Merge branch 'mlx5-next' into rdma.git

From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

mlx5 updates taken for dependencies on later ODP patches.

Conflict resolved by deleting mlx5_ib_get_vector_affinity()

* branch 'mlx5-next': (21 commits)
  net/mlx5: EQ, Make EQE access methods inline
  {net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA
  net/mlx5: EQ, Generic EQ
  net/mlx5: EQ, Different EQ types
  net/mlx5: EQ, Privatize eq_table and friends
  net/mlx5: EQ, irq_info and rmap belong to eq_table
  net/mlx5: EQ, Create all EQs in one place
  net/mlx5: EQ, Move all EQ logic to eq.c
  net/mlx5: EQ, Remove redundant completion EQ list lock
  net/mlx5: EQ, No need to store eq index as a field
  net/mlx5: EQ, Remove unused fields and structures
  net/mlx5: EQ, Use the right place to store/read IRQ affinity hint
  IB/mlx5: Improve ODP debugging messages
  net/mlx5: Use multi threaded workqueue for page fault handling
  net/mlx5: Return success for PAGE_FAULT_RESUME in internal error state
  IB/mlx5: Lock QP during page fault handling
  net/mlx5: Enumerate page fault types
  net/mlx5: Add interface to hold and release core resources
  net/mlx5: Release resource on error flow
  net/mlx5: Fix offsets of ifc reserved fields
  ...

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

6 files changed, 91 insertions, 150 deletions

diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 31a750570c38..28b757a64029 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -60,7 +60,7 @@ struct mlx5_core_cq {
 	} tasklet_ctx;
 	int			reset_notify_added;
 	struct list_head	reset_notify;
-	struct mlx5_eq		*eq;
+	struct mlx5_eq_comp	*eq;
 	u16 uid;
 };
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index b4c0457fbebd..e326524bafcc 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -212,6 +212,13 @@ enum {
 	MLX5_PFAULT_SUBTYPE_RDMA = 1,
 };
 
+enum wqe_page_fault_type {
+	MLX5_WQE_PF_TYPE_RMP = 0,
+	MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE = 1,
+	MLX5_WQE_PF_TYPE_RESP = 2,
+	MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC = 3,
+};
+
 enum {
 	MLX5_PERM_LOCAL_READ	= 1 << 2,
 	MLX5_PERM_LOCAL_WRITE	= 1 << 3,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6b6b3d9dcc00..f41e6713df10 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -85,18 +85,6 @@ enum {
 };
 
 enum {
-	MLX5_EQ_VEC_PAGES	 = 0,
-	MLX5_EQ_VEC_CMD		 = 1,
-	MLX5_EQ_VEC_ASYNC	 = 2,
-	MLX5_EQ_VEC_PFAULT	 = 3,
-	MLX5_EQ_VEC_COMP_BASE,
-};
-
-enum {
-	MLX5_MAX_IRQ_NAME	= 32
-};
-
-enum {
 	MLX5_ATOMIC_MODE_OFFSET = 16,
 	MLX5_ATOMIC_MODE_IB_COMP = 1,
 	MLX5_ATOMIC_MODE_CX = 2,
@@ -222,14 +210,6 @@ enum mlx5_port_status {
 	MLX5_PORT_DOWN      = 2,
 };
 
-enum mlx5_eq_type {
-	MLX5_EQ_TYPE_COMP,
-	MLX5_EQ_TYPE_ASYNC,
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	MLX5_EQ_TYPE_PF,
-#endif
-};
-
 struct mlx5_bfreg_info {
 	u32		       *sys_pages;
 	int			num_low_latency_bfregs;
@@ -366,51 +346,6 @@ struct mlx5_frag_buf_ctrl {
 	u8			log_frag_strides;
 };
 
-struct mlx5_eq_tasklet {
-	struct list_head list;
-	struct list_head process_list;
-	struct tasklet_struct task;
-	/* lock on completion tasklet list */
-	spinlock_t lock;
-};
-
-struct mlx5_eq_pagefault {
-	struct work_struct       work;
-	/* Pagefaults lock */
-	spinlock_t		 lock;
-	struct workqueue_struct *wq;
-	mempool_t		*pool;
-};
-
-struct mlx5_cq_table {
-	/* protect radix tree */
-	spinlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
-struct mlx5_eq {
-	struct mlx5_core_dev   *dev;
-	struct mlx5_cq_table	cq_table;
-	__be32 __iomem	       *doorbell;
-	u32			cons_index;
-	struct mlx5_frag_buf	buf;
-	int			size;
-	unsigned int		irqn;
-	u8			eqn;
-	int			nent;
-	u64			mask;
-	struct list_head	list;
-	int			index;
-	struct mlx5_rsc_debug	*dbg;
-	enum mlx5_eq_type	type;
-	union {
-		struct mlx5_eq_tasklet   tasklet_ctx;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		struct mlx5_eq_pagefault pf_ctx;
-#endif
-	};
-};
-
 struct mlx5_core_psv {
 	u32	psv_idx;
 	struct psv_layout {
@@ -477,22 +412,6 @@ struct mlx5_core_srq {
 	u16		uid;
 };
 
-struct mlx5_eq_table {
-	void __iomem	       *update_ci;
-	void __iomem	       *update_arm_ci;
-	struct list_head	comp_eqs_list;
-	struct mlx5_eq		pages_eq;
-	struct mlx5_eq		async_eq;
-	struct mlx5_eq		cmd_eq;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	struct mlx5_eq		pfault_eq;
-#endif
-	int			num_comp_vectors;
-	/* protect EQs list
-	 */
-	spinlock_t		lock;
-};
-
 struct mlx5_uars_page {
 	void __iomem	       *map;
 	bool			wc;
@@ -575,11 +494,6 @@ struct mlx5_core_sriov {
 	int			enabled_vfs;
 };
 
-struct mlx5_irq_info {
-	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
-};
-
 struct mlx5_fc_stats {
 	spinlock_t counters_idr_lock; /* protects counters_idr */
 	struct idr counters_idr;
@@ -596,7 +510,7 @@ struct mlx5_fc_stats {
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
-struct mlx5_pagefault;
+struct mlx5_eq_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -646,8 +560,7 @@ struct mlx5_port_module_event_stats {
 
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
-	struct mlx5_eq_table	eq_table;
-	struct mlx5_irq_info	*irq_info;
+	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
 	struct workqueue_struct *pg_wq;
@@ -705,13 +618,6 @@ struct mlx5_priv {
 
 	struct mlx5_port_module_event_stats  pme_stats;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	void		      (*pfault)(struct mlx5_core_dev *dev,
-					void *context,
-					struct mlx5_pagefault *pfault);
-	void		       *pfault_ctx;
-	struct srcu_struct      pfault_srcu;
-#endif
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
 };
@@ -736,44 +642,6 @@ enum mlx5_pagefault_type_flags {
 	MLX5_PFAULT_RDMA      = 1 << 2,
 };
 
-/* Contains the details of a pagefault. */
-struct mlx5_pagefault {
-	u32			bytes_committed;
-	u32			token;
-	u8			event_subtype;
-	u8			type;
-	union {
-		/* Initiator or send message responder pagefault details. */
-		struct {
-			/* Received packet size, only valid for responders. */
-			u32	packet_size;
-			/*
-			 * Number of resource holding WQE, depends on type.
-			 */
-			u32	wq_num;
-			/*
-			 * WQE index. Refers to either the send queue or
-			 * receive queue, according to event_subtype.
-			 */
-			u16	wqe_index;
-		} wqe;
-		/* RDMA responder pagefault details */
-		struct {
-			u32	r_key;
-			/*
-			 * Received packet size, minimal size page fault
-			 * resolution required for forward progress.
-			 */
-			u32	packet_size;
-			u32	rdma_op_len;
-			u64	rdma_va;
-		} rdma;
-	};
-
-	struct mlx5_eq	       *eq;
-	struct work_struct	work;
-};
-
 struct mlx5_td {
 	struct list_head tirs_list;
 	u32              tdn;
@@ -859,9 +727,6 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap         *rmap;
-#endif
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct page             *clock_info_page;
@@ -1155,6 +1020,9 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 		     bool map_wc, bool fast_path);
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
@@ -1204,9 +1072,6 @@ struct mlx5_interface {
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
 	void			(*event)(struct mlx5_core_dev *dev, void *context,
 					 enum mlx5_dev_event event, unsigned long param);
-	void			(*pfault)(struct mlx5_core_dev *dev,
-					  void *context,
-					  struct mlx5_pagefault *pfault);
 	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
new file mode 100644
index 000000000000..71d82c5a1a02
--- /dev/null
+++ b/include/linux/mlx5/eq.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef MLX5_CORE_EQ_H
+#define MLX5_CORE_EQ_H
+
+#include <linux/mlx5/driver.h>
+
+enum {
+	MLX5_EQ_PAGEREQ_IDX        = 0,
+	MLX5_EQ_CMD_IDX            = 1,
+	MLX5_EQ_ASYNC_IDX          = 2,
+	/* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */
+	MLX5_EQ_PFAULT_IDX         = 3,
+	MLX5_EQ_MAX_ASYNC_EQS,
+	/* completion eqs vector indices start here */
+	MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS,
+};
+
+#define MLX5_NUM_CMD_EQE   (32)
+#define MLX5_NUM_ASYNC_EQE (0x1000)
+#define MLX5_NUM_SPARE_EQE (0x80)
+
+struct mlx5_eq;
+
+struct mlx5_eq_param {
+	u8             index;
+	int            nent;
+	u64            mask;
+	void          *context;
+	irq_handler_t  handler;
+};
+
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+		       struct mlx5_eq_param *param);
+int
+mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc);
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm);
+
+/* The HCA will think the queue has overflowed if we
+ * don't tell it we've been processing events.  We
+ * create EQs with MLX5_NUM_SPARE_EQE extra entries,
+ * so we must update our consumer index at
+ * least that often.
+ *
+ * mlx5_eq_update_cc must be called on every EQE @EQ irq handler
+ */
+static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc)
+{
+	if (unlikely(cc >= MLX5_NUM_SPARE_EQE)) {
+		mlx5_eq_update_ci(eq, cc, 0);
+		cc = 0;
+	}
+	return cc;
+}
+
+#endif /* MLX5_CORE_EQ_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index dbff9ff28f2c..6f64e814cc10 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -349,7 +349,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
-	u8         reserved_at_14[0xb];
+	u8         reserved_at_15[0xb];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -586,7 +586,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      fdb_multi_path_to_table[0x1];
 	u8      reserved_at_1d[0x1];
 	u8      multi_fdb_encap[0x1];
-	u8      reserved_at_1e[0x1e1];
+	u8      reserved_at_1f[0x1e1];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
 
@@ -829,7 +829,7 @@ struct mlx5_ifc_vector_calc_cap_bits {
 	struct mlx5_ifc_calc_op calc2;
 	struct mlx5_ifc_calc_op calc3;
 
-	u8         reserved_at_e0[0x720];
+	u8         reserved_at_c0[0x720];
 };
 
 enum {
@@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits {
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         dbr_umem_valid[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
 	u8         basic_cyclic_rcv_wqe[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_at_46[0x2];
+	u8         reserved_at_46[0x1];
+	u8         dbr_umem_valid[0x1];
 	u8         cqn[0x18];
 
 	u8         reserved_at_60[0x20];
@@ -5566,7 +5567,7 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits {
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
 	u8         reserved_at_0[0x12];
 	u8	   affiliation[0x1];
-	u8	   reserved_at_e[0x1];
+	u8	   reserved_at_13[0x1];
 	u8         disable_uc_local_lb[0x1];
 	u8         disable_mc_local_lb[0x1];
 	u8         node_guid[0x1];
@@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits {
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_at_280[0x40];
+	u8         reserved_at_280[0x60];
+
 	u8         xrc_srq_umem_valid[0x1];
-	u8         reserved_at_2c1[0x5bf];
+	u8         reserved_at_2e1[0x1f];
+
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
@@ -9024,7 +9028,7 @@ struct mlx5_ifc_dcbx_param_bits {
 	u8         dcbx_cee_cap[0x1];
 	u8         dcbx_ieee_cap[0x1];
 	u8         dcbx_standby_cap[0x1];
-	u8         reserved_at_0[0x5];
+	u8         reserved_at_3[0x5];
 	u8         port_number[0x8];
 	u8         reserved_at_10[0xa];
 	u8         max_application_table_size[6];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index fbe322c966bc..b26ea9077384 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -596,6 +596,11 @@ int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id);
 int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 			      int reset, void *out, int out_size);
 
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type);
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res);
+
 static inline const char *mlx5_qp_type_str(int type)
 {
 	switch (type) {