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

Pull rdma updates from Jason Gunthorpe:

 - Usual minor updates and fixes for bnxt_re, hfi1, rxe, mana, iser,
   mlx5, vmw_pvrdma, hns

 - Make rxe work on tun devices

 - mana gains more standard verbs as it moves toward supporting
   in-kernel verbs

 - DMABUF support for mana

 - Fix page size calculations when memory registration exceeds 4G

 - On Demand Paging support for rxe

 - mlx5 support for RDMA TRANSPORT flow tables and a new ucap mechanism
   to access control use of them

 - Optional RDMA_TX/RX counters per QP in mlx5

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (73 commits)
  IB/mad: Check available slots before posting receive WRs
  RDMA/mana_ib: Fix integer overflow during queue creation
  RDMA/mlx5: Fix calculation of total invalidated pages
  RDMA/mlx5: Fix mlx5_poll_one() cur_qp update flow
  RDMA/mlx5: Fix page_size variable overflow
  RDMA/mlx5: Drop access_flags from _mlx5_mr_cache_alloc()
  RDMA/mlx5: Fix cache entry update on dereg error
  RDMA/mlx5: Fix MR cache initialization error flow
  RDMA/mlx5: Support optional-counters binding for QPs
  RDMA/mlx5: Compile fs.c regardless of INFINIBAND_USER_ACCESS config
  RDMA/core: Pass port to counter bind/unbind operations
  RDMA/core: Add support to optional-counters binding configuration
  RDMA/core: Create and destroy rdma_counter using rdma_zalloc_drv_obj()
  RDMA/mlx5: Add optional counters for RDMA_TX/RX_packets/bytes
  RDMA/core: Fix use-after-free when rename device name
  RDMA/bnxt_re: Support perf management counters
  RDMA/rxe: Fix incorrect return value of rxe_odp_atomic_op()
  RDMA/uverbs: Propagate errors from rdma_lookup_get_uobject()
  RDMA/mana_ib: Handle net event for pointing to the current netdev
  net: mana: Change the function signature of mana_get_primary_netdev_rcu
  ...

11 files changed, 82 insertions, 8 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 904804e995aa..6822cfa5f4ad 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1533,8 +1533,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 	return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz;
 }
 
-#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2
-#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1
+#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 6
+#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 4
 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16
 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16
 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 62e9d7673862..228603bf03f2 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -152,6 +152,7 @@ struct gdma_general_req {
 #define GDMA_MESSAGE_V1 1
 #define GDMA_MESSAGE_V2 2
 #define GDMA_MESSAGE_V3 3
+#define GDMA_MESSAGE_V4 4
 
 struct gdma_general_resp {
 	struct gdma_resp_hdr hdr;
@@ -778,6 +779,7 @@ struct gdma_destroy_dma_region_req {
 
 enum gdma_pd_flags {
 	GDMA_PD_FLAG_INVALID = 0,
+	GDMA_PD_FLAG_ALLOW_GPA_MR = 1,
 };
 
 struct gdma_create_pd_req {
@@ -803,6 +805,11 @@ struct gdma_destory_pd_resp {
 };/* HW DATA */
 
 enum gdma_mr_type {
+	/*
+	 * Guest Physical Address - MRs of this type allow access
+	 * to any DMA-mapped memory using bus-logical address
+	 */
+	GDMA_MR_TYPE_GPA = 1,
 	/* Guest Virtual Address - MRs of this type allow access
 	 * to memory mapped by PTEs associated with this MR using a virtual
 	 * address that is set up in the MST
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 0d00b24eacaf..0f78065de8fe 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -827,5 +827,7 @@ int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
 		   u32 doorbell_pg_id);
 void mana_uncfg_vport(struct mana_port_context *apc);
 
-struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index);
+struct net_device *mana_get_primary_netdev(struct mana_context *ac,
+					   u32 port_index,
+					   netdevice_tracker *tracker);
 #endif /* _MANA_H */
diff --git a/include/rdma/ib_ucaps.h b/include/rdma/ib_ucaps.h
new file mode 100644
index 000000000000..d9f96be3a553
--- /dev/null
+++ b/include/rdma/ib_ucaps.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#ifndef _IB_UCAPS_H_
+#define _IB_UCAPS_H_
+
+#define UCAP_ENABLED(ucaps, type) (!!((ucaps) & (1U << (type))))
+
+enum rdma_user_cap {
+	RDMA_UCAP_MLX5_CTRL_LOCAL,
+	RDMA_UCAP_MLX5_CTRL_OTHER_VHCA,
+	RDMA_UCAP_MAX
+};
+
+void ib_cleanup_ucaps(void);
+int ib_get_ucaps(int *fds, int fd_count, uint64_t *idx_mask);
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
+int ib_create_ucap(enum rdma_user_cap type);
+void ib_remove_ucap(enum rdma_user_cap type);
+#else
+static inline int ib_create_ucap(enum rdma_user_cap type)
+{
+	return -EOPNOTSUPP;
+}
+static inline void ib_remove_ucap(enum rdma_user_cap type) {}
+#endif /* CONFIG_INFINIBAND_USER_ACCESS */
+
+#endif /* _IB_UCAPS_H_ */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0ad104dae253..d42eae69d9a8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -519,6 +519,23 @@ enum ib_port_state {
 	IB_PORT_ACTIVE_DEFER	= 5
 };
 
+static inline const char *__attribute_const__
+ib_port_state_to_str(enum ib_port_state state)
+{
+	const char * const states[] = {
+		[IB_PORT_NOP] = "NOP",
+		[IB_PORT_DOWN] = "DOWN",
+		[IB_PORT_INIT] = "INIT",
+		[IB_PORT_ARMED] = "ARMED",
+		[IB_PORT_ACTIVE] = "ACTIVE",
+		[IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER",
+	};
+
+	if (state < ARRAY_SIZE(states))
+		return states[state];
+	return "UNKNOWN";
+}
+
 enum ib_port_phys_state {
 	IB_PORT_PHYS_STATE_SLEEP = 1,
 	IB_PORT_PHYS_STATE_POLLING = 2,
@@ -1513,6 +1530,7 @@ struct ib_ucontext {
 	struct ib_uverbs_file  *ufile;
 
 	struct ib_rdmacg_object	cg_obj;
+	u64 enabled_caps;
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */
@@ -2626,12 +2644,13 @@ struct ib_device_ops {
 	 * @counter - The counter to be bound. If counter->id is zero then
 	 *   the driver needs to allocate a new counter and set counter->id
 	 */
-	int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp);
+	int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp,
+			       u32 port);
 	/**
 	 * counter_unbind_qp - Unbind the qp from the dynamically-allocated
 	 *   counter and bind it onto the default one
 	 */
-	int (*counter_unbind_qp)(struct ib_qp *qp);
+	int (*counter_unbind_qp)(struct ib_qp *qp, u32 port);
 	/**
 	 * counter_dealloc -De-allocate the hw counter
 	 */
@@ -2648,6 +2667,11 @@ struct ib_device_ops {
 	int (*counter_update_stats)(struct rdma_counter *counter);
 
 	/**
+	 * counter_init - Initialize the driver specific rdma counter struct.
+	 */
+	void (*counter_init)(struct rdma_counter *counter);
+
+	/**
 	 * Allows rdma drivers to add their own restrack attributes
 	 * dumped via 'rdma stat' iproute2 command.
 	 */
@@ -2698,6 +2722,7 @@ struct ib_device_ops {
 	DECLARE_RDMA_OBJ_SIZE(ib_srq);
 	DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
 	DECLARE_RDMA_OBJ_SIZE(ib_xrcd);
+	DECLARE_RDMA_OBJ_SIZE(rdma_counter);
 };
 
 struct ib_core_device {
@@ -2750,6 +2775,7 @@ struct ib_device {
 	 * It is a NULL terminated array.
 	 */
 	const struct attribute_group	*groups[4];
+	u8				hw_stats_attr_index;
 
 	u64			     uverbs_cmd_mask;
 
diff --git a/include/rdma/rdma_counter.h b/include/rdma/rdma_counter.h
index 45d5481a7846..4204d08a010a 100644
--- a/include/rdma/rdma_counter.h
+++ b/include/rdma/rdma_counter.h
@@ -23,6 +23,7 @@ struct rdma_counter_mode {
 	enum rdma_nl_counter_mode mode;
 	enum rdma_nl_counter_mask mask;
 	struct auto_mode_param param;
+	bool bind_opcnt;
 };
 
 struct rdma_port_counter {
@@ -47,9 +48,10 @@ void rdma_counter_init(struct ib_device *dev);
 void rdma_counter_release(struct ib_device *dev);
 int rdma_counter_set_auto_mode(struct ib_device *dev, u32 port,
 			       enum rdma_nl_counter_mask mask,
+			       bool bind_opcnt,
 			       struct netlink_ext_ack *extack);
 int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port);
-int rdma_counter_unbind_qp(struct ib_qp *qp, bool force);
+int rdma_counter_unbind_qp(struct ib_qp *qp, u32 port, bool force);
 
 int rdma_counter_query_stats(struct rdma_counter *counter);
 u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u32 port, u32 index);
@@ -61,7 +63,8 @@ int rdma_counter_unbind_qpn(struct ib_device *dev, u32 port,
 			    u32 qp_num, u32 counter_id);
 int rdma_counter_get_mode(struct ib_device *dev, u32 port,
 			  enum rdma_nl_counter_mode *mode,
-			  enum rdma_nl_counter_mask *mask);
+			  enum rdma_nl_counter_mask *mask,
+			  bool *opcnt);
 
 int rdma_counter_modify(struct ib_device *dev, u32 port,
 			unsigned int index, bool enable);
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index fe0512116958..555ea3d142a4 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -34,7 +34,7 @@
 static inline void *_uobj_get_obj_read(struct ib_uobject *uobj)
 {
 	if (IS_ERR(uobj))
-		return NULL;
+		return ERR_CAST(uobj);
 	return uobj->object;
 }
 #define uobj_get_obj_read(_object, _type, _id, _attrs)                         \
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index ec719053aab9..ac7b162611ed 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -88,6 +88,7 @@ enum uverbs_attrs_query_port_cmd_attr_ids {
 enum uverbs_attrs_get_context_attr_ids {
 	UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
 	UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
+	UVERBS_ATTR_GET_CONTEXT_FD_ARR,
 };
 
 enum uverbs_attrs_query_context_attr_ids {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index fd2e4a3a56b3..18f9fe070213 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -239,6 +239,7 @@ enum mlx5_ib_flow_matcher_create_attrs {
 	MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA,
 	MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS,
 	MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE,
+	MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT,
 };
 
 enum mlx5_ib_flow_matcher_destroy_attrs {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 7c233df475e7..8f86e79d78a5 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -45,6 +45,8 @@ enum mlx5_ib_uapi_flow_table_type {
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB	= 0x2,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX	= 0x3,
 	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TX	= 0x4,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_RX	= 0x5,
+	MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_TX	= 0x6,
 };
 
 enum mlx5_ib_uapi_flow_action_packet_reformat_type {
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 9f9cf20c1cd8..f41f0228fcd0 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -580,6 +580,8 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_EVENT_TYPE,		/* u8 */
 
 	RDMA_NLDEV_SYS_ATTR_MONITOR_MODE,	/* u8 */
+
+	RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED,	/* u8 */
 	/*
 	 * Always the end
 	 */