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

Pull more rdma updates from Doug Ledford:
 "This is the second group of code for the 4.7 merge window.  It looks
  large, but only in one sense.  I'll get to that in a minute.  The list
  of changes here breaks down as follows:

   - Dynamic counter infrastructure in the IB drivers

     This is a sysfs based code to allow free form access to the
     hardware counters RDMA devices might support so drivers don't need
     to code this up repeatedly themselves

   - SendOnlyFullMember multicast support

   - IB router support

   - A couple misc fixes

   - The big item on the list: hfi1 driver updates, plus moving the hfi1
     driver out of staging

  There was a group of 15 patches in the hfi1 list that I thought I had
  in the first pull request but they weren't.  So that added to the
  length of the hfi1 section here.

  As far as these go, everything but the hfi1 is pretty straight
  forward.

  The hfi1 is, if you recall, the driver that Al had complaints about
  how it used the write/writev interfaces in an overloaded fashion.  The
  write portion of their interface behaved like the write handler in the
  IB stack proper and did bi-directional communications.  The writev
  interface, on the other hand, only accepts SDMA request structures.
  The completions for those structures are sent back via an entirely
  different event mechanism.

  With the security patch, we put security checks on the write
  interface, however, we also knew they would be going away soon.  Now,
  we've converted the write handler in the hfi1 driver to use ioctls
  from the IB reserved magic area for its bidirectional communications.
  With that change, Intel has addressed all of the items originally on
  their TODO when they went into staging (as well as many items added to
  the list later).

  As such, I moved them out, and since they were the last item in the
  staging/rdma directory, and I don't have immediate plans to use the
  staging area again, I removed the staging/rdma area.

  Because of the move out of staging, as well as a series of 5 patches
  in the hfi1 driver that removed code people thought should be done in
  a different way and was optional to begin with (a snoop debug
  interface, an eeprom driver for an eeprom connected directory to their
  hfi1 chip and not via an i2c bus, and a few other things like that),
  the line count, especially the removal count, is high"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (56 commits)
  staging/rdma: Remove the entire rdma subdirectory of staging
  IB/core: Make device counter infrastructure dynamic
  IB/hfi1: Fix pio map initialization
  IB/hfi1: Correct 8051 link parameter settings
  IB/hfi1: Update pkey table properly after link down or FM start
  IB/rdamvt: Fix rdmavt s_ack_queue sizing
  IB/rdmavt: Max atomic value should be a u8
  IB/hfi1: Fix hard lockup due to not using save/restore spin lock
  IB/hfi1: Add tracing support for send with invalidate opcode
  IB/hfi1, qib: Add ieth to the packet header definitions
  IB/hfi1: Move driver out of staging
  IB/hfi1: Do not free hfi1 cdev parent structure early
  IB/hfi1: Add trace message in user IOCTL handling
  IB/hfi1: Remove write(), use ioctl() for user cmds
  IB/hfi1: Add ioctl() interface for user commands
  IB/hfi1: Remove unused user command
  IB/hfi1: Remove snoop/diag interface
  IB/hfi1: Remove EPROM functionality from data device
  IB/hfi1: Remove UI char device
  IB/hfi1: Remove multiple device cdev
  ...

1 files changed, 325 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
new file mode 100644
index 000000000000..b7a80aa1ae30
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/mmu_notifier.h>
+#include <linux/interval_tree_generic.h>
+
+#include "mmu_rb.h"
+#include "trace.h"
+
+struct mmu_rb_handler {
+	struct list_head list;
+	struct mmu_notifier mn;
+	struct rb_root *root;
+	spinlock_t lock;        /* protect the RB tree */
+	struct mmu_rb_ops *ops;
+};
+
+static LIST_HEAD(mmu_rb_handlers);
+static DEFINE_SPINLOCK(mmu_rb_lock); /* protect mmu_rb_handlers list */
+
+static unsigned long mmu_node_start(struct mmu_rb_node *);
+static unsigned long mmu_node_last(struct mmu_rb_node *);
+static struct mmu_rb_handler *find_mmu_handler(struct rb_root *);
+static inline void mmu_notifier_page(struct mmu_notifier *, struct mm_struct *,
+				     unsigned long);
+static inline void mmu_notifier_range_start(struct mmu_notifier *,
+					    struct mm_struct *,
+					    unsigned long, unsigned long);
+static void mmu_notifier_mem_invalidate(struct mmu_notifier *,
+					struct mm_struct *,
+					unsigned long, unsigned long);
+static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *,
+					   unsigned long, unsigned long);
+
+static struct mmu_notifier_ops mn_opts = {
+	.invalidate_page = mmu_notifier_page,
+	.invalidate_range_start = mmu_notifier_range_start,
+};
+
+INTERVAL_TREE_DEFINE(struct mmu_rb_node, node, unsigned long, __last,
+		     mmu_node_start, mmu_node_last, static, __mmu_int_rb);
+
+static unsigned long mmu_node_start(struct mmu_rb_node *node)
+{
+	return node->addr & PAGE_MASK;
+}
+
+static unsigned long mmu_node_last(struct mmu_rb_node *node)
+{
+	return PAGE_ALIGN(node->addr + node->len) - 1;
+}
+
+int hfi1_mmu_rb_register(struct rb_root *root, struct mmu_rb_ops *ops)
+{
+	struct mmu_rb_handler *handlr;
+
+	if (!ops->invalidate)
+		return -EINVAL;
+
+	handlr = kmalloc(sizeof(*handlr), GFP_KERNEL);
+	if (!handlr)
+		return -ENOMEM;
+
+	handlr->root = root;
+	handlr->ops = ops;
+	INIT_HLIST_NODE(&handlr->mn.hlist);
+	spin_lock_init(&handlr->lock);
+	handlr->mn.ops = &mn_opts;
+	spin_lock(&mmu_rb_lock);
+	list_add_tail_rcu(&handlr->list, &mmu_rb_handlers);
+	spin_unlock(&mmu_rb_lock);
+
+	return mmu_notifier_register(&handlr->mn, current->mm);
+}
+
+void hfi1_mmu_rb_unregister(struct rb_root *root)
+{
+	struct mmu_rb_handler *handler = find_mmu_handler(root);
+	unsigned long flags;
+
+	if (!handler)
+		return;
+
+	/* Unregister first so we don't get any more notifications. */
+	if (current->mm)
+		mmu_notifier_unregister(&handler->mn, current->mm);
+
+	spin_lock(&mmu_rb_lock);
+	list_del_rcu(&handler->list);
+	spin_unlock(&mmu_rb_lock);
+	synchronize_rcu();
+
+	spin_lock_irqsave(&handler->lock, flags);
+	if (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node;
+		struct mmu_rb_node *rbnode;
+
+		while ((node = rb_first(root))) {
+			rbnode = rb_entry(node, struct mmu_rb_node, node);
+			rb_erase(node, root);
+			if (handler->ops->remove)
+				handler->ops->remove(root, rbnode, NULL);
+		}
+	}
+	spin_unlock_irqrestore(&handler->lock, flags);
+
+	kfree(handler);
+}
+
+int hfi1_mmu_rb_insert(struct rb_root *root, struct mmu_rb_node *mnode)
+{
+	struct mmu_rb_handler *handler = find_mmu_handler(root);
+	struct mmu_rb_node *node;
+	unsigned long flags;
+	int ret = 0;
+
+	if (!handler)
+		return -EINVAL;
+
+	spin_lock_irqsave(&handler->lock, flags);
+	hfi1_cdbg(MMU, "Inserting node addr 0x%llx, len %u", mnode->addr,
+		  mnode->len);
+	node = __mmu_rb_search(handler, mnode->addr, mnode->len);
+	if (node) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+	__mmu_int_rb_insert(mnode, root);
+
+	if (handler->ops->insert) {
+		ret = handler->ops->insert(root, mnode);
+		if (ret)
+			__mmu_int_rb_remove(mnode, root);
+	}
+unlock:
+	spin_unlock_irqrestore(&handler->lock, flags);
+	return ret;
+}
+
+/* Caller must hold handler lock */
+static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler,
+					   unsigned long addr,
+					   unsigned long len)
+{
+	struct mmu_rb_node *node = NULL;
+
+	hfi1_cdbg(MMU, "Searching for addr 0x%llx, len %u", addr, len);
+	if (!handler->ops->filter) {
+		node = __mmu_int_rb_iter_first(handler->root, addr,
+					       (addr + len) - 1);
+	} else {
+		for (node = __mmu_int_rb_iter_first(handler->root, addr,
+						    (addr + len) - 1);
+		     node;
+		     node = __mmu_int_rb_iter_next(node, addr,
+						   (addr + len) - 1)) {
+			if (handler->ops->filter(node, addr, len))
+				return node;
+		}
+	}
+	return node;
+}
+
+/* Caller must *not* hold handler lock. */
+static void __mmu_rb_remove(struct mmu_rb_handler *handler,
+			    struct mmu_rb_node *node, struct mm_struct *mm)
+{
+	unsigned long flags;
+
+	/* Validity of handler and node pointers has been checked by caller. */
+	hfi1_cdbg(MMU, "Removing node addr 0x%llx, len %u", node->addr,
+		  node->len);
+	spin_lock_irqsave(&handler->lock, flags);
+	__mmu_int_rb_remove(node, handler->root);
+	spin_unlock_irqrestore(&handler->lock, flags);
+
+	if (handler->ops->remove)
+		handler->ops->remove(handler->root, node, mm);
+}
+
+struct mmu_rb_node *hfi1_mmu_rb_search(struct rb_root *root, unsigned long addr,
+				       unsigned long len)
+{
+	struct mmu_rb_handler *handler = find_mmu_handler(root);
+	struct mmu_rb_node *node;
+	unsigned long flags;
+
+	if (!handler)
+		return ERR_PTR(-EINVAL);
+
+	spin_lock_irqsave(&handler->lock, flags);
+	node = __mmu_rb_search(handler, addr, len);
+	spin_unlock_irqrestore(&handler->lock, flags);
+
+	return node;
+}
+
+struct mmu_rb_node *hfi1_mmu_rb_extract(struct rb_root *root,
+					unsigned long addr, unsigned long len)
+{
+	struct mmu_rb_handler *handler = find_mmu_handler(root);
+	struct mmu_rb_node *node;
+	unsigned long flags;
+
+	if (!handler)
+		return ERR_PTR(-EINVAL);
+
+	spin_lock_irqsave(&handler->lock, flags);
+	node = __mmu_rb_search(handler, addr, len);
+	if (node)
+		__mmu_int_rb_remove(node, handler->root);
+	spin_unlock_irqrestore(&handler->lock, flags);
+
+	return node;
+}
+
+void hfi1_mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node)
+{
+	struct mmu_rb_handler *handler = find_mmu_handler(root);
+
+	if (!handler || !node)
+		return;
+
+	__mmu_rb_remove(handler, node, NULL);
+}
+
+static struct mmu_rb_handler *find_mmu_handler(struct rb_root *root)
+{
+	struct mmu_rb_handler *handler;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(handler, &mmu_rb_handlers, list) {
+		if (handler->root == root)
+			goto unlock;
+	}
+	handler = NULL;
+unlock:
+	rcu_read_unlock();
+	return handler;
+}
+
+static inline void mmu_notifier_page(struct mmu_notifier *mn,
+				     struct mm_struct *mm, unsigned long addr)
+{
+	mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE);
+}
+
+static inline void mmu_notifier_range_start(struct mmu_notifier *mn,
+					    struct mm_struct *mm,
+					    unsigned long start,
+					    unsigned long end)
+{
+	mmu_notifier_mem_invalidate(mn, mm, start, end);
+}
+
+static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn,
+					struct mm_struct *mm,
+					unsigned long start, unsigned long end)
+{
+	struct mmu_rb_handler *handler =
+		container_of(mn, struct mmu_rb_handler, mn);
+	struct rb_root *root = handler->root;
+	struct mmu_rb_node *node, *ptr = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&handler->lock, flags);
+	for (node = __mmu_int_rb_iter_first(root, start, end - 1);
+	     node; node = ptr) {
+		/* Guard against node removal. */
+		ptr = __mmu_int_rb_iter_next(node, start, end - 1);
+		hfi1_cdbg(MMU, "Invalidating node addr 0x%llx, len %u",
+			  node->addr, node->len);
+		if (handler->ops->invalidate(root, node)) {
+			__mmu_int_rb_remove(node, root);
+			if (handler->ops->remove)
+				handler->ops->remove(root, node, mm);
+		}
+	}
+	spin_unlock_irqrestore(&handler->lock, flags);
+}