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
  ...

Author: torvalds

Documentation/infiniband/index.rst

@@ -12,6 +12,7 @@ InfiniBand
    opa_vnic
    sysfs
    tag_matching
+   ucaps
    user_mad
    user_verbs
 

Documentation/infiniband/ucaps.rst

@@ -0,0 +1,71 @@
+=================================
+Infiniband Userspace Capabilities
+=================================
+
+   User CAPabilities (UCAPs) provide fine-grained control over specific
+   firmware features in Infiniband (IB) devices. This approach offers
+   more granular capabilities than the existing Linux capabilities,
+   which may be too generic for certain FW features.
+
+   Each user capability is represented as a character device with root
+   read-write access. Root processes can grant users special privileges
+   by allowing access to these character devices (e.g., using chown).
+
+Usage
+=====
+
+   UCAPs allow control over specific features of an IB device using file
+   descriptors of UCAP character devices. Here is how a user enables
+   specific features of an IB device:
+
+      * A root process grants the user access to the UCAP files that
+        represents the capabilities (e.g., using chown).
+      * The user opens the UCAP files, obtaining file descriptors.
+      * When opening an IB device, include an array of the UCAP file
+        descriptors as an attribute.
+      * The ib_uverbs driver recognizes the UCAP file descriptors and enables
+        the corresponding capabilities for the IB device.
+
+Creating UCAPs
+==============
+
+   To create a new UCAP, drivers must first define a type in the
+   rdma_user_cap enum in rdma/ib_ucaps.h. The name of the UCAP character
+   device should be added to the ucap_names array in
+   drivers/infiniband/core/ucaps.c. Then, the driver can create the UCAP
+   character device by calling the ib_create_ucap API with the UCAP
+   type.
+
+   A reference count is stored for each UCAP to track creations and
+   removals of the UCAP device. If multiple creation calls are made with
+   the same type (e.g., for two IB devices), the UCAP character device
+   is created during the first call and subsequent calls increment the
+   reference count.
+
+   The UCAP character device is created under /dev/infiniband, and its
+   permissions are set to allow root read and write access only.
+
+Removing UCAPs
+==============
+
+   Each removal decrements the reference count of the UCAP. The UCAP
+   character device is removed from the filesystem only when the
+   reference count is decreased to 0.
+
+/dev and /sys/class files
+=========================
+
+   The class::
+
+      /sys/class/infiniband_ucaps
+
+   is created when the first UCAP character device is created.
+
+   The UCAP character device is created under /dev/infiniband.
+
+   For example, if mlx5_ib adds the rdma_user_cap
+   RDMA_UCAP_MLX5_CTRL_LOCAL with name "mlx5_perm_ctrl_local", this will
+   create the device node::
+
+      /dev/infiniband/mlx5_perm_ctrl_local
+

drivers/infiniband/core/Makefile

@@ -39,6 +39,7 @@ ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				uverbs_std_types_async_fd.o \
 				uverbs_std_types_srq.o \
 				uverbs_std_types_wq.o \
-				uverbs_std_types_qp.o
+				uverbs_std_types_qp.o \
+				ucaps.o
 ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o umem_dmabuf.o
 ib_uverbs-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o

drivers/infiniband/core/cache.c

@@ -1501,6 +1501,12 @@ ib_cache_update(struct ib_device *device, u32 port, bool update_gids,
 		device->port_data[port].cache.pkey = pkey_cache;
 	}
 	device->port_data[port].cache.lmc = tprops->lmc;
+
+	if (device->port_data[port].cache.port_state != IB_PORT_NOP &&
+	    device->port_data[port].cache.port_state != tprops->state)
+		ibdev_info(device, "Port: %d Link %s\n", port,
+			   ib_port_state_to_str(tprops->state));
+
 	device->port_data[port].cache.port_state = tprops->state;
 
 	device->port_data[port].cache.subnet_prefix = tprops->subnet_prefix;

drivers/infiniband/core/cma.c

@@ -739,12 +739,26 @@ cma_validate_port(struct ib_device *device, u32 port,
 		goto out;
 	}
 
-	if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) {
-		ndev = dev_get_by_index(dev_addr->net, bound_if_index);
-		if (!ndev)
-			goto out;
+	/*
+	 * For a RXE device, it should work with TUN device and normal ethernet
+	 * devices. Use driver_id to check if a device is a RXE device or not.
+	 * ARPHDR_NONE means a TUN device.
+	 */
+	if (device->ops.driver_id == RDMA_DRIVER_RXE) {
+		if ((dev_type == ARPHRD_NONE || dev_type == ARPHRD_ETHER)
+			&& rdma_protocol_roce(device, port)) {
+			ndev = dev_get_by_index(dev_addr->net, bound_if_index);
+			if (!ndev)
+				goto out;
+		}
 	} else {
-		gid_type = IB_GID_TYPE_IB;
+		if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) {
+			ndev = dev_get_by_index(dev_addr->net, bound_if_index);
+			if (!ndev)
+				goto out;
+		} else {
+			gid_type = IB_GID_TYPE_IB;
+		}
 	}
 
 	sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev);

drivers/infiniband/core/counters.c

@@ -12,7 +12,8 @@
 
 static int __counter_set_mode(struct rdma_port_counter *port_counter,
 			      enum rdma_nl_counter_mode new_mode,
-			      enum rdma_nl_counter_mask new_mask)
+			      enum rdma_nl_counter_mask new_mask,
+			      bool bind_opcnt)
 {
 	if (new_mode == RDMA_COUNTER_MODE_AUTO) {
 		if (new_mask & (~ALL_AUTO_MODE_MASKS))
@@ -23,6 +24,7 @@ static int __counter_set_mode(struct rdma_port_counter *port_counter,
 
 	port_counter->mode.mode = new_mode;
 	port_counter->mode.mask = new_mask;
+	port_counter->mode.bind_opcnt = bind_opcnt;
 	return 0;
 }
 
@@ -41,6 +43,7 @@ static int __counter_set_mode(struct rdma_port_counter *port_counter,
  */
 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)
 {
 	struct rdma_port_counter *port_counter;
@@ -59,12 +62,13 @@ int rdma_counter_set_auto_mode(struct ib_device *dev, u32 port,
 						      RDMA_COUNTER_MODE_NONE;
 
 	if (port_counter->mode.mode == mode &&
-	    port_counter->mode.mask == mask) {
+	    port_counter->mode.mask == mask &&
+	    port_counter->mode.bind_opcnt == bind_opcnt) {
 		ret = 0;
 		goto out;
 	}
 
-	ret = __counter_set_mode(port_counter, mode, mask);
+	ret = __counter_set_mode(port_counter, mode, mask, bind_opcnt);
 
 out:
 	mutex_unlock(&port_counter->lock);
@@ -89,7 +93,7 @@ static void auto_mode_init_counter(struct rdma_counter *counter,
 }
 
 static int __rdma_counter_bind_qp(struct rdma_counter *counter,
-				  struct ib_qp *qp)
+				  struct ib_qp *qp, u32 port)
 {
 	int ret;
 
@@ -100,7 +104,7 @@ static int __rdma_counter_bind_qp(struct rdma_counter *counter,
 		return -EOPNOTSUPP;
 
 	mutex_lock(&counter->lock);
-	ret = qp->device->ops.counter_bind_qp(counter, qp);
+	ret = qp->device->ops.counter_bind_qp(counter, qp, port);
 	mutex_unlock(&counter->lock);
 
 	return ret;
@@ -140,7 +144,8 @@ int rdma_counter_modify(struct ib_device *dev, u32 port,
 
 static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port,
 					   struct ib_qp *qp,
-					   enum rdma_nl_counter_mode mode)
+					   enum rdma_nl_counter_mode mode,
+					   bool bind_opcnt)
 {
 	struct rdma_port_counter *port_counter;
 	struct rdma_counter *counter;
@@ -149,13 +154,15 @@ static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port,
 	if (!dev->ops.counter_dealloc || !dev->ops.counter_alloc_stats)
 		return NULL;
 
-	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+	counter = rdma_zalloc_drv_obj(dev, rdma_counter);
 	if (!counter)
 		return NULL;
 
 	counter->device    = dev;
 	counter->port      = port;
 
+	dev->ops.counter_init(counter);
+
 	rdma_restrack_new(&counter->res, RDMA_RESTRACK_COUNTER);
 	counter->stats = dev->ops.counter_alloc_stats(counter);
 	if (!counter->stats)
@@ -166,7 +173,7 @@ static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port,
 	switch (mode) {
 	case RDMA_COUNTER_MODE_MANUAL:
 		ret = __counter_set_mode(port_counter, RDMA_COUNTER_MODE_MANUAL,
-					 0);
+					 0, bind_opcnt);
 		if (ret) {
 			mutex_unlock(&port_counter->lock);
 			goto err_mode;
@@ -185,10 +192,11 @@ static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port,
 	mutex_unlock(&port_counter->lock);
 
 	counter->mode.mode = mode;
+	counter->mode.bind_opcnt = bind_opcnt;
 	kref_init(&counter->kref);
 	mutex_init(&counter->lock);
 
-	ret = __rdma_counter_bind_qp(counter, qp);
+	ret = __rdma_counter_bind_qp(counter, qp, port);
 	if (ret)
 		goto err_mode;
 
@@ -213,7 +221,8 @@ static void rdma_counter_free(struct rdma_counter *counter)
 	port_counter->num_counters--;
 	if (!port_counter->num_counters &&
 	    (port_counter->mode.mode == RDMA_COUNTER_MODE_MANUAL))
-		__counter_set_mode(port_counter, RDMA_COUNTER_MODE_NONE, 0);
+		__counter_set_mode(port_counter, RDMA_COUNTER_MODE_NONE, 0,
+				   false);
 
 	mutex_unlock(&port_counter->lock);
 
@@ -238,7 +247,7 @@ static bool auto_mode_match(struct ib_qp *qp, struct rdma_counter *counter,
 	return match;
 }
 
-static int __rdma_counter_unbind_qp(struct ib_qp *qp)
+static int __rdma_counter_unbind_qp(struct ib_qp *qp, u32 port)
 {
 	struct rdma_counter *counter = qp->counter;
 	int ret;
@@ -247,7 +256,7 @@ static int __rdma_counter_unbind_qp(struct ib_qp *qp)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&counter->lock);
-	ret = qp->device->ops.counter_unbind_qp(qp);
+	ret = qp->device->ops.counter_unbind_qp(qp, port);
 	mutex_unlock(&counter->lock);
 
 	return ret;
@@ -339,13 +348,14 @@ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port)
 
 	counter = rdma_get_counter_auto_mode(qp, port);
 	if (counter) {
-		ret = __rdma_counter_bind_qp(counter, qp);
+		ret = __rdma_counter_bind_qp(counter, qp, port);
 		if (ret) {
 			kref_put(&counter->kref, counter_release);
 			return ret;
 		}
 	} else {
-		counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_AUTO);
+		counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_AUTO,
+					 port_counter->mode.bind_opcnt);
 		if (!counter)
 			return -ENOMEM;
 	}
@@ -358,15 +368,15 @@ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port)
  * @force:
  *   true - Decrease the counter ref-count anyway (e.g., qp destroy)
  */
-int rdma_counter_unbind_qp(struct ib_qp *qp, bool force)
+int rdma_counter_unbind_qp(struct ib_qp *qp, u32 port, bool force)
 {
 	struct rdma_counter *counter = qp->counter;
 	int ret;
 
 	if (!counter)
 		return -EINVAL;
 
-	ret = __rdma_counter_unbind_qp(qp);
+	ret = __rdma_counter_unbind_qp(qp, port);
 	if (ret && !force)
 		return ret;
 
@@ -513,7 +523,7 @@ int rdma_counter_bind_qpn(struct ib_device *dev, u32 port,
 		goto err_task;
 	}
 
-	ret = __rdma_counter_bind_qp(counter, qp);
+	ret = __rdma_counter_bind_qp(counter, qp, port);
 	if (ret)
 		goto err_task;
 
@@ -558,7 +568,7 @@ int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u32 port,
 		goto err;
 	}
 
-	counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_MANUAL);
+	counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_MANUAL, true);
 	if (!counter) {
 		ret = -ENOMEM;
 		goto err;
@@ -604,7 +614,7 @@ int rdma_counter_unbind_qpn(struct ib_device *dev, u32 port,
 		goto out;
 	}
 
-	ret = rdma_counter_unbind_qp(qp, false);
+	ret = rdma_counter_unbind_qp(qp, port, false);
 
 out:
 	rdma_restrack_put(&qp->res);
@@ -613,13 +623,15 @@ int rdma_counter_unbind_qpn(struct ib_device *dev, u32 port,
 
 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)
 {
 	struct rdma_port_counter *port_counter;
 
 	port_counter = &dev->port_data[port].port_counter;
 	*mode = port_counter->mode.mode;
 	*mask = port_counter->mode.mask;
+	*opcnt = port_counter->mode.bind_opcnt;
 
 	return 0;
 }