From 65959522f8060659e308977f09f3eb7b7af5e43f Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Tue, 23 Jun 2020 14:30:40 +0300
Subject: RDMA: Add support to dump resource tracker in RAW format

Add support to get resource dump in raw format. It enable drivers to
return the entire device specific QP/CQ/MR context without a need from the
driver to set each field separately.

The raw query returns only the device specific data, general data is still
returned by using the existing queries.

Example:

$ rdma res show mr dev mlx5_1 mrn 2 -r -j
[{"ifindex":7,"ifname":"mlx5_1",
"data":[0,4,255,254,0,0,0,0,0,0,0,0,16,28,0,216,...]}]

Link: https://lore.kernel.org/r/20200623113043.1228482-9-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/rdma/rdma_netlink.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 8e277783fa96..3826143d420d 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -287,6 +287,12 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_STAT_DEL,
 
+	RDMA_NLDEV_CMD_RES_QP_GET_RAW,
+
+	RDMA_NLDEV_CMD_RES_CQ_GET_RAW,
+
+	RDMA_NLDEV_CMD_RES_MR_GET_RAW,
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -525,6 +531,8 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_DEV_DIM,                /* u8 */
 
+	RDMA_NLDEV_ATTR_RES_RAW,	/* binary */
+
 	/*
 	 * Always the end
 	 */
-- 
cgit v1.2.3


From 1c8fb1ea5a1dbd2159e78fa580aaffb001794cfa Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Tue, 30 Jun 2020 12:39:12 +0300
Subject: IB/uverbs: Expose UAPI to query ucontext

Expose UAPI to query ucontext, this will let user space application that
didn't allocate the ucontext but has access to by owning the matching
command FD to retrieve the ucontext information.

Link: https://lore.kernel.org/r/20200630093916.332097-4-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/device.c                  |  1 +
 drivers/infiniband/core/uverbs_std_types_device.c | 41 ++++++++++++++++++++++-
 include/rdma/ib_verbs.h                           |  4 +++
 include/uapi/rdma/ib_user_ioctl_cmds.h            |  6 ++++
 4 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 40cf07129f66..1900c0df3c8a 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2674,6 +2674,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, query_port);
 	SET_DEVICE_OP(dev_ops, query_qp);
 	SET_DEVICE_OP(dev_ops, query_srq);
+	SET_DEVICE_OP(dev_ops, query_ucontext);
 	SET_DEVICE_OP(dev_ops, rdma_netdev_get_params);
 	SET_DEVICE_OP(dev_ops, read_counters);
 	SET_DEVICE_OP(dev_ops, reg_dm_mr);
diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index ae4a59d6f9b1..8e58605a17be 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -229,6 +229,37 @@ static int UVERBS_HANDLER(UVERBS_METHOD_GET_CONTEXT)(
 	return 0;
 }
 
+static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_CONTEXT)(
+	struct uverbs_attr_bundle *attrs)
+{
+	u64 core_support = IB_UVERBS_CORE_SUPPORT_OPTIONAL_MR_ACCESS;
+	struct ib_ucontext *ucontext;
+	struct ib_device *ib_dev;
+	u32 num_comp;
+	int ret;
+
+	ucontext = ib_uverbs_get_ucontext(attrs);
+	if (IS_ERR(ucontext))
+		return PTR_ERR(ucontext);
+	ib_dev = ucontext->device;
+
+	if (!ib_dev->ops.query_ucontext)
+		return -EOPNOTSUPP;
+
+	num_comp = attrs->ufile->device->num_comp_vectors;
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_CONTEXT_NUM_COMP_VECTORS,
+			     &num_comp, sizeof(num_comp));
+	if (IS_UVERBS_COPY_ERR(ret))
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_CONTEXT_CORE_SUPPORT,
+			     &core_support, sizeof(core_support));
+	if (IS_UVERBS_COPY_ERR(ret))
+		return ret;
+
+	return ucontext->device->ops.query_ucontext(ucontext, attrs);
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_GET_CONTEXT,
 	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
@@ -237,6 +268,13 @@ DECLARE_UVERBS_NAMED_METHOD(
 			    UVERBS_ATTR_TYPE(u64), UA_OPTIONAL),
 	UVERBS_ATTR_UHW());
 
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_QUERY_CONTEXT,
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_CONTEXT_NUM_COMP_VECTORS,
+			    UVERBS_ATTR_TYPE(u32), UA_OPTIONAL),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_CONTEXT_CORE_SUPPORT,
+			    UVERBS_ATTR_TYPE(u64), UA_OPTIONAL));
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_INFO_HANDLES,
 	/* Also includes any device specific object ids */
@@ -260,7 +298,8 @@ DECLARE_UVERBS_GLOBAL_METHODS(UVERBS_OBJECT_DEVICE,
 			      &UVERBS_METHOD(UVERBS_METHOD_GET_CONTEXT),
 			      &UVERBS_METHOD(UVERBS_METHOD_INVOKE_WRITE),
 			      &UVERBS_METHOD(UVERBS_METHOD_INFO_HANDLES),
-			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_PORT));
+			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_PORT),
+			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_CONTEXT));
 
 const struct uapi_definition uverbs_def_obj_device[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_DEVICE),
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 20c801730fed..6c72bb194148 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2645,6 +2645,10 @@ struct ib_device_ops {
 	 */
 	int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
 
+	/* query driver for its ucontext properties */
+	int (*query_ucontext)(struct ib_ucontext *context,
+			      struct uverbs_attr_bundle *attrs);
+
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index 4961d5e858eb..83b6e71ea216 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -69,6 +69,7 @@ enum uverbs_methods_device {
 	UVERBS_METHOD_INFO_HANDLES,
 	UVERBS_METHOD_QUERY_PORT,
 	UVERBS_METHOD_GET_CONTEXT,
+	UVERBS_METHOD_QUERY_CONTEXT,
 };
 
 enum uverbs_attrs_invoke_write_cmd_attr_ids {
@@ -87,6 +88,11 @@ enum uverbs_attrs_get_context_attr_ids {
 	UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
 };
 
+enum uverbs_attrs_query_context_attr_ids {
+	UVERBS_ATTR_QUERY_CONTEXT_NUM_COMP_VECTORS,
+	UVERBS_ATTR_QUERY_CONTEXT_CORE_SUPPORT,
+};
+
 enum uverbs_attrs_create_cq_cmd_attr_ids {
 	UVERBS_ATTR_CREATE_CQ_HANDLE,
 	UVERBS_ATTR_CREATE_CQ_CQE,
-- 
cgit v1.2.3


From 0fb556b2b58d6b8336c94379042bad2a8512af1a Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Tue, 30 Jun 2020 12:39:14 +0300
Subject: RDMA/mlx5: Implement the query ucontext functionality

Implement the query ucontext functionality by returning the original
ucontext data as part of an extra mlx5 attribute that holds the driver
UAPI response.

Link: https://lore.kernel.org/r/20200630093916.332097-6-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_ioctl.c   |  1 +
 drivers/infiniband/hw/mlx5/main.c        | 35 ++++++++++++++++++++++++++++++++
 include/uapi/rdma/mlx5_user_ioctl_cmds.h |  4 ++++
 3 files changed, 40 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index 2d882c02387c..ef04a261097f 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -790,6 +790,7 @@ int uverbs_copy_to_struct_or_zero(const struct uverbs_attr_bundle *bundle,
 	}
 	return uverbs_copy_to(bundle, idx, from, size);
 }
+EXPORT_SYMBOL(uverbs_copy_to_struct_or_zero);
 
 /* Once called an abort will call through to the type's destroy_hw() */
 void uverbs_finalize_uobj_create(const struct uverbs_attr_bundle *bundle,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 56039fa6c530..dc77388464c9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1990,6 +1990,29 @@ out_ctx:
 	return err;
 }
 
+static int mlx5_ib_query_ucontext(struct ib_ucontext *ibcontext,
+				  struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_ib_alloc_ucontext_resp uctx_resp = {};
+	int ret;
+
+	ret = set_ucontext_resp(ibcontext, &uctx_resp);
+	if (ret)
+		return ret;
+
+	uctx_resp.response_length =
+		min_t(size_t,
+		      uverbs_attr_get_len(attrs,
+				MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX),
+		      sizeof(uctx_resp));
+
+	ret = uverbs_copy_to_struct_or_zero(attrs,
+					MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX,
+					&uctx_resp,
+					sizeof(uctx_resp));
+	return ret;
+}
+
 static void mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
 {
 	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
@@ -6364,6 +6387,16 @@ ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	UVERBS_ATTR_FLAGS_IN(MLX5_IB_ATTR_CREATE_FLOW_ACTION_FLAGS,
 			     enum mlx5_ib_uapi_flow_action_flags));
 
+ADD_UVERBS_ATTRIBUTES_SIMPLE(
+	mlx5_ib_query_context,
+	UVERBS_OBJECT_DEVICE,
+	UVERBS_METHOD_QUERY_CONTEXT,
+	UVERBS_ATTR_PTR_OUT(
+		MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX,
+		UVERBS_ATTR_STRUCT(struct mlx5_ib_alloc_ucontext_resp,
+				   dump_fill_mkey),
+		UA_MANDATORY));
+
 static const struct uapi_definition mlx5_ib_defs[] = {
 	UAPI_DEF_CHAIN(mlx5_ib_devx_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_flow_defs),
@@ -6372,6 +6405,7 @@ static const struct uapi_definition mlx5_ib_defs[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION,
 				&mlx5_ib_flow_action),
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_DM, &mlx5_ib_dm),
+	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_DEVICE, &mlx5_ib_query_context),
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_VAR,
 				UAPI_DEF_IS_OBJ_SUPPORTED(var_is_supported)),
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_UAR),
@@ -6605,6 +6639,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.query_pkey = mlx5_ib_query_pkey,
 	.query_qp = mlx5_ib_query_qp,
 	.query_srq = mlx5_ib_query_srq,
+	.query_ucontext = mlx5_ib_query_ucontext,
 	.read_counters = mlx5_ib_read_counters,
 	.reg_user_mr = mlx5_ib_reg_user_mr,
 	.req_notify_cq = mlx5_ib_arm_cq,
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 8e316ef896b5..496309e8a856 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -228,6 +228,10 @@ enum mlx5_ib_flow_matcher_methods {
 	MLX5_IB_METHOD_FLOW_MATCHER_DESTROY,
 };
 
+enum mlx5_ib_device_query_context_attrs {
+	MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT),
+};
+
 #define MLX5_IB_DW_MATCH_PARAM 0x80
 
 struct mlx5_ib_match_params {
-- 
cgit v1.2.3


From 05f71ef9797454b9384c740b8acd0d02eca1d1bc Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Tue, 30 Jun 2020 12:39:15 +0300
Subject: RDMA/mlx5: Introduce UAPI to query PD attributes

Introduce UAPI to query PD attributes, this can be used to retrieve PD
attributes by having the PD handle of the created one and owning the
command FD for the ucontxet.

Link: https://lore.kernel.org/r/20200630093916.332097-7-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/Makefile      |  3 ++-
 drivers/infiniband/hw/mlx5/main.c        |  1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h     |  2 ++
 drivers/infiniband/hw/mlx5/std_types.c   | 45 ++++++++++++++++++++++++++++++++
 include/uapi/rdma/mlx5_user_ioctl_cmds.h | 10 +++++++
 5 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 drivers/infiniband/hw/mlx5/std_types.c

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index 8cca61c671f8..9838719aacb9 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -23,4 +23,5 @@ mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o
 mlx5_ib-$(CONFIG_MLX5_ESWITCH) += ib_rep.o
 mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o \
 					    flow.o \
-					    qos.o
+					    qos.o \
+					    std_types.o
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index dc77388464c9..324a98c77ad5 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6401,6 +6401,7 @@ static const struct uapi_definition mlx5_ib_defs[] = {
 	UAPI_DEF_CHAIN(mlx5_ib_devx_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_flow_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_qos_defs),
+	UAPI_DEF_CHAIN(mlx5_ib_std_types_defs),
 
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION,
 				&mlx5_ib_flow_action),
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 74d3507d6f80..27b069ef63d9 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1384,6 +1384,8 @@ int mlx5_ib_fill_stat_mr_entry(struct sk_buff *msg, struct ib_mr *ib_mr);
 extern const struct uapi_definition mlx5_ib_devx_defs[];
 extern const struct uapi_definition mlx5_ib_flow_defs[];
 extern const struct uapi_definition mlx5_ib_qos_defs[];
+extern const struct uapi_definition mlx5_ib_std_types_defs[];
+
 
 #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user);
diff --git a/drivers/infiniband/hw/mlx5/std_types.c b/drivers/infiniband/hw/mlx5/std_types.c
new file mode 100644
index 000000000000..16145fda68d0
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/std_types.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2020, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <rdma/uverbs_ioctl.h>
+#include <rdma/mlx5_user_ioctl_cmds.h>
+#include <rdma/mlx5_user_ioctl_verbs.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_ib.h"
+
+#define UVERBS_MODULE_NAME mlx5_ib
+#include <rdma/uverbs_named_ioctl.h>
+
+static int UVERBS_HANDLER(MLX5_IB_METHOD_PD_QUERY)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_pd *pd =
+		uverbs_attr_get_obj(attrs, MLX5_IB_ATTR_QUERY_PD_HANDLE);
+	struct mlx5_ib_pd *mpd = to_mpd(pd);
+
+	return uverbs_copy_to(attrs, MLX5_IB_ATTR_QUERY_PD_RESP_PDN,
+			      &mpd->pdn, sizeof(mpd->pdn));
+}
+
+DECLARE_UVERBS_NAMED_METHOD(
+	MLX5_IB_METHOD_PD_QUERY,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_QUERY_PD_HANDLE,
+			UVERBS_OBJECT_PD,
+			UVERBS_ACCESS_READ,
+			UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_QUERY_PD_RESP_PDN,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_MANDATORY));
+
+ADD_UVERBS_METHODS(mlx5_ib_pd,
+		   UVERBS_OBJECT_PD,
+		   &UVERBS_METHOD(MLX5_IB_METHOD_PD_QUERY));
+
+const struct uapi_definition mlx5_ib_std_types_defs[] = {
+	UAPI_DEF_CHAIN_OBJ_TREE(
+		UVERBS_OBJECT_PD,
+		&mlx5_ib_pd),
+	{},
+};
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 496309e8a856..b330e6eee626 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -290,4 +290,14 @@ enum mlx5_ib_create_flow_action_create_packet_reformat_attrs {
 	MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF,
 };
 
+enum mlx5_ib_query_pd_attrs {
+	MLX5_IB_ATTR_QUERY_PD_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_QUERY_PD_RESP_PDN,
+};
+
+enum mlx5_ib_pd_methods {
+	MLX5_IB_METHOD_PD_QUERY = (1U << UVERBS_ID_NS_SHIFT),
+
+};
+
 #endif
-- 
cgit v1.2.3


From 6c01e6b218aea09ec9947cbf88a4db97b4dd155c Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Tue, 30 Jun 2020 12:39:16 +0300
Subject: IB/uverbs: Expose UAPI to query MR

Expose UAPI to query MR, this will let user space application that
didn't allocate the MR but has access to by owning the matching command
FD to retrieve its information.

Link: https://lore.kernel.org/r/20200630093916.332097-8-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_mr.c | 52 ++++++++++++++++++++++++++-
 include/uapi/rdma/ib_user_ioctl_cmds.h        |  9 +++++
 2 files changed, 60 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/uverbs_std_types_mr.c b/drivers/infiniband/core/uverbs_std_types_mr.c
index a2722ef8496e..62f58ad56afd 100644
--- a/drivers/infiniband/core/uverbs_std_types_mr.c
+++ b/drivers/infiniband/core/uverbs_std_types_mr.c
@@ -148,6 +148,36 @@ static int UVERBS_HANDLER(UVERBS_METHOD_DM_MR_REG)(
 	return ret;
 }
 
+static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_MR)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_mr *mr =
+		uverbs_attr_get_obj(attrs, UVERBS_ATTR_QUERY_MR_HANDLE);
+	int ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_MR_RESP_LKEY, &mr->lkey,
+			     sizeof(mr->lkey));
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_MR_RESP_RKEY,
+			     &mr->rkey, sizeof(mr->rkey));
+
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_MR_RESP_LENGTH,
+			     &mr->length, sizeof(mr->length));
+
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_QUERY_MR_RESP_IOVA,
+			     &mr->iova, sizeof(mr->iova));
+
+	return IS_UVERBS_COPY_ERR(ret) ? ret : 0;
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_ADVISE_MR,
 	UVERBS_ATTR_IDR(UVERBS_ATTR_ADVISE_MR_PD_HANDLE,
@@ -165,6 +195,25 @@ DECLARE_UVERBS_NAMED_METHOD(
 			   UA_MANDATORY,
 			   UA_ALLOC_AND_COPY));
 
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_QUERY_MR,
+	UVERBS_ATTR_IDR(UVERBS_ATTR_QUERY_MR_HANDLE,
+			UVERBS_OBJECT_MR,
+			UVERBS_ACCESS_READ,
+			UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_MR_RESP_RKEY,
+			    UVERBS_ATTR_TYPE(u32),
+			    UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_MR_RESP_LKEY,
+			    UVERBS_ATTR_TYPE(u32),
+			    UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_MR_RESP_LENGTH,
+			    UVERBS_ATTR_TYPE(u64),
+			    UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_MR_RESP_IOVA,
+			    UVERBS_ATTR_TYPE(u64),
+			    UA_OPTIONAL));
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_DM_MR_REG,
 	UVERBS_ATTR_IDR(UVERBS_ATTR_REG_DM_MR_HANDLE,
@@ -206,7 +255,8 @@ DECLARE_UVERBS_NAMED_OBJECT(
 	UVERBS_TYPE_ALLOC_IDR(uverbs_free_mr),
 	&UVERBS_METHOD(UVERBS_METHOD_DM_MR_REG),
 	&UVERBS_METHOD(UVERBS_METHOD_MR_DESTROY),
-	&UVERBS_METHOD(UVERBS_METHOD_ADVISE_MR));
+	&UVERBS_METHOD(UVERBS_METHOD_ADVISE_MR),
+	&UVERBS_METHOD(UVERBS_METHOD_QUERY_MR));
 
 const struct uapi_definition uverbs_def_obj_mr[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_MR,
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index 83b6e71ea216..99dcabf61a71 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -248,6 +248,7 @@ enum uverbs_methods_mr {
 	UVERBS_METHOD_DM_MR_REG,
 	UVERBS_METHOD_MR_DESTROY,
 	UVERBS_METHOD_ADVISE_MR,
+	UVERBS_METHOD_QUERY_MR,
 };
 
 enum uverbs_attrs_mr_destroy_ids {
@@ -261,6 +262,14 @@ enum uverbs_attrs_advise_mr_cmd_attr_ids {
 	UVERBS_ATTR_ADVISE_MR_SGE_LIST,
 };
 
+enum uverbs_attrs_query_mr_cmd_attr_ids {
+	UVERBS_ATTR_QUERY_MR_HANDLE,
+	UVERBS_ATTR_QUERY_MR_RESP_LKEY,
+	UVERBS_ATTR_QUERY_MR_RESP_RKEY,
+	UVERBS_ATTR_QUERY_MR_RESP_LENGTH,
+	UVERBS_ATTR_QUERY_MR_RESP_IOVA,
+};
+
 enum uverbs_attrs_create_counters_cmd_attr_ids {
 	UVERBS_ATTR_CREATE_COUNTERS_HANDLE,
 };
-- 
cgit v1.2.3


From 7c97f3aded10aa86fc1944341288434117e9c926 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Thu, 2 Jul 2020 11:29:31 +0300
Subject: RDMA/counter: Add PID category support in auto mode

With the "PID" category QPs have same PID will be bound to same counter;
If this category is not set then QPs have different PIDs will be bound
to same counter.

This is implemented for 2 reasons:
1. The counter is a limited resource, while there may be dozens of
   applications, each of which creates several types of QPs, which means
   it may doesn't have enough counter.
2. The system administrator needs all QPs created by all applications
   with same type bound to one counter.

The counter name and PID is only make sense when "PID" category are
configured.

This category can also be used in combine with others, e.g. QP type.

Link: https://lore.kernel.org/r/20200702082933.424537-2-leon@kernel.org
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/counters.c | 20 +++++---------------
 drivers/infiniband/core/nldev.c    |  8 ++++++--
 include/uapi/rdma/rdma_netlink.h   |  1 +
 3 files changed, 12 insertions(+), 17 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index 2257d7f7810f..40204c6caa5b 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -8,7 +8,7 @@
 #include "core_priv.h"
 #include "restrack.h"
 
-#define ALL_AUTO_MODE_MASKS (RDMA_COUNTER_MASK_QP_TYPE)
+#define ALL_AUTO_MODE_MASKS (RDMA_COUNTER_MASK_QP_TYPE | RDMA_COUNTER_MASK_PID)
 
 static int __counter_set_mode(struct rdma_counter_mode *curr,
 			      enum rdma_nl_counter_mode new_mode,
@@ -149,23 +149,13 @@ static bool auto_mode_match(struct ib_qp *qp, struct rdma_counter *counter,
 	struct auto_mode_param *param = &counter->mode.param;
 	bool match = true;
 
-	/*
-	 * Ensure that counter belongs to the right PID.  This operation can
-	 * race with user space which kills the process and leaves QP and
-	 * counters orphans.
-	 *
-	 * It is not a big deal because exitted task will leave both QP and
-	 * counter in the same bucket of zombie process. Just ensure that
-	 * process is still alive before procedding.
-	 *
-	 */
-	if (task_pid_nr(counter->res.task) != task_pid_nr(qp->res.task) ||
-	    !task_pid_nr(qp->res.task))
-		return false;
-
 	if (auto_mask & RDMA_COUNTER_MASK_QP_TYPE)
 		match &= (param->qp_type == qp->qp_type);
 
+	if (auto_mask & RDMA_COUNTER_MASK_PID)
+		match &= (task_pid_nr(counter->res.task) ==
+			  task_pid_nr(qp->res.task));
+
 	return match;
 }
 
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 1051b5622b62..76af7ea2875d 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -711,11 +711,16 @@ static int fill_stat_counter_mode(struct sk_buff *msg,
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, m->mode))
 		return -EMSGSIZE;
 
-	if (m->mode == RDMA_COUNTER_MODE_AUTO)
+	if (m->mode == RDMA_COUNTER_MODE_AUTO) {
 		if ((m->mask & RDMA_COUNTER_MASK_QP_TYPE) &&
 		    nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, m->param.qp_type))
 			return -EMSGSIZE;
 
+		if ((m->mask & RDMA_COUNTER_MASK_PID) &&
+		    fill_res_name_pid(msg, &counter->res))
+			return -EMSGSIZE;
+	}
+
 	return 0;
 }
 
@@ -855,7 +860,6 @@ static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin,
 
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, counter->port) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, counter->id) ||
-	    fill_res_name_pid(msg, &counter->res) ||
 	    fill_stat_counter_mode(msg, counter) ||
 	    fill_stat_counter_qps(msg, counter) ||
 	    fill_stat_counter_hwcounters(msg, counter))
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 3826143d420d..d2f5b8396243 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -569,5 +569,6 @@ enum rdma_nl_counter_mode {
  */
 enum rdma_nl_counter_mask {
 	RDMA_COUNTER_MASK_QP_TYPE = 1,
+	RDMA_COUNTER_MASK_PID = 1 << 1,
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3


From bbe4f4245271bd0f21bf826996c0c5d87a3529c9 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Tue, 7 Jul 2020 09:30:59 +0300
Subject: RDMA/qedr: Add EDPM mode type for user-fw compatibility

In older FW versions the completion flag was treated as the ack flag in
edpm messages.  commit ff937b916eb6 ("qed: Add EDPM mode type for user-fw
compatibility") exposed the FW option of setting which mode the QP is in
by adding a flag to the qedr <-> qed API.

This patch adds the qedr <-> libqedr interface so that the libqedr can set
the flag appropriately and qedr can pass it down to FW.  Flag is added for
backward compatibility with libqedr.

For older libs, this flag didn't exist and therefore set to zero.

Fixes: ac1b36e55a51 ("qedr: Add support for user context verbs")
Link: https://lore.kernel.org/r/20200707063100.3811-2-michal.kalderon@marvell.com
Signed-off-by: Yuval Bason <yuval.bason@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/qedr/qedr.h  |  1 +
 drivers/infiniband/hw/qedr/verbs.c | 11 ++++++++---
 include/uapi/rdma/qedr-abi.h       |  4 ++--
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index aa332027da86..460292179b32 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -235,6 +235,7 @@ struct qedr_ucontext {
 	u32 dpi_size;
 	u16 dpi;
 	bool db_rec;
+	u8 edpm_mode;
 };
 
 union db_prod32 {
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 42273aa0b5e1..5008149ea116 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -275,7 +275,8 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 			DP_ERR(dev, "Problem copying data from user space\n");
 			return -EFAULT;
 		}
-
+		ctx->edpm_mode = !!(ureq.context_flags &
+				    QEDR_ALLOC_UCTX_EDPM_MODE);
 		ctx->db_rec = !!(ureq.context_flags & QEDR_ALLOC_UCTX_DB_REC);
 	}
 
@@ -316,7 +317,8 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 		uresp.dpm_flags = QEDR_DPM_TYPE_IWARP_LEGACY;
 	else
 		uresp.dpm_flags = QEDR_DPM_TYPE_ROCE_ENHANCED |
-				  QEDR_DPM_TYPE_ROCE_LEGACY;
+				  QEDR_DPM_TYPE_ROCE_LEGACY |
+				  QEDR_DPM_TYPE_ROCE_EDPM_MODE;
 
 	uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
 	uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
@@ -1750,7 +1752,7 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 	struct qed_rdma_create_qp_out_params out_params;
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
 	struct qedr_create_qp_uresp uresp;
-	struct qedr_ucontext *ctx = NULL;
+	struct qedr_ucontext *ctx = pd ? pd->uctx : NULL;
 	struct qedr_create_qp_ureq ureq;
 	int alloc_and_init = rdma_protocol_roce(&dev->ibdev, 1);
 	int rc = -EINVAL;
@@ -1788,6 +1790,9 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 		in_params.rq_pbl_ptr = qp->urq.pbl_tbl->pa;
 	}
 
+	if (ctx)
+		SET_FIELD(in_params.flags, QED_ROCE_EDPM_MODE, ctx->edpm_mode);
+
 	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
 					      &in_params, &out_params);
 
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index a0b83c9d4498..b261c9fca07b 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -39,7 +39,7 @@
 
 /* user kernel communication data structures. */
 enum qedr_alloc_ucontext_flags {
-	QEDR_ALLOC_UCTX_RESERVED	= 1 << 0,
+	QEDR_ALLOC_UCTX_EDPM_MODE	= 1 << 0,
 	QEDR_ALLOC_UCTX_DB_REC		= 1 << 1
 };
 
@@ -56,7 +56,7 @@ enum qedr_rdma_dpm_type {
 	QEDR_DPM_TYPE_ROCE_ENHANCED	= 1 << 0,
 	QEDR_DPM_TYPE_ROCE_LEGACY	= 1 << 1,
 	QEDR_DPM_TYPE_IWARP_LEGACY	= 1 << 2,
-	QEDR_DPM_TYPE_RESERVED		= 1 << 3,
+	QEDR_DPM_TYPE_ROCE_EDPM_MODE	= 1 << 3,
 	QEDR_DPM_SIZES_SET		= 1 << 4,
 };
 
-- 
cgit v1.2.3


From eb7f84e379daad69b4c92538baeaf93bbf493c14 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Tue, 7 Jul 2020 09:31:00 +0300
Subject: RDMA/qedr: Add EDPM max size to alloc ucontext response

User space should receive the maximum edpm size from kernel driver,
similar to other edpm/ldpm related limits.  Add an additional parameter to
the alloc_ucontext_resp structure for the edpm maximum size.

In addition, pass an indication from user-space to kernel
(and not just kernel to user) that the DPM sizes are supported.

This is for supporting backward-forward compatibility between driver and
lib for everything related to DPM transaction and limit sizes.

This should have been part of commit mentioned in Fixes tag.

Link: https://lore.kernel.org/r/20200707063100.3811-3-michal.kalderon@marvell.com
Fixes: 93a3d05f9d68 ("RDMA/qedr: Add kernel capability flags for dpm enabled mode")
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/qedr/verbs.c | 9 ++++++---
 include/uapi/rdma/qedr-abi.h       | 6 +++++-
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 5008149ea116..fcf2eaa3b459 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -320,9 +320,12 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 				  QEDR_DPM_TYPE_ROCE_LEGACY |
 				  QEDR_DPM_TYPE_ROCE_EDPM_MODE;
 
-	uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
-	uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
-	uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+	if (ureq.context_flags & QEDR_SUPPORT_DPM_SIZES) {
+		uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
+		uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
+		uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+		uresp.edpm_limit_size = QEDR_EDPM_MAX_SIZE;
+	}
 
 	uresp.wids_enabled = 1;
 	uresp.wid_count = oparams.wid_count;
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index b261c9fca07b..bf7333b2b5d7 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -40,7 +40,8 @@
 /* user kernel communication data structures. */
 enum qedr_alloc_ucontext_flags {
 	QEDR_ALLOC_UCTX_EDPM_MODE	= 1 << 0,
-	QEDR_ALLOC_UCTX_DB_REC		= 1 << 1
+	QEDR_ALLOC_UCTX_DB_REC		= 1 << 1,
+	QEDR_SUPPORT_DPM_SIZES		= 1 << 2,
 };
 
 struct qedr_alloc_ucontext_req {
@@ -50,6 +51,7 @@ struct qedr_alloc_ucontext_req {
 
 #define QEDR_LDPM_MAX_SIZE	(8192)
 #define QEDR_EDPM_TRANS_SIZE	(64)
+#define QEDR_EDPM_MAX_SIZE	(ROCE_REQ_MAX_INLINE_DATA_SIZE)
 
 enum qedr_rdma_dpm_type {
 	QEDR_DPM_TYPE_NONE		= 0,
@@ -77,6 +79,8 @@ struct qedr_alloc_ucontext_resp {
 	__u16 ldpm_limit_size;
 	__u8 edpm_trans_size;
 	__u8 reserved;
+	__u16 edpm_limit_size;
+	__u8 padding[6];
 };
 
 struct qedr_alloc_pd_ureq {
-- 
cgit v1.2.3


From 8e7eafb816ab7e5047b74cb8eb1db2f8f14f7d7a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:32:20 -0700
Subject: RDMA: rdma_user_ioctl.h: fix a duplicated word + clarify

Change the repeated word "it" in a comment to "it to".
Also insert a dash in the sentence to add clarity.

Link: https://lore.kernel.org/r/20200719003220.21250-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/rdma/rdma_user_ioctl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index d92d2721b28c..53c55188dd2a 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -43,7 +43,7 @@
 
 /*
  * General blocks assignments
- * It is closed on purpose do not expose it it user space
+ * It is closed on purpose - do not expose it to user space
  * #define MAD_CMD_BASE		0x00
  * #define HFI1_CMD_BAS		0xE0
  */
-- 
cgit v1.2.3


From 8b603d0715a372f5827d3a6b19d9568bf854b687 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Fri, 24 Jul 2020 10:41:12 +0200
Subject: RDMA/mlx5: Fix typo in enum name

Nnothing uses the enum name, so this is harmless.

Fixes: 322694412400 ("IB/mlx5: Introduce driver create and destroy flow methods")
Link: https://lore.kernel.org/r/20200724084112.GC31930@amd
Signed-off-by: Pavel Machek (CIP) <pavel@denx.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/rdma/mlx5_user_ioctl_cmds.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index b330e6eee626..e24d66d278cf 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -263,7 +263,7 @@ enum mlx5_ib_create_flow_attrs {
 	MLX5_IB_ATTR_CREATE_FLOW_FLAGS,
 };
 
-enum mlx5_ib_destoy_flow_attrs {
+enum mlx5_ib_destroy_flow_attrs {
 	MLX5_IB_ATTR_DESTROY_FLOW_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
 };
 
-- 
cgit v1.2.3


From 556c811f24b30cc883733a2eaf9e939817589231 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Wed, 22 Jul 2020 17:03:09 +0300
Subject: RDMA/efa: Expose maximum TX doorbell batch

The device reports the maximum number of bytes to be written before
ringing the doorbell (zero means unlimited).

This patch queries the max batch size and reports it back to the userspace
library.

Link: https://lore.kernel.org/r/20200722140312.3651-2-galpress@amazon.com
Reviewed-by: Daniel Kranzdorf <dkkranzd@amazon.com>
Reviewed-by: Firas JahJah <firasj@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 11 +++++++++++
 drivers/infiniband/hw/efa/efa_com_cmd.c         |  1 +
 drivers/infiniband/hw/efa/efa_com_cmd.h         |  1 +
 drivers/infiniband/hw/efa/efa_verbs.c           |  1 +
 include/uapi/rdma/efa-abi.h                     |  4 +++-
 5 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index bef2bd291054..03e7388af06e 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -632,6 +632,17 @@ struct efa_admin_feature_queue_attr_desc {
 
 	/* Maximum number of SGEs for a single RDMA read WQE */
 	u16 max_wr_rdma_sges;
+
+	/*
+	 * Maximum number of bytes that can be written to SQ between two
+	 * consecutive doorbells (in units of 64B). Driver must ensure that only
+	 * complete WQEs are written to queue before issuing a doorbell.
+	 * Examples: max_tx_batch=16 and WQE size = 64B, means up to 16 WQEs can
+	 * be written to SQ between two consecutive doorbells. max_tx_batch=11
+	 * and WQE size = 128B, means up to 5 WQEs can be written to SQ between
+	 * two consecutive doorbells. Zero means unlimited.
+	 */
+	u16 max_tx_batch;
 };
 
 struct efa_admin_feature_aenq_desc {
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c
index fabd8df2e78f..53cfde5c43d8 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.c
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.c
@@ -480,6 +480,7 @@ int efa_com_get_device_attr(struct efa_com_dev *edev,
 	result->max_llq_size = resp.u.queue_attr.max_llq_size;
 	result->sub_cqs_per_cq = resp.u.queue_attr.sub_cqs_per_cq;
 	result->max_wr_rdma_sge = resp.u.queue_attr.max_wr_rdma_sges;
+	result->max_tx_batch = resp.u.queue_attr.max_tx_batch;
 
 	err = efa_com_get_feature(edev, &resp, EFA_ADMIN_NETWORK_ATTR);
 	if (err) {
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h
index 41ce4a476ee6..8df2a26d57d4 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.h
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.h
@@ -127,6 +127,7 @@ struct efa_com_get_device_attr_result {
 	u16 max_sq_sge;
 	u16 max_rq_sge;
 	u16 max_wr_rdma_sge;
+	u16 max_tx_batch;
 	u8 db_bar;
 };
 
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 08313f7c73bc..f49d14cebe4a 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1525,6 +1525,7 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata)
 	resp.sub_cqs_per_cq = dev->dev_attr.sub_cqs_per_cq;
 	resp.inline_buf_size = dev->dev_attr.inline_buf_size;
 	resp.max_llq_size = dev->dev_attr.max_llq_size;
+	resp.max_tx_batch = dev->dev_attr.max_tx_batch;
 
 	if (udata && udata->outlen) {
 		err = ib_copy_to_udata(udata, &resp,
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 53b6e2036a9b..10781763da37 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
 /*
- * Copyright 2018-2019 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef EFA_ABI_USER_H
@@ -31,6 +31,8 @@ struct efa_ibv_alloc_ucontext_resp {
 	__u16 sub_cqs_per_cq;
 	__u16 inline_buf_size;
 	__u32 max_llq_size; /* bytes */
+	__u16 max_tx_batch; /* units of 64 bytes */
+	__u8 reserved_90[6];
 };
 
 struct efa_ibv_alloc_pd_resp {
-- 
cgit v1.2.3


From da2924bdca99768442c5e0ed0a9024ae79d62765 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Wed, 22 Jul 2020 17:03:10 +0300
Subject: RDMA/efa: Expose minimum SQ size

The device reports the minimum SQ size required for creation.

This patch queries the min SQ size and reports it back to the userspace
library.

Link: https://lore.kernel.org/r/20200722140312.3651-3-galpress@amazon.com
Reviewed-by: Firas JahJah <firasj@amazon.com>
Reviewed-by: Shadi Ammouri <sammouri@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 4 ++--
 drivers/infiniband/hw/efa/efa_com_cmd.c         | 1 +
 drivers/infiniband/hw/efa/efa_com_cmd.h         | 1 +
 drivers/infiniband/hw/efa/efa_verbs.c           | 1 +
 include/uapi/rdma/efa-abi.h                     | 3 ++-
 5 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index 03e7388af06e..5484b08bbc5d 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -606,8 +606,8 @@ struct efa_admin_feature_queue_attr_desc {
 	/* Number of sub-CQs to be created for each CQ */
 	u16 sub_cqs_per_cq;
 
-	/* MBZ */
-	u16 reserved;
+	/* Minimum number of WQEs per SQ */
+	u16 min_sq_depth;
 
 	/* Maximum number of SGEs (buffers) allowed for a single send WQE */
 	u16 max_wr_send_sges;
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c
index 53cfde5c43d8..6ac23627f65a 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.c
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.c
@@ -481,6 +481,7 @@ int efa_com_get_device_attr(struct efa_com_dev *edev,
 	result->sub_cqs_per_cq = resp.u.queue_attr.sub_cqs_per_cq;
 	result->max_wr_rdma_sge = resp.u.queue_attr.max_wr_rdma_sges;
 	result->max_tx_batch = resp.u.queue_attr.max_tx_batch;
+	result->min_sq_depth = resp.u.queue_attr.min_sq_depth;
 
 	err = efa_com_get_feature(edev, &resp, EFA_ADMIN_NETWORK_ATTR);
 	if (err) {
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h
index 8df2a26d57d4..190bac23f585 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.h
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.h
@@ -128,6 +128,7 @@ struct efa_com_get_device_attr_result {
 	u16 max_rq_sge;
 	u16 max_wr_rdma_sge;
 	u16 max_tx_batch;
+	u16 min_sq_depth;
 	u8 db_bar;
 };
 
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index f49d14cebe4a..26102ab333b2 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1526,6 +1526,7 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata)
 	resp.inline_buf_size = dev->dev_attr.inline_buf_size;
 	resp.max_llq_size = dev->dev_attr.max_llq_size;
 	resp.max_tx_batch = dev->dev_attr.max_tx_batch;
+	resp.min_sq_wr = dev->dev_attr.min_sq_depth;
 
 	if (udata && udata->outlen) {
 		err = ib_copy_to_udata(udata, &resp,
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 10781763da37..7ef2306f8dd4 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -32,7 +32,8 @@ struct efa_ibv_alloc_ucontext_resp {
 	__u16 inline_buf_size;
 	__u32 max_llq_size; /* bytes */
 	__u16 max_tx_batch; /* units of 64 bytes */
-	__u8 reserved_90[6];
+	__u16 min_sq_wr;
+	__u8 reserved_a0[4];
 };
 
 struct efa_ibv_alloc_pd_resp {
-- 
cgit v1.2.3


From a5d87b698547233321466b2dc91271f5855a4df6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Wed, 22 Jul 2020 17:03:11 +0300
Subject: RDMA/efa: User/kernel compatibility handshake mechanism

Introduce a mechanism that performs an handshake between the userspace
provider and kernel driver which verifies that the user supports all
required features in order to operate correctly.

The handshake verifies the needed functionality by comparing the reported
device caps and the provider caps. If the device reports a non-zero
capability the appropriate comp mask is required from the userspace
provider in order to allocate the context.

Link: https://lore.kernel.org/r/20200722140312.3651-4-galpress@amazon.com
Reviewed-by: Shadi Ammouri <sammouri@amazon.com>
Reviewed-by: Yossi Leybovich <sleybo@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/efa/efa_verbs.c | 40 +++++++++++++++++++++++++++++++++++
 include/uapi/rdma/efa-abi.h           | 10 +++++++++
 2 files changed, 50 insertions(+)

(limited to 'include/uapi')

diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 26102ab333b2..fda175836fb6 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1501,11 +1501,39 @@ static int efa_dealloc_uar(struct efa_dev *dev, u16 uarn)
 	return efa_com_dealloc_uar(&dev->edev, &params);
 }
 
+#define EFA_CHECK_USER_COMP(_dev, _comp_mask, _attr, _mask, _attr_str) \
+	(_attr_str = (!(_dev)->dev_attr._attr || ((_comp_mask) & (_mask))) ? \
+		     NULL : #_attr)
+
+static int efa_user_comp_handshake(const struct ib_ucontext *ibucontext,
+				   const struct efa_ibv_alloc_ucontext_cmd *cmd)
+{
+	struct efa_dev *dev = to_edev(ibucontext->device);
+	char *attr_str;
+
+	if (EFA_CHECK_USER_COMP(dev, cmd->comp_mask, max_tx_batch,
+				EFA_ALLOC_UCONTEXT_CMD_COMP_TX_BATCH, attr_str))
+		goto err;
+
+	if (EFA_CHECK_USER_COMP(dev, cmd->comp_mask, min_sq_depth,
+				EFA_ALLOC_UCONTEXT_CMD_COMP_MIN_SQ_WR,
+				attr_str))
+		goto err;
+
+	return 0;
+
+err:
+	ibdev_dbg(&dev->ibdev, "Userspace handshake failed for %s attribute\n",
+		  attr_str);
+	return -EOPNOTSUPP;
+}
+
 int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata)
 {
 	struct efa_ucontext *ucontext = to_eucontext(ibucontext);
 	struct efa_dev *dev = to_edev(ibucontext->device);
 	struct efa_ibv_alloc_ucontext_resp resp = {};
+	struct efa_ibv_alloc_ucontext_cmd cmd = {};
 	struct efa_com_alloc_uar_result result;
 	int err;
 
@@ -1514,6 +1542,18 @@ int efa_alloc_ucontext(struct ib_ucontext *ibucontext, struct ib_udata *udata)
 	 * we will ack input fields in our response.
 	 */
 
+	err = ib_copy_from_udata(&cmd, udata,
+				 min(sizeof(cmd), udata->inlen));
+	if (err) {
+		ibdev_dbg(&dev->ibdev,
+			  "Cannot copy udata for alloc_ucontext\n");
+		goto err_out;
+	}
+
+	err = efa_user_comp_handshake(ibucontext, &cmd);
+	if (err)
+		goto err_out;
+
 	err = efa_com_alloc_uar(&dev->edev, &result);
 	if (err)
 		goto err_out;
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 7ef2306f8dd4..507a2862bedb 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -20,6 +20,16 @@
  * hex bit offset of the field.
  */
 
+enum {
+	EFA_ALLOC_UCONTEXT_CMD_COMP_TX_BATCH  = 1 << 0,
+	EFA_ALLOC_UCONTEXT_CMD_COMP_MIN_SQ_WR = 1 << 1,
+};
+
+struct efa_ibv_alloc_ucontext_cmd {
+	__u32 comp_mask;
+	__u8 reserved_20[4];
+};
+
 enum efa_ibv_user_cmds_supp_udata {
 	EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE = 1 << 0,
 	EFA_USER_CMDS_SUPP_UDATA_CREATE_AH    = 1 << 1,
-- 
cgit v1.2.3