Merge branch 'mlx5-hyperv'

Haiyang Zhang says:

====================
Add software backchannel and mlx5e HV VHCA stats

This patch set adds paravirtual backchannel in software in pci_hyperv,
which is required by the mlx5e driver HV VHCA stats agent.

The stats agent is responsible on running a periodic rx/tx packets/bytes
stats update.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

MAINTAINERS

@@ -7469,6 +7469,7 @@ F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
 F:	drivers/pci/controller/pci-hyperv.c
+F:	drivers/pci/controller/pci-hyperv-intf.c
 F:	drivers/net/hyperv/
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/uio/uio_hv_generic.c

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -36,6 +36,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
 					lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
 					en/tc_tun_geneve.o diag/en_tc_tracepoint.o
+mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
 
 #
 # Core extra
@@ -45,6 +46,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offlo
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
+mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o lib/hv_vhca.o
 
 #
 # Ipoib netdev

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -54,6 +54,7 @@
 #include "mlx5_core.h"
 #include "en_stats.h"
 #include "en/fs.h"
+#include "lib/hv_vhca.h"
 
 extern const struct net_device_ops mlx5e_netdev_ops;
 struct page_pool;
@@ -782,6 +783,15 @@ struct mlx5e_modify_sq_param {
 	int rl_index;
 };
 
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+struct mlx5e_hv_vhca_stats_agent {
+	struct mlx5_hv_vhca_agent *agent;
+	struct delayed_work        work;
+	u16                        delay;
+	void                      *buf;
+};
+#endif
+
 struct mlx5e_xsk {
 	/* UMEMs are stored separately from channels, because we don't want to
 	 * lose them when channels are recreated. The kernel also stores UMEMs,
@@ -853,6 +863,9 @@ struct mlx5e_priv {
 	struct devlink_health_reporter *tx_reporter;
 	struct devlink_health_reporter *rx_reporter;
 	struct mlx5e_xsk           xsk;
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+	struct mlx5e_hv_vhca_stats_agent stats_agent;
+#endif
 };
 
 struct mlx5e_profile {

drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include "en.h"
+#include "en/hv_vhca_stats.h"
+#include "lib/hv_vhca.h"
+#include "lib/hv.h"
+
+struct mlx5e_hv_vhca_per_ring_stats {
+	u64     rx_packets;
+	u64     rx_bytes;
+	u64     tx_packets;
+	u64     tx_bytes;
+};
+
+static void
+mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch,
+			      struct mlx5e_hv_vhca_per_ring_stats *data)
+{
+	struct mlx5e_channel_stats *stats;
+	int tc;
+
+	stats = &priv->channel_stats[ch];
+	data->rx_packets = stats->rq.packets;
+	data->rx_bytes   = stats->rq.bytes;
+
+	for (tc = 0; tc < priv->max_opened_tc; tc++) {
+		data->tx_packets += stats->sq[tc].packets;
+		data->tx_bytes   += stats->sq[tc].bytes;
+	}
+}
+
+static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, u64 *data,
+				     int buf_len)
+{
+	int ch, i = 0;
+
+	for (ch = 0; ch < priv->max_nch; ch++) {
+		u64 *buf = data + i;
+
+		if (WARN_ON_ONCE(buf +
+				 sizeof(struct mlx5e_hv_vhca_per_ring_stats) >
+				 data + buf_len))
+			return;
+
+		mlx5e_hv_vhca_fill_ring_stats(priv, ch,
+					      (struct mlx5e_hv_vhca_per_ring_stats *)buf);
+		i += sizeof(struct mlx5e_hv_vhca_per_ring_stats) / sizeof(u64);
+	}
+}
+
+static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv)
+{
+	return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) *
+		priv->max_nch);
+}
+
+static void mlx5e_hv_vhca_stats_work(struct work_struct *work)
+{
+	struct mlx5e_hv_vhca_stats_agent *sagent;
+	struct mlx5_hv_vhca_agent *agent;
+	struct delayed_work *dwork;
+	struct mlx5e_priv *priv;
+	int buf_len, rc;
+	void *buf;
+
+	dwork = to_delayed_work(work);
+	sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work);
+	priv = container_of(sagent, struct mlx5e_priv, stats_agent);
+	buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
+	agent = sagent->agent;
+	buf = sagent->buf;
+
+	memset(buf, 0, buf_len);
+	mlx5e_hv_vhca_fill_stats(priv, buf, buf_len);
+
+	rc = mlx5_hv_vhca_agent_write(agent, buf, buf_len);
+	if (rc) {
+		mlx5_core_err(priv->mdev,
+			      "%s: Failed to write stats, err = %d\n",
+			      __func__, rc);
+		return;
+	}
+
+	if (sagent->delay)
+		queue_delayed_work(priv->wq, &sagent->work, sagent->delay);
+}
+
+enum {
+	MLX5_HV_VHCA_STATS_VERSION     = 1,
+	MLX5_HV_VHCA_STATS_UPDATE_ONCE = 0xFFFF,
+};
+
+static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent,
+					struct mlx5_hv_vhca_control_block *block)
+{
+	struct mlx5e_hv_vhca_stats_agent *sagent;
+	struct mlx5e_priv *priv;
+
+	priv = mlx5_hv_vhca_agent_priv(agent);
+	sagent = &priv->stats_agent;
+
+	block->version = MLX5_HV_VHCA_STATS_VERSION;
+	block->rings   = priv->max_nch;
+
+	if (!block->command) {
+		cancel_delayed_work_sync(&priv->stats_agent.work);
+		return;
+	}
+
+	sagent->delay = block->command == MLX5_HV_VHCA_STATS_UPDATE_ONCE ? 0 :
+			msecs_to_jiffies(block->command * 100);
+
+	queue_delayed_work(priv->wq, &sagent->work, sagent->delay);
+}
+
+static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent)
+{
+	struct mlx5e_priv *priv = mlx5_hv_vhca_agent_priv(agent);
+
+	cancel_delayed_work_sync(&priv->stats_agent.work);
+}
+
+int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
+{
+	int buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
+	struct mlx5_hv_vhca_agent *agent;
+
+	priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL);
+	if (!priv->stats_agent.buf)
+		return -ENOMEM;
+
+	agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca,
+					  MLX5_HV_VHCA_AGENT_STATS,
+					  mlx5e_hv_vhca_stats_control, NULL,
+					  mlx5e_hv_vhca_stats_cleanup,
+					  priv);
+
+	if (IS_ERR_OR_NULL(agent)) {
+		if (IS_ERR(agent))
+			netdev_warn(priv->netdev,
+				    "Failed to create hv vhca stats agent, err = %ld\n",
+				    PTR_ERR(agent));
+
+		kfree(priv->stats_agent.buf);
+		return IS_ERR_OR_NULL(agent);
+	}
+
+	priv->stats_agent.agent = agent;
+	INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
+
+	return 0;
+}
+
+void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
+{
+	if (IS_ERR_OR_NULL(priv->stats_agent.agent))
+		return;
+
+	mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
+	kfree(priv->stats_agent.buf);
+}

drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_STATS_VHCA_H__
+#define __MLX5_EN_STATS_VHCA_H__
+#include "en.h"
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv);
+void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv);
+
+#else
+
+static inline int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
+{
+	return 0;
+}
+
+static inline void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
+{
+}
+#endif
+
+#endif /* __MLX5_EN_STATS_VHCA_H__ */

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -62,6 +62,7 @@
 #include "en/xsk/setup.h"
 #include "en/xsk/rx.h"
 #include "en/xsk/tx.h"
+#include "en/hv_vhca_stats.h"
 
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
@@ -5109,6 +5110,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_init(priv);
 
+	mlx5e_hv_vhca_stats_create(priv);
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -5141,6 +5143,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
+	mlx5e_hv_vhca_stats_destroy(priv);
 	if (mlx5e_monitor_counter_supported(priv))
 		mlx5e_monitor_counter_cleanup(priv);
 

drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/hyperv.h>
+#include "mlx5_core.h"
+#include "lib/hv.h"
+
+static int mlx5_hv_config_common(struct mlx5_core_dev *dev, void *buf, int len,
+				 int offset, bool read)
+{
+	int rc = -EOPNOTSUPP;
+	int bytes_returned;
+	int block_id;
+
+	if (offset % HV_CONFIG_BLOCK_SIZE_MAX || len % HV_CONFIG_BLOCK_SIZE_MAX)
+		return -EINVAL;
+
+	block_id = offset / HV_CONFIG_BLOCK_SIZE_MAX;
+
+	rc = read ?
+	     hyperv_read_cfg_blk(dev->pdev, buf,
+				 HV_CONFIG_BLOCK_SIZE_MAX, block_id,
+				 &bytes_returned) :
+	     hyperv_write_cfg_blk(dev->pdev, buf,
+				  HV_CONFIG_BLOCK_SIZE_MAX, block_id);
+
+	/* Make sure len bytes were read successfully  */
+	if (read)
+		rc |= !(len == bytes_returned);
+
+	if (rc) {
+		mlx5_core_err(dev, "Failed to %s hv config, err = %d, len = %d, offset = %d\n",
+			      read ? "read" : "write", rc, len,
+			      offset);
+		return rc;
+	}
+
+	return 0;
+}
+
+int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len,
+			int offset)
+{
+	return mlx5_hv_config_common(dev, buf, len, offset, true);
+}
+
+int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len,
+			 int offset)
+{
+	return mlx5_hv_config_common(dev, buf, len, offset, false);
+}
+
+int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context,
+				void (*block_invalidate)(void *context,
+							 u64 block_mask))
+{
+	return hyperv_reg_block_invalidate(dev->pdev, context,
+					   block_invalidate);
+}
+
+void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev)
+{
+	hyperv_reg_block_invalidate(dev->pdev, NULL, NULL);
+}

drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __LIB_HV_H__
+#define __LIB_HV_H__
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+#include <linux/hyperv.h>
+#include <linux/mlx5/driver.h>
+
+int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len,
+			int offset);
+int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len,
+			 int offset);
+int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context,
+				void (*block_invalidate)(void *context,
+							 u64 block_mask));
+void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev);
+#endif
+
+#endif /* __LIB_HV_H__ */

drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/hyperv.h>
+#include "mlx5_core.h"
+#include "lib/hv.h"
+#include "lib/hv_vhca.h"
+
+struct mlx5_hv_vhca {
+	struct mlx5_core_dev       *dev;
+	struct workqueue_struct    *work_queue;
+	struct mlx5_hv_vhca_agent  *agents[MLX5_HV_VHCA_AGENT_MAX];
+	struct mutex                agents_lock; /* Protect agents array */
+};
+
+struct mlx5_hv_vhca_work {
+	struct work_struct     invalidate_work;
+	struct mlx5_hv_vhca   *hv_vhca;
+	u64                    block_mask;
+};
+
+struct mlx5_hv_vhca_data_block {
+	u16     sequence;
+	u16     offset;
+	u8      reserved[4];
+	u64     data[15];
+};
+
+struct mlx5_hv_vhca_agent {
+	enum mlx5_hv_vhca_agent_type	 type;
+	struct mlx5_hv_vhca		*hv_vhca;
+	void				*priv;
+	u16                              seq;
+	void (*control)(struct mlx5_hv_vhca_agent *agent,
+			struct mlx5_hv_vhca_control_block *block);
+	void (*invalidate)(struct mlx5_hv_vhca_agent *agent,
+			   u64 block_mask);
+	void (*cleanup)(struct mlx5_hv_vhca_agent *agent);
+};
+
+struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_hv_vhca *hv_vhca = NULL;
+
+	hv_vhca = kzalloc(sizeof(*hv_vhca), GFP_KERNEL);
+	if (!hv_vhca)
+		return ERR_PTR(-ENOMEM);
+
+	hv_vhca->work_queue = create_singlethread_workqueue("mlx5_hv_vhca");
+	if (!hv_vhca->work_queue) {
+		kfree(hv_vhca);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	hv_vhca->dev = dev;
+	mutex_init(&hv_vhca->agents_lock);
+
+	return hv_vhca;
+}
+
+void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca)
+{
+	if (IS_ERR_OR_NULL(hv_vhca))
+		return;
+
+	destroy_workqueue(hv_vhca->work_queue);
+	kfree(hv_vhca);
+}
+
+static void mlx5_hv_vhca_invalidate_work(struct work_struct *work)
+{
+	struct mlx5_hv_vhca_work *hwork;
+	struct mlx5_hv_vhca *hv_vhca;
+	int i;
+
+	hwork = container_of(work, struct mlx5_hv_vhca_work, invalidate_work);
+	hv_vhca = hwork->hv_vhca;
+
+	mutex_lock(&hv_vhca->agents_lock);
+	for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+		struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+		if (!agent || !agent->invalidate)
+			continue;
+
+		if (!(BIT(agent->type) & hwork->block_mask))
+			continue;
+
+		agent->invalidate(agent, hwork->block_mask);
+	}
+	mutex_unlock(&hv_vhca->agents_lock);
+
+	kfree(hwork);
+}
+
+void mlx5_hv_vhca_invalidate(void *context, u64 block_mask)
+{
+	struct mlx5_hv_vhca *hv_vhca = (struct mlx5_hv_vhca *)context;
+	struct mlx5_hv_vhca_work *work;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	INIT_WORK(&work->invalidate_work, mlx5_hv_vhca_invalidate_work);
+	work->hv_vhca    = hv_vhca;
+	work->block_mask = block_mask;
+
+	queue_work(hv_vhca->work_queue, &work->invalidate_work);
+}
+
+#define AGENT_MASK(type) (type ? BIT(type - 1) : 0 /* control */)
+
+static void mlx5_hv_vhca_agents_control(struct mlx5_hv_vhca *hv_vhca,
+					struct mlx5_hv_vhca_control_block *block)
+{
+	int i;
+
+	for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+		struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+		if (!agent || !agent->control)
+			continue;
+
+		if (!(AGENT_MASK(agent->type) & block->control))
+			continue;
+
+		agent->control(agent, block);
+	}
+}
+
+static void mlx5_hv_vhca_capabilities(struct mlx5_hv_vhca *hv_vhca,
+				      u32 *capabilities)
+{
+	int i;
+
+	for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+		struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+		if (agent)
+			*capabilities |= AGENT_MASK(agent->type);
+	}
+}
+
+static void
+mlx5_hv_vhca_control_agent_invalidate(struct mlx5_hv_vhca_agent *agent,
+				      u64 block_mask)
+{
+	struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca;
+	struct mlx5_core_dev *dev = hv_vhca->dev;
+	struct mlx5_hv_vhca_control_block *block;
+	u32 capabilities = 0;
+	int err;
+
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return;
+
+	err = mlx5_hv_read_config(dev, block, sizeof(*block), 0);
+	if (err)
+		goto free_block;
+
+	mlx5_hv_vhca_capabilities(hv_vhca, &capabilities);
+
+	/* In case no capabilities, send empty block in return */
+	if (!capabilities) {
+		memset(block, 0, sizeof(*block));
+		goto write;
+	}
+
+	if (block->capabilities != capabilities)
+		block->capabilities = capabilities;
+
+	if (block->control & ~capabilities)
+		goto free_block;
+
+	mlx5_hv_vhca_agents_control(hv_vhca, block);
+	block->command_ack = block->command;
+
+write:
+	mlx5_hv_write_config(dev, block, sizeof(*block), 0);
+
+free_block:
+	kfree(block);
+}
+
+static struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_control_agent_create(struct mlx5_hv_vhca *hv_vhca)
+{
+	return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL,
+					 NULL,
+					 mlx5_hv_vhca_control_agent_invalidate,
+					 NULL, NULL);
+}
+
+static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+	mlx5_hv_vhca_agent_destroy(agent);
+}
+
+int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca)
+{
+	struct mlx5_hv_vhca_agent *agent;
+	int err;
+
+	if (IS_ERR_OR_NULL(hv_vhca))
+		return IS_ERR_OR_NULL(hv_vhca);
+
+	err = mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca,
+					  mlx5_hv_vhca_invalidate);
+	if (err)
+		return err;
+
+	agent = mlx5_hv_vhca_control_agent_create(hv_vhca);
+	if (IS_ERR_OR_NULL(agent)) {
+		mlx5_hv_unregister_invalidate(hv_vhca->dev);
+		return IS_ERR_OR_NULL(agent);
+	}
+
+	hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL] = agent;
+
+	return 0;
+}
+
+void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
+{
+	struct mlx5_hv_vhca_agent *agent;
+	int i;
+
+	if (IS_ERR_OR_NULL(hv_vhca))
+		return;
+
+	agent = hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL];
+	if (agent)
+		mlx5_hv_vhca_control_agent_destroy(agent);
+
+	mutex_lock(&hv_vhca->agents_lock);
+	for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++)
+		WARN_ON(hv_vhca->agents[i]);
+
+	mutex_unlock(&hv_vhca->agents_lock);
+
+	mlx5_hv_unregister_invalidate(hv_vhca->dev);
+}
+
+static void mlx5_hv_vhca_agents_update(struct mlx5_hv_vhca *hv_vhca)
+{
+	mlx5_hv_vhca_invalidate(hv_vhca, BIT(MLX5_HV_VHCA_AGENT_CONTROL));
+}
+
+struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+			  enum mlx5_hv_vhca_agent_type type,
+			  void (*control)(struct mlx5_hv_vhca_agent*,
+					  struct mlx5_hv_vhca_control_block *block),
+			  void (*invalidate)(struct mlx5_hv_vhca_agent*,
+					     u64 block_mask),
+			  void (*cleaup)(struct mlx5_hv_vhca_agent *agent),
+			  void *priv)
+{
+	struct mlx5_hv_vhca_agent *agent;
+
+	if (IS_ERR_OR_NULL(hv_vhca))
+		return ERR_PTR(-ENOMEM);
+
+	if (type >= MLX5_HV_VHCA_AGENT_MAX)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&hv_vhca->agents_lock);
+	if (hv_vhca->agents[type]) {
+		mutex_unlock(&hv_vhca->agents_lock);
+		return ERR_PTR(-EINVAL);
+	}
+	mutex_unlock(&hv_vhca->agents_lock);
+
+	agent = kzalloc(sizeof(*agent), GFP_KERNEL);
+	if (!agent)
+		return ERR_PTR(-ENOMEM);
+
+	agent->type      = type;
+	agent->hv_vhca   = hv_vhca;
+	agent->priv      = priv;
+	agent->control   = control;
+	agent->invalidate = invalidate;
+	agent->cleanup   = cleaup;
+
+	mutex_lock(&hv_vhca->agents_lock);
+	hv_vhca->agents[type] = agent;
+	mutex_unlock(&hv_vhca->agents_lock);
+
+	mlx5_hv_vhca_agents_update(hv_vhca);
+
+	return agent;
+}
+
+void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+	struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca;
+
+	mutex_lock(&hv_vhca->agents_lock);
+
+	if (WARN_ON(agent != hv_vhca->agents[agent->type])) {
+		mutex_unlock(&hv_vhca->agents_lock);
+		return;
+	}
+
+	hv_vhca->agents[agent->type] = NULL;
+	mutex_unlock(&hv_vhca->agents_lock);
+
+	if (agent->cleanup)
+		agent->cleanup(agent);
+
+	kfree(agent);
+
+	mlx5_hv_vhca_agents_update(hv_vhca);
+}
+
+static int mlx5_hv_vhca_data_block_prepare(struct mlx5_hv_vhca_agent *agent,
+					   struct mlx5_hv_vhca_data_block *data_block,
+					   void *src, int len, int *offset)
+{
+	int bytes = min_t(int, (int)sizeof(data_block->data), len);
+
+	data_block->sequence = agent->seq;
+	data_block->offset   = (*offset)++;
+	memcpy(data_block->data, src, bytes);
+
+	return bytes;
+}
+
+static void mlx5_hv_vhca_agent_seq_update(struct mlx5_hv_vhca_agent *agent)
+{
+	agent->seq++;
+}
+
+int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent,
+			     void *buf, int len)
+{
+	int offset = agent->type * HV_CONFIG_BLOCK_SIZE_MAX;
+	int block_offset = 0;
+	int total = 0;
+	int err;
+
+	while (len) {
+		struct mlx5_hv_vhca_data_block data_block = {0};
+		int bytes;
+
+		bytes = mlx5_hv_vhca_data_block_prepare(agent, &data_block,
+							buf + total,
+							len, &block_offset);
+		if (!bytes)
+			return -ENOMEM;
+
+		err = mlx5_hv_write_config(agent->hv_vhca->dev, &data_block,
+					   sizeof(data_block), offset);
+		if (err)
+			return err;
+
+		total += bytes;
+		len   -= bytes;
+	}
+
+	mlx5_hv_vhca_agent_seq_update(agent);
+
+	return 0;
+}
+
+void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent)
+{
+	return agent->priv;
+}

drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __LIB_HV_VHCA_H__
+#define __LIB_HV_VHCA_H__
+
+#include "en.h"
+#include "lib/hv.h"
+
+struct mlx5_hv_vhca_agent;
+struct mlx5_hv_vhca;
+struct mlx5_hv_vhca_control_block;
+
+enum mlx5_hv_vhca_agent_type {
+	MLX5_HV_VHCA_AGENT_CONTROL = 0,
+	MLX5_HV_VHCA_AGENT_STATS   = 1,
+	MLX5_HV_VHCA_AGENT_MAX = 32,
+};
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+struct mlx5_hv_vhca_control_block {
+	u32     capabilities;
+	u32     control;
+	u16     command;
+	u16     command_ack;
+	u16     version;
+	u16     rings;
+	u32     reserved1[28];
+};
+
+struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev);
+void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca);
+int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca);
+void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca);
+void mlx5_hv_vhca_invalidate(void *context, u64 block_mask);
+
+struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+			  enum mlx5_hv_vhca_agent_type type,
+			  void (*control)(struct mlx5_hv_vhca_agent*,
+					  struct mlx5_hv_vhca_control_block *block),
+			  void (*invalidate)(struct mlx5_hv_vhca_agent*,
+					     u64 block_mask),
+			  void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
+			  void *context);
+
+void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent);
+int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent,
+			     void *buf, int len);
+void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent);
+
+#else
+
+static inline struct mlx5_hv_vhca *
+mlx5_hv_vhca_create(struct mlx5_core_dev *dev)
+{
+	return NULL;
+}
+
+static inline void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca)
+{
+}
+
+static inline int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca)
+{
+	return 0;
+}
+
+static inline void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
+{
+}
+
+static inline void mlx5_hv_vhca_invalidate(void *context,
+					   u64 block_mask)
+{
+}
+
+static inline struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+			  enum mlx5_hv_vhca_agent_type type,
+			  void (*control)(struct mlx5_hv_vhca_agent*,
+					  struct mlx5_hv_vhca_control_block *block),
+			  void (*invalidate)(struct mlx5_hv_vhca_agent*,
+					     u64 block_mask),
+			  void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
+			  void *context)
+{
+	return NULL;
+}
+
+static inline void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+}
+
+static inline int
+mlx5_hv_vhca_write_agent(struct mlx5_hv_vhca_agent *agent,
+			 void *buf, int len)
+{
+	return 0;
+}
+#endif
+
+#endif /* __LIB_HV_VHCA_H__ */

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -69,6 +69,7 @@
 #include "lib/pci_vsc.h"
 #include "diag/fw_tracer.h"
 #include "ecpf.h"
+#include "lib/hv_vhca.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -870,6 +871,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->tracer = mlx5_fw_tracer_create(dev);
+	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 
 	return 0;
 
@@ -900,6 +902,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
@@ -1067,6 +1070,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fw_tracer;
 	}
 
+	mlx5_hv_vhca_init(dev->hv_vhca);
+
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
 		mlx5_core_err(dev, "fpga device start failed %d\n", err);
@@ -1122,6 +1127,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
 err_fpga_start:
+	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
@@ -1142,6 +1148,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_accel_tls_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
+	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);

drivers/pci/Kconfig

@@ -182,6 +182,7 @@ config PCI_LABEL
 config PCI_HYPERV
         tristate "Hyper-V PCI Frontend"
         depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+	select PCI_HYPERV_INTERFACE
         help
           The PCI device frontend driver allows the kernel to import arbitrary
           PCI devices from a PCI backend to support PCI driver domains.

drivers/pci/controller/Kconfig

@@ -281,5 +281,12 @@ config VMD
 	  To compile this driver as a module, choose M here: the
 	  module will be called vmd.
 
+config PCI_HYPERV_INTERFACE
+	tristate "Hyper-V PCI Interface"
+	depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+	help
+	  The Hyper-V PCI Interface is a helper driver allows other drivers to
+	  have a common interface with the Hyper-V PCI frontend driver.
+
 source "drivers/pci/controller/dwc/Kconfig"
 endmenu

drivers/pci/controller/Makefile

@@ -4,6 +4,7 @@ obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o
 obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o
 obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o
 obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
+obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
 obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o

drivers/pci/controller/pci-hyperv-intf.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) Microsoft Corporation.
+ *
+ * Author:
+ *   Haiyang Zhang <haiyangz@microsoft.com>
+ *
+ * This small module is a helper driver allows other drivers to
+ * have a common interface with the Hyper-V PCI frontend driver.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/hyperv.h>
+
+struct hyperv_pci_block_ops hvpci_block_ops;
+EXPORT_SYMBOL_GPL(hvpci_block_ops);
+
+int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len,
+			unsigned int block_id, unsigned int *bytes_returned)
+{
+	if (!hvpci_block_ops.read_block)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.read_block(dev, buf, buf_len, block_id,
+					  bytes_returned);
+}
+EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk);
+
+int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
+			 unsigned int block_id)
+{
+	if (!hvpci_block_ops.write_block)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.write_block(dev, buf, len, block_id);
+}
+EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk);
+
+int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
+				void (*block_invalidate)(void *context,
+							 u64 block_mask))
+{
+	if (!hvpci_block_ops.reg_blk_invalidate)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.reg_blk_invalidate(dev, context,
+						  block_invalidate);
+}
+EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate);
+
+static void __exit exit_hv_pci_intf(void)
+{
+}
+
+static int __init init_hv_pci_intf(void)
+{
+	return 0;
+}
+
+module_init(init_hv_pci_intf);
+module_exit(exit_hv_pci_intf);
+
+MODULE_DESCRIPTION("Hyper-V PCI Interface");
+MODULE_LICENSE("GPL v2");

drivers/pci/controller/pci-hyperv.c

@@ -365,6 +365,39 @@ struct pci_delete_interrupt {
 	struct tran_int_desc int_desc;
 } __packed;
 
+/*
+ * Note: the VM must pass a valid block id, wslot and bytes_requested.
+ */
+struct pci_read_block {
+	struct pci_message message_type;
+	u32 block_id;
+	union win_slot_encoding wslot;
+	u32 bytes_requested;
+} __packed;
+
+struct pci_read_block_response {
+	struct vmpacket_descriptor hdr;
+	u32 status;
+	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+/*
+ * Note: the VM must pass a valid block id, wslot and byte_count.
+ */
+struct pci_write_block {
+	struct pci_message message_type;
+	u32 block_id;
+	union win_slot_encoding wslot;
+	u32 byte_count;
+	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+struct pci_dev_inval_block {
+	struct pci_incoming_message incoming;
+	union win_slot_encoding wslot;
+	u64 block_mask;
+} __packed;
+
 struct pci_dev_incoming {
 	struct pci_incoming_message incoming;
 	union win_slot_encoding wslot;
@@ -499,6 +532,9 @@ struct hv_pci_dev {
 	struct hv_pcibus_device *hbus;
 	struct work_struct wrk;
 
+	void (*block_invalidate)(void *context, u64 block_mask);
+	void *invalidate_context;
+
 	/*
 	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
 	 * read it back, for each of the BAR offsets within config space.
@@ -817,6 +853,253 @@ static struct pci_ops hv_pcifront_ops = {
 	.write = hv_pcifront_write_config,
 };
 
+/*
+ * Paravirtual backchannel
+ *
+ * Hyper-V SR-IOV provides a backchannel mechanism in software for
+ * communication between a VF driver and a PF driver.  These
+ * "configuration blocks" are similar in concept to PCI configuration space,
+ * but instead of doing reads and writes in 32-bit chunks through a very slow
+ * path, packets of up to 128 bytes can be sent or received asynchronously.
+ *
+ * Nearly every SR-IOV device contains just such a communications channel in
+ * hardware, so using this one in software is usually optional.  Using the
+ * software channel, however, allows driver implementers to leverage software
+ * tools that fuzz the communications channel looking for vulnerabilities.
+ *
+ * The usage model for these packets puts the responsibility for reading or
+ * writing on the VF driver.  The VF driver sends a read or a write packet,
+ * indicating which "block" is being referred to by number.
+ *
+ * If the PF driver wishes to initiate communication, it can "invalidate" one or
+ * more of the first 64 blocks.  This invalidation is delivered via a callback
+ * supplied by the VF driver by this driver.
+ *
+ * No protocol is implied, except that supplied by the PF and VF drivers.
+ */
+
+struct hv_read_config_compl {
+	struct hv_pci_compl comp_pkt;
+	void *buf;
+	unsigned int len;
+	unsigned int bytes_returned;
+};
+
+/**
+ * hv_pci_read_config_compl() - Invoked when a response packet
+ * for a read config block operation arrives.
+ * @context:		Identifies the read config operation
+ * @resp:		The response packet itself
+ * @resp_packet_size:	Size in bytes of the response packet
+ */
+static void hv_pci_read_config_compl(void *context, struct pci_response *resp,
+				     int resp_packet_size)
+{
+	struct hv_read_config_compl *comp = context;
+	struct pci_read_block_response *read_resp =
+		(struct pci_read_block_response *)resp;
+	unsigned int data_len, hdr_len;
+
+	hdr_len = offsetof(struct pci_read_block_response, bytes);
+	if (resp_packet_size < hdr_len) {
+		comp->comp_pkt.completion_status = -1;
+		goto out;
+	}
+
+	data_len = resp_packet_size - hdr_len;
+	if (data_len > 0 && read_resp->status == 0) {
+		comp->bytes_returned = min(comp->len, data_len);
+		memcpy(comp->buf, read_resp->bytes, comp->bytes_returned);
+	} else {
+		comp->bytes_returned = 0;
+	}
+
+	comp->comp_pkt.completion_status = read_resp->status;
+out:
+	complete(&comp->comp_pkt.host_event);
+}
+
+/**
+ * hv_read_config_block() - Sends a read config block request to
+ * the back-end driver running in the Hyper-V parent partition.
+ * @pdev:		The PCI driver's representation for this device.
+ * @buf:		Buffer into which the config block will be copied.
+ * @len:		Size in bytes of buf.
+ * @block_id:		Identifies the config block which has been requested.
+ * @bytes_returned:	Size which came back from the back-end driver.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+			 unsigned int block_id, unsigned int *bytes_returned)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct {
+		struct pci_packet pkt;
+		char buf[sizeof(struct pci_read_block)];
+	} pkt;
+	struct hv_read_config_compl comp_pkt;
+	struct pci_read_block *read_blk;
+	int ret;
+
+	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+		return -EINVAL;
+
+	init_completion(&comp_pkt.comp_pkt.host_event);
+	comp_pkt.buf = buf;
+	comp_pkt.len = len;
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.pkt.completion_func = hv_pci_read_config_compl;
+	pkt.pkt.compl_ctxt = &comp_pkt;
+	read_blk = (struct pci_read_block *)&pkt.pkt.message;
+	read_blk->message_type.type = PCI_READ_BLOCK;
+	read_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+	read_blk->block_id = block_id;
+	read_blk->bytes_requested = len;
+
+	ret = vmbus_sendpacket(hbus->hdev->channel, read_blk,
+			       sizeof(*read_blk), (unsigned long)&pkt.pkt,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		return ret;
+
+	ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event);
+	if (ret)
+		return ret;
+
+	if (comp_pkt.comp_pkt.completion_status != 0 ||
+	    comp_pkt.bytes_returned == 0) {
+		dev_err(&hbus->hdev->device,
+			"Read Config Block failed: 0x%x, bytes_returned=%d\n",
+			comp_pkt.comp_pkt.completion_status,
+			comp_pkt.bytes_returned);
+		return -EIO;
+	}
+
+	*bytes_returned = comp_pkt.bytes_returned;
+	return 0;
+}
+
+/**
+ * hv_pci_write_config_compl() - Invoked when a response packet for a write
+ * config block operation arrives.
+ * @context:		Identifies the write config operation
+ * @resp:		The response packet itself
+ * @resp_packet_size:	Size in bytes of the response packet
+ */
+static void hv_pci_write_config_compl(void *context, struct pci_response *resp,
+				      int resp_packet_size)
+{
+	struct hv_pci_compl *comp_pkt = context;
+
+	comp_pkt->completion_status = resp->status;
+	complete(&comp_pkt->host_event);
+}
+
+/**
+ * hv_write_config_block() - Sends a write config block request to the
+ * back-end driver running in the Hyper-V parent partition.
+ * @pdev:		The PCI driver's representation for this device.
+ * @buf:		Buffer from which the config block will	be copied.
+ * @len:		Size in bytes of buf.
+ * @block_id:		Identifies the config block which is being written.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+			  unsigned int block_id)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct {
+		struct pci_packet pkt;
+		char buf[sizeof(struct pci_write_block)];
+		u32 reserved;
+	} pkt;
+	struct hv_pci_compl comp_pkt;
+	struct pci_write_block *write_blk;
+	u32 pkt_size;
+	int ret;
+
+	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+		return -EINVAL;
+
+	init_completion(&comp_pkt.host_event);
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.pkt.completion_func = hv_pci_write_config_compl;
+	pkt.pkt.compl_ctxt = &comp_pkt;
+	write_blk = (struct pci_write_block *)&pkt.pkt.message;
+	write_blk->message_type.type = PCI_WRITE_BLOCK;
+	write_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+	write_blk->block_id = block_id;
+	write_blk->byte_count = len;
+	memcpy(write_blk->bytes, buf, len);
+	pkt_size = offsetof(struct pci_write_block, bytes) + len;
+	/*
+	 * This quirk is required on some hosts shipped around 2018, because
+	 * these hosts don't check the pkt_size correctly (new hosts have been
+	 * fixed since early 2019). The quirk is also safe on very old hosts
+	 * and new hosts, because, on them, what really matters is the length
+	 * specified in write_blk->byte_count.
+	 */
+	pkt_size += sizeof(pkt.reserved);
+
+	ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size,
+			       (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		return ret;
+
+	ret = wait_for_response(hbus->hdev, &comp_pkt.host_event);
+	if (ret)
+		return ret;
+
+	if (comp_pkt.completion_status != 0) {
+		dev_err(&hbus->hdev->device,
+			"Write Config Block failed: 0x%x\n",
+			comp_pkt.completion_status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * hv_register_block_invalidate() - Invoked when a config block invalidation
+ * arrives from the back-end driver.
+ * @pdev:		The PCI driver's representation for this device.
+ * @context:		Identifies the device.
+ * @block_invalidate:	Identifies all of the blocks being invalidated.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_register_block_invalidate(struct pci_dev *pdev, void *context,
+				 void (*block_invalidate)(void *context,
+							  u64 block_mask))
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		return -ENODEV;
+
+	hpdev->block_invalidate = block_invalidate;
+	hpdev->invalidate_context = context;
+
+	put_pcichild(hpdev);
+	return 0;
+
+}
+
 /* Interrupt management hooks */
 static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 			     struct tran_int_desc *int_desc)
@@ -1968,6 +2251,7 @@ static void hv_pci_onchannelcallback(void *context)
 	struct pci_response *response;
 	struct pci_incoming_message *new_message;
 	struct pci_bus_relations *bus_rel;
+	struct pci_dev_inval_block *inval;
 	struct pci_dev_incoming *dev_message;
 	struct hv_pci_dev *hpdev;
 
@@ -2045,6 +2329,21 @@ static void hv_pci_onchannelcallback(void *context)
 				}
 				break;
 
+			case PCI_INVALIDATE_BLOCK:
+
+				inval = (struct pci_dev_inval_block *)buffer;
+				hpdev = get_pcichild_wslot(hbus,
+							   inval->wslot.slot);
+				if (hpdev) {
+					if (hpdev->block_invalidate) {
+						hpdev->block_invalidate(
+						    hpdev->invalidate_context,
+						    inval->block_mask);
+					}
+					put_pcichild(hpdev);
+				}
+				break;
+
 			default:
 				dev_warn(&hbus->hdev->device,
 					"Unimplemented protocol message %x\n",
@@ -2743,10 +3042,19 @@ static struct hv_driver hv_pci_drv = {
 static void __exit exit_hv_pci_drv(void)
 {
 	vmbus_driver_unregister(&hv_pci_drv);
+
+	hvpci_block_ops.read_block = NULL;
+	hvpci_block_ops.write_block = NULL;
+	hvpci_block_ops.reg_blk_invalidate = NULL;
 }
 
 static int __init init_hv_pci_drv(void)
 {
+	/* Initialize PCI block r/w interface */
+	hvpci_block_ops.read_block = hv_read_config_block;
+	hvpci_block_ops.write_block = hv_write_config_block;
+	hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate;
+
 	return vmbus_driver_register(&hv_pci_drv);
 }
 

include/linux/hyperv.h

@@ -1578,4 +1578,33 @@ hv_pkt_iter_next(struct vmbus_channel *channel,
 	for (pkt = hv_pkt_iter_first(channel); pkt; \
 	    pkt = hv_pkt_iter_next(channel, pkt))
 
+/*
+ * Interface for passing data between SR-IOV PF and VF drivers. The VF driver
+ * sends requests to read and write blocks. Each block must be 128 bytes or
+ * smaller. Optionally, the VF driver can register a callback function which
+ * will be invoked when the host says that one or more of the first 64 block
+ * IDs is "invalid" which means that the VF driver should reread them.
+ */
+#define HV_CONFIG_BLOCK_SIZE_MAX 128
+
+int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len,
+			unsigned int block_id, unsigned int *bytes_returned);
+int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
+			 unsigned int block_id);
+int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
+				void (*block_invalidate)(void *context,
+							 u64 block_mask));
+
+struct hyperv_pci_block_ops {
+	int (*read_block)(struct pci_dev *dev, void *buf, unsigned int buf_len,
+			  unsigned int block_id, unsigned int *bytes_returned);
+	int (*write_block)(struct pci_dev *dev, void *buf, unsigned int len,
+			   unsigned int block_id);
+	int (*reg_blk_invalidate)(struct pci_dev *dev, void *context,
+				  void (*block_invalidate)(void *context,
+							   u64 block_mask));
+};
+
+extern struct hyperv_pci_block_ops hvpci_block_ops;
+
 #endif /* _HYPERV_H */

include/linux/mlx5/driver.h

@@ -659,6 +659,7 @@ struct mlx5_clock {
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 struct mlx5_geneve;
+struct mlx5_hv_vhca;
 
 struct mlx5_core_dev {
 	struct device *device;
@@ -706,6 +707,7 @@ struct mlx5_core_dev {
 	struct mlx5_ib_clock_info  *clock_info;
 	struct mlx5_fw_tracer   *tracer;
 	u32                      vsc_addr;
+	struct mlx5_hv_vhca	*hv_vhca;
 };
 
 struct mlx5_db {