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

…el/git/roland/infiniband

Pull infiniband/RDMA updates from Roland Dreier:
 - large set of iSER initiator improvements
 - hardware driver fixes for cxgb4, mlx5 and ocrdma
 - small fixes to core midlayer

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (47 commits)
  RDMA/cxgb4: Fix ntuple calculation for ipv6 and remove duplicate line
  RDMA/cxgb4: Add missing neigh_release in find_route
  RDMA/cxgb4: Take IPv6 into account for best_mtu and set_emss
  RDMA/cxgb4: Make c4iw_wr_log_size_order static
  IB/core: Fix XRC race condition in ib_uverbs_open_qp
  IB/core: Clear AH attr variable to prevent garbage data
  RDMA/ocrdma: Save the bit environment, spare unncessary parenthesis
  RDMA/ocrdma: The kernel has a perfectly good BIT() macro - use it
  RDMA/ocrdma: Don't memset() buffers we just allocated with kzalloc()
  RDMA/ocrdma: Remove a unused-label warning
  RDMA/ocrdma: Convert kernel VA to PA for mmap in user
  RDMA/ocrdma: Get vlan tag from ib_qp_attrs
  RDMA/ocrdma: Add default GID at index 0
  IB/mlx5, iser, isert: Add Signature API additions
  Target/iser: Centralize ib_sig_domain setting
  IB/iser: Centralize ib_sig_domain settings
  IB/mlx5: Use extended internal signature layout
  IB/iser: Set IP_CSUM as default guard type
  IB/iser: Remove redundant assignment
  IB/mlx5: Use enumerations for PI copy mask
  ...

MAINTAINERS

@@ -5112,6 +5112,7 @@ F:	include/scsi/*iscsi*
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Or Gerlitz <[email protected]>
+M:	Sagi Grimberg <[email protected]>
 M:	Roi Dayan <[email protected]>
 L:	[email protected]
 S:	Supported

drivers/infiniband/core/uverbs_cmd.c

@@ -2518,6 +2518,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	attr.grh.sgid_index    = cmd.attr.grh.sgid_index;
 	attr.grh.hop_limit     = cmd.attr.grh.hop_limit;
 	attr.grh.traffic_class = cmd.attr.grh.traffic_class;
+	attr.vlan_id           = 0;
+	memset(&attr.dmac, 0, sizeof(attr.dmac));
 	memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
 
 	ah = ib_create_ah(pd, &attr);

drivers/infiniband/core/uverbs_main.c

@@ -477,6 +477,7 @@ static void ib_uverbs_async_handler(struct ib_uverbs_file *file,
 
 	entry->desc.async.element    = element;
 	entry->desc.async.event_type = event;
+	entry->desc.async.reserved   = 0;
 	entry->counter               = counter;
 
 	list_add_tail(&entry->list, &file->async_file->event_list);
@@ -502,6 +503,10 @@ void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr)
 {
 	struct ib_uevent_object *uobj;
 
+	/* for XRC target qp's, check that qp is live */
+	if (!event->element.qp->uobject || !event->element.qp->uobject->live)
+		return;
+
 	uobj = container_of(event->element.qp->uobject,
 			    struct ib_uevent_object, uobject);
 

drivers/infiniband/hw/cxgb4/cm.c

@@ -236,10 +236,12 @@ static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
 static void set_emss(struct c4iw_ep *ep, u16 opt)
 {
 	ep->emss = ep->com.dev->rdev.lldi.mtus[GET_TCPOPT_MSS(opt)] -
-		   sizeof(struct iphdr) - sizeof(struct tcphdr);
+		   ((AF_INET == ep->com.remote_addr.ss_family) ?
+		    sizeof(struct iphdr) : sizeof(struct ipv6hdr)) -
+		   sizeof(struct tcphdr);
 	ep->mss = ep->emss;
 	if (GET_TCPOPT_TSTAMP(opt))
-		ep->emss -= 12;
+		ep->emss -= round_up(TCPOLEN_TIMESTAMP, 4);
 	if (ep->emss < 128)
 		ep->emss = 128;
 	if (ep->emss & 7)
@@ -415,6 +417,7 @@ static struct dst_entry *find_route(struct c4iw_dev *dev, __be32 local_ip,
 		return NULL;
 	if (!our_interface(dev, n->dev) &&
 	    !(n->dev->flags & IFF_LOOPBACK)) {
+		neigh_release(n);
 		dst_release(&rt->dst);
 		return NULL;
 	}
@@ -581,11 +584,14 @@ static void c4iw_record_pm_msg(struct c4iw_ep *ep,
 }
 
 static void best_mtu(const unsigned short *mtus, unsigned short mtu,
-		     unsigned int *idx, int use_ts)
+		     unsigned int *idx, int use_ts, int ipv6)
 {
-	unsigned short hdr_size = sizeof(struct iphdr) +
+	unsigned short hdr_size = (ipv6 ?
+				   sizeof(struct ipv6hdr) :
+				   sizeof(struct iphdr)) +
 				  sizeof(struct tcphdr) +
-				  (use_ts ? 12 : 0);
+				  (use_ts ?
+				   round_up(TCPOLEN_TIMESTAMP, 4) : 0);
 	unsigned short data_size = mtu - hdr_size;
 
 	cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
@@ -634,7 +640,8 @@ static int send_connect(struct c4iw_ep *ep)
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
 
 	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
-		 enable_tcp_timestamps);
+		 enable_tcp_timestamps,
+		 (AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
 	wscale = compute_wscale(rcv_win);
 
 	/*
@@ -668,6 +675,7 @@ static int send_connect(struct c4iw_ep *ep)
 	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
 		opt2 |= T5_OPT_2_VALID;
 		opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
 	}
 	t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
 
@@ -713,8 +721,6 @@ static int send_connect(struct c4iw_ep *ep)
 	} else {
 		u32 isn = (prandom_u32() & ~7UL) - 1;
 
-		opt2 |= T5_OPT_2_VALID;
-		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
 		if (peer2peer)
 			isn += 4;
 
@@ -756,10 +762,10 @@ static int send_connect(struct c4iw_ep *ep)
 			t5_req6->peer_ip_lo = *((__be64 *)
 						(ra6->sin6_addr.s6_addr + 8));
 			t5_req6->opt0 = cpu_to_be64(opt0);
-			t5_req6->params = (__force __be64)cpu_to_be32(
+			t5_req6->params = cpu_to_be64(V_FILTER_TUPLE(
 							cxgb4_select_ntuple(
 						ep->com.dev->rdev.lldi.ports[0],
-						ep->l2t));
+						ep->l2t)));
 			t5_req6->rsvd = cpu_to_be32(isn);
 			PDBG("%s snd_isn %u\n", __func__,
 			     be32_to_cpu(t5_req6->rsvd));
@@ -1763,7 +1769,8 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 	req->tcb.tx_max = (__force __be32) jiffies;
 	req->tcb.rcv_adv = htons(1);
 	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
-		 enable_tcp_timestamps);
+		 enable_tcp_timestamps,
+		 (AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
 	wscale = compute_wscale(rcv_win);
 
 	/*
@@ -2162,7 +2169,8 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 						    ep->hwtid));
 
 	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
-		 enable_tcp_timestamps && req->tcpopt.tstamp);
+		 enable_tcp_timestamps && req->tcpopt.tstamp,
+		 (AF_INET == ep->com.remote_addr.ss_family) ? 0 : 1);
 	wscale = compute_wscale(rcv_win);
 
 	/*

drivers/infiniband/hw/cxgb4/device.c

@@ -60,7 +60,7 @@ int c4iw_wr_log = 0;
 module_param(c4iw_wr_log, int, 0444);
 MODULE_PARM_DESC(c4iw_wr_log, "Enables logging of work request timing data.");
 
-int c4iw_wr_log_size_order = 12;
+static int c4iw_wr_log_size_order = 12;
 module_param(c4iw_wr_log_size_order, int, 0444);
 MODULE_PARM_DESC(c4iw_wr_log_size_order,
 		 "Number of entries (log2) in the work request timing log.");

drivers/infiniband/hw/mlx5/main.c

@@ -657,13 +657,13 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 			return -EINVAL;
 
 		idx = get_index(vma->vm_pgoff);
+		if (idx >= uuari->num_uars)
+			return -EINVAL;
+
 		pfn = uar_index2pfn(dev, uuari->uars[idx].index);
 		mlx5_ib_dbg(dev, "uar idx 0x%lx, pfn 0x%llx\n", idx,
 			    (unsigned long long)pfn);
 
-		if (idx >= uuari->num_uars)
-			return -EINVAL;
-
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
 				       PAGE_SIZE, vma->vm_page_prot))
@@ -1425,8 +1425,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 {
 	struct mlx5_ib_dev *dev = context;
-	destroy_umrc_res(dev);
 	ib_unregister_device(&dev->ib_dev);
+	destroy_umrc_res(dev);
 	destroy_dev_resources(&dev->devr);
 	free_comp_eqs(dev);
 	ib_dealloc_device(&dev->ib_dev);

drivers/infiniband/hw/mlx5/mem.c

@@ -55,16 +55,17 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	u64 pfn;
 	struct scatterlist *sg;
 	int entry;
+	unsigned long page_shift = ilog2(umem->page_size);
 
-	addr = addr >> PAGE_SHIFT;
+	addr = addr >> page_shift;
 	tmp = (unsigned long)addr;
 	m = find_first_bit(&tmp, sizeof(tmp));
 	skip = 1 << m;
 	mask = skip - 1;
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
-		len = sg_dma_len(sg) >> PAGE_SHIFT;
-		pfn = sg_dma_address(sg) >> PAGE_SHIFT;
+		len = sg_dma_len(sg) >> page_shift;
+		pfn = sg_dma_address(sg) >> page_shift;
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
 				tmp = (unsigned long)pfn;
@@ -103,14 +104,15 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 
 		*ncont = 0;
 	}
-	*shift = PAGE_SHIFT + m;
+	*shift = page_shift + m;
 	*count = i;
 }
 
 void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 			  int page_shift, __be64 *pas, int umr)
 {
-	int shift = page_shift - PAGE_SHIFT;
+	unsigned long umem_page_shift = ilog2(umem->page_size);
+	int shift = page_shift - umem_page_shift;
 	int mask = (1 << shift) - 1;
 	int i, k;
 	u64 cur = 0;
@@ -121,11 +123,11 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
-		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		len = sg_dma_len(sg) >> umem_page_shift;
 		base = sg_dma_address(sg);
 		for (k = 0; k < len; k++) {
 			if (!(i & mask)) {
-				cur = base + (k << PAGE_SHIFT);
+				cur = base + (k << umem_page_shift);
 				if (umr)
 					cur |= 3;
 
@@ -134,7 +136,7 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 					    i >> shift, be64_to_cpu(pas[i >> shift]));
 			}  else
 				mlx5_ib_dbg(dev, "=====> 0x%llx\n",
-					    base + (k << PAGE_SHIFT));
+					    base + (k << umem_page_shift));
 			i++;
 		}
 	}

drivers/infiniband/hw/mlx5/mr.c

@@ -881,12 +881,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int order;
 	int err;
 
-	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx\n",
-		    start, virt_addr, length);
+	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
+		    start, virt_addr, length, access_flags);
 	umem = ib_umem_get(pd->uobject->context, start, length, access_flags,
 			   0);
 	if (IS_ERR(umem)) {
-		mlx5_ib_dbg(dev, "umem get failed\n");
+		mlx5_ib_dbg(dev, "umem get failed (%ld)\n", PTR_ERR(umem));
 		return (void *)umem;
 	}