diff mbox series

[net-next,2/2,v9] net: ethernet: Add a driver for Gemini gigabit ethernet

Message ID 20171216193911.6938-2-linus.walleij@linaro.org
State Superseded
Headers show
Series None | expand

Commit Message

Linus Walleij Dec. 16, 2017, 7:39 p.m. UTC
The Gemini ethernet has been around for years as an out-of-tree
patch used with the NAS boxen and routers built on StorLink
SL3512 and SL3516, later Storm Semiconductor, later Cortina
Systems. These ASICs are still being deployed and brand new
off-the-shelf systems using it can easily be acquired.

The full name of the IP block is "Net Engine and Gigabit
Ethernet MAC" commonly just called "GMAC".

The hardware block contains a common TCP Offload Enginer (TOE)
that can be used by both MACs. The current driver does not use
it.

Cc: Tobias Waldvogel <tobias.waldvogel@gmail.com>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

---
Changes from v8:
- Remove dependency guards in Kconfig to get a wider compile
  coverage for the driver to detect broken APIs etc.

Changes from v7:
- Dropped all the typedefs and use structs and unions
  directly in the code.
- Pile all local variables in inverse christmas-tree descending
  order. Rewrite code and move assignments to make this strict.
- Cut the uppercase type names in the process.
- Drop a whole bunch of unused unions and types. If we want to
  unionize these registers when we add functioality then do so
  later.
- Do not disallow mapping 0 however unlikely.
- Do not issue any nasty BUG_ON() for unaligned allocations, but
  fail gracefully instead.
- Update stats on linearized TX fragments even if mapping fails.
- Update RX stats on the (rare) failed SKB from NAPI frags too.
- Set up the mask correctly in the IFF_ALLMULTI RX mode case.
- Pick up the DT node name changes.
- Fix up a bunch of typing: explicit unsigned int, switch to
  u32 where we certainly deal with that.
- Drop a whole slew of pointless unlikely() markups.
- Fix some UTF-8 flunky.
- Fixed a few thousand checkpatch errors/warnings. Kept a very
  few select ones I didn't find reasonable.

Changes from v6:
- Drop all arch support code using the old board files.
- Adapted for device tree probing
- Getting all resources using devm_* accessors where applicable
- Split in parent ethernet device and two per-port devices
  that get spawn from the parent. This is necessary with
  device tree and other aspects of the PHY device model and
  device tree structure that requires a 1:1 mapping between
  a device and PHY to work properly.
- Grab clocks and reset handles as resources from the clock
  and reset subsystems infrastructure instead of open coding
  access to system devices.
- Let the pin control subsystem deal with setting up the
  multplexing and clock skew/delay settings of the RGMII
  lines.
- A separate SoC driver was created to deal with setting up
  bus arbitration and will be merged separately.
- Tested with the D-Link DNS-313 NAS box with a Realtek RTL8211B
  transciever.
- Rename and move code around to fit better with the new device
  handling with a top level device and two children.
- Order code as net vendor Cortina and adapter Gemini. We have
  confirmed with Faraday that this network device is not from
  them (which was initially suspected).
- Rebased onto v4.15-rc1

Changes from v5:
 - merge arch setup code into the patch
 - move platform data include to include/linux/platform_data/gemini_gmac.h
 - use new hw_features instead of ethtool_ops for offload setting
 - add some #ifdefs for build testing on other arches
 - a bit of cleanups

Changes from v4:
 - rebased on upcoming 2.6.38 (removal of page_to_dma() and per-txq stats)
 - removed setting last_rx and trans_start as that's handled by net core
 - changed __raw_read/writel() to read/writel()
 - added setting of AHB_WEIGHT register (didn't improve anything, I'm afraid)
 - fixed DMA unmapping bug
 - added limit of packet size for TX offload (HW checks only 13 bits of mtu_size field)
 - reduced RX_MAX_ALLOC_ORDER as it caused a lot of order 4 allocation failures
   under load
 - cleanups

Changes from v3:
 - fixed remaining tx_queue_len misuse bugs
 - bulk RX DMA page map/unmap
 - whitespace changes to make checkpatch happier (please ignore remaining
   complaints - long lines in .c and typedefs/whitespace/long lines in .h)

Changes from v2:
 - converted to page buffers and napi_gro_frags()
 - later IRQ acking and NAPI exits
 - larger rings by default
 - tx-interrupt coalescing
 - MTU changing
 - jumbo frames support
 - ringparam and coalesce settings via ethtool
 - more fixes/cleanups

Changes from v1:
 - fixed stats (now using u64_stats_sync; no-op on UP anyway)
 - pre-load mdio-gpio if built as module
 - disable TX checksum offload by default (unreliable HW)
 - convert to NAPI+GRO (netperf TCP STREAM RX test:
        before: 156mbit/s, now: 185mbit/s)

Later TODO:
 - netpoll (netconsole)
 - parse MAC address from flash settings and pass it through platform data
 - move TX completion to NAPI poll
 - implement rx copybreak
 - remove DMA API abuse on RX (large map, small unmaps)
 - better test multicast support
---
 MAINTAINERS                           |    2 +
 drivers/net/ethernet/Kconfig          |    1 +
 drivers/net/ethernet/Makefile         |    1 +
 drivers/net/ethernet/cortina/Kconfig  |   22 +
 drivers/net/ethernet/cortina/Makefile |    4 +
 drivers/net/ethernet/cortina/gemini.c | 2470 +++++++++++++++++++++++++++++++++
 drivers/net/ethernet/cortina/gemini.h |  958 +++++++++++++
 7 files changed, 3458 insertions(+)
 create mode 100644 drivers/net/ethernet/cortina/Kconfig
 create mode 100644 drivers/net/ethernet/cortina/Makefile
 create mode 100644 drivers/net/ethernet/cortina/gemini.c
 create mode 100644 drivers/net/ethernet/cortina/gemini.h

-- 
2.14.3

Comments

Linus Walleij Dec. 18, 2017, 1:57 p.m. UTC | #1
On Sat, Dec 16, 2017 at 8:39 PM, Linus Walleij <linus.walleij@linaro.org> wrote:

> The Gemini ethernet has been around for years as an out-of-tree

> patch used with the NAS boxen and routers built on StorLink

> SL3512 and SL3516, later Storm Semiconductor, later Cortina

> Systems. These ASICs are still being deployed and brand new

> off-the-shelf systems using it can easily be acquired.

>

> The full name of the IP block is "Net Engine and Gigabit

> Ethernet MAC" commonly just called "GMAC".

>

> The hardware block contains a common TCP Offload Enginer (TOE)

> that can be used by both MACs. The current driver does not use

> it.

>

> Cc: Tobias Waldvogel <tobias.waldvogel@gmail.com>

> Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>

> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

> ---

> Changes from v8:

> - Remove dependency guards in Kconfig to get a wider compile

>   coverage for the driver to detect broken APIs etc.


I guess we need to hold this off for a while, the code does
some weird stuff using the ARM-internal page DMA mapping
API.

I *think* what happens is that the driver allocates a global queue
used for RX and TX on both interfaces, then initializes that with
page pointers and gives that to the hardware to play with.

When an RX packet comes in, the RX routine needs to figure
out from the DMA (physical) address which remapped
page/address this random physical address pointer
corresponds to.

The Linux DMA API assumption is that the driver keeps track
of this mapping, not the hardware. So we need to figure out
a way to reverse-map this. Preferably quickly, and without
using any ARM-internal mapping APIs.

Yours,
Linus Walleij
Michał Mirosław Dec. 18, 2017, 2:48 p.m. UTC | #2
On Mon, Dec 18, 2017 at 02:57:37PM +0100, Linus Walleij wrote:
> On Sat, Dec 16, 2017 at 8:39 PM, Linus Walleij <linus.walleij@linaro.org> wrote:

> 

> > The Gemini ethernet has been around for years as an out-of-tree

> > patch used with the NAS boxen and routers built on StorLink

> > SL3512 and SL3516, later Storm Semiconductor, later Cortina

> > Systems. These ASICs are still being deployed and brand new

> > off-the-shelf systems using it can easily be acquired.

[...]
> > ---

> > Changes from v8:

> > - Remove dependency guards in Kconfig to get a wider compile

> >   coverage for the driver to detect broken APIs etc.

> 

> I guess we need to hold this off for a while, the code does

> some weird stuff using the ARM-internal page DMA mapping

> API.

> 

> I *think* what happens is that the driver allocates a global queue

> used for RX and TX on both interfaces, then initializes that with

> page pointers and gives that to the hardware to play with.

> 

> When an RX packet comes in, the RX routine needs to figure

> out from the DMA (physical) address which remapped

> page/address this random physical address pointer

> corresponds to.

> 

> The Linux DMA API assumption is that the driver keeps track

> of this mapping, not the hardware. So we need to figure out

> a way to reverse-map this. Preferably quickly, and without

> using any ARM-internal mapping APIs.


IIRC, the hardware copies descriptors from free queue (FREEQ)
to RX queues. FREEQ is shared among the two ethernet ports.

This platform is CPU bound, so every additional lookup will
hit performance here. In my version I had an #ifdef for
COMPILE_TEST that replaced ARM-specific calls with stubs.
Since the driver is not expected to work on other platforms,
this seemed like the best workaround to make it compile
on other arches.

Best Regards,
Michał Mirosław
Russell King (Oracle) Dec. 18, 2017, 2:54 p.m. UTC | #3
On Mon, Dec 18, 2017 at 03:48:17PM +0100, Michał Mirosław wrote:
> On Mon, Dec 18, 2017 at 02:57:37PM +0100, Linus Walleij wrote:

> > On Sat, Dec 16, 2017 at 8:39 PM, Linus Walleij <linus.walleij@linaro.org> wrote:

> > 

> > > The Gemini ethernet has been around for years as an out-of-tree

> > > patch used with the NAS boxen and routers built on StorLink

> > > SL3512 and SL3516, later Storm Semiconductor, later Cortina

> > > Systems. These ASICs are still being deployed and brand new

> > > off-the-shelf systems using it can easily be acquired.

> [...]

> > > ---

> > > Changes from v8:

> > > - Remove dependency guards in Kconfig to get a wider compile

> > >   coverage for the driver to detect broken APIs etc.

> > 

> > I guess we need to hold this off for a while, the code does

> > some weird stuff using the ARM-internal page DMA mapping

> > API.

> > 

> > I *think* what happens is that the driver allocates a global queue

> > used for RX and TX on both interfaces, then initializes that with

> > page pointers and gives that to the hardware to play with.

> > 

> > When an RX packet comes in, the RX routine needs to figure

> > out from the DMA (physical) address which remapped

> > page/address this random physical address pointer

> > corresponds to.

> > 

> > The Linux DMA API assumption is that the driver keeps track

> > of this mapping, not the hardware. So we need to figure out

> > a way to reverse-map this. Preferably quickly, and without

> > using any ARM-internal mapping APIs.

> 

> IIRC, the hardware copies descriptors from free queue (FREEQ)

> to RX queues. FREEQ is shared among the two ethernet ports.

> 

> This platform is CPU bound, so every additional lookup will

> hit performance here. In my version I had an #ifdef for

> COMPILE_TEST that replaced ARM-specific calls with stubs.

> Since the driver is not expected to work on other platforms,

> this seemed like the best workaround to make it compile

> on other arches.


Really.  No.  Stop going beneath the covers and using ARM private
implementation APIs in drivers.

Take that as a big NAK to that.

(I don't seem have the patch in question here to look at though.)

-- 
RMK's Patch system: http://www.armlinux.org.uk/developer/patches/
FTTC broadband for 0.8mile line in suburbia: sync at 8.8Mbps down 630kbps up
According to speedtest.net: 8.21Mbps down 510kbps up
Linus Walleij Dec. 18, 2017, 8:55 p.m. UTC | #4
On Mon, Dec 18, 2017 at 3:54 PM, Russell King - ARM Linux
<linux@armlinux.org.uk> wrote:
> On Mon, Dec 18, 2017 at 03:48:17PM +0100, Michał Mirosław wrote:

>> On Mon, Dec 18, 2017 at 02:57:37PM +0100, Linus Walleij wrote:

>> > On Sat, Dec 16, 2017 at 8:39 PM, Linus Walleij <linus.walleij@linaro.org> wrote:

>> >

>> > > The Gemini ethernet has been around for years as an out-of-tree

>> > > patch used with the NAS boxen and routers built on StorLink

>> > > SL3512 and SL3516, later Storm Semiconductor, later Cortina

>> > > Systems. These ASICs are still being deployed and brand new

>> > > off-the-shelf systems using it can easily be acquired.

>> [...]

>> > > ---

>> > > Changes from v8:

>> > > - Remove dependency guards in Kconfig to get a wider compile

>> > >   coverage for the driver to detect broken APIs etc.

>> >

>> > I guess we need to hold this off for a while, the code does

>> > some weird stuff using the ARM-internal page DMA mapping

>> > API.

>> >

>> > I *think* what happens is that the driver allocates a global queue

>> > used for RX and TX on both interfaces, then initializes that with

>> > page pointers and gives that to the hardware to play with.

>> >

>> > When an RX packet comes in, the RX routine needs to figure

>> > out from the DMA (physical) address which remapped

>> > page/address this random physical address pointer

>> > corresponds to.

>> >

>> > The Linux DMA API assumption is that the driver keeps track

>> > of this mapping, not the hardware. So we need to figure out

>> > a way to reverse-map this. Preferably quickly, and without

>> > using any ARM-internal mapping APIs.

>>

>> IIRC, the hardware copies descriptors from free queue (FREEQ)

>> to RX queues. FREEQ is shared among the two ethernet ports.


Seems like that to me too. I will try to refactor and break it
apart a bit.

The way freeq works is undocumented, even in the official
datasheet for CS3516 (the memory area is just "reserved"),
so the code is the only documentation of it.

>> This platform is CPU bound, so every additional lookup will

>> hit performance here. In my version I had an #ifdef for

>> COMPILE_TEST that replaced ARM-specific calls with stubs.

>> Since the driver is not expected to work on other platforms,

>> this seemed like the best workaround to make it compile

>> on other arches.

>

> Really.  No.  Stop going beneath the covers and using ARM private

> implementation APIs in drivers.

>

> Take that as a big NAK to that.


Don't worry, it won't happen. I am already thinking about better
approaches that stay with the public DMA-API.

> (I don't seem have the patch in question here to look at though.)


I'll put you on CC in future postings.

Yours,
Linus Walleij
diff mbox series

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index aa71ab52fd76..200ff7670276 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1326,8 +1326,10 @@  T:	git git://github.com/ulli-kroll/linux.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/gemini.txt
 F:	Documentation/devicetree/bindings/pinctrl/cortina,gemini-pinctrl.txt
+F:	Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt
 F:	Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt
 F:	arch/arm/mach-gemini/
+F:	drivers/net/ethernet/cortina/gemini/*
 F:	drivers/pinctrl/pinctrl-gemini.c
 F:	drivers/rtc/rtc-ftrtc010.c
 
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index c60421339a98..f02727175857 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -42,6 +42,7 @@  source "drivers/net/ethernet/cavium/Kconfig"
 source "drivers/net/ethernet/chelsio/Kconfig"
 source "drivers/net/ethernet/cirrus/Kconfig"
 source "drivers/net/ethernet/cisco/Kconfig"
+source "drivers/net/ethernet/cortina/Kconfig"
 
 config CX_ECAT
 	tristate "Beckhoff CX5020 EtherCAT master support"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 39f6273358ed..1b356f6ec87a 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -29,6 +29,7 @@  obj-$(CONFIG_NET_VENDOR_CAVIUM) += cavium/
 obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
 obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
 obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
+obj-$(CONFIG_NET_VENDOR_CORTINA) += cortina/
 obj-$(CONFIG_CX_ECAT) += ec_bhf.o
 obj-$(CONFIG_DM9000) += davicom/
 obj-$(CONFIG_DNET) += dnet.o
diff --git a/drivers/net/ethernet/cortina/Kconfig b/drivers/net/ethernet/cortina/Kconfig
new file mode 100644
index 000000000000..0df743ea51f1
--- /dev/null
+++ b/drivers/net/ethernet/cortina/Kconfig
@@ -0,0 +1,22 @@ 
+# SPDX-License-Identifier: GPL-2.0
+# Cortina ethernet devices
+
+config NET_VENDOR_CORTINA
+	bool "Cortina Gemini devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) card belonging to this class, say Y
+	  and read the Ethernet-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+if NET_VENDOR_CORTINA
+
+config GEMINI_ETHERNET
+	tristate "Gemini Gigabit Ethernet support"
+	depends on OF
+	select PHYLIB
+	select CRC32
+	---help---
+	  This driver supports StorLink SL351x (Gemini) dual Gigabit Ethernet.
+
+endif # NET_VENDOR_CORTINA
diff --git a/drivers/net/ethernet/cortina/Makefile b/drivers/net/ethernet/cortina/Makefile
new file mode 100644
index 000000000000..4e86d398a89c
--- /dev/null
+++ b/drivers/net/ethernet/cortina/Makefile
@@ -0,0 +1,4 @@ 
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for the Cortina Gemini network device drivers.
+
+obj-$(CONFIG_GEMINI_ETHERNET) += gemini.o
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
new file mode 100644
index 000000000000..b6bb2b706cf2
--- /dev/null
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -0,0 +1,2470 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/* Ethernet device driver for Cortina Systems Gemini SoC
+ * Also known as the StorLink SL3512 and SL3516 (SL351x) or Lepus
+ * Net Engine and Gigabit Ethernet MAC (GMAC)
+ * This hardware contains a TCP Offload Engine (TOE) but currently the
+ * driver does not make use of it.
+ *
+ * Authors:
+ * Linus Walleij <linus.walleij@linaro.org>
+ * Tobias Waldvogel <tobias.waldvogel@gmail.com> (OpenWRT)
+ * Michał Mirosław <mirq-linux@rere.qmqm.pl>
+ * Paulius Zaleckas <paulius.zaleckas@gmail.com>
+ * Giuseppe De Robertis <Giuseppe.DeRobertis@ba.infn.it>
+ * Gary Chen & Ch Hsu Storlink Semiconductor
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/cache.h>
+#include <linux/interrupt.h>
+#include <linux/reset.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/skbuff.h>
+#include <linux/phy.h>
+#include <linux/crc32.h>
+#include <linux/ethtool.h>
+#include <linux/tcp.h>
+#include <linux/u64_stats_sync.h>
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include "gemini.h"
+
+#define DRV_NAME		"gmac-gemini"
+#define DRV_VERSION		"1.0"
+
+#define HSIZE_8			0x00
+#define HSIZE_16		0x01
+#define HSIZE_32		0x02
+
+#define HBURST_SINGLE		0x00
+#define HBURST_INCR		0x01
+#define HBURST_INCR4		0x02
+#define HBURST_INCR8		0x03
+
+#define HPROT_DATA_CACHE	BIT(0)
+#define HPROT_PRIVILIGED	BIT(1)
+#define HPROT_BUFFERABLE	BIT(2)
+#define HPROT_CACHABLE		BIT(3)
+
+#define DEFAULT_RX_COALESCE_NSECS	0
+#define DEFAULT_GMAC_RXQ_ORDER		9
+#define DEFAULT_GMAC_TXQ_ORDER		8
+#define DEFAULT_RX_BUF_ORDER		11
+#define DEFAULT_NAPI_WEIGHT		64
+#define TX_MAX_FRAGS			16
+#define TX_QUEUE_NUM			1	/* max: 6 */
+#define RX_MAX_ALLOC_ORDER		2
+
+#define GMAC0_IRQ0_2 (GMAC0_TXDERR_INT_BIT | GMAC0_TXPERR_INT_BIT | \
+		      GMAC0_RXDERR_INT_BIT | GMAC0_RXPERR_INT_BIT)
+#define GMAC0_IRQ0_TXQ0_INTS (GMAC0_SWTQ00_EOF_INT_BIT | \
+			      GMAC0_SWTQ00_FIN_INT_BIT)
+#define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT)
+
+#define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \
+		NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \
+		NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
+
+struct gmac_txq {
+	struct gmac_txdesc *ring;
+	struct sk_buff	**skb;
+	unsigned int	cptr;
+	unsigned int	noirq_packets;
+};
+
+struct gemini_ethernet;
+
+struct gemini_ethernet_port {
+	u8 id; /* 0 or 1 */
+
+	struct gemini_ethernet *geth;
+	struct net_device *netdev;
+	struct device *dev;
+	void __iomem *dma_base;
+	void __iomem *gmac_base;
+	struct clk *pclk;
+	struct reset_control *reset;
+	int irq;
+	__le32 mac_addr[3];
+
+	void __iomem		*rxq_rwptr;
+	struct gmac_rxdesc	*rxq_ring;
+	unsigned int		rxq_order;
+
+	struct napi_struct	napi;
+	struct hrtimer		rx_coalesce_timer;
+	unsigned int		rx_coalesce_nsecs;
+	unsigned int		freeq_refill;
+	struct gmac_txq		txq[TX_QUEUE_NUM];
+	unsigned int		txq_order;
+	unsigned int		irq_every_tx_packets;
+
+	dma_addr_t		rxq_dma_base;
+	dma_addr_t		txq_dma_base;
+
+	unsigned int		msg_enable;
+	spinlock_t		config_lock; /* Locks config register */
+
+	struct u64_stats_sync	tx_stats_syncp;
+	struct u64_stats_sync	rx_stats_syncp;
+	struct u64_stats_sync	ir_stats_syncp;
+
+	struct rtnl_link_stats64 stats;
+	u64			hw_stats[RX_STATS_NUM];
+	u64			rx_stats[RX_STATUS_NUM];
+	u64			rx_csum_stats[RX_CHKSUM_NUM];
+	u64			rx_napi_exits;
+	u64			tx_frag_stats[TX_MAX_FRAGS];
+	u64			tx_frags_linearized;
+	u64			tx_hw_csummed;
+};
+
+struct gemini_ethernet {
+	struct device *dev;
+	void __iomem *base;
+	struct gemini_ethernet_port *port0;
+	struct gemini_ethernet_port *port1;
+
+	spinlock_t	irq_lock; /* Locks IRQ-related registers */
+	unsigned int	freeq_order;
+	unsigned int	freeq_frag_order;
+	struct gmac_rxdesc *freeq_ring;
+	dma_addr_t	freeq_dma_base;
+	struct page	**freeq_page_tab;
+	spinlock_t	freeq_lock; /* Locks queue from reentrance */
+};
+
+#define GMAC_STATS_NUM	( \
+	RX_STATS_NUM + RX_STATUS_NUM + RX_CHKSUM_NUM + 1 + \
+	TX_MAX_FRAGS + 2)
+
+static const char gmac_stats_strings[GMAC_STATS_NUM][ETH_GSTRING_LEN] = {
+	"GMAC_IN_DISCARDS",
+	"GMAC_IN_ERRORS",
+	"GMAC_IN_MCAST",
+	"GMAC_IN_BCAST",
+	"GMAC_IN_MAC1",
+	"GMAC_IN_MAC2",
+	"RX_STATUS_GOOD_FRAME",
+	"RX_STATUS_TOO_LONG_GOOD_CRC",
+	"RX_STATUS_RUNT_FRAME",
+	"RX_STATUS_SFD_NOT_FOUND",
+	"RX_STATUS_CRC_ERROR",
+	"RX_STATUS_TOO_LONG_BAD_CRC",
+	"RX_STATUS_ALIGNMENT_ERROR",
+	"RX_STATUS_TOO_LONG_BAD_ALIGN",
+	"RX_STATUS_RX_ERR",
+	"RX_STATUS_DA_FILTERED",
+	"RX_STATUS_BUFFER_FULL",
+	"RX_STATUS_11",
+	"RX_STATUS_12",
+	"RX_STATUS_13",
+	"RX_STATUS_14",
+	"RX_STATUS_15",
+	"RX_CHKSUM_IP_UDP_TCP_OK",
+	"RX_CHKSUM_IP_OK_ONLY",
+	"RX_CHKSUM_NONE",
+	"RX_CHKSUM_3",
+	"RX_CHKSUM_IP_ERR_UNKNOWN",
+	"RX_CHKSUM_IP_ERR",
+	"RX_CHKSUM_TCP_UDP_ERR",
+	"RX_CHKSUM_7",
+	"RX_NAPI_EXITS",
+	"TX_FRAGS[1]",
+	"TX_FRAGS[2]",
+	"TX_FRAGS[3]",
+	"TX_FRAGS[4]",
+	"TX_FRAGS[5]",
+	"TX_FRAGS[6]",
+	"TX_FRAGS[7]",
+	"TX_FRAGS[8]",
+	"TX_FRAGS[9]",
+	"TX_FRAGS[10]",
+	"TX_FRAGS[11]",
+	"TX_FRAGS[12]",
+	"TX_FRAGS[13]",
+	"TX_FRAGS[14]",
+	"TX_FRAGS[15]",
+	"TX_FRAGS[16+]",
+	"TX_FRAGS_LINEARIZED",
+	"TX_HW_CSUMMED",
+};
+
+static void gmac_dump_dma_state(struct net_device *netdev);
+
+static void gmac_update_config0_reg(struct net_device *netdev,
+				    u32 val, u32 vmask)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&port->config_lock, flags);
+
+	reg = readl(port->gmac_base + GMAC_CONFIG0);
+	reg = (reg & ~vmask) | val;
+	writel(reg, port->gmac_base + GMAC_CONFIG0);
+
+	spin_unlock_irqrestore(&port->config_lock, flags);
+}
+
+static void gmac_enable_tx_rx(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&port->config_lock, flags);
+
+	reg = readl(port->gmac_base + GMAC_CONFIG0);
+	reg &= ~CONFIG0_TX_RX_DISABLE;
+	writel(reg, port->gmac_base + GMAC_CONFIG0);
+
+	spin_unlock_irqrestore(&port->config_lock, flags);
+}
+
+static void gmac_disable_tx_rx(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&port->config_lock, flags);
+
+	val = readl(port->gmac_base + GMAC_CONFIG0);
+	val |= CONFIG0_TX_RX_DISABLE;
+	writel(val, port->gmac_base + GMAC_CONFIG0);
+
+	spin_unlock_irqrestore(&port->config_lock, flags);
+
+	mdelay(10);	/* let GMAC consume packet */
+}
+
+static void gmac_set_flow_control(struct net_device *netdev, bool tx, bool rx)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&port->config_lock, flags);
+
+	val = readl(port->gmac_base + GMAC_CONFIG0);
+	val &= ~CONFIG0_FLOW_CTL;
+	if (tx)
+		val |= CONFIG0_FLOW_TX;
+	if (rx)
+		val |= CONFIG0_FLOW_RX;
+	writel(val, port->gmac_base + GMAC_CONFIG0);
+
+	spin_unlock_irqrestore(&port->config_lock, flags);
+}
+
+static void gmac_speed_set(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
+	union gmac_status status, old_status;
+	int pause_tx = 0;
+	int pause_rx = 0;
+
+	status.bits32 = readl(port->gmac_base + GMAC_STATUS);
+	old_status.bits32 = status.bits32;
+	status.bits.link = phydev->link;
+	status.bits.duplex = phydev->duplex;
+
+	switch (phydev->speed) {
+	case 1000:
+		status.bits.speed = GMAC_SPEED_1000;
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			status.bits.mii_rmii = GMAC_PHY_RGMII_1000;
+		netdev_info(netdev, "connect to RGMII @ 1Gbit\n");
+		break;
+	case 100:
+		status.bits.speed = GMAC_SPEED_100;
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
+		netdev_info(netdev, "connect to RGMII @ 100 Mbit\n");
+		break;
+	case 10:
+		status.bits.speed = GMAC_SPEED_10;
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
+		netdev_info(netdev, "connect to RGMII @ 10 Mbit\n");
+		break;
+	default:
+		netdev_warn(netdev, "Not supported PHY speed (%d)\n",
+			    phydev->speed);
+	}
+
+	if (phydev->duplex == DUPLEX_FULL) {
+		u16 lcladv = phy_read(phydev, MII_ADVERTISE);
+		u16 rmtadv = phy_read(phydev, MII_LPA);
+		u8 cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv);
+
+		if (cap & FLOW_CTRL_RX)
+			pause_rx = 1;
+		if (cap & FLOW_CTRL_TX)
+			pause_tx = 1;
+	}
+
+	gmac_set_flow_control(netdev, pause_tx, pause_rx);
+
+	if (old_status.bits32 == status.bits32)
+		return;
+
+	if (netif_msg_link(port)) {
+		phy_print_status(phydev);
+		netdev_info(netdev, "link flow control: %s\n",
+			    phydev->pause
+			    ? (phydev->asym_pause ? "tx" : "both")
+			    : (phydev->asym_pause ? "rx" : "none")
+		);
+	}
+
+	gmac_disable_tx_rx(netdev);
+	writel(status.bits32, port->gmac_base + GMAC_STATUS);
+	gmac_enable_tx_rx(netdev);
+}
+
+static int gmac_setup_phy(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	union gmac_status status = { .bits32 = 0 };
+	struct device *dev = port->dev;
+	struct phy_device *phy;
+
+	phy = of_phy_get_and_connect(netdev,
+				     dev->of_node,
+				     gmac_speed_set);
+	if (!phy)
+		return -ENODEV;
+	netdev->phydev = phy;
+
+	netdev_info(netdev, "connected to PHY \"%s\"\n",
+		    phydev_name(phy));
+	phy_attached_print(phy, "phy_id=0x%.8lx, phy_mode=%s\n",
+			   (unsigned long)phy->phy_id,
+			   phy_modes(phy->interface));
+
+	phy->supported &= PHY_GBIT_FEATURES;
+	phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause;
+	phy->advertising = phy->supported;
+
+	/* set PHY interface type */
+	switch (phy->interface) {
+	case PHY_INTERFACE_MODE_MII:
+		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		status.bits.mii_rmii = GMAC_PHY_MII;
+		netdev_info(netdev, "connect to MII\n");
+		break;
+	case PHY_INTERFACE_MODE_GMII:
+		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		status.bits.mii_rmii = GMAC_PHY_GMII;
+		netdev_info(netdev, "connect to GMII\n");
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+		dev_info(dev, "set GMAC0 and GMAC1 to MII/RGMII mode\n");
+		status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
+		netdev_info(netdev, "connect to RGMII\n");
+		break;
+	default:
+		netdev_err(netdev, "Unsupported MII interface\n");
+		phy_disconnect(phy);
+		netdev->phydev = NULL;
+		return -EINVAL;
+	}
+	writel(status.bits32, port->gmac_base + GMAC_STATUS);
+
+	return 0;
+}
+
+static int gmac_pick_rx_max_len(int max_l3_len)
+{
+	/* index = CONFIG_MAXLEN_XXX values */
+	static const int max_len[8] = {
+		1536, 1518, 1522, 1542,
+		9212, 10236, 1518, 1518
+	};
+	int i, n = 5;
+
+	max_l3_len += ETH_HLEN + VLAN_HLEN;
+
+	if (max_l3_len > max_len[n])
+		return -1;
+
+	for (i = 0; i < 5; i++) {
+		if (max_len[i] >= max_l3_len && max_len[i] < max_len[n])
+			n = i;
+	}
+
+	return n;
+}
+
+static int gmac_init(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	union gmac_config0 config0 = { .bits = {
+		.dis_tx = 1,
+		.dis_rx = 1,
+		.ipv4_rx_chksum = 1,
+		.ipv6_rx_chksum = 1,
+		.rx_err_detect = 1,
+		.rgmm_edge = 1,
+		.port0_chk_hwq = 1,
+		.port1_chk_hwq = 1,
+		.port0_chk_toeq = 1,
+		.port1_chk_toeq = 1,
+		.port0_chk_classq = 1,
+		.port1_chk_classq = 1,
+	} };
+	union gmac_ahb_weight ahb_weight = { .bits = {
+		.rx_weight = 1,
+		.tx_weight = 1,
+		.hash_weight = 1,
+		.pre_req = 0x1f,
+		.tq_dv_threshold = 0,
+	} };
+	union gmac_tx_wcr0 hw_weigh = { .bits = {
+		.hw_tq3 = 1,
+		.hw_tq2 = 1,
+		.hw_tq1 = 1,
+		.hw_tq0 = 1,
+	} };
+	union gmac_tx_wcr1 sw_weigh = { .bits = {
+		.sw_tq5 = 1,
+		.sw_tq4 = 1,
+		.sw_tq3 = 1,
+		.sw_tq2 = 1,
+		.sw_tq1 = 1,
+		.sw_tq0 = 1,
+	} };
+	union gmac_config1 config1 = { .bits = {
+		.set_threshold = 16,
+		.rel_threshold = 24,
+	} };
+	union gmac_config2 config2 = { .bits = {
+		.set_threshold = 16,
+		.rel_threshold = 32,
+	} };
+	union gmac_config3 config3 = { .bits = {
+		.set_threshold = 0,
+		.rel_threshold = 0,
+	} };
+	u32 val;
+
+	config0.bits.max_len = gmac_pick_rx_max_len(netdev->mtu);
+
+	val = readl(port->gmac_base + GMAC_CONFIG0);
+	config0.bits.reserved = ((union gmac_config0)val).bits.reserved;
+	writel(config0.bits32, port->gmac_base + GMAC_CONFIG0);
+	writel(config1.bits32, port->gmac_base + GMAC_CONFIG1);
+	writel(config2.bits32, port->gmac_base + GMAC_CONFIG2);
+	writel(config3.bits32, port->gmac_base + GMAC_CONFIG3);
+
+	val = readl(port->dma_base + GMAC_AHB_WEIGHT_REG);
+	writel(ahb_weight.bits32, port->dma_base + GMAC_AHB_WEIGHT_REG);
+
+	writel(hw_weigh.bits32,
+	       port->dma_base + GMAC_TX_WEIGHTING_CTRL_0_REG);
+	writel(sw_weigh.bits32,
+	       port->dma_base + GMAC_TX_WEIGHTING_CTRL_1_REG);
+
+	port->rxq_order = DEFAULT_GMAC_RXQ_ORDER;
+	port->txq_order = DEFAULT_GMAC_TXQ_ORDER;
+	port->rx_coalesce_nsecs = DEFAULT_RX_COALESCE_NSECS;
+
+	/* Mark every quarter of the queue a packet for interrupt
+	 * in order to be able to wake up the queue if it was stopped
+	 */
+	port->irq_every_tx_packets = 1 << (port->txq_order - 2);
+
+	return 0;
+}
+
+static void gmac_uninit(struct net_device *netdev)
+{
+	if (netdev->phydev)
+		phy_disconnect(netdev->phydev);
+}
+
+static int gmac_setup_txqs(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int n_txq = netdev->num_tx_queues;
+	struct gemini_ethernet *geth = port->geth;
+	size_t entries = 1 << port->txq_order;
+	struct gmac_txq *txq = port->txq;
+	struct gmac_txdesc *desc_ring;
+	size_t len = n_txq * entries;
+	struct sk_buff **skb_tab;
+	void __iomem *rwptr_reg;
+	unsigned int r;
+	int i;
+
+	rwptr_reg = port->dma_base + GMAC_SW_TX_QUEUE0_PTR_REG;
+
+	skb_tab = kcalloc(len, sizeof(*skb_tab), GFP_KERNEL);
+	if (!skb_tab)
+		return -ENOMEM;
+
+	desc_ring = dma_alloc_coherent(geth->dev, len * sizeof(*desc_ring),
+				       &port->txq_dma_base, GFP_KERNEL);
+
+	if (!desc_ring) {
+		kfree(skb_tab);
+		return -ENOMEM;
+	}
+
+	if (port->txq_dma_base & ~DMA_Q_BASE_MASK) {
+		dev_warn(geth->dev, "TX queue base it not aligned\n");
+		return -ENOMEM;
+	}
+
+	writel(port->txq_dma_base | port->txq_order,
+	       port->dma_base + GMAC_SW_TX_QUEUE_BASE_REG);
+
+	for (i = 0; i < n_txq; i++) {
+		txq->ring = desc_ring;
+		txq->skb = skb_tab;
+		txq->noirq_packets = 0;
+
+		r = readw(rwptr_reg);
+		rwptr_reg += 2;
+		writew(r, rwptr_reg);
+		rwptr_reg += 2;
+		txq->cptr = r;
+
+		txq++;
+		desc_ring += entries;
+		skb_tab += entries;
+	}
+
+	return 0;
+}
+
+static void gmac_clean_txq(struct net_device *netdev, struct gmac_txq *txq,
+			   unsigned int r)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int m = (1 << port->txq_order) - 1;
+	struct gemini_ethernet *geth = port->geth;
+	unsigned int c = txq->cptr;
+	union gmac_txdesc_0 word0;
+	union gmac_txdesc_1 word1;
+	unsigned int hwchksum = 0;
+	unsigned long bytes = 0;
+	struct gmac_txdesc *txd;
+	unsigned short nfrags;
+	unsigned int errs = 0;
+	unsigned int pkts = 0;
+	unsigned int word3;
+	dma_addr_t mapping;
+
+	if (c == r)
+		return;
+
+	while (c != r) {
+		txd = txq->ring + c;
+		word0 = txd->word0;
+		word1 = txd->word1;
+		mapping = txd->word2.buf_adr;
+		word3 = txd->word3.bits32;
+
+		dma_unmap_single(geth->dev, mapping,
+				 word0.bits.buffer_size, DMA_TO_DEVICE);
+
+		if (word3 & EOF_BIT)
+			dev_kfree_skb(txq->skb[c]);
+
+		c++;
+		c &= m;
+
+		if (!(word3 & SOF_BIT))
+			continue;
+
+		if (!word0.bits.status_tx_ok) {
+			errs++;
+			continue;
+		}
+
+		pkts++;
+		bytes += txd->word1.bits.byte_count;
+
+		if (word1.bits32 & TSS_CHECKUM_ENABLE)
+			hwchksum++;
+
+		nfrags = word0.bits.desc_count - 1;
+		if (nfrags) {
+			if (nfrags >= TX_MAX_FRAGS)
+				nfrags = TX_MAX_FRAGS - 1;
+
+			u64_stats_update_begin(&port->tx_stats_syncp);
+			port->tx_frag_stats[nfrags]++;
+			u64_stats_update_end(&port->ir_stats_syncp);
+		}
+	}
+
+	u64_stats_update_begin(&port->ir_stats_syncp);
+	port->stats.tx_errors += errs;
+	port->stats.tx_packets += pkts;
+	port->stats.tx_bytes += bytes;
+	port->tx_hw_csummed += hwchksum;
+	u64_stats_update_end(&port->ir_stats_syncp);
+
+	txq->cptr = c;
+}
+
+static void gmac_cleanup_txqs(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int n_txq = netdev->num_tx_queues;
+	struct gemini_ethernet *geth = port->geth;
+	void __iomem *rwptr_reg;
+	unsigned int r, i;
+
+	rwptr_reg = port->dma_base + GMAC_SW_TX_QUEUE0_PTR_REG;
+
+	for (i = 0; i < n_txq; i++) {
+		r = readw(rwptr_reg);
+		rwptr_reg += 2;
+		writew(r, rwptr_reg);
+		rwptr_reg += 2;
+
+		gmac_clean_txq(netdev, port->txq + i, r);
+	}
+	writel(0, port->dma_base + GMAC_SW_TX_QUEUE_BASE_REG);
+
+	kfree(port->txq->skb);
+	dma_free_coherent(geth->dev,
+			  n_txq * sizeof(*port->txq->ring) << port->txq_order,
+			  port->txq->ring, port->txq_dma_base);
+}
+
+static int gmac_setup_rxq(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	struct nontoe_qhdr __iomem *qhdr;
+
+	qhdr = geth->base + TOE_DEFAULT_Q_HDR_BASE(netdev->dev_id);
+	port->rxq_rwptr = &qhdr->word1;
+
+	port->rxq_ring = dma_alloc_coherent(geth->dev,
+				sizeof(*port->rxq_ring) << port->rxq_order,
+				&port->rxq_dma_base, GFP_KERNEL);
+	if (!port->rxq_ring)
+		return -ENOMEM;
+	if (port->rxq_dma_base & ~NONTOE_QHDR0_BASE_MASK) {
+		dev_warn(geth->dev, "RX queue base it not aligned\n");
+		return -ENOMEM;
+	}
+
+	writel(port->rxq_dma_base | port->rxq_order, &qhdr->word0);
+	writel(0, port->rxq_rwptr);
+	return 0;
+}
+
+static void gmac_cleanup_rxq(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	struct gmac_rxdesc *rxd = port->rxq_ring;
+	struct nontoe_qhdr __iomem *qhdr;
+	void __iomem *dma_reg;
+	void __iomem *ptr_reg;
+	dma_addr_t mapping;
+	union dma_rwptr rw;
+	unsigned int r, w;
+	struct page *page;
+
+	qhdr = geth->base +
+		TOE_DEFAULT_Q_HDR_BASE(netdev->dev_id);
+	dma_reg = &qhdr->word0;
+	ptr_reg = &qhdr->word1;
+
+	rw.bits32 = readl(ptr_reg);
+	r = rw.bits.rptr;
+	w = rw.bits.wptr;
+	writew(r, ptr_reg + 2);
+
+	writel(0, dma_reg);
+
+	while (r != w) {
+		mapping = rxd[r].word2.buf_adr;
+		r++;
+		r &= ((1 << port->rxq_order) - 1);
+
+		if (!mapping)
+			continue;
+
+		page = pfn_to_page(dma_to_pfn(geth->dev, mapping));
+		put_page(page);
+	}
+
+	dma_free_coherent(geth->dev, sizeof(*port->rxq_ring) << port->rxq_order,
+			  port->rxq_ring, port->rxq_dma_base);
+}
+
+static struct page *geth_freeq_alloc_map_page(struct gemini_ethernet *geth,
+					      int pn)
+{
+	unsigned int fpp_order = PAGE_SHIFT - geth->freeq_frag_order;
+	unsigned int frag_len = 1 << geth->freeq_frag_order;
+	struct gmac_rxdesc *freeq_entry;
+	dma_addr_t mapping;
+	struct page *page;
+	int i;
+
+	page = alloc_page(GFP_ATOMIC);
+	if (!page)
+		return NULL;
+
+	mapping = dma_map_single(geth->dev, page_address(page),
+				 PAGE_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(geth->dev, mapping)) {
+		put_page(page);
+		return NULL;
+	}
+
+	freeq_entry = geth->freeq_ring + (pn << fpp_order);
+	for (i = (1 << fpp_order); i > 0; i--) {
+		freeq_entry->word2.buf_adr = mapping;
+		freeq_entry++;
+		mapping += frag_len;
+	}
+
+	if (geth->freeq_page_tab[pn]) {
+		mapping = geth->freeq_ring[pn << fpp_order].word2.buf_adr;
+		dma_unmap_single(geth->dev, mapping, frag_len, DMA_FROM_DEVICE);
+		put_page(geth->freeq_page_tab[pn]);
+	}
+
+	geth->freeq_page_tab[pn] = page;
+	return page;
+}
+
+static unsigned int geth_fill_freeq(struct gemini_ethernet *geth, int reset)
+{
+	unsigned int fpp_order = PAGE_SHIFT - geth->freeq_frag_order;
+	unsigned int count = 0;
+	unsigned int pn, epn;
+	unsigned long flags;
+	union dma_rwptr rw;
+	struct page *page;
+	unsigned int m_pn;
+
+	/* Mask for page */
+	m_pn = (1 << (geth->freeq_order - fpp_order)) - 1;
+
+	spin_lock_irqsave(&geth->freeq_lock, flags);
+
+	rw.bits32 = readl(geth->base + GLOBAL_SWFQ_RWPTR_REG);
+	pn = (reset ? rw.bits.rptr : rw.bits.wptr) >> fpp_order;
+	epn = (rw.bits.rptr >> fpp_order) - 1;
+	epn &= m_pn;
+
+	while (pn != epn) {
+		page = geth->freeq_page_tab[pn];
+
+		if (page_ref_count(page) > 1) {
+			unsigned int fl = (pn - epn) & m_pn;
+
+			if (fl > 64 >> fpp_order)
+				break;
+
+			page = geth_freeq_alloc_map_page(geth, pn);
+			if (!page)
+				break;
+		}
+
+		page_ref_add(page, 1 << fpp_order);
+		count += 1 << fpp_order;
+		pn++;
+		pn &= m_pn;
+	}
+
+	writew(pn << fpp_order, geth->base + GLOBAL_SWFQ_RWPTR_REG + 2);
+
+	spin_unlock_irqrestore(&geth->freeq_lock, flags);
+	return count;
+}
+
+static int geth_setup_freeq(struct gemini_ethernet *geth)
+{
+	unsigned int fpp_order = PAGE_SHIFT - geth->freeq_frag_order;
+	unsigned int frag_len = 1 << geth->freeq_frag_order;
+	unsigned int len = 1 << geth->freeq_order;
+	unsigned int pages = len >> fpp_order;
+	union queue_threshold qt;
+	union dma_skb_size skbsz;
+	unsigned int filled;
+	dma_addr_t mapping;
+	unsigned int pn;
+
+	geth->freeq_ring = dma_alloc_coherent(geth->dev,
+		sizeof(*geth->freeq_ring) << geth->freeq_order,
+		&geth->freeq_dma_base, GFP_KERNEL);
+	if (!geth->freeq_ring)
+		return -ENOMEM;
+	if (geth->freeq_dma_base & ~DMA_Q_BASE_MASK) {
+		dev_warn(geth->dev, "queue ring base it not aligned\n");
+		goto err_freeq;
+	}
+
+	geth->freeq_page_tab = kzalloc(pages * sizeof(*geth->freeq_page_tab),
+				       GFP_KERNEL);
+	if (!geth->freeq_page_tab)
+		goto err_freeq;
+
+	dev_dbg(geth->dev, "allocate %d pages for queue\n", pages);
+	for (pn = 0; pn < pages; pn++)
+		if (!geth_freeq_alloc_map_page(geth, pn))
+			goto err_freeq_alloc;
+
+	filled = geth_fill_freeq(geth, 1);
+	if (!filled)
+		goto err_freeq_alloc;
+
+	qt.bits32 = readl(geth->base + GLOBAL_QUEUE_THRESHOLD_REG);
+	qt.bits.swfq_empty = 32;
+	writel(qt.bits32, geth->base + GLOBAL_QUEUE_THRESHOLD_REG);
+
+	skbsz.bits.sw_skb_size = 1 << geth->freeq_frag_order;
+	writel(skbsz.bits32, geth->base + GLOBAL_DMA_SKB_SIZE_REG);
+	writel(geth->freeq_dma_base | geth->freeq_order,
+	       geth->base + GLOBAL_SW_FREEQ_BASE_SIZE_REG);
+
+	return 0;
+
+err_freeq_alloc:
+	while (pn > 0) {
+		--pn;
+		mapping = geth->freeq_ring[pn << fpp_order].word2.buf_adr;
+		dma_unmap_single(geth->dev, mapping, frag_len, DMA_FROM_DEVICE);
+		put_page(geth->freeq_page_tab[pn]);
+	}
+
+err_freeq:
+	dma_free_coherent(geth->dev,
+			  sizeof(*geth->freeq_ring) << geth->freeq_order,
+			  geth->freeq_ring, geth->freeq_dma_base);
+	geth->freeq_ring = NULL;
+	return -ENOMEM;
+}
+
+/**
+ * geth_cleanup_freeq() - cleanup the DMA mappings and free the queue
+ * @geth: the Gemini global ethernet state
+ */
+static void geth_cleanup_freeq(struct gemini_ethernet *geth)
+{
+	unsigned int fpp_order = PAGE_SHIFT - geth->freeq_frag_order;
+	unsigned int frag_len = 1 << geth->freeq_frag_order;
+	unsigned int len = 1 << geth->freeq_order;
+	unsigned int pages = len >> fpp_order;
+	dma_addr_t mapping;
+	struct page *page;
+	unsigned int pn;
+
+	writew(readw(geth->base + GLOBAL_SWFQ_RWPTR_REG),
+	       geth->base + GLOBAL_SWFQ_RWPTR_REG + 2);
+	writel(0, geth->base + GLOBAL_SW_FREEQ_BASE_SIZE_REG);
+
+	for (pn = 0; pn < pages; pn++) {
+		mapping = geth->freeq_ring[pn << fpp_order].word2.buf_adr;
+		dma_unmap_single(geth->dev, mapping, frag_len, DMA_FROM_DEVICE);
+
+		page = geth->freeq_page_tab[pn];
+		while (page_ref_count(page) > 0)
+			put_page(page);
+	}
+
+	kfree(geth->freeq_page_tab);
+
+	dma_free_coherent(geth->dev,
+			  sizeof(*geth->freeq_ring) << geth->freeq_order,
+			  geth->freeq_ring, geth->freeq_dma_base);
+}
+
+/**
+ * geth_resize_freeq() - resize the software queue depth
+ * @port: the port requesting the change
+ *
+ * This gets called at least once during probe() so the device queue gets
+ * "resized" from the hardware defaults. Since both ports/net devices share
+ * the same hardware queue, some synchronization between the ports is
+ * needed.
+ */
+static int geth_resize_freeq(struct gemini_ethernet_port *port)
+{
+	struct gemini_ethernet *geth = port->geth;
+	struct net_device *netdev = port->netdev;
+	struct gemini_ethernet_port *other_port;
+	struct net_device *other_netdev;
+	unsigned int new_size = 0;
+	unsigned int new_order;
+	unsigned long flags;
+	u32 en;
+	int ret;
+
+	if (netdev->dev_id == 0)
+		other_netdev = geth->port1->netdev;
+	else
+		other_netdev = geth->port0->netdev;
+
+	if (other_netdev && netif_running(other_netdev))
+		return -EBUSY;
+
+	new_size = 1 << (port->rxq_order + 1);
+	netdev_dbg(netdev, "port %d size: %d order %d\n",
+		   netdev->dev_id,
+		   new_size,
+		   port->rxq_order);
+	if (other_netdev) {
+		other_port = netdev_priv(other_netdev);
+		new_size += 1 << (other_port->rxq_order + 1);
+		netdev_dbg(other_netdev, "port %d size: %d order %d\n",
+			   other_netdev->dev_id,
+			   (1 << (other_port->rxq_order + 1)),
+			   other_port->rxq_order);
+	}
+
+	new_order = min(15, ilog2(new_size - 1) + 1);
+	dev_dbg(geth->dev, "set shared queue to size %d order %d\n",
+		new_size, new_order);
+	if (geth->freeq_order == new_order)
+		return 0;
+
+	spin_lock_irqsave(&geth->irq_lock, flags);
+
+	/* Disable the software queue IRQs */
+	en = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	en &= ~SWFQ_EMPTY_INT_BIT;
+	writel(en, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+
+	/* Drop the old queue */
+	if (geth->freeq_ring)
+		geth_cleanup_freeq(geth);
+
+	/* Allocate a new queue with the desired order */
+	geth->freeq_order = new_order;
+	ret = geth_setup_freeq(geth);
+
+	/* Restart the interrupts - NOTE if this is the first resize
+	 * after probe(), this is where the interrupts get turned on
+	 * in the first place.
+	 */
+	en |= SWFQ_EMPTY_INT_BIT;
+	writel(en, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+
+	return ret;
+}
+
+static void gmac_tx_irq_enable(struct net_device *netdev,
+			       unsigned int txq, int en)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	u32 val, mask;
+
+	netdev_dbg(netdev, "%s device %d\n", __func__, netdev->dev_id);
+
+	mask = GMAC0_IRQ0_TXQ0_INTS << (6 * netdev->dev_id + txq);
+
+	if (en)
+		writel(mask, geth->base + GLOBAL_INTERRUPT_STATUS_0_REG);
+
+	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+	val = en ? val | mask : val & ~mask;
+	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+}
+
+static void gmac_tx_irq(struct net_device *netdev, unsigned int txq_num)
+{
+	struct netdev_queue *ntxq = netdev_get_tx_queue(netdev, txq_num);
+
+	gmac_tx_irq_enable(netdev, txq_num, 0);
+	netif_tx_wake_queue(ntxq);
+}
+
+static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
+			    struct gmac_txq *txq, unsigned short *desc)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct skb_shared_info *skb_si =  skb_shinfo(skb);
+	unsigned short m = (1 << port->txq_order) - 1;
+	short frag, last_frag = skb_si->nr_frags - 1;
+	struct gemini_ethernet *geth = port->geth;
+	unsigned int word1, word3, buflen;
+	unsigned short w = *desc;
+	struct gmac_txdesc *txd;
+	skb_frag_t *skb_frag;
+	dma_addr_t mapping;
+	unsigned short mtu;
+	void *buffer;
+
+	mtu  = ETH_HLEN;
+	mtu += netdev->mtu;
+	if (skb->protocol == htons(ETH_P_8021Q))
+		mtu += VLAN_HLEN;
+
+	word1 = skb->len;
+	word3 = SOF_BIT;
+
+	if (word1 > mtu) {
+		word1 |= TSS_MTU_ENABLE_BIT;
+		word3 |= mtu;
+	}
+
+	if (skb->ip_summed != CHECKSUM_NONE) {
+		int tcp = 0;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			word1 |= TSS_IP_CHKSUM_BIT;
+			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
+		} else { /* IPv6 */
+			word1 |= TSS_IPV6_ENABLE_BIT;
+			tcp = ipv6_hdr(skb)->nexthdr == IPPROTO_TCP;
+		}
+
+		word1 |= tcp ? TSS_TCP_CHKSUM_BIT : TSS_UDP_CHKSUM_BIT;
+	}
+
+	frag = -1;
+	while (frag <= last_frag) {
+		if (frag == -1) {
+			buffer = skb->data;
+			buflen = skb_headlen(skb);
+		} else {
+			skb_frag = skb_si->frags + frag;
+			buffer = page_address(skb_frag_page(skb_frag)) +
+				 skb_frag->page_offset;
+			buflen = skb_frag->size;
+		}
+
+		if (frag == last_frag) {
+			word3 |= EOF_BIT;
+			txq->skb[w] = skb;
+		}
+
+		mapping = dma_map_single(geth->dev, buffer, buflen,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(geth->dev, mapping))
+			goto map_error;
+
+		txd = txq->ring + w;
+		txd->word0.bits32 = buflen;
+		txd->word1.bits32 = word1;
+		txd->word2.buf_adr = mapping;
+		txd->word3.bits32 = word3;
+
+		word3 &= MTU_SIZE_BIT_MASK;
+		w++;
+		w &= m;
+		frag++;
+	}
+
+	*desc = w;
+	return 0;
+
+map_error:
+	while (w != *desc) {
+		w--;
+		w &= m;
+
+		dma_unmap_page(geth->dev, txq->ring[w].word2.buf_adr,
+			       txq->ring[w].word0.bits.buffer_size,
+			       DMA_TO_DEVICE);
+	}
+	return -ENOMEM;
+}
+
+static int gmac_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned short m = (1 << port->txq_order) - 1;
+	struct netdev_queue *ntxq;
+	unsigned short r, w, d;
+	void __iomem *ptr_reg;
+	struct gmac_txq *txq;
+	int txq_num, nfrags;
+	union dma_rwptr rw;
+
+	SKB_FRAG_ASSERT(skb);
+
+	if (skb->len >= 0x10000)
+		goto out_drop_free;
+
+	txq_num = skb_get_queue_mapping(skb);
+	ptr_reg = port->dma_base + GMAC_SW_TX_QUEUE_PTR_REG(txq_num);
+	txq = &port->txq[txq_num];
+	ntxq = netdev_get_tx_queue(netdev, txq_num);
+	nfrags = skb_shinfo(skb)->nr_frags;
+
+	rw.bits32 = readl(ptr_reg);
+	r = rw.bits.rptr;
+	w = rw.bits.wptr;
+
+	d = txq->cptr - w - 1;
+	d &= m;
+
+	if (d < nfrags + 2) {
+		gmac_clean_txq(netdev, txq, r);
+		d = txq->cptr - w - 1;
+		d &= m;
+
+		if (d < nfrags + 2) {
+			netif_tx_stop_queue(ntxq);
+
+			d = txq->cptr + nfrags + 16;
+			d &= m;
+			txq->ring[d].word3.bits.eofie = 1;
+			gmac_tx_irq_enable(netdev, txq_num, 1);
+
+			u64_stats_update_begin(&port->tx_stats_syncp);
+			netdev->stats.tx_fifo_errors++;
+			u64_stats_update_end(&port->tx_stats_syncp);
+			return NETDEV_TX_BUSY;
+		}
+	}
+
+	if (gmac_map_tx_bufs(netdev, skb, txq, &w)) {
+		if (skb_linearize(skb))
+			goto out_drop;
+
+		u64_stats_update_begin(&port->tx_stats_syncp);
+		port->tx_frags_linearized++;
+		u64_stats_update_end(&port->tx_stats_syncp);
+
+		if (gmac_map_tx_bufs(netdev, skb, txq, &w))
+			goto out_drop_free;
+	}
+
+	writew(w, ptr_reg + 2);
+
+	gmac_clean_txq(netdev, txq, r);
+	return NETDEV_TX_OK;
+
+out_drop_free:
+	dev_kfree_skb(skb);
+out_drop:
+	u64_stats_update_begin(&port->tx_stats_syncp);
+	port->stats.tx_dropped++;
+	u64_stats_update_end(&port->tx_stats_syncp);
+	return NETDEV_TX_OK;
+}
+
+static void gmac_tx_timeout(struct net_device *netdev)
+{
+	netdev_err(netdev, "Tx timeout\n");
+	gmac_dump_dma_state(netdev);
+}
+
+static void gmac_enable_irq(struct net_device *netdev, int enable)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	unsigned long flags;
+	u32 val, mask;
+
+	netdev_info(netdev, "%s device %d %s\n", __func__,
+		    netdev->dev_id, enable ? "enable" : "disable");
+	spin_lock_irqsave(&geth->irq_lock, flags);
+
+	mask = GMAC0_IRQ0_2 << (netdev->dev_id * 2);
+	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+	val = enable ? (val | mask) : (val & ~mask);
+	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+
+	mask = DEFAULT_Q0_INT_BIT << netdev->dev_id;
+	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+	val = enable ? (val | mask) : (val & ~mask);
+	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+
+	mask = GMAC0_IRQ4_8 << (netdev->dev_id * 8);
+	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	val = enable ? (val | mask) : (val & ~mask);
+	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+}
+
+static void gmac_enable_rx_irq(struct net_device *netdev, int enable)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	unsigned long flags;
+	u32 val, mask;
+
+	netdev_dbg(netdev, "%s device %d %s\n", __func__, netdev->dev_id,
+		   enable ? "enable" : "disable");
+	spin_lock_irqsave(&geth->irq_lock, flags);
+	mask = DEFAULT_Q0_INT_BIT << netdev->dev_id;
+
+	val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+	val = enable ? (val | mask) : (val & ~mask);
+	writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+}
+
+static struct sk_buff *gmac_skb_if_good_frame(struct gemini_ethernet_port *port,
+					      union gmac_rxdesc_0 word0,
+					      unsigned int frame_len)
+{
+	unsigned int rx_csum = word0.bits.chksum_status;
+	unsigned int rx_status = word0.bits.status;
+	struct sk_buff *skb = NULL;
+
+	port->rx_stats[rx_status]++;
+	port->rx_csum_stats[rx_csum]++;
+
+	if (word0.bits.derr || word0.bits.perr ||
+	    rx_status || frame_len < ETH_ZLEN ||
+	    rx_csum >= RX_CHKSUM_IP_ERR_UNKNOWN) {
+		port->stats.rx_errors++;
+
+		if (frame_len < ETH_ZLEN || RX_ERROR_LENGTH(rx_status))
+			port->stats.rx_length_errors++;
+		if (RX_ERROR_OVER(rx_status))
+			port->stats.rx_over_errors++;
+		if (RX_ERROR_CRC(rx_status))
+			port->stats.rx_crc_errors++;
+		if (RX_ERROR_FRAME(rx_status))
+			port->stats.rx_frame_errors++;
+		return NULL;
+	}
+
+	skb = napi_get_frags(&port->napi);
+	if (!skb)
+		goto update_exit;
+
+	if (rx_csum == RX_CHKSUM_IP_UDP_TCP_OK)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+update_exit:
+	port->stats.rx_bytes += frame_len;
+	port->stats.rx_packets++;
+	return skb;
+}
+
+static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned short m = (1 << port->rxq_order) - 1;
+	struct gemini_ethernet *geth = port->geth;
+	void __iomem *ptr_reg = port->rxq_rwptr;
+	unsigned int frame_len, frag_len;
+	struct gmac_rxdesc *rx = NULL;
+	static struct sk_buff *skb;
+	union gmac_rxdesc_0 word0;
+	union gmac_rxdesc_1 word1;
+	union gmac_rxdesc_3 word3;
+	struct page *page = NULL;
+	unsigned int page_offs;
+	unsigned short r, w;
+	union dma_rwptr rw;
+	dma_addr_t mapping;
+	int frag_nr = 0;
+
+	rw.bits32 = readl(ptr_reg);
+	/* Reset interrupt as all packages until here are taken into account */
+	writel(DEFAULT_Q0_INT_BIT << netdev->dev_id,
+	       geth->base + GLOBAL_INTERRUPT_STATUS_1_REG);
+	r = rw.bits.rptr;
+	w = rw.bits.wptr;
+
+	while (budget && w != r) {
+		rx = port->rxq_ring + r;
+		word0 = rx->word0;
+		word1 = rx->word1;
+		mapping = rx->word2.buf_adr;
+		word3 = rx->word3;
+
+		r++;
+		r &= m;
+
+		frag_len = word0.bits.buffer_size;
+		frame_len = word1.bits.byte_count;
+		page_offs = mapping & ~PAGE_MASK;
+
+		if (!mapping) {
+			netdev_err(netdev,
+				   "rxq[%u]: HW BUG: zero DMA desc\n", r);
+			goto err_drop;
+		}
+
+		page = pfn_to_page(dma_to_pfn(geth->dev, mapping));
+
+		if (word3.bits32 & SOF_BIT) {
+			if (skb) {
+				napi_free_frags(&port->napi);
+				port->stats.rx_dropped++;
+			}
+
+			skb = gmac_skb_if_good_frame(port, word0, frame_len);
+			if (!skb)
+				goto err_drop;
+
+			page_offs += NET_IP_ALIGN;
+			frag_len -= NET_IP_ALIGN;
+			frag_nr = 0;
+
+		} else if (!skb) {
+			put_page(page);
+			continue;
+		}
+
+		if (word3.bits32 & EOF_BIT)
+			frag_len = frame_len - skb->len;
+
+		/* append page frag to skb */
+		if (frag_nr == MAX_SKB_FRAGS)
+			goto err_drop;
+
+		if (frag_len == 0)
+			netdev_err(netdev, "Received fragment with len = 0\n");
+
+		skb_fill_page_desc(skb, frag_nr, page, page_offs, frag_len);
+		skb->len += frag_len;
+		skb->data_len += frag_len;
+		skb->truesize += frag_len;
+		frag_nr++;
+
+		if (word3.bits32 & EOF_BIT) {
+			napi_gro_frags(&port->napi);
+			skb = NULL;
+			--budget;
+		}
+		continue;
+
+err_drop:
+		if (skb) {
+			napi_free_frags(&port->napi);
+			skb = NULL;
+		}
+
+		if (mapping)
+			put_page(page);
+
+		port->stats.rx_dropped++;
+	}
+
+	writew(r, ptr_reg);
+	return budget;
+}
+
+static int gmac_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct gemini_ethernet_port *port = netdev_priv(napi->dev);
+	struct gemini_ethernet *geth = port->geth;
+	unsigned int freeq_threshold;
+	unsigned int received;
+
+	freeq_threshold = 1 << (geth->freeq_order - 1);
+	u64_stats_update_begin(&port->rx_stats_syncp);
+
+	received = gmac_rx(napi->dev, budget);
+	if (received < budget) {
+		napi_gro_flush(napi, false);
+		napi_complete_done(napi, received);
+		gmac_enable_rx_irq(napi->dev, 1);
+		++port->rx_napi_exits;
+	}
+
+	port->freeq_refill += (budget - received);
+	if (port->freeq_refill > freeq_threshold) {
+		port->freeq_refill -= freeq_threshold;
+		geth_fill_freeq(geth, 0);
+	}
+
+	u64_stats_update_end(&port->rx_stats_syncp);
+	return received;
+}
+
+static void gmac_dump_dma_state(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	void __iomem *ptr_reg;
+	u32 reg[5];
+
+	/* Interrupt status */
+	reg[0] = readl(geth->base + GLOBAL_INTERRUPT_STATUS_0_REG);
+	reg[1] = readl(geth->base + GLOBAL_INTERRUPT_STATUS_1_REG);
+	reg[2] = readl(geth->base + GLOBAL_INTERRUPT_STATUS_2_REG);
+	reg[3] = readl(geth->base + GLOBAL_INTERRUPT_STATUS_3_REG);
+	reg[4] = readl(geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+	netdev_err(netdev, "IRQ status: 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   reg[0], reg[1], reg[2], reg[3], reg[4]);
+
+	/* Interrupt enable */
+	reg[0] = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+	reg[1] = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+	reg[2] = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_2_REG);
+	reg[3] = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_3_REG);
+	reg[4] = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	netdev_err(netdev, "IRQ enable: 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   reg[0], reg[1], reg[2], reg[3], reg[4]);
+
+	/* RX DMA status */
+	reg[0] = readl(port->dma_base + GMAC_DMA_RX_FIRST_DESC_REG);
+	reg[1] = readl(port->dma_base + GMAC_DMA_RX_CURR_DESC_REG);
+	reg[2] = GET_RPTR(port->rxq_rwptr);
+	reg[3] = GET_WPTR(port->rxq_rwptr);
+	netdev_err(netdev, "RX DMA regs: 0x%08x 0x%08x, ptr: %u %u\n",
+		   reg[0], reg[1], reg[2], reg[3]);
+
+	reg[0] = readl(port->dma_base + GMAC_DMA_RX_DESC_WORD0_REG);
+	reg[1] = readl(port->dma_base + GMAC_DMA_RX_DESC_WORD1_REG);
+	reg[2] = readl(port->dma_base + GMAC_DMA_RX_DESC_WORD2_REG);
+	reg[3] = readl(port->dma_base + GMAC_DMA_RX_DESC_WORD3_REG);
+	netdev_err(netdev, "RX DMA descriptor: 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   reg[0], reg[1], reg[2], reg[3]);
+
+	/* TX DMA status */
+	ptr_reg = port->dma_base + GMAC_SW_TX_QUEUE0_PTR_REG;
+
+	reg[0] = readl(port->dma_base + GMAC_DMA_TX_FIRST_DESC_REG);
+	reg[1] = readl(port->dma_base + GMAC_DMA_TX_CURR_DESC_REG);
+	reg[2] = GET_RPTR(ptr_reg);
+	reg[3] = GET_WPTR(ptr_reg);
+	netdev_err(netdev, "TX DMA regs: 0x%08x 0x%08x, ptr: %u %u\n",
+		   reg[0], reg[1], reg[2], reg[3]);
+
+	reg[0] = readl(port->dma_base + GMAC_DMA_TX_DESC_WORD0_REG);
+	reg[1] = readl(port->dma_base + GMAC_DMA_TX_DESC_WORD1_REG);
+	reg[2] = readl(port->dma_base + GMAC_DMA_TX_DESC_WORD2_REG);
+	reg[3] = readl(port->dma_base + GMAC_DMA_TX_DESC_WORD3_REG);
+	netdev_err(netdev, "TX DMA descriptor: 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   reg[0], reg[1], reg[2], reg[3]);
+
+	/* FREE queues status */
+	ptr_reg = geth->base + GLOBAL_SWFQ_RWPTR_REG;
+
+	reg[0] = GET_RPTR(ptr_reg);
+	reg[1] = GET_WPTR(ptr_reg);
+
+	ptr_reg = geth->base + GLOBAL_HWFQ_RWPTR_REG;
+
+	reg[2] = GET_RPTR(ptr_reg);
+	reg[3] = GET_WPTR(ptr_reg);
+	netdev_err(netdev, "FQ SW ptr: %u %u, HW ptr: %u %u\n",
+		   reg[0], reg[1], reg[2], reg[3]);
+}
+
+static void gmac_update_hw_stats(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int rx_discards, rx_mcast, rx_bcast;
+	struct gemini_ethernet *geth = port->geth;
+	unsigned long flags;
+
+	spin_lock_irqsave(&geth->irq_lock, flags);
+	u64_stats_update_begin(&port->ir_stats_syncp);
+
+	rx_discards = readl(port->gmac_base + GMAC_IN_DISCARDS);
+	port->hw_stats[0] += rx_discards;
+	port->hw_stats[1] += readl(port->gmac_base + GMAC_IN_ERRORS);
+	rx_mcast = readl(port->gmac_base + GMAC_IN_MCAST);
+	port->hw_stats[2] += rx_mcast;
+	rx_bcast = readl(port->gmac_base + GMAC_IN_BCAST);
+	port->hw_stats[3] += rx_bcast;
+	port->hw_stats[4] += readl(port->gmac_base + GMAC_IN_MAC1);
+	port->hw_stats[5] += readl(port->gmac_base + GMAC_IN_MAC2);
+
+	port->stats.rx_missed_errors += rx_discards;
+	port->stats.multicast += rx_mcast;
+	port->stats.multicast += rx_bcast;
+
+	writel(GMAC0_MIB_INT_BIT << (netdev->dev_id * 8),
+	       geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+
+	u64_stats_update_end(&port->ir_stats_syncp);
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+}
+
+/**
+ * gmac_get_intr_flags() - get interrupt status flags for a port from
+ * @netdev: the net device for the port to get flags from
+ * @i: the interrupt status register 0..4
+ */
+static u32 gmac_get_intr_flags(struct net_device *netdev, int i)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	struct gemini_ethernet *geth = port->geth;
+	void __iomem *irqif_reg, *irqen_reg;
+	unsigned int offs, val;
+
+	/* Calculate the offset using the stride of the status registers */
+	offs = i * (GLOBAL_INTERRUPT_STATUS_1_REG -
+		    GLOBAL_INTERRUPT_STATUS_0_REG);
+
+	irqif_reg = geth->base + GLOBAL_INTERRUPT_STATUS_0_REG + offs;
+	irqen_reg = geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG + offs;
+
+	val = readl(irqif_reg) & readl(irqen_reg);
+	return val;
+}
+
+enum hrtimer_restart gmac_coalesce_delay_expired(struct hrtimer *timer)
+{
+	struct gemini_ethernet_port *port =
+		container_of(timer, struct gemini_ethernet_port,
+			     rx_coalesce_timer);
+
+	napi_schedule(&port->napi);
+	return HRTIMER_NORESTART;
+}
+
+static irqreturn_t gmac_irq(int irq, void *data)
+{
+	struct gemini_ethernet_port *port;
+	struct net_device *netdev = data;
+	struct gemini_ethernet *geth;
+	u32 val, orr = 0;
+
+	port = netdev_priv(netdev);
+	geth = port->geth;
+
+	val = gmac_get_intr_flags(netdev, 0);
+	orr |= val;
+
+	if (val & (GMAC0_IRQ0_2 << (netdev->dev_id * 2))) {
+		/* Oh, crap */
+		netdev_err(netdev, "hw failure/sw bug\n");
+		gmac_dump_dma_state(netdev);
+
+		/* don't know how to recover, just reduce losses */
+		gmac_enable_irq(netdev, 0);
+		return IRQ_HANDLED;
+	}
+
+	if (val & (GMAC0_IRQ0_TXQ0_INTS << (netdev->dev_id * 6)))
+		gmac_tx_irq(netdev, 0);
+
+	val = gmac_get_intr_flags(netdev, 1);
+	orr |= val;
+
+	if (val & (DEFAULT_Q0_INT_BIT << netdev->dev_id)) {
+		gmac_enable_rx_irq(netdev, 0);
+
+		if (!port->rx_coalesce_nsecs) {
+			napi_schedule(&port->napi);
+		} else {
+			ktime_t ktime;
+
+			ktime = ktime_set(0, port->rx_coalesce_nsecs);
+			hrtimer_start(&port->rx_coalesce_timer, ktime,
+				      HRTIMER_MODE_REL);
+		}
+	}
+
+	val = gmac_get_intr_flags(netdev, 4);
+	orr |= val;
+
+	if (val & (GMAC0_MIB_INT_BIT << (netdev->dev_id * 8)))
+		gmac_update_hw_stats(netdev);
+
+	if (val & (GMAC0_RX_OVERRUN_INT_BIT << (netdev->dev_id * 8))) {
+		writel(GMAC0_RXDERR_INT_BIT << (netdev->dev_id * 8),
+		       geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+
+		spin_lock(&geth->irq_lock);
+		u64_stats_update_begin(&port->ir_stats_syncp);
+		++port->stats.rx_fifo_errors;
+		u64_stats_update_end(&port->ir_stats_syncp);
+		spin_unlock(&geth->irq_lock);
+	}
+
+	return orr ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static void gmac_start_dma(struct gemini_ethernet_port *port)
+{
+	void __iomem *dma_ctrl_reg = port->dma_base + GMAC_DMA_CTRL_REG;
+	union gmac_dma_ctrl dma_ctrl;
+
+	dma_ctrl.bits32 = readl(dma_ctrl_reg);
+	dma_ctrl.bits.rd_enable = 1;
+	dma_ctrl.bits.td_enable = 1;
+	dma_ctrl.bits.loopback = 0;
+	dma_ctrl.bits.drop_small_ack = 0;
+	dma_ctrl.bits.rd_insert_bytes = NET_IP_ALIGN;
+	dma_ctrl.bits.rd_prot = HPROT_DATA_CACHE | HPROT_PRIVILIGED;
+	dma_ctrl.bits.rd_burst_size = HBURST_INCR8;
+	dma_ctrl.bits.rd_bus = HSIZE_8;
+	dma_ctrl.bits.td_prot = HPROT_DATA_CACHE;
+	dma_ctrl.bits.td_burst_size = HBURST_INCR8;
+	dma_ctrl.bits.td_bus = HSIZE_8;
+
+	writel(dma_ctrl.bits32, dma_ctrl_reg);
+}
+
+static void gmac_stop_dma(struct gemini_ethernet_port *port)
+{
+	void __iomem *dma_ctrl_reg = port->dma_base + GMAC_DMA_CTRL_REG;
+	union gmac_dma_ctrl dma_ctrl;
+
+	dma_ctrl.bits32 = readl(dma_ctrl_reg);
+	dma_ctrl.bits.rd_enable = 0;
+	dma_ctrl.bits.td_enable = 0;
+	writel(dma_ctrl.bits32, dma_ctrl_reg);
+}
+
+static int gmac_open(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	int err;
+
+	if (!netdev->phydev) {
+		err = gmac_setup_phy(netdev);
+		if (err) {
+			netif_err(port, ifup, netdev,
+				  "PHY init failed: %d\n", err);
+			return err;
+		}
+	}
+
+	err = request_irq(netdev->irq, gmac_irq,
+			  IRQF_SHARED, netdev->name, netdev);
+	if (err) {
+		netdev_err(netdev, "no IRQ\n");
+		return err;
+	}
+
+	netif_carrier_off(netdev);
+	phy_start(netdev->phydev);
+
+	err = geth_resize_freeq(port);
+	if (err) {
+		netdev_err(netdev, "could not resize freeq\n");
+		goto err_stop_phy;
+	}
+
+	err = gmac_setup_rxq(netdev);
+	if (err) {
+		netdev_err(netdev, "could not setup RXQ\n");
+		goto err_stop_phy;
+	}
+
+	err = gmac_setup_txqs(netdev);
+	if (err) {
+		netdev_err(netdev, "could not setup TXQs\n");
+		gmac_cleanup_rxq(netdev);
+		goto err_stop_phy;
+	}
+
+	napi_enable(&port->napi);
+
+	gmac_start_dma(port);
+	gmac_enable_irq(netdev, 1);
+	gmac_enable_tx_rx(netdev);
+	netif_tx_start_all_queues(netdev);
+
+	hrtimer_init(&port->rx_coalesce_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
+
+	netdev_info(netdev, "opened\n");
+
+	return 0;
+
+err_stop_phy:
+	phy_stop(netdev->phydev);
+	free_irq(netdev->irq, netdev);
+	return err;
+}
+
+static int gmac_stop(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	hrtimer_cancel(&port->rx_coalesce_timer);
+	netif_tx_stop_all_queues(netdev);
+	gmac_disable_tx_rx(netdev);
+	gmac_stop_dma(port);
+	napi_disable(&port->napi);
+
+	gmac_enable_irq(netdev, 0);
+	gmac_cleanup_rxq(netdev);
+	gmac_cleanup_txqs(netdev);
+
+	phy_stop(netdev->phydev);
+	free_irq(netdev->irq, netdev);
+
+	gmac_update_hw_stats(netdev);
+	return 0;
+}
+
+static void gmac_set_rx_mode(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	union gmac_rx_fltr filter = { .bits = {
+		.broadcast = 1,
+		.multicast = 1,
+		.unicast = 1,
+	} };
+	struct netdev_hw_addr *ha;
+	unsigned int bit_nr;
+	u32 mc_filter[2];
+
+	mc_filter[1] = 0;
+	mc_filter[0] = 0;
+
+	if (netdev->flags & IFF_PROMISC) {
+		filter.bits.error = 1;
+		filter.bits.promiscuous = 1;
+		mc_filter[1] = ~0;
+		mc_filter[0] = ~0;
+	} else if (netdev->flags & IFF_ALLMULTI) {
+		mc_filter[1] = ~0;
+		mc_filter[0] = ~0;
+	} else {
+		netdev_for_each_mc_addr(ha, netdev) {
+			bit_nr = ~crc32_le(~0, ha->addr, ETH_ALEN) & 0x3f;
+			mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 0x1f);
+		}
+	}
+
+	writel(mc_filter[0], port->gmac_base + GMAC_MCAST_FIL0);
+	writel(mc_filter[1], port->gmac_base + GMAC_MCAST_FIL1);
+	writel(filter.bits32, port->gmac_base + GMAC_RX_FLTR);
+}
+
+static void gmac_write_mac_address(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	__le32 addr[3];
+
+	memset(addr, 0, sizeof(addr));
+	memcpy(addr, netdev->dev_addr, ETH_ALEN);
+
+	writel(le32_to_cpu(addr[0]), port->gmac_base + GMAC_STA_ADD0);
+	writel(le32_to_cpu(addr[1]), port->gmac_base + GMAC_STA_ADD1);
+	writel(le32_to_cpu(addr[2]), port->gmac_base + GMAC_STA_ADD2);
+}
+
+static int gmac_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct sockaddr *sa = addr;
+
+	memcpy(netdev->dev_addr, sa->sa_data, ETH_ALEN);
+	gmac_write_mac_address(netdev);
+
+	return 0;
+}
+
+static void gmac_clear_hw_stats(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	readl(port->gmac_base + GMAC_IN_DISCARDS);
+	readl(port->gmac_base + GMAC_IN_ERRORS);
+	readl(port->gmac_base + GMAC_IN_MCAST);
+	readl(port->gmac_base + GMAC_IN_BCAST);
+	readl(port->gmac_base + GMAC_IN_MAC1);
+	readl(port->gmac_base + GMAC_IN_MAC2);
+}
+
+static void gmac_get_stats64(struct net_device *netdev,
+			     struct rtnl_link_stats64 *stats)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int start;
+
+	gmac_update_hw_stats(netdev);
+
+	/* Racing with RX NAPI */
+	do {
+		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+
+		stats->rx_packets = port->stats.rx_packets;
+		stats->rx_bytes = port->stats.rx_bytes;
+		stats->rx_errors = port->stats.rx_errors;
+		stats->rx_dropped = port->stats.rx_dropped;
+
+		stats->rx_length_errors = port->stats.rx_length_errors;
+		stats->rx_over_errors = port->stats.rx_over_errors;
+		stats->rx_crc_errors = port->stats.rx_crc_errors;
+		stats->rx_frame_errors = port->stats.rx_frame_errors;
+
+	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+
+	/* Racing with MIB and TX completion interrupts */
+	do {
+		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+
+		stats->tx_errors = port->stats.tx_errors;
+		stats->tx_packets = port->stats.tx_packets;
+		stats->tx_bytes = port->stats.tx_bytes;
+
+		stats->multicast = port->stats.multicast;
+		stats->rx_missed_errors = port->stats.rx_missed_errors;
+		stats->rx_fifo_errors = port->stats.rx_fifo_errors;
+
+	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+
+	/* Racing with hard_start_xmit */
+	do {
+		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+
+		stats->tx_dropped = port->stats.tx_dropped;
+
+	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+
+	stats->rx_dropped += stats->rx_missed_errors;
+}
+
+static int gmac_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int max_len = gmac_pick_rx_max_len(new_mtu);
+
+	if (max_len < 0)
+		return -EINVAL;
+
+	gmac_disable_tx_rx(netdev);
+
+	netdev->mtu = new_mtu;
+	gmac_update_config0_reg(netdev, max_len << CONFIG0_MAXLEN_SHIFT,
+				CONFIG0_MAXLEN_MASK);
+
+	netdev_update_features(netdev);
+
+	gmac_enable_tx_rx(netdev);
+
+	return 0;
+}
+
+static netdev_features_t gmac_fix_features(struct net_device *netdev,
+					   netdev_features_t features)
+{
+	if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK)
+		features &= ~GMAC_OFFLOAD_FEATURES;
+
+	return features;
+}
+
+static int gmac_set_features(struct net_device *netdev,
+			     netdev_features_t features)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	int enable = features & NETIF_F_RXCSUM;
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&port->config_lock, flags);
+
+	reg = readl(port->gmac_base + GMAC_CONFIG0);
+	reg = enable ? reg | CONFIG0_RX_CHKSUM : reg & ~CONFIG0_RX_CHKSUM;
+	writel(reg, port->gmac_base + GMAC_CONFIG0);
+
+	spin_unlock_irqrestore(&port->config_lock, flags);
+	return 0;
+}
+
+static int gmac_get_sset_count(struct net_device *netdev, int sset)
+{
+	return sset == ETH_SS_STATS ? GMAC_STATS_NUM : 0;
+}
+
+static void gmac_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	memcpy(data, gmac_stats_strings, sizeof(gmac_stats_strings));
+}
+
+static void gmac_get_ethtool_stats(struct net_device *netdev,
+				   struct ethtool_stats *estats, u64 *values)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	unsigned int start;
+	u64 *p;
+	int i;
+
+	gmac_update_hw_stats(netdev);
+
+	/* Racing with MIB interrupt */
+	do {
+		p = values;
+		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+
+		for (i = 0; i < RX_STATS_NUM; i++)
+			*p++ = port->hw_stats[i];
+
+	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+	values = p;
+
+	/* Racing with RX NAPI */
+	do {
+		p = values;
+		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+
+		for (i = 0; i < RX_STATUS_NUM; i++)
+			*p++ = port->rx_stats[i];
+		for (i = 0; i < RX_CHKSUM_NUM; i++)
+			*p++ = port->rx_csum_stats[i];
+		*p++ = port->rx_napi_exits;
+
+	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+	values = p;
+
+	/* Racing with TX start_xmit */
+	do {
+		p = values;
+		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+
+		for (i = 0; i < TX_MAX_FRAGS; i++) {
+			*values++ = port->tx_frag_stats[i];
+			port->tx_frag_stats[i] = 0;
+		}
+		*values++ = port->tx_frags_linearized;
+		*values++ = port->tx_hw_csummed;
+
+	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+}
+
+static int gmac_get_ksettings(struct net_device *netdev,
+			      struct ethtool_link_ksettings *cmd)
+{
+	if (!netdev->phydev)
+		return -ENXIO;
+	phy_ethtool_ksettings_get(netdev->phydev, cmd);
+
+	return 0;
+}
+
+static int gmac_set_ksettings(struct net_device *netdev,
+			      const struct ethtool_link_ksettings *cmd)
+{
+	if (!netdev->phydev)
+		return -ENXIO;
+	return phy_ethtool_ksettings_set(netdev->phydev, cmd);
+}
+
+static int gmac_nway_reset(struct net_device *netdev)
+{
+	if (!netdev->phydev)
+		return -ENXIO;
+	return phy_start_aneg(netdev->phydev);
+}
+
+static void gmac_get_pauseparam(struct net_device *netdev,
+				struct ethtool_pauseparam *pparam)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	union gmac_config0 config0;
+
+	config0.bits32 = readl(port->gmac_base + GMAC_CONFIG0);
+
+	pparam->rx_pause = config0.bits.rx_fc_en;
+	pparam->tx_pause = config0.bits.tx_fc_en;
+	pparam->autoneg = true;
+}
+
+static void gmac_get_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *rp)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	union gmac_config0 config0;
+
+	config0.bits32 = readl(port->gmac_base + GMAC_CONFIG0);
+
+	rp->rx_max_pending = 1 << 15;
+	rp->rx_mini_max_pending = 0;
+	rp->rx_jumbo_max_pending = 0;
+	rp->tx_max_pending = 1 << 15;
+
+	rp->rx_pending = 1 << port->rxq_order;
+	rp->rx_mini_pending = 0;
+	rp->rx_jumbo_pending = 0;
+	rp->tx_pending = 1 << port->txq_order;
+}
+
+static int gmac_set_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *rp)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+	int err = 0;
+
+	if (netif_running(netdev))
+		return -EBUSY;
+
+	if (rp->rx_pending) {
+		port->rxq_order = min(15, ilog2(rp->rx_pending - 1) + 1);
+		err = geth_resize_freeq(port);
+	}
+	if (rp->tx_pending) {
+		port->txq_order = min(15, ilog2(rp->tx_pending - 1) + 1);
+		port->irq_every_tx_packets = 1 << (port->txq_order - 2);
+	}
+
+	return err;
+}
+
+static int gmac_get_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *ecmd)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	ecmd->rx_max_coalesced_frames = 1;
+	ecmd->tx_max_coalesced_frames = port->irq_every_tx_packets;
+	ecmd->rx_coalesce_usecs = port->rx_coalesce_nsecs / 1000;
+
+	return 0;
+}
+
+static int gmac_set_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *ecmd)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	if (ecmd->tx_max_coalesced_frames < 1)
+		return -EINVAL;
+	if (ecmd->tx_max_coalesced_frames >= 1 << port->txq_order)
+		return -EINVAL;
+
+	port->irq_every_tx_packets = ecmd->tx_max_coalesced_frames;
+	port->rx_coalesce_nsecs = ecmd->rx_coalesce_usecs * 1000;
+
+	return 0;
+}
+
+static u32 gmac_get_msglevel(struct net_device *netdev)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	return port->msg_enable;
+}
+
+static void gmac_set_msglevel(struct net_device *netdev, u32 level)
+{
+	struct gemini_ethernet_port *port = netdev_priv(netdev);
+
+	port->msg_enable = level;
+}
+
+static void gmac_get_drvinfo(struct net_device *netdev,
+			     struct ethtool_drvinfo *info)
+{
+	strcpy(info->driver,  DRV_NAME);
+	strcpy(info->version, DRV_VERSION);
+	strcpy(info->bus_info, netdev->dev_id ? "1" : "0");
+}
+
+static const struct net_device_ops gmac_351x_ops = {
+	.ndo_init		= gmac_init,
+	.ndo_uninit		= gmac_uninit,
+	.ndo_open		= gmac_open,
+	.ndo_stop		= gmac_stop,
+	.ndo_start_xmit		= gmac_start_xmit,
+	.ndo_tx_timeout		= gmac_tx_timeout,
+	.ndo_set_rx_mode	= gmac_set_rx_mode,
+	.ndo_set_mac_address	= gmac_set_mac_address,
+	.ndo_get_stats64	= gmac_get_stats64,
+	.ndo_change_mtu		= gmac_change_mtu,
+	.ndo_fix_features	= gmac_fix_features,
+	.ndo_set_features	= gmac_set_features,
+};
+
+static const struct ethtool_ops gmac_351x_ethtool_ops = {
+	.get_sset_count	= gmac_get_sset_count,
+	.get_strings	= gmac_get_strings,
+	.get_ethtool_stats = gmac_get_ethtool_stats,
+	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = gmac_get_ksettings,
+	.set_link_ksettings = gmac_set_ksettings,
+	.nway_reset	= gmac_nway_reset,
+	.get_pauseparam	= gmac_get_pauseparam,
+	.get_ringparam	= gmac_get_ringparam,
+	.set_ringparam	= gmac_set_ringparam,
+	.get_coalesce	= gmac_get_coalesce,
+	.set_coalesce	= gmac_set_coalesce,
+	.get_msglevel	= gmac_get_msglevel,
+	.set_msglevel	= gmac_set_msglevel,
+	.get_drvinfo	= gmac_get_drvinfo,
+};
+
+static irqreturn_t gemini_port_irq_thread(int irq, void *data)
+{
+	unsigned long irqmask = SWFQ_EMPTY_INT_BIT;
+	struct gemini_ethernet_port *port = data;
+	struct gemini_ethernet *geth;
+	unsigned long flags;
+
+	geth = port->geth;
+	geth_fill_freeq(geth, 0);
+
+	spin_lock_irqsave(&geth->irq_lock, flags);
+	/* ACK queue interrupt */
+	writel(irqmask, geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+	/* Enable queue interrupt again */
+	irqmask |= readl(geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	writel(irqmask, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+	spin_unlock_irqrestore(&geth->irq_lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t gemini_port_irq(int irq, void *data)
+{
+	struct gemini_ethernet_port *port = data;
+	struct gemini_ethernet *geth;
+	irqreturn_t ret = IRQ_NONE;
+	u32 val, en;
+
+	geth = port->geth;
+	spin_lock(&geth->irq_lock);
+
+	val = readl(geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+	en = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+
+	if (val & en & SWFQ_EMPTY_INT_BIT) {
+		/* Disable the queue empty interrupt while we work on
+		 * processing the queue. Also disable overrun interrupts
+		 * as there is not much we can do about it here.
+		 */
+		en &= ~(SWFQ_EMPTY_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT
+					   | GMAC1_RX_OVERRUN_INT_BIT);
+		writel(en, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+		ret = IRQ_WAKE_THREAD;
+	}
+
+	spin_unlock(&geth->irq_lock);
+
+	return ret;
+}
+
+static void gemini_port_remove(struct gemini_ethernet_port *port)
+{
+	if (port->netdev)
+		unregister_netdev(port->netdev);
+	clk_disable_unprepare(port->pclk);
+	geth_cleanup_freeq(port->geth);
+}
+
+static void gemini_ethernet_init(struct gemini_ethernet *geth)
+{
+	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
+	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
+	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_2_REG);
+	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_3_REG);
+	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_4_REG);
+
+	/* Interrupt config:
+	 *
+	 *	GMAC0 intr bits ------> int0 ----> eth0
+	 *	GMAC1 intr bits ------> int1 ----> eth1
+	 *	TOE intr -------------> int1 ----> eth1
+	 *	Classification Intr --> int0 ----> eth0
+	 *	Default Q0 -----------> int0 ----> eth0
+	 *	Default Q1 -----------> int1 ----> eth1
+	 *	FreeQ intr -----------> int1 ----> eth1
+	 */
+	writel(0xCCFC0FC0, geth->base + GLOBAL_INTERRUPT_SELECT_0_REG);
+	writel(0x00F00002, geth->base + GLOBAL_INTERRUPT_SELECT_1_REG);
+	writel(0xFFFFFFFF, geth->base + GLOBAL_INTERRUPT_SELECT_2_REG);
+	writel(0xFFFFFFFF, geth->base + GLOBAL_INTERRUPT_SELECT_3_REG);
+	writel(0xFF000003, geth->base + GLOBAL_INTERRUPT_SELECT_4_REG);
+
+	/* edge-triggered interrupts packed to level-triggered one... */
+	writel(~0, geth->base + GLOBAL_INTERRUPT_STATUS_0_REG);
+	writel(~0, geth->base + GLOBAL_INTERRUPT_STATUS_1_REG);
+	writel(~0, geth->base + GLOBAL_INTERRUPT_STATUS_2_REG);
+	writel(~0, geth->base + GLOBAL_INTERRUPT_STATUS_3_REG);
+	writel(~0, geth->base + GLOBAL_INTERRUPT_STATUS_4_REG);
+
+	/* Set up queue */
+	writel(0, geth->base + GLOBAL_SW_FREEQ_BASE_SIZE_REG);
+	writel(0, geth->base + GLOBAL_HW_FREEQ_BASE_SIZE_REG);
+	writel(0, geth->base + GLOBAL_SWFQ_RWPTR_REG);
+	writel(0, geth->base + GLOBAL_HWFQ_RWPTR_REG);
+
+	geth->freeq_frag_order = DEFAULT_RX_BUF_ORDER;
+	/* This makes the queue resize on probe() so that we
+	 * set up and enable the queue IRQ. FIXME: fragile.
+	 */
+	geth->freeq_order = 1;
+}
+
+static void gemini_port_save_mac_addr(struct gemini_ethernet_port *port)
+{
+	port->mac_addr[0] =
+		cpu_to_le32(readl(port->gmac_base + GMAC_STA_ADD0));
+	port->mac_addr[1] =
+		cpu_to_le32(readl(port->gmac_base + GMAC_STA_ADD1));
+	port->mac_addr[2] =
+		cpu_to_le32(readl(port->gmac_base + GMAC_STA_ADD2));
+}
+
+static int gemini_ethernet_port_probe(struct platform_device *pdev)
+{
+	char *port_names[2] = { "ethernet0", "ethernet1" };
+	struct gemini_ethernet_port *port;
+	struct device *dev = &pdev->dev;
+	struct gemini_ethernet *geth;
+	struct net_device *netdev;
+	struct resource *gmacres;
+	struct resource *dmares;
+	struct device *parent;
+	unsigned int id;
+	int irq;
+	int ret;
+
+	parent = dev->parent;
+	geth = dev_get_drvdata(parent);
+
+	if (!strcmp(dev_name(dev), "60008000.ethernet-port"))
+		id = 0;
+	else if (!strcmp(dev_name(dev), "6000c000.ethernet-port"))
+		id = 1;
+	else
+		return -ENODEV;
+
+	dev_info(dev, "probe %s ID %d\n", dev_name(dev), id);
+
+	netdev = alloc_etherdev_mq(sizeof(*port), TX_QUEUE_NUM);
+	if (!netdev) {
+		dev_err(dev, "Can't allocate ethernet device #%d\n", id);
+		return -ENOMEM;
+	}
+
+	port = netdev_priv(netdev);
+	SET_NETDEV_DEV(netdev, dev);
+	port->netdev = netdev;
+	port->id = id;
+	port->geth = geth;
+	port->dev = dev;
+
+	/* DMA memory */
+	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!dmares) {
+		dev_err(dev, "no DMA resource\n");
+		return -ENODEV;
+	}
+	port->dma_base = devm_ioremap_resource(dev, dmares);
+	if (IS_ERR(port->dma_base))
+		return PTR_ERR(port->dma_base);
+
+	/* GMAC config memory */
+	gmacres = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!gmacres) {
+		dev_err(dev, "no GMAC resource\n");
+		return -ENODEV;
+	}
+	port->gmac_base = devm_ioremap_resource(dev, gmacres);
+	if (IS_ERR(port->gmac_base))
+		return PTR_ERR(port->gmac_base);
+
+	/* Interrupt */
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev, "no IRQ\n");
+		return irq ? irq : -ENODEV;
+	}
+	port->irq = irq;
+
+	/* Clock the port */
+	port->pclk = devm_clk_get(dev, "PCLK");
+	if (IS_ERR(port->pclk)) {
+		dev_err(dev, "no PCLK\n");
+		return PTR_ERR(port->pclk);
+	}
+	ret = clk_prepare_enable(port->pclk);
+	if (ret)
+		return ret;
+
+	/* Maybe there is a nice ethernet address we should use */
+	gemini_port_save_mac_addr(port);
+
+	/* Reset the port */
+	port->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(port->reset)) {
+		dev_err(dev, "no reset\n");
+		return PTR_ERR(port->reset);
+	}
+	reset_control_reset(port->reset);
+	usleep_range(100, 500);
+
+	/* Assign pointer in the main state container */
+	if (!id)
+		geth->port0 = port;
+	else
+		geth->port1 = port;
+	platform_set_drvdata(pdev, port);
+
+	/* Set up and register the netdev */
+	netdev->dev_id = port->id;
+	netdev->irq = irq;
+	netdev->netdev_ops = &gmac_351x_ops;
+	netdev->ethtool_ops = &gmac_351x_ethtool_ops;
+
+	spin_lock_init(&port->config_lock);
+	gmac_clear_hw_stats(netdev);
+
+	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
+	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
+
+	port->freeq_refill = 0;
+	netif_napi_add(netdev, &port->napi, gmac_napi_poll,
+		       DEFAULT_NAPI_WEIGHT);
+
+	if (is_valid_ether_addr((void *)port->mac_addr)) {
+		memcpy(netdev->dev_addr, port->mac_addr, ETH_ALEN);
+	} else {
+		dev_dbg(dev, "ethernet address 0x%08x%08x%08x invalid\n",
+			port->mac_addr[0], port->mac_addr[1],
+			port->mac_addr[2]);
+		dev_info(dev, "using a random ethernet address\n");
+		random_ether_addr(netdev->dev_addr);
+	}
+	gmac_write_mac_address(netdev);
+
+	ret = devm_request_threaded_irq(port->dev,
+					port->irq,
+					gemini_port_irq,
+					gemini_port_irq_thread,
+					IRQF_SHARED,
+					port_names[port->id],
+					port);
+	if (ret)
+		return ret;
+
+	ret = register_netdev(netdev);
+	if (!ret) {
+		netdev_info(netdev,
+			    "irq %d, DMA @ 0x%08x, GMAC @ 0x%08x\n",
+			    port->irq, dmares->start,
+			    gmacres->start);
+		ret = gmac_setup_phy(netdev);
+		if (ret)
+			netdev_info(netdev,
+				    "PHY init failed, deferring to ifup time\n");
+		return 0;
+	}
+
+	port->netdev = NULL;
+	free_netdev(netdev);
+	return ret;
+}
+
+static int gemini_ethernet_port_remove(struct platform_device *pdev)
+{
+	struct gemini_ethernet_port *port = platform_get_drvdata(pdev);
+
+	gemini_port_remove(port);
+	return 0;
+}
+
+static const struct of_device_id gemini_ethernet_port_of_match[] = {
+	{
+		.compatible = "cortina,gemini-ethernet-port",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, gemini_ethernet_port_of_match);
+
+static struct platform_driver gemini_ethernet_port_driver = {
+	.driver = {
+		.name = "gemini-ethernet-port",
+		.of_match_table = of_match_ptr(gemini_ethernet_port_of_match),
+	},
+	.probe = gemini_ethernet_port_probe,
+	.remove = gemini_ethernet_port_remove,
+};
+module_platform_driver(gemini_ethernet_port_driver);
+
+static int gemini_ethernet_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct gemini_ethernet *geth;
+	unsigned int retry = 5;
+	struct resource *res;
+	u32 val;
+
+	/* Global registers */
+	geth = devm_kzalloc(dev, sizeof(*geth), GFP_KERNEL);
+	if (!geth)
+		return -ENOMEM;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+	geth->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(geth->base))
+		return PTR_ERR(geth->base);
+	geth->dev = dev;
+
+	/* Wait for ports to stabilize */
+	do {
+		udelay(2);
+		val = readl(geth->base + GLOBAL_TOE_VERSION_REG);
+		barrier();
+	} while (!val && --retry);
+	if (!retry) {
+		dev_err(dev, "failed to reset ethernet\n");
+		return -EIO;
+	}
+	dev_info(dev, "Ethernet device ID: 0x%03x, revision 0x%01x\n",
+		 (val >> 4) & 0xFFFU, val & 0xFU);
+
+	spin_lock_init(&geth->irq_lock);
+	spin_lock_init(&geth->freeq_lock);
+	gemini_ethernet_init(geth);
+
+	/* The children will use this */
+	platform_set_drvdata(pdev, geth);
+
+	/* Spawn child devices for the two ports */
+	return devm_of_platform_populate(dev);
+}
+
+static int gemini_ethernet_remove(struct platform_device *pdev)
+{
+	struct gemini_ethernet *geth = platform_get_drvdata(pdev);
+
+	gemini_ethernet_init(geth);
+	geth_cleanup_freeq(geth);
+
+	return 0;
+}
+
+static const struct of_device_id gemini_ethernet_of_match[] = {
+	{
+		.compatible = "cortina,gemini-ethernet",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, gemini_ethernet_of_match);
+
+static struct platform_driver gemini_ethernet_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = of_match_ptr(gemini_ethernet_of_match),
+	},
+	.probe = gemini_ethernet_probe,
+	.remove = gemini_ethernet_remove,
+};
+module_platform_driver(gemini_ethernet_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("StorLink SL351x (Gemini) ethernet driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h
new file mode 100644
index 000000000000..3b51bcc1fafd
--- /dev/null
+++ b/drivers/net/ethernet/cortina/gemini.h
@@ -0,0 +1,958 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/* Register definitions for Gemini GMAC Ethernet device driver
+ *
+ * Copyright (C) 2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ * Copyright (C) 2010 Michał Mirosław <mirq-linux@rere.qmqm.pl>
+ * Copytight (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ */
+#ifndef _GEMINI_ETHERNET_H
+#define _GEMINI_ETHERNET_H
+
+#include <linux/bitops.h>
+
+/* Base Registers */
+#define TOE_NONTOE_QUE_HDR_BASE		0x2000
+#define TOE_TOE_QUE_HDR_BASE		0x3000
+
+/* Queue ID */
+#define TOE_SW_FREE_QID			0x00
+#define TOE_HW_FREE_QID			0x01
+#define TOE_GMAC0_SW_TXQ0_QID		0x02
+#define TOE_GMAC0_SW_TXQ1_QID		0x03
+#define TOE_GMAC0_SW_TXQ2_QID		0x04
+#define TOE_GMAC0_SW_TXQ3_QID		0x05
+#define TOE_GMAC0_SW_TXQ4_QID		0x06
+#define TOE_GMAC0_SW_TXQ5_QID		0x07
+#define TOE_GMAC0_HW_TXQ0_QID		0x08
+#define TOE_GMAC0_HW_TXQ1_QID		0x09
+#define TOE_GMAC0_HW_TXQ2_QID		0x0A
+#define TOE_GMAC0_HW_TXQ3_QID		0x0B
+#define TOE_GMAC1_SW_TXQ0_QID		0x12
+#define TOE_GMAC1_SW_TXQ1_QID		0x13
+#define TOE_GMAC1_SW_TXQ2_QID		0x14
+#define TOE_GMAC1_SW_TXQ3_QID		0x15
+#define TOE_GMAC1_SW_TXQ4_QID		0x16
+#define TOE_GMAC1_SW_TXQ5_QID		0x17
+#define TOE_GMAC1_HW_TXQ0_QID		0x18
+#define TOE_GMAC1_HW_TXQ1_QID		0x19
+#define TOE_GMAC1_HW_TXQ2_QID		0x1A
+#define TOE_GMAC1_HW_TXQ3_QID		0x1B
+#define TOE_GMAC0_DEFAULT_QID		0x20
+#define TOE_GMAC1_DEFAULT_QID		0x21
+#define TOE_CLASSIFICATION_QID(x)	(0x22 + x)	/* 0x22 ~ 0x2F */
+#define TOE_TOE_QID(x)			(0x40 + x)	/* 0x40 ~ 0x7F */
+
+/* TOE DMA Queue Size should be 2^n, n = 6...12
+ * TOE DMA Queues are the following queue types:
+ *		SW Free Queue, HW Free Queue,
+ *		GMAC 0/1 SW TX Q0-5, and GMAC 0/1 HW TX Q0-5
+ * The base address and descriptor number are configured at
+ * DMA Queues Descriptor Ring Base Address/Size Register (offset 0x0004)
+ */
+#define GET_WPTR(addr)			readw((addr) + 2)
+#define GET_RPTR(addr)			readw((addr))
+#define SET_WPTR(addr, data)		writew((data), (addr) + 2)
+#define SET_RPTR(addr, data)		writew((data), (addr))
+#define __RWPTR_NEXT(x, mask)		(((unsigned int)(x) + 1) & (mask))
+#define __RWPTR_PREV(x, mask)		(((unsigned int)(x) - 1) & (mask))
+#define __RWPTR_DISTANCE(r, w, mask)	(((unsigned int)(w) - (r)) & (mask))
+#define __RWPTR_MASK(order)		((1 << (order)) - 1)
+#define RWPTR_NEXT(x, order)		__RWPTR_NEXT((x), __RWPTR_MASK((order)))
+#define RWPTR_PREV(x, order)		__RWPTR_PREV((x), __RWPTR_MASK((order)))
+#define RWPTR_DISTANCE(r, w, order)	__RWPTR_DISTANCE((r), (w), \
+						__RWPTR_MASK((order)))
+
+/* Global registers */
+#define GLOBAL_TOE_VERSION_REG		0x0000
+#define GLOBAL_SW_FREEQ_BASE_SIZE_REG	0x0004
+#define GLOBAL_HW_FREEQ_BASE_SIZE_REG	0x0008
+#define GLOBAL_DMA_SKB_SIZE_REG		0x0010
+#define GLOBAL_SWFQ_RWPTR_REG		0x0014
+#define GLOBAL_HWFQ_RWPTR_REG		0x0018
+#define GLOBAL_INTERRUPT_STATUS_0_REG	0x0020
+#define GLOBAL_INTERRUPT_ENABLE_0_REG	0x0024
+#define GLOBAL_INTERRUPT_SELECT_0_REG	0x0028
+#define GLOBAL_INTERRUPT_STATUS_1_REG	0x0030
+#define GLOBAL_INTERRUPT_ENABLE_1_REG	0x0034
+#define GLOBAL_INTERRUPT_SELECT_1_REG	0x0038
+#define GLOBAL_INTERRUPT_STATUS_2_REG	0x0040
+#define GLOBAL_INTERRUPT_ENABLE_2_REG	0x0044
+#define GLOBAL_INTERRUPT_SELECT_2_REG	0x0048
+#define GLOBAL_INTERRUPT_STATUS_3_REG	0x0050
+#define GLOBAL_INTERRUPT_ENABLE_3_REG	0x0054
+#define GLOBAL_INTERRUPT_SELECT_3_REG	0x0058
+#define GLOBAL_INTERRUPT_STATUS_4_REG	0x0060
+#define GLOBAL_INTERRUPT_ENABLE_4_REG	0x0064
+#define GLOBAL_INTERRUPT_SELECT_4_REG	0x0068
+#define GLOBAL_HASH_TABLE_BASE_REG	0x006C
+#define GLOBAL_QUEUE_THRESHOLD_REG	0x0070
+
+/* GMAC 0/1 DMA/TOE register */
+#define GMAC_DMA_CTRL_REG		0x0000
+#define GMAC_TX_WEIGHTING_CTRL_0_REG	0x0004
+#define GMAC_TX_WEIGHTING_CTRL_1_REG	0x0008
+#define GMAC_SW_TX_QUEUE0_PTR_REG	0x000C
+#define GMAC_SW_TX_QUEUE1_PTR_REG	0x0010
+#define GMAC_SW_TX_QUEUE2_PTR_REG	0x0014
+#define GMAC_SW_TX_QUEUE3_PTR_REG	0x0018
+#define GMAC_SW_TX_QUEUE4_PTR_REG	0x001C
+#define GMAC_SW_TX_QUEUE5_PTR_REG	0x0020
+#define GMAC_SW_TX_QUEUE_PTR_REG(i)	(GMAC_SW_TX_QUEUE0_PTR_REG + 4 * (i))
+#define GMAC_HW_TX_QUEUE0_PTR_REG	0x0024
+#define GMAC_HW_TX_QUEUE1_PTR_REG	0x0028
+#define GMAC_HW_TX_QUEUE2_PTR_REG	0x002C
+#define GMAC_HW_TX_QUEUE3_PTR_REG	0x0030
+#define GMAC_HW_TX_QUEUE_PTR_REG(i)	(GMAC_HW_TX_QUEUE0_PTR_REG + 4 * (i))
+#define GMAC_DMA_TX_FIRST_DESC_REG	0x0038
+#define GMAC_DMA_TX_CURR_DESC_REG	0x003C
+#define GMAC_DMA_TX_DESC_WORD0_REG	0x0040
+#define GMAC_DMA_TX_DESC_WORD1_REG	0x0044
+#define GMAC_DMA_TX_DESC_WORD2_REG	0x0048
+#define GMAC_DMA_TX_DESC_WORD3_REG	0x004C
+#define GMAC_SW_TX_QUEUE_BASE_REG	0x0050
+#define GMAC_HW_TX_QUEUE_BASE_REG	0x0054
+#define GMAC_DMA_RX_FIRST_DESC_REG	0x0058
+#define GMAC_DMA_RX_CURR_DESC_REG	0x005C
+#define GMAC_DMA_RX_DESC_WORD0_REG	0x0060
+#define GMAC_DMA_RX_DESC_WORD1_REG	0x0064
+#define GMAC_DMA_RX_DESC_WORD2_REG	0x0068
+#define GMAC_DMA_RX_DESC_WORD3_REG	0x006C
+#define GMAC_HASH_ENGINE_REG0		0x0070
+#define GMAC_HASH_ENGINE_REG1		0x0074
+/* matching rule 0 Control register 0 */
+#define GMAC_MR0CR0			0x0078
+#define GMAC_MR0CR1			0x007C
+#define GMAC_MR0CR2			0x0080
+#define GMAC_MR1CR0			0x0084
+#define GMAC_MR1CR1			0x0088
+#define GMAC_MR1CR2			0x008C
+#define GMAC_MR2CR0			0x0090
+#define GMAC_MR2CR1			0x0094
+#define GMAC_MR2CR2			0x0098
+#define GMAC_MR3CR0			0x009C
+#define GMAC_MR3CR1			0x00A0
+#define GMAC_MR3CR2			0x00A4
+/* Support Protocol Register 0 */
+#define GMAC_SPR0			0x00A8
+#define GMAC_SPR1			0x00AC
+#define GMAC_SPR2			0x00B0
+#define GMAC_SPR3			0x00B4
+#define GMAC_SPR4			0x00B8
+#define GMAC_SPR5			0x00BC
+#define GMAC_SPR6			0x00C0
+#define GMAC_SPR7			0x00C4
+/* GMAC Hash/Rx/Tx AHB Weighting register */
+#define GMAC_AHB_WEIGHT_REG		0x00C8
+
+/* TOE GMAC 0/1 register */
+#define GMAC_STA_ADD0			0x0000
+#define GMAC_STA_ADD1			0x0004
+#define GMAC_STA_ADD2			0x0008
+#define GMAC_RX_FLTR			0x000c
+#define GMAC_MCAST_FIL0			0x0010
+#define GMAC_MCAST_FIL1			0x0014
+#define GMAC_CONFIG0			0x0018
+#define GMAC_CONFIG1			0x001c
+#define GMAC_CONFIG2			0x0020
+#define GMAC_CONFIG3			0x0024
+#define GMAC_RESERVED			0x0028
+#define GMAC_STATUS			0x002c
+#define GMAC_IN_DISCARDS		0x0030
+#define GMAC_IN_ERRORS			0x0034
+#define GMAC_IN_MCAST			0x0038
+#define GMAC_IN_BCAST			0x003c
+#define GMAC_IN_MAC1			0x0040	/* for STA 1 MAC Address */
+#define GMAC_IN_MAC2			0x0044	/* for STA 2 MAC Address */
+
+#define RX_STATS_NUM	6
+
+/* DMA Queues description Ring Base Address/Size Register (offset 0x0004) */
+union dma_q_base_size {
+	unsigned int bits32;
+	unsigned int base_size;
+};
+
+#define DMA_Q_BASE_MASK		(~0x0f)
+
+/* DMA SKB Buffer register (offset 0x0008) */
+union dma_skb_size {
+	unsigned int bits32;
+	struct bit_0008 {
+		unsigned int sw_skb_size : 16;	/* SW Free poll SKB Size */
+		unsigned int hw_skb_size : 16;	/* HW Free poll SKB Size */
+	} bits;
+};
+
+/* DMA SW Free Queue Read/Write Pointer Register (offset 0x000c) */
+union dma_rwptr {
+	unsigned int bits32;
+	struct bit_000c {
+		unsigned int rptr	: 16;	/* Read Ptr, RO */
+		unsigned int wptr	: 16;	/* Write Ptr, RW */
+	} bits;
+};
+
+/* Interrupt Status Register 0	(offset 0x0020)
+ * Interrupt Mask Register 0	(offset 0x0024)
+ * Interrupt Select Register 0	(offset 0x0028)
+ */
+#define GMAC1_TXDERR_INT_BIT		BIT(31)
+#define GMAC1_TXPERR_INT_BIT		BIT(30)
+#define GMAC0_TXDERR_INT_BIT		BIT(29)
+#define GMAC0_TXPERR_INT_BIT		BIT(28)
+#define GMAC1_RXDERR_INT_BIT		BIT(27)
+#define GMAC1_RXPERR_INT_BIT		BIT(26)
+#define GMAC0_RXDERR_INT_BIT		BIT(25)
+#define GMAC0_RXPERR_INT_BIT		BIT(24)
+#define GMAC1_SWTQ15_FIN_INT_BIT	BIT(23)
+#define GMAC1_SWTQ14_FIN_INT_BIT	BIT(22)
+#define GMAC1_SWTQ13_FIN_INT_BIT	BIT(21)
+#define GMAC1_SWTQ12_FIN_INT_BIT	BIT(20)
+#define GMAC1_SWTQ11_FIN_INT_BIT	BIT(19)
+#define GMAC1_SWTQ10_FIN_INT_BIT	BIT(18)
+#define GMAC0_SWTQ05_FIN_INT_BIT	BIT(17)
+#define GMAC0_SWTQ04_FIN_INT_BIT	BIT(16)
+#define GMAC0_SWTQ03_FIN_INT_BIT	BIT(15)
+#define GMAC0_SWTQ02_FIN_INT_BIT	BIT(14)
+#define GMAC0_SWTQ01_FIN_INT_BIT	BIT(13)
+#define GMAC0_SWTQ00_FIN_INT_BIT	BIT(12)
+#define GMAC1_SWTQ15_EOF_INT_BIT	BIT(11)
+#define GMAC1_SWTQ14_EOF_INT_BIT	BIT(10)
+#define GMAC1_SWTQ13_EOF_INT_BIT	BIT(9)
+#define GMAC1_SWTQ12_EOF_INT_BIT	BIT(8)
+#define GMAC1_SWTQ11_EOF_INT_BIT	BIT(7)
+#define GMAC1_SWTQ10_EOF_INT_BIT	BIT(6)
+#define GMAC0_SWTQ05_EOF_INT_BIT	BIT(5)
+#define GMAC0_SWTQ04_EOF_INT_BIT	BIT(4)
+#define GMAC0_SWTQ03_EOF_INT_BIT	BIT(3)
+#define GMAC0_SWTQ02_EOF_INT_BIT	BIT(2)
+#define GMAC0_SWTQ01_EOF_INT_BIT	BIT(1)
+#define GMAC0_SWTQ00_EOF_INT_BIT	BIT(0)
+
+/* Interrupt Status Register 1	(offset 0x0030)
+ * Interrupt Mask Register 1	(offset 0x0034)
+ * Interrupt Select Register 1	(offset 0x0038)
+ */
+#define TOE_IQ3_FULL_INT_BIT		BIT(31)
+#define TOE_IQ2_FULL_INT_BIT		BIT(30)
+#define TOE_IQ1_FULL_INT_BIT		BIT(29)
+#define TOE_IQ0_FULL_INT_BIT		BIT(28)
+#define TOE_IQ3_INT_BIT			BIT(27)
+#define TOE_IQ2_INT_BIT			BIT(26)
+#define TOE_IQ1_INT_BIT			BIT(25)
+#define TOE_IQ0_INT_BIT			BIT(24)
+#define GMAC1_HWTQ13_EOF_INT_BIT	BIT(23)
+#define GMAC1_HWTQ12_EOF_INT_BIT	BIT(22)
+#define GMAC1_HWTQ11_EOF_INT_BIT	BIT(21)
+#define GMAC1_HWTQ10_EOF_INT_BIT	BIT(20)
+#define GMAC0_HWTQ03_EOF_INT_BIT	BIT(19)
+#define GMAC0_HWTQ02_EOF_INT_BIT	BIT(18)
+#define GMAC0_HWTQ01_EOF_INT_BIT	BIT(17)
+#define GMAC0_HWTQ00_EOF_INT_BIT	BIT(16)
+#define CLASS_RX_INT_BIT(x)		BIT((x + 2))
+#define DEFAULT_Q1_INT_BIT		BIT(1)
+#define DEFAULT_Q0_INT_BIT		BIT(0)
+
+#define TOE_IQ_INT_BITS		(TOE_IQ0_INT_BIT | TOE_IQ1_INT_BIT | \
+				 TOE_IQ2_INT_BIT | TOE_IQ3_INT_BIT)
+#define	TOE_IQ_FULL_BITS	(TOE_IQ0_FULL_INT_BIT | TOE_IQ1_FULL_INT_BIT | \
+				 TOE_IQ2_FULL_INT_BIT | TOE_IQ3_FULL_INT_BIT)
+#define	TOE_IQ_ALL_BITS		(TOE_IQ_INT_BITS | TOE_IQ_FULL_BITS)
+#define TOE_CLASS_RX_INT_BITS	0xfffc
+
+/* Interrupt Status Register 2	(offset 0x0040)
+ * Interrupt Mask Register 2	(offset 0x0044)
+ * Interrupt Select Register 2	(offset 0x0048)
+ */
+#define TOE_QL_FULL_INT_BIT(x)		BIT(x)
+
+/* Interrupt Status Register 3	(offset 0x0050)
+ * Interrupt Mask Register 3	(offset 0x0054)
+ * Interrupt Select Register 3	(offset 0x0058)
+ */
+#define TOE_QH_FULL_INT_BIT(x)		BIT(x - 32)
+
+/* Interrupt Status Register 4	(offset 0x0060)
+ * Interrupt Mask Register 4	(offset 0x0064)
+ * Interrupt Select Register 4	(offset 0x0068)
+ */
+#define GMAC1_RESERVED_INT_BIT		BIT(31)
+#define GMAC1_MIB_INT_BIT		BIT(30)
+#define GMAC1_RX_PAUSE_ON_INT_BIT	BIT(29)
+#define GMAC1_TX_PAUSE_ON_INT_BIT	BIT(28)
+#define GMAC1_RX_PAUSE_OFF_INT_BIT	BIT(27)
+#define GMAC1_TX_PAUSE_OFF_INT_BIT	BIT(26)
+#define GMAC1_RX_OVERRUN_INT_BIT	BIT(25)
+#define GMAC1_STATUS_CHANGE_INT_BIT	BIT(24)
+#define GMAC0_RESERVED_INT_BIT		BIT(23)
+#define GMAC0_MIB_INT_BIT		BIT(22)
+#define GMAC0_RX_PAUSE_ON_INT_BIT	BIT(21)
+#define GMAC0_TX_PAUSE_ON_INT_BIT	BIT(20)
+#define GMAC0_RX_PAUSE_OFF_INT_BIT	BIT(19)
+#define GMAC0_TX_PAUSE_OFF_INT_BIT	BIT(18)
+#define GMAC0_RX_OVERRUN_INT_BIT	BIT(17)
+#define GMAC0_STATUS_CHANGE_INT_BIT	BIT(16)
+#define CLASS_RX_FULL_INT_BIT(x)	BIT(x + 2)
+#define HWFQ_EMPTY_INT_BIT		BIT(1)
+#define SWFQ_EMPTY_INT_BIT		BIT(0)
+
+#define GMAC0_INT_BITS	(GMAC0_RESERVED_INT_BIT | GMAC0_MIB_INT_BIT | \
+			 GMAC0_RX_PAUSE_ON_INT_BIT | \
+			 GMAC0_TX_PAUSE_ON_INT_BIT | \
+			 GMAC0_RX_PAUSE_OFF_INT_BIT | \
+			 GMAC0_TX_PAUSE_OFF_INT_BIT | \
+			 GMAC0_RX_OVERRUN_INT_BIT | \
+			 GMAC0_STATUS_CHANGE_INT_BIT)
+#define GMAC1_INT_BITS	(GMAC1_RESERVED_INT_BIT | GMAC1_MIB_INT_BIT | \
+			 GMAC1_RX_PAUSE_ON_INT_BIT | \
+			 GMAC1_TX_PAUSE_ON_INT_BIT | \
+			 GMAC1_RX_PAUSE_OFF_INT_BIT | \
+			 GMAC1_TX_PAUSE_OFF_INT_BIT | \
+			 GMAC1_RX_OVERRUN_INT_BIT | \
+			 GMAC1_STATUS_CHANGE_INT_BIT)
+
+#define CLASS_RX_FULL_INT_BITS		0xfffc
+
+/* GLOBAL_QUEUE_THRESHOLD_REG	(offset 0x0070) */
+union queue_threshold {
+	unsigned int bits32;
+	struct bit_0070_2 {
+		/*  7:0 Software Free Queue Empty Threshold */
+		unsigned int swfq_empty:8;
+		/* 15:8 Hardware Free Queue Empty Threshold */
+		unsigned int hwfq_empty:8;
+		/* 23:16 */
+		unsigned int intrq:8;
+		/* 31:24 */
+		unsigned int toe_class:8;
+	} bits;
+};
+
+/* GMAC DMA Control Register
+ * GMAC0 offset 0x8000
+ * GMAC1 offset 0xC000
+ */
+union gmac_dma_ctrl {
+	unsigned int bits32;
+	struct bit_8000 {
+		/* bit 1:0 Peripheral Bus Width */
+		unsigned int td_bus:2;
+		/* bit 3:2 TxDMA max burst size for every AHB request */
+		unsigned int td_burst_size:2;
+		/* bit 7:4 TxDMA protection control */
+		unsigned int td_prot:4;
+		/* bit 9:8 Peripheral Bus Width */
+		unsigned int rd_bus:2;
+		/* bit 11:10 DMA max burst size for every AHB request */
+		unsigned int rd_burst_size:2;
+		/* bit 15:12 DMA Protection Control */
+		unsigned int rd_prot:4;
+		/* bit 17:16 */
+		unsigned int rd_insert_bytes:2;
+		/* bit 27:18 */
+		unsigned int reserved:10;
+		/* bit 28 1: Drop, 0: Accept */
+		unsigned int drop_small_ack:1;
+		/* bit 29 Loopback TxDMA to RxDMA */
+		unsigned int loopback:1;
+		/* bit 30 Tx DMA Enable */
+		unsigned int td_enable:1;
+		/* bit 31 Rx DMA Enable */
+		unsigned int rd_enable:1;
+	} bits;
+};
+
+/* GMAC Tx Weighting Control Register 0
+ * GMAC0 offset 0x8004
+ * GMAC1 offset 0xC004
+ */
+union gmac_tx_wcr0 {
+	unsigned int bits32;
+	struct bit_8004 {
+		/* bit 5:0 HW TX Queue 3 */
+		unsigned int hw_tq0:6;
+		/* bit 11:6 HW TX Queue 2 */
+		unsigned int hw_tq1:6;
+		/* bit 17:12 HW TX Queue 1 */
+		unsigned int hw_tq2:6;
+		/* bit 23:18 HW TX Queue 0 */
+		unsigned int hw_tq3:6;
+		/* bit 31:24 */
+		unsigned int reserved:8;
+	} bits;
+};
+
+/* GMAC Tx Weighting Control Register 1
+ * GMAC0 offset 0x8008
+ * GMAC1 offset 0xC008
+ */
+union gmac_tx_wcr1 {
+	unsigned int bits32;
+	struct bit_8008 {
+		/* bit 4:0 SW TX Queue 0 */
+		unsigned int sw_tq0:5;
+		/* bit 9:5 SW TX Queue 1 */
+		unsigned int sw_tq1:5;
+		/* bit 14:10 SW TX Queue 2 */
+		unsigned int sw_tq2:5;
+		/* bit 19:15 SW TX Queue 3 */
+		unsigned int sw_tq3:5;
+		/* bit 24:20 SW TX Queue 4 */
+		unsigned int sw_tq4:5;
+		/* bit 29:25 SW TX Queue 5 */
+		unsigned int sw_tq5:5;
+		/* bit 31:30 */
+		unsigned int reserved:2;
+	} bits;
+};
+
+/* GMAC DMA Tx Description Word 0 Register
+ * GMAC0 offset 0x8040
+ * GMAC1 offset 0xC040
+ */
+union gmac_txdesc_0 {
+	unsigned int bits32;
+	struct bit_8040 {
+		/* bit 15:0 Transfer size */
+		unsigned int buffer_size:16;
+		/* bit 21:16 number of descriptors used for the current frame */
+		unsigned int desc_count:6;
+		/* bit 22 Tx Status, 1: Successful 0: Failed */
+		unsigned int status_tx_ok:1;
+		/* bit 28:23 Tx Status, Reserved bits */
+		unsigned int status_rvd:6;
+		/* bit 29 protocol error during processing this descriptor */
+		unsigned int perr:1;
+		/* bit 30 data error during processing this descriptor */
+		unsigned int derr:1;
+		/* bit 31 */
+		unsigned int reserved:1;
+	} bits;
+};
+
+/* GMAC DMA Tx Description Word 1 Register
+ * GMAC0 offset 0x8044
+ * GMAC1 offset 0xC044
+ */
+union gmac_txdesc_1 {
+	unsigned int bits32;
+	struct txdesc_word1 {
+		/* bit 15: 0 Tx Frame Byte Count */
+		unsigned int byte_count:16;
+		/* bit 16 TSS segmentation use MTU setting */
+		unsigned int mtu_enable:1;
+		/* bit 17 IPV4 Header Checksum Enable */
+		unsigned int ip_chksum:1;
+		/* bit 18 IPV6 Tx Enable */
+		unsigned int ipv6_enable:1;
+		/* bit 19 TCP Checksum Enable */
+		unsigned int tcp_chksum:1;
+		/* bit 20 UDP Checksum Enable */
+		unsigned int udp_chksum:1;
+		/* bit 21 Bypass HW offload engine */
+		unsigned int bypass_tss:1;
+		/* bit 22 Don't update IP length field */
+		unsigned int ip_fixed_len:1;
+		/* bit 31:23 Tx Flag, Reserved */
+		unsigned int reserved:9;
+	} bits;
+};
+
+#define TSS_IP_FIXED_LEN_BIT	BIT(22)
+#define TSS_BYPASS_BIT		BIT(21)
+#define TSS_UDP_CHKSUM_BIT	BIT(20)
+#define TSS_TCP_CHKSUM_BIT	BIT(19)
+#define TSS_IPV6_ENABLE_BIT	BIT(18)
+#define TSS_IP_CHKSUM_BIT	BIT(17)
+#define TSS_MTU_ENABLE_BIT	BIT(16)
+
+#define TSS_CHECKUM_ENABLE	\
+	(TSS_IP_CHKSUM_BIT | TSS_IPV6_ENABLE_BIT | \
+	 TSS_TCP_CHKSUM_BIT | TSS_UDP_CHKSUM_BIT)
+
+/* GMAC DMA Tx Description Word 2 Register
+ * GMAC0 offset 0x8048
+ * GMAC1 offset 0xC048
+ */
+union gmac_txdesc_2 {
+	unsigned int	bits32;
+	unsigned int	buf_adr;
+};
+
+/* GMAC DMA Tx Description Word 3 Register
+ * GMAC0 offset 0x804C
+ * GMAC1 offset 0xC04C
+ */
+union gmac_txdesc_3 {
+	unsigned int bits32;
+	struct txdesc_word3 {
+		/* bit 12: 0 Tx Frame Byte Count */
+		unsigned int mtu_size:13;
+		/* bit 28:13 */
+		unsigned int reserved:16;
+		/* bit 29 End of frame interrupt enable */
+		unsigned int eofie:1;
+		/* bit 31:30 11: only one, 10: first, 01: last, 00: linking */
+		unsigned int sof_eof:2;
+	} bits;
+};
+
+#define SOF_EOF_BIT_MASK	0x3fffffff
+#define SOF_BIT			0x80000000
+#define EOF_BIT			0x40000000
+#define EOFIE_BIT		BIT(29)
+#define MTU_SIZE_BIT_MASK	0x1fff
+
+/* GMAC Tx Descriptor */
+struct gmac_txdesc {
+	union gmac_txdesc_0 word0;
+	union gmac_txdesc_1 word1;
+	union gmac_txdesc_2 word2;
+	union gmac_txdesc_3 word3;
+};
+
+/* GMAC DMA Rx Description Word 0 Register
+ * GMAC0 offset 0x8060
+ * GMAC1 offset 0xC060
+ */
+union gmac_rxdesc_0 {
+	unsigned int bits32;
+	struct bit_8060 {
+		/* bit 15:0 number of descriptors used for the current frame */
+		unsigned int buffer_size:16;
+		/* bit 21:16 number of descriptors used for the current frame */
+		unsigned int desc_count:6;
+		/* bit 24:22 Status of rx frame */
+		unsigned int status:4;
+		/* bit 28:26 Check Sum Status */
+		unsigned int chksum_status:3;
+		/* bit 29 protocol error during processing this descriptor */
+		unsigned int perr:1;
+		/* bit 30 data error during processing this descriptor */
+		unsigned int derr:1;
+		/* bit 31 TOE/CIS Queue Full dropped packet to default queue */
+		unsigned int drop:1;
+	} bits;
+};
+
+#define	GMAC_RXDESC_0_T_derr			BIT(30)
+#define	GMAC_RXDESC_0_T_perr			BIT(29)
+#define	GMAC_RXDESC_0_T_chksum_status(x)	BIT(x + 26)
+#define	GMAC_RXDESC_0_T_status(x)		BIT(x + 22)
+#define	GMAC_RXDESC_0_T_desc_count(x)		BIT(x + 16)
+
+#define	RX_CHKSUM_IP_UDP_TCP_OK			0
+#define	RX_CHKSUM_IP_OK_ONLY			1
+#define	RX_CHKSUM_NONE				2
+#define	RX_CHKSUM_IP_ERR_UNKNOWN		4
+#define	RX_CHKSUM_IP_ERR			5
+#define	RX_CHKSUM_TCP_UDP_ERR			6
+#define RX_CHKSUM_NUM				8
+
+#define RX_STATUS_GOOD_FRAME			0
+#define RX_STATUS_TOO_LONG_GOOD_CRC		1
+#define RX_STATUS_RUNT_FRAME			2
+#define RX_STATUS_SFD_NOT_FOUND			3
+#define RX_STATUS_CRC_ERROR			4
+#define RX_STATUS_TOO_LONG_BAD_CRC		5
+#define RX_STATUS_ALIGNMENT_ERROR		6
+#define RX_STATUS_TOO_LONG_BAD_ALIGN		7
+#define RX_STATUS_RX_ERR			8
+#define RX_STATUS_DA_FILTERED			9
+#define RX_STATUS_BUFFER_FULL			10
+#define RX_STATUS_NUM				16
+
+#define RX_ERROR_LENGTH(s) \
+	((s) == RX_STATUS_TOO_LONG_GOOD_CRC || \
+	 (s) == RX_STATUS_TOO_LONG_BAD_CRC || \
+	 (s) == RX_STATUS_TOO_LONG_BAD_ALIGN)
+#define RX_ERROR_OVER(s) \
+	((s) == RX_STATUS_BUFFER_FULL)
+#define RX_ERROR_CRC(s) \
+	((s) == RX_STATUS_CRC_ERROR || \
+	 (s) == RX_STATUS_TOO_LONG_BAD_CRC)
+#define RX_ERROR_FRAME(s) \
+	((s) == RX_STATUS_ALIGNMENT_ERROR || \
+	 (s) == RX_STATUS_TOO_LONG_BAD_ALIGN)
+#define RX_ERROR_FIFO(s) \
+	(0)
+
+/* GMAC DMA Rx Description Word 1 Register
+ * GMAC0 offset 0x8064
+ * GMAC1 offset 0xC064
+ */
+union gmac_rxdesc_1 {
+	unsigned int bits32;
+	struct rxdesc_word1 {
+		/* bit 15: 0 Rx Frame Byte Count */
+		unsigned int byte_count:16;
+		/* bit 31:16 Software ID */
+		unsigned int sw_id:16;
+	} bits;
+};
+
+/* GMAC DMA Rx Description Word 2 Register
+ * GMAC0 offset 0x8068
+ * GMAC1 offset 0xC068
+ */
+union gmac_rxdesc_2 {
+	unsigned int	bits32;
+	unsigned int	buf_adr;
+};
+
+#define RX_INSERT_NONE		0
+#define RX_INSERT_1_BYTE	1
+#define RX_INSERT_2_BYTE	2
+#define RX_INSERT_3_BYTE	3
+
+/* GMAC DMA Rx Description Word 3 Register
+ * GMAC0 offset 0x806C
+ * GMAC1 offset 0xC06C
+ */
+union gmac_rxdesc_3 {
+	unsigned int bits32;
+	struct rxdesc_word3 {
+		/* bit 7: 0 L3 data offset */
+		unsigned int l3_offset:8;
+		/* bit 15: 8 L4 data offset */
+		unsigned int l4_offset:8;
+		/* bit 23: 16 L7 data offset */
+		unsigned int l7_offset:8;
+		/* bit 24 Duplicated ACK detected */
+		unsigned int dup_ack:1;
+		/* bit 25 abnormal case found */
+		unsigned int abnormal:1;
+		/* bit 26 IPV4 option or IPV6 extension header */
+		unsigned int option:1;
+		/* bit 27 Out of Sequence packet */
+		unsigned int out_of_seq:1;
+		/* bit 28 Control Flag is present */
+		unsigned int ctrl_flag:1;
+		/* bit 29 End of frame interrupt enable */
+		unsigned int eofie:1;
+		/* bit 31:30 11: only one, 10: first, 01: last, 00: linking */
+		unsigned int sof_eof:2;
+	} bits;
+};
+
+/* GMAC Rx Descriptor */
+struct gmac_rxdesc {
+	union gmac_rxdesc_0 word0;
+	union gmac_rxdesc_1 word1;
+	union gmac_rxdesc_2 word2;
+	union gmac_rxdesc_3 word3;
+};
+
+/* GMAC Matching Rule Control Register 0
+ * GMAC0 offset 0x8078
+ * GMAC1 offset 0xC078
+ */
+#define MR_L2_BIT		BIT(31)
+#define MR_L3_BIT		BIT(30)
+#define MR_L4_BIT		BIT(29)
+#define MR_L7_BIT		BIT(28)
+#define MR_PORT_BIT		BIT(27)
+#define MR_PRIORITY_BIT		BIT(26)
+#define MR_DA_BIT		BIT(23)
+#define MR_SA_BIT		BIT(22)
+#define MR_ETHER_TYPE_BIT	BIT(21)
+#define MR_VLAN_BIT		BIT(20)
+#define MR_PPPOE_BIT		BIT(19)
+#define MR_IP_VER_BIT		BIT(15)
+#define MR_IP_HDR_LEN_BIT	BIT(14)
+#define MR_FLOW_LABLE_BIT	BIT(13)
+#define MR_TOS_TRAFFIC_BIT	BIT(12)
+#define MR_SPR_BIT(x)		BIT(x)
+#define MR_SPR_BITS		0xff
+
+/* GMAC_AHB_WEIGHT registers
+ * GMAC0 offset 0x80C8
+ * GMAC1 offset 0xC0C8
+ */
+union gmac_ahb_weight {
+	unsigned int bits32;
+	struct bit_80C8 {
+		/* 4:0 */
+		unsigned int hash_weight:5;
+		/* 9:5 */
+		unsigned int rx_weight:5;
+		/* 14:10 */
+		unsigned int tx_weight:5;
+		/* 19:15 Rx Data Pre Request FIFO Threshold */
+		unsigned int pre_req:5;
+		/* 24:20 DMA TqCtrl to Start tqDV FIFO Threshold */
+		unsigned int tq_dv_threshold:5;
+		/* 31:25 */
+		unsigned int reserved:7;
+	} bits;
+};
+
+/* GMAC RX FLTR
+ * GMAC0 Offset 0xA00C
+ * GMAC1 Offset 0xE00C
+ */
+union gmac_rx_fltr {
+	unsigned int bits32;
+	struct bit1_000c {
+		/* Enable receive of unicast frames that are sent to STA
+		 * address
+		 */
+		unsigned int unicast:1;
+		/* Enable receive of multicast frames that pass multicast
+		 * filter
+		 */
+		unsigned int multicast:1;
+		/* Enable receive of broadcast frames */
+		unsigned int broadcast:1;
+		/* Enable receive of all frames */
+		unsigned int promiscuous:1;
+		/* Enable receive of all error frames */
+		unsigned int error:1;
+		unsigned int reserved:27;
+	} bits;
+};
+
+/* GMAC Configuration 0
+ * GMAC0 Offset 0xA018
+ * GMAC1 Offset 0xE018
+ */
+union gmac_config0 {
+	unsigned int bits32;
+	struct bit1_0018 {
+		/* 0: disable transmit */
+		unsigned int dis_tx:1;
+		/* 1: disable receive */
+		unsigned int dis_rx:1;
+		/* 2: transmit data loopback enable */
+		unsigned int loop_back:1;
+		/* 3: flow control also trigged by Rx queues */
+		unsigned int flow_ctrl:1;
+		/* 4-7: adjust IFG from 96+/-56 */
+		unsigned int adj_ifg:4;
+		/* 8-10 maximum receive frame length allowed */
+		unsigned int max_len:3;
+		/* 11: disable back-off function */
+		unsigned int dis_bkoff:1;
+		/* 12: disable 16 collisions abort function */
+		unsigned int dis_col:1;
+		/* 13: speed up timers in simulation */
+		unsigned int sim_test:1;
+		/* 14: RX flow control enable */
+		unsigned int rx_fc_en:1;
+		/* 15: TX flow control enable */
+		unsigned int tx_fc_en:1;
+		/* 16: RGMII in-band status enable */
+		unsigned int rgmii_en:1;
+		/* 17: IPv4 RX Checksum enable */
+		unsigned int ipv4_rx_chksum:1;
+		/* 18: IPv6 RX Checksum enable */
+		unsigned int ipv6_rx_chksum:1;
+		/* 19: Remove Rx VLAN tag */
+		unsigned int rx_tag_remove:1;
+		/* 20 */
+		unsigned int rgmm_edge:1;
+		/* 21 */
+		unsigned int rxc_inv:1;
+		/* 22 */
+		unsigned int ipv6_exthdr_order:1;
+		/* 23 */
+		unsigned int rx_err_detect:1;
+		/* 24 */
+		unsigned int port0_chk_hwq:1;
+		/* 25 */
+		unsigned int port1_chk_hwq:1;
+		/* 26 */
+		unsigned int port0_chk_toeq:1;
+		/* 27 */
+		unsigned int port1_chk_toeq:1;
+		/* 28 */
+		unsigned int port0_chk_classq:1;
+		/* 29 */
+		unsigned int port1_chk_classq:1;
+		/* 30, 31 */
+		unsigned int reserved:2;
+	} bits;
+};
+
+#define CONFIG0_TX_RX_DISABLE	(BIT(1) | BIT(0))
+#define CONFIG0_RX_CHKSUM	(BIT(18) | BIT(17))
+#define CONFIG0_FLOW_RX		BIT(14)
+#define CONFIG0_FLOW_TX		BIT(15)
+#define CONFIG0_FLOW_TX_RX	(BIT(14) | BIT(15))
+#define CONFIG0_FLOW_CTL	(BIT(14) | BIT(15))
+
+#define CONFIG0_MAXLEN_SHIFT	8
+#define CONFIG0_MAXLEN_MASK	(7 << CONFIG0_MAXLEN_SHIFT)
+#define  CONFIG0_MAXLEN_1536	0
+#define  CONFIG0_MAXLEN_1518	1
+#define  CONFIG0_MAXLEN_1522	2
+#define  CONFIG0_MAXLEN_1542	3
+#define  CONFIG0_MAXLEN_9k	4	/* 9212 */
+#define  CONFIG0_MAXLEN_10k	5	/* 10236 */
+#define  CONFIG0_MAXLEN_1518__6	6
+#define  CONFIG0_MAXLEN_1518__7	7
+
+/* GMAC Configuration 1
+ * GMAC0 Offset 0xA01C
+ * GMAC1 Offset 0xE01C
+ */
+union gmac_config1 {
+	unsigned int bits32;
+	struct bit1_001c {
+		/* Flow control set threshold */
+		unsigned int set_threshold:8;
+		/* Flow control release threshold */
+		unsigned int rel_threshold:8;
+		unsigned int reserved:16;
+	} bits;
+};
+
+#define GMAC_FLOWCTRL_SET_MAX		32
+#define GMAC_FLOWCTRL_SET_MIN		0
+#define GMAC_FLOWCTRL_RELEASE_MAX	32
+#define GMAC_FLOWCTRL_RELEASE_MIN	0
+
+/* GMAC Configuration 2
+ * GMAC0 Offset 0xA020
+ * GMAC1 Offset 0xE020
+ */
+union gmac_config2 {
+	unsigned int bits32;
+	struct bit1_0020 {
+		/* Flow control set threshold */
+		unsigned int set_threshold:16;
+		/* Flow control release threshold */
+		unsigned int rel_threshold:16;
+	} bits;
+};
+
+/* GMAC Configuration 3
+ * GMAC0 Offset 0xA024
+ * GMAC1 Offset 0xE024
+ */
+union gmac_config3 {
+	unsigned int bits32;
+	struct bit1_0024 {
+		/* Flow control set threshold */
+		unsigned int set_threshold:16;
+		/* Flow control release threshold */
+		unsigned int rel_threshold:16;
+	} bits;
+};
+
+/* GMAC STATUS
+ * GMAC0 Offset 0xA02C
+ * GMAC1 Offset 0xE02C
+ */
+union gmac_status {
+	unsigned int bits32;
+	struct bit1_002c {
+		/* Link status */
+		unsigned int link:1;
+		/* Link speed(00->2.5M 01->25M 10->125M) */
+		unsigned int speed:2;
+		/* Duplex mode */
+		unsigned int duplex:1;
+		unsigned int reserved_1:1;
+		/* PHY interface type */
+		unsigned int mii_rmii:2;
+		unsigned int reserved_2:25;
+	} bits;
+};
+
+#define GMAC_SPEED_10			0
+#define GMAC_SPEED_100			1
+#define GMAC_SPEED_1000			2
+
+#define GMAC_PHY_MII			0
+#define GMAC_PHY_GMII			1
+#define GMAC_PHY_RGMII_100_10		2
+#define GMAC_PHY_RGMII_1000		3
+
+/* Queue Header
+ *	(1) TOE Queue Header
+ *	(2) Non-TOE Queue Header
+ *	(3) Interrupt Queue Header
+ *
+ * memory Layout
+ *	TOE Queue Header
+ *		     0x60003000 +---------------------------+ 0x0000
+ *				|     TOE Queue 0 Header    |
+ *				|         8 * 4 Bytes	    |
+ *				+---------------------------+ 0x0020
+ *				|     TOE Queue 1 Header    |
+ *				|         8 * 4 Bytes	    |
+ *				+---------------------------+ 0x0040
+ *				|          ......           |
+ *				|                           |
+ *				+---------------------------+
+ *
+ *	Non TOE Queue Header
+ *		     0x60002000 +---------------------------+ 0x0000
+ *				|   Default Queue 0 Header  |
+ *				|         2 * 4 Bytes       |
+ *				+---------------------------+ 0x0008
+ *				|   Default Queue 1 Header  |
+ *				|         2 * 4 Bytes       |
+ *				+---------------------------+ 0x0010
+ *				|   Classification Queue 0  |
+ *				|	  2 * 4 Bytes       |
+ *				+---------------------------+
+ *				|   Classification Queue 1  |
+ *				|	  2 * 4 Bytes       |
+ *				+---------------------------+ (n * 8 + 0x10)
+ *				|		...	    |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+ (13 * 8 + 0x10)
+ *				|   Classification Queue 13 |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+ 0x80
+ *				|      Interrupt Queue 0    |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+
+ *				|      Interrupt Queue 1    |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+
+ *				|      Interrupt Queue 2    |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+
+ *				|      Interrupt Queue 3    |
+ *				|	  2 * 4 Bytes	    |
+ *				+---------------------------+
+ *
+ */
+#define TOE_QUEUE_HDR_ADDR(n)	(TOE_TOE_QUE_HDR_BASE + n * 32)
+#define TOE_Q_HDR_AREA_END	(TOE_QUEUE_HDR_ADDR(TOE_TOE_QUEUE_MAX + 1))
+#define TOE_DEFAULT_Q_HDR_BASE(x) (TOE_NONTOE_QUE_HDR_BASE + 0x08 * (x))
+#define TOE_CLASS_Q_HDR_BASE	(TOE_NONTOE_QUE_HDR_BASE + 0x10)
+#define TOE_INTR_Q_HDR_BASE	(TOE_NONTOE_QUE_HDR_BASE + 0x80)
+#define INTERRUPT_QUEUE_HDR_ADDR(n) (TOE_INTR_Q_HDR_BASE + n * 8)
+#define NONTOE_Q_HDR_AREA_END (INTERRUPT_QUEUE_HDR_ADDR(TOE_INTR_QUEUE_MAX + 1))
+
+/* NONTOE Queue Header Word 0 */
+union nontoe_qhdr0 {
+	unsigned int bits32;
+	unsigned int base_size;
+};
+
+#define NONTOE_QHDR0_BASE_MASK	(~0x0f)
+
+/* NONTOE Queue Header Word 1 */
+union nontoe_qhdr1 {
+	unsigned int bits32;
+	struct bit_nonqhdr1 {
+		/* bit 15:0 */
+		unsigned int rptr:16;
+		/* bit 31:16 */
+		unsigned int wptr:16;
+	} bits;
+};
+
+/* Non-TOE Queue Header */
+struct nontoe_qhdr {
+	union nontoe_qhdr0 word0;
+	union nontoe_qhdr1 word1;
+};
+
+#endif /* _GEMINI_ETHERNET_H */