mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
}
+ int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
+ {
+ int err = 0;
+
+ mutex_lock(&dev->lb.mutex);
+ if (td)
+ dev->lb.user_td++;
+ if (qp)
+ dev->lb.qps++;
+
+ if (dev->lb.user_td == 2 ||
+ dev->lb.qps == 1) {
+ if (!dev->lb.enabled) {
+ err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
+ dev->lb.enabled = true;
+ }
+ }
+
+ mutex_unlock(&dev->lb.mutex);
+
+ return err;
+ }
+
+ void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
+ {
+ mutex_lock(&dev->lb.mutex);
+ if (td)
+ dev->lb.user_td--;
+ if (qp)
+ dev->lb.qps--;
+
+ if (dev->lb.user_td == 1 &&
+ dev->lb.qps == 0) {
+ if (dev->lb.enabled) {
+ mlx5_nic_vport_update_local_lb(dev->mdev, false);
+ dev->lb.enabled = false;
+ }
+ }
+
+ mutex_unlock(&dev->lb.mutex);
+ }
+
static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
{
int err;
!MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
return err;
- mutex_lock(&dev->lb_mutex);
- dev->user_td++;
-
- if (dev->user_td == 2)
- err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
-
- mutex_unlock(&dev->lb_mutex);
- return err;
+ return mlx5_ib_enable_lb(dev, true, false);
}
static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
!MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
return;
- mutex_lock(&dev->lb_mutex);
- dev->user_td--;
-
- if (dev->user_td < 2)
- mlx5_nic_vport_update_local_lb(dev->mdev, false);
-
- mutex_unlock(&dev->lb_mutex);
+ mlx5_ib_disable_lb(dev, true, false);
}
static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
goto out_mdev;
}
- INIT_LIST_HEAD(&context->vma_private_list);
- mutex_init(&context->vma_private_list_mutex);
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);
context->lib_caps = req.lib_caps;
print_lib_caps(dev, context->lib_caps);
+ if (mlx5_lag_is_active(dev->mdev)) {
+ u8 port = mlx5_core_native_port_num(dev->mdev);
+
+ atomic_set(&context->tx_port_affinity,
+ atomic_add_return(
+ 1, &dev->roce[port].tx_port_affinity));
+ }
+
return &context->ibucontext;
out_mdev:
struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
struct mlx5_bfreg_info *bfregi;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+ /* All umem's must be destroyed before destroying the ucontext. */
+ mutex_lock(&ibcontext->per_mm_list_lock);
+ WARN_ON(!list_empty(&ibcontext->per_mm_list));
+ mutex_unlock(&ibcontext->per_mm_list_lock);
+#endif
+
if (context->devx_uid)
mlx5_ib_devx_destroy(dev, context);
return get_arg(offset) | ((offset >> 16) & 0xff) << 8;
}
-static void mlx5_ib_vma_open(struct vm_area_struct *area)
-{
- /* vma_open is called when a new VMA is created on top of our VMA. This
- * is done through either mremap flow or split_vma (usually due to
- * mlock, madvise, munmap, etc.) We do not support a clone of the VMA,
- * as this VMA is strongly hardware related. Therefore we set the
- * vm_ops of the newly created/cloned VMA to NULL, to prevent it from
- * calling us again and trying to do incorrect actions. We assume that
- * the original VMA size is exactly a single page, and therefore all
- * "splitting" operation will not happen to it.
- */
- area->vm_ops = NULL;
-}
-
-static void mlx5_ib_vma_close(struct vm_area_struct *area)
-{
- struct mlx5_ib_vma_private_data *mlx5_ib_vma_priv_data;
-
- /* It's guaranteed that all VMAs opened on a FD are closed before the
- * file itself is closed, therefore no sync is needed with the regular
- * closing flow. (e.g. mlx5 ib_dealloc_ucontext)
- * However need a sync with accessing the vma as part of
- * mlx5_ib_disassociate_ucontext.
- * The close operation is usually called under mm->mmap_sem except when
- * process is exiting.
- * The exiting case is handled explicitly as part of
- * mlx5_ib_disassociate_ucontext.
- */
- mlx5_ib_vma_priv_data = (struct mlx5_ib_vma_private_data *)area->vm_private_data;
-
- /* setting the vma context pointer to null in the mlx5_ib driver's
- * private data, to protect a race condition in
- * mlx5_ib_disassociate_ucontext().
- */
- mlx5_ib_vma_priv_data->vma = NULL;
- mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
- list_del(&mlx5_ib_vma_priv_data->list);
- mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
- kfree(mlx5_ib_vma_priv_data);
-}
-
-static const struct vm_operations_struct mlx5_ib_vm_ops = {
- .open = mlx5_ib_vma_open,
- .close = mlx5_ib_vma_close
-};
-
-static int mlx5_ib_set_vma_data(struct vm_area_struct *vma,
- struct mlx5_ib_ucontext *ctx)
-{
- struct mlx5_ib_vma_private_data *vma_prv;
- struct list_head *vma_head = &ctx->vma_private_list;
-
- vma_prv = kzalloc(sizeof(*vma_prv), GFP_KERNEL);
- if (!vma_prv)
- return -ENOMEM;
-
- vma_prv->vma = vma;
- vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex;
- vma->vm_private_data = vma_prv;
- vma->vm_ops = &mlx5_ib_vm_ops;
-
- mutex_lock(&ctx->vma_private_list_mutex);
- list_add(&vma_prv->list, vma_head);
- mutex_unlock(&ctx->vma_private_list_mutex);
-
- return 0;
-}
static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
{
- struct vm_area_struct *vma;
- struct mlx5_ib_vma_private_data *vma_private, *n;
- struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
-
- mutex_lock(&context->vma_private_list_mutex);
- list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
- list) {
- vma = vma_private->vma;
- zap_vma_ptes(vma, vma->vm_start, PAGE_SIZE);
- /* context going to be destroyed, should
- * not access ops any more.
- */
- vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
- vma->vm_ops = NULL;
- list_del(&vma_private->list);
- kfree(vma_private);
- }
- mutex_unlock(&context->vma_private_list_mutex);
}
static inline char *mmap_cmd2str(enum mlx5_ib_mmap_cmd cmd)
struct vm_area_struct *vma,
struct mlx5_ib_ucontext *context)
{
- phys_addr_t pfn;
- int err;
-
if (vma->vm_end - vma->vm_start != PAGE_SIZE)
return -EINVAL;
if (!dev->mdev->clock_info_page)
return -EOPNOTSUPP;
- pfn = page_to_pfn(dev->mdev->clock_info_page);
- err = remap_pfn_range(vma, vma->vm_start, pfn, PAGE_SIZE,
- vma->vm_page_prot);
- if (err)
- return err;
-
- return mlx5_ib_set_vma_data(vma, context);
+ return rdma_user_mmap_page(&context->ibucontext, vma,
+ dev->mdev->clock_info_page, PAGE_SIZE);
}
static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
pfn = uar_index2pfn(dev, uar_index);
mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn %pa\n", idx, &pfn);
- vma->vm_page_prot = prot;
- err = io_remap_pfn_range(vma, vma->vm_start, pfn,
- PAGE_SIZE, vma->vm_page_prot);
+ err = rdma_user_mmap_io(&context->ibucontext, vma, pfn, PAGE_SIZE,
+ prot);
if (err) {
mlx5_ib_err(dev,
- "io_remap_pfn_range failed with error=%d, mmap_cmd=%s\n",
+ "rdma_user_mmap_io failed with error=%d, mmap_cmd=%s\n",
err, mmap_cmd2str(cmd));
- err = -EAGAIN;
goto err;
}
- err = mlx5_ib_set_vma_data(vma, context);
- if (err)
- goto err;
-
if (dyn_uar)
bfregi->sys_pages[idx] = uar_index;
return 0;
size_t map_size = vma->vm_end - vma->vm_start;
u32 npages = map_size >> PAGE_SHIFT;
phys_addr_t pfn;
- pgprot_t prot;
if (find_next_zero_bit(mctx->dm_pages, page_idx + npages, page_idx) !=
page_idx + npages)
MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
PAGE_SHIFT) +
page_idx;
- prot = pgprot_writecombine(vma->vm_page_prot);
- vma->vm_page_prot = prot;
-
- if (io_remap_pfn_range(vma, vma->vm_start, pfn, map_size,
- vma->vm_page_prot))
- return -EAGAIN;
-
- return mlx5_ib_set_vma_data(vma, mctx);
+ return rdma_user_mmap_io(context, vma, pfn, map_size,
+ pgprot_writecombine(vma->vm_page_prot));
}
static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
offsetof(typeof(filter), field) -\
sizeof(filter.field))
-static int parse_flow_flow_action(const union ib_flow_spec *ib_spec,
- const struct ib_flow_attr *flow_attr,
- struct mlx5_flow_act *action)
+int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
+ bool is_egress,
+ struct mlx5_flow_act *action)
{
- struct mlx5_ib_flow_action *maction = to_mflow_act(ib_spec->action.act);
switch (maction->ib_action.type) {
case IB_FLOW_ACTION_ESP:
+ if (action->action & (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
+ MLX5_FLOW_CONTEXT_ACTION_DECRYPT))
+ return -EINVAL;
/* Currently only AES_GCM keymat is supported by the driver */
action->esp_id = (uintptr_t)maction->esp_aes_gcm.ctx;
- action->action |= flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS ?
+ action->action |= is_egress ?
MLX5_FLOW_CONTEXT_ACTION_ENCRYPT :
MLX5_FLOW_CONTEXT_ACTION_DECRYPT;
return 0;
+ case IB_FLOW_ACTION_UNSPECIFIED:
+ if (maction->flow_action_raw.sub_type ==
+ MLX5_IB_FLOW_ACTION_MODIFY_HEADER) {
+ if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ return -EINVAL;
+ action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ action->modify_id = maction->flow_action_raw.action_id;
+ return 0;
+ }
+ if (maction->flow_action_raw.sub_type ==
+ MLX5_IB_FLOW_ACTION_DECAP) {
+ if (action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
+ return -EINVAL;
+ action->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+ return 0;
+ }
+ if (maction->flow_action_raw.sub_type ==
+ MLX5_IB_FLOW_ACTION_PACKET_REFORMAT) {
+ if (action->action &
+ MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
+ return -EINVAL;
+ action->action |=
+ MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+ action->reformat_id =
+ maction->flow_action_raw.action_id;
+ return 0;
+ }
+ /* fall through */
default:
return -EOPNOTSUPP;
}
action->action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
break;
case IB_FLOW_SPEC_ACTION_HANDLE:
- ret = parse_flow_flow_action(ib_spec, flow_attr, action);
+ ret = parse_flow_flow_action(to_mflow_act(ib_spec->action.act),
+ flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS, action);
if (ret)
return ret;
break;
* rules would be supported, always return VALID_SPEC_NA.
*/
if (!is_crypto)
- return egress ? VALID_SPEC_INVALID : VALID_SPEC_NA;
+ return VALID_SPEC_NA;
return is_crypto && is_ipsec &&
(!egress || (!is_drop && !flow_act->has_flow_tag)) ?
static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_flow_namespace *ns,
struct mlx5_ib_flow_prio *prio,
int priority,
- int num_entries, int num_groups)
+ int num_entries, int num_groups,
+ u32 flags)
{
struct mlx5_flow_table *ft;
ft = mlx5_create_auto_grouped_flow_table(ns, priority,
num_entries,
num_groups,
- 0, 0);
+ 0, flags);
if (IS_ERR(ft))
return ERR_CAST(ft);
int max_table_size;
int num_entries;
int num_groups;
+ u32 flags = 0;
int priority;
max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
log_max_ft_size));
if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
- if (ft_type == MLX5_IB_FT_TX)
- priority = 0;
- else if (flow_is_multicast_only(flow_attr) &&
- !dont_trap)
+ enum mlx5_flow_namespace_type fn_type;
+
+ if (flow_is_multicast_only(flow_attr) &&
+ !dont_trap)
priority = MLX5_IB_FLOW_MCAST_PRIO;
else
priority = ib_prio_to_core_prio(flow_attr->priority,
dont_trap);
- ns = mlx5_get_flow_namespace(dev->mdev,
- ft_type == MLX5_IB_FT_TX ?
- MLX5_FLOW_NAMESPACE_EGRESS :
- MLX5_FLOW_NAMESPACE_BYPASS);
+ if (ft_type == MLX5_IB_FT_RX) {
+ fn_type = MLX5_FLOW_NAMESPACE_BYPASS;
+ prio = &dev->flow_db->prios[priority];
+ if (!dev->rep &&
+ MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
+ if (!dev->rep &&
+ MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
+ reformat_l3_tunnel_to_l2))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+ } else {
+ max_table_size =
+ BIT(MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
+ log_max_ft_size));
+ fn_type = MLX5_FLOW_NAMESPACE_EGRESS;
+ prio = &dev->flow_db->egress_prios[priority];
+ if (!dev->rep &&
+ MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+ }
+ ns = mlx5_get_flow_namespace(dev->mdev, fn_type);
num_entries = MLX5_FS_MAX_ENTRIES;
num_groups = MLX5_FS_MAX_TYPES;
- prio = &dev->flow_db->prios[priority];
} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
ns = mlx5_get_flow_namespace(dev->mdev,
ft = prio->flow_table;
if (!ft)
- return _get_prio(ns, prio, priority, num_entries, num_groups);
+ return _get_prio(ns, prio, priority, num_entries, num_groups,
+ flags);
return prio;
}
if (!is_valid_attr(dev->mdev, flow_attr))
return ERR_PTR(-EINVAL);
+ if (dev->rep && is_egress)
+ return ERR_PTR(-EINVAL);
+
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
handler = kzalloc(sizeof(*handler), GFP_KERNEL);
if (!handler || !spec) {
return ERR_PTR(err);
}
-static struct mlx5_ib_flow_prio *_get_flow_table(struct mlx5_ib_dev *dev,
- int priority, bool mcast)
+static struct mlx5_ib_flow_prio *
+_get_flow_table(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_flow_matcher *fs_matcher,
+ bool mcast)
{
- int max_table_size;
struct mlx5_flow_namespace *ns = NULL;
struct mlx5_ib_flow_prio *prio;
+ int max_table_size;
+ u32 flags = 0;
+ int priority;
+
+ if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS) {
+ max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
+ log_max_ft_size));
+ if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP;
+ if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
+ reformat_l3_tunnel_to_l2))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+ } else { /* Can only be MLX5_FLOW_NAMESPACE_EGRESS */
+ max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev,
+ log_max_ft_size));
+ if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
+ }
- max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev,
- log_max_ft_size));
if (max_table_size < MLX5_FS_MAX_ENTRIES)
return ERR_PTR(-ENOMEM);
if (mcast)
priority = MLX5_IB_FLOW_MCAST_PRIO;
else
- priority = ib_prio_to_core_prio(priority, false);
+ priority = ib_prio_to_core_prio(fs_matcher->priority, false);
- ns = mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS);
+ ns = mlx5_get_flow_namespace(dev->mdev, fs_matcher->ns_type);
if (!ns)
return ERR_PTR(-ENOTSUPP);
- prio = &dev->flow_db->prios[priority];
+ if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS)
+ prio = &dev->flow_db->prios[priority];
+ else
+ prio = &dev->flow_db->egress_prios[priority];
if (prio->flow_table)
return prio;
return _get_prio(ns, prio, priority, MLX5_FS_MAX_ENTRIES,
- MLX5_FS_MAX_TYPES);
+ MLX5_FS_MAX_TYPES, flags);
}
static struct mlx5_ib_flow_handler *
struct mlx5_ib_flow_prio *ft_prio,
struct mlx5_flow_destination *dst,
struct mlx5_ib_flow_matcher *fs_matcher,
+ struct mlx5_flow_act *flow_act,
void *cmd_in, int inlen)
{
struct mlx5_ib_flow_handler *handler;
- struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
struct mlx5_flow_spec *spec;
struct mlx5_flow_table *ft = ft_prio->flow_table;
int err = 0;
fs_matcher->mask_len);
spec->match_criteria_enable = fs_matcher->match_criteria_enable;
- flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
handler->rule = mlx5_add_flow_rules(ft, spec,
- &flow_act, dst, 1);
+ flow_act, dst, 1);
if (IS_ERR(handler->rule)) {
err = PTR_ERR(handler->rule);
struct mlx5_ib_flow_handler *
mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
struct mlx5_ib_flow_matcher *fs_matcher,
+ struct mlx5_flow_act *flow_act,
void *cmd_in, int inlen, int dest_id,
int dest_type)
{
struct mlx5_flow_destination *dst;
struct mlx5_ib_flow_prio *ft_prio;
- int priority = fs_matcher->priority;
struct mlx5_ib_flow_handler *handler;
bool mcast;
int err;
mcast = raw_fs_is_multicast(fs_matcher, cmd_in);
mutex_lock(&dev->flow_db->lock);
- ft_prio = _get_flow_table(dev, priority, mcast);
+ ft_prio = _get_flow_table(dev, fs_matcher, mcast);
if (IS_ERR(ft_prio)) {
err = PTR_ERR(ft_prio);
goto unlock;
if (dest_type == MLX5_FLOW_DESTINATION_TYPE_TIR) {
dst->type = dest_type;
dst->tir_num = dest_id;
- } else {
+ flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ } else if (dest_type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) {
dst->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM;
dst->ft_num = dest_id;
+ flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ } else {
+ dst->type = MLX5_FLOW_DESTINATION_TYPE_PORT;
+ flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
}
- handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, cmd_in,
- inlen);
+ handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
+ cmd_in, inlen);
if (IS_ERR(handler)) {
err = PTR_ERR(handler);
*/
mlx5_accel_esp_destroy_xfrm(maction->esp_aes_gcm.ctx);
break;
+ case IB_FLOW_ACTION_UNSPECIFIED:
+ mlx5_ib_destroy_flow_action_raw(maction);
+ break;
default:
WARN_ON(true);
break;
if ((MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
(MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) ||
MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
- mutex_init(&dev->lb_mutex);
+ mutex_init(&dev->lb.mutex);
return 0;
}
#include <rdma/ib_smi.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cq.h>
+#include <linux/mlx5/fs.h>
#include <linux/mlx5/qp.h>
#include <linux/mlx5/srq.h>
+#include <linux/mlx5/fs.h>
#include <linux/types.h>
#include <linux/mlx5/transobj.h>
#include <rdma/ib_user_verbs.h>
MLX5_MEMIC_BASE_SIZE = 1 << MLX5_MEMIC_BASE_ALIGN,
};
-struct mlx5_ib_vma_private_data {
- struct list_head list;
- struct vm_area_struct *vma;
- /* protect vma_private_list add/del */
- struct mutex *vma_private_list_mutex;
-};
-
struct mlx5_ib_ucontext {
struct ib_ucontext ibucontext;
struct list_head db_page_list;
u8 cqe_version;
/* Transport Domain number */
u32 tdn;
- struct list_head vma_private_list;
- /* protect vma_private_list add/del */
- struct mutex vma_private_list_mutex;
u64 lib_caps;
DECLARE_BITMAP(dm_pages, MLX5_MAX_MEMIC_PAGES);
u16 devx_uid;
+ /* For RoCE LAG TX affinity */
+ atomic_t tx_port_affinity;
};
static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibucontext)
u32 pdn;
};
+enum {
+ MLX5_IB_FLOW_ACTION_MODIFY_HEADER,
+ MLX5_IB_FLOW_ACTION_PACKET_REFORMAT,
+ MLX5_IB_FLOW_ACTION_DECAP,
+};
+
#define MLX5_IB_FLOW_MCAST_PRIO (MLX5_BY_PASS_NUM_PRIOS - 1)
#define MLX5_IB_FLOW_LAST_PRIO (MLX5_BY_PASS_NUM_REGULAR_PRIOS - 1)
#if (MLX5_IB_FLOW_LAST_PRIO <= 0)
struct mlx5_ib_match_params matcher_mask;
int mask_len;
enum mlx5_ib_flow_type flow_type;
+ enum mlx5_flow_namespace_type ns_type;
u16 priority;
struct mlx5_core_dev *mdev;
atomic_t usecnt;
struct mlx5_ib_flow_db {
struct mlx5_ib_flow_prio prios[MLX5_IB_NUM_FLOW_FT];
+ struct mlx5_ib_flow_prio egress_prios[MLX5_IB_NUM_FLOW_FT];
struct mlx5_ib_flow_prio sniffer[MLX5_IB_NUM_SNIFFER_FTS];
struct mlx5_ib_flow_prio egress[MLX5_IB_NUM_EGRESS_FTS];
struct mlx5_flow_table *lag_demux_ft;
struct list_head cq_send_list;
struct mlx5_rate_limit rl;
u32 underlay_qpn;
- bool tunnel_offload_en;
+ u32 flags_en;
/* storage for qp sub type when core qp type is IB_QPT_DRIVER */
enum ib_qp_type qp_sub_type;
};
rwlock_t netdev_lock;
struct net_device *netdev;
struct notifier_block nb;
- atomic_t next_port;
+ atomic_t tx_port_affinity;
enum ib_port_state last_port_state;
struct mlx5_ib_dev *dev;
u8 native_port_num;
u64 ib_flags;
struct mlx5_accel_esp_xfrm *ctx;
} esp_aes_gcm;
+ struct {
+ struct mlx5_ib_dev *dev;
+ u32 sub_type;
+ u32 action_id;
+ } flow_action_raw;
};
};
return container_of(ibcntrs, struct mlx5_ib_mcounters, ibcntrs);
}
+int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
+ bool is_egress,
+ struct mlx5_flow_act *action);
+ struct mlx5_ib_lb_state {
+ /* protect the user_td */
+ struct mutex mutex;
+ u32 user_td;
+ int qps;
+ bool enabled;
+ };
+
struct mlx5_ib_dev {
struct ib_device ib_dev;
- const struct uverbs_object_tree_def *driver_trees[6];
+ const struct uverbs_object_tree_def *driver_trees[7];
struct mlx5_core_dev *mdev;
struct mlx5_roce roce[MLX5_MAX_PORTS];
int num_ports;
const struct mlx5_ib_profile *profile;
struct mlx5_eswitch_rep *rep;
- /* protect the user_td */
- struct mutex lb_mutex;
- u32 user_td;
+ struct mlx5_ib_lb_state lb;
u8 umr_fence;
struct list_head ib_dev_list;
u64 sys_image_guid;
int mlx5_ib_destroy_srq(struct ib_srq *srq);
int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
const struct ib_recv_wr **bad_wr);
+ int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
+ void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
struct ib_qp_init_attr *init_attr,
struct ib_udata *udata);
int mlx5_ib_odp_init_one(struct mlx5_ib_dev *ibdev);
int __init mlx5_ib_odp_init(void);
void mlx5_ib_odp_cleanup(void);
-void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
+void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
unsigned long end);
void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent);
void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
const struct uverbs_object_tree_def *mlx5_ib_get_devx_tree(void);
struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add(
struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher,
- void *cmd_in, int inlen, int dest_id, int dest_type);
+ struct mlx5_flow_act *flow_act, void *cmd_in, int inlen,
+ int dest_id, int dest_type);
bool mlx5_ib_devx_is_flow_dest(void *obj, int *dest_id, int *dest_type);
int mlx5_ib_get_flow_trees(const struct uverbs_object_tree_def **root);
+void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction);
#else
static inline int
mlx5_ib_devx_create(struct mlx5_ib_dev *dev,
{
return 0;
}
+static inline void
+mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
+{
+ return;
+};
#endif
static inline void init_query_mad(struct ib_smp *mad)
{
MLX5_CAP_ETH(dev, tunnel_stateless_geneve_rx));
}
+ static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq,
+ u32 qp_flags_en)
+ {
+ if (qp_flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+ mlx5_ib_disable_lb(dev, false, true);
+ mlx5_core_destroy_tir(dev->mdev, rq->tirn);
+ }
+
static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
struct mlx5_ib_rq *rq, u32 tdn,
- bool tunnel_offload_en)
+ u32 *qp_flags_en)
{
+ u8 lb_flag = 0;
u32 *in;
void *tirc;
int inlen;
MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn);
MLX5_SET(tirc, tirc, transport_domain, tdn);
- if (tunnel_offload_en)
+ if (*qp_flags_en & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
- if (dev->rep)
- MLX5_SET(tirc, tirc, self_lb_block,
- MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_);
+ if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC)
+ lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+
+ if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)
+ lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+ if (dev->rep) {
+ lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+ *qp_flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+ }
+
+ MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
+ if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+ err = mlx5_ib_enable_lb(dev, false, true);
+
+ if (err)
+ destroy_raw_packet_qp_tir(dev, rq, 0);
+ }
kvfree(in);
return err;
}
- static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
- struct mlx5_ib_rq *rq)
- {
- mlx5_core_destroy_tir(dev->mdev, rq->tirn);
- }
-
static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
u32 *in, size_t inlen,
struct ib_pd *pd)
goto err_destroy_sq;
- err = create_raw_packet_qp_tir(dev, rq, tdn,
- qp->tunnel_offload_en);
+ err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en);
if (err)
goto err_destroy_rq;
}
struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
if (qp->rq.wqe_cnt) {
- destroy_raw_packet_qp_tir(dev, rq);
+ destroy_raw_packet_qp_tir(dev, rq, qp->flags_en);
destroy_raw_packet_qp_rq(dev, rq);
}
static void destroy_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
{
+ if (qp->flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+ mlx5_ib_disable_lb(dev, false, true);
mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
}
u32 tdn = mucontext->tdn;
struct mlx5_ib_create_qp_rss ucmd = {};
size_t required_cmd_sz;
+ u8 lb_flag = 0;
if (init_attr->qp_type != IB_QPT_RAW_PACKET)
return -EOPNOTSUPP;
return -EOPNOTSUPP;
}
- if (ucmd.flags & ~MLX5_QP_FLAG_TUNNEL_OFFLOADS) {
+ if (ucmd.flags & ~(MLX5_QP_FLAG_TUNNEL_OFFLOADS |
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+ MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)) {
mlx5_ib_dbg(dev, "invalid flags\n");
return -EOPNOTSUPP;
}
return -EOPNOTSUPP;
}
+ if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC || dev->rep) {
+ lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+ qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+ }
+
+ if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+ lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+ qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
+ }
+
err = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
if (err) {
mlx5_ib_dbg(dev, "copy failed\n");
if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
+ MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
+
if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER)
hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner);
else
MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
create_tir:
- if (dev->rep)
- MLX5_SET(tirc, tirc, self_lb_block,
- MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_);
-
err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
+ if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+ err = mlx5_ib_enable_lb(dev, false, true);
+
+ if (err)
+ mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
+ }
+
if (err)
goto err;
mlx5_ib_dbg(dev, "Tunnel offload isn't supported\n");
return -EOPNOTSUPP;
}
- qp->tunnel_offload_en = true;
+ qp->flags_en |= MLX5_QP_FLAG_TUNNEL_OFFLOADS;
+ }
+
+ if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC) {
+ if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+ mlx5_ib_dbg(dev, "Self-LB UC isn't supported\n");
+ return -EOPNOTSUPP;
+ }
+ qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+ }
+
+ if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+ if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+ mlx5_ib_dbg(dev, "Self-LB UM isn't supported\n");
+ return -EOPNOTSUPP;
+ }
+ qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
}
if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) {
return 0;
}
+static unsigned int get_tx_affinity(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_pd *pd,
+ struct mlx5_ib_qp_base *qp_base,
+ u8 port_num)
+{
+ struct mlx5_ib_ucontext *ucontext = NULL;
+ unsigned int tx_port_affinity;
+
+ if (pd && pd->ibpd.uobject && pd->ibpd.uobject->context)
+ ucontext = to_mucontext(pd->ibpd.uobject->context);
+
+ if (ucontext) {
+ tx_port_affinity = (unsigned int)atomic_add_return(
+ 1, &ucontext->tx_port_affinity) %
+ MLX5_MAX_PORTS +
+ 1;
+ mlx5_ib_dbg(dev, "Set tx affinity 0x%x to qpn 0x%x ucontext %p\n",
+ tx_port_affinity, qp_base->mqp.qpn, ucontext);
+ } else {
+ tx_port_affinity =
+ (unsigned int)atomic_add_return(
+ 1, &dev->roce[port_num].tx_port_affinity) %
+ MLX5_MAX_PORTS +
+ 1;
+ mlx5_ib_dbg(dev, "Set tx affinity 0x%x to qpn 0x%x\n",
+ tx_port_affinity, qp_base->mqp.qpn);
+ }
+
+ return tx_port_affinity;
+}
+
static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
const struct ib_qp_attr *attr, int attr_mask,
enum ib_qp_state cur_state, enum ib_qp_state new_state,
if (!context)
return -ENOMEM;
+ pd = get_pd(qp);
context->flags = cpu_to_be32(mlx5_st << 16);
if (!(attr_mask & IB_QP_PATH_MIG_STATE)) {
(ibqp->qp_type == IB_QPT_XRC_TGT)) {
if (mlx5_lag_is_active(dev->mdev)) {
u8 p = mlx5_core_native_port_num(dev->mdev);
- tx_affinity = (unsigned int)atomic_add_return(1,
- &dev->roce[p].next_port) %
- MLX5_MAX_PORTS + 1;
+ tx_affinity = get_tx_affinity(dev, pd, base, p);
context->flags |= cpu_to_be32(tx_affinity << 24);
}
}
goto out;
}
- pd = get_pd(qp);
get_cqs(qp->ibqp.qp_type, qp->ibqp.send_cq, qp->ibqp.recv_cq,
&send_cq, &recv_cq);
int req = IB_QP_STATE;
int opt = 0;
- if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
+ if (new_state == IB_QPS_RESET) {
+ return is_valid_mask(attr_mask, req, opt);
+ } else if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
req |= IB_QP_PKEY_INDEX | IB_QP_PORT;
return is_valid_mask(attr_mask, req, opt);
} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
u8 next_fence = 0;
u8 fence;
+ if (unlikely(mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR &&
+ !drain)) {
+ *bad_wr = wr;
+ return -EIO;
+ }
+
if (unlikely(ibqp->qp_type == IB_QPT_GSI))
return mlx5_ib_gsi_post_send(ibqp, wr, bad_wr);
spin_lock_irqsave(&qp->sq.lock, flags);
- if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR && !drain) {
- err = -EIO;
- *bad_wr = wr;
- nreq = 0;
- goto out;
- }
-
for (nreq = 0; wr; nreq++, wr = wr->next) {
if (unlikely(wr->opcode >= ARRAY_SIZE(mlx5_ib_opcode))) {
mlx5_ib_warn(dev, "\n");
int ind;
int i;
+ if (unlikely(mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR &&
+ !drain)) {
+ *bad_wr = wr;
+ return -EIO;
+ }
+
if (unlikely(ibqp->qp_type == IB_QPT_GSI))
return mlx5_ib_gsi_post_recv(ibqp, wr, bad_wr);
spin_lock_irqsave(&qp->rq.lock, flags);
- if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR && !drain) {
- err = -EIO;
- *bad_wr = wr;
- nreq = 0;
- goto out;
- }
-
ind = qp->rq.head & (qp->rq.wqe_cnt - 1);
for (nreq = 0; wr; nreq++, wr = wr->next) {