Merge branch 'for-3.17/drivers' of git://git.kernel.dk/linux-block

Pull block driver changes from Jens Axboe:
 "Nothing out of the ordinary here, this pull request contains:

   - A big round of fixes for bcache from Kent Overstreet, Slava Pestov,
     and Surbhi Palande.  No new features, just a lot of fixes.

   - The usual round of drbd updates from Andreas Gruenbacher, Lars
     Ellenberg, and Philipp Reisner.

   - virtio_blk was converted to blk-mq back in 3.13, but now Ming Lei
     has taken it one step further and added support for actually using
     more than one queue.

   - Addition of an explicit SG_FLAG_Q_AT_HEAD for block/bsg, to
     compliment the the default behavior of adding to the tail of the
     queue.  From Douglas Gilbert"

* 'for-3.17/drivers' of git://git.kernel.dk/linux-block: (86 commits)
  bcache: Drop unneeded blk_sync_queue() calls
  bcache: add mutex lock for bch_is_open
  bcache: Correct printing of btree_gc_max_duration_ms
  bcache: try to set b->parent properly
  bcache: fix memory corruption in init error path
  bcache: fix crash with incomplete cache set
  bcache: Fix more early shutdown bugs
  bcache: fix use-after-free in btree_gc_coalesce()
  bcache: Fix an infinite loop in journal replay
  bcache: fix crash in bcache_btree_node_alloc_fail tracepoint
  bcache: bcache_write tracepoint was crashing
  bcache: fix typo in bch_bkey_equal_header
  bcache: Allocate bounce buffers with GFP_NOWAIT
  bcache: Make sure to pass GFP_WAIT to mempool_alloc()
  bcache: fix uninterruptible sleep in writeback thread
  bcache: wait for buckets when allocating new btree root
  bcache: fix crash on shutdown in passthrough mode
  bcache: fix lockdep warnings on shutdown
  bcache allocator: send discards with correct size
  bcache: Fix to remove the rcu_sched stalls.
  ...

block/scsi_ioctl.c

@@ -290,6 +290,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	unsigned long start_time;
 	ssize_t ret = 0;
 	int writing = 0;
+	int at_head = 0;
 	struct request *rq;
 	char sense[SCSI_SENSE_BUFFERSIZE];
 	struct bio *bio;
@@ -313,6 +314,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		case SG_DXFER_FROM_DEV:
 			break;
 		}
+	if (hdr->flags & SG_FLAG_Q_AT_HEAD)
+		at_head = 1;
 
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
 	if (!rq)
@@ -369,7 +372,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	 * (if he doesn't check that is his problem).
 	 * N.B. a non-zero SCSI status is _not_ necessarily an error.
 	 */
-	blk_execute_rq(q, bd_disk, rq, 0);
+	blk_execute_rq(q, bd_disk, rq, at_head);
 
 	hdr->duration = jiffies_to_msecs(jiffies - start_time);
 

drivers/block/drbd/Makefile

@@ -3,5 +3,6 @@ drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o
 drbd-y += drbd_main.o drbd_strings.o drbd_nl.o
 drbd-y += drbd_interval.o drbd_state.o
 drbd-y += drbd_nla.o
+drbd-$(CONFIG_DEBUG_FS) += drbd_debugfs.o
 
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o

drivers/block/drbd/drbd_debugfs.h

+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/debugfs.h>
+
+#include "drbd_int.h"
+
+#ifdef CONFIG_DEBUG_FS
+int __init drbd_debugfs_init(void);
+void drbd_debugfs_cleanup(void);
+
+void drbd_debugfs_resource_add(struct drbd_resource *resource);
+void drbd_debugfs_resource_cleanup(struct drbd_resource *resource);
+
+void drbd_debugfs_connection_add(struct drbd_connection *connection);
+void drbd_debugfs_connection_cleanup(struct drbd_connection *connection);
+
+void drbd_debugfs_device_add(struct drbd_device *device);
+void drbd_debugfs_device_cleanup(struct drbd_device *device);
+
+void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device);
+void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device);
+#else
+
+static inline int __init drbd_debugfs_init(void) { return -ENODEV; }
+static inline void drbd_debugfs_cleanup(void) { }
+
+static inline void drbd_debugfs_resource_add(struct drbd_resource *resource) { }
+static inline void drbd_debugfs_resource_cleanup(struct drbd_resource *resource) { }
+
+static inline void drbd_debugfs_connection_add(struct drbd_connection *connection) { }
+static inline void drbd_debugfs_connection_cleanup(struct drbd_connection *connection) { }
+
+static inline void drbd_debugfs_device_add(struct drbd_device *device) { }
+static inline void drbd_debugfs_device_cleanup(struct drbd_device *device) { }
+
+static inline void drbd_debugfs_peer_device_add(struct drbd_peer_device *peer_device) { }
+static inline void drbd_debugfs_peer_device_cleanup(struct drbd_peer_device *peer_device) { }
+
+#endif

drivers/block/drbd/drbd_interval.h

@@ -10,7 +10,9 @@ struct drbd_interval {
 	unsigned int size;	/* size in bytes */
 	sector_t end;		/* highest interval end in subtree */
 	int local:1		/* local or remote request? */;
-	int waiting:1;
+	int waiting:1;		/* someone is waiting for this to complete */
+	int completed:1;	/* this has been completed already;
+				 * ignore for conflict detection */
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)

drivers/block/drbd/drbd_proc.c

@@ -60,20 +60,65 @@ static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v)
 		seq_printf(seq, "%ld", v);
 }
 
+static void drbd_get_syncer_progress(struct drbd_device *device,
+		union drbd_dev_state state, unsigned long *rs_total,
+		unsigned long *bits_left, unsigned int *per_mil_done)
+{
+	/* this is to break it at compile time when we change that, in case we
+	 * want to support more than (1<<32) bits on a 32bit arch. */
+	typecheck(unsigned long, device->rs_total);
+	*rs_total = device->rs_total;
+
+	/* note: both rs_total and rs_left are in bits, i.e. in
+	 * units of BM_BLOCK_SIZE.
+	 * for the percentage, we don't care. */
+
+	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
+		*bits_left = device->ov_left;
+	else
+		*bits_left = drbd_bm_total_weight(device) - device->rs_failed;
+	/* >> 10 to prevent overflow,
+	 * +1 to prevent division by zero */
+	if (*bits_left > *rs_total) {
+		/* D'oh. Maybe a logic bug somewhere.  More likely just a race
+		 * between state change and reset of rs_total.
+		 */
+		*bits_left = *rs_total;
+		*per_mil_done = *rs_total ? 0 : 1000;
+	} else {
+		/* Make sure the division happens in long context.
+		 * We allow up to one petabyte storage right now,
+		 * at a granularity of 4k per bit that is 2**38 bits.
+		 * After shift right and multiplication by 1000,
+		 * this should still fit easily into a 32bit long,
+		 * so we don't need a 64bit division on 32bit arch.
+		 * Note: currently we don't support such large bitmaps on 32bit
+		 * arch anyways, but no harm done to be prepared for it here.
+		 */
+		unsigned int shift = *rs_total > UINT_MAX ? 16 : 10;
+		unsigned long left = *bits_left >> shift;
+		unsigned long total = 1UL + (*rs_total >> shift);
+		unsigned long tmp = 1000UL - left * 1000UL/total;
+		*per_mil_done = tmp;
+	}
+}
+
+
 /*lge
  * progress bars shamelessly adapted from driver/md/md.c
  * output looks like
  *	[=====>..............] 33.5% (23456/123456)
  *	finish: 2:20:20 speed: 6,345 (6,456) K/sec
  */
-static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *seq)
+static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *seq,
+		union drbd_dev_state state)
 {
-	unsigned long db, dt, dbdt, rt, rs_left;
+	unsigned long db, dt, dbdt, rt, rs_total, rs_left;
 	unsigned int res;
 	int i, x, y;
 	int stalled = 0;
 
-	drbd_get_syncer_progress(device, &rs_left, &res);
+	drbd_get_syncer_progress(device, state, &rs_total, &rs_left, &res);
 
 	x = res/50;
 	y = 20-x;
@@ -85,21 +130,21 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		seq_printf(seq, ".");
 	seq_printf(seq, "] ");
 
-	if (device->state.conn == C_VERIFY_S || device->state.conn == C_VERIFY_T)
+	if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T)
 		seq_printf(seq, "verified:");
 	else
 		seq_printf(seq, "sync'ed:");
 	seq_printf(seq, "%3u.%u%% ", res / 10, res % 10);
 
 	/* if more than a few GB, display in MB */
-	if (device->rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
+	if (rs_total > (4UL << (30 - BM_BLOCK_SHIFT)))
 		seq_printf(seq, "(%lu/%lu)M",
 			    (unsigned long) Bit2KB(rs_left >> 10),
-			    (unsigned long) Bit2KB(device->rs_total >> 10));
+			    (unsigned long) Bit2KB(rs_total >> 10));
 	else
 		seq_printf(seq, "(%lu/%lu)K\n\t",
 			    (unsigned long) Bit2KB(rs_left),
-			    (unsigned long) Bit2KB(device->rs_total));
+			    (unsigned long) Bit2KB(rs_total));
 
 	/* see drivers/md/md.c
 	 * We do not want to overflow, so the order of operands and
@@ -150,13 +195,13 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	dt = (jiffies - device->rs_start - device->rs_paused) / HZ;
 	if (dt == 0)
 		dt = 1;
-	db = device->rs_total - rs_left;
+	db = rs_total - rs_left;
 	dbdt = Bit2KB(db/dt);
 	seq_printf_with_thousands_grouping(seq, dbdt);
 	seq_printf(seq, ")");
 
-	if (device->state.conn == C_SYNC_TARGET ||
-	    device->state.conn == C_VERIFY_S) {
+	if (state.conn == C_SYNC_TARGET ||
+	    state.conn == C_VERIFY_S) {
 		seq_printf(seq, " want: ");
 		seq_printf_with_thousands_grouping(seq, device->c_sync_rate);
 	}
@@ -168,8 +213,8 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 		unsigned long bm_bits = drbd_bm_bits(device);
 		unsigned long bit_pos;
 		unsigned long long stop_sector = 0;
-		if (device->state.conn == C_VERIFY_S ||
-		    device->state.conn == C_VERIFY_T) {
+		if (state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T) {
 			bit_pos = bm_bits - device->ov_left;
 			if (verify_can_do_stop_sector(device))
 				stop_sector = device->ov_stop_sector;
@@ -188,22 +233,13 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	}
 }
 
-static void resync_dump_detail(struct seq_file *seq, struct lc_element *e)
-{
-	struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
-
-	seq_printf(seq, "%5d %s %s\n", bme->rs_left,
-		   bme->flags & BME_NO_WRITES ? "NO_WRITES" : "---------",
-		   bme->flags & BME_LOCKED ? "LOCKED" : "------"
-		   );
-}
-
 static int drbd_seq_show(struct seq_file *seq, void *v)
 {
 	int i, prev_i = -1;
 	const char *sn;
 	struct drbd_device *device;
 	struct net_conf *nc;
+	union drbd_dev_state state;
 	char wp;
 
 	static char write_ordering_chars[] = {
@@ -241,11 +277,12 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			seq_printf(seq, "\n");
 		prev_i = i;
 
-		sn = drbd_conn_str(device->state.conn);
+		state = device->state;
+		sn = drbd_conn_str(state.conn);
 
-		if (device->state.conn == C_STANDALONE &&
-		    device->state.disk == D_DISKLESS &&
-		    device->state.role == R_SECONDARY) {
+		if (state.conn == C_STANDALONE &&
+		    state.disk == D_DISKLESS &&
+		    state.role == R_SECONDARY) {
 			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
 		} else {
 			/* reset device->congestion_reason */
@@ -258,15 +295,15 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			   "    ns:%u nr:%u dw:%u dr:%u al:%u bm:%u "
 			   "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c",
 			   i, sn,
-			   drbd_role_str(device->state.role),
-			   drbd_role_str(device->state.peer),
-			   drbd_disk_str(device->state.disk),
-			   drbd_disk_str(device->state.pdsk),
+			   drbd_role_str(state.role),
+			   drbd_role_str(state.peer),
+			   drbd_disk_str(state.disk),
+			   drbd_disk_str(state.pdsk),
 			   wp,
 			   drbd_suspended(device) ? 's' : 'r',
-			   device->state.aftr_isp ? 'a' : '-',
-			   device->state.peer_isp ? 'p' : '-',
-			   device->state.user_isp ? 'u' : '-',
+			   state.aftr_isp ? 'a' : '-',
+			   state.peer_isp ? 'p' : '-',
+			   state.user_isp ? 'u' : '-',
 			   device->congestion_reason ?: '-',
 			   test_bit(AL_SUSPENDED, &device->flags) ? 's' : '-',
 			   device->send_cnt/2,
@@ -281,17 +318,17 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			   atomic_read(&device->unacked_cnt),
 			   atomic_read(&device->ap_bio_cnt),
 			   first_peer_device(device)->connection->epochs,
-			   write_ordering_chars[first_peer_device(device)->connection->write_ordering]
+			   write_ordering_chars[device->resource->write_ordering]
 			);
 			seq_printf(seq, " oos:%llu\n",
 				   Bit2KB((unsigned long long)
 					   drbd_bm_total_weight(device)));
 		}
-		if (device->state.conn == C_SYNC_SOURCE ||
-		    device->state.conn == C_SYNC_TARGET ||
-		    device->state.conn == C_VERIFY_S ||
-		    device->state.conn == C_VERIFY_T)
-			drbd_syncer_progress(device, seq);
+		if (state.conn == C_SYNC_SOURCE ||
+		    state.conn == C_SYNC_TARGET ||
+		    state.conn == C_VERIFY_S ||
+		    state.conn == C_VERIFY_T)
+			drbd_syncer_progress(device, seq, state);
 
 		if (proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) {
 			lc_seq_printf_stats(seq, device->resync);
@@ -299,12 +336,8 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			put_ldev(device);
 		}
 
-		if (proc_details >= 2) {
-			if (device->resync) {
-				lc_seq_dump_details(seq, device->resync, "rs_left",
-					resync_dump_detail);
-			}
-		}
+		if (proc_details >= 2)
+			seq_printf(seq, "\tblocked on activity log: %d\n", atomic_read(&device->ap_actlog_cnt));
 	}
 	rcu_read_unlock();
 
@@ -316,7 +349,7 @@ static int drbd_proc_open(struct inode *inode, struct file *file)
 	int err;
 
 	if (try_module_get(THIS_MODULE)) {
-		err = single_open(file, drbd_seq_show, PDE_DATA(inode));
+		err = single_open(file, drbd_seq_show, NULL);
 		if (err)
 			module_put(THIS_MODULE);
 		return err;

drivers/block/drbd/drbd_req.h

@@ -288,6 +288,7 @@ extern void complete_master_bio(struct drbd_device *device,
 extern void request_timer_fn(unsigned long data);
 extern void tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
 extern void _tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
+extern void tl_abort_disk_io(struct drbd_device *device);
 
 /* this is in drbd_main.c */
 extern void drbd_restart_request(struct drbd_request *req);

drivers/md/bcache/alloc.c

@@ -331,7 +331,7 @@ static int bch_allocator_thread(void *arg)
 				mutex_unlock(&ca->set->bucket_lock);
 				blkdev_issue_discard(ca->bdev,
 					bucket_to_sector(ca->set, bucket),
-					ca->sb.block_size, GFP_KERNEL, 0);
+					ca->sb.bucket_size, GFP_KERNEL, 0);
 				mutex_lock(&ca->set->bucket_lock);
 			}
 

drivers/md/bcache/bcache.h

@@ -477,9 +477,13 @@ struct gc_stat {
  * CACHE_SET_STOPPING always gets set first when we're closing down a cache set;
  * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e.
  * flushing dirty data).
+ *
+ * CACHE_SET_RUNNING means all cache devices have been registered and journal
+ * replay is complete.
  */
 #define CACHE_SET_UNREGISTERING		0
 #define	CACHE_SET_STOPPING		1
+#define	CACHE_SET_RUNNING		2
 
 struct cache_set {
 	struct closure		cl;

drivers/md/bcache/bset.c

@@ -1182,7 +1182,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
 {
 	uint64_t start_time;
 	bool used_mempool = false;
-	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO,
+	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOWAIT,
 						     order);
 	if (!out) {
 		struct page *outp;

drivers/md/bcache/bset.h

@@ -453,7 +453,7 @@ static inline bool bch_bkey_equal_header(const struct bkey *l,
 {
 	return (KEY_DIRTY(l) == KEY_DIRTY(r) &&
 		KEY_PTRS(l) == KEY_PTRS(r) &&
-		KEY_CSUM(l) == KEY_CSUM(l));
+		KEY_CSUM(l) == KEY_CSUM(r));
 }
 
 /* Keylists */

drivers/md/bcache/btree.h

@@ -242,9 +242,10 @@ void __bch_btree_node_write(struct btree *, struct closure *);
 void bch_btree_node_write(struct btree *, struct closure *);
 
 void bch_btree_set_root(struct btree *);
-struct btree *bch_btree_node_alloc(struct cache_set *, struct btree_op *, int);
+struct btree *__bch_btree_node_alloc(struct cache_set *, struct btree_op *,
+				     int, bool, struct btree *);
 struct btree *bch_btree_node_get(struct cache_set *, struct btree_op *,
-				 struct bkey *, int, bool);
+				 struct bkey *, int, bool, struct btree *);
 
 int bch_btree_insert_check_key(struct btree *, struct btree_op *,
 			       struct bkey *);

drivers/md/bcache/extents.h

@@ -9,5 +9,6 @@ struct cache_set;
 
 void bch_extent_to_text(char *, size_t, const struct bkey *);
 bool __bch_btree_ptr_invalid(struct cache_set *, const struct bkey *);
+bool __bch_extent_invalid(struct cache_set *, const struct bkey *);
 
 #endif /* _BCACHE_EXTENTS_H */

drivers/md/bcache/request.c

@@ -311,7 +311,8 @@ void bch_data_insert(struct closure *cl)
 {
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	trace_bcache_write(op->bio, op->writeback, op->bypass);
+	trace_bcache_write(op->c, op->inode, op->bio,
+			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);