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

Pull rdma updates from Jason Gunthorpe:
 "The majority of the patches are cleanups, refactorings and clarity
  improvements.

  This cycle saw some more activity from Syzkaller, I think we are now
  clean on all but one of those bugs, including the long standing and
  obnoxious rdma_cm locking design defect. Continue to see many drivers
  getting cleanups, with a few new user visible features.

  Summary:

   - Various driver updates for siw, bnxt_re, rxe, efa, mlx5, hfi1

   - Lots of cleanup patches for hns

   - Convert more places to use refcount

   - Aggressively lock the RDMA CM code that syzkaller says isn't
     working

   - Work to clarify ib_cm

   - Use the new ib_device lifecycle model in bnxt_re

   - Fix mlx5's MR cache which seems to be failing more often with the
     new ODP code

   - mlx5 'dynamic uar' and 'tx steering' user interfaces"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (144 commits)
  RDMA/bnxt_re: make bnxt_re_ib_init static
  IB/qib: Delete struct qib_ivdev.qp_rnd
  RDMA/hns: Fix uninitialized variable bug
  RDMA/hns: Modify the mask of QP number for CQE of hip08
  RDMA/hns: Reduce the maximum number of extend SGE per WQE
  RDMA/hns: Reduce PFC frames in congestion scenarios
  RDMA/mlx5: Add support for RDMA TX flow table
  net/mlx5: Add support for RDMA TX steering
  IB/hfi1: Call kobject_put() when kobject_init_and_add() fails
  IB/hfi1: Fix memory leaks in sysfs registration and unregistration
  IB/mlx5: Move to fully dynamic UAR mode once user space supports it
  IB/mlx5: Limit the scope of struct mlx5_bfreg_info to mlx5_ib
  IB/mlx5: Extend QP creation to get uar page index from user space
  IB/mlx5: Extend CQ creation to get uar page index from user space
  IB/mlx5: Expose UAR object and its alloc/destroy commands
  IB/hfi1: Get rid of a warning
  RDMA/hns: Remove redundant judgment of qp_type
  RDMA/hns: Remove redundant assignment of wc->smac when polling cq
  RDMA/hns: Remove redundant qpc setup operations
  RDMA/hns: Remove meaningless prints
  ...

1 files changed, 216 insertions, 49 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3efa7493456b..6679756506e6 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -39,9 +39,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/bitmap.h>
-#if defined(CONFIG_X86)
-#include <asm/memtype.h>
-#endif
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
@@ -898,7 +895,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			props->raw_packet_caps |=
 				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
 
-		if (field_avail(typeof(resp), tso_caps, uhw_outlen)) {
+		if (offsetofend(typeof(resp), tso_caps) <= uhw_outlen) {
 			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
 			if (max_tso) {
 				resp.tso_caps.max_tso = 1 << max_tso;
@@ -908,7 +905,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			}
 		}
 
-		if (field_avail(typeof(resp), rss_caps, uhw_outlen)) {
+		if (offsetofend(typeof(resp), rss_caps) <= uhw_outlen) {
 			resp.rss_caps.rx_hash_function =
 						MLX5_RX_HASH_FUNC_TOEPLITZ;
 			resp.rss_caps.rx_hash_fields_mask =
@@ -928,9 +925,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			resp.response_length += sizeof(resp.rss_caps);
 		}
 	} else {
-		if (field_avail(typeof(resp), tso_caps, uhw_outlen))
+		if (offsetofend(typeof(resp), tso_caps) <= uhw_outlen)
 			resp.response_length += sizeof(resp.tso_caps);
-		if (field_avail(typeof(resp), rss_caps, uhw_outlen))
+		if (offsetofend(typeof(resp), rss_caps) <= uhw_outlen)
 			resp.response_length += sizeof(resp.rss_caps);
 	}
 
@@ -1072,7 +1069,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 						MLX5_MAX_CQ_PERIOD;
 	}
 
-	if (field_avail(typeof(resp), cqe_comp_caps, uhw_outlen)) {
+	if (offsetofend(typeof(resp), cqe_comp_caps) <= uhw_outlen) {
 		resp.response_length += sizeof(resp.cqe_comp_caps);
 
 		if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
@@ -1090,7 +1087,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), packet_pacing_caps, uhw_outlen) &&
+	if (offsetofend(typeof(resp), packet_pacing_caps) <= uhw_outlen &&
 	    raw_support) {
 		if (MLX5_CAP_QOS(mdev, packet_pacing) &&
 		    MLX5_CAP_GEN(mdev, qos)) {
@@ -1108,8 +1105,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.packet_pacing_caps);
 	}
 
-	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
-			uhw_outlen)) {
+	if (offsetofend(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes) <=
+	    uhw_outlen) {
 		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
 			resp.mlx5_ib_support_multi_pkt_send_wqes =
 				MLX5_IB_ALLOW_MPW;
@@ -1122,7 +1119,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}
 
-	if (field_avail(typeof(resp), flags, uhw_outlen)) {
+	if (offsetofend(typeof(resp), flags) <= uhw_outlen) {
 		resp.response_length += sizeof(resp.flags);
 
 		if (MLX5_CAP_GEN(mdev, cqe_compression_128))
@@ -1138,7 +1135,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
-	if (field_avail(typeof(resp), sw_parsing_caps, uhw_outlen)) {
+	if (offsetofend(typeof(resp), sw_parsing_caps) <= uhw_outlen) {
 		resp.response_length += sizeof(resp.sw_parsing_caps);
 		if (MLX5_CAP_ETH(mdev, swp)) {
 			resp.sw_parsing_caps.sw_parsing_offloads |=
@@ -1158,7 +1155,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), striding_rq_caps, uhw_outlen) &&
+	if (offsetofend(typeof(resp), striding_rq_caps) <= uhw_outlen &&
 	    raw_support) {
 		resp.response_length += sizeof(resp.striding_rq_caps);
 		if (MLX5_CAP_GEN(mdev, striding_rq)) {
@@ -1181,7 +1178,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), tunnel_offloads_caps, uhw_outlen)) {
+	if (offsetofend(typeof(resp), tunnel_offloads_caps) <= uhw_outlen) {
 		resp.response_length += sizeof(resp.tunnel_offloads_caps);
 		if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan))
 			resp.tunnel_offloads_caps |=
@@ -1192,12 +1189,10 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_GRE;
-		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
-		    MLX5_FLEX_PROTO_CW_MPLS_GRE)
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_GRE;
-		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
-		    MLX5_FLEX_PROTO_CW_MPLS_UDP)
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_udp))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
 	}
@@ -1791,6 +1786,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 				     max_cqe_version);
 	u32 dump_fill_mkey;
 	bool lib_uar_4k;
+	bool lib_uar_dyn;
 
 	if (!dev->ib_active)
 		return -EAGAIN;
@@ -1849,8 +1845,14 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	}
 
 	lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR;
+	lib_uar_dyn = req.lib_caps & MLX5_LIB_CAP_DYN_UAR;
 	bfregi = &context->bfregi;
 
+	if (lib_uar_dyn) {
+		bfregi->lib_uar_dyn = lib_uar_dyn;
+		goto uar_done;
+	}
+
 	/* updates req->total_num_bfregs */
 	err = calc_total_bfregs(dev, lib_uar_4k, &req, bfregi);
 	if (err)
@@ -1877,6 +1879,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	if (err)
 		goto out_sys_pages;
 
+uar_done:
 	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
 		err = mlx5_ib_devx_create(dev, true);
 		if (err < 0)
@@ -1898,19 +1901,19 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
-	resp.tot_bfregs = req.total_num_bfregs;
+	resp.tot_bfregs = lib_uar_dyn ? 0 : req.total_num_bfregs;
 	resp.num_ports = dev->num_ports;
 
-	if (field_avail(typeof(resp), cqe_version, udata->outlen))
+	if (offsetofend(typeof(resp), cqe_version) <= udata->outlen)
 		resp.response_length += sizeof(resp.cqe_version);
 
-	if (field_avail(typeof(resp), cmds_supp_uhw, udata->outlen)) {
+	if (offsetofend(typeof(resp), cmds_supp_uhw) <= udata->outlen) {
 		resp.cmds_supp_uhw |= MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE |
 				      MLX5_USER_CMDS_SUPP_UHW_CREATE_AH;
 		resp.response_length += sizeof(resp.cmds_supp_uhw);
 	}
 
-	if (field_avail(typeof(resp), eth_min_inline, udata->outlen)) {
+	if (offsetofend(typeof(resp), eth_min_inline) <= udata->outlen) {
 		if (mlx5_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) {
 			mlx5_query_min_inline(dev->mdev, &resp.eth_min_inline);
 			resp.eth_min_inline++;
@@ -1918,7 +1921,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 		resp.response_length += sizeof(resp.eth_min_inline);
 	}
 
-	if (field_avail(typeof(resp), clock_info_versions, udata->outlen)) {
+	if (offsetofend(typeof(resp), clock_info_versions) <= udata->outlen) {
 		if (mdev->clock_info)
 			resp.clock_info_versions = BIT(MLX5_IB_CLOCK_INFO_V1);
 		resp.response_length += sizeof(resp.clock_info_versions);
@@ -1930,7 +1933,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	 * pretend we don't support reading the HCA's core clock. This is also
 	 * forced by mmap function.
 	 */
-	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+	if (offsetofend(typeof(resp), hca_core_clock_offset) <= udata->outlen) {
 		if (PAGE_SIZE <= 4096) {
 			resp.comp_mask |=
 				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
@@ -1940,18 +1943,18 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
 	}
 
-	if (field_avail(typeof(resp), log_uar_size, udata->outlen))
+	if (offsetofend(typeof(resp), log_uar_size) <= udata->outlen)
 		resp.response_length += sizeof(resp.log_uar_size);
 
-	if (field_avail(typeof(resp), num_uars_per_page, udata->outlen))
+	if (offsetofend(typeof(resp), num_uars_per_page) <= udata->outlen)
 		resp.response_length += sizeof(resp.num_uars_per_page);
 
-	if (field_avail(typeof(resp), num_dyn_bfregs, udata->outlen)) {
+	if (offsetofend(typeof(resp), num_dyn_bfregs) <= udata->outlen) {
 		resp.num_dyn_bfregs = bfregi->num_dyn_bfregs;
 		resp.response_length += sizeof(resp.num_dyn_bfregs);
 	}
 
-	if (field_avail(typeof(resp), dump_fill_mkey, udata->outlen)) {
+	if (offsetofend(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 |=
@@ -2026,6 +2029,17 @@ static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
 	return (dev->mdev->bar_addr >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
 }
 
+static u64 uar_index2paddress(struct mlx5_ib_dev *dev,
+				 int uar_idx)
+{
+	unsigned int fw_uars_per_page;
+
+	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ?
+				MLX5_UARS_IN_PAGE : 1;
+
+	return (dev->mdev->bar_addr + (uar_idx / fw_uars_per_page) * PAGE_SIZE);
+}
+
 static int get_command(unsigned long offset)
 {
 	return (offset >> MLX5_IB_MMAP_CMD_SHIFT) & MLX5_IB_MMAP_CMD_MASK;
@@ -2110,6 +2124,11 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
 		mutex_unlock(&var_table->bitmap_lock);
 		kfree(mentry);
 		break;
+	case MLX5_IB_MMAP_TYPE_UAR_WC:
+	case MLX5_IB_MMAP_TYPE_UAR_NC:
+		mlx5_cmd_free_uar(dev->mdev, mentry->page_idx);
+		kfree(mentry);
+		break;
 	default:
 		WARN_ON(true);
 	}
@@ -2130,6 +2149,9 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 	int max_valid_idx = dyn_uar ? bfregi->num_sys_pages :
 				bfregi->num_static_sys_pages;
 
+	if (bfregi->lib_uar_dyn)
+		return -EINVAL;
+
 	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
 		return -EINVAL;
 
@@ -2147,14 +2169,6 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 	switch (cmd) {
 	case MLX5_IB_MMAP_WC_PAGE:
 	case MLX5_IB_MMAP_ALLOC_WC:
-/* Some architectures don't support WC memory */
-#if defined(CONFIG_X86)
-		if (!pat_enabled())
-			return -EPERM;
-#elif !(defined(CONFIG_PPC) || (defined(CONFIG_ARM) && defined(CONFIG_MMU)))
-			return -EPERM;
-#endif
-	/* fall through */
 	case MLX5_IB_MMAP_REGULAR_PAGE:
 		/* For MLX5_IB_MMAP_REGULAR_PAGE do the best effort to get WC */
 		prot = pgprot_writecombine(vma->vm_page_prot);
@@ -2269,7 +2283,8 @@ static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev,
 
 	mentry = to_mmmap(entry);
 	pfn = (mentry->address >> PAGE_SHIFT);
-	if (mentry->mmap_flag == MLX5_IB_MMAP_TYPE_VAR)
+	if (mentry->mmap_flag == MLX5_IB_MMAP_TYPE_VAR ||
+	    mentry->mmap_flag == MLX5_IB_MMAP_TYPE_UAR_NC)
 		prot = pgprot_noncached(vma->vm_page_prot);
 	else
 		prot = pgprot_writecombine(vma->vm_page_prot);
@@ -2300,9 +2315,12 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	command = get_command(vma->vm_pgoff);
 	switch (command) {
 	case MLX5_IB_MMAP_WC_PAGE:
+	case MLX5_IB_MMAP_ALLOC_WC:
+		if (!dev->wc_support)
+			return -EPERM;
+		fallthrough;
 	case MLX5_IB_MMAP_NC_PAGE:
 	case MLX5_IB_MMAP_REGULAR_PAGE:
-	case MLX5_IB_MMAP_ALLOC_WC:
 		return uar_mmap(dev, command, vma, context);
 
 	case MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES:
@@ -4046,6 +4064,11 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 			BIT(MLX5_CAP_FLOWTABLE_RDMA_RX(dev->mdev,
 						       log_max_ft_size));
 		priority = fs_matcher->priority;
+	} else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX) {
+		max_table_size =
+			BIT(MLX5_CAP_FLOWTABLE_RDMA_TX(dev->mdev,
+						       log_max_ft_size));
+		priority = fs_matcher->priority;
 	}
 
 	max_table_size = min_t(int, max_table_size, MLX5_FS_MAX_ENTRIES);
@@ -4062,6 +4085,8 @@ _get_flow_table(struct mlx5_ib_dev *dev,
 		prio = &dev->flow_db->fdb;
 	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX)
 		prio = &dev->flow_db->rdma_rx[priority];
+	else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_TX)
+		prio = &dev->flow_db->rdma_tx[priority];
 
 	if (!prio)
 		return ERR_PTR(-EINVAL);
@@ -6090,9 +6115,9 @@ static void mlx5_ib_cleanup_multiport_master(struct mlx5_ib_dev *dev)
 	mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
-static int var_obj_cleanup(struct ib_uobject *uobject,
-			   enum rdma_remove_reason why,
-			   struct uverbs_attr_bundle *attrs)
+static int mmap_obj_cleanup(struct ib_uobject *uobject,
+			    enum rdma_remove_reason why,
+			    struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_user_mmap_entry *obj = uobject->object;
 
@@ -6100,6 +6125,16 @@ static int var_obj_cleanup(struct ib_uobject *uobject,
 	return 0;
 }
 
+static int mlx5_rdma_user_mmap_entry_insert(struct mlx5_ib_ucontext *c,
+					    struct mlx5_user_mmap_entry *entry,
+					    size_t length)
+{
+	return rdma_user_mmap_entry_insert_range(
+		&c->ibucontext, &entry->rdma_entry, length,
+		(MLX5_IB_MMAP_OFFSET_START << 16),
+		((MLX5_IB_MMAP_OFFSET_END << 16) + (1UL << 16) - 1));
+}
+
 static struct mlx5_user_mmap_entry *
 alloc_var_entry(struct mlx5_ib_ucontext *c)
 {
@@ -6130,10 +6165,8 @@ alloc_var_entry(struct mlx5_ib_ucontext *c)
 	entry->page_idx = page_idx;
 	entry->mmap_flag = MLX5_IB_MMAP_TYPE_VAR;
 
-	err = rdma_user_mmap_entry_insert_range(
-		&c->ibucontext, &entry->rdma_entry, var_table->stride_size,
-		MLX5_IB_MMAP_OFFSET_START << 16,
-		(MLX5_IB_MMAP_OFFSET_END << 16) + (1UL << 16) - 1);
+	err = mlx5_rdma_user_mmap_entry_insert(c, entry,
+					       var_table->stride_size);
 	if (err)
 		goto err_insert;
 
@@ -6217,7 +6250,7 @@ DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 			UA_MANDATORY));
 
 DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_VAR,
-			    UVERBS_TYPE_ALLOC_IDR(var_obj_cleanup),
+			    UVERBS_TYPE_ALLOC_IDR(mmap_obj_cleanup),
 			    &UVERBS_METHOD(MLX5_IB_METHOD_VAR_OBJ_ALLOC),
 			    &UVERBS_METHOD(MLX5_IB_METHOD_VAR_OBJ_DESTROY));
 
@@ -6229,6 +6262,134 @@ static bool var_is_supported(struct ib_device *device)
 			MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q);
 }
 
+static struct mlx5_user_mmap_entry *
+alloc_uar_entry(struct mlx5_ib_ucontext *c,
+		enum mlx5_ib_uapi_uar_alloc_type alloc_type)
+{
+	struct mlx5_user_mmap_entry *entry;
+	struct mlx5_ib_dev *dev;
+	u32 uar_index;
+	int err;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	dev = to_mdev(c->ibucontext.device);
+	err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index);
+	if (err)
+		goto end;
+
+	entry->page_idx = uar_index;
+	entry->address = uar_index2paddress(dev, uar_index);
+	if (alloc_type == MLX5_IB_UAPI_UAR_ALLOC_TYPE_BF)
+		entry->mmap_flag = MLX5_IB_MMAP_TYPE_UAR_WC;
+	else
+		entry->mmap_flag = MLX5_IB_MMAP_TYPE_UAR_NC;
+
+	err = mlx5_rdma_user_mmap_entry_insert(c, entry, PAGE_SIZE);
+	if (err)
+		goto err_insert;
+
+	return entry;
+
+err_insert:
+	mlx5_cmd_free_uar(dev->mdev, uar_index);
+end:
+	kfree(entry);
+	return ERR_PTR(err);
+}
+
+static int UVERBS_HANDLER(MLX5_IB_METHOD_UAR_OBJ_ALLOC)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj = uverbs_attr_get_uobject(
+		attrs, MLX5_IB_ATTR_UAR_OBJ_ALLOC_HANDLE);
+	enum mlx5_ib_uapi_uar_alloc_type alloc_type;
+	struct mlx5_ib_ucontext *c;
+	struct mlx5_user_mmap_entry *entry;
+	u64 mmap_offset;
+	u32 length;
+	int err;
+
+	c = to_mucontext(ib_uverbs_get_ucontext(attrs));
+	if (IS_ERR(c))
+		return PTR_ERR(c);
+
+	err = uverbs_get_const(&alloc_type, attrs,
+			       MLX5_IB_ATTR_UAR_OBJ_ALLOC_TYPE);
+	if (err)
+		return err;
+
+	if (alloc_type != MLX5_IB_UAPI_UAR_ALLOC_TYPE_BF &&
+	    alloc_type != MLX5_IB_UAPI_UAR_ALLOC_TYPE_NC)
+		return -EOPNOTSUPP;
+
+	if (!to_mdev(c->ibucontext.device)->wc_support &&
+	    alloc_type == MLX5_IB_UAPI_UAR_ALLOC_TYPE_BF)
+		return -EOPNOTSUPP;
+
+	entry = alloc_uar_entry(c, alloc_type);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
+
+	mmap_offset = mlx5_entry_to_mmap_offset(entry);
+	length = entry->rdma_entry.npages * PAGE_SIZE;
+	uobj->object = entry;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_UAR_OBJ_ALLOC_MMAP_OFFSET,
+			     &mmap_offset, sizeof(mmap_offset));
+	if (err)
+		goto err;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_UAR_OBJ_ALLOC_PAGE_ID,
+			     &entry->page_idx, sizeof(entry->page_idx));
+	if (err)
+		goto err;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_UAR_OBJ_ALLOC_MMAP_LENGTH,
+			     &length, sizeof(length));
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	rdma_user_mmap_entry_remove(&entry->rdma_entry);
+	return err;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(
+	MLX5_IB_METHOD_UAR_OBJ_ALLOC,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_UAR_OBJ_ALLOC_HANDLE,
+			MLX5_IB_OBJECT_UAR,
+			UVERBS_ACCESS_NEW,
+			UA_MANDATORY),
+	UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_UAR_OBJ_ALLOC_TYPE,
+			     enum mlx5_ib_uapi_uar_alloc_type,
+			     UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_UAR_OBJ_ALLOC_PAGE_ID,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_UAR_OBJ_ALLOC_MMAP_LENGTH,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_UAR_OBJ_ALLOC_MMAP_OFFSET,
+			    UVERBS_ATTR_TYPE(u64),
+			    UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD_DESTROY(
+	MLX5_IB_METHOD_UAR_OBJ_DESTROY,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_UAR_OBJ_DESTROY_HANDLE,
+			MLX5_IB_OBJECT_UAR,
+			UVERBS_ACCESS_DESTROY,
+			UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_UAR,
+			    UVERBS_TYPE_ALLOC_IDR(mmap_obj_cleanup),
+			    &UVERBS_METHOD(MLX5_IB_METHOD_UAR_OBJ_ALLOC),
+			    &UVERBS_METHOD(MLX5_IB_METHOD_UAR_OBJ_DESTROY));
+
 ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	mlx5_ib_dm,
 	UVERBS_OBJECT_DM,
@@ -6253,12 +6414,14 @@ ADD_UVERBS_ATTRIBUTES_SIMPLE(
 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_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_NAMED(MLX5_IB_OBJECT_VAR,
 				UAPI_DEF_IS_OBJ_SUPPORTED(var_is_supported)),
+	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_UAR),
 	{}
 };
 
@@ -6392,7 +6555,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	spin_lock_init(&dev->reset_flow_resource_lock);
 	xa_init(&dev->odp_mkeys);
 	xa_init(&dev->sig_mrs);
-	spin_lock_init(&dev->mkey_lock);
+	atomic_set(&dev->mkey_var, 0);
 
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
@@ -6548,7 +6711,8 @@ static int mlx5_ib_init_var_table(struct mlx5_ib_dev *dev)
 					doorbell_bar_offset);
 	bar_size = (1ULL << log_doorbell_bar_size) * 4096;
 	var_table->stride_size = 1ULL << log_doorbell_stride;
-	var_table->num_var_hw_entries = div64_u64(bar_size, var_table->stride_size);
+	var_table->num_var_hw_entries = div_u64(bar_size,
+						var_table->stride_size);
 	mutex_init(&var_table->bitmap_lock);
 	var_table->bitmap = bitmap_zalloc(var_table->num_var_hw_entries,
 					  GFP_KERNEL);
@@ -7080,6 +7244,9 @@ const struct mlx5_ib_profile raw_eth_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_COUNTERS,
 		     mlx5_ib_stage_counters_init,
 		     mlx5_ib_stage_counters_cleanup),
+	STAGE_CREATE(MLX5_IB_STAGE_CONG_DEBUGFS,
+		     mlx5_ib_stage_cong_debugfs_init,
+		     mlx5_ib_stage_cong_debugfs_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_UAR,
 		     mlx5_ib_stage_uar_init,
 		     mlx5_ib_stage_uar_cleanup),