Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 84 insertions, 0 deletions

diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index f2a2488f1bf..9573d0c48c6 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -15,6 +15,13 @@ amemthresh - INTEGER
         enabled and the variable is automatically set to 2, otherwise
         the strategy is disabled and the variable is  set  to 1.
 
+backup_only - BOOLEAN
+	0 - disabled (default)
+	not 0 - enabled
+
+	If set, disable the director function while the server is
+	in backup mode to avoid packet loops for DR/TUN methods.
+
 conntrack - BOOLEAN
 	0 - disabled (default)
 	not 0 - enabled
diff --git a/Documentation/networking/tuntap.txt b/Documentation/networking/tuntap.txt
index c0aab985bad..949d5dcdd9a 100644
--- a/Documentation/networking/tuntap.txt
+++ b/Documentation/networking/tuntap.txt
@@ -105,6 +105,83 @@ Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
      Proto [2 bytes]
      Raw protocol(IP, IPv6, etc) frame.
 
+  3.3 Multiqueue tuntap interface:
+
+  From version 3.8, Linux supports multiqueue tuntap which can uses multiple
+  file descriptors (queues) to parallelize packets sending or receiving. The
+  device allocation is the same as before, and if user wants to create multiple
+  queues, TUNSETIFF with the same device name must be called many times with
+  IFF_MULTI_QUEUE flag.
+
+  char *dev should be the name of the device, queues is the number of queues to
+  be created, fds is used to store and return the file descriptors (queues)
+  created to the caller. Each file descriptor were served as the interface of a
+  queue which could be accessed by userspace.
+
+  #include <linux/if.h>
+  #include <linux/if_tun.h>
+
+  int tun_alloc_mq(char *dev, int queues, int *fds)
+  {
+      struct ifreq ifr;
+      int fd, err, i;
+
+      if (!dev)
+          return -1;
+
+      memset(&ifr, 0, sizeof(ifr));
+      /* Flags: IFF_TUN   - TUN device (no Ethernet headers)
+       *        IFF_TAP   - TAP device
+       *
+       *        IFF_NO_PI - Do not provide packet information
+       *        IFF_MULTI_QUEUE - Create a queue of multiqueue device
+       */
+      ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_MULTI_QUEUE;
+      strcpy(ifr.ifr_name, dev);
+
+      for (i = 0; i < queues; i++) {
+          if ((fd = open("/dev/net/tun", O_RDWR)) < 0)
+             goto err;
+          err = ioctl(fd, TUNSETIFF, (void *)&ifr);
+          if (err) {
+             close(fd);
+             goto err;
+          }
+          fds[i] = fd;
+      }
+
+      return 0;
+  err:
+      for (--i; i >= 0; i--)
+          close(fds[i]);
+      return err;
+  }
+
+  A new ioctl(TUNSETQUEUE) were introduced to enable or disable a queue. When
+  calling it with IFF_DETACH_QUEUE flag, the queue were disabled. And when
+  calling it with IFF_ATTACH_QUEUE flag, the queue were enabled. The queue were
+  enabled by default after it was created through TUNSETIFF.
+
+  fd is the file descriptor (queue) that we want to enable or disable, when
+  enable is true we enable it, otherwise we disable it
+
+  #include <linux/if.h>
+  #include <linux/if_tun.h>
+
+  int tun_set_queue(int fd, int enable)
+  {
+      struct ifreq ifr;
+
+      memset(&ifr, 0, sizeof(ifr));
+
+      if (enable)
+         ifr.ifr_flags = IFF_ATTACH_QUEUE;
+      else
+         ifr.ifr_flags = IFF_DETACH_QUEUE;
+
+      return ioctl(fd, TUNSETQUEUE, (void *)&ifr);
+  }
+
 Universal TUN/TAP device driver Frequently Asked Question.
    
 1. What platforms are supported by TUN/TAP driver ?