Merge tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Another set of mainly bugfixes and a couple of cleanups.  No new
  functionality in this round.

  Highlights include:

  Stable patches:
   - Fix a regression in /proc/self/mountstats
   - Fix the pNFS flexfiles O_DIRECT support
   - Fix high load average due to callback thread sleeping

  Bugfixes:
   - Various patches to fix the pNFS layoutcommit support
   - Do not cache pNFS deviceids unless server notifications are enabled
   - Fix a SUNRPC transport reconnection regression
   - make debugfs file creation failure non-fatal in SUNRPC
   - Another fix for circular directory warnings on NFSv4 "junctioned"
     mountpoints
   - Fix locking around NFSv4.2 fallocate() support
   - Truncating NFSv4 file opens should also sync O_DIRECT writes
   - Prevent infinite loop in rpcrdma_ep_create()

  Features:
   - Various improvements to the RDMA transport code's handling of
     memory registration
   - Various code cleanups"

* tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (55 commits)
  fs/nfs: fix new compiler warning about boolean in switch
  nfs: Remove unneeded casts in nfs
  NFS: Don't attempt to decode missing directory entries
  Revert "nfs: replace nfs_add_stats with nfs_inc_stats when add one"
  NFS: Rename idmap.c to nfs4idmap.c
  NFS: Move nfs_idmap.h into fs/nfs/
  NFS: Remove CONFIG_NFS_V4 checks from nfs_idmap.h
  NFS: Add a stub for GETDEVICELIST
  nfs: remove WARN_ON_ONCE from nfs_direct_good_bytes
  nfs: fix DIO good bytes calculation
  nfs: Fetch MOUNTED_ON_FILEID when updating an inode
  sunrpc: make debugfs file creation failure non-fatal
  nfs: fix high load average due to callback thread sleeping
  NFS: Reduce time spent holding the i_mutex during fallocate()
  NFS: Don't zap caches on fallocate()
  xprtrdma: Make rpcrdma_{un}map_one() into inline functions
  xprtrdma: Handle non-SEND completions via a callout
  xprtrdma: Add "open" memreg op
  xprtrdma: Add "destroy MRs" memreg op
  xprtrdma: Add "reset MRs" memreg op
  ...

10 files changed, 889 insertions, 732 deletions

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index b91fd9c597b4..337ca851a350 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -89,8 +89,8 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	if (!task->tk_timeout)
 		return;
 
-	dprintk("RPC: %5u setting alarm for %lu ms\n",
-			task->tk_pid, task->tk_timeout * 1000 / HZ);
+	dprintk("RPC: %5u setting alarm for %u ms\n",
+		task->tk_pid, jiffies_to_msecs(task->tk_timeout));
 
 	task->u.tk_wait.expires = jiffies + task->tk_timeout;
 	if (list_empty(&queue->timer_list.list) || time_before(task->u.tk_wait.expires, queue->timer_list.expires))
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 9949722d99ce..1d4fe24af06a 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -326,6 +326,15 @@ out_unlock:
 	xprt_clear_locked(xprt);
 }
 
+static void xprt_task_clear_bytes_sent(struct rpc_task *task)
+{
+	if (task != NULL) {
+		struct rpc_rqst *req = task->tk_rqstp;
+		if (req != NULL)
+			req->rq_bytes_sent = 0;
+	}
+}
+
 /**
  * xprt_release_xprt - allow other requests to use a transport
  * @xprt: transport with other tasks potentially waiting
@@ -336,11 +345,7 @@ out_unlock:
 void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next(xprt);
 	}
@@ -358,11 +363,7 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt);
 void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	if (xprt->snd_task == task) {
-		if (task != NULL) {
-			struct rpc_rqst *req = task->tk_rqstp;
-			if (req != NULL)
-				req->rq_bytes_sent = 0;
-		}
+		xprt_task_clear_bytes_sent(task);
 		xprt_clear_locked(xprt);
 		__xprt_lock_write_next_cong(xprt);
 	}
@@ -700,6 +701,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt,
 		goto out;
 	if (xprt->snd_task != task)
 		goto out;
+	xprt_task_clear_bytes_sent(task);
 	xprt->snd_task = cookie;
 	ret = true;
 out:
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index da5136fd5694..579f72bbcf4b 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -1,6 +1,7 @@
 obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o
 
-xprtrdma-y := transport.o rpc_rdma.o verbs.o
+xprtrdma-y := transport.o rpc_rdma.o verbs.o \
+	fmr_ops.o frwr_ops.o physical_ops.o
 
 obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o
 
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
new file mode 100644
index 000000000000..302d4ebf6fbf
--- /dev/null
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -0,0 +1,208 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Memory Regions (FMR).
+ * Referred to sometimes as MTHCAFMR mode.
+ *
+ * FMR uses synchronous memory registration and deregistration.
+ * FMR registration is known to be fast, but FMR deregistration
+ * can take tens of usecs to complete.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+/* Maximum scatter/gather per FMR */
+#define RPCRDMA_MAX_FMR_SGES	(64)
+
+static int
+fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	    struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* FMR mode conveys up to 64 pages of payload per chunk segment.
+ */
+static size_t
+fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES);
+}
+
+static int
+fmr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
+	struct ib_fmr_attr fmr_attr = {
+		.max_pages	= RPCRDMA_MAX_FMR_SGES,
+		.max_maps	= 1,
+		.page_shift	= PAGE_SHIFT
+	};
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int i, rc;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FMRs\n", __func__, i);
+
+	while (i--) {
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
+		if (IS_ERR(r->r.fmr))
+			goto out_fmr_err;
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+	}
+	return 0;
+
+out_fmr_err:
+	rc = PTR_ERR(r->r.fmr);
+	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
+	kfree(r);
+	return rc;
+}
+
+/* Use the ib_map_phys_fmr() verb to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	   int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
+	int len, pageoff, i, rc;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > RPCRDMA_MAX_FMR_SGES)
+		nsegs = RPCRDMA_MAX_FMR_SGES;
+	for (i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		physaddrs[i] = seg->mr_dma;
+		len += seg->mr_len;
+		++seg;
+		++i;
+		/* Check for holes */
+		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
+			break;
+	}
+
+	rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma);
+	if (rc)
+		goto out_maperr;
+
+	seg1->mr_rkey = mw->r.fmr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_maperr:
+	dprintk("RPC:       %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
+		__func__, len, (unsigned long long)seg1->mr_dma,
+		pageoff, i, rc);
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Use the ib_unmap_fmr() verb to prevent further remote
+ * access via RDMA READ or RDMA WRITE.
+ */
+static int
+fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct ib_device *device;
+	int rc, nsegs = seg->mr_nsegs;
+	LIST_HEAD(l);
+
+	list_add(&seg1->rl_mw->r.fmr->list, &l);
+	rc = ib_unmap_fmr(&l);
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	dprintk("RPC:       %s: ib_unmap_fmr status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, unmap all FMRs.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_fmr_external().
+ */
+static void
+fmr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_mw *r;
+	LIST_HEAD(list);
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all)
+		list_add(&r->r.fmr->list, &list);
+
+	rc = ib_unmap_fmr(&list);
+	if (rc)
+		dprintk("RPC:       %s: ib_unmap_fmr failed %i\n",
+			__func__, rc);
+}
+
+static void
+fmr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+	int rc;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		rc = ib_dealloc_fmr(r->r.fmr);
+		if (rc)
+			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
+				__func__, rc);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
+	.ro_map				= fmr_op_map,
+	.ro_unmap			= fmr_op_unmap,
+	.ro_open			= fmr_op_open,
+	.ro_maxpages			= fmr_op_maxpages,
+	.ro_init			= fmr_op_init,
+	.ro_reset			= fmr_op_reset,
+	.ro_destroy			= fmr_op_destroy,
+	.ro_displayname			= "fmr",
+};
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
new file mode 100644
index 000000000000..dff0481dbcf8
--- /dev/null
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* Lightweight memory registration using Fast Registration Work
+ * Requests (FRWR). Also referred to sometimes as FRMR mode.
+ *
+ * FRWR features ordered asynchronous registration and deregistration
+ * of arbitrarily sized memory regions. This is the fastest and safest
+ * but most complex memory registration mode.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
+	    unsigned int depth)
+{
+	struct rpcrdma_frmr *f = &r->r.frmr;
+	int rc;
+
+	f->fr_mr = ib_alloc_fast_reg_mr(pd, depth);
+	if (IS_ERR(f->fr_mr))
+		goto out_mr_err;
+	f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth);
+	if (IS_ERR(f->fr_pgl))
+		goto out_list_err;
+	return 0;
+
+out_mr_err:
+	rc = PTR_ERR(f->fr_mr);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_mr status %i\n",
+		__func__, rc);
+	return rc;
+
+out_list_err:
+	rc = PTR_ERR(f->fr_pgl);
+	dprintk("RPC:       %s: ib_alloc_fast_reg_page_list status %i\n",
+		__func__, rc);
+	ib_dereg_mr(f->fr_mr);
+	return rc;
+}
+
+static void
+__frwr_release(struct rpcrdma_mw *r)
+{
+	int rc;
+
+	rc = ib_dereg_mr(r->r.frmr.fr_mr);
+	if (rc)
+		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
+			__func__, rc);
+	ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+}
+
+static int
+frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+	     struct rpcrdma_create_data_internal *cdata)
+{
+	struct ib_device_attr *devattr = &ia->ri_devattr;
+	int depth, delta;
+
+	ia->ri_max_frmr_depth =
+			min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+			      devattr->max_fast_reg_page_list_len);
+	dprintk("RPC:       %s: device's max FR page list len = %u\n",
+		__func__, ia->ri_max_frmr_depth);
+
+	/* Add room for frmr register and invalidate WRs.
+	 * 1. FRMR reg WR for head
+	 * 2. FRMR invalidate WR for head
+	 * 3. N FRMR reg WRs for pagelist
+	 * 4. N FRMR invalidate WRs for pagelist
+	 * 5. FRMR reg WR for tail
+	 * 6. FRMR invalidate WR for tail
+	 * 7. The RDMA_SEND WR
+	 */
+	depth = 7;
+
+	/* Calculate N if the device max FRMR depth is smaller than
+	 * RPCRDMA_MAX_DATA_SEGS.
+	 */
+	if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) {
+		delta = RPCRDMA_MAX_DATA_SEGS - ia->ri_max_frmr_depth;
+		do {
+			depth += 2; /* FRMR reg + invalidate */
+			delta -= ia->ri_max_frmr_depth;
+		} while (delta > 0);
+	}
+
+	ep->rep_attr.cap.max_send_wr *= depth;
+	if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) {
+		cdata->max_requests = devattr->max_qp_wr / depth;
+		if (!cdata->max_requests)
+			return -EINVAL;
+		ep->rep_attr.cap.max_send_wr = cdata->max_requests *
+					       depth;
+	}
+
+	return 0;
+}
+
+/* FRWR mode conveys a list of pages per chunk segment. The
+ * maximum length of that list is the FRWR page list depth.
+ */
+static size_t
+frwr_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth);
+}
+
+/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */
+static void
+frwr_sendcompletion(struct ib_wc *wc)
+{
+	struct rpcrdma_mw *r;
+
+	if (likely(wc->status == IB_WC_SUCCESS))
+		return;
+
+	/* WARNING: Only wr_id and status are reliable at this point */
+	r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	dprintk("RPC:       %s: frmr %p (stale), status %d\n",
+		__func__, r, wc->status);
+	r->r.frmr.fr_state = FRMR_IS_STALE;
+}
+
+static int
+frwr_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	int i;
+
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+
+	i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS;
+	dprintk("RPC:       %s: initializing %d FRMRs\n", __func__, i);
+
+	while (i--) {
+		struct rpcrdma_mw *r;
+		int rc;
+
+		r = kzalloc(sizeof(*r), GFP_KERNEL);
+		if (!r)
+			return -ENOMEM;
+
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			kfree(r);
+			return rc;
+		}
+
+		list_add(&r->mw_list, &buf->rb_mws);
+		list_add(&r->mw_all, &buf->rb_all);
+		r->mw_sendcompletion = frwr_sendcompletion;
+	}
+
+	return 0;
+}
+
+/* Post a FAST_REG Work Request to register a memory region
+ * for remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+	    int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_device *device = ia->ri_id->device;
+	enum dma_data_direction direction = rpcrdma_data_dir(writing);
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_mw *mw = seg1->rl_mw;
+	struct rpcrdma_frmr *frmr = &mw->r.frmr;
+	struct ib_mr *mr = frmr->fr_mr;
+	struct ib_send_wr fastreg_wr, *bad_wr;
+	u8 key;
+	int len, pageoff;
+	int i, rc;
+	int seg_len;
+	u64 pa;
+	int page_no;
+
+	pageoff = offset_in_page(seg1->mr_offset);
+	seg1->mr_offset -= pageoff;	/* start of page */
+	seg1->mr_len += pageoff;
+	len = -pageoff;
+	if (nsegs > ia->ri_max_frmr_depth)
+		nsegs = ia->ri_max_frmr_depth;
+	for (page_no = i = 0; i < nsegs;) {
+		rpcrdma_map_one(device, seg, direction);
+		pa = seg->mr_dma;
+		for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) {
+			frmr->fr_pgl->page_list[page_no++] = pa;
+			pa += PAGE_SIZE;
+		}
+		len += seg->mr_len;
+		++seg;
+		++i;
+		/* Check for holes */
+		if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
+			break;
+	}
+	dprintk("RPC:       %s: Using frmr %p to map %d segments (%d bytes)\n",
+		__func__, mw, i, len);
+
+	frmr->fr_state = FRMR_IS_VALID;
+
+	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
+	fastreg_wr.wr_id = (unsigned long)(void *)mw;
+	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
+	fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma + pageoff;
+	fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl;
+	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+	fastreg_wr.wr.fast_reg.page_list_len = page_no;
+	fastreg_wr.wr.fast_reg.length = len;
+	fastreg_wr.wr.fast_reg.access_flags = writing ?
+				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
+				IB_ACCESS_REMOTE_READ;
+	key = (u8)(mr->rkey & 0x000000FF);
+	ib_update_fast_reg_key(mr, ++key);
+	fastreg_wr.wr.fast_reg.rkey = mr->rkey;
+
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+	rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr);
+	if (rc)
+		goto out_senderr;
+
+	seg1->mr_rkey = mr->rkey;
+	seg1->mr_base = seg1->mr_dma + pageoff;
+	seg1->mr_nsegs = i;
+	seg1->mr_len = len;
+	return i;
+
+out_senderr:
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	ib_update_fast_reg_key(mr, --key);
+	frmr->fr_state = FRMR_IS_INVALID;
+	while (i--)
+		rpcrdma_unmap_one(device, --seg);
+	return rc;
+}
+
+/* Post a LOCAL_INV Work Request to prevent further remote access
+ * via RDMA READ or RDMA WRITE.
+ */
+static int
+frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_mr_seg *seg1 = seg;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct ib_send_wr invalidate_wr, *bad_wr;
+	int rc, nsegs = seg->mr_nsegs;
+	struct ib_device *device;
+
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID;
+
+	memset(&invalidate_wr, 0, sizeof(invalidate_wr));
+	invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw;
+	invalidate_wr.opcode = IB_WR_LOCAL_INV;
+	invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey;
+	DECR_CQCOUNT(&r_xprt->rx_ep);
+
+	read_lock(&ia->ri_qplock);
+	device = ia->ri_id->device;
+	while (seg1->mr_nsegs--)
+		rpcrdma_unmap_one(device, seg++);
+	rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr);
+	read_unlock(&ia->ri_qplock);
+	if (rc)
+		goto out_err;
+	return nsegs;
+
+out_err:
+	/* Force rpcrdma_buffer_get() to retry */
+	seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE;
+	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
+	return nsegs;
+}
+
+/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
+ * an unusable state. Find FRMRs in this state and dereg / reg
+ * each.  FRMRs that are VALID and attached to an rpcrdma_req are
+ * also torn down.
+ *
+ * This gives all in-use FRMRs a fresh rkey and leaves them INVALID.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_frmr_external().
+ */
+static void
+frwr_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_device *device = r_xprt->rx_ia.ri_id->device;
+	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
+	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
+	struct rpcrdma_mw *r;
+	int rc;
+
+	list_for_each_entry(r, &buf->rb_all, mw_all) {
+		if (r->r.frmr.fr_state == FRMR_IS_INVALID)
+			continue;
+
+		__frwr_release(r);
+		rc = __frwr_init(r, pd, device, depth);
+		if (rc) {
+			dprintk("RPC:       %s: mw %p left %s\n",
+				__func__, r,
+				(r->r.frmr.fr_state == FRMR_IS_STALE ?
+					"stale" : "valid"));
+			continue;
+		}
+
+		r->r.frmr.fr_state = FRMR_IS_INVALID;
+	}
+}
+
+static void
+frwr_op_destroy(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_mw *r;
+
+	while (!list_empty(&buf->rb_all)) {
+		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&r->mw_all);
+		__frwr_release(r);
+		kfree(r);
+	}
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
+	.ro_map				= frwr_op_map,
+	.ro_unmap			= frwr_op_unmap,
+	.ro_open			= frwr_op_open,
+	.ro_maxpages			= frwr_op_maxpages,
+	.ro_init			= frwr_op_init,
+	.ro_reset			= frwr_op_reset,
+	.ro_destroy			= frwr_op_destroy,
+	.ro_displayname			= "frwr",
+};
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
new file mode 100644
index 000000000000..ba518af16787
--- /dev/null
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
+ */
+
+/* No-op chunk preparation. All client memory is pre-registered.
+ * Sometimes referred to as ALLPHYSICAL mode.
+ *
+ * Physical registration is simple because all client memory is
+ * pre-registered and never deregistered. This mode is good for
+ * adapter bring up, but is considered not safe: the server is
+ * trusted not to abuse its access to client memory not involved
+ * in RDMA I/O.
+ */
+
+#include "xprt_rdma.h"
+
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+# define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+static int
+physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
+		 struct rpcrdma_create_data_internal *cdata)
+{
+	return 0;
+}
+
+/* PHYSICAL memory registration conveys one page per chunk segment.
+ */
+static size_t
+physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
+{
+	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
+		     rpcrdma_max_segments(r_xprt));
+}
+
+static int
+physical_op_init(struct rpcrdma_xprt *r_xprt)
+{
+	return 0;
+}
+
+/* The client's physical memory is already exposed for
+ * remote access via RDMA READ or RDMA WRITE.
+ */
+static int
+physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
+		int nsegs, bool writing)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	rpcrdma_map_one(ia->ri_id->device, seg,
+			rpcrdma_data_dir(writing));
+	seg->mr_rkey = ia->ri_bind_mem->rkey;
+	seg->mr_base = seg->mr_dma;
+	seg->mr_nsegs = 1;
+	return 1;
+}
+
+/* Unmap a memory region, but leave it registered.
+ */
+static int
+physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
+{
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+	read_lock(&ia->ri_qplock);
+	rpcrdma_unmap_one(ia->ri_id->device, seg);
+	read_unlock(&ia->ri_qplock);
+
+	return 1;
+}
+
+static void
+physical_op_reset(struct rpcrdma_xprt *r_xprt)
+{
+}
+
+static void
+physical_op_destroy(struct rpcrdma_buffer *buf)
+{
+}
+
+const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
+	.ro_map				= physical_op_map,
+	.ro_unmap			= physical_op_unmap,
+	.ro_open			= physical_op_open,
+	.ro_maxpages			= physical_op_maxpages,
+	.ro_init			= physical_op_init,
+	.ro_reset			= physical_op_reset,
+	.ro_destroy			= physical_op_destroy,
+	.ro_displayname			= "physical",
+};
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 91ffde82fa0c..2c53ea9e1b83 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -53,6 +53,14 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
+enum rpcrdma_chunktype {
+	rpcrdma_noch = 0,
+	rpcrdma_readch,
+	rpcrdma_areadch,
+	rpcrdma_writech,
+	rpcrdma_replych
+};
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 static const char transfertypes[][12] = {
 	"pure inline",	/* no chunks */
@@ -179,6 +187,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	struct rpcrdma_write_array *warray = NULL;
 	struct rpcrdma_write_chunk *cur_wchunk = NULL;
 	__be32 *iptr = headerp->rm_body.rm_chunks;
+	int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool);
 
 	if (type == rpcrdma_readch || type == rpcrdma_areadch) {
 		/* a read chunk - server will RDMA Read our memory */
@@ -201,9 +210,9 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	if (nsegs < 0)
 		return nsegs;
 
+	map = r_xprt->rx_ia.ri_ops->ro_map;
 	do {
-		n = rpcrdma_register_external(seg, nsegs,
-						cur_wchunk != NULL, r_xprt);
+		n = map(r_xprt, seg, nsegs, cur_wchunk != NULL);
 		if (n <= 0)
 			goto out;
 		if (cur_rchunk) {	/* read */
@@ -275,34 +284,13 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	return (unsigned char *)iptr - (unsigned char *)headerp;
 
 out:
-	if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_FRMR) {
-		for (pos = 0; nchunks--;)
-			pos += rpcrdma_deregister_external(
-					&req->rl_segments[pos], r_xprt);
-	}
-	return n;
-}
+	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+		return n;
 
-/*
- * Marshal chunks. This routine returns the header length
- * consumed by marshaling.
- *
- * Returns positive RPC/RDMA header size, or negative errno.
- */
-
-ssize_t
-rpcrdma_marshal_chunks(struct rpc_rqst *rqst, ssize_t result)
-{
-	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
-	struct rpcrdma_msg *headerp = rdmab_to_msg(req->rl_rdmabuf);
-
-	if (req->rl_rtype != rpcrdma_noch)
-		result = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
-					       headerp, req->rl_rtype);
-	else if (req->rl_wtype != rpcrdma_noch)
-		result = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
-					       headerp, req->rl_wtype);
-	return result;
+	for (pos = 0; nchunks--;)
+		pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt,
+						      &req->rl_segments[pos]);
+	return n;
 }
 
 /*
@@ -397,6 +385,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	char *base;
 	size_t rpclen, padlen;
 	ssize_t hdrlen;
+	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
 
 	/*
@@ -433,13 +422,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * into pages; otherwise use reply chunks.
 	 */
 	if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst))
-		req->rl_wtype = rpcrdma_noch;
+		wtype = rpcrdma_noch;
 	else if (rqst->rq_rcv_buf.page_len == 0)
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
-		req->rl_wtype = rpcrdma_writech;
+		wtype = rpcrdma_writech;
 	else
-		req->rl_wtype = rpcrdma_replych;
+		wtype = rpcrdma_replych;
 
 	/*
 	 * Chunks needed for arguments?
@@ -456,16 +445,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * TBD check NFSv4 setacl
 	 */
 	if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst))
-		req->rl_rtype = rpcrdma_noch;
+		rtype = rpcrdma_noch;
 	else if (rqst->rq_snd_buf.page_len == 0)
-		req->rl_rtype = rpcrdma_areadch;
+		rtype = rpcrdma_areadch;
 	else
-		req->rl_rtype = rpcrdma_readch;
+		rtype = rpcrdma_readch;
 
 	/* The following simplification is not true forever */
-	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype == rpcrdma_replych)
-		req->rl_wtype = rpcrdma_noch;
-	if (req->rl_rtype != rpcrdma_noch && req->rl_wtype != rpcrdma_noch) {
+	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
+		wtype = rpcrdma_noch;
+	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
 		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
 			__func__);
 		return -EIO;
@@ -479,7 +468,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * When padding is in use and applies to the transfer, insert
 	 * it and change the message type.
 	 */
-	if (req->rl_rtype == rpcrdma_noch) {
+	if (rtype == rpcrdma_noch) {
 
 		padlen = rpcrdma_inline_pullup(rqst,
 						RPCRDMA_INLINE_PAD_VALUE(rqst));
@@ -494,7 +483,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero;
 			headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero;
 			hdrlen += 2 * sizeof(u32); /* extra words in padhdr */
-			if (req->rl_wtype != rpcrdma_noch) {
+			if (wtype != rpcrdma_noch) {
 				dprintk("RPC:       %s: invalid chunk list\n",
 					__func__);
 				return -EIO;
@@ -515,18 +504,26 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (req->rl_wtype == rpcrdma_noch)
-				req->rl_wtype = rpcrdma_replych;
+			if (wtype == rpcrdma_noch)
+				wtype = rpcrdma_replych;
 		}
 	}
 
-	hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen);
+	if (rtype != rpcrdma_noch) {
+		hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf,
+					       headerp, rtype);
+		wtype = rtype;	/* simplify dprintk */
+
+	} else if (wtype != rpcrdma_noch) {
+		hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf,
+					       headerp, wtype);
+	}
 	if (hdrlen < 0)
 		return hdrlen;
 
 	dprintk("RPC:       %s: %s: hdrlen %zd rpclen %zd padlen %zd"
 		" headerp 0x%p base 0x%p lkey 0x%x\n",
-		__func__, transfertypes[req->rl_wtype], hdrlen, rpclen, padlen,
+		__func__, transfertypes[wtype], hdrlen, rpclen, padlen,
 		headerp, base, rdmab_lkey(req->rl_rdmabuf));
 
 	/*
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 2e192baa59f3..54f23b1be986 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -157,12 +157,47 @@ static struct ctl_table sunrpc_table[] = {
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
 static void
+xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	char buf[20];
+
+	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA;
+}
+
+static void
+xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char buf[40];
+
+	snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
+
+	xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6;
+}
+
+static void
 xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 {
 	struct sockaddr *sap = (struct sockaddr *)
 					&rpcx_to_rdmad(xprt).addr;
-	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	char buf[64];
+	char buf[128];
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		xprt_rdma_format_addresses4(xprt, sap);
+		break;
+	case AF_INET6:
+		xprt_rdma_format_addresses6(xprt, sap);
+		break;
+	default:
+		pr_err("rpcrdma: Unrecognized address family\n");
+		return;
+	}
 
 	(void)rpc_ntop(sap, buf, sizeof(buf));
 	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
@@ -170,16 +205,10 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
-
-	snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
-
 	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
 	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
 
-	/* netid */
-	xprt->address_strings[RPC_DISPLAY_NETID] = "rdma";
+	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
 }
 
 static void
@@ -377,7 +406,10 @@ xprt_setup_rdma(struct xprt_create *args)
 			  xprt_rdma_connect_worker);
 
 	xprt_rdma_format_addresses(xprt);
-	xprt->