Merge branch 'mlx5-dump-fill-mkey' into rdma.git for-next

For dependencies, branch based on 'mellanox/mlx5-next' of
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux.git

Pull Dump and fill MKEY from Leon Romanovsky:

====================
MLX5 IB HCA offers the memory key, dump_fill_mkey to increase performance,
when used in a send or receive operations.

It is used to force local HCA operations to skip the PCI bus access, while
keeping track of the processed length in the ibv_sge handling.

In this three patch series, we expose various bits in our HW spec
file (mlx5_ifc.h), move unneeded for mlx5_core FW command and export such
memory key to user space thought our mlx5-abi header file.
====================

Botched auto-merge in mlx5_ib_alloc_ucontext() resolved by hand.

* branch 'mlx5-dump-fill-mkey':
  IB/mlx5: Expose dump and fill memory key
  net/mlx5: Add hardware definitions for dump_fill_mkey
  net/mlx5: Limit scope of dump_fill_mkey function
  net/mlx5: Rate limit errors in command interface
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/mlx5/cmd.c

@@ -32,6 +32,21 @@
 
 #include "cmd.h"
 
+int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)]   = {0};
+	int err;
+
+	MLX5_SET(query_special_contexts_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*mkey = MLX5_GET(query_special_contexts_out, out,
+				 dump_fill_mkey);
+	return err;
+}
+
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
 {
 	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};

drivers/infiniband/hw/mlx5/cmd.h

@@ -37,6 +37,7 @@
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
 
+int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey);
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 			       void *out, int out_size);

drivers/infiniband/hw/mlx5/main.c

@@ -1632,6 +1632,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	int err;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
+	u32 dump_fill_mkey;
 	bool lib_uar_4k;
 
 	if (!dev->ib_active)
@@ -1743,6 +1744,12 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 			goto out_td;
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
+		err = mlx5_cmd_dump_fill_mkey(dev->mdev, &dump_fill_mkey);
+		if (err)
+			goto out_mdev;
+	}
+
 	INIT_LIST_HEAD(&context->vma_private_list);
 	mutex_init(&context->vma_private_list_mutex);
 	INIT_LIST_HEAD(&context->db_page_list);
@@ -1801,6 +1808,15 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.num_dyn_bfregs);
 	}
 
+	if (field_avail(typeof(resp), dump_fill_mkey, udata->outlen)) {
+		if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
+			resp.dump_fill_mkey = dump_fill_mkey;
+			resp.comp_mask |=
+				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY;
+		}
+		resp.response_length += sizeof(resp.dump_fill_mkey);
+	}
+
 	err = ib_copy_to_udata(udata, &resp, resp.response_length);
 	if (err)
 		goto out_mdev;

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -717,13 +717,10 @@ static int mlx5_cmd_check(struct mlx5_core_dev *dev, void *in, void *out)
 	uid    = MLX5_GET(mbox_in, in, uid);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY)
-		mlx5_core_err(dev,
-		      "%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
-		      mlx5_command_str(opcode),
-		      opcode, op_mod,
-		      cmd_status_str(status),
-		      status,
-		      syndrome);
+		mlx5_core_err_rl(dev,
+			"%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",
+			mlx5_command_str(opcode), opcode, op_mod,
+			cmd_status_str(status), status, syndrome);
 	else
 		mlx5_core_dbg(dev,
 		      "%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x)\n",

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -66,6 +66,12 @@ do {									\
 		__func__, __LINE__, current->pid,	\
 	       ##__VA_ARGS__)
 
+#define mlx5_core_err_rl(__dev, format, ...)				\
+	dev_err_ratelimited(&(__dev)->pdev->dev,			\
+			   "%s:%d:(pid %d): " format,			\
+			   __func__, __LINE__, current->pid,		\
+			   ##__VA_ARGS__)
+
 #define mlx5_core_warn(__dev, format, ...)				\
 	dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
 		 __func__, __LINE__, current->pid,			\

drivers/net/ethernet/mellanox/mlx5/core/mr.c

@@ -146,23 +146,6 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
 }
 EXPORT_SYMBOL(mlx5_core_query_mkey);
 
-int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey,
-			     u32 *mkey)
-{
-	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)]   = {0};
-	int err;
-
-	MLX5_SET(query_special_contexts_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (!err)
-		*mkey = MLX5_GET(query_special_contexts_out, out,
-				 dump_fill_mkey);
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_dump_fill_mkey);
-
 static inline u32 mlx5_get_psv(u32 *out, int psv_index)
 {
 	switch (psv_index) {

include/linux/mlx5/driver.h

@@ -1067,8 +1067,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
 			   struct mlx5_core_mkey *mkey);
 int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey,
 			 u32 *out, int outlen);
-int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *_mkey,
-			     u32 *mkey);
 int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn);
 int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn);
 int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,

include/linux/mlx5/mlx5_ifc.h

@@ -889,7 +889,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_eq_sz[0x8];
 	u8         reserved_at_e8[0x2];
 	u8         log_max_mkey[0x6];
-	u8         reserved_at_f0[0xc];
+	u8         reserved_at_f0[0x8];
+	u8         dump_fill_mkey[0x1];
+	u8         reserved_at_f9[0x3];
 	u8         log_max_eq[0x4];
 
 	u8         max_indirection[0x8];

include/uapi/rdma/mlx5-abi.h

@@ -93,6 +93,7 @@ struct mlx5_ib_alloc_ucontext_req_v2 {
 
 enum mlx5_ib_alloc_ucontext_resp_mask {
 	MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET = 1UL << 0,
+	MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY    = 1UL << 1,
 };
 
 enum mlx5_user_cmds_supp_uhw {
@@ -141,7 +142,7 @@ struct mlx5_ib_alloc_ucontext_resp {
 	__u32	log_uar_size;
 	__u32	num_uars_per_page;
 	__u32	num_dyn_bfregs;
-	__u32	reserved3;
+	__u32	dump_fill_mkey;
 };
 
 struct mlx5_ib_alloc_pd_resp {