[PATCH 0/3] dma-mapping: introduce new dma unmap and sync variants

[PATCH 0/3] dma-mapping: introduce new dma unmap and sync variants

[Laurentiu Tudor]

From: Laurentiu Tudor <laurentiu.tudor@nxp.com>

This series introduces a few new dma unmap and sync api variants that,
on top of what the originals do, return the physical address
corresponding to the input dma address. In order to do that a new dma
map op is added, .get_phys_addr that takes the input dma address and
returns the physical address backing it up.
The second patch adds an implementation for this new dma map op in the
generic iommu dma glue code and wires it in.
The third patch updates the dpaa2-eth driver to use the new apis.

Context: https://lkml.org/lkml/2019/5/31/684

Changes since RFC
 * completely changed the approach: added unmap and sync variants that
   return the phys addr instead of adding a new dma to phys conversion
   function

Laurentiu Tudor (3):
  dma-mapping: introduce new dma unmap and sync api variants
  iommu/dma: wire-up new dma map op .get_phys_addr
  dpaa2_eth: use new unmap and sync dma api variants

 drivers/iommu/dma-iommu.c                     | 12 ++++
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 43 ++++++---------
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.h  |  1 -
 include/linux/dma-mapping.h                   | 55 +++++++++++++++++++
 4 files changed, 85 insertions(+), 26 deletions(-)

-- 
2.17.1

[PATCH 1/3] dma-mapping: introduce new dma unmap and sync api variants

[Laurentiu Tudor]

From: Laurentiu Tudor <laurentiu.tudor@nxp.com>

Introduce a few new dma unmap and sync variants that, on top of the
original variants, return the physical address corresponding to the
input dma address.
In order to implement this a new dma map op is added and used:
    phys_addr_t get_phys_addr(dev, dma_handle);
It does the actual conversion of an input dma address to the output
physical address.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
---
 include/linux/dma-mapping.h | 55 +++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4a1c4fca475a..d2bccb814eac 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -132,6 +132,7 @@ struct dma_map_ops {
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
 	unsigned long (*get_merge_boundary)(struct device *dev);
+	phys_addr_t (*get_phys_addr)(struct device *dev, dma_addr_t dma_handle);
 };
 
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
@@ -304,6 +305,21 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 	debug_dma_unmap_page(dev, addr, size, dir);
 }
 
+static inline phys_addr_t
+dma_unmap_page_phys_attrs(struct device *dev, dma_addr_t addr, size_t size,
+			  enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	phys_addr_t phys = 0;
+
+	if (ops && ops->get_phys_addr)
+		phys = ops->get_phys_addr(dev, addr);
+
+	dma_unmap_page_attrs(dev, addr, size, dir, attrs);
+
+	return phys;
+}
+
 /*
  * dma_maps_sg_attrs returns 0 on error and > 0 on success.
  * It should never return a value < 0.
@@ -390,6 +406,21 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
 }
 
+static inline phys_addr_t
+dma_sync_single_for_cpu_phys(struct device *dev, dma_addr_t addr, size_t size,
+			     enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	phys_addr_t phys = 0;
+
+	if (ops && ops->get_phys_addr)
+		phys = ops->get_phys_addr(dev, addr);
+
+	dma_sync_single_for_cpu(dev, addr, size, dir);
+
+	return phys;
+}
+
 static inline void dma_sync_single_for_device(struct device *dev,
 					      dma_addr_t addr, size_t size,
 					      enum dma_data_direction dir)
@@ -500,6 +531,12 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir)
 {
 }
+
+static inline phys_addr_t
+dma_sync_single_for_cpu_phys(struct device *dev, dma_addr_t addr, size_t size,
+			     enum dma_data_direction dir)
+{
+}
 static inline void dma_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
@@ -594,6 +631,21 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
 	return dma_unmap_page_attrs(dev, addr, size, dir, attrs);
 }
 
+static inline phys_addr_t
+dma_unmap_single_phys_attrs(struct device *dev, dma_addr_t addr, size_t size,
+			    enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	phys_addr_t phys = 0;
+
+	if (ops && ops->get_phys_addr)
+		phys = ops->get_phys_addr(dev, addr);
+
+	dma_unmap_single_attrs(dev, addr, size, dir, attrs);
+
+	return phys;
+}
+
 static inline void dma_sync_single_range_for_cpu(struct device *dev,
 		dma_addr_t addr, unsigned long offset, size_t size,
 		enum dma_data_direction dir)
@@ -610,10 +662,13 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 
 #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0)
 #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0)
+#define dma_unmap_single_phys(d, a, s, r) \
+		dma_unmap_single_phys_attrs(d, a, s, r, 0)
 #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0)
 #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0)
 #define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0)
 #define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0)
+#define dma_unmap_page_phys(d, a, s, r) dma_unmap_page_phys_attrs(d, a, s, r, 0)
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
-- 
2.17.1

[PATCH 2/3] iommu/dma: wire-up new dma map op .get_phys_addr

[Laurentiu Tudor]

From: Laurentiu Tudor <laurentiu.tudor@nxp.com>

Add an implementation of the newly introduced dma map op in the
generic DMA IOMMU generic glue layer and wire it up.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
---
 drivers/iommu/dma-iommu.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f321279baf9e..e4e2bde586e0 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1091,6 +1091,17 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static phys_addr_t iommu_dma_get_phys_addr(struct device *dev,
+					   dma_addr_t dma_handle)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (domain)
+		return iommu_iova_to_phys(domain, dma_handle);
+
+	return 0;
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1107,6 +1118,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.get_phys_addr		= iommu_dma_get_phys_addr,
 };
 
 /*
-- 
2.17.1

[PATCH 3/3] dpaa2_eth: use new unmap and sync dma api variants

[Laurentiu Tudor]

From: Laurentiu Tudor <laurentiu.tudor@nxp.com>

Convert this driver to usage of the newly introduced dma unmap and
sync DMA APIs. This will get rid of the unsupported direct usage of
iommu_iova_to_phys() API.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 43 ++++++++-----------
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.h  |  1 -
 2 files changed, 18 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 19379bae0144..bd43bfcb3126 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -29,16 +29,6 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Freescale Semiconductor, Inc");
 MODULE_DESCRIPTION("Freescale DPAA2 Ethernet Driver");
 
-static void *dpaa2_iova_to_virt(struct iommu_domain *domain,
-				dma_addr_t iova_addr)
-{
-	phys_addr_t phys_addr;
-
-	phys_addr = domain ? iommu_iova_to_phys(domain, iova_addr) : iova_addr;
-
-	return phys_to_virt(phys_addr);
-}
-
 static void validate_rx_csum(struct dpaa2_eth_priv *priv,
 			     u32 fd_status,
 			     struct sk_buff *skb)
@@ -85,9 +75,10 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	sgt = vaddr + dpaa2_fd_get_offset(fd);
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
-		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-			       DMA_BIDIRECTIONAL);
+		sg_vaddr = phys_to_virt
+				(dma_unmap_page_phys(dev, addr,
+						    DPAA2_ETH_RX_BUF_SIZE,
+						    DMA_BIDIRECTIONAL));
 
 		free_pages((unsigned long)sg_vaddr, 0);
 		if (dpaa2_sg_is_final(&sgt[i]))
@@ -143,9 +134,10 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
-		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
-			       DMA_BIDIRECTIONAL);
+		sg_vaddr = phys_to_virt
+				(dma_unmap_page_phys(dev, sg_addr,
+						    DPAA2_ETH_RX_BUF_SIZE,
+						    DMA_BIDIRECTIONAL));
 
 		sg_length = dpaa2_sg_get_len(sge);
 
@@ -210,9 +202,9 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 	int i;
 
 	for (i = 0; i < count; i++) {
-		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
-			       DMA_BIDIRECTIONAL);
+		vaddr = phys_to_virt(dma_unmap_page_phys(dev, buf_array[i],
+							 DPAA2_ETH_RX_BUF_SIZE,
+							 DMA_BIDIRECTIONAL));
 		free_pages((unsigned long)vaddr, 0);
 	}
 }
@@ -369,9 +361,9 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	/* Tracing point */
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
-	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				DMA_BIDIRECTIONAL);
+	vaddr = phys_to_virt(dma_sync_single_for_cpu_phys(dev, addr,
+							  DPAA2_ETH_RX_BUF_SIZE,
+							  DMA_BIDIRECTIONAL));
 
 	fas = dpaa2_get_fas(vaddr, false);
 	prefetch(fas);
@@ -682,7 +674,10 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv,
 	u32 fd_len = dpaa2_fd_get_len(fd);
 
 	fd_addr = dpaa2_fd_get_addr(fd);
-	buffer_start = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr);
+	buffer_start = phys_to_virt
+			(dma_sync_single_for_cpu_phys(dev, fd_addr,
+						      sizeof(*swa),
+						      DMA_BIDIRECTIONAL));
 	swa = (struct dpaa2_eth_swa *)buffer_start;
 
 	if (fd_format == dpaa2_fd_single) {
@@ -3448,8 +3443,6 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	priv = netdev_priv(net_dev);
 	priv->net_dev = net_dev;
 
-	priv->iommu_domain = iommu_get_domain_for_dev(dev);
-
 	/* Obtain a MC portal */
 	err = fsl_mc_portal_allocate(dpni_dev, FSL_MC_IO_ATOMIC_CONTEXT_PORTAL,
 				     &priv->mc_io);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 8a0e65b3267f..4e5183617ebd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -374,7 +374,6 @@ struct dpaa2_eth_priv {
 
 	struct fsl_mc_device *dpbp_dev;
 	u16 bpid;
-	struct iommu_domain *iommu_domain;
 
 	bool tx_tstamp; /* Tx timestamping enabled */
 	bool rx_tstamp; /* Rx timestamping enabled */
-- 
2.17.1