pcnet: access descriptor rings & init block uncached

The prior accesses to the descriptor rings & init block via cached
memory had a few issues:

  - The memory needs cache flushes or invalidation at the appropriate
    times, but was not necessarily aligned on cache line boundaries.
    This could lead to data being incorrectly lost or written back to
    RAM at the wrong time.

  - There are points where ordering of writes to the memory is
    important, but because it's cached memory the pcnet controller
    would see cache lines written back ordered by address. This could
    occasionally lead to hardware seeing descriptors in an incorrect
    state.

  - Flushing the cache constantly is inefficient.

So, to avoid all of those issues simply access the descriptors & init
block via uncached memory. The MIPS-specific UNCACHED_SDRAM macro is
used to do this (retrieving an address in kseg1) as I could see no
existing generic solution. Since the MIPS Malta board is the only user
of the pcnet driver, hopefully this doesn't matter.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>

1 files changed, 35 insertions, 31 deletions

diff --git a/drivers/net/pcnet.c b/drivers/net/pcnet.c
index 71a3110712..8c334c7abc 100644
--- a/drivers/net/pcnet.c
+++ b/drivers/net/pcnet.c
@@ -71,10 +71,14 @@ struct pcnet_init_block {
 	u32 reserved2;
 };
 
-typedef struct pcnet_priv {
+struct pcnet_uncached_priv {
 	struct pcnet_rx_head rx_ring[RX_RING_SIZE];
 	struct pcnet_tx_head tx_ring[TX_RING_SIZE];
 	struct pcnet_init_block init_block;
+};
+
+typedef struct pcnet_priv {
+	struct pcnet_uncached_priv *uc;
 	/* Receive Buffer space */
 	unsigned char rx_buf[RX_RING_SIZE][PKT_BUF_SZ + 4];
 	int cur_rx;
@@ -283,6 +287,7 @@ static int pcnet_probe(struct eth_device *dev, bd_t *bis, int dev_nr)
 
 static int pcnet_init(struct eth_device *dev, bd_t *bis)
 {
+	struct pcnet_uncached_priv *uc;
 	int i, val;
 	u32 addr;
 
@@ -325,24 +330,31 @@ static int pcnet_init(struct eth_device *dev, bd_t *bis)
 		addr = (u32)malloc(sizeof(pcnet_priv_t) + 0x10);
 		addr = (addr + 0xf) & ~0xf;
 		lp = (pcnet_priv_t *)addr;
+
+		addr = (u32)memalign(ARCH_DMA_MINALIGN, sizeof(*lp->uc));
+		flush_dcache_range(addr, addr + sizeof(*lp->uc));
+		addr = UNCACHED_SDRAM(addr);
+		lp->uc = (struct pcnet_uncached_priv *)addr;
 	}
 
-	lp->init_block.mode = cpu_to_le16(0x0000);
-	lp->init_block.filter[0] = 0x00000000;
-	lp->init_block.filter[1] = 0x00000000;
+	uc = lp->uc;
+
+	uc->init_block.mode = cpu_to_le16(0x0000);
+	uc->init_block.filter[0] = 0x00000000;
+	uc->init_block.filter[1] = 0x00000000;
 
 	/*
 	 * Initialize the Rx ring.
 	 */
 	lp->cur_rx = 0;
 	for (i = 0; i < RX_RING_SIZE; i++) {
-		lp->rx_ring[i].base = PCI_TO_MEM_LE(dev, lp->rx_buf[i]);
-		lp->rx_ring[i].buf_length = cpu_to_le16(-PKT_BUF_SZ);
-		lp->rx_ring[i].status = cpu_to_le16(0x8000);
+		uc->rx_ring[i].base = PCI_TO_MEM_LE(dev, lp->rx_buf[i]);
+		uc->rx_ring[i].buf_length = cpu_to_le16(-PKT_BUF_SZ);
+		uc->rx_ring[i].status = cpu_to_le16(0x8000);
 		PCNET_DEBUG1
 			("Rx%d: base=0x%x buf_length=0x%hx status=0x%hx\n", i,
-			 lp->rx_ring[i].base, lp->rx_ring[i].buf_length,
-			 lp->rx_ring[i].status);
+			 uc->rx_ring[i].base, uc->rx_ring[i].buf_length,
+			 uc->rx_ring[i].status);
 	}
 
 	/*
@@ -351,34 +363,34 @@ static int pcnet_init(struct eth_device *dev, bd_t *bis)
 	 */
 	lp->cur_tx = 0;
 	for (i = 0; i < TX_RING_SIZE; i++) {
-		lp->tx_ring[i].base = 0;
-		lp->tx_ring[i].status = 0;
+		uc->tx_ring[i].base = 0;
+		uc->tx_ring[i].status = 0;
 	}
 
 	/*
 	 * Setup Init Block.
 	 */
-	PCNET_DEBUG1("Init block at 0x%p: MAC", &lp->init_block);
+	PCNET_DEBUG1("Init block at 0x%p: MAC", &lp->uc->init_block);
 
 	for (i = 0; i < 6; i++) {
-		lp->init_block.phys_addr[i] = dev->enetaddr[i];
-		PCNET_DEBUG1(" %02x", lp->init_block.phys_addr[i]);
+		lp->uc->init_block.phys_addr[i] = dev->enetaddr[i];
+		PCNET_DEBUG1(" %02x", lp->uc->init_block.phys_addr[i]);
 	}
 
-	lp->init_block.tlen_rlen = cpu_to_le16(TX_RING_LEN_BITS |
+	uc->init_block.tlen_rlen = cpu_to_le16(TX_RING_LEN_BITS |
 					       RX_RING_LEN_BITS);
-	lp->init_block.rx_ring = PCI_TO_MEM_LE(dev, lp->rx_ring);
-	lp->init_block.tx_ring = PCI_TO_MEM_LE(dev, lp->tx_ring);
-	flush_dcache_range((unsigned long)lp, (unsigned long)&lp->rx_buf);
+	uc->init_block.rx_ring = PCI_TO_MEM_LE(dev, uc->rx_ring);
+	uc->init_block.tx_ring = PCI_TO_MEM_LE(dev, uc->tx_ring);
 
 	PCNET_DEBUG1("\ntlen_rlen=0x%x rx_ring=0x%x tx_ring=0x%x\n",
-		     lp->init_block.tlen_rlen,
-		     lp->init_block.rx_ring, lp->init_block.tx_ring);
+		     uc->init_block.tlen_rlen,
+		     uc->init_block.rx_ring, uc->init_block.tx_ring);
 
 	/*
 	 * Tell the controller where the Init Block is located.
 	 */
-	addr = PCI_TO_MEM(dev, &lp->init_block);
+	barrier();
+	addr = PCI_TO_MEM(dev, &lp->uc->init_block);
 	pcnet_write_csr(dev, 1, addr & 0xffff);
 	pcnet_write_csr(dev, 2, (addr >> 16) & 0xffff);
 
@@ -408,7 +420,7 @@ static int pcnet_init(struct eth_device *dev, bd_t *bis)
 static int pcnet_send(struct eth_device *dev, void *packet, int pkt_len)
 {
 	int i, status;
-	struct pcnet_tx_head *entry = &lp->tx_ring[lp->cur_tx];
+	struct pcnet_tx_head *entry = &lp->uc->tx_ring[lp->cur_tx];
 
 	PCNET_DEBUG2("Tx%d: %d bytes from 0x%p ", lp->cur_tx, pkt_len,
 		     packet);
@@ -418,8 +430,6 @@ static int pcnet_send(struct eth_device *dev, void *packet, int pkt_len)
 
 	/* Wait for completion by testing the OWN bit */
 	for (i = 1000; i > 0; i--) {
-		invalidate_dcache_range((unsigned long)entry,
-					(unsigned long)entry + sizeof(*entry));
 		status = le16_to_cpu(entry->status);
 		if ((status & 0x8000) == 0)
 			break;
@@ -442,8 +452,6 @@ static int pcnet_send(struct eth_device *dev, void *packet, int pkt_len)
 	entry->misc = 0x00000000;
 	entry->base = PCI_TO_MEM_LE(dev, packet);
 	entry->status = cpu_to_le16(status);
-	flush_dcache_range((unsigned long)entry,
-			   (unsigned long)entry + sizeof(*entry));
 
 	/* Trigger an immediate send poll. */
 	pcnet_write_csr(dev, 0, 0x0008);
@@ -463,9 +471,7 @@ static int pcnet_recv (struct eth_device *dev)
 	u16 status;
 
 	while (1) {
-		entry = &lp->rx_ring[lp->cur_rx];
-		invalidate_dcache_range((unsigned long)entry,
-					(unsigned long)entry + sizeof(*entry));
+		entry = &lp->uc->rx_ring[lp->cur_rx];
 		/*
 		 * If we own the next entry, it's a new packet. Send it up.
 		 */
@@ -505,8 +511,6 @@ static int pcnet_recv (struct eth_device *dev)
 			}
 		}
 		entry->status |= cpu_to_le16(0x8000);
-		flush_dcache_range((unsigned long)entry,
-				   (unsigned long)entry + sizeof(*entry));
 
 		if (++lp->cur_rx >= RX_RING_SIZE)
 			lp->cur_rx = 0;