summaryrefslogtreecommitdiff
path: root/drivers/vdpa
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-11-04 01:00:39 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-11-04 01:00:39 +0300
commit43e1b12927276cde8052122a24ff796649f09d60 (patch)
treee1629f35aca8b865691932bea03d51517926acb0 /drivers/vdpa
parentd4ec3d5535c784c3adbc41c2bbc5d17a00a4a898 (diff)
parent540061ac79f0302ae91e44e6cd216cbaa3af1757 (diff)
downloadlinux-43e1b12927276cde8052122a24ff796649f09d60.tar.xz
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio updates from Michael Tsirkin: "vhost and virtio fixes and features: - Hardening work by Jason - vdpa driver for Alibaba ENI - Performance tweaks for virtio blk - virtio rng rework using an internal buffer - mac/mtu programming for mlx5 vdpa - Misc fixes, cleanups" * tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (45 commits) vdpa/mlx5: Forward only packets with allowed MAC address vdpa/mlx5: Support configuration of MAC vdpa/mlx5: Fix clearing of VIRTIO_NET_F_MAC feature bit vdpa_sim_net: Enable user to set mac address and mtu vdpa: Enable user to set mac and mtu of vdpa device vdpa: Use kernel coding style for structure comments vdpa: Introduce query of device config layout vdpa: Introduce and use vdpa device get, set config helpers virtio-scsi: don't let virtio core to validate used buffer length virtio-blk: don't let virtio core to validate used length virtio-net: don't let virtio core to validate used length virtio_ring: validate used buffer length virtio_blk: correct types for status handling virtio_blk: allow 0 as num_request_queues i2c: virtio: Add support for zero-length requests virtio-blk: fixup coccinelle warnings virtio_ring: fix typos in vring_desc_extra virtio-pci: harden INTX interrupts virtio_pci: harden MSI-X interrupts virtio_config: introduce a new .enable_cbs method ...
Diffstat (limited to 'drivers/vdpa')
-rw-r--r--drivers/vdpa/Kconfig8
-rw-r--r--drivers/vdpa/Makefile1
-rw-r--r--drivers/vdpa/alibaba/Makefile3
-rw-r--r--drivers/vdpa/alibaba/eni_vdpa.c553
-rw-r--r--drivers/vdpa/ifcvf/ifcvf_main.c3
-rw-r--r--drivers/vdpa/mlx5/core/mlx5_vdpa.h2
-rw-r--r--drivers/vdpa/mlx5/net/mlx5_vnet.c202
-rw-r--r--drivers/vdpa/vdpa.c261
-rw-r--r--drivers/vdpa/vdpa_sim/vdpa_sim_blk.c3
-rw-r--r--drivers/vdpa/vdpa_sim/vdpa_sim_net.c38
-rw-r--r--drivers/vdpa/vdpa_user/vduse_dev.c3
-rw-r--r--drivers/vdpa/virtio_pci/vp_vdpa.c12
12 files changed, 1034 insertions, 55 deletions
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 3d91982d8371..50f45d037611 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -78,4 +78,12 @@ config VP_VDPA
help
This kernel module bridges virtio PCI device to vDPA bus.
+config ALIBABA_ENI_VDPA
+ tristate "vDPA driver for Alibaba ENI"
+ select VIRTIO_PCI_LIB_LEGACY
+ depends on PCI_MSI && X86
+ help
+ VDPA driver for Alibaba ENI (Elastic Network Interface) which is built upon
+ virtio 0.9.5 specification.
+
endif # VDPA
diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile
index f02ebed33f19..15665563a7f4 100644
--- a/drivers/vdpa/Makefile
+++ b/drivers/vdpa/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_VDPA_USER) += vdpa_user/
obj-$(CONFIG_IFCVF) += ifcvf/
obj-$(CONFIG_MLX5_VDPA) += mlx5/
obj-$(CONFIG_VP_VDPA) += virtio_pci/
+obj-$(CONFIG_ALIBABA_ENI_VDPA) += alibaba/
diff --git a/drivers/vdpa/alibaba/Makefile b/drivers/vdpa/alibaba/Makefile
new file mode 100644
index 000000000000..ef4aae69f87a
--- /dev/null
+++ b/drivers/vdpa/alibaba/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ALIBABA_ENI_VDPA) += eni_vdpa.o
+
diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c
new file mode 100644
index 000000000000..3f788794571a
--- /dev/null
+++ b/drivers/vdpa/alibaba/eni_vdpa.c
@@ -0,0 +1,553 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vDPA bridge driver for Alibaba ENI(Elastic Network Interface)
+ *
+ * Copyright (c) 2021, Alibaba Inc. All rights reserved.
+ * Author: Wu Zongyong <wuzongyong@linux.alibaba.com>
+ *
+ */
+
+#include "linux/bits.h"
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_pci_legacy.h>
+#include <uapi/linux/virtio_net.h>
+
+#define ENI_MSIX_NAME_SIZE 256
+
+#define ENI_ERR(pdev, fmt, ...) \
+ dev_err(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+#define ENI_DBG(pdev, fmt, ...) \
+ dev_dbg(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+#define ENI_INFO(pdev, fmt, ...) \
+ dev_info(&pdev->dev, "%s"fmt, "eni_vdpa: ", ##__VA_ARGS__)
+
+struct eni_vring {
+ void __iomem *notify;
+ char msix_name[ENI_MSIX_NAME_SIZE];
+ struct vdpa_callback cb;
+ int irq;
+};
+
+struct eni_vdpa {
+ struct vdpa_device vdpa;
+ struct virtio_pci_legacy_device ldev;
+ struct eni_vring *vring;
+ struct vdpa_callback config_cb;
+ char msix_name[ENI_MSIX_NAME_SIZE];
+ int config_irq;
+ int queues;
+ int vectors;
+};
+
+static struct eni_vdpa *vdpa_to_eni(struct vdpa_device *vdpa)
+{
+ return container_of(vdpa, struct eni_vdpa, vdpa);
+}
+
+static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+ return &eni_vdpa->ldev;
+}
+
+static u64 eni_vdpa_get_features(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+ u64 features = vp_legacy_get_features(ldev);
+
+ features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
+ features |= BIT_ULL(VIRTIO_F_ORDER_PLATFORM);
+
+ return features;
+}
+
+static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ if (!(features & BIT_ULL(VIRTIO_NET_F_MRG_RXBUF)) && features) {
+ ENI_ERR(ldev->pci_dev,
+ "VIRTIO_NET_F_MRG_RXBUF is not negotiated\n");
+ return -EINVAL;
+ }
+
+ vp_legacy_set_features(ldev, (u32)features);
+
+ return 0;
+}
+
+static u8 eni_vdpa_get_status(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return vp_legacy_get_status(ldev);
+}
+
+static int eni_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+ int irq = eni_vdpa->vring[idx].irq;
+
+ if (irq == VIRTIO_MSI_NO_VECTOR)
+ return -EINVAL;
+
+ return irq;
+}
+
+static void eni_vdpa_free_irq(struct eni_vdpa *eni_vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ struct pci_dev *pdev = ldev->pci_dev;
+ int i;
+
+ for (i = 0; i < eni_vdpa->queues; i++) {
+ if (eni_vdpa->vring[i].irq != VIRTIO_MSI_NO_VECTOR) {
+ vp_legacy_queue_vector(ldev, i, VIRTIO_MSI_NO_VECTOR);
+ devm_free_irq(&pdev->dev, eni_vdpa->vring[i].irq,
+ &eni_vdpa->vring[i]);
+ eni_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+ }
+ }
+
+ if (eni_vdpa->config_irq != VIRTIO_MSI_NO_VECTOR) {
+ vp_legacy_config_vector(ldev, VIRTIO_MSI_NO_VECTOR);
+ devm_free_irq(&pdev->dev, eni_vdpa->config_irq, eni_vdpa);
+ eni_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+ }
+
+ if (eni_vdpa->vectors) {
+ pci_free_irq_vectors(pdev);
+ eni_vdpa->vectors = 0;
+ }
+}
+
+static irqreturn_t eni_vdpa_vq_handler(int irq, void *arg)
+{
+ struct eni_vring *vring = arg;
+
+ if (vring->cb.callback)
+ return vring->cb.callback(vring->cb.private);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t eni_vdpa_config_handler(int irq, void *arg)
+{
+ struct eni_vdpa *eni_vdpa = arg;
+
+ if (eni_vdpa->config_cb.callback)
+ return eni_vdpa->config_cb.callback(eni_vdpa->config_cb.private);
+
+ return IRQ_HANDLED;
+}
+
+static int eni_vdpa_request_irq(struct eni_vdpa *eni_vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ struct pci_dev *pdev = ldev->pci_dev;
+ int i, ret, irq;
+ int queues = eni_vdpa->queues;
+ int vectors = queues + 1;
+
+ ret = pci_alloc_irq_vectors(pdev, vectors, vectors, PCI_IRQ_MSIX);
+ if (ret != vectors) {
+ ENI_ERR(pdev,
+ "failed to allocate irq vectors want %d but %d\n",
+ vectors, ret);
+ return ret;
+ }
+
+ eni_vdpa->vectors = vectors;
+
+ for (i = 0; i < queues; i++) {
+ snprintf(eni_vdpa->vring[i].msix_name, ENI_MSIX_NAME_SIZE,
+ "eni-vdpa[%s]-%d\n", pci_name(pdev), i);
+ irq = pci_irq_vector(pdev, i);
+ ret = devm_request_irq(&pdev->dev, irq,
+ eni_vdpa_vq_handler,
+ 0, eni_vdpa->vring[i].msix_name,
+ &eni_vdpa->vring[i]);
+ if (ret) {
+ ENI_ERR(pdev, "failed to request irq for vq %d\n", i);
+ goto err;
+ }
+ vp_legacy_queue_vector(ldev, i, i);
+ eni_vdpa->vring[i].irq = irq;
+ }
+
+ snprintf(eni_vdpa->msix_name, ENI_MSIX_NAME_SIZE, "eni-vdpa[%s]-config\n",
+ pci_name(pdev));
+ irq = pci_irq_vector(pdev, queues);
+ ret = devm_request_irq(&pdev->dev, irq, eni_vdpa_config_handler, 0,
+ eni_vdpa->msix_name, eni_vdpa);
+ if (ret) {
+ ENI_ERR(pdev, "failed to request irq for config vq %d\n", i);
+ goto err;
+ }
+ vp_legacy_config_vector(ldev, queues);
+ eni_vdpa->config_irq = irq;
+
+ return 0;
+err:
+ eni_vdpa_free_irq(eni_vdpa);
+ return ret;
+}
+
+static void eni_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ u8 s = eni_vdpa_get_status(vdpa);
+
+ if (status & VIRTIO_CONFIG_S_DRIVER_OK &&
+ !(s & VIRTIO_CONFIG_S_DRIVER_OK)) {
+ eni_vdpa_request_irq(eni_vdpa);
+ }
+
+ vp_legacy_set_status(ldev, status);
+
+ if (!(status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+ (s & VIRTIO_CONFIG_S_DRIVER_OK))
+ eni_vdpa_free_irq(eni_vdpa);
+}
+
+static int eni_vdpa_reset(struct vdpa_device *vdpa)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ u8 s = eni_vdpa_get_status(vdpa);
+
+ vp_legacy_set_status(ldev, 0);
+
+ if (s & VIRTIO_CONFIG_S_DRIVER_OK)
+ eni_vdpa_free_irq(eni_vdpa);
+
+ return 0;
+}
+
+static u16 eni_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return vp_legacy_get_queue_size(ldev, 0);
+}
+
+static u16 eni_vdpa_get_vq_num_min(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return vp_legacy_get_queue_size(ldev, 0);
+}
+
+static int eni_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 qid,
+ struct vdpa_vq_state *state)
+{
+ return -EOPNOTSUPP;
+}
+
+static int eni_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 qid,
+ const struct vdpa_vq_state *state)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+ const struct vdpa_vq_state_split *split = &state->split;
+
+ /* ENI is build upon virtio-pci specfication which not support
+ * to set state of virtqueue. But if the state is equal to the
+ * device initial state by chance, we can let it go.
+ */
+ if (!vp_legacy_get_queue_enable(ldev, qid)
+ && split->avail_index == 0)
+ return 0;
+
+ return -EOPNOTSUPP;
+}
+
+
+static void eni_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 qid,
+ struct vdpa_callback *cb)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+ eni_vdpa->vring[qid].cb = *cb;
+}
+
+static void eni_vdpa_set_vq_ready(struct vdpa_device *vdpa, u16 qid,
+ bool ready)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ /* ENI is a legacy virtio-pci device. This is not supported
+ * by specification. But we can disable virtqueue by setting
+ * address to 0.
+ */
+ if (!ready)
+ vp_legacy_set_queue_address(ldev, qid, 0);
+}
+
+static bool eni_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 qid)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return vp_legacy_get_queue_enable(ldev, qid);
+}
+
+static void eni_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 qid,
+ u32 num)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+ struct pci_dev *pdev = ldev->pci_dev;
+ u16 n = vp_legacy_get_queue_size(ldev, qid);
+
+ /* ENI is a legacy virtio-pci device which not allow to change
+ * virtqueue size. Just report a error if someone tries to
+ * change it.
+ */
+ if (num != n)
+ ENI_ERR(pdev,
+ "not support to set vq %u fixed num %u to %u\n",
+ qid, n, num);
+}
+
+static int eni_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 qid,
+ u64 desc_area, u64 driver_area,
+ u64 device_area)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+ u32 pfn = desc_area >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
+
+ vp_legacy_set_queue_address(ldev, qid, pfn);
+
+ return 0;
+}
+
+static void eni_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+ iowrite16(qid, eni_vdpa->vring[qid].notify);
+}
+
+static u32 eni_vdpa_get_device_id(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return ldev->id.device;
+}
+
+static u32 eni_vdpa_get_vendor_id(struct vdpa_device *vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa);
+
+ return ldev->id.vendor;
+}
+
+static u32 eni_vdpa_get_vq_align(struct vdpa_device *vdpa)
+{
+ return VIRTIO_PCI_VRING_ALIGN;
+}
+
+static size_t eni_vdpa_get_config_size(struct vdpa_device *vdpa)
+{
+ return sizeof(struct virtio_net_config);
+}
+
+
+static void eni_vdpa_get_config(struct vdpa_device *vdpa,
+ unsigned int offset,
+ void *buf, unsigned int len)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ void __iomem *ioaddr = ldev->ioaddr +
+ VIRTIO_PCI_CONFIG_OFF(eni_vdpa->vectors) +
+ offset;
+ u8 *p = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ *p++ = ioread8(ioaddr + i);
+}
+
+static void eni_vdpa_set_config(struct vdpa_device *vdpa,
+ unsigned int offset, const void *buf,
+ unsigned int len)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ void __iomem *ioaddr = ldev->ioaddr +
+ VIRTIO_PCI_CONFIG_OFF(eni_vdpa->vectors) +
+ offset;
+ const u8 *p = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ iowrite8(*p++, ioaddr + i);
+}
+
+static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa,
+ struct vdpa_callback *cb)
+{
+ struct eni_vdpa *eni_vdpa = vdpa_to_eni(vdpa);
+
+ eni_vdpa->config_cb = *cb;
+}
+
+static const struct vdpa_config_ops eni_vdpa_ops = {
+ .get_features = eni_vdpa_get_features,
+ .set_features = eni_vdpa_set_features,
+ .get_status = eni_vdpa_get_status,
+ .set_status = eni_vdpa_set_status,
+ .reset = eni_vdpa_reset,
+ .get_vq_num_max = eni_vdpa_get_vq_num_max,
+ .get_vq_num_min = eni_vdpa_get_vq_num_min,
+ .get_vq_state = eni_vdpa_get_vq_state,
+ .set_vq_state = eni_vdpa_set_vq_state,
+ .set_vq_cb = eni_vdpa_set_vq_cb,
+ .set_vq_ready = eni_vdpa_set_vq_ready,
+ .get_vq_ready = eni_vdpa_get_vq_ready,
+ .set_vq_num = eni_vdpa_set_vq_num,
+ .set_vq_address = eni_vdpa_set_vq_address,
+ .kick_vq = eni_vdpa_kick_vq,
+ .get_device_id = eni_vdpa_get_device_id,
+ .get_vendor_id = eni_vdpa_get_vendor_id,
+ .get_vq_align = eni_vdpa_get_vq_align,
+ .get_config_size = eni_vdpa_get_config_size,
+ .get_config = eni_vdpa_get_config,
+ .set_config = eni_vdpa_set_config,
+ .set_config_cb = eni_vdpa_set_config_cb,
+ .get_vq_irq = eni_vdpa_get_vq_irq,
+};
+
+
+static u16 eni_vdpa_get_num_queues(struct eni_vdpa *eni_vdpa)
+{
+ struct virtio_pci_legacy_device *ldev = &eni_vdpa->ldev;
+ u32 features = vp_legacy_get_features(ldev);
+ u16 num = 2;
+
+ if (features & BIT_ULL(VIRTIO_NET_F_MQ)) {
+ __virtio16 max_virtqueue_pairs;
+
+ eni_vdpa_get_config(&eni_vdpa->vdpa,
+ offsetof(struct virtio_net_config, max_virtqueue_pairs),
+ &max_virtqueue_pairs,
+ sizeof(max_virtqueue_pairs));
+ num = 2 * __virtio16_to_cpu(virtio_legacy_is_little_endian(),
+ max_virtqueue_pairs);
+ }
+
+ if (features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))
+ num += 1;
+
+ return num;
+}
+
+static void eni_vdpa_free_irq_vectors(void *data)
+{
+ pci_free_irq_vectors(data);
+}
+
+static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct device *dev = &pdev->dev;
+ struct eni_vdpa *eni_vdpa;
+ struct virtio_pci_legacy_device *ldev;
+ int ret, i;
+
+ ret = pcim_enable_device(pdev);
+ if (ret)
+ return ret;
+
+ eni_vdpa = vdpa_alloc_device(struct eni_vdpa, vdpa,
+ dev, &eni_vdpa_ops, NULL, false);
+ if (IS_ERR(eni_vdpa)) {
+ ENI_ERR(pdev, "failed to allocate vDPA structure\n");
+ return PTR_ERR(eni_vdpa);
+ }
+
+ ldev = &eni_vdpa->ldev;
+ ldev->pci_dev = pdev;
+
+ ret = vp_legacy_probe(ldev);
+ if (ret) {
+ ENI_ERR(pdev, "failed to probe legacy PCI device\n");
+ goto err;
+ }
+
+ pci_set_master(pdev);
+ pci_set_drvdata(pdev, eni_vdpa);
+
+ eni_vdpa->vdpa.dma_dev = &pdev->dev;
+ eni_vdpa->queues = eni_vdpa_get_num_queues(eni_vdpa);
+
+ ret = devm_add_action_or_reset(dev, eni_vdpa_free_irq_vectors, pdev);
+ if (ret) {
+ ENI_ERR(pdev,
+ "failed for adding devres for freeing irq vectors\n");
+ goto err;
+ }
+
+ eni_vdpa->vring = devm_kcalloc(&pdev->dev, eni_vdpa->queues,
+ sizeof(*eni_vdpa->vring),
+ GFP_KERNEL);
+ if (!eni_vdpa->vring) {
+ ret = -ENOMEM;
+ ENI_ERR(pdev, "failed to allocate virtqueues\n");
+ goto err;
+ }
+
+ for (i = 0; i < eni_vdpa->queues; i++) {
+ eni_vdpa->vring[i].irq = VIRTIO_MSI_NO_VECTOR;
+ eni_vdpa->vring[i].notify = ldev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+ }
+ eni_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR;
+
+ ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues);
+ if (ret) {
+ ENI_ERR(pdev, "failed to register to vdpa bus\n");
+ goto err;
+ }
+
+ return 0;
+
+err:
+ put_device(&eni_vdpa->vdpa.dev);
+ return ret;
+}
+
+static void eni_vdpa_remove(struct pci_dev *pdev)
+{
+ struct eni_vdpa *eni_vdpa = pci_get_drvdata(pdev);
+
+ vdpa_unregister_device(&eni_vdpa->vdpa);
+ vp_legacy_remove(&eni_vdpa->ldev);
+}
+
+static struct pci_device_id eni_pci_ids[] = {
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
+ VIRTIO_TRANS_ID_NET,
+ PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
+ VIRTIO_ID_NET) },
+ { 0 },
+};
+
+static struct pci_driver eni_vdpa_driver = {
+ .name = "alibaba-eni-vdpa",
+ .id_table = eni_pci_ids,
+ .probe = eni_vdpa_probe,
+ .remove = eni_vdpa_remove,
+};
+
+module_pci_driver(eni_vdpa_driver);
+
+MODULE_AUTHOR("Wu Zongyong <wuzongyong@linux.alibaba.com>");
+MODULE_DESCRIPTION("Alibaba ENI vDPA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index dcd648e1f7e7..6dc75ca70b37 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -499,7 +499,8 @@ static u32 get_dev_type(struct pci_dev *pdev)
return dev_type;
}
-static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+ const struct vdpa_dev_set_config *config)
{
struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
struct ifcvf_adapter *adapter;
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 3163b313a470..daaf7b503677 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -63,7 +63,7 @@ struct mlx5_control_vq {
unsigned short head;
};
-struct mlx5_ctrl_wq_ent {
+struct mlx5_vdpa_wq_ent {
struct work_struct work;
struct mlx5_vdpa_dev *mvdev;
};
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 5c7d2a953dbd..63813fbb5f62 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -6,6 +6,7 @@
#include <linux/vringh.h>
#include <uapi/linux/virtio_net.h>
#include <uapi/linux/virtio_ids.h>
+#include <uapi/linux/vdpa.h>
#include <linux/virtio_config.h>
#include <linux/auxiliary_bus.h>
#include <linux/mlx5/cq.h>
@@ -157,10 +158,12 @@ struct mlx5_vdpa_net {
struct mutex reslock;
struct mlx5_flow_table *rxft;
struct mlx5_fc *rx_counter;
- struct mlx5_flow_handle *rx_rule;
+ struct mlx5_flow_handle *rx_rule_ucast;
+ struct mlx5_flow_handle *rx_rule_mcast;
bool setup;
- u16 mtu;
u32 cur_num_vqs;
+ struct notifier_block nb;
+ struct vdpa_callback config_cb;
};
static void free_resources(struct mlx5_vdpa_net *ndev);
@@ -1381,21 +1384,33 @@ static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev)
struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_flow_act flow_act = {};
struct mlx5_flow_namespace *ns;
+ struct mlx5_flow_spec *spec;
+ void *headers_c;
+ void *headers_v;
+ u8 *dmac_c;
+ u8 *dmac_v;
int err;
- /* for now, one entry, match all, forward to tir */
- ft_attr.max_fte = 1;
- ft_attr.autogroup.max_num_groups = 1;
+ spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+ if (!spec)
+ return -ENOMEM;
+
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ ft_attr.max_fte = 2;
+ ft_attr.autogroup.max_num_groups = 2;
ns = mlx5_get_flow_namespace(ndev->mvdev.mdev, MLX5_FLOW_NAMESPACE_BYPASS);
if (!ns) {
- mlx5_vdpa_warn(&ndev->mvdev, "get flow namespace\n");
- return -EOPNOTSUPP;
+ mlx5_vdpa_warn(&ndev->mvdev, "failed to get flow namespace\n");
+ err = -EOPNOTSUPP;
+ goto err_ns;
}
ndev->rxft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
- if (IS_ERR(ndev->rxft))
- return PTR_ERR(ndev->rxft);
+ if (IS_ERR(ndev->rxft)) {
+ err = PTR_ERR(ndev->rxft);
+ goto err_ns;
+ }
ndev->rx_counter = mlx5_fc_create(ndev->mvdev.mdev, false);
if (IS_ERR(ndev->rx_counter)) {
@@ -1403,37 +1418,64 @@ static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev)
goto err_fc;
}
+ headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers);
+ dmac_c = MLX5_ADDR_OF(fte_match_param, headers_c, outer_headers.dmac_47_16);
+ memset(dmac_c, 0xff, ETH_ALEN);
+ headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+ dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
+ ether_addr_copy(dmac_v, ndev->config.mac);
+
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT;
dest[0].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dest[0].tir_num = ndev->res.tirn;
dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
dest[1].counter_id = mlx5_fc_id(ndev->rx_counter);
- ndev->rx_rule = mlx5_add_flow_rules(ndev->rxft, NULL, &flow_act, dest, 2);
- if (IS_ERR(ndev->rx_rule)) {
- err = PTR_ERR(ndev->rx_rule);
- ndev->rx_rule = NULL;
- goto err_rule;
+ ndev->rx_rule_ucast = mlx5_add_flow_rules(ndev->rxft, spec, &flow_act, dest, 2);
+
+ if (IS_ERR(ndev->rx_rule_ucast)) {
+ err = PTR_ERR(ndev->rx_rule_ucast);
+ ndev->rx_rule_ucast = NULL;
+ goto err_rule_ucast;
}
+ memset(dmac_c, 0, ETH_ALEN);
+ memset(dmac_v, 0, ETH_ALEN);
+ dmac_c[0] = 1;
+ dmac_v[0] = 1;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ ndev->rx_rule_mcast = mlx5_add_flow_rules(ndev->rxft, spec, &flow_act, dest, 1);
+ if (IS_ERR(ndev->rx_rule_mcast)) {
+ err = PTR_ERR(ndev->rx_rule_mcast);
+ ndev->rx_rule_mcast = NULL;
+ goto err_rule_mcast;
+ }
+
+ kvfree(spec);
return 0;
-err_rule:
+err_rule_mcast:
+ mlx5_del_flow_rules(ndev->rx_rule_ucast);
+ ndev->rx_rule_ucast = NULL;
+err_rule_ucast:
mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
err_fc:
mlx5_destroy_flow_table(ndev->rxft);
+err_ns:
+ kvfree(spec);
return err;
}
static void remove_fwd_to_tir(struct mlx5_vdpa_net *ndev)
{
- if (!ndev->rx_rule)
+ if (!ndev->rx_rule_ucast)
return;
- mlx5_del_flow_rules(ndev->rx_rule);
+ mlx5_del_flow_rules(ndev->rx_rule_mcast);
+ ndev->rx_rule_mcast = NULL;
+ mlx5_del_flow_rules(ndev->rx_rule_ucast);
+ ndev->rx_rule_ucast = NULL;
mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
mlx5_destroy_flow_table(ndev->rxft);
-
- ndev->rx_rule = NULL;
}
static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd)
@@ -1557,14 +1599,14 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
{
virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
struct virtio_net_ctrl_hdr ctrl;
- struct mlx5_ctrl_wq_ent *wqent;
+ struct mlx5_vdpa_wq_ent *wqent;
struct mlx5_vdpa_dev *mvdev;
struct mlx5_control_vq *cvq;
struct mlx5_vdpa_net *ndev;
size_t read, write;
int err;
- wqent = container_of(work, struct mlx5_ctrl_wq_ent, work);
+ wqent = container_of(work, struct mlx5_vdpa_wq_ent, work);
mvdev = wqent->mvdev;
ndev = to_mlx5_vdpa_ndev(mvdev);
cvq = &mvdev->cvq;
@@ -1616,7 +1658,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
struct mlx5_vdpa_virtqueue *mvq;
- struct mlx5_ctrl_wq_ent *wqent;
+ struct mlx5_vdpa_wq_ent *wqent;
if (!is_index_valid(mvdev, idx))
return;
@@ -1852,6 +1894,7 @@ static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ);
ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR);
ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MQ);
+ ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_STATUS);
print_features(mvdev, ndev->mvdev.mlx_features, false);
return ndev->mvdev.mlx_features;
@@ -1942,16 +1985,16 @@ static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
return err;
ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features;
- ndev->config.mtu = cpu_to_mlx5vdpa16(mvdev, ndev->mtu);
- ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
update_cvq_info(mvdev);
return err;
}
static void mlx5_vdpa_set_config_cb(struct vdpa_device *vdev, struct vdpa_callback *cb)
{
- /* not implemented */
- mlx5_vdpa_warn(to_mvdev(vdev), "set config callback not supported\n");
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+
+ ndev->config_cb = *cb;
}
#define MLX5_VDPA_MAX_VQ_ENTRIES 256
@@ -2192,7 +2235,6 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
clear_vqs_ready(ndev);
mlx5_vdpa_destroy_mr(&ndev->mvdev);
ndev->mvdev.status = 0;
- ndev->mvdev.mlx_features = 0;
memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs));
ndev->mvdev.actual_features = 0;
++mvdev->generation;
@@ -2404,7 +2446,84 @@ struct mlx5_vdpa_mgmtdev {
struct mlx5_vdpa_net *ndev;
};
-static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
+static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
+{
+ u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {};
+ int err;
+
+ MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE);
+ MLX5_SET(query_vport_state_in, in, op_mod, opmod);
+ MLX5_SET(query_vport_state_in, in, vport_number, vport);
+ if (vport)
+ MLX5_SET(query_vport_state_in, in, other_vport, 1);
+
+ err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out);
+ if (err)
+ return 0;
+
+ return MLX5_GET(query_vport_state_out, out, state);
+}
+
+static bool get_link_state(struct mlx5_vdpa_dev *mvdev)
+{
+ if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) ==
+ VPORT_STATE_UP)
+ return true;
+
+ return false;
+}
+
+static void update_carrier(struct work_struct *work)
+{
+ struct mlx5_vdpa_wq_ent *wqent;
+ struct mlx5_vdpa_dev *mvdev;
+ struct mlx5_vdpa_net *ndev;
+
+ wqent = container_of(work, struct mlx5_vdpa_wq_ent, work);
+ mvdev = wqent->mvdev;
+ ndev = to_mlx5_vdpa_ndev(mvdev);
+ if (get_link_state(mvdev))
+ ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
+ else
+ ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
+
+ if (ndev->config_cb.callback)
+ ndev->config_cb.callback(ndev->config_cb.private);
+
+ kfree(wqent);
+}
+
+static int event_handler(struct notifier_block *nb, unsigned long event, void *param)
+{
+ struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb);
+ struct mlx5_eqe *eqe = param;
+ int ret = NOTIFY_DONE;
+ struct mlx5_vdpa_wq_ent *wqent;
+
+ if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
+ switch (eqe->sub_type) {
+ case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+ case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+ wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
+ if (!wqent)
+ return NOTIFY_DONE;
+
+ wqent->mvdev = &ndev->mvdev;
+ INIT_WORK(&wqent->work, update_carrier);
+ queue_work(ndev->mvdev.wq, &wqent->work);
+ ret = NOTIFY_OK;
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+ return ret;
+ }
+ return ret;
+}
+
+static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
+ const struct vdpa_dev_set_config *add_config)
{
struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
struct virtio_net_config *config;
@@ -2413,6 +2532,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
struct mlx5_vdpa_net *ndev;
struct mlx5_core_dev *mdev;
u32 max_vqs;
+ u16 mtu;
int err;
if (mgtdev->ndev)
@@ -2440,13 +2560,24 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
init_mvqs(ndev);
mutex_init(&ndev->reslock);
config = &ndev->config;
- err = query_mtu(mdev, &ndev->mtu);
+ err = query_mtu(mdev, &mtu);
if (err)
goto err_mtu;
- err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac);
- if (err)
- goto err_mtu;
+ ndev->config.mtu = cpu_to_mlx5vdpa16(mvdev, mtu);
+
+ if (get_link_state(mvdev))
+ ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
+ else
+ ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
+
+ if (add_config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR)) {
+ memcpy(ndev->config.mac, add_config->net.mac, ETH_ALEN);
+ } else {
+ err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac);
+ if (err)
+ goto err_mtu;
+ }
if (!is_zero_ether_addr(config->mac)) {
pfmdev = pci_get_drvdata(pci_physfn(mdev->pdev));
@@ -2473,12 +2604,14 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
if (err)
goto err_mr;
- mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_ctrl_wq");
+ mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq");
if (!mvdev->wq) {
err = -ENOMEM;
goto err_res2;
}
+ ndev->nb.notifier_call = event_handler;
+ mlx5_notifier_register(mdev, &ndev->nb);
ndev->cur_num_vqs = 2 * mlx5_vdpa_max_qps(max_vqs);
mvdev->vdev.mdev = &mgtdev->mgtdev;
err = _vdpa_register_device(&mvdev->vdev, ndev->cur_num_vqs + 1);
@@ -2509,7 +2642,9 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
{
struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
struct mlx5_vdpa_dev *mvdev = to_mvdev(dev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
destroy_workqueue(mvdev->wq);
_vdpa_unregister_device(dev);
mgtdev->ndev = NULL;
@@ -2541,6 +2676,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
mgtdev->mgtdev.ops = &mdev_ops;
mgtdev->mgtdev.device = mdev->device;
mgtdev->mgtdev.id_table = id_table;
+ mgtdev->mgtdev.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
mgtdev->madev = madev;
err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 1dc121a07a93..7332a74a4b00 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -14,6 +14,7 @@
#include <uapi/linux/vdpa.h>
#include <net/genetlink.h>
#include <linux/mod_devicetable.h>
+#include <linux/virtio_ids.h>
static LIST_HEAD(mdev_head);
/* A global mutex that protects vdpa management device and device level operations. */
@@ -26,8 +27,16 @@ static int vdpa_dev_probe(struct device *d)
{
struct vdpa_device *vdev = dev_to_vdpa(d);
struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver);
+ const struct vdpa_config_ops *ops = vdev->config;
+ u32 max_num, min_num = 1;
int ret = 0;
+ max_num = ops->get_vq_num_max(vdev);
+ if (ops->get_vq_num_min)
+ min_num = ops->get_vq_num_min(vdev);
+ if (max_num < min_num)
+ return -EINVAL;
+
if (drv && drv->probe)
ret = drv->probe(vdev);
@@ -58,6 +67,7 @@ static void vdpa_release_dev(struct device *d)
ops->free(vdev);
ida_simple_remove(&vdpa_index_ida, vdev->index);
+ mutex_destroy(&vdev->cf_mutex);
kfree(vdev);
}
@@ -119,6 +129,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
if (err)
goto err_name;
+ mutex_init(&vdev->cf_mutex);
device_initialize(&vdev->dev);
return vdev;
@@ -289,6 +300,46 @@ void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev)
}
EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister);
+/**
+ * vdpa_get_config - Get one or more device configuration fields.
+ * @vdev: vdpa device to operate on
+ * @offset: starting byte offset of the field
+ * @buf: buffer pointer to read to
+ * @len: length of the configuration fields in bytes
+ */
+void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset,
+ void *buf, unsigned int len)
+{
+ const struct vdpa_config_ops *ops = vdev->config;
+
+ mutex_lock(&vdev->cf_mutex);
+ /*
+ * Config accesses aren't supposed to trigger before features are set.
+ * If it does happen we assume a legacy guest.
+ */
+ if (!vdev->features_valid)
+ vdpa_set_features(vdev, 0);
+ ops->get_config(vdev, offset, buf, len);
+ mutex_unlock(&vdev->cf_mutex);
+}
+EXPORT_SYMBOL_GPL(vdpa_get_config);
+
+/**
+ * vdpa_set_config - Set one or more device configuration fields.
+ * @vdev: vdpa device to operate on
+ * @offset: starting byte offset of the field
+ * @buf: buffer pointer to read from
+ * @length: length of the configuration fields in bytes
+ */
+void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset,
+ const void *buf, unsigned int length)
+{
+ mutex_lock(&vdev->cf_mutex);
+ vdev->config->set_config(vdev, offset, buf, length);
+ mutex_unlock(&vdev->cf_mutex);
+}
+EXPORT_SYMBOL_GPL(vdpa_set_config);
+
static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev,
const char *busname, const char *devname)
{
@@ -428,9 +479,15 @@ out:
return msg->len;
}
+#define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \
+ (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
+
static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info)
{
+ struct vdpa_dev_set_config config = {};
+ struct nlattr **nl_attrs = info->attrs;
struct vdpa_mgmt_dev *mdev;
+ const u8 *macaddr;
const char *name;
int err = 0;
@@ -439,6 +496,26 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
+ if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) {
+ macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]);
+ memcpy(config.net.mac, macaddr, sizeof(config.net.mac));
+ config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR);
+ }
+ if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) {
+ config.net.mtu =
+ nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]);
+ config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU);
+ }
+
+ /* Skip checking capability if user didn't prefer to configure any
+ * device networking attributes. It is likely that user might have used
+ * a device specific method to configure such attributes or using device
+ * default attributes.
+ */
+ if ((config.mask & VDPA_DEV_NET_ATTRS_MASK) &&
+ !netlink_capable(skb, CAP_NET_ADMIN))
+ return -EPERM;
+
mutex_lock(&vdpa_dev_mutex);
mdev = vdpa_mgmtdev_get_from_attr(info->attrs);
if (IS_ERR(mdev)) {
@@ -446,8 +523,14 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
err = PTR_ERR(mdev);
goto err;
}
+ if ((config.mask & mdev->config_attr_mask) != config.mask) {
+ NL_SET_ERR_MSG_MOD(info->extack,
+ "All provided attributes are not supported");
+ err = -EOPNOTSUPP;
+ goto err;
+ }
- err = mdev->ops->dev_add(mdev, name);
+ err = mdev->ops->dev_add(mdev, name, &config);
err:
mutex_unlock(&vdpa_dev_mutex);
return err;
@@ -492,6 +575,7 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq
int flags, struct netlink_ext_ack *extack)
{
u16 max_vq_size;
+ u16 min_vq_size = 1;
u32 device_id;
u32 vendor_id;
void *hdr;
@@ -508,6 +592,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq
device_id = vdev->config->get_device_id(vdev);
vendor_id = vdev->config->get_vendor_id(vdev);
max_vq_size = vdev->config->get_vq_num_max(vdev);
+ if (vdev->config->get_vq_num_min)
+ min_vq_size = vdev->config->get_vq_num_min(vdev);
err = -EMSGSIZE;
if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev)))
@@ -520,6 +606,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq
goto msg_err;
if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size))
goto msg_err;
+ if (nla_put_u16(msg, VDPA_ATTR_DEV_MIN_VQ_SIZE, min_vq_size))
+ goto msg_err;
genlmsg_end(msg, hdr);
return 0;
@@ -612,10 +700,175 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba
return msg->len;
}
+static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
+ struct sk_buff *msg, u64 features,
+ const struct virtio_net_config *config)
+{
+ u16 val_u16;
+
+ if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0)
+ return 0;
+
+ val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
+ return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16);
+}
+
+static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg)
+{
+ struct virtio_net_config config = {};
+ u64 features;
+ u16 val_u16;
+
+ vdpa_get_config(vdev, 0, &config, sizeof(config));
+
+ if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
+ config.mac))
+ return -EMSGSIZE;
+
+ val_u16 = le16_to_cpu(config.status);
+ if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16))
+ return -EMSGSIZE;
+
+ val_u16 = le16_to_cpu(config.mtu);
+ if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
+ return -EMSGSIZE;
+
+ features = vdev->config->get_features(vdev);
+
+ return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
+}
+
+static int
+vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq,
+ int flags, struct netlink_ext_ack *extack)
+{
+ u32 device_id;
+ void *hdr;
+ int err;
+
+ hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags,
+ VDPA_CMD_DEV_CONFIG_GET);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) {
+ err = -EMSGSIZE;
+ goto msg_err;
+ }
+
+ device_id = vdev->config->get_device_id(vdev);
+ if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) {
+ err = -EMSGSIZE;
+ goto msg_err;
+ }
+
+ switch (device_id) {
+ case VIRTIO_ID_NET:
+ err = vdpa_dev_net_config_fill(vdev, msg);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+ if (err)
+ goto msg_err;
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+msg_err:
+ genlmsg_cancel(msg, hdr);
+ return err;
+}
+
+static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct vdpa_device *vdev;
+ struct sk_buff *msg;
+ const char *devname;
+ struct device *dev;
+ int err;
+
+ if (!info->attrs[VDPA_ATTR_DEV_NAME])
+ return -EINVAL;
+ devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]);
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ mutex_lock(&vdpa_dev_mutex);
+ dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match);
+ if (!dev) {
+ NL_SET_ERR_MSG_MOD(info->extack, "device not found");
+ err = -ENODEV;
+ goto dev_err;
+ }
+ vdev = container_of(dev, struct vdpa_device, dev);
+ if (!vdev->mdev) {
+ NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device");
+ err = -EINVAL;
+ goto mdev_err;
+ }
+ err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq,
+ 0, info->extack);
+ if (!err)
+ err = genlmsg_reply(msg, info);
+
+mdev_err:
+ put_device(dev);
+dev_err:
+ mutex_unlock(&vdpa_dev_mutex);
+ if (err)
+ nlmsg_free(msg);
+ return err;
+}
+
+static int vdpa_dev_config_dump(struct device *dev, void *data)
+{
+ struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev);
+ struct vdpa_dev_dump_info *info = data;
+ int err;
+
+ if (!vdev->mdev)
+ return 0;
+ if (info->idx < info->start_idx) {
+ info->idx++;
+ return 0;
+ }
+ err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid,
+ info->cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ info->cb->extack);
+ if (err)
+ return err;
+
+ info->idx++;
+ return 0;
+}
+
+static int
+vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb)
+{
+ struct vdpa_dev_dump_info info;
+
+ info.msg = msg;
+ info.cb = cb;
+ info.start_idx = cb->args[0];
+ info.idx = 0;
+
+ mutex_lock(&vdpa_dev_mutex);
+ bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump);
+ mutex_unlock(&vdpa_dev_mutex);
+ cb->args[0] = info.idx;
+ return msg->len;
+}
+
static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = {
[VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING },
[VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING },
[VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING },
+ [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR,
+ /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */
+ [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68),
};
static const struct genl_ops vdpa_nl_ops[] = {
@@ -643,6 +896,12 @@ static const struct genl_ops vdpa_nl_ops[] = {
.doit = vdpa_nl_cmd_dev_get_doit,
.dumpit = vdpa_nl_cmd_dev_get_dumpit,
},
+ {
+ .cmd = VDPA_CMD_DEV_CONFIG_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .doit = vdpa_nl_cmd_dev_config_get_doit,
+ .dumpit = vdpa_nl_cmd_dev_config_get_dumpit,
+ },
};
static struct genl_family vdpa_nl_family __ro_after_init = {
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index a790903f243e..42d401d43911 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -248,7 +248,8 @@ static struct device vdpasim_blk_mgmtdev = {
.release = vdpasim_blk_mgmtdev_release,
};
-static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+ const struct vdpa_dev_set_config *config)
{
struct vdpasim_dev_attr dev_attr = {};
struct vdpasim *simdev;
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index a1ab6163f7d1..76dd24abc791 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -16,6 +16,7 @@
#include <linux/vringh.h>
#include <linux/vdpa.h>
#include <uapi/linux/virtio_net.h>
+#include <uapi/linux/vdpa.h>
#include "vdpa_sim.h"
@@ -29,12 +30,6 @@
#define VDPASIM_NET_VQ_NUM 2
-static char *macaddr;
-module_param(macaddr, charp, 0);
-MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
-
-static u8 macaddr_buf[ETH_ALEN];
-
static void vdpasim_net_work(struct work_struct *work)
{
struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
@@ -112,9 +107,21 @@ static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
{
struct virtio_net_config *net_config = config;
- net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
- memcpy(net_config->mac, macaddr_buf, ETH_ALEN);
+}
+
+static void vdpasim_net_setup_config(struct vdpasim *vdpasim,
+ const struct vdpa_dev_set_config *config)
+{
+ struct virtio_net_config *vio_config = vdpasim->config;
+
+ if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR))
+ memcpy(vio_config->mac, config->net.mac, ETH_ALEN);
+ if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
+ vio_config->mtu = cpu_to_vdpasim16(vdpasim, config->net.mtu);
+ else
+ /* Setup default MTU to be 1500 */
+ vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
}
static void vdpasim_net_mgmtdev_release(struct device *dev)
@@ -126,7 +133,8 @@ static struct device vdpasim_net_mgmtdev = {
.release = vdpasim_net_mgmtdev_release,
};
-static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+ const struct vdpa_dev_set_config *config)
{
struct vdpasim_dev_attr dev_attr = {};
struct vdpasim *simdev;
@@ -146,6 +154,8 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
if (IS_ERR(simdev))
return PTR_ERR(simdev);
+ vdpasim_net_setup_config(simdev, config);
+
ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM);
if (ret)
goto reg_err;
@@ -179,20 +189,14 @@ static struct vdpa_mgmt_dev mgmt_dev = {
.device = &vdpasim_net_mgmtdev,
.id_table = id_table,
.ops = &vdpasim_net_mgmtdev_ops,
+ .config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
+ 1 << VDPA_ATTR_DEV_NET_CFG_MTU),
};
static int __init vdpasim_net_init(void)
{
int ret;
- if (macaddr) {
- mac_pton(macaddr, macaddr_buf);
- if (!is_valid_ether_addr(macaddr_buf))
- return -EADDRNOTAVAIL;
- } else {
- eth_random_addr(macaddr_buf);
- }
-
ret = device_register(&vdpasim_net_mgmtdev);
if (ret)
return ret;
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 841667a896dd..c9204c62f339 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1503,7 +1503,8 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
return 0;
}
-static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
+ const struct vdpa_dev_set_config *config)
{
struct vduse_dev *dev;
int ret;
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index 5bcd00246d2e..e3ff7875e123 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -76,6 +76,17 @@ static u8 vp_vdpa_get_status(struct vdpa_device *vdpa)
return vp_modern_get_status(mdev);
}
+static int vp_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx)
+{
+ struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+ int irq = vp_vdpa->vring[idx].irq;
+
+ if (irq == VIRTIO_MSI_NO_VECTOR)
+ return -EINVAL;
+
+ return irq;
+}
+
static void vp_vdpa_free_irq(struct vp_vdpa *vp_vdpa)
{
struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
@@ -427,6 +438,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = {
.get_config = vp_vdpa_get_config,
.set_config = vp_vdpa_set_config,
.set_config_cb = vp_vdpa_set_config_cb,
+ .get_vq_irq = vp_vdpa_get_vq_irq,
};
static void vp_vdpa_free_irq_vectors(void *data)