Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 59795700 authored by Bob Liu's avatar Bob Liu Committed by Konrad Rzeszutek Wilk
Browse files

xen/blkback: separate ring information out of struct xen_blkif 



Split per ring information to an new structure "xen_blkif_ring", so that one vbd
device can be associated with one or more rings/hardware queues.

Introduce 'pers_gnts_lock' to protect the pool of persistent grants since we
may have multi backend threads.

This patch is a preparation for supporting multi hardware queues/rings.

Signed-off-by: default avatarArianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: default avatarBob Liu <bob.liu@oracle.com>
Signed-off-by: default avatarKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
v2: Align the variables in the structure.
parent 45fc8264

drivers/block/xen-blkback/blkback.c

+133 −102
Original line number Diff line number Diff line
@@ -173,11 +173,11 @@ static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num) 


#define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))



static int do_block_io_op(struct xen_blkif *blkif);

static int dispatch_rw_block_io(struct xen_blkif *blkif,

static int do_block_io_op(struct xen_blkif_ring *ring);

static int dispatch_rw_block_io(struct xen_blkif_ring *ring,

				struct blkif_request *req,

				struct pending_req *pending_req);

static void make_response(struct xen_blkif *blkif, u64 id,

static void make_response(struct xen_blkif_ring *ring, u64 id,

			  unsigned short op, int st);



#define foreach_grant_safe(pos, n, rbtree, node) \
@@ -189,14 +189,8 @@ static void make_response(struct xen_blkif *blkif, u64 id, 




/*

 * We don't need locking around the persistent grant helpers

 * because blkback uses a single-thread for each backed, so we

 * can be sure that this functions will never be called recursively.

 *

 * The only exception to that is put_persistent_grant, that can be called

 * from interrupt context (by xen_blkbk_unmap), so we have to use atomic

 * bit operations to modify the flags of a persistent grant and to count

 * the number of used grants.

 * pers_gnts_lock must be used around all the persistent grant helpers

 * because blkback may use multi-thread/queue for each backend.

 */

static int add_persistent_gnt(struct xen_blkif *blkif,

			       struct persistent_gnt *persistent_gnt)
@@ -204,6 +198,7 @@ static int add_persistent_gnt(struct xen_blkif *blkif, 
	struct rb_node **new = NULL, *parent = NULL;

	struct persistent_gnt *this;



	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));

	if (blkif->persistent_gnt_c >= xen_blkif_max_pgrants) {

		if (!blkif->vbd.overflow_max_grants)

			blkif->vbd.overflow_max_grants = 1;
@@ -241,6 +236,7 @@ static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif, 
	struct persistent_gnt *data;

	struct rb_node *node = NULL;



	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));

	node = blkif->persistent_gnts.rb_node;

	while (node) {

		data = container_of(node, struct persistent_gnt, node);
@@ -265,6 +261,7 @@ static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif, 
static void put_persistent_gnt(struct xen_blkif *blkif,

                               struct persistent_gnt *persistent_gnt)

{

	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));

	if(!test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags))

		pr_alert_ratelimited("freeing a grant already unused\n");

	set_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags);
@@ -286,6 +283,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, 
	unmap_data.unmap_ops = unmap;

	unmap_data.kunmap_ops = NULL;



	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));

	foreach_grant_safe(persistent_gnt, n, root, node) {

		BUG_ON(persistent_gnt->handle ==

			BLKBACK_INVALID_HANDLE);
@@ -322,11 +320,13 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) 
	int segs_to_unmap = 0;

	struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work);

	struct gntab_unmap_queue_data unmap_data;

	unsigned long flags;



	unmap_data.pages = pages;

	unmap_data.unmap_ops = unmap;

	unmap_data.kunmap_ops = NULL;



	spin_lock_irqsave(&blkif->pers_gnts_lock, flags);

	while(!list_empty(&blkif->persistent_purge_list)) {

		persistent_gnt = list_first_entry(&blkif->persistent_purge_list,

		                                  struct persistent_gnt,
@@ -348,6 +348,7 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work) 
		}

		kfree(persistent_gnt);

	}

	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);

	if (segs_to_unmap > 0) {

		unmap_data.count = segs_to_unmap;

		BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
@@ -362,16 +363,18 @@ static void purge_persistent_gnt(struct xen_blkif *blkif) 
	unsigned int num_clean, total;

	bool scan_used = false, clean_used = false;

	struct rb_root *root;

	unsigned long flags;



	spin_lock_irqsave(&blkif->pers_gnts_lock, flags);

	if (blkif->persistent_gnt_c < xen_blkif_max_pgrants ||

	    (blkif->persistent_gnt_c == xen_blkif_max_pgrants &&

	    !blkif->vbd.overflow_max_grants)) {

		return;

		goto out;

	}



	if (work_busy(&blkif->persistent_purge_work)) {

		pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n");

		return;

		goto out;

	}



	num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN;
@@ -379,7 +382,7 @@ static void purge_persistent_gnt(struct xen_blkif *blkif) 
	num_clean = min(blkif->persistent_gnt_c, num_clean);

	if ((num_clean == 0) ||

	    (num_clean > (blkif->persistent_gnt_c - atomic_read(&blkif->persistent_gnt_in_use))))

		return;

		goto out;



	/*

	 * At this point, we can assure that there will be no calls
@@ -436,29 +439,35 @@ static void purge_persistent_gnt(struct xen_blkif *blkif) 
	}



	blkif->persistent_gnt_c -= (total - num_clean);

	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);

	blkif->vbd.overflow_max_grants = 0;



	/* We can defer this work */

	schedule_work(&blkif->persistent_purge_work);

	pr_debug("Purged %u/%u\n", (total - num_clean), total);

	return;



out:

	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);



	return;

}



/*

 * Retrieve from the 'pending_reqs' a free pending_req structure to be used.

 */

static struct pending_req *alloc_req(struct xen_blkif *blkif)

static struct pending_req *alloc_req(struct xen_blkif_ring *ring)

{

	struct pending_req *req = NULL;

	unsigned long flags;



	spin_lock_irqsave(&blkif->pending_free_lock, flags);

	if (!list_empty(&blkif->pending_free)) {

		req = list_entry(blkif->pending_free.next, struct pending_req,

	spin_lock_irqsave(&ring->pending_free_lock, flags);

	if (!list_empty(&ring->pending_free)) {

		req = list_entry(ring->pending_free.next, struct pending_req,

				 free_list);

		list_del(&req->free_list);

	}

	spin_unlock_irqrestore(&blkif->pending_free_lock, flags);

	spin_unlock_irqrestore(&ring->pending_free_lock, flags);

	return req;

}
@@ -466,17 +475,17 @@ static struct pending_req *alloc_req(struct xen_blkif *blkif) 
 * Return the 'pending_req' structure back to the freepool. We also

 * wake up the thread if it was waiting for a free page.

 */

static void free_req(struct xen_blkif *blkif, struct pending_req *req)

static void free_req(struct xen_blkif_ring *ring, struct pending_req *req)

{

	unsigned long flags;

	int was_empty;



	spin_lock_irqsave(&blkif->pending_free_lock, flags);

	was_empty = list_empty(&blkif->pending_free);

	list_add(&req->free_list, &blkif->pending_free);

	spin_unlock_irqrestore(&blkif->pending_free_lock, flags);

	spin_lock_irqsave(&ring->pending_free_lock, flags);

	was_empty = list_empty(&ring->pending_free);

	list_add(&req->free_list, &ring->pending_free);

	spin_unlock_irqrestore(&ring->pending_free_lock, flags);

	if (was_empty)

		wake_up(&blkif->pending_free_wq);

		wake_up(&ring->pending_free_wq);

}



/*
@@ -556,10 +565,10 @@ static void xen_vbd_resize(struct xen_blkif *blkif) 
/*

 * Notification from the guest OS.

 */

static void blkif_notify_work(struct xen_blkif *blkif)

static void blkif_notify_work(struct xen_blkif_ring *ring)

{

	blkif->waiting_reqs = 1;

	wake_up(&blkif->wq);

	ring->waiting_reqs = 1;

	wake_up(&ring->wq);

}



irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
@@ -590,7 +599,8 @@ static void print_stats(struct xen_blkif *blkif) 


int xen_blkif_schedule(void *arg)

{

	struct xen_blkif *blkif = arg;

	struct xen_blkif_ring *ring = arg;

	struct xen_blkif *blkif = ring->blkif;

	struct xen_vbd *vbd = &blkif->vbd;

	unsigned long timeout;

	int ret;
@@ -606,27 +616,27 @@ int xen_blkif_schedule(void *arg) 
		timeout = msecs_to_jiffies(LRU_INTERVAL);



		timeout = wait_event_interruptible_timeout(

			blkif->wq,

			blkif->waiting_reqs || kthread_should_stop(),

			ring->wq,

			ring->waiting_reqs || kthread_should_stop(),

			timeout);

		if (timeout == 0)

			goto purge_gnt_list;

		timeout = wait_event_interruptible_timeout(

			blkif->pending_free_wq,

			!list_empty(&blkif->pending_free) ||

			ring->pending_free_wq,

			!list_empty(&ring->pending_free) ||

			kthread_should_stop(),

			timeout);

		if (timeout == 0)

			goto purge_gnt_list;



		blkif->waiting_reqs = 0;

		ring->waiting_reqs = 0;

		smp_mb(); /* clear flag *before* checking for work */



		ret = do_block_io_op(blkif);

		ret = do_block_io_op(ring);

		if (ret > 0)

			blkif->waiting_reqs = 1;

			ring->waiting_reqs = 1;

		if (ret == -EACCES)

			wait_event_interruptible(blkif->shutdown_wq,

			wait_event_interruptible(ring->shutdown_wq,

						 kthread_should_stop());



purge_gnt_list:
@@ -649,7 +659,7 @@ int xen_blkif_schedule(void *arg) 
	if (log_stats)

		print_stats(blkif);



	blkif->xenblkd = NULL;

	ring->xenblkd = NULL;

	xen_blkif_put(blkif);



	return 0;
@@ -658,32 +668,40 @@ int xen_blkif_schedule(void *arg) 
/*

 * Remove persistent grants and empty the pool of free pages

 */

void xen_blkbk_free_caches(struct xen_blkif *blkif)

void xen_blkbk_free_caches(struct xen_blkif_ring *ring)

{

	struct xen_blkif *blkif = ring->blkif;

	unsigned long flags;



	/* Free all persistent grant pages */

	spin_lock_irqsave(&blkif->pers_gnts_lock, flags);

	if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))

		free_persistent_gnts(blkif, &blkif->persistent_gnts,

			blkif->persistent_gnt_c);



	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));

	blkif->persistent_gnt_c = 0;

	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);



	/* Since we are shutting down remove all pages from the buffer */

	shrink_free_pagepool(blkif, 0 /* All */);

}



static unsigned int xen_blkbk_unmap_prepare(

	struct xen_blkif *blkif,

	struct xen_blkif_ring *ring,

	struct grant_page **pages,

	unsigned int num,

	struct gnttab_unmap_grant_ref *unmap_ops,

	struct page **unmap_pages)

{

	unsigned int i, invcount = 0;

	unsigned long flags;



	for (i = 0; i < num; i++) {

		if (pages[i]->persistent_gnt != NULL) {

			put_persistent_gnt(blkif, pages[i]->persistent_gnt);

			spin_lock_irqsave(&ring->blkif->pers_gnts_lock, flags);

			put_persistent_gnt(ring->blkif, pages[i]->persistent_gnt);

			spin_unlock_irqrestore(&ring->blkif->pers_gnts_lock, flags);

			continue;

		}

		if (pages[i]->handle == BLKBACK_INVALID_HANDLE)
@@ -701,16 +719,17 @@ static unsigned int xen_blkbk_unmap_prepare( 
static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_queue_data *data)

{

	struct pending_req *pending_req = (struct pending_req *)(data->data);

	struct xen_blkif *blkif = pending_req->blkif;

	struct xen_blkif_ring *ring = pending_req->ring;

	struct xen_blkif *blkif = ring->blkif;



	/* BUG_ON used to reproduce existing behaviour,

	   but is this the best way to deal with this? */

	BUG_ON(result);



	put_free_pages(blkif, data->pages, data->count);

	make_response(blkif, pending_req->id,

	make_response(ring, pending_req->id,

		      pending_req->operation, pending_req->status);

	free_req(blkif, pending_req);

	free_req(ring, pending_req);

	/*

	 * Make sure the request is freed before releasing blkif,

	 * or there could be a race between free_req and the
@@ -723,7 +742,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_ 
	 * pending_free_wq if there's a drain going on, but it has

	 * to be taken into account if the current model is changed.

	 */

	if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {

	if (atomic_dec_and_test(&ring->inflight) && atomic_read(&blkif->drain)) {

		complete(&blkif->drain_complete);

	}

	xen_blkif_put(blkif);
@@ -732,11 +751,11 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_ 
static void xen_blkbk_unmap_and_respond(struct pending_req *req)

{

	struct gntab_unmap_queue_data* work = &req->gnttab_unmap_data;

	struct xen_blkif *blkif = req->blkif;

	struct xen_blkif_ring *ring = req->ring;

	struct grant_page **pages = req->segments;

	unsigned int invcount;



	invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_segs,

	invcount = xen_blkbk_unmap_prepare(ring, pages, req->nr_segs,

					   req->unmap, req->unmap_pages);



	work->data = req;
@@ -757,7 +776,7 @@ static void xen_blkbk_unmap_and_respond(struct pending_req *req) 
 * of hypercalls, but since this is only used in error paths there's

 * no real need.

 */

static void xen_blkbk_unmap(struct xen_blkif *blkif,

static void xen_blkbk_unmap(struct xen_blkif_ring *ring,

                            struct grant_page *pages[],

                            int num)

{
@@ -769,19 +788,19 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif, 
	while (num) {

		unsigned int batch = min(num, BLKIF_MAX_SEGMENTS_PER_REQUEST);



		invcount = xen_blkbk_unmap_prepare(blkif, pages, batch,

		invcount = xen_blkbk_unmap_prepare(ring, pages, batch,

						   unmap, unmap_pages);

		if (invcount) {

			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);

			BUG_ON(ret);

			put_free_pages(blkif, unmap_pages, invcount);

			put_free_pages(ring->blkif, unmap_pages, invcount);

		}

		pages += batch;

		num -= batch;

	}

}



static int xen_blkbk_map(struct xen_blkif *blkif,

static int xen_blkbk_map(struct xen_blkif_ring *ring,

			 struct grant_page *pages[],

			 int num, bool ro)

{
@@ -794,6 +813,8 @@ static int xen_blkbk_map(struct xen_blkif *blkif, 
	int ret = 0;

	int last_map = 0, map_until = 0;

	int use_persistent_gnts;

	struct xen_blkif *blkif = ring->blkif;

	unsigned long irq_flags;



	use_persistent_gnts = (blkif->vbd.feature_gnt_persistent);
@@ -806,10 +827,13 @@ static int xen_blkbk_map(struct xen_blkif *blkif, 
	for (i = map_until; i < num; i++) {

		uint32_t flags;



		if (use_persistent_gnts)

		if (use_persistent_gnts) {

			spin_lock_irqsave(&blkif->pers_gnts_lock, irq_flags);

			persistent_gnt = get_persistent_gnt(

				blkif,

				pages[i]->gref);

			spin_unlock_irqrestore(&blkif->pers_gnts_lock, irq_flags);

		}



		if (persistent_gnt) {

			/*
@@ -880,8 +904,10 @@ static int xen_blkbk_map(struct xen_blkif *blkif, 
			persistent_gnt->gnt = map[new_map_idx].ref;

			persistent_gnt->handle = map[new_map_idx].handle;

			persistent_gnt->page = pages[seg_idx]->page;

			spin_lock_irqsave(&blkif->pers_gnts_lock, irq_flags);

			if (add_persistent_gnt(blkif,

			                       persistent_gnt)) {

				spin_unlock_irqrestore(&blkif->pers_gnts_lock, irq_flags);

				kfree(persistent_gnt);

				persistent_gnt = NULL;

				goto next;
@@ -890,6 +916,7 @@ static int xen_blkbk_map(struct xen_blkif *blkif, 
			pr_debug("grant %u added to the tree of persistent grants, using %u/%u\n",

				 persistent_gnt->gnt, blkif->persistent_gnt_c,

				 xen_blkif_max_pgrants);

			spin_unlock_irqrestore(&blkif->pers_gnts_lock, irq_flags);

			goto next;

		}

		if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) {
@@ -921,7 +948,7 @@ static int xen_blkbk_map_seg(struct pending_req *pending_req) 
{

	int rc;



	rc = xen_blkbk_map(pending_req->blkif, pending_req->segments,

	rc = xen_blkbk_map(pending_req->ring, pending_req->segments,

			   pending_req->nr_segs,

	                   (pending_req->operation != BLKIF_OP_READ));
@@ -934,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, 
				    struct phys_req *preq)

{

	struct grant_page **pages = pending_req->indirect_pages;

	struct xen_blkif *blkif = pending_req->blkif;

	struct xen_blkif_ring *ring = pending_req->ring;

	int indirect_grefs, rc, n, nseg, i;

	struct blkif_request_segment *segments = NULL;
@@ -945,7 +972,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, 
	for (i = 0; i < indirect_grefs; i++)

		pages[i]->gref = req->u.indirect.indirect_grefs[i];



	rc = xen_blkbk_map(blkif, pages, indirect_grefs, true);

	rc = xen_blkbk_map(ring, pages, indirect_grefs, true);

	if (rc)

		goto unmap;
@@ -972,15 +999,16 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, 
unmap:

	if (segments)

		kunmap_atomic(segments);

	xen_blkbk_unmap(blkif, pages, indirect_grefs);

	xen_blkbk_unmap(ring, pages, indirect_grefs);

	return rc;

}



static int dispatch_discard_io(struct xen_blkif *blkif,

static int dispatch_discard_io(struct xen_blkif_ring *ring,

				struct blkif_request *req)

{

	int err = 0;

	int status = BLKIF_RSP_OKAY;

	struct xen_blkif *blkif = ring->blkif;

	struct block_device *bdev = blkif->vbd.bdev;

	unsigned long secure;

	struct phys_req preq;
@@ -1013,26 +1041,28 @@ static int dispatch_discard_io(struct xen_blkif *blkif, 
	} else if (err)

		status = BLKIF_RSP_ERROR;



	make_response(blkif, req->u.discard.id, req->operation, status);

	make_response(ring, req->u.discard.id, req->operation, status);

	xen_blkif_put(blkif);

	return err;

}



static int dispatch_other_io(struct xen_blkif *blkif,

static int dispatch_other_io(struct xen_blkif_ring *ring,

			     struct blkif_request *req,

			     struct pending_req *pending_req)

{

	free_req(blkif, pending_req);

	make_response(blkif, req->u.other.id, req->operation,

	free_req(ring, pending_req);

	make_response(ring, req->u.other.id, req->operation,

		      BLKIF_RSP_EOPNOTSUPP);

	return -EIO;

}



static void xen_blk_drain_io(struct xen_blkif *blkif)

static void xen_blk_drain_io(struct xen_blkif_ring *ring)

{

	struct xen_blkif *blkif = ring->blkif;



	atomic_set(&blkif->drain, 1);

	do {

		if (atomic_read(&blkif->inflight) == 0)

		if (atomic_read(&ring->inflight) == 0)

			break;

		wait_for_completion_interruptible_timeout(

				&blkif->drain_complete, HZ);
@@ -1053,12 +1083,12 @@ static void __end_block_io_op(struct pending_req *pending_req, int error) 
	if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) &&

	    (error == -EOPNOTSUPP)) {

		pr_debug("flush diskcache op failed, not supported\n");

		xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0);

		xen_blkbk_flush_diskcache(XBT_NIL, pending_req->ring->blkif->be, 0);

		pending_req->status = BLKIF_RSP_EOPNOTSUPP;

	} else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) &&

		    (error == -EOPNOTSUPP)) {

		pr_debug("write barrier op failed, not supported\n");

		xen_blkbk_barrier(XBT_NIL, pending_req->blkif->be, 0);

		xen_blkbk_barrier(XBT_NIL, pending_req->ring->blkif->be, 0);

		pending_req->status = BLKIF_RSP_EOPNOTSUPP;

	} else if (error) {

		pr_debug("Buffer not up-to-date at end of operation,"
@@ -1092,9 +1122,9 @@ static void end_block_io_op(struct bio *bio) 
 * and transmute  it to the block API to hand it over to the proper block disk.

 */

static int

__do_block_io_op(struct xen_blkif *blkif)

__do_block_io_op(struct xen_blkif_ring *ring)

{

	union blkif_back_rings *blk_rings = &blkif->blk_rings;

	union blkif_back_rings *blk_rings = &ring->blk_rings;

	struct blkif_request req;

	struct pending_req *pending_req;

	RING_IDX rc, rp;
@@ -1107,7 +1137,7 @@ __do_block_io_op(struct xen_blkif *blkif) 
	if (RING_REQUEST_PROD_OVERFLOW(&blk_rings->common, rp)) {

		rc = blk_rings->common.rsp_prod_pvt;

		pr_warn("Frontend provided bogus ring requests (%d - %d = %d). Halting ring processing on dev=%04x\n",

			rp, rc, rp - rc, blkif->vbd.pdevice);

			rp, rc, rp - rc, ring->blkif->vbd.pdevice);

		return -EACCES;

	}

	while (rc != rp) {
@@ -1120,14 +1150,14 @@ __do_block_io_op(struct xen_blkif *blkif) 
			break;

		}



		pending_req = alloc_req(blkif);

		pending_req = alloc_req(ring);

		if (NULL == pending_req) {

			blkif->st_oo_req++;

			ring->blkif->st_oo_req++;

			more_to_do = 1;

			break;

		}



		switch (blkif->blk_protocol) {

		switch (ring->blkif->blk_protocol) {

		case BLKIF_PROTOCOL_NATIVE:

			memcpy(&req, RING_GET_REQUEST(&blk_rings->native, rc), sizeof(req));

			break;
@@ -1151,16 +1181,16 @@ __do_block_io_op(struct xen_blkif *blkif) 
		case BLKIF_OP_WRITE_BARRIER:

		case BLKIF_OP_FLUSH_DISKCACHE:

		case BLKIF_OP_INDIRECT:

			if (dispatch_rw_block_io(blkif, &req, pending_req))

			if (dispatch_rw_block_io(ring, &req, pending_req))

				goto done;

			break;

		case BLKIF_OP_DISCARD:

			free_req(blkif, pending_req);

			if (dispatch_discard_io(blkif, &req))

			free_req(ring, pending_req);

			if (dispatch_discard_io(ring, &req))

				goto done;

			break;

		default:

			if (dispatch_other_io(blkif, &req, pending_req))

			if (dispatch_other_io(ring, &req, pending_req))

				goto done;

			break;

		}
@@ -1173,13 +1203,13 @@ __do_block_io_op(struct xen_blkif *blkif) 
}



static int

do_block_io_op(struct xen_blkif *blkif)

do_block_io_op(struct xen_blkif_ring *ring)

{

	union blkif_back_rings *blk_rings = &blkif->blk_rings;

	union blkif_back_rings *blk_rings = &ring->blk_rings;

	int more_to_do;



	do {

		more_to_do = __do_block_io_op(blkif);

		more_to_do = __do_block_io_op(ring);

		if (more_to_do)

			break;
@@ -1192,7 +1222,7 @@ do_block_io_op(struct xen_blkif *blkif) 
 * Transmutation of the 'struct blkif_request' to a proper 'struct bio'

 * and call the 'submit_bio' to pass it to the underlying storage.

 */

static int dispatch_rw_block_io(struct xen_blkif *blkif,

static int dispatch_rw_block_io(struct xen_blkif_ring *ring,

				struct blkif_request *req,

				struct pending_req *pending_req)

{
@@ -1220,17 +1250,17 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 


	switch (req_operation) {

	case BLKIF_OP_READ:

		blkif->st_rd_req++;

		ring->blkif->st_rd_req++;

		operation = READ;

		break;

	case BLKIF_OP_WRITE:

		blkif->st_wr_req++;

		ring->blkif->st_wr_req++;

		operation = WRITE_ODIRECT;

		break;

	case BLKIF_OP_WRITE_BARRIER:

		drain = true;

	case BLKIF_OP_FLUSH_DISKCACHE:

		blkif->st_f_req++;

		ring->blkif->st_f_req++;

		operation = WRITE_FLUSH;

		break;

	default:
@@ -1255,7 +1285,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 


	preq.nr_sects      = 0;



	pending_req->blkif     = blkif;

	pending_req->ring      = ring;

	pending_req->id        = req->u.rw.id;

	pending_req->operation = req_operation;

	pending_req->status    = BLKIF_RSP_OKAY;
@@ -1282,12 +1312,12 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
			goto fail_response;

	}



	if (xen_vbd_translate(&preq, blkif, operation) != 0) {

	if (xen_vbd_translate(&preq, ring->blkif, operation) != 0) {

		pr_debug("access denied: %s of [%llu,%llu] on dev=%04x\n",

			 operation == READ ? "read" : "write",

			 preq.sector_number,

			 preq.sector_number + preq.nr_sects,

			 blkif->vbd.pdevice);

			 ring->blkif->vbd.pdevice);

		goto fail_response;

	}
@@ -1299,7 +1329,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
		if (((int)preq.sector_number|(int)seg[i].nsec) &

		    ((bdev_logical_block_size(preq.bdev) >> 9) - 1)) {

			pr_debug("Misaligned I/O request from domain %d\n",

				 blkif->domid);

				 ring->blkif->domid);

			goto fail_response;

		}

	}
@@ -1308,7 +1338,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
	 * issue the WRITE_FLUSH.

	 */

	if (drain)

		xen_blk_drain_io(pending_req->blkif);

		xen_blk_drain_io(pending_req->ring);



	/*

	 * If we have failed at this point, we need to undo the M2P override,
@@ -1323,8 +1353,8 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
	 * This corresponding xen_blkif_put is done in __end_block_io_op, or

	 * below (in "!bio") if we are handling a BLKIF_OP_DISCARD.

	 */

	xen_blkif_get(blkif);

	atomic_inc(&blkif->inflight);

	xen_blkif_get(ring->blkif);

	atomic_inc(&ring->inflight);



	for (i = 0; i < nseg; i++) {

		while ((bio == NULL) ||
@@ -1372,19 +1402,19 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
	blk_finish_plug(&plug);



	if (operation == READ)

		blkif->st_rd_sect += preq.nr_sects;

		ring->blkif->st_rd_sect += preq.nr_sects;

	else if (operation & WRITE)

		blkif->st_wr_sect += preq.nr_sects;

		ring->blkif->st_wr_sect += preq.nr_sects;



	return 0;



 fail_flush:

	xen_blkbk_unmap(blkif, pending_req->segments,

	xen_blkbk_unmap(ring, pending_req->segments,

	                pending_req->nr_segs);

 fail_response:

	/* Haven't submitted any bio's yet. */

	make_response(blkif, req->u.rw.id, req_operation, BLKIF_RSP_ERROR);

	free_req(blkif, pending_req);

	make_response(ring, req->u.rw.id, req_operation, BLKIF_RSP_ERROR);

	free_req(ring, pending_req);

	msleep(1); /* back off a bit */

	return -EIO;
@@ -1402,21 +1432,22 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, 
/*

 * Put a response on the ring on how the operation fared.

 */

static void make_response(struct xen_blkif *blkif, u64 id,

static void make_response(struct xen_blkif_ring *ring, u64 id,

			  unsigned short op, int st)

{

	struct blkif_response  resp;

	unsigned long     flags;

	union blkif_back_rings *blk_rings = &blkif->blk_rings;

	union blkif_back_rings *blk_rings;

	int notify;



	resp.id        = id;

	resp.operation = op;

	resp.status    = st;



	spin_lock_irqsave(&blkif->blk_ring_lock, flags);

	spin_lock_irqsave(&ring->blk_ring_lock, flags);

	blk_rings = &ring->blk_rings;

	/* Place on the response ring for the relevant domain. */

	switch (blkif->blk_protocol) {

	switch (ring->blkif->blk_protocol) {

	case BLKIF_PROTOCOL_NATIVE:

		memcpy(RING_GET_RESPONSE(&blk_rings->native, blk_rings->native.rsp_prod_pvt),

		       &resp, sizeof(resp));
@@ -1434,9 +1465,9 @@ static void make_response(struct xen_blkif *blkif, u64 id, 
	}

	blk_rings->common.rsp_prod_pvt++;

	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&blk_rings->common, notify);

	spin_unlock_irqrestore(&blkif->blk_ring_lock, flags);

	spin_unlock_irqrestore(&ring->blk_ring_lock, flags);

	if (notify)

		notify_remote_via_irq(blkif->irq);

		notify_remote_via_irq(ring->irq);

}



static int __init xen_blkif_init(void)

drivers/block/xen-blkback/common.h

+33 −23
Original line number Diff line number Diff line
@@ -269,34 +269,50 @@ struct persistent_gnt { 
	struct list_head remove_node;

};



/* Per-ring information. */

struct xen_blkif_ring {

	/* Physical parameters of the comms window. */

	unsigned int		irq;

	union blkif_back_rings	blk_rings;

	void			*blk_ring;

	/* Private fields. */

	spinlock_t		blk_ring_lock;



	wait_queue_head_t	wq;

	atomic_t		inflight;

	/* One thread per blkif ring. */

	struct task_struct	*xenblkd;

	unsigned int		waiting_reqs;



	/* List of all 'pending_req' available */

	struct list_head	pending_free;

	/* And its spinlock. */

	spinlock_t		pending_free_lock;

	wait_queue_head_t	pending_free_wq;



	struct work_struct	free_work;

	/* Thread shutdown wait queue. */

	wait_queue_head_t	shutdown_wq;

	struct xen_blkif 	*blkif;

};



struct xen_blkif {

	/* Unique identifier for this interface. */

	domid_t			domid;

	unsigned int		handle;

	/* Physical parameters of the comms window. */

	unsigned int		irq;

	/* Comms information. */

	enum blkif_protocol	blk_protocol;

	union blkif_back_rings	blk_rings;

	void			*blk_ring;

	/* The VBD attached to this interface. */

	struct xen_vbd		vbd;

	/* Back pointer to the backend_info. */

	struct backend_info	*be;

	/* Private fields. */

	spinlock_t		blk_ring_lock;

	atomic_t		refcnt;



	wait_queue_head_t	wq;

	/* for barrier (drain) requests */

	struct completion	drain_complete;

	atomic_t		drain;

	atomic_t		inflight;

	/* One thread per one blkif. */

	struct task_struct	*xenblkd;

	unsigned int		waiting_reqs;



	/* tree to store persistent grants */

	spinlock_t		pers_gnts_lock;

	struct rb_root		persistent_gnts;

	unsigned int		persistent_gnt_c;

	atomic_t		persistent_gnt_in_use;
@@ -311,12 +327,6 @@ struct xen_blkif { 
	int			free_pages_num;

	struct list_head	free_pages;



	/* List of all 'pending_req' available */

	struct list_head	pending_free;

	/* And its spinlock. */

	spinlock_t		pending_free_lock;

	wait_queue_head_t	pending_free_wq;



	/* statistics */

	unsigned long		st_print;

	unsigned long long			st_rd_req;
@@ -328,9 +338,9 @@ struct xen_blkif { 
	unsigned long long			st_wr_sect;



	struct work_struct	free_work;

	/* Thread shutdown wait queue. */

	wait_queue_head_t	shutdown_wq;

	unsigned int 		nr_ring_pages;

	/* All rings for this device. */

	struct xen_blkif_ring 	ring;

};



struct seg_buf {
@@ -352,7 +362,7 @@ struct grant_page { 
 * response queued for it, with the saved 'id' passed back.

 */

struct pending_req {

	struct xen_blkif	*blkif;

	struct xen_blkif_ring   *ring;

	u64			id;

	int			nr_segs;

	atomic_t		pendcnt;
@@ -394,7 +404,7 @@ int xen_blkif_xenbus_init(void); 
irqreturn_t xen_blkif_be_int(int irq, void *dev_id);

int xen_blkif_schedule(void *arg);

int xen_blkif_purge_persistent(void *arg);

void xen_blkbk_free_caches(struct xen_blkif *blkif);

void xen_blkbk_free_caches(struct xen_blkif_ring *ring);



int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,

			      struct backend_info *be, int state);

drivers/block/xen-blkback/xenbus.c

+49 −47

File changed.

Preview size limit exceeded, changes collapsed.