1 files changed, 44 insertions, 36 deletions

diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index df6e4b0b84e9..17006705287a 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -162,10 +162,11 @@ static void tmc_pages_free(struct tmc_pages *tmc_pages,
 			   struct device *dev, enum dma_data_direction dir)
 {
 	int i;
+	struct device *real_dev = dev->parent;
 
 	for (i = 0; i < tmc_pages->nr_pages; i++) {
 		if (tmc_pages->daddrs && tmc_pages->daddrs[i])
-			dma_unmap_page(dev, tmc_pages->daddrs[i],
+			dma_unmap_page(real_dev, tmc_pages->daddrs[i],
 					 PAGE_SIZE, dir);
 		if (tmc_pages->pages && tmc_pages->pages[i])
 			__free_page(tmc_pages->pages[i]);
@@ -193,6 +194,7 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages,
 	int i, nr_pages;
 	dma_addr_t paddr;
 	struct page *page;
+	struct device *real_dev = dev->parent;
 
 	nr_pages = tmc_pages->nr_pages;
 	tmc_pages->daddrs = kcalloc(nr_pages, sizeof(*tmc_pages->daddrs),
@@ -216,8 +218,8 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages,
 			page = alloc_pages_node(node,
 						GFP_KERNEL | __GFP_ZERO, 0);
 		}
-		paddr = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
-		if (dma_mapping_error(dev, paddr))
+		paddr = dma_map_page(real_dev, page, 0, PAGE_SIZE, dir);
+		if (dma_mapping_error(real_dev, paddr))
 			goto err;
 		tmc_pages->daddrs[i] = paddr;
 		tmc_pages->pages[i] = page;
@@ -304,7 +306,7 @@ static int tmc_alloc_data_pages(struct tmc_sg_table *sg_table, void **pages)
  * and data buffers. TMC writes to the data buffers and reads from the SG
  * Table pages.
  *
- * @dev		- Device to which page should be DMA mapped.
+ * @dev		- Coresight device to which page should be DMA mapped.
  * @node	- Numa node for mem allocations
  * @nr_tpages	- Number of pages for the table entries.
  * @nr_dpages	- Number of pages for Data buffer.
@@ -348,13 +350,13 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table,
 {
 	int i, index, start;
 	int npages = DIV_ROUND_UP(size, PAGE_SIZE);
-	struct device *dev = table->dev;
+	struct device *real_dev = table->dev->parent;
 	struct tmc_pages *data = &table->data_pages;
 
 	start = offset >> PAGE_SHIFT;
 	for (i = start; i < (start + npages); i++) {
 		index = i % data->nr_pages;
-		dma_sync_single_for_cpu(dev, data->daddrs[index],
+		dma_sync_single_for_cpu(real_dev, data->daddrs[index],
 					PAGE_SIZE, DMA_FROM_DEVICE);
 	}
 }
@@ -363,11 +365,11 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table,
 void tmc_sg_table_sync_table(struct tmc_sg_table *sg_table)
 {
 	int i;
-	struct device *dev = sg_table->dev;
+	struct device *real_dev = sg_table->dev->parent;
 	struct tmc_pages *table_pages = &sg_table->table_pages;
 
 	for (i = 0; i < table_pages->nr_pages; i++)
-		dma_sync_single_for_device(dev, table_pages->daddrs[i],
+		dma_sync_single_for_device(real_dev, table_pages->daddrs[i],
 					   PAGE_SIZE, DMA_TO_DEVICE);
 }
 
@@ -590,6 +592,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 				  void **pages)
 {
 	struct etr_flat_buf *flat_buf;
+	struct device *real_dev = drvdata->csdev->dev.parent;
 
 	/* We cannot reuse existing pages for flat buf */
 	if (pages)
@@ -599,7 +602,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 	if (!flat_buf)
 		return -ENOMEM;
 
-	flat_buf->vaddr = dma_alloc_coherent(drvdata->dev, etr_buf->size,
+	flat_buf->vaddr = dma_alloc_coherent(real_dev, etr_buf->size,
 					     &flat_buf->daddr, GFP_KERNEL);
 	if (!flat_buf->vaddr) {
 		kfree(flat_buf);
@@ -607,7 +610,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 	}
 
 	flat_buf->size = etr_buf->size;
-	flat_buf->dev = drvdata->dev;
+	flat_buf->dev = &drvdata->csdev->dev;
 	etr_buf->hwaddr = flat_buf->daddr;
 	etr_buf->mode = ETR_MODE_FLAT;
 	etr_buf->private = flat_buf;
@@ -618,9 +621,12 @@ static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf)
 {
 	struct etr_flat_buf *flat_buf = etr_buf->private;
 
-	if (flat_buf && flat_buf->daddr)
-		dma_free_coherent(flat_buf->dev, flat_buf->size,
+	if (flat_buf && flat_buf->daddr) {
+		struct device *real_dev = flat_buf->dev->parent;
+
+		dma_free_coherent(real_dev, flat_buf->size,
 				  flat_buf->vaddr, flat_buf->daddr);
+	}
 	kfree(flat_buf);
 }
 
@@ -666,8 +672,9 @@ static int tmc_etr_alloc_sg_buf(struct tmc_drvdata *drvdata,
 				void **pages)
 {
 	struct etr_sg_table *etr_table;
+	struct device *dev = &drvdata->csdev->dev;
 
-	etr_table = tmc_init_etr_sg_table(drvdata->dev, node,
+	etr_table = tmc_init_etr_sg_table(dev, node,
 					  etr_buf->size, pages);
 	if (IS_ERR(etr_table))
 		return -ENOMEM;
@@ -751,8 +758,8 @@ tmc_etr_get_catu_device(struct tmc_drvdata *drvdata)
 	if (!IS_ENABLED(CONFIG_CORESIGHT_CATU))
 		return NULL;
 
-	for (i = 0; i < etr->nr_outport; i++) {
-		tmp = etr->conns[i].child_dev;
+	for (i = 0; i < etr->pdata->nr_outport; i++) {
+		tmp = etr->pdata->conns[i].child_dev;
 		if (tmp && coresight_is_catu_device(tmp))
 			return tmp;
 	}
@@ -823,9 +830,10 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 	bool has_etr_sg, has_iommu;
 	bool has_sg, has_catu;
 	struct etr_buf *etr_buf;
+	struct device *dev = &drvdata->csdev->dev;
 
 	has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
-	has_iommu = iommu_get_domain_for_dev(drvdata->dev);
+	has_iommu = iommu_get_domain_for_dev(dev->parent);
 	has_catu = !!tmc_etr_get_catu_device(drvdata);
 
 	has_sg = has_catu || has_etr_sg;
@@ -863,7 +871,7 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 		return ERR_PTR(rc);
 	}
 
-	dev_dbg(drvdata->dev, "allocated buffer of size %ldKB in mode %d\n",
+	dev_dbg(dev, "allocated buffer of size %ldKB in mode %d\n",
 		(unsigned long)size >> 10, etr_buf->mode);
 	return etr_buf;
 }
@@ -1162,7 +1170,7 @@ out:
 		tmc_etr_free_sysfs_buf(free_buf);
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "TMC-ETR enabled\n");
+		dev_dbg(&csdev->dev, "TMC-ETR enabled\n");
 
 	return ret;
 }
@@ -1178,14 +1186,11 @@ static struct etr_buf *
 alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
 	      int nr_pages, void **pages, bool snapshot)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct etr_buf *etr_buf;
 	unsigned long size;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
-
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 	/*
 	 * Try to match the perf ring buffer size if it is larger
 	 * than the size requested via sysfs.
@@ -1317,13 +1322,11 @@ static struct etr_perf_buffer *
 tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
 		       int nr_pages, void **pages, bool snapshot)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct etr_buf *etr_buf;
 	struct etr_perf_buffer *etr_perf;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 
 	etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node);
 	if (!etr_perf)
@@ -1358,7 +1361,7 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev,
 	etr_perf = tmc_etr_setup_perf_buf(drvdata, event,
 					  nr_pages, pages, snapshot);
 	if (IS_ERR(etr_perf)) {
-		dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n");
+		dev_dbg(&csdev->dev, "Unable to allocate ETR buffer\n");
 		return NULL;
 	}
 
@@ -1501,18 +1504,23 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 	tmc_etr_sync_perf_buffer(etr_perf);
 
 	/*
-	 * Update handle->head in snapshot mode. Also update the size to the
-	 * hardware buffer size if there was an overflow.
+	 * In snapshot mode we simply increment the head by the number of byte
+	 * that were written.  User space function  cs_etm_find_snapshot() will
+	 * figure out how many bytes to get from the AUX buffer based on the
+	 * position of the head.
 	 */
-	if (etr_perf->snapshot) {
+	if (etr_perf->snapshot)
 		handle->head += size;
-		if (etr_buf->full)
-			size = etr_buf->size;
-	}
 
 	lost |= etr_buf->full;
 out:
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!etr_perf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	return size;
 }
@@ -1612,7 +1620,7 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev)
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "TMC-ETR disabled\n");
+	dev_dbg(&csdev->dev, "TMC-ETR disabled\n");
 	return 0;
 }