Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zhu Lingshan <lingshan.zhu@intel.com>
To:     mst@redhat.com, jasowang@redhat.com, alex.williamson@redhat.com
Cc:     linux-kernel@vger.kernel.org,
        virtualization@lists.linux-foundation.org, kvm@vger.kernel.org,
        netdev@vger.kernel.org, dan.daly@intel.com,
        cunming.liang@intel.com, tiwei.bie@intel.com, jason.zeng@intel.com,
        zhiyuan.lv@intel.com, Zhu Lingshan <lingshan.zhu@intel.com>
Subject: [RFC V4 1/2] This commit introduced ifcvf_base layer.
Date:   Wed, 20 Nov 2019 17:17:10 +0800
Message-Id: <1574241431-24792-2-git-send-email-lingshan.zhu@intel.com>
In-Reply-To: <1574241431-24792-1-git-send-email-lingshan.zhu@intel.com>
References: <1574241431-24792-1-git-send-email-lingshan.zhu@intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

IFC NIC is a new type of Intel hardware virtio datapath
offloading card, this commit intend to handle hardware operations
and configurations.

Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
---
 drivers/vhost/ifcvf/ifcvf_base.c | 326 +++++++++++++++++++++++++++++++++++++++
 drivers/vhost/ifcvf/ifcvf_base.h | 129 ++++++++++++++++
 2 files changed, 455 insertions(+)
 create mode 100644 drivers/vhost/ifcvf/ifcvf_base.c
 create mode 100644 drivers/vhost/ifcvf/ifcvf_base.h

diff --git a/drivers/vhost/ifcvf/ifcvf_base.c b/drivers/vhost/ifcvf/ifcvf_base.c
new file mode 100644
index 0000000..6bf2ddd
--- /dev/null
+++ b/drivers/vhost/ifcvf/ifcvf_base.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 Intel Corporation.
+ */
+
+#include "ifcvf_base.h"
+
+static void *get_cap_addr(struct ifcvf_hw *hw, struct virtio_pci_cap *cap)
+{
+	struct ifcvf_adapter *ifcvf;
+	u32 length, offset;
+	u8 bar;
+
+	length = le32_to_cpu(cap->length);
+	offset = le32_to_cpu(cap->offset);
+	bar = le32_to_cpu(cap->bar);
+
+	ifcvf = container_of(hw, struct ifcvf_adapter, vf);
+
+	if (bar >= IFCVF_PCI_MAX_RESOURCE) {
+		IFC_DBG(ifcvf->dev,
+			"Invalid bar number %u to get capabilities\n", bar);
+		return NULL;
+	}
+
+	if (offset + length > hw->mem_resource[cap->bar].len) {
+		IFC_DBG(ifcvf->dev,
+			"offset(%u) + len(%u) overflows bar%u to get capabilities\n",
+			offset, length, bar);
+		return NULL;
+	}
+
+	return hw->mem_resource[bar].addr + offset;
+}
+
+int ifcvf_read_config_range(struct pci_dev *dev,
+			uint32_t *val, int size, int where)
+{
+	int ret, i;
+
+	for (i = 0; i < size; i += 4) {
+		ret = pci_read_config_dword(dev, where + i, val + i / 4);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev)
+{
+	struct virtio_pci_cap cap;
+	u16 notify_off;
+	int ret;
+	u8 pos;
+	u32 i;
+
+	ret = pci_read_config_byte(dev, PCI_CAPABILITY_LIST, &pos);
+
+	if (ret < 0) {
+		IFC_ERR(&dev->dev, "Failed to read PCI capability list\n");
+		return -EIO;
+	}
+
+	while (pos) {
+		ret = ifcvf_read_config_range(dev, (u32 *)&cap,
+					      sizeof(cap), pos);
+
+		if (ret < 0) {
+			IFC_ERR(&dev->dev, "Failed to get PCI capability at %x\n",
+				pos);
+			break;
+		}
+
+		if (cap.cap_vndr != PCI_CAP_ID_VNDR)
+			goto next;
+
+		IFC_DBG(&dev->dev, "read PCI config: config type: %u, PCI bar: %u, PCI bar offset: %u, PCI config len: %u\n",
+			cap.cfg_type, cap.bar, cap.offset, cap.length);
+
+		switch (cap.cfg_type) {
+		case VIRTIO_PCI_CAP_COMMON_CFG:
+			hw->common_cfg = get_cap_addr(hw, &cap);
+			IFC_DBG(&dev->dev, "hw->common_cfg = %p\n",
+				hw->common_cfg);
+			break;
+		case VIRTIO_PCI_CAP_NOTIFY_CFG:
+			pci_read_config_dword(dev, pos + sizeof(cap),
+					      &hw->notify_off_multiplier);
+			hw->notify_bar = cap.bar;
+			hw->notify_base = get_cap_addr(hw, &cap);
+			IFC_DBG(&dev->dev, "hw->notify_base = %p\n",
+				hw->notify_base);
+			break;
+		case VIRTIO_PCI_CAP_ISR_CFG:
+			hw->isr = get_cap_addr(hw, &cap);
+			IFC_DBG(&dev->dev, "hw->isr = %p\n", hw->isr);
+			break;
+		case VIRTIO_PCI_CAP_DEVICE_CFG:
+			hw->net_cfg = get_cap_addr(hw, &cap);
+			IFC_DBG(&dev->dev, "hw->net_cfg = %p\n", hw->net_cfg);
+			break;
+		}
+next:
+		pos = cap.cap_next;
+	}
+
+	if (hw->common_cfg == NULL || hw->notify_base == NULL ||
+	    hw->isr == NULL || hw->net_cfg == NULL) {
+		IFC_DBG(&dev->dev, "Incomplete PCI capabilities\n");
+		return -1;
+	}
+
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+		iowrite16(i, &hw->common_cfg->queue_select);
+		notify_off = ioread16(&hw->common_cfg->queue_notify_off);
+		hw->vring->notify_addr[i] = (void *)((u8 *)hw->notify_base +
+				     notify_off * hw->notify_off_multiplier);
+	}
+
+	hw->lm_cfg = hw->mem_resource[IFCVF_LM_BAR].addr;
+
+	IFC_DBG(&dev->dev, "PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n",
+		hw->common_cfg, hw->notify_base, hw->isr,
+		hw->net_cfg, hw->notify_off_multiplier);
+
+	return 0;
+}
+
+u8 ifcvf_get_status(struct ifcvf_hw *hw)
+{
+	return ioread8(&hw->common_cfg->device_status);
+}
+
+void ifcvf_set_status(struct ifcvf_hw *hw, u8 status)
+{
+	iowrite8(status, &hw->common_cfg->device_status);
+}
+
+void ifcvf_reset(struct ifcvf_hw *hw)
+{
+	ifcvf_set_status(hw, 0);
+	ifcvf_get_status(hw);
+}
+
+static void ifcvf_add_status(struct ifcvf_hw *hw, u8 status)
+{
+	if (status != 0)
+		status |= ifcvf_get_status(hw);
+
+	ifcvf_set_status(hw, status);
+	ifcvf_get_status(hw);
+}
+
+u64 ifcvf_get_features(struct ifcvf_hw *hw)
+{
+	struct virtio_pci_common_cfg *cfg = hw->common_cfg;
+	u32 features_lo, features_hi;
+
+	iowrite32(0, &cfg->device_feature_select);
+	features_lo = ioread32(&cfg->device_feature);
+
+	iowrite32(1, &cfg->device_feature_select);
+	features_hi = ioread32(&cfg->device_feature);
+
+	return ((u64)features_hi << 32) | features_lo;
+}
+
+void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+		       void *dst, int length)
+{
+	u8 old_gen, new_gen, *p;
+	int i;
+
+	WARN_ON(offset + length > sizeof (struct virtio_net_config));
+
+	do {
+		old_gen = ioread8(&hw->common_cfg->config_generation);
+		p = dst;
+
+		for (i = 0; i < length; i++)
+			*p++ = ioread8((u8 *)hw->net_cfg + offset + i);
+
+		new_gen = ioread8(&hw->common_cfg->config_generation);
+	} while (old_gen != new_gen);
+}
+
+void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+			    const void *src, int length)
+{
+	const u8 *p;
+	int i;
+
+	p = src;
+	WARN_ON(offset + length > sizeof(struct virtio_net_config));
+
+	for (i = 0; i < length; i++)
+		iowrite8(*p++, (u8 *)hw->net_cfg + offset + i);
+}
+
+static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)
+{
+	struct virtio_pci_common_cfg *cfg = hw->common_cfg;
+
+	iowrite32(0, &cfg->guest_feature_select);
+	iowrite32((u32)features, &cfg->guest_feature);
+
+	iowrite32(1, &cfg->guest_feature_select);
+	iowrite32(features >> 32, &cfg->guest_feature);
+}
+
+static int ifcvf_config_features(struct ifcvf_hw *hw)
+{
+	struct ifcvf_adapter *ifcvf;
+
+	ifcvf = container_of(hw, struct ifcvf_adapter, vf);
+	ifcvf_set_features(hw, hw->req_features);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_FEATURES_OK);
+
+	if (!(ifcvf_get_status(hw) & VIRTIO_CONFIG_S_FEATURES_OK)) {
+		IFC_ERR(ifcvf->dev, "Failed to set FEATURES_OK status\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+void io_write64_twopart(u64 val, u32 *lo, u32 *hi)
+{
+	iowrite32(val & ((1ULL << 32) - 1), lo);
+	iowrite32(val >> 32, hi);
+}
+
+static int ifcvf_hw_enable(struct ifcvf_hw *hw)
+{
+	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
+	struct virtio_pci_common_cfg *cfg;
+	struct ifcvf_adapter *ifcvf;
+	u32 __iomem* idx_addr;
+	u32 i, val;
+
+	ifcvf_lm = (struct ifcvf_lm_cfg*)hw->lm_cfg;
+	ifcvf = container_of(hw, struct ifcvf_adapter, vf);
+	cfg = hw->common_cfg;
+	iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config);
+
+	if (ioread16(&cfg->msix_config) == VIRTIO_MSI_NO_VECTOR) {
+		IFC_ERR(ifcvf->dev, "No msix vector for device config\n");
+		return -1;
+	}
+
+	for (i = 0; i < hw->nr_vring; i++) {
+		if (!hw->vring[i].ready)
+			break;
+
+		iowrite16(i, &cfg->queue_select);
+		io_write64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo,
+				&cfg->queue_desc_hi);
+		io_write64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo,
+				&cfg->queue_avail_hi);
+		io_write64_twopart(hw->vring[i].used, &cfg->queue_used_lo,
+				&cfg->queue_used_hi);
+		iowrite16(hw->vring[i].size, &cfg->queue_size);
+		idx_addr = &(ifcvf_lm->vring_lm_cfg[i/IFCVF_MAX_QUEUES].idx_addr[i%IFCVF_MAX_QUEUES]);
+		val = (u32)hw->vring[i].last_avail_idx |
+			((u32)hw->vring[i].last_used_idx << 16);
+		iowrite32(val, idx_addr);
+		iowrite16(i + IFCVF_MSI_QUEUE_OFF, &cfg->queue_msix_vector);
+
+		if (ioread16(&cfg->queue_msix_vector) ==
+		    VIRTIO_MSI_NO_VECTOR) {
+			IFC_ERR(ifcvf->dev,
+				"No msix vector for queue %u\n", i);
+			return -1;
+		}
+
+		iowrite16(1, &cfg->queue_enable);
+	}
+
+	return 0;
+}
+
+static void ifcvf_hw_disable(struct ifcvf_hw *hw)
+{
+	struct virtio_pci_common_cfg *cfg;
+	u32 i;
+
+	cfg = hw->common_cfg;
+	iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->msix_config);
+
+	for (i = 0; i < hw->nr_vring; i++) {
+		iowrite16(i, &cfg->queue_select);
+		iowrite16(0, &cfg->queue_enable);
+		iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->queue_msix_vector);
+	}
+
+	ioread16(&cfg->queue_msix_vector);
+}
+
+int ifcvf_start_hw(struct ifcvf_hw *hw)
+{
+	ifcvf_reset(hw);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER);
+
+	if (ifcvf_config_features(hw) < 0)
+		return -1;
+
+	if (ifcvf_hw_enable(hw) < 0)
+		return -1;
+
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	return 0;
+}
+
+void ifcvf_stop_hw(struct ifcvf_hw *hw)
+{
+	ifcvf_hw_disable(hw);
+	ifcvf_reset(hw);
+}
+
+void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid)
+{
+	iowrite16(qid, hw->vring->notify_addr[qid]);
+}
diff --git a/drivers/vhost/ifcvf/ifcvf_base.h b/drivers/vhost/ifcvf/ifcvf_base.h
new file mode 100644
index 0000000..d757f75
--- /dev/null
+++ b/drivers/vhost/ifcvf/ifcvf_base.h
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 Intel Corporation.
+ */
+
+#ifndef _IFCVF_H_
+#define _IFCVF_H_
+
+#include <linux/mdev_virtio.h>
+#include <linux/mdev.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <uapi/linux/virtio_net.h>
+#include <uapi/linux/virtio_config.h>
+#include <uapi/linux/virtio_pci.h>
+
+#define IFCVF_VENDOR_ID         0x1AF4
+#define IFCVF_DEVICE_ID         0x1041
+#define IFCVF_SUBSYS_VENDOR_ID  0x8086
+#define IFCVF_SUBSYS_DEVICE_ID  0x001A
+
+#define IFCVF_MDEV_LIMIT	1
+
+#define IFC_SUPPORTED_FEATURES \
+		((1ULL << VIRTIO_NET_F_MAC)			| \
+		 (1ULL << VIRTIO_F_ANY_LAYOUT)			| \
+		 (1ULL << VIRTIO_F_VERSION_1)			| \
+		 (1ULL << VIRTIO_F_ORDER_PLATFORM)		| \
+		 (1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE)		| \
+		 (1ULL << VIRTIO_F_IOMMU_PLATFORM)		| \
+		 (1ULL << VIRTIO_NET_F_MRG_RXBUF)		| \
+
+/* Not support MQ, only one queue pair for now. */
+#define IFCVF_MAX_QUEUE_PAIRS		1
+#define IFCVF_MAX_QUEUES		2
+
+#define IFCVF_QUEUE_ALIGNMENT		PAGE_SIZE
+#define IFCVF_QUEUE_MAX		32 * 1024
+#define IFCVF_MSI_CONFIG_OFF	0
+#define IFCVF_MSI_QUEUE_OFF	1
+#define IFCVF_PCI_MAX_RESOURCE	6
+
+#define IFCVF_LM_CFG_SIZE		0x40
+#define IFCVF_LM_RING_STATE_OFFSET	0x20
+#define IFCVF_LM_BAR	4
+
+#define IFCVF_32_BIT_MASK		0xffffffff
+
+#define IFC_ERR(dev, fmt, ...)	dev_err(dev, fmt, ##__VA_ARGS__)
+#define IFC_DBG(dev, fmt, ...)	dev_dbg(dev, fmt, ##__VA_ARGS__)
+#define IFC_INFO(dev, fmt, ...)	dev_info(dev, fmt, ##__VA_ARGS__)
+
+#define IFC_PRIVATE_TO_VF(adapter) \
+	(&((struct ifcvf_adapter *)adapter)->vf)
+
+#define IFCVF_MAX_INTR (IFCVF_MAX_QUEUE_PAIRS * 2 + 1)
+
+struct ifcvf_pci_mem_resource {
+	/* Physical address, 0 if not resource. */
+	u64      phys_addr;
+	/* Length of the resource. */
+	u64      len;
+	/* Virtual address, NULL when not mapped. */
+	u8       *addr;
+};
+
+struct vring_info {
+	u64 desc;
+	u64 avail;
+	u64 used;
+	u16 size;
+	u16 last_avail_idx;
+	u16 last_used_idx;
+	bool ready;
+	char msix_name[256];
+	u16 __iomem *notify_addr[IFCVF_MAX_QUEUE_PAIRS * 2];
+	struct virtio_mdev_callback cb;
+};
+
+struct ifcvf_hw {
+	u8	*isr;
+	/* Bar to nofity the VF (queue) */
+	u8	notify_bar;
+	/* live migration */
+	u8	__iomem	*lm_cfg;
+	u8	nr_vring;
+	/* Notificaiton bar address*/
+	u16	*notify_base;
+	u32	notify_off_multiplier;
+	u64	req_features;
+	struct	virtio_pci_common_cfg __iomem	*common_cfg;
+	struct	virtio_net_config __iomem	*net_cfg;
+	struct	vring_info vring[IFCVF_MAX_QUEUE_PAIRS * 2];
+	struct	ifcvf_pci_mem_resource mem_resource[IFCVF_PCI_MAX_RESOURCE];
+};
+
+struct ifcvf_adapter {
+	struct	device *dev;
+	struct	mutex mdev_lock;
+	int	mdev_count;
+	int	vectors;
+	struct	ifcvf_hw vf;
+};
+
+struct ifcvf_vring_lm_cfg {
+	u32 idx_addr[2];
+	u8 reserved[IFCVF_LM_CFG_SIZE - 8];
+};
+
+struct ifcvf_lm_cfg {
+	u8 reserved[IFCVF_LM_RING_STATE_OFFSET];
+	struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUE_PAIRS];
+};
+
+int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
+int ifcvf_start_hw(struct ifcvf_hw *hw);
+void ifcvf_stop_hw(struct ifcvf_hw *hw);
+void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid);
+void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+			   void *dst, int length);
+void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+			    const void *src, int length);
+u8 ifcvf_get_status(struct ifcvf_hw *hw);
+void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
+void io_write64_twopart(u64 val, u32 *lo, u32 *hi);
+void ifcvf_reset(struct ifcvf_hw *hw);
+u64 ifcvf_get_features(struct ifcvf_hw *hw);
+
+#endif /* _IFCVF_H_ */
-- 
1.8.3.1