Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.38 as permitted sender) client-ip=23.128.96.38;
From:   Mao Jinlong <quic_jinlmao@quicinc.com>
To:     Suzuki K Poulose <suzuki.poulose@arm.com>,
        Mike Leach <mike.leach@linaro.org>,
        James Clark <james.clark@arm.com>,
        Leo Yan <leo.yan@linaro.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>
CC:     Shilpa Suresh <quic_c_sbsure@quicinc.com>,
        <coresight@lists.linaro.org>,
        <linux-arm-kernel@lists.infradead.org>,
        <linux-kernel@vger.kernel.org>, <linux-arm-msm@vger.kernel.org>,
        Tingwei Zhang <quic_tingweiz@quicinc.com>,
        Jinlong Mao <quic_jinlmao@quicinc.com>,
        Yuanfang Zhang <quic_yuanfang@quicinc.com>,
        Tao Zhang <quic_taozha@quicinc.com>
Subject: [PATCH] coresight: etr: Use noncontiguous api instead of noncoherent
Date:   Thu, 12 Oct 2023 19:11:52 +0800
Message-ID: <20231012111152.37849-1-quic_jinlmao@quicinc.com>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

From: Shilpa Suresh <quic_c_sbsure@quicinc.com>

The iommu support for noncoherent is removed by commit(dma-mapping:
remove the {alloc,free}_noncoherent methods
81d88ce55092edf1a1f928efb373f289c6b90efd). Use alloc_noncontiguous
function for etr flat buffer allocation.

Signed-off-by: Shilpa Suresh <quic_c_sbsure@quicinc.com>
Signed-off-by: Mao Jinlong <quic_jinlmao@quicinc.com>
---
 .../hwtracing/coresight/coresight-tmc-etr.c   | 47 ++++++++++++++-----
 1 file changed, 35 insertions(+), 12 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 66dc5f97a009..80e5aa4a16c9 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -24,6 +24,7 @@ struct etr_flat_buf {
 	dma_addr_t	daddr;
 	void		*vaddr;
 	size_t		size;
+	struct sg_table	*sgt;
 };
 
 /*
@@ -608,14 +609,24 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 	if (!flat_buf)
 		return -ENOMEM;
 
-	flat_buf->vaddr = dma_alloc_noncoherent(real_dev, etr_buf->size,
-						&flat_buf->daddr,
-						DMA_FROM_DEVICE, GFP_KERNEL);
-	if (!flat_buf->vaddr) {
+	flat_buf->sgt = dma_alloc_noncontiguous(real_dev, etr_buf->size,
+						DMA_FROM_DEVICE, GFP_KERNEL, 0);
+	if (!flat_buf->sgt) {
 		kfree(flat_buf);
 		return -ENOMEM;
 	}
 
+	flat_buf->daddr = sg_dma_address(flat_buf->sgt->sgl);
+	flat_buf->vaddr = dma_vmap_noncontiguous(real_dev, etr_buf->size,
+						flat_buf->sgt);
+	if (!flat_buf->vaddr) {
+		dma_free_noncontiguous(real_dev, etr_buf->size,
+					flat_buf->sgt,
+					DMA_FROM_DEVICE);
+		flat_buf->sgt = NULL;
+		return -ENOMEM;
+	}
+
 	flat_buf->size = etr_buf->size;
 	flat_buf->dev = &drvdata->csdev->dev;
 	etr_buf->hwaddr = flat_buf->daddr;
@@ -631,9 +642,12 @@ static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf)
 	if (flat_buf && flat_buf->daddr) {
 		struct device *real_dev = flat_buf->dev->parent;
 
-		dma_free_noncoherent(real_dev, etr_buf->size,
-				     flat_buf->vaddr, flat_buf->daddr,
+		dma_vunmap_noncontiguous(real_dev, flat_buf->vaddr);
+		dma_free_noncontiguous(real_dev, etr_buf->size,
+				     flat_buf->sgt,
 				     DMA_FROM_DEVICE);
+		flat_buf->vaddr = NULL;
+		flat_buf->sgt = NULL;
 	}
 	kfree(flat_buf);
 }
@@ -642,6 +656,9 @@ static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp)
 {
 	struct etr_flat_buf *flat_buf = etr_buf->private;
 	struct device *real_dev = flat_buf->dev->parent;
+	s64 buf_len;
+	int i;
+	struct scatterlist *sg;
 
 	/*
 	 * Adjust the buffer to point to the beginning of the trace data
@@ -658,13 +675,19 @@ static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp)
 	 * the only reason why we would get a wrap around is when the buffer
 	 * is full.  Sync the entire buffer in one go for this case.
 	 */
+
 	if (etr_buf->offset + etr_buf->len > etr_buf->size)
-		dma_sync_single_for_cpu(real_dev, flat_buf->daddr,
-					etr_buf->size, DMA_FROM_DEVICE);
-	else
-		dma_sync_single_for_cpu(real_dev,
-					flat_buf->daddr + etr_buf->offset,
-					etr_buf->len, DMA_FROM_DEVICE);
+		dma_sync_sgtable_for_cpu(real_dev, flat_buf->sgt,
+					DMA_FROM_DEVICE);
+	else {
+		buf_len = etr_buf->len;
+		for_each_sg(flat_buf->sgt->sgl, sg, flat_buf->sgt->orig_nents, i) {
+			dma_sync_sg_for_cpu(real_dev, sg, 1, DMA_FROM_DEVICE);
+			buf_len -= sg->length;
+			if (buf_len <= 0)
+				break;
+		}
+	}
 }
 
 static ssize_t tmc_etr_get_data_flat_buf(struct etr_buf *etr_buf,
-- 
2.17.1