summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/um/drivers/virtio_uml.c2
-rw-r--r--arch/x86/kvm/x86.c12
-rw-r--r--drivers/crypto/virtio/virtio_crypto_core.c46
-rw-r--r--drivers/gpu/drm/virtio/virtgpu_kms.c16
-rw-r--r--drivers/gpu/drm/virtio/virtgpu_object.c2
-rw-r--r--drivers/gpu/drm/virtio/virtgpu_vq.c4
-rw-r--r--drivers/iommu/virtio-iommu.c34
-rw-r--r--drivers/net/virtio_net.c9
-rw-r--r--drivers/nvdimm/virtio_pmem.c4
-rw-r--r--drivers/platform/mellanox/mlxbf-tmfifo.c13
-rw-r--r--drivers/scsi/virtio_scsi.c4
-rw-r--r--drivers/vdpa/Kconfig19
-rw-r--r--drivers/vdpa/Makefile1
-rw-r--r--drivers/vdpa/ifcvf/ifcvf_base.c4
-rw-r--r--drivers/vdpa/ifcvf/ifcvf_base.h6
-rw-r--r--drivers/vdpa/ifcvf/ifcvf_main.c31
-rw-r--r--drivers/vdpa/mlx5/Makefile4
-rw-r--r--drivers/vdpa/mlx5/core/mlx5_vdpa.h91
-rw-r--r--drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h168
-rw-r--r--drivers/vdpa/mlx5/core/mr.c486
-rw-r--r--drivers/vdpa/mlx5/core/resources.c284
-rw-r--r--drivers/vdpa/mlx5/net/main.c76
-rw-r--r--drivers/vdpa/mlx5/net/mlx5_vnet.c1974
-rw-r--r--drivers/vdpa/mlx5/net/mlx5_vnet.h24
-rw-r--r--drivers/vdpa/vdpa.c4
-rw-r--r--drivers/vdpa/vdpa_sim/vdpa_sim.c124
-rw-r--r--drivers/vhost/Kconfig1
-rw-r--r--drivers/vhost/net.c22
-rw-r--r--drivers/vhost/vdpa.c183
-rw-r--r--drivers/vhost/vhost.c39
-rw-r--r--drivers/vhost/vhost.h11
-rw-r--r--drivers/virtio/virtio_balloon.c30
-rw-r--r--drivers/virtio/virtio_input.c32
-rw-r--r--drivers/virtio/virtio_mem.c30
-rw-r--r--drivers/virtio/virtio_pci_modern.c1
-rw-r--r--drivers/virtio/virtio_ring.c7
-rw-r--r--drivers/virtio/virtio_vdpa.c9
-rw-r--r--fs/fuse/virtio_fs.c4
-rw-r--r--include/linux/vdpa.h66
-rw-r--r--include/linux/virtio_caif.h6
-rw-r--r--include/linux/virtio_config.h187
-rw-r--r--include/linux/virtio_ring.h19
-rw-r--r--include/uapi/linux/vhost.h2
-rw-r--r--include/uapi/linux/vhost_types.h11
-rw-r--r--include/uapi/linux/virtio_9p.h4
-rw-r--r--include/uapi/linux/virtio_balloon.h10
-rw-r--r--include/uapi/linux/virtio_blk.h26
-rw-r--r--include/uapi/linux/virtio_config.h10
-rw-r--r--include/uapi/linux/virtio_console.h8
-rw-r--r--include/uapi/linux/virtio_crypto.h26
-rw-r--r--include/uapi/linux/virtio_fs.h2
-rw-r--r--include/uapi/linux/virtio_gpu.h8
-rw-r--r--include/uapi/linux/virtio_input.h18
-rw-r--r--include/uapi/linux/virtio_iommu.h12
-rw-r--r--include/uapi/linux/virtio_mem.h14
-rw-r--r--include/uapi/linux/virtio_net.h8
-rw-r--r--include/uapi/linux/virtio_pmem.h4
-rw-r--r--include/uapi/linux/virtio_scsi.h20
-rw-r--r--tools/virtio/linux/virtio_config.h6
-rw-r--r--virt/lib/irqbypass.c16
60 files changed, 3886 insertions, 408 deletions
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 351aee52aca6..a6c4bb6c2c01 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data)
}
break;
case VHOST_USER_SLAVE_IOTLB_MSG:
- /* not supported - VIRTIO_F_IOMMU_PLATFORM */
+ /* not supported - VIRTIO_F_ACCESS_PLATFORM */
case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
/* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */
default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 12ea77f99ff3..232dd2f9a081 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10667,11 +10667,17 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ int ret;
irqfd->producer = prod;
+ kvm_arch_start_assignment(irqfd->kvm);
+ ret = kvm_x86_ops.update_pi_irte(irqfd->kvm,
+ prod->irq, irqfd->gsi, 1);
+
+ if (ret)
+ kvm_arch_end_assignment(irqfd->kvm);
- return kvm_x86_ops.update_pi_irte(irqfd->kvm,
- prod->irq, irqfd->gsi, 1);
+ return ret;
}
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
@@ -10694,6 +10700,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+
+ kvm_arch_end_assignment(irqfd->kvm);
}
int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 0c66d6193ca2..080955a1dd9c 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -204,8 +204,8 @@ static int virtcrypto_update_status(struct virtio_crypto *vcrypto)
u32 status;
int err;
- virtio_cread(vcrypto->vdev,
- struct virtio_crypto_config, status, &status);
+ virtio_cread_le(vcrypto->vdev,
+ struct virtio_crypto_config, status, &status);
/*
* Unknown status bits would be a host error and the driver
@@ -323,31 +323,31 @@ static int virtcrypto_probe(struct virtio_device *vdev)
if (!vcrypto)
return -ENOMEM;
- virtio_cread(vdev, struct virtio_crypto_config,
+ virtio_cread_le(vdev, struct virtio_crypto_config,
max_dataqueues, &max_data_queues);
if (max_data_queues < 1)
max_data_queues = 1;
- virtio_cread(vdev, struct virtio_crypto_config,
- max_cipher_key_len, &max_cipher_key_len);
- virtio_cread(vdev, struct virtio_crypto_config,
- max_auth_key_len, &max_auth_key_len);
- virtio_cread(vdev, struct virtio_crypto_config,
- max_size, &max_size);
- virtio_cread(vdev, struct virtio_crypto_config,
- crypto_services, &crypto_services);
- virtio_cread(vdev, struct virtio_crypto_config,
- cipher_algo_l, &cipher_algo_l);
- virtio_cread(vdev, struct virtio_crypto_config,
- cipher_algo_h, &cipher_algo_h);
- virtio_cread(vdev, struct virtio_crypto_config,
- hash_algo, &hash_algo);
- virtio_cread(vdev, struct virtio_crypto_config,
- mac_algo_l, &mac_algo_l);
- virtio_cread(vdev, struct virtio_crypto_config,
- mac_algo_h, &mac_algo_h);
- virtio_cread(vdev, struct virtio_crypto_config,
- aead_algo, &aead_algo);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ max_cipher_key_len, &max_cipher_key_len);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ max_auth_key_len, &max_auth_key_len);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ max_size, &max_size);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ crypto_services, &crypto_services);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ cipher_algo_l, &cipher_algo_l);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ cipher_algo_h, &cipher_algo_h);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ hash_algo, &hash_algo);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ mac_algo_l, &mac_algo_l);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ mac_algo_h, &mac_algo_h);
+ virtio_cread_le(vdev, struct virtio_crypto_config,
+ aead_algo, &aead_algo);
/* Add virtio crypto device to global table */
err = virtcrypto_devmgr_add_dev(vcrypto);
diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c
index 0a5c8cf409fb..4d944a0dff3e 100644
--- a/drivers/gpu/drm/virtio/virtgpu_kms.c
+++ b/drivers/gpu/drm/virtio/virtgpu_kms.c
@@ -39,8 +39,8 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work)
u32 events_read, events_clear = 0;
/* read the config space */
- virtio_cread(vgdev->vdev, struct virtio_gpu_config,
- events_read, &events_read);
+ virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
+ events_read, &events_read);
if (events_read & VIRTIO_GPU_EVENT_DISPLAY) {
if (vgdev->has_edid)
virtio_gpu_cmd_get_edids(vgdev);
@@ -49,8 +49,8 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work)
drm_helper_hpd_irq_event(vgdev->ddev);
events_clear |= VIRTIO_GPU_EVENT_DISPLAY;
}
- virtio_cwrite(vgdev->vdev, struct virtio_gpu_config,
- events_clear, &events_clear);
+ virtio_cwrite_le(vgdev->vdev, struct virtio_gpu_config,
+ events_clear, &events_clear);
}
static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq,
@@ -165,8 +165,8 @@ int virtio_gpu_init(struct drm_device *dev)
}
/* get display info */
- virtio_cread(vgdev->vdev, struct virtio_gpu_config,
- num_scanouts, &num_scanouts);
+ virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
+ num_scanouts, &num_scanouts);
vgdev->num_scanouts = min_t(uint32_t, num_scanouts,
VIRTIO_GPU_MAX_SCANOUTS);
if (!vgdev->num_scanouts) {
@@ -176,8 +176,8 @@ int virtio_gpu_init(struct drm_device *dev)
}
DRM_INFO("number of scanouts: %d\n", num_scanouts);
- virtio_cread(vgdev->vdev, struct virtio_gpu_config,
- num_capsets, &num_capsets);
+ virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
+ num_capsets, &num_capsets);
DRM_INFO("number of cap sets: %d\n", num_capsets);
virtio_gpu_modeset_init(vgdev);
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 346cef5ce251..2cdd3cd9ce75 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -141,7 +141,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
struct virtio_gpu_mem_entry **ents,
unsigned int *nents)
{
- bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+ bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
struct scatterlist *sg;
int si, ret;
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 9e663a5d9952..53af60d484a4 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -599,7 +599,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
struct virtio_gpu_transfer_to_host_2d *cmd_p;
struct virtio_gpu_vbuffer *vbuf;
- bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+ bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
if (use_dma_api)
@@ -1015,7 +1015,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
struct virtio_gpu_transfer_host_3d *cmd_p;
struct virtio_gpu_vbuffer *vbuf;
- bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+ bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
if (use_dma_api)
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index f6f07489a9aa..b4da396cce60 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -1010,8 +1010,8 @@ static int viommu_probe(struct virtio_device *vdev)
if (ret)
return ret;
- virtio_cread(vdev, struct virtio_iommu_config, page_size_mask,
- &viommu->pgsize_bitmap);
+ virtio_cread_le(vdev, struct virtio_iommu_config, page_size_mask,
+ &viommu->pgsize_bitmap);
if (!viommu->pgsize_bitmap) {
ret = -EINVAL;
@@ -1022,25 +1022,25 @@ static int viommu_probe(struct virtio_device *vdev)
viommu->last_domain = ~0U;
/* Optional features */
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
- struct virtio_iommu_config, input_range.start,
- &input_start);
+ virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+ struct virtio_iommu_config, input_range.start,
+ &input_start);
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
- struct virtio_iommu_config, input_range.end,
- &input_end);
+ virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+ struct virtio_iommu_config, input_range.end,
+ &input_end);
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
- struct virtio_iommu_config, domain_range.start,
- &viommu->first_domain);
+ virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+ struct virtio_iommu_config, domain_range.start,
+ &viommu->first_domain);
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
- struct virtio_iommu_config, domain_range.end,
- &viommu->last_domain);
+ virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+ struct virtio_iommu_config, domain_range.end,
+ &viommu->last_domain);
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE,
- struct virtio_iommu_config, probe_size,
- &viommu->probe_size);
+ virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_PROBE,
+ struct virtio_iommu_config, probe_size,
+ &viommu->probe_size);
viommu->geometry = (struct iommu_domain_geometry) {
.aperture_start = input_start,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6fa8fe5ef160..0ada48edf749 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2264,12 +2264,13 @@ static void virtnet_update_settings(struct virtnet_info *vi)
if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
return;
- speed = virtio_cread32(vi->vdev, offsetof(struct virtio_net_config,
- speed));
+ virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
+
if (ethtool_validate_speed(speed))
vi->speed = speed;
- duplex = virtio_cread8(vi->vdev, offsetof(struct virtio_net_config,
- duplex));
+
+ virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
+
if (ethtool_validate_duplex(duplex))
vi->duplex = duplex;
}
diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index 5e3d07b47e0c..726c7354d465 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -58,9 +58,9 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
goto out_err;
}
- virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+ virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
start, &vpmem->start);
- virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+ virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
size, &vpmem->size);
res.start = vpmem->start;
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 5739a9669b29..bbc4e71a16ff 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -625,7 +625,10 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
vdev_id = VIRTIO_ID_NET;
hdr_len = sizeof(struct virtio_net_hdr);
config = &fifo->vdev[vdev_id]->config.net;
- if (ntohs(hdr.len) > config->mtu +
+ /* A legacy-only interface for now. */
+ if (ntohs(hdr.len) >
+ __virtio16_to_cpu(virtio_legacy_is_little_endian(),
+ config->mtu) +
MLXBF_TMFIFO_NET_L2_OVERHEAD)
return;
} else {
@@ -1231,8 +1234,12 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev)
/* Create the network vdev. */
memset(&net_config, 0, sizeof(net_config));
- net_config.mtu = ETH_DATA_LEN;
- net_config.status = VIRTIO_NET_S_LINK_UP;
+
+ /* A legacy-only interface for now. */
+ net_config.mtu = __cpu_to_virtio16(virtio_legacy_is_little_endian(),
+ ETH_DATA_LEN);
+ net_config.status = __cpu_to_virtio16(virtio_legacy_is_little_endian(),
+ VIRTIO_NET_S_LINK_UP);
mlxbf_tmfifo_get_cfg_mac(net_config.mac);
rc = mlxbf_tmfifo_create_vdev(dev, fifo, VIRTIO_ID_NET,
MLXBF_TMFIFO_NET_FEATURES, &net_config,
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 8cc003aa4d00..ca1c39b6f631 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -754,14 +754,14 @@ static struct scsi_host_template virtscsi_host_template = {
#define virtscsi_config_get(vdev, fld) \
({ \
- typeof(((struct virtio_scsi_config *)0)->fld) __val; \
+ __virtio_native_type(struct virtio_scsi_config, fld) __val; \
virtio_cread(vdev, struct virtio_scsi_config, fld, &__val); \
__val; \
})
#define virtscsi_config_set(vdev, fld, val) \
do { \
- typeof(((struct virtio_scsi_config *)0)->fld) __val = (val); \
+ __virtio_native_type(struct virtio_scsi_config, fld) __val = (val); \
virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \
} while(0)
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index d93a69b12f81..4271c408103e 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -29,4 +29,23 @@ config IFCVF
To compile this driver as a module, choose M here: the module will
be called ifcvf.
+config MLX5_VDPA
+ bool "MLX5 VDPA support library for ConnectX devices"
+ depends on MLX5_CORE
+ default n
+ help
+ Support library for Mellanox VDPA drivers. Provides code that is
+ common for all types of VDPA drivers. The following drivers are planned:
+ net, block.
+
+config MLX5_VDPA_NET
+ tristate "vDPA driver for ConnectX devices"
+ depends on MLX5_VDPA
+ default n
+ help
+ VDPA network driver for ConnectX6 and newer. Provides offloading
+ of virtio net datapath such that descriptors put on the ring will
+ be executed by the hardware. It also supports a variety of stateless
+ offloads depending on the actual device used and firmware version.
+
endif # VDPA
diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile
index 8bbb686ca7a2..d160e9b63a66 100644
--- a/drivers/vdpa/Makefile
+++ b/drivers/vdpa/Makefile
@@ -2,3 +2,4 @@
obj-$(CONFIG_VDPA) += vdpa.o
obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
obj-$(CONFIG_IFCVF) += ifcvf/
+obj-$(CONFIG_MLX5_VDPA) += mlx5/
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index 94bf0328b68d..f2a128e56de5 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -272,7 +272,7 @@ static int ifcvf_config_features(struct ifcvf_hw *hw)
return 0;
}
-u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
{
struct ifcvf_lm_cfg __iomem *ifcvf_lm;
void __iomem *avail_idx_addr;
@@ -287,7 +287,7 @@ u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
return last_avail_idx;
}
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num)
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num)
{
struct ifcvf_lm_cfg __iomem *ifcvf_lm;
void __iomem *avail_idx_addr;
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index f4554412e607..08f267a2aafe 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -29,7 +29,7 @@
(1ULL << VIRTIO_F_VERSION_1) | \
(1ULL << VIRTIO_NET_F_STATUS) | \
(1ULL << VIRTIO_F_ORDER_PLATFORM) | \
- (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM) | \
(1ULL << VIRTIO_NET_F_MRG_RXBUF))
/* Only one queue pair for now. */
@@ -116,7 +116,7 @@ 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);
-u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num);
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num);
struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
#endif /* _IFCVF_H_ */
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index f5a60c14b979..076d7ac5e723 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -50,8 +50,10 @@ static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues)
int i;
- for (i = 0; i < queues; i++)
+ for (i = 0; i < queues; i++) {
devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]);
+ vf->vring[i].irq = -EINVAL;
+ }
ifcvf_free_irq_vectors(pdev);
}
@@ -235,19 +237,21 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
return IFCVF_QUEUE_MAX;
}
-static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid)
+static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+ struct vdpa_vq_state *state)
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
- return ifcvf_get_vq_state(vf, qid);
+ state->avail_index = ifcvf_get_vq_state(vf, qid);
+ return 0;
}
static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
- u64 num)
+ const struct vdpa_vq_state *state)
{
struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
- return ifcvf_set_vq_state(vf, qid, num);
+ return ifcvf_set_vq_state(vf, qid, state->avail_index);
}
static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
@@ -352,6 +356,14 @@ static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
vf->config_cb.private = cb->private;
}
+static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev,
+ u16 qid)
+{
+ struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+ return vf->vring[qid].irq;
+}
+
/*
* IFCVF currently does't have on-chip IOMMU, so not
* implemented set_map()/dma_map()/dma_unmap()
@@ -369,6 +381,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = {
.get_vq_ready = ifcvf_vdpa_get_vq_ready,
.set_vq_num = ifcvf_vdpa_set_vq_num,
.set_vq_address = ifcvf_vdpa_set_vq_address,
+ .get_vq_irq = ifcvf_vdpa_get_vq_irq,
.kick_vq = ifcvf_vdpa_kick_vq,
.get_generation = ifcvf_vdpa_get_generation,
.get_device_id = ifcvf_vdpa_get_device_id,
@@ -384,7 +397,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
struct device *dev = &pdev->dev;
struct ifcvf_adapter *adapter;
struct ifcvf_hw *vf;
- int ret;
+ int ret, i;
ret = pcim_enable_device(pdev);
if (ret) {
@@ -420,7 +433,8 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
}
adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
- dev, &ifc_vdpa_ops);
+ dev, &ifc_vdpa_ops,
+ IFCVF_MAX_QUEUE_PAIRS * 2);
if (adapter == NULL) {
IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
return -ENOMEM;
@@ -441,6 +455,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
goto err;
}
+ for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
+ vf->vring[i].irq = -EINVAL;
+
ret = vdpa_register_device(&adapter->vdpa);
if (ret) {
IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
diff --git a/drivers/vdpa/mlx5/Makefile b/drivers/vdpa/mlx5/Makefile
new file mode 100644
index 000000000000..89a5bededc9f
--- /dev/null
+++ b/drivers/vdpa/mlx5/Makefile
@@ -0,0 +1,4 @@
+subdir-ccflags-y += -I$(srctree)/drivers/vdpa/mlx5/core
+
+obj-$(CONFIG_MLX5_VDPA_NET) += mlx5_vdpa.o
+mlx5_vdpa-$(CONFIG_MLX5_VDPA_NET) += net/main.o net/mlx5_vnet.o core/resources.o core/mr.o
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
new file mode 100644
index 000000000000..5c92a576edae
--- /dev/null
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VDPA_H__
+#define __MLX5_VDPA_H__
+
+#include <linux/vdpa.h>
+#include <linux/mlx5/driver.h>
+
+struct mlx5_vdpa_direct_mr {
+ u64 start;
+ u64 end;
+ u32 perm;
+ struct mlx5_core_mkey mr;
+ struct sg_table sg_head;
+ int log_size;
+ int nsg;
+ struct list_head list;
+ u64 offset;
+};
+
+struct mlx5_vdpa_mr {
+ struct mlx5_core_mkey mkey;
+
+ /* list of direct MRs descendants of this indirect mr */
+ struct list_head head;
+ unsigned long num_directs;
+ unsigned long num_klms;
+ bool initialized;
+
+ /* serialize mkey creation and destruction */
+ struct mutex mkey_mtx;
+};
+
+struct mlx5_vdpa_resources {
+ u32 pdn;
+ struct mlx5_uars_page *uar;
+ void __iomem *kick_addr;
+ u16 uid;
+ u32 null_mkey;
+ bool valid;
+};
+
+struct mlx5_vdpa_dev {
+ struct vdpa_device vdev;
+ struct mlx5_core_dev *mdev;
+ struct mlx5_vdpa_resources res;
+
+ u64 mlx_features;
+ u64 actual_features;
+ u8 status;
+ u32 max_vqs;
+ u32 generation;
+
+ struct mlx5_vdpa_mr mr;
+};
+
+int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid);
+int mlx5_vdpa_dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid);
+int mlx5_vdpa_get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey);
+int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn);
+void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn);
+int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn);
+void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn);
+int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn);
+void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn);
+int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn);
+void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn);
+int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev);
+void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev);
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+ int inlen);
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey);
+int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ bool *change_map);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
+
+#define mlx5_vdpa_warn(__dev, format, ...) \
+ dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \
+ current->pid, ##__VA_ARGS__)
+
+#define mlx5_vdpa_info(__dev, format, ...) \
+ dev_info((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__, \
+ current->pid, ##__VA_ARGS__)
+
+#define mlx5_vdpa_dbg(__dev, format, ...) \
+ dev_debug((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__, \
+ current->pid, ##__VA_ARGS__)
+
+#endif /* __MLX5_VDPA_H__ */
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h b/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h
new file mode 100644
index 000000000000..f6f57a29b38e
--- /dev/null
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VDPA_IFC_H_
+#define __MLX5_VDPA_IFC_H_
+
+#include <linux/mlx5/mlx5_ifc.h>
+
+enum {
+ MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE = 0x0,
+ MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE = 0x1,
+ MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE = 0x2,
+};
+
+enum {
+ MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = 0x1, // do I check this caps?
+ MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = 0x2,
+};
+
+enum {
+ MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0,
+ MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1,
+};
+
+struct mlx5_ifc_virtio_q_bits {
+ u8 virtio_q_type[0x8];
+ u8 reserved_at_8[0x5];
+ u8 event_mode[0x3];
+ u8 queue_index[0x10];
+
+ u8 full_emulation[0x1];
+ u8 virtio_version_1_0[0x1];
+ u8 reserved_at_22[0x2];
+ u8 offload_type[0x4];
+ u8 event_qpn_or_msix[0x18];
+
+ u8 doorbell_stride_index[0x10];
+ u8 queue_size[0x10];
+
+ u8 device_emulation_id[0x20];
+
+ u8 desc_addr[0x40];
+
+ u8 used_addr[0x40];
+
+ u8 available_addr[0x40];
+
+ u8 virtio_q_mkey[0x20];
+
+ u8 max_tunnel_desc[0x10];
+ u8 reserved_at_170[0x8];
+ u8 error_type[0x8];
+
+ u8 umem_1_id[0x20];
+
+ u8 umem_1_size[0x20];
+
+ u8 umem_1_offset[0x40];
+
+ u8 umem_2_id[0x20];
+
+ u8 umem_2_size[0x20];
+
+ u8 umem_2_offset[0x40];
+
+ u8 umem_3_id[0x20];
+
+ u8 umem_3_size[0x20];
+
+ u8 umem_3_offset[0x40];
+
+ u8 counter_set_id[0x20];
+
+ u8 reserved_at_320[0x8];
+ u8 pd[0x18];
+
+ u8 reserved_at_340[0xc0];
+};
+
+struct mlx5_ifc_virtio_net_q_object_bits {
+ u8 modify_field_select[0x40];
+
+ u8 reserved_at_40[0x20];
+
+ u8 vhca_id[0x10];
+ u8 reserved_at_70[0x10];
+
+ u8 queue_feature_bit_mask_12_3[0xa];
+ u8 dirty_bitmap_dump_enable[0x1];
+ u8 vhost_log_page[0x5];
+ u8 reserved_at_90[0xc];
+ u8 state[0x4];
+
+ u8 reserved_at_a0[0x5];
+ u8 queue_feature_bit_mask_2_0[0x3];
+ u8 tisn_or_qpn[0x18];
+
+ u8 dirty_bitmap_mkey[0x20];
+
+ u8 dirty_bitmap_size[0x20];
+
+ u8 dirty_bitmap_addr[0x40];
+
+ u8 hw_available_index[0x10];
+ u8 hw_used_index[0x10];
+
+ u8 reserved_at_160[0xa0];
+
+ struct mlx5_ifc_virtio_q_bits virtio_q_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+ struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_out_bits {
+ struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_out_bits {
+ struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_out_bits {
+ struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+
+ struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+enum {
+ MLX5_VIRTQ_MODIFY_MASK_STATE = (u64)1 << 0,
+ MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS = (u64)1 << 3,
+ MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+};
+
+enum {
+ MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT = 0x0,
+ MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY = 0x1,
+ MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND = 0x2,
+ MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR = 0x3,
+};
+
+enum {
+ MLX5_RQTC_LIST_Q_TYPE_RQ = 0x0,
+ MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q = 0x1,
+};
+
+struct mlx5_ifc_modify_virtio_net_q_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+ struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_modify_virtio_net_q_out_bits {
+ struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+#endif /* __MLX5_VDPA_IFC_H_ */
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
new file mode 100644
index 000000000000..ef1c550f8266
--- /dev/null
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/vdpa.h>
+#include <linux/gcd.h>
+#include <linux/string.h>
+#include <linux/mlx5/qp.h>
+#include "mlx5_vdpa.h"
+
+/* DIV_ROUND_UP where the divider is a power of 2 give by its log base 2 value */
+#define MLX5_DIV_ROUND_UP_POW2(_n, _s) \
+({ \
+ u64 __s = _s; \
+ u64 _res; \
+ _res = (((_n) + (1 << (__s)) - 1) >> (__s)); \
+ _res; \
+})
+
+static int get_octo_len(u64 len, int page_shift)
+{
+ u64 page_size = 1ULL << page_shift;
+ int npages;
+
+ npages = ALIGN(len, page_size) >> page_shift;
+ return (npages + 1) / 2;
+}
+
+static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in)
+{
+ struct scatterlist *sg;
+ __be64 *pas;
+ int i;
+
+ pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+ for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i)
+ (*pas) = cpu_to_be64(sg_dma_address(sg));
+}
+
+static void mlx5_set_access_mode(void *mkc, int mode)
+{
+ MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3);
+ MLX5_SET(mkc, mkc, access_mode_4_2, mode >> 2);
+}
+
+static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i)
+ mtt[i] = cpu_to_be64(sg_dma_address(sg));
+}
+
+static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
+{
+ int inlen;
+ void *mkc;
+ void *in;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + roundup(MLX5_ST_SZ_BYTES(mtt) * mr->nsg, 16);
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid);
+ fill_sg(mr, in);
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+ MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO));
+ MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO));
+ mlx5_set_access_mode(mkc, MLX5_MKC_ACCESS_MODE_MTT);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+ MLX5_SET(mkc, mkc, pd, mvdev->res.pdn);
+ MLX5_SET64(mkc, mkc, start_addr, mr->offset);
+ MLX5_SET64(mkc, mkc, len, mr->end - mr->start);
+ MLX5_SET(mkc, mkc, log_page_size, mr->log_size);
+ MLX5_SET(mkc, mkc, translations_octword_size,
+ get_octo_len(mr->end - mr->start, mr->log_size));
+ MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+ get_octo_len(mr->end - mr->start, mr->log_size));
+ populate_mtts(mr, MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt));
+ err = mlx5_vdpa_create_mkey(mvdev, &mr->mr, in, inlen);
+ kvfree(in);
+ if (err) {
+ mlx5_vdpa_warn(mvdev, "Failed to create direct MR\n");
+ return err;
+ }
+
+ return 0;
+}
+
+static void destroy_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
+{
+ mlx5_vdpa_destroy_mkey(mvdev, &mr->mr);
+}
+
+static u64 map_start(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr)
+{
+ return max_t(u64, map->start, mr->start);
+}
+
+static u64 map_end(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr)
+{
+ return min_t(u64, map->last + 1, mr->end);
+}
+
+static u64 maplen(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr)
+{
+ return map_end(map, mr) - map_start(map, mr);
+}
+
+#define MLX5_VDPA_INVALID_START_ADDR ((u64)-1)
+#define MLX5_VDPA_INVALID_LEN ((u64)-1)
+
+static u64 indir_start_addr(struct mlx5_vdpa_mr *mkey)
+{
+ struct mlx5_vdpa_direct_mr *s;
+
+ s = list_first_entry_or_null(&mkey->head, struct mlx5_vdpa_direct_mr, list);
+ if (!s)
+ return MLX5_VDPA_INVALID_START_ADDR;
+
+ return s->start;
+}
+
+static u64 indir_len(struct mlx5_vdpa_mr *mkey)
+{
+ struct mlx5_vdpa_direct_mr *s;
+ struct mlx5_vdpa_direct_mr *e;
+
+ s = list_first_entry_or_null(&mkey->head, struct mlx5_vdpa_direct_mr, list);
+ if (!s)
+ return MLX5_VDPA_INVALID_LEN;
+
+ e = list_last_entry(&mkey->head, struct mlx5_vdpa_direct_mr, list);
+
+ return e->end - s->start;
+}
+
+#define LOG_MAX_KLM_SIZE 30
+#define MAX_KLM_SIZE BIT(LOG_MAX_KLM_SIZE)
+
+static u32 klm_bcount(u64 size)
+{
+ return (u32)size;
+}
+
+static void fill_indir(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey, void *in)
+{
+ struct mlx5_vdpa_direct_mr *dmr;
+ struct mlx5_klm *klmarr;
+ struct mlx5_klm *klm;
+ bool first = true;
+ u64 preve;
+ int i;
+
+ klmarr = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+ i = 0;
+ list_for_each_entry(dmr, &mkey->head, list) {
+again:
+ klm = &klmarr[i++];
+ if (first) {
+ preve = dmr->start;
+ first = false;
+ }
+
+ if (preve == dmr->start) {
+ klm->key = cpu_to_be32(dmr->mr.key);
+ klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start));
+ preve = dmr->end;
+ } else {
+ klm->key = cpu_to_be32(mvdev->res.null_mkey);
+ klm->bcount = cpu_to_be32(klm_bcount(dmr->start - preve));
+ preve = dmr->start;
+ goto again;
+ }
+ }
+}
+
+static int klm_byte_size(int nklms)
+{
+ return 16 * ALIGN(nklms, 4);
+}
+
+static int create_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
+{
+ int inlen;
+ void *mkc;
+ void *in;
+ int err;
+ u64 start;
+ u64 len;
+
+ start = indir_start_addr(mr);
+ len = indir_len(mr);
+ if (start == MLX5_VDPA_INVALID_START_ADDR || len == MLX5_VDPA_INVALID_LEN)
+ return -EINVAL;
+
+ inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + klm_byte_size(mr->num_klms);
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid);
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+ MLX5_SET(mkc, mkc, lw, 1);
+ MLX5_SET(mkc, mkc, lr, 1);
+ mlx5_set_access_mode(mkc, MLX5_MKC_ACCESS_MODE_KLMS);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+ MLX5_SET(mkc, mkc, pd, mvdev->res.pdn);
+ MLX5_SET64(mkc, mkc, start_addr, start);
+ MLX5_SET64(mkc, mkc, len, len);
+ MLX5_SET(mkc, mkc, translations_octword_size, klm_byte_size(mr->num_klms) / 16);
+ MLX5_SET(create_mkey_in, in, translations_octword_actual_size, mr->num_klms);
+ fill_indir(mvdev, mr, in);
+ err = mlx5_vdpa_create_mkey(mvdev, &mr->mkey, in, inlen);
+ kfree(in);
+ return err;
+}
+
+static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey)
+{
+ mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey);
+}
+
+static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr,
+ struct vhost_iotlb *iotlb)
+{
+ struct vhost_iotlb_map *map;
+ unsigned long lgcd = 0;
+ int log_entity_size;
+ unsigned long size;
+ u64 start = 0;
+ int err;
+ struct page *pg;
+ unsigned int nsg;
+ int sglen;
+ u64 pa;
+ u64 paend;
+ struct scatterlist *sg;
+ struct device *dma = mvdev->mdev->device;
+ int ret;
+
+ for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
+ map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
+ size = maplen(map, mr);
+ lgcd = gcd(lgcd, size);
+ start += size;
+ }
+ log_entity_size = ilog2(lgcd);
+
+ sglen = 1 << log_entity_size;
+ nsg = MLX5_DIV_ROUND_UP_POW2(mr->end - mr->start, log_entity_size);
+
+ err = sg_alloc_table(&mr->sg_head, nsg, GFP_KERNEL);
+ if (err)
+ return err;
+
+ sg = mr->sg_head.sgl;
+ for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
+ map; map = vhost_iotlb_itree_next(map, mr->start, mr->end - 1)) {
+ paend = map->addr + maplen(map, mr);
+ for (pa = map->addr; pa < paend; pa += sglen) {
+ pg = pfn_to_page(__phys_to_pfn(pa));
+ if (!sg) {
+ mlx5_vdpa_warn(mvdev, "sg null. start 0x%llx, end 0x%llx\n",
+ map->start, map->last + 1);
+ err = -ENOMEM;
+ goto err_map;
+ }
+ sg_set_page(sg, pg, sglen, 0);
+ sg = sg_next(sg);
+ if (!sg)
+ goto done;
+ }
+ }
+done:
+ mr->log_size = log_entity_size;
+ mr->nsg = nsg;
+ ret = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
+ if (!ret)
+ goto err_map;
+
+ err = create_direct_mr(mvdev, mr);
+ if (err)
+ goto err_direct;
+
+ return 0;
+
+err_direct:
+ dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
+err_map:
+ sg_free_table(&mr->sg_head);
+ return err;
+}
+
+static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
+{
+ struct device *dma = mvdev->mdev->device;
+
+ destroy_direct_mr(mvdev, mr);
+ dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
+ sg_free_table(&mr->sg_head);
+}
+
+static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8 perm,
+ struct vhost_iotlb *iotlb)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+ struct mlx5_vdpa_direct_mr *dmr;
+ struct mlx5_vdpa_direct_mr *n;
+ LIST_HEAD(tmp);
+ u64 st;
+ u64 sz;
+ int err;
+ int i = 0;
+
+ st = start;
+ while (size) {
+ sz = (u32)min_t(u64, MAX_KLM_SIZE, size);
+ dmr = kzalloc(sizeof(*dmr), GFP_KERNEL);
+ if (!dmr) {
+ err = -ENOMEM;
+ goto err_alloc;
+ }
+
+ dmr->start = st;
+ dmr->end = st + sz;
+ dmr->perm = perm;
+ err = map_direct_mr(mvdev, dmr, iotlb);
+ if (err) {
+ kfree(dmr);
+ goto err_alloc;
+ }
+
+ list_add_tail(&dmr->list, &tmp);
+ size -= sz;
+ mr->num_directs++;
+ mr->num_klms++;
+ st += sz;
+ i++;
+ }
+ list_splice_tail(&tmp, &mr->head);
+ return 0;
+
+err_alloc:
+ list_for_each_entry_safe(dmr, n, &mr->head, list) {
+ list_del_init(&dmr->list);
+ unmap_direct_mr(mvdev, dmr);
+ kfree(dmr);
+ }
+ return err;
+}
+
+/* The iotlb pointer contains a list of maps. Go over the maps, possibly
+ * merging mergeable maps, and create direct memory keys that provide the
+ * device access to memory. The direct mkeys are then referred to by the
+ * indirect memory key that provides access to the enitre address space given
+ * by iotlb.
+ */
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+ struct mlx5_vdpa_direct_mr *dmr;
+ struct mlx5_vdpa_direct_mr *n;
+ struct vhost_iotlb_map *map;
+ u32 pperm = U16_MAX;
+ u64 last = U64_MAX;
+ u64 ps = U64_MAX;
+ u64 pe = U64_MAX;
+ u64 start = 0;
+ int err = 0;
+ int nnuls;
+
+ if (mr->initialized)
+ return 0;
+
+ INIT_LIST_HEAD(&mr->head);
+ for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+ map = vhost_iotlb_itree_next(map, start, last)) {
+ start = map->start;
+ if (pe == map->start && pperm == map->perm) {
+ pe = map->last + 1;
+ } else {
+ if (ps != U64_MAX) {
+ if (pe < map->start) {
+ /* We have a hole in the map. Check how
+ * many null keys are required to fill it.
+ */
+ nnuls = MLX5_DIV_ROUND_UP_POW2(map->start - pe,
+ LOG_MAX_KLM_SIZE);
+ mr->num_klms += nnuls;
+ }
+ err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb);
+ if (err)
+ goto err_chain;
+ }
+ ps = map->start;
+ pe = map->last + 1;
+ pperm = map->perm;
+ }
+ }
+ err = add_direct_chain(mvdev, ps, pe - ps, pperm, iotlb);
+ if (err)
+ goto err_chain;
+
+ /* Create the memory key that defines the guests's address space. This
+ * memory key refers to the direct keys that contain the MTT
+ * translations
+ */
+ err = create_indirect_key(mvdev, mr);
+ if (err)
+ goto err_chain;
+
+ mr->initialized = true;
+ return 0;
+
+err_chain:
+ list_for_each_entry_safe_reverse(dmr, n, &mr->head, list) {
+ list_del_init(&dmr->list);
+ unmap_direct_mr(mvdev, dmr);
+ kfree(dmr);
+ }
+ return err;
+}
+
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+ int err;
+
+ mutex_lock(&mr->mkey_mtx);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ mutex_unlock(&mr->mkey_mtx);
+ return err;
+}
+
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+ struct mlx5_vdpa_direct_mr *dmr;
+ struct mlx5_vdpa_direct_mr *n;
+
+ mutex_lock(&mr->mkey_mtx);
+ if (!mr->initialized)
+ goto out;
+
+ destroy_indirect_key(mvdev, mr);
+ list_for_each_entry_safe_reverse(dmr, n, &mr->head, list) {
+ list_del_init(&dmr->list);
+ unmap_direct_mr(mvdev, dmr);
+ kfree(dmr);
+ }
+ memset(mr, 0, sizeof(*mr));
+ mr->initialized = false;
+out:
+ mutex_unlock(&mr->mkey_mtx);
+}
+
+static bool map_empty(struct vhost_iotlb *iotlb)
+{
+ return !vhost_iotlb_itree_first(iotlb, 0, U64_MAX);
+}
+
+int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ bool *change_map)
+{
+ struct mlx5_vdpa_mr *mr = &mvdev->mr;
+ int err = 0;
+
+ *change_map = false;
+ if (map_empty(iotlb)) {
+ mlx5_vdpa_destroy_mr(mvdev);
+ return 0;
+ }
+ mutex_lock(&mr->mkey_mtx);
+ if (mr->initialized) {
+ mlx5_vdpa_info(mvdev, "memory map update\n");
+ *change_map = true;
+ }
+ if (!*change_map)
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ mutex_unlock(&mr->mkey_mtx);
+
+ return err;
+}
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
new file mode 100644
index 000000000000..96e6421c5d1c
--- /dev/null
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_vdpa.h"
+
+static int alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid)
+{
+ struct mlx5_core_dev *mdev = dev->mdev;
+
+ u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(alloc_pd_in)] = {};
+ int err;
+
+ MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD);
+ MLX5_SET(alloc_pd_in, in, uid, uid);
+
+ err = mlx5_cmd_exec_inout(mdev, alloc_pd, in, out);
+ if (!err)
+ *pdn = MLX5_GET(alloc_pd_out, out, pd);
+
+ return err;
+}
+
+static int dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid)
+{
+ u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)] = {};
+ struct mlx5_core_dev *mdev = dev->mdev;
+
+ MLX5_SET(dealloc_pd_in, in, opcode, MLX5_CMD_OP_DEALLOC_PD);
+ MLX5_SET(dealloc_pd_in, in, pd, pdn);
+ MLX5_SET(dealloc_pd_in, in, uid, uid);
+ return mlx5_cmd_exec_in(mdev, dealloc_pd, in);
+}
+
+static int get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey)
+{
+ u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
+ struct mlx5_core_dev *mdev = dev->mdev;
+ int err;
+
+ MLX5_SET(query_special_contexts_in, in, opcode, MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+ err = mlx5_cmd_exec_inout(mdev, query_special_contexts, in, out);
+ if (!err)
+ *null_mkey = MLX5_GET(query_special_contexts_out, out, null_mkey);
+ return err;
+}
+
+static int create_uctx(struct mlx5_vdpa_dev *mvdev, u16 *uid)
+{
+ u32 out[MLX5_ST_SZ_DW(create_uctx_out)] = {};
+ int inlen;
+ void *in;
+ int err;
+
+ /* 0 means not supported */
+ if (!MLX5_CAP_GEN(mvdev->mdev, log_max_uctx))
+ return -EOPNOTSUPP;
+
+ inlen = MLX5_ST_SZ_BYTES(create_uctx_in);
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_uctx_in, in, opcode, MLX5_CMD_OP_CREATE_UCTX);
+ MLX5_SET(create_uctx_in, in, uctx.cap, MLX5_UCTX_CAP_RAW_TX);
+
+ err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out));
+ kfree(in);
+ if (!err)
+ *uid = MLX5_GET(create_uctx_out, out, uid);
+
+ return err;
+}
+
+static void destroy_uctx(struct mlx5_vdpa_dev *mvdev, u32 uid)
+{
+ u32 out[MLX5_ST_SZ_DW(destroy_uctx_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(destroy_uctx_in)] = {};
+
+ MLX5_SET(destroy_uctx_in, in, opcode, MLX5_CMD_OP_DESTROY_UCTX);
+ MLX5_SET(destroy_uctx_in, in, uid, uid);
+
+ mlx5_cmd_exec(mvdev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn)
+{
+ u32 out[MLX5_ST_SZ_DW(create_tis_out)] = {};
+ int err;
+
+ MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS);
+ MLX5_SET(create_tis_in, in, uid, mvdev->res.uid);
+ err = mlx5_cmd_exec_inout(mvdev->mdev, create_tis, in, out);
+ if (!err)
+ *tisn = MLX5_GET(create_tis_out, out, tisn);
+
+ return err;
+}
+
+void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_tis_in)] = {};
+
+ MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS);
+ MLX5_SET(destroy_tis_in, in, uid, mvdev->res.uid);
+ MLX5_SET(destroy_tis_in, in, tisn, tisn);
+ mlx5_cmd_exec_in(mvdev->mdev, destroy_tis, in);
+}
+
+int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn)
+{
+ u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {};
+ int err;
+
+ MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT);
+ err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out));
+ if (!err)
+ *rqtn = MLX5_GET(create_rqt_out, out, rqtn);
+
+ return err;
+}
+
+void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {};
+
+ MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT);
+ MLX5_SET(destroy_rqt_in, in, uid, mvdev->res.uid);
+ MLX5_SET(destroy_rqt_in, in, rqtn, rqtn);
+ mlx5_cmd_exec_in(mvdev->mdev, destroy_rqt, in);
+}
+
+int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn)
+{
+ u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
+ int err;
+
+ MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+ err = mlx5_cmd_exec_inout(mvdev->mdev, create_tir, in, out);
+ if (!err)
+ *tirn = MLX5_GET(create_tir_out, out, tirn);
+
+ return err;
+}
+
+void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_tir_in)] = {};
+
+ MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR);
+ MLX5_SET(destroy_tir_in, in, uid, mvdev->res.uid);
+ MLX5_SET(destroy_tir_in, in, tirn, tirn);
+ mlx5_cmd_exec_in(mvdev->mdev, destroy_tir, in);
+}
+
+int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn)
+{
+ u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)] = {};
+ int err;
+
+ MLX5_SET(alloc_transport_domain_in, in, opcode, MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN);
+ MLX5_SET(alloc_transport_domain_in, in, uid, mvdev->res.uid);
+
+ err = mlx5_cmd_exec_inout(mvdev->mdev, alloc_transport_domain, in, out);
+ if (!err)
+ *tdn = MLX5_GET(alloc_transport_domain_out, out, transport_domain);
+
+ return err;
+}
+
+void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn)
+{
+ u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)] = {};
+
+ MLX5_SET(dealloc_transport_domain_in, in, opcode, MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN);
+ MLX5_SET(dealloc_transport_domain_in, in, uid, mvdev->res.uid);
+ MLX5_SET(dealloc_transport_domain_in, in, transport_domain, tdn);
+ mlx5_cmd_exec_in(mvdev->mdev, dealloc_transport_domain, in);
+}
+
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+ int inlen)
+{
+ u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {};
+ u32 mkey_index;
+ void *mkc;
+ int err;
+
+ MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY);
+ MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid);
+
+ err = mlx5_cmd_exec(mvdev->mdev, in, inlen, lout, sizeof(lout));
+ if (err)
+ return err;
+
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+ mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
+ mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
+ mkey->size = MLX5_GET64(mkc, mkc, len);
+ mkey->key |= mlx5_idx_to_mkey(mkey_index);
+ mkey->pd = MLX5_GET(mkc, mkc, pd);
+ return 0;
+}
+
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {};
+
+ MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid);
+ MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
+ MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
+ return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in);
+}
+
+int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev)
+{
+ u64 offset = MLX5_CAP64_DEV_VDPA_EMULATION(mvdev->mdev, doorbell_bar_offset);
+ struct mlx5_vdpa_resources *res = &mvdev->res;
+ struct mlx5_core_dev *mdev = mvdev->mdev;
+ u64 kick_addr;
+ int err;
+
+ if (res->valid) {
+ mlx5_vdpa_warn(mvdev, "resources already allocated\n");
+ return -EINVAL;
+ }
+ mutex_init(&mvdev->mr.mkey_mtx);
+ res->uar = mlx5_get_uars_page(mdev);
+ if (IS_ERR(res->uar)) {
+ err = PTR_ERR(res->uar);
+ goto err_uars;
+ }
+
+ err = create_uctx(mvdev, &res->uid);
+ if (err)
+ goto err_uctx;
+
+ err = alloc_pd(mvdev, &res->pdn, res->uid);
+ if (err)
+ goto err_pd;
+
+ err = get_null_mkey(mvdev, &res->null_mkey);
+ if (err)
+ goto err_key;
+
+ kick_addr = pci_resource_start(mdev->pdev, 0) + offset;
+ res->kick_addr = ioremap(kick_addr, PAGE_SIZE);
+ if (!res->kick_addr) {
+ err = -ENOMEM;
+ goto err_key;
+ }
+ res->valid = true;
+
+ return 0;
+
+err_key:
+ dealloc_pd(mvdev, res->pdn, res->uid);
+err_pd:
+ destroy_uctx(mvdev, res->uid);
+err_uctx:
+ mlx5_put_uars_page(mdev, res->uar);
+err_uars:
+ mutex_destroy(&mvdev->mr.mkey_mtx);
+ return err;
+}
+
+void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev)
+{
+ struct mlx5_vdpa_resources *res = &mvdev->res;
+
+ if (!res->valid)
+ return;
+
+ iounmap(res->kick_addr);
+ res->kick_addr = NULL;
+ dealloc_pd(mvdev, res->pdn, res->uid);
+ destroy_uctx(mvdev, res->uid);
+ mlx5_put_uars_page(mvdev->mdev, res->uar);
+ mutex_destroy(&mvdev->mr.mkey_mtx);
+ res->valid = false;
+}
diff --git a/drivers/vdpa/mlx5/net/main.c b/drivers/vdpa/mlx5/net/main.c
new file mode 100644
index 000000000000..838cd98386ff
--- /dev/null
+++ b/drivers/vdpa/mlx5/net/main.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_vdpa_ifc.h"
+#include "mlx5_vnet.h"
+
+MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox VDPA driver");
+MODULE_LICENSE("Dual BSD/GPL");
+
+static bool required_caps_supported(struct mlx5_core_dev *mdev)
+{
+ u8 event_mode;
+ u64 got;
+
+ got = MLX5_CAP_GEN_64(mdev, general_obj_types);
+
+ if (!(got & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q))
+ return false;
+
+ event_mode = MLX5_CAP_DEV_VDPA_EMULATION(mdev, event_mode);
+ if (!(event_mode & MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE))
+ return false;
+
+ if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, eth_frame_offload_type))
+ return false;
+
+ return true;
+}
+
+static void *mlx5_vdpa_add(struct mlx5_core_dev *mdev)
+{
+ struct mlx5_vdpa_dev *vdev;
+
+ if (mlx5_core_is_pf(mdev))
+ return NULL;
+
+ if (!required_caps_supported(mdev)) {
+ dev_info(mdev->device, "virtio net emulation not supported\n");
+ return NULL;
+ }
+ vdev = mlx5_vdpa_add_dev(mdev);
+ if (IS_ERR(vdev))
+ return NULL;
+
+ return vdev;
+}
+
+static void mlx5_vdpa_remove(struct mlx5_core_dev *mdev, void *context)
+{
+ struct mlx5_vdpa_dev *vdev = context;
+
+ mlx5_vdpa_remove_dev(vdev);
+}
+
+static struct mlx5_interface mlx5_vdpa_interface = {
+ .add = mlx5_vdpa_add,
+ .remove = mlx5_vdpa_remove,
+ .protocol = MLX5_INTERFACE_PROTOCOL_VDPA,
+};
+
+static int __init mlx5_vdpa_init(void)
+{
+ return mlx5_register_interface(&mlx5_vdpa_interface);
+}
+
+static void __exit mlx5_vdpa_exit(void)
+{
+ mlx5_unregister_interface(&mlx5_vdpa_interface);
+}
+
+module_init(mlx5_vdpa_init);
+module_exit(mlx5_vdpa_exit);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
new file mode 100644
index 000000000000..9df69d5efe8c
--- /dev/null
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -0,0 +1,1974 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/vdpa.h>
+#include <uapi/linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/mlx5/qp.h>
+#include <linux/mlx5/device.h>
+#include <linux/mlx5/vport.h>
+#include <linux/mlx5/fs.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_vnet.h"
+#include "mlx5_vdpa_ifc.h"
+#include "mlx5_vdpa.h"
+
+#define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev)
+
+#define VALID_FEATURES_MASK \
+ (BIT(VIRTIO_NET_F_CSUM) | BIT(VIRTIO_NET_F_GUEST_CSUM) | \
+ BIT(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) | BIT(VIRTIO_NET_F_MTU) | BIT(VIRTIO_NET_F_MAC) | \
+ BIT(VIRTIO_NET_F_GUEST_TSO4) | BIT(VIRTIO_NET_F_GUEST_TSO6) | \
+ BIT(VIRTIO_NET_F_GUEST_ECN) | BIT(VIRTIO_NET_F_GUEST_UFO) | BIT(VIRTIO_NET_F_HOST_TSO4) | \
+ BIT(VIRTIO_NET_F_HOST_TSO6) | BIT(VIRTIO_NET_F_HOST_ECN) | BIT(VIRTIO_NET_F_HOST_UFO) | \
+ BIT(VIRTIO_NET_F_MRG_RXBUF) | BIT(VIRTIO_NET_F_STATUS) | BIT(VIRTIO_NET_F_CTRL_VQ) | \
+ BIT(VIRTIO_NET_F_CTRL_RX) | BIT(VIRTIO_NET_F_CTRL_VLAN) | \
+ BIT(VIRTIO_NET_F_CTRL_RX_EXTRA) | BIT(VIRTIO_NET_F_GUEST_ANNOUNCE) | \
+ BIT(VIRTIO_NET_F_MQ) | BIT(VIRTIO_NET_F_CTRL_MAC_ADDR) | BIT(VIRTIO_NET_F_HASH_REPORT) | \
+ BIT(VIRTIO_NET_F_RSS) | BIT(VIRTIO_NET_F_RSC_EXT) | BIT(VIRTIO_NET_F_STANDBY) | \
+ BIT(VIRTIO_NET_F_SPEED_DUPLEX) | BIT(VIRTIO_F_NOTIFY_ON_EMPTY) | \
+ BIT(VIRTIO_F_ANY_LAYOUT) | BIT(VIRTIO_F_VERSION_1) | BIT(VIRTIO_F_ACCESS_PLATFORM) | \
+ BIT(VIRTIO_F_RING_PACKED) | BIT(VIRTIO_F_ORDER_PLATFORM) | BIT(VIRTIO_F_SR_IOV))
+
+#define VALID_STATUS_MASK \
+ (VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK | \
+ VIRTIO_CONFIG_S_FEATURES_OK | VIRTIO_CONFIG_S_NEEDS_RESET | VIRTIO_CONFIG_S_FAILED)
+
+struct mlx5_vdpa_net_resources {
+ u32 tisn;
+ u32 tdn;
+ u32 tirn;
+ u32 rqtn;
+ bool valid;
+};
+
+struct mlx5_vdpa_cq_buf {
+ struct mlx5_frag_buf_ctrl fbc;
+ struct mlx5_frag_buf frag_buf;
+ int cqe_size;
+ int nent;
+};
+
+struct mlx5_vdpa_cq {
+ struct mlx5_core_cq mcq;
+ struct mlx5_vdpa_cq_buf buf;
+ struct mlx5_db db;
+ int cqe;
+};
+
+struct mlx5_vdpa_umem {
+ struct mlx5_frag_buf_ctrl fbc;
+ struct mlx5_frag_buf frag_buf;
+ int size;
+ u32 id;
+};
+
+struct mlx5_vdpa_qp {
+ struct mlx5_core_qp mqp;
+ struct mlx5_frag_buf frag_buf;
+ struct mlx5_db db;
+ u16 head;
+ bool fw;
+};
+
+struct mlx5_vq_restore_info {
+ u32 num_ent;
+ u64 desc_addr;
+ u64 device_addr;
+ u64 driver_addr;
+ u16 avail_index;
+ bool ready;
+ struct vdpa_callback cb;
+ bool restore;
+};
+
+struct mlx5_vdpa_virtqueue {
+ bool ready;
+ u64 desc_addr;
+ u64 device_addr;
+ u64 driver_addr;
+ u32 num_ent;
+ struct vdpa_callback event_cb;
+
+ /* Resources for implementing the notification channel from the device
+ * to the driver. fwqp is the firmware end of an RC connection; the
+ * other end is vqqp used by the driver. cq is is where completions are
+ * reported.
+ */
+ struct mlx5_vdpa_cq cq;
+ struct mlx5_vdpa_qp fwqp;
+ struct mlx5_vdpa_qp vqqp;
+
+ /* umem resources are required for the virtqueue operation. They're use
+ * is internal and they must be provided by the driver.
+ */
+ struct mlx5_vdpa_umem umem1;
+ struct mlx5_vdpa_umem umem2;
+ struct mlx5_vdpa_umem umem3;
+
+ bool initialized;
+ int index;
+ u32 virtq_id;
+ struct mlx5_vdpa_net *ndev;
+ u16 avail_idx;
+ int fw_state;
+
+ /* keep last in the struct */
+ struct mlx5_vq_restore_info ri;
+};
+
+/* We will remove this limitation once mlx5_vdpa_alloc_resources()
+ * provides for driver space allocation
+ */
+#define MLX5_MAX_SUPPORTED_VQS 16
+
+struct mlx5_vdpa_net {
+ struct mlx5_vdpa_dev mvdev;
+ struct mlx5_vdpa_net_resources res;
+ struct virtio_net_config config;
+ struct mlx5_vdpa_virtqueue vqs[MLX5_MAX_SUPPORTED_VQS];
+
+ /* Serialize vq resources creation and destruction. This is required
+ * since memory map might change and we need to destroy and create
+ * resources while driver in operational.
+ */
+ struct mutex reslock;
+ struct mlx5_flow_table *rxft;
+ struct mlx5_fc *rx_counter;
+ struct mlx5_flow_handle *rx_rule;
+ bool setup;
+ u16 mtu;
+};
+
+static void free_resources(struct mlx5_vdpa_net *ndev);
+static void init_mvqs(struct mlx5_vdpa_net *ndev);
+static int setup_driver(struct mlx5_vdpa_net *ndev);
+static void teardown_driver(struct mlx5_vdpa_net *ndev);
+
+static bool mlx5_vdpa_debug;
+
+#define MLX5_LOG_VIO_FLAG(_feature) \
+ do { \
+ if (features & BIT(_feature)) \
+ mlx5_vdpa_info(mvdev, "%s\n", #_feature); \
+ } while (0)
+
+#define MLX5_LOG_VIO_STAT(_status) \
+ do { \
+ if (status & (_status)) \
+ mlx5_vdpa_info(mvdev, "%s\n", #_status); \
+ } while (0)
+
+static void print_status(struct mlx5_vdpa_dev *mvdev, u8 status, bool set)
+{
+ if (status & ~VALID_STATUS_MASK)
+ mlx5_vdpa_warn(mvdev, "Warning: there are invalid status bits 0x%x\n",
+ status & ~VALID_STATUS_MASK);
+
+ if (!mlx5_vdpa_debug)
+ return;
+
+ mlx5_vdpa_info(mvdev, "driver status %s", set ? "set" : "get");
+ if (set && !status) {
+ mlx5_vdpa_info(mvdev, "driver resets the device\n");
+ return;
+ }
+
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_ACKNOWLEDGE);
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_DRIVER);
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_DRIVER_OK);
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_FEATURES_OK);
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_NEEDS_RESET);
+ MLX5_LOG_VIO_STAT(VIRTIO_CONFIG_S_FAILED);
+}
+
+static void print_features(struct mlx5_vdpa_dev *mvdev, u64 features, bool set)
+{
+ if (features & ~VALID_FEATURES_MASK)
+ mlx5_vdpa_warn(mvdev, "There are invalid feature bits 0x%llx\n",
+ features & ~VALID_FEATURES_MASK);
+
+ if (!mlx5_vdpa_debug)
+ return;
+
+ mlx5_vdpa_info(mvdev, "driver %s feature bits:\n", set ? "sets" : "reads");
+ if (!features)
+ mlx5_vdpa_info(mvdev, "all feature bits are cleared\n");
+
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CSUM);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_CSUM);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MTU);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MAC);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_TSO4);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_TSO6);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_ECN);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_UFO);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_TSO4);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_TSO6);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_ECN);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HOST_UFO);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MRG_RXBUF);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_STATUS);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_VQ);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_RX);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_VLAN);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_RX_EXTRA);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_GUEST_ANNOUNCE);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_MQ);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_CTRL_MAC_ADDR);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_HASH_REPORT);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_RSS);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_RSC_EXT);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_STANDBY);
+ MLX5_LOG_VIO_FLAG(VIRTIO_NET_F_SPEED_DUPLEX);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_NOTIFY_ON_EMPTY);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_ANY_LAYOUT);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_VERSION_1);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_ACCESS_PLATFORM);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_RING_PACKED);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_ORDER_PLATFORM);
+ MLX5_LOG_VIO_FLAG(VIRTIO_F_SR_IOV);
+}
+
+static int create_tis(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+ u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+ void *tisc;
+ int err;
+
+ tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+ MLX5_SET(tisc, tisc, transport_domain, ndev->res.tdn);
+ err = mlx5_vdpa_create_tis(mvdev, in, &ndev->res.tisn);
+ if (err)
+ mlx5_vdpa_warn(mvdev, "create TIS (%d)\n", err);
+
+ return err;
+}
+
+static void destroy_tis(struct mlx5_vdpa_net *ndev)
+{
+ mlx5_vdpa_destroy_tis(&ndev->mvdev, ndev->res.tisn);
+}
+
+#define MLX5_VDPA_CQE_SIZE 64
+#define MLX5_VDPA_LOG_CQE_SIZE ilog2(MLX5_VDPA_CQE_SIZE)
+
+static int cq_frag_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_cq_buf *buf, int nent)
+{
+ struct mlx5_frag_buf *frag_buf = &buf->frag_buf;
+ u8 log_wq_stride = MLX5_VDPA_LOG_CQE_SIZE;
+ u8 log_wq_sz = MLX5_VDPA_LOG_CQE_SIZE;
+ int err;
+
+ err = mlx5_frag_buf_alloc_node(ndev->mvdev.mdev, nent * MLX5_VDPA_CQE_SIZE, frag_buf,
+ ndev->mvdev.mdev->priv.numa_node);
+ if (err)
+ return err;
+
+ mlx5_init_fbc(frag_buf->frags, log_wq_stride, log_wq_sz, &buf->fbc);
+
+ buf->cqe_size = MLX5_VDPA_CQE_SIZE;
+ buf->nent = nent;
+
+ return 0;
+}
+
+static int umem_frag_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_umem *umem, int size)
+{
+ struct mlx5_frag_buf *frag_buf = &umem->frag_buf;
+
+ return mlx5_frag_buf_alloc_node(ndev->mvdev.mdev, size, frag_buf,
+ ndev->mvdev.mdev->priv.numa_node);
+}
+
+static void cq_frag_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_cq_buf *buf)
+{
+ mlx5_frag_buf_free(ndev->mvdev.mdev, &buf->frag_buf);
+}
+
+static void *get_cqe(struct mlx5_vdpa_cq *vcq, int n)
+{
+ return mlx5_frag_buf_get_wqe(&vcq->buf.fbc, n);
+}
+
+static void cq_frag_buf_init(struct mlx5_vdpa_cq *vcq, struct mlx5_vdpa_cq_buf *buf)
+{
+ struct mlx5_cqe64 *cqe64;
+ void *cqe;
+ int i;
+
+ for (i = 0; i < buf->nent; i++) {
+ cqe = get_cqe(vcq, i);
+ cqe64 = cqe;
+ cqe64->op_own = MLX5_CQE_INVALID << 4;
+ }
+}
+
+static void *get_sw_cqe(struct mlx5_vdpa_cq *cq, int n)
+{
+ struct mlx5_cqe64 *cqe64 = get_cqe(cq, n & (cq->cqe - 1));
+
+ if (likely(get_cqe_opcode(cqe64) != MLX5_CQE_INVALID) &&
+ !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & cq->cqe)))
+ return cqe64;
+
+ return NULL;
+}
+
+static void rx_post(struct mlx5_vdpa_qp *vqp, int n)
+{
+ vqp->head += n;
+ vqp->db.db[0] = cpu_to_be32(vqp->head);
+}
+
+static void qp_prepare(struct mlx5_vdpa_net *ndev, bool fw, void *in,
+ struct mlx5_vdpa_virtqueue *mvq, u32 num_ent)
+{
+ struct mlx5_vdpa_qp *vqp;
+ __be64 *pas;
+ void *qpc;
+
+ vqp = fw ? &mvq->fwqp : &mvq->vqqp;
+ MLX5_SET(create_qp_in, in, uid, ndev->mvdev.res.uid);
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ if (vqp->fw) {
+ /* Firmware QP is allocated by the driver for the firmware's
+ * use so we can skip part of the params as they will be chosen by firmware
+ */
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ MLX5_SET(qpc, qpc, rq_type, MLX5_ZERO_LEN_RQ);
+ MLX5_SET(qpc, qpc, no_sq, 1);
+ return;
+ }
+
+ MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+ MLX5_SET(qpc, qpc, pd, ndev->mvdev.res.pdn);
+ MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES);
+ MLX5_SET(qpc, qpc, uar_page, ndev->mvdev.res.uar->index);
+ MLX5_SET(qpc, qpc, log_page_size, vqp->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET(qpc, qpc, no_sq, 1);
+ MLX5_SET(qpc, qpc, cqn_rcv, mvq->cq.mcq.cqn);
+ MLX5_SET(qpc, qpc, log_rq_size, ilog2(num_ent));
+ MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
+ pas = (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas);
+ mlx5_fill_page_frag_array(&vqp->frag_buf, pas);
+}
+
+static int rq_buf_alloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp, u32 num_ent)
+{
+ return mlx5_frag_buf_alloc_node(ndev->mvdev.mdev,
+ num_ent * sizeof(struct mlx5_wqe_data_seg), &vqp->frag_buf,
+ ndev->mvdev.mdev->priv.numa_node);
+}
+
+static void rq_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp)
+{
+ mlx5_frag_buf_free(ndev->mvdev.mdev, &vqp->frag_buf);
+}
+
+static int qp_create(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq,
+ struct mlx5_vdpa_qp *vqp)
+{
+ struct mlx5_core_dev *mdev = ndev->mvdev.mdev;
+ int inlen = MLX5_ST_SZ_BYTES(create_qp_in);
+ u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
+ void *qpc;
+ void *in;
+ int err;
+
+ if (!vqp->fw) {
+ vqp = &mvq->vqqp;
+ err = rq_buf_alloc(ndev, vqp, mvq->num_ent);
+ if (err)
+ return err;
+
+ err = mlx5_db_alloc(ndev->mvdev.mdev, &vqp->db);
+ if (err)
+ goto err_db;
+ inlen += vqp->frag_buf.npages * sizeof(__be64);
+ }
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_kzalloc;
+ }
+
+ qp_prepare(ndev, vqp->fw, in, mvq, mvq->num_ent);
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+ MLX5_SET(qpc, qpc, pd, ndev->mvdev.res.pdn);
+ MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES);
+ if (!vqp->fw)
+ MLX5_SET64(qpc, qpc, dbr_addr, vqp->db.dma);
+ MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
+ err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+ kfree(in);
+ if (err)
+ goto err_kzalloc;
+
+ vqp->mqp.uid = ndev->mvdev.res.uid;
+ vqp->mqp.qpn = MLX5_GET(create_qp_out, out, qpn);
+
+ if (!vqp->fw)
+ rx_post(vqp, mvq->num_ent);
+
+ return 0;
+
+err_kzalloc:
+ if (!vqp->fw)
+ mlx5_db_free(ndev->mvdev.mdev, &vqp->db);
+err_db:
+ if (!vqp->fw)
+ rq_buf_free(ndev, vqp);
+
+ return err;
+}
+
+static void qp_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_qp *vqp)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_qp_in)] = {};
+
+ MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
+ MLX5_SET(destroy_qp_in, in, qpn, vqp->mqp.qpn);
+ MLX5_SET(destroy_qp_in, in, uid, ndev->mvdev.res.uid);
+ if (mlx5_cmd_exec_in(ndev->mvdev.mdev, destroy_qp, in))
+ mlx5_vdpa_warn(&ndev->mvdev, "destroy qp 0x%x\n", vqp->mqp.qpn);
+ if (!vqp->fw) {
+ mlx5_db_free(ndev->mvdev.mdev, &vqp->db);
+ rq_buf_free(ndev, vqp);
+ }
+}
+
+static void *next_cqe_sw(struct mlx5_vdpa_cq *cq)
+{
+ return get_sw_cqe(cq, cq->mcq.cons_index);
+}
+
+static int mlx5_vdpa_poll_one(struct mlx5_vdpa_cq *vcq)
+{
+ struct mlx5_cqe64 *cqe64;
+
+ cqe64 = next_cqe_sw(vcq);
+ if (!cqe64)
+ return -EAGAIN;
+
+ vcq->mcq.cons_index++;
+ return 0;
+}
+
+static void mlx5_vdpa_handle_completions(struct mlx5_vdpa_virtqueue *mvq, int num)
+{
+ mlx5_cq_set_ci(&mvq->cq.mcq);
+ rx_post(&mvq->vqqp, num);
+ if (mvq->event_cb.callback)
+ mvq->event_cb.callback(mvq->event_cb.private);
+}
+
+static void mlx5_vdpa_cq_comp(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe)
+{
+ struct mlx5_vdpa_virtqueue *mvq = container_of(mcq, struct mlx5_vdpa_virtqueue, cq.mcq);
+ struct mlx5_vdpa_net *ndev = mvq->ndev;
+ void __iomem *uar_page = ndev->mvdev.res.uar->map;
+ int num = 0;
+
+ while (!mlx5_vdpa_poll_one(&mvq->cq)) {
+ num++;
+ if (num > mvq->num_ent / 2) {
+ /* If completions keep coming while we poll, we want to
+ * let the hardware know that we consumed them by
+ * updating the doorbell record. We also let vdpa core
+ * know about this so it passes it on the virtio driver
+ * on the guest.
+ */
+ mlx5_vdpa_handle_completions(mvq, num);
+ num = 0;
+ }
+ }
+
+ if (num)
+ mlx5_vdpa_handle_completions(mvq, num);
+
+ mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index);
+}
+
+static int cq_create(struct mlx5_vdpa_net *ndev, u16 idx, u32 num_ent)
+{
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+ struct mlx5_core_dev *mdev = ndev->mvdev.mdev;
+ void __iomem *uar_page = ndev->mvdev.res.uar->map;
+ u32 out[MLX5_ST_SZ_DW(create_cq_out)];
+ struct mlx5_vdpa_cq *vcq = &mvq->cq;
+ unsigned int irqn;
+ __be64 *pas;
+ int inlen;
+ void *cqc;
+ void *in;
+ int err;
+ int eqn;
+
+ err = mlx5_db_alloc(mdev, &vcq->db);
+ if (err)
+ return err;
+
+ vcq->mcq.set_ci_db = vcq->db.db;
+ vcq->mcq.arm_db = vcq->db.db + 1;
+ vcq->mcq.cqe_sz = 64;
+
+ err = cq_frag_buf_alloc(ndev, &vcq->buf, num_ent);
+ if (err)
+ goto err_db;
+
+ cq_frag_buf_init(vcq, &vcq->buf);
+
+ inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+ MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * vcq->buf.frag_buf.npages;
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_vzalloc;
+ }
+
+ MLX5_SET(create_cq_in, in, uid, ndev->mvdev.res.uid);
+ pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
+ mlx5_fill_page_frag_array(&vcq->buf.frag_buf, pas);
+
+ cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+ MLX5_SET(cqc, cqc, log_page_size, vcq->buf.frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+
+ /* Use vector 0 by default. Consider adding code to choose least used
+ * vector.
+ */
+ err = mlx5_vector2eqn(mdev, 0, &eqn, &irqn);
+ if (err)
+ goto err_vec;
+
+ cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+ MLX5_SET(cqc, cqc, log_cq_size, ilog2(num_ent));
+ MLX5_SET(cqc, cqc, uar_page, ndev->mvdev.res.uar->index);
+ MLX5_SET(cqc, cqc, c_eqn, eqn);
+ MLX5_SET64(cqc, cqc, dbr_addr, vcq->db.dma);
+
+ err = mlx5_core_create_cq(mdev, &vcq->mcq, in, inlen, out, sizeof(out));
+ if (err)
+ goto err_vec;
+
+ vcq->mcq.comp = mlx5_vdpa_cq_comp;
+ vcq->cqe = num_ent;
+ vcq->mcq.set_ci_db = vcq->db.db;
+ vcq->mcq.arm_db = vcq->db.db + 1;
+ mlx5_cq_arm(&mvq->cq.mcq, MLX5_CQ_DB_REQ_NOT, uar_page, mvq->cq.mcq.cons_index);
+ kfree(in);
+ return 0;
+
+err_vec:
+ kfree(in);
+err_vzalloc:
+ cq_frag_buf_free(ndev, &vcq->buf);
+err_db:
+ mlx5_db_free(ndev->mvdev.mdev, &vcq->db);
+ return err;
+}
+
+static void cq_destroy(struct mlx5_vdpa_net *ndev, u16 idx)
+{
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+ struct mlx5_core_dev *mdev = ndev->mvdev.mdev;
+ struct mlx5_vdpa_cq *vcq = &mvq->cq;
+
+ if (mlx5_core_destroy_cq(mdev, &vcq->mcq)) {
+ mlx5_vdpa_warn(&ndev->mvdev, "destroy CQ 0x%x\n", vcq->mcq.cqn);
+ return;
+ }
+ cq_frag_buf_free(ndev, &vcq->buf);
+ mlx5_db_free(ndev->mvdev.mdev, &vcq->db);
+}
+
+static int umem_size(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num,
+ struct mlx5_vdpa_umem **umemp)
+{
+ struct mlx5_core_dev *mdev = ndev->mvdev.mdev;
+ int p_a;
+ int p_b;
+
+ switch (num) {
+ case 1:
+ p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_a);
+ p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_b);
+ *umemp = &mvq->umem1;
+ break;
+ case 2:
+ p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_a);
+ p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_b);
+ *umemp = &mvq->umem2;
+ break;
+ case 3:
+ p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_a);
+ p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_b);
+ *umemp = &mvq->umem3;
+ break;
+ }
+ return p_a * mvq->num_ent + p_b;
+}
+
+static void umem_frag_buf_free(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_umem *umem)
+{
+ mlx5_frag_buf_free(ndev->mvdev.mdev, &umem->frag_buf);
+}
+
+static int create_umem(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num)
+{
+ int inlen;
+ u32 out[MLX5_ST_SZ_DW(create_umem_out)] = {};
+ void *um;
+ void *in;
+ int err;
+ __be64 *pas;
+ int size;
+ struct mlx5_vdpa_umem *umem;
+
+ size = umem_size(ndev, mvq, num, &umem);
+ if (size < 0)
+ return size;
+
+ umem->size = size;
+ err = umem_frag_buf_alloc(ndev, umem, size);
+ if (err)
+ return err;
+
+ inlen = MLX5_ST_SZ_BYTES(create_umem_in) + MLX5_ST_SZ_BYTES(mtt) * umem->frag_buf.npages;
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_in;
+ }
+
+ MLX5_SET(create_umem_in, in, opcode, MLX5_CMD_OP_CREATE_UMEM);
+ MLX5_SET(create_umem_in, in, uid, ndev->mvdev.res.uid);
+ um = MLX5_ADDR_OF(create_umem_in, in, umem);
+ MLX5_SET(umem, um, log_page_size, umem->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET64(umem, um, num_of_mtt, umem->frag_buf.npages);
+
+ pas = (__be64 *)MLX5_ADDR_OF(umem, um, mtt[0]);
+ mlx5_fill_page_frag_array_perm(&umem->frag_buf, pas, MLX5_MTT_PERM_RW);
+
+ err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "create umem(%d)\n", err);
+ goto err_cmd;
+ }
+
+ kfree(in);
+ umem->id = MLX5_GET(create_umem_out, out, umem_id);
+
+ return 0;
+
+err_cmd:
+ kfree(in);
+err_in:
+ umem_frag_buf_free(ndev, umem);
+ return err;
+}
+
+static void umem_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_umem_in)] = {};
+ u32 out[MLX5_ST_SZ_DW(destroy_umem_out)] = {};
+ struct mlx5_vdpa_umem *umem;
+
+ switch (num) {
+ case 1:
+ umem = &mvq->umem1;
+ break;
+ case 2:
+ umem = &mvq->umem2;
+ break;
+ case 3:
+ umem = &mvq->umem3;
+ break;
+ }
+
+ MLX5_SET(destroy_umem_in, in, opcode, MLX5_CMD_OP_DESTROY_UMEM);
+ MLX5_SET(destroy_umem_in, in, umem_id, umem->id);
+ if (mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out)))
+ return;
+
+ umem_frag_buf_free(ndev, umem);
+}
+
+static int umems_create(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ int num;
+ int err;
+
+ for (num = 1; num <= 3; num++) {
+ err = create_umem(ndev, mvq, num);
+ if (err)
+ goto err_umem;
+ }
+ return 0;
+
+err_umem:
+ for (num--; num > 0; num--)
+ umem_destroy(ndev, mvq, num);
+
+ return err;
+}
+
+static void umems_destroy(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ int num;
+
+ for (num = 3; num > 0; num--)
+ umem_destroy(ndev, mvq, num);
+}
+
+static int get_queue_type(struct mlx5_vdpa_net *ndev)
+{
+ u32 type_mask;
+
+ type_mask = MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, virtio_queue_type);
+
+ /* prefer split queue */
+ if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED)
+ return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED;
+
+ WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT));
+
+ return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT;
+}
+
+static bool vq_is_tx(u16 idx)
+{
+ return idx % 2;
+}
+
+static u16 get_features_12_3(u64 features)
+{
+ return (!!(features & BIT(VIRTIO_NET_F_HOST_TSO4)) << 9) |
+ (!!(features & BIT(VIRTIO_NET_F_HOST_TSO6)) << 8) |
+ (!!(features & BIT(VIRTIO_NET_F_CSUM)) << 7) |
+ (!!(features & BIT(VIRTIO_NET_F_GUEST_CSUM)) << 6);
+}
+
+static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in);
+ u32 out[MLX5_ST_SZ_DW(create_virtio_net_q_out)] = {};
+ void *obj_context;
+ void *cmd_hdr;
+ void *vq_ctx;
+ void *in;
+ int err;
+
+ err = umems_create(ndev, mvq);
+ if (err)
+ return err;
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_alloc;
+ }
+
+ cmd_hdr = MLX5_ADDR_OF(create_virtio_net_q_in, in, general_obj_in_cmd_hdr);
+
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
+
+ obj_context = MLX5_ADDR_OF(create_virtio_net_q_in, in, obj_context);
+ MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx);
+ MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_12_3,
+ get_features_12_3(ndev->mvdev.actual_features));
+ vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context);
+ MLX5_SET(virtio_q, vq_ctx, virtio_q_type, get_queue_type(ndev));
+
+ if (vq_is_tx(mvq->index))
+ MLX5_SET(virtio_net_q_object, obj_context, tisn_or_qpn, ndev->res.tisn);
+
+ MLX5_SET(virtio_q, vq_ctx, event_mode, MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE);
+ MLX5_SET(virtio_q, vq_ctx, queue_index, mvq->index);
+ MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn);
+ MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent);
+ MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0,
+ !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1));
+ MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
+ MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
+ MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
+ MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey.key);
+ MLX5_SET(virtio_q, vq_ctx, umem_1_id, mvq->umem1.id);
+ MLX5_SET(virtio_q, vq_ctx, umem_1_size, mvq->umem1.size);
+ MLX5_SET(virtio_q, vq_ctx, umem_2_id, mvq->umem2.id);
+ MLX5_SET(virtio_q, vq_ctx, umem_2_size, mvq->umem1.size);
+ MLX5_SET(virtio_q, vq_ctx, umem_3_id, mvq->umem3.id);
+ MLX5_SET(virtio_q, vq_ctx, umem_3_size, mvq->umem1.size);
+ MLX5_SET(virtio_q, vq_ctx, pd, ndev->mvdev.res.pdn);
+ if (MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, eth_frame_offload_type))
+ MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, 1);
+
+ err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
+ if (err)
+ goto err_cmd;
+
+ kfree(in);
+ mvq->virtq_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+ return 0;
+
+err_cmd:
+ kfree(in);
+err_alloc:
+ umems_destroy(ndev, mvq);
+ return err;
+}
+
+static void destroy_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_virtio_net_q_in)] = {};
+ u32 out[MLX5_ST_SZ_DW(destroy_virtio_net_q_out)] = {};
+
+ MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.opcode,
+ MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+ MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.obj_id, mvq->virtq_id);
+ MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.uid, ndev->mvdev.res.uid);
+ MLX5_SET(destroy_virtio_net_q_in, in, general_obj_out_cmd_hdr.obj_type,
+ MLX5_OBJ_TYPE_VIRTIO_NET_Q);
+ if (mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, sizeof(out))) {
+ mlx5_vdpa_warn(&ndev->mvdev, "destroy virtqueue 0x%x\n", mvq->virtq_id);
+ return;
+ }
+ umems_destroy(ndev, mvq);
+}
+
+static u32 get_rqpn(struct mlx5_vdpa_virtqueue *mvq, bool fw)
+{
+ return fw ? mvq->vqqp.mqp.qpn : mvq->fwqp.mqp.qpn;
+}
+
+static u32 get_qpn(struct mlx5_vdpa_virtqueue *mvq, bool fw)
+{
+ return fw ? mvq->fwqp.mqp.qpn : mvq->vqqp.mqp.qpn;
+}
+
+static void alloc_inout(struct mlx5_vdpa_net *ndev, int cmd, void **in, int *inlen, void **out,
+ int *outlen, u32 qpn, u32 rqpn)
+{
+ void *qpc;
+ void *pp;
+
+ switch (cmd) {
+ case MLX5_CMD_OP_2RST_QP:
+ *inlen = MLX5_ST_SZ_BYTES(qp_2rst_in);
+ *outlen = MLX5_ST_SZ_BYTES(qp_2rst_out);
+ *in = kzalloc(*inlen, GFP_KERNEL);
+ *out = kzalloc(*outlen, GFP_KERNEL);
+ if (!*in || !*out)
+ goto outerr;
+
+ MLX5_SET(qp_2rst_in, *in, opcode, cmd);
+ MLX5_SET(qp_2rst_in, *in, uid, ndev->mvdev.res.uid);
+ MLX5_SET(qp_2rst_in, *in, qpn, qpn);
+ break;
+ case MLX5_CMD_OP_RST2INIT_QP:
+ *inlen = MLX5_ST_SZ_BYTES(rst2init_qp_in);
+ *outlen = MLX5_ST_SZ_BYTES(rst2init_qp_out);
+ *in = kzalloc(*inlen, GFP_KERNEL);
+ *out = kzalloc(MLX5_ST_SZ_BYTES(rst2init_qp_out), GFP_KERNEL);
+ if (!*in || !*out)
+ goto outerr;
+
+ MLX5_SET(rst2init_qp_in, *in, opcode, cmd);
+ MLX5_SET(rst2init_qp_in, *in, uid, ndev->mvdev.res.uid);
+ MLX5_SET(rst2init_qp_in, *in, qpn, qpn);
+ qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc);
+ MLX5_SET(qpc, qpc, remote_qpn, rqpn);
+ MLX5_SET(qpc, qpc, rwe, 1);
+ pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path);
+ MLX5_SET(ads, pp, vhca_port_num, 1);
+ break;
+ case MLX5_CMD_OP_INIT2RTR_QP:
+ *inlen = MLX5_ST_SZ_BYTES(init2rtr_qp_in);
+ *outlen = MLX5_ST_SZ_BYTES(init2rtr_qp_out);
+ *in = kzalloc(*inlen, GFP_KERNEL);
+ *out = kzalloc(MLX5_ST_SZ_BYTES(init2rtr_qp_out), GFP_KERNEL);
+ if (!*in || !*out)
+ goto outerr;
+
+ MLX5_SET(init2rtr_qp_in, *in, opcode, cmd);
+ MLX5_SET(init2rtr_qp_in, *in, uid, ndev->mvdev.res.uid);
+ MLX5_SET(init2rtr_qp_in, *in, qpn, qpn);
+ qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc);
+ MLX5_SET(qpc, qpc, mtu, MLX5_QPC_MTU_256_BYTES);
+ MLX5_SET(qpc, qpc, log_msg_max, 30);
+ MLX5_SET(qpc, qpc, remote_qpn, rqpn);
+ pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path);
+ MLX5_SET(ads, pp, fl, 1);
+ break;
+ case MLX5_CMD_OP_RTR2RTS_QP:
+ *inlen = MLX5_ST_SZ_BYTES(rtr2rts_qp_in);
+ *outlen = MLX5_ST_SZ_BYTES(rtr2rts_qp_out);
+ *in = kzalloc(*inlen, GFP_KERNEL);
+ *out = kzalloc(MLX5_ST_SZ_BYTES(rtr2rts_qp_out), GFP_KERNEL);
+ if (!*in || !*out)
+ goto outerr;
+
+ MLX5_SET(rtr2rts_qp_in, *in, opcode, cmd);
+ MLX5_SET(rtr2rts_qp_in, *in, uid, ndev->mvdev.res.uid);
+ MLX5_SET(rtr2rts_qp_in, *in, qpn, qpn);
+ qpc = MLX5_ADDR_OF(rst2init_qp_in, *in, qpc);
+ pp = MLX5_ADDR_OF(qpc, qpc, primary_address_path);
+ MLX5_SET(ads, pp, ack_timeout, 14);
+ MLX5_SET(qpc, qpc, retry_count, 7);
+ MLX5_SET(qpc, qpc, rnr_retry, 7);
+ break;
+ default:
+ goto outerr_nullify;
+ }
+
+ return;
+
+outerr:
+ kfree(*in);
+ kfree(*out);
+outerr_nullify:
+ *in = NULL;
+ *out = NULL;
+}
+
+static void free_inout(void *in, void *out)
+{
+ kfree(in);
+ kfree(out);
+}
+
+/* Two QPs are used by each virtqueue. One is used by the driver and one by
+ * firmware. The fw argument indicates whether the subjected QP is the one used
+ * by firmware.
+ */
+static int modify_qp(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, bool fw, int cmd)
+{
+ int outlen;
+ int inlen;
+ void *out;
+ void *in;
+ int err;
+
+ alloc_inout(ndev, cmd, &in, &inlen, &out, &outlen, get_qpn(mvq, fw), get_rqpn(mvq, fw));
+ if (!in || !out)
+ return -ENOMEM;
+
+ err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, outlen);
+ free_inout(in, out);
+ return err;
+}
+
+static int connect_qps(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ int err;
+
+ err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_2RST_QP);
+ if (err)
+ return err;
+
+ err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_2RST_QP);
+ if (err)
+ return err;
+
+ err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_RST2INIT_QP);
+ if (err)
+ return err;
+
+ err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_RST2INIT_QP);
+ if (err)
+ return err;
+
+ err = modify_qp(ndev, mvq, true, MLX5_CMD_OP_INIT2RTR_QP);
+ if (err)
+ return err;
+
+ err = modify_qp(ndev, mvq, false, MLX5_CMD_OP_INIT2RTR_QP);
+ if (err)
+ return err;
+
+ return modify_qp(ndev, mvq, true, MLX5_CMD_OP_RTR2RTS_QP);
+}
+
+struct mlx5_virtq_attr {
+ u8 state;
+ u16 available_index;
+};
+
+static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq,
+ struct mlx5_virtq_attr *attr)
+{
+ int outlen = MLX5_ST_SZ_BYTES(query_virtio_net_q_out);
+ u32 in[MLX5_ST_SZ_DW(query_virtio_net_q_in)] = {};
+ void *out;
+ void *obj_context;
+ void *cmd_hdr;
+ int err;
+
+ out = kzalloc(outlen, GFP_KERNEL);
+ if (!out)
+ return -ENOMEM;
+
+ cmd_hdr = MLX5_ADDR_OF(query_virtio_net_q_in, in, general_obj_in_cmd_hdr);
+
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_QUERY_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->virtq_id);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
+ err = mlx5_cmd_exec(ndev->mvdev.mdev, in, sizeof(in), out, outlen);
+ if (err)
+ goto err_cmd;
+
+ obj_context = MLX5_ADDR_OF(query_virtio_net_q_out, out, obj_context);
+ memset(attr, 0, sizeof(*attr));
+ attr->state = MLX5_GET(virtio_net_q_object, obj_context, state);
+ attr->available_index = MLX5_GET(virtio_net_q_object, obj_context, hw_available_index);
+ kfree(out);
+ return 0;
+
+err_cmd:
+ kfree(out);
+ return err;
+}
+
+static int modify_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int state)
+{
+ int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
+ u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
+ void *obj_context;
+ void *cmd_hdr;
+ void *in;
+ int err;
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ cmd_hdr = MLX5_ADDR_OF(modify_virtio_net_q_in, in, general_obj_in_cmd_hdr);
+
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_MODIFY_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_type, MLX5_OBJ_TYPE_VIRTIO_NET_Q);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, obj_id, mvq->virtq_id);
+ MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
+
+ obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
+ MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select,
+ MLX5_VIRTQ_MODIFY_MASK_STATE);
+ MLX5_SET(virtio_net_q_object, obj_context, state, state);
+ err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
+ kfree(in);
+ if (!err)
+ mvq->fw_state = state;
+
+ return err;
+}
+
+static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ u16 idx = mvq->index;
+ int err;
+
+ if (!mvq->num_ent)
+ return 0;
+
+ if (mvq->initialized) {
+ mlx5_vdpa_warn(&ndev->mvdev, "attempt re init\n");
+ return -EINVAL;
+ }
+
+ err = cq_create(ndev, idx, mvq->num_ent);
+ if (err)
+ return err;
+
+ err = qp_create(ndev, mvq, &mvq->fwqp);
+ if (err)
+ goto err_fwqp;
+
+ err = qp_create(ndev, mvq, &mvq->vqqp);
+ if (err)
+ goto err_vqqp;
+
+ err = connect_qps(ndev, mvq);
+ if (err)
+ goto err_connect;
+
+ err = create_virtqueue(ndev, mvq);
+ if (err)
+ goto err_connect;
+
+ if (mvq->ready) {
+ err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n",
+ idx, err);
+ goto err_connect;
+ }
+ }
+
+ mvq->initialized = true;
+ return 0;
+
+err_connect:
+ qp_destroy(ndev, &mvq->vqqp);
+err_vqqp:
+ qp_destroy(ndev, &mvq->fwqp);
+err_fwqp:
+ cq_destroy(ndev, idx);
+ return err;
+}
+
+static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ struct mlx5_virtq_attr attr;
+
+ if (!mvq->initialized)
+ return;
+
+ if (query_virtqueue(ndev, mvq, &attr)) {
+ mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n");
+ return;
+ }
+ if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY)
+ return;
+
+ if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND))
+ mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n");
+}
+
+static void suspend_vqs(struct mlx5_vdpa_net *ndev)
+{
+ int i;
+
+ for (i = 0; i < MLX5_MAX_SUPPORTED_VQS; i++)
+ suspend_vq(ndev, &ndev->vqs[i]);
+}
+
+static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ if (!mvq->initialized)
+ return;
+
+ suspend_vq(ndev, mvq);
+ destroy_virtqueue(ndev, mvq);
+ qp_destroy(ndev, &mvq->vqqp);
+ qp_destroy(ndev, &mvq->fwqp);
+ cq_destroy(ndev, mvq->index);
+ mvq->initialized = false;
+}
+
+static int create_rqt(struct mlx5_vdpa_net *ndev)
+{
+ int log_max_rqt;
+ __be32 *list;
+ void *rqtc;
+ int inlen;
+ void *in;
+ int i, j;
+ int err;
+
+ log_max_rqt = min_t(int, 1, MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
+ if (log_max_rqt < 1)
+ return -EOPNOTSUPP;
+
+ inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + (1 << log_max_rqt) * MLX5_ST_SZ_BYTES(rq_num);
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_rqt_in, in, uid, ndev->mvdev.res.uid);
+ rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
+
+ MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
+ MLX5_SET(rqtc, rqtc, rqt_max_size, 1 << log_max_rqt);
+ MLX5_SET(rqtc, rqtc, rqt_actual_size, 1);
+ list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
+ for (i = 0, j = 0; j < ndev->mvdev.max_vqs; j++) {
+ if (!ndev->vqs[j].initialized)
+ continue;
+
+ if (!vq_is_tx(ndev->vqs[j].index)) {
+ list[i] = cpu_to_be32(ndev->vqs[j].virtq_id);
+ i++;
+ }
+ }
+
+ err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn);
+ kfree(in);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static void destroy_rqt(struct mlx5_vdpa_net *ndev)
+{
+ mlx5_vdpa_destroy_rqt(&ndev->mvdev, ndev->res.rqtn);
+}
+
+static int create_tir(struct mlx5_vdpa_net *ndev)
+{
+#define HASH_IP_L4PORTS \
+ (MLX5_HASH_FIELD_SEL_SRC_IP | MLX5_HASH_FIELD_SEL_DST_IP | MLX5_HASH_FIELD_SEL_L4_SPORT | \
+ MLX5_HASH_FIELD_SEL_L4_DPORT)
+ static const u8 rx_hash_toeplitz_key[] = { 0x2c, 0xc6, 0x81, 0xd1, 0x5b, 0xdb, 0xf4, 0xf7,
+ 0xfc, 0xa2, 0x83, 0x19, 0xdb, 0x1a, 0x3e, 0x94,
+ 0x6b, 0x9e, 0x38, 0xd9, 0x2c, 0x9c, 0x03, 0xd1,
+ 0xad, 0x99, 0x44, 0xa7, 0xd9, 0x56, 0x3d, 0x59,
+ 0x06, 0x3c, 0x25, 0xf3, 0xfc, 0x1f, 0xdc, 0x2a };
+ void *rss_key;
+ void *outer;
+ void *tirc;
+ void *in;
+ int err;
+
+ in = kzalloc(MLX5_ST_SZ_BYTES(create_tir_in), GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_tir_in, in, uid, ndev->mvdev.res.uid);
+ tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+ MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
+
+ MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+ MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ);
+ rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key);
+ memcpy(rss_key, rx_hash_toeplitz_key, sizeof(rx_hash_toeplitz_key));
+
+ outer = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+ MLX5_SET(rx_hash_field_select, outer, l3_prot_type, MLX5_L3_PROT_TYPE_IPV4);
+ MLX5_SET(rx_hash_field_select, outer, l4_prot_type, MLX5_L4_PROT_TYPE_TCP);
+ MLX5_SET(rx_hash_field_select, outer, selected_fields, HASH_IP_L4PORTS);
+
+ MLX5_SET(tirc, tirc, indirect_table, ndev->res.rqtn);
+ MLX5_SET(tirc, tirc, transport_domain, ndev->res.tdn);
+
+ err = mlx5_vdpa_create_tir(&ndev->mvdev, in, &ndev->res.tirn);
+ kfree(in);
+ return err;
+}
+
+static void destroy_tir(struct mlx5_vdpa_net *ndev)
+{
+ mlx5_vdpa_destroy_tir(&ndev->mvdev, ndev->res.tirn);
+}
+
+static int add_fwd_to_tir(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_flow_destination dest[2] = {};
+ struct mlx5_flow_table_attr ft_attr = {};
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_namespace *ns;
+ int err;
+
+ /* for now, one entry, match all, forward to tir */
+ ft_attr.max_fte = 1;
+ ft_attr.autogroup.max_num_groups = 1;
+
+ 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;
+ }
+
+ ndev->rxft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+ if (IS_ERR(ndev->rxft))
+ return PTR_ERR(ndev->rxft);
+
+ ndev->rx_counter = mlx5_fc_create(ndev->mvdev.mdev, false);
+ if (IS_ERR(ndev->rx_counter)) {
+ err = PTR_ERR(ndev->rx_counter);
+ goto err_fc;
+ }
+
+ 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;
+ }
+
+ return 0;
+
+err_rule:
+ mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
+err_fc:
+ mlx5_destroy_flow_table(ndev->rxft);
+ return err;
+}
+
+static void remove_fwd_to_tir(struct mlx5_vdpa_net *ndev)
+{
+ if (!ndev->rx_rule)
+ return;
+
+ mlx5_del_flow_rules(ndev->rx_rule);
+ mlx5_fc_destroy(ndev->mvdev.mdev, ndev->rx_counter);
+ mlx5_destroy_flow_table(ndev->rxft);
+
+ ndev->rx_rule = NULL;
+}
+
+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 = &ndev->vqs[idx];
+
+ if (unlikely(!mvq->ready))
+ return;
+
+ iowrite16(idx, ndev->mvdev.res.kick_addr);
+}
+
+static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_area,
+ u64 driver_area, u64 device_area)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+
+ mvq->desc_addr = desc_area;
+ mvq->device_addr = device_area;
+ mvq->driver_addr = driver_area;
+ return 0;
+}
+
+static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *mvq;
+
+ mvq = &ndev->vqs[idx];
+ mvq->num_ent = num;
+}
+
+static void mlx5_vdpa_set_vq_cb(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *vq = &ndev->vqs[idx];
+
+ vq->event_cb = *cb;
+}
+
+static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+
+ if (!ready)
+ suspend_vq(ndev, mvq);
+
+ mvq->ready = ready;
+}
+
+static bool mlx5_vdpa_get_vq_ready(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 = &ndev->vqs[idx];
+
+ return mvq->ready;
+}
+
+static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
+ const struct vdpa_vq_state *state)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+
+ if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) {
+ mlx5_vdpa_warn(mvdev, "can't modify available index\n");
+ return -EINVAL;
+ }
+
+ mvq->avail_idx = state->avail_index;
+ return 0;
+}
+
+static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+ struct mlx5_virtq_attr attr;
+ int err;
+
+ if (!mvq->initialized)
+ return -EAGAIN;
+
+ err = query_virtqueue(ndev, mvq, &attr);
+ if (err) {
+ mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n");
+ return err;
+ }
+ state->avail_index = attr.available_index;
+ return 0;
+}
+
+static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)
+{
+ return PAGE_SIZE;
+}
+
+enum { MLX5_VIRTIO_NET_F_GUEST_CSUM = 1 << 9,
+ MLX5_VIRTIO_NET_F_CSUM = 1 << 10,
+ MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11,
+ MLX5_VIRTIO_NET_F_HOST_TSO4 = 1 << 12,
+};
+
+static u64 mlx_to_vritio_features(u16 dev_features)
+{
+ u64 result = 0;
+
+ if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM)
+ result |= BIT(VIRTIO_NET_F_GUEST_CSUM);
+ if (dev_features & MLX5_VIRTIO_NET_F_CSUM)
+ result |= BIT(VIRTIO_NET_F_CSUM);
+ if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6)
+ result |= BIT(VIRTIO_NET_F_HOST_TSO6);
+ if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4)
+ result |= BIT(VIRTIO_NET_F_HOST_TSO4);
+
+ return result;
+}
+
+static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ u16 dev_features;
+
+ dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
+ ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features);
+ if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
+ ndev->mvdev.mlx_features |= BIT(VIRTIO_F_VERSION_1);
+ ndev->mvdev.mlx_features |= BIT(VIRTIO_F_ACCESS_PLATFORM);
+ print_features(mvdev, ndev->mvdev.mlx_features, false);
+ return ndev->mvdev.mlx_features;
+}
+
+static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features)
+{
+ if (!(features & BIT(VIRTIO_F_ACCESS_PLATFORM)))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int setup_virtqueues(struct mlx5_vdpa_net *ndev)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); i++) {
+ err = setup_vq(ndev, &ndev->vqs[i]);
+ if (err)
+ goto err_vq;
+ }
+
+ return 0;
+
+err_vq:
+ for (--i; i >= 0; i--)
+ teardown_vq(ndev, &ndev->vqs[i]);
+
+ return err;
+}
+
+static void teardown_virtqueues(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_virtqueue *mvq;
+ int i;
+
+ for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) {
+ mvq = &ndev->vqs[i];
+ if (!mvq->initialized)
+ continue;
+
+ teardown_vq(ndev, mvq);
+ }
+}
+
+/* TODO: cross-endian support */
+static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
+{
+ return virtio_legacy_is_little_endian() ||
+ (mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1));
+}
+
+static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ int err;
+
+ print_features(mvdev, features, true);
+
+ err = verify_min_features(mvdev, features);
+ if (err)
+ return err;
+
+ ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features;
+ ndev->config.mtu = __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev),
+ ndev->mtu);
+ 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");
+}
+
+#define MLX5_VDPA_MAX_VQ_ENTRIES 256
+static u16 mlx5_vdpa_get_vq_num_max(struct vdpa_device *vdev)
+{
+ return MLX5_VDPA_MAX_VQ_ENTRIES;
+}
+
+static u32 mlx5_vdpa_get_device_id(struct vdpa_device *vdev)
+{
+ return VIRTIO_ID_NET;
+}
+
+static u32 mlx5_vdpa_get_vendor_id(struct vdpa_device *vdev)
+{
+ return PCI_VENDOR_ID_MELLANOX;
+}
+
+static u8 mlx5_vdpa_get_status(struct vdpa_device *vdev)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+
+ print_status(mvdev, ndev->mvdev.status, false);
+ return ndev->mvdev.status;
+}
+
+static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
+{
+ struct mlx5_vq_restore_info *ri = &mvq->ri;
+ struct mlx5_virtq_attr attr;
+ int err;
+
+ if (!mvq->initialized)
+ return 0;
+
+ err = query_virtqueue(ndev, mvq, &attr);
+ if (err)
+ return err;
+
+ ri->avail_index = attr.available_index;
+ ri->ready = mvq->ready;
+ ri->num_ent = mvq->num_ent;
+ ri->desc_addr = mvq->desc_addr;
+ ri->device_addr = mvq->device_addr;
+ ri->driver_addr = mvq->driver_addr;
+ ri->cb = mvq->event_cb;
+ ri->restore = true;
+ return 0;
+}
+
+static int save_channels_info(struct mlx5_vdpa_net *ndev)
+{
+ int i;
+
+ for (i = 0; i < ndev->mvdev.max_vqs; i++) {
+ memset(&ndev->vqs[i].ri, 0, sizeof(ndev->vqs[i].ri));
+ save_channel_info(ndev, &ndev->vqs[i]);
+ }
+ return 0;
+}
+
+static void mlx5_clear_vqs(struct mlx5_vdpa_net *ndev)
+{
+ int i;
+
+ for (i = 0; i < ndev->mvdev.max_vqs; i++)
+ memset(&ndev->vqs[i], 0, offsetof(struct mlx5_vdpa_virtqueue, ri));
+}
+
+static void restore_channels_info(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_virtqueue *mvq;
+ struct mlx5_vq_restore_info *ri;
+ int i;
+
+ mlx5_clear_vqs(ndev);
+ init_mvqs(ndev);
+ for (i = 0; i < ndev->mvdev.max_vqs; i++) {
+ mvq = &ndev->vqs[i];
+ ri = &mvq->ri;
+ if (!ri->restore)
+ continue;
+
+ mvq->avail_idx = ri->avail_index;
+ mvq->ready = ri->ready;
+ mvq->num_ent = ri->num_ent;
+ mvq->desc_addr = ri->desc_addr;
+ mvq->device_addr = ri->device_addr;
+ mvq->driver_addr = ri->driver_addr;
+ mvq->event_cb = ri->cb;
+ }
+}
+
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_net *ndev, struct vhost_iotlb *iotlb)
+{
+ int err;
+
+ suspend_vqs(ndev);
+ err = save_channels_info(ndev);
+ if (err)
+ goto err_mr;
+
+ teardown_driver(ndev);
+ mlx5_vdpa_destroy_mr(&ndev->mvdev);
+ err = mlx5_vdpa_create_mr(&ndev->mvdev, iotlb);
+ if (err)
+ goto err_mr;
+
+ restore_channels_info(ndev);
+ err = setup_driver(ndev);
+ if (err)
+ goto err_setup;
+
+ return 0;
+
+err_setup:
+ mlx5_vdpa_destroy_mr(&ndev->mvdev);
+err_mr:
+ return err;
+}
+
+static int setup_driver(struct mlx5_vdpa_net *ndev)
+{
+ int err;
+
+ mutex_lock(&ndev->reslock);
+ if (ndev->setup) {
+ mlx5_vdpa_warn(&ndev->mvdev, "setup driver called for already setup driver\n");
+ err = 0;
+ goto out;
+ }
+ err = setup_virtqueues(ndev);
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "setup_virtqueues\n");
+ goto out;
+ }
+
+ err = create_rqt(ndev);
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "create_rqt\n");
+ goto err_rqt;
+ }
+
+ err = create_tir(ndev);
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "create_tir\n");
+ goto err_tir;
+ }
+
+ err = add_fwd_to_tir(ndev);
+ if (err) {
+ mlx5_vdpa_warn(&ndev->mvdev, "add_fwd_to_tir\n");
+ goto err_fwd;
+ }
+ ndev->setup = true;
+ mutex_unlock(&ndev->reslock);
+
+ return 0;
+
+err_fwd:
+ destroy_tir(ndev);
+err_tir:
+ destroy_rqt(ndev);
+err_rqt:
+ teardown_virtqueues(ndev);
+out:
+ mutex_unlock(&ndev->reslock);
+ return err;
+}
+
+static void teardown_driver(struct mlx5_vdpa_net *ndev)
+{
+ mutex_lock(&ndev->reslock);
+ if (!ndev->setup)
+ goto out;
+
+ remove_fwd_to_tir(ndev);
+ destroy_tir(ndev);
+ destroy_rqt(ndev);
+ teardown_virtqueues(ndev);
+ ndev->setup = false;
+out:
+ mutex_unlock(&ndev->reslock);
+}
+
+static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ int err;
+
+ print_status(mvdev, status, true);
+ if (!status) {
+ mlx5_vdpa_info(mvdev, "performing device reset\n");
+ teardown_driver(ndev);
+ mlx5_vdpa_destroy_mr(&ndev->mvdev);
+ ndev->mvdev.status = 0;
+ ndev->mvdev.mlx_features = 0;
+ ++mvdev->generation;
+ return;
+ }
+
+ if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) {
+ if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
+ err = setup_driver(ndev);
+ if (err) {
+ mlx5_vdpa_warn(mvdev, "failed to setup driver\n");
+ goto err_setup;
+ }
+ } else {
+ mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n");
+ return;
+ }
+ }
+
+ ndev->mvdev.status = status;
+ return;
+
+err_setup:
+ mlx5_vdpa_destroy_mr(&ndev->mvdev);
+ ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED;
+}
+
+static void mlx5_vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf,
+ unsigned int len)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+
+ if (offset + len < sizeof(struct virtio_net_config))
+ memcpy(buf, (u8 *)&ndev->config + offset, len);
+}
+
+static void mlx5_vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf,
+ unsigned int len)
+{
+ /* not supported */
+}
+
+static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+
+ return mvdev->generation;
+}
+
+static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+ bool change_map;
+ int err;
+
+ err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+ if (err) {
+ mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
+ return err;
+ }
+
+ if (change_map)
+ return mlx5_vdpa_change_map(ndev, iotlb);
+
+ return 0;
+}
+
+static void mlx5_vdpa_free(struct vdpa_device *vdev)
+{
+ struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+ struct mlx5_vdpa_net *ndev;
+
+ ndev = to_mlx5_vdpa_ndev(mvdev);
+
+ free_resources(ndev);
+ mlx5_vdpa_free_resources(&ndev->mvdev);
+ mutex_destroy(&ndev->reslock);
+}
+
+static struct vdpa_notification_area mlx5_get_vq_notification(struct vdpa_device *vdev, u16 idx)
+{
+ struct vdpa_notification_area ret = {};
+
+ return ret;
+}
+
+static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx)
+{
+ return -EOPNOTSUPP;
+}
+
+static const struct vdpa_config_ops mlx5_vdpa_ops = {
+ .set_vq_address = mlx5_vdpa_set_vq_address,
+ .set_vq_num = mlx5_vdpa_set_vq_num,
+ .kick_vq = mlx5_vdpa_kick_vq,
+ .set_vq_cb = mlx5_vdpa_set_vq_cb,
+ .set_vq_ready = mlx5_vdpa_set_vq_ready,
+ .get_vq_ready = mlx5_vdpa_get_vq_ready,
+ .set_vq_state = mlx5_vdpa_set_vq_state,
+ .get_vq_state = mlx5_vdpa_get_vq_state,
+ .get_vq_notification = mlx5_get_vq_notification,
+ .get_vq_irq = mlx5_get_vq_irq,
+ .get_vq_align = mlx5_vdpa_get_vq_align,
+ .get_features = mlx5_vdpa_get_features,
+ .set_features = mlx5_vdpa_set_features,
+ .set_config_cb = mlx5_vdpa_set_config_cb,
+ .get_vq_num_max = mlx5_vdpa_get_vq_num_max,
+ .get_device_id = mlx5_vdpa_get_device_id,
+ .get_vendor_id = mlx5_vdpa_get_vendor_id,
+ .get_status = mlx5_vdpa_get_status,
+ .set_status = mlx5_vdpa_set_status,
+ .get_config = mlx5_vdpa_get_config,
+ .set_config = mlx5_vdpa_set_config,
+ .get_generation = mlx5_vdpa_get_generation,
+ .set_map = mlx5_vdpa_set_map,
+ .free = mlx5_vdpa_free,
+};
+
+static int alloc_resources(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_net_resources *res = &ndev->res;
+ int err;
+
+ if (res->valid) {
+ mlx5_vdpa_warn(&ndev->mvdev, "resources already allocated\n");
+ return -EEXIST;
+ }
+
+ err = mlx5_vdpa_alloc_transport_domain(&ndev->mvdev, &res->tdn);
+ if (err)
+ return err;
+
+ err = create_tis(ndev);
+ if (err)
+ goto err_tis;
+
+ res->valid = true;
+
+ return 0;
+
+err_tis:
+ mlx5_vdpa_dealloc_transport_domain(&ndev->mvdev, res->tdn);
+ return err;
+}
+
+static void free_resources(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_net_resources *res = &ndev->res;
+
+ if (!res->valid)
+ return;
+
+ destroy_tis(ndev);
+ mlx5_vdpa_dealloc_transport_domain(&ndev->mvdev, res->tdn);
+ res->valid = false;
+}
+
+static void init_mvqs(struct mlx5_vdpa_net *ndev)
+{
+ struct mlx5_vdpa_virtqueue *mvq;
+ int i;
+
+ for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); ++i) {
+ mvq = &ndev->vqs[i];
+ memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri));
+ mvq->index = i;
+ mvq->ndev = ndev;
+ mvq->fwqp.fw = true;
+ }
+ for (; i < ndev->mvdev.max_vqs; i++) {
+ mvq = &ndev->vqs[i];
+ memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri));
+ mvq->index = i;
+ mvq->ndev = ndev;
+ }
+}
+
+void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev)
+{
+ struct virtio_net_config *config;
+ struct mlx5_vdpa_dev *mvdev;
+ struct mlx5_vdpa_net *ndev;
+ u32 max_vqs;
+ int err;
+
+ /* we save one virtqueue for control virtqueue should we require it */
+ max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues);
+ max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
+
+ ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
+ 2 * mlx5_vdpa_max_qps(max_vqs));
+ if (IS_ERR(ndev))
+ return ndev;
+
+ ndev->mvdev.max_vqs = max_vqs;
+ mvdev = &ndev->mvdev;
+ mvdev->mdev = mdev;
+ init_mvqs(ndev);
+ mutex_init(&ndev->reslock);
+ config = &ndev->config;
+ err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu);
+ if (err)
+ goto err_mtu;
+
+ err = mlx5_query_nic_vport_mac_address(mdev, 0, 0, config->mac);
+ if (err)
+ goto err_mtu;
+
+ mvdev->vdev.dma_dev = mdev->device;
+ err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
+ if (err)
+ goto err_mtu;
+
+ err = alloc_resources(ndev);
+ if (err)
+ goto err_res;
+
+ err = vdpa_register_device(&mvdev->vdev);
+ if (err)
+ goto err_reg;
+
+ return ndev;
+
+err_reg:
+ free_resources(ndev);
+err_res:
+ mlx5_vdpa_free_resources(&ndev->mvdev);
+err_mtu:
+ mutex_destroy(&ndev->reslock);
+ put_device(&mvdev->vdev.dev);
+ return ERR_PTR(err);
+}
+
+void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev)
+{
+ vdpa_unregister_device(&mvdev->vdev);
+}
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.h b/drivers/vdpa/mlx5/net/mlx5_vnet.h
new file mode 100644
index 000000000000..f2d6d68b020e
--- /dev/null
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VNET_H_
+#define __MLX5_VNET_H_
+
+#include <linux/vdpa.h>
+#include <linux/virtio_net.h>
+#include <linux/vringh.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/cq.h>
+#include <linux/mlx5/qp.h>
+#include "mlx5_vdpa.h"
+
+static inline u32 mlx5_vdpa_max_qps(int max_vqs)
+{
+ return max_vqs / 2;
+}
+
+#define to_mlx5_vdpa_ndev(__mvdev) container_of(__mvdev, struct mlx5_vdpa_net, mvdev)
+void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev);
+void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev);
+
+#endif /* __MLX5_VNET_H_ */
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index de211ef3738c..a69ffc991e13 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -61,6 +61,7 @@ static void vdpa_release_dev(struct device *d)
* initialized but before registered.
* @parent: the parent device
* @config: the bus operations that is supported by this device
+ * @nvqs: number of virtqueues supported by this device
* @size: size of the parent structure that contains private data
*
* Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -71,6 +72,7 @@ static void vdpa_release_dev(struct device *d)
*/
struct vdpa_device *__vdpa_alloc_device(struct device *parent,
const struct vdpa_config_ops *config,
+ int nvqs,
size_t size)
{
struct vdpa_device *vdev;
@@ -96,6 +98,8 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
vdev->dev.release = vdpa_release_dev;
vdev->index = err;
vdev->config = config;
+ vdev->features_valid = false;
+ vdev->nvqs = nvqs;
err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
if (err)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index c7334cc65bb2..62d640327145 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -24,6 +24,7 @@
#include <linux/etherdevice.h>
#include <linux/vringh.h>
#include <linux/vdpa.h>
+#include <linux/virtio_byteorder.h>
#include <linux/vhost_iotlb.h>
#include <uapi/linux/virtio_config.h>
#include <uapi/linux/virtio_net.h>
@@ -33,6 +34,10 @@
#define DRV_DESC "vDPA Device Simulator"
#define DRV_LICENSE "GPL v2"
+static int batch_mapping = 1;
+module_param(batch_mapping, int, 0444);
+MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
+
struct vdpasim_virtqueue {
struct vringh vring;
struct vringh_kiov iov;
@@ -55,12 +60,12 @@ struct vdpasim_virtqueue {
static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
(1ULL << VIRTIO_F_VERSION_1) |
- (1ULL << VIRTIO_F_IOMMU_PLATFORM);
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM);
/* State of each vdpasim device */
struct vdpasim {
struct vdpa_device vdpa;
- struct vdpasim_virtqueue vqs[2];
+ struct vdpasim_virtqueue vqs[VDPASIM_VQ_NUM];
struct work_struct work;
/* spinlock to synchronize virtqueue state */
spinlock_t lock;
@@ -70,8 +75,27 @@ struct vdpasim {
u32 status;
u32 generation;
u64 features;
+ /* spinlock to synchronize iommu table */
+ spinlock_t iommu_lock;
};
+/* TODO: cross-endian support */
+static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
+{
+ return virtio_legacy_is_little_endian() ||
+ (vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
+}
+
+static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
+{
+ return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
+{
+ return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
+}
+
static struct vdpasim *vdpasim_dev;
static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa)
@@ -118,7 +142,9 @@ static void vdpasim_reset(struct vdpasim *vdpasim)
for (i = 0; i < VDPASIM_VQ_NUM; i++)
vdpasim_vq_reset(&vdpasim->vqs[i]);
+ spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_reset(vdpasim->iommu);
+ spin_unlock(&vdpasim->iommu_lock);
vdpasim->features = 0;
vdpasim->status = 0;
@@ -236,8 +262,10 @@ static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page,
/* For simplicity, use identical mapping to avoid e.g iova
* allocator.
*/
+ spin_lock(&vdpasim->iommu_lock);
ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1,
pa, dir_to_perm(dir));
+ spin_unlock(&vdpasim->iommu_lock);
if (ret)
return DMA_MAPPING_ERROR;
@@ -251,8 +279,10 @@ static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr,
struct vdpasim *vdpasim = dev_to_sim(dev);
struct vhost_iotlb *iommu = vdpasim->iommu;
+ spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(iommu, (u64)dma_addr,
(u64)dma_addr + size - 1);
+ spin_unlock(&vdpasim->iommu_lock);
}
static void *vdpasim_alloc_coherent(struct device *dev, size_t size,
@@ -264,9 +294,10 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size,
void *addr = kmalloc(size, flag);
int ret;
- if (!addr)
+ spin_lock(&vdpasim->iommu_lock);
+ if (!addr) {
*dma_addr = DMA_MAPPING_ERROR;
- else {
+ } else {
u64 pa = virt_to_phys(addr);
ret = vhost_iotlb_add_range(iommu, (u64)pa,
@@ -279,6 +310,7 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size,
} else
*dma_addr = (dma_addr_t)pa;
}
+ spin_unlock(&vdpasim->iommu_lock);
return addr;
}
@@ -290,8 +322,11 @@ static void vdpasim_free_coherent(struct device *dev, size_t size,
struct vdpasim *vdpasim = dev_to_sim(dev);
struct vhost_iotlb *iommu = vdpasim->iommu;
+ spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(iommu, (u64)dma_addr,
(u64)dma_addr + size - 1);
+ spin_unlock(&vdpasim->iommu_lock);
+
kfree(phys_to_virt((uintptr_t)dma_addr));
}
@@ -303,21 +338,27 @@ static const struct dma_map_ops vdpasim_dma_ops = {
};
static const struct vdpa_config_ops vdpasim_net_config_ops;
+static const struct vdpa_config_ops vdpasim_net_batch_config_ops;
static struct vdpasim *vdpasim_create(void)
{
- struct virtio_net_config *config;
+ const struct vdpa_config_ops *ops;
struct vdpasim *vdpasim;
struct device *dev;
int ret = -ENOMEM;
- vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL,
- &vdpasim_net_config_ops);
+ if (batch_mapping)
+ ops = &vdpasim_net_batch_config_ops;
+ else
+ ops = &vdpasim_net_config_ops;
+
+ vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
if (!vdpasim)
goto err_alloc;
INIT_WORK(&vdpasim->work, vdpasim_work);
spin_lock_init(&vdpasim->lock);
+ spin_lock_init(&vdpasim->iommu_lock);
dev = &vdpasim->vdpa.dev;
dev->coherent_dma_mask = DMA_BIT_MASK(64);
@@ -331,10 +372,7 @@ static struct vdpasim *vdpasim_create(void)
if (!vdpasim->buffer)
goto err_iommu;
- config = &vdpasim->config;
- config->mtu = 1500;
- config->status = VIRTIO_NET_S_LINK_UP;
- eth_random_addr(config->mac);
+ eth_random_addr(vdpasim->config.mac);
vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
@@ -413,26 +451,29 @@ static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
return vq->ready;
}
-static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, u64 state)
+static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx,
+ const struct vdpa_vq_state *state)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
struct vringh *vrh = &vq->vring;
spin_lock(&vdpasim->lock);
- vrh->last_avail_idx = state;
+ vrh->last_avail_idx = state->avail_index;
spin_unlock(&vdpasim->lock);
return 0;
}
-static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx)
+static int vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx,
+ struct vdpa_vq_state *state)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
struct vringh *vrh = &vq->vring;
- return vrh->last_avail_idx;
+ state->avail_index = vrh->last_avail_idx;
+ return 0;
}
static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
@@ -448,13 +489,22 @@ static u64 vdpasim_get_features(struct vdpa_device *vdpa)
static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+ struct virtio_net_config *config = &vdpasim->config;
/* DMA mapping must be done by driver */
- if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
+ if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
return -EINVAL;
vdpasim->features = features & vdpasim_features;
+ /* We generally only know whether guest is using the legacy interface
+ * here, so generally that's the earliest we can set config fields.
+ * Note: We actually require VIRTIO_F_ACCESS_PLATFORM above which
+ * implies VIRTIO_F_VERSION_1, but let's not try to be clever here.
+ */
+
+ config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
+ config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
return 0;
}
@@ -508,7 +558,7 @@ static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset,
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
if (offset + len < sizeof(struct virtio_net_config))
- memcpy(buf, &vdpasim->config + offset, len);
+ memcpy(buf, (u8 *)&vdpasim->config + offset, len);
}
static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset,
@@ -532,6 +582,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,
u64 start = 0ULL, last = 0ULL - 1;
int ret;
+ spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_reset(vdpasim->iommu);
for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
@@ -541,10 +592,12 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,
if (ret)
goto err;
}
+ spin_unlock(&vdpasim->iommu_lock);
return 0;
err:
vhost_iotlb_reset(vdpasim->iommu);
+ spin_unlock(&vdpasim->iommu_lock);
return ret;
}
@@ -552,16 +605,23 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
u64 pa, u32 perm)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+ int ret;
+
+ spin_lock(&vdpasim->iommu_lock);
+ ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa,
+ perm);
+ spin_unlock(&vdpasim->iommu_lock);
- return vhost_iotlb_add_range(vdpasim->iommu, iova,
- iova + size - 1, pa, perm);
+ return ret;
}
static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+ spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(vdpasim->iommu, iova, iova + size - 1);
+ spin_unlock(&vdpasim->iommu_lock);
return 0;
}
@@ -597,12 +657,36 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = {
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
.get_generation = vdpasim_get_generation,
- .set_map = vdpasim_set_map,
.dma_map = vdpasim_dma_map,
.dma_unmap = vdpasim_dma_unmap,
.free = vdpasim_free,
};
+static const struct vdpa_config_ops vdpasim_net_batch_config_ops = {
+ .set_vq_address = vdpasim_set_vq_address,
+ .set_vq_num = vdpasim_set_vq_num,
+ .kick_vq = vdpasim_kick_vq,
+ .set_vq_cb = vdpasim_set_vq_cb,
+ .set_vq_ready = vdpasim_set_vq_ready,
+ .get_vq_ready = vdpasim_get_vq_ready,
+ .set_vq_state = vdpasim_set_vq_state,
+ .get_vq_state = vdpasim_get_vq_state,
+ .get_vq_align = vdpasim_get_vq_align,
+ .get_features = vdpasim_get_features,
+ .set_features = vdpasim_set_features,
+ .set_config_cb = vdpasim_set_config_cb,
+ .get_vq_num_max = vdpasim_get_vq_num_max,
+ .get_device_id = vdpasim_get_device_id,
+ .get_vendor_id = vdpasim_get_vendor_id,
+ .get_status = vdpasim_get_status,
+ .set_status = vdpasim_set_status,
+ .get_config = vdpasim_get_config,
+ .set_config = vdpasim_set_config,
+ .get_generation = vdpasim_get_generation,
+ .set_map = vdpasim_set_map,
+ .free = vdpasim_free,
+};
+
static int __init vdpasim_dev_init(void)
{
vdpasim_dev = vdpasim_create();
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index d3688c6afb87..587fbae06182 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -65,6 +65,7 @@ config VHOST_VDPA
tristate "Vhost driver for vDPA-based backend"
depends on EVENTFD
select VHOST
+ select IRQ_BYPASS_MANAGER
depends on VDPA
help
This kernel module can be loaded in host kernel to accelerate
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index eea902b83afe..531a00d703cd 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -73,7 +73,7 @@ enum {
VHOST_NET_FEATURES = VHOST_FEATURES |
(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
- (1ULL << VIRTIO_F_IOMMU_PLATFORM)
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM)
};
enum {
@@ -1615,21 +1615,6 @@ done:
return err;
}
-static int vhost_net_set_backend_features(struct vhost_net *n, u64 features)
-{
- int i;
-
- mutex_lock(&n->dev.mutex);
- for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
- mutex_lock(&n->vqs[i].vq.mutex);
- n->vqs[i].vq.acked_backend_features = features;
- mutex_unlock(&n->vqs[i].vq.mutex);
- }
- mutex_unlock(&n->dev.mutex);
-
- return 0;
-}
-
static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
size_t vhost_hlen, sock_hlen, hdr_len;
@@ -1653,7 +1638,7 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
!vhost_log_access_ok(&n->dev))
goto out_unlock;
- if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
+ if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
if (vhost_init_device_iotlb(&n->dev, true))
goto out_unlock;
}
@@ -1730,7 +1715,8 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
return -EFAULT;
if (features & ~VHOST_NET_BACKEND_FEATURES)
return -EOPNOTSUPP;
- return vhost_net_set_backend_features(n, features);
+ vhost_set_backend_features(&n->dev, features);
+ return 0;
case VHOST_RESET_OWNER:
return vhost_net_reset_owner(n);
case VHOST_SET_OWNER:
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index a54b60d6623f..3fab94f88894 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -27,37 +27,11 @@
#include "vhost.h"
enum {
- VHOST_VDPA_FEATURES =
- (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
- (1ULL << VIRTIO_F_ANY_LAYOUT) |
- (1ULL << VIRTIO_F_VERSION_1) |
- (1ULL << VIRTIO_F_IOMMU_PLATFORM) |
- (1ULL << VIRTIO_F_RING_PACKED) |
- (1ULL << VIRTIO_F_ORDER_PLATFORM) |
- (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
- (1ULL << VIRTIO_RING_F_EVENT_IDX),
-
- VHOST_VDPA_NET_FEATURES = VHOST_VDPA_FEATURES |
- (1ULL << VIRTIO_NET_F_CSUM) |
- (1ULL << VIRTIO_NET_F_GUEST_CSUM) |
- (1ULL << VIRTIO_NET_F_MTU) |
- (1ULL << VIRTIO_NET_F_MAC) |
- (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
- (1ULL << VIRTIO_NET_F_GUEST_TSO6) |
- (1ULL << VIRTIO_NET_F_GUEST_ECN) |
- (1ULL << VIRTIO_NET_F_GUEST_UFO) |
- (1ULL << VIRTIO_NET_F_HOST_TSO4) |
- (1ULL << VIRTIO_NET_F_HOST_TSO6) |
- (1ULL << VIRTIO_NET_F_HOST_ECN) |
- (1ULL << VIRTIO_NET_F_HOST_UFO) |
- (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
- (1ULL << VIRTIO_NET_F_STATUS) |
- (1ULL << VIRTIO_NET_F_SPEED_DUPLEX),
+ VHOST_VDPA_BACKEND_FEATURES =
+ (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) |
+ (1ULL << VHOST_BACKEND_F_IOTLB_BATCH),
};
-/* Currently, only network backend w/o multiqueue is supported. */
-#define VHOST_VDPA_VQ_MAX 2
-
#define VHOST_VDPA_DEV_MAX (1U << MINORBITS)
struct vhost_vdpa {
@@ -73,16 +47,13 @@ struct vhost_vdpa {
int virtio_id;
int minor;
struct eventfd_ctx *config_ctx;
+ int in_batch;
};
static DEFINE_IDA(vhost_vdpa_ida);
static dev_t vhost_vdpa_major;
-static const u64 vhost_vdpa_features[] = {
- [VIRTIO_ID_NET] = VHOST_VDPA_NET_FEATURES,
-};
-
static void handle_vq_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -96,7 +67,7 @@ static void handle_vq_kick(struct vhost_work *work)
static irqreturn_t vhost_vdpa_virtqueue_cb(void *private)
{
struct vhost_virtqueue *vq = private;
- struct eventfd_ctx *call_ctx = vq->call_ctx;
+ struct eventfd_ctx *call_ctx = vq->call_ctx.ctx;
if (call_ctx)
eventfd_signal(call_ctx, 1);
@@ -115,12 +86,45 @@ static irqreturn_t vhost_vdpa_config_cb(void *private)
return IRQ_HANDLED;
}
+static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid)
+{
+ struct vhost_virtqueue *vq = &v->vqs[qid];
+ const struct vdpa_config_ops *ops = v->vdpa->config;
+ struct vdpa_device *vdpa = v->vdpa;
+ int ret, irq;
+
+ if (!ops->get_vq_irq)
+ return;
+
+ irq = ops->get_vq_irq(vdpa, qid);
+ spin_lock(&vq->call_ctx.ctx_lock);
+ irq_bypass_unregister_producer(&vq->call_ctx.producer);
+ if (!vq->call_ctx.ctx || irq < 0) {
+ spin_unlock(&vq->call_ctx.ctx_lock);
+ return;
+ }
+
+ vq->call_ctx.producer.token = vq->call_ctx.ctx;
+ vq->call_ctx.producer.irq = irq;
+ ret = irq_bypass_register_producer(&vq->call_ctx.producer);
+ spin_unlock(&vq->call_ctx.ctx_lock);
+}
+
+static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid)
+{
+ struct vhost_virtqueue *vq = &v->vqs[qid];
+
+ spin_lock(&vq->call_ctx.ctx_lock);
+ irq_bypass_unregister_producer(&vq->call_ctx.producer);
+ spin_unlock(&vq->call_ctx.ctx_lock);
+}
+
static void vhost_vdpa_reset(struct vhost_vdpa *v)
{
struct vdpa_device *vdpa = v->vdpa;
- const struct vdpa_config_ops *ops = vdpa->config;
- ops->set_status(vdpa, 0);
+ vdpa_reset(vdpa);
+ v->in_batch = 0;
}
static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp)
@@ -155,11 +159,15 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
{
struct vdpa_device *vdpa = v->vdpa;
const struct vdpa_config_ops *ops = vdpa->config;
- u8 status;
+ u8 status, status_old;
+ int nvqs = v->nvqs;
+ u16 i;
if (copy_from_user(&status, statusp, sizeof(status)))
return -EFAULT;
+ status_old = ops->get_status(vdpa);
+
/*
* Userspace shouldn't remove status bits unless reset the
* status to 0.
@@ -169,6 +177,14 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
ops->set_status(vdpa, status);
+ if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
+ for (i = 0; i < nvqs; i++)
+ vhost_vdpa_setup_vq_irq(v, i);
+
+ if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK))
+ for (i = 0; i < nvqs; i++)
+ vhost_vdpa_unsetup_vq_irq(v, i);
+
return 0;
}
@@ -196,7 +212,6 @@ static long vhost_vdpa_get_config(struct vhost_vdpa *v,
struct vhost_vdpa_config __user *c)
{
struct vdpa_device *vdpa = v->vdpa;
- const struct vdpa_config_ops *ops = vdpa->config;
struct vhost_vdpa_config config;
unsigned long size = offsetof(struct vhost_vdpa_config, buf);
u8 *buf;
@@ -209,7 +224,7 @@ static long vhost_vdpa_get_config(struct vhost_vdpa *v,
if (!buf)
return -ENOMEM;
- ops->get_config(vdpa, config.off, buf, config.len);
+ vdpa_get_config(vdpa, config.off, buf, config.len);
if (copy_to_user(c->buf, buf, config.len)) {
kvfree(buf);
@@ -255,7 +270,6 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
u64 features;
features = ops->get_features(vdpa);
- features &= vhost_vdpa_features[v->virtio_id];
if (copy_to_user(featurep, &features, sizeof(features)))
return -EFAULT;
@@ -279,10 +293,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
if (copy_from_user(&features, featurep, sizeof(features)))
return -EFAULT;
- if (features & ~vhost_vdpa_features[v->virtio_id])
- return -EINVAL;
-
- if (ops->set_features(vdpa, features))
+ if (vdpa_set_features(vdpa, features))
return -EINVAL;
return 0;
@@ -332,14 +343,18 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp)
return 0;
}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
struct vdpa_device *vdpa = v->vdpa;
const struct vdpa_config_ops *ops = vdpa->config;
+ struct vdpa_vq_state vq_state;
struct vdpa_callback cb;
struct vhost_virtqueue *vq;
struct vhost_vring_state s;
+ u64 __user *featurep = argp;
+ u64 features;
u32 idx;
long r;
@@ -353,15 +368,32 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
idx = array_index_nospec(idx, v->nvqs);
vq = &v->vqs[idx];
- if (cmd == VHOST_VDPA_SET_VRING_ENABLE) {
+ switch (cmd) {
+ case VHOST_VDPA_SET_VRING_ENABLE:
if (copy_from_user(&s, argp, sizeof(s)))
return -EFAULT;
ops->set_vq_ready(vdpa, idx, s.num);
return 0;
- }
+ case VHOST_GET_VRING_BASE:
+ r = ops->get_vq_state(v->vdpa, idx, &vq_state);
+ if (r)
+ return r;
- if (cmd == VHOST_GET_VRING_BASE)
- vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx);
+ vq->last_avail_idx = vq_state.avail_index;
+ break;
+ case VHOST_GET_BACKEND_FEATURES:
+ features = VHOST_VDPA_BACKEND_FEATURES;
+ if (copy_to_user(featurep, &features, sizeof(features)))
+ return -EFAULT;
+ return 0;
+ case VHOST_SET_BACKEND_FEATURES:
+ if (copy_from_user(&features, featurep, sizeof(features)))
+ return -EFAULT;
+ if (features & ~VHOST_VDPA_BACKEND_FEATURES)
+ return -EOPNOTSUPP;
+ vhost_set_backend_features(&v->vdev, features);
+ return 0;
+ }
r = vhost_vring_ioctl(&v->vdev, cmd, argp);
if (r)
@@ -377,12 +409,13 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
break;
case VHOST_SET_VRING_BASE:
- if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx))
+ vq_state.avail_index = vq->last_avail_idx;
+ if (ops->set_vq_state(vdpa, idx, &vq_state))
r = -EINVAL;
break;
case VHOST_SET_VRING_CALL:
- if (vq->call_ctx) {
+ if (vq->call_ctx.ctx) {
cb.callback = vhost_vdpa_virtqueue_cb;
cb.private = vq;
} else {
@@ -390,6 +423,7 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
cb.private = NULL;
}
ops->set_vq_cb(vdpa, idx, &cb);
+ vhost_vdpa_setup_vq_irq(v, idx);
break;
case VHOST_SET_VRING_NUM:
@@ -519,13 +553,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,
if (r)
return r;
- if (ops->dma_map)
+ if (ops->dma_map) {
r = ops->dma_map(vdpa, iova, size, pa, perm);
- else if (ops->set_map)
- r = ops->set_map(vdpa, dev->iotlb);
- else
+ } else if (ops->set_map) {
+ if (!v->in_batch)
+ r = ops->set_map(vdpa, dev->iotlb);
+ } else {
r = iommu_map(v->domain, iova, pa, size,
perm_to_iommu_flags(perm));
+ }
return r;
}
@@ -538,12 +574,14 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1);
- if (ops->dma_map)
+ if (ops->dma_map) {
ops->dma_unmap(vdpa, iova, size);
- else if (ops->set_map)
- ops->set_map(vdpa, dev->iotlb);
- else
+ } else if (ops->set_map) {
+ if (!v->in_batch)
+ ops->set_map(vdpa, dev->iotlb);
+ } else {
iommu_unmap(v->domain, iova, size);
+ }
}
static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
@@ -636,6 +674,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *msg)
{
struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev);
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
int r = 0;
r = vhost_dev_check_owner(dev);
@@ -649,6 +689,14 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
case VHOST_IOTLB_INVALIDATE:
vhost_vdpa_unmap(v, msg->iova, msg->size);
break;
+ case VHOST_IOTLB_BATCH_BEGIN:
+ v->in_batch = true;
+ break;
+ case VHOST_IOTLB_BATCH_END:
+ if (v->in_batch && ops->set_map)
+ ops->set_map(vdpa, dev->iotlb);
+ v->in_batch = false;
+ break;
default:
r = -EINVAL;
break;
@@ -765,6 +813,18 @@ err:
return r;
}
+static void vhost_vdpa_clean_irq(struct vhost_vdpa *v)
+{
+ struct vhost_virtqueue *vq;
+ int i;
+
+ for (i = 0; i < v->nvqs; i++) {
+ vq = &v->vqs[i];
+ if (vq->call_ctx.producer.irq)
+ irq_bypass_unregister_producer(&vq->call_ctx.producer);
+ }
+}
+
static int vhost_vdpa_release(struct inode *inode, struct file *filep)
{
struct vhost_vdpa *v = filep->private_data;
@@ -777,6 +837,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)
vhost_vdpa_iotlb_free(v);
vhost_vdpa_free_domain(v);
vhost_vdpa_config_put(v);
+ vhost_vdpa_clean_irq(v);
vhost_dev_cleanup(&v->vdev);
kfree(v->vdev.vqs);
mutex_unlock(&d->mutex);
@@ -872,7 +933,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
{
const struct vdpa_config_ops *ops = vdpa->config;
struct vhost_vdpa *v;
- int minor, nvqs = VHOST_VDPA_VQ_MAX;
+ int minor;
int r;
/* Currently, we only accept the network devices. */
@@ -893,14 +954,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
atomic_set(&v->opened, 0);
v->minor = minor;
v->vdpa = vdpa;
- v->nvqs = nvqs;
+ v->nvqs = vdpa->nvqs;
v->virtio_id = ops->get_device_id(vdpa);
device_initialize(&v->dev);
v->dev.release = vhost_vdpa_release_dev;
v->dev.parent = &vdpa->dev;
v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor);
- v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue),
+ v->vqs = kmalloc_array(v->nvqs, sizeof(struct vhost_virtqueue),
GFP_KERNEL);
if (!v->vqs) {
r = -ENOMEM;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 74d135ee7e26..5857d4eec9d7 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -298,6 +298,13 @@ static void vhost_vq_meta_reset(struct vhost_dev *d)
__vhost_vq_meta_reset(d->vqs[i]);
}
+static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx)
+{
+ call_ctx->ctx = NULL;
+ memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
+ spin_lock_init(&call_ctx->ctx_lock);
+}
+
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
@@ -319,13 +326,13 @@ static void vhost_vq_reset(struct vhost_dev *dev,
vq->log_base = NULL;
vq->error_ctx = NULL;
vq->kick = NULL;
- vq->call_ctx = NULL;
vq->log_ctx = NULL;
vhost_reset_is_le(vq);
vhost_disable_cross_endian(vq);
vq->busyloop_timeout = 0;
vq->umem = NULL;
vq->iotlb = NULL;
+ vhost_vring_call_reset(&vq->call_ctx);
__vhost_vq_meta_reset(vq);
}
@@ -685,8 +692,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
eventfd_ctx_put(dev->vqs[i]->error_ctx);
if (dev->vqs[i]->kick)
fput(dev->vqs[i]->kick);
- if (dev->vqs[i]->call_ctx)
- eventfd_ctx_put(dev->vqs[i]->call_ctx);
+ if (dev->vqs[i]->call_ctx.ctx)
+ eventfd_ctx_put(dev->vqs[i]->call_ctx.ctx);
vhost_vq_reset(dev, dev->vqs[i]);
}
vhost_dev_free_iovecs(dev);
@@ -1405,7 +1412,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
memcpy(newmem, &mem, size);
if (copy_from_user(newmem->regions, m->regions,
- mem.nregions * sizeof *m->regions)) {
+ flex_array_size(newmem, regions, mem.nregions))) {
kvfree(newmem);
return -EFAULT;
}
@@ -1629,7 +1636,10 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
r = PTR_ERR(ctx);
break;
}
- swap(ctx, vq->call_ctx);
+
+ spin_lock(&vq->call_ctx.ctx_lock);
+ swap(ctx, vq->call_ctx.ctx);
+ spin_unlock(&vq->call_ctx.ctx_lock);
break;
case VHOST_SET_VRING_ERR:
if (copy_from_user(&f, argp, sizeof f)) {
@@ -2435,8 +2445,8 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
/* Signal the Guest tell them we used something up. */
- if (vq->call_ctx && vhost_notify(dev, vq))
- eventfd_signal(vq->call_ctx, 1);
+ if (vq->call_ctx.ctx && vhost_notify(dev, vq))
+ eventfd_signal(vq->call_ctx.ctx, 1);
}
EXPORT_SYMBOL_GPL(vhost_signal);
@@ -2576,6 +2586,21 @@ struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
}
EXPORT_SYMBOL_GPL(vhost_dequeue_msg);
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features)
+{
+ struct vhost_virtqueue *vq;
+ int i;
+
+ mutex_lock(&dev->mutex);
+ for (i = 0; i < dev->nvqs; ++i) {
+ vq = dev->vqs[i];
+ mutex_lock(&vq->mutex);
+ vq->acked_backend_features = features;
+ mutex_unlock(&vq->mutex);
+ }
+ mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(vhost_set_backend_features);
static int __init vhost_init(void)
{
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index c8e96a095d3b..9032d3c2a9f4 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -13,6 +13,7 @@
#include <linux/virtio_ring.h>
#include <linux/atomic.h>
#include <linux/vhost_iotlb.h>
+#include <linux/irqbypass.h>
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -60,6 +61,12 @@ enum vhost_uaddr_type {
VHOST_NUM_ADDRS = 3,
};
+struct vhost_vring_call {
+ struct eventfd_ctx *ctx;
+ struct irq_bypass_producer producer;
+ spinlock_t ctx_lock;
+};
+
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
@@ -72,7 +79,7 @@ struct vhost_virtqueue {
vring_used_t __user *used;
const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
struct file *kick;
- struct eventfd_ctx *call_ctx;
+ struct vhost_vring_call call_ctx;
struct eventfd_ctx *error_ctx;
struct eventfd_ctx *log_ctx;
@@ -207,6 +214,8 @@ void vhost_enqueue_msg(struct vhost_dev *dev,
struct vhost_msg_node *node);
struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
struct list_head *head);
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features);
+
__poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev,
poll_table *wait);
ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 8be02f333b7a..31cc97f2f515 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -398,12 +398,9 @@ static inline s64 towards_target(struct virtio_balloon *vb)
s64 target;
u32 num_pages;
- virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages,
- &num_pages);
-
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- num_pages = le32_to_cpu((__force __le32)num_pages);
+ virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages,
+ &num_pages);
target = num_pages;
return target - vb->num_pages;
@@ -462,11 +459,8 @@ static void update_balloon_size(struct virtio_balloon *vb)
u32 actual = vb->num_pages;
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- actual = (__force u32)cpu_to_le32(actual);
-
- virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
- &actual);
+ virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual,
+ &actual);
}
static void update_balloon_stats_func(struct work_struct *work)
@@ -579,12 +573,10 @@ static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
{
if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
&vb->config_read_bitmap)) {
- virtio_cread(vb->vdev, struct virtio_balloon_config,
- free_page_hint_cmd_id,
- &vb->cmd_id_received_cache);
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache);
+ virtio_cread_le(vb->vdev, struct virtio_balloon_config,
+ free_page_hint_cmd_id,
+ &vb->cmd_id_received_cache);
}
return vb->cmd_id_received_cache;
@@ -600,7 +592,7 @@ static int send_cmd_id_start(struct virtio_balloon *vb)
while (virtqueue_get_buf(vq, &unused))
;
- vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
+ vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
virtio_balloon_cmd_id_received(vb));
sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
@@ -987,8 +979,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
if (!want_init_on_free())
memset(&poison_val, PAGE_POISON, sizeof(poison_val));
- virtio_cwrite(vb->vdev, struct virtio_balloon_config,
- poison_val, &poison_val);
+ virtio_cwrite_le(vb->vdev, struct virtio_balloon_config,
+ poison_val, &poison_val);
}
vb->pr_dev_info.report = virtballoon_free_page_report;
@@ -1129,7 +1121,7 @@ static int virtballoon_validate(struct virtio_device *vdev)
else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
- __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
+ __virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
return 0;
}
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index efaf65b0f42d..877b2ea3ed05 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -113,9 +113,9 @@ static u8 virtinput_cfg_select(struct virtio_input *vi,
{
u8 size;
- virtio_cwrite(vi->vdev, struct virtio_input_config, select, &select);
- virtio_cwrite(vi->vdev, struct virtio_input_config, subsel, &subsel);
- virtio_cread(vi->vdev, struct virtio_input_config, size, &size);
+ virtio_cwrite_le(vi->vdev, struct virtio_input_config, select, &select);
+ virtio_cwrite_le(vi->vdev, struct virtio_input_config, subsel, &subsel);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, size, &size);
return size;
}
@@ -158,11 +158,11 @@ static void virtinput_cfg_abs(struct virtio_input *vi, int abs)
u32 mi, ma, re, fu, fl;
virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.res, &re);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.res, &re);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
input_set_abs_params(vi->idev, abs, mi, ma, fu, fl);
input_abs_set_res(vi->idev, abs, re);
}
@@ -244,14 +244,14 @@ static int virtinput_probe(struct virtio_device *vdev)
size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0);
if (size >= sizeof(struct virtio_input_devids)) {
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.bustype, &vi->idev->id.bustype);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.vendor, &vi->idev->id.vendor);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.product, &vi->idev->id.product);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.version, &vi->idev->id.version);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.bustype, &vi->idev->id.bustype);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.vendor, &vi->idev->id.vendor);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.product, &vi->idev->id.product);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.version, &vi->idev->id.version);
} else {
vi->idev->id.bustype = BUS_VIRTUAL;
}
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index f26f5f64ae82..c08512fcea90 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -1530,21 +1530,21 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm)
uint64_t new_plugged_size, usable_region_size, end_addr;
/* the plugged_size is just a reflection of what _we_ did previously */
- virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
- &new_plugged_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+ &new_plugged_size);
if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size))
vm->plugged_size = new_plugged_size;
/* calculate the last usable memory block id */
- virtio_cread(vm->vdev, struct virtio_mem_config,
- usable_region_size, &usable_region_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config,
+ usable_region_size, &usable_region_size);
end_addr = vm->addr + usable_region_size;
end_addr = min(end_addr, phys_limit);
vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1;
/* see if there is a request to change the size */
- virtio_cread(vm->vdev, struct virtio_mem_config, requested_size,
- &vm->requested_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size,
+ &vm->requested_size);
dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size);
dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size);
@@ -1677,16 +1677,16 @@ static int virtio_mem_init(struct virtio_mem *vm)
}
/* Fetch all properties that can't change. */
- virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
- &vm->plugged_size);
- virtio_cread(vm->vdev, struct virtio_mem_config, block_size,
- &vm->device_block_size);
- virtio_cread(vm->vdev, struct virtio_mem_config, node_id,
- &node_id);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+ &vm->plugged_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
+ &vm->device_block_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
+ &node_id);
vm->nid = virtio_mem_translate_node_id(vm, node_id);
- virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
- virtio_cread(vm->vdev, struct virtio_mem_config, region_size,
- &vm->region_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
+ &vm->region_size);
/*
* We always hotplug memory in memory block granularity. This way,
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index db93cedd262f..9bdc6f68221f 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -481,6 +481,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
* @dev: the pci device
* @cfg_type: the VIRTIO_PCI_CAP_* value we seek
* @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ * @bars: the bitmask of BARs
*
* Returns offset of the capability, or 0.
*/
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index a2de775801af..becc77697960 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -240,7 +240,7 @@ static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
static bool vring_use_dma_api(struct virtio_device *vdev)
{
- if (!virtio_has_iommu_quirk(vdev))
+ if (!virtio_has_dma_quirk(vdev))
return true;
/* Otherwise, we are left to guess. */
@@ -1960,6 +1960,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
+ if (unlikely(vq->broken))
+ return false;
+
virtio_mb(vq->weak_barriers);
return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) :
virtqueue_poll_split(_vq, last_used_idx);
@@ -2225,7 +2228,7 @@ void vring_transport_features(struct virtio_device *vdev)
break;
case VIRTIO_F_VERSION_1:
break;
- case VIRTIO_F_IOMMU_PLATFORM:
+ case VIRTIO_F_ACCESS_PLATFORM:
break;
case VIRTIO_F_RING_PACKED:
break;
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index c30eb55030be..4a9ddb44b2a7 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -57,9 +57,8 @@ static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset,
void *buf, unsigned len)
{
struct vdpa_device *vdpa = vd_get_vdpa(vdev);
- const struct vdpa_config_ops *ops = vdpa->config;
- ops->get_config(vdpa, offset, buf, len);
+ vdpa_get_config(vdpa, offset, buf, len);
}
static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
@@ -101,9 +100,8 @@ static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
static void virtio_vdpa_reset(struct virtio_device *vdev)
{
struct vdpa_device *vdpa = vd_get_vdpa(vdev);
- const struct vdpa_config_ops *ops = vdpa->config;
- return ops->set_status(vdpa, 0);
+ vdpa_reset(vdpa);
}
static bool virtio_vdpa_notify(struct virtqueue *vq)
@@ -294,12 +292,11 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
{
struct vdpa_device *vdpa = vd_get_vdpa(vdev);
- const struct vdpa_config_ops *ops = vdpa->config;
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
- return ops->set_features(vdpa, vdev->features);
+ return vdpa_set_features(vdpa, vdev->features);
}
static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 4c4ef5d69298..104f35de5270 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -606,8 +606,8 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
unsigned int i;
int ret = 0;
- virtio_cread(vdev, struct virtio_fs_config, num_request_queues,
- &fs->num_request_queues);
+ virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues,
+ &fs->num_request_queues);
if (fs->num_request_queues == 0)
return -EINVAL;
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 239db794357c..eae0bfd87d91 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -28,17 +28,28 @@ struct vdpa_notification_area {
};
/**
+ * vDPA vq_state definition
+ * @avail_index: available index
+ */
+struct vdpa_vq_state {
+ u16 avail_index;
+};
+
+/**
* vDPA device - representation of a vDPA device
* @dev: underlying device
* @dma_dev: the actual device that is performing DMA
* @config: the configuration ops for this device.
* @index: device index
+ * @features_valid: were features initialized? for legacy guests
*/
struct vdpa_device {
struct device dev;
struct device *dma_dev;
const struct vdpa_config_ops *config;
unsigned int index;
+ bool features_valid;
+ int nvqs;
};
/**
@@ -77,16 +88,22 @@ struct vdpa_device {
* @set_vq_state: Set the state for a virtqueue
* @vdev: vdpa device
* @idx: virtqueue index
- * @state: virtqueue state (last_avail_idx)
+ * @state: pointer to set virtqueue state (last_avail_idx)
* Returns integer: success (0) or error (< 0)
* @get_vq_state: Get the state for a virtqueue
* @vdev: vdpa device
* @idx: virtqueue index
- * Returns virtqueue state (last_avail_idx)
+ * @state: pointer to returned state (last_avail_idx)
* @get_vq_notification: Get the notification area for a virtqueue
* @vdev: vdpa device
* @idx: virtqueue index
* Returns the notifcation area
+ * @get_vq_irq: Get the irq number of a virtqueue (optional,
+ * but must implemented if require vq irq offloading)
+ * @vdev: vdpa device
+ * @idx: virtqueue index
+ * Returns int: irq number of a virtqueue,
+ * negative number if no irq assigned.
* @get_vq_align: Get the virtqueue align requirement
* for the device
* @vdev: vdpa device
@@ -174,10 +191,14 @@ struct vdpa_config_ops {
struct vdpa_callback *cb);
void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready);
bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
- int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state);
- u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
+ int (*set_vq_state)(struct vdpa_device *vdev, u16 idx,
+ const struct vdpa_vq_state *state);
+ int (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
+ struct vdpa_vq_state *state);
struct vdpa_notification_area
(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
+ /* vq irq is not expected to be changed once DRIVER_OK is set */
+ int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx);
/* Device ops */
u32 (*get_vq_align)(struct vdpa_device *vdev);
@@ -208,11 +229,12 @@ struct vdpa_config_ops {
struct vdpa_device *__vdpa_alloc_device(struct device *parent,
const struct vdpa_config_ops *config,
+ int nvqs,
size_t size);
-#define vdpa_alloc_device(dev_struct, member, parent, config) \
+#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \
container_of(__vdpa_alloc_device( \
- parent, config, \
+ parent, config, nvqs, \
sizeof(dev_struct) + \
BUILD_BUG_ON_ZERO(offsetof( \
dev_struct, member))), \
@@ -266,4 +288,36 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
{
return vdev->dma_dev;
}
+
+static inline void vdpa_reset(struct vdpa_device *vdev)
+{
+ const struct vdpa_config_ops *ops = vdev->config;
+
+ vdev->features_valid = false;
+ ops->set_status(vdev, 0);
+}
+
+static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
+{
+ const struct vdpa_config_ops *ops = vdev->config;
+
+ vdev->features_valid = true;
+ return ops->set_features(vdev, features);
+}
+
+
+static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
+ void *buf, unsigned int len)
+{
+ const struct vdpa_config_ops *ops = vdev->config;
+
+ /*
+ * 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);
+}
+
#endif /* _LINUX_VDPA_H */
diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h
index 5d2d3124ca3d..ea722479510c 100644
--- a/include/linux/virtio_caif.h
+++ b/include/linux/virtio_caif.h
@@ -11,9 +11,9 @@
#include <linux/types.h>
struct virtio_caif_transf_config {
- u16 headroom;
- u16 tailroom;
- u32 mtu;
+ __virtio16 headroom;
+ __virtio16 tailroom;
+ __virtio32 mtu;
u8 reserved[4];
};
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index bb4cc4910750..8fe857e27ef3 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -6,6 +6,7 @@
#include <linux/bug.h>
#include <linux/virtio.h>
#include <linux/virtio_byteorder.h>
+#include <linux/compiler_types.h>
#include <uapi/linux/virtio_config.h>
struct irq_affinity;
@@ -162,16 +163,16 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
}
/**
- * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * virtio_has_dma_quirk - determine whether this device has the DMA quirk
* @vdev: the device
*/
-static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev)
{
/*
* Note the reverse polarity of the quirk feature (compared to most
* other features), this is for compatibility with legacy systems.
*/
- return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+ return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM);
}
static inline
@@ -287,70 +288,133 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
}
+#define virtio_to_cpu(vdev, x) \
+ _Generic((x), \
+ __u8: (x), \
+ __virtio16: virtio16_to_cpu((vdev), (x)), \
+ __virtio32: virtio32_to_cpu((vdev), (x)), \
+ __virtio64: virtio64_to_cpu((vdev), (x)) \
+ )
+
+#define cpu_to_virtio(vdev, x, m) \
+ _Generic((m), \
+ __u8: (x), \
+ __virtio16: cpu_to_virtio16((vdev), (x)), \
+ __virtio32: cpu_to_virtio32((vdev), (x)), \
+ __virtio64: cpu_to_virtio64((vdev), (x)) \
+ )
+
+#define __virtio_native_type(structname, member) \
+ typeof(virtio_to_cpu(NULL, ((structname*)0)->member))
+
/* Config space accessors. */
#define virtio_cread(vdev, structname, member, ptr) \
do { \
+ typeof(((structname*)0)->member) virtio_cread_v; \
+ \
might_sleep(); \
- /* Must match the member's type, and be integer */ \
- if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
- (*ptr) = 1; \
+ /* Sanity check: must match the member's type */ \
+ typecheck(typeof(virtio_to_cpu((vdev), virtio_cread_v)), *(ptr)); \
\
- switch (sizeof(*ptr)) { \
+ switch (sizeof(virtio_cread_v)) { \
case 1: \
- *(ptr) = virtio_cread8(vdev, \
- offsetof(structname, member)); \
- break; \
case 2: \
- *(ptr) = virtio_cread16(vdev, \
- offsetof(structname, member)); \
- break; \
case 4: \
- *(ptr) = virtio_cread32(vdev, \
- offsetof(structname, member)); \
- break; \
- case 8: \
- *(ptr) = virtio_cread64(vdev, \
- offsetof(structname, member)); \
+ vdev->config->get((vdev), \
+ offsetof(structname, member), \
+ &virtio_cread_v, \
+ sizeof(virtio_cread_v)); \
break; \
default: \
- BUG(); \
+ __virtio_cread_many((vdev), \
+ offsetof(structname, member), \
+ &virtio_cread_v, \
+ 1, \
+ sizeof(virtio_cread_v)); \
+ break; \
} \
+ *(ptr) = virtio_to_cpu(vdev, virtio_cread_v); \
} while(0)
/* Config space accessors. */
#define virtio_cwrite(vdev, structname, member, ptr) \
do { \
+ typeof(((structname*)0)->member) virtio_cwrite_v = \
+ cpu_to_virtio(vdev, *(ptr), ((structname*)0)->member); \
+ \
+ might_sleep(); \
+ /* Sanity check: must match the member's type */ \
+ typecheck(typeof(virtio_to_cpu((vdev), virtio_cwrite_v)), *(ptr)); \
+ \
+ vdev->config->set((vdev), offsetof(structname, member), \
+ &virtio_cwrite_v, \
+ sizeof(virtio_cwrite_v)); \
+ } while(0)
+
+/*
+ * Nothing virtio-specific about these, but let's worry about generalizing
+ * these later.
+ */
+#define virtio_le_to_cpu(x) \
+ _Generic((x), \
+ __u8: (u8)(x), \
+ __le16: (u16)le16_to_cpu(x), \
+ __le32: (u32)le32_to_cpu(x), \
+ __le64: (u64)le64_to_cpu(x) \
+ )
+
+#define virtio_cpu_to_le(x, m) \
+ _Generic((m), \
+ __u8: (x), \
+ __le16: cpu_to_le16(x), \
+ __le32: cpu_to_le32(x), \
+ __le64: cpu_to_le64(x) \
+ )
+
+/* LE (e.g. modern) Config space accessors. */
+#define virtio_cread_le(vdev, structname, member, ptr) \
+ do { \
+ typeof(((structname*)0)->member) virtio_cread_v; \
+ \
might_sleep(); \
- /* Must match the member's type, and be integer */ \
- if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
- BUG_ON((*ptr) == 1); \
+ /* Sanity check: must match the member's type */ \
+ typecheck(typeof(virtio_le_to_cpu(virtio_cread_v)), *(ptr)); \
\
- switch (sizeof(*ptr)) { \
+ switch (sizeof(virtio_cread_v)) { \
case 1: \
- virtio_cwrite8(vdev, \
- offsetof(structname, member), \
- *(ptr)); \
- break; \
case 2: \
- virtio_cwrite16(vdev, \
- offsetof(structname, member), \
- *(ptr)); \
- break; \
case 4: \
- virtio_cwrite32(vdev, \
- offsetof(structname, member), \
- *(ptr)); \
- break; \
- case 8: \
- virtio_cwrite64(vdev, \
- offsetof(structname, member), \
- *(ptr)); \
+ vdev->config->get((vdev), \
+ offsetof(structname, member), \
+ &virtio_cread_v, \
+ sizeof(virtio_cread_v)); \
break; \
default: \
- BUG(); \
+ __virtio_cread_many((vdev), \
+ offsetof(structname, member), \
+ &virtio_cread_v, \
+ 1, \
+ sizeof(virtio_cread_v)); \
+ break; \
} \
+ *(ptr) = virtio_le_to_cpu(virtio_cread_v); \
+ } while(0)
+
+#define virtio_cwrite_le(vdev, structname, member, ptr) \
+ do { \
+ typeof(((structname*)0)->member) virtio_cwrite_v = \
+ virtio_cpu_to_le(*(ptr), ((structname*)0)->member); \
+ \
+ might_sleep(); \
+ /* Sanity check: must match the member's type */ \
+ typecheck(typeof(virtio_le_to_cpu(virtio_cwrite_v)), *(ptr)); \
+ \
+ vdev->config->set((vdev), offsetof(structname, member), \
+ &virtio_cwrite_v, \
+ sizeof(virtio_cwrite_v)); \
} while(0)
+
/* Read @count fields, @bytes each. */
static inline void __virtio_cread_many(struct virtio_device *vdev,
unsigned int offset,
@@ -399,53 +463,60 @@ static inline void virtio_cwrite8(struct virtio_device *vdev,
static inline u16 virtio_cread16(struct virtio_device *vdev,
unsigned int offset)
{
- u16 ret;
+ __virtio16 ret;
might_sleep();
vdev->config->get(vdev, offset, &ret, sizeof(ret));
- return virtio16_to_cpu(vdev, (__force __virtio16)ret);
+ return virtio16_to_cpu(vdev, ret);
}
static inline void virtio_cwrite16(struct virtio_device *vdev,
unsigned int offset, u16 val)
{
+ __virtio16 v;
+
might_sleep();
- val = (__force u16)cpu_to_virtio16(vdev, val);
- vdev->config->set(vdev, offset, &val, sizeof(val));
+ v = cpu_to_virtio16(vdev, val);
+ vdev->config->set(vdev, offset, &v, sizeof(v));
}
static inline u32 virtio_cread32(struct virtio_device *vdev,
unsigned int offset)
{
- u32 ret;
+ __virtio32 ret;
might_sleep();
vdev->config->get(vdev, offset, &ret, sizeof(ret));
- return virtio32_to_cpu(vdev, (__force __virtio32)ret);
+ return virtio32_to_cpu(vdev, ret);
}
static inline void virtio_cwrite32(struct virtio_device *vdev,
unsigned int offset, u32 val)
{
+ __virtio32 v;
+
might_sleep();
- val = (__force u32)cpu_to_virtio32(vdev, val);
- vdev->config->set(vdev, offset, &val, sizeof(val));
+ v = cpu_to_virtio32(vdev, val);
+ vdev->config->set(vdev, offset, &v, sizeof(v));
}
static inline u64 virtio_cread64(struct virtio_device *vdev,
unsigned int offset)
{
- u64 ret;
+ __virtio64 ret;
+
__virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret));
- return virtio64_to_cpu(vdev, (__force __virtio64)ret);
+ return virtio64_to_cpu(vdev, ret);
}
static inline void virtio_cwrite64(struct virtio_device *vdev,
unsigned int offset, u64 val)
{
+ __virtio64 v;
+
might_sleep();
- val = (__force u64)cpu_to_virtio64(vdev, val);
- vdev->config->set(vdev, offset, &val, sizeof(val));
+ v = cpu_to_virtio64(vdev, val);
+ vdev->config->set(vdev, offset, &v, sizeof(v));
}
/* Conditional config space accessors. */
@@ -459,4 +530,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
_r; \
})
+/* Conditional config space accessors. */
+#define virtio_cread_le_feature(vdev, fbit, structname, member, ptr) \
+ ({ \
+ int _r = 0; \
+ if (!virtio_has_feature(vdev, fbit)) \
+ _r = -ENOENT; \
+ else \
+ virtio_cread_le((vdev), structname, member, ptr); \
+ _r; \
+ })
#endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 3dc70adfe5f5..b485b13fa50b 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -46,16 +46,15 @@ static inline void virtio_wmb(bool weak_barriers)
dma_wmb();
}
-static inline void virtio_store_mb(bool weak_barriers,
- __virtio16 *p, __virtio16 v)
-{
- if (weak_barriers) {
- virt_store_mb(*p, v);
- } else {
- WRITE_ONCE(*p, v);
- mb();
- }
-}
+#define virtio_store_mb(weak_barriers, p, v) \
+do { \
+ if (weak_barriers) { \
+ virt_store_mb(*p, v); \
+ } else { \
+ WRITE_ONCE(*p, v); \
+ mb(); \
+ } \
+} while (0) \
struct virtio_device;
struct virtqueue;
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 0c2349612e77..75232185324a 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -91,6 +91,8 @@
/* Use message type V2 */
#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+/* IOTLB can accept batching hints */
+#define VHOST_BACKEND_F_IOTLB_BATCH 0x2
#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 669457ce5c48..9a269a88a6ff 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -60,6 +60,17 @@ struct vhost_iotlb_msg {
#define VHOST_IOTLB_UPDATE 2
#define VHOST_IOTLB_INVALIDATE 3
#define VHOST_IOTLB_ACCESS_FAIL 4
+/*
+ * VHOST_IOTLB_BATCH_BEGIN and VHOST_IOTLB_BATCH_END allow modifying
+ * multiple mappings in one go: beginning with
+ * VHOST_IOTLB_BATCH_BEGIN, followed by any number of
+ * VHOST_IOTLB_UPDATE messages, and ending with VHOST_IOTLB_BATCH_END.
+ * When one of these two values is used as the message type, the rest
+ * of the fields in the message are ignored. There's no guarantee that
+ * these changes take place automatically in the device.
+ */
+#define VHOST_IOTLB_BATCH_BEGIN 5
+#define VHOST_IOTLB_BATCH_END 6
__u8 type;
};
diff --git a/include/uapi/linux/virtio_9p.h b/include/uapi/linux/virtio_9p.h
index 277c4ad44e84..441047432258 100644
--- a/include/uapi/linux/virtio_9p.h
+++ b/include/uapi/linux/virtio_9p.h
@@ -25,7 +25,7 @@
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE. */
-#include <linux/types.h>
+#include <linux/virtio_types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
@@ -36,7 +36,7 @@
struct virtio_9p_config {
/* length of the tag name */
- __u16 tag_len;
+ __virtio16 tag_len;
/* non-NULL terminated tag name */
__u8 tag[0];
} __attribute__((packed));
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index dc3e656470dd..ddaa45e723c4 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -45,20 +45,20 @@
#define VIRTIO_BALLOON_CMD_ID_DONE 1
struct virtio_balloon_config {
/* Number of pages host wants Guest to give up. */
- __u32 num_pages;
+ __le32 num_pages;
/* Number of pages we've actually got in balloon. */
- __u32 actual;
+ __le32 actual;
/*
* Free page hint command id, readonly by guest.
* Was previously named free_page_report_cmd_id so we
* need to carry that name for legacy support.
*/
union {
- __u32 free_page_hint_cmd_id;
- __u32 free_page_report_cmd_id; /* deprecated */
+ __le32 free_page_hint_cmd_id;
+ __le32 free_page_report_cmd_id; /* deprecated */
};
/* Stores PAGE_POISON if page poisoning is in use */
- __u32 poison_val;
+ __le32 poison_val;
};
#define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 0f99d7b49ede..d888f013d9ff 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -57,20 +57,20 @@
struct virtio_blk_config {
/* The capacity (in 512-byte sectors). */
- __u64 capacity;
+ __virtio64 capacity;
/* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */
- __u32 size_max;
+ __virtio32 size_max;
/* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */
- __u32 seg_max;
+ __virtio32 seg_max;
/* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */
struct virtio_blk_geometry {
- __u16 cylinders;
+ __virtio16 cylinders;
__u8 heads;
__u8 sectors;
} geometry;
/* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
- __u32 blk_size;
+ __virtio32 blk_size;
/* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY */
/* exponent for physical block per logical block. */
@@ -78,42 +78,42 @@ struct virtio_blk_config {
/* alignment offset in logical blocks. */
__u8 alignment_offset;
/* minimum I/O size without performance penalty in logical blocks. */
- __u16 min_io_size;
+ __virtio16 min_io_size;
/* optimal sustained I/O size in logical blocks. */
- __u32 opt_io_size;
+ __virtio32 opt_io_size;
/* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */
__u8 wce;
__u8 unused;
/* number of vqs, only available when VIRTIO_BLK_F_MQ is set */
- __u16 num_queues;
+ __virtio16 num_queues;
/* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */
/*
* The maximum discard sectors (in 512-byte sectors) for
* one segment.
*/
- __u32 max_discard_sectors;
+ __virtio32 max_discard_sectors;
/*
* The maximum number of discard segments in a
* discard command.
*/
- __u32 max_discard_seg;
+ __virtio32 max_discard_seg;
/* Discard commands must be aligned to this number of sectors. */
- __u32 discard_sector_alignment;
+ __virtio32 discard_sector_alignment;
/* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */
/*
* The maximum number of write zeroes sectors (in 512-byte sectors) in
* one segment.
*/
- __u32 max_write_zeroes_sectors;
+ __virtio32 max_write_zeroes_sectors;
/*
* The maximum number of segments in a write zeroes
* command.
*/
- __u32 max_write_zeroes_seg;
+ __virtio32 max_write_zeroes_seg;
/*
* Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the
* deallocation of one or more of the sectors.
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index ff8e7dc9d4dd..b5eda06f0d57 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -67,13 +67,17 @@
#define VIRTIO_F_VERSION_1 32
/*
- * If clear - device has the IOMMU bypass quirk feature.
- * If set - use platform tools to detect the IOMMU.
+ * If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature.
+ * If set - use platform DMA tools to access the memory.
*
* Note the reverse polarity (compared to most other features),
* this is for compatibility with legacy systems.
*/
-#define VIRTIO_F_IOMMU_PLATFORM 33
+#define VIRTIO_F_ACCESS_PLATFORM 33
+#ifndef __KERNEL__
+/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */
+#define VIRTIO_F_IOMMU_PLATFORM VIRTIO_F_ACCESS_PLATFORM
+#endif /* __KERNEL__ */
/* This feature indicates support for the packed virtqueue layout. */
#define VIRTIO_F_RING_PACKED 34
diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h
index b7fb108c9310..7e6ec2ff0560 100644
--- a/include/uapi/linux/virtio_console.h
+++ b/include/uapi/linux/virtio_console.h
@@ -45,13 +45,13 @@
struct virtio_console_config {
/* colums of the screens */
- __u16 cols;
+ __virtio16 cols;
/* rows of the screens */
- __u16 rows;
+ __virtio16 rows;
/* max. number of ports this device can hold */
- __u32 max_nr_ports;
+ __virtio32 max_nr_ports;
/* emergency write register */
- __u32 emerg_wr;
+ __virtio32 emerg_wr;
} __attribute__((packed));
/*
diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h
index 50cdc8aebfcf..a03932f10565 100644
--- a/include/uapi/linux/virtio_crypto.h
+++ b/include/uapi/linux/virtio_crypto.h
@@ -414,33 +414,33 @@ struct virtio_crypto_op_data_req {
struct virtio_crypto_config {
/* See VIRTIO_CRYPTO_OP_* above */
- __u32 status;
+ __le32 status;
/*
* Maximum number of data queue
*/
- __u32 max_dataqueues;
+ __le32 max_dataqueues;
/*
* Specifies the services mask which the device support,
* see VIRTIO_CRYPTO_SERVICE_* above
*/
- __u32 crypto_services;
+ __le32 crypto_services;
/* Detailed algorithms mask */
- __u32 cipher_algo_l;
- __u32 cipher_algo_h;
- __u32 hash_algo;
- __u32 mac_algo_l;
- __u32 mac_algo_h;
- __u32 aead_algo;
+ __le32 cipher_algo_l;
+ __le32 cipher_algo_h;
+ __le32 hash_algo;
+ __le32 mac_algo_l;
+ __le32 mac_algo_h;
+ __le32 aead_algo;
/* Maximum length of cipher key */
- __u32 max_cipher_key_len;
+ __le32 max_cipher_key_len;
/* Maximum length of authenticated key */
- __u32 max_auth_key_len;
- __u32 reserve;
+ __le32 max_auth_key_len;
+ __le32 reserve;
/* Maximum size of each crypto request's content */
- __u64 max_size;
+ __le64 max_size;
};
struct virtio_crypto_inhdr {
diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h
index b02eb2ac3d99..3056b6e9f8ce 100644
--- a/include/uapi/linux/virtio_fs.h
+++ b/include/uapi/linux/virtio_fs.h
@@ -13,7 +13,7 @@ struct virtio_fs_config {
__u8 tag[36];
/* Number of request queues */
- __u32 num_request_queues;
+ __le32 num_request_queues;
} __attribute__((packed));
#endif /* _UAPI_LINUX_VIRTIO_FS_H */
diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h
index 0c85914d9369..ccbd174ef321 100644
--- a/include/uapi/linux/virtio_gpu.h
+++ b/include/uapi/linux/virtio_gpu.h
@@ -320,10 +320,10 @@ struct virtio_gpu_resp_edid {
#define VIRTIO_GPU_EVENT_DISPLAY (1 << 0)
struct virtio_gpu_config {
- __u32 events_read;
- __u32 events_clear;
- __u32 num_scanouts;
- __u32 num_capsets;
+ __le32 events_read;
+ __le32 events_clear;
+ __le32 num_scanouts;
+ __le32 num_capsets;
};
/* simple formats for fbcon/X use */
diff --git a/include/uapi/linux/virtio_input.h b/include/uapi/linux/virtio_input.h
index a7fe5c8fb135..52084b1fb965 100644
--- a/include/uapi/linux/virtio_input.h
+++ b/include/uapi/linux/virtio_input.h
@@ -40,18 +40,18 @@ enum virtio_input_config_select {
};
struct virtio_input_absinfo {
- __u32 min;
- __u32 max;
- __u32 fuzz;
- __u32 flat;
- __u32 res;
+ __le32 min;
+ __le32 max;
+ __le32 fuzz;
+ __le32 flat;
+ __le32 res;
};
struct virtio_input_devids {
- __u16 bustype;
- __u16 vendor;
- __u16 product;
- __u16 version;
+ __le16 bustype;
+ __le16 vendor;
+ __le16 product;
+ __le16 version;
};
struct virtio_input_config {
diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h
index 48e3c29223b5..237e36a280cb 100644
--- a/include/uapi/linux/virtio_iommu.h
+++ b/include/uapi/linux/virtio_iommu.h
@@ -18,24 +18,24 @@
#define VIRTIO_IOMMU_F_MMIO 5
struct virtio_iommu_range_64 {
- __u64 start;
- __u64 end;
+ __le64 start;
+ __le64 end;
};
struct virtio_iommu_range_32 {
- __u32 start;
- __u32 end;
+ __le32 start;
+ __le32 end;
};
struct virtio_iommu_config {
/* Supported page sizes */
- __u64 page_size_mask;
+ __le64 page_size_mask;
/* Supported IOVA range */
struct virtio_iommu_range_64 input_range;
/* Max domain ID size */
struct virtio_iommu_range_32 domain_range;
/* Probe buffer size */
- __u32 probe_size;
+ __le32 probe_size;
};
/* Request types */
diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h
index a9ffe041843c..70e01c687d5e 100644
--- a/include/uapi/linux/virtio_mem.h
+++ b/include/uapi/linux/virtio_mem.h
@@ -185,27 +185,27 @@ struct virtio_mem_resp {
struct virtio_mem_config {
/* Block size and alignment. Cannot change. */
- __u64 block_size;
+ __le64 block_size;
/* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */
- __u16 node_id;
+ __le16 node_id;
__u8 padding[6];
/* Start address of the memory region. Cannot change. */
- __u64 addr;
+ __le64 addr;
/* Region size (maximum). Cannot change. */
- __u64 region_size;
+ __le64 region_size;
/*
* Currently usable region size. Can grow up to region_size. Can
* shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config
* update will be sent).
*/
- __u64 usable_region_size;
+ __le64 usable_region_size;
/*
* Currently used size. Changes due to plug/unplug requests, but no
* config updates will be sent.
*/
- __u64 plugged_size;
+ __le64 plugged_size;
/* Requested size. New plug requests cannot exceed it. Can change. */
- __u64 requested_size;
+ __le64 requested_size;
};
#endif /* _LINUX_VIRTIO_MEM_H */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 19d23e5baa4e..3f55a4215f11 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -87,19 +87,19 @@ struct virtio_net_config {
/* The config defining mac address (if VIRTIO_NET_F_MAC) */
__u8 mac[ETH_ALEN];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
- __u16 status;
+ __virtio16 status;
/* Maximum number of each of transmit and receive queues;
* see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ.
* Legal values are between 1 and 0x8000
*/
- __u16 max_virtqueue_pairs;
+ __virtio16 max_virtqueue_pairs;
/* Default maximum transmit unit advice */
- __u16 mtu;
+ __virtio16 mtu;
/*
* speed, in units of 1Mb. All values 0 to INT_MAX are legal.
* Any other value stands for unknown.
*/
- __u32 speed;
+ __le32 speed;
/*
* 0x00 - half duplex
* 0x01 - full duplex
diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
index b022787ffb94..d676b3620383 100644
--- a/include/uapi/linux/virtio_pmem.h
+++ b/include/uapi/linux/virtio_pmem.h
@@ -15,8 +15,8 @@
#include <linux/virtio_config.h>
struct virtio_pmem_config {
- __u64 start;
- __u64 size;
+ __le64 start;
+ __le64 size;
};
#define VIRTIO_PMEM_REQ_TYPE_FLUSH 0
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
index cc18ef8825c0..0abaae4027c0 100644
--- a/include/uapi/linux/virtio_scsi.h
+++ b/include/uapi/linux/virtio_scsi.h
@@ -103,16 +103,16 @@ struct virtio_scsi_event {
} __attribute__((packed));
struct virtio_scsi_config {
- __u32 num_queues;
- __u32 seg_max;
- __u32 max_sectors;
- __u32 cmd_per_lun;
- __u32 event_info_size;
- __u32 sense_size;
- __u32 cdb_size;
- __u16 max_channel;
- __u16 max_target;
- __u32 max_lun;
+ __virtio32 num_queues;
+ __virtio32 seg_max;
+ __virtio32 max_sectors;
+ __virtio32 cmd_per_lun;
+ __virtio32 event_info_size;
+ __virtio32 sense_size;
+ __virtio32 cdb_size;
+ __virtio16 max_channel;
+ __virtio16 max_target;
+ __virtio32 max_lun;
} __attribute__((packed));
/* Feature Bits */
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index dbf14c1e2188..f2640e505c4e 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -42,16 +42,16 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
(__virtio_test_bit((dev), feature))
/**
- * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * virtio_has_dma_quirk - determine whether this device has the DMA quirk
* @vdev: the device
*/
-static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev)
{
/*
* Note the reverse polarity of the quirk feature (compared to most
* other features), this is for compatibility with legacy systems.
*/
- return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+ return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM);
}
static inline bool virtio_is_little_endian(struct virtio_device *vdev)
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 28fda42e471b..c9bb3957f58a 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -40,17 +40,21 @@ static int __connect(struct irq_bypass_producer *prod,
if (prod->add_consumer)
ret = prod->add_consumer(prod, cons);
- if (!ret) {
- ret = cons->add_producer(cons, prod);
- if (ret && prod->del_consumer)
- prod->del_consumer(prod, cons);
- }
+ if (ret)
+ goto err_add_consumer;
+
+ ret = cons->add_producer(cons, prod);
+ if (ret)
+ goto err_add_producer;
if (cons->start)
cons->start(cons);
if (prod->start)
prod->start(prod);
-
+err_add_producer:
+ if (prod->del_consumer)
+ prod->del_consumer(prod, cons);
+err_add_consumer:
return ret;
}