
 

index f55203d48673..07c0bf1d9269 100644
@@ -54,11 +54,26 @@
 #define TMC_STS_TMCREADY_BIT	2
 #define TMC_STS_FULL		BIT(0)
 #define TMC_STS_TRIGGERED	BIT(1)
-/* TMC_AXICTL - 0x110 */
+/*
+ * TMC_AXICTL - 0x110
+ *
+ * TMC AXICTL format for SoC-400
+ *	Bits [0-1]	: ProtCtrlBit0-1
+ *	Bits [2-5]	: CacheCtrlBits 0-3 (AxCACHE)
+ *	Bit  6		: Reserved
+ *	Bit  7		: ScatterGatherMode
+ *	Bits [8-11]	: WrBurstLen
+ *	Bits [12-31]	: Reserved.
+ */
+#define TMC_AXICTL_CLEAR_MASK 0xfbf
+
 #define TMC_AXICTL_PROT_CTL_B0	BIT(0)
 #define TMC_AXICTL_PROT_CTL_B1	BIT(1)
 #define TMC_AXICTL_SCT_GAT_MODE	BIT(7)
 #define TMC_AXICTL_WR_BURST_16	0xF00
+/* Write-back Read and Write-allocate */
+#define TMC_AXICTL_AXCACHE_OS	(0xf << 2)
+
 /* TMC_FFCR - 0x304 */
 #define TMC_FFCR_FLUSHMAN_BIT	6
 #define TMC_FFCR_EN_FMT		BIT(0)

index 880b53527599..40ddcf11ae4c 100644
@@ -39,6 +39,12 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 	axictl &= ~TMC_AXICTL_CLEAR_MASK;
 	axictl |= (TMC_AXICTL_PROT_CTL_B1 | TMC_AXICTL_WR_BURST_16);
 	axictl |= TMC_AXICTL_AXCACHE_OS;
+
+	if (tmc_etr_has_cap(drvdata, TMC_ETR_AXI_ARCACHE)) {
+		axictl &= ~TMC_AXICTL_ARCACHE_MASK;
+		axictl |= TMC_AXICTL_ARCACHE_OS;
+	}
+
 	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
 	tmc_write_dba(drvdata, drvdata->paddr);
 

index 07c0bf1d9269..f39caa6a45c3 100644
@@ -59,13 +59,18 @@
  *
  * TMC AXICTL format for SoC-400
  *	Bits [0-1]	: ProtCtrlBit0-1
- *	Bits [2-5]	: CacheCtrlBits 0-3 (AxCACHE)
+ *	Bits [2-5]	: CacheCtrlBits 0-3 (AXCACHE)
  *	Bit  6		: Reserved
  *	Bit  7		: ScatterGatherMode
  *	Bits [8-11]	: WrBurstLen
  *	Bits [12-31]	: Reserved.
+ * TMC AXICTL format for SoC-600, as above except:
+ *	Bits [2-5]	: AXI WCACHE
+ *	Bits [16-19]	: AXI RCACHE
+ *	Bits [20-31]	: Reserved
  */
 #define TMC_AXICTL_CLEAR_MASK 0xfbf
+#define TMC_AXICTL_ARCACHE_MASK (0xf << 16)
 
 #define TMC_AXICTL_PROT_CTL_B0	BIT(0)
 #define TMC_AXICTL_PROT_CTL_B1	BIT(1)

@@ -73,6 +78,7 @@
 #define TMC_AXICTL_WR_BURST_16	0xF00
 /* Write-back Read and Write-allocate */
 #define TMC_AXICTL_AXCACHE_OS	(0xf << 2)
+#define TMC_AXICTL_ARCACHE_OS	(0xf << 16)
 
 /* TMC_FFCR - 0x304 */
 #define TMC_FFCR_FLUSHMAN_BIT	6

@@ -111,6 +117,8 @@ enum tmc_mem_intf_width {
 
 /* TMC ETR Capability bit definitions */
 #define TMC_ETR_SG			(0x1U << 0)
+/* ETR has separate read/write cache encodings */
+#define TMC_ETR_AXI_ARCACHE		(0x1U << 1)
 
 /**
  * struct tmc_drvdata - specifics associated to an TMC component

index 40ddcf11ae4c..68fbc8f7450e 100644
@@ -22,7 +22,7 @@
 
 static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 {
-	u32 axictl;
+	u32 axictl, sts;
 
 	/* Zero out the memory to help with debug */
 	memset(drvdata->vaddr, 0, drvdata->size);

@@ -47,6 +47,17 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
 
 	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
 	tmc_write_dba(drvdata, drvdata->paddr);
+	/*
+	 * If the TMC pointers must be programmed before the session,
+	 * we have to set it properly (i.e, RRP/RWP to base address and
+	 * STS to "not full").
+	 */
+	if (tmc_etr_has_cap(drvdata, TMC_ETR_SAVE_RESTORE)) {
+		tmc_write_rrp(drvdata, drvdata->paddr);
+		tmc_write_rwp(drvdata, drvdata->paddr);
+		sts = readl_relaxed(drvdata->base + TMC_STS) & ~TMC_STS_FULL;
+		writel_relaxed(sts, drvdata->base + TMC_STS);
+	}
 
 	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
 		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |

index f39caa6a45c3..d0da43a14246 100644
@@ -119,6 +119,15 @@ enum tmc_mem_intf_width {
 #define TMC_ETR_SG			(0x1U << 0)
 /* ETR has separate read/write cache encodings */
 #define TMC_ETR_AXI_ARCACHE		(0x1U << 1)
+/*
+ * TMC_ETR_SAVE_RESTORE - Values of RRP/RWP/STS.Full are
+ * retained when TMC leaves Disabled state, allowing us to continue
+ * the tracing from a point where we stopped. This also implies that
+ * the RRP/RWP/STS.Full should always be programmed to the correct
+ * value. Unfortunately this is not advertised by the hardware,
+ * so we have to rely on PID of the IP to detect the functionality.
+ */
+#define TMC_ETR_SAVE_RESTORE		(0x1U << 2)
 
 /**
  * struct tmc_drvdata - specifics associated to an TMC component

index 5bfc1b3ab80c..4fd112f11096 100644
@@ -442,6 +442,22 @@ static struct amba_id tmc_ids[] = {
 		.id     = 0x0003b961,
 		.mask   = 0x0003ffff,
 	},
+	{
+		/* Coresight SoC 600 TMC-ETR/ETS */
+		.id	= 0x000bb9e8,
+		.mask	= 0x000fffff,
+		.data	= (void *)(unsigned long)CORESIGHT_SOC_600_ETR_CAPS,
+	},
+	{
+		/* Coresight SoC 600 TMC-ETB */
+		.id	= 0x000bb9e9,
+		.mask	= 0x000fffff,
+	},
+	{
+		/* Coresight SoC 600 TMC-ETF */
+		.id	= 0x000bb9ea,
+		.mask	= 0x000fffff,
+	},
 	{ 0, 0},
 };
 

index d0da43a14246..8df7a813f537 100644
@@ -129,6 +129,10 @@ enum tmc_mem_intf_width {
  */
 #define TMC_ETR_SAVE_RESTORE		(0x1U << 2)
 
+/* Coresight SoC-600 TMC-ETR unadvertised capabilities */
+#define CORESIGHT_SOC_600_ETR_CAPS	\
+	(TMC_ETR_SAVE_RESTORE | TMC_ETR_AXI_ARCACHE)
+
 /**
  * struct tmc_drvdata - specifics associated to an TMC component
  * @base:	memory mapped base address for this component.

index b00ea2d7d13f..87bcf2123e66 100644
@@ -202,6 +202,11 @@ static struct amba_id replicator_ids[] = {
 		.id     = 0x0003b909,
 		.mask   = 0x0003ffff,
 	},
+	{
+		/* Coresight SoC-600 */
+		.id     = 0x000bb9ec,
+		.mask   = 0x000fffff,
+	},
 	{ 0, 0 },
 };
 

index 860fe6ef5632..e55851564273 100644
@@ -251,6 +251,11 @@ static struct amba_id funnel_ids[] = {
 		.id     = 0x0003b908,
 		.mask   = 0x0003ffff,
 	},
+	{
+		/* Coresight SoC-600 */
+		.id     = 0x000bb9eb,
+		.mask   = 0x000fffff,
+	},
 	{ 0, 0},
 };
 

index 0673baf0f2f5..0e9d57e372bd 100644
@@ -201,6 +201,11 @@ static struct amba_id tpiu_ids[] = {
 		.id	= 0x0004b912,
 		.mask	= 0x0007ffff,
 	},
+	{
+		/* Coresight SoC-600 */
+		.id	= 0x000bb9e7,
+		.mask	= 0x000fffff,
+	},
 	{ 0, 0},
 };
 

index 45852c2cd096..edfeaba95429 100644
@@ -26,6 +26,11 @@
 #define ETM_OPT_TS      28
 #define ETM_OPT_RETSTK	29
 
+/* ETMv4 CONFIGR programming bits for the ETM OPTs */
+#define ETM4_CFG_BIT_CYCACC	4
+#define ETM4_CFG_BIT_TS		11
+#define ETM4_CFG_BIT_RETSTK	12
+
 static inline int coresight_get_trace_id(int cpu)
 {
 	/*

index 45852c2cd096..edfeaba95429 100644
@@ -26,6 +26,11 @@
 #define ETM_OPT_TS      28
 #define ETM_OPT_RETSTK	29
 
+/* ETMv4 CONFIGR programming bits for the ETM OPTs */
+#define ETM4_CFG_BIT_CYCACC	4
+#define ETM4_CFG_BIT_TS		11
+#define ETM4_CFG_BIT_RETSTK	12
+
 static inline int coresight_get_trace_id(int cpu)
 {
 	/*

index 7ce3d1a25133..fbfc055d3f4d 100644
@@ -266,6 +266,32 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr)
 	return config;
 }
 
+#ifndef BIT
+#define BIT(N) (1UL << (N))
+#endif
+
+static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
+{
+	u64 config = 0;
+	u64 config_opts = 0;
+
+	/*
+	 * The perf event variable config bits represent both
+	 * the command line options and register programming
+	 * bits in ETMv3/PTM. For ETMv4 we must remap options
+	 * to real bits
+	 */
+	config_opts = cs_etm_get_config(itr);
+	if (config_opts & BIT(ETM_OPT_CYCACC))
+		config |= BIT(ETM4_CFG_BIT_CYCACC);
+	if (config_opts & BIT(ETM_OPT_TS))
+		config |= BIT(ETM4_CFG_BIT_TS);
+	if (config_opts & BIT(ETM_OPT_RETSTK))
+		config |= BIT(ETM4_CFG_BIT_RETSTK);
+
+	return config;
+}
+
 static size_t
 cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		      struct perf_evlist *evlist __maybe_unused)

@@ -363,7 +389,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
 		magic = __perf_cs_etmv4_magic;
 		/* Get trace configuration register */
 		info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
-						cs_etm_get_config(itr);
+						cs_etmv4_get_config(itr);
 		/* Get traceID from the framework */
 		info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
 						coresight_get_trace_id(cpu);

index 202ed7a909e1..8ec4c4f8a2f2 100644
@@ -276,7 +276,7 @@ static void stm_disable(struct coresight_device *csdev,
 		spin_unlock(&drvdata->spinlock);
 
 		/* Wait until the engine has completely stopped */
-		coresight_timeout(drvdata, STMTCSR, STMTCSR_BUSY_BIT, 0);
+		coresight_timeout(drvdata->base, STMTCSR, STMTCSR_BUSY_BIT, 0);
 
 		pm_runtime_put(drvdata->dev);
 

@@ -307,7 +307,8 @@ static inline bool stm_addr_unaligned(const void *addr, u8 write_bytes)
 	return ((unsigned long)addr & (write_bytes - 1));
 }
 
-static void stm_send(void *addr, const void *data, u32 size, u8 write_bytes)
+static void stm_send(void __iomem *addr, const void *data,
+		     u32 size, u8 write_bytes)
 {
 	u8 paload[8];
 

@@ -414,7 +415,7 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 				  unsigned int size,
 				  const unsigned char *payload)
 {
-	unsigned long ch_addr;
+	void __iomem *ch_addr;
 	struct stm_drvdata *drvdata = container_of(stm_data,
 						   struct stm_drvdata, stm);
 

@@ -424,7 +425,7 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 	if (channel >= drvdata->numsp)
 		return -EINVAL;
 
-	ch_addr = (unsigned long)stm_channel_addr(drvdata, channel);
+	ch_addr = stm_channel_addr(drvdata, channel);
 
 	flags = (flags == STP_PACKET_TIMESTAMPED) ? STM_FLAG_TIMESTAMPED : 0;
 	flags |= test_bit(channel, drvdata->chs.guaranteed) ?

@@ -437,20 +438,20 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 
 	switch (packet) {
 	case STP_PACKET_FLAG:
-		ch_addr |= stm_channel_off(STM_PKT_TYPE_FLAG, flags);
+		ch_addr += stm_channel_off(STM_PKT_TYPE_FLAG, flags);
 
 		/*
 		 * The generic STM core sets a size of '0' on flag packets.
 		 * As such send a flag packet of size '1' and tell the
 		 * core we did so.
 		 */
-		stm_send((void *)ch_addr, payload, 1, drvdata->write_bytes);
+		stm_send(ch_addr, payload, 1, drvdata->write_bytes);
 		size = 1;
 		break;
 
 	case STP_PACKET_DATA:
-		ch_addr |= stm_channel_off(STM_PKT_TYPE_DATA, flags);
-		stm_send((void *)ch_addr, payload, size,
+		ch_addr += stm_channel_off(STM_PKT_TYPE_DATA, flags);
+		stm_send(ch_addr, payload, size,
 				drvdata->write_bytes);
 		break;