Merge branch 'for-3.16/drivers' of git://git.kernel.dk/linux-block into next

Pull block driver changes from Jens Axboe:
 "Now that the core bits are in, here's the pull request for the driver
  related changes for 3.16.  Nothing out of the ordinary here, mostly
  business as usual.  There are a few pulls of for-3.16/core into this
  branch, which were done when the blk-mq was modified after the
  mtip32xx conversion was put in.

  The pull request contains:

   - skd and cciss converted to use pci_enable_msix_exact().  From
     Alexander Gordeev.

   - A few mtip32xx fixes from Asai @ Micron.

   - The conversion of mtip32xx from make_request_fn to blk-mq, and a
     later small fix for that conversion on quiescing for non-queued IO.
     From me.

   - A fix for bsg to use an exported function to check whether this
     driver is request based or not.  Needed updating for blk-mq, which
     is request based, but does not have a request_fn hook.  From me.

   - Small floppy bug fix from Jiri.

   - A series of cleanups for the cdrom uniform layer from Joe Perches.
     Gets rid of various old ugly macros, making the code conform more
     to the modern coding style.

   - A series of patches for drbd from the drbd crew (Lars Ellenberg and
     Philipp Reisner).

   - A use-after-free fix for null_blk from Ming Lei.

   - Also from Ming Lei is a performance patch for virtio-blk, which can
     net us a 3x win on kvm platforms where world notification is
     expensive.

   - Ming Lei also fixed a stall issue in virtio-blk, due to a race
     between queue start/stop and resource limits.

   - A small batch of fixes for xen-blk{back,front} from Olaf Hering and
     Valentin Priescu"

* 'for-3.16/drivers' of git://git.kernel.dk/linux-block: (54 commits)
  block: virtio_blk: don't hold spin lock during world switch
  xen-blkback: defer freeing blkif to avoid blocking xenwatch
  xen blkif.h: fix comment typo in discard-alignment
  xen/blkback: disable discard feature if requested by toolstack
  xen-blkfront: remove type check from blkfront_setup_discard
  floppy: do not corrupt bio.bi_flags when reading block 0
  mtip32xx: move error handling to service thread
  virtio_blk: fix race between start and stop queue
  mtip32xx: stop block hardware queues before quiescing IO
  mtip32xx: blk_mq_init_queue() returns an ERR_PTR
  mtip32xx: convert to use blk-mq
  cdrom: Remove unnecessary prototype for cdrom_get_disc_info
  cdrom: Remove unnecessary prototype for cdrom_mrw_exit
  cdrom: Remove cdrom_count_tracks prototype
  cdrom: Remove cdrom_get_next_writeable prototype
  cdrom: Remove cdrom_get_last_written prototype
  cdrom: Move mmc_ioctls above cdrom_ioctl to remove unnecessary prototype
  cdrom: Remove unnecessary sanitize_format prototype
  cdrom: Remove unnecessary check_for_audio_disc prototype
  cdrom: Remove prototype for open_for_data
  ...

23 files changed, 1212 insertions, 1148 deletions

diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 73894ca33956..4595c22f33f7 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -4080,7 +4080,7 @@ static void cciss_interrupt_mode(ctlr_info_t *h)
 		goto default_int_mode;
 
 	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSIX)) {
-		err = pci_enable_msix(h->pdev, cciss_msix_entries, 4);
+		err = pci_enable_msix_exact(h->pdev, cciss_msix_entries, 4);
 		if (!err) {
 			h->intr[0] = cciss_msix_entries[0].vector;
 			h->intr[1] = cciss_msix_entries[1].vector;
@@ -4088,10 +4088,6 @@ static void cciss_interrupt_mode(ctlr_info_t *h)
 			h->intr[3] = cciss_msix_entries[3].vector;
 			h->msix_vector = 1;
 			return;
-		}
-		if (err > 0) {
-			dev_warn(&h->pdev->dev,
-				"only %d MSI-X vectors available\n", err);
 		} else {
 			dev_warn(&h->pdev->dev,
 				"MSI-X init failed %d\n", err);
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 90ae4ba8f9ee..05a1780ffa85 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -29,7 +29,6 @@
 #include <linux/drbd_limits.h>
 #include <linux/dynamic_debug.h>
 #include "drbd_int.h"
-#include "drbd_wrappers.h"
 
 
 enum al_transaction_types {
@@ -204,7 +203,7 @@ int drbd_md_sync_page_io(struct drbd_device *device, struct drbd_backing_dev *bd
 
 	BUG_ON(!bdev->md_bdev);
 
-	drbd_dbg(device, "meta_data io: %s [%d]:%s(,%llus,%s) %pS\n",
+	dynamic_drbd_dbg(device, "meta_data io: %s [%d]:%s(,%llus,%s) %pS\n",
 	     current->comm, current->pid, __func__,
 	     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ",
 	     (void*)_RET_IP_ );
@@ -276,7 +275,6 @@ bool drbd_al_begin_io_fastpath(struct drbd_device *device, struct drbd_interval
 	return _al_get(device, first, true);
 }
 
-static
 bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i)
 {
 	/* for bios crossing activity log extent boundaries,
@@ -846,7 +844,7 @@ void __drbd_set_in_sync(struct drbd_device *device, sector_t sector, int size,
 	int wake_up = 0;
 	unsigned long flags;
 
-	if (size <= 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_BIO_SIZE) {
+	if (size <= 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_DISCARD_SIZE) {
 		drbd_err(device, "drbd_set_in_sync: sector=%llus size=%d nonsense!\n",
 				(unsigned long long)sector, size);
 		return;
@@ -920,7 +918,7 @@ int __drbd_set_out_of_sync(struct drbd_device *device, sector_t sector, int size
 	if (size == 0)
 		return 0;
 
-	if (size < 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_BIO_SIZE) {
+	if (size < 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_DISCARD_SIZE) {
 		drbd_err(device, "sector: %llus, size: %d\n",
 			(unsigned long long)sector, size);
 		return 0;
@@ -1023,8 +1021,7 @@ int drbd_rs_begin_io(struct drbd_device *device, sector_t sector)
 	unsigned int enr = BM_SECT_TO_EXT(sector);
 	struct bm_extent *bm_ext;
 	int i, sig;
-	int sa = 200; /* Step aside 200 times, then grab the extent and let app-IO wait.
-			 200 times -> 20 seconds. */
+	bool sa;
 
 retry:
 	sig = wait_event_interruptible(device->al_wait,
@@ -1035,12 +1032,15 @@ retry:
 	if (test_bit(BME_LOCKED, &bm_ext->flags))
 		return 0;
 
+	/* step aside only while we are above c-min-rate; unless disabled. */
+	sa = drbd_rs_c_min_rate_throttle(device);
+
 	for (i = 0; i < AL_EXT_PER_BM_SECT; i++) {
 		sig = wait_event_interruptible(device->al_wait,
 					       !_is_in_al(device, enr * AL_EXT_PER_BM_SECT + i) ||
-					       test_bit(BME_PRIORITY, &bm_ext->flags));
+					       (sa && test_bit(BME_PRIORITY, &bm_ext->flags)));
 
-		if (sig || (test_bit(BME_PRIORITY, &bm_ext->flags) && sa)) {
+		if (sig || (sa && test_bit(BME_PRIORITY, &bm_ext->flags))) {
 			spin_lock_irq(&device->al_lock);
 			if (lc_put(device->resync, &bm_ext->lce) == 0) {
 				bm_ext->flags = 0; /* clears BME_NO_WRITES and eventually BME_PRIORITY */
@@ -1052,9 +1052,6 @@ retry:
 				return -EINTR;
 			if (schedule_timeout_interruptible(HZ/10))
 				return -EINTR;
-			if (sa && --sa == 0)
-				drbd_warn(device, "drbd_rs_begin_io() stepped aside for 20sec."
-					 "Resync stalled?\n");
 			goto retry;
 		}
 	}
@@ -1288,7 +1285,7 @@ void drbd_rs_failed_io(struct drbd_device *device, sector_t sector, int size)
 	sector_t esector, nr_sectors;
 	int wake_up = 0;
 
-	if (size <= 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_BIO_SIZE) {
+	if (size <= 0 || !IS_ALIGNED(size, 512) || size > DRBD_MAX_DISCARD_SIZE) {
 		drbd_err(device, "drbd_rs_failed_io: sector=%llus size=%d nonsense!\n",
 				(unsigned long long)sector, size);
 		return;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index e7093d4291f1..a76ceb344d64 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -382,6 +382,12 @@ enum {
 	__EE_CALL_AL_COMPLETE_IO,
 	__EE_MAY_SET_IN_SYNC,
 
+	/* is this a TRIM aka REQ_DISCARD? */
+	__EE_IS_TRIM,
+	/* our lower level cannot handle trim,
+	 * and we want to fall back to zeroout instead */
+	__EE_IS_TRIM_USE_ZEROOUT,
+
 	/* In case a barrier failed,
 	 * we need to resubmit without the barrier flag. */
 	__EE_RESUBMITTED,
@@ -405,7 +411,9 @@ enum {
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
-#define	EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
+#define EE_IS_TRIM             (1<<__EE_IS_TRIM)
+#define EE_IS_TRIM_USE_ZEROOUT (1<<__EE_IS_TRIM_USE_ZEROOUT)
+#define EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
 #define EE_RESTART_REQUESTS	(1<<__EE_RESTART_REQUESTS)
@@ -579,6 +587,7 @@ struct drbd_resource {
 	struct list_head resources;
 	struct res_opts res_opts;
 	struct mutex conf_update;	/* mutex for ready-copy-update of net_conf and disk_conf */
+	struct mutex adm_mutex;		/* mutex to serialize administrative requests */
 	spinlock_t req_lock;
 
 	unsigned susp:1;		/* IO suspended by user */
@@ -609,6 +618,7 @@ struct drbd_connection {
 	struct drbd_socket data;	/* data/barrier/cstate/parameter packets */
 	struct drbd_socket meta;	/* ping/ack (metadata) packets */
 	int agreed_pro_version;		/* actually used protocol version */
+	u32 agreed_features;
 	unsigned long last_received;	/* in jiffies, either socket */
 	unsigned int ko_count;
 
@@ -814,6 +824,28 @@ struct drbd_device {
 	struct submit_worker submit;
 };
 
+struct drbd_config_context {
+	/* assigned from drbd_genlmsghdr */
+	unsigned int minor;
+	/* assigned from request attributes, if present */
+	unsigned int volume;
+#define VOLUME_UNSPECIFIED		(-1U)
+	/* pointer into the request skb,
+	 * limited lifetime! */
+	char *resource_name;
+	struct nlattr *my_addr;
+	struct nlattr *peer_addr;
+
+	/* reply buffer */
+	struct sk_buff *reply_skb;
+	/* pointer into reply buffer */
+	struct drbd_genlmsghdr *reply_dh;
+	/* resolved from attributes, if possible */
+	struct drbd_device *device;
+	struct drbd_resource *resource;
+	struct drbd_connection *connection;
+};
+
 static inline struct drbd_device *minor_to_device(unsigned int minor)
 {
 	return (struct drbd_device *)idr_find(&drbd_devices, minor);
@@ -821,7 +853,7 @@ static inline struct drbd_device *minor_to_device(unsigned int minor)
 
 static inline struct drbd_peer_device *first_peer_device(struct drbd_device *device)
 {
-	return list_first_entry(&device->peer_devices, struct drbd_peer_device, peer_devices);
+	return list_first_entry_or_null(&device->peer_devices, struct drbd_peer_device, peer_devices);
 }
 
 #define for_each_resource(resource, _resources) \
@@ -1139,6 +1171,12 @@ struct bm_extent {
 #define DRBD_MAX_SIZE_H80_PACKET (1U << 15) /* Header 80 only allows packets up to 32KiB data */
 #define DRBD_MAX_BIO_SIZE_P95    (1U << 17) /* Protocol 95 to 99 allows bios up to 128KiB */
 
+/* For now, don't allow more than one activity log extent worth of data
+ * to be discarded in one go. We may need to rework drbd_al_begin_io()
+ * to allow for even larger discard ranges */
+#define DRBD_MAX_DISCARD_SIZE	AL_EXTENT_SIZE
+#define DRBD_MAX_DISCARD_SECTORS (DRBD_MAX_DISCARD_SIZE >> 9)
+
 extern int  drbd_bm_init(struct drbd_device *device);
 extern int  drbd_bm_resize(struct drbd_device *device, sector_t sectors, int set_new_bits);
 extern void drbd_bm_cleanup(struct drbd_device *device);
@@ -1229,9 +1267,9 @@ extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
 extern rwlock_t global_state_lock;
 
 extern int conn_lowest_minor(struct drbd_connection *connection);
-enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned int minor, int vnr);
+extern enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsigned int minor);
 extern void drbd_destroy_device(struct kref *kref);
-extern void drbd_delete_device(struct drbd_device *mdev);
+extern void drbd_delete_device(struct drbd_device *device);
 
 extern struct drbd_resource *drbd_create_resource(const char *name);
 extern void drbd_free_resource(struct drbd_resource *resource);
@@ -1257,7 +1295,7 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
-extern int drbd_msg_put_info(const char *info);
+extern int drbd_msg_put_info(struct sk_buff *skb, const char *info);
 extern void drbd_suspend_io(struct drbd_device *device);
 extern void drbd_resume_io(struct drbd_device *device);
 extern char *ppsize(char *buf, unsigned long long size);
@@ -1283,6 +1321,10 @@ extern void conn_try_outdate_peer_async(struct drbd_connection *connection);
 extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* drbd_worker.c */
+/* bi_end_io handlers */
+extern void drbd_md_io_complete(struct bio *bio, int error);
+extern void drbd_peer_request_endio(struct bio *bio, int error);
+extern void drbd_request_endio(struct bio *bio, int error);
 extern int drbd_worker(struct drbd_thread *thi);
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor);
 void drbd_resync_after_changed(struct drbd_device *device);
@@ -1332,16 +1374,20 @@ extern int w_start_resync(struct drbd_work *, int);
 extern void resync_timer_fn(unsigned long data);
 extern void start_resync_timer_fn(unsigned long data);
 
+extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
+
 /* drbd_receiver.c */
 extern int drbd_receiver(struct drbd_thread *thi);
 extern int drbd_asender(struct drbd_thread *thi);
-extern int drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector);
+extern bool drbd_rs_c_min_rate_throttle(struct drbd_device *device);
+extern bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector);
 extern int drbd_submit_peer_request(struct drbd_device *,
 				    struct drbd_peer_request *, const unsigned,
 				    const int);
 extern int drbd_free_peer_reqs(struct drbd_device *, struct list_head *);
 extern struct drbd_peer_request *drbd_alloc_peer_req(struct drbd_peer_device *, u64,
 						     sector_t, unsigned int,
+						     bool,
 						     gfp_t) __must_hold(local);
 extern void __drbd_free_peer_req(struct drbd_device *, struct drbd_peer_request *,
 				 int);
@@ -1401,6 +1447,37 @@ static inline void drbd_tcp_quickack(struct socket *sock)
 			(char*)&val, sizeof(val));
 }
 
+/* sets the number of 512 byte sectors of our virtual device */
+static inline void drbd_set_my_capacity(struct drbd_device *device,
+					sector_t size)
+{
+	/* set_capacity(device->this_bdev->bd_disk, size); */
+	set_capacity(device->vdisk, size);
+	device->this_bdev->bd_inode->i_size = (loff_t)size << 9;
+}
+
+/*
+ * used to submit our private bio
+ */
+static inline void drbd_generic_make_request(struct drbd_device *device,
+					     int fault_type, struct bio *bio)
+{
+	__release(local);
+	if (!bio->bi_bdev) {
+		printk(KERN_ERR "drbd%d: drbd_generic_make_request: "
+				"bio->bi_bdev == NULL\n",
+		       device_to_minor(device));
+		dump_stack();
+		bio_endio(bio, -ENODEV);
+		return;
+	}
+
+	if (drbd_insert_fault(device, fault_type))
+		bio_endio(bio, -EIO);
+	else
+		generic_make_request(bio);
+}
+
 void drbd_bump_write_ordering(struct drbd_connection *connection, enum write_ordering_e wo);
 
 /* drbd_proc.c */
@@ -1410,6 +1487,7 @@ extern const char *drbd_conn_str(enum drbd_conns s);
 extern const char *drbd_role_str(enum drbd_role s);
 
 /* drbd_actlog.c */
+extern bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i);
 extern int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *i);
 extern void drbd_al_begin_io_commit(struct drbd_device *device, bool delegate);
 extern bool drbd_al_begin_io_fastpath(struct drbd_device *device, struct drbd_interval *i);
@@ -2144,7 +2222,7 @@ static inline void drbd_md_flush(struct drbd_device *device)
 
 static inline struct drbd_connection *first_connection(struct drbd_resource *resource)
 {
-	return list_first_entry(&resource->connections,
+	return list_first_entry_or_null(&resource->connections,
 				struct drbd_connection, connections);
 }
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 331e5cc1227d..960645c26e6f 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1607,8 +1607,8 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection, unsigned long b
 		return bi_rw & REQ_SYNC ? DP_RW_SYNC : 0;
 }
 
-/* Used to send write requests
- * R_PRIMARY -> Peer	(P_DATA)
+/* Used to send write or TRIM aka REQ_DISCARD requests
+ * R_PRIMARY -> Peer	(P_DATA, P_TRIM)
  */
 int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *req)
 {
@@ -1640,6 +1640,16 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 			dp_flags |= DP_SEND_WRITE_ACK;
 	}
 	p->dp_flags = cpu_to_be32(dp_flags);
+
+	if (dp_flags & DP_DISCARD) {
+		struct p_trim *t = (struct p_trim*)p;
+		t->size = cpu_to_be32(req->i.size);
+		err = __send_command(peer_device->connection, device->vnr, sock, P_TRIM, sizeof(*t), NULL, 0);
+		goto out;
+	}
+
+	/* our digest is still only over the payload.
+	 * TRIM does not carry any payload. */
 	if (dgs)
 		drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, p + 1);
 	err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + dgs, NULL, req->i.size);
@@ -1675,6 +1685,7 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 		     ... Be noisy about digest too large ...
 		} */
 	}
+out:
 	mutex_unlock(&sock->mutex);  /* locked by drbd_prepare_command() */
 
 	return err;
@@ -2570,6 +2581,7 @@ struct drbd_resource *drbd_create_resource(const char *name)
 	INIT_LIST_HEAD(&resource->connections);
 	list_add_tail_rcu(&resource->resources, &drbd_resources);
 	mutex_init(&resource->conf_update);
+	mutex_init(&resource->adm_mutex);
 	spin_lock_init(&resource->req_lock);
 	return resource;
 
@@ -2687,14 +2699,16 @@ static int init_submitter(struct drbd_device *device)
 	return 0;
 }
 
-enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned int minor, int vnr)
+enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsigned int minor)
 {
+	struct drbd_resource *resource = adm_ctx->resource;
 	struct drbd_connection *connection;
 	struct drbd_device *device;
 	struct drbd_peer_device *peer_device, *tmp_peer_device;
 	struct gendisk *disk;
 	struct request_queue *q;
 	int id;
+	int vnr = adm_ctx->volume;
 	enum drbd_ret_code err = ERR_NOMEM;
 
 	device = minor_to_device(minor);
@@ -2763,7 +2777,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned i
 	if (id < 0) {
 		if (id == -ENOSPC) {
 			err = ERR_MINOR_EXISTS;
-			drbd_msg_put_info("requested minor exists already");
+			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_no_minor_idr;
 	}
@@ -2773,7 +2787,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned i
 	if (id < 0) {
 		if (id == -ENOSPC) {
 			err = ERR_MINOR_EXISTS;
-			drbd_msg_put_info("requested minor exists already");
+			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_idr_remove_minor;
 	}
@@ -2794,7 +2808,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned i
 		if (id < 0) {
 			if (id == -ENOSPC) {
 				err = ERR_INVALID_REQUEST;
-				drbd_msg_put_info("requested volume exists already");
+				drbd_msg_put_info(adm_ctx->reply_skb, "requested volume exists already");
 			}
 			goto out_idr_remove_from_resource;
 		}
@@ -2803,7 +2817,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_resource *resource, unsigned i
 
 	if (init_submitter(device)) {
 		err = ERR_NOMEM;
-		drbd_msg_put_info("unable to create submit workqueue");
+		drbd_msg_put_info(adm_ctx->reply_skb, "unable to create submit workqueue");
 		goto out_idr_remove_vol;
 	}
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 526414bc2cab..1b35c45c92b7 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -34,7 +34,6 @@
 #include "drbd_int.h"
 #include "drbd_protocol.h"
 #include "drbd_req.h"
-#include "drbd_wrappers.h"
 #include <asm/unaligned.h>
 #include <linux/drbd_limits.h>
 #include <linux/kthread.h>
@@ -82,32 +81,6 @@ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb);
 /* used blkdev_get_by_path, to claim our meta data device(s) */
 static char *drbd_m_holder = "Hands off! this is DRBD's meta data device.";
 
-/* Configuration is strictly serialized, because generic netlink message
- * processing is strictly serialized by the genl_lock().
- * Which means we can use one static global drbd_config_context struct.
- */
-static struct drbd_config_context {
-	/* assigned from drbd_genlmsghdr */
-	unsigned int minor;
-	/* assigned from request attributes, if present */
-	unsigned int volume;
-#define VOLUME_UNSPECIFIED		(-1U)
-	/* pointer into the request skb,
-	 * limited lifetime! */
-	char *resource_name;
-	struct nlattr *my_addr;
-	struct nlattr *peer_addr;
-
-	/* reply buffer */
-	struct sk_buff *reply_skb;
-	/* pointer into reply buffer */
-	struct drbd_genlmsghdr *reply_dh;
-	/* resolved from attributes, if possible */
-	struct drbd_device *device;
-	struct drbd_resource *resource;
-	struct drbd_connection *connection;
-} adm_ctx;
-
 static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	genlmsg_end(skb, genlmsg_data(nlmsg_data(nlmsg_hdr(skb))));
@@ -117,9 +90,8 @@ static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 
 /* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
  * reason it could fail was no space in skb, and there are 4k available. */
-int drbd_msg_put_info(const char *info)
+int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 {
-	struct sk_buff *skb = adm_ctx.reply_skb;
 	struct nlattr *nla;
 	int err = -EMSGSIZE;
 
@@ -143,42 +115,46 @@ int drbd_msg_put_info(const char *info)
  * and per-family private info->pointers.
  * But we need to stay compatible with older kernels.
  * If it returns successfully, adm_ctx members are valid.
+ *
+ * At this point, we still rely on the global genl_lock().
+ * If we want to avoid that, and allow "genl_family.parallel_ops", we may need
+ * to add additional synchronization against object destruction/modification.
  */
 #define DRBD_ADM_NEED_MINOR	1
 #define DRBD_ADM_NEED_RESOURCE	2
 #define DRBD_ADM_NEED_CONNECTION 4
-static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
-		unsigned flags)
+static int drbd_adm_prepare(struct drbd_config_context *adm_ctx,
+	struct sk_buff *skb, struct genl_info *info, unsigned flags)
 {
 	struct drbd_genlmsghdr *d_in = info->userhdr;
 	const u8 cmd = info->genlhdr->cmd;
 	int err;
 
-	memset(&adm_ctx, 0, sizeof(adm_ctx));
+	memset(adm_ctx, 0, sizeof(*adm_ctx));
 
 	/* genl_rcv_msg only checks for CAP_NET_ADMIN on "GENL_ADMIN_PERM" :( */
 	if (cmd != DRBD_ADM_GET_STATUS && !capable(CAP_NET_ADMIN))
 	       return -EPERM;
 
-	adm_ctx.reply_skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!adm_ctx.reply_skb) {
+	adm_ctx->reply_skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!adm_ctx->reply_skb) {
 		err = -ENOMEM;
 		goto fail;
 	}
 
-	adm_ctx.reply_dh = genlmsg_put_reply(adm_ctx.reply_skb,
+	adm_ctx->reply_dh = genlmsg_put_reply(adm_ctx->reply_skb,
 					info, &drbd_genl_family, 0, cmd);
 	/* put of a few bytes into a fresh skb of >= 4k will always succeed.
 	 * but anyways */
-	if (!adm_ctx.reply_dh) {
+	if (!adm_ctx->reply_dh) {
 		err = -ENOMEM;
 		goto fail;
 	}
 
-	adm_ctx.reply_dh->minor = d_in->minor;
-	adm_ctx.reply_dh->ret_code = NO_ERROR;
+	adm_ctx->reply_dh->minor = d_in->minor;
+	adm_ctx->reply_dh->ret_code = NO_ERROR;
 
-	adm_ctx.volume = VOLUME_UNSPECIFIED;
+	adm_ctx->volume = VOLUME_UNSPECIFIED;
 	if (info->attrs[DRBD_NLA_CFG_CONTEXT]) {
 		struct nlattr *nla;
 		/* parse and validate only */
@@ -188,111 +164,131 @@ static int drbd_adm_prepare(struct sk_buff *skb, struct genl_info *info,
 
 		/* It was present, and valid,
 		 * copy it over to the reply skb. */
-		err = nla_put_nohdr(adm_ctx.reply_skb,
+		err = nla_put_nohdr(adm_ctx->reply_skb,
 				info->attrs[DRBD_NLA_CFG_CONTEXT]->nla_len,
 				info->attrs[DRBD_NLA_CFG_CONTEXT]);
 		if (err)
 			goto fail;
 
-		/* and assign stuff to the global adm_ctx */
+		/* and assign stuff to the adm_ctx */
 		nla = nested_attr_tb[__nla_type(T_ctx_volume)];
 		if (nla)
-			adm_ctx.volume = nla_get_u32(nla);
+			adm_ctx->volume = nla_get_u32(nla);
 		nla = nested_attr_tb[__nla_type(T_ctx_resource_name)];
 		if (nla)
-			adm_ctx.resource_name = nla_data(nla);
-		adm_ctx.my_addr = nested_attr_tb[__nla_type(T_ctx_my_addr)];
-		adm_ctx.peer_addr = nested_attr_tb[__nla_type(T_ctx_peer_addr)];
-		if ((adm_ctx.my_addr &&
-		     nla_len(adm_ctx.my_addr) > sizeof(adm_ctx.connection->my_addr)) ||
-		    (adm_ctx.peer_addr &&
-		     nla_len(adm_ctx.peer_addr) > sizeof(adm_ctx.connection->peer_addr))) {
+			adm_ctx->resource_name = nla_data(nla);
+		adm_ctx->my_addr = nested_attr_tb[__nla_type(T_ctx_my_addr)];
+		adm_ctx->peer_addr = nested_attr_tb[__nla_type(T_ctx_peer_addr)];
+		if ((adm_ctx->my_addr &&
+		     nla_len(adm_ctx->my_addr) > sizeof(adm_ctx->connection->my_addr)) ||
+		    (adm_ctx->peer_addr &&
+		     nla_len(adm_ctx->peer_addr) > sizeof(adm_ctx->connection->peer_addr))) {
 			err = -EINVAL;
 			goto fail;
 		}
 	}
 
-	adm_ctx.minor = d_in->minor;
-	adm_ctx.device = minor_to_device(d_in->minor);
-	if (adm_ctx.resource_name) {
-		adm_ctx.resource = drbd_find_resource(adm_ctx.resource_name);
+	adm_ctx->minor = d_in->minor;
+	adm_ctx->device = minor_to_device(d_in->minor);
+
+	/* We are protected by the global genl_lock().
+	 * But we may explicitly drop it/retake it in drbd_adm_set_role(),
+	 * so make sure this object stays around. */
+	if (adm_ctx->device)
+		kref_get(&adm_ctx->device->kref);
+
+	if (adm_ctx->resource_name) {
+		adm_ctx->resource = drbd_find_resource(adm_ctx->resource_name);
 	}
 
-	if (!adm_ctx.device && (flags & DRBD_ADM_NEED_MINOR)) {
-		drbd_msg_put_info("unknown minor");
+	if (!adm_ctx->device && (flags & DRBD_ADM_NEED_MINOR)) {
+		drbd_msg_put_info(adm_ctx->reply_skb, "unknown minor");
 		return ERR_MINOR_INVALID;
 	}
-	if (!adm_ctx.resource && (flags & DRBD_ADM_NEED_RESOURCE)) {
-		drbd_msg_put_info("unknown resource");
-		if (adm_ctx.resource_name)
+	if (!adm_ctx->resource && (flags & DRBD_ADM_NEED_RESOURCE)) {
+		drbd_msg_put_info(adm_ctx->reply_skb, "unknown resource");
+		if (adm_ctx->resource_name)
 			return ERR_RES_NOT_KNOWN;
 		return ERR_INVALID_REQUEST;
 	}
 
 	if (flags & DRBD_ADM_NEED_CONNECTION) {
-		if (adm_ctx.resource) {
-			drbd_msg_put_info("no resource name expected");
+		if (adm_ctx->resource) {
+			drbd_msg_put_info(adm_ctx->reply_skb, "no resource name expected");
 			return ERR_INVALID_REQUEST;
 		}
-		if (adm_ctx.device) {
-			drbd_msg_put_info("no minor number expected");
+		if (adm_ctx->device) {
+			drbd_msg_put_info(adm_ctx->reply_skb, "no minor number expected");
 			return ERR_INVALID_REQUEST;
 		}
-		if (adm_ctx.my_addr && adm_ctx.peer_addr)
-			adm_ctx.connection = conn_get_by_addrs(nla_data(adm_ctx.my_addr),
-							  nla_len(adm_ctx.my_addr),
-							  nla_data(adm_ctx.peer_addr),
-							  nla_len(adm_ctx.peer_addr));
-		if (!adm_ctx.connection) {
-			drbd_msg_put_info("unknown connection");
+		if (adm_ctx->my_addr && adm_ctx->peer_addr)
+			adm_ctx->connection = conn_get_by_addrs(nla_data(adm_ctx->my_addr),
+							  nla_len(adm_ctx->my_addr),
+							  nla_data(adm_ctx->peer_addr),
+							  nla_len(adm_ctx->peer_addr));
+		if (!adm_ctx->connection) {
+			drbd_msg_put_info(adm_ctx->reply_skb, "unknown connection");
 			return ERR_INVALID_REQUEST;
 		}
 	}
 
 	/* some more paranoia, if the request was over-determined */
-	if (adm_ctx.device && adm_ctx.resource &&
-	    adm_ctx.device->resource != adm_ctx.resource) {
+	if (adm_ctx->device && adm_ctx->resource &&
+	    adm_ctx->device->resource != adm_ctx->resource) {
 		pr_warning("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
-				adm_ctx.minor, adm_ctx.resource->name,
-				adm_ctx.device->resource->name);
-		drbd_msg_put_info("minor exists in different resource");
+				adm_ctx->minor, adm_ctx->resource->name,
+				adm_ctx->device->resource->name);
+		drbd_msg_put_info(adm_ctx->reply_skb, "minor exists in different resource");
 		return ERR_INVALID_REQUEST;
 	}
-	if (adm_ctx.device &&
-	    adm_ctx.volume != VOLUME_UNSPECIFIED &&
-	    adm_ctx.volume != adm_ctx.device->vnr) {
+	if (adm_ctx->device &&
+	    adm_ctx->volume != VOLUME_UNSPECIFIED &&
+	    adm_ctx->volume != adm_ctx->device->vnr) {
 		pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
-				adm_ctx.minor, adm_ctx.volume,
-				adm_ctx.device->vnr,
-				adm_ctx.device->resource->name);
-		drbd_msg_put_info("minor exists as different volume");
+				adm_ctx->minor, adm_ctx->volume,
+				adm_ctx->device->vnr,
+				adm_ctx->device->resource->name);
+		drbd_msg_put_info(adm_ctx->reply_skb, "minor exists as different volume");
 		return ERR_INVALID_REQUEST;
 	}
 
+	/* still, provide adm_ctx->resource always, if possible. */
+	if (!adm_ctx->resource) {
+		adm_ctx->resource = adm_ctx->device ? adm_ctx->device->resource
+			: adm_ctx->connection ? adm_ctx->connection->resource : NULL;
+		if (adm_ctx->resource)
+			kref_get(&adm_ctx->resource->kref);
+	}
+
 	return NO_ERROR;
 
 fail:
-	nlmsg_free(adm_ctx.reply_skb);
-	adm_ctx.reply_skb = NULL;
+	nlmsg_free(adm_ctx->reply_skb);
+	adm_ctx->reply_skb = NULL;
 	return err;
 }
 
-static int drbd_adm_finish(struct genl_info *info, int retcode)
+static int drbd_adm_finish(struct drbd_config_context *adm_ctx,
+	struct genl_info *info, int retcode)
 {
-	if (adm_ctx.connection) {
-		kref_put(&adm_ctx.connection->kref, drbd_destroy_connection);
-		adm_ctx.connection = NULL;
+	if (adm_ctx->device) {
+		kref_put(&adm_ctx->device->kref, drbd_destroy_device);
+		adm_ctx->device = NULL;
 	}
-	if (adm_ctx.resource) {
-		kref_put(&adm_ctx.resource->kref, drbd_destroy_resource);
-		adm_ctx.resource = NULL;
+	if (adm_ctx->connection) {
+		kref_put(&adm_ctx->connection->kref, &drbd_destroy_connection);
+		adm_ctx->connection = NULL;
+	}
+	if (adm_ctx->resource) {
+		kref_put(&adm_ctx->resource->kref, drbd_destroy_resource);
+		adm_ctx->resource = NULL;
 	}
 
-	if (!adm_ctx.reply_skb)
+	if (!adm_ctx->reply_skb)
 		return -ENOMEM;
 
-	adm_ctx.reply_dh->ret_code = retcode;
-	drbd_adm_send_reply(adm_ctx.reply_skb, info);
+	adm_ctx->reply_dh->ret_code = retcode;
+	drbd_adm_send_reply(adm_ctx->reply_skb, info);
 	return 0;
 }
 
@@ -426,6 +422,14 @@ static enum drbd_fencing_p highest_fencing_policy(struct drbd_connection *connec
 	}
 	rcu_read_unlock();
 
+	if (fp == FP_NOT_AVAIL) {
+		/* IO Suspending works on the whole resource.
+		   Do it only for one device. */
+		vnr = 0;
+		peer_device = idr_get_next(&connection->peer_devices, &vnr);
+		drbd_change_state(peer_device->device, CS_VERBOSE | CS_HARD, NS(susp_fen, 0));
+	}
+
 	return fp;
 }
 
@@ -438,12 +442,13 @@ bool conn_try_outdate_peer(struct drbd_connection *connection)
 	char *ex_to_string;
 	int r;
 
+	spin_lock_irq(&connection->resource->req_lock);
 	if (connection->cstate >= C_WF_REPORT_PARAMS) {
 		drbd_err(connection, "Expected cstate < C_WF_REPORT_PARAMS\n");
+		spin_unlock_irq(&connection->resource->req_lock);
 		return false;
 	}
 
-	spin_lock_irq(&connection->resource->req_lock);
 	connect_cnt = connection->connect_cnt;
 	spin_unlock_irq(&connection->resource->req_lock);
 
@@ -654,11 +659,11 @@ drbd_set_role(struct drbd_device *device, enum drbd_role new_role, int force)
 			put_ldev(device);
 		}
 	} else {
-		mutex_lock(&device->resource->conf_update);
+		/* Called from drbd_adm_set_role only.
+		 * We are still holding the conf_update mutex. */
 		nc = first_peer_device(device)->connection->net_conf;
 		if (nc)
 			nc->discard_my_data = 0; /* without copy; single bit op is atomic */
-		mutex_unlock(&device->resource->conf_update);
 
 		set_disk_ro(device->vdisk, false);
 		if (get_ldev(device)) {
@@ -700,11 +705,12 @@ static const char *from_attrs_err_to_txt(int err)
 
 int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct set_role_parms parms;
 	int err;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -715,17 +721,22 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
 		err = set_role_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto out;
 		}
 	}
+	genl_unlock();
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 
 	if (info->genlhdr->cmd == DRBD_ADM_PRIMARY)
 		retcode = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate);
 	else
 		retcode = drbd_set_role(adm_ctx.device, R_SECONDARY, 0);
+
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+	genl_lock();
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -1104,15 +1115,18 @@ static void drbd_setup_queue_param(struct drbd_device *device, unsigned int max_
 	struct request_queue * const q = device->rq_queue;
 	unsigned int max_hw_sectors = max_bio_size >> 9;
 	unsigned int max_segments = 0;
+	struct request_queue *b = NULL;
 
 	if (get_ldev_if_state(device, D_ATTACHING)) {
-		struct request_queue * const b = device->ldev->backing_bdev->bd_disk->queue;
+		b = device->ldev->backing_bdev->bd_disk->queue;
 
 		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
 		rcu_read_lock();
 		max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
 		rcu_read_unlock();
-		put_ldev(device);
+
+		blk_set_stacking_limits(&q->limits);
+		blk_queue_max_write_same_sectors(q, 0);
 	}
 
 	blk_queue_logical_block_size(q, 512);
@@ -1121,8 +1135,25 @@ static void drbd_setup_queue_param(struct drbd_device *device, unsigned int max_
 	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
 	blk_queue_segment_boundary(q, PAGE_CACHE_SIZE-1);
 
-	if (get_ldev_if_state(device, D_ATTACHING)) {
-		struct request_queue * const b = device->ldev->backing_bdev->bd_disk->queue;
+	if (b) {
+		struct drbd_connection *connection = first_peer_device(device)->connection;
+
+		if (blk_queue_discard(b) &&
+		    (connection->cstate < C_CONNECTED || connection->agreed_features & FF_TRIM)) {
+			/* For now, don't allow more than one activity log extent worth of data
+			 * to be discarded in one go. We may need to rework drbd_al_begin_io()
+			 * to allow for even larger discard ranges */
+			q->limits.max_discard_sectors = DRBD_MAX_DISCARD_SECTORS;
+
+			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+			/* REALLY? Is stacking secdiscard "legal"? */
+			if (blk_queue_secdiscard(b))
+				queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
+		} else {
+			q->limits.max_discard_sectors = 0;
+			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
+			queue_flag_clear_unlocked(QUEUE_FLAG_SECDISCARD, q);
+		}
 
 		blk_queue_stack_limits(q, b);
 
@@ -1164,8 +1195,14 @@ void drbd_reconsider_max_bio_size(struct drbd_device *device)
 			peer = DRBD_MAX_BIO_SIZE_P95;  /* drbd 8.3.8 onwards, before 8.4.0 */
 		else
 			peer = DRBD_MAX_BIO_SIZE;
-	}
 
+		/* We may later detach and re-attach on a disconnected Primary.
+		 * Avoid this setting to jump back in that case.
+		 * We want to store what we know the peer DRBD can handle,
+		 * not what the peer IO backend can handle. */
+		if (peer > device->peer_max_bio_size)
+			device->peer_max_bio_size = peer;
+	}
 	new = min(local, peer);
 
 	if (device->state.role == R_PRIMARY && new < now)
@@ -1258,19 +1295,21 @@ static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
 
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct drbd_device *device;
 	struct disk_conf *new_disk_conf, *old_disk_conf;
 	struct fifo_buffer *old_plan = NULL, *new_plan = NULL;
 	int err, fifo_size;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
-		goto out;
+		goto finish;
 
 	device = adm_ctx.device;
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 
 	/* we also need a disk
 	 * to change the options on */
@@ -1294,7 +1333,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	err = disk_conf_from_attrs_for_change(new_disk_conf, info);
 	if (err && err != -ENOMSG) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto fail_unlock;
 	}
 
@@ -1385,12 +1424,15 @@ fail_unlock:
 success:
 	put_ldev(device);
  out:
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+ finish:
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
 	int err;
 	enum drbd_ret_code retcode;
@@ -1406,13 +1448,14 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	enum drbd_state_rv rv;
 	struct net_conf *nc;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto finish;
 
 	device = adm_ctx.device;
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	conn_reconfig_start(first_peer_device(device)->connection);
 
 	/* if you want to reconfigure, please tear down first */
@@ -1455,7 +1498,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	err = disk_conf_from_attrs(new_disk_conf, info);
 	if (err) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
@@ -1619,7 +1662,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (device->state.conn < C_CONNECTED &&
-	    device->state.role == R_PRIMARY &&
+	    device->state.role == R_PRIMARY && device->ed_uuid &&
 	    (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
 		drbd_err(device, "Can only attach to data with current UUID=%016llX\n",
 		    (unsigned long long)device->ed_uuid);
@@ -1797,7 +1840,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	kobject_uevent(&disk_to_dev(device->vdisk)->kobj, KOBJ_CHANGE);
 	put_ldev(device);
 	conn_reconfig_done(first_peer_device(device)->connection);
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 
  force_diskless_dec:
@@ -1819,9 +1863,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	kfree(new_disk_conf);
 	lc_destroy(resync_lru);
 	kfree(new_plan);
-
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
  finish:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -1860,11 +1904,12 @@ out:
  * Only then we have finally detached. */
 int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct detach_parms parms = { };
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -1874,14 +1919,16 @@ int drbd_adm_detach(struct sk_buff *skb, struct genl_info *info)
 		err = detach_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto out;
 		}
 	}
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	retcode = adm_detach(adm_ctx.device, parms.force_detach);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2055,6 +2102,7 @@ static void free_crypto(struct crypto *crypto)
 
 int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct drbd_connection *connection;
 	struct net_conf *old_net_conf, *new_net_conf = NULL;
@@ -2063,13 +2111,14 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 	int rsr; /* re-sync running */
 	struct crypto crypto = { };
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONNECTION);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_CONNECTION);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
-		goto out;
+		goto finish;
 
 	connection = adm_ctx.connection;
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 
 	new_net_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL);
 	if (!new_net_conf) {
@@ -2084,7 +2133,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 	old_net_conf = connection->net_conf;
 
 	if (!old_net_conf) {
-		drbd_msg_put_info("net conf missing, try connect");
+		drbd_msg_put_info(adm_ctx.reply_skb, "net conf missing, try connect");
 		retcode = ERR_INVALID_REQUEST;
 		goto fail;
 	}
@@ -2096,7 +2145,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 	err = net_conf_from_attrs_for_change(new_net_conf, info);
 	if (err && err != -ENOMSG) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
@@ -2167,12 +2216,15 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
  done:
 	conn_reconfig_done(connection);
  out:
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+ finish:
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_peer_device *peer_device;
 	struct net_conf *old_net_conf, *new_net_conf = NULL;
 	struct crypto crypto = { };
@@ -2182,14 +2234,14 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	int i;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
 
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 	if (!(adm_ctx.my_addr && adm_ctx.peer_addr)) {
-		drbd_msg_put_info("connection endpoint(s) missing");
+		drbd_msg_put_info(adm_ctx.reply_skb, "connection endpoint(s) missing");
 		retcode = ERR_INVALID_REQUEST;
 		goto out;
 	}
@@ -2215,6 +2267,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	connection = first_connection(adm_ctx.resource);
 	conn_reconfig_start(connection);
 
@@ -2235,7 +2288,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	err = net_conf_from_attrs(new_net_conf, info);
 	if (err && err != -ENOMSG) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
@@ -2284,7 +2337,8 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 	retcode = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE);
 
 	conn_reconfig_done(connection);
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 
 fail:
@@ -2292,8 +2346,9 @@ fail:
 	kfree(new_net_conf);
 
 	conn_reconfig_done(connection);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2356,13 +2411,14 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection
 
 int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct disconnect_parms parms;
 	struct drbd_connection *connection;
 	enum drbd_state_rv rv;
 	enum drbd_ret_code retcode;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_CONNECTION);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_CONNECTION);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -2374,18 +2430,20 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info)
 		err = disconnect_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto fail;
 		}
 	}
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	rv = conn_try_disconnect(connection, parms.force_disconnect);
 	if (rv < SS_SUCCESS)
 		retcode = rv;  /* FIXME: Type mismatch. */
 	else
 		retcode = NO_ERROR;
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
  fail:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2407,6 +2465,7 @@ void resync_after_online_grow(struct drbd_device *device)
 
 int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct disk_conf *old_disk_conf, *new_disk_conf = NULL;
 	struct resize_parms rs;
 	struct drbd_device *device;
@@ -2417,12 +2476,13 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	sector_t u_size;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
-		goto fail;
+		goto finish;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
 	if (!get_ldev(device)) {
 		retcode = ERR_NO_DISK;
@@ -2436,7 +2496,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 		err = resize_parms_from_attrs(&rs, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto fail_ldev;
 		}
 	}
@@ -2482,7 +2542,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 			goto fail_ldev;
 		}
 
-		if (device->state.conn != C_CONNECTED) {
+		if (device->state.conn != C_CONNECTED && !rs.resize_force) {
 			retcode = ERR_MD_LAYOUT_CONNECTED;
 			goto fail_ldev;
 		}
@@ -2528,7 +2588,9 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 	}
 
  fail:
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
+ finish:
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 
  fail_ldev:
@@ -2538,11 +2600,12 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info)
 
 int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct res_opts res_opts;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -2555,33 +2618,37 @@ int drbd_adm_resource_opts(struct sk_buff *skb, struct genl_info *info)
 	err = res_opts_from_attrs(&res_opts, info);
 	if (err && err != -ENOMSG) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto fail;
 	}
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	err = set_resource_options(adm_ctx.resource, &res_opts);
 	if (err) {
 		retcode = ERR_INVALID_REQUEST;
 		if (err == -ENOMEM)
 			retcode = ERR_NOMEM;
 	}
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 
 fail:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
 	int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
 
 	/* If there is still bitmap IO pending, probably because of a previous
@@ -2605,26 +2672,29 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 	} else
 		retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_T));
 	drbd_resume_io(device);
-
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 static int drbd_adm_simple_request_state(struct sk_buff *skb, struct genl_info *info,
 		union drbd_state mask, union drbd_state val)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	retcode = drbd_request_state(adm_ctx.device, mask, val);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2639,15 +2709,17 @@ static int drbd_bmio_set_susp_al(struct drbd_device *device)
 
 int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	int retcode; /* drbd_ret_code, drbd_state_rv */
 	struct drbd_device *device;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
 
 	/* If there is still bitmap IO pending, probably because of a previous
@@ -2674,40 +2746,45 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 	} else
 		retcode = drbd_request_state(device, NS(conn, C_STARTING_SYNC_S));
 	drbd_resume_io(device);
-
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_pause_sync(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	if (drbd_request_state(adm_ctx.device, NS(user_isp, 1)) == SS_NOTHING_TO_DO)
 		retcode = ERR_PAUSE_IS_SET;
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	union drbd_dev_state s;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	if (drbd_request_state(adm_ctx.device, NS(user_isp, 0)) == SS_NOTHING_TO_DO) {
 		s = adm_ctx.device->state;
 		if (s.conn == C_PAUSED_SYNC_S || s.conn == C_PAUSED_SYNC_T) {
@@ -2717,9 +2794,9 @@ int drbd_adm_resume_sync(struct sk_buff *skb, struct genl_info *info)
 			retcode = ERR_PAUSE_IS_CLEAR;
 		}
 	}
-
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2730,15 +2807,17 @@ int drbd_adm_suspend_io(struct sk_buff *skb, struct genl_info *info)
 
 int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
 	int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	device = adm_ctx.device;
 	if (test_bit(NEW_CUR_UUID, &device->flags)) {
 		drbd_uuid_new_current(device);
@@ -2753,9 +2832,9 @@ int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info)
 			tl_restart(first_peer_device(device)->connection, FAIL_FROZEN_DISK_IO);
 	}
 	drbd_resume_io(device);
-
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -2931,10 +3010,11 @@ nla_put_failure:
 
 int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -2946,7 +3026,7 @@ int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info)
 		return err;
 	}
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -3133,11 +3213,12 @@ dump:
 
 int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct timeout_parms tp;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -3154,17 +3235,18 @@ int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info)
 		return err;
 	}
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
 	enum drbd_ret_code retcode;
 	struct start_ov_parms parms;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -3179,10 +3261,12 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 		int err = start_ov_parms_from_attrs(&parms, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto out;
 		}
 	}
+	mutex_lock(&adm_ctx.resource->adm_mutex);
+
 	/* w_make_ov_request expects position to be aligned */
 	device->ov_start_sector = parms.ov_start_sector & ~(BM_SECT_PER_BIT-1);
 	device->ov_stop_sector = parms.ov_stop_sector;
@@ -3193,21 +3277,24 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
 	wait_event(device->misc_wait, !test_bit(BITMAP_IO, &device->flags));
 	retcode = drbd_request_state(device, NS(conn, C_VERIFY_S));
 	drbd_resume_io(device);
+
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 
 int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_device *device;
 	enum drbd_ret_code retcode;
 	int skip_initial_sync = 0;
 	int err;
 	struct new_c_uuid_parms args;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -3219,11 +3306,12 @@ int drbd_adm_new_c_uuid(struct sk_buff *skb, struct genl_info *info)
 		err = new_c_uuid_parms_from_attrs(&args, info);
 		if (err) {
 			retcode = ERR_MANDATORY_TAG;
-			drbd_msg_put_info(from_attrs_err_to_txt(err));
+			drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 			goto out_nolock;
 		}
 	}
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	mutex_lock(device->state_mutex); /* Protects us against serialized state changes. */
 
 	if (!get_ldev(device)) {
@@ -3268,22 +3356,24 @@ out_dec:
 	put_ldev(device);
 out:
 	mutex_unlock(device->state_mutex);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out_nolock:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 static enum drbd_ret_code
-drbd_check_resource_name(const char *name)
+drbd_check_resource_name(struct drbd_config_context *adm_ctx)
 {
+	const char *name = adm_ctx->resource_name;
 	if (!name || !name[0]) {
-		drbd_msg_put_info("resource name missing");
+		drbd_msg_put_info(adm_ctx->reply_skb, "resource name missing");
 		return ERR_MANDATORY_TAG;
 	}
 	/* if we want to use these in sysfs/configfs/debugfs some day,
 	 * we must not allow slashes */
 	if (strchr(name, '/')) {
-		drbd_msg_put_info("invalid resource name");
+		drbd_msg_put_info(adm_ctx->reply_skb, "invalid resource name");
 		return ERR_INVALID_REQUEST;
 	}
 	return NO_ERROR;
@@ -3291,11 +3381,12 @@ drbd_check_resource_name(const char *name)
 
 int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 	struct res_opts res_opts;
 	int err;
 
-	retcode = drbd_adm_prepare(skb, info, 0);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, 0);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
@@ -3305,48 +3396,50 @@ int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info)
 	err = res_opts_from_attrs(&res_opts, info);
 	if (err && err != -ENOMSG) {
 		retcode = ERR_MANDATORY_TAG;
-		drbd_msg_put_info(from_attrs_err_to_txt(err));
+		drbd_msg_put_info(adm_ctx.reply_skb, from_attrs_err_to_txt(err));
 		goto out;
 	}
 
-	retcode = drbd_check_resource_name(adm_ctx.resource_name);
+	retcode = drbd_check_resource_name(&adm_ctx);
 	if (retcode != NO_ERROR)
 		goto out;
 
 	if (adm_ctx.resource) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) {
 			retcode = ERR_INVALID_REQUEST;
-			drbd_msg_put_info("resource exists");
+			drbd_msg_put_info(adm_ctx.reply_skb, "resource exists");
 		}
 		/* else: still NO_ERROR */
 		goto out;
 	}
 
+	/* not yet safe for genl_family.parallel_ops */
 	if (!conn_create(adm_ctx.resource_name, &res_opts))
 		retcode = ERR_NOMEM;
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_genlmsghdr *dh = info->userhdr;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
 	if (dh->minor > MINORMASK) {
-		drbd_msg_put_info("requested minor out of range");
+		drbd_msg_put_info(adm_ctx.reply_skb, "requested minor out of range");
 		retcode = ERR_INVALID_REQUEST;
 		goto out;
 	}
 	if (adm_ctx.volume > DRBD_VOLUME_MAX) {
-		drbd_msg_put_info("requested volume id out of range");
+		drbd_msg_put_info(adm_ctx.reply_skb, "requested volume id out of range");
 		retcode = ERR_INVALID_REQUEST;
 		goto out;
 	}
@@ -3360,9 +3453,11 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	retcode = drbd_create_device(adm_ctx.resource, dh->minor, adm_ctx.volume);
+	mutex_lock(&adm_ctx.resource->adm_mutex);
+	retcode = drbd_create_device(&adm_ctx, dh->minor);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
@@ -3383,35 +3478,40 @@ static enum drbd_ret_code adm_del_minor(struct drbd_device *device)
 
 int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_MINOR);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto out;
 
+	mutex_lock(&adm_ctx.resource->adm_mutex);
 	retcode = adm_del_minor(adm_ctx.device);
+	mutex_unlock(&adm_ctx.resource->adm_mutex);
 out:
-	drbd_adm_finish(info, retcode);
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
 	struct drbd_connection *connection;
 	struct drbd_device *device;
 	int retcode; /* enum drbd_ret_code rsp. enum drbd_state_rv */
 	unsigned i;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
-		goto out;
+		goto finish;
 
 	resource = adm_ctx.resource;
+	mutex_lock(&resource->adm_mutex);
 	/* demote */
 	for_each_connection(connection, resource) {
 		struct drbd_peer_device *peer_device;
@@ -3419,14 +3519,14 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		idr_for_each_entry(&connection->peer_devices, peer_device, i) {
 			retcode = drbd_set_role(peer_device->device, R_SECONDARY, 0);
 			if (retcode < SS_SUCCESS) {
-				drbd_msg_put_info("failed to demote");
+				drbd_msg_put_info(adm_ctx.reply_skb, "failed to demote");
 				goto out;
 			}
 		}
 
 		retcode = conn_try_disconnect(connection, 0);
 		if (retcode < SS_SUCCESS) {
-			drbd_msg_put_info("failed to disconnect");
+			drbd_msg_put_info(adm_ctx.reply_skb, "failed to disconnect");
 			goto out;
 		}
 	}
@@ -3435,7 +3535,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 	idr_for_each_entry(&resource->devices, device, i) {
 		retcode = adm_detach(device, 0);
 		if (retcode < SS_SUCCESS || retcode > NO_ERROR) {
-			drbd_msg_put_info("failed to detach");
+			drbd_msg_put_info(adm_ctx.reply_skb, "failed to detach");
 			goto out;
 		}
 	}
@@ -3453,7 +3553,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		retcode = adm_del_minor(device);
 		if (retcode != NO_ERROR) {
 			/* "can not happen" */
-			drbd_msg_put_info("failed to delete volume");
+			drbd_msg_put_info(adm_ctx.reply_skb, "failed to delete volume");
 			goto out;
 		}
 	}
@@ -3462,25 +3562,28 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 	synchronize_rcu();
 	drbd_free_resource(resource);
 	retcode = NO_ERROR;
-
 out:
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&resource->adm_mutex);
+finish:
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
 int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
+	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
 	struct drbd_connection *connection;
 	enum drbd_ret_code retcode;
 
-	retcode = drbd_adm_prepare(skb, info, DRBD_ADM_NEED_RESOURCE);
+	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
 	if (!adm_ctx.reply_skb)
 		return retcode;
 	if (retcode != NO_ERROR)
-		goto out;
+		goto finish;
 
 	resource = adm_ctx.resource;
+	mutex_lock(&resource->adm_mutex);
 	for_each_connection(connection, resource) {
 		if (connection->cstate > C_STANDALONE) {
 			retcode = ERR_NET_CONFIGURED;
@@ -3499,7 +3602,9 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 	drbd_free_resource(resource);
 	retcode = NO_ERROR;
 out:
-	drbd_adm_finish(info, retcode);
+	mutex_unlock(&resource->adm_mutex);
+finish:
+	drbd_adm_finish(&adm_ctx, info, retcode);
 	return 0;
 }
 
diff --git a/drivers/block/drbd/drbd_nla.c b/drivers/block/drbd/drbd_nla.c
index fa672b6df8d6..b2d4791498a6 100644
--- a/drivers/block/drbd/drbd_nla.c
+++ b/drivers/block/drbd/drbd_nla.c
@@ -1,4 +1,3 @@
-#include "drbd_wrappers.h"
 #include <linux/kernel.h>
 #include <net/netlink.h>
 #include <linux/drbd_genl_api.h>
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 2f26e8ffa45b..89736bdbbc70 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -116,7 +116,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 	/* ------------------------ ~18s average ------------------------ */
 	i = (device->rs_last_mark + 2) % DRBD_SYNC_MARKS;
 	dt = (jiffies - device->rs_mark_time[i]) / HZ;
-	if (dt > (DRBD_SYNC_MARK_STEP * DRBD_SYNC_MARKS))
+	if (dt > 180)
 		stalled = 1;
 
 	if (!dt)
diff --git a/drivers/block/drbd/drbd_protocol.h b/drivers/block/drbd/drbd_protocol.h
index 3c04ec0ea333..2da9104a3851 100644
--- a/drivers/block/drbd/drbd_protocol.h
+++ b/drivers/block/drbd/drbd_protocol.h
@@ -54,6 +54,11 @@ enum drbd_packet {
 	P_CONN_ST_CHG_REPLY   = 0x2b, /* meta sock: Connection side state req reply */
 	P_RETRY_WRITE	      = 0x2c, /* Protocol C: retry conflicting write request */
 	P_PROTOCOL_UPDATE     = 0x2d, /* data sock: is used in established connections */
+        /* 0x2e to 0x30 reserved, used in drbd 9 */
+
+	/* REQ_DISCARD. We used "discard" in different contexts before,
+	 * which is why I chose TRIM here, to disambiguate. */
+	P_TRIM                = 0x31,
 
 	P_MAY_IGNORE	      = 0x100, /* Flag to test if (cmd > P_MAY_IGNORE) ... */
 	P_MAX_OPT_CMD	      = 0x101,
@@ -119,6 +124,11 @@ struct p_data {
 	u32	    dp_flags;
 } __packed;
 
+struct p_trim {
+	struct p_data p_data;
+	u32	    size;	/* == bio->bi_size */
+} __packed;
+
 /*
  * commands which share a struct:
  *  p_block_ack:
@@ -150,6 +160,8 @@ struct p_block_req {
  *   ReportParams
  */
 
+#define FF_TRIM      1
+
 struct p_connection_features {
 	u32 protocol_min;
 	u32 feature_flags;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 68e3992e8838..b6c8aaf4931b 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -46,9 +46,10 @@
 #include "drbd_int.h"
 #include "drbd_protocol.h"
 #include "drbd_req.h"
-
 #include "drbd_vli.h"
 
+#define PRO_FEATURES (FF_TRIM)
+
 struct packet_info {
 	enum drbd_packet cmd;
 	unsigned int size;
@@ -65,7 +66,7 @@ enum finish_epoch {
 static int drbd_do_features(struct drbd_connection *connection);
 static int drbd_do_auth(struct drbd_connection *connection);
 static int drbd_disconnected(struct drbd_peer_device *);
-
+static void conn_wait_active_ee_empty(struct drbd_connection *connection);
 static enum finish_epoch drbd_may_finish_epoch(struct drbd_connection *, struct drbd_epoch *, enum epoch_event);
 static int e_end_block(struct drbd_work *, int);
 
@@ -234,9 +235,17 @@ static void drbd_kick_lo_and_reclaim_net(struct drbd_device *device)
  * @retry:	whether to retry, if not enough pages are available right now
  *
  * Tries to allocate number pages, first from our own page pool, then from
- * the kernel, unless this allocation would exceed the max_buffers setting.
+ * the kernel.
  * Possibly retry until DRBD frees sufficient pages somewhere else.
  *
+ * If this allocation would exceed the max_buffers setting, we throttle
+ * allocation (schedule_timeout) to give the system some room to breathe.
+ *
+ * We do not use max-buffers as hard limit, because it could lead to
+ * congestion and further to a distributed deadlock during online-verify or
+ * (checksum based) resync, if the max-buffers, socket buffer sizes and
+ * resync-rate settings are mis-configured.
+ *
  * Returns a page chain linked via page->private.
  */
 struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int number,
@@ -246,10 +255,8 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int
 	struct page *page = NULL;
 	struct net_conf *nc;
 	DEFINE_WAIT(wait);
-	int mxb;
+	unsigned int mxb;
 
-	/* Yes, we may run up to @number over max_buffers. If we
-	 * follow it strictly, the admin will get it wrong anyways. */
 	rcu_read_lock();
 	nc = rcu_dereference(peer_device->connection->net_conf);
 	mxb = nc ? nc->max_buffers : 1000000;
@@ -277,7 +284,8 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int
 			break;
 		}
 
-		schedule();
+		if (schedule_timeout(HZ/10) == 0)
+			mxb = UINT_MAX;
 	}
 	finish_wait(&drbd_pp_wait, &wait);
 
@@ -331,7 +339,7 @@ You must not have the req_lock:
 
 struct drbd_peer_request *
 drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
-		    unsigned int data_size, gfp_t gfp_mask) __must_hold(local)
+		    unsigned int data_size, bool has_payload, gfp_t gfp_mask) __must_hold(local)
 {
 	struct drbd_device *device = peer_device->device;
 	struct drbd_peer_request *peer_req;
@@ -348,7 +356,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 		return NULL;
 	}
 
-	if (data_size) {
+	if (has_payload && data_size) {
 		page = drbd_alloc_pages(peer_device, nr_pages, (gfp_mask & __GFP_WAIT));
 		if (!page)
 			goto fail;
@@ -1026,24 +1034,27 @@ randomize:
 	if (drbd_send_protocol(connection) == -EOPNOTSUPP)
 		return -1;
 
+	/* Prevent a race between resync-handshake and
+	 * being promoted to Primary.
+	 *
+	 * Grab and release the state mutex, so we know that any current
+	 * drbd_set_role() is finished, and any incoming drbd_set_role
+	 * will see the STATE_SENT flag, and wait for it to be cleared.
+	 */
+	idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
+		mutex_lock(peer_device->device->state_mutex);
+
 	set_bit(STATE_SENT, &connection->flags);
 
+	idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
+		mutex_unlock(peer_device->device->state_mutex);
+
 	rcu_read_lock();
 	idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 		struct drbd_device *device = peer_device->device;
 		kref_get(&device->kref);
 		rcu_read_unlock();
 
-		/* Prevent a race between resync-handshake and
-		 * being promoted to Primary.
-		 *
-		 * Grab and release the state mutex, so we know that any current
-		 * drbd_set_role() is finished, and any incoming drbd_set_role
-		 * will see the STATE_SENT flag, and wait for it to be cleared.
-		 */
-		mutex_lock(device->state_mutex);
-		mutex_unlock(device->state_mutex);
-
 		if (discard_my_data)
 			set_bit(DISCARD_MY_DATA, &device->flags);
 		else
@@ -1315,6 +1326,20 @@ int drbd_submit_peer_request(struct drbd_device *device,
 	unsigned nr_pages = (ds + PAGE_SIZE -1) >> PAGE_SHIFT;
 	int err = -ENOMEM;
 
+	if (peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) {
+		/* wait for all pending IO completions, before we start
+		 * zeroing things out. */
+		conn_wait_active_ee_empty(first_peer_device(device)->connection);
+		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
+			sector, ds >> 9, GFP_NOIO))
+			peer_req->flags |= EE_WAS_ERROR;
+		drbd_endio_write_sec_final(peer_req);
+		return 0;
+	}
+
+	if (peer_req->flags & EE_IS_TRIM)
+		nr_pages = 0; /* discards don't have any payload. */
+
 	/* In most cases, we will only need one bio.  But in case the lower
 	 * level restrictions happen to be different at this offset on this
 	 * side than those of the sending peer, we may need to submit the
@@ -1326,7 +1351,7 @@ int drbd_submit_peer_request(struct drbd_device *device,
 next_bio:
 	bio = bio_alloc(GFP_NOIO, nr_pages);
 	if (!bio) {
-		drbd_err(device, "submit_ee: Allocation of a bio failed\n");
+		drbd_err(device, "submit_ee: Allocation of a bio failed (nr_pages=%u)\n", nr_pages);
 		goto fail;
 	}
 	/* > peer_req->i.sector, unless this is the first bio */
@@ -1340,6 +1365,11 @@ next_bio:
 	bios = bio;
 	++n_bios;
 
+	if (rw & REQ_DISCARD) {
+		bio->bi_iter.bi_size = ds;
+		goto submit;
+	}
+
 	page_chain_for_each(page) {
 		unsigned len = min_t(unsigned, ds, PAGE_SIZE);
 		if (!bio_add_page(bio, page, len, 0)) {
@@ -1360,8 +1390,9 @@ next_bio:
 		sector += len >> 9;
 		--nr_pages;
 	}
-	D_ASSERT(device, page == NULL);
 	D_ASSERT(device, ds == 0);
+submit:
+	D_ASSERT(device, page == NULL);
 
 	atomic_set(&peer_req->pending_bios, n_bios);
 	do {
@@ -1490,19 +1521,21 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf
  * and from receive_Data */
 static struct drbd_peer_request *
 read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
-	      int data_size) __must_hold(local)
+	      struct packet_info *pi) __must_hold(local)
 {
 	struct drbd_device *device = peer_device->device;
 	const sector_t capacity = drbd_get_capacity(device->this_bdev);
 	struct drbd_peer_request *peer_req;
 	struct page *page;
 	int dgs, ds, err;
+	int data_size = pi->size;
 	void *dig_in = peer_device->connection->int_dig_in;
 	void *dig_vv = peer_device->connection->int_dig_vv;
 	unsigned long *data;
+	struct p_trim *trim = (pi->cmd == P_TRIM) ? pi->data : NULL;
 
 	dgs = 0;
-	if (peer_device->connection->peer_integrity_tfm) {
+	if (!trim && peer_device->connection->peer_integrity_tfm) {
 		dgs = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
 		/*
 		 * FIXME: Receive the incoming digest into the receive buffer
@@ -1514,9 +1547,15 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 		data_size -= dgs;
 	}
 
+	if (trim) {
+		D_ASSERT(peer_device, data_size == 0);
+		data_size = be32_to_cpu(trim->size);
+	}
+
 	if (!expect(IS_ALIGNED(data_size, 512)))
 		return NULL;
-	if (!expect(data_size <= DRBD_MAX_BIO_SIZE))
+	/* prepare for larger trim requests. */
+	if (!trim && !expect(data_size <= DRBD_MAX_BIO_SIZE))
 		return NULL;
 
 	/* even though we trust out peer,
@@ -1532,11 +1571,11 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
 	 * "criss-cross" setup, that might cause write-out on some other DRBD,
 	 * which in turn might block on the other node at this very place.  */
-	peer_req = drbd_alloc_peer_req(peer_device, id, sector, data_size, GFP_NOIO);
+	peer_req = drbd_alloc_peer_req(peer_device, id, sector, data_size, trim == NULL, GFP_NOIO);
 	if (!peer_req)
 		return NULL;
 
-	if (!data_size)
+	if (trim)
 		return peer_req;
 
 	ds = data_size;
@@ -1676,12 +1715,12 @@ static int e_end_resync_block(struct drbd_work *w, int unused)
 }
 
 static int recv_resync_read(struct drbd_peer_device *peer_device, sector_t sector,
-			    int data_size) __releases(local)
+			    struct packet_info *pi) __releases(local)
 {
 	struct drbd_device *device = peer_device->device;
 	struct drbd_peer_request *peer_req;
 
-	peer_req = read_in_block(peer_device, ID_SYNCER, sector, data_size);
+	peer_req = read_in_block(peer_device, ID_SYNCER, sector, pi);
 	if (!peer_req)
 		goto fail;
 
@@ -1697,7 +1736,7 @@ static int recv_resync_read(struct drbd_peer_device *peer_device, sector_t secto
 	list_add(&peer_req->w.list, &device->sync_ee);
 	spin_unlock_irq(&device->resource->req_lock);
 
-	atomic_add(data_size >> 9, &device->rs_sect_ev);
+	atomic_add(pi->size >> 9, &device->rs_sect_ev);
 	if (drbd_submit_peer_request(device, peer_req, WRITE, DRBD_FAULT_RS_WR) == 0)
 		return 0;
 
@@ -1785,7 +1824,7 @@ static int receive_RSDataReply(struct drbd_connection *connection, struct packet
 		/* data is submitted to disk within recv_resync_read.
 		 * corresponding put_ldev done below on error,
 		 * or in drbd_peer_request_endio. */
-		err = recv_resync_read(peer_device, sector, pi->size);
+		err = recv_resync_read(peer_device, sector, pi);
 	} else {
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_err(device, "Can not write resync data to local disk.\n");
@@ -2196,7 +2235,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	 */
 
 	sector = be64_to_cpu(p->sector);
-	peer_req = read_in_block(peer_device, p->block_id, sector, pi->size);
+	peer_req = read_in_block(peer_device, p->block_id, sector, pi);
 	if (!peer_req) {
 		put_ldev(device);
 		return -EIO;
@@ -2206,7 +2245,15 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 
 	dp_flags = be32_to_cpu(p->dp_flags);
 	rw |= wire_flags_to_bio(dp_flags);
-	if (peer_req->pages == NULL) {
+	if (pi->cmd == P_TRIM) {
+		struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
+		peer_req->flags |= EE_IS_TRIM;
+		if (!blk_queue_discard(q))
+			peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+		D_ASSERT(peer_device, peer_req->i.size > 0);
+		D_ASSERT(peer_device, rw & REQ_DISCARD);
+		D_ASSERT(peer_device, peer_req->pages == NULL);
+	} else if (peer_req->pages == NULL) {
 		D_ASSERT(device, peer_req->i.size == 0);
 		D_ASSERT(device, dp_flags & DP_FLUSH);
 	}
@@ -2242,7 +2289,12 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 		update_peer_seq(peer_device, peer_seq);
 		spin_lock_irq(&device->resource->req_lock);
 	}
-	list_add(&peer_req->w.list, &device->active_ee);
+	/* if we use the zeroout fallback code, we process synchronously
+	 * and we wait for all pending requests, respectively wait for
+	 * active_ee to become empty in drbd_submit_peer_request();
+	 * better not add ourselves here. */
+	if ((peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) == 0)
+		list_add(&peer_req->w.list, &device->active_ee);
 	spin_unlock_irq(&device->resource->req_lock);
 
 	if (device->state.conn == C_SYNC_TARGET)
@@ -2313,39 +2365,45 @@ out_interrupted:
  * The current sync rate used here uses only the most recent two step marks,
  * to have a short time average so we can react faster.
  */
-int drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector)
+bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector)
 {
-	struct gendisk *disk = device->ldev->backing_bdev->bd_contains->bd_disk;
-	unsigned long db, dt, dbdt;
 	struct lc_element *tmp;
-	int curr_events;
-	int throttle = 0;
-	unsigned int c_min_rate;
-
-	rcu_read_lock();
-	c_min_rate = rcu_dereference(device->ldev->disk_conf)->c_min_rate;
-	rcu_read_unlock();
+	bool throttle = true;
 
-	/* feature disabled? */
-	if (c_min_rate == 0)
-		return 0;
+	if (!drbd_rs_c_min_rate_throttle(device))
+		return false;
 
 	spin_lock_irq(&device->al_lock);
 	tmp = lc_find(device->resync, BM_SECT_TO_EXT(sector));
 	if (tmp) {
 		struct bm_extent *bm_ext = lc_entry(tmp, struct bm_extent, lce);
-		if (test_bit(BME_PRIORITY, &bm_ext->flags)) {
-			spin_unlock_irq(&device->al_lock);
-			return 0;
-		}
+		if (test_bit(BME_PRIORITY, &bm_ext->flags))
+			throttle = false;
 		/* Do not slow down if app IO is already waiting for this extent */
 	}
 	spin_unlock_irq(&device->al_lock);
 
+	return throttle;
+}
+
+bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
+{
+	struct gendisk *disk = device->ldev->backing_bdev->bd_contains->bd_disk;
+	unsigned long db, dt, dbdt;
+	unsigned int c_min_rate;
+	int curr_events;
+
+	rcu_read_lock();
+	c_min_rate = rcu_dereference(device->ldev->disk_conf)->c_min_rate;
+	rcu_read_unlock();
+
+	/* feature disabled? */
+	if (c_min_rate == 0)
+		return false;
+
 	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
 		      (int)part_stat_read(&disk->part0, sectors[1]) -
 			atomic_read(&device->rs_sect_ev);
-
 	if (!device->rs_last_events || curr_events - device->rs_last_events > 64) {
 		unsigned long rs_left;
 		int i;
@@ -2368,12 +2426,11 @@ int drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector)
 		dbdt = Bit2KB(db/dt);
 
 		if (dbdt > c_min_rate)
-			throttle = 1;
+			return true;
 	}
-	return throttle;
+	return false;
 }
 
-
 static int receive_DataRequest(struct drbd_connection *connection, struct packet_info *pi)
 {
 	struct drbd_peer_device *peer_device;
@@ -2436,7 +2493,8 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
 	 * "criss-cross" setup, that might cause write-out on some other DRBD,
 	 * which in turn might block on the other node at this very place.  */
-	peer_req = drbd_alloc_peer_req(peer_device, p->block_id, sector, size, GFP_NOIO);
+	peer_req = drbd_alloc_peer_req(peer_device, p->block_id, sector, size,
+			true /* has real payload */, GFP_NOIO);
 	if (!peer_req) {
 		put_ldev(device);
 		return -ENOMEM;
@@ -3648,6 +3706,13 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		put_ldev(device);
 	}
 
+	device->peer_max_bio_size = be32_to_cpu(p->max_bio_size);
+	drbd_reconsider_max_bio_size(device);
+	/* Leave drbd_reconsider_max_bio_size() before drbd_determine_dev_size().
+	   In case we cleared the QUEUE_FLAG_DISCARD from our queue in
+	   drbd_reconsider_max_bio_size(), we can be sure that after
+	   drbd_determine_dev_size() no REQ_DISCARDs are in the queue. */
+
 	ddsf = be16_to_cpu(p->dds_flags);
 	if (get_ldev(device)) {
 		dd = drbd_determine_dev_size(device, ddsf, NULL);
@@ -3660,9 +3725,6 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		drbd_set_my_capacity(device, p_size);
 	}
 
-	device->peer_max_bio_size = be32_to_cpu(p->max_bio_size);
-	drbd_reconsider_max_bio_size(device);
-
 	if (get_ldev(device)) {
 		if (device->ldev->known_size != drbd_get_capacity(device->ldev->backing_bdev)) {
 			device->ldev->known_size = drbd_get_capacity(device->ldev->backing_bdev);
@@ -4423,6 +4485,7 @@ static struct data_cmd drbd_cmd_handler[] = {
 	[P_OUT_OF_SYNC]     = { 0, sizeof(struct p_block_desc), receive_out_of_sync },
 	[P_CONN_ST_CHG_REQ] = { 0, sizeof(struct p_req_state), receive_req_conn_state },
 	[P_PROTOCOL_UPDATE] = { 1, sizeof(struct p_protocol), receive_protocol },
+	[P_TRIM]	    = { 0, sizeof(struct p_trim), receive_Data },
 };
 
 static void drbdd(struct drbd_connection *connection)
@@ -4630,6 +4693,7 @@ static int drbd_send_features(struct drbd_connection *connection)
 	memset(p, 0, sizeof(*p));
 	p->protocol_min = cpu_to_be32(PRO_VERSION_MIN);
 	p->protocol_max = cpu_to_be32(PRO_VERSION_MAX);
+	p->feature_flags = cpu_to_be32(PRO_FEATURES);
 	return conn_send_command(connection, sock, P_CONNECTION_FEATURES, sizeof(*p), NULL, 0);
 }
 
@@ -4683,10 +4747,14 @@ static int drbd_do_features(struct drbd_connection *connection)
 		goto incompat;
 
 	connection->agreed_pro_version = min_t(int, PRO_VERSION_MAX, p->protocol_max);
+	connection->agreed_features = PRO_FEATURES & be32_to_cpu(p->feature_flags);
 
 	drbd_info(connection, "Handshake successful: "
 	     "Agreed network protocol version %d\n", connection->agreed_pro_version);
 
+	drbd_info(connection, "Agreed to%ssupport TRIM on protocol level\n",
+		  connection->agreed_features & FF_TRIM ? " " : " not ");
+
 	return 1;
 
  incompat:
@@ -4778,6 +4846,12 @@ static int drbd_do_auth(struct drbd_connection *connection)
 		goto fail;
 	}
 
+	if (pi.size < CHALLENGE_LEN) {
+		drbd_err(connection, "AuthChallenge payload too small.\n");
+		rv = -1;
+		goto fail;
+	}
+
 	peers_ch = kmalloc(pi.size, GFP_NOIO);
 	if (peers_ch == NULL) {
 		drbd_err(connection, "kmalloc of peers_ch failed\n");
@@ -4791,6 +4865,12 @@ static int drbd_do_auth(struct drbd_connection *connection)
 		goto fail;
 	}
 
+	if (!memcmp(my_challenge, peers_ch, CHALLENGE_LEN)) {
+		drbd_err(connection, "Peer presented the same challenge!\n");
+		rv = -1;
+		goto fail;
+	}
+
 	resp_size = crypto_hash_digestsize(connection->cram_hmac_tfm);
 	response = kmalloc(resp_size, GFP_NOIO);
 	if (response == NULL) {
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3779c8d2875b..09803d0d5207 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -522,6 +522,13 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		mod_rq_state(req, m, RQ_LOCAL_PENDING, RQ_LOCAL_COMPLETED);
 		break;
 
+	case DISCARD_COMPLETED_NOTSUPP:
+	case DISCARD_COMPLETED_WITH_ERROR:
+		/* I'd rather not detach from local disk just because it
+		 * failed a REQ_DISCARD. */
+		mod_rq_state(req, m, RQ_LOCAL_PENDING, RQ_LOCAL_COMPLETED);
+		break;
+
 	case QUEUE_FOR_NET_READ:
 		/* READ or READA, and
 		 * no local disk,
@@ -1235,6 +1242,7 @@ void do_submit(struct work_struct *ws)
 		if (list_empty(&incoming))
 			break;
 
+skip_fast_path:
 		wait_event(device->al_wait, prepare_al_transaction_nonblock(device, &incoming, &pending));
 		/* Maybe more was queued, while we prepared the transaction?
 		 * Try to stuff them into this transaction as well.
@@ -1273,6 +1281,25 @@ void do_submit(struct work_struct *ws)
 			list_del_init(&req->tl_requests);
 			drbd_send_and_submit(device, req);
 		}
+
+		/* If all currently hot activity log extents are kept busy by
+		 * incoming requests, we still must not totally starve new
+		 * requests to cold extents. In that case, prepare one request
+		 * in blocking mode. */
+		list_for_each_entry_safe(req, tmp, &incoming, tl_requests) {
+			list_del_init(&req->tl_requests);
+			req->rq_state |= RQ_IN_ACT_LOG;
+			if (!drbd_al_begin_io_prepare(device, &req->i)) {
+				/* Corresponding extent was hot after all? */
+				drbd_send_and_submit(device, req);
+			} else {
+				/* Found a request to a cold extent.
+				 * Put on "pending" list,
+				 * and try to cumulate with more. */
+				list_add(&req->tl_requests, &pending);
+				goto skip_fast_path;
+			}
+		}
 	}
 }
 
@@ -1326,23 +1353,35 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 	return limit;
 }
 
-static struct drbd_request *find_oldest_request(struct drbd_connection *connection)
+static void find_oldest_requests(
+		struct drbd_connection *connection,
+		struct drbd_device *device,
+		struct drbd_request **oldest_req_waiting_for_peer,
+		struct drbd_request **oldest_req_waiting_for_disk)
 {
-	/* Walk the transfer log,
-	 * and find the oldest not yet completed request */
 	struct drbd_request *r;
+	*oldest_req_waiting_for_peer = NULL;
+	*oldest_req_waiting_for_disk = NULL;
 	list_for_each_entry(r, &connection->transfer_log, tl_requests) {
-		if (atomic_read(&r->completion_ref))
-			return r;
+		const unsigned s = r->rq_state;
+		if (!*oldest_req_waiting_for_peer
+		&& ((s & RQ_NET_MASK) && !(s & RQ_NET_DONE)))
+			*oldest_req_waiting_for_peer = r;
+
+		if (!*oldest_req_waiting_for_disk
+		&& (s & RQ_LOCAL_PENDING) && r->device == device)
+			*oldest_req_waiting_for_disk = r;
+
+		if (*oldest_req_waiting_for_peer && *oldest_req_waiting_for_disk)
+			break;
 	}
-	return NULL;
 }
 
 void request_timer_fn(unsigned long data)
 {
 	struct drbd_device *device = (struct drbd_device *) data;
 	struct drbd_connection *connection = first_peer_device(device)->connection;
-	struct drbd_request *req; /* oldest request */
+	struct drbd_request *req_disk, *req_peer; /* oldest request */
 	struct net_conf *nc;
 	unsigned long ent = 0, dt = 0, et, nt; /* effective timeout = ko_count * timeout */
 	unsigned long now;
@@ -1366,8 +1405,8 @@ void request_timer_fn(unsigned long data)
 	now = jiffies;
 
 	spin_lock_irq(&device->resource->req_lock);
-	req = find_oldest_request(connection);
-	if (!req) {
+	find_oldest_requests(connection, device, &req_peer, &req_disk);
+	if (req_peer == NULL && req_disk == NULL) {
 		spin_unlock_irq(&device->resource->req_lock);
 		mod_timer(&device->request_timer, now + et);
 		return;
@@ -1389,19 +1428,26 @@ void request_timer_fn(unsigned long data)
 	 * ~198 days with 250 HZ, we have a window where the timeout would need
 	 * to expire twice (worst case) to become effective. Good enough.
 	 */
-	if (ent && req->rq_state & RQ_NET_PENDING &&
-		 time_after(now, req->start_time + ent) &&
+	if (ent && req_peer &&
+		 time_after(now, req_peer->start_time + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
 		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
 	}
-	if (dt && req->rq_state & RQ_LOCAL_PENDING && req->device == device &&
-		 time_after(now, req->start_time + dt) &&
+	if (dt && req_disk &&
+		 time_after(now, req_disk->start_time + dt) &&
 		!time_in_range(now, device->last_reattach_jif, device->last_reattach_jif + dt)) {
 		drbd_warn(device, "Local backing device failed to meet the disk-timeout\n");
 		__drbd_chk_io_error(device, DRBD_FORCE_DETACH);
 	}
-	nt = (time_after(now, req->start_time + et) ? now : req->start_time) + et;
+
+	/* Reschedule timer for the nearest not already expired timeout.
+	 * Fallback to now + min(effective network timeout, disk timeout). */
+	ent = (ent && req_peer && time_before(now, req_peer->start_time + ent))
+		? req_peer->start_time + ent : now + et;
+	dt = (dt && req_disk && time_before(now, req_disk->start_time + dt))
+		? req_disk->start_time + dt : now + et;
+	nt = time_before(ent, dt) ? ent : dt;
 	spin_unlock_irq(&connection->resource->req_lock);
 	mod_timer(&device->request_timer, nt);
 }
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index c684c963538e..8566cd5866b4 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -30,7 +30,6 @@
 #include <linux/slab.h>
 #include <linux/drbd.h>
 #include "drbd_int.h"
-#include "drbd_wrappers.h"
 
 /* The request callbacks will be called in irq context by the IDE drivers,
    and in Softirqs/Tasklets/BH context by the SCSI drivers,
@@ -111,11 +110,14 @@ enum drbd_req_event {
 	BARRIER_ACKED, /* in protocol A and B */
 	DATA_RECEIVED, /* (remote read) */
 
+	COMPLETED_OK,
 	READ_COMPLETED_WITH_ERROR,
 	READ_AHEAD_COMPLETED_WITH_ERROR,
 	WRITE_COMPLETED_WITH_ERROR,
+	DISCARD_COMPLETED_NOTSUPP,
+	DISCARD_COMPLETED_WITH_ERROR,
+
 	ABORT_DISK_IO,
-	COMPLETED_OK,
 	RESEND,
 	FAIL_FROZEN_DISK_IO,
 	RESTART_FROZEN_DISK_IO,
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 1a84345a3868..a5d8aae00e04 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -54,8 +54,8 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os,
 static enum drbd_state_rv is_valid_state(struct drbd_device *, union drbd_state);
 static enum drbd_state_rv is_valid_soft_transition(union drbd_state, union drbd_state, struct drbd_connection *);
 static enum drbd_state_rv is_valid_transition(union drbd_state os, union drbd_state ns);
-static union drbd_state sanitize_state(struct drbd_device *device, union drbd_state ns,
-				       enum sanitize_state_warnings *warn);
+static union drbd_state sanitize_state(struct drbd_device *device, union drbd_state os,
+				       union drbd_state ns, enum sanitize_state_warnings *warn);
 
 static inline bool is_susp(union drbd_state s)
 {
@@ -287,7 +287,7 @@ _req_st_cond(struct drbd_device *device, union drbd_state mask,
 
 	spin_lock_irqsave(&device->resource->req_lock, flags);
 	os = drbd_read_state(device);
-	ns = sanitize_state(device, apply_mask_val(os, mask, val), NULL);
+	ns = sanitize_state(device, os, apply_mask_val(os, mask, val), NULL);
 	rv = is_valid_transition(os, ns);
 	if (rv >= SS_SUCCESS)
 		rv = SS_UNKNOWN_ERROR;  /* cont waiting, otherwise fail. */
@@ -333,7 +333,7 @@ drbd_req_state(struct drbd_device *device, union drbd_state mask,
 
 	spin_lock_irqsave(&device->resource->req_lock, flags);
 	os = drbd_read_state(device);
-	ns = sanitize_state(device, apply_mask_val(os, mask, val), NULL);
+	ns = sanitize_state(device, os, apply_mask_val(os, mask, val), NULL);
 	rv = is_valid_transition(os, ns);
 	if (rv < SS_SUCCESS) {
 		spin_unlock_irqrestore(&device->resource->req_lock, flags);
@@ -740,8 +740,8 @@ static void print_sanitize_warnings(struct drbd_device *device, enum sanitize_st
  * When we loose connection, we have to set the state of the peers disk (pdsk)
  * to D_UNKNOWN. This rule and many more along those lines are in this function.
  */
-static union drbd_state sanitize_state(struct drbd_device *device, union drbd_state ns,
-				       enum sanitize_state_warnings *warn)
+static union drbd_state sanitize_state(struct drbd_device *device, union drbd_state os,
+				       union drbd_state ns, enum sanitize_state_warnings *warn)
 {
 	enum drbd_fencing_p fp;
 	enum drbd_disk_state disk_min, disk_max, pdsk_min, pdsk_max;
@@ -882,11 +882,13 @@ static union drbd_state sanitize_state(struct drbd_device *device, union drbd_st
 	}
 
 	if (fp == FP_STONITH &&
-	    (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED))
+	    (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED) &&
+	    !(os.role == R_PRIMARY && os.conn < C_CONNECTED && os.pdsk > D_OUTDATED))
 		ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */
 
 	if (device->resource->res_opts.on_no_data == OND_SUSPEND_IO &&
-	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE))
+	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE) &&
+	    !(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE))
 		ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */
 
 	if (ns.aftr_isp || ns.peer_isp || ns.user_isp) {
@@ -958,7 +960,7 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 	os = drbd_read_state(device);
 
-	ns = sanitize_state(device, ns, &ssw);
+	ns = sanitize_state(device, os, ns, &ssw);
 	if (ns.i == os.i)
 		return SS_NOTHING_TO_DO;
 
@@ -1656,7 +1658,7 @@ conn_is_valid_transition(struct drbd_connection *connection, union drbd_state ma
 	idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 		struct drbd_device *device = peer_device->device;
 		os = drbd_read_state(device);
-		ns = sanitize_state(device, apply_mask_val(os, mask, val), NULL);
+		ns = sanitize_state(device, os, apply_mask_val(os, mask, val), NULL);
 
 		if (flags & CS_IGN_OUTD_FAIL && ns.disk == D_OUTDATED && os.disk < D_OUTDATED)
 			ns.disk = os.disk;
@@ -1718,7 +1720,7 @@ conn_set_state(struct drbd_connection *connection, union drbd_state mask, union
 		number_of_volumes++;
 		os = drbd_read_state(device);
 		ns = apply_mask_val(os, mask, val);
-		ns = sanitize_state(device, ns, NULL);
+		ns = sanitize_state(device, os, ns, NULL);
 
 		if (flags & CS_IGN_OUTD_FAIL && ns.disk == D_OUTDATED && os.disk < D_OUTDATED)
 			ns.disk = os.disk;
@@ -1763,19 +1765,19 @@ conn_set_state(struct drbd_connection *connection, union drbd_state mask, union
 static enum drbd_state_rv
 _conn_rq_cond(struct drbd_connection *connection, union drbd_state mask, union drbd_state val)
 {
-	enum drbd_state_rv rv;
+	enum drbd_state_rv err, rv = SS_UNKNOWN_ERROR; /* continue waiting */;
 
 	if (test_and_clear_bit(CONN_WD_ST_CHG_OKAY, &connection->flags))
-		return SS_CW_SUCCESS;
+		rv = SS_CW_SUCCESS;
 
 	if (test_and_clear_bit(CONN_WD_ST_CHG_FAIL, &connection->flags))
-		return SS_CW_FAILED_BY_PEER;
+		rv = SS_CW_FAILED_BY_PEER;
 
-	rv = conn_is_valid_transition(connection, mask, val, 0);
-	if (rv == SS_SUCCESS && connection->cstate == C_WF_REPORT_PARAMS)
-		rv = SS_UNKNOWN_ERROR; /* continue waiting */
+	err = conn_is_valid_transition(connection, mask, val, 0);
+	if (err == SS_SUCCESS && connection->cstate == C_WF_REPORT_PARAMS)
+		return rv;
 
-	return rv;
+	return err;
 }
 
 enum drbd_state_rv
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 2c4ce42c3657..d8f57b6305cd 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -118,7 +118,7 @@ static void drbd_endio_read_sec_final(struct drbd_peer_request *peer_req) __rele
 
 /* writes on behalf of the partner, or resync writes,
  * "submitted" by the receiver, final stage.  */
-static void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(local)
+void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(local)
 {
 	unsigned long flags = 0;
 	struct drbd_peer_device *peer_device = peer_req->peer_device;
@@ -150,7 +150,9 @@ static void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __rel
 
 	do_wake = list_empty(block_id == ID_SYNCER ? &device->sync_ee : &device->active_ee);
 
-	if (test_bit(__EE_WAS_ERROR, &peer_req->flags))
+	/* FIXME do we want to detach for failed REQ_DISCARD?
+	 * ((peer_req->flags & (EE_WAS_ERROR|EE_IS_TRIM)) == EE_WAS_ERROR) */
+	if (peer_req->flags & EE_WAS_ERROR)
 		__drbd_chk_io_error(device, DRBD_WRITE_ERROR);
 	spin_unlock_irqrestore(&device->resource->req_lock, flags);
 
@@ -176,10 +178,12 @@ void drbd_peer_request_endio(struct bio *bio, int error)
 	struct drbd_device *device = peer_req->peer_device->device;
 	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 	int is_write = bio_data_dir(bio) == WRITE;
+	int is_discard = !!(bio->bi_rw & REQ_DISCARD);
 
 	if (error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
-				is_write ? "write" : "read", error,
+				is_write ? (is_discard ? "discard" : "write")
+					: "read", error,
 				(unsigned long long)peer_req->i.sector);
 	if (!error && !uptodate) {
 		if (__ratelimit(&drbd_ratelimit_state))
@@ -263,7 +267,12 @@ void drbd_request_endio(struct bio *bio, int error)
 
 	/* to avoid recursion in __req_mod */
 	if (unlikely(error)) {
-		what = (bio_data_dir(bio) == WRITE)
+		if (bio->bi_rw & REQ_DISCARD)
+			what = (error == -EOPNOTSUPP)
+				? DISCARD_COMPLETED_NOTSUPP
+				: DISCARD_COMPLETED_WITH_ERROR;
+		else
+			what = (bio_data_dir(bio) == WRITE)
 			? WRITE_COMPLETED_WITH_ERROR
 			: (bio_rw(bio) == READ)
 			  ? READ_COMPLETED_WITH_ERROR
@@ -395,7 +404,7 @@ static int read_for_csum(struct drbd_peer_device *peer_device, sector_t sector,
 	/* GFP_TRY, because if there is no memory available right now, this may
 	 * be rescheduled for later. It is "only" background resync, after all. */
 	peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER /* unused */, sector,
-				       size, GFP_TRY);
+				       size, true /* has real payload */, GFP_TRY);
 	if (!peer_req)
 		goto defer;
 
@@ -492,10 +501,9 @@ struct fifo_buffer *fifo_alloc(int fifo_size)
 	return fb;
 }
 
-static int drbd_rs_controller(struct drbd_device *device)
+static int drbd_rs_controller(struct drbd_device *device, unsigned int sect_in)
 {
 	struct disk_conf *dc;
-	unsigned int sect_in;  /* Number of sectors that came in since the last turn */
 	unsigned int want;     /* The number of sectors we want in the proxy */
 	int req_sect; /* Number of sectors to request in this turn */
 	int correction; /* Number of sectors more we need in the proxy*/
@@ -505,9 +513,6 @@ static int drbd_rs_controller(struct drbd_device *device)
 	int max_sect;
 	struct fifo_buffer *plan;
 
-	sect_in = atomic_xchg(&device->rs_sect_in, 0); /* Number of sectors that came in */
-	device->rs_in_flight -= sect_in;
-
 	dc = rcu_dereference(device->ldev->disk_conf);
 	plan = rcu_dereference(device->rs_plan_s);
 
@@ -550,11 +555,16 @@ static int drbd_rs_controller(struct drbd_device *device)
 
 static int drbd_rs_number_requests(struct drbd_device *device)
 {
-	int number;
+	unsigned int sect_in;  /* Number of sectors that came in since the last turn */
+	int number, mxb;
+
+	sect_in = atomic_xchg(&device->rs_sect_in, 0);
+	device->rs_in_flight -= sect_in;
 
 	rcu_read_lock();
+	mxb = drbd_get_max_buffers(device) / 2;
 	if (rcu_dereference(device->rs_plan_s)->size) {
-		number = drbd_rs_controller(device) >> (BM_BLOCK_SHIFT - 9);
+		number = drbd_rs_controller(device, sect_in) >> (BM_BLOCK_SHIFT - 9);
 		device->c_sync_rate = number * HZ * (BM_BLOCK_SIZE / 1024) / SLEEP_TIME;
 	} else {
 		device->c_sync_rate = rcu_dereference(device->ldev->disk_conf)->resync_rate;
@@ -562,8 +572,14 @@ static int drbd_rs_number_requests(struct drbd_device *device)
 	}
 	rcu_read_unlock();
 
-	/* ignore the amount of pending requests, the resync controller should
-	 * throttle down to incoming reply rate soon enough anyways. */
+	/* Don't have more than "max-buffers"/2 in-flight.
+	 * Otherwise we may cause the remote site to stall on drbd_alloc_pages(),
+	 * potentially causing a distributed deadlock on congestion during
+	 * online-verify or (checksum-based) resync, if max-buffers,
+	 * socket buffer sizes and resync rate settings are mis-configured. */
+	if (mxb - device->rs_in_flight < number)
+		number = mxb - device->rs_in_flight;
+
 	return number;
 }
 
@@ -597,7 +613,7 @@ static int make_resync_request(struct drbd_device *device, int cancel)
 
 	max_bio_size = queue_max_hw_sectors(device->rq_queue) << 9;
 	number = drbd_rs_number_requests(device);
-	if (number == 0)
+	if (number <= 0)
 		goto requeue;
 
 	for (i = 0; i < number; i++) {
@@ -647,7 +663,7 @@ next_sector:
 		 */
 		align = 1;
 		rollback_i = i;
-		for (;;) {
+		while (i < number) {
 			if (size + BM_BLOCK_SIZE > max_bio_size)
 				break;
 
@@ -1670,11 +1686,15 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 	}
 	clear_bit(B_RS_H_DONE, &device->flags);
 
-	write_lock_irq(&global_state_lock);
+	/* req_lock: serialize with drbd_send_and_submit() and others
+	 * global_state_lock: for stable sync-after dependencies */
+	spin_lock_irq(&device->resource->req_lock);
+	write_lock(&global_state_lock);
 	/* Did some connection breakage or IO error race with us? */
 	if (device->state.conn < C_CONNECTED
 	|| !get_ldev_if_state(device, D_NEGOTIATING)) {
-		write_unlock_irq(&global_state_lock);
+		write_unlock(&global_state_lock);
+		spin_unlock_irq(&device->resource->req_lock);
 		mutex_unlock(device->state_mutex);
 		return;
 	}
@@ -1714,7 +1734,8 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		}
 		_drbd_pause_after(device);
 	}
-	write_unlock_irq(&global_state_lock);
+	write_unlock(&global_state_lock);
+	spin_unlock_irq(&device->resource->req_lock);
 
 	if (r == SS_SUCCESS) {
 		/* reset rs_last_bcast when a resync or verify is started,
@@ -1778,34 +1799,6 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 	mutex_unlock(device->state_mutex);
 }
 
-/* If the resource already closed the current epoch, but we did not
- * (because we have not yet seen new requests), we should send the
- * corresponding barrier now.  Must be checked within the same spinlock
- * that is used to check for new requests. */
-static bool need_to_send_barrier(struct drbd_connection *connection)
-{
-	if (!connection->send.seen_any_write_yet)
-		return false;
-
-	/* Skip barriers that do not contain any writes.
-	 * This may happen during AHEAD mode. */
-	if (!connection->send.current_epoch_writes)
-		return false;
-
-	/* ->req_lock is held when requests are queued on
-	 * connection->sender_work, and put into ->transfer_log.
-	 * It is also held when ->current_tle_nr is increased.
-	 * So either there are already new requests queued,
-	 * and corresponding barriers will be send there.
-	 * Or nothing new is queued yet, so the difference will be 1.
-	 */
-	if (atomic_read(&connection->current_tle_nr) !=
-	    connection->send.current_epoch_nr + 1)
-		return false;
-
-	return true;
-}
-
 static bool dequeue_work_batch(struct drbd_work_queue *queue, struct list_head *work_list)
 {
 	spin_lock_irq(&queue->q_lock);
@@ -1864,12 +1857,22 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *
 			spin_unlock_irq(&connection->resource->req_lock);
 			break;
 		}
-		send_barrier = need_to_send_barrier(connection);
+
+		/* We found nothing new to do, no to-be-communicated request,
+		 * no other work item.  We may still need to close the last
+		 * epoch.  Next incoming request epoch will be connection ->
+		 * current transfer log epoch number.  If that is different
+		 * from the epoch of the last request we communicated, it is
+		 * safe to send the epoch separating barrier now.
+		 */
+		send_barrier =
+			atomic_read(&connection->current_tle_nr) !=
+			connection->send.current_epoch_nr;
 		spin_unlock_irq(&connection->resource->req_lock);
-		if (send_barrier) {
-			drbd_send_barrier(connection);
-			connection->send.current_epoch_nr++;
-		}
+
+		if (send_barrier)
+			maybe_send_barrier(connection,
+					connection->send.current_epoch_nr + 1);
 		schedule();
 		/* may be woken up for other things but new work, too,
 		 * e.g. if the current epoch got closed.
diff --git a/drivers/block/drbd/drbd_wrappers.h b/drivers/block/drbd/drbd_wrappers.h
deleted file mode 100644
index 3db9ebaf64f6..000000000000
--- a/drivers/block/drbd/drbd_wrappers.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef _DRBD_WRAPPERS_H
-#define _DRBD_WRAPPERS_H
-
-#include <linux/ctype.h>
-#include <linux/mm.h>
-#include "drbd_int.h"
-
-/* see get_sb_bdev and bd_claim */
-extern char *drbd_sec_holder;
-
-/* sets the number of 512 byte sectors of our virtual device */
-static inline void drbd_set_my_capacity(struct drbd_device *device,
-					sector_t size)
-{
-	/* set_capacity(device->this_bdev->bd_disk, size); */
-	set_capacity(device->vdisk, size);
-	device->this_bdev->bd_inode->i_size = (loff_t)size << 9;
-}
-
-#define drbd_bio_uptodate(bio) bio_flagged(bio, BIO_UPTODATE)
-
-/* bi_end_io handlers */
-extern void drbd_md_io_complete(struct bio *bio, int error);
-extern void drbd_peer_request_endio(struct bio *bio, int error);
-extern void drbd_request_endio(struct bio *bio, int error);
-
-/*
- * used to submit our private bio
- */
-static inline void drbd_generic_make_request(struct drbd_device *device,
-					     int fault_type, struct bio *bio)
-{
-	__release(local);
-	if (!bio->bi_bdev) {
-		printk(KERN_ERR "drbd%d: drbd_generic_make_request: "
-				"bio->bi_bdev == NULL\n",
-		       device_to_minor(device));
-		dump_stack();
-		bio_endio(bio, -ENODEV);
-		return;
-	}
-
-	if (drbd_insert_fault(device, fault_type))
-		bio_endio(bio, -EIO);
-	else
-		generic_make_request(bio);
-}
-
-#ifndef __CHECKER__
-# undef __cond_lock
-# define __cond_lock(x,c) (c)
-#endif
-
-#endif
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index dc3a41c82b38..677db049f55a 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3812,7 +3812,7 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive)
 	bio.bi_iter.bi_size = size;
 	bio.bi_bdev = bdev;
 	bio.bi_iter.bi_sector = 0;
-	bio.bi_flags = (1 << BIO_QUIET);
+	bio.bi_flags |= (1 << BIO_QUIET);
 	bio.bi_private = &cbdata;
 	bio.bi_end_io = floppy_rb0_cb;
 
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 59c5abe32f06..abc858b3528b 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/bio.h>
 #include <linux/dma-mapping.h>
 #include <linux/idr.h>
@@ -173,60 +174,34 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 	return false; /* device present */
 }
 
-/*
- * Obtain an empty command slot.
- *
- * This function needs to be reentrant since it could be called
- * at the same time on multiple CPUs. The allocation of the
- * command slot must be atomic.
- *
- * @port Pointer to the port data structure.
- *
- * return value
- *	>= 0	Index of command slot obtained.
- *	-1	No command slots available.
- */
-static int get_slot(struct mtip_port *port)
+static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
-	int slot, i;
-	unsigned int num_command_slots = port->dd->slot_groups * 32;
+	struct request *rq;
 
-	/*
-	 * Try 10 times, because there is a small race here.
-	 *  that's ok, because it's still cheaper than a lock.
-	 *
-	 * Race: Since this section is not protected by lock, same bit
-	 * could be chosen by different process contexts running in
-	 * different processor. So instead of costly lock, we are going
-	 * with loop.
-	 */
-	for (i = 0; i < 10; i++) {
-		slot = find_next_zero_bit(port->allocated,
-					 num_command_slots, 1);
-		if ((slot < num_command_slots) &&
-		    (!test_and_set_bit(slot, port->allocated)))
-			return slot;
-	}
-	dev_warn(&port->dd->pdev->dev, "Failed to get a tag.\n");
+	rq = blk_mq_alloc_request(dd->queue, 0, __GFP_WAIT, true);
+	return blk_mq_rq_to_pdu(rq);
+}
 
-	mtip_check_surprise_removal(port->dd->pdev);
-	return -1;
+static void mtip_put_int_command(struct driver_data *dd, struct mtip_cmd *cmd)
+{
+	blk_put_request(blk_mq_rq_from_pdu(cmd));
 }
 
 /*
- * Release a command slot.
- *
- * @port Pointer to the port data structure.
- * @tag  Tag of command to release
- *
- * return value
- *	None
+ * Once we add support for one hctx per mtip group, this will change a bit
  */
-static inline void release_slot(struct mtip_port *port, int tag)
+static struct request *mtip_rq_from_tag(struct driver_data *dd,
+					unsigned int tag)
+{
+	return blk_mq_tag_to_rq(dd->queue->queue_hw_ctx[0], tag);
+}
+
+static struct mtip_cmd *mtip_cmd_from_tag(struct driver_data *dd,
+					  unsigned int tag)
 {
-	smp_mb__before_clear_bit();
-	clear_bit(tag, port->allocated);
-	smp_mb__after_clear_bit();
+	struct request *rq = mtip_rq_from_tag(dd, tag);
+
+	return blk_mq_rq_to_pdu(rq);
 }
 
 /*
@@ -248,93 +223,28 @@ static inline void release_slot(struct mtip_port *port, int tag)
  *	None
  */
 static void mtip_async_complete(struct mtip_port *port,
-				int tag,
-				void *data,
-				int status)
+				int tag, struct mtip_cmd *cmd, int status)
 {
-	struct mtip_cmd *cmd;
-	struct driver_data *dd = data;
-	int unaligned, cb_status = status ? -EIO : 0;
-	void (*func)(void *, int);
+	struct driver_data *dd = port->dd;
+	struct request *rq;
 
 	if (unlikely(!dd) || unlikely(!port))
 		return;
 
-	cmd = &port->commands[tag];
-
 	if (unlikely(status == PORT_IRQ_TF_ERR)) {
 		dev_warn(&port->dd->pdev->dev,
 			"Command tag %d failed due to TFE\n", tag);
 	}
 
-	/* Clear the active flag */
-	atomic_set(&port->commands[tag].active, 0);
+	/* Unmap the DMA scatter list entries */
+	dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, cmd->direction);
 
-	/* Upper layer callback */
-	func = cmd->async_callback;
-	if (likely(func && cmpxchg(&cmd->async_callback, func, 0) == func)) {
+	rq = mtip_rq_from_tag(dd, tag);
 
-		/* Unmap the DMA scatter list entries */
-		dma_unmap_sg(&dd->pdev->dev,
-			cmd->sg,
-			cmd->scatter_ents,
-			cmd->direction);
+	if (unlikely(cmd->unaligned))
+		up(&port->cmd_slot_unal);
 
-		func(cmd->async_data, cb_status);
-		unaligned = cmd->unaligned;
-
-		/* Clear the allocated bit for the command */
-		release_slot(port, tag);
-
-		if (unlikely(unaligned))
-			up(&port->cmd_slot_unal);
-		else
-			up(&port->cmd_slot);
-	}
-}
-
-/*
- * This function is called for clean the pending command in the
- * command slot during the surprise removal of device and return
- * error to the upper layer.
- *
- * @dd Pointer to the DRIVER_DATA structure.
- *
- * return value
- *	None
- */
-static void mtip_command_cleanup(struct driver_data *dd)
-{
-	int tag = 0;
-	struct mtip_cmd *cmd;
-	struct mtip_port *port = dd->port;
-	unsigned int num_cmd_slots = dd->slot_groups * 32;
-
-	if (!test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
-		return;
-
-	if (!port)
-		return;
-
-	cmd = &port->commands[MTIP_TAG_INTERNAL];
-	if (atomic_read(&cmd->active))
-		if (readl(port->cmd_issue[MTIP_TAG_INTERNAL]) &
-					(1 << MTIP_TAG_INTERNAL))
-			if (cmd->comp_func)
-				cmd->comp_func(port, MTIP_TAG_INTERNAL,
-					 cmd->comp_data, -ENODEV);
-
-	while (1) {
-		tag = find_next_bit(port->allocated, num_cmd_slots, tag);
-		if (tag >= num_cmd_slots)
-			break;
-
-		cmd = &port->commands[tag];
-		if (atomic_read(&cmd->active))
-			mtip_async_complete(port, tag, dd, -ENODEV);
-	}
-
-	set_bit(MTIP_DDF_CLEANUP_BIT, &dd->dd_flag);
+	blk_mq_end_io(rq, status ? -EIO : 0);
 }
 
 /*
@@ -388,8 +298,6 @@ static inline void mtip_issue_ncq_command(struct mtip_port *port, int tag)
 {
 	int group = tag >> 5;
 
-	atomic_set(&port->commands[tag].active, 1);
-
 	/* guard SACT and CI registers */
 	spin_lock(&port->cmd_issue_lock[group]);
 	writel((1 << MTIP_TAG_BIT(tag)),
@@ -397,10 +305,6 @@ static inline void mtip_issue_ncq_command(struct mtip_port *port, int tag)
 	writel((1 << MTIP_TAG_BIT(tag)),
 			port->cmd_issue[MTIP_TAG_INDEX(tag)]);
 	spin_unlock(&port->cmd_issue_lock[group]);
-
-	/* Set the command's timeout value.*/
-	port->commands[tag].comp_time = jiffies + msecs_to_jiffies(
-					MTIP_NCQ_COMMAND_TIMEOUT_MS);
 }
 
 /*
@@ -648,132 +552,13 @@ static void print_tags(struct driver_data *dd,
 
 	memset(tagmap, 0, sizeof(tagmap));
 	for (group = SLOTBITS_IN_LONGS; group > 0; group--)
-		tagmap_len = sprintf(tagmap + tagmap_len, "%016lX ",
+		tagmap_len += sprintf(tagmap + tagmap_len, "%016lX ",
 						tagbits[group-1]);
 	dev_warn(&dd->pdev->dev,
 			"%d command(s) %s: tagmap [%s]", cnt, msg, tagmap);
 }
 
 /*
- * Called periodically to see if any read/write commands are
- * taking too long to complete.
- *
- * @data Pointer to the PORT data structure.
- *
- * return value
- *	None
- */
-static void mtip_timeout_function(unsigned long int data)
-{
-	struct mtip_port *port = (struct mtip_port *) data;
-	struct host_to_dev_fis *fis;
-	struct mtip_cmd *cmd;
-	int unaligned, tag, cmdto_cnt = 0;
-	unsigned int bit, group;
-	unsigned int num_command_slots;
-	unsigned long to, tagaccum[SLOTBITS_IN_LONGS];
-	void (*func)(void *, int);
-
-	if (unlikely(!port))
-		return;
-
-	if (unlikely(port->dd->sr))
-		return;
-
-	if (test_bit(MTIP_DDF_RESUME_BIT, &port->dd->dd_flag)) {
-		mod_timer(&port->cmd_timer,
-			jiffies + msecs_to_jiffies(30000));
-		return;
-	}
-	/* clear the tag accumulator */
-	memset(tagaccum, 0, SLOTBITS_IN_LONGS * sizeof(long));
-	num_command_slots = port->dd->slot_groups * 32;
-
-	for (tag = 0; tag < num_command_slots; tag++) {
-		/*
-		 * Skip internal command slot as it has
-		 * its own timeout mechanism
-		 */
-		if (tag == MTIP_TAG_INTERNAL)
-			continue;
-
-		if (atomic_read(&port->commands[tag].active) &&
-		   (time_after(jiffies, port->commands[tag].comp_time))) {
-			group = tag >> 5;
-			bit = tag & 0x1F;
-
-			cmd = &port->commands[tag];
-			fis = (struct host_to_dev_fis *) cmd->command;
-
-			set_bit(tag, tagaccum);
-			cmdto_cnt++;
-			if (cmdto_cnt == 1)
-				set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
-
-			/*
-			 * Clear the completed bit. This should prevent
-			 *  any interrupt handlers from trying to retire
-			 *  the command.
-			 */
-			writel(1 << bit, port->completed[group]);
-
-			/* Clear the active flag for the command */
-			atomic_set(&port->commands[tag].active, 0);
-
-			func = cmd->async_callback;
-			if (func &&
-			    cmpxchg(&cmd->async_callback, func, 0) == func) {
-
-				/* Unmap the DMA scatter list entries */
-				dma_unmap_sg(&port->dd->pdev->dev,
-						cmd->sg,
-						cmd->scatter_ents,
-						cmd->direction);
-
-				func(cmd->async_data, -EIO);
-				unaligned = cmd->unaligned;
-
-				/* Clear the allocated bit for the command. */
-				release_slot(port, tag);
-
-				if (unaligned)
-					up(&port->cmd_slot_unal);
-				else
-					up(&port->cmd_slot);
-			}
-		}
-	}
-
-	if (cmdto_cnt) {
-		print_tags(port->dd, "timed out", tagaccum, cmdto_cnt);
-		if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
-			mtip_device_reset(port->dd);
-			wake_up_interruptible(&port->svc_wait);
-		}
-		clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
-	}
-
-	if (port->ic_pause_timer) {
-		to  = port->ic_pause_timer + msecs_to_jiffies(1000);
-		if (time_after(jiffies, to)) {
-			if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
-				port->ic_pause_timer = 0;
-				clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
-				clear_bit(MTIP_PF_DM_ACTIVE_BIT, &port->flags);
-				clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
-				wake_up_interruptible(&port->svc_wait);
-			}
-
-
-		}
-	}
-
-	/* Restart the timer */
-	mod_timer(&port->cmd_timer,
-		jiffies + msecs_to_jiffies(MTIP_TIMEOUT_CHECK_PERIOD));
-}
-
-/*
  * Internal command completion callback function.
  *
  * This function is normally called by the driver ISR when an internal
@@ -789,28 +574,19 @@ static void mtip_timeout_function(unsigned long int data)
  *	None
  */
 static void mtip_completion(struct mtip_port *port,
-			    int tag,
-			    void *data,
-			    int status)
+			    int tag, struct mtip_cmd *command, int status)
 {
-	struct mtip_cmd *command = &port->commands[tag];
-	struct completion *waiting = data;
+	struct completion *waiting = command->comp_data;
 	if (unlikely(status == PORT_IRQ_TF_ERR))
 		dev_warn(&port->dd->pdev->dev,
 			"Internal command %d completed with TFE\n", tag);
 
-	command->async_callback = NULL;
-	command->comp_func = NULL;
-
 	complete(waiting);
 }
 
 static void mtip_null_completion(struct mtip_port *port,
-			    int tag,
-			    void *data,
-			    int status)
+			    int tag, struct mtip_cmd *command, int status)
 {
-	return;
 }
 
 static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer,
@@ -842,19 +618,16 @@ static void mtip_handle_tfe(struct driver_data *dd)
 
 	port = dd->port;
 
-	/* Stop the timer to prevent command timeouts. */
-	del_timer(&port->cmd_timer);
 	set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
 
 	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags) &&
 			test_bit(MTIP_TAG_INTERNAL, port->allocated)) {
-		cmd = &port->commands[MTIP_TAG_INTERNAL];
+		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
 
-		atomic_inc(&cmd->active); /* active > 1 indicates error */
 		if (cmd->comp_data && cmd->comp_func) {
 			cmd->comp_func(port, MTIP_TAG_INTERNAL,
-					cmd->comp_data, PORT_IRQ_TF_ERR);
+					cmd, PORT_IRQ_TF_ERR);
 		}
 		goto handle_tfe_exit;
 	}
@@ -866,6 +639,8 @@ static void mtip_handle_tfe(struct driver_data *dd)
 	for (group = 0; group < dd->slot_groups; group++) {
 		completed = readl(port->completed[group]);
 
+		dev_warn(&dd->pdev->dev, "g=%u, comp=%x\n", group, completed);
+
 		/* clear completed status register in the hardware.*/
 		writel(completed, port->completed[group]);
 
@@ -879,15 +654,11 @@ static void mtip_handle_tfe(struct driver_data *dd)
 			if (tag == MTIP_TAG_INTERNAL)
 				continue;
 
-			cmd = &port->commands[tag];
+			cmd = mtip_cmd_from_tag(dd, tag);
 			if (likely(cmd->comp_func)) {
 				set_bit(tag, tagaccum);
 				cmd_cnt++;
-				atomic_set(&cmd->active, 0);
-				cmd->comp_func(port,
-					 tag,
-					 cmd->comp_data,
-					 0);
+				cmd->comp_func(port, tag, cmd, 0);
 			} else {
 				dev_err(&port->dd->pdev->dev,
 					"Missing completion func for tag %d",
@@ -947,11 +718,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 		for (bit = 0; bit < 32; bit++) {
 			reissue = 1;
 			tag = (group << 5) + bit;
-			cmd = &port->commands[tag];
-
-			/* If the active bit is set re-issue the command */
-			if (atomic_read(&cmd->active) == 0)
-				continue;
+			cmd = mtip_cmd_from_tag(dd, tag);
 
 			fis = (struct host_to_dev_fis *)cmd->command;
 
@@ -970,11 +737,9 @@ static void mtip_handle_tfe(struct driver_data *dd)
 					tag,
 					fail_reason != NULL ?
 						fail_reason : "unknown");
-					atomic_set(&cmd->active, 0);
 					if (cmd->comp_func) {
 						cmd->comp_func(port, tag,
-							cmd->comp_data,
-							-ENODATA);
+							cmd, -ENODATA);
 					}
 					continue;
 				}
@@ -997,14 +762,9 @@ static void mtip_handle_tfe(struct driver_data *dd)
 			/* Retire a command that will not be reissued */
 			dev_warn(&port->dd->pdev->dev,
 				"retiring tag %d\n", tag);
-			atomic_set(&cmd->active, 0);
 
 			if (cmd->comp_func)
-				cmd->comp_func(
-					port,
-					tag,
-					cmd->comp_data,
-					PORT_IRQ_TF_ERR);
+				cmd->comp_func(port, tag, cmd, PORT_IRQ_TF_ERR);
 			else
 				dev_warn(&port->dd->pdev->dev,
 					"Bad completion for tag %d\n",
@@ -1017,9 +777,6 @@ handle_tfe_exit:
 	/* clear eh_active */
 	clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
 	wake_up_interruptible(&port->svc_wait);
-
-	mod_timer(&port->cmd_timer,
-		 jiffies + msecs_to_jiffies(MTIP_TIMEOUT_CHECK_PERIOD));
 }
 
 /*
@@ -1048,15 +805,10 @@ static inline void mtip_workq_sdbfx(struct mtip_port *port, int group,
 			if (unlikely(tag == MTIP_TAG_INTERNAL))
 				continue;
 
-			command = &port->commands[tag];
-			/* make internal callback */
-			if (likely(command->comp_func)) {
-				command->comp_func(
-					port,
-					tag,
-					command->comp_data,
-					0);
-			} else {
+			command = mtip_cmd_from_tag(dd, tag);
+			if (likely(command->comp_func))
+				command->comp_func(port, tag, command, 0);
+			else {
 				dev_dbg(&dd->pdev->dev,
 					"Null completion for tag %d",
 					tag);
@@ -1081,16 +833,13 @@ static inline void mtip_workq_sdbfx(struct mtip_port *port, int group,
 static inline void mtip_process_legacy(struct driver_data *dd, u32 port_stat)
 {
 	struct mtip_port *port = dd->port;
-	struct mtip_cmd *cmd = &port->commands[MTIP_TAG_INTERNAL];
+	struct mtip_cmd *cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 
 	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags) &&
 	    (cmd != NULL) && !(readl(port->cmd_issue[MTIP_TAG_INTERNAL])
 		& (1 << MTIP_TAG_INTERNAL))) {
 		if (cmd->comp_func) {
-			cmd->comp_func(port,
-				MTIP_TAG_INTERNAL,
-				cmd->comp_data,
-				0);
+			cmd->comp_func(port, MTIP_TAG_INTERNAL, cmd, 0);
 			return;
 		}
 	}
@@ -1103,8 +852,6 @@ static inline void mtip_process_legacy(struct driver_data *dd, u32 port_stat)
  */
 static inline void mtip_process_errors(struct driver_data *dd, u32 port_stat)
 {
-	if (likely(port_stat & (PORT_IRQ_TF_ERR | PORT_IRQ_IF_ERR)))
-		mtip_handle_tfe(dd);
 
 	if (unlikely(port_stat & PORT_IRQ_CONNECT)) {
 		dev_warn(&dd->pdev->dev,
@@ -1122,6 +869,12 @@ static inline void mtip_process_errors(struct driver_data *dd, u32 port_stat)
 		dev_warn(&dd->pdev->dev,
 			"Port stat errors %x unhandled\n",
 			(port_stat & ~PORT_IRQ_HANDLED));
+		if (mtip_check_surprise_removal(dd->pdev))
+			return;
+	}
+	if (likely(port_stat & (PORT_IRQ_TF_ERR | PORT_IRQ_IF_ERR))) {
+		set_bit(MTIP_PF_EH_ACTIVE_BIT, &dd->port->flags);
+		wake_up_interruptible(&dd->port->svc_wait);
 	}
 }
 
@@ -1222,7 +975,6 @@ static irqreturn_t mtip_irq_handler(int irq, void *instance)
 
 static void mtip_issue_non_ncq_command(struct mtip_port *port, int tag)
 {
-	atomic_set(&port->commands[tag].active, 1);
 	writel(1 << MTIP_TAG_BIT(tag),
 		port->cmd_issue[MTIP_TAG_INDEX(tag)]);
 }
@@ -1280,6 +1032,8 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
 	unsigned int n;
 	unsigned int active = 1;
 
+	blk_mq_stop_hw_queues(port->dd->queue);
+
 	to = jiffies + msecs_to_jiffies(timeout);
 	do {
 		if (test_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags) &&
@@ -1287,8 +1041,13 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
 			msleep(20);
 			continue; /* svc thd is actively issuing commands */
 		}
+
+		msleep(100);
+		if (mtip_check_surprise_removal(port->dd->pdev))
+			goto err_fault;
 		if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &port->dd->dd_flag))
-			return -EFAULT;
+			goto err_fault;
+
 		/*
 		 * Ignore s_active bit 0 of array element 0.
 		 * This bit will always be set
@@ -1299,11 +1058,13 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
 
 		if (!active)
 			break;
-
-		msleep(20);
 	} while (time_before(jiffies, to));
 
+	blk_mq_start_stopped_hw_queues(port->dd->queue, true);
 	return active ? -EBUSY : 0;
+err_fault:
+	blk_mq_start_stopped_hw_queues(port->dd->queue, true);
+	return -EFAULT;
 }
 
 /*
@@ -1335,10 +1096,9 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 {
 	struct mtip_cmd_sg *command_sg;
 	DECLARE_COMPLETION_ONSTACK(wait);
-	int rv = 0, ready2go = 1;
-	struct mtip_cmd *int_cmd = &port->commands[MTIP_TAG_INTERNAL];
-	unsigned long to;
+	struct mtip_cmd *int_cmd;
 	struct driver_data *dd = port->dd;
+	int rv = 0;
 
 	/* Make sure the buffer is 8 byte aligned. This is asic specific. */
 	if (buffer & 0x00000007) {
@@ -1346,19 +1106,8 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 		return -EFAULT;
 	}
 
-	to = jiffies + msecs_to_jiffies(timeout);
-	do {
-		ready2go = !test_and_set_bit(MTIP_TAG_INTERNAL,
-						port->allocated);
-		if (ready2go)
-			break;
-		mdelay(100);
-	} while (time_before(jiffies, to));
-	if (!ready2go) {
-		dev_warn(&dd->pdev->dev,
-			"Internal cmd active. new cmd [%02X]\n", fis->command);
-		return -EBUSY;
-	}
+	int_cmd = mtip_get_int_command(dd);
+
 	set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 	port->ic_pause_timer = 0;
 
@@ -1368,10 +1117,11 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	if (atomic == GFP_KERNEL) {
 		if (fis->command != ATA_CMD_STANDBYNOW1) {
 			/* wait for io to complete if non atomic */
-			if (mtip_quiesce_io(port, 5000) < 0) {
+			if (mtip_quiesce_io(port,
+					MTIP_QUIESCE_IO_TIMEOUT_MS) < 0) {
 				dev_warn(&dd->pdev->dev,
 					"Failed to quiesce IO\n");
-				release_slot(port, MTIP_TAG_INTERNAL);
+				mtip_put_int_command(dd, int_cmd);
 				clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 				wake_up_interruptible(&port->svc_wait);
 				return -EBUSY;
@@ -1416,9 +1166,9 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 
 	if (atomic == GFP_KERNEL) {
 		/* Wait for the command to complete or timeout. */
-		if (wait_for_completion_interruptible_timeout(
+		if ((rv = wait_for_completion_interruptible_timeout(
 				&wait,
-				msecs_to_jiffies(timeout)) <= 0) {
+				msecs_to_jiffies(timeout))) <= 0) {
 			if (rv == -ERESTARTSYS) { /* interrupted */
 				dev_err(&dd->pdev->dev,
 					"Internal command [%02X] was interrupted after %lu ms\n",
@@ -1497,8 +1247,7 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	}
 exec_ic_exit:
 	/* Clear the allocated and active bits for the internal command. */
-	atomic_set(&int_cmd->active, 0);
-	release_slot(port, MTIP_TAG_INTERNAL);
+	mtip_put_int_command(dd, int_cmd);
 	if (rv >= 0 && mtip_pause_ncq(port, fis)) {
 		/* NCQ paused */
 		return rv;
@@ -1529,6 +1278,37 @@ static inline void ata_swap_string(u16 *buf, unsigned int len)
 		be16_to_cpus(&buf[i]);
 }
 
+static void mtip_set_timeout(struct driver_data *dd,
+					struct host_to_dev_fis *fis,
+					unsigned int *timeout, u8 erasemode)
+{
+	switch (fis->command) {
+	case ATA_CMD_DOWNLOAD_MICRO:
+		*timeout = 120000; /* 2 minutes */
+		break;
+	case ATA_CMD_SEC_ERASE_UNIT:
+	case 0xFC:
+		if (erasemode)
+			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+		else
+			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
+		break;
+	case ATA_CMD_STANDBYNOW1:
+		*timeout = 120000;  /* 2 minutes */
+		break;
+	case 0xF7:
+	case 0xFA:
+		*timeout = 60000;  /* 60 seconds */
+		break;
+	case ATA_CMD_SMART:
+		*timeout = 15000;  /* 15 seconds */
+		break;
+	default:
+		*timeout = MTIP_IOCTL_CMD_TIMEOUT_MS;
+		break;
+	}
+}
+
 /*
  * Request the device identity information.
  *
@@ -1576,7 +1356,7 @@ static int mtip_get_identify(struct mtip_port *port, void __user *user_buffer)
 				sizeof(u16) * ATA_ID_WORDS,
 				0,
 				GFP_KERNEL,
-				MTIP_INTERNAL_COMMAND_TIMEOUT_MS)
+				MTIP_INT_CMD_TIMEOUT_MS)
 				< 0) {
 		rv = -1;
 		goto out;
@@ -1644,6 +1424,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	int rv;
 	struct host_to_dev_fis	fis;
 	unsigned long start;
+	unsigned int timeout;
 
 	/* Build the FIS. */
 	memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -1651,6 +1432,8 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	fis.opts	= 1 << 7;
 	fis.command	= ATA_CMD_STANDBYNOW1;
 
+	mtip_set_timeout(port->dd, &fis, &timeout, 0);
+
 	start = jiffies;
 	rv = mtip_exec_internal_command(port,
 					&fis,
@@ -1659,7 +1442,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 					0,
 					0,
 					GFP_ATOMIC,
-					15000);
+					timeout);
 	dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
 			jiffies_to_msecs(jiffies - start));
 	if (rv)
@@ -1705,7 +1488,7 @@ static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer,
 					sectors * ATA_SECT_SIZE,
 					0,
 					GFP_ATOMIC,
-					MTIP_INTERNAL_COMMAND_TIMEOUT_MS);
+					MTIP_INT_CMD_TIMEOUT_MS);
 }
 
 /*
@@ -1998,6 +1781,7 @@ static int exec_drive_task(struct mtip_port *port, u8 *command)
 {
 	struct host_to_dev_fis	fis;
 	struct host_to_dev_fis *reply = (port->rxfis + RX_FIS_D2H_REG);
+	unsigned int to;
 
 	/* Build the FIS. */
 	memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -2011,6 +1795,8 @@ static int exec_drive_task(struct mtip_port *port, u8 *command)
 	fis.cyl_hi	= command[5];
 	fis.device	= command[6] & ~0x10; /* Clear the dev bit*/
 
+	mtip_set_timeout(port->dd, &fis, &to, 0);
+
 	dbg_printk(MTIP_DRV_NAME " %s: User Command: cmd %x, feat %x, nsect %x, sect %x, lcyl %x, hcyl %x, sel %x\n",
 		__func__,
 		command[0],
@@ -2029,7 +1815,7 @@ static int exec_drive_task(struct mtip_port *port, u8 *command)
 				 0,
 				 0,
 				 GFP_KERNEL,
-				 MTIP_IOCTL_COMMAND_TIMEOUT_MS) < 0) {
+				 to) < 0) {
 		return -1;
 	}
 
@@ -2069,6 +1855,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command,
 	u8 *buf = NULL;
 	dma_addr_t dma_addr = 0;
 	int rv = 0, xfer_sz = command[3];
+	unsigned int to;
 
 	if (xfer_sz) {
 		if (!user_buffer)
@@ -2100,6 +1887,8 @@ static int exec_drive_command(struct mtip_port *port, u8 *command,
 		fis.cyl_hi	= 0xC2;
 	}
 
+	mtip_set_timeout(port->dd, &fis, &to, 0);
+
 	if (xfer_sz)
 		reply = (port->rxfis + RX_FIS_PIO_SETUP);
 	else
@@ -2122,7 +1911,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command,
 				 (xfer_sz ? ATA_SECT_SIZE * xfer_sz : 0),
 				 0,
 				 GFP_KERNEL,
-				 MTIP_IOCTL_COMMAND_TIMEOUT_MS)
+				 to)
 				 < 0) {
 		rv = -EFAULT;
 		goto exit_drive_command;
@@ -2202,36 +1991,6 @@ static unsigned int implicit_sector(unsigned char command,
 	}
 	return rv;
 }
-static void mtip_set_timeout(struct driver_data *dd,
-					struct host_to_dev_fis *fis,
-					unsigned int *timeout, u8 erasemode)
-{
-	switch (fis->command) {
-	case ATA_CMD_DOWNLOAD_MICRO:
-		*timeout = 120000; /* 2 minutes */
-		break;
-	case ATA_CMD_SEC_ERASE_UNIT:
-	case 0xFC:
-		if (erasemode)
-			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
-		else
-			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
-		break;
-	case ATA_CMD_STANDBYNOW1:
-		*timeout = 120000;  /* 2 minutes */
-		break;
-	case 0xF7:
-	case 0xFA:
-		*timeout = 60000;  /* 60 seconds */
-		break;
-	case ATA_CMD_SMART:
-		*timeout = 15000;  /* 15 seconds */
-		break;
-	default:
-		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
-		break;
-	}
-}
 
 /*
  * Executes a taskfile
@@ -2606,22 +2365,21 @@ static int mtip_hw_ioctl(struct driver_data *dd, unsigned int cmd,
  * return value
  *	None
  */
-static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
-			      int nsect, int nents, int tag, void *callback,
-			      void *data, int dir, int unaligned)
+static void mtip_hw_submit_io(struct driver_data *dd, struct request *rq,
+			      struct mtip_cmd *command, int nents,
+			      struct blk_mq_hw_ctx *hctx)
 {
 	struct host_to_dev_fis	*fis;
 	struct mtip_port *port = dd->port;
-	struct mtip_cmd *command = &port->commands[tag];
-	int dma_dir = (dir == READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-	u64 start = sector;
+	int dma_dir = rq_data_dir(rq) == READ ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	u64 start = blk_rq_pos(rq);
+	unsigned int nsect = blk_rq_sectors(rq);
 
 	/* Map the scatter list for DMA access */
 	nents = dma_map_sg(&dd->pdev->dev, command->sg, nents, dma_dir);
 
 	command->scatter_ents = nents;
 
-	command->unaligned = unaligned;
 	/*
 	 * The number of retries for this command before it is
 	 * reported as a failure to the upper layers.
@@ -2632,8 +2390,10 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 	fis = command->command;
 	fis->type        = 0x27;
 	fis->opts        = 1 << 7;
-	fis->command     =
-		(dir == READ ? ATA_CMD_FPDMA_READ : ATA_CMD_FPDMA_WRITE);
+	if (rq_data_dir(rq) == READ)
+		fis->command = ATA_CMD_FPDMA_READ;
+	else
+		fis->command = ATA_CMD_FPDMA_WRITE;
 	fis->lba_low     = start & 0xFF;
 	fis->lba_mid     = (start >> 8) & 0xFF;
 	fis->lba_hi      = (start >> 16) & 0xFF;
@@ -2643,14 +2403,14 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 	fis->device	 = 1 << 6;
 	fis->features    = nsect & 0xFF;
 	fis->features_ex = (nsect >> 8) & 0xFF;
-	fis->sect_count  = ((tag << 3) | (tag >> 5));
+	fis->sect_count  = ((rq->tag << 3) | (rq->tag >> 5));
 	fis->sect_cnt_ex = 0;
 	fis->control     = 0;
 	fis->res2        = 0;
 	fis->res3        = 0;
 	fill_command_sg(dd, command, nents);
 
-	if (unaligned)
+	if (command->unaligned)
 		fis->device |= 1 << 7;
 
 	/* Populate the command header */
@@ -2668,81 +2428,17 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 	command->direction = dma_dir;
 
 	/*
-	 * Set the completion function and data for the command passed
-	 * from the upper layer.
-	 */
-	command->async_data = data;
-	command->async_callback = callback;
-
-	/*
 	 * To prevent this command from being issued
 	 * if an internal command is in progress or error handling is active.
 	 */
 	if (port->flags & MTIP_PF_PAUSE_IO) {
-		set_bit(tag, port->cmds_to_issue);
+		set_bit(rq->tag, port->cmds_to_issue);
 		set_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags);
 		return;
 	}
 
 	/* Issue the command to the hardware */
-	mtip_issue_ncq_command(port, tag);
-
-	return;
-}
-
-/*
- * Release a command slot.
- *
- * @dd  Pointer to the driver data structure.
- * @tag Slot tag
- *
- * return value
- *      None
- */
-static void mtip_hw_release_scatterlist(struct driver_data *dd, int tag,
-								int unaligned)
-{
-	struct semaphore *sem = unaligned ? &dd->port->cmd_slot_unal :
-							&dd->port->cmd_slot;
-	release_slot(dd->port, tag);
-	up(sem);
-}
-
-/*
- * Obtain a command slot and return its associated scatter list.
- *
- * @dd  Pointer to the driver data structure.
- * @tag Pointer to an int that will receive the allocated command
- *            slot tag.
- *
- * return value
- *	Pointer to the scatter list for the allocated command slot
- *	or NULL if no command slots are available.
- */
-static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd,
-						   int *tag, int unaligned)
-{
-	struct semaphore *sem = unaligned ? &dd->port->cmd_slot_unal :
-							&dd->port->cmd_slot;
-
-	/*
-	 * It is possible that, even with this semaphore, a thread
-	 * may think that no command slots are available. Therefore, we
-	 * need to make an attempt to get_slot().
-	 */
-	down(sem);
-	*tag = get_slot(dd->port);
-
-	if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag))) {
-		up(sem);
-		return NULL;
-	}
-	if (unlikely(*tag < 0)) {
-		up(sem);
-		return NULL;
-	}
-
-	return dd->port->commands[*tag].sg;
+	mtip_issue_ncq_command(port, rq->tag);
 }
 
 /*
@@ -3113,6 +2809,7 @@ static int mtip_free_orphan(struct driver_data *dd)
 		if (dd->queue) {
 			dd->queue->queuedata = NULL;
 			blk_cleanup_queue(dd->queue);
+			blk_mq_free_tag_set(&dd->tags);
 			dd->queue = NULL;
 		}
 	}
@@ -3270,6 +2967,11 @@ static int mtip_service_thread(void *data)
 	int ret;
 
 	while (1) {
+		if (kthread_should_stop() ||
+			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
+			goto st_out;
+		clear_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+
 		/*
 		 * the condition is to check neither an internal command is
 		 * is in progress nor error handling is active
@@ -3277,11 +2979,12 @@ static int mtip_service_thread(void *data)
 		wait_event_interruptible(port->svc_wait, (port->flags) &&
 			!(port->flags & MTIP_PF_PAUSE_IO));
 
-		if (kthread_should_stop())
-			goto st_out;
-
 		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
 
+		if (kthread_should_stop() ||
+			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
+			goto st_out;
+
 		/* If I am an orphan, start self cleanup */
 		if (test_bit(MTIP_PF_SR_CLEANUP_BIT, &port->flags))
 			break;
@@ -3290,6 +2993,16 @@ static int mtip_service_thread(void *data)
 				&dd->dd_flag)))
 			goto st_out;
 
+restart_eh:
+		/* Demux bits: start with error handling */
+		if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) {
+			mtip_handle_tfe(dd);
+			clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
+		}
+
+		if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags))
+			goto restart_eh;
+
 		if (test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) {
 			slot = 1;
 			/* used to restrict the loop to one iteration */
@@ -3319,16 +3032,14 @@ static int mtip_service_thread(void *data)
 			}
 
 			clear_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags);
-		} else if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) {
+		}
+
+		if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) {
 			if (mtip_ftl_rebuild_poll(dd) < 0)
 				set_bit(MTIP_DDF_REBUILD_FAILED_BIT,
 							&dd->dd_flag);
 			clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
 		}
-		clear_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
-
-		if (test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
-			goto st_out;
 	}
 
 	/* wait for pci remove to exit */
@@ -3365,7 +3076,6 @@ st_out:
  */
 static void mtip_dma_free(struct driver_data *dd)
 {
-	int i;
 	struct mtip_port *port = dd->port;
 
 	if (port->block1)
@@ -3376,13 +3086,6 @@ static void mtip_dma_free(struct driver_data *dd)
 		dmam_free_coherent(&dd->pdev->dev, AHCI_CMD_TBL_SZ,
 				port->command_list, port->command_list_dma);
 	}
-
-	for (i = 0; i < MTIP_MAX_COMMAND_SLOTS; i++) {
-		if (port->commands[i].command)
-			dmam_free_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
-				port->commands[i].command,
-				port->commands[i].command_dma);
-	}
 }
 
 /*
@@ -3396,8 +3099,6 @@ static void mtip_dma_free(struct driver_data *dd)
 static int mtip_dma_alloc(struct driver_data *dd)
 {
 	struct mtip_port *port = dd->port;
-	int i, rv = 0;
-	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
 
 	/* Allocate dma memory for RX Fis, Identify, and Sector Bufffer */
 	port->block1 =
@@ -3430,41 +3131,63 @@ static int mtip_dma_alloc(struct driver_data *dd)
 	port->smart_buf     = port->block1 + AHCI_SMARTBUF_OFFSET;
 	port->smart_buf_dma = port->block1_dma + AHCI_SMARTBUF_OFFSET;
 
-	/* Setup per command SGL DMA region */
-
-	/* Point the command headers at the command tables */
-	for (i = 0; i < MTIP_MAX_COMMAND_SLOTS; i++) {
-		port->commands[i].command =
-			dmam_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
-				&port->commands[i].command_dma, GFP_KERNEL);
-		if (!port->commands[i].command) {
-			rv = -ENOMEM;
-			mtip_dma_free(dd);
-			return rv;
-		}
-		memset(port->commands[i].command, 0, CMD_DMA_ALLOC_SZ);
-
-		port->commands[i].command_header = port->command_list +
-					(sizeof(struct mtip_cmd_hdr) * i);
-		port->commands[i].command_header_dma =
-					dd->port->command_list_dma +
-					(sizeof(struct mtip_cmd_hdr) * i);
+	return 0;
+}
 
-		if (host_cap_64)
-			port->commands[i].command_header->ctbau =
-				__force_bit2int cpu_to_le32(
-				(port->commands[i].command_dma >> 16) >> 16);
+static int mtip_hw_get_identify(struct driver_data *dd)
+{
+	struct smart_attr attr242;
+	unsigned char *buf;
+	int rv;
 
-		port->commands[i].command_header->ctba =
-				__force_bit2int cpu_to_le32(
-				port->commands[i].command_dma & 0xFFFFFFFF);
+	if (mtip_get_identify(dd->port, NULL) < 0)
+		return -EFAULT;
 
-		sg_init_table(port->commands[i].sg, MTIP_MAX_SG);
+	if (*(dd->port->identify + MTIP_FTL_REBUILD_OFFSET) ==
+		MTIP_FTL_REBUILD_MAGIC) {
+		set_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags);
+		return MTIP_FTL_REBUILD_MAGIC;
+	}
+	mtip_dump_identify(dd->port);
 
-		/* Mark command as currently inactive */
-		atomic_set(&dd->port->commands[i].active, 0);
+	/* check write protect, over temp and rebuild statuses */
+	rv = mtip_read_log_page(dd->port, ATA_LOG_SATA_NCQ,
+				dd->port->log_buf,
+				dd->port->log_buf_dma, 1);
+	if (rv) {
+		dev_warn(&dd->pdev->dev,
+			"Error in READ LOG EXT (10h) command\n");
+		/* non-critical error, don't fail the load */
+	} else {
+		buf = (unsigned char *)dd->port->log_buf;
+		if (buf[259] & 0x1) {
+			dev_info(&dd->pdev->dev,
+				"Write protect bit is set.\n");
+			set_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag);
+		}
+		if (buf[288] == 0xF7) {
+			dev_info(&dd->pdev->dev,
+				"Exceeded Tmax, drive in thermal shutdown.\n");
+			set_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag);
+		}
+		if (buf[288] == 0xBF) {
+			dev_info(&dd->pdev->dev,
+				"Drive indicates rebuild has failed.\n");
+			/* TODO */
+		}
 	}
-	return 0;
+
+	/* get write protect progess */
+	memset(&attr242, 0, sizeof(struct smart_attr));
+	if (mtip_get_smart_attr(dd->port, 242, &attr242))
+		dev_warn(&dd->pdev->dev,
+				"Unable to check write protect progress\n");
+	else
+		dev_info(&dd->pdev->dev,
+				"Write protect progress: %u%% (%u blocks)\n",
+				attr242.cur, le32_to_cpu(attr242.data));
+
+	return rv;
 }
 
 /*
@@ -3481,8 +3204,6 @@ static int mtip_hw_init(struct driver_data *dd)
 	int rv;
 	unsigned int num_command_slots;
 	unsigned long timeout, timetaken;
-	unsigned char *buf;
-	struct smart_attr attr242;
 
 	dd->mmio = pcim_iomap_table(dd->pdev)[MTIP_ABAR];
 
@@ -3513,8 +3234,6 @@ static int mtip_hw_init(struct driver_data *dd)
 	else
 		dd->unal_qdepth = 0;
 
-	/* Counting semaphore to track command slot usage */
-	sema_init(&dd->port->cmd_slot, num_command_slots - 1 - dd->unal_qdepth);
 	sema_init(&dd->port->cmd_slot_unal, dd->unal_qdepth);
 
 	/* Spinlock to prevent concurrent issue */
@@ -3599,73 +3318,16 @@ static int mtip_hw_init(struct driver_data *dd)
 	writel(readl(dd->mmio + HOST_CTL) | HOST_IRQ_EN,
 					dd->mmio + HOST_CTL);
 
-	init_timer(&dd->port->cmd_timer);
 	init_waitqueue_head(&dd->port->svc_wait);
 
-	dd->port->cmd_timer.data = (unsigned long int) dd->port;
-	dd->port->cmd_timer.function = mtip_timeout_function;
-	mod_timer(&dd->port->cmd_timer,
-		jiffies + msecs_to_jiffies(MTIP_TIMEOUT_CHECK_PERIOD));
-
-
 	if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag)) {
 		rv = -EFAULT;
 		goto out3;
 	}
 
-	if (mtip_get_identify(dd->port, NULL) < 0) {
-		rv = -EFAULT;
-		goto out3;
-	}
-	mtip_dump_identify(dd->port);
-
-	if (*(dd->port->identify + MTIP_FTL_REBUILD_OFFSET) ==
-		MTIP_FTL_REBUILD_MAGIC) {
-		set_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags);
-		return MTIP_FTL_REBUILD_MAGIC;
-	}
-
-	/* check write protect, over temp and rebuild statuses */
-	rv = mtip_read_log_page(dd->port, ATA_LOG_SATA_NCQ,
-				dd->port->log_buf,
-				dd->port->log_buf_dma, 1);
-	if (rv) {
-		dev_warn(&dd->pdev->dev,
-			"Error in READ LOG EXT (10h) command\n");
-		/* non-critical error, don't fail the load */
-	} else {
-		buf = (unsigned char *)dd->port->log_buf;
-		if (buf[259] & 0x1) {
-			dev_info(&dd->pdev->dev,
-				"Write protect bit is set.\n");
-			set_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag);
-		}
-		if (buf[288] == 0xF7) {
-			dev_info(&dd->pdev->dev,
-				"Exceeded Tmax, drive in thermal shutdown.\n");
-			set_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag);
-		}
-		if (buf[288] == 0xBF) {
-			dev_info(&dd->pdev->dev,
-				"Drive is in security locked state.\n");
-			set_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag);
-		}
-	}
-
-	/* get write protect progess */
-	memset(&attr242, 0, sizeof(struct smart_attr));
-	if (mtip_get_smart_attr(dd->port, 242, &attr242))
-		dev_warn(&dd->pdev->dev,
-				"Unable to check write protect progress\n");
-	else
-		dev_info(&dd->pdev->dev,
-				"Write protect progress: %u%% (%u blocks)\n",
-				attr242.cur, le32_to_cpu(attr242.data));
 	return rv;
 
 out3:
-	del_timer_sync(&dd->port->cmd_timer);
-
 	/* Disable interrupts on the HBA. */
 	writel(readl(dd->mmio + HOST_CTL) & ~HOST_IRQ_EN,
 			dd->mmio + HOST_CTL);
@@ -3685,6 +3347,22 @@ out1:
 	return rv;
 }
 
+static void mtip_standby_drive(struct driver_data *dd)
+{
+	if (dd->sr)
+		return;
+
+	/*
+	 * Send standby immediate (E0h) to the drive so that it
+	 * saves its state.
+	 */
+	if (!test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags) &&
+	    !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))
+		if (mtip_standby_immediate(dd->port))
+			dev_warn(&dd->pdev->dev,
+				"STANDBY IMMEDIATE failed\n");
+}
+
 /*
  * Called to deinitialize an interface.
  *
@@ -3700,12 +3378,6 @@ static int mtip_hw_exit(struct driver_data *dd)
 	 * saves its state.
 	 */
 	if (!dd->sr) {
-		if (!test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags) &&
-		    !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))
-			if (mtip_standby_immediate(dd->port))
-				dev_warn(&dd->pdev->dev,
-					"STANDBY IMMEDIATE failed\n");
-
 		/* de-initialize the port. */
 		mtip_deinit_port(dd->port);
 
@@ -3714,8 +3386,6 @@ static int mtip_hw_exit(struct driver_data *dd)
 				dd->mmio + HOST_CTL);
 	}
 
-	del_timer_sync(&dd->port->cmd_timer);
-
 	/* Release the IRQ. */
 	irq_set_affinity_hint(dd->pdev->irq, NULL);
 	devm_free_irq(&dd->pdev->dev, dd->pdev->irq, dd);
@@ -4032,100 +3702,138 @@ static const struct block_device_operations mtip_block_ops = {
  *
  * @queue Pointer to the request queue. Unused other than to obtain
  *              the driver data structure.
- * @bio   Pointer to the BIO.
+ * @rq    Pointer to the request.
  *
  */
-static void mtip_make_request(struct request_queue *queue, struct bio *bio)
+static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
-	struct driver_data *dd = queue->queuedata;
-	struct scatterlist *sg;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-	int nents = 0;
-	int tag = 0, unaligned = 0;
+	struct driver_data *dd = hctx->queue->queuedata;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	unsigned int nents;
 
 	if (unlikely(dd->dd_flag & MTIP_DDF_STOP_IO)) {
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
 							&dd->dd_flag))) {
-			bio_endio(bio, -ENXIO);
-			return;
+			return -ENXIO;
 		}
 		if (unlikely(test_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag))) {
-			bio_endio(bio, -ENODATA);
-			return;
+			return -ENODATA;
 		}
 		if (unlikely(test_bit(MTIP_DDF_WRITE_PROTECT_BIT,
 							&dd->dd_flag) &&
-				bio_data_dir(bio))) {
-			bio_endio(bio, -ENODATA);
-			return;
-		}
-		if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))) {
-			bio_endio(bio, -ENODATA);
-			return;
-		}
-		if (test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)) {
-			bio_endio(bio, -ENXIO);
-			return;
+				rq_data_dir(rq))) {
+			return -ENODATA;
 		}
+		if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)))
+			return -ENODATA;
+		if (test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag))
+			return -ENXIO;
 	}
 
-	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
-		bio_endio(bio, mtip_send_trim(dd, bio->bi_iter.bi_sector,
-						bio_sectors(bio)));
-		return;
-	}
+	if (rq->cmd_flags & REQ_DISCARD) {
+		int err;
 
-	if (unlikely(!bio_has_data(bio))) {
-		blk_queue_flush(queue, 0);
-		bio_endio(bio, 0);
-		return;
+		err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
+		blk_mq_end_io(rq, err);
+		return 0;
 	}
 
-	if (bio_data_dir(bio) == WRITE && bio_sectors(bio) <= 64 &&
-							dd->unal_qdepth) {
-		if (bio->bi_iter.bi_sector % 8 != 0)
-			/* Unaligned on 4k boundaries */
-			unaligned = 1;
-		else if (bio_sectors(bio) % 8 != 0) /* Aligned but not 4k/8k */
-			unaligned = 1;
+	/* Create the scatter list for this request. */
+	nents = blk_rq_map_sg(hctx->queue, rq, cmd->sg);
+
+	/* Issue the read/write. */
+	mtip_hw_submit_io(dd, rq, cmd, nents, hctx);
+	return 0;
+}
+
+static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
+				  struct request *rq)
+{
+	struct driver_data *dd = hctx->queue->queuedata;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (!dd->unal_qdepth || rq_data_dir(rq) == READ)
+		return false;
+
+	/*
+	 * If unaligned depth must be limited on this controller, mark it
+	 * as unaligned if the IO isn't on a 4k boundary (start of length).
+	 */
+	if (blk_rq_sectors(rq) <= 64) {
+		if ((blk_rq_pos(rq) & 7) || (blk_rq_sectors(rq) & 7))
+			cmd->unaligned = 1;
 	}
 
-	sg = mtip_hw_get_scatterlist(dd, &tag, unaligned);
-	if (likely(sg != NULL)) {
-		blk_queue_bounce(queue, &bio);
+	if (cmd->unaligned && down_trylock(&dd->port->cmd_slot_unal))
+		return true;
 
-		if (unlikely((bio)->bi_vcnt > MTIP_MAX_SG)) {
-			dev_warn(&dd->pdev->dev,
-				"Maximum number of SGL entries exceeded\n");
-			bio_io_error(bio);
-			mtip_hw_release_scatterlist(dd, tag, unaligned);
-			return;
-		}
+	return false;
+}
 
-		/* Create the scatter list for this bio. */
-		bio_for_each_segment(bvec, bio, iter) {
-			sg_set_page(&sg[nents],
-					bvec.bv_page,
-					bvec.bv_len,
-					bvec.bv_offset);
-			nents++;
-		}
+static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	int ret;
 
-		/* Issue the read/write. */
-		mtip_hw_submit_io(dd,
-				bio->bi_iter.bi_sector,
-				bio_sectors(bio),
-				nents,
-				tag,
-				bio_endio,
-				bio,
-				bio_data_dir(bio),
-				unaligned);
-	} else
-		bio_io_error(bio);
+	if (mtip_check_unal_depth(hctx, rq))
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
+	ret = mtip_submit_request(hctx, rq);
+	if (!ret)
+		return BLK_MQ_RQ_QUEUE_OK;
+
+	rq->errors = ret;
+	return BLK_MQ_RQ_QUEUE_ERROR;
+}
+
+static void mtip_free_cmd(void *data, struct request *rq,
+			  unsigned int hctx_idx, unsigned int request_idx)
+{
+	struct driver_data *dd = data;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (!cmd->command)
+		return;
+
+	dmam_free_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
+				cmd->command, cmd->command_dma);
+}
+
+static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
+			 unsigned int request_idx, unsigned int numa_node)
+{
+	struct driver_data *dd = data;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+	cmd->command = dmam_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
+			&cmd->command_dma, GFP_KERNEL);
+	if (!cmd->command)
+		return -ENOMEM;
+
+	memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
+
+	/* Point the command headers at the command tables. */
+	cmd->command_header = dd->port->command_list +
+				(sizeof(struct mtip_cmd_hdr) * request_idx);
+	cmd->command_header_dma = dd->port->command_list_dma +
+				(sizeof(struct mtip_cmd_hdr) * request_idx);
+
+	if (host_cap_64)
+		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+
+	sg_init_table(cmd->sg, MTIP_MAX_SG);
+	return 0;
 }
 
+static struct blk_mq_ops mtip_mq_ops = {
+	.queue_rq	= mtip_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= mtip_init_cmd,
+	.exit_request	= mtip_free_cmd,
+};
+
 /*
  * Block layer initialization function.
  *
@@ -4148,11 +3856,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 	if (dd->disk)
 		goto skip_create_disk; /* hw init done, before rebuild */
 
-	/* Initialize the protocol layer. */
-	wait_for_rebuild = mtip_hw_init(dd);
-	if (wait_for_rebuild < 0) {
-		dev_err(&dd->pdev->dev,
-			"Protocol layer initialization failed\n");
+	if (mtip_hw_init(dd)) {
 		rv = -EINVAL;
 		goto protocol_init_error;
 	}
@@ -4194,29 +3898,53 @@ static int mtip_block_initialize(struct driver_data *dd)
 
 	mtip_hw_debugfs_init(dd);
 
-	/*
-	 * if rebuild pending, start the service thread, and delay the block
-	 * queue creation and add_disk()
-	 */
-	if (wait_for_rebuild == MTIP_FTL_REBUILD_MAGIC)
-		goto start_service_thread;
-
 skip_create_disk:
-	/* Allocate the request queue. */
-	dd->queue = blk_alloc_queue_node(GFP_KERNEL, dd->numa_node);
-	if (dd->queue == NULL) {
+	memset(&dd->tags, 0, sizeof(dd->tags));
+	dd->tags.ops = &mtip_mq_ops;
+	dd->tags.nr_hw_queues = 1;
+	dd->tags.queue_depth = MTIP_MAX_COMMAND_SLOTS;
+	dd->tags.reserved_tags = 1;
+	dd->tags.cmd_size = sizeof(struct mtip_cmd);
+	dd->tags.numa_node = dd->numa_node;
+	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE;
+	dd->tags.driver_data = dd;
+
+	rv = blk_mq_alloc_tag_set(&dd->tags);
+	if (rv) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
 		rv = -ENOMEM;
 		goto block_queue_alloc_init_error;
 	}
 
-	/* Attach our request function to the request queue. */
-	blk_queue_make_request(dd->queue, mtip_make_request);
+	/* Allocate the request queue. */
+	dd->queue = blk_mq_init_queue(&dd->tags);
+	if (IS_ERR(dd->queue)) {
+		dev_err(&dd->pdev->dev,
+			"Unable to allocate request queue\n");
+		rv = -ENOMEM;
+		goto block_queue_alloc_init_error;
+	}
 
 	dd->disk->queue		= dd->queue;
 	dd->queue->queuedata	= dd;
 
+	/* Initialize the protocol layer. */
+	wait_for_rebuild = mtip_hw_get_identify(dd);
+	if (wait_for_rebuild < 0) {
+		dev_err(&dd->pdev->dev,
+			"Protocol layer initialization failed\n");
+		rv = -EINVAL;
+		goto init_hw_cmds_error;
+	}
+
+	/*
+	 * if rebuild pending, start the service thread, and delay the block
+	 * queue creation and add_disk()
+	 */
+	if (wait_for_rebuild == MTIP_FTL_REBUILD_MAGIC)
+		goto start_service_thread;
+
 	/* Set device limits. */
 	set_bit(QUEUE_FLAG_NONROT, &dd->queue->queue_flags);
 	blk_queue_max_segments(dd->queue, MTIP_MAX_SG);
@@ -4295,8 +4023,9 @@ kthread_run_error:
 	del_gendisk(dd->disk);
 
 read_capacity_error:
+init_hw_cmds_error:
 	blk_cleanup_queue(dd->queue);
-
+	blk_mq_free_tag_set(&dd->tags);
 block_queue_alloc_init_error:
 	mtip_hw_debugfs_exit(dd);
 disk_index_error:
@@ -4345,6 +4074,9 @@ static int mtip_block_remove(struct driver_data *dd)
 				kobject_put(kobj);
 			}
 		}
+
+		mtip_standby_drive(dd);
+
 		/*
 		 * Delete our gendisk structure. This also removes the device
 		 * from /dev
@@ -4357,6 +4089,7 @@ static int mtip_block_remove(struct driver_data *dd)
 			if (dd->disk->queue) {
 				del_gendisk(dd->disk);
 				blk_cleanup_queue(dd->queue);
+				blk_mq_free_tag_set(&dd->tags);
 				dd->queue = NULL;
 			} else
 				put_disk(dd->disk);
@@ -4391,6 +4124,8 @@ static int mtip_block_remove(struct driver_data *dd)
  */
 static int mtip_block_shutdown(struct driver_data *dd)
 {
+	mtip_hw_shutdown(dd);
+
 	/* Delete our gendisk structure, and cleanup the blk queue. */
 	if (dd->disk) {
 		dev_info(&dd->pdev->dev,
@@ -4399,6 +4134,7 @@ static int mtip_block_shutdown(struct driver_data *dd)
 		if (dd->disk->queue) {
 			del_gendisk(dd->disk);
 			blk_cleanup_queue(dd->queue);
+			blk_mq_free_tag_set(&dd->tags);
 		} else
 			put_disk(dd->disk);
 		dd->disk  = NULL;
@@ -4408,8 +4144,6 @@ static int mtip_block_shutdown(struct driver_data *dd)
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);
 	spin_unlock(&rssd_index_lock);
-
-	mtip_hw_shutdown(dd);
 	return 0;
 }
 
@@ -4479,6 +4213,57 @@ static DEFINE_HANDLER(5);
 static DEFINE_HANDLER(6);
 static DEFINE_HANDLER(7);
 
+static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev)
+{
+	int pos;
+	unsigned short pcie_dev_ctrl;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	if (pos) {
+		pci_read_config_word(pdev,
+			pos + PCI_EXP_DEVCTL,
+			&pcie_dev_ctrl);
+		if (pcie_dev_ctrl & (1 << 11) ||
+		    pcie_dev_ctrl & (1 << 4)) {
+			dev_info(&dd->pdev->dev,
+				"Disabling ERO/No-Snoop on bridge device %04x:%04x\n",
+					pdev->vendor, pdev->device);
+			pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN |
+						PCI_EXP_DEVCTL_RELAX_EN);
+			pci_write_config_word(pdev,
+				pos + PCI_EXP_DEVCTL,
+				pcie_dev_ctrl);
+		}
+	}
+}
+
+static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev)
+{
+	/*
+	 * This workaround is specific to AMD/ATI chipset with a PCI upstream
+	 * device with device id 0x5aXX
+	 */
+	if (pdev->bus && pdev->bus->self) {
+		if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI &&
+		    ((pdev->bus->self->device & 0xff00) == 0x5a00)) {
+			mtip_disable_link_opts(dd, pdev->bus->self);
+		} else {
+			/* Check further up the topology */
+			struct pci_dev *parent_dev = pdev->bus->self;
+			if (parent_dev->bus &&
+				parent_dev->bus->parent &&
+				parent_dev->bus->parent->self &&
+				parent_dev->bus->parent->self->vendor ==
+					 PCI_VENDOR_ID_ATI &&
+				(parent_dev->bus->parent->self->device &
+					0xff00) == 0x5a00) {
+				mtip_disable_link_opts(dd,
+					parent_dev->bus->parent->self);
+			}
+		}
+	}
+}
+
 /*
  * Called for each supported PCI device detected.
  *
@@ -4630,6 +4415,8 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 		goto msi_initialize_err;
 	}
 
+	mtip_fix_ero_nosnoop(dd, pdev);
+
 	/* Initialize the block layer. */
 	rv = mtip_block_initialize(dd);
 	if (rv < 0) {
@@ -4710,8 +4497,6 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 		dev_warn(&dd->pdev->dev,
 			"Completion workers still active!\n");
 	}
-	/* Cleanup the outstanding commands */
-	mtip_command_cleanup(dd);
 
 	/* Clean up the block layer. */
 	mtip_block_remove(dd);
@@ -4737,8 +4522,6 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 
 	pcim_iounmap_regions(pdev, 1 << MTIP_ABAR);
 	pci_set_drvdata(pdev, NULL);
-	pci_dev_put(pdev);
-
 }
 
 /*
@@ -4935,13 +4718,13 @@ static int __init mtip_init(void)
  */
 static void __exit mtip_exit(void)
 {
-	debugfs_remove_recursive(dfs_parent);
-
 	/* Release the allocated major block device number. */
 	unregister_blkdev(mtip_major, MTIP_DRV_NAME);
 
 	/* Unregister the PCI driver. */
 	pci_unregister_driver(&mtip_pci_driver);
+
+	debugfs_remove_recursive(dfs_parent);
 }
 
 MODULE_AUTHOR("Micron Technology, Inc");
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index ffb955e7ccb9..4b9b554234bc 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -40,9 +40,11 @@
 #define MTIP_MAX_RETRIES	2
 
 /* Various timeout values in ms */
-#define MTIP_NCQ_COMMAND_TIMEOUT_MS       5000
-#define MTIP_IOCTL_COMMAND_TIMEOUT_MS     5000
-#define MTIP_INTERNAL_COMMAND_TIMEOUT_MS  5000
+#define MTIP_NCQ_CMD_TIMEOUT_MS      15000
+#define MTIP_IOCTL_CMD_TIMEOUT_MS    5000
+#define MTIP_INT_CMD_TIMEOUT_MS      5000
+#define MTIP_QUIESCE_IO_TIMEOUT_MS   (MTIP_NCQ_CMD_TIMEOUT_MS * \
+				     (MTIP_MAX_RETRIES + 1))
 
 /* check for timeouts every 500ms */
 #define MTIP_TIMEOUT_CHECK_PERIOD	500
@@ -331,12 +333,8 @@ struct mtip_cmd {
 	 */
 	void (*comp_func)(struct mtip_port *port,
 				int tag,
-				void *data,
+				struct mtip_cmd *cmd,
 				int status);
-	/* Additional callback function that may be called by comp_func() */
-	void (*async_callback)(void *data, int status);
-
-	void *async_data; /* Addl. data passed to async_callback() */
 
 	int scatter_ents; /* Number of scatter list entries used */
 
@@ -347,10 +345,6 @@ struct mtip_cmd {
 	int retries; /* The number of retries left for this command. */
 
 	int direction; /* Data transfer direction */
-
-	unsigned long comp_time; /* command completion time, in jiffies */
-
-	atomic_t active; /* declares if this command sent to the drive. */
 };
 
 /* Structure used to describe a port. */
@@ -436,12 +430,6 @@ struct mtip_port {
 	 * or error handling is active
 	 */
 	unsigned long cmds_to_issue[SLOTBITS_IN_LONGS];
-	/*
-	 * Array of command slots. Structure includes pointers to the
-	 * command header and command table, and completion function and data
-	 * pointers.
-	 */
-	struct mtip_cmd commands[MTIP_MAX_COMMAND_SLOTS];
 	/* Used by mtip_service_thread to wait for an event */
 	wait_queue_head_t svc_wait;
 	/*
@@ -452,13 +440,7 @@ struct mtip_port {
 	/*
 	 * Timer used to complete commands that have been active for too long.
 	 */
-	struct timer_list cmd_timer;
 	unsigned long ic_pause_timer;
-	/*
-	 * Semaphore used to block threads if there are no
-	 * command slots available.
-	 */
-	struct semaphore cmd_slot;
 
 	/* Semaphore to control queue depth of unaligned IOs */
 	struct semaphore cmd_slot_unal;
@@ -485,6 +467,8 @@ struct driver_data {
 
 	struct request_queue *queue; /* Our request queue. */
 
+	struct blk_mq_tag_set tags; /* blk_mq tags */
+
 	struct mtip_port *port; /* Pointer to the port data structure. */
 
 	unsigned product_type; /* magic value declaring the product type */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index b40af63a5476..77087a29b127 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -203,8 +203,8 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 		entry = llist_reverse_order(entry);
 		do {
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
-			end_cmd(cmd);
 			entry = entry->next;
+			end_cmd(cmd);
 		} while (entry);
 	}
 
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index c48d9084c965..608532d3f8c9 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -3944,15 +3944,14 @@ static int skd_acquire_msix(struct skd_device *skdev)
 	for (i = 0; i < SKD_MAX_MSIX_COUNT; i++)
 		entries[i].entry = i;
 
-	rc = pci_enable_msix_range(pdev, entries,
-				   SKD_MIN_MSIX_COUNT, SKD_MAX_MSIX_COUNT);
-	if (rc < 0) {
+	rc = pci_enable_msix_exact(pdev, entries, SKD_MAX_MSIX_COUNT);
+	if (rc) {
 		pr_err("(%s): failed to enable MSI-X %d\n",
 		       skd_name(skdev), rc);
 		goto msix_out;
 	}
 
-	skdev->msix_count = rc;
+	skdev->msix_count = SKD_MAX_MSIX_COUNT;
 	skdev->msix_entries = kzalloc(sizeof(struct skd_msix_entry) *
 				      skdev->msix_count, GFP_KERNEL);
 	if (!skdev->msix_entries) {
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c8f286e8d80f..f63d358f3d93 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -162,6 +162,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	unsigned int num;
 	const bool last = (req->cmd_flags & REQ_END) != 0;
 	int err;
+	bool notify = false;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
@@ -214,10 +215,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
-	if (last)
-		virtqueue_kick(vblk->vq);
-
+	if (last && virtqueue_kick_prepare(vblk->vq))
+		notify = true;
 	spin_unlock_irqrestore(&vblk->vq_lock, flags);
+
+	if (notify)
+		virtqueue_notify(vblk->vq);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index be052773ad03..f65b807e3236 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -314,7 +314,7 @@ struct xen_blkif {
 	unsigned long long			st_rd_sect;
 	unsigned long long			st_wr_sect;
 
-	wait_queue_head_t	waiting_to_free;
+	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
 	wait_queue_head_t	shutdown_wq;
 };
@@ -361,7 +361,7 @@ struct pending_req {
 #define xen_blkif_put(_b)				\
 	do {						\
 		if (atomic_dec_and_test(&(_b)->refcnt))	\
-			wake_up(&(_b)->waiting_to_free);\
+			schedule_work(&(_b)->free_work);\
 	} while (0)
 
 struct phys_req {
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 9a547e6b6ebf..3a8b810b4980 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -35,12 +35,26 @@ static void connect(struct backend_info *);
 static int connect_ring(struct backend_info *);
 static void backend_changed(struct xenbus_watch *, const char **,
 			    unsigned int);
+static void xen_blkif_free(struct xen_blkif *blkif);
+static void xen_vbd_free(struct xen_vbd *vbd);
 
 struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be)
 {
 	return be->dev;
 }
 
+/*
+ * The last request could free the device from softirq context and
+ * xen_blkif_free() can sleep.
+ */
+static void xen_blkif_deferred_free(struct work_struct *work)
+{
+	struct xen_blkif *blkif;
+
+	blkif = container_of(work, struct xen_blkif, free_work);
+	xen_blkif_free(blkif);
+}
+
 static int blkback_name(struct xen_blkif *blkif, char *buf)
 {
 	char *devpath, *devname;
@@ -121,7 +135,6 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	init_completion(&blkif->drain_complete);
 	atomic_set(&blkif->drain, 0);
 	blkif->st_print = jiffies;
-	init_waitqueue_head(&blkif->waiting_to_free);
 	blkif->persistent_gnts.rb_node = NULL;
 	spin_lock_init(&blkif->free_pages_lock);
 	INIT_LIST_HEAD(&blkif->free_pages);
@@ -132,6 +145,7 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants);
 
 	INIT_LIST_HEAD(&blkif->pending_free);
+	INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);
 
 	for (i = 0; i < XEN_BLKIF_REQS; i++) {
 		req = kzalloc(sizeof(*req), GFP_KERNEL);
@@ -231,7 +245,7 @@ static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page,
 	return 0;
 }
 
-static void xen_blkif_disconnect(struct xen_blkif *blkif)
+static int xen_blkif_disconnect(struct xen_blkif *blkif)
 {
 	if (blkif->xenblkd) {
 		kthread_stop(blkif->xenblkd);
@@ -239,9 +253,12 @@ static void xen_blkif_disconnect(struct xen_blkif *blkif)
 		blkif->xenblkd = NULL;
 	}
 
-	atomic_dec(&blkif->refcnt);
-	wait_event(blkif->waiting_to_free, atomic_read(&blkif->refcnt) == 0);
-	atomic_inc(&blkif->refcnt);
+	/* The above kthread_stop() guarantees that at this point we
+	 * don't have any discard_io or other_io requests. So, checking
+	 * for inflight IO is enough.
+	 */
+	if (atomic_read(&blkif->inflight) > 0)
+		return -EBUSY;
 
 	if (blkif->irq) {
 		unbind_from_irqhandler(blkif->irq, blkif);
@@ -252,6 +269,8 @@ static void xen_blkif_disconnect(struct xen_blkif *blkif)
 		xenbus_unmap_ring_vfree(blkif->be->dev, blkif->blk_ring);
 		blkif->blk_rings.common.sring = NULL;
 	}
+
+	return 0;
 }
 
 static void xen_blkif_free(struct xen_blkif *blkif)
@@ -259,8 +278,8 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 	struct pending_req *req, *n;
 	int i = 0, j;
 
-	if (!atomic_dec_and_test(&blkif->refcnt))
-		BUG();
+	xen_blkif_disconnect(blkif);
+	xen_vbd_free(&blkif->vbd);
 
 	/* Remove all persistent grants and the cache of ballooned pages. */
 	xen_blkbk_free_caches(blkif);
@@ -449,16 +468,15 @@ static int xen_blkbk_remove(struct xenbus_device *dev)
 		be->backend_watch.node = NULL;
 	}
 
+	dev_set_drvdata(&dev->dev, NULL);
+
 	if (be->blkif) {
 		xen_blkif_disconnect(be->blkif);
-		xen_vbd_free(&be->blkif->vbd);
-		xen_blkif_free(be->blkif);
-		be->blkif = NULL;
+		xen_blkif_put(be->blkif);
 	}
 
 	kfree(be->mode);
 	kfree(be);
-	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
 }
 
@@ -481,10 +499,15 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	struct xenbus_device *dev = be->dev;
 	struct xen_blkif *blkif = be->blkif;
 	int err;
-	int state = 0;
+	int state = 0, discard_enable;
 	struct block_device *bdev = be->blkif->vbd.bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
 
+	err = xenbus_scanf(XBT_NIL, dev->nodename, "discard-enable", "%d",
+			   &discard_enable);
+	if (err == 1 && !discard_enable)
+		return;
+
 	if (blk_queue_discard(q)) {
 		err = xenbus_printf(xbt, dev->nodename,
 			"discard-granularity", "%u",
@@ -700,7 +723,11 @@ static void frontend_changed(struct xenbus_device *dev,
 		 * Enforce precondition before potential leak point.
 		 * xen_blkif_disconnect() is idempotent.
 		 */
-		xen_blkif_disconnect(be->blkif);
+		err = xen_blkif_disconnect(be->blkif);
+		if (err) {
+			xenbus_dev_fatal(dev, err, "pending I/O");
+			break;
+		}
 
 		err = connect_ring(be);
 		if (err)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 283a30e88287..5deb235bd18f 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1635,36 +1635,24 @@ blkfront_closing(struct blkfront_info *info)
 static void blkfront_setup_discard(struct blkfront_info *info)
 {
 	int err;
-	char *type;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	unsigned int discard_secure;
 
-	type = xenbus_read(XBT_NIL, info->xbdev->otherend, "type", NULL);
-	if (IS_ERR(type))
-		return;
-
-	info->feature_secdiscard = 0;
-	if (strncmp(type, "phy", 3) == 0) {
-		err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			"discard-granularity", "%u", &discard_granularity,
-			"discard-alignment", "%u", &discard_alignment,
-			NULL);
-		if (!err) {
-			info->feature_discard = 1;
-			info->discard_granularity = discard_granularity;
-			info->discard_alignment = discard_alignment;
-		}
-		err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "discard-secure", "%d", &discard_secure,
-			    NULL);
-		if (!err)
-			info->feature_secdiscard = discard_secure;
-
-	} else if (strncmp(type, "file", 4) == 0)
-		info->feature_discard = 1;
-
-	kfree(type);
+	info->feature_discard = 1;
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+		"discard-granularity", "%u", &discard_granularity,
+		"discard-alignment", "%u", &discard_alignment,
+		NULL);
+	if (!err) {
+		info->discard_granularity = discard_granularity;
+		info->discard_alignment = discard_alignment;
+	}
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+		    "discard-secure", "%d", &discard_secure,
+		    NULL);
+	if (!err)
+		info->feature_secdiscard = !!discard_secure;
 }
 
 static int blkfront_setup_indirect(struct blkfront_info *info)