net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)

Add a VF driver for Microsoft Azure Network Adapter (MANA) that will be
available in the future.

Co-developed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Co-developed-by: Shachar Raindel <shacharr@microsoft.com>
Signed-off-by: Shachar Raindel <shacharr@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

MAINTAINERS

@@ -8267,11 +8267,12 @@ S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/i2c/hi556.c
 
-Hyper-V CORE AND DRIVERS
+Hyper-V/Azure CORE AND DRIVERS
 M:	"K. Y. Srinivasan" <kys@microsoft.com>
 M:	Haiyang Zhang <haiyangz@microsoft.com>
 M:	Stephen Hemminger <sthemmin@microsoft.com>
 M:	Wei Liu <wei.liu@kernel.org>
+M:	Dexuan Cui <decui@microsoft.com>
 L:	linux-hyperv@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@@ -8288,6 +8289,7 @@ F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
 F:	drivers/iommu/hyperv-iommu.c
+F:	drivers/net/ethernet/microsoft/
 F:	drivers/net/hyperv/
 F:	drivers/pci/controller/pci-hyperv-intf.c
 F:	drivers/pci/controller/pci-hyperv.c

drivers/net/ethernet/Kconfig

@@ -82,6 +82,7 @@ source "drivers/net/ethernet/huawei/Kconfig"
 source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
+source "drivers/net/ethernet/microsoft/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
 
 config JME

drivers/net/ethernet/Makefile

@@ -45,6 +45,7 @@ obj-$(CONFIG_NET_VENDOR_HUAWEI) += huawei/
 obj-$(CONFIG_NET_VENDOR_IBM) += ibm/
 obj-$(CONFIG_NET_VENDOR_INTEL) += intel/
 obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/
+obj-$(CONFIG_NET_VENDOR_MICROSOFT) += microsoft/
 obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/
 obj-$(CONFIG_JME) += jme.o
 obj-$(CONFIG_KORINA) += korina.o

drivers/net/ethernet/microsoft/Kconfig

@@ -0,0 +1,29 @@
+#
+# Microsoft Azure network device configuration
+#
+
+config NET_VENDOR_MICROSOFT
+	bool "Microsoft Network Devices"
+	default y
+	help
+	  If you have a network (Ethernet) 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 the
+	  question about Microsoft network devices. If you say Y, you will be
+	  asked for your specific device in the following question.
+
+if NET_VENDOR_MICROSOFT
+
+config MICROSOFT_MANA
+	tristate "Microsoft Azure Network Adapter (MANA) support"
+	depends on PCI_MSI && X86_64
+	select PCI_HYPERV
+	help
+	  This driver supports Microsoft Azure Network Adapter (MANA).
+	  So far, the driver is only supported on X86_64.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called mana.
+
+endif #NET_VENDOR_MICROSOFT

drivers/net/ethernet/microsoft/Makefile

@@ -0,0 +1,5 @@
+#
+# Makefile for the Microsoft Azure network device driver.
+#
+
+obj-$(CONFIG_MICROSOFT_MANA) += mana/

drivers/net/ethernet/microsoft/mana/Makefile

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# Makefile for the Microsoft Azure Network Adapter driver
+
+obj-$(CONFIG_MICROSOFT_MANA) += mana.o
+mana-objs := gdma_main.o shm_channel.o hw_channel.o mana_en.o mana_ethtool.o

drivers/net/ethernet/microsoft/mana/hw_channel.h

@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#ifndef _HW_CHANNEL_H
+#define _HW_CHANNEL_H
+
+#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ  4
+
+#define HW_CHANNEL_MAX_REQUEST_SIZE  0x1000
+#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000
+
+#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1
+
+#define HWC_INIT_DATA_CQID		1
+#define HWC_INIT_DATA_RQID		2
+#define HWC_INIT_DATA_SQID		3
+#define HWC_INIT_DATA_QUEUE_DEPTH	4
+#define HWC_INIT_DATA_MAX_REQUEST	5
+#define HWC_INIT_DATA_MAX_RESPONSE	6
+#define HWC_INIT_DATA_MAX_NUM_CQS	7
+#define HWC_INIT_DATA_PDID		8
+#define HWC_INIT_DATA_GPA_MKEY		9
+
+/* Structures labeled with "HW DATA" are exchanged with the hardware. All of
+ * them are naturally aligned and hence don't need __packed.
+ */
+
+union hwc_init_eq_id_db {
+	u32 as_uint32;
+
+	struct {
+		u32 eq_id	: 16;
+		u32 doorbell	: 16;
+	};
+}; /* HW DATA */
+
+union hwc_init_type_data {
+	u32 as_uint32;
+
+	struct {
+		u32 value	: 24;
+		u32 type	:  8;
+	};
+}; /* HW DATA */
+
+struct hwc_rx_oob {
+	u32 type	: 6;
+	u32 eom		: 1;
+	u32 som		: 1;
+	u32 vendor_err	: 8;
+	u32 reserved1	: 16;
+
+	u32 src_virt_wq	: 24;
+	u32 src_vfid	: 8;
+
+	u32 reserved2;
+
+	union {
+		u32 wqe_addr_low;
+		u32 wqe_offset;
+	};
+
+	u32 wqe_addr_high;
+
+	u32 client_data_unit	: 14;
+	u32 reserved3		: 18;
+
+	u32 tx_oob_data_size;
+
+	u32 chunk_offset	: 21;
+	u32 reserved4		: 11;
+}; /* HW DATA */
+
+struct hwc_tx_oob {
+	u32 reserved1;
+
+	u32 reserved2;
+
+	u32 vrq_id	: 24;
+	u32 dest_vfid	: 8;
+
+	u32 vrcq_id	: 24;
+	u32 reserved3	: 8;
+
+	u32 vscq_id	: 24;
+	u32 loopback	: 1;
+	u32 lso_override: 1;
+	u32 dest_pf	: 1;
+	u32 reserved4	: 5;
+
+	u32 vsq_id	: 24;
+	u32 reserved5	: 8;
+}; /* HW DATA */
+
+struct hwc_work_request {
+	void *buf_va;
+	void *buf_sge_addr;
+	u32 buf_len;
+	u32 msg_size;
+
+	struct gdma_wqe_request wqe_req;
+	struct hwc_tx_oob tx_oob;
+
+	struct gdma_sge sge;
+};
+
+/* hwc_dma_buf represents the array of in-flight WQEs.
+ * mem_info as know as the GDMA mapped memory is partitioned and used by
+ * in-flight WQEs.
+ * The number of WQEs is determined by the number of in-flight messages.
+ */
+struct hwc_dma_buf {
+	struct gdma_mem_info mem_info;
+
+	u32 gpa_mkey;
+
+	u32 num_reqs;
+	struct hwc_work_request reqs[];
+};
+
+typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id,
+				    const struct hwc_rx_oob *rx_oob);
+
+typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id,
+				    const struct hwc_rx_oob *rx_oob);
+
+struct hwc_cq {
+	struct hw_channel_context *hwc;
+
+	struct gdma_queue *gdma_cq;
+	struct gdma_queue *gdma_eq;
+	struct gdma_comp *comp_buf;
+	u16 queue_depth;
+
+	hwc_rx_event_handler_t *rx_event_handler;
+	void *rx_event_ctx;
+
+	hwc_tx_event_handler_t *tx_event_handler;
+	void *tx_event_ctx;
+};
+
+struct hwc_wq {
+	struct hw_channel_context *hwc;
+
+	struct gdma_queue *gdma_wq;
+	struct hwc_dma_buf *msg_buf;
+	u16 queue_depth;
+
+	struct hwc_cq *hwc_cq;
+};
+
+struct hwc_caller_ctx {
+	struct completion comp_event;
+	void *output_buf;
+	u32 output_buflen;
+
+	u32 error; /* Linux error code */
+	u32 status_code;
+};
+
+struct hw_channel_context {
+	struct gdma_dev *gdma_dev;
+	struct device *dev;
+
+	u16 num_inflight_msg;
+	u32 max_req_msg_size;
+
+	u16 hwc_init_q_depth_max;
+	u32 hwc_init_max_req_msg_size;
+	u32 hwc_init_max_resp_msg_size;
+
+	struct completion hwc_init_eqe_comp;
+
+	struct hwc_wq *rxq;
+	struct hwc_wq *txq;
+	struct hwc_cq *cq;
+
+	struct semaphore sema;
+	struct gdma_resource inflight_msg_res;
+
+	struct hwc_caller_ctx *caller_ctx;
+};
+
+int mana_hwc_create_channel(struct gdma_context *gc);
+void mana_hwc_destroy_channel(struct gdma_context *gc);
+
+int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
+			  const void *req, u32 resp_len, void *resp);
+
+#endif /* _HW_CHANNEL_H */

drivers/net/ethernet/microsoft/mana/mana_ethtool.c

@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+
+#include "mana.h"
+
+static const struct {
+	char name[ETH_GSTRING_LEN];
+	u16 offset;
+} mana_eth_stats[] = {
+	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
+	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
+};
+
+static int mana_get_sset_count(struct net_device *ndev, int stringset)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	unsigned int num_queues = apc->num_queues;
+
+	if (stringset != ETH_SS_STATS)
+		return -EINVAL;
+
+	return ARRAY_SIZE(mana_eth_stats) + num_queues * 4;
+}
+
+static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	unsigned int num_queues = apc->num_queues;
+	u8 *p = data;
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++) {
+		memcpy(p, mana_eth_stats[i].name, ETH_GSTRING_LEN);
+		p += ETH_GSTRING_LEN;
+	}
+
+	for (i = 0; i < num_queues; i++) {
+		sprintf(p, "rx_%d_packets", i);
+		p += ETH_GSTRING_LEN;
+		sprintf(p, "rx_%d_bytes", i);
+		p += ETH_GSTRING_LEN;
+	}
+
+	for (i = 0; i < num_queues; i++) {
+		sprintf(p, "tx_%d_packets", i);
+		p += ETH_GSTRING_LEN;
+		sprintf(p, "tx_%d_bytes", i);
+		p += ETH_GSTRING_LEN;
+	}
+}
+
+static void mana_get_ethtool_stats(struct net_device *ndev,
+				   struct ethtool_stats *e_stats, u64 *data)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	unsigned int num_queues = apc->num_queues;
+	void *eth_stats = &apc->eth_stats;
+	struct mana_stats *stats;
+	unsigned int start;
+	u64 packets, bytes;
+	int q, i = 0;
+
+	if (!apc->port_is_up)
+		return;
+
+	for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++)
+		data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset);
+
+	for (q = 0; q < num_queues; q++) {
+		stats = &apc->rxqs[q]->stats;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		data[i++] = packets;
+		data[i++] = bytes;
+	}
+
+	for (q = 0; q < num_queues; q++) {
+		stats = &apc->tx_qp[q].txq.stats;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		data[i++] = packets;
+		data[i++] = bytes;
+	}
+}
+
+static int mana_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *cmd,
+			  u32 *rules)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = apc->num_queues;
+		return 0;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static u32 mana_get_rxfh_key_size(struct net_device *ndev)
+{
+	return MANA_HASH_KEY_SIZE;
+}
+
+static u32 mana_rss_indir_size(struct net_device *ndev)
+{
+	return MANA_INDIRECT_TABLE_SIZE;
+}
+
+static int mana_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
+			 u8 *hfunc)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	int i;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+
+	if (indir) {
+		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
+			indir[i] = apc->indir_table[i];
+	}
+
+	if (key)
+		memcpy(key, apc->hashkey, MANA_HASH_KEY_SIZE);
+
+	return 0;
+}
+
+static int mana_set_rxfh(struct net_device *ndev, const u32 *indir,
+			 const u8 *key, const u8 hfunc)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	bool update_hash = false, update_table = false;
+	u32 save_table[MANA_INDIRECT_TABLE_SIZE];
+	u8 save_key[MANA_HASH_KEY_SIZE];
+	int i, err;
+
+	if (!apc->port_is_up)
+		return -EOPNOTSUPP;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
+			if (indir[i] >= apc->num_queues)
+				return -EINVAL;
+
+		update_table = true;
+		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) {
+			save_table[i] = apc->indir_table[i];
+			apc->indir_table[i] = indir[i];
+		}
+	}
+
+	if (key) {
+		update_hash = true;
+		memcpy(save_key, apc->hashkey, MANA_HASH_KEY_SIZE);
+		memcpy(apc->hashkey, key, MANA_HASH_KEY_SIZE);
+	}
+
+	err = mana_config_rss(apc, TRI_STATE_TRUE, update_hash, update_table);
+
+	if (err) { /* recover to original values */
+		if (update_table) {
+			for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
+				apc->indir_table[i] = save_table[i];
+		}
+
+		if (update_hash)
+			memcpy(apc->hashkey, save_key, MANA_HASH_KEY_SIZE);
+
+		mana_config_rss(apc, TRI_STATE_TRUE, update_hash, update_table);
+	}
+
+	return err;
+}
+
+static void mana_get_channels(struct net_device *ndev,
+			      struct ethtool_channels *channel)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	channel->max_combined = apc->max_queues;
+	channel->combined_count = apc->num_queues;
+}
+
+static int mana_set_channels(struct net_device *ndev,
+			     struct ethtool_channels *channels)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	unsigned int new_count = channels->combined_count;
+	unsigned int old_count = apc->num_queues;
+	int err, err2;
+
+	if (!apc->port_is_up)
+		return -EOPNOTSUPP;
+
+	err = mana_detach(ndev, false);
+	if (err) {
+		netdev_err(ndev, "mana_detach failed: %d\n", err);
+		return err;
+	}
+
+	apc->num_queues = new_count;
+	err = mana_attach(ndev);
+	if (!err)
+		return 0;
+
+	netdev_err(ndev, "mana_attach failed: %d\n", err);
+
+	/* Try to roll it back to the old configuration. */
+	apc->num_queues = old_count;
+	err2 = mana_attach(ndev);
+	if (err2)
+		netdev_err(ndev, "mana re-attach failed: %d\n", err2);
+
+	return err;
+}
+
+const struct ethtool_ops mana_ethtool_ops = {
+	.get_ethtool_stats	= mana_get_ethtool_stats,
+	.get_sset_count		= mana_get_sset_count,
+	.get_strings		= mana_get_strings,
+	.get_rxnfc		= mana_get_rxnfc,
+	.get_rxfh_key_size	= mana_get_rxfh_key_size,
+	.get_rxfh_indir_size	= mana_rss_indir_size,
+	.get_rxfh		= mana_get_rxfh,
+	.set_rxfh		= mana_set_rxfh,
+	.get_channels		= mana_get_channels,
+	.set_channels		= mana_set_channels,
+};

drivers/net/ethernet/microsoft/mana/shm_channel.c

@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+
+#include "shm_channel.h"
+
+#define PAGE_FRAME_L48_WIDTH_BYTES 6
+#define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8)
+#define PAGE_FRAME_L48_MASK 0x0000FFFFFFFFFFFF
+#define PAGE_FRAME_H4_WIDTH_BITS 4
+#define VECTOR_MASK 0xFFFF
+#define SHMEM_VF_RESET_STATE ((u32)-1)
+
+#define SMC_MSG_TYPE_ESTABLISH_HWC 1
+#define SMC_MSG_TYPE_ESTABLISH_HWC_VERSION 0
+
+#define SMC_MSG_TYPE_DESTROY_HWC 2
+#define SMC_MSG_TYPE_DESTROY_HWC_VERSION 0
+
+#define SMC_MSG_DIRECTION_REQUEST 0
+#define SMC_MSG_DIRECTION_RESPONSE 1
+
+/* Structures labeled with "HW DATA" are exchanged with the hardware. All of
+ * them are naturally aligned and hence don't need __packed.
+ */
+
+/* Shared memory channel protocol header
+ *
+ * msg_type: set on request and response; response matches request.
+ * msg_version: newer PF writes back older response (matching request)
+ *  older PF acts on latest version known and sets that version in result
+ *  (less than request).
+ * direction: 0 for request, VF->PF; 1 for response, PF->VF.
+ * status: 0 on request,
+ *   operation result on response (success = 0, failure = 1 or greater).
+ * reset_vf: If set on either establish or destroy request, indicates perform
+ *  FLR before/after the operation.
+ * owner_is_pf: 1 indicates PF owned, 0 indicates VF owned.
+ */
+union smc_proto_hdr {
+	u32 as_uint32;
+
+	struct {
+		u8 msg_type	: 3;
+		u8 msg_version	: 3;
+		u8 reserved_1	: 1;
+		u8 direction	: 1;
+
+		u8 status;
+
+		u8 reserved_2;
+
+		u8 reset_vf	: 1;
+		u8 reserved_3	: 6;
+		u8 owner_is_pf	: 1;
+	};
+}; /* HW DATA */
+
+#define SMC_APERTURE_BITS 256
+#define SMC_BASIC_UNIT (sizeof(u32))
+#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8))
+#define SMC_LAST_DWORD (SMC_APERTURE_DWORDS - 1)
+
+static int mana_smc_poll_register(void __iomem *base, bool reset)
+{
+	void __iomem *ptr = base + SMC_LAST_DWORD * SMC_BASIC_UNIT;
+	u32 last_dword;
+	int i;
+
+	/* Poll the hardware for the ownership bit. This should be pretty fast,
+	 * but let's do it in a loop just in case the hardware or the PF
+	 * driver are temporarily busy.
+	 */
+	for (i = 0; i < 20 * 1000; i++)  {
+		last_dword = readl(ptr);
+
+		/* shmem reads as 0xFFFFFFFF in the reset case */
+		if (reset && last_dword == SHMEM_VF_RESET_STATE)
+			return 0;
+
+		/* If bit_31 is set, the PF currently owns the SMC. */
+		if (!(last_dword & BIT(31)))
+			return 0;
+
+		usleep_range(1000, 2000);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int mana_smc_read_response(struct shm_channel *sc, u32 msg_type,
+				  u32 msg_version, bool reset_vf)
+{
+	void __iomem *base = sc->base;
+	union smc_proto_hdr hdr;
+	int err;
+
+	/* Wait for PF to respond. */
+	err = mana_smc_poll_register(base, reset_vf);
+	if (err)
+		return err;
+
+	hdr.as_uint32 = readl(base + SMC_LAST_DWORD * SMC_BASIC_UNIT);
+
+	if (reset_vf && hdr.as_uint32 == SHMEM_VF_RESET_STATE)
+		return 0;
+
+	/* Validate protocol fields from the PF driver */
+	if (hdr.msg_type != msg_type || hdr.msg_version > msg_version ||
+	    hdr.direction != SMC_MSG_DIRECTION_RESPONSE) {
+		dev_err(sc->dev, "Wrong SMC response 0x%x, type=%d, ver=%d\n",
+			hdr.as_uint32, msg_type, msg_version);
+		return -EPROTO;
+	}
+
+	/* Validate the operation result */
+	if (hdr.status != 0) {
+		dev_err(sc->dev, "SMC operation failed: 0x%x\n", hdr.status);
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+void mana_smc_init(struct shm_channel *sc, struct device *dev,
+		   void __iomem *base)
+{
+	sc->dev = dev;
+	sc->base = base;
+}
+
+int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr,
+		       u64 cq_addr, u64 rq_addr, u64 sq_addr,
+		       u32 eq_msix_index)
+{
+	union smc_proto_hdr *hdr;
+	u16 all_addr_h4bits = 0;
+	u16 frame_addr_seq = 0;
+	u64 frame_addr = 0;
+	u8 shm_buf[32];
+	u64 *shmem;
+	u32 *dword;
+	u8 *ptr;
+	int err;
+	int i;
+
+	/* Ensure VF already has possession of shared memory */
+	err = mana_smc_poll_register(sc->base, false);
+	if (err) {
+		dev_err(sc->dev, "Timeout when setting up HWC: %d\n", err);
+		return err;
+	}
+
+	if (!PAGE_ALIGNED(eq_addr) || !PAGE_ALIGNED(cq_addr) ||
+	    !PAGE_ALIGNED(rq_addr) || !PAGE_ALIGNED(sq_addr))
+		return -EINVAL;
+
+	if ((eq_msix_index & VECTOR_MASK) != eq_msix_index)
+		return -EINVAL;
+
+	/* Scheme for packing four addresses and extra info into 256 bits.
+	 *
+	 * Addresses must be page frame aligned, so only frame address bits
+	 * are transferred.
+	 *
+	 * 52-bit frame addresses are split into the lower 48 bits and upper
+	 * 4 bits. Lower 48 bits of 4 address are written sequentially from
+	 * the start of the 256-bit shared memory region followed by 16 bits
+	 * containing the upper 4 bits of the 4 addresses in sequence.
+	 *
+	 * A 16 bit EQ vector number fills out the next-to-last 32-bit dword.
+	 *
+	 * The final 32-bit dword is used for protocol control information as
+	 * defined in smc_proto_hdr.
+	 */
+
+	memset(shm_buf, 0, sizeof(shm_buf));
+	ptr = shm_buf;
+
+	/* EQ addr: low 48 bits of frame address */
+	shmem = (u64 *)ptr;
+	frame_addr = PHYS_PFN(eq_addr);
+	*shmem = frame_addr & PAGE_FRAME_L48_MASK;
+	all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) <<
+		(frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS);
+	ptr += PAGE_FRAME_L48_WIDTH_BYTES;
+
+	/* CQ addr: low 48 bits of frame address */
+	shmem = (u64 *)ptr;
+	frame_addr = PHYS_PFN(cq_addr);
+	*shmem = frame_addr & PAGE_FRAME_L48_MASK;
+	all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) <<
+		(frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS);
+	ptr += PAGE_FRAME_L48_WIDTH_BYTES;
+
+	/* RQ addr: low 48 bits of frame address */
+	shmem = (u64 *)ptr;
+	frame_addr = PHYS_PFN(rq_addr);
+	*shmem = frame_addr & PAGE_FRAME_L48_MASK;
+	all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) <<
+		(frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS);
+	ptr += PAGE_FRAME_L48_WIDTH_BYTES;
+
+	/* SQ addr: low 48 bits of frame address */
+	shmem = (u64 *)ptr;
+	frame_addr = PHYS_PFN(sq_addr);
+	*shmem = frame_addr & PAGE_FRAME_L48_MASK;
+	all_addr_h4bits |= (frame_addr >> PAGE_FRAME_L48_WIDTH_BITS) <<
+		(frame_addr_seq++ * PAGE_FRAME_H4_WIDTH_BITS);
+	ptr += PAGE_FRAME_L48_WIDTH_BYTES;
+
+	/* High 4 bits of the four frame addresses */
+	*((u16 *)ptr) = all_addr_h4bits;
+	ptr += sizeof(u16);
+
+	/* EQ MSIX vector number */
+	*((u16 *)ptr) = (u16)eq_msix_index;
+	ptr += sizeof(u16);
+
+	/* 32-bit protocol header in final dword */
+	*((u32 *)ptr) = 0;
+
+	hdr = (union smc_proto_hdr *)ptr;
+	hdr->msg_type = SMC_MSG_TYPE_ESTABLISH_HWC;
+	hdr->msg_version = SMC_MSG_TYPE_ESTABLISH_HWC_VERSION;
+	hdr->direction = SMC_MSG_DIRECTION_REQUEST;
+	hdr->reset_vf = reset_vf;
+
+	/* Write 256-message buffer to shared memory (final 32-bit write
+	 * triggers HW to set possession bit to PF).
+	 */
+	dword = (u32 *)shm_buf;
+	for (i = 0; i < SMC_APERTURE_DWORDS; i++)
+		writel(*dword++, sc->base + i * SMC_BASIC_UNIT);
+
+	/* Read shmem response (polling for VF possession) and validate.
+	 * For setup, waiting for response on shared memory is not strictly
+	 * necessary, since wait occurs later for results to appear in EQE's.
+	 */
+	err = mana_smc_read_response(sc, SMC_MSG_TYPE_ESTABLISH_HWC,
+				     SMC_MSG_TYPE_ESTABLISH_HWC_VERSION,
+				     reset_vf);
+	if (err) {
+		dev_err(sc->dev, "Error when setting up HWC: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf)
+{
+	union smc_proto_hdr hdr = {};
+	int err;
+
+	/* Ensure already has possession of shared memory */
+	err = mana_smc_poll_register(sc->base, false);
+	if (err) {
+		dev_err(sc->dev, "Timeout when tearing down HWC\n");
+		return err;
+	}
+
+	/* Set up protocol header for HWC destroy message */
+	hdr.msg_type = SMC_MSG_TYPE_DESTROY_HWC;
+	hdr.msg_version = SMC_MSG_TYPE_DESTROY_HWC_VERSION;
+	hdr.direction = SMC_MSG_DIRECTION_REQUEST;
+	hdr.reset_vf = reset_vf;
+
+	/* Write message in high 32 bits of 256-bit shared memory, causing HW
+	 * to set possession bit to PF.
+	 */
+	writel(hdr.as_uint32, sc->base + SMC_LAST_DWORD * SMC_BASIC_UNIT);
+
+	/* Read shmem response (polling for VF possession) and validate.
+	 * For teardown, waiting for response is required to ensure hardware
+	 * invalidates MST entries before software frees memory.
+	 */
+	err = mana_smc_read_response(sc, SMC_MSG_TYPE_DESTROY_HWC,
+				     SMC_MSG_TYPE_DESTROY_HWC_VERSION,
+				     reset_vf);
+	if (err) {
+		dev_err(sc->dev, "Error when tearing down HWC: %d\n", err);
+		return err;
+	}
+
+	return 0;
+}

drivers/net/ethernet/microsoft/mana/shm_channel.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright (c) 2021, Microsoft Corporation. */
+
+#ifndef _SHM_CHANNEL_H
+#define _SHM_CHANNEL_H
+
+struct shm_channel {
+	struct device *dev;
+	void __iomem *base;
+};
+
+void mana_smc_init(struct shm_channel *sc, struct device *dev,
+		   void __iomem *base);
+
+int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr,
+		       u64 cq_addr, u64 rq_addr, u64 sq_addr,
+		       u32 eq_msix_index);
+
+int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf);
+
+#endif /* _SHM_CHANNEL_H */