| 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
| ||
|
Date: Fri, 12 Sep 2014 01:57:23 +0200
From: Arianna Avanzini <avanzini.arianna@...il.com>
To: konrad.wilk@...cle.com, boris.ostrovsky@...cle.com,
david.vrabel@...rix.com, xen-devel@...ts.xenproject.org,
linux-kernel@...r.kernel.org
Cc: hch@...radead.org, bob.liu@...cle.com, felipe.franciosi@...rix.com,
axboe@...com, avanzini.arianna@...il.com
Subject: [PATCH RFC v2 4/5] xen, blkback: introduce support for multiple block rings
This commit adds to xen-blkback the support to map and make use
of a variable number of ringbuffers. The number of rings to be
mapped is forcedly set to one.
Signed-off-by: Arianna Avanzini <avanzini.arianna@...il.com>
---
drivers/block/xen-blkback/blkback.c | 377 ++++++++++++++++---------------
drivers/block/xen-blkback/common.h | 110 +++++----
drivers/block/xen-blkback/xenbus.c | 432 +++++++++++++++++++++++-------------
3 files changed, 548 insertions(+), 371 deletions(-)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 64c60ed..b31acfb 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -80,6 +80,9 @@ module_param_named(max_persistent_grants, xen_blkif_max_pgrants, int, 0644);
MODULE_PARM_DESC(max_persistent_grants,
"Maximum number of grants to map persistently");
+#define XEN_RING_MAX_PGRANTS(nr_rings) \
+ (max((int)(xen_blkif_max_pgrants / nr_rings), 16))
+
/*
* The LRU mechanism to clean the lists of persistent grants needs to
* be executed periodically. The time interval between consecutive executions
@@ -103,71 +106,71 @@ module_param(log_stats, int, 0644);
/* Number of free pages to remove on each call to free_xenballooned_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 alloc_xenballooned_pages(1, page, false);
}
- 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,
- int num)
+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);
free_xenballooned_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)
free_xenballooned_pages(num_pages, page);
}
#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) \
@@ -188,19 +191,21 @@ static void make_response(struct xen_blkif *blkif, u64 id,
* 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 xen_blkif *blkif = ring->blkif;
struct rb_node **new = NULL, *parent = NULL;
struct persistent_gnt *this;
- if (blkif->persistent_gnt_c >= xen_blkif_max_pgrants) {
+ if (ring->persistent_gnt_c >=
+ XEN_RING_MAX_PGRANTS(ring->blkif->nr_rings)) {
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);
@@ -219,19 +224,19 @@ 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;
- node = blkif->persistent_gnts.rb_node;
+ node = ring->persistent_gnts.rb_node;
while (node) {
data = container_of(node, struct persistent_gnt, node);
@@ -245,25 +250,25 @@ 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)
{
if(!test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags))
pr_alert_ratelimited(DRV_PFX " freeing a grant already unused");
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,
- unsigned int num)
+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];
struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -288,7 +293,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
ret = gnttab_unmap_refs(unmap, NULL, pages,
segs_to_unmap);
BUG_ON(ret);
- put_free_pages(blkif, pages, segs_to_unmap);
+ put_free_pages(ring, pages, segs_to_unmap);
segs_to_unmap = 0;
}
@@ -305,10 +310,10 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct persistent_gnt *persistent_gnt;
int ret, 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);
- 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);
@@ -324,7 +329,7 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
ret = gnttab_unmap_refs(unmap, NULL, pages,
segs_to_unmap);
BUG_ON(ret);
- put_free_pages(blkif, pages, segs_to_unmap);
+ put_free_pages(ring, pages, segs_to_unmap);
segs_to_unmap = 0;
}
kfree(persistent_gnt);
@@ -332,34 +337,36 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
if (segs_to_unmap > 0) {
ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap);
BUG_ON(ret);
- 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 xen_blkif *blkif = ring->blkif;
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 nr_rings = ring->blkif->nr_rings;
- if (blkif->persistent_gnt_c < xen_blkif_max_pgrants ||
- (blkif->persistent_gnt_c == xen_blkif_max_pgrants &&
+ if (ring->persistent_gnt_c < XEN_RING_MAX_PGRANTS(nr_rings) ||
+ (ring->persistent_gnt_c == XEN_RING_MAX_PGRANTS(nr_rings) &&
!blkif->vbd.overflow_max_grants)) {
return;
}
- if (work_pending(&blkif->persistent_purge_work)) {
+ if (work_pending(&ring->persistent_purge_work)) {
pr_alert_ratelimited(DRV_PFX "Scheduled work from previous purge is still pending, cannot purge list\n");
return;
}
- 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 = (XEN_RING_MAX_PGRANTS(nr_rings) / 100) * LRU_PERCENT_CLEAN;
+ num_clean = ring->persistent_gnt_c - XEN_RING_MAX_PGRANTS(nr_rings) + 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))))
return;
/*
@@ -375,8 +382,8 @@ static void purge_persistent_gnt(struct xen_blkif *blkif)
pr_debug(DRV_PFX "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 ==
@@ -395,7 +402,7 @@ 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;
}
@@ -416,11 +423,11 @@ finished:
goto purge_list;
}
- blkif->persistent_gnt_c -= (total - num_clean);
+ ring->persistent_gnt_c -= (total - num_clean);
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(DRV_PFX "Purged %u/%u\n", (total - num_clean), total);
return;
}
@@ -428,18 +435,18 @@ finished:
/*
* 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;
}
@@ -447,17 +454,17 @@ 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);
}
/*
@@ -537,10 +544,10 @@ abort:
/*
* 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)
@@ -553,30 +560,33 @@ 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)
{
+ spin_lock_irq(&ring->stats_lock);
pr_info("xen-blkback (%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,
- xen_blkif_max_pgrants);
- blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
- blkif->st_rd_req = 0;
- blkif->st_wr_req = 0;
- blkif->st_oo_req = 0;
- blkif->st_ds_req = 0;
+ current->comm, ring->st_oo_req,
+ ring->st_rd_req, ring->st_wr_req,
+ ring->st_f_req, ring->st_ds_req,
+ ring->persistent_gnt_c,
+ XEN_RING_MAX_PGRANTS(ring->blkif->nr_rings));
+ ring->st_print = jiffies + msecs_to_jiffies(10 * 1000);
+ ring->st_rd_req = 0;
+ ring->st_wr_req = 0;
+ ring->st_oo_req = 0;
+ ring->st_ds_req = 0;
+ spin_unlock_irq(&ring->stats_lock);
}
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;
- xen_blkif_get(blkif);
+ xen_ring_get(ring);
while (!kthread_should_stop()) {
if (try_to_freeze())
@@ -587,51 +597,51 @@ 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:
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->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);
- blkif->xenblkd = NULL;
- xen_blkif_put(blkif);
+ ring->xenblkd = NULL;
+ xen_ring_put(ring);
return 0;
}
@@ -639,25 +649,25 @@ purge_gnt_list:
/*
* 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)
{
/* Free all persistent grant pages */
- 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;
+ 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 */);
}
/*
* Unmap the grant references, and also remove the M2P over-rides
* used in the 'pending_req'.
*/
-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)
{
@@ -668,7 +678,7 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif,
for (i = 0; i < num; i++) {
if (pages[i]->persistent_gnt != NULL) {
- put_persistent_gnt(blkif, pages[i]->persistent_gnt);
+ put_persistent_gnt(ring, pages[i]->persistent_gnt);
continue;
}
if (pages[i]->handle == BLKBACK_INVALID_HANDLE)
@@ -681,21 +691,22 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif,
ret = gnttab_unmap_refs(unmap, NULL, unmap_pages,
invcount);
BUG_ON(ret);
- put_free_pages(blkif, unmap_pages, invcount);
+ put_free_pages(ring, unmap_pages, invcount);
invcount = 0;
}
}
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, unmap_pages, invcount);
}
}
-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)
{
+ struct xen_blkif *blkif = ring->blkif;
struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct page *pages_to_gnt[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct persistent_gnt *persistent_gnt = NULL;
@@ -719,7 +730,7 @@ again:
if (use_persistent_gnts)
persistent_gnt = get_persistent_gnt(
- blkif,
+ ring,
pages[i]->gref);
if (persistent_gnt) {
@@ -730,7 +741,7 @@ 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;
@@ -772,7 +783,8 @@ again:
continue;
}
if (use_persistent_gnts &&
- blkif->persistent_gnt_c < xen_blkif_max_pgrants) {
+ ring->persistent_gnt_c <
+ XEN_RING_MAX_PGRANTS(ring->blkif->nr_rings)) {
/*
* We are using persistent grants, the grant is
* not mapped but we might have room for it.
@@ -790,7 +802,7 @@ again:
persistent_gnt->gnt = map[new_map_idx].ref;
persistent_gnt->handle = map[new_map_idx].handle;
persistent_gnt->page = pages[seg_idx]->page;
- if (add_persistent_gnt(blkif,
+ if (add_persistent_gnt(ring,
persistent_gnt)) {
kfree(persistent_gnt);
persistent_gnt = NULL;
@@ -798,8 +810,8 @@ again:
}
pages[seg_idx]->persistent_gnt = persistent_gnt;
pr_debug(DRV_PFX " grant %u added to the tree of persistent grants, using %u/%u\n",
- persistent_gnt->gnt, blkif->persistent_gnt_c,
- xen_blkif_max_pgrants);
+ persistent_gnt->gnt, ring->persistent_gnt_c,
+ XEN_RING_MAX_PGRANTS(ring->blkif->nr_rings));
goto next;
}
if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) {
@@ -823,7 +835,7 @@ next:
out_of_memory:
pr_alert(DRV_PFX "%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;
}
@@ -831,7 +843,7 @@ 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_pages,
(pending_req->operation != BLKIF_OP_READ));
@@ -844,7 +856,7 @@ 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;
@@ -855,7 +867,7 @@ 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;
@@ -882,20 +894,21 @@ 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;
- xen_blkif_get(blkif);
+ xen_ring_get(ring);
preq.sector_number = req->u.discard.sector_number;
preq.nr_sects = req->u.discard.nr_sectors;
@@ -907,7 +920,9 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
preq.sector_number + preq.nr_sects, blkif->vbd.pdevice);
goto fail_response;
}
- blkif->st_ds_req++;
+ spin_lock_irq(&ring->stats_lock);
+ ring->st_ds_req++;
+ spin_unlock_irq(&ring->stats_lock);
secure = (blkif->vbd.discard_secure &&
(req->u.discard.flag & BLKIF_DISCARD_SECURE)) ?
@@ -923,26 +938,27 @@ fail_response:
} else if (err)
status = BLKIF_RSP_ERROR;
- make_response(blkif, req->u.discard.id, req->operation, status);
- xen_blkif_put(blkif);
+ make_response(ring, req->u.discard.id, req->operation, status);
+ xen_ring_put(ring);
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);
@@ -963,12 +979,12 @@ 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(DRV_PFX "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(DRV_PFX "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(DRV_PFX "Buffer not up-to-date at end of operation,"
@@ -982,14 +998,15 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
* the proper response on the ring.
*/
if (atomic_dec_and_test(&pending_req->pendcnt)) {
- struct xen_blkif *blkif = pending_req->blkif;
+ struct xen_blkif_ring *ring = pending_req->ring;
+ struct xen_blkif *blkif = ring->blkif;
- xen_blkbk_unmap(blkif,
+ xen_blkbk_unmap(ring,
pending_req->segments,
pending_req->nr_pages);
- 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
@@ -1002,10 +1019,10 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
* 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);
+ xen_ring_put(ring);
}
}
@@ -1026,9 +1043,10 @@ static void end_block_io_op(struct bio *bio, int error)
* 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 xen_blkif *blkif = ring->blkif;
struct blkif_request req;
struct pending_req *pending_req;
RING_IDX rc, rp;
@@ -1054,9 +1072,11 @@ __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++;
+ spin_lock_irq(&ring->stats_lock);
+ ring->st_oo_req++;
+ spin_unlock_irq(&ring->stats_lock);
more_to_do = 1;
break;
}
@@ -1085,16 +1105,16 @@ __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;
}
@@ -1107,13 +1127,13 @@ done:
}
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;
@@ -1126,7 +1146,7 @@ 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)
{
@@ -1140,6 +1160,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
struct blk_plug plug;
bool drain = false;
struct grant_page **pages = pending_req->segments;
+ struct xen_blkif *blkif = ring->blkif;
unsigned short req_operation;
req_operation = req->operation == BLKIF_OP_INDIRECT ?
@@ -1152,26 +1173,29 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
goto fail_response;
}
+ spin_lock_irq(&ring->stats_lock);
switch (req_operation) {
case BLKIF_OP_READ:
- blkif->st_rd_req++;
+ ring->st_rd_req++;
operation = READ;
break;
case BLKIF_OP_WRITE:
- blkif->st_wr_req++;
+ ring->st_wr_req++;
operation = WRITE_ODIRECT;
break;
case BLKIF_OP_WRITE_BARRIER:
drain = true;
case BLKIF_OP_FLUSH_DISKCACHE:
- blkif->st_f_req++;
+ ring->st_f_req++;
operation = WRITE_FLUSH;
break;
default:
operation = 0; /* make gcc happy */
+ spin_unlock_irq(&ring->stats_lock);
goto fail_response;
break;
}
+ spin_unlock_irq(&ring->stats_lock);
/* Check that the number of segments is sane. */
nseg = req->operation == BLKIF_OP_INDIRECT ?
@@ -1190,7 +1214,7 @@ 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;
@@ -1243,7 +1267,7 @@ 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,
@@ -1255,11 +1279,11 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
goto fail_flush;
/*
- * This corresponding xen_blkif_put is done in __end_block_io_op, or
+ * This corresponding xen_ring_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_ring_get(ring);
+ atomic_inc(&ring->inflight);
for (i = 0; i < nseg; i++) {
while ((bio == NULL) ||
@@ -1306,20 +1330,22 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
/* Let the I/Os go.. */
blk_finish_plug(&plug);
+ spin_lock_irq(&ring->stats_lock);
if (operation == READ)
- blkif->st_rd_sect += preq.nr_sects;
+ ring->st_rd_sect += preq.nr_sects;
else if (operation & WRITE)
- blkif->st_wr_sect += preq.nr_sects;
+ ring->st_wr_sect += preq.nr_sects;
+ spin_unlock_irq(&ring->stats_lock);
return 0;
fail_flush:
- xen_blkbk_unmap(blkif, pending_req->segments,
+ xen_blkbk_unmap(ring, pending_req->segments,
pending_req->nr_pages);
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;
@@ -1337,19 +1363,20 @@ 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 = &ring->blk_rings;
+ struct xen_blkif *blkif = ring->blkif;
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);
/* Place on the response ring for the relevant domain. */
switch (blkif->blk_protocol) {
case BLKIF_PROTOCOL_NATIVE:
@@ -1369,9 +1396,9 @@ 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)
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index f65b807..6f074ce 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -226,6 +226,7 @@ struct xen_vbd {
struct block_device *bdev;
/* Cached size parameter. */
sector_t size;
+ unsigned int nr_supported_hw_queues;
unsigned int flush_support:1;
unsigned int discard_secure:1;
unsigned int feature_gnt_persistent:1;
@@ -246,6 +247,7 @@ struct backend_info;
/* Number of requests that we can fit in a ring */
#define XEN_BLKIF_REQS 32
+#define XEN_RING_REQS(nr_rings) (max((int)(XEN_BLKIF_REQS / nr_rings), 8))
struct persistent_gnt {
struct page *page;
@@ -256,32 +258,29 @@ struct persistent_gnt {
struct list_head remove_node;
};
-struct xen_blkif {
- /* Unique identifier for this interface. */
- domid_t domid;
- unsigned int handle;
+struct xen_blkif_ring {
+ union blkif_back_rings blk_rings;
/* 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;
+ void *blk_ring;
+ spinlock_t blk_ring_lock;
+
+ struct work_struct free_work;
+ /* Thread shutdown wait queue. */
+ wait_queue_head_t shutdown_wq;
+
+ /* buffer of free pages to map grant refs */
+ spinlock_t free_pages_lock;
+ int free_pages_num;
+
+ /* used by the kworker that offload work from the persistent purge */
+ struct list_head persistent_purge_list;
+ struct work_struct persistent_purge_work;
/* tree to store persistent grants */
struct rb_root persistent_gnts;
@@ -289,13 +288,6 @@ struct xen_blkif {
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;
/* List of all 'pending_req' available */
@@ -303,20 +295,54 @@ struct xen_blkif {
/* And its spinlock. */
spinlock_t pending_free_lock;
wait_queue_head_t pending_free_wq;
+ atomic_t inflight;
+
+ /* Private fields. */
+ atomic_t refcnt;
+
+ struct xen_blkif *blkif;
+ unsigned ring_index;
+ spinlock_t stats_lock;
/* statistics */
unsigned long st_print;
- unsigned long long st_rd_req;
- unsigned long long st_wr_req;
- unsigned long long st_oo_req;
- unsigned long long st_f_req;
- unsigned long long st_ds_req;
- unsigned long long st_rd_sect;
- unsigned long long st_wr_sect;
+ unsigned long long st_rd_req;
+ unsigned long long st_wr_req;
+ unsigned long long st_oo_req;
+ unsigned long long st_f_req;
+ unsigned long long st_ds_req;
+ unsigned long long st_rd_sect;
+ unsigned long long st_wr_sect;
+};
- struct work_struct free_work;
- /* Thread shutdown wait queue. */
- wait_queue_head_t shutdown_wq;
+struct xen_blkif {
+ /* Unique identifier for this interface. */
+ domid_t domid;
+ unsigned int handle;
+ /* Comms information. */
+ enum blkif_protocol blk_protocol;
+ /* The VBD attached to this interface. */
+ struct xen_vbd vbd;
+ /* Rings for this device */
+ struct xen_blkif_ring *rings;
+ unsigned int nr_rings;
+ /* Back pointer to the backend_info. */
+ struct backend_info *be;
+
+ /* for barrier (drain) requests */
+ struct completion drain_complete;
+ atomic_t drain;
+
+ atomic_t refcnt;
+
+ /* statistics */
+ unsigned long long st_rd_req;
+ unsigned long long st_wr_req;
+ unsigned long long st_oo_req;
+ unsigned long long st_f_req;
+ unsigned long long st_ds_req;
+ unsigned long long st_rd_sect;
+ unsigned long long st_wr_sect;
};
struct seg_buf {
@@ -338,7 +364,7 @@ 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_pages;
atomic_t pendcnt;
@@ -357,11 +383,11 @@ struct pending_req {
(_v)->bdev->bd_part->nr_sects : \
get_capacity((_v)->bdev->bd_disk))
-#define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
-#define xen_blkif_put(_b) \
+#define xen_ring_get(_r) (atomic_inc(&(_r)->refcnt))
+#define xen_ring_put(_r) \
do { \
- if (atomic_dec_and_test(&(_b)->refcnt)) \
- schedule_work(&(_b)->free_work);\
+ if (atomic_dec_and_test(&(_r)->refcnt)) \
+ schedule_work(&(_r)->free_work);\
} while (0)
struct phys_req {
@@ -377,7 +403,7 @@ 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);
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3a8b810..a4f13cc 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -35,7 +35,7 @@ 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_ring_free(struct xen_blkif_ring *ring);
static void xen_vbd_free(struct xen_vbd *vbd);
struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be)
@@ -45,17 +45,17 @@ struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be)
/*
* The last request could free the device from softirq context and
- * xen_blkif_free() can sleep.
+ * xen_ring_free() can sleep.
*/
-static void xen_blkif_deferred_free(struct work_struct *work)
+static void xen_ring_deferred_free(struct work_struct *work)
{
- struct xen_blkif *blkif;
+ struct xen_blkif_ring *ring;
- blkif = container_of(work, struct xen_blkif, free_work);
- xen_blkif_free(blkif);
+ ring = container_of(work, struct xen_blkif_ring, free_work);
+ xen_ring_free(ring);
}
-static int blkback_name(struct xen_blkif *blkif, char *buf)
+static int blkback_name(struct xen_blkif *blkif, char *buf, bool save_space)
{
char *devpath, *devname;
struct xenbus_device *dev = blkif->be->dev;
@@ -70,7 +70,10 @@ static int blkback_name(struct xen_blkif *blkif, char *buf)
else
devname = devpath;
- snprintf(buf, TASK_COMM_LEN, "blkback.%d.%s", blkif->domid, devname);
+ if (save_space)
+ snprintf(buf, TASK_COMM_LEN, "blkbk.%d.%s", blkif->domid, devname);
+ else
+ snprintf(buf, TASK_COMM_LEN, "blkback.%d.%s", blkif->domid, devname);
kfree(devpath);
return 0;
@@ -78,11 +81,15 @@ static int blkback_name(struct xen_blkif *blkif, char *buf)
static void xen_update_blkif_status(struct xen_blkif *blkif)
{
- int err;
- char name[TASK_COMM_LEN];
+ int i, err;
+ char name[TASK_COMM_LEN], per_ring_name[TASK_COMM_LEN];
+ struct xen_blkif_ring *ring;
- /* Not ready to connect? */
- if (!blkif->irq || !blkif->vbd.bdev)
+ /*
+ * Not ready to connect? Check irq of first ring as the others
+ * should all be the same.
+ */
+ if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev)
return;
/* Already connected? */
@@ -94,7 +101,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
if (blkif->be->dev->state != XenbusStateConnected)
return;
- err = blkback_name(blkif, name);
+ err = blkback_name(blkif, name, blkif->vbd.nr_supported_hw_queues);
if (err) {
xenbus_dev_error(blkif->be->dev, err, "get blkback dev name");
return;
@@ -107,20 +114,96 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
}
invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping);
- blkif->xenblkd = kthread_run(xen_blkif_schedule, blkif, "%s", name);
- if (IS_ERR(blkif->xenblkd)) {
- err = PTR_ERR(blkif->xenblkd);
- blkif->xenblkd = NULL;
- xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
- return;
+ for (i = 0 ; i < blkif->nr_rings ; i++) {
+ ring = &blkif->rings[i];
+ if (blkif->vbd.nr_supported_hw_queues)
+ snprintf(per_ring_name, TASK_COMM_LEN, "%s-%d", name, i);
+ else {
+ BUG_ON(i != 0);
+ snprintf(per_ring_name, TASK_COMM_LEN, "%s", name);
+ }
+ ring->xenblkd = kthread_run(xen_blkif_schedule, ring, "%s", per_ring_name);
+ if (IS_ERR(ring->xenblkd)) {
+ err = PTR_ERR(ring->xenblkd);
+ ring->xenblkd = NULL;
+ xenbus_dev_error(blkif->be->dev, err, "start %s", per_ring_name);
+ return;
+ }
}
}
+static struct xen_blkif_ring *xen_blkif_ring_alloc(struct xen_blkif *blkif,
+ int nr_rings)
+{
+ int r, i, j;
+ struct xen_blkif_ring *rings;
+ struct pending_req *req;
+
+ rings = kzalloc(nr_rings * sizeof(struct xen_blkif_ring),
+ GFP_KERNEL);
+ if (!rings)
+ return NULL;
+
+ for (r = 0 ; r < nr_rings ; r++) {
+ struct xen_blkif_ring *ring = &rings[r];
+
+ spin_lock_init(&ring->blk_ring_lock);
+
+ init_waitqueue_head(&ring->wq);
+ init_waitqueue_head(&ring->shutdown_wq);
+
+ ring->persistent_gnts.rb_node = NULL;
+ spin_lock_init(&ring->free_pages_lock);
+ INIT_LIST_HEAD(&ring->free_pages);
+ INIT_LIST_HEAD(&ring->persistent_purge_list);
+ ring->free_pages_num = 0;
+ atomic_set(&ring->persistent_gnt_in_use, 0);
+ atomic_set(&ring->refcnt, 1);
+ atomic_set(&ring->inflight, 0);
+ INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
+ spin_lock_init(&ring->pending_free_lock);
+ init_waitqueue_head(&ring->pending_free_wq);
+ INIT_LIST_HEAD(&ring->pending_free);
+ for (i = 0; i < XEN_RING_REQS(nr_rings); i++) {
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+ if (!req)
+ goto fail;
+ list_add_tail(&req->free_list,
+ &ring->pending_free);
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+ req->segments[j] = kzalloc(sizeof(*req->segments[0]),
+ GFP_KERNEL);
+ if (!req->segments[j])
+ goto fail;
+ }
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+ req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
+ GFP_KERNEL);
+ if (!req->indirect_pages[j])
+ goto fail;
+ }
+ }
+
+ INIT_WORK(&ring->free_work, xen_ring_deferred_free);
+ ring->blkif = blkif;
+ ring->ring_index = r;
+
+ spin_lock_init(&ring->stats_lock);
+ ring->st_print = jiffies;
+
+ atomic_inc(&blkif->refcnt);
+ }
+
+ return rings;
+
+fail:
+ kfree(rings);
+ return NULL;
+}
+
static struct xen_blkif *xen_blkif_alloc(domid_t domid)
{
struct xen_blkif *blkif;
- struct pending_req *req, *n;
- int i, j;
BUILD_BUG_ON(MAX_INDIRECT_PAGES > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);
@@ -129,80 +212,26 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
return ERR_PTR(-ENOMEM);
blkif->domid = domid;
- spin_lock_init(&blkif->blk_ring_lock);
- atomic_set(&blkif->refcnt, 1);
- init_waitqueue_head(&blkif->wq);
init_completion(&blkif->drain_complete);
atomic_set(&blkif->drain, 0);
- blkif->st_print = jiffies;
- blkif->persistent_gnts.rb_node = NULL;
- spin_lock_init(&blkif->free_pages_lock);
- INIT_LIST_HEAD(&blkif->free_pages);
- INIT_LIST_HEAD(&blkif->persistent_purge_list);
- blkif->free_pages_num = 0;
- atomic_set(&blkif->persistent_gnt_in_use, 0);
- atomic_set(&blkif->inflight, 0);
- 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);
- if (!req)
- goto fail;
- list_add_tail(&req->free_list,
- &blkif->pending_free);
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
- req->segments[j] = kzalloc(sizeof(*req->segments[0]),
- GFP_KERNEL);
- if (!req->segments[j])
- goto fail;
- }
- for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
- req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
- GFP_KERNEL);
- if (!req->indirect_pages[j])
- goto fail;
- }
- }
- spin_lock_init(&blkif->pending_free_lock);
- init_waitqueue_head(&blkif->pending_free_wq);
- init_waitqueue_head(&blkif->shutdown_wq);
return blkif;
-
-fail:
- list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
- list_del(&req->free_list);
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
- if (!req->segments[j])
- break;
- kfree(req->segments[j]);
- }
- for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
- if (!req->indirect_pages[j])
- break;
- kfree(req->indirect_pages[j]);
- }
- kfree(req);
- }
-
- kmem_cache_free(xen_blkif_cachep, blkif);
-
- return ERR_PTR(-ENOMEM);
}
-static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page,
- unsigned int evtchn)
+static int xen_blkif_map(struct xen_blkif_ring *ring, unsigned long shared_page,
+ unsigned int evtchn, unsigned int ring_idx)
{
int err;
+ struct xen_blkif *blkif;
+ char dev_name[64];
/* Already connected through? */
- if (blkif->irq)
+ if (ring->irq)
return 0;
- err = xenbus_map_ring_valloc(blkif->be->dev, shared_page, &blkif->blk_ring);
+ blkif = ring->blkif;
+
+ err = xenbus_map_ring_valloc(ring->blkif->be->dev, shared_page, &ring->blk_ring);
if (err < 0)
return err;
@@ -210,64 +239,73 @@ static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page,
case BLKIF_PROTOCOL_NATIVE:
{
struct blkif_sring *sring;
- sring = (struct blkif_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE);
+ sring = (struct blkif_sring *)ring->blk_ring;
+ BACK_RING_INIT(&ring->blk_rings.native, sring, PAGE_SIZE);
break;
}
case BLKIF_PROTOCOL_X86_32:
{
struct blkif_x86_32_sring *sring_x86_32;
- sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE);
+ sring_x86_32 = (struct blkif_x86_32_sring *)ring->blk_ring;
+ BACK_RING_INIT(&ring->blk_rings.x86_32, sring_x86_32, PAGE_SIZE);
break;
}
case BLKIF_PROTOCOL_X86_64:
{
struct blkif_x86_64_sring *sring_x86_64;
- sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE);
+ sring_x86_64 = (struct blkif_x86_64_sring *)ring->blk_ring;
+ BACK_RING_INIT(&ring->blk_rings.x86_64, sring_x86_64, PAGE_SIZE);
break;
}
default:
BUG();
}
+ if (blkif->vbd.nr_supported_hw_queues)
+ snprintf(dev_name, 64, "blkif-backend-%d", ring_idx);
+ else
+ snprintf(dev_name, 64, "blkif-backend");
err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn,
xen_blkif_be_int, 0,
- "blkif-backend", blkif);
+ dev_name, ring);
if (err < 0) {
- xenbus_unmap_ring_vfree(blkif->be->dev, blkif->blk_ring);
- blkif->blk_rings.common.sring = NULL;
+ xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
+ ring->blk_rings.common.sring = NULL;
return err;
}
- blkif->irq = err;
+ ring->irq = err;
return 0;
}
static int xen_blkif_disconnect(struct xen_blkif *blkif)
{
- if (blkif->xenblkd) {
- kthread_stop(blkif->xenblkd);
- wake_up(&blkif->shutdown_wq);
- blkif->xenblkd = NULL;
- }
+ int i;
+
+ for (i = 0 ; i < blkif->nr_rings ; i++) {
+ struct xen_blkif_ring *ring = &blkif->rings[i];
+ if (ring->xenblkd) {
+ kthread_stop(ring->xenblkd);
+ wake_up(&ring->shutdown_wq);
+ ring->xenblkd = NULL;
+ }
- /* 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;
+ /* 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(&ring->inflight) > 0)
+ return -EBUSY;
- if (blkif->irq) {
- unbind_from_irqhandler(blkif->irq, blkif);
- blkif->irq = 0;
- }
+ if (ring->irq) {
+ unbind_from_irqhandler(ring->irq, ring);
+ ring->irq = 0;
+ }
- if (blkif->blk_rings.common.sring) {
- xenbus_unmap_ring_vfree(blkif->be->dev, blkif->blk_ring);
- blkif->blk_rings.common.sring = NULL;
+ if (ring->blk_rings.common.sring) {
+ xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
+ ring->blk_rings.common.sring = NULL;
+ }
}
return 0;
@@ -275,40 +313,52 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
static void xen_blkif_free(struct xen_blkif *blkif)
{
- struct pending_req *req, *n;
- int i = 0, j;
xen_blkif_disconnect(blkif);
xen_vbd_free(&blkif->vbd);
+ kfree(blkif->rings);
+
+ kmem_cache_free(xen_blkif_cachep, blkif);
+}
+
+static void xen_ring_free(struct xen_blkif_ring *ring)
+{
+ struct pending_req *req, *n;
+ int i, j;
+
/* Remove all persistent grants and the cache of ballooned pages. */
- xen_blkbk_free_caches(blkif);
+ xen_blkbk_free_caches(ring);
/* 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));
-
+ BUG_ON(ring->persistent_gnt_c != 0);
+ BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
+ BUG_ON(ring->free_pages_num != 0);
+ BUG_ON(!list_empty(&ring->persistent_purge_list));
+ BUG_ON(!list_empty(&ring->free_pages));
+ BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
+
+ i = 0;
/* Check that there is no request in use */
- list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
+ list_for_each_entry_safe(req, n, &ring->pending_free, free_list) {
list_del(&req->free_list);
-
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+ if (!req->segments[j])
+ break;
kfree(req->segments[j]);
-
- for (j = 0; j < MAX_INDIRECT_PAGES; j++)
+ }
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+ if (!req->segments[j])
+ break;
kfree(req->indirect_pages[j]);
-
+ }
kfree(req);
i++;
}
+ WARN_ON(i != XEN_RING_REQS(ring->blkif->nr_rings));
- WARN_ON(i != XEN_BLKIF_REQS);
-
- kmem_cache_free(xen_blkif_cachep, blkif);
+ if (atomic_dec_and_test(&ring->blkif->refcnt))
+ xen_blkif_free(ring->blkif);
}
int __init xen_blkif_interface_init(void)
@@ -333,6 +383,29 @@ int __init xen_blkif_interface_init(void)
{ \
struct xenbus_device *dev = to_xenbus_device(_dev); \
struct backend_info *be = dev_get_drvdata(&dev->dev); \
+ struct xen_blkif *blkif = be->blkif; \
+ struct xen_blkif_ring *ring; \
+ int i; \
+ \
+ blkif->st_oo_req = 0; \
+ blkif->st_rd_req = 0; \
+ blkif->st_wr_req = 0; \
+ blkif->st_f_req = 0; \
+ blkif->st_ds_req = 0; \
+ blkif->st_rd_sect = 0; \
+ blkif->st_wr_sect = 0; \
+ for (i = 0 ; i < blkif->nr_rings ; i++) { \
+ ring = &blkif->rings[i]; \
+ spin_lock_irq(&ring->stats_lock); \
+ blkif->st_oo_req += ring->st_oo_req; \
+ blkif->st_rd_req += ring->st_rd_req; \
+ blkif->st_wr_req += ring->st_wr_req; \
+ blkif->st_f_req += ring->st_f_req; \
+ blkif->st_ds_req += ring->st_ds_req; \
+ blkif->st_rd_sect += ring->st_rd_sect; \
+ blkif->st_wr_sect += ring->st_wr_sect; \
+ spin_unlock_irq(&ring->stats_lock); \
+ } \
\
return sprintf(buf, format, ##args); \
} \
@@ -453,6 +526,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
handle, blkif->domid);
return 0;
}
+
static int xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -468,13 +542,14 @@ static int xen_blkbk_remove(struct xenbus_device *dev)
be->backend_watch.node = NULL;
}
- dev_set_drvdata(&dev->dev, NULL);
-
if (be->blkif) {
+ int i = 0;
xen_blkif_disconnect(be->blkif);
- xen_blkif_put(be->blkif);
+ for (; i < be->blkif->nr_rings ; i++)
+ xen_ring_put(&be->blkif->rings[i]);
}
+ dev_set_drvdata(&dev->dev, NULL);
kfree(be->mode);
kfree(be);
return 0;
@@ -851,21 +926,46 @@ again:
static int connect_ring(struct backend_info *be)
{
struct xenbus_device *dev = be->dev;
- unsigned long ring_ref;
- unsigned int evtchn;
+ struct xen_blkif *blkif = be->blkif;
+ unsigned long *ring_ref;
+ unsigned int *evtchn;
unsigned int pers_grants;
- char protocol[64] = "";
- int err;
+ char protocol[64] = "", ring_ref_s[64] = "", evtchn_s[64] = "";
+ int i, err;
DPRINTK("%s", dev->otherend);
- err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu",
- &ring_ref, "event-channel", "%u", &evtchn, NULL);
- if (err) {
- xenbus_dev_fatal(dev, err,
- "reading %s/ring-ref and event-channel",
- dev->otherend);
- return err;
+ blkif->nr_rings = 1;
+
+ ring_ref = kzalloc(sizeof(unsigned long) * blkif->nr_rings, GFP_KERNEL);
+ if (!ring_ref)
+ return -ENOMEM;
+ evtchn = kzalloc(sizeof(unsigned int) * blkif->nr_rings,
+ GFP_KERNEL);
+ if (!evtchn) {
+ kfree(ring_ref);
+ return -ENOMEM;
+ }
+
+ for (i = 0 ; i < blkif->nr_rings ; i++) {
+ if (blkif->vbd.nr_supported_hw_queues == 0) {
+ BUG_ON(i != 0);
+ /* Support old XenStore keys for compatibility */
+ snprintf(ring_ref_s, 64, "ring-ref");
+ snprintf(evtchn_s, 64, "event-channel");
+ } else {
+ snprintf(ring_ref_s, 64, "ring-ref-%d", i);
+ snprintf(evtchn_s, 64, "event-channel-%d", i);
+ }
+ err = xenbus_gather(XBT_NIL, dev->otherend,
+ ring_ref_s, "%lu", &ring_ref[i],
+ evtchn_s, "%u", &evtchn[i], NULL);
+ if (err) {
+ xenbus_dev_fatal(dev, err,
+ "reading %s/%s and event-channel",
+ dev->otherend, ring_ref_s);
+ goto fail;
+ }
}
be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
@@ -881,7 +981,8 @@ static int connect_ring(struct backend_info *be)
be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_64;
else {
xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
- return -1;
+ err = -1;
+ goto fail;
}
err = xenbus_gather(XBT_NIL, dev->otherend,
"feature-persistent", "%u",
@@ -892,19 +993,42 @@ static int connect_ring(struct backend_info *be)
be->blkif->vbd.feature_gnt_persistent = pers_grants;
be->blkif->vbd.overflow_max_grants = 0;
- pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
- ring_ref, evtchn, be->blkif->blk_protocol, protocol,
- pers_grants ? "persistent grants" : "");
+ blkif->rings = xen_blkif_ring_alloc(blkif, blkif->nr_rings);
+ if (!blkif->rings) {
+ err = -ENOMEM;
+ goto fail;
+ }
+ /*
+ * Enforce postcondition on number of allocated rings; note that if we are
+ * resuming it might happen that nr_supported_hw_queues != nr_rings,
+ * so we cannot rely on such a postcondition.
+ */
+ BUG_ON(!blkif->vbd.nr_supported_hw_queues &&
+ blkif->nr_rings != 1);
- /* Map the shared frame, irq etc. */
- err = xen_blkif_map(be->blkif, ring_ref, evtchn);
- if (err) {
- xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
- ring_ref, evtchn);
- return err;
+ for (i = 0; i < blkif->nr_rings ; i++) {
+ pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
+ ring_ref[i], evtchn[i], blkif->blk_protocol, protocol,
+ pers_grants ? "persistent grants" : "");
+
+ /* Map the shared frame, irq etc. */
+ err = xen_blkif_map(&blkif->rings[i], ring_ref[i], evtchn[i], i);
+ if (err) {
+ xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u of ring %d",
+ ring_ref[i], evtchn[i], i);
+ goto fail;
+ }
}
+ kfree(ring_ref);
+ kfree(evtchn);
+
return 0;
+
+fail:
+ kfree(ring_ref);
+ kfree(evtchn);
+ return err;
}
--
2.1.0
--
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