#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/bitmap.h>
-#include <linux/llist.h>
+#include <linux/list.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
struct grant {
grant_ref_t gref;
unsigned long pfn;
- struct llist_node node;
+ struct list_head node;
};
struct blk_shadow {
struct blkif_request req;
struct request *request;
- unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
- struct grant *grants_used[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ struct grant **grants_used;
+ struct grant **indirect_grants;
+ struct scatterlist *sg;
+};
+
+struct split_bio {
+ struct bio *bio;
+ atomic_t pending;
+ int err;
};
static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;
+/*
+ * Maximum number of segments in indirect requests, the actual value used by
+ * the frontend driver is the minimum of this value and the value provided
+ * by the backend driver.
+ */
+
+static unsigned int xen_blkif_max_segments = 32;
+module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
+MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests (default is 32)");
+
#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)
/*
enum blkif_state connected;
int ring_ref;
struct blkif_front_ring ring;
- struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
unsigned int evtchn, irq;
struct request_queue *rq;
struct work_struct work;
struct gnttab_free_callback callback;
struct blk_shadow shadow[BLK_RING_SIZE];
- struct llist_head persistent_gnts;
+ struct list_head persistent_gnts;
unsigned int persistent_gnts_c;
unsigned long shadow_free;
unsigned int feature_flush;
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned int feature_persistent:1;
+ unsigned int max_indirect_segments;
int is_ready;
};
#define DEV_NAME "xvd" /* name in /dev */
+#define SEGS_PER_INDIRECT_FRAME \
+ (PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+#define INDIRECT_GREFS(_segs) \
+ ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+
+static int blkfront_setup_indirect(struct blkfront_info *info);
+
static int get_id_from_freelist(struct blkfront_info *info)
{
unsigned long free = info->shadow_free;
return 0;
}
+static int fill_grant_buffer(struct blkfront_info *info, int num)
+{
+ struct page *granted_page;
+ struct grant *gnt_list_entry, *n;
+ int i = 0;
+
+ while(i < num) {
+ gnt_list_entry = kzalloc(sizeof(struct grant), GFP_NOIO);
+ if (!gnt_list_entry)
+ goto out_of_memory;
+
+ granted_page = alloc_page(GFP_NOIO);
+ if (!granted_page) {
+ kfree(gnt_list_entry);
+ goto out_of_memory;
+ }
+
+ gnt_list_entry->pfn = page_to_pfn(granted_page);
+ gnt_list_entry->gref = GRANT_INVALID_REF;
+ list_add(&gnt_list_entry->node, &info->persistent_gnts);
+ i++;
+ }
+
+ return 0;
+
+out_of_memory:
+ list_for_each_entry_safe(gnt_list_entry, n,
+ &info->persistent_gnts, node) {
+ list_del(&gnt_list_entry->node);
+ __free_page(pfn_to_page(gnt_list_entry->pfn));
+ kfree(gnt_list_entry);
+ i--;
+ }
+ BUG_ON(i != 0);
+ return -ENOMEM;
+}
+
+static struct grant *get_grant(grant_ref_t *gref_head,
+ struct blkfront_info *info)
+{
+ struct grant *gnt_list_entry;
+ unsigned long buffer_mfn;
+
+ BUG_ON(list_empty(&info->persistent_gnts));
+ gnt_list_entry = list_first_entry(&info->persistent_gnts, struct grant,
+ node);
+ list_del(&gnt_list_entry->node);
+
+ if (gnt_list_entry->gref != GRANT_INVALID_REF) {
+ info->persistent_gnts_c--;
+ return gnt_list_entry;
+ }
+
+ /* Assign a gref to this page */
+ gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
+ BUG_ON(gnt_list_entry->gref == -ENOSPC);
+ buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
+ gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
+ info->xbdev->otherend_id,
+ buffer_mfn, 0);
+ return gnt_list_entry;
+}
+
static const char *op_name(int op)
{
static const char *const names[] = {
static int blkif_queue_request(struct request *req)
{
struct blkfront_info *info = req->rq_disk->private_data;
- unsigned long buffer_mfn;
struct blkif_request *ring_req;
unsigned long id;
unsigned int fsect, lsect;
- int i, ref;
+ int i, ref, n;
+ struct blkif_request_segment_aligned *segments = NULL;
/*
* Used to store if we are able to queue the request by just using
*/
bool new_persistent_gnts;
grant_ref_t gref_head;
- struct page *granted_page;
struct grant *gnt_list_entry = NULL;
struct scatterlist *sg;
+ int nseg, max_grefs;
if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
return 1;
- /* Check if we have enought grants to allocate a requests */
- if (info->persistent_gnts_c < BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+ max_grefs = info->max_indirect_segments ?
+ info->max_indirect_segments +
+ INDIRECT_GREFS(info->max_indirect_segments) :
+ BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+ /* Check if we have enough grants to allocate a requests */
+ if (info->persistent_gnts_c < max_grefs) {
new_persistent_gnts = 1;
if (gnttab_alloc_grant_references(
- BLKIF_MAX_SEGMENTS_PER_REQUEST - info->persistent_gnts_c,
+ max_grefs - info->persistent_gnts_c,
&gref_head) < 0) {
gnttab_request_free_callback(
&info->callback,
blkif_restart_queue_callback,
info,
- BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ max_grefs);
return 1;
}
} else
id = get_id_from_freelist(info);
info->shadow[id].request = req;
- ring_req->u.rw.id = id;
- ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
- ring_req->u.rw.handle = info->handle;
-
- ring_req->operation = rq_data_dir(req) ?
- BLKIF_OP_WRITE : BLKIF_OP_READ;
-
- if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
- /*
- * Ideally we can do an unordered flush-to-disk. In case the
- * backend onlysupports barriers, use that. A barrier request
- * a superset of FUA, so we can implement it the same
- * way. (It's also a FLUSH+FUA, since it is
- * guaranteed ordered WRT previous writes.)
- */
- ring_req->operation = info->flush_op;
- }
-
if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
- /* id, sector_number and handle are set above. */
ring_req->operation = BLKIF_OP_DISCARD;
ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+ ring_req->u.discard.id = id;
+ ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
else
ring_req->u.discard.flag = 0;
} else {
- ring_req->u.rw.nr_segments = blk_rq_map_sg(req->q, req,
- info->sg);
- BUG_ON(ring_req->u.rw.nr_segments >
- BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
- for_each_sg(info->sg, sg, ring_req->u.rw.nr_segments, i) {
+ BUG_ON(info->max_indirect_segments == 0 &&
+ req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ BUG_ON(info->max_indirect_segments &&
+ req->nr_phys_segments > info->max_indirect_segments);
+ nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
+ ring_req->u.rw.id = id;
+ if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+ /*
+ * The indirect operation can only be a BLKIF_OP_READ or
+ * BLKIF_OP_WRITE
+ */
+ BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+ ring_req->operation = BLKIF_OP_INDIRECT;
+ ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
+ BLKIF_OP_WRITE : BLKIF_OP_READ;
+ ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.indirect.handle = info->handle;
+ ring_req->u.indirect.nr_segments = nseg;
+ } else {
+ ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.rw.handle = info->handle;
+ ring_req->operation = rq_data_dir(req) ?
+ BLKIF_OP_WRITE : BLKIF_OP_READ;
+ if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+ /*
+ * Ideally we can do an unordered flush-to-disk. In case the
+ * backend onlysupports barriers, use that. A barrier request
+ * a superset of FUA, so we can implement it the same
+ * way. (It's also a FLUSH+FUA, since it is
+ * guaranteed ordered WRT previous writes.)
+ */
+ ring_req->operation = info->flush_op;
+ }
+ ring_req->u.rw.nr_segments = nseg;
+ }
+ for_each_sg(info->shadow[id].sg, sg, nseg, i) {
fsect = sg->offset >> 9;
lsect = fsect + (sg->length >> 9) - 1;
- if (info->persistent_gnts_c) {
- BUG_ON(llist_empty(&info->persistent_gnts));
- gnt_list_entry = llist_entry(
- llist_del_first(&info->persistent_gnts),
- struct grant, node);
+ if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
+ (i % SEGS_PER_INDIRECT_FRAME == 0)) {
+ if (segments)
+ kunmap_atomic(segments);
- ref = gnt_list_entry->gref;
- buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
- info->persistent_gnts_c--;
- } else {
- ref = gnttab_claim_grant_reference(&gref_head);
- BUG_ON(ref == -ENOSPC);
-
- gnt_list_entry =
- kmalloc(sizeof(struct grant),
- GFP_ATOMIC);
- if (!gnt_list_entry)
- return -ENOMEM;
-
- granted_page = alloc_page(GFP_ATOMIC);
- if (!granted_page) {
- kfree(gnt_list_entry);
- return -ENOMEM;
- }
-
- gnt_list_entry->pfn =
- page_to_pfn(granted_page);
- gnt_list_entry->gref = ref;
-
- buffer_mfn = pfn_to_mfn(page_to_pfn(
- granted_page));
- gnttab_grant_foreign_access_ref(ref,
- info->xbdev->otherend_id,
- buffer_mfn, 0);
+ n = i / SEGS_PER_INDIRECT_FRAME;
+ gnt_list_entry = get_grant(&gref_head, info);
+ info->shadow[id].indirect_grants[n] = gnt_list_entry;
+ segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
+ ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
}
+ gnt_list_entry = get_grant(&gref_head, info);
+ ref = gnt_list_entry->gref;
+
info->shadow[id].grants_used[i] = gnt_list_entry;
if (rq_data_dir(req)) {
BUG_ON(sg->offset + sg->length > PAGE_SIZE);
- shared_data = kmap_atomic(
- pfn_to_page(gnt_list_entry->pfn));
+ shared_data = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
bvec_data = kmap_atomic(sg_page(sg));
/*
kunmap_atomic(bvec_data);
kunmap_atomic(shared_data);
}
-
- info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
- ring_req->u.rw.seg[i] =
- (struct blkif_request_segment) {
- .gref = ref,
- .first_sect = fsect,
- .last_sect = lsect };
+ if (ring_req->operation != BLKIF_OP_INDIRECT) {
+ ring_req->u.rw.seg[i] =
+ (struct blkif_request_segment) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ } else {
+ n = i % SEGS_PER_INDIRECT_FRAME;
+ segments[n] =
+ (struct blkif_request_segment_aligned) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ }
}
+ if (segments)
+ kunmap_atomic(segments);
}
info->ring.req_prod_pvt++;
flush_requests(info);
}
-static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
+static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
+ unsigned int segments)
{
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ blk_queue_max_segments(rq, segments);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
static void xlvbd_flush(struct blkfront_info *info)
{
blk_queue_flush(info->rq, info->feature_flush);
- printk(KERN_INFO "blkfront: %s: %s: %s %s\n",
+ printk(KERN_INFO "blkfront: %s: %s: %s %s %s %s %s\n",
info->gd->disk_name,
info->flush_op == BLKIF_OP_WRITE_BARRIER ?
"barrier" : (info->flush_op == BLKIF_OP_FLUSH_DISKCACHE ?
"flush diskcache" : "barrier or flush"),
- info->feature_flush ? "enabled" : "disabled",
- info->feature_persistent ? "using persistent grants" : "");
+ info->feature_flush ? "enabled;" : "disabled;",
+ "persistent grants:",
+ info->feature_persistent ? "enabled;" : "disabled;",
+ "indirect descriptors:",
+ info->max_indirect_segments ? "enabled;" : "disabled;");
}
static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
gd->driverfs_dev = &(info->xbdev->dev);
set_capacity(gd, capacity);
- if (xlvbd_init_blk_queue(gd, sector_size)) {
+ if (xlvbd_init_blk_queue(gd, sector_size,
+ info->max_indirect_segments ? :
+ BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
del_gendisk(gd);
goto release;
}
static void blkif_free(struct blkfront_info *info, int suspend)
{
- struct llist_node *all_gnts;
- struct grant *persistent_gnt, *tmp;
- struct llist_node *n;
+ struct grant *persistent_gnt;
+ struct grant *n;
+ int i, j, segs;
/* Prevent new requests being issued until we fix things up. */
spin_lock_irq(&info->io_lock);
blk_stop_queue(info->rq);
/* Remove all persistent grants */
- if (info->persistent_gnts_c) {
- all_gnts = llist_del_all(&info->persistent_gnts);
- persistent_gnt = llist_entry(all_gnts, typeof(*(persistent_gnt)), node);
- while (persistent_gnt) {
+ if (!list_empty(&info->persistent_gnts)) {
+ list_for_each_entry_safe(persistent_gnt, n,
+ &info->persistent_gnts, node) {
+ list_del(&persistent_gnt->node);
+ if (persistent_gnt->gref != GRANT_INVALID_REF) {
+ gnttab_end_foreign_access(persistent_gnt->gref,
+ 0, 0UL);
+ info->persistent_gnts_c--;
+ }
+ __free_page(pfn_to_page(persistent_gnt->pfn));
+ kfree(persistent_gnt);
+ }
+ }
+ BUG_ON(info->persistent_gnts_c != 0);
+
+ for (i = 0; i < BLK_RING_SIZE; i++) {
+ /*
+ * Clear persistent grants present in requests already
+ * on the shared ring
+ */
+ if (!info->shadow[i].request)
+ goto free_shadow;
+
+ segs = info->shadow[i].req.operation == BLKIF_OP_INDIRECT ?
+ info->shadow[i].req.u.indirect.nr_segments :
+ info->shadow[i].req.u.rw.nr_segments;
+ for (j = 0; j < segs; j++) {
+ persistent_gnt = info->shadow[i].grants_used[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
__free_page(pfn_to_page(persistent_gnt->pfn));
- tmp = persistent_gnt;
- n = persistent_gnt->node.next;
- if (n)
- persistent_gnt = llist_entry(n, typeof(*(persistent_gnt)), node);
- else
- persistent_gnt = NULL;
- kfree(tmp);
+ kfree(persistent_gnt);
+ }
+
+ if (info->shadow[i].req.operation != BLKIF_OP_INDIRECT)
+ /*
+ * If this is not an indirect operation don't try to
+ * free indirect segments
+ */
+ goto free_shadow;
+
+ for (j = 0; j < INDIRECT_GREFS(segs); j++) {
+ persistent_gnt = info->shadow[i].indirect_grants[j];
+ gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+ __free_page(pfn_to_page(persistent_gnt->pfn));
+ kfree(persistent_gnt);
}
- info->persistent_gnts_c = 0;
+
+free_shadow:
+ kfree(info->shadow[i].grants_used);
+ info->shadow[i].grants_used = NULL;
+ kfree(info->shadow[i].indirect_grants);
+ info->shadow[i].indirect_grants = NULL;
+ kfree(info->shadow[i].sg);
+ info->shadow[i].sg = NULL;
}
/* No more gnttab callback work. */
struct blkif_response *bret)
{
int i = 0;
- struct bio_vec *bvec;
- struct req_iterator iter;
- unsigned long flags;
+ struct scatterlist *sg;
char *bvec_data;
void *shared_data;
- unsigned int offset = 0;
+ int nseg;
+
+ nseg = s->req.operation == BLKIF_OP_INDIRECT ?
+ s->req.u.indirect.nr_segments : s->req.u.rw.nr_segments;
if (bret->operation == BLKIF_OP_READ) {
/*
* than PAGE_SIZE, we have to keep track of the current offset,
* to be sure we are copying the data from the right shared page.
*/
- rq_for_each_segment(bvec, s->request, iter) {
- BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
- if (bvec->bv_offset < offset)
- i++;
- BUG_ON(i >= s->req.u.rw.nr_segments);
+ for_each_sg(s->sg, sg, nseg, i) {
+ BUG_ON(sg->offset + sg->length > PAGE_SIZE);
shared_data = kmap_atomic(
pfn_to_page(s->grants_used[i]->pfn));
- bvec_data = bvec_kmap_irq(bvec, &flags);
- memcpy(bvec_data, shared_data + bvec->bv_offset,
- bvec->bv_len);
- bvec_kunmap_irq(bvec_data, &flags);
+ bvec_data = kmap_atomic(sg_page(sg));
+ memcpy(bvec_data + sg->offset,
+ shared_data + sg->offset,
+ sg->length);
+ kunmap_atomic(bvec_data);
kunmap_atomic(shared_data);
- offset = bvec->bv_offset + bvec->bv_len;
}
}
/* Add the persistent grant into the list of free grants */
- for (i = 0; i < s->req.u.rw.nr_segments; i++) {
- llist_add(&s->grants_used[i]->node, &info->persistent_gnts);
+ for (i = 0; i < nseg; i++) {
+ list_add(&s->grants_used[i]->node, &info->persistent_gnts);
info->persistent_gnts_c++;
}
+ if (s->req.operation == BLKIF_OP_INDIRECT) {
+ for (i = 0; i < INDIRECT_GREFS(nseg); i++) {
+ list_add(&s->indirect_grants[i]->node, &info->persistent_gnts);
+ info->persistent_gnts_c++;
+ }
+ }
}
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
SHARED_RING_INIT(sring);
FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
- sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
if (err < 0) {
free_page((unsigned long)sring);
spin_lock_init(&info->io_lock);
info->xbdev = dev;
info->vdevice = vdevice;
- init_llist_head(&info->persistent_gnts);
+ INIT_LIST_HEAD(&info->persistent_gnts);
info->persistent_gnts_c = 0;
info->connected = BLKIF_STATE_DISCONNECTED;
INIT_WORK(&info->work, blkif_restart_queue);
return 0;
}
+/*
+ * This is a clone of md_trim_bio, used to split a bio into smaller ones
+ */
+static void trim_bio(struct bio *bio, int offset, int size)
+{
+ /* 'bio' is a cloned bio which we need to trim to match
+ * the given offset and size.
+ * This requires adjusting bi_sector, bi_size, and bi_io_vec
+ */
+ int i;
+ struct bio_vec *bvec;
+ int sofar = 0;
+
+ size <<= 9;
+ if (offset == 0 && size == bio->bi_size)
+ return;
+
+ bio->bi_sector += offset;
+ bio->bi_size = size;
+ offset <<= 9;
+ clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+
+ while (bio->bi_idx < bio->bi_vcnt &&
+ bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
+ /* remove this whole bio_vec */
+ offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
+ bio->bi_idx++;
+ }
+ if (bio->bi_idx < bio->bi_vcnt) {
+ bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
+ bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
+ }
+ /* avoid any complications with bi_idx being non-zero*/
+ if (bio->bi_idx) {
+ memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
+ (bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
+ bio->bi_vcnt -= bio->bi_idx;
+ bio->bi_idx = 0;
+ }
+ /* Make sure vcnt and last bv are not too big */
+ bio_for_each_segment(bvec, bio, i) {
+ if (sofar + bvec->bv_len > size)
+ bvec->bv_len = size - sofar;
+ if (bvec->bv_len == 0) {
+ bio->bi_vcnt = i;
+ break;
+ }
+ sofar += bvec->bv_len;
+ }
+}
+
+static void split_bio_end(struct bio *bio, int error)
+{
+ struct split_bio *split_bio = bio->bi_private;
+
+ if (error)
+ split_bio->err = error;
+
+ if (atomic_dec_and_test(&split_bio->pending)) {
+ split_bio->bio->bi_phys_segments = 0;
+ bio_endio(split_bio->bio, split_bio->err);
+ kfree(split_bio);
+ }
+ bio_put(bio);
+}
static int blkif_recover(struct blkfront_info *info)
{
int i;
- struct blkif_request *req;
+ struct request *req, *n;
struct blk_shadow *copy;
- int j;
+ int rc;
+ struct bio *bio, *cloned_bio;
+ struct bio_list bio_list, merge_bio;
+ unsigned int segs, offset;
+ int pending, size;
+ struct split_bio *split_bio;
+ struct list_head requests;
/* Stage 1: Make a safe copy of the shadow state. */
- copy = kmalloc(sizeof(info->shadow),
+ copy = kmemdup(info->shadow, sizeof(info->shadow),
GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
if (!copy)
return -ENOMEM;
- memcpy(copy, info->shadow, sizeof(info->shadow));
/* Stage 2: Set up free list. */
memset(&info->shadow, 0, sizeof(info->shadow));
info->shadow_free = info->ring.req_prod_pvt;
info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
- /* Stage 3: Find pending requests and requeue them. */
+ rc = blkfront_setup_indirect(info);
+ if (rc) {
+ kfree(copy);
+ return rc;
+ }
+
+ segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
+ blk_queue_max_segments(info->rq, segs);
+ bio_list_init(&bio_list);
+ INIT_LIST_HEAD(&requests);
for (i = 0; i < BLK_RING_SIZE; i++) {
/* Not in use? */
if (!copy[i].request)
continue;
- /* Grab a request slot and copy shadow state into it. */
- req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
- *req = copy[i].req;
-
- /* We get a new request id, and must reset the shadow state. */
- req->u.rw.id = get_id_from_freelist(info);
- memcpy(&info->shadow[req->u.rw.id], ©[i], sizeof(copy[i]));
-
- if (req->operation != BLKIF_OP_DISCARD) {
- /* Rewrite any grant references invalidated by susp/resume. */
- for (j = 0; j < req->u.rw.nr_segments; j++)
- gnttab_grant_foreign_access_ref(
- req->u.rw.seg[j].gref,
- info->xbdev->otherend_id,
- pfn_to_mfn(info->shadow[req->u.rw.id].frame[j]),
- 0);
+ /*
+ * Get the bios in the request so we can re-queue them.
+ */
+ if (copy[i].request->cmd_flags &
+ (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+ /*
+ * Flush operations don't contain bios, so
+ * we need to requeue the whole request
+ */
+ list_add(©[i].request->queuelist, &requests);
+ continue;
}
- info->shadow[req->u.rw.id].req = *req;
-
- info->ring.req_prod_pvt++;
+ merge_bio.head = copy[i].request->bio;
+ merge_bio.tail = copy[i].request->biotail;
+ bio_list_merge(&bio_list, &merge_bio);
+ copy[i].request->bio = NULL;
+ blk_put_request(copy[i].request);
}
kfree(copy);
+ /*
+ * Empty the queue, this is important because we might have
+ * requests in the queue with more segments than what we
+ * can handle now.
+ */
+ spin_lock_irq(&info->io_lock);
+ while ((req = blk_fetch_request(info->rq)) != NULL) {
+ if (req->cmd_flags &
+ (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+ list_add(&req->queuelist, &requests);
+ continue;
+ }
+ merge_bio.head = req->bio;
+ merge_bio.tail = req->biotail;
+ bio_list_merge(&bio_list, &merge_bio);
+ req->bio = NULL;
+ if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
+ pr_alert("diskcache flush request found!\n");
+ __blk_put_request(info->rq, req);
+ }
+ spin_unlock_irq(&info->io_lock);
+
xenbus_switch_state(info->xbdev, XenbusStateConnected);
spin_lock_irq(&info->io_lock);
/* Now safe for us to use the shared ring */
info->connected = BLKIF_STATE_CONNECTED;
- /* Send off requeued requests */
- flush_requests(info);
-
/* Kick any other new requests queued since we resumed */
kick_pending_request_queues(info);
+ list_for_each_entry_safe(req, n, &requests, queuelist) {
+ /* Requeue pending requests (flush or discard) */
+ list_del_init(&req->queuelist);
+ BUG_ON(req->nr_phys_segments > segs);
+ blk_requeue_request(info->rq, req);
+ }
spin_unlock_irq(&info->io_lock);
+ while ((bio = bio_list_pop(&bio_list)) != NULL) {
+ /* Traverse the list of pending bios and re-queue them */
+ if (bio_segments(bio) > segs) {
+ /*
+ * This bio has more segments than what we can
+ * handle, we have to split it.
+ */
+ pending = (bio_segments(bio) + segs - 1) / segs;
+ split_bio = kzalloc(sizeof(*split_bio), GFP_NOIO);
+ BUG_ON(split_bio == NULL);
+ atomic_set(&split_bio->pending, pending);
+ split_bio->bio = bio;
+ for (i = 0; i < pending; i++) {
+ offset = (i * segs * PAGE_SIZE) >> 9;
+ size = min((unsigned int)(segs * PAGE_SIZE) >> 9,
+ (unsigned int)(bio->bi_size >> 9) - offset);
+ cloned_bio = bio_clone(bio, GFP_NOIO);
+ BUG_ON(cloned_bio == NULL);
+ trim_bio(cloned_bio, offset, size);
+ cloned_bio->bi_private = split_bio;
+ cloned_bio->bi_end_io = split_bio_end;
+ submit_bio(cloned_bio->bi_rw, cloned_bio);
+ }
+ /*
+ * Now we have to wait for all those smaller bios to
+ * end, so we can also end the "parent" bio.
+ */
+ continue;
+ }
+ /* We don't need to split this bio */
+ submit_bio(bio->bi_rw, bio);
+ }
+
return 0;
}
blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
err = talk_to_blkback(dev, info);
- if (info->connected == BLKIF_STATE_SUSPENDED && !err)
- err = blkif_recover(info);
+
+ /*
+ * We have to wait for the backend to switch to
+ * connected state, since we want to read which
+ * features it supports.
+ */
return err;
}
kfree(type);
}
+static int blkfront_setup_indirect(struct blkfront_info *info)
+{
+ unsigned int indirect_segments, segs;
+ int err, i;
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-max-indirect-segments", "%u", &indirect_segments,
+ NULL);
+ if (err) {
+ info->max_indirect_segments = 0;
+ segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+ } else {
+ info->max_indirect_segments = min(indirect_segments,
+ xen_blkif_max_segments);
+ segs = info->max_indirect_segments;
+ }
+
+ err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
+ if (err)
+ goto out_of_memory;
+
+ for (i = 0; i < BLK_RING_SIZE; i++) {
+ info->shadow[i].grants_used = kzalloc(
+ sizeof(info->shadow[i].grants_used[0]) * segs,
+ GFP_NOIO);
+ info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
+ if (info->max_indirect_segments)
+ info->shadow[i].indirect_grants = kzalloc(
+ sizeof(info->shadow[i].indirect_grants[0]) *
+ INDIRECT_GREFS(segs),
+ GFP_NOIO);
+ if ((info->shadow[i].grants_used == NULL) ||
+ (info->shadow[i].sg == NULL) ||
+ (info->max_indirect_segments &&
+ (info->shadow[i].indirect_grants == NULL)))
+ goto out_of_memory;
+ sg_init_table(info->shadow[i].sg, segs);
+ }
+
+
+ return 0;
+
+out_of_memory:
+ for (i = 0; i < BLK_RING_SIZE; i++) {
+ kfree(info->shadow[i].grants_used);
+ info->shadow[i].grants_used = NULL;
+ kfree(info->shadow[i].sg);
+ info->shadow[i].sg = NULL;
+ kfree(info->shadow[i].indirect_grants);
+ info->shadow[i].indirect_grants = NULL;
+ }
+ return -ENOMEM;
+}
+
/*
* Invoked when the backend is finally 'ready' (and has told produced
* the details about the physical device - #sectors, size, etc).
set_capacity(info->gd, sectors);
revalidate_disk(info->gd);
- /* fall through */
+ return;
case BLKIF_STATE_SUSPENDED:
+ /*
+ * If we are recovering from suspension, we need to wait
+ * for the backend to announce it's features before
+ * reconnecting, at least we need to know if the backend
+ * supports indirect descriptors, and how many.
+ */
+ blkif_recover(info);
return;
default:
else
info->feature_persistent = persistent;
+ err = blkfront_setup_indirect(info);
+ if (err) {
+ xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
+ info->xbdev->otherend);
+ return;
+ }
+
err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
if (err) {
xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",