rocker: introduce rocker switch driver

This patch introduces the first driver to benefit from the switchdev
infrastructure and to implement newly introduced switch ndos. This is a
driver for emulated switch chip implemented in qemu:
https://github.com/sfeldma/qemu-rocker/

This patch is a result of joint work with Scott Feldman.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Reviewed-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 2521 insertions, 0 deletions

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 1ed1fbba5d58..df76050d0a9d 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -155,6 +155,7 @@ source "drivers/net/ethernet/qualcomm/Kconfig"
 source "drivers/net/ethernet/realtek/Kconfig"
 source "drivers/net/ethernet/renesas/Kconfig"
 source "drivers/net/ethernet/rdc/Kconfig"
+source "drivers/net/ethernet/rocker/Kconfig"
 
 config S6GMAC
 	tristate "S6105 GMAC ethernet support"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 6e0b629e9859..bf56f8b36e90 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_NET_VENDOR_QUALCOMM) += qualcomm/
 obj-$(CONFIG_NET_VENDOR_REALTEK) += realtek/
 obj-$(CONFIG_SH_ETH) += renesas/
 obj-$(CONFIG_NET_VENDOR_RDC) += rdc/
+obj-$(CONFIG_NET_VENDOR_ROCKER) += rocker/
 obj-$(CONFIG_S6GMAC) += s6gmac.o
 obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
 obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
diff --git a/drivers/net/ethernet/rocker/Kconfig b/drivers/net/ethernet/rocker/Kconfig
new file mode 100644
index 000000000000..11a850eab628
--- /dev/null
+++ b/drivers/net/ethernet/rocker/Kconfig
@@ -0,0 +1,27 @@
+#
+# Rocker device configuration
+#
+
+config NET_VENDOR_ROCKER
+	bool "Rocker devices"
+	default y
+	---help---
+	  If you have a network device belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Rocker devices. If you say Y, you will be asked for
+	  your specific card in the following questions.
+
+if NET_VENDOR_ROCKER
+
+config ROCKER
+	tristate "Rocker switch driver (EXPERIMENTAL)"
+	depends on PCI && NET_SWITCHDEV
+	---help---
+	  This driver supports Rocker switch device.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rocker.
+
+endif # NET_VENDOR_ROCKER
diff --git a/drivers/net/ethernet/rocker/Makefile b/drivers/net/ethernet/rocker/Makefile
new file mode 100644
index 000000000000..f85fb12f36f1
--- /dev/null
+++ b/drivers/net/ethernet/rocker/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Rocker network device drivers.
+#
+
+obj-$(CONFIG_ROCKER) += rocker.o
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
new file mode 100644
index 000000000000..a53011c2b4aa
--- /dev/null
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -0,0 +1,2060 @@
+/*
+ * drivers/net/ethernet/rocker/rocker.c - Rocker switch device driver
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/spinlock.h>
+#include <linux/crc32.h>
+#include <linux/sort.h>
+#include <linux/random.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/switchdev.h>
+#include <net/rtnetlink.h>
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
+#include <generated/utsrelease.h>
+
+#include "rocker.h"
+
+static const char rocker_driver_name[] = "rocker";
+
+static const struct pci_device_id rocker_pci_id_table[] = {
+	{PCI_VDEVICE(REDHAT, PCI_DEVICE_ID_REDHAT_ROCKER), 0},
+	{0, }
+};
+
+struct rocker_desc_info {
+	char *data; /* mapped */
+	size_t data_size;
+	size_t tlv_size;
+	struct rocker_desc *desc;
+	DEFINE_DMA_UNMAP_ADDR(mapaddr);
+};
+
+struct rocker_dma_ring_info {
+	size_t size;
+	u32 head;
+	u32 tail;
+	struct rocker_desc *desc; /* mapped */
+	dma_addr_t mapaddr;
+	struct rocker_desc_info *desc_info;
+	unsigned int type;
+};
+
+struct rocker;
+
+struct rocker_port {
+	struct net_device *dev;
+	struct rocker *rocker;
+	unsigned int port_number;
+	u32 lport;
+	struct napi_struct napi_tx;
+	struct napi_struct napi_rx;
+	struct rocker_dma_ring_info tx_ring;
+	struct rocker_dma_ring_info rx_ring;
+};
+
+struct rocker {
+	struct pci_dev *pdev;
+	u8 __iomem *hw_addr;
+	struct msix_entry *msix_entries;
+	unsigned int port_count;
+	struct rocker_port **ports;
+	struct {
+		u64 id;
+	} hw;
+	spinlock_t cmd_ring_lock;
+	struct rocker_dma_ring_info cmd_ring;
+	struct rocker_dma_ring_info event_ring;
+};
+
+struct rocker_wait {
+	wait_queue_head_t wait;
+	bool done;
+	bool nowait;
+};
+
+static void rocker_wait_reset(struct rocker_wait *wait)
+{
+	wait->done = false;
+	wait->nowait = false;
+}
+
+static void rocker_wait_init(struct rocker_wait *wait)
+{
+	init_waitqueue_head(&wait->wait);
+	rocker_wait_reset(wait);
+}
+
+static struct rocker_wait *rocker_wait_create(gfp_t gfp)
+{
+	struct rocker_wait *wait;
+
+	wait = kmalloc(sizeof(*wait), gfp);
+	if (!wait)
+		return NULL;
+	rocker_wait_init(wait);
+	return wait;
+}
+
+static void rocker_wait_destroy(struct rocker_wait *work)
+{
+	kfree(work);
+}
+
+static bool rocker_wait_event_timeout(struct rocker_wait *wait,
+				      unsigned long timeout)
+{
+	wait_event_timeout(wait->wait, wait->done, HZ / 10);
+	if (!wait->done)
+		return false;
+	return true;
+}
+
+static void rocker_wait_wake_up(struct rocker_wait *wait)
+{
+	wait->done = true;
+	wake_up(&wait->wait);
+}
+
+static u32 rocker_msix_vector(struct rocker *rocker, unsigned int vector)
+{
+	return rocker->msix_entries[vector].vector;
+}
+
+static u32 rocker_msix_tx_vector(struct rocker_port *rocker_port)
+{
+	return rocker_msix_vector(rocker_port->rocker,
+				  ROCKER_MSIX_VEC_TX(rocker_port->port_number));
+}
+
+static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port)
+{
+	return rocker_msix_vector(rocker_port->rocker,
+				  ROCKER_MSIX_VEC_RX(rocker_port->port_number));
+}
+
+#define rocker_write32(rocker, reg, val)	\
+	writel((val), (rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_read32(rocker, reg)	\
+	readl((rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_write64(rocker, reg, val)	\
+	writeq((val), (rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_read64(rocker, reg)	\
+	readq((rocker)->hw_addr + (ROCKER_ ## reg))
+
+/*****************************
+ * HW basic testing functions
+ *****************************/
+
+static int rocker_reg_test(struct rocker *rocker)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	u64 test_reg;
+	u64 rnd;
+
+	rnd = prandom_u32();
+	rnd >>= 1;
+	rocker_write32(rocker, TEST_REG, rnd);
+	test_reg = rocker_read32(rocker, TEST_REG);
+	if (test_reg != rnd * 2) {
+		dev_err(&pdev->dev, "unexpected 32bit register value %08llx, expected %08llx\n",
+			test_reg, rnd * 2);
+		return -EIO;
+	}
+
+	rnd = prandom_u32();
+	rnd <<= 31;
+	rnd |= prandom_u32();
+	rocker_write64(rocker, TEST_REG64, rnd);
+	test_reg = rocker_read64(rocker, TEST_REG64);
+	if (test_reg != rnd * 2) {
+		dev_err(&pdev->dev, "unexpected 64bit register value %16llx, expected %16llx\n",
+			test_reg, rnd * 2);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait,
+			       u32 test_type, dma_addr_t dma_handle,
+			       unsigned char *buf, unsigned char *expect,
+			       size_t size)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	int i;
+
+	rocker_wait_reset(wait);
+	rocker_write32(rocker, TEST_DMA_CTRL, test_type);
+
+	if (!rocker_wait_event_timeout(wait, HZ / 10)) {
+		dev_err(&pdev->dev, "no interrupt received within a timeout\n");
+		return -EIO;
+	}
+
+	for (i = 0; i < size; i++) {
+		if (buf[i] != expect[i]) {
+			dev_err(&pdev->dev, "unexpected memory content %02x at byte %x\n, %02x expected",
+				buf[i], i, expect[i]);
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+#define ROCKER_TEST_DMA_BUF_SIZE (PAGE_SIZE * 4)
+#define ROCKER_TEST_DMA_FILL_PATTERN 0x96
+
+static int rocker_dma_test_offset(struct rocker *rocker,
+				  struct rocker_wait *wait, int offset)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	unsigned char *alloc;
+	unsigned char *buf;
+	unsigned char *expect;
+	dma_addr_t dma_handle;
+	int i;
+	int err;
+
+	alloc = kzalloc(ROCKER_TEST_DMA_BUF_SIZE * 2 + offset,
+			GFP_KERNEL | GFP_DMA);
+	if (!alloc)
+		return -ENOMEM;
+	buf = alloc + offset;
+	expect = buf + ROCKER_TEST_DMA_BUF_SIZE;
+
+	dma_handle = pci_map_single(pdev, buf, ROCKER_TEST_DMA_BUF_SIZE,
+				    PCI_DMA_BIDIRECTIONAL);
+	if (pci_dma_mapping_error(pdev, dma_handle)) {
+		err = -EIO;
+		goto free_alloc;
+	}
+
+	rocker_write64(rocker, TEST_DMA_ADDR, dma_handle);
+	rocker_write32(rocker, TEST_DMA_SIZE, ROCKER_TEST_DMA_BUF_SIZE);
+
+	memset(expect, ROCKER_TEST_DMA_FILL_PATTERN, ROCKER_TEST_DMA_BUF_SIZE);
+	err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_FILL,
+				  dma_handle, buf, expect,
+				  ROCKER_TEST_DMA_BUF_SIZE);
+	if (err)
+		goto unmap;
+
+	memset(expect, 0, ROCKER_TEST_DMA_BUF_SIZE);
+	err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_CLEAR,
+				  dma_handle, buf, expect,
+				  ROCKER_TEST_DMA_BUF_SIZE);
+	if (err)
+		goto unmap;
+
+	prandom_bytes(buf, ROCKER_TEST_DMA_BUF_SIZE);
+	for (i = 0; i < ROCKER_TEST_DMA_BUF_SIZE; i++)
+		expect[i] = ~buf[i];
+	err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_INVERT,
+				  dma_handle, buf, expect,
+				  ROCKER_TEST_DMA_BUF_SIZE);
+	if (err)
+		goto unmap;
+
+unmap:
+	pci_unmap_single(pdev, dma_handle, ROCKER_TEST_DMA_BUF_SIZE,
+			 PCI_DMA_BIDIRECTIONAL);
+free_alloc:
+	kfree(alloc);
+
+	return err;
+}
+
+static int rocker_dma_test(struct rocker *rocker, struct rocker_wait *wait)
+{
+	int i;
+	int err;
+
+	for (i = 0; i < 8; i++) {
+		err = rocker_dma_test_offset(rocker, wait, i);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static irqreturn_t rocker_test_irq_handler(int irq, void *dev_id)
+{
+	struct rocker_wait *wait = dev_id;
+
+	rocker_wait_wake_up(wait);
+
+	return IRQ_HANDLED;
+}
+
+static int rocker_basic_hw_test(struct rocker *rocker)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	struct rocker_wait wait;
+	int err;
+
+	err = rocker_reg_test(rocker);
+	if (err) {
+		dev_err(&pdev->dev, "reg test failed\n");
+		return err;
+	}
+
+	err = request_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_TEST),
+			  rocker_test_irq_handler, 0,
+			  rocker_driver_name, &wait);
+	if (err) {
+		dev_err(&pdev->dev, "cannot assign test irq\n");
+		return err;
+	}
+
+	rocker_wait_init(&wait);
+	rocker_write32(rocker, TEST_IRQ, ROCKER_MSIX_VEC_TEST);
+
+	if (!rocker_wait_event_timeout(&wait, HZ / 10)) {
+		dev_err(&pdev->dev, "no interrupt received within a timeout\n");
+		err = -EIO;
+		goto free_irq;
+	}
+
+	err = rocker_dma_test(rocker, &wait);
+	if (err)
+		dev_err(&pdev->dev, "dma test failed\n");
+
+free_irq:
+	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_TEST), &wait);
+	return err;
+}
+
+/******
+ * TLV
+ ******/
+
+#define ROCKER_TLV_ALIGNTO 8U
+#define ROCKER_TLV_ALIGN(len) \
+	(((len) + ROCKER_TLV_ALIGNTO - 1) & ~(ROCKER_TLV_ALIGNTO - 1))
+#define ROCKER_TLV_HDRLEN ROCKER_TLV_ALIGN(sizeof(struct rocker_tlv))
+
+/*  <------- ROCKER_TLV_HDRLEN -------> <--- ROCKER_TLV_ALIGN(payload) --->
+ * +-----------------------------+- - -+- - - - - - - - - - - - - - -+- - -+
+ * |             Header          | Pad |           Payload           | Pad |
+ * |      (struct rocker_tlv)    | ing |                             | ing |
+ * +-----------------------------+- - -+- - - - - - - - - - - - - - -+- - -+
+ *  <--------------------------- tlv->len -------------------------->
+ */
+
+static struct rocker_tlv *rocker_tlv_next(const struct rocker_tlv *tlv,
+					  int *remaining)
+{
+	int totlen = ROCKER_TLV_ALIGN(tlv->len);
+
+	*remaining -= totlen;
+	return (struct rocker_tlv *) ((char *) tlv + totlen);
+}
+
+static int rocker_tlv_ok(const struct rocker_tlv *tlv, int remaining)
+{
+	return remaining >= (int) ROCKER_TLV_HDRLEN &&
+	       tlv->len >= ROCKER_TLV_HDRLEN &&
+	       tlv->len <= remaining;
+}
+
+#define rocker_tlv_for_each(pos, head, len, rem)	\
+	for (pos = head, rem = len;			\
+	     rocker_tlv_ok(pos, rem);			\
+	     pos = rocker_tlv_next(pos, &(rem)))
+
+#define rocker_tlv_for_each_nested(pos, tlv, rem)	\
+	rocker_tlv_for_each(pos, rocker_tlv_data(tlv),	\
+			    rocker_tlv_len(tlv), rem)
+
+static int rocker_tlv_attr_size(int payload)
+{
+	return ROCKER_TLV_HDRLEN + payload;
+}
+
+static int rocker_tlv_total_size(int payload)
+{
+	return ROCKER_TLV_ALIGN(rocker_tlv_attr_size(payload));
+}
+
+static int rocker_tlv_padlen(int payload)
+{
+	return rocker_tlv_total_size(payload) - rocker_tlv_attr_size(payload);
+}
+
+static int rocker_tlv_type(const struct rocker_tlv *tlv)
+{
+	return tlv->type;
+}
+
+static void *rocker_tlv_data(const struct rocker_tlv *tlv)
+{
+	return (char *) tlv + ROCKER_TLV_HDRLEN;
+}
+
+static int rocker_tlv_len(const struct rocker_tlv *tlv)
+{
+	return tlv->len - ROCKER_TLV_HDRLEN;
+}
+
+static u8 rocker_tlv_get_u8(const struct rocker_tlv *tlv)
+{
+	return *(u8 *) rocker_tlv_data(tlv);
+}
+
+static u16 rocker_tlv_get_u16(const struct rocker_tlv *tlv)
+{
+	return *(u16 *) rocker_tlv_data(tlv);
+}
+
+static u32 rocker_tlv_get_u32(const struct rocker_tlv *tlv)
+{
+	return *(u32 *) rocker_tlv_data(tlv);
+}
+
+static u64 rocker_tlv_get_u64(const struct rocker_tlv *tlv)
+{
+	return *(u64 *) rocker_tlv_data(tlv);
+}
+
+static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype,
+			     const char *buf, int buf_len)
+{
+	const struct rocker_tlv *tlv;
+	const struct rocker_tlv *head = (const struct rocker_tlv *) buf;
+	int rem;
+
+	memset(tb, 0, sizeof(struct rocker_tlv *) * (maxtype + 1));
+
+	rocker_tlv_for_each(tlv, head, buf_len, rem) {
+		u32 type = rocker_tlv_type(tlv);
+
+		if (type > 0 && type <= maxtype)
+			tb[type] = (struct rocker_tlv *) tlv;
+	}
+}
+
+static void rocker_tlv_parse_nested(struct rocker_tlv **tb, int maxtype,
+				    const struct rocker_tlv *tlv)
+{
+	rocker_tlv_parse(tb, maxtype, rocker_tlv_data(tlv),
+			 rocker_tlv_len(tlv));
+}
+
+static void rocker_tlv_parse_desc(struct rocker_tlv **tb, int maxtype,
+				  struct rocker_desc_info *desc_info)
+{
+	rocker_tlv_parse(tb, maxtype, desc_info->data,
+			 desc_info->desc->tlv_size);
+}
+
+static struct rocker_tlv *rocker_tlv_start(struct rocker_desc_info *desc_info)
+{
+	return (struct rocker_tlv *) ((char *) desc_info->data +
+					       desc_info->tlv_size);
+}
+
+static int rocker_tlv_put(struct rocker_desc_info *desc_info,
+			  int attrtype, int attrlen, const void *data)
+{
+	int tail_room = desc_info->data_size - desc_info->tlv_size;
+	int total_size = rocker_tlv_total_size(attrlen);
+	struct rocker_tlv *tlv;
+
+	if (unlikely(tail_room < total_size))
+		return -EMSGSIZE;
+
+	tlv = rocker_tlv_start(desc_info);
+	desc_info->tlv_size += total_size;
+	tlv->type = attrtype;
+	tlv->len = rocker_tlv_attr_size(attrlen);
+	memcpy(rocker_tlv_data(tlv), data, attrlen);
+	memset((char *) tlv + tlv->len, 0, rocker_tlv_padlen(attrlen));
+	return 0;
+}
+
+static int rocker_tlv_put_u8(struct rocker_desc_info *desc_info,
+			     int attrtype, u8 value)
+{
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value);
+}
+
+static int rocker_tlv_put_u16(struct rocker_desc_info *desc_info,
+			      int attrtype, u16 value)
+{
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value);
+}
+
+static int rocker_tlv_put_u32(struct rocker_desc_info *desc_info,
+			      int attrtype, u32 value)
+{
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value);
+}
+
+static int rocker_tlv_put_u64(struct rocker_desc_info *desc_info,
+			      int attrtype, u64 value)
+{
+	return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value);
+}
+
+static struct rocker_tlv *
+rocker_tlv_nest_start(struct rocker_desc_info *desc_info, int attrtype)
+{
+	struct rocker_tlv *start = rocker_tlv_start(desc_info);
+
+	if (rocker_tlv_put(desc_info, attrtype, 0, NULL) < 0)
+		return NULL;
+
+	return start;
+}
+
+static void rocker_tlv_nest_end(struct rocker_desc_info *desc_info,
+				struct rocker_tlv *start)
+{
+	start->len = (char *) rocker_tlv_start(desc_info) - (char *) start;
+}
+
+static void rocker_tlv_nest_cancel(struct rocker_desc_info *desc_info,
+				   struct rocker_tlv *start)
+{
+	desc_info->tlv_size = (char *) start - desc_info->data;
+}
+
+/******************************************
+ * DMA rings and descriptors manipulations
+ ******************************************/
+
+static u32 __pos_inc(u32 pos, size_t limit)
+{
+	return ++pos == limit ? 0 : pos;
+}
+
+static int rocker_desc_err(struct rocker_desc_info *desc_info)
+{
+	return -(desc_info->desc->comp_err & ~ROCKER_DMA_DESC_COMP_ERR_GEN);
+}
+
+static void rocker_desc_gen_clear(struct rocker_desc_info *desc_info)
+{
+	desc_info->desc->comp_err &= ~ROCKER_DMA_DESC_COMP_ERR_GEN;
+}
+
+static bool rocker_desc_gen(struct rocker_desc_info *desc_info)
+{
+	u32 comp_err = desc_info->desc->comp_err;
+
+	return comp_err & ROCKER_DMA_DESC_COMP_ERR_GEN ? true : false;
+}
+
+static void *rocker_desc_cookie_ptr_get(struct rocker_desc_info *desc_info)
+{
+	return (void *) desc_info->desc->cookie;
+}
+
+static void rocker_desc_cookie_ptr_set(struct rocker_desc_info *desc_info,
+				       void *ptr)
+{
+	desc_info->desc->cookie = (long) ptr;
+}
+
+static struct rocker_desc_info *
+rocker_desc_head_get(struct rocker_dma_ring_info *info)
+{
+	static struct rocker_desc_info *desc_info;
+	u32 head = __pos_inc(info->head, info->size);
+
+	desc_info = &info->desc_info[info->head];
+	if (head == info->tail)
+		return NULL; /* ring full */
+	desc_info->tlv_size = 0;
+	return desc_info;
+}
+
+static void rocker_desc_commit(struct rocker_desc_info *desc_info)
+{
+	desc_info->desc->buf_size = desc_info->data_size;
+	desc_info->desc->tlv_size = desc_info->tlv_size;
+}
+
+static void rocker_desc_head_set(struct rocker *rocker,
+				 struct rocker_dma_ring_info *info,
+				 struct rocker_desc_info *desc_info)
+{
+	u32 head = __pos_inc(info->head, info->size);
+
+	BUG_ON(head == info->tail);
+	rocker_desc_commit(desc_info);
+	info->head = head;
+	rocker_write32(rocker, DMA_DESC_HEAD(info->type), head);
+}
+
+static struct rocker_desc_info *
+rocker_desc_tail_get(struct rocker_dma_ring_info *info)
+{
+	static struct rocker_desc_info *desc_info;
+
+	if (info->tail == info->head)
+		return NULL; /* nothing to be done between head and tail */
+	desc_info = &info->desc_info[info->tail];
+	if (!rocker_desc_gen(desc_info))
+		return NULL; /* gen bit not set, desc is not ready yet */
+	info->tail = __pos_inc(info->tail, info->size);
+	desc_info->tlv_size = desc_info->desc->tlv_size;
+	return desc_info;
+}
+
+static void rocker_dma_ring_credits_set(struct rocker *rocker,
+					struct rocker_dma_ring_info *info,
+					u32 credits)
+{
+	if (credits)
+		rocker_write32(rocker, DMA_DESC_CREDITS(info->type), credits);
+}
+
+static unsigned long rocker_dma_ring_size_fix(size_t size)
+{
+	return max(ROCKER_DMA_SIZE_MIN,
+		   min(roundup_pow_of_two(size), ROCKER_DMA_SIZE_MAX));
+}
+
+static int rocker_dma_ring_create(struct rocker *rocker,
+				  unsigned int type,
+				  size_t size,
+				  struct rocker_dma_ring_info *info)
+{
+	int i;
+
+	BUG_ON(size != rocker_dma_ring_size_fix(size));
+	info->size = size;
+	info->type = type;
+	info->head = 0;
+	info->tail = 0;
+	info->desc_info = kcalloc(info->size, sizeof(*info->desc_info),
+				  GFP_KERNEL);
+	if (!info->desc_info)
+		return -ENOMEM;
+
+	info->desc = pci_alloc_consistent(rocker->pdev,
+					  info->size * sizeof(*info->desc),
+					  &info->mapaddr);
+	if (!info->desc) {
+		kfree(info->desc_info);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < info->size; i++)
+		info->desc_info[i].desc = &info->desc[i];
+
+	rocker_write32(rocker, DMA_DESC_CTRL(info->type),
+		       ROCKER_DMA_DESC_CTRL_RESET);
+	rocker_write64(rocker, DMA_DESC_ADDR(info->type), info->mapaddr);
+	rocker_write32(rocker, DMA_DESC_SIZE(info->type), info->size);
+
+	return 0;
+}
+
+static void rocker_dma_ring_destroy(struct rocker *rocker,
+				    struct rocker_dma_ring_info *info)
+{
+	rocker_write64(rocker, DMA_DESC_ADDR(info->type), 0);
+
+	pci_free_consistent(rocker->pdev,
+			    info->size * sizeof(struct rocker_desc),
+			    info->desc, info->mapaddr);
+	kfree(info->desc_info);
+}
+
+static void rocker_dma_ring_pass_to_producer(struct rocker *rocker,
+					     struct rocker_dma_ring_info *info)
+{
+	int i;
+
+	BUG_ON(info->head || info->tail);
+
+	/* When ring is consumer, we need to advance head for each desc.
+	 * That tells hw that the desc is ready to be used by it.
+	 */
+	for (i = 0; i < info->size - 1; i++)
+		rocker_desc_head_set(rocker, info, &info->desc_info[i]);
+	rocker_desc_commit(&info->desc_info[i]);
+}
+
+static int rocker_dma_ring_bufs_alloc(struct rocker *rocker,
+				      struct rocker_dma_ring_info *info,
+				      int direction, size_t buf_size)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	int i;
+	int err;
+
+	for (i = 0; i < info->size; i++) {
+		struct rocker_desc_info *desc_info = &info->desc_info[i];
+		struct rocker_desc *desc = &info->desc[i];
+		dma_addr_t dma_handle;
+		char *buf;
+
+		buf = kzalloc(buf_size, GFP_KERNEL | GFP_DMA);
+		if (!buf) {
+			err = -ENOMEM;
+			goto rollback;
+		}
+
+		dma_handle = pci_map_single(pdev, buf, buf_size, direction);
+		if (pci_dma_mapping_error(pdev, dma_handle)) {
+			kfree(buf);
+			err = -EIO;
+			goto rollback;
+		}
+
+		desc_info->data = buf;
+		desc_info->data_size = buf_size;
+		dma_unmap_addr_set(desc_info, mapaddr, dma_handle);
+
+		desc->buf_addr = dma_handle;
+		desc->buf_size = buf_size;
+	}
+	return 0;
+
+rollback:
+	for (i--; i >= 0; i--) {
+		struct rocker_desc_info *desc_info = &info->desc_info[i];
+
+		pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr),
+				 desc_info->data_size, direction);
+		kfree(desc_info->data);
+	}
+	return err;
+}
+
+static void rocker_dma_ring_bufs_free(struct rocker *rocker,
+				      struct rocker_dma_ring_info *info,
+				      int direction)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	int i;
+
+	for (i = 0; i < info->size; i++) {
+		struct rocker_desc_info *desc_info = &info->desc_info[i];
+		struct rocker_desc *desc = &info->desc[i];
+
+		desc->buf_addr = 0;
+		desc->buf_size = 0;
+		pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr),
+				 desc_info->data_size, direction);
+		kfree(desc_info->data);
+	}
+}
+
+static int rocker_dma_rings_init(struct rocker *rocker)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	int err;
+
+	err = rocker_dma_ring_create(rocker, ROCKER_DMA_CMD,
+				     ROCKER_DMA_CMD_DEFAULT_SIZE,
+				     &rocker->cmd_ring);
+	if (err) {
+		dev_err(&pdev->dev, "failed to create command dma ring\n");
+		return err;
+	}
+
+	spin_lock_init(&rocker->cmd_ring_lock);
+
+	err = rocker_dma_ring_bufs_alloc(rocker, &rocker->cmd_ring,
+					 PCI_DMA_BIDIRECTIONAL, PAGE_SIZE);
+	if (err) {
+		dev_err(&pdev->dev, "failed to alloc command dma ring buffers\n");
+		goto err_dma_cmd_ring_bufs_alloc;
+	}
+
+	err = rocker_dma_ring_create(rocker, ROCKER_DMA_EVENT,
+				     ROCKER_DMA_EVENT_DEFAULT_SIZE,
+				     &rocker->event_ring);
+	if (err) {
+		dev_err(&pdev->dev, "failed to create event dma ring\n");
+		goto err_dma_event_ring_create;
+	}
+
+	err = rocker_dma_ring_bufs_alloc(rocker, &rocker->event_ring,
+					 PCI_DMA_FROMDEVICE, PAGE_SIZE);
+	if (err) {
+		dev_err(&pdev->dev, "failed to alloc event dma ring buffers\n");
+		goto err_dma_event_ring_bufs_alloc;
+	}
+	rocker_dma_ring_pass_to_producer(rocker, &rocker->event_ring);
+	return 0;
+
+err_dma_event_ring_bufs_alloc:
+	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
+err_dma_event_ring_create:
+	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
+				  PCI_DMA_BIDIRECTIONAL);
+err_dma_cmd_ring_bufs_alloc:
+	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
+	return err;
+}
+
+static void rocker_dma_rings_fini(struct rocker *rocker)
+{
+	rocker_dma_ring_bufs_free(rocker, &rocker->event_ring,
+				  PCI_DMA_BIDIRECTIONAL);
+	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
+	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
+				  PCI_DMA_BIDIRECTIONAL);
+	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
+}
+
+static int rocker_dma_rx_ring_skb_map(struct rocker *rocker,
+				      struct rocker_port *rocker_port,
+				      struct rocker_desc_info *desc_info,
+				      struct sk_buff *skb, size_t buf_len)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	dma_addr_t dma_handle;
+
+	dma_handle = pci_map_single(pdev, skb->data, buf_len,
+				    PCI_DMA_FROMDEVICE);
+	if (pci_dma_mapping_error(pdev, dma_handle))
+		return -EIO;
+	if (rocker_tlv_put_u64(desc_info, ROCKER_TLV_RX_FRAG_ADDR, dma_handle))
+		goto tlv_put_failure;
+	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_RX_FRAG_MAX_LEN, buf_len))
+		goto tlv_put_failure;
+	return 0;
+
+tlv_put_failure:
+	pci_unmap_single(pdev, dma_handle, buf_len, PCI_DMA_FROMDEVICE);
+	desc_info->tlv_size = 0;
+	return -EMSGSIZE;
+}
+
+static size_t rocker_port_rx_buf_len(struct rocker_port *rocker_port)
+{
+	return rocker_port->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+}
+
+static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker,
+					struct rocker_port *rocker_port,
+					struct rocker_desc_info *desc_info)
+{
+	struct net_device *dev = rocker_port->dev;
+	struct sk_buff *skb;
+	size_t buf_len = rocker_port_rx_buf_len(rocker_port);
+	int err;
+
+	/* Ensure that hw will see tlv_size zero in case of an error.
+	 * That tells hw to use another descriptor.
+	 */
+	rocker_desc_cookie_ptr_set(desc_info, NULL);
+	desc_info->tlv_size = 0;
+
+	skb = netdev_alloc_skb_ip_align(dev, buf_len);
+	if (!skb)
+		return -ENOMEM;
+	err = rocker_dma_rx_ring_skb_map(rocker, rocker_port, desc_info,
+					 skb, buf_len);
+	if (err) {
+		dev_kfree_skb_any(skb);
+		return err;
+	}
+	rocker_desc_cookie_ptr_set(desc_info, skb);
+	return 0;
+}
+
+static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker,
+					 struct rocker_tlv **attrs)
+{
+	struct pci_dev *pdev = rocker->pdev;
+	dma_addr_t dma_handle;
+	size_t len;
+
+	if (!attrs[ROCKER_TLV_RX_FRAG_ADDR] ||
+	    !attrs[ROCKER_TLV_RX_FRAG_MAX_LEN])
+		return;
+	dma_handle = rocker_tlv_get_u64(attrs[ROCKER_TLV_RX_FRAG_ADDR]);
+	len = rocker_tlv_get_u16(attrs[ROCKER_TLV_RX_FRAG_MAX_LEN]);
+	pci_unmap_single(pdev, dma_handle, len, PCI_DMA_FROMDEVICE);
+}
+
+static void rocker_dma_rx_ring_skb_free(struct rocker *rocker,
+					struct rocker_desc_info *desc_info)
+{
+	struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
+	struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info);
+
+	if (!skb)
+		return;
+	rocker_tlv_parse_desc(attrs, ROCKER_TLV_RX_MAX, desc_info);
+	rocker_dma_rx_ring_skb_unmap(rocker, attrs);
+	dev_kfree_skb_any(skb);
+}
+
+static int rocker_dma_rx_ring_skbs_alloc(struct rocker *rocker,
+					 struct rocker_port *rocker_port)
+{
+	struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	int i;
+	int err;
+
+	for (i = 0; i < rx_ring->size; i++) {
+		err = rocker_dma_rx_ring_skb_alloc(rocker, rocker_port,
+						   &rx_ring->desc_info[i]);
+		if (err)
+			goto rollback;
+	}
+	return 0;
+
+rollback:
+	for (i--; i >= 0; i--)
+		rocker_dma_rx_ring_skb_free(rocker, &rx_ring->desc_info[i]);
+	return err;
+}
+
+static void rocker_dma_rx_ring_skbs_free(struct rocker *rocker,
+					 struct rocker_port *rocker_port)
+{
+	struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	int i;
+
+	for (i = 0; i < rx_ring->size; i++)
+		rocker_dma_rx_ring_skb_free(rocker, &rx_ring->desc_info[i]);
+}
+
+static int rocker_port_dma_rings_init(struct rocker_port *rocker_port)
+{
+	struct rocker *rocker = rocker_port->rocker;
+	int err;
+
+	err = rocker_dma_ring_create(rocker,
+				     ROCKER_DMA_TX(rocker_port->port_number),
+				     ROCKER_DMA_TX_DEFAULT_SIZE,
+				     &rocker_port->tx_ring);
+	if (err) {
+		netdev_err(rocker_port->dev, "failed to create tx dma ring\n");
+		return err;
+	}
+
+	err = rocker_dma_ring_bufs_alloc(rocker, &rocker_port->tx_ring,
+					 PCI_DMA_TODEVICE,
+					 ROCKER_DMA_TX_DESC_SIZE);
+	if (err) {
+		netdev_err(rocker_port->dev, "failed to alloc tx dma ring buffers\n");
+		goto err_dma_tx_ring_bufs_alloc;
+	}
+
+	err = rocker_dma_ring_create(rocker,
+				     ROCKER_DMA_RX(rocker_port->port_number),
+				     ROCKER_DMA_RX_DEFAULT_SIZE,
+				     &rocker_port->rx_ring);
+	if (err) {
+		netdev_err(rocker_port->dev, "failed to create rx dma ring\n");
+		goto err_dma_rx_ring_create;
+	}
+
+	err = rocker_dma_ring_bufs_alloc(rocker, &rocker_port->rx_ring,
+					 PCI_DMA_BIDIRECTIONAL,
+					 ROCKER_DMA_RX_DESC_SIZE);
+	if (err) {
+		netdev_err(rocker_port->dev, "failed to alloc rx dma ring buffers\n");
+		goto err_dma_rx_ring_bufs_alloc;
+	}
+
+	err = rocker_dma_rx_ring_skbs_alloc(rocker, rocker_port);
+	if (err) {
+		netdev_err(rocker_port->dev, "failed to alloc rx dma ring skbs\n");
+		goto err_dma_rx_ring_skbs_alloc;
+	}
+	rocker_dma_ring_pass_to_producer(rocker, &rocker_port->rx_ring);
+
+	return 0;
+
+err_dma_rx_ring_skbs_alloc:
+	rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring,
+				  PCI_DMA_BIDIRECTIONAL);
+err_dma_rx_ring_bufs_alloc:
+	rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring);
+err_dma_rx_ring_create:
+	rocker_dma_ring_bufs_free(rocker, &rocker_port->tx_ring,
+				  PCI_DMA_TODEVICE);
+err_dma_tx_ring_bufs_alloc:
+	rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring);
+	return err;
+}
+
+static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port)
+{
+	struct rocker *rocker = rocker_port->rocker;
+
+	rocker_dma_rx_ring_skbs_free(rocker, rocker_port);
+	rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring,
+				  PCI_DMA_BIDIRECTIONAL);
+	rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring);
+	rocker_dma_ring_bufs_free(rocker, &rocker_port->tx_ring,
+				  PCI_DMA_TODEVICE);
+	rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring);
+}
+
+static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable)
+{
+	u64 val = rocker_read64(rocker_port->rocker, PORT_PHYS_ENABLE);
+
+	if (enable)
+		val |= 1 << rocker_port->lport;
+	else
+		val &= ~(1 << rocker_port->lport);
+	rocker_write64(rocker_port->rocker, PORT_PHYS_ENABLE, val);
+}
+
+/********************************
+ * Interrupt handler and helpers
+ ********************************/
+
+static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id)
+{
+	struct rocker *rocker = dev_id;
+	struct rocker_desc_info *desc_info;
+	struct rocker_wait *wait;
+	u32 cred