Merge branch 'for-3.13/core' of git://git.kernel.dk/linux-block

Pull block IO core updates from Jens Axboe:
 "This is the pull request for the core changes in the block layer for
  3.13.  It contains:

   - The new blk-mq request interface.

     This is a new and more scalable queueing model that marries the
     best part of the request based interface we currently have (which
     is fully featured, but scales poorly) and the bio based "interface"
     which the new drivers for high IOPS devices end up using because
     it's much faster than the request based one.

     The bio interface has no block layer support, since it taps into
     the stack much earlier.  This means that drivers end up having to
     implement a lot of functionality on their own, like tagging,
     timeout handling, requeue, etc.  The blk-mq interface provides all
     these.  Some drivers even provide a switch to select bio or rq and
     has code to handle both, since things like merging only works in
     the rq model and hence is faster for some workloads.  This is a
     huge mess.  Conversion of these drivers nets us a substantial code
     reduction.  Initial results on converting SCSI to this model even
     shows an 8x improvement on single queue devices.  So while the
     model was intended to work on the newer multiqueue devices, it has
     substantial improvements for "classic" hardware as well.  This code
     has gone through extensive testing and development, it's now ready
     to go.  A pull request is coming to convert virtio-blk to this
     model will be will be coming as well, with more drivers scheduled
     for 3.14 conversion.

   - Two blktrace fixes from Jan and Chen Gang.

   - A plug merge fix from Alireza Haghdoost.

   - Conversion of __get_cpu_var() from Christoph Lameter.

   - Fix for sector_div() with 64-bit divider from Geert Uytterhoeven.

   - A fix for a race between request completion and the timeout
     handling from Jeff Moyer.  This is what caused the merge conflict
     with blk-mq/core, in case you are looking at that.

   - A dm stacking fix from Mike Snitzer.

   - A code consolidation fix and duplicated code removal from Kent
     Overstreet.

   - A handful of block bug fixes from Mikulas Patocka, fixing a loop
     crash and memory corruption on blk cg.

   - Elevator switch bug fix from Tomoki Sekiyama.

  A heads-up that I had to rebase this branch.  Initially the immutable
  bio_vecs had been queued up for inclusion, but a week later, it became
  clear that it wasn't fully cooked yet.  So the decision was made to
  pull this out and postpone it until 3.14.  It was a straight forward
  rebase, just pruning out the immutable series and the later fixes of
  problems with it.  The rest of the patches applied directly and no
  further changes were made"

* 'for-3.13/core' of git://git.kernel.dk/linux-block: (31 commits)
  block: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
  block: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
  block: Do not call sector_div() with a 64-bit divisor
  kernel: trace: blktrace: remove redundent memcpy() in compat_blk_trace_setup()
  block: Consolidate duplicated bio_trim() implementations
  block: Use rw_copy_check_uvector()
  block: Enable sysfs nomerge control for I/O requests in the plug list
  block: properly stack underlying max_segment_size to DM device
  elevator: acquire q->sysfs_lock in elevator_change()
  elevator: Fix a race in elevator switching and md device initialization
  block: Replace __get_cpu_var uses
  bdi: test bdi_init failure
  block: fix a probe argument to blk_register_region
  loop: fix crash if blk_alloc_queue fails
  blk-core: Fix memory corruption if blkcg_init_queue fails
  block: fix race between request completion and timeout handling
  blktrace: Send BLK_TN_PROCESS events to all running traces
  blk-mq: don't disallow request merges for req->special being set
  blk-mq: mq plug list breakage
  blk-mq: fix for flush deadlock
  ...

1 files changed, 28 insertions, 8 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b8b8560bfb95..f785aef65799 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
+#include <linux/list.h>
 
 #include <trace/events/block.h>
 
@@ -38,6 +39,9 @@ static unsigned int blktrace_seq __read_mostly = 1;
 static struct trace_array *blk_tr;
 static bool blk_tracer_enabled __read_mostly;
 
+static LIST_HEAD(running_trace_list);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
+
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
 
@@ -107,10 +111,18 @@ record_it:
  * Send out a notify for this process, if we haven't done so since a trace
  * started
  */
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+static void trace_note_tsk(struct task_struct *tsk)
 {
+	unsigned long flags;
+	struct blk_trace *bt;
+
 	tsk->btrace_seq = blktrace_seq;
-	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+	spin_lock_irqsave(&running_trace_lock, flags);
+	list_for_each_entry(bt, &running_trace_list, running_list) {
+		trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
+			   sizeof(tsk->comm));
+	}
+	spin_unlock_irqrestore(&running_trace_lock, flags);
 }
 
 static void trace_note_time(struct blk_trace *bt)
@@ -229,16 +241,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		goto record_it;
 	}
 
+	if (unlikely(tsk->btrace_seq != blktrace_seq))
+		trace_note_tsk(tsk);
+
 	/*
 	 * A word about the locking here - we disable interrupts to reserve
 	 * some space in the relay per-cpu buffer, to prevent an irq
 	 * from coming in and stepping on our toes.
 	 */
 	local_irq_save(flags);
-
-	if (unlikely(tsk->btrace_seq != blktrace_seq))
-		trace_note_tsk(bt, tsk);
-
 	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
 	if (t) {
 		sequence = per_cpu_ptr(bt->sequence, cpu);
@@ -477,6 +488,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->dir = dir;
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
+	INIT_LIST_HEAD(&bt->running_list);
 
 	ret = -EIO;
 	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
@@ -567,13 +579,12 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 		.end_lba = cbuts.end_lba,
 		.pid = cbuts.pid,
 	};
-	memcpy(&buts.name, &cbuts.name, 32);
 
 	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
 	if (ret)
 		return ret;
 
-	if (copy_to_user(arg, &buts.name, 32)) {
+	if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
 		blk_trace_remove(q);
 		return -EFAULT;
 	}
@@ -601,6 +612,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 			blktrace_seq++;
 			smp_mb();
 			bt->trace_state = Blktrace_running;
+			spin_lock_irq(&running_trace_lock);
+			list_add(&bt->running_list, &running_trace_list);
+			spin_unlock_irq(&running_trace_lock);
 
 			trace_note_time(bt);
 			ret = 0;
@@ -608,6 +622,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 	} else {
 		if (bt->trace_state == Blktrace_running) {
 			bt->trace_state = Blktrace_stopped;
+			spin_lock_irq(&running_trace_lock);
+			list_del_init(&bt->running_list);
+			spin_unlock_irq(&running_trace_lock);
 			relay_flush(bt->rchan);
 			ret = 0;
 		}
@@ -1472,6 +1489,9 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (atomic_dec_and_test(&blk_probes_ref))
 		blk_unregister_tracepoints();
 
+	spin_lock_irq(&running_trace_lock);
+	list_del(&bt->running_list);
+	spin_unlock_irq(&running_trace_lock);
 	blk_trace_free(bt);
 	return 0;
 }