Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull Mellanox rdma updates from Doug Ledford:
 "Mellanox specific updates for 4.11 merge window

  Because the Mellanox code required being based on a net-next tree, I
  keept it separate from the remainder of the RDMA stack submission that
  is based on 4.10-rc3.

  This branch contains:

   - Various mlx4 and mlx5 fixes and minor changes

   - Support for adding a tag match rule to flow specs

   - Support for cvlan offload operation for raw ethernet QPs

   - A change to the core IB code to recognize raw eth capabilities and
     enumerate them (touches non-Mellanox code)

   - Implicit On-Demand Paging memory registration support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (40 commits)
  IB/mlx5: Fix configuration of port capabilities
  IB/mlx4: Take source GID by index from HW GID table
  IB/mlx5: Fix blue flame buffer size calculation
  IB/mlx4: Remove unused variable from function declaration
  IB: Query ports via the core instead of direct into the driver
  IB: Add protocol for USNIC
  IB/mlx4: Support raw packet protocol
  IB/mlx5: Support raw packet protocol
  IB/core: Add raw packet protocol
  IB/mlx5: Add implicit MR support
  IB/mlx5: Expose MR cache for mlx5_ib
  IB/mlx5: Add null_mkey access
  IB/umem: Indicate that process is being terminated
  IB/umem: Update on demand page (ODP) support
  IB/core: Add implicit MR flag
  IB/mlx5: Support creation of a WQ with scatter FCS offload
  IB/mlx5: Enable QP creation with cvlan offload
  IB/mlx5: Enable WQ creation and modification with cvlan offload
  IB/mlx5: Expose vlan offloads capabilities
  IB/uverbs: Enable QP creation with cvlan offload
  ...

2 files changed, 71 insertions, 7 deletions

diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 3da0b167041b..542cd8b3414c 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -79,11 +79,15 @@ struct ib_umem_odp {
 
 	struct completion	notifier_completion;
 	int			dying;
+	struct work_struct	work;
 };
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 
 int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem);
+struct ib_umem *ib_alloc_odp_umem(struct ib_ucontext *context,
+				  unsigned long addr,
+				  size_t size);
 
 void ib_umem_odp_release(struct ib_umem *umem);
 
@@ -117,10 +121,12 @@ typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
 int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
 				  umem_call_back cb, void *cookie);
 
-struct umem_odp_node *rbt_ib_umem_iter_first(struct rb_root *root,
-					     u64 start, u64 last);
-struct umem_odp_node *rbt_ib_umem_iter_next(struct umem_odp_node *node,
-					    u64 start, u64 last);
+/*
+ * Find first region intersecting with address range.
+ * Return NULL if not found
+ */
+struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root *root,
+				       u64 addr, u64 length);
 
 static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
 					     unsigned long mmu_seq)
@@ -153,6 +159,13 @@ static inline int ib_umem_odp_get(struct ib_ucontext *context,
 	return -EINVAL;
 }
 
+static inline struct ib_umem *ib_alloc_odp_umem(struct ib_ucontext *context,
+						unsigned long addr,
+						size_t size)
+{
+	return ERR_PTR(-EINVAL);
+}
+
 static inline void ib_umem_odp_release(struct ib_umem *umem) {}
 
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8c61532cf521..89f5bd4e1d52 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -207,6 +207,7 @@ enum ib_device_cap_flags {
 	IB_DEVICE_MEM_WINDOW_TYPE_2A		= (1 << 23),
 	IB_DEVICE_MEM_WINDOW_TYPE_2B		= (1 << 24),
 	IB_DEVICE_RC_IP_CSUM			= (1 << 25),
+	/* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */
 	IB_DEVICE_RAW_IP_CSUM			= (1 << 26),
 	/*
 	 * Devices should set IB_DEVICE_CROSS_CHANNEL if they
@@ -220,6 +221,7 @@ enum ib_device_cap_flags {
 	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
 	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
 	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
+	/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
 	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
 };
 
@@ -241,7 +243,8 @@ enum ib_atomic_cap {
 };
 
 enum ib_odp_general_cap_bits {
-	IB_ODP_SUPPORT = 1 << 0,
+	IB_ODP_SUPPORT		= 1 << 0,
+	IB_ODP_SUPPORT_IMPLICIT = 1 << 1,
 };
 
 enum ib_odp_transport_cap_bits {
@@ -330,6 +333,7 @@ struct ib_device_attr {
 	uint64_t		hca_core_clock; /* in KHZ */
 	struct ib_rss_caps	rss_caps;
 	u32			max_wq_type_rq;
+	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
 };
 
 enum ib_mtu {
@@ -499,6 +503,8 @@ static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
 #define RDMA_CORE_CAP_PROT_ROCE         0x00200000
 #define RDMA_CORE_CAP_PROT_IWARP        0x00400000
 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
+#define RDMA_CORE_CAP_PROT_RAW_PACKET   0x01000000
+#define RDMA_CORE_CAP_PROT_USNIC        0x02000000
 
 #define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
 					| RDMA_CORE_CAP_IB_MAD \
@@ -522,6 +528,10 @@ static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
 #define RDMA_CORE_PORT_INTEL_OPA       (RDMA_CORE_PORT_IBA_IB  \
 					| RDMA_CORE_CAP_OPA_MAD)
 
+#define RDMA_CORE_PORT_RAW_PACKET	(RDMA_CORE_CAP_PROT_RAW_PACKET)
+
+#define RDMA_CORE_PORT_USNIC		(RDMA_CORE_CAP_PROT_USNIC)
+
 struct ib_port_attr {
 	u64			subnet_prefix;
 	enum ib_port_state	state;
@@ -1019,6 +1029,7 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
 	IB_QP_CREATE_USE_GFP_NOIO		= 1 << 7,
 	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
+	IB_QP_CREATE_CVLAN_STRIPPING		= 1 << 9,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1470,6 +1481,18 @@ struct ib_srq {
 	} ext;
 };
 
+enum ib_raw_packet_caps {
+	/* Strip cvlan from incoming packet and report it in the matching work
+	 * completion is supported.
+	 */
+	IB_RAW_PACKET_CAP_CVLAN_STRIPPING	= (1 << 0),
+	/* Scatter FCS field of an incoming packet to host memory is supported.
+	 */
+	IB_RAW_PACKET_CAP_SCATTER_FCS		= (1 << 1),
+	/* Checksum offloads are supported (for both send and receive). */
+	IB_RAW_PACKET_CAP_IP_CSUM		= (1 << 2),
+};
+
 enum ib_wq_type {
 	IB_WQT_RQ
 };
@@ -1493,6 +1516,11 @@ struct ib_wq {
 	atomic_t		usecnt;
 };
 
+enum ib_wq_flags {
+	IB_WQ_FLAGS_CVLAN_STRIPPING	= 1 << 0,
+	IB_WQ_FLAGS_SCATTER_FCS		= 1 << 1,
+};
+
 struct ib_wq_init_attr {
 	void		       *wq_context;
 	enum ib_wq_type	wq_type;
@@ -1500,16 +1528,20 @@ struct ib_wq_init_attr {
 	u32		max_sge;
 	struct	ib_cq	       *cq;
 	void		    (*event_handler)(struct ib_event *, void *);
+	u32		create_flags; /* Use enum ib_wq_flags */
 };
 
 enum ib_wq_attr_mask {
-	IB_WQ_STATE	= 1 << 0,
-	IB_WQ_CUR_STATE	= 1 << 1,
+	IB_WQ_STATE		= 1 << 0,
+	IB_WQ_CUR_STATE		= 1 << 1,
+	IB_WQ_FLAGS		= 1 << 2,
 };
 
 struct ib_wq_attr {
 	enum	ib_wq_state	wq_state;
 	enum	ib_wq_state	curr_wq_state;
+	u32			flags; /* Use enum ib_wq_flags */
+	u32			flags_mask; /* Use enum ib_wq_flags */
 };
 
 struct ib_rwq_ind_table {
@@ -1618,6 +1650,8 @@ enum ib_flow_spec_type {
 	IB_FLOW_SPEC_UDP		= 0x41,
 	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
 	IB_FLOW_SPEC_INNER		= 0x100,
+	/* Actions */
+	IB_FLOW_SPEC_ACTION_TAG         = 0x1000,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 8
@@ -1740,6 +1774,12 @@ struct ib_flow_spec_tunnel {
 	struct ib_flow_tunnel_filter  mask;
 };
 
+struct ib_flow_spec_action_tag {
+	enum ib_flow_spec_type	      type;
+	u16			      size;
+	u32                           tag_id;
+};
+
 union ib_flow_spec {
 	struct {
 		u32			type;
@@ -1751,6 +1791,7 @@ union ib_flow_spec {
 	struct ib_flow_spec_tcp_udp	tcp_udp;
 	struct ib_flow_spec_ipv6        ipv6;
 	struct ib_flow_spec_tunnel      tunnel;
+	struct ib_flow_spec_action_tag  flow_tag;
 };
 
 struct ib_flow_attr {
@@ -2333,6 +2374,16 @@ static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num)
 		rdma_protocol_roce(device, port_num);
 }
 
+static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET;
+}
+
+static inline bool rdma_protocol_usnic(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_USNIC;
+}
+
 /**
  * rdma_cap_ib_mad - Check if the port of a device supports Infiniband
  * Management Datagrams.