aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/block/xen-blkfront.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/xen-blkfront.c')
-rw-r--r--drivers/block/xen-blkfront.c120
1 files changed, 76 insertions, 44 deletions
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a9e07d09b230..b4807d12ef29 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -151,6 +151,10 @@ static unsigned int xen_blkif_max_ring_order;
module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
+static bool __read_mostly xen_blkif_trusted = true;
+module_param_named(trusted, xen_blkif_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
#define BLK_RING_SIZE(info) \
__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
@@ -211,6 +215,7 @@ struct blkfront_info
unsigned int feature_discard:1;
unsigned int feature_secdiscard:1;
unsigned int feature_persistent:1;
+ unsigned int bounce:1;
unsigned int discard_granularity;
unsigned int discard_alignment;
/* Number of 4KB segments handled */
@@ -300,8 +305,8 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
if (!gnt_list_entry)
goto out_of_memory;
- if (info->feature_persistent) {
- granted_page = alloc_page(GFP_NOIO);
+ if (info->bounce) {
+ granted_page = alloc_page(GFP_NOIO | __GFP_ZERO);
if (!granted_page) {
kfree(gnt_list_entry);
goto out_of_memory;
@@ -320,7 +325,7 @@ out_of_memory:
list_for_each_entry_safe(gnt_list_entry, n,
&rinfo->grants, node) {
list_del(&gnt_list_entry->node);
- if (info->feature_persistent)
+ if (info->bounce)
__free_page(gnt_list_entry->page);
kfree(gnt_list_entry);
i--;
@@ -366,7 +371,7 @@ static struct grant *get_grant(grant_ref_t *gref_head,
/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
- if (info->feature_persistent)
+ if (info->bounce)
grant_foreign_access(gnt_list_entry, info);
else {
/* Grant access to the GFN passed by the caller */
@@ -390,7 +395,7 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head,
/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
- if (!info->feature_persistent) {
+ if (!info->bounce) {
struct page *indirect_page;
/* Fetch a pre-allocated page to use for indirect grefs */
@@ -705,7 +710,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
.grant_idx = 0,
.segments = NULL,
.rinfo = rinfo,
- .need_copy = rq_data_dir(req) && info->feature_persistent,
+ .need_copy = rq_data_dir(req) && info->bounce,
};
/*
@@ -774,7 +779,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
ring_req->u.rw.handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
- if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) {
+ if (req_op(req) == REQ_OP_FLUSH ||
+ (req_op(req) == REQ_OP_WRITE && (req->cmd_flags & REQ_FUA))) {
/*
* Ideally we can do an unordered flush-to-disk.
* In case the backend onlysupports barriers, use that.
@@ -1026,11 +1032,12 @@ static void xlvbd_flush(struct blkfront_info *info)
{
blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
info->feature_fua ? true : false);
- pr_info("blkfront: %s: %s %s %s %s %s\n",
+ pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
info->gd->disk_name, flush_info(info),
"persistent grants:", info->feature_persistent ?
"enabled;" : "disabled;", "indirect descriptors:",
- info->max_indirect_segments ? "enabled;" : "disabled;");
+ info->max_indirect_segments ? "enabled;" : "disabled;",
+ "bounce buffer:", info->bounce ? "enabled" : "disabled;");
}
static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -1265,7 +1272,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
if (!list_empty(&rinfo->indirect_pages)) {
struct page *indirect_page, *n;
- BUG_ON(info->feature_persistent);
+ BUG_ON(info->bounce);
list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
list_del(&indirect_page->lru);
__free_page(indirect_page);
@@ -1282,7 +1289,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
0, 0UL);
rinfo->persistent_gnts_c--;
}
- if (info->feature_persistent)
+ if (info->bounce)
__free_page(persistent_gnt->page);
kfree(persistent_gnt);
}
@@ -1303,7 +1310,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
for (j = 0; j < segs; j++) {
persistent_gnt = rinfo->shadow[i].grants_used[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
- if (info->feature_persistent)
+ if (info->bounce)
__free_page(persistent_gnt->page);
kfree(persistent_gnt);
}
@@ -1344,7 +1351,8 @@ free_shadow:
rinfo->ring_ref[i] = GRANT_INVALID_REF;
}
}
- free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
+ free_pages_exact(rinfo->ring.sring,
+ info->nr_ring_pages * XEN_PAGE_SIZE);
rinfo->ring.sring = NULL;
if (rinfo->irq)
@@ -1428,9 +1436,15 @@ static int blkif_get_final_status(enum blk_req_status s1,
return BLKIF_RSP_OKAY;
}
-static bool blkif_completion(unsigned long *id,
- struct blkfront_ring_info *rinfo,
- struct blkif_response *bret)
+/*
+ * Return values:
+ * 1 response processed.
+ * 0 missing further responses.
+ * -1 error while processing.
+ */
+static int blkif_completion(unsigned long *id,
+ struct blkfront_ring_info *rinfo,
+ struct blkif_response *bret)
{
int i = 0;
struct scatterlist *sg;
@@ -1453,7 +1467,7 @@ static bool blkif_completion(unsigned long *id,
/* Wait the second response if not yet here. */
if (s2->status < REQ_DONE)
- return false;
+ return 0;
bret->status = blkif_get_final_status(s->status,
s2->status);
@@ -1486,7 +1500,7 @@ static bool blkif_completion(unsigned long *id,
data.s = s;
num_sg = s->num_sg;
- if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
+ if (bret->operation == BLKIF_OP_READ && info->bounce) {
for_each_sg(s->sg, sg, num_sg, i) {
BUG_ON(sg->offset + sg->length > PAGE_SIZE);
@@ -1504,47 +1518,48 @@ static bool blkif_completion(unsigned long *id,
}
/* Add the persistent grant into the list of free grants */
for (i = 0; i < num_grant; i++) {
- if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+ if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) {
/*
* If the grant is still mapped by the backend (the
* backend has chosen to make this grant persistent)
* we add it at the head of the list, so it will be
* reused first.
*/
- if (!info->feature_persistent)
- pr_alert_ratelimited("backed has not unmapped grant: %u\n",
- s->grants_used[i]->gref);
+ if (!info->feature_persistent) {
+ pr_alert("backed has not unmapped grant: %u\n",
+ s->grants_used[i]->gref);
+ return -1;
+ }
list_add(&s->grants_used[i]->node, &rinfo->grants);
rinfo->persistent_gnts_c++;
} else {
/*
- * If the grant is not mapped by the backend we end the
- * foreign access and add it to the tail of the list,
- * so it will not be picked again unless we run out of
- * persistent grants.
+ * If the grant is not mapped by the backend we add it
+ * to the tail of the list, so it will not be picked
+ * again unless we run out of persistent grants.
*/
- gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
s->grants_used[i]->gref = GRANT_INVALID_REF;
list_add_tail(&s->grants_used[i]->node, &rinfo->grants);
}
}
if (s->req.operation == BLKIF_OP_INDIRECT) {
for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
- if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
- if (!info->feature_persistent)
- pr_alert_ratelimited("backed has not unmapped grant: %u\n",
- s->indirect_grants[i]->gref);
+ if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) {
+ if (!info->feature_persistent) {
+ pr_alert("backed has not unmapped grant: %u\n",
+ s->indirect_grants[i]->gref);
+ return -1;
+ }
list_add(&s->indirect_grants[i]->node, &rinfo->grants);
rinfo->persistent_gnts_c++;
} else {
struct page *indirect_page;
- gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL);
/*
* Add the used indirect page back to the list of
* available pages for indirect grefs.
*/
- if (!info->feature_persistent) {
+ if (!info->bounce) {
indirect_page = s->indirect_grants[i]->page;
list_add(&indirect_page->lru, &rinfo->indirect_pages);
}
@@ -1554,7 +1569,7 @@ static bool blkif_completion(unsigned long *id,
}
}
- return true;
+ return 1;
}
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
@@ -1620,12 +1635,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
}
if (bret.operation != BLKIF_OP_DISCARD) {
+ int ret;
+
/*
* We may need to wait for an extra response if the
* I/O request is split in 2
*/
- if (!blkif_completion(&id, rinfo, &bret))
+ ret = blkif_completion(&id, rinfo, &bret);
+ if (!ret)
continue;
+ if (unlikely(ret < 0))
+ goto err;
}
if (add_id_to_freelist(rinfo, id)) {
@@ -1731,8 +1751,7 @@ static int setup_blkring(struct xenbus_device *dev,
for (i = 0; i < info->nr_ring_pages; i++)
rinfo->ring_ref[i] = GRANT_INVALID_REF;
- sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH,
- get_order(ring_size));
+ sring = alloc_pages_exact(ring_size, GFP_NOIO | __GFP_ZERO);
if (!sring) {
xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
return -ENOMEM;
@@ -1742,7 +1761,7 @@ static int setup_blkring(struct xenbus_device *dev,
err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref);
if (err < 0) {
- free_pages((unsigned long)sring, get_order(ring_size));
+ free_pages_exact(sring, ring_size);
rinfo->ring.sring = NULL;
goto fail;
}
@@ -1835,6 +1854,10 @@ static int talk_to_blkback(struct xenbus_device *dev,
if (!info)
return -ENODEV;
+ /* Check if backend is trusted. */
+ info->bounce = !xen_blkif_trusted ||
+ !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
max_page_order = xenbus_read_unsigned(info->xbdev->otherend,
"max-ring-page-order", 0);
ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
@@ -2261,17 +2284,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
if (err)
goto out_of_memory;
- if (!info->feature_persistent && info->max_indirect_segments) {
+ if (!info->bounce && info->max_indirect_segments) {
/*
- * We are using indirect descriptors but not persistent
- * grants, we need to allocate a set of pages that can be
+ * We are using indirect descriptors but don't have a bounce
+ * buffer, we need to allocate a set of pages that can be
* used for mapping indirect grefs
*/
int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
BUG_ON(!list_empty(&rinfo->indirect_pages));
for (i = 0; i < num; i++) {
- struct page *indirect_page = alloc_page(GFP_KERNEL);
+ struct page *indirect_page = alloc_page(GFP_KERNEL |
+ __GFP_ZERO);
if (!indirect_page)
goto out_of_memory;
list_add(&indirect_page->lru, &rinfo->indirect_pages);
@@ -2363,6 +2387,8 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
info->feature_persistent =
!!xenbus_read_unsigned(info->xbdev->otherend,
"feature-persistent", 0);
+ if (info->feature_persistent)
+ info->bounce = true;
indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
"feature-max-indirect-segments", 0);
@@ -2720,11 +2746,10 @@ static void purge_persistent_grants(struct blkfront_info *info)
list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants,
node) {
if (gnt_list_entry->gref == GRANT_INVALID_REF ||
- gnttab_query_foreign_access(gnt_list_entry->gref))
+ !gnttab_try_end_foreign_access(gnt_list_entry->gref))
continue;
list_del(&gnt_list_entry->node);
- gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
rinfo->persistent_gnts_c--;
gnt_list_entry->gref = GRANT_INVALID_REF;
list_add_tail(&gnt_list_entry->node, &rinfo->grants);
@@ -2739,6 +2764,13 @@ static void blkfront_delay_work(struct work_struct *work)
struct blkfront_info *info;
bool need_schedule_work = false;
+ /*
+ * Note that when using bounce buffers but not persistent grants
+ * there's no need to run blkfront_delay_work because grants are
+ * revoked in blkif_completion or else an error is reported and the
+ * connection is closed.
+ */
+
mutex_lock(&blkfront_mutex);
list_for_each_entry(info, &info_list, info_list) {