Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 439 insertions, 178 deletions

diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index 925161959b9b..6f987a7ffcb3 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -41,7 +41,10 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
+#include <linux/iopoll.h>
 #include <linux/in.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/delay.h>
@@ -54,21 +57,246 @@
 #include <linux/ethtool.h>
 #include <linux/crc32.h>
 #include <linux/pgtable.h>
-
-#include <asm/bootinfo.h>
-#include <asm/bitops.h>
-#include <asm/io.h>
-#include <asm/dma.h>
-
-#include <asm/mach-rc32434/rb.h>
-#include <asm/mach-rc32434/rc32434.h>
-#include <asm/mach-rc32434/eth.h>
-#include <asm/mach-rc32434/dma_v.h>
+#include <linux/clk.h>
 
 #define DRV_NAME	"korina"
 #define DRV_VERSION	"0.20"
 #define DRV_RELDATE	"15Sep2017"
 
+struct eth_regs {
+	u32 ethintfc;
+	u32 ethfifott;
+	u32 etharc;
+	u32 ethhash0;
+	u32 ethhash1;
+	u32 ethu0[4];		/* Reserved. */
+	u32 ethpfs;
+	u32 ethmcp;
+	u32 eth_u1[10];		/* Reserved. */
+	u32 ethspare;
+	u32 eth_u2[42];		/* Reserved. */
+	u32 ethsal0;
+	u32 ethsah0;
+	u32 ethsal1;
+	u32 ethsah1;
+	u32 ethsal2;
+	u32 ethsah2;
+	u32 ethsal3;
+	u32 ethsah3;
+	u32 ethrbc;
+	u32 ethrpc;
+	u32 ethrupc;
+	u32 ethrfc;
+	u32 ethtbc;
+	u32 ethgpf;
+	u32 eth_u9[50];		/* Reserved. */
+	u32 ethmac1;
+	u32 ethmac2;
+	u32 ethipgt;
+	u32 ethipgr;
+	u32 ethclrt;
+	u32 ethmaxf;
+	u32 eth_u10;		/* Reserved. */
+	u32 ethmtest;
+	u32 miimcfg;
+	u32 miimcmd;
+	u32 miimaddr;
+	u32 miimwtd;
+	u32 miimrdd;
+	u32 miimind;
+	u32 eth_u11;		/* Reserved. */
+	u32 eth_u12;		/* Reserved. */
+	u32 ethcfsa0;
+	u32 ethcfsa1;
+	u32 ethcfsa2;
+};
+
+/* Ethernet interrupt registers */
+#define ETH_INT_FC_EN		BIT(0)
+#define ETH_INT_FC_ITS		BIT(1)
+#define ETH_INT_FC_RIP		BIT(2)
+#define ETH_INT_FC_JAM		BIT(3)
+#define ETH_INT_FC_OVR		BIT(4)
+#define ETH_INT_FC_UND		BIT(5)
+#define ETH_INT_FC_IOC		0x000000c0
+
+/* Ethernet FIFO registers */
+#define ETH_FIFI_TT_TTH_BIT	0
+#define ETH_FIFO_TT_TTH		0x0000007f
+
+/* Ethernet ARC/multicast registers */
+#define ETH_ARC_PRO		BIT(0)
+#define ETH_ARC_AM		BIT(1)
+#define ETH_ARC_AFM		BIT(2)
+#define ETH_ARC_AB		BIT(3)
+
+/* Ethernet SAL registers */
+#define ETH_SAL_BYTE_5		0x000000ff
+#define ETH_SAL_BYTE_4		0x0000ff00
+#define ETH_SAL_BYTE_3		0x00ff0000
+#define ETH_SAL_BYTE_2		0xff000000
+
+/* Ethernet SAH registers */
+#define ETH_SAH_BYTE1		0x000000ff
+#define ETH_SAH_BYTE0		0x0000ff00
+
+/* Ethernet GPF register */
+#define ETH_GPF_PTV		0x0000ffff
+
+/* Ethernet PFG register */
+#define ETH_PFS_PFD		BIT(0)
+
+/* Ethernet CFSA[0-3] registers */
+#define ETH_CFSA0_CFSA4		0x000000ff
+#define ETH_CFSA0_CFSA5		0x0000ff00
+#define ETH_CFSA1_CFSA2		0x000000ff
+#define ETH_CFSA1_CFSA3		0x0000ff00
+#define ETH_CFSA1_CFSA0		0x000000ff
+#define ETH_CFSA1_CFSA1		0x0000ff00
+
+/* Ethernet MAC1 registers */
+#define ETH_MAC1_RE		BIT(0)
+#define ETH_MAC1_PAF		BIT(1)
+#define ETH_MAC1_RFC		BIT(2)
+#define ETH_MAC1_TFC		BIT(3)
+#define ETH_MAC1_LB		BIT(4)
+#define ETH_MAC1_MR		BIT(31)
+
+/* Ethernet MAC2 registers */
+#define ETH_MAC2_FD		BIT(0)
+#define ETH_MAC2_FLC		BIT(1)
+#define ETH_MAC2_HFE		BIT(2)
+#define ETH_MAC2_DC		BIT(3)
+#define ETH_MAC2_CEN		BIT(4)
+#define ETH_MAC2_PE		BIT(5)
+#define ETH_MAC2_VPE		BIT(6)
+#define ETH_MAC2_APE		BIT(7)
+#define ETH_MAC2_PPE		BIT(8)
+#define ETH_MAC2_LPE		BIT(9)
+#define ETH_MAC2_NB		BIT(12)
+#define ETH_MAC2_BP		BIT(13)
+#define ETH_MAC2_ED		BIT(14)
+
+/* Ethernet IPGT register */
+#define ETH_IPGT		0x0000007f
+
+/* Ethernet IPGR registers */
+#define ETH_IPGR_IPGR2		0x0000007f
+#define ETH_IPGR_IPGR1		0x00007f00
+
+/* Ethernet CLRT registers */
+#define ETH_CLRT_MAX_RET	0x0000000f
+#define ETH_CLRT_COL_WIN	0x00003f00
+
+/* Ethernet MAXF register */
+#define ETH_MAXF		0x0000ffff
+
+/* Ethernet test registers */
+#define ETH_TEST_REG		BIT(2)
+#define ETH_MCP_DIV		0x000000ff
+
+/* MII registers */
+#define ETH_MII_CFG_RSVD	0x0000000c
+#define ETH_MII_CMD_RD		BIT(0)
+#define ETH_MII_CMD_SCN		BIT(1)
+#define ETH_MII_REG_ADDR	0x0000001f
+#define ETH_MII_PHY_ADDR	0x00001f00
+#define ETH_MII_WTD_DATA	0x0000ffff
+#define ETH_MII_RDD_DATA	0x0000ffff
+#define ETH_MII_IND_BSY		BIT(0)
+#define ETH_MII_IND_SCN		BIT(1)
+#define ETH_MII_IND_NV		BIT(2)
+
+/* Values for the DEVCS field of the Ethernet DMA Rx and Tx descriptors. */
+#define ETH_RX_FD		BIT(0)
+#define ETH_RX_LD		BIT(1)
+#define ETH_RX_ROK		BIT(2)
+#define ETH_RX_FM		BIT(3)
+#define ETH_RX_MP		BIT(4)
+#define ETH_RX_BP		BIT(5)
+#define ETH_RX_VLT		BIT(6)
+#define ETH_RX_CF		BIT(7)
+#define ETH_RX_OVR		BIT(8)
+#define ETH_RX_CRC		BIT(9)
+#define ETH_RX_CV		BIT(10)
+#define ETH_RX_DB		BIT(11)
+#define ETH_RX_LE		BIT(12)
+#define ETH_RX_LOR		BIT(13)
+#define ETH_RX_CES		BIT(14)
+#define ETH_RX_LEN_BIT		16
+#define ETH_RX_LEN		0xffff0000
+
+#define ETH_TX_FD		BIT(0)
+#define ETH_TX_LD		BIT(1)
+#define ETH_TX_OEN		BIT(2)
+#define ETH_TX_PEN		BIT(3)
+#define ETH_TX_CEN		BIT(4)
+#define ETH_TX_HEN		BIT(5)
+#define ETH_TX_TOK		BIT(6)
+#define ETH_TX_MP		BIT(7)
+#define ETH_TX_BP		BIT(8)
+#define ETH_TX_UND		BIT(9)
+#define ETH_TX_OF		BIT(10)
+#define ETH_TX_ED		BIT(11)
+#define ETH_TX_EC		BIT(12)
+#define ETH_TX_LC		BIT(13)
+#define ETH_TX_TD		BIT(14)
+#define ETH_TX_CRC		BIT(15)
+#define ETH_TX_LE		BIT(16)
+#define ETH_TX_CC		0x001E0000
+
+/* DMA descriptor (in physical memory). */
+struct dma_desc {
+	u32 control;			/* Control. use DMAD_* */
+	u32 ca;				/* Current Address. */
+	u32 devcs;			/* Device control and status. */
+	u32 link;			/* Next descriptor in chain. */
+};
+
+#define DMA_DESC_COUNT_BIT		0
+#define DMA_DESC_COUNT_MSK		0x0003ffff
+#define DMA_DESC_DS_BIT			20
+#define DMA_DESC_DS_MSK			0x00300000
+
+#define DMA_DESC_DEV_CMD_BIT		22
+#define DMA_DESC_DEV_CMD_MSK		0x01c00000
+
+/* DMA descriptors interrupts */
+#define DMA_DESC_COF			BIT(25) /* Chain on finished */
+#define DMA_DESC_COD			BIT(26) /* Chain on done */
+#define DMA_DESC_IOF			BIT(27) /* Interrupt on finished */
+#define DMA_DESC_IOD			BIT(28) /* Interrupt on done */
+#define DMA_DESC_TERM			BIT(29) /* Terminated */
+#define DMA_DESC_DONE			BIT(30) /* Done */
+#define DMA_DESC_FINI			BIT(31) /* Finished */
+
+/* DMA register (within Internal Register Map).  */
+struct dma_reg {
+	u32 dmac;		/* Control. */
+	u32 dmas;		/* Status. */
+	u32 dmasm;		/* Mask. */
+	u32 dmadptr;		/* Descriptor pointer. */
+	u32 dmandptr;		/* Next descriptor pointer. */
+};
+
+/* DMA channels specific registers */
+#define DMA_CHAN_RUN_BIT		BIT(0)
+#define DMA_CHAN_DONE_BIT		BIT(1)
+#define DMA_CHAN_MODE_BIT		BIT(2)
+#define DMA_CHAN_MODE_MSK		0x0000000c
+#define	 DMA_CHAN_MODE_AUTO		0
+#define	 DMA_CHAN_MODE_BURST		1
+#define	 DMA_CHAN_MODE_XFRT		2
+#define	 DMA_CHAN_MODE_RSVD		3
+#define DMA_CHAN_ACT_BIT		BIT(4)
+
+/* DMA status registers */
+#define DMA_STAT_FINI			BIT(0)
+#define DMA_STAT_DONE			BIT(1)
+#define DMA_STAT_CHAIN			BIT(2)
+#define DMA_STAT_ERR			BIT(3)
+#define DMA_STAT_HALT			BIT(4)
+
 #define STATION_ADDRESS_HIGH(dev) (((dev)->dev_addr[0] << 8) | \
 				   ((dev)->dev_addr[1]))
 #define STATION_ADDRESS_LOW(dev)  (((dev)->dev_addr[2] << 24) | \
@@ -95,24 +323,30 @@
 
 enum chain_status {
 	desc_filled,
-	desc_empty
+	desc_is_empty
 };
 
+#define DMA_COUNT(count)	((count) & DMA_DESC_COUNT_MSK)
 #define IS_DMA_FINISHED(X)	(((X) & (DMA_DESC_FINI)) != 0)
 #define IS_DMA_DONE(X)		(((X) & (DMA_DESC_DONE)) != 0)
 #define RCVPKT_LENGTH(X)	(((X) & ETH_RX_LEN) >> ETH_RX_LEN_BIT)
 
 /* Information that need to be kept for each board. */
 struct korina_private {
-	struct eth_regs *eth_regs;
-	struct dma_reg *rx_dma_regs;
-	struct dma_reg *tx_dma_regs;
+	struct eth_regs __iomem *eth_regs;
+	struct dma_reg __iomem *rx_dma_regs;
+	struct dma_reg __iomem *tx_dma_regs;
 	struct dma_desc *td_ring; /* transmit descriptor ring */
 	struct dma_desc *rd_ring; /* receive descriptor ring  */
+	dma_addr_t td_dma;
+	dma_addr_t rd_dma;
 
 	struct sk_buff *tx_skb[KORINA_NUM_TDS];
 	struct sk_buff *rx_skb[KORINA_NUM_RDS];
 
+	dma_addr_t rx_skb_dma[KORINA_NUM_RDS];
+	dma_addr_t tx_skb_dma[KORINA_NUM_TDS];
+
 	int rx_next_done;
 	int rx_chain_head;
 	int rx_chain_tail;
@@ -137,15 +371,18 @@ struct korina_private {
 	struct mii_if_info mii_if;
 	struct work_struct restart_task;
 	struct net_device *dev;
-	int phy_addr;
+	struct device *dmadev;
+	int mii_clock_freq;
 };
 
-extern unsigned int idt_cpu_freq;
+static dma_addr_t korina_tx_dma(struct korina_private *lp, int idx)
+{
+	return lp->td_dma + (idx * sizeof(struct dma_desc));
+}
 
-static inline void korina_start_dma(struct dma_reg *ch, u32 dma_addr)
+static dma_addr_t korina_rx_dma(struct korina_private *lp, int idx)
 {
-	writel(0, &ch->dmandptr);
-	writel(dma_addr, &ch->dmadptr);
+	return lp->rd_dma + (idx * sizeof(struct dma_desc));
 }
 
 static inline void korina_abort_dma(struct net_device *dev,
@@ -164,11 +401,6 @@ static inline void korina_abort_dma(struct net_device *dev,
 	writel(0, &ch->dmandptr);
 }
 
-static inline void korina_chain_dma(struct dma_reg *ch, u32 dma_addr)
-{
-	writel(dma_addr, &ch->dmandptr);
-}
-
 static void korina_abort_tx(struct net_device *dev)
 {
 	struct korina_private *lp = netdev_priv(dev);
@@ -183,30 +415,21 @@ static void korina_abort_rx(struct net_device *dev)
 	korina_abort_dma(dev, lp->rx_dma_regs);
 }
 
-static void korina_start_rx(struct korina_private *lp,
-					struct dma_desc *rd)
-{
-	korina_start_dma(lp->rx_dma_regs, CPHYSADDR(rd));
-}
-
-static void korina_chain_rx(struct korina_private *lp,
-					struct dma_desc *rd)
-{
-	korina_chain_dma(lp->rx_dma_regs, CPHYSADDR(rd));
-}
-
 /* transmit packet */
 static int korina_send_packet(struct sk_buff *skb, struct net_device *dev)
 {
 	struct korina_private *lp = netdev_priv(dev);
-	unsigned long flags;
-	u32 length;
 	u32 chain_prev, chain_next;
+	unsigned long flags;
 	struct dma_desc *td;
+	dma_addr_t ca;
+	u32 length;
+	int idx;
 
 	spin_lock_irqsave(&lp->lock, flags);
 
-	td = &lp->td_ring[lp->tx_chain_tail];
+	idx = lp->tx_chain_tail;
+	td = &lp->td_ring[idx];
 
 	/* stop queue when full, drop pkts if queue already full */
 	if (lp->tx_count >= (KORINA_NUM_TDS - 2)) {
@@ -214,38 +437,37 @@ static int korina_send_packet(struct sk_buff *skb, struct net_device *dev)
 
 		if (lp->tx_count == (KORINA_NUM_TDS - 2))
 			netif_stop_queue(dev);
-		else {
-			dev->stats.tx_dropped++;
-			dev_kfree_skb_any(skb);
-			spin_unlock_irqrestore(&lp->lock, flags);
-
-			return NETDEV_TX_OK;
-		}
+		else
+			goto drop_packet;
 	}
 
 	lp->tx_count++;
 
-	lp->tx_skb[lp->tx_chain_tail] = skb;
+	lp->tx_skb[idx] = skb;
 
 	length = skb->len;
-	dma_cache_wback((u32)skb->data, skb->len);
 
 	/* Setup the transmit descriptor. */
-	dma_cache_inv((u32) td, sizeof(*td));
-	td->ca = CPHYSADDR(skb->data);
-	chain_prev = (lp->tx_chain_tail - 1) & KORINA_TDS_MASK;
-	chain_next = (lp->tx_chain_tail + 1) & KORINA_TDS_MASK;
+	ca = dma_map_single(lp->dmadev, skb->data, length, DMA_TO_DEVICE);
+	if (dma_mapping_error(lp->dmadev, ca))
+		goto drop_packet;
+
+	lp->tx_skb_dma[idx] = ca;
+	td->ca = ca;
+
+	chain_prev = (idx - 1) & KORINA_TDS_MASK;
+	chain_next = (idx + 1) & KORINA_TDS_MASK;
 
 	if (readl(&(lp->tx_dma_regs->dmandptr)) == 0) {
-		if (lp->tx_chain_status == desc_empty) {
+		if (lp->tx_chain_status == desc_is_empty) {
 			/* Update tail */
 			td->control = DMA_COUNT(length) |
 					DMA_DESC_COF | DMA_DESC_IOF;
 			/* Move tail */
 			lp->tx_chain_tail = chain_next;
 			/* Write to NDPTR */
-			writel(CPHYSADDR(&lp->td_ring[lp->tx_chain_head]),
-					&lp->tx_dma_regs->dmandptr);
+			writel(korina_tx_dma(lp, lp->tx_chain_head),
+			       &lp->tx_dma_regs->dmandptr);
 			/* Move head to tail */
 			lp->tx_chain_head = lp->tx_chain_tail;
 		} else {
@@ -256,18 +478,18 @@ static int korina_send_packet(struct sk_buff *skb, struct net_device *dev)
 			lp->td_ring[chain_prev].control &=
 					~DMA_DESC_COF;
 			/* Link to prev */
-			lp->td_ring[chain_prev].link =  CPHYSADDR(td);
+			lp->td_ring[chain_prev].link = korina_tx_dma(lp, idx);
 			/* Move tail */
 			lp->tx_chain_tail = chain_next;
 			/* Write to NDPTR */
-			writel(CPHYSADDR(&lp->td_ring[lp->tx_chain_head]),
-					&(lp->tx_dma_regs->dmandptr));
+			writel(korina_tx_dma(lp, lp->tx_chain_head),
+			       &lp->tx_dma_regs->dmandptr);
 			/* Move head to tail */
 			lp->tx_chain_head = lp->tx_chain_tail;
-			lp->tx_chain_status = desc_empty;
+			lp->tx_chain_status = desc_is_empty;
 		}
 	} else {
-		if (lp->tx_chain_status == desc_empty) {
+		if (lp->tx_chain_status == desc_is_empty) {
 			/* Update tail */
 			td->control = DMA_COUNT(length) |
 					DMA_DESC_COF | DMA_DESC_IOF;
@@ -280,44 +502,66 @@ static int korina_send_packet(struct sk_buff *skb, struct net_device *dev)
 					DMA_DESC_COF | DMA_DESC_IOF;
 			lp->td_ring[chain_prev].control &=
 					~DMA_DESC_COF;
-			lp->td_ring[chain_prev].link =  CPHYSADDR(td);
+			lp->td_ring[chain_prev].link = korina_tx_dma(lp, idx);
 			lp->tx_chain_tail = chain_next;
 		}
 	}
-	dma_cache_wback((u32) td, sizeof(*td));
 
 	netif_trans_update(dev);
 	spin_unlock_irqrestore(&lp->lock, flags);
 
 	return NETDEV_TX_OK;
+
+drop_packet:
+	dev->stats.tx_dropped++;
+	dev_kfree_skb_any(skb);
+	spin_unlock_irqrestore(&lp->lock, flags);
+
+	return NETDEV_TX_OK;
 }
 
-static int mdio_read(struct net_device *dev, int mii_id, int reg)
+static int korina_mdio_wait(struct korina_private *lp)
+{
+	u32 value;
+
+	return readl_poll_timeout_atomic(&lp->eth_regs->miimind,
+					 value, value & ETH_MII_IND_BSY,
+					 1, 1000);
+}
+
+static int korina_mdio_read(struct net_device *dev, int phy, int reg)
 {
 	struct korina_private *lp = netdev_priv(dev);
 	int ret;
 
-	mii_id = ((lp->rx_irq == 0x2c ? 1 : 0) << 8);
+	ret = korina_mdio_wait(lp);
+	if (ret < 0)
+		return ret;
 
-	writel(0, &lp->eth_regs->miimcfg);
-	writel(0, &lp->eth_regs->miimcmd);
-	writel(mii_id | reg, &lp->eth_regs->miimaddr);
-	writel(ETH_MII_CMD_SCN, &lp->eth_regs->miimcmd);
+	writel(phy << 8 | reg, &lp->eth_regs->miimaddr);
+	writel(1, &lp->eth_regs->miimcmd);
+
+	ret = korina_mdio_wait(lp);
+	if (ret < 0)
+		return ret;
 
-	ret = (int)(readl(&lp->eth_regs->miimrdd));
+	if (readl(&lp->eth_regs->miimind) & ETH_MII_IND_NV)
+		return -EINVAL;
+
+	ret = readl(&lp->eth_regs->miimrdd);
+	writel(0, &lp->eth_regs->miimcmd);
 	return ret;
 }
 
-static void mdio_write(struct net_device *dev, int mii_id, int reg, int val)
+static void korina_mdio_write(struct net_device *dev, int phy, int reg, int val)
 {
 	struct korina_private *lp = netdev_priv(dev);
 
-	mii_id = ((lp->rx_irq == 0x2c ? 1 : 0) << 8);
+	if (korina_mdio_wait(lp))
+		return;
 
-	writel(0, &lp->eth_regs->miimcfg);
-	writel(1, &lp->eth_regs->miimcmd);
-	writel(mii_id | reg, &lp->eth_regs->miimaddr);
-	writel(ETH_MII_CMD_SCN, &lp->eth_regs->miimcmd);
+	writel(0, &lp->eth_regs->miimcmd);
+	writel(phy << 8 | reg, &lp->eth_regs->miimaddr);
 	writel(val, &lp->eth_regs->miimwtd);
 }
 
@@ -353,12 +597,10 @@ static int korina_rx(struct net_device *dev, int limit)
 	struct korina_private *lp = netdev_priv(dev);
 	struct dma_desc *rd = &lp->rd_ring[lp->rx_next_done];
 	struct sk_buff *skb, *skb_new;
-	u8 *pkt_buf;
 	u32 devcs, pkt_len, dmas;
+	dma_addr_t ca;
 	int count;
 
-	dma_cache_inv((u32)rd, sizeof(*rd));
-
 	for (count = 0; count < limit; count++) {
 		skb = lp->rx_skb[lp->rx_next_done];
 		skb_new = NULL;
@@ -392,20 +634,22 @@ static int korina_rx(struct net_device *dev, int limit)
 			goto next;
 		}
 
-		pkt_len = RCVPKT_LENGTH(devcs);
-
-		/* must be the (first and) last
-		 * descriptor then */
-		pkt_buf = (u8 *)lp->rx_skb[lp->rx_next_done]->data;
-
-		/* invalidate the cache */
-		dma_cache_inv((unsigned long)pkt_buf, pkt_len - 4);
-
 		/* Malloc up new buffer. */
 		skb_new = netdev_alloc_skb_ip_align(dev, KORINA_RBSIZE);
-
 		if (!skb_new)
 			break;
+
+		ca = dma_map_single(lp->dmadev, skb_new->data, KORINA_RBSIZE,
+				    DMA_FROM_DEVICE);
+		if (dma_mapping_error(lp->dmadev, ca)) {
+			dev_kfree_skb_any(skb_new);
+			break;
+		}
+
+		pkt_len = RCVPKT_LENGTH(devcs);
+		dma_unmap_single(lp->dmadev, lp->rx_skb_dma[lp->rx_next_done],
+				 pkt_len, DMA_FROM_DEVICE);
+
 		/* Do not count the CRC */
 		skb_put(skb, pkt_len - 4);
 		skb->protocol = eth_type_trans(skb, dev);
@@ -420,15 +664,13 @@ static int korina_rx(struct net_device *dev, int limit)
 			dev->stats.multicast++;
 
 		lp->rx_skb[lp->rx_next_done] = skb_new;
+		lp->rx_skb_dma[lp->rx_next_done] = ca;
 
 next:
 		rd->devcs = 0;
 
 		/* Restore descriptor's curr_addr */
-		if (skb_new)
-			rd->ca = CPHYSADDR(skb_new->data);
-		else
-			rd->ca = CPHYSADDR(skb->data);
+		rd->ca = lp->rx_skb_dma[lp->rx_next_done];
 
 		rd->control = DMA_COUNT(KORINA_RBSIZE) |
 			DMA_DESC_COD | DMA_DESC_IOD;
@@ -437,23 +679,21 @@ next:
 			~DMA_DESC_COD;
 
 		lp->rx_next_done = (lp->rx_next_done + 1) & KORINA_RDS_MASK;
-		dma_cache_wback((u32)rd, sizeof(*rd));
 		rd = &lp->rd_ring[lp->rx_next_done];
-		writel(~DMA_STAT_DONE, &lp->rx_dma_regs->dmas);
+		writel((u32)~DMA_STAT_DONE, &lp->rx_dma_regs->dmas);
 	}
 
 	dmas = readl(&lp->rx_dma_regs->dmas);
 
 	if (dmas & DMA_STAT_HALT) {
-		writel(~(DMA_STAT_HALT | DMA_STAT_ERR),
-				&lp->rx_dma_regs->dmas);
+		writel((u32)~(DMA_STAT_HALT | DMA_STAT_ERR),
+		       &lp->rx_dma_regs->dmas);
 
 		lp->dma_halt_cnt++;
 		rd->devcs = 0;
-		skb = lp->rx_skb[lp->rx_next_done];
-		rd->ca = CPHYSADDR(skb->data);
-		dma_cache_wback((u32)rd, sizeof(*rd));
-		korina_chain_rx(lp, rd);
+		rd->ca = lp->rx_skb_dma[lp->rx_next_done];
+		writel(korina_rx_dma(lp, rd - lp->rd_ring),
+		       &lp->rx_dma_regs->dmandptr);
 	}
 
 	return count;
@@ -576,6 +816,10 @@ static void korina_tx(struct net_device *dev)
 
 		/* We must always free the original skb */
 		if (lp->tx_skb[lp->tx_next_done]) {
+			dma_unmap_single(lp->dmadev,
+					 lp->tx_skb_dma[lp->tx_next_done],
+					 lp->tx_skb[lp->tx_next_done]->len,
+					 DMA_TO_DEVICE);
 			dev_kfree_skb_any(lp->tx_skb[lp->tx_next_done]);
 			lp->tx_skb[lp->tx_next_done] = NULL;
 		}
@@ -622,9 +866,9 @@ korina_tx_dma_interrupt(int irq, void *dev_id)
 
 		if (lp->tx_chain_status == desc_filled &&
 			(readl(&(lp->tx_dma_regs->dmandptr)) == 0)) {
-			writel(CPHYSADDR(&lp->td_ring[lp->tx_chain_head]),
-				&(lp->tx_dma_regs->dmandptr));
-			lp->tx_chain_status = desc_empty;
+			writel(korina_tx_dma(lp, lp->tx_chain_head),
+			       &lp->tx_dma_regs->dmandptr);
+			lp->tx_chain_status = desc_is_empty;
 			lp->tx_chain_head = lp->tx_chain_tail;
 			netif_trans_update(dev);
 		}
@@ -643,7 +887,7 @@ static void korina_check_media(struct net_device *dev, unsigned int init_media)
 {
 	struct korina_private *lp = netdev_priv(dev);
 
-	mii_check_media(&lp->mii_if, 0, init_media);
+	mii_check_media(&lp->mii_if, 1, init_media);
 
 	if (lp->mii_if.full_duplex)
 		writel(readl(&lp->eth_regs->ethmac2) | ETH_MAC2_FD,
@@ -743,6 +987,7 @@ static int korina_alloc_ring(struct net_device *dev)
 {
 	struct korina_private *lp = netdev_priv(dev);
 	struct sk_buff *skb;
+	dma_addr_t ca;
 	int i;
 
 	/* Initialize the transmit descriptors */
@@ -754,7 +999,7 @@ static int korina_alloc_ring(struct net_device *dev)
 	}
 	lp->tx_next_done = lp->tx_chain_head = lp->tx_chain_tail =
 			lp->tx_full = lp->tx_count = 0;
-	lp->tx_chain_status = desc_empty;
+	lp->tx_chain_status = desc_is_empty;
 
 	/* Initialize the receive descriptors */
 	for (i = 0; i < KORINA_NUM_RDS; i++) {
@@ -765,19 +1010,24 @@ static int korina_alloc_ring(struct net_device *dev)
 		lp->rd_ring[i].control = DMA_DESC_IOD |
 				DMA_COUNT(KORINA_RBSIZE);
 		lp->rd_ring[i].devcs = 0;
-		lp->rd_ring[i].ca = CPHYSADDR(skb->data);
-		lp->rd_ring[i].link = CPHYSADDR(&lp->rd_ring[i+1]);
+		ca = dma_map_single(lp->dmadev, skb->data, KORINA_RBSIZE,
+				    DMA_FROM_DEVICE);
+		if (dma_mapping_error(lp->dmadev, ca))
+			return -ENOMEM;
+		lp->rd_ring[i].ca = ca;
+		lp->rx_skb_dma[i] = ca;
+		lp->rd_ring[i].link = korina_rx_dma(lp, i + 1);
 	}
 
 	/* loop back receive descriptors, so the last
 	 * descriptor points to the first one */
-	lp->rd_ring[i - 1].link = CPHYSADDR(&lp->rd_ring[0]);
+	lp->rd_ring[i - 1].link = lp->rd_dma;
 	lp->rd_ring[i - 1].control |= DMA_DESC_COD;
 
 	lp->rx_next_done  = 0;
 	lp->rx_chain_head = 0;
 	lp->rx_chain_tail = 0;
-	lp->rx_chain_status = desc_empty;
+	lp->rx_chain_status = desc_is_empty;
 
 	return 0;
 }
@@ -789,16 +1039,22 @@ static void korina_free_ring(struct net_device *dev)
 
 	for (i = 0; i < KORINA_NUM_RDS; i++) {
 		lp->rd_ring[i].control = 0;
-		if (lp->rx_skb[i])
+		if (lp->rx_skb[i]) {
+			dma_unmap_single(lp->dmadev, lp->rx_skb_dma[i],
+					 KORINA_RBSIZE, DMA_FROM_DEVICE);
 			dev_kfree_skb_any(lp->rx_skb[i]);
-		lp->rx_skb[i] = NULL;
+			lp->rx_skb[i] = NULL;
+		}
 	}
 
 	for (i = 0; i < KORINA_NUM_TDS; i++) {
 		lp->td_ring[i].control = 0;
-		if (lp->tx_skb[i])
+		if (lp->tx_skb[i]) {
+			dma_unmap_single(lp->dmadev, lp->tx_skb_dma[i],
+					 lp->tx_skb[i]->len, DMA_TO_DEVICE);
 			dev_kfree_skb_any(lp->tx_skb[i]);
-		lp->tx_skb[i] = NULL;
+			lp->tx_skb[i] = NULL;
+		}
 	}
 }
 
@@ -830,7 +1086,8 @@ static int korina_init(struct net_device *dev)
 
 	writel(0, &lp->rx_dma_regs->dmas);
 	/* Start Rx DMA */
-	korina_start_rx(lp, &lp->rd_ring[0]);
+	writel(0, &lp->rx_dma_regs->dmandptr);
+	writel(korina_rx_dma(lp, 0), &lp->rx_dma_regs->dmadptr);
 
 	writel(readl(&lp->tx_dma_regs->dmasm) &
 			~(DMA_STAT_FINI | DMA_STAT_ERR),
@@ -867,14 +1124,17 @@ static int korina_init(struct net_device *dev)
 
 	/* Management Clock Prescaler Divisor
 	 * Clock independent setting */
-	writel(((idt_cpu_freq) / MII_CLOCK + 1) & ~1,
-			&lp->eth_regs->ethmcp);
+	writel(((lp->mii_clock_freq) / MII_CLOCK + 1) & ~1,
+	       &lp->eth_regs->ethmcp);
+	writel(0, &lp->eth_regs->miimcfg);
 
 	/* don't transmit until fifo contains 48b */
 	writel(48, &lp->eth_regs->ethfifott);
 
 	writel(ETH_MAC1_RE, &lp->eth_regs->ethmac1);
 
+	korina_check_media(dev, 1);
+
 	napi_enable(&lp->napi);
 	netif_start_queue(dev);
 
@@ -1022,86 +1282,94 @@ static const struct net_device_ops korina_netdev_ops = {
 
 static int korina_probe(struct platform_device *pdev)
 {
-	struct korina_device *bif = platform_get_drvdata(pdev);
+	u8 *mac_addr = dev_get_platdata(&pdev->dev);
 	struct korina_private *lp;
 	struct net_device *dev;
-	struct resource *r;
+	struct clk *clk;
+	void __iomem *p;
 	int rc;
 
-	dev = alloc_etherdev(sizeof(struct korina_private));
+	dev = devm_alloc_etherdev(&pdev->dev, sizeof(struct korina_private));
 	if (!dev)
 		return -ENOMEM;
 
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	lp = netdev_priv(dev);
 
-	bif->dev = dev;
-	memcpy(dev->dev_addr, bif->mac, ETH_ALEN);
+	if (mac_addr)
+		ether_addr_copy(dev->dev_addr, mac_addr);
+	else if (of_get_mac_address(pdev->dev.of_node, dev->dev_addr) < 0)
+		eth_hw_addr_random(dev);
+
+	clk = devm_clk_get_optional(&pdev->dev, "mdioclk");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+	if (clk) {
+		clk_prepare_enable(clk);
+		lp->mii_clock_freq = clk_get_rate(clk);
+	} else {
+		lp->mii_clock_freq = 200000000; /* max possible input clk */
+	}
 
-	lp->rx_irq = platform_get_irq_byname(pdev, "korina_rx");
-	lp->tx_irq = platform_get_irq_byname(pdev, "korina_tx");
+	lp->rx_irq = platform_get_irq_byname(pdev, "rx");
+	lp->tx_irq = platform_get_irq_byname(pdev, "tx");
 
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "korina_regs");
-	dev->base_addr = r->start;
-	lp->eth_regs = ioremap(r->start, resource_size(r));
-	if (!lp->eth_regs) {
+	p = devm_platform_ioremap_resource_byname(pdev, "emac");
+	if (!p) {
 		printk(KERN_ERR DRV_NAME ": cannot remap registers\n");
-		rc = -ENXIO;
-		goto probe_err_out;
+		return -ENOMEM;
 	}
+	lp->eth_regs = p;
 
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "korina_dma_rx");
-	lp->rx_dma_regs = ioremap(r->start, resource_size(r));
-	if (!lp->rx_dma_regs) {
+	p = devm_platform_ioremap_resource_byname(pdev, "dma_rx");
+	if (!p) {
 		printk(KERN_ERR DRV_NAME ": cannot remap Rx DMA registers\n");
-		rc = -ENXIO;
-		goto probe_err_dma_rx;
+		return -ENOMEM;
 	}
+	lp->rx_dma_regs = p;
 
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "korina_dma_tx");
-	lp->tx_dma_regs = ioremap(r->start, resource_size(r));
-	if (!lp->tx_dma_regs) {
+	p = devm_platform_ioremap_resource_byname(pdev, "dma_tx");
+	if (!p) {
 		printk(KERN_ERR DRV_NAME ": cannot remap Tx DMA registers\n");
-		rc = -ENXIO;
-		goto probe_err_dma_tx;
-	}
-
-	lp->td_ring = kmalloc(TD_RING_SIZE + RD_RING_SIZE, GFP_KERNEL);
-	if (!lp->td_ring) {
-		rc = -ENXIO;
-		goto probe_err_td_ring;
+		return -ENOMEM;
 	}
+	lp->tx_dma_regs = p;
 
-	dma_cache_inv((unsigned long)(lp->td_ring),
-			TD_RING_SIZE + RD_RING_SIZE);
+	lp->td_ring = dmam_alloc_coherent(&pdev->dev, TD_RING_SIZE,
+					  &lp->td_dma, GFP_KERNEL);
+	if (!lp->td_ring)
+		return -ENOMEM;
 
-	/* now convert TD_RING pointer to KSEG1 */
-	lp->td_ring = (struct dma_desc *)KSEG1ADDR(lp->td_ring);
-	lp->rd_ring = &lp->td_ring[KORINA_NUM_TDS];
+	lp->rd_ring = dmam_alloc_coherent(&pdev->dev, RD_RING_SIZE,
+					  &lp->rd_dma, GFP_KERNEL);
+	if (!lp->rd_ring)
+		return -ENOMEM;
 
 	spin_lock_init(&lp->lock);
 	/* just use the rx dma irq */
 	dev->irq = lp->rx_irq;
 	lp->dev = dev;
+	lp->dmadev = &pdev->dev;
 
 	dev->netdev_ops = &korina_netdev_ops;
 	dev->ethtool_ops = &netdev_ethtool_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 	netif_napi_add(dev, &lp->napi, korina_poll, NAPI_POLL_WEIGHT);
 
-	lp->phy_addr = (((lp->rx_irq == 0x2c? 1:0) << 8) | 0x05);
 	lp->mii_if.dev = dev;
-	lp->mii_if.mdio_read = mdio_read;
-	lp->mii_if.mdio_write = mdio_write;
-	lp->mii_if.phy_id = lp->phy_addr;
+	lp->mii_if.mdio_read = korina_mdio_read;
+	lp->mii_if.mdio_write = korina_mdio_write;
+	lp->mii_if.phy_id = 1;
 	lp->mii_if.phy_id_mask = 0x1f;
 	lp->mii_if.reg_num_mask = 0x1f;
 
+	platform_set_drvdata(pdev, dev);
+
 	rc = register_netdev(dev);
 	if (rc < 0) {
 		printk(KERN_ERR DRV_NAME
 			": cannot register net device: %d\n", rc);
-		goto probe_err_register;
+		return rc;
 	}
 	timer_setup(&lp->media_check_timer, korina_poll_media, 0);
 
@@ -1109,40 +1377,33 @@ static int korina_probe(struct platform_device *pdev)
 
 	printk(KERN_INFO "%s: " DRV_NAME "-" DRV_VERSION " " DRV_RELDATE "\n",
 			dev->name);
-out:
 	return rc;
-
-probe_err_register:
-	kfree((struct dma_desc *)KSEG0ADDR(lp->td_ring));
-probe_err_td_ring:
-	iounmap(lp->tx_dma_regs);
-probe_err_dma_tx:
-	iounmap(lp->rx_dma_regs);
-probe_err_dma_rx:
-	iounmap(lp->eth_regs);
-probe_err_out:
-	free_netdev(dev);
-	goto out;
 }
 
 static int korina_remove(struct platform_device *pdev)
 {
-	struct korina_device *bif = platform_get_drvdata(pdev);
-	struct korina_private *lp = netdev_priv(bif->dev);
-
-	iounmap(lp->eth_regs);
-	iounmap(lp->rx_dma_regs);
-	iounmap(lp->tx_dma_regs);
-	kfree((struct dma_desc *)KSEG0ADDR(lp->td_ring));
+	struct net_device *dev = platform_get_drvdata(pdev);
 
-	unregister_netdev(bif->dev);
-	free_netdev(bif->dev);
+	unregister_netdev(dev);
 
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id korina_match[] = {
+	{
+		.compatible = "idt,3243x-emac",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, korina_match);
+#endif
+
 static struct platform_driver korina_driver = {
-	.driver.name = "korina",
+	.driver = {
+		.name = "korina",
+		.of_match_table = of_match_ptr(korina_match),
+	},
 	.probe = korina_probe,
 	.remove = korina_remove,
 };