lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1447470739-18136-11-git-send-email-bob.liu@oracle.com>
Date:	Sat, 14 Nov 2015 11:12:19 +0800
From:	Bob Liu <bob.liu@...cle.com>
To:	xen-devel@...ts.xen.org
Cc:	linux-kernel@...r.kernel.org, roger.pau@...rix.com,
	konrad.wilk@...cle.com, felipe.franciosi@...rix.com, axboe@...com,
	avanzini.arianna@...il.com, rafal.mielniczuk@...rix.com,
	jonathan.davies@...rix.com, david.vrabel@...rix.com,
	Bob Liu <bob.liu@...cle.com>
Subject: [PATCH v5 10/10] xen/blkback: make pool of persistent grants and free pages per-queue

Make pool of persistent grants and free pages per-queue/ring instead of
per-device to get better scalability.

Test was done based on null_blk driver:
dom0: v4.2-rc8 16vcpus 10GB "modprobe null_blk"
domu: v4.2-rc8 16vcpus 10GB

[test]
rw=read
direct=1
ioengine=libaio
bs=4k
time_based
runtime=30
filename=/dev/xvdb
numjobs=16
iodepth=64
iodepth_batch=64
iodepth_batch_complete=64
group_reporting

Results:
iops1: After commit("xen/blkfront: make persistent grants per-queue").
iops2: After this commit.

Queues:			  1 	   4 	  	  8 	 	 16
Iops orig(k):		810 	1064 		780 		700
Iops1(k):		810     1230(~20%)	1024(~20%)	850(~20%)
Iops2(k):		810     1410(~35%)	1354(~75%)      1440(~100%)

With 4 queues after this commit we can get ~75% increase in IOPS, and
performance won't drop if incresing queue numbers.

Please find the respective chart in this link:
https://www.dropbox.com/s/agrcy2pbzbsvmwv/iops.png?dl=0

Signed-off-by: Bob Liu <bob.liu@...cle.com>
---
 drivers/block/xen-blkback/blkback.c |  202 ++++++++++++++++-------------------
 drivers/block/xen-blkback/common.h  |   32 +++---
 drivers/block/xen-blkback/xenbus.c  |   21 ++--
 3 files changed, 118 insertions(+), 137 deletions(-)

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index acedc46..0e8a04d 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -122,60 +122,60 @@ module_param(log_stats, int, 0644);
 /* Number of free pages to remove on each call to gnttab_free_pages */
 #define NUM_BATCH_FREE_PAGES 10
 
-static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
+static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkif->free_pages_lock, flags);
-	if (list_empty(&blkif->free_pages)) {
-		BUG_ON(blkif->free_pages_num != 0);
-		spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+	spin_lock_irqsave(&ring->free_pages_lock, flags);
+	if (list_empty(&ring->free_pages)) {
+		BUG_ON(ring->free_pages_num != 0);
+		spin_unlock_irqrestore(&ring->free_pages_lock, flags);
 		return gnttab_alloc_pages(1, page);
 	}
-	BUG_ON(blkif->free_pages_num == 0);
-	page[0] = list_first_entry(&blkif->free_pages, struct page, lru);
+	BUG_ON(ring->free_pages_num == 0);
+	page[0] = list_first_entry(&ring->free_pages, struct page, lru);
 	list_del(&page[0]->lru);
-	blkif->free_pages_num--;
-	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+	ring->free_pages_num--;
+	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
 
 	return 0;
 }
 
-static inline void put_free_pages(struct xen_blkif *blkif, struct page **page,
+static inline void put_free_pages(struct xen_blkif_ring *ring, struct page **page,
                                   int num)
 {
 	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&blkif->free_pages_lock, flags);
+	spin_lock_irqsave(&ring->free_pages_lock, flags);
 	for (i = 0; i < num; i++)
-		list_add(&page[i]->lru, &blkif->free_pages);
-	blkif->free_pages_num += num;
-	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+		list_add(&page[i]->lru, &ring->free_pages);
+	ring->free_pages_num += num;
+	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
 }
 
-static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num)
+static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num)
 {
 	/* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */
 	struct page *page[NUM_BATCH_FREE_PAGES];
 	unsigned int num_pages = 0;
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkif->free_pages_lock, flags);
-	while (blkif->free_pages_num > num) {
-		BUG_ON(list_empty(&blkif->free_pages));
-		page[num_pages] = list_first_entry(&blkif->free_pages,
+	spin_lock_irqsave(&ring->free_pages_lock, flags);
+	while (ring->free_pages_num > num) {
+		BUG_ON(list_empty(&ring->free_pages));
+		page[num_pages] = list_first_entry(&ring->free_pages,
 		                                   struct page, lru);
 		list_del(&page[num_pages]->lru);
-		blkif->free_pages_num--;
+		ring->free_pages_num--;
 		if (++num_pages == NUM_BATCH_FREE_PAGES) {
-			spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+			spin_unlock_irqrestore(&ring->free_pages_lock, flags);
 			gnttab_free_pages(num_pages, page);
-			spin_lock_irqsave(&blkif->free_pages_lock, flags);
+			spin_lock_irqsave(&ring->free_pages_lock, flags);
 			num_pages = 0;
 		}
 	}
-	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
+	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
 	if (num_pages != 0)
 		gnttab_free_pages(num_pages, page);
 }
@@ -198,23 +198,29 @@ static void make_response(struct xen_blkif_ring *ring, u64 id,
 
 
 /*
- * pers_gnts_lock must be used around all the persistent grant helpers
- * because blkback may use multi-thread/queue for each backend.
+ * We don't need locking around the persistent grant helpers
+ * because blkback uses a single-thread for each backend, 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.
  */
-static int add_persistent_gnt(struct xen_blkif *blkif,
+static int add_persistent_gnt(struct xen_blkif_ring *ring,
 			       struct persistent_gnt *persistent_gnt)
 {
 	struct rb_node **new = NULL, *parent = NULL;
 	struct persistent_gnt *this;
+	struct xen_blkif *blkif = ring->blkif;
 
-	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));
-	if (blkif->persistent_gnt_c >= xen_blkif_max_pgrants) {
+	if (ring->persistent_gnt_c >= xen_blkif_max_pgrants) {
 		if (!blkif->vbd.overflow_max_grants)
 			blkif->vbd.overflow_max_grants = 1;
 		return -EBUSY;
 	}
 	/* Figure out where to put new node */
-	new = &blkif->persistent_gnts.rb_node;
+	new = &ring->persistent_gnts.rb_node;
 	while (*new) {
 		this = container_of(*new, struct persistent_gnt, node);
 
@@ -233,20 +239,19 @@ static int add_persistent_gnt(struct xen_blkif *blkif,
 	set_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags);
 	/* Add new node and rebalance tree. */
 	rb_link_node(&(persistent_gnt->node), parent, new);
-	rb_insert_color(&(persistent_gnt->node), &blkif->persistent_gnts);
-	blkif->persistent_gnt_c++;
-	atomic_inc(&blkif->persistent_gnt_in_use);
+	rb_insert_color(&(persistent_gnt->node), &ring->persistent_gnts);
+	ring->persistent_gnt_c++;
+	atomic_inc(&ring->persistent_gnt_in_use);
 	return 0;
 }
 
-static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif,
+static struct persistent_gnt *get_persistent_gnt(struct xen_blkif_ring *ring,
 						 grant_ref_t gref)
 {
 	struct persistent_gnt *data;
 	struct rb_node *node = NULL;
 
-	BUG_ON(!spin_is_locked(&blkif->pers_gnts_lock));
-	node = blkif->persistent_gnts.rb_node;
+	node = ring->persistent_gnts.rb_node;
 	while (node) {
 		data = container_of(node, struct persistent_gnt, node);
 
@@ -260,25 +265,24 @@ static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif,
 				return NULL;
 			}
 			set_bit(PERSISTENT_GNT_ACTIVE, data->flags);
-			atomic_inc(&blkif->persistent_gnt_in_use);
+			atomic_inc(&ring->persistent_gnt_in_use);
 			return data;
 		}
 	}
 	return NULL;
 }
 
-static void put_persistent_gnt(struct xen_blkif *blkif,
+static void put_persistent_gnt(struct xen_blkif_ring *ring,
                                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);
 	clear_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags);
-	atomic_dec(&blkif->persistent_gnt_in_use);
+	atomic_dec(&ring->persistent_gnt_in_use);
 }
 
-static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
+static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *root,
                                  unsigned int num)
 {
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -292,7 +296,6 @@ 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);
@@ -310,7 +313,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 
-			put_free_pages(blkif, pages, segs_to_unmap);
+			put_free_pages(ring, pages, segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 
@@ -327,17 +330,15 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
 	int segs_to_unmap = 0;
-	struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work);
+	struct xen_blkif_ring *ring = container_of(work, typeof(*ring), 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,
+	while(!list_empty(&ring->persistent_purge_list)) {
+		persistent_gnt = list_first_entry(&ring->persistent_purge_list,
 		                                  struct persistent_gnt,
 		                                  remove_node);
 		list_del(&persistent_gnt->remove_node);
@@ -352,45 +353,42 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
-			put_free_pages(blkif, pages, segs_to_unmap);
+			put_free_pages(ring, pages, segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 		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));
-		put_free_pages(blkif, pages, segs_to_unmap);
+		put_free_pages(ring, pages, segs_to_unmap);
 	}
 }
 
-static void purge_persistent_gnt(struct xen_blkif *blkif)
+static void purge_persistent_gnt(struct xen_blkif_ring *ring)
 {
 	struct persistent_gnt *persistent_gnt;
 	struct rb_node *n;
 	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)) {
+	if (ring->persistent_gnt_c < xen_blkif_max_pgrants ||
+	    (ring->persistent_gnt_c == xen_blkif_max_pgrants &&
+	    !ring->blkif->vbd.overflow_max_grants)) {
 		goto out;
 	}
 
-	if (work_busy(&blkif->persistent_purge_work)) {
+	if (work_busy(&ring->persistent_purge_work)) {
 		pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n");
 		goto out;
 	}
 
 	num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN;
-	num_clean = blkif->persistent_gnt_c - xen_blkif_max_pgrants + num_clean;
-	num_clean = min(blkif->persistent_gnt_c, num_clean);
+	num_clean = ring->persistent_gnt_c - xen_blkif_max_pgrants + num_clean;
+	num_clean = min(ring->persistent_gnt_c, num_clean);
 	if ((num_clean == 0) ||
-	    (num_clean > (blkif->persistent_gnt_c - atomic_read(&blkif->persistent_gnt_in_use))))
+	    (num_clean > (ring->persistent_gnt_c - atomic_read(&ring->persistent_gnt_in_use))))
 		goto out;
 
 	/*
@@ -406,8 +404,8 @@ static void purge_persistent_gnt(struct xen_blkif *blkif)
 
 	pr_debug("Going to purge %u persistent grants\n", num_clean);
 
-	BUG_ON(!list_empty(&blkif->persistent_purge_list));
-	root = &blkif->persistent_gnts;
+	BUG_ON(!list_empty(&ring->persistent_purge_list));
+	root = &ring->persistent_gnts;
 purge_list:
 	foreach_grant_safe(persistent_gnt, n, root, node) {
 		BUG_ON(persistent_gnt->handle ==
@@ -426,7 +424,7 @@ purge_list:
 
 		rb_erase(&persistent_gnt->node, root);
 		list_add(&persistent_gnt->remove_node,
-		         &blkif->persistent_purge_list);
+			 &ring->persistent_purge_list);
 		if (--num_clean == 0)
 			goto finished;
 	}
@@ -447,18 +445,14 @@ finished:
 		goto purge_list;
 	}
 
-	blkif->persistent_gnt_c -= (total - num_clean);
-	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);
-	blkif->vbd.overflow_max_grants = 0;
+	ring->persistent_gnt_c -= (total - num_clean);
+	ring->blkif->vbd.overflow_max_grants = 0;
 
 	/* We can defer this work */
-	schedule_work(&blkif->persistent_purge_work);
+	schedule_work(&ring->persistent_purge_work);
 	pr_debug("Purged %u/%u\n", (total - num_clean), total);
-	return;
 
 out:
-	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);
-
 	return;
 }
 
@@ -590,14 +584,16 @@ irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
  * SCHEDULER FUNCTIONS
  */
 
-static void print_stats(struct xen_blkif *blkif)
+static void print_stats(struct xen_blkif_ring *ring)
 {
+	struct xen_blkif *blkif = ring->blkif;
+
 	pr_info("(%s): oo %3llu  |  rd %4llu  |  wr %4llu  |  f %4llu"
 		 "  |  ds %4llu | pg: %4u/%4d\n",
 		 current->comm, blkif->st_oo_req,
 		 blkif->st_rd_req, blkif->st_wr_req,
 		 blkif->st_f_req, blkif->st_ds_req,
-		 blkif->persistent_gnt_c,
+		 ring->persistent_gnt_c,
 		 xen_blkif_max_pgrants);
 	blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
 	blkif->st_rd_req = 0;
@@ -650,23 +646,23 @@ int xen_blkif_schedule(void *arg)
 
 purge_gnt_list:
 		if (blkif->vbd.feature_gnt_persistent &&
-		    time_after(jiffies, blkif->next_lru)) {
-			purge_persistent_gnt(blkif);
-			blkif->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL);
+		    time_after(jiffies, ring->next_lru)) {
+			purge_persistent_gnt(ring);
+			ring->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL);
 		}
 
 		/* Shrink if we have more than xen_blkif_max_buffer_pages */
-		shrink_free_pagepool(blkif, xen_blkif_max_buffer_pages);
+		shrink_free_pagepool(ring, xen_blkif_max_buffer_pages);
 
-		if (log_stats && time_after(jiffies, blkif->st_print))
-			print_stats(blkif);
+		if (log_stats && time_after(jiffies, ring->blkif->st_print))
+			print_stats(ring);
 	}
 
 	/* Drain pending purge work */
-	flush_work(&blkif->persistent_purge_work);
+	flush_work(&ring->persistent_purge_work);
 
 	if (log_stats)
-		print_stats(blkif);
+		print_stats(ring);
 
 	ring->xenblkd = NULL;
 	xen_blkif_put(blkif);
@@ -679,21 +675,16 @@ purge_gnt_list:
  */
 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);
+	if (!RB_EMPTY_ROOT(&ring->persistent_gnts))
+		free_persistent_gnts(ring, &ring->persistent_gnts,
+			ring->persistent_gnt_c);
 
-	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
-	blkif->persistent_gnt_c = 0;
-	spin_unlock_irqrestore(&blkif->pers_gnts_lock, flags);
+	BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
+	ring->persistent_gnt_c = 0;
 
 	/* Since we are shutting down remove all pages from the buffer */
-	shrink_free_pagepool(blkif, 0 /* All */);
+	shrink_free_pagepool(ring, 0 /* All */);
 }
 
 static unsigned int xen_blkbk_unmap_prepare(
@@ -704,13 +695,10 @@ static unsigned int xen_blkbk_unmap_prepare(
 	struct page **unmap_pages)
 {
 	unsigned int i, invcount = 0;
-	unsigned long flags;
 
 	for (i = 0; i < num; i++) {
 		if (pages[i]->persistent_gnt != NULL) {
-			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);
+			put_persistent_gnt(ring, pages[i]->persistent_gnt);
 			continue;
 		}
 		if (pages[i]->handle == BLKBACK_INVALID_HANDLE)
@@ -735,7 +723,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_
 	   but is this the best way to deal with this? */
 	BUG_ON(result);
 
-	put_free_pages(blkif, data->pages, data->count);
+	put_free_pages(ring, data->pages, data->count);
 	make_response(ring, pending_req->id,
 		      pending_req->operation, pending_req->status);
 	free_req(ring, pending_req);
@@ -802,7 +790,7 @@ static void xen_blkbk_unmap(struct xen_blkif_ring *ring,
 		if (invcount) {
 			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
 			BUG_ON(ret);
-			put_free_pages(ring->blkif, unmap_pages, invcount);
+			put_free_pages(ring, unmap_pages, invcount);
 		}
 		pages += batch;
 		num -= batch;
@@ -823,7 +811,6 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 	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);
 
@@ -837,11 +824,9 @@ again:
 		uint32_t flags;
 
 		if (use_persistent_gnts) {
-			spin_lock_irqsave(&blkif->pers_gnts_lock, irq_flags);
 			persistent_gnt = get_persistent_gnt(
-				blkif,
+				ring,
 				pages[i]->gref);
-			spin_unlock_irqrestore(&blkif->pers_gnts_lock, irq_flags);
 		}
 
 		if (persistent_gnt) {
@@ -852,7 +837,7 @@ again:
 			pages[i]->page = persistent_gnt->page;
 			pages[i]->persistent_gnt = persistent_gnt;
 		} else {
-			if (get_free_page(blkif, &pages[i]->page))
+			if (get_free_page(ring, &pages[i]->page))
 				goto out_of_memory;
 			addr = vaddr(pages[i]->page);
 			pages_to_gnt[segs_to_map] = pages[i]->page;
@@ -885,7 +870,7 @@ again:
 			BUG_ON(new_map_idx >= segs_to_map);
 			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug("invalid buffer -- could not remap it\n");
-				put_free_pages(blkif, &pages[seg_idx]->page, 1);
+				put_free_pages(ring, &pages[seg_idx]->page, 1);
 				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
 				goto next;
@@ -895,7 +880,7 @@ again:
 			continue;
 		}
 		if (use_persistent_gnts &&
-		    blkif->persistent_gnt_c < xen_blkif_max_pgrants) {
+		    ring->persistent_gnt_c < xen_blkif_max_pgrants) {
 			/*
 			 * We are using persistent grants, the grant is
 			 * not mapped but we might have room for it.
@@ -913,19 +898,16 @@ again:
 			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,
+			if (add_persistent_gnt(ring,
 			                       persistent_gnt)) {
-				spin_unlock_irqrestore(&blkif->pers_gnts_lock, irq_flags);
 				kfree(persistent_gnt);
 				persistent_gnt = NULL;
 				goto next;
 			}
 			pages[seg_idx]->persistent_gnt = persistent_gnt;
 			pr_debug("grant %u added to the tree of persistent grants, using %u/%u\n",
-				 persistent_gnt->gnt, blkif->persistent_gnt_c,
+				 persistent_gnt->gnt, ring->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) {
@@ -949,7 +931,7 @@ next:
 
 out_of_memory:
 	pr_alert("%s: out of memory\n", __func__);
-	put_free_pages(blkif, pages_to_gnt, segs_to_map);
+	put_free_pages(ring, pages_to_gnt, segs_to_map);
 	return -ENOMEM;
 }
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 0833dc6..54f126e 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -291,6 +291,22 @@ struct xen_blkif_ring {
 	spinlock_t		pending_free_lock;
 	wait_queue_head_t	pending_free_wq;
 
+	/* 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;
+	unsigned long           next_lru;
+
+	/* Used by the kworker that offload work from the persistent purge. */
+	struct list_head	persistent_purge_list;
+	struct work_struct	persistent_purge_work;
+
+	/* Buffer of free pages to map grant refs. */
+	spinlock_t		free_pages_lock;
+	int			free_pages_num;
+	struct list_head	free_pages;
+
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
 	wait_queue_head_t	shutdown_wq;
@@ -312,22 +328,6 @@ struct xen_blkif {
 	struct completion	drain_complete;
 	atomic_t		drain;
 
-	/* 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;
-	unsigned long           next_lru;
-
-	/* used by the kworker that offload work from the persistent purge */
-	struct list_head	persistent_purge_list;
-	struct work_struct	persistent_purge_work;
-
-	/* buffer of free pages to map grant refs */
-	spinlock_t		free_pages_lock;
-	int			free_pages_num;
-	struct list_head	free_pages;
-
 	/* statistics */
 	unsigned long		st_print;
 	unsigned long long			st_rd_req;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index d83b790..db8ad57 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -150,6 +150,10 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
 		spin_lock_init(&ring->blk_ring_lock);
 		init_waitqueue_head(&ring->wq);
 		INIT_LIST_HEAD(&ring->pending_free);
+		INIT_LIST_HEAD(&ring->persistent_purge_list);
+		INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
+		spin_lock_init(&ring->free_pages_lock);
+		INIT_LIST_HEAD(&ring->free_pages);
 
 		spin_lock_init(&ring->pending_free_lock);
 		init_waitqueue_head(&ring->pending_free_wq);
@@ -175,11 +179,7 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	atomic_set(&blkif->refcnt, 1);
 	init_completion(&blkif->drain_complete);
 	INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);
-	spin_lock_init(&blkif->free_pages_lock);
-	INIT_LIST_HEAD(&blkif->free_pages);
-	INIT_LIST_HEAD(&blkif->persistent_purge_list);
 	blkif->st_print = jiffies;
-	INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants);
 
 	return blkif;
 }
@@ -290,6 +290,12 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 			i++;
 		}
 
+		BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
+		BUG_ON(!list_empty(&ring->persistent_purge_list));
+		BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
+		BUG_ON(!list_empty(&ring->free_pages));
+		BUG_ON(ring->free_pages_num != 0);
+		BUG_ON(ring->persistent_gnt_c != 0);
 		WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
 	}
 	blkif->nr_ring_pages = 0;
@@ -304,13 +310,6 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 	xen_vbd_free(&blkif->vbd);
 
 	/* Make sure everything is drained before shutting down */
-	BUG_ON(blkif->persistent_gnt_c != 0);
-	BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
-	BUG_ON(blkif->free_pages_num != 0);
-	BUG_ON(!list_empty(&blkif->persistent_purge_list));
-	BUG_ON(!list_empty(&blkif->free_pages));
-	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
-
 	kfree(blkif->rings);
 	kmem_cache_free(xen_blkif_cachep, blkif);
 }
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ