[PATCH 0/3 v2] Fixes for running a big-endian kernel on Cubieboard2

[PATCH 0/3 v2] Fixes for running a big-endian kernel on Cubieboard2

[Michael Weiser]

Hello,

the following patches fix up endianness problems with DMA descriptors in the
sunxi-mmc and stmmac drivers preventing a big-endian kernel from working
correctly on the Cubieboard2. The final patch enables the big-endian kernel
configuration option for sunxi devices in order to be able to compile a
big-endian kernel for the Cubieboard2. All of these have been tested
successfull on a Cubieboard2 Dual-Card.

Changes since v1:
- fixed checkpatch niggles
- added respective Cc:s

Regards,
Michael

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>

[PATCH 1/3] mmc: sunxi-mmc: change idma descriptor to __le32

[Michael Weiser]

The sunxi-mmc driver does not take into account the processor may be big
endian when writing the DMA descriptors. This causes cards not to be
detected when running a big-endian kernel. Change the descriptors for
IDMA to use __le32 and ensure they are suitably swapped before writing.
Tested successfully on the Cubieboard2.

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: linux-mmc at vger.kernel.org
---
 drivers/mmc/host/sunxi-mmc.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 2ee4c21..1e6df8a 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -223,10 +223,10 @@ struct sunxi_mmc_clk_delay {
 };
 
 struct sunxi_idma_des {
-	u32	config;
-	u32	buf_size;
-	u32	buf_addr_ptr1;
-	u32	buf_addr_ptr2;
+	__le32 config;
+	__le32 buf_size;
+	__le32 buf_addr_ptr1;
+	__le32 buf_addr_ptr2;
 };
 
 struct sunxi_mmc_host {
@@ -325,22 +325,25 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host,
 	int i, max_len = (1 << host->idma_des_size_bits);
 
 	for (i = 0; i < data->sg_len; i++) {
-		pdes[i].config = SDXC_IDMAC_DES0_CH | SDXC_IDMAC_DES0_OWN |
-				 SDXC_IDMAC_DES0_DIC;
+		pdes[i].config = cpu_to_le32(SDXC_IDMAC_DES0_CH |
+					     SDXC_IDMAC_DES0_OWN |
+					     SDXC_IDMAC_DES0_DIC);
 
 		if (data->sg[i].length == max_len)
 			pdes[i].buf_size = 0; /* 0 == max_len */
 		else
-			pdes[i].buf_size = data->sg[i].length;
+			pdes[i].buf_size = cpu_to_le32(data->sg[i].length);
 
 		next_desc += sizeof(struct sunxi_idma_des);
-		pdes[i].buf_addr_ptr1 = sg_dma_address(&data->sg[i]);
-		pdes[i].buf_addr_ptr2 = (u32)next_desc;
+		pdes[i].buf_addr_ptr1 =
+			cpu_to_le32(sg_dma_address(&data->sg[i]));
+		pdes[i].buf_addr_ptr2 = cpu_to_le32((u32)next_desc);
 	}
 
-	pdes[0].config |= SDXC_IDMAC_DES0_FD;
-	pdes[i - 1].config |= SDXC_IDMAC_DES0_LD | SDXC_IDMAC_DES0_ER;
-	pdes[i - 1].config &= ~SDXC_IDMAC_DES0_DIC;
+	pdes[0].config |= cpu_to_le32(SDXC_IDMAC_DES0_FD);
+	pdes[i - 1].config |= cpu_to_le32(SDXC_IDMAC_DES0_LD |
+					  SDXC_IDMAC_DES0_ER);
+	pdes[i - 1].config &= cpu_to_le32(~SDXC_IDMAC_DES0_DIC);
 	pdes[i - 1].buf_addr_ptr2 = 0;
 
 	/*
-- 
2.9.0

[PATCH 2/3] stmmac: change dma descriptors to __le32

[Michael Weiser]

The stmmac driver does not take into account the processor may be big
endian when writing the DMA descriptors. This causes the ethernet
interface not to be initialised correctly when running a big-endian
kernel. Change the descriptors for DMA to use __le32 and ensure they are
suitably swapped before writing. Tested successfully on the
Cubieboard2.

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: netdev at vger.kernel.org
---
 drivers/net/ethernet/stmicro/stmmac/chain_mode.c   | 55 ++++++++++----------
 drivers/net/ethernet/stmicro/stmmac/descs.h        | 20 ++++----
 drivers/net/ethernet/stmicro/stmmac/descs_com.h    | 48 +++++++++--------
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 60 +++++++++++-----------
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     | 55 ++++++++++----------
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    | 48 ++++++++---------
 drivers/net/ethernet/stmicro/stmmac/ring_mode.c    | 39 +++++++-------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 53 ++++++++++---------
 8 files changed, 196 insertions(+), 182 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index b3e669a..026e8e9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -34,7 +34,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 	unsigned int entry = priv->cur_tx;
 	struct dma_desc *desc = priv->dma_tx + entry;
 	unsigned int nopaged_len = skb_headlen(skb);
-	unsigned int bmax;
+	unsigned int bmax, des2;
 	unsigned int i = 1, len;
 
 	if (priv->plat->enh_desc)
@@ -44,11 +44,12 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 	len = nopaged_len - bmax;
 
-	desc->des2 = dma_map_single(priv->device, skb->data,
-				    bmax, DMA_TO_DEVICE);
-	if (dma_mapping_error(priv->device, desc->des2))
+	des2 = dma_map_single(priv->device, skb->data,
+			      bmax, DMA_TO_DEVICE);
+	desc->des2 = cpu_to_le32(des2);
+	if (dma_mapping_error(priv->device, des2))
 		return -1;
-	priv->tx_skbuff_dma[entry].buf = desc->des2;
+	priv->tx_skbuff_dma[entry].buf = des2;
 	priv->tx_skbuff_dma[entry].len = bmax;
 	/* do not close the descriptor and do not set own bit */
 	priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
@@ -60,12 +61,13 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		desc = priv->dma_tx + entry;
 
 		if (len > bmax) {
-			desc->des2 = dma_map_single(priv->device,
-						    (skb->data + bmax * i),
-						    bmax, DMA_TO_DEVICE);
-			if (dma_mapping_error(priv->device, desc->des2))
+			des2 = dma_map_single(priv->device,
+					      (skb->data + bmax * i),
+					      bmax, DMA_TO_DEVICE);
+			desc->des2 = cpu_to_le32(des2);
+			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = desc->des2;
+			priv->tx_skbuff_dma[entry].buf = des2;
 			priv->tx_skbuff_dma[entry].len = bmax;
 			priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
 							STMMAC_CHAIN_MODE, 1,
@@ -73,12 +75,13 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 			len -= bmax;
 			i++;
 		} else {
-			desc->des2 = dma_map_single(priv->device,
-						    (skb->data + bmax * i), len,
-						    DMA_TO_DEVICE);
-			if (dma_mapping_error(priv->device, desc->des2))
+			des2 = dma_map_single(priv->device,
+					      (skb->data + bmax * i), len,
+					      DMA_TO_DEVICE);
+			desc->des2 = cpu_to_le32(des2);
+			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = desc->des2;
+			priv->tx_skbuff_dma[entry].buf = des2;
 			priv->tx_skbuff_dma[entry].len = len;
 			/* last descriptor can be set now */
 			priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
@@ -119,19 +122,19 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr,
 		struct dma_extended_desc *p = (struct dma_extended_desc *)des;
 		for (i = 0; i < (size - 1); i++) {
 			dma_phy += sizeof(struct dma_extended_desc);
-			p->basic.des3 = (unsigned int)dma_phy;
+			p->basic.des3 = cpu_to_le32((unsigned int)dma_phy);
 			p++;
 		}
-		p->basic.des3 = (unsigned int)phy_addr;
+		p->basic.des3 = cpu_to_le32((unsigned int)phy_addr);
 
 	} else {
 		struct dma_desc *p = (struct dma_desc *)des;
 		for (i = 0; i < (size - 1); i++) {
 			dma_phy += sizeof(struct dma_desc);
-			p->des3 = (unsigned int)dma_phy;
+			p->des3 = cpu_to_le32((unsigned int)dma_phy);
 			p++;
 		}
-		p->des3 = (unsigned int)phy_addr;
+		p->des3 = cpu_to_le32((unsigned int)phy_addr);
 	}
 }
 
@@ -144,10 +147,10 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = (unsigned int)(priv->dma_rx_phy +
-					 (((priv->dirty_rx) + 1) %
-					  DMA_RX_SIZE) *
-					 sizeof(struct dma_desc));
+		p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy +
+				      (((priv->dirty_rx) + 1) %
+				       DMA_RX_SIZE) *
+				      sizeof(struct dma_desc)));
 }
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
@@ -161,9 +164,9 @@ static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = (unsigned int)((priv->dma_tx_phy +
-					  ((priv->dirty_tx + 1) % DMA_TX_SIZE))
-					  * sizeof(struct dma_desc));
+		p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy +
+				      ((priv->dirty_tx + 1) % DMA_TX_SIZE))
+				      * sizeof(struct dma_desc)));
 }
 
 const struct stmmac_mode_ops chain_mode_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 2e4c171..4000af4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -87,7 +87,7 @@
 #define	TDES0_ERROR_SUMMARY		BIT(15)
 #define	TDES0_IP_HEADER_ERROR		BIT(16)
 #define	TDES0_TIME_STAMP_STATUS		BIT(17)
-#define	TDES0_OWN			BIT(31)
+#define	TDES0_OWN			((u32)BIT(31))	/* silence sparse */
 /* TDES1 */
 #define	TDES1_BUFFER1_SIZE_MASK		GENMASK(10, 0)
 #define	TDES1_BUFFER2_SIZE_MASK		GENMASK(21, 11)
@@ -130,7 +130,7 @@
 #define	ETDES0_FIRST_SEGMENT		BIT(28)
 #define	ETDES0_LAST_SEGMENT		BIT(29)
 #define	ETDES0_INTERRUPT		BIT(30)
-#define	ETDES0_OWN			BIT(31)
+#define	ETDES0_OWN			((u32)BIT(31))	/* silence sparse */
 /* TDES1 */
 #define	ETDES1_BUFFER1_SIZE_MASK	GENMASK(12, 0)
 #define	ETDES1_BUFFER2_SIZE_MASK	GENMASK(28, 16)
@@ -166,19 +166,19 @@
 
 /* Basic descriptor structure for normal and alternate descriptors */
 struct dma_desc {
-	unsigned int des0;
-	unsigned int des1;
-	unsigned int des2;
-	unsigned int des3;
+	__le32 des0;
+	__le32 des1;
+	__le32 des2;
+	__le32 des3;
 };
 
 /* Extended descriptor structure (e.g. >= databook 3.50a) */
 struct dma_extended_desc {
 	struct dma_desc basic;	/* Basic descriptors */
-	unsigned int des4;	/* Extended Status */
-	unsigned int des5;	/* Reserved */
-	unsigned int des6;	/* Tx/Rx Timestamp Low */
-	unsigned int des7;	/* Tx/Rx Timestamp High */
+	__le32 des4;	/* Extended Status */
+	__le32 des5;	/* Reserved */
+	__le32 des6;	/* Tx/Rx Timestamp Low */
+	__le32 des7;	/* Tx/Rx Timestamp High */
 };
 
 /* Transmit checksum insertion control */
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index 7635a46..1d181e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -35,47 +35,50 @@
 /* Enhanced descriptors */
 static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
 {
-	p->des1 |= ((BUF_SIZE_8KiB - 1) << ERDES1_BUFFER2_SIZE_SHIFT)
-		   & ERDES1_BUFFER2_SIZE_MASK;
+	p->des1 |= cpu_to_le32(((BUF_SIZE_8KiB - 1)
+			<< ERDES1_BUFFER2_SIZE_SHIFT)
+		   & ERDES1_BUFFER2_SIZE_MASK);
 
 	if (end)
-		p->des1 |= ERDES1_END_RING;
+		p->des1 |= cpu_to_le32(ERDES1_END_RING);
 }
 
 static inline void enh_desc_end_tx_desc_on_ring(struct dma_desc *p, int end)
 {
 	if (end)
-		p->des0 |= ETDES0_END_RING;
+		p->des0 |= cpu_to_le32(ETDES0_END_RING);
 	else
-		p->des0 &= ~ETDES0_END_RING;
+		p->des0 &= cpu_to_le32(~ETDES0_END_RING);
 }
 
 static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 {
 	if (unlikely(len > BUF_SIZE_4KiB)) {
-		p->des1 |= (((len - BUF_SIZE_4KiB) << ETDES1_BUFFER2_SIZE_SHIFT)
+		p->des1 |= cpu_to_le32((((len - BUF_SIZE_4KiB)
+					<< ETDES1_BUFFER2_SIZE_SHIFT)
 			    & ETDES1_BUFFER2_SIZE_MASK) | (BUF_SIZE_4KiB
-			    & ETDES1_BUFFER1_SIZE_MASK);
+			    & ETDES1_BUFFER1_SIZE_MASK));
 	} else
-		p->des1 |= (len & ETDES1_BUFFER1_SIZE_MASK);
+		p->des1 |= cpu_to_le32((len & ETDES1_BUFFER1_SIZE_MASK));
 }
 
 /* Normal descriptors */
 static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
 {
-	p->des1 |= ((BUF_SIZE_2KiB - 1) << RDES1_BUFFER2_SIZE_SHIFT)
-		    & RDES1_BUFFER2_SIZE_MASK;
+	p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
+				<< RDES1_BUFFER2_SIZE_SHIFT)
+		    & RDES1_BUFFER2_SIZE_MASK);
 
 	if (end)
-		p->des1 |= RDES1_END_RING;
+		p->des1 |= cpu_to_le32(RDES1_END_RING);
 }
 
 static inline void ndesc_end_tx_desc_on_ring(struct dma_desc *p, int end)
 {
 	if (end)
-		p->des1 |= TDES1_END_RING;
+		p->des1 |= cpu_to_le32(TDES1_END_RING);
 	else
-		p->des1 &= ~TDES1_END_RING;
+		p->des1 &= cpu_to_le32(~TDES1_END_RING);
 }
 
 static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
@@ -83,10 +86,11 @@ static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 	if (unlikely(len > BUF_SIZE_2KiB)) {
 		unsigned int buffer1 = (BUF_SIZE_2KiB - 1)
 					& TDES1_BUFFER1_SIZE_MASK;
-		p->des1 |= ((((len - buffer1) << TDES1_BUFFER2_SIZE_SHIFT)
-			    & TDES1_BUFFER2_SIZE_MASK) | buffer1);
+		p->des1 |= cpu_to_le32((((len - buffer1)
+					<< TDES1_BUFFER2_SIZE_SHIFT)
+				& TDES1_BUFFER2_SIZE_MASK) | buffer1);
 	} else
-		p->des1 |= (len & TDES1_BUFFER1_SIZE_MASK);
+		p->des1 |= cpu_to_le32((len & TDES1_BUFFER1_SIZE_MASK));
 }
 
 /* Specific functions used for Chain mode */
@@ -94,32 +98,32 @@ static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 /* Enhanced descriptors */
 static inline void ehn_desc_rx_set_on_chain(struct dma_desc *p)
 {
-	p->des1 |= ERDES1_SECOND_ADDRESS_CHAINED;
+	p->des1 |= cpu_to_le32(ERDES1_SECOND_ADDRESS_CHAINED);
 }
 
 static inline void enh_desc_end_tx_desc_on_chain(struct dma_desc *p)
 {
-	p->des0 |= ETDES0_SECOND_ADDRESS_CHAINED;
+	p->des0 |= cpu_to_le32(ETDES0_SECOND_ADDRESS_CHAINED);
 }
 
 static inline void enh_set_tx_desc_len_on_chain(struct dma_desc *p, int len)
 {
-	p->des1 |= (len & ETDES1_BUFFER1_SIZE_MASK);
+	p->des1 |= cpu_to_le32(len & ETDES1_BUFFER1_SIZE_MASK);
 }
 
 /* Normal descriptors */
 static inline void ndesc_rx_set_on_chain(struct dma_desc *p, int end)
 {
-	p->des1 |= RDES1_SECOND_ADDRESS_CHAINED;
+	p->des1 |= cpu_to_le32(RDES1_SECOND_ADDRESS_CHAINED);
 }
 
 static inline void ndesc_tx_set_on_chain(struct dma_desc *p)
 {
-	p->des1 |= TDES1_SECOND_ADDRESS_CHAINED;
+	p->des1 |= cpu_to_le32(TDES1_SECOND_ADDRESS_CHAINED);
 }
 
 static inline void norm_set_tx_desc_len_on_chain(struct dma_desc *p, int len)
 {
-	p->des1 |= len & TDES1_BUFFER1_SIZE_MASK;
+	p->des1 |= cpu_to_le32(len & TDES1_BUFFER1_SIZE_MASK);
 }
 #endif /* __DESC_COM_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 4ec7397..e35e7f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -23,7 +23,7 @@ static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x,
 	unsigned int tdes3;
 	int ret = tx_done;
 
-	tdes3 = p->des3;
+	tdes3 = le32_to_cpu(p->des3);
 
 	/* Get tx owner first */
 	if (unlikely(tdes3 & TDES3_OWN))
@@ -77,9 +77,9 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
 				       struct dma_desc *p)
 {
 	struct net_device_stats *stats = (struct net_device_stats *)data;
-	unsigned int rdes1 = p->des1;
-	unsigned int rdes2 = p->des2;
-	unsigned int rdes3 = p->des3;
+	unsigned int rdes1 = le32_to_cpu(p->des1);
+	unsigned int rdes2 = le32_to_cpu(p->des2);
+	unsigned int rdes3 = le32_to_cpu(p->des3);
 	int message_type;
 	int ret = good_frame;
 
@@ -169,42 +169,43 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
 
 static int dwmac4_rd_get_tx_len(struct dma_desc *p)
 {
-	return (p->des2 & TDES2_BUFFER1_SIZE_MASK);
+	return (le32_to_cpu(p->des2) & TDES2_BUFFER1_SIZE_MASK);
 }
 
 static int dwmac4_get_tx_owner(struct dma_desc *p)
 {
-	return (p->des3 & TDES3_OWN) >> TDES3_OWN_SHIFT;
+	return (le32_to_cpu(p->des3) & TDES3_OWN) >> TDES3_OWN_SHIFT;
 }
 
 static void dwmac4_set_tx_owner(struct dma_desc *p)
 {
-	p->des3 |= TDES3_OWN;
+	p->des3 |= cpu_to_le32(TDES3_OWN);
 }
 
 static void dwmac4_set_rx_owner(struct dma_desc *p)
 {
-	p->des3 |= RDES3_OWN;
+	p->des3 |= cpu_to_le32(RDES3_OWN);
 }
 
 static int dwmac4_get_tx_ls(struct dma_desc *p)
 {
-	return (p->des3 & TDES3_LAST_DESCRIPTOR) >> TDES3_LAST_DESCRIPTOR_SHIFT;
+	return (le32_to_cpu(p->des3) & TDES3_LAST_DESCRIPTOR)
+		>> TDES3_LAST_DESCRIPTOR_SHIFT;
 }
 
 static int dwmac4_wrback_get_rx_frame_len(struct dma_desc *p, int rx_coe)
 {
-	return (p->des3 & RDES3_PACKET_SIZE_MASK);
+	return (le32_to_cpu(p->des3) & RDES3_PACKET_SIZE_MASK);
 }
 
 static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p)
 {
-	p->des2 |= TDES2_TIMESTAMP_ENABLE;
+	p->des2 |= cpu_to_le32(TDES2_TIMESTAMP_ENABLE);
 }
 
 static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p)
 {
-	return (p->des3 & TDES3_TIMESTAMP_STATUS)
+	return (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS)
 		>> TDES3_TIMESTAMP_STATUS_SHIFT;
 }
 
@@ -216,9 +217,9 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
 	struct dma_desc *p = (struct dma_desc *)desc;
 	u64 ns;
 
-	ns = p->des0;
+	ns = le32_to_cpu(p->des0);
 	/* convert high/sec time stamp value to nanosecond */
-	ns += p->des1 * 1000000000ULL;
+	ns += le32_to_cpu(p->des1) * 1000000000ULL;
 
 	return ns;
 }
@@ -227,17 +228,17 @@ static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
 
-	return (p->des1 & RDES1_TIMESTAMP_AVAILABLE)
+	return (le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)
 		>> RDES1_TIMESTAMP_AVAILABLE_SHIFT;
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 				   int mode, int end)
 {
-	p->des3 = RDES3_OWN | RDES3_BUFFER1_VALID_ADDR;
+	p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
 
 	if (!disable_rx_ic)
-		p->des3 |= RDES3_INT_ON_COMPLETION_EN;
+		p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
 }
 
 static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
@@ -252,9 +253,9 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				      bool csum_flag, int mode, bool tx_own,
 				      bool ls)
 {
-	unsigned int tdes3 = p->des3;
+	unsigned int tdes3 = le32_to_cpu(p->des3);
 
-	p->des2 |= (len & TDES2_BUFFER1_SIZE_MASK);
+	p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK);
 
 	if (is_fs)
 		tdes3 |= TDES3_FIRST_DESCRIPTOR;
@@ -282,7 +283,7 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 		 */
 		wmb();
 
-	p->des3 = tdes3;
+	p->des3 = cpu_to_le32(tdes3);
 }
 
 static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
@@ -290,14 +291,14 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
 					  bool ls, unsigned int tcphdrlen,
 					  unsigned int tcppayloadlen)
 {
-	unsigned int tdes3 = p->des3;
+	unsigned int tdes3 = le32_to_cpu(p->des3);
 
 	if (len1)
-		p->des2 |= (len1 & TDES2_BUFFER1_SIZE_MASK);
+		p->des2 |= cpu_to_le32((len1 & TDES2_BUFFER1_SIZE_MASK));
 
 	if (len2)
-		p->des2 |= (len2 << TDES2_BUFFER2_SIZE_MASK_SHIFT)
-			    & TDES2_BUFFER2_SIZE_MASK;
+		p->des2 |= cpu_to_le32((len2 << TDES2_BUFFER2_SIZE_MASK_SHIFT)
+			    & TDES2_BUFFER2_SIZE_MASK);
 
 	if (is_fs) {
 		tdes3 |= TDES3_FIRST_DESCRIPTOR |
@@ -325,7 +326,7 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
 		 */
 		wmb();
 
-	p->des3 = tdes3;
+	p->des3 = cpu_to_le32(tdes3);
 }
 
 static void dwmac4_release_tx_desc(struct dma_desc *p, int mode)
@@ -336,7 +337,7 @@ static void dwmac4_release_tx_desc(struct dma_desc *p, int mode)
 
 static void dwmac4_rd_set_tx_ic(struct dma_desc *p)
 {
-	p->des2 |= TDES2_INTERRUPT_ON_COMPLETION;
+	p->des2 |= cpu_to_le32(TDES2_INTERRUPT_ON_COMPLETION);
 }
 
 static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
@@ -350,7 +351,8 @@ static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
 		if (p->des0)
 			pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
 				i, (unsigned int)virt_to_phys(p),
-				p->des0, p->des1, p->des2, p->des3);
+				le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+				le32_to_cpu(p->des2), le32_to_cpu(p->des3));
 		p++;
 	}
 }
@@ -359,8 +361,8 @@ static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
 {
 	p->des0 = 0;
 	p->des1 = 0;
-	p->des2 = mss;
-	p->des3 = TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV;
+	p->des2 = cpu_to_le32(mss);
+	p->des3 = cpu_to_le32(TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV);
 }
 
 const struct stmmac_desc_ops dwmac4_desc_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 38f19c9..8295aa9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -30,7 +30,7 @@ static int enh_desc_get_tx_status(void *data, struct stmmac_extra_stats *x,
 				  struct dma_desc *p, void __iomem *ioaddr)
 {
 	struct net_device_stats *stats = (struct net_device_stats *)data;
-	unsigned int tdes0 = p->des0;
+	unsigned int tdes0 = le32_to_cpu(p->des0);
 	int ret = tx_done;
 
 	/* Get tx owner first */
@@ -95,7 +95,7 @@ static int enh_desc_get_tx_status(void *data, struct stmmac_extra_stats *x,
 
 static int enh_desc_get_tx_len(struct dma_desc *p)
 {
-	return (p->des1 & ETDES1_BUFFER1_SIZE_MASK);
+	return (le32_to_cpu(p->des1) & ETDES1_BUFFER1_SIZE_MASK);
 }
 
 static int enh_desc_coe_rdes0(int ipc_err, int type, int payload_err)
@@ -134,8 +134,8 @@ static int enh_desc_coe_rdes0(int ipc_err, int type, int payload_err)
 static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
 				    struct dma_extended_desc *p)
 {
-	unsigned int rdes0 = p->basic.des0;
-	unsigned int rdes4 = p->des4;
+	unsigned int rdes0 = le32_to_cpu(p->basic.des0);
+	unsigned int rdes4 = le32_to_cpu(p->des4);
 
 	if (unlikely(rdes0 & ERDES0_RX_MAC_ADDR)) {
 		int message_type = (rdes4 & ERDES4_MSG_TYPE_MASK) >> 8;
@@ -191,7 +191,7 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 				  struct dma_desc *p)
 {
 	struct net_device_stats *stats = (struct net_device_stats *)data;
-	unsigned int rdes0 = p->des0;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
 	int ret = good_frame;
 
 	if (unlikely(rdes0 & RDES0_OWN))
@@ -257,8 +257,8 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 				  int mode, int end)
 {
-	p->des0 |= RDES0_OWN;
-	p->des1 |= ((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK);
+	p->des0 |= cpu_to_le32(RDES0_OWN);
+	p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_rx_set_on_chain(p);
@@ -266,12 +266,12 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 		ehn_desc_rx_set_on_ring(p, end);
 
 	if (disable_rx_ic)
-		p->des1 |= ERDES1_DISABLE_IC;
+		p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
 }
 
 static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des0 &= ~ETDES0_OWN;
+	p->des0 &= cpu_to_le32(~ETDES0_OWN);
 	if (mode == STMMAC_CHAIN_MODE)
 		enh_desc_end_tx_desc_on_chain(p);
 	else
@@ -280,27 +280,27 @@ static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
 
 static int enh_desc_get_tx_owner(struct dma_desc *p)
 {
-	return (p->des0 & ETDES0_OWN) >> 31;
+	return (le32_to_cpu(p->des0) & ETDES0_OWN) >> 31;
 }
 
 static void enh_desc_set_tx_owner(struct dma_desc *p)
 {
-	p->des0 |= ETDES0_OWN;
+	p->des0 |= cpu_to_le32(ETDES0_OWN);
 }
 
 static void enh_desc_set_rx_owner(struct dma_desc *p)
 {
-	p->des0 |= RDES0_OWN;
+	p->des0 |= cpu_to_le32(RDES0_OWN);
 }
 
 static int enh_desc_get_tx_ls(struct dma_desc *p)
 {
-	return (p->des0 & ETDES0_LAST_SEGMENT) >> 29;
+	return (le32_to_cpu(p->des0) & ETDES0_LAST_SEGMENT) >> 29;
 }
 
 static void enh_desc_release_tx_desc(struct dma_desc *p, int mode)
 {
-	int ter = (p->des0 & ETDES0_END_RING) >> 21;
+	int ter = (le32_to_cpu(p->des0) & ETDES0_END_RING) >> 21;
 
 	memset(p, 0, offsetof(struct dma_desc, des2));
 	if (mode == STMMAC_CHAIN_MODE)
@@ -313,7 +313,7 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				     bool csum_flag, int mode, bool tx_own,
 				     bool ls)
 {
-	unsigned int tdes0 = p->des0;
+	unsigned int tdes0 = le32_to_cpu(p->des0);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		enh_set_tx_desc_len_on_chain(p, len);
@@ -344,12 +344,12 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 		 */
 		wmb();
 
-	p->des0 = tdes0;
+	p->des0 = cpu_to_le32(tdes0);
 }
 
 static void enh_desc_set_tx_ic(struct dma_desc *p)
 {
-	p->des0 |= ETDES0_INTERRUPT;
+	p->des0 |= cpu_to_le32(ETDES0_INTERRUPT);
 }
 
 static int enh_desc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
@@ -364,18 +364,18 @@ static int enh_desc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
 	if (rx_coe_type == STMMAC_RX_COE_TYPE1)
 		csum = 2;
 
-	return (((p->des0 & RDES0_FRAME_LEN_MASK) >> RDES0_FRAME_LEN_SHIFT) -
-		csum);
+	return (((le32_to_cpu(p->des0) & RDES0_FRAME_LEN_MASK)
+				>> RDES0_FRAME_LEN_SHIFT) - csum);
 }
 
 static void enh_desc_enable_tx_timestamp(struct dma_desc *p)
 {
-	p->des0 |= ETDES0_TIME_STAMP_ENABLE;
+	p->des0 |= cpu_to_le32(ETDES0_TIME_STAMP_ENABLE);
 }
 
 static int enh_desc_get_tx_timestamp_status(struct dma_desc *p)
 {
-	return (p->des0 & ETDES0_TIME_STAMP_STATUS) >> 17;
+	return (le32_to_cpu(p->des0) & ETDES0_TIME_STAMP_STATUS) >> 17;
 }
 
 static u64 enh_desc_get_timestamp(void *desc, u32 ats)
@@ -384,13 +384,13 @@ static u64 enh_desc_get_timestamp(void *desc, u32 ats)
 
 	if (ats) {
 		struct dma_extended_desc *p = (struct dma_extended_desc *)desc;
-		ns = p->des6;
+		ns = le32_to_cpu(p->des6);
 		/* convert high/sec time stamp value to nanosecond */
-		ns += p->des7 * 1000000000ULL;
+		ns += le32_to_cpu(p->des7) * 1000000000ULL;
 	} else {
 		struct dma_desc *p = (struct dma_desc *)desc;
-		ns = p->des2;
-		ns += p->des3 * 1000000000ULL;
+		ns = le32_to_cpu(p->des2);
+		ns += le32_to_cpu(p->des3) * 1000000000ULL;
 	}
 
 	return ns;
@@ -400,10 +400,11 @@ static int enh_desc_get_rx_timestamp_status(void *desc, u32 ats)
 {
 	if (ats) {
 		struct dma_extended_desc *p = (struct dma_extended_desc *)desc;
-		return (p->basic.des0 & RDES0_IPC_CSUM_ERROR) >> 7;
+		return (le32_to_cpu(p->basic.des0) & RDES0_IPC_CSUM_ERROR) >> 7;
 	} else {
 		struct dma_desc *p = (struct dma_desc *)desc;
-		if ((p->des2 == 0xffffffff) && (p->des3 == 0xffffffff))
+		if ((le32_to_cpu(p->des2) == 0xffffffff) &&
+		    (le32_to_cpu(p->des3) == 0xffffffff))
 			/* timestamp is corrupted, hence don't store it */
 			return 0;
 		else
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 2beacd0..fd78406 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -30,8 +30,8 @@ static int ndesc_get_tx_status(void *data, struct stmmac_extra_stats *x,
 			       struct dma_desc *p, void __iomem *ioaddr)
 {
 	struct net_device_stats *stats = (struct net_device_stats *)data;
-	unsigned int tdes0 = p->des0;
-	unsigned int tdes1 = p->des1;
+	unsigned int tdes0 = le32_to_cpu(p->des0);
+	unsigned int tdes1 = le32_to_cpu(p->des1);
 	int ret = tx_done;
 
 	/* Get tx owner first */
@@ -77,7 +77,7 @@ static int ndesc_get_tx_status(void *data, struct stmmac_extra_stats *x,
 
 static int ndesc_get_tx_len(struct dma_desc *p)
 {
-	return (p->des1 & RDES1_BUFFER1_SIZE_MASK);
+	return (le32_to_cpu(p->des1) & RDES1_BUFFER1_SIZE_MASK);
 }
 
 /* This function verifies if each incoming frame has some errors
@@ -88,7 +88,7 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 			       struct dma_desc *p)
 {
 	int ret = good_frame;
-	unsigned int rdes0 = p->des0;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
 	struct net_device_stats *stats = (struct net_device_stats *)data;
 
 	if (unlikely(rdes0 & RDES0_OWN))
@@ -141,8 +141,8 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 			       int end)
 {
-	p->des0 |= RDES0_OWN;
-	p->des1 |= (BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK;
+	p->des0 |= cpu_to_le32(RDES0_OWN);
+	p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_rx_set_on_chain(p, end);
@@ -150,12 +150,12 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 		ndesc_rx_set_on_ring(p, end);
 
 	if (disable_rx_ic)
-		p->des1 |= RDES1_DISABLE_IC;
+		p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
 }
 
 static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des0 &= ~TDES0_OWN;
+	p->des0 &= cpu_to_le32(~TDES0_OWN);
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_tx_set_on_chain(p);
 	else
@@ -164,27 +164,27 @@ static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
 
 static int ndesc_get_tx_owner(struct dma_desc *p)
 {
-	return (p->des0 & TDES0_OWN) >> 31;
+	return (le32_to_cpu(p->des0) & TDES0_OWN) >> 31;
 }
 
 static void ndesc_set_tx_owner(struct dma_desc *p)
 {
-	p->des0 |= TDES0_OWN;
+	p->des0 |= cpu_to_le32(TDES0_OWN);
 }
 
 static void ndesc_set_rx_owner(struct dma_desc *p)
 {
-	p->des0 |= RDES0_OWN;
+	p->des0 |= cpu_to_le32(RDES0_OWN);
 }
 
 static int ndesc_get_tx_ls(struct dma_desc *p)
 {
-	return (p->des1 & TDES1_LAST_SEGMENT) >> 30;
+	return (le32_to_cpu(p->des1) & TDES1_LAST_SEGMENT) >> 30;
 }
 
 static void ndesc_release_tx_desc(struct dma_desc *p, int mode)
 {
-	int ter = (p->des1 & TDES1_END_RING) >> 25;
+	int ter = (le32_to_cpu(p->des1) & TDES1_END_RING) >> 25;
 
 	memset(p, 0, offsetof(struct dma_desc, des2));
 	if (mode == STMMAC_CHAIN_MODE)
@@ -197,7 +197,7 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				  bool csum_flag, int mode, bool tx_own,
 				  bool ls)
 {
-	unsigned int tdes1 = p->des1;
+	unsigned int tdes1 = le32_to_cpu(p->des1);
 
 	if (is_fs)
 		tdes1 |= TDES1_FIRST_SEGMENT;
@@ -212,7 +212,7 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 	if (ls)
 		tdes1 |= TDES1_LAST_SEGMENT;
 
-	p->des1 = tdes1;
+	p->des1 = cpu_to_le32(tdes1);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		norm_set_tx_desc_len_on_chain(p, len);
@@ -220,12 +220,12 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 		norm_set_tx_desc_len_on_ring(p, len);
 
 	if (tx_own)
-		p->des0 |= TDES0_OWN;
+		p->des0 |= cpu_to_le32(TDES0_OWN);
 }
 
 static void ndesc_set_tx_ic(struct dma_desc *p)
 {
-	p->des1 |= TDES1_INTERRUPT;
+	p->des1 |= cpu_to_le32(TDES1_INTERRUPT);
 }
 
 static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
@@ -241,19 +241,20 @@ static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
 	if (rx_coe_type == STMMAC_RX_COE_TYPE1)
 		csum = 2;
 
-	return (((p->des0 & RDES0_FRAME_LEN_MASK) >> RDES0_FRAME_LEN_SHIFT) -
+	return (((le32_to_cpu(p->des0) & RDES0_FRAME_LEN_MASK)
+				>> RDES0_FRAME_LEN_SHIFT) -
 		csum);
 
 }
 
 static void ndesc_enable_tx_timestamp(struct dma_desc *p)
 {
-	p->des1 |= TDES1_TIME_STAMP_ENABLE;
+	p->des1 |= cpu_to_le32(TDES1_TIME_STAMP_ENABLE);
 }
 
 static int ndesc_get_tx_timestamp_status(struct dma_desc *p)
 {
-	return (p->des0 & TDES0_TIME_STAMP_STATUS) >> 17;
+	return (le32_to_cpu(p->des0) & TDES0_TIME_STAMP_STATUS) >> 17;
 }
 
 static u64 ndesc_get_timestamp(void *desc, u32 ats)
@@ -261,9 +262,9 @@ static u64 ndesc_get_timestamp(void *desc, u32 ats)
 	struct dma_desc *p = (struct dma_desc *)desc;
 	u64 ns;
 
-	ns = p->des2;
+	ns = le32_to_cpu(p->des2);
 	/* convert high/sec time stamp value to nanosecond */
-	ns += p->des3 * 1000000000ULL;
+	ns += le32_to_cpu(p->des3) * 1000000000ULL;
 
 	return ns;
 }
@@ -272,7 +273,8 @@ static int ndesc_get_rx_timestamp_status(void *desc, u32 ats)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
 
-	if ((p->des2 == 0xffffffff) && (p->des3 == 0xffffffff))
+	if ((le32_to_cpu(p->des2) == 0xffffffff) &&
+	    (le32_to_cpu(p->des3) == 0xffffffff))
 		/* timestamp is corrupted, hence don't store it */
 		return 0;
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index 7723b5d..9983ce9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -34,7 +34,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 	unsigned int entry = priv->cur_tx;
 	struct dma_desc *desc;
 	unsigned int nopaged_len = skb_headlen(skb);
-	unsigned int bmax, len;
+	unsigned int bmax, len, des2;
 
 	if (priv->extend_desc)
 		desc = (struct dma_desc *)(priv->dma_etx + entry);
@@ -50,16 +50,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 	if (nopaged_len > BUF_SIZE_8KiB) {
 
-		desc->des2 = dma_map_single(priv->device, skb->data,
-					    bmax, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->device, desc->des2))
+		des2 = dma_map_single(priv->device, skb->data, bmax,
+				      DMA_TO_DEVICE);
+		desc->des2 = cpu_to_le32(des2);
+		if (dma_mapping_error(priv->device, des2))
 			return -1;
 
-		priv->tx_skbuff_dma[entry].buf = desc->des2;
+		priv->tx_skbuff_dma[entry].buf = des2;
 		priv->tx_skbuff_dma[entry].len = bmax;
 		priv->tx_skbuff_dma[entry].is_jumbo = true;
 
-		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
 						STMMAC_RING_MODE, 0, false);
 		priv->tx_skbuff[entry] = NULL;
@@ -70,26 +71,28 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		else
 			desc = priv->dma_tx + entry;
 
-		desc->des2 = dma_map_single(priv->device, skb->data + bmax,
-					    len, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->device, desc->des2))
+		des2 = dma_map_single(priv->device, skb->data + bmax, len,
+				      DMA_TO_DEVICE);
+		desc->des2 = cpu_to_le32(des2);
+		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = desc->des2;
+		priv->tx_skbuff_dma[entry].buf = des2;
 		priv->tx_skbuff_dma[entry].len = len;
 		priv->tx_skbuff_dma[entry].is_jumbo = true;
 
-		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
 						STMMAC_RING_MODE, 1, true);
 	} else {
-		desc->des2 = dma_map_single(priv->device, skb->data,
-					    nopaged_len, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->device, desc->des2))
+		des2 = dma_map_single(priv->device, skb->data,
+				      nopaged_len, DMA_TO_DEVICE);
+		desc->des2 = cpu_to_le32(des2);
+		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = desc->des2;
+		priv->tx_skbuff_dma[entry].buf = des2;
 		priv->tx_skbuff_dma[entry].len = nopaged_len;
 		priv->tx_skbuff_dma[entry].is_jumbo = true;
-		desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
 						STMMAC_RING_MODE, 0, true);
 	}
@@ -115,13 +118,13 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
 
 	/* Fill DES3 in case of RING mode */
 	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
-		p->des3 = p->des2 + BUF_SIZE_8KiB;
+		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
 /* In ring mode we need to fill the desc3 because it is used as buffer */
 static void stmmac_init_desc3(struct dma_desc *p)
 {
-	p->des3 = p->des2 + BUF_SIZE_8KiB;
+	p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e407126..57fdd31 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -973,9 +973,9 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 	}
 
 	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		p->des0 = priv->rx_skbuff_dma[i];
+		p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]);
 	else
-		p->des2 = priv->rx_skbuff_dma[i];
+		p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]);
 
 	if ((priv->hw->mode->init_desc3) &&
 	    (priv->dma_buf_sz == BUF_SIZE_16KiB))
@@ -1916,7 +1916,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
 		priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
 		desc = priv->dma_tx + priv->cur_tx;
 
-		desc->des0 = des + (total_len - tmp_len);
+		desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
 		buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
 			    TSO_MAX_BUFF_SIZE : tmp_len;
 
@@ -2018,11 +2018,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
 	priv->tx_skbuff[first_entry] = skb;
 
-	first->des0 = des;
+	first->des0 = cpu_to_le32(des);
 
 	/* Fill start of payload in buff2 of first descriptor */
 	if (pay_len)
-		first->des1 =  des + proto_hdr_len;
+		first->des1 = cpu_to_le32(des + proto_hdr_len);
 
 	/* If needed take extra descriptors to fill the remaining payload */
 	tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
@@ -2211,13 +2211,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		priv->tx_skbuff[entry] = NULL;
 
-		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-			desc->des0 = des;
-			priv->tx_skbuff_dma[entry].buf = desc->des0;
-		} else {
-			desc->des2 = des;
-			priv->tx_skbuff_dma[entry].buf = desc->des2;
-		}
+		priv->tx_skbuff_dma[entry].buf = des;
+		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
+			desc->des0 = cpu_to_le32(des);
+		else
+			desc->des2 = cpu_to_le32(des);
 
 		priv->tx_skbuff_dma[entry].map_as_page = true;
 		priv->tx_skbuff_dma[entry].len = len;
@@ -2288,13 +2286,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (dma_mapping_error(priv->device, des))
 			goto dma_map_err;
 
-		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-			first->des0 = des;
-			priv->tx_skbuff_dma[first_entry].buf = first->des0;
-		} else {
-			first->des2 = des;
-			priv->tx_skbuff_dma[first_entry].buf = first->des2;
-		}
+		priv->tx_skbuff_dma[first_entry].buf = des;
+		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
+			first->des0 = cpu_to_le32(des);
+		else
+			first->des2 = cpu_to_le32(des);
 
 		priv->tx_skbuff_dma[first_entry].len = nopaged_len;
 		priv->tx_skbuff_dma[first_entry].last_segment = last_segment;
@@ -2408,10 +2404,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
 			}
 
 			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-				p->des0 = priv->rx_skbuff_dma[entry];
+				p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
 				p->des1 = 0;
 			} else {
-				p->des2 = priv->rx_skbuff_dma[entry];
+				p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
 			}
 			if (priv->hw->mode->refill_desc3)
 				priv->hw->mode->refill_desc3(priv, p);
@@ -2512,9 +2508,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 			unsigned int des;
 
 			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
-				des = p->des0;
+				des = le32_to_cpu(p->des0);
 			else
-				des = p->des2;
+				des = le32_to_cpu(p->des2);
 
 			frame_len = priv->hw->desc->get_rx_frame_len(p, coe);
 
@@ -2880,14 +2876,17 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
 			x = *(u64 *) ep;
 			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
 				   i, (unsigned int)virt_to_phys(ep),
-				   ep->basic.des0, ep->basic.des1,
-				   ep->basic.des2, ep->basic.des3);
-			ep++;
+				   le32_to_cpu(ep->basic.des0),
+				   le32_to_cpu(ep->basic.des1),
+				   le32_to_cpu(ep->basic.des2),
+				   le32_to_cpu(ep->basic.des3));
+			ep++);
 		} else {
 			x = *(u64 *) p;
 			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
 				   i, (unsigned int)virt_to_phys(ep),
-				   p->des0, p->des1, p->des2, p->des3);
+				   le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+				   le32_to_cpu(p->des2), le32_to_cpu(p->des3));
 			p++;
 		}
 		seq_printf(seq, "\n");
-- 
2.9.0

[PATCH 3/3] ARM: sunxi: enable big-endian

[Michael Weiser]

At least the Cubieboard2 incarnation of sunxi works correctly in
big-endian mode. Allow the selection of big-endian.

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: linux-arm-kernel at lists.infradead.org
---
 arch/arm/mach-sunxi/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index c124d65..4dcbbfe 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -1,6 +1,7 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs"
 	depends on ARCH_MULTI_V7
+	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
-- 
2.9.0

[PATCH 1/3] mmc: sunxi-mmc: change idma descriptor to __le32

[Maxime Ripard]

On Thu, Jul 21, 2016 at 08:23:27PM +0200, Michael Weiser wrote:
> The sunxi-mmc driver does not take into account the processor may be big
> endian when writing the DMA descriptors. This causes cards not to be
> detected when running a big-endian kernel. Change the descriptors for
> IDMA to use __le32 and ensure they are suitably swapped before writing.
> Tested successfully on the Cubieboard2.
> 
> Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
> Cc: Ulf Hansson <ulf.hansson@linaro.org>
> Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
> Cc: Chen-Yu Tsai <wens@csie.org>
> Cc: linux-mmc at vger.kernel.org

Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>

Thanks,
Maxime

-- 
Maxime Ripard, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20160722/f4b399ca/attachment.sig>

[PATCH 3/3] ARM: sunxi: enable big-endian

[Maxime Ripard]

Hi,

On Thu, Jul 21, 2016 at 08:23:29PM +0200, Michael Weiser wrote:
> At least the Cubieboard2 incarnation of sunxi works correctly in
> big-endian mode. Allow the selection of big-endian.
> 
> Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
> Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
> Cc: Chen-Yu Tsai <wens@csie.org>
> Cc: linux-arm-kernel at lists.infradead.org

With what devices has it been tested? The one doing DMA will probably
be the one who fail, have you tested the DMA engine? EMAC? GMAC?

Thanks,
Maxime

-- 
Maxime Ripard, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20160722/0e68325a/attachment.sig>

[PATCH 3/3] ARM: sunxi: enable big-endian

[Michael Weiser]

Hi Maxime,

On Fri, Jul 22, 2016 at 11:01:01AM +0200, Maxime Ripard wrote:

> > At least the Cubieboard2 incarnation of sunxi works correctly in
> > big-endian mode. Allow the selection of big-endian.
> With what devices has it been tested? The one doing DMA will probably
> be the one who fail, have you tested the DMA engine? EMAC? GMAC?

I've tested with a Cubieboard2 Two-Card (on-board EMMC replaced with a
second slot). I ran into and fixed DMA problems with stmmac (that's
GMAC) and sunxi-mmc. Patches are submitted as part of this patchset.
Endianness fixes to stmmac went much farther than just GMAC but remain
untested since the Cubieboard2 only uses GMAC.

I have also successfully used SATA, SPI, UART, security system (with
cryptodev), the hwmon part of the touchscreen controller, pinctrl with a
custom interrupt pin via fdt for ethernet via SPI (ENC28J60), watchdog
as reset controller, onboard RTC and external battery-backed DS1307 RTC
via I2C. I have not deliberately/synthetically tested the DMA engine. It's
enabled in the my kernel config and seems happy but was not selected by
any other driver so seems to be unused currently.

I was reluctant to enable big endian support this generically but found
no better way. Since board specifics are in device tree now, I can't
really do a && CONFIG_MACH_CUBIEBOARD2 or somesuch. Or can I?
-- 
Thanks,
Michael

[PATCH 3/3] ARM: sunxi: enable big-endian

[Maxime Ripard]

On Fri, Jul 22, 2016 at 03:56:58PM +0200, Michael Weiser wrote:
> Hi Maxime,
> 
> On Fri, Jul 22, 2016 at 11:01:01AM +0200, Maxime Ripard wrote:
> 
> > > At least the Cubieboard2 incarnation of sunxi works correctly in
> > > big-endian mode. Allow the selection of big-endian.
> > With what devices has it been tested? The one doing DMA will probably
> > be the one who fail, have you tested the DMA engine? EMAC? GMAC?
> 
> I've tested with a Cubieboard2 Two-Card (on-board EMMC replaced with a
> second slot). I ran into and fixed DMA problems with stmmac (that's
> GMAC) and sunxi-mmc. Patches are submitted as part of this patchset.
> Endianness fixes to stmmac went much farther than just GMAC but remain
> untested since the Cubieboard2 only uses GMAC.
> 
> I have also successfully used SATA, SPI, UART, security system (with
> cryptodev), the hwmon part of the touchscreen controller, pinctrl with a
> custom interrupt pin via fdt for ethernet via SPI (ENC28J60), watchdog
> as reset controller, onboard RTC and external battery-backed DS1307 RTC
> via I2C. I have not deliberately/synthetically tested the DMA engine. It's
> enabled in the my kernel config and seems happy but was not selected by
> any other driver so seems to be unused currently.

You can test the DMA using the audio components, either the codec, i2s
or spdif. EMAC would be worth testing too.

> I was reluctant to enable big endian support this generically but found
> no better way. Since board specifics are in device tree now, I can't
> really do a && CONFIG_MACH_CUBIEBOARD2 or somesuch. Or can I?

Not really, but it doesn't really matter, since all those drivers are
at the SoC level and should affect all boards equally. And you have
MACH_SUN7I :)

Maxime

-- 
Maxime Ripard, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20160725/5783092e/attachment.sig>

[PATCH 2/3] stmmac: change dma descriptors to __le32

[Giuseppe CAVALLARO]

On 7/21/2016 8:23 PM, Michael Weiser wrote:
> The stmmac driver does not take into account the processor may be big
> endian when writing the DMA descriptors. This causes the ethernet
> interface not to be initialised correctly when running a big-endian
> kernel. Change the descriptors for DMA to use __le32 and ensure they are
> suitably swapped before writing. Tested successfully on the
> Cubieboard2.

Thx for the effort on big endian platform.
>
> Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
> Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
> Cc: Alexandre Torgue <alexandre.torgue@st.com>
> Cc: netdev at vger.kernel.org
> ---
...
>
> @@ -2880,14 +2876,17 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
>  			x = *(u64 *) ep;
>  			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
>  				   i, (unsigned int)virt_to_phys(ep),
> -				   ep->basic.des0, ep->basic.des1,
> -				   ep->basic.des2, ep->basic.des3);
> -			ep++;
> +				   le32_to_cpu(ep->basic.des0),
> +				   le32_to_cpu(ep->basic.des1),
> +				   le32_to_cpu(ep->basic.des2),
> +				   le32_to_cpu(ep->basic.des3));
> +			ep++);


there is a build problem here.

Pls fix it.


Peppe

[PATCH 3/3] ARM: sunxi: enable big-endian

[Michael Weiser]

Hi Maxime,

On Mon, Jul 25, 2016 at 02:25:22PM +0200, Maxime Ripard wrote:

> > via I2C. I have not deliberately/synthetically tested the DMA engine. It's
> > enabled in the my kernel config and seems happy but was not selected by
> > any other driver so seems to be unused currently.
> You can test the DMA using the audio components, either the codec, i2s
> or spdif.

I've enabled the codec and it's currently playing some King Khan to me.

[PATCH 3/3] ARM: sunxi: enable big-endian

[Chen-Yu Tsai]

On Wed, Jul 27, 2016 at 3:26 AM, Michael Weiser <michael.weiser@gmx.de> wrote:
> Hi Maxime,
>
> On Mon, Jul 25, 2016 at 02:25:22PM +0200, Maxime Ripard wrote:
>
>> > via I2C. I have not deliberately/synthetically tested the DMA engine. It's
>> > enabled in the my kernel config and seems happy but was not selected by
>> > any other driver so seems to be unused currently.
>> You can test the DMA using the audio components, either the codec, i2s
>> or spdif.
>
> I've enabled the codec and it's currently playing some King Khan to me.
> From looking at sun4i-dma.c it seems that all communication with the
> silicon is via registers, including transfer of the DMA descriptors, and
> all is done using {read,write}l{,_relaxed} already.
>
>> EMAC would be worth testing too.
>
> As far as I gather, the Cubieboard2 does not route the EMAC pins anywhere.
> So I can't connect a PHY to it for testing.

The EMAC pins are muxed with the GMAC pins. All you need to do is disable
the GMAC, enable the EMAC, and use emac_pins_a for the pinctrl.

ChenYu

[PATCH 2/3] stmmac: change dma descriptors to __le32

[Michael Weiser]

Hi Giuseppe,

On Tue, Jul 26, 2016 at 02:13:45PM +0200, Giuseppe CAVALLARO wrote:

> > -			ep++;
> > +			ep++);
> there is a build problem here.
> Pls fix it.

Thanks for your review. I've got it fixed locally. An updated patchset
will be forthcoming as soon as I've sorted a problem with sun4i-emac
which I've been asked to look into as well.
-- 
Thanks,
Michael

[PATCH 3/3] ARM: sunxi: enable big-endian

[Michael Weiser]

Hi ChenYu,

On Wed, Jul 27, 2016 at 09:55:11AM +0800, Chen-Yu Tsai wrote:
> > As far as I gather, the Cubieboard2 does not route the EMAC pins anywhere.
> > So I can't connect a PHY to it for testing.
> The EMAC pins are muxed with the GMAC pins. All you need to do is disable
> the GMAC, enable the EMAC, and use emac_pins_a for the pinctrl.

Okay, I've done that by copying the relevant dts sections from
sun4i-a10-cubieboard.dts. It initialises and transmits packets fine. But
it doesn't seem to accept incoming packets. I suspect that programming
of its own MAC address (which the driver chooses randomly) suffers from
an endianness issue. I'm somewhat stumped as to what is causing it since
all accesses use {read,write}l. Interrupt handling is another possible
culprit. I'm still digging.
-- 
Thanks,
Michael

[PATCH 2/3] stmmac: change dma descriptors to __le32

[Giuseppe CAVALLARO]

On 7/29/2016 9:53 AM, Michael Weiser wrote:
> Hi Giuseppe,
>
> On Tue, Jul 26, 2016 at 02:13:45PM +0200, Giuseppe CAVALLARO wrote:
>
>>> -			ep++;
>>> +			ep++);
>> there is a build problem here.
>> Pls fix it.
>
> Thanks for your review. I've got it fixed locally. An updated patchset
> will be forthcoming as soon as I've sorted a problem with sun4i-emac
> which I've been asked to look into as well.
>

ok, as you send the new version I will do a run on ARM box based too

peppe

[PATCH 3/3] ARM: sunxi: enable big-endian

[Maxime Ripard]

Hi,

On Fri, Jul 29, 2016 at 09:59:23AM +0200, Michael Weiser wrote:
> Hi ChenYu,
> 
> On Wed, Jul 27, 2016 at 09:55:11AM +0800, Chen-Yu Tsai wrote:
> > > As far as I gather, the Cubieboard2 does not route the EMAC pins anywhere.
> > > So I can't connect a PHY to it for testing.
> > The EMAC pins are muxed with the GMAC pins. All you need to do is disable
> > the GMAC, enable the EMAC, and use emac_pins_a for the pinctrl.
> 
> Okay, I've done that by copying the relevant dts sections from
> sun4i-a10-cubieboard.dts. It initialises and transmits packets fine. But
> it doesn't seem to accept incoming packets. I suspect that programming
> of its own MAC address (which the driver chooses randomly) suffers from
> an endianness issue. I'm somewhat stumped as to what is causing it since
> all accesses use {read,write}l. Interrupt handling is another possible
> culprit. I'm still digging.

Maybe a good way to confirm that would be to generate outgoing
traffic, dump that and see what the mac address is? If it's not
programmed properly, you should see it in the packets.

Maxime

-- 
Maxime Ripard, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20160729/ba256feb/attachment-0001.sig>

[PATCH 3/3] ARM: sunxi: enable big-endian

[Michael Weiser]

Hi Maxime,

On Fri, Jul 29, 2016 at 06:39:07PM +0200, Maxime Ripard wrote:

> > it doesn't seem to accept incoming packets. I suspect that programming
> > of its own MAC address (which the driver chooses randomly) suffers from
> > an endianness issue. I'm somewhat stumped as to what is causing it since
> Maybe a good way to confirm that would be to generate outgoing
> traffic, dump that and see what the mac address is? If it's not
> programmed properly, you should see it in the packets.

That's what I've done: When trying to ping another machine, with tcpdump
I see ARP requests coming from the cubieboard with the right MAC and I
see the target machine sending ARP responses to the right MAC. But I do
not see them coming in with tcpdump on the cubieboard.

The same process works fine with a little-endian kernel (same .config and
dtb) and userland, so I'm sure it's an endianess issue somewhere.

I'll do some more comparison of little- and big-endian kernel behaviour
and dig a bit deeper into the code.
-- 
Thanks,
Michael

[PATCH 1/3] mmc: sunxi-mmc: change idma descriptor to __le32

[Michael Weiser]

The sunxi-mmc driver does not take into account the processor may be big
endian when writing the DMA descriptors. This causes cards not to be
detected when running a big-endian kernel. Change the descriptors for
IDMA to use __le32 and ensure they are suitably swapped before writing.
Tested successfully on the Cubieboard2.

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>
---
 drivers/mmc/host/sunxi-mmc.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 2ee4c21..8b8f08c 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -223,10 +223,10 @@ struct sunxi_mmc_clk_delay {
 };
 
 struct sunxi_idma_des {
-	u32	config;
-	u32	buf_size;
-	u32	buf_addr_ptr1;
-	u32	buf_addr_ptr2;
+	__le32 config;
+	__le32 buf_size;
+	__le32 buf_addr_ptr1;
+	__le32 buf_addr_ptr2;
 };
 
 struct sunxi_mmc_host {
@@ -325,22 +325,22 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host,
 	int i, max_len = (1 << host->idma_des_size_bits);
 
 	for (i = 0; i < data->sg_len; i++) {
-		pdes[i].config = SDXC_IDMAC_DES0_CH | SDXC_IDMAC_DES0_OWN |
-				 SDXC_IDMAC_DES0_DIC;
+		pdes[i].config = cpu_to_le32(SDXC_IDMAC_DES0_CH | SDXC_IDMAC_DES0_OWN |
+				 SDXC_IDMAC_DES0_DIC);
 
 		if (data->sg[i].length == max_len)
 			pdes[i].buf_size = 0; /* 0 == max_len */
 		else
-			pdes[i].buf_size = data->sg[i].length;
+			pdes[i].buf_size = cpu_to_le32(data->sg[i].length);
 
 		next_desc += sizeof(struct sunxi_idma_des);
-		pdes[i].buf_addr_ptr1 = sg_dma_address(&data->sg[i]);
-		pdes[i].buf_addr_ptr2 = (u32)next_desc;
+		pdes[i].buf_addr_ptr1 = cpu_to_le32(sg_dma_address(&data->sg[i]));
+		pdes[i].buf_addr_ptr2 = cpu_to_le32((u32)next_desc);
 	}
 
-	pdes[0].config |= SDXC_IDMAC_DES0_FD;
-	pdes[i - 1].config |= SDXC_IDMAC_DES0_LD | SDXC_IDMAC_DES0_ER;
-	pdes[i - 1].config &= ~SDXC_IDMAC_DES0_DIC;
+	pdes[0].config |= cpu_to_le32(SDXC_IDMAC_DES0_FD);
+	pdes[i - 1].config |= cpu_to_le32(SDXC_IDMAC_DES0_LD | SDXC_IDMAC_DES0_ER);
+	pdes[i - 1].config &= cpu_to_le32(~SDXC_IDMAC_DES0_DIC);
 	pdes[i - 1].buf_addr_ptr2 = 0;
 
 	/*
-- 
2.9.0