summaryrefslogtreecommitdiffstats
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/paride/pcd.c4
-rw-r--r--drivers/block/rbd.c396
-rw-r--r--drivers/block/rsxx/core.c81
-rw-r--r--drivers/block/sunvdc.c167
-rw-r--r--drivers/block/virtio_blk.c40
-rw-r--r--drivers/block/xen-blkback/xenbus.c11
-rw-r--r--drivers/block/xen-blkfront.c5
-rw-r--r--drivers/block/zram/zram_drv.c106
-rw-r--r--drivers/block/zram/zram_drv.h6
9 files changed, 550 insertions, 266 deletions
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 719cb1b..3b7c9f1 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -69,8 +69,8 @@
nice This parameter controls the driver's use of
idle CPU time, at the expense of some speed.
- If this driver is built into the kernel, you can use kernel
- the following command line parameters, with the same values
+ If this driver is built into the kernel, you can use the
+ following kernel command line parameters, with the same values
as the corresponding module parameters listed above:
pcd.drive0
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4b97baf..0a54c58 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -210,6 +210,12 @@ enum obj_request_type {
OBJ_REQUEST_NODATA, OBJ_REQUEST_BIO, OBJ_REQUEST_PAGES
};
+enum obj_operation_type {
+ OBJ_OP_WRITE,
+ OBJ_OP_READ,
+ OBJ_OP_DISCARD,
+};
+
enum obj_req_flags {
OBJ_REQ_DONE, /* completion flag: not done = 0, done = 1 */
OBJ_REQ_IMG_DATA, /* object usage: standalone = 0, image = 1 */
@@ -276,6 +282,7 @@ enum img_req_flags {
IMG_REQ_WRITE, /* I/O direction: read = 0, write = 1 */
IMG_REQ_CHILD, /* initiator: block = 0, child image = 1 */
IMG_REQ_LAYERED, /* ENOENT handling: normal = 0, layered = 1 */
+ IMG_REQ_DISCARD, /* discard: normal = 0, discard request = 1 */
};
struct rbd_img_request {
@@ -785,6 +792,20 @@ static int parse_rbd_opts_token(char *c, void *private)
return 0;
}
+static char* obj_op_name(enum obj_operation_type op_type)
+{
+ switch (op_type) {
+ case OBJ_OP_READ:
+ return "read";
+ case OBJ_OP_WRITE:
+ return "write";
+ case OBJ_OP_DISCARD:
+ return "discard";
+ default:
+ return "???";
+ }
+}
+
/*
* Get a ceph client with specific addr and configuration, if one does
* not exist create it. Either way, ceph_opts is consumed by this
@@ -1600,6 +1621,21 @@ static bool img_request_write_test(struct rbd_img_request *img_request)
return test_bit(IMG_REQ_WRITE, &img_request->flags) != 0;
}
+/*
+ * Set the discard flag when the img_request is an discard request
+ */
+static void img_request_discard_set(struct rbd_img_request *img_request)
+{
+ set_bit(IMG_REQ_DISCARD, &img_request->flags);
+ smp_mb();
+}
+
+static bool img_request_discard_test(struct rbd_img_request *img_request)
+{
+ smp_mb();
+ return test_bit(IMG_REQ_DISCARD, &img_request->flags) != 0;
+}
+
static void img_request_child_set(struct rbd_img_request *img_request)
{
set_bit(IMG_REQ_CHILD, &img_request->flags);
@@ -1636,6 +1672,17 @@ static bool img_request_layered_test(struct rbd_img_request *img_request)
return test_bit(IMG_REQ_LAYERED, &img_request->flags) != 0;
}
+static enum obj_operation_type
+rbd_img_request_op_type(struct rbd_img_request *img_request)
+{
+ if (img_request_write_test(img_request))
+ return OBJ_OP_WRITE;
+ else if (img_request_discard_test(img_request))
+ return OBJ_OP_DISCARD;
+ else
+ return OBJ_OP_READ;
+}
+
static void
rbd_img_obj_request_read_callback(struct rbd_obj_request *obj_request)
{
@@ -1722,6 +1769,21 @@ static void rbd_osd_write_callback(struct rbd_obj_request *obj_request)
obj_request_done_set(obj_request);
}
+static void rbd_osd_discard_callback(struct rbd_obj_request *obj_request)
+{
+ dout("%s: obj %p result %d %llu\n", __func__, obj_request,
+ obj_request->result, obj_request->length);
+ /*
+ * There is no such thing as a successful short discard. Set
+ * it to our originally-requested length.
+ */
+ obj_request->xferred = obj_request->length;
+ /* discarding a non-existent object is not a problem */
+ if (obj_request->result == -ENOENT)
+ obj_request->result = 0;
+ obj_request_done_set(obj_request);
+}
+
/*
* For a simple stat call there's nothing to do. We'll do more if
* this is part of a write sequence for a layered image.
@@ -1773,6 +1835,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_STAT:
rbd_osd_stat_callback(obj_request);
break;
+ case CEPH_OSD_OP_DELETE:
+ case CEPH_OSD_OP_TRUNCATE:
+ case CEPH_OSD_OP_ZERO:
+ rbd_osd_discard_callback(obj_request);
+ break;
case CEPH_OSD_OP_CALL:
case CEPH_OSD_OP_NOTIFY_ACK:
case CEPH_OSD_OP_WATCH:
@@ -1823,7 +1890,7 @@ static void rbd_osd_req_format_write(struct rbd_obj_request *obj_request)
*/
static struct ceph_osd_request *rbd_osd_req_create(
struct rbd_device *rbd_dev,
- bool write_request,
+ enum obj_operation_type op_type,
unsigned int num_ops,
struct rbd_obj_request *obj_request)
{
@@ -1831,16 +1898,18 @@ static struct ceph_osd_request *rbd_osd_req_create(
struct ceph_osd_client *osdc;
struct ceph_osd_request *osd_req;
- if (obj_request_img_data_test(obj_request)) {
+ if (obj_request_img_data_test(obj_request) &&
+ (op_type == OBJ_OP_DISCARD || op_type == OBJ_OP_WRITE)) {
struct rbd_img_request *img_request = obj_request->img_request;
-
- rbd_assert(write_request ==
- img_request_write_test(img_request));
- if (write_request)
- snapc = img_request->snapc;
+ if (op_type == OBJ_OP_WRITE) {
+ rbd_assert(img_request_write_test(img_request));
+ } else {
+ rbd_assert(img_request_discard_test(img_request));
+ }
+ snapc = img_request->snapc;
}
- rbd_assert(num_ops == 1 || (write_request && num_ops == 2));
+ rbd_assert(num_ops == 1 || ((op_type == OBJ_OP_WRITE) && num_ops == 2));
/* Allocate and initialize the request, for the num_ops ops */
@@ -1850,7 +1919,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
if (!osd_req)
return NULL; /* ENOMEM */
- if (write_request)
+ if (op_type == OBJ_OP_WRITE || op_type == OBJ_OP_DISCARD)
osd_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
else
osd_req->r_flags = CEPH_OSD_FLAG_READ;
@@ -1865,9 +1934,10 @@ static struct ceph_osd_request *rbd_osd_req_create(
}
/*
- * Create a copyup osd request based on the information in the
- * object request supplied. A copyup request has three osd ops,
- * a copyup method call, a hint op, and a write op.
+ * Create a copyup osd request based on the information in the object
+ * request supplied. A copyup request has two or three osd ops, a
+ * copyup method call, potentially a hint op, and a write or truncate
+ * or zero op.
*/
static struct ceph_osd_request *
rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
@@ -1877,18 +1947,24 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
struct rbd_device *rbd_dev;
struct ceph_osd_client *osdc;
struct ceph_osd_request *osd_req;
+ int num_osd_ops = 3;
rbd_assert(obj_request_img_data_test(obj_request));
img_request = obj_request->img_request;
rbd_assert(img_request);
- rbd_assert(img_request_write_test(img_request));
+ rbd_assert(img_request_write_test(img_request) ||
+ img_request_discard_test(img_request));
+
+ if (img_request_discard_test(img_request))
+ num_osd_ops = 2;
- /* Allocate and initialize the request, for the three ops */
+ /* Allocate and initialize the request, for all the ops */
snapc = img_request->snapc;
rbd_dev = img_request->rbd_dev;
osdc = &rbd_dev->rbd_client->client->osdc;
- osd_req = ceph_osdc_alloc_request(osdc, snapc, 3, false, GFP_ATOMIC);
+ osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops,
+ false, GFP_ATOMIC);
if (!osd_req)
return NULL; /* ENOMEM */
@@ -2057,7 +2133,8 @@ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
static struct rbd_img_request *rbd_img_request_create(
struct rbd_device *rbd_dev,
u64 offset, u64 length,
- bool write_request)
+ enum obj_operation_type op_type,
+ struct ceph_snap_context *snapc)
{
struct rbd_img_request *img_request;
@@ -2065,20 +2142,17 @@ static struct rbd_img_request *rbd_img_request_create(
if (!img_request)
return NULL;
- if (write_request) {
- down_read(&rbd_dev->header_rwsem);
- ceph_get_snap_context(rbd_dev->header.snapc);
- up_read(&rbd_dev->header_rwsem);
- }
-
img_request->rq = NULL;
img_request->rbd_dev = rbd_dev;
img_request->offset = offset;
img_request->length = length;
img_request->flags = 0;
- if (write_request) {
+ if (op_type == OBJ_OP_DISCARD) {
+ img_request_discard_set(img_request);
+ img_request->snapc = snapc;
+ } else if (op_type == OBJ_OP_WRITE) {
img_request_write_set(img_request);
- img_request->snapc = rbd_dev->header.snapc;
+ img_request->snapc = snapc;
} else {
img_request->snap_id = rbd_dev->spec->snap_id;
}
@@ -2093,8 +2167,7 @@ static struct rbd_img_request *rbd_img_request_create(
kref_init(&img_request->kref);
dout("%s: rbd_dev %p %s %llu/%llu -> img %p\n", __func__, rbd_dev,
- write_request ? "write" : "read", offset, length,
- img_request);
+ obj_op_name(op_type), offset, length, img_request);
return img_request;
}
@@ -2118,7 +2191,8 @@ static void rbd_img_request_destroy(struct kref *kref)
rbd_dev_parent_put(img_request->rbd_dev);
}
- if (img_request_write_test(img_request))
+ if (img_request_write_test(img_request) ||
+ img_request_discard_test(img_request))
ceph_put_snap_context(img_request->snapc);
kmem_cache_free(rbd_img_request_cache, img_request);
@@ -2134,8 +2208,8 @@ static struct rbd_img_request *rbd_parent_request_create(
rbd_assert(obj_request->img_request);
rbd_dev = obj_request->img_request->rbd_dev;
- parent_request = rbd_img_request_create(rbd_dev->parent,
- img_offset, length, false);
+ parent_request = rbd_img_request_create(rbd_dev->parent, img_offset,
+ length, OBJ_OP_READ, NULL);
if (!parent_request)
return NULL;
@@ -2176,11 +2250,18 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
result = obj_request->result;
if (result) {
struct rbd_device *rbd_dev = img_request->rbd_dev;
+ enum obj_operation_type op_type;
+
+ if (img_request_discard_test(img_request))
+ op_type = OBJ_OP_DISCARD;
+ else if (img_request_write_test(img_request))
+ op_type = OBJ_OP_WRITE;
+ else
+ op_type = OBJ_OP_READ;
rbd_warn(rbd_dev, "%s %llx at %llx (%llx)",
- img_request_write_test(img_request) ? "write" : "read",
- obj_request->length, obj_request->img_offset,
- obj_request->offset);
+ obj_op_name(op_type), obj_request->length,
+ obj_request->img_offset, obj_request->offset);
rbd_warn(rbd_dev, " result %d xferred %x",
result, xferred);
if (!img_request->result)
@@ -2245,6 +2326,67 @@ out:
}
/*
+ * Add individual osd ops to the given ceph_osd_request and prepare
+ * them for submission. num_ops is the current number of
+ * osd operations already to the object request.
+ */
+static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request,
+ struct ceph_osd_request *osd_request,
+ enum obj_operation_type op_type,
+ unsigned int num_ops)
+{
+ struct rbd_img_request *img_request = obj_request->img_request;
+ struct rbd_device *rbd_dev = img_request->rbd_dev;
+ u64 object_size = rbd_obj_bytes(&rbd_dev->header);
+ u64 offset = obj_request->offset;
+ u64 length = obj_request->length;
+ u64 img_end;
+ u16 opcode;
+
+ if (op_type == OBJ_OP_DISCARD) {
+ if (!offset && length == object_size &&
+ (!img_request_layered_test(img_request) ||
+ !obj_request_overlaps_parent(obj_request))) {
+ opcode = CEPH_OSD_OP_DELETE;
+ } else if ((offset + length == object_size)) {
+ opcode = CEPH_OSD_OP_TRUNCATE;
+ } else {
+ down_read(&rbd_dev->header_rwsem);
+ img_end = rbd_dev->header.image_size;
+ up_read(&rbd_dev->header_rwsem);
+
+ if (obj_request->img_offset + length == img_end)
+ opcode = CEPH_OSD_OP_TRUNCATE;
+ else
+ opcode = CEPH_OSD_OP_ZERO;
+ }
+ } else if (op_type == OBJ_OP_WRITE) {
+ opcode = CEPH_OSD_OP_WRITE;
+ osd_req_op_alloc_hint_init(osd_request, num_ops,
+ object_size, object_size);
+ num_ops++;
+ } else {
+ opcode = CEPH_OSD_OP_READ;
+ }
+
+ osd_req_op_extent_init(osd_request, num_ops, opcode, offset, length,
+ 0, 0);
+ if (obj_request->type == OBJ_REQUEST_BIO)
+ osd_req_op_extent_osd_data_bio(osd_request, num_ops,
+ obj_request->bio_list, length);
+ else if (obj_request->type == OBJ_REQUEST_PAGES)
+ osd_req_op_extent_osd_data_pages(osd_request, num_ops,
+ obj_request->pages, length,
+ offset & ~PAGE_MASK, false, false);
+
+ /* Discards are also writes */
+ if (op_type == OBJ_OP_WRITE || op_type == OBJ_OP_DISCARD)
+ rbd_osd_req_format_write(obj_request);
+ else
+ rbd_osd_req_format_read(obj_request);
+}
+
+/*
* Split up an image request into one or more object requests, each
* to a different object. The "type" parameter indicates whether
* "data_desc" is the pointer to the head of a list of bio
@@ -2259,28 +2401,26 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
struct rbd_device *rbd_dev = img_request->rbd_dev;
struct rbd_obj_request *obj_request = NULL;
struct rbd_obj_request *next_obj_request;
- bool write_request = img_request_write_test(img_request);
struct bio *bio_list = NULL;
unsigned int bio_offset = 0;
struct page **pages = NULL;
+ enum obj_operation_type op_type;
u64 img_offset;
u64 resid;
- u16 opcode;
dout("%s: img %p type %d data_desc %p\n", __func__, img_request,
(int)type, data_desc);
- opcode = write_request ? CEPH_OSD_OP_WRITE : CEPH_OSD_OP_READ;
img_offset = img_request->offset;
resid = img_request->length;
rbd_assert(resid > 0);
+ op_type = rbd_img_request_op_type(img_request);
if (type == OBJ_REQUEST_BIO) {
bio_list = data_desc;
rbd_assert(img_offset ==
bio_list->bi_iter.bi_sector << SECTOR_SHIFT);
- } else {
- rbd_assert(type == OBJ_REQUEST_PAGES);
+ } else if (type == OBJ_REQUEST_PAGES) {
pages = data_desc;
}
@@ -2289,7 +2429,6 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
const char *object_name;
u64 offset;
u64 length;
- unsigned int which = 0;
object_name = rbd_segment_name(rbd_dev, img_offset);
if (!object_name)
@@ -2321,7 +2460,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
GFP_ATOMIC);
if (!obj_request->bio_list)
goto out_unwind;
- } else {
+ } else if (type == OBJ_REQUEST_PAGES) {
unsigned int page_count;
obj_request->pages = pages;
@@ -2332,38 +2471,19 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
pages += page_count;
}
- osd_req = rbd_osd_req_create(rbd_dev, write_request,
- (write_request ? 2 : 1),
- obj_request);
+ osd_req = rbd_osd_req_create(rbd_dev, op_type,
+ (op_type == OBJ_OP_WRITE) ? 2 : 1,
+ obj_request);
if (!osd_req)
goto out_unwind;
+
obj_request->osd_req = osd_req;
obj_request->callback = rbd_img_obj_callback;
- rbd_img_request_get(img_request);
-
- if (write_request) {
- osd_req_op_alloc_hint_init(osd_req, which,
- rbd_obj_bytes(&rbd_dev->header),
- rbd_obj_bytes(&rbd_dev->header));
- which++;
- }
-
- osd_req_op_extent_init(osd_req, which, opcode, offset, length,
- 0, 0);
- if (type == OBJ_REQUEST_BIO)
- osd_req_op_extent_osd_data_bio(osd_req, which,
- obj_request->bio_list, length);
- else
- osd_req_op_extent_osd_data_pages(osd_req, which,
- obj_request->pages, length,
- offset & ~PAGE_MASK, false, false);
+ obj_request->img_offset = img_offset;
- if (write_request)
- rbd_osd_req_format_write(obj_request);
- else
- rbd_osd_req_format_read(obj_request);
+ rbd_img_obj_request_fill(obj_request, osd_req, op_type, 0);
- obj_request->img_offset = img_offset;
+ rbd_img_request_get(img_request);
img_offset += length;
resid -= length;
@@ -2386,7 +2506,8 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
struct page **pages;
u32 page_count;
- rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+ rbd_assert(obj_request->type == OBJ_REQUEST_BIO ||
+ obj_request->type == OBJ_REQUEST_NODATA);
rbd_assert(obj_request_img_data_test(obj_request));
img_request = obj_request->img_request;
rbd_assert(img_request);
@@ -2424,11 +2545,10 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
struct ceph_osd_client *osdc;
struct rbd_device *rbd_dev;
struct page **pages;
+ enum obj_operation_type op_type;
u32 page_count;
int img_result;
u64 parent_length;
- u64 offset;
- u64 length;
rbd_assert(img_request_child_test(img_request));
@@ -2492,26 +2612,10 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
osd_req_op_cls_request_data_pages(osd_req, 0, pages, parent_length, 0,
false, false);
- /* Then the hint op */
+ /* Add the other op(s) */
- osd_req_op_alloc_hint_init(osd_req, 1, rbd_obj_bytes(&rbd_dev->header),
- rbd_obj_bytes(&rbd_dev->header));
-
- /* And the original write request op */
-
- offset = orig_request->offset;
- length = orig_request->length;
- osd_req_op_extent_init(osd_req, 2, CEPH_OSD_OP_WRITE,
- offset, length, 0, 0);
- if (orig_request->type == OBJ_REQUEST_BIO)
- osd_req_op_extent_osd_data_bio(osd_req, 2,
- orig_request->bio_list, length);
- else
- osd_req_op_extent_osd_data_pages(osd_req, 2,
- orig_request->pages, length,
- offset & ~PAGE_MASK, false, false);
-
- rbd_osd_req_format_write(orig_request);
+ op_type = rbd_img_request_op_type(orig_request->img_request);
+ rbd_img_obj_request_fill(orig_request, osd_req, op_type, 1);
/* All set, send it off. */
@@ -2728,7 +2832,7 @@ static int rbd_img_obj_exists_submit(struct rbd_obj_request *obj_request)
rbd_assert(obj_request->img_request);
rbd_dev = obj_request->img_request->rbd_dev;
- stat_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+ stat_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
stat_request);
if (!stat_request->osd_req)
goto out;
@@ -2748,11 +2852,10 @@ out:
return ret;
}
-static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
+static bool img_obj_request_simple(struct rbd_obj_request *obj_request)
{
struct rbd_img_request *img_request;
struct rbd_device *rbd_dev;
- bool known;
rbd_assert(obj_request_img_data_test(obj_request));
@@ -2760,22 +2863,44 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
rbd_assert(img_request);
rbd_dev = img_request->rbd_dev;
+ /* Reads */
+ if (!img_request_write_test(img_request) &&
+ !img_request_discard_test(img_request))
+ return true;
+
+ /* Non-layered writes */
+ if (!img_request_layered_test(img_request))
+ return true;
+
+ /*
+ * Layered writes outside of the parent overlap range don't
+ * share any data with the parent.
+ */
+ if (!obj_request_overlaps_parent(obj_request))
+ return true;
+
/*
- * Only writes to layered images need special handling.
- * Reads and non-layered writes are simple object requests.
- * Layered writes that start beyond the end of the overlap
- * with the parent have no parent data, so they too are
- * simple object requests. Finally, if the target object is
- * known to already exist, its parent data has already been
- * copied, so a write to the object can also be handled as a
- * simple object request.
+ * Entire-object layered writes - we will overwrite whatever
+ * parent data there is anyway.
*/
- if (!img_request_write_test(img_request) ||
- !img_request_layered_test(img_request) ||
- !obj_request_overlaps_parent(obj_request) ||
- ((known = obj_request_known_test(obj_request)) &&
- obj_request_exists_test(obj_request))) {
+ if (!obj_request->offset &&
+ obj_request->length == rbd_obj_bytes(&rbd_dev->header))
+ return true;
+
+ /*
+ * If the object is known to already exist, its parent data has
+ * already been copied.
+ */
+ if (obj_request_known_test(obj_request) &&
+ obj_request_exists_test(obj_request))
+ return true;
+
+ return false;
+}
+static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
+{
+ if (img_obj_request_simple(obj_request)) {
struct rbd_device *rbd_dev;
struct ceph_osd_client *osdc;
@@ -2791,7 +2916,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
* start by reading the data for the full target object from
* the parent so we can use it for a copyup to the target.
*/
- if (known)
+ if (obj_request_known_test(obj_request))
return rbd_img_obj_parent_read_full(obj_request);
/* We don't know whether the target exists. Go find out. */
@@ -2932,7 +3057,7 @@ static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
return -ENOMEM;
ret = -ENOMEM;
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+ obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
obj_request);
if (!obj_request->osd_req)
goto out;
@@ -2995,7 +3120,7 @@ static struct rbd_obj_request *rbd_obj_watch_request_helper(
if (!obj_request)
return ERR_PTR(-ENOMEM);
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
+ obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_WRITE, 1,
obj_request);
if (!obj_request->osd_req) {
ret = -ENOMEM;
@@ -3133,7 +3258,7 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
obj_request->pages = pages;
obj_request->page_count = page_count;
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+ obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
obj_request);
if (!obj_request->osd_req)
goto out;
@@ -3183,11 +3308,20 @@ out:
static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
{
struct rbd_img_request *img_request;
+ struct ceph_snap_context *snapc = NULL;
u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT;
u64 length = blk_rq_bytes(rq);
- bool wr = rq_data_dir(rq) == WRITE;
+ enum obj_operation_type op_type;
+ u64 mapping_size;
int result;
+ if (rq->cmd_flags & REQ_DISCARD)
+ op_type = OBJ_OP_DISCARD;
+ else if (rq->cmd_flags & REQ_WRITE)
+ op_type = OBJ_OP_WRITE;
+ else
+ op_type = OBJ_OP_READ;
+
/* Ignore/skip any zero-length requests */
if (!length) {
@@ -3196,9 +3330,9 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
goto err_rq;
}
- /* Disallow writes to a read-only device */
+ /* Only reads are allowed to a read-only device */
- if (wr) {
+ if (op_type != OBJ_OP_READ) {
if (rbd_dev->mapping.read_only) {
result = -EROFS;
goto err_rq;
@@ -3226,21 +3360,35 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
goto err_rq; /* Shouldn't happen */
}
- if (offset + length > rbd_dev->mapping.size) {
+ down_read(&rbd_dev->header_rwsem);
+ mapping_size = rbd_dev->mapping.size;
+ if (op_type != OBJ_OP_READ) {
+ snapc = rbd_dev->header.snapc;
+ ceph_get_snap_context(snapc);
+ }
+ up_read(&rbd_dev->header_rwsem);
+
+ if (offset + length > mapping_size) {
rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", offset,
- length, rbd_dev->mapping.size);
+ length, mapping_size);
result = -EIO;
goto err_rq;
}
- img_request = rbd_img_request_create(rbd_dev, offset, length, wr);
+ img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,
+ snapc);
if (!img_request) {
result = -ENOMEM;
goto err_rq;
}
img_request->rq = rq;
- result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO, rq->bio);
+ if (op_type == OBJ_OP_DISCARD)
+ result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
+ NULL);
+ else
+ result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
+ rq->bio);
if (result)
goto err_img_request;
@@ -3255,7 +3403,9 @@ err_img_request:
err_rq:
if (result)
rbd_warn(rbd_dev, "%s %llx at %llx result %d",
- wr ? "write" : "read", length, offset, result);
+ obj_op_name(op_type), length, offset, result);
+ if (snapc)
+ ceph_put_snap_context(snapc);
blk_end_request_all(rq, result);
}
@@ -3393,7 +3543,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
obj_request->pages = pages;
obj_request->page_count = page_count;
- obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+ obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
obj_request);
if (!obj_request->osd_req)
goto out;
@@ -3610,6 +3760,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
blk_queue_io_min(q, segment_size);
blk_queue_io_opt(q, segment_size);
+ /* enable the discard support */
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+ q->limits.discard_granularity = segment_size;
+ q->limits.discard_alignment = segment_size;
+ q->limits.max_discard_sectors = segment_size / SECTOR_SIZE;
+ q->limits.discard_zeroes_data = 1;
+
blk_queue_merge_bvec(q, rbd_merge_bvec);
disk->queue = q;
@@ -4924,7 +5081,7 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev)
ret = image_id ? 0 : -ENOMEM;
if (!ret)
rbd_dev->image_format = 1;
- } else if (ret > sizeof (__le32)) {
+ } else if (ret >= 0) {
void *p = response;
image_id = ceph_extract_encoded_string(&p, p + ret,
@@ -4932,8 +5089,6 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev)
ret = PTR_ERR_OR_ZERO(image_id);
if (!ret)
rbd_dev->image_format = 2;
- } else {
- ret = -EINVAL;
}
if (!ret) {
@@ -5087,7 +5242,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
- rbd_dev->rq_wq = alloc_workqueue("%s", 0, 0, rbd_dev->disk->disk_name);
+ rbd_dev->rq_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+ rbd_dev->disk->disk_name);
if (!rbd_dev->rq_wq) {
ret = -ENOMEM;
goto err_out_mapping;
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 820b400..3265ce9 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -62,12 +62,6 @@ static DEFINE_SPINLOCK(rsxx_ida_lock);
/* --------------------Debugfs Setup ------------------- */
-struct rsxx_cram {
- u32 f_pos;
- u32 offset;
- void *i_private;
-};
-
static int rsxx_attr_pci_regs_show(struct seq_file *m, void *p)
{
struct rsxx_cardinfo *card = m->private;
@@ -184,93 +178,50 @@ static int rsxx_attr_pci_regs_open(struct inode *inode, struct file *file)
static ssize_t rsxx_cram_read(struct file *fp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct rsxx_cram *info = fp->private_data;
- struct rsxx_cardinfo *card = info->i_private;
+ struct rsxx_cardinfo *card = file_inode(fp)->i_private;
char *buf;
- int st;
+ ssize_t st;
- buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+ buf = kzalloc(cnt, GFP_KERNEL);
if (!buf)
return -ENOMEM;
- info->f_pos = (u32)*ppos + info->offset;
-
- st = rsxx_creg_read(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
- if (st)
- return st;
-
- st = copy_to_user(ubuf, buf, cnt);
+ st = rsxx_creg_read(card, CREG_ADD_CRAM + (u32)*ppos, cnt, buf, 1);
+ if (!st)
+ st = copy_to_user(ubuf, buf, cnt);
+ kfree(buf);
if (st)
return st;
-
- info->offset += cnt;
-
- kfree(buf);
-
+ *ppos += cnt;
return cnt;
}
static ssize_t rsxx_cram_write(struct file *fp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct rsxx_cram *info = fp->private_data;
- struct rsxx_cardinfo *card = info->i_private;
+ struct rsxx_cardinfo *card = file_inode(fp)->i_private;
char *buf;
- int st;
+ ssize_t st;
- buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+ buf = kzalloc(cnt, GFP_KERNEL);
if (!buf)
return -ENOMEM;
st = copy_from_user(buf, ubuf, cnt);
+ if (!st)
+ st = rsxx_creg_write(card, CREG_ADD_CRAM + (u32)*ppos, cnt,
+ buf, 1);
+ kfree(buf);
if (st)
return st;
-
- info->f_pos = (u32)*ppos + info->offset;
-
- st = rsxx_creg_write(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
- if (st)
- return st;
-
- info->offset += cnt;
-
- kfree(buf);
-
+ *ppos += cnt;
return cnt;
}
-static int rsxx_cram_open(struct inode *inode, struct file *file)
-{
- struct rsxx_cram *info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info)
- return -ENOMEM;
-
- info->i_private = inode->i_private;
- info->f_pos = file->f_pos;
- file->private_data = info;
-
- return 0;
-}
-
-static int rsxx_cram_release(struct inode *inode, struct file *file)
-{
- struct rsxx_cram *info = file->private_data;
-
- if (!info)
- return 0;
-
- kfree(info);
- file->private_data = NULL;
-
- return 0;
-}
-
static const struct file_operations debugfs_cram_fops = {
.owner = THIS_MODULE,
- .open = rsxx_cram_open,
.read = rsxx_cram_read,
.write = rsxx_cram_write,
- .release = rsxx_cram_release,
};
static const struct file_operations debugfs_stats_fops = {
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb..756b8ec 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/genhd.h>
+#include <linux/cdrom.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
@@ -22,8 +23,8 @@
#define DRV_MODULE_NAME "sunvdc"
#define PFX DRV_MODULE_NAME ": "
-#define DRV_MODULE_VERSION "1.0"
-#define DRV_MODULE_RELDATE "June 25, 2007"
+#define DRV_MODULE_VERSION "1.1"
+#define DRV_MODULE_RELDATE "February 13, 2013"
static char version[] =
DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_VERSION);
-#define VDC_TX_RING_SIZE 256
+#define VDC_TX_RING_SIZE 512
#define WAITING_FOR_LINK_UP 0x01
#define WAITING_FOR_TX_SPACE 0x02
@@ -65,10 +66,10 @@ struct vdc_port {
u64 operations;
u32 vdisk_size;
u8 vdisk_type;
+ u8 vdisk_mtype;
char disk_name[32];
- struct vio_disk_geom geom;
struct vio_disk_vtoc label;
};
@@ -79,9 +80,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
/* Ordered from largest major to lowest */
static struct vio_version vdc_versions[] = {
+ { .major = 1, .minor = 1 },
{ .major = 1, .minor = 0 },
};
+static inline int vdc_version_supported(struct vdc_port *port,
+ u16 major, u16 minor)
+{
+ return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
#define VDCBLK_NAME "vdisk"
static int vdc_major;
#define PARTITION_SHIFT 3
@@ -94,18 +102,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct gendisk *disk = bdev->bd_disk;
- struct vdc_port *port = disk->private_data;
+ sector_t nsect = get_capacity(disk);
+ sector_t cylinders = nsect;
- geo->heads = (u8) port->geom.num_hd;
- geo->sectors = (u8) port->geom.num_sec;
- geo->cylinders = port->geom.num_cyl;
+ geo->heads = 0xff;
+ geo->sectors = 0x3f;
+ sector_div(cylinders, geo->heads * geo->sectors);
+ geo->cylinders = cylinders;
+ if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+ geo->cylinders = 0xffff;
return 0;
}
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned command, unsigned long argument)
+{
+ int i;
+ struct gendisk *disk;
+
+ switch (command) {
+ case CDROMMULTISESSION:
+ pr_debug(PFX "Multisession CDs not supported\n");
+ for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+ if (put_user(0, (char __user *)(argument + i)))
+ return -EFAULT;
+ return 0;
+
+ case CDROM_GET_CAPABILITY:
+ disk = bdev->bd_disk;
+
+ if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+ return 0;
+ return -EINVAL;
+
+ default:
+ pr_debug(PFX "ioctl %08x not supported\n", command);
+ return -EINVAL;
+ }
+}
+
static const struct block_device_operations vdc_fops = {
.owner = THIS_MODULE,
.getgeo = vdc_getgeo,
+ .ioctl = vdc_ioctl,
};
static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +209,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
struct vio_disk_attr_info *pkt = arg;
viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
- "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+ "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
pkt->tag.stype, pkt->operations,
- pkt->vdisk_size, pkt->vdisk_type,
+ pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
pkt->xfer_mode, pkt->vdisk_block_size,
pkt->max_xfer_size);
@@ -192,8 +236,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
}
port->operations = pkt->operations;
- port->vdisk_size = pkt->vdisk_size;
port->vdisk_type = pkt->vdisk_type;
+ if (vdc_version_supported(port, 1, 1)) {
+ port->vdisk_size = pkt->vdisk_size;
+ port->vdisk_mtype = pkt->vdisk_mtype;
+ }
if (pkt->max_xfer_size < port->max_xfer_size)
port->max_xfer_size = pkt->max_xfer_size;
port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +283,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
- if (blk_queue_stopped(port->disk->queue))
+ /* restart blk queue when ring is half emptied */
+ if (blk_queue_stopped(port->disk->queue) &&
+ vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
blk_start_queue(port->disk->queue);
}
@@ -388,12 +437,6 @@ static int __send_request(struct request *req)
for (i = 0; i < nsg; i++)
len += sg[i].length;
- if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
- blk_stop_queue(port->disk->queue);
- err = -ENOMEM;
- goto out;
- }
-
desc = vio_dring_cur(dr);
err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +476,32 @@ static int __send_request(struct request *req)
port->req_id++;
dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
}
-out:
return err;
}
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
{
- while (1) {
- struct request *req = blk_fetch_request(q);
+ struct request *req;
- if (!req)
- break;
+ while ((req = blk_peek_request(rq)) != NULL) {
+ struct vdc_port *port;
+ struct vio_dring_state *dr;
+
+ port = req->rq_disk->private_data;
+ dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+ if (unlikely(vdc_tx_dring_avail(dr) < 1))
+ goto wait;
+
+ blk_start_request(req);
- if (__send_request(req) < 0)
- __blk_end_request_all(req, -EIO);
+ if (__send_request(req) < 0) {
+ blk_requeue_request(rq, req);
+wait:
+ /* Avoid pointless unplugs. */
+ blk_stop_queue(rq);
+ break;
+ }
}
}
@@ -663,18 +717,27 @@ static int probe_disk(struct vdc_port *port)
return err;
}
- err = generic_request(port, VD_OP_GET_DISKGEOM,
- &port->geom, sizeof(port->geom));
- if (err < 0) {
- printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
- "error %d\n", err);
- return err;
+ if (vdc_version_supported(port, 1, 1)) {
+ /* vdisk_size should be set during the handshake, if it wasn't
+ * then the underlying disk is reserved by another system
+ */
+ if (port->vdisk_size == -1)
+ return -ENODEV;
+ } else {
+ struct vio_disk_geom geom;
+
+ err = generic_request(port, VD_OP_GET_DISKGEOM,
+ &geom, sizeof(geom));
+ if (err < 0) {
+ printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+ "error %d\n", err);
+ return err;
+ }
+ port->vdisk_size = ((u64)geom.num_cyl *
+ (u64)geom.num_hd *
+ (u64)geom.num_sec);
}
- port->vdisk_size = ((u64)port->geom.num_cyl *
- (u64)port->geom.num_hd *
- (u64)port->geom.num_sec);
-
q = blk_init_queue(do_vdc_request, &port->vio.lock);
if (!q) {
printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +754,10 @@ static int probe_disk(struct vdc_port *port)
port->disk = g;
+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(q, PAGE_SIZE);
+
blk_queue_max_segments(q, port->ring_cookies);
blk_queue_max_hw_sectors(q, port->max_xfer_size);
g->major = vdc_major;
@@ -704,9 +771,32 @@ static int probe_disk(struct vdc_port *port)
set_capacity(g, port->vdisk_size);
- printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+ if (vdc_version_supported(port, 1, 1)) {
+ switch (port->vdisk_mtype) {
+ case VD_MEDIA_TYPE_CD:
+ pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_DVD:
+ pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_FIXED:
+ pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+ break;
+ }
+ }
+
+ pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
g->disk_name,
- port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+ port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+ port->vio.ver.major, port->vio.ver.minor);
add_disk(g);
@@ -765,6 +855,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
else
snprintf(port->disk_name, sizeof(port->disk_name),
VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+ port->vdisk_size = -1;
err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index f751fc3..c6a27d5 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -41,12 +41,6 @@ struct virtio_blk
/* Process context for config space updates */
struct work_struct config_work;
- /* Lock for config space updates */
- struct mutex config_lock;
-
- /* enable config space updates */
- bool config_enable;
-
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems;
@@ -349,10 +343,6 @@ static void virtblk_config_changed_work(struct work_struct *work)
char *envp[] = { "RESIZE=1", NULL };
u64 capacity, size;
- mutex_lock(&vblk->config_lock);
- if (!vblk->config_enable)
- goto done;
-
/* Host must always specify the capacity. */
virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity);
@@ -376,8 +366,6 @@ static void virtblk_config_changed_work(struct work_struct *work)
set_capacity(vblk->disk, capacity);
revalidate_disk(vblk->disk);
kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
-done:
- mutex_unlock(&vblk->config_lock);
}
static void virtblk_config_changed(struct virtio_device *vdev)
@@ -608,10 +596,8 @@ static int virtblk_probe(struct virtio_device *vdev)
vblk->vdev = vdev;
vblk->sg_elems = sg_elems;
- mutex_init(&vblk->config_lock);
INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
- vblk->config_enable = true;
err = init_vq(vblk);
if (err)
@@ -735,6 +721,8 @@ static int virtblk_probe(struct virtio_device *vdev)
if (!err && opt_io_size)
blk_queue_io_opt(q, blk_size * opt_io_size);
+ virtio_device_ready(vdev);
+
add_disk(vblk->disk);
err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
if (err)
@@ -773,10 +761,8 @@ static void virtblk_remove(struct virtio_device *vdev)
int index = vblk->index;
int refc;
- /* Prevent config work handler from accessing the device. */
- mutex_lock(&vblk->config_lock);
- vblk->config_enable = false;
- mutex_unlock(&vblk->config_lock);
+ /* Make sure no work handler is accessing the device. */
+ flush_work(&vblk->config_work);
del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
@@ -786,8 +772,6 @@ static void virtblk_remove(struct virtio_device *vdev)
/* Stop all the virtqueues. */
vdev->config->reset(vdev);
- flush_work(&vblk->config_work);
-
refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
put_disk(vblk->disk);
vdev->config->del_vqs(vdev);
@@ -807,11 +791,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
/* Ensure we don't receive any more interrupts */
vdev->config->reset(vdev);
- /* Prevent config work handler from accessing the device. */
- mutex_lock(&vblk->config_lock);
- vblk->config_enable = false;
- mutex_unlock(&vblk->config_lock);
-
+ /* Make sure no work handler is accessing the device. */
flush_work(&vblk->config_work);
blk_mq_stop_hw_queues(vblk->disk->queue);
@@ -825,12 +805,14 @@ static int virtblk_restore(struct virtio_device *vdev)
struct virtio_blk *vblk = vdev->priv;
int ret;
- vblk->config_enable = true;
ret = init_vq(vdev->priv);
- if (!ret)
- blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+ if (ret)
+ return ret;
- return ret;
+ virtio_device_ready(vdev);
+
+ blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+ return 0;
}
#endif
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3a8b810..0b13b1c 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -907,22 +907,17 @@ static int connect_ring(struct backend_info *be)
return 0;
}
-
-/* ** Driver Registration ** */
-
-
static const struct xenbus_device_id xen_blkbk_ids[] = {
{ "vbd" },
{ "" }
};
-
-static DEFINE_XENBUS_DRIVER(xen_blkbk, ,
+static struct xenbus_driver xen_blkbk_driver = {
+ .ids = xen_blkbk_ids,
.probe = xen_blkbk_probe,
.remove = xen_blkbk_remove,
.otherend_changed = frontend_changed
-);
-
+};
int xen_blkif_xenbus_init(void)
{
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 5deb235..37af03e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2055,13 +2055,14 @@ static const struct xenbus_device_id blkfront_ids[] = {
{ "" }
};
-static DEFINE_XENBUS_DRIVER(blkfront, ,
+static struct xenbus_driver blkfront_driver = {
+ .ids = blkfront_ids,
.probe = blkfront_probe,
.remove = blkfront_remove,
.resume = blkfront_resume,
.otherend_changed = blkback_changed,
.is_ready = blkfront_is_ready,
-);
+};
static int __init xlblk_init(void)
{
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d00831c..3b85016 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -103,10 +103,10 @@ static ssize_t mem_used_total_show(struct device *dev,
down_read(&zram->init_lock);
if (init_done(zram))
- val = zs_get_total_size_bytes(meta->mem_pool);
+ val = zs_get_total_pages(meta->mem_pool);
up_read(&zram->init_lock);
- return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
}
static ssize_t max_comp_streams_show(struct device *dev,
@@ -122,6 +122,72 @@ static ssize_t max_comp_streams_show(struct device *dev,
return scnprintf(buf, PAGE_SIZE, "%d\n", val);
}
+static ssize_t mem_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = zram->limit_pages;
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_limit_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 limit;
+ char *tmp;
+ struct zram *zram = dev_to_zram(dev);
+
+ limit = memparse(buf, &tmp);
+ if (buf == tmp) /* no chars parsed, invalid input */
+ return -EINVAL;
+
+ down_write(&zram->init_lock);
+ zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+ up_write(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t mem_used_max_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ if (init_done(zram))
+ val = atomic_long_read(&zram->stats.max_used_pages);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int err;
+ unsigned long val;
+ struct zram *zram = dev_to_zram(dev);
+ struct zram_meta *meta = zram->meta;
+
+ err = kstrtoul(buf, 10, &val);
+ if (err || val != 0)
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (init_done(zram))
+ atomic_long_set(&zram->stats.max_used_pages,
+ zs_get_total_pages(meta->mem_pool));
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
static ssize_t max_comp_streams_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
@@ -434,6 +500,21 @@ out_cleanup:
return ret;
}
+static inline void update_used_max(struct zram *zram,
+ const unsigned long pages)
+{
+ int old_max, cur_max;
+
+ old_max = atomic_long_read(&zram->stats.max_used_pages);
+
+ do {
+ cur_max = old_max;
+ if (pages > cur_max)
+ old_max = atomic_long_cmpxchg(
+ &zram->stats.max_used_pages, cur_max, pages);
+ } while (old_max != cur_max);
+}
+
static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
int offset)
{
@@ -445,6 +526,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
struct zram_meta *meta = zram->meta;
struct zcomp_strm *zstrm;
bool locked = false;
+ unsigned long alloced_pages;
page = bvec->bv_page;
if (is_partial_io(bvec)) {
@@ -513,6 +595,16 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
ret = -ENOMEM;
goto out;
}
+
+ alloced_pages = zs_get_total_pages(meta->mem_pool);
+ if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+ zs_free(meta->mem_pool, handle);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ update_used_max(zram, alloced_pages);
+
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
@@ -606,6 +698,7 @@ static void zram_bio_discard(struct zram *zram, u32 index,
bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
zram_free_page(zram, index);
bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ atomic64_inc(&zram->stats.notify_free);
index++;
n -= PAGE_SIZE;
}
@@ -617,6 +710,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
struct zram_meta *meta;
down_write(&zram->init_lock);
+
+ zram->limit_pages = 0;
+
if (!init_done(zram)) {
up_write(&zram->init_lock);
return;
@@ -857,6 +953,10 @@ static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
+ mem_limit_store);
+static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
+ mem_used_max_store);
static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
max_comp_streams_show, max_comp_streams_store);
static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
@@ -885,6 +985,8 @@ static struct attribute *zram_disk_attrs[] = {
&dev_attr_orig_data_size.attr,
&dev_attr_compr_data_size.attr,
&dev_attr_mem_used_total.attr,
+ &dev_attr_mem_limit.attr,
+ &dev_attr_mem_used_max.attr,
&dev_attr_max_comp_streams.attr,
&dev_attr_comp_algorithm.attr,
NULL,
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index e0f725c..c6ee271 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -90,6 +90,7 @@ struct zram_stats {
atomic64_t notify_free; /* no. of swap slot free notifications */
atomic64_t zero_pages; /* no. of zero filled pages */
atomic64_t pages_stored; /* no. of pages currently stored */
+ atomic_long_t max_used_pages; /* no. of maximum pages stored */
};
struct zram_meta {
@@ -112,6 +113,11 @@ struct zram {
u64 disksize; /* bytes */
int max_comp_streams;
struct zram_stats stats;
+ /*
+ * the number of pages zram can consume for storing compressed data
+ */
+ unsigned long limit_pages;
+
char compressor[10];
};
#endif
OpenPOWER on IntegriCloud