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

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.19:

   - On-demand paging support in core midlayer and mlx5 driver.  This
     lets userspace create non-pinned memory regions and have the
     adapter HW trigger page faults.
   - iSER and IPoIB updates and fixes.
   - Low-level HW driver updates for cxgb4, mlx4 and ocrdma.
   - Other miscellaneous fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (56 commits)
  IB/mlx5: Implement on demand paging by adding support for MMU notifiers
  IB/mlx5: Add support for RDMA read/write responder page faults
  IB/mlx5: Handle page faults
  IB/mlx5: Page faults handling infrastructure
  IB/mlx5: Add mlx5_ib_update_mtt to update page tables after creation
  IB/mlx5: Changes in memory region creation to support on-demand paging
  IB/mlx5: Implement the ODP capability query verb
  mlx5_core: Add support for page faults events and low level handling
  mlx5_core: Re-add MLX5_DEV_CAP_FLAG_ON_DMND_PG flag
  IB/srp: Allow newline separator for connection string
  IB/core: Implement support for MMU notifiers regarding on demand paging regions
  IB/core: Add support for on demand paging regions
  IB/core: Add flags for on demand paging support
  IB/core: Add support for extended query device caps
  IB/mlx5: Add function to read WQE from user-space
  IB/core: Add umem function to read data from user-space
  IB/core: Replace ib_umem's offset field with a full address
  IB/mlx5: Enhance UMR support to allow partial page table update
  IB/mlx5: Remove per-MR pas and dma pointers
  RDMA/ocrdma: Always resolve destination mac from GRH for UD QPs
  ...

drivers/infiniband/Kconfig

@@ -38,6 +38,17 @@ config INFINIBAND_USER_MEM
 	depends on INFINIBAND_USER_ACCESS != n
 	default y
 
+config INFINIBAND_ON_DEMAND_PAGING
+	bool "InfiniBand on-demand paging support"
+	depends on INFINIBAND_USER_MEM
+	select MMU_NOTIFIER
+	default y
+	---help---
+	  On demand paging support for the InfiniBand subsystem.
+	  Together with driver support this allows registration of
+	  memory regions without pinning their pages, fetching the
+	  pages on demand instead.
+
 config INFINIBAND_ADDR_TRANS
 	bool
 	depends on INFINIBAND

drivers/infiniband/core/Makefile

@@ -11,6 +11,7 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
+ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
 ib_mad-y :=			mad.o smi.o agent.o mad_rmpp.o
 

drivers/infiniband/core/addr.c

@@ -176,8 +176,8 @@ static void set_timeout(unsigned long time)
 	unsigned long delay;
 
 	delay = time - jiffies;
-	if ((long)delay <= 0)
-		delay = 1;
+	if ((long)delay < 0)
+		delay = 0;
 
 	mod_delayed_work(addr_wq, &work, delay);
 }

drivers/infiniband/core/multicast.c

@@ -525,17 +525,22 @@ static void join_handler(int status, struct ib_sa_mcmember_rec *rec,
 	if (status)
 		process_join_error(group, status);
 	else {
+		int mgids_changed, is_mgid0;
 		ib_find_pkey(group->port->dev->device, group->port->port_num,
 			     be16_to_cpu(rec->pkey), &pkey_index);
 
 		spin_lock_irq(&group->port->lock);
-		group->rec = *rec;
 		if (group->state == MCAST_BUSY &&
 		    group->pkey_index == MCAST_INVALID_PKEY_INDEX)
 			group->pkey_index = pkey_index;
-		if (!memcmp(&mgid0, &group->rec.mgid, sizeof mgid0)) {
+		mgids_changed = memcmp(&rec->mgid, &group->rec.mgid,
+				       sizeof(group->rec.mgid));
+		group->rec = *rec;
+		if (mgids_changed) {
 			rb_erase(&group->node, &group->port->table);
-			mcast_insert(group->port, group, 1);
+			is_mgid0 = !memcmp(&mgid0, &group->rec.mgid,
+					   sizeof(mgid0));
+			mcast_insert(group->port, group, is_mgid0);
 		}
 		spin_unlock_irq(&group->port->lock);
 	}

drivers/infiniband/core/umem.c

@@ -39,6 +39,7 @@
 #include <linux/hugetlb.h>
 #include <linux/dma-attrs.h>
 #include <linux/slab.h>
+#include <rdma/ib_umem_odp.h>
 
 #include "uverbs.h"
 
@@ -69,6 +70,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 /**
  * ib_umem_get - Pin and DMA map userspace memory.
+ *
+ * If access flags indicate ODP memory, avoid pinning. Instead, stores
+ * the mm for future page fault handling in conjunction with MMU notifiers.
+ *
  * @context: userspace context to pin memory for
  * @addr: userspace virtual address to start at
  * @size: length of region to pin
@@ -103,17 +108,30 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	umem->context   = context;
 	umem->length    = size;
-	umem->offset    = addr & ~PAGE_MASK;
+	umem->address   = addr;
 	umem->page_size = PAGE_SIZE;
 	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
-	 * We ask for writable memory if any access flags other than
-	 * "remote read" are set.  "Local write" and "remote write"
+	 * We ask for writable memory if any of the following
+	 * access flags are set.  "Local write" and "remote write"
 	 * obviously require write access.  "Remote atomic" can do
 	 * things like fetch and add, which will modify memory, and
 	 * "MW bind" can change permissions by binding a window.
 	 */
-	umem->writable  = !!(access & ~IB_ACCESS_REMOTE_READ);
+	umem->writable  = !!(access &
+		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
+		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
+
+	if (access & IB_ACCESS_ON_DEMAND) {
+		ret = ib_umem_odp_get(context, umem);
+		if (ret) {
+			kfree(umem);
+			return ERR_PTR(ret);
+		}
+		return umem;
+	}
+
+	umem->odp_data = NULL;
 
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
@@ -132,7 +150,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (!vma_list)
 		umem->hugetlb = 0;
 
-	npages = PAGE_ALIGN(size + umem->offset) >> PAGE_SHIFT;
+	npages = ib_umem_num_pages(umem);
 
 	down_write(&current->mm->mmap_sem);
 
@@ -235,6 +253,11 @@ void ib_umem_release(struct ib_umem *umem)
 	struct task_struct *task;
 	unsigned long diff;
 
+	if (umem->odp_data) {
+		ib_umem_odp_release(umem);
+		return;
+	}
+
 	__ib_umem_release(umem->context->device, umem, 1);
 
 	task = get_pid_task(umem->pid, PIDTYPE_PID);
@@ -246,7 +269,7 @@ void ib_umem_release(struct ib_umem *umem)
 	if (!mm)
 		goto out;
 
-	diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;
+	diff = ib_umem_num_pages(umem);
 
 	/*
 	 * We may be called with the mm's mmap_sem already held.  This
@@ -283,6 +306,9 @@ int ib_umem_page_count(struct ib_umem *umem)
 	int n;
 	struct scatterlist *sg;
 
+	if (umem->odp_data)
+		return ib_umem_num_pages(umem);
+
 	shift = ilog2(umem->page_size);
 
 	n = 0;
@@ -292,3 +318,37 @@ int ib_umem_page_count(struct ib_umem *umem)
 	return n;
 }
 EXPORT_SYMBOL(ib_umem_page_count);
+
+/*
+ * Copy from the given ib_umem's pages to the given buffer.
+ *
+ * umem - the umem to copy from
+ * offset - offset to start copying from
+ * dst - destination buffer
+ * length - buffer length
+ *
+ * Returns 0 on success, or an error code.
+ */
+int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      size_t length)
+{
+	size_t end = offset + length;
+	int ret;
+
+	if (offset > umem->length || length > umem->length - offset) {
+		pr_err("ib_umem_copy_from not in range. offset: %zd umem length: %zd end: %zd\n",
+		       offset, umem->length, end);
+		return -EINVAL;
+	}
+
+	ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->nmap, dst, length,
+				 offset + ib_umem_offset(umem));
+
+	if (ret < 0)
+		return ret;
+	else if (ret != length)
+		return -EINVAL;
+	else
+		return 0;
+}
+EXPORT_SYMBOL(ib_umem_copy_from);

drivers/infiniband/core/umem_rbtree.c

@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2014 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interval_tree_generic.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <rdma/ib_umem_odp.h>
+
+/*
+ * The ib_umem list keeps track of memory regions for which the HW
+ * device request to receive notification when the related memory
+ * mapping is changed.
+ *
+ * ib_umem_lock protects the list.
+ */
+
+static inline u64 node_start(struct umem_odp_node *n)
+{
+	struct ib_umem_odp *umem_odp =
+			container_of(n, struct ib_umem_odp, interval_tree);
+
+	return ib_umem_start(umem_odp->umem);
+}
+
+/* Note that the representation of the intervals in the interval tree
+ * considers the ending point as contained in the interval, while the
+ * function ib_umem_end returns the first address which is not contained
+ * in the umem.
+ */
+static inline u64 node_last(struct umem_odp_node *n)
+{
+	struct ib_umem_odp *umem_odp =
+			container_of(n, struct ib_umem_odp, interval_tree);
+
+	return ib_umem_end(umem_odp->umem) - 1;
+}
+
+INTERVAL_TREE_DEFINE(struct umem_odp_node, rb, u64, __subtree_last,
+		     node_start, node_last, , rbt_ib_umem)
+
+/* @last is not a part of the interval. See comment for function
+ * node_last.
+ */
+int rbt_ib_umem_for_each_in_range(struct rb_root *root,
+				  u64 start, u64 last,
+				  umem_call_back cb,
+				  void *cookie)
+{
+	int ret_val = 0;
+	struct umem_odp_node *node;
+	struct ib_umem_odp *umem;
+
+	if (unlikely(start == last))
+		return ret_val;
+
+	for (node = rbt_ib_umem_iter_first(root, start, last - 1); node;
+			node = rbt_ib_umem_iter_next(node, start, last - 1)) {
+		umem = container_of(node, struct ib_umem_odp, interval_tree);
+		ret_val = cb(umem->umem, start, last, cookie) || ret_val;
+	}
+
+	return ret_val;
+}

drivers/infiniband/core/uverbs.h

@@ -258,5 +258,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
+IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */

drivers/infiniband/core/uverbs_cmd.c

@@ -36,6 +36,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include <asm/uaccess.h>
 
@@ -288,6 +289,9 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	struct ib_uverbs_get_context_resp resp;
 	struct ib_udata                   udata;
 	struct ib_device                 *ibdev = file->device->ib_dev;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct ib_device_attr		  dev_attr;
+#endif
 	struct ib_ucontext		 *ucontext;
 	struct file			 *filp;
 	int ret;
@@ -325,8 +329,25 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	INIT_LIST_HEAD(&ucontext->ah_list);
 	INIT_LIST_HEAD(&ucontext->xrcd_list);
 	INIT_LIST_HEAD(&ucontext->rule_list);
+	rcu_read_lock();
+	ucontext->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
+	rcu_read_unlock();
 	ucontext->closing = 0;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	ucontext->umem_tree = RB_ROOT;
+	init_rwsem(&ucontext->umem_rwsem);
+	ucontext->odp_mrs_count = 0;
+	INIT_LIST_HEAD(&ucontext->no_private_counters);
+
+	ret = ib_query_device(ibdev, &dev_attr);
+	if (ret)
+		goto err_free;
+	if (!(dev_attr.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))
+		ucontext->invalidate_range = NULL;
+
+#endif
+
 	resp.num_comp_vectors = file->device->num_comp_vectors;
 
 	ret = get_unused_fd_flags(O_CLOEXEC);
@@ -371,6 +392,7 @@ err_fd:
 	put_unused_fd(resp.async_fd);
 
 err_free:
+	put_pid(ucontext->tgid);
 	ibdev->dealloc_ucontext(ucontext);
 
 err:
@@ -378,6 +400,52 @@ err:
 	return ret;
 }
 
+static void copy_query_dev_fields(struct ib_uverbs_file *file,
+				  struct ib_uverbs_query_device_resp *resp,
+				  struct ib_device_attr *attr)
+{
+	resp->fw_ver		= attr->fw_ver;
+	resp->node_guid		= file->device->ib_dev->node_guid;
+	resp->sys_image_guid	= attr->sys_image_guid;
+	resp->max_mr_size	= attr->max_mr_size;
+	resp->page_size_cap	= attr->page_size_cap;
+	resp->vendor_id		= attr->vendor_id;
+	resp->vendor_part_id	= attr->vendor_part_id;
+	resp->hw_ver		= attr->hw_ver;
+	resp->max_qp		= attr->max_qp;
+	resp->max_qp_wr		= attr->max_qp_wr;
+	resp->device_cap_flags	= attr->device_cap_flags;
+	resp->max_sge		= attr->max_sge;
+	resp->max_sge_rd	= attr->max_sge_rd;
+	resp->max_cq		= attr->max_cq;
+	resp->max_cqe		= attr->max_cqe;
+	resp->max_mr		= attr->max_mr;
+	resp->max_pd		= attr->max_pd;
+	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
+	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
+	resp->max_res_rd_atom	= attr->max_res_rd_atom;
+	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
+	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
+	resp->atomic_cap		= attr->atomic_cap;
+	resp->max_ee			= attr->max_ee;
+	resp->max_rdd			= attr->max_rdd;
+	resp->max_mw			= attr->max_mw;
+	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
+	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
+	resp->max_mcast_grp		= attr->max_mcast_grp;
+	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
+	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
+	resp->max_ah			= attr->max_ah;
+	resp->max_fmr			= attr->max_fmr;
+	resp->max_map_per_fmr		= attr->max_map_per_fmr;
+	resp->max_srq			= attr->max_srq;
+	resp->max_srq_wr		= attr->max_srq_wr;
+	resp->max_srq_sge		= attr->max_srq_sge;
+	resp->max_pkeys			= attr->max_pkeys;
+	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
+	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
+}
+
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -398,47 +466,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-
-	resp.fw_ver 		       = attr.fw_ver;
-	resp.node_guid 		       = file->device->ib_dev->node_guid;
-	resp.sys_image_guid 	       = attr.sys_image_guid;
-	resp.max_mr_size 	       = attr.max_mr_size;
-	resp.page_size_cap 	       = attr.page_size_cap;
-	resp.vendor_id 		       = attr.vendor_id;
-	resp.vendor_part_id 	       = attr.vendor_part_id;
-	resp.hw_ver 		       = attr.hw_ver;
-	resp.max_qp 		       = attr.max_qp;
-	resp.max_qp_wr 		       = attr.max_qp_wr;
-	resp.device_cap_flags 	       = attr.device_cap_flags;
-	resp.max_sge 		       = attr.max_sge;
-	resp.max_sge_rd 	       = attr.max_sge_rd;
-	resp.max_cq 		       = attr.max_cq;
-	resp.max_cqe 		       = attr.max_cqe;
-	resp.max_mr 		       = attr.max_mr;
-	resp.max_pd 		       = attr.max_pd;
-	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
-	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
-	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
-	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
-	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
-	resp.atomic_cap 	       = attr.atomic_cap;
-	resp.max_ee 		       = attr.max_ee;
-	resp.max_rdd 		       = attr.max_rdd;
-	resp.max_mw 		       = attr.max_mw;
-	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
-	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
-	resp.max_mcast_grp 	       = attr.max_mcast_grp;
-	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
-	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
-	resp.max_ah 		       = attr.max_ah;
-	resp.max_fmr 		       = attr.max_fmr;
-	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
-	resp.max_srq 		       = attr.max_srq;
-	resp.max_srq_wr 	       = attr.max_srq_wr;
-	resp.max_srq_sge 	       = attr.max_srq_sge;
-	resp.max_pkeys 		       = attr.max_pkeys;
-	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
-	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
+	copy_query_dev_fields(file, &resp, &attr);
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -947,6 +975,18 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 		goto err_free;
 	}
 
+	if (cmd.access_flags & IB_ACCESS_ON_DEMAND) {
+		struct ib_device_attr attr;
+
+		ret = ib_query_device(pd->device, &attr);
+		if (ret || !(attr.device_cap_flags &
+				IB_DEVICE_ON_DEMAND_PAGING)) {
+			pr_debug("ODP support not available\n");
+			ret = -EINVAL;
+			goto err_put;
+		}
+	}
+
 	mr = pd->device->reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
 				     cmd.access_flags, &udata);
 	if (IS_ERR(mr)) {
@@ -3253,3 +3293,52 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 
 	return ret ? ret : in_len;
 }
+
+int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
+			      struct ib_udata *ucore,
+			      struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_query_device_resp resp;
+	struct ib_uverbs_ex_query_device  cmd;
+	struct ib_device_attr attr;
+	struct ib_device *device;
+	int err;
+
+	device = file->device->ib_dev;
+	if (ucore->inlen < sizeof(cmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	if (cmd.reserved)
+		return -EINVAL;
+
+	err = device->query_device(device, &attr);
+	if (err)
+		return err;
+
+	memset(&resp, 0, sizeof(resp));
+	copy_query_dev_fields(file, &resp.base, &attr);
+	resp.comp_mask = 0;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
+		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
+		resp.odp_caps.per_transport_caps.rc_odp_caps =
+			attr.odp_caps.per_transport_caps.rc_odp_caps;
+		resp.odp_caps.per_transport_caps.uc_odp_caps =
+			attr.odp_caps.per_transport_caps.uc_odp_caps;
+		resp.odp_caps.per_transport_caps.ud_odp_caps =
+			attr.odp_caps.per_transport_caps.ud_odp_caps;
+		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
+	}
+#endif
+
+	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
+	if (err)
+		return err;
+
+	return 0;
+}

drivers/infiniband/core/uverbs_main.c

@@ -122,7 +122,8 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 				    struct ib_udata *ucore,
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
-	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow
+	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
+	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
@@ -296,6 +297,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 		kfree(uobj);
 	}
 
+	put_pid(context->tgid);
+
 	return context->device->dealloc_ucontext(context);
 }
 

drivers/infiniband/core/verbs.c

@@ -879,7 +879,8 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
 		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
 			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw, qp_attr->ah_attr.dmac);
 			rdma_get_ll_mac((struct in6_addr *)sgid.raw, qp_attr->smac);
-			qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
+			if (!(*qp_attr_mask & IB_QP_VID))
+				qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
 		} else {
 			ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
 					qp_attr->ah_attr.dmac, &qp_attr->vlan_id);

drivers/infiniband/hw/amso1100/c2_provider.c

@@ -476,7 +476,7 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 					 c2mr->umem->page_size,
 					 i,
 					 length,
-					 c2mr->umem->offset,
+					 ib_umem_offset(c2mr->umem),
 					 &kva,
 					 c2_convert_access(acc),
 					 c2mr);

drivers/infiniband/hw/cxgb4/cm.c

@@ -1640,7 +1640,8 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
 		__state_set(&ep->com, MPA_REQ_RCVD);
 
 		/* drive upcall */
-		mutex_lock(&ep->parent_ep->com.mutex);
+		mutex_lock_nested(&ep->parent_ep->com.mutex,
+				  SINGLE_DEPTH_NESTING);
 		if (ep->parent_ep->com.state != DEAD) {
 			if (connect_request_upcall(ep))
 				abort_connection(ep, skb, GFP_KERNEL);
@@ -3126,6 +3127,8 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
 		err = c4iw_wait_for_reply(&ep->com.dev->rdev,
 					  &ep->com.wr_wait,
 					  0, 0, __func__);
+	else if (err > 0)
+		err = net_xmit_errno(err);
 	if (err)
 		pr_err("cxgb4_create_server6/filter failed err %d stid %d laddr %pI6 lport %d\n",
 		       err, ep->stid,
@@ -3159,6 +3162,8 @@ static int create_server4(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
 			err = c4iw_wait_for_reply(&ep->com.dev->rdev,
 						  &ep->com.wr_wait,
 						  0, 0, __func__);
+		else if (err > 0)
+			err = net_xmit_errno(err);
 	}
 	if (err)
 		pr_err("cxgb4_create_server/filter failed err %d stid %d laddr %pI4 lport %d\n"

drivers/infiniband/hw/cxgb4/device.c

@@ -670,7 +670,7 @@ static int ep_open(struct inode *inode, struct file *file)
 	idr_for_each(&epd->devp->stid_idr, count_idrs, &count);
 	spin_unlock_irq(&epd->devp->lock);
 
-	epd->bufsize = count * 160;
+	epd->bufsize = count * 240;
 	epd->buf = vmalloc(epd->bufsize);
 	if (!epd->buf) {
 		ret = -ENOMEM;

drivers/infiniband/hw/cxgb4/mem.c

@@ -50,6 +50,13 @@ static int inline_threshold = C4IW_INLINE_THRESHOLD;
 module_param(inline_threshold, int, 0644);
 MODULE_PARM_DESC(inline_threshold, "inline vs dsgl threshold (default=128)");
 
+static int mr_exceeds_hw_limits(struct c4iw_dev *dev, u64 length)
+{
+	return (is_t4(dev->rdev.lldi.adapter_type) ||
+		is_t5(dev->rdev.lldi.adapter_type)) &&
+		length >= 8*1024*1024*1024ULL;
+}
+
 static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr,
 				       u32 len, dma_addr_t data, int wait)
 {
@@ -369,9 +376,11 @@ static int register_mem(struct c4iw_dev *rhp, struct c4iw_pd *php,
 	int ret;
 
 	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, mhp->attr.pdid,
-			      FW_RI_STAG_NSMR, mhp->attr.perms,
+			      FW_RI_STAG_NSMR, mhp->attr.len ?
+			      mhp->attr.perms : 0,
 			      mhp->attr.mw_bind_enable, mhp->attr.zbva,
-			      mhp->attr.va_fbo, mhp->attr.len, shift - 12,
+			      mhp->attr.va_fbo, mhp->attr.len ?
+			      mhp->attr.len : -1, shift - 12,
 			      mhp->attr.pbl_size, mhp->attr.pbl_addr);
 	if (ret)
 		return ret;
@@ -536,6 +545,11 @@ int c4iw_reregister_phys_mem(struct ib_mr *mr, int mr_rereg_mask,
 			return ret;
 	}
 
+	if (mr_exceeds_hw_limits(rhp, total_size)) {
+		kfree(page_list);
+		return -EINVAL;
+	}
+
 	ret = reregister_mem(rhp, php, &mh, shift, npages);
 	kfree(page_list);
 	if (ret)
@@ -596,6 +610,12 @@ struct ib_mr *c4iw_register_phys_mem(struct ib_pd *pd,
 	if (ret)
 		goto err;
 
+	if (mr_exceeds_hw_limits(rhp, total_size)) {
+		kfree(page_list);
+		ret = -EINVAL;
+		goto err;
+	}
+
 	ret = alloc_pbl(mhp, npages);
 	if (ret) {
 		kfree(page_list);
@@ -699,6 +719,10 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	php = to_c4iw_pd(pd);
 	rhp = php->rhp;
+
+	if (mr_exceeds_hw_limits(rhp, length))
+		return ERR_PTR(-EINVAL);
+
 	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
 	if (!mhp)
 		return ERR_PTR(-ENOMEM);

drivers/infiniband/hw/cxgb4/qp.c

@@ -1538,9 +1538,9 @@ err:
 	set_state(qhp, C4IW_QP_STATE_ERROR);
 	free = 1;
 	abort = 1;
-	wake_up(&qhp->wait);
 	BUG_ON(!ep);
 	flush_qp(qhp);
+	wake_up(&qhp->wait);
 out:
 	mutex_unlock(&qhp->mutex);
 

drivers/infiniband/hw/ehca/ehca_mrmw.c

@@ -399,7 +399,7 @@ reg_user_mr_fallback:
 	pginfo.num_kpages = num_kpages;
 	pginfo.num_hwpages = num_hwpages;
 	pginfo.u.usr.region = e_mr->umem;
-	pginfo.next_hwpage = e_mr->umem->offset / hwpage_size;
+	pginfo.next_hwpage = ib_umem_offset(e_mr->umem) / hwpage_size;
 	pginfo.u.usr.next_sg = pginfo.u.usr.region->sg_head.sgl;
 	ret = ehca_reg_mr(shca, e_mr, (u64 *)virt, length, mr_access_flags,
 			  e_pd, &pginfo, &e_mr->ib.ib_mr.lkey,

drivers/infiniband/hw/ipath/ipath_mr.c

@@ -214,7 +214,7 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->mr.user_base = start;
 	mr->mr.iova = virt_addr;
 	mr->mr.length = length;
-	mr->mr.offset = umem->offset;
+	mr->mr.offset = ib_umem_offset(umem);
 	mr->mr.access_flags = mr_access_flags;
 	mr->mr.max_segs = n;
 	mr->umem = umem;

drivers/infiniband/hw/mlx4/mr.c

@@ -223,7 +223,6 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
 
 	if (flags & IB_MR_REREG_TRANS) {
 		int shift;
-		int err;
 		int n;
 
 		mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);

drivers/infiniband/hw/mlx5/Makefile

@@ -1,3 +1,4 @@
 obj-$(CONFIG_MLX5_INFINIBAND)	+= mlx5_ib.o
 
 mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o
+mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o