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

Pull rdma updates from Jason Gunthorpe:
 "This has been a slightly more active cycle than normal with ongoing
  core changes and quite a lot of collected driver updates.

   - Various driver fixes for bnxt_re, cxgb4, hns, mlx5, pvrdma, rxe

   - A new data transfer mode for HFI1 giving higher performance

   - Significant functional and bug fix update to the mlx5
     On-Demand-Paging MR feature

   - A chip hang reset recovery system for hns

   - Change mm->pinned_vm to an atomic64

   - Update bnxt_re to support a new 57500 chip

   - A sane netlink 'rdma link add' method for creating rxe devices and
     fixing the various unregistration race conditions in rxe's
     unregister flow

   - Allow lookup up objects by an ID over netlink

   - Various reworking of the core to driver interface:
       - drivers should not assume umem SGLs are in PAGE_SIZE chunks
       - ucontext is accessed via udata not other means
       - start to make the core code responsible for object memory
         allocation
       - drivers should convert struct device to struct ib_device via a
         helper
       - drivers have more tools to avoid use after unregister problems"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (280 commits)
  net/mlx5: ODP support for XRC transport is not enabled by default in FW
  IB/hfi1: Close race condition on user context disable and close
  RDMA/umem: Revert broken 'off by one' fix
  RDMA/umem: minor bug fix in error handling path
  RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
  cxgb4: kfree mhp after the debug print
  IB/rdmavt: Fix concurrency panics in QP post_send and modify to error
  IB/rdmavt: Fix loopback send with invalidate ordering
  IB/iser: Fix dma_nents type definition
  IB/mlx5: Set correct write permissions for implicit ODP MR
  bnxt_re: Clean cq for kernel consumers only
  RDMA/uverbs: Don't do double free of allocated PD
  RDMA: Handle ucontext allocations by IB/core
  RDMA/core: Fix a WARN() message
  bnxt_re: fix the regression due to changes in alloc_pbl
  IB/mlx4: Increase the timeout for CM cache
  IB/core: Abort page fault handler silently during owning process exit
  IB/mlx5: Validate correct PD before prefetch MR
  IB/mlx5: Protect against prefetch of invalid MR
  RDMA/uverbs: Store PR pointer before it is overwritten
  ...

7 files changed, 53 insertions, 126 deletions

diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c
index 5ed1ed93380f..caeb77d07a58 100644
--- a/drivers/infiniband/hw/qib/qib_debugfs.c
+++ b/drivers/infiniband/hw/qib/qib_debugfs.c
@@ -66,15 +66,6 @@ static const struct file_operations _##name##_file_ops = { \
 	.release = seq_release \
 };
 
-#define DEBUGFS_FILE_CREATE(name) \
-do { \
-	struct dentry *ent; \
-	ent = debugfs_create_file(#name , 0400, ibd->qib_ibdev_dbg, \
-		ibd, &_##name##_file_ops); \
-	if (!ent) \
-		pr_warn("create of " #name " failed\n"); \
-} while (0)
-
 static void *_opcode_stats_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct qib_opcode_stats_perctx *opstats;
@@ -249,17 +240,17 @@ DEBUGFS_FILE(qp_stats)
 
 void qib_dbg_ibdev_init(struct qib_ibdev *ibd)
 {
+	struct dentry *root;
 	char name[10];
 
 	snprintf(name, sizeof(name), "qib%d", dd_from_dev(ibd)->unit);
-	ibd->qib_ibdev_dbg = debugfs_create_dir(name, qib_dbg_root);
-	if (!ibd->qib_ibdev_dbg) {
-		pr_warn("create of %s failed\n", name);
-		return;
-	}
-	DEBUGFS_FILE_CREATE(opcode_stats);
-	DEBUGFS_FILE_CREATE(ctx_stats);
-	DEBUGFS_FILE_CREATE(qp_stats);
+	root = debugfs_create_dir(name, qib_dbg_root);
+	ibd->qib_ibdev_dbg = root;
+
+	debugfs_create_file("opcode_stats", 0400, root, ibd,
+			    &_opcode_stats_file_ops);
+	debugfs_create_file("ctx_stats", 0400, root, ibd, &_ctx_stats_file_ops);
+	debugfs_create_file("qp_stats", 0400, root, ibd, &_qp_stats_file_ops);
 }
 
 void qib_dbg_ibdev_exit(struct qib_ibdev *ibd)
@@ -274,8 +265,6 @@ out:
 void qib_dbg_init(void)
 {
 	qib_dbg_root = debugfs_create_dir(QIB_DRV_NAME, NULL);
-	if (!qib_dbg_root)
-		pr_warn("init of debugfs failed\n");
 }
 
 void qib_dbg_exit(void)
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 6fa002940451..50dd9811b088 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -45,12 +45,7 @@ static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 	u32 len;
 
 	len = ((psn - wqe->psn) & QIB_PSN_MASK) * pmtu;
-	ss->sge = wqe->sg_list[0];
-	ss->sg_list = wqe->sg_list + 1;
-	ss->num_sge = wqe->wr.num_sge;
-	ss->total_len = wqe->length;
-	rvt_skip_sge(ss, len, false);
-	return wqe->length - len;
+	return rvt_restart_sge(ss, wqe, len);
 }
 
 /**
diff --git a/drivers/infiniband/hw/qib/qib_sdma.c b/drivers/infiniband/hw/qib/qib_sdma.c
index 3d64081c4819..99e11c347130 100644
--- a/drivers/infiniband/hw/qib/qib_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_sdma.c
@@ -565,13 +565,8 @@ retry:
 	sge = &ss->sge;
 	while (dwords) {
 		u32 dw;
-		u32 len;
+		u32 len = rvt_get_sge_length(sge, dwords << 2);
 
-		len = dwords << 2;
-		if (len > sge->length)
-			len = sge->length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
 		dw = (len + 3) >> 2;
 		addr = dma_map_single(&ppd->dd->pcidev->dev, sge->vaddr,
 				      dw << 2, DMA_TO_DEVICE);
@@ -594,24 +589,7 @@ retry:
 			descqp = &ppd->sdma_descq[0].qw[0];
 			++ppd->sdma_generation;
 		}
-		sge->vaddr += len;
-		sge->length -= len;
-		sge->sge_length -= len;
-		if (sge->sge_length == 0) {
-			if (--ss->num_sge)
-				*sge = *ss->sg_list++;
-		} else if (sge->length == 0 && sge->mr->lkey) {
-			if (++sge->n >= RVT_SEGSZ) {
-				if (++sge->m >= sge->mr->mapsz)
-					break;
-				sge->n = 0;
-			}
-			sge->vaddr =
-				sge->mr->map[sge->m]->segs[sge->n].vaddr;
-			sge->length =
-				sge->mr->map[sge->m]->segs[sge->n].length;
-		}
-
+		rvt_update_sge(ss, len, false);
 		dwoffset += dw;
 		dwords -= dw;
 	}
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index 1cf4ca3f23e3..905206a0c2d5 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -555,7 +555,7 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr,
 			   char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 
 	return sprintf(buf, "%x\n", dd_from_dev(dev)->minrev);
 }
@@ -565,7 +565,7 @@ static ssize_t hca_type_show(struct device *device,
 			     struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 	int ret;
 
@@ -590,7 +590,7 @@ static ssize_t boardversion_show(struct device *device,
 				 struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 
 	/* The string printed here is already newline-terminated. */
@@ -602,7 +602,7 @@ static ssize_t localbus_info_show(struct device *device,
 				  struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 
 	/* The string printed here is already newline-terminated. */
@@ -614,7 +614,7 @@ static ssize_t nctxts_show(struct device *device,
 			   struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 
 	/* Return the number of user ports (contexts) available. */
@@ -630,7 +630,7 @@ static ssize_t nfreectxts_show(struct device *device,
 			       struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 
 	/* Return the number of free user ports (contexts) available. */
@@ -642,7 +642,7 @@ static ssize_t serial_show(struct device *device,
 			   struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 
 	buf[sizeof(dd->serial)] = '\0';
@@ -657,7 +657,7 @@ static ssize_t chip_reset_store(struct device *device,
 				size_t count)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 	int ret;
 
@@ -679,7 +679,7 @@ static ssize_t tempsense_show(struct device *device,
 			      struct device_attribute *attr, char *buf)
 {
 	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, rdi.ibdev.dev);
+		rdma_device_to_drv_device(device, struct qib_ibdev, rdi.ibdev);
 	struct qib_devdata *dd = dd_from_dev(dev);
 	int ret;
 	int idx;
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index 445ea19a2ec8..5cdedba2d164 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -172,12 +172,8 @@ static void qib_ud_loopback(struct rvt_qp *sqp, struct rvt_swqe *swqe)
 	ssge.num_sge = swqe->wr.num_sge;
 	sge = &ssge.sge;
 	while (length) {
-		u32 len = sge->length;
+		u32 len = rvt_get_sge_length(sge, length);
 
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
 		rvt_copy_sge(qp, &qp->r_sge, sge->vaddr, len, true, false);
 		sge->vaddr += len;
 		sge->length -= len;
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 16543d5e80c3..123ca8f64f75 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -49,43 +49,6 @@ static void __qib_release_user_pages(struct page **p, size_t num_pages,
 	}
 }
 
-/*
- * Call with current->mm->mmap_sem held.
- */
-static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
-				struct page **p)
-{
-	unsigned long lock_limit;
-	size_t got;
-	int ret;
-
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-	if (num_pages > lock_limit && !capable(CAP_IPC_LOCK)) {
-		ret = -ENOMEM;
-		goto bail;
-	}
-
-	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages(start_page + got * PAGE_SIZE,
-				     num_pages - got,
-				     FOLL_WRITE | FOLL_FORCE,
-				     p + got, NULL);
-		if (ret < 0)
-			goto bail_release;
-	}
-
-	current->mm->pinned_vm += num_pages;
-
-	ret = 0;
-	goto bail;
-
-bail_release:
-	__qib_release_user_pages(p, got, 0);
-bail:
-	return ret;
-}
-
 /**
  * qib_map_page - a safety wrapper around pci_map_page()
  *
@@ -137,26 +100,44 @@ int qib_map_page(struct pci_dev *hwdev, struct page *page, dma_addr_t *daddr)
 int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 		       struct page **p)
 {
+	unsigned long locked, lock_limit;
+	size_t got;
 	int ret;
 
-	down_write(&current->mm->mmap_sem);
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	locked = atomic64_add_return(num_pages, &current->mm->pinned_vm);
 
-	ret = __qib_get_user_pages(start_page, num_pages, p);
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		ret = -ENOMEM;
+		goto bail;
+	}
 
-	up_write(&current->mm->mmap_sem);
+	down_read(&current->mm->mmap_sem);
+	for (got = 0; got < num_pages; got += ret) {
+		ret = get_user_pages_longterm(start_page + got * PAGE_SIZE,
+					      num_pages - got,
+					      FOLL_WRITE | FOLL_FORCE,
+					      p + got, NULL);
+		if (ret < 0) {
+			up_read(&current->mm->mmap_sem);
+			goto bail_release;
+		}
+	}
+	up_read(&current->mm->mmap_sem);
 
+	return 0;
+bail_release:
+	__qib_release_user_pages(p, got, 0);
+bail:
+	atomic64_sub(num_pages, &current->mm->pinned_vm);
 	return ret;
 }
 
 void qib_release_user_pages(struct page **p, size_t num_pages)
 {
-	if (current->mm) /* during close after signal, mm can be NULL */
-		down_write(&current->mm->mmap_sem);
-
 	__qib_release_user_pages(p, num_pages, 1);
 
-	if (current->mm) {
-		current->mm->pinned_vm -= num_pages;
-		up_write(&current->mm->mmap_sem);
-	}
+	/* during close after signal, mm can be NULL */
+	if (current->mm)
+		atomic64_sub(num_pages, &current->mm->pinned_vm);
 }
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 276304f611ab..5ff32d32c61c 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -144,12 +144,8 @@ static u32 qib_count_sge(struct rvt_sge_state *ss, u32 length)
 	u32 ndesc = 1;  /* count the header */
 
 	while (length) {
-		u32 len = sge.length;
+		u32 len = rvt_get_sge_length(&sge, length);
 
-		if (len > length)
-			len = length;
-		if (len > sge.sge_length)
-			len = sge.sge_length;
 		if (((long) sge.vaddr & (sizeof(u32) - 1)) ||
 		    (len != length && (len & (sizeof(u32) - 1)))) {
 			ndesc = 0;
@@ -186,12 +182,8 @@ static void qib_copy_from_sge(void *data, struct rvt_sge_state *ss, u32 length)
 	struct rvt_sge *sge = &ss->sge;
 
 	while (length) {
-		u32 len = sge->length;
+		u32 len = rvt_get_sge_length(sge, length);
 
-		if (len > length)
-			len = length;
-		if (len > sge->sge_length)
-			len = sge->sge_length;
 		memcpy(data, sge->vaddr, len);
 		sge->vaddr += len;
 		sge->length -= len;
@@ -440,13 +432,9 @@ static void copy_io(u32 __iomem *piobuf, struct rvt_sge_state *ss,
 	u32 last;
 
 	while (1) {
-		u32 len = ss->sge.length;
+		u32 len = rvt_get_sge_length(&ss->sge, length);
 		u32 off;
 
-		if (len > length)
-			len = length;
-		if (len > ss->sge.sge_length)
-			len = ss->sge.sge_length;
 		/* If the source address is not aligned, try to align it. */
 		off = (unsigned long)ss->sge.vaddr & (sizeof(u32) - 1);
 		if (off) {
@@ -1494,6 +1482,7 @@ static void qib_fill_device_attr(struct qib_devdata *dd)
 }
 
 static const struct ib_device_ops qib_dev_ops = {
+	.init_port = qib_create_port_files,
 	.modify_device = qib_modify_device,
 	.process_mad = qib_process_mad,
 };
@@ -1567,7 +1556,6 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	/*
 	 * Fill in rvt info object.
 	 */
-	dd->verbs_dev.rdi.driver_f.port_callback = qib_create_port_files;
 	dd->verbs_dev.rdi.driver_f.get_pci_dev = qib_get_pci_dev;
 	dd->verbs_dev.rdi.driver_f.check_ah = qib_check_ah;
 	dd->verbs_dev.rdi.driver_f.setup_wqe = qib_check_send_wqe;