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

…t/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "A usual cycle for RDMA with a typical mix of driver and core subsystem
  updates:

   - Driver minor changes and bug fixes for mlx5, efa, rxe, vmw_pvrdma,
     hns, usnic, qib, qedr, cxgb4, hns, bnxt_re

   - Various rtrs fixes and updates

   - Bug fix for mlx4 CM emulation for virtualization scenarios where
     MRA wasn't working right

   - Use tracepoints instead of pr_debug in the CM code

   - Scrub the locking in ucma and cma to close more syzkaller bugs

   - Use tasklet_setup in the subsystem

   - Revert the idea that 'destroy' operations are not allowed to fail
     at the driver level. This proved unworkable from a HW perspective.

   - Revise how the umem API works so drivers make fewer mistakes using
     it

   - XRC support for qedr

   - Convert uverbs objects RWQ and MW to new the allocation scheme

   - Large queue entry sizes for hns

   - Use hmm_range_fault() for mlx5 On Demand Paging

   - uverbs APIs to inspect the GID table instead of sysfs

   - Move some of the RDMA code for building large page SGLs into
     lib/scatterlist"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (191 commits)
  RDMA/ucma: Fix use after free in destroy id flow
  RDMA/rxe: Handle skb_clone() failure in rxe_recv.c
  RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI
  RDMA: Explicitly pass in the dma_device to ib_register_device
  lib/scatterlist: Do not limit max_segment to PAGE_ALIGNED values
  IB/mlx4: Convert rej_tmout radix-tree to XArray
  RDMA/rxe: Fix bug rejecting all multicast packets
  RDMA/rxe: Fix skb lifetime in rxe_rcv_mcast_pkt()
  RDMA/rxe: Remove duplicate entries in struct rxe_mr
  IB/hfi,rdmavt,qib,opa_vnic: Update MAINTAINERS
  IB/rdmavt: Fix sizeof mismatch
  MAINTAINERS: CISCO VIC LOW LATENCY NIC DRIVER
  RDMA/bnxt_re: Fix sizeof mismatch for allocation of pbl_tbl.
  RDMA/bnxt_re: Use rdma_umem_for_each_dma_block()
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test
  RDMA/ipoib: Set rtnl_link_ops for ipoib interfaces
  RDMA/uverbs: Expose the new GID query API to user space
  ...

.clang-format

@@ -429,6 +429,7 @@ ForEachMacros:
   - 'rbtree_postorder_for_each_entry_safe'
   - 'rdma_for_each_block'
   - 'rdma_for_each_port'
+  - 'rdma_umem_for_each_dma_block'
   - 'resource_list_for_each_entry'
   - 'resource_list_for_each_entry_safe'
   - 'rhl_for_each_entry_rcu'

Documentation/ABI/stable/sysfs-class-infiniband

@@ -258,23 +258,6 @@ Description:
 		userspace ABI compatibility of umad & issm devices.
 
 
-What:		/sys/class/infiniband_cm/ucmN/ibdev
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	[email protected]
-Description:
-		(RO) Display Infiniband (IB) device name
-
-
-What:		/sys/class/infiniband_cm/abi_version
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	[email protected]
-Description:
-		(RO) Value is incremented if any changes are made that break
-		userspace ABI compatibility of ucm devices.
-
-
 What:		/sys/class/infiniband_verbs/uverbsN/ibdev
 What:		/sys/class/infiniband_verbs/uverbsN/abi_version
 Date:		Sept, 2005

MAINTAINERS

@@ -4256,7 +4256,6 @@ F:	drivers/net/ethernet/cisco/enic/
 CISCO VIC LOW LATENCY NIC DRIVER
 M:	Christian Benvenuti <[email protected]>
 M:	Nelson Escobar <[email protected]>
-M:	Parvi Kaustubhi <[email protected]>
 S:	Supported
 F:	drivers/infiniband/hw/usnic/
 
@@ -7793,8 +7792,8 @@ F:	include/linux/cciss*.h
 F:	include/uapi/linux/cciss*.h
 
 HFI1 DRIVER
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/hw/hfi1
@@ -12999,8 +12998,8 @@ S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
 
 OPA-VNIC DRIVER
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/ulp/opa_vnic
@@ -14301,8 +14300,8 @@ F:	drivers/firmware/qemu_fw_cfg.c
 F:	include/uapi/linux/qemu_fw_cfg.h
 
 QIB DRIVER
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/hw/qib/
@@ -14727,8 +14726,8 @@ S:	Maintained
 F:	drivers/net/ethernet/rdc/r6040.c
 
 RDMAVT - RDMA verbs software
-M:	Dennis Dalessandro <dennis.dalessandro@intel.com>
-M:	Mike Marciniszyn <mike.marciniszyn@intel.com>
+M:	Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
+M:	Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/sw/rdmavt

drivers/gpu/drm/drm_prime.c

@@ -806,30 +806,27 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
 struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
 				       struct page **pages, unsigned int nr_pages)
 {
-	struct sg_table *sg = NULL;
+	struct sg_table *sg;
+	struct scatterlist *sge;
 	size_t max_segment = 0;
-	int ret;
 
 	sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
-	if (!sg) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!sg)
+		return ERR_PTR(-ENOMEM);
 
 	if (dev)
 		max_segment = dma_max_mapping_size(dev->dev);
 	if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT)
 		max_segment = SCATTERLIST_MAX_SEGMENT;
-	ret = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
+	sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
 					  nr_pages << PAGE_SHIFT,
-					  max_segment, GFP_KERNEL);
-	if (ret)
-		goto out;
-
+					  max_segment,
+					  NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sge)) {
+		kfree(sg);
+		sg = ERR_CAST(sge);
+	}
 	return sg;
-out:
-	kfree(sg);
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(drm_prime_pages_to_sg);
 

drivers/gpu/drm/i915/gem/i915_gem_userptr.c

@@ -403,20 +403,20 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
+	struct scatterlist *sg;
 	int ret;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
 	if (!st)
 		return ERR_PTR(-ENOMEM);
 
 alloc_table:
-	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
-					  0, num_pages << PAGE_SHIFT,
-					  max_segment,
-					  GFP_KERNEL);
-	if (ret) {
+	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
+					 num_pages << PAGE_SHIFT, max_segment,
+					 NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ERR_CAST(sg);
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);

drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c

@@ -432,6 +432,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	int ret = 0;
 	static size_t sgl_size;
 	static size_t sgt_size;
+	struct scatterlist *sg;
 
 	if (vmw_tt->mapped)
 		return 0;
@@ -454,13 +455,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = __sg_alloc_table_from_pages
-			(&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
-			 (unsigned long) vsgt->num_pages << PAGE_SHIFT,
-			 dma_get_max_seg_size(dev_priv->dev->dev),
-			 GFP_KERNEL);
-		if (unlikely(ret != 0))
+		sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
+				vsgt->num_pages, 0,
+				(unsigned long) vsgt->num_pages << PAGE_SHIFT,
+				dma_get_max_seg_size(dev_priv->dev->dev),
+				NULL, 0, GFP_KERNEL);
+		if (IS_ERR(sg)) {
+			ret = PTR_ERR(sg);
 			goto out_sg_alloc_fail;
+		}
 
 		if (vsgt->num_pages > vmw_tt->sgt.orig_nents) {
 			uint64_t over_alloc =

drivers/infiniband/Kconfig

@@ -48,6 +48,7 @@ config INFINIBAND_ON_DEMAND_PAGING
 	depends on INFINIBAND_USER_MEM
 	select MMU_NOTIFIER
 	select INTERVAL_TREE
+	select HMM_MIRROR
 	default y
 	help
 	  On demand paging support for the InfiniBand subsystem.

drivers/infiniband/core/Makefile

@@ -17,7 +17,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
 
-ib_cm-y :=			cm.o
+ib_cm-y :=			cm.o cm_trace.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
 

drivers/infiniband/core/addr.c

@@ -647,13 +647,12 @@ static void process_one_req(struct work_struct *_work)
 	req->callback = NULL;
 
 	spin_lock_bh(&lock);
+	/*
+	 * Although the work will normally have been canceled by the workqueue,
+	 * it can still be requeued as long as it is on the req_list.
+	 */
+	cancel_delayed_work(&req->work);
 	if (!list_empty(&req->list)) {
-		/*
-		 * Although the work will normally have been canceled by the
-		 * workqueue, it can still be requeued as long as it is on the
-		 * req_list.
-		 */
-		cancel_delayed_work(&req->work);
 		list_del_init(&req->list);
 		kfree(req);
 	}

drivers/infiniband/core/cache.c

@@ -133,7 +133,11 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 }
 
 static const char * const gid_type_str[] = {
+	/* IB/RoCE v1 value is set for IB_GID_TYPE_IB and IB_GID_TYPE_ROCE for
+	 * user space compatibility reasons.
+	 */
 	[IB_GID_TYPE_IB]	= "IB/RoCE v1",
+	[IB_GID_TYPE_ROCE]	= "IB/RoCE v1",
 	[IB_GID_TYPE_ROCE_UDP_ENCAP]	= "RoCE v2",
 };
 
@@ -1220,7 +1224,7 @@ EXPORT_SYMBOL(ib_get_cached_port_state);
 const struct ib_gid_attr *
 rdma_get_gid_attr(struct ib_device *device, u8 port_num, int index)
 {
-	const struct ib_gid_attr *attr = ERR_PTR(-EINVAL);
+	const struct ib_gid_attr *attr = ERR_PTR(-ENODATA);
 	struct ib_gid_table *table;
 	unsigned long flags;
 
@@ -1243,6 +1247,67 @@ rdma_get_gid_attr(struct ib_device *device, u8 port_num, int index)
 }
 EXPORT_SYMBOL(rdma_get_gid_attr);
 
+/**
+ * rdma_query_gid_table - Reads GID table entries of all the ports of a device up to max_entries.
+ * @device: The device to query.
+ * @entries: Entries where GID entries are returned.
+ * @max_entries: Maximum number of entries that can be returned.
+ * Entries array must be allocated to hold max_entries number of entries.
+ * @num_entries: Updated to the number of entries that were successfully read.
+ *
+ * Returns number of entries on success or appropriate error code.
+ */
+ssize_t rdma_query_gid_table(struct ib_device *device,
+			     struct ib_uverbs_gid_entry *entries,
+			     size_t max_entries)
+{
+	const struct ib_gid_attr *gid_attr;
+	ssize_t num_entries = 0, ret;
+	struct ib_gid_table *table;
+	unsigned int port_num, i;
+	struct net_device *ndev;
+	unsigned long flags;
+
+	rdma_for_each_port(device, port_num) {
+		if (!rdma_ib_or_roce(device, port_num))
+			continue;
+
+		table = rdma_gid_table(device, port_num);
+		read_lock_irqsave(&table->rwlock, flags);
+		for (i = 0; i < table->sz; i++) {
+			if (!is_gid_entry_valid(table->data_vec[i]))
+				continue;
+			if (num_entries >= max_entries) {
+				ret = -EINVAL;
+				goto err;
+			}
+
+			gid_attr = &table->data_vec[i]->attr;
+
+			memcpy(&entries->gid, &gid_attr->gid,
+			       sizeof(gid_attr->gid));
+			entries->gid_index = gid_attr->index;
+			entries->port_num = gid_attr->port_num;
+			entries->gid_type = gid_attr->gid_type;
+			ndev = rcu_dereference_protected(
+				gid_attr->ndev,
+				lockdep_is_held(&table->rwlock));
+			if (ndev)
+				entries->netdev_ifindex = ndev->ifindex;
+
+			num_entries++;
+			entries++;
+		}
+		read_unlock_irqrestore(&table->rwlock, flags);
+	}
+
+	return num_entries;
+err:
+	read_unlock_irqrestore(&table->rwlock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_query_gid_table);
+
 /**
  * rdma_put_gid_attr - Release reference to the GID attribute
  * @attr:		Pointer to the GID attribute whose reference
@@ -1299,7 +1364,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	struct ib_gid_table_entry *entry =
 			container_of(attr, struct ib_gid_table_entry, attr);
 	struct ib_device *device = entry->attr.device;
-	struct net_device *ndev = ERR_PTR(-ENODEV);
+	struct net_device *ndev = ERR_PTR(-EINVAL);
 	u8 port_num = entry->attr.port_num;
 	struct ib_gid_table *table;
 	unsigned long flags;
@@ -1311,8 +1376,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	valid = is_gid_entry_valid(table->data_vec[attr->index]);
 	if (valid) {
 		ndev = rcu_dereference(attr->ndev);
-		if (!ndev ||
-		    (ndev && ((READ_ONCE(ndev->flags) & IFF_UP) == 0)))
+		if (!ndev)
 			ndev = ERR_PTR(-ENODEV);
 	}
 	read_unlock_irqrestore(&table->rwlock, flags);