Merge branch 'stable/for-jens-3.9' of...

Merge branch 'stable/for-jens-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen into for-linus

Konrad writes:

[the branch] has a bunch of fixes. They vary from being able to deal
with unknown requests, overflow in statistics, compile warnings, bug in
the error path, removal of unnecessary logic. There is also one
performance fix - which is to allocate pages for requests when the
driver loads - instead of doing it per request

drivers/block/xen-blkback/blkback.c

@@ -164,7 +164,7 @@ static void make_response(struct xen_blkif *blkif, u64 id,
 
 #define foreach_grant_safe(pos, n, rbtree, node) \
 	for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node), \
-	     (n) = rb_next(&(pos)->node); \
+	     (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL; \
 	     &(pos)->node != NULL; \
 	     (pos) = container_of(n, typeof(*(pos)), node), \
 	     (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL)
@@ -381,8 +381,8 @@ irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
 
 static void print_stats(struct xen_blkif *blkif)
 {
-	pr_info("xen-blkback (%s): oo %3d  |  rd %4d  |  wr %4d  |  f %4d"
-		 "  |  ds %4d\n",
+	pr_info("xen-blkback (%s): oo %3llu  |  rd %4llu  |  wr %4llu  |  f %4llu"
+		 "  |  ds %4llu\n",
 		 current->comm, blkif->st_oo_req,
 		 blkif->st_rd_req, blkif->st_wr_req,
 		 blkif->st_f_req, blkif->st_ds_req);
@@ -442,7 +442,7 @@ int xen_blkif_schedule(void *arg)
 }
 
 struct seg_buf {
-	unsigned long buf;
+	unsigned int offset;
 	unsigned int nsec;
 };
 /*
@@ -621,30 +621,21 @@ static int xen_blkbk_map(struct blkif_request *req,
 				 * If this is a new persistent grant
 				 * save the handler
 				 */
-				persistent_gnts[i]->handle = map[j].handle;
-				persistent_gnts[i]->dev_bus_addr =
-					map[j++].dev_bus_addr;
+				persistent_gnts[i]->handle = map[j++].handle;
 			}
 			pending_handle(pending_req, i) =
 				persistent_gnts[i]->handle;
 
 			if (ret)
 				continue;
-
-			seg[i].buf = persistent_gnts[i]->dev_bus_addr |
-				(req->u.rw.seg[i].first_sect << 9);
 		} else {
-			pending_handle(pending_req, i) = map[j].handle;
+			pending_handle(pending_req, i) = map[j++].handle;
 			bitmap_set(pending_req->unmap_seg, i, 1);
 
-			if (ret) {
-				j++;
+			if (ret)
 				continue;
-			}
-
-			seg[i].buf = map[j++].dev_bus_addr |
-				(req->u.rw.seg[i].first_sect << 9);
 		}
+		seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
 	}
 	return ret;
 }
@@ -679,6 +670,16 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	return err;
 }
 
+static int dispatch_other_io(struct xen_blkif *blkif,
+			     struct blkif_request *req,
+			     struct pending_req *pending_req)
+{
+	free_req(pending_req);
+	make_response(blkif, req->u.other.id, req->operation,
+		      BLKIF_RSP_EOPNOTSUPP);
+	return -EIO;
+}
+
 static void xen_blk_drain_io(struct xen_blkif *blkif)
 {
 	atomic_set(&blkif->drain, 1);
@@ -800,17 +801,30 @@ __do_block_io_op(struct xen_blkif *blkif)
 
 		/* Apply all sanity checks to /private copy/ of request. */
 		barrier();
-		if (unlikely(req.operation == BLKIF_OP_DISCARD)) {
+
+		switch (req.operation) {
+		case BLKIF_OP_READ:
+		case BLKIF_OP_WRITE:
+		case BLKIF_OP_WRITE_BARRIER:
+		case BLKIF_OP_FLUSH_DISKCACHE:
+			if (dispatch_rw_block_io(blkif, &req, pending_req))
+				goto done;
+			break;
+		case BLKIF_OP_DISCARD:
 			free_req(pending_req);
 			if (dispatch_discard_io(blkif, &req))
-				break;
-		} else if (dispatch_rw_block_io(blkif, &req, pending_req))
+				goto done;
 			break;
+		default:
+			if (dispatch_other_io(blkif, &req, pending_req))
+				goto done;
+			break;
+		}
 
 		/* Yield point for this unbounded loop. */
 		cond_resched();
 	}
-
+done:
 	return more_to_do;
 }
 
@@ -904,7 +918,8 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 		pr_debug(DRV_PFX "access denied: %s of [%llu,%llu] on dev=%04x\n",
 			 operation == READ ? "read" : "write",
 			 preq.sector_number,
-			 preq.sector_number + preq.nr_sects, preq.dev);
+			 preq.sector_number + preq.nr_sects,
+			 blkif->vbd.pdevice);
 		goto fail_response;
 	}
 
@@ -947,7 +962,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 		       (bio_add_page(bio,
 				     pages[i],
 				     seg[i].nsec << 9,
-				     seg[i].buf & ~PAGE_MASK) == 0)) {
+				     seg[i].offset) == 0)) {
 
 			bio = bio_alloc(GFP_KERNEL, nseg-i);
 			if (unlikely(bio == NULL))
@@ -977,13 +992,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 		bio->bi_end_io  = end_block_io_op;
 	}
 
-	/*
-	 * We set it one so that the last submit_bio does not have to call
-	 * atomic_inc.
-	 */
 	atomic_set(&pending_req->pendcnt, nbio);
-
-	/* Get a reference count for the disk queue and start sending I/O */
 	blk_start_plug(&plug);
 
 	for (i = 0; i < nbio; i++)
@@ -1011,6 +1020,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
  fail_put_bio:
 	for (i = 0; i < nbio; i++)
 		bio_put(biolist[i]);
+	atomic_set(&pending_req->pendcnt, 1);
 	__end_block_io_op(pending_req, -EINVAL);
 	msleep(1); /* back off a bit */
 	return -EIO;

drivers/block/xen-blkback/common.h

@@ -77,11 +77,18 @@ struct blkif_x86_32_request_discard {
 	uint64_t       nr_sectors;
 } __attribute__((__packed__));
 
+struct blkif_x86_32_request_other {
+	uint8_t        _pad1;
+	blkif_vdev_t   _pad2;
+	uint64_t       id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_x86_32_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_32_request_rw rw;
 		struct blkif_x86_32_request_discard discard;
+		struct blkif_x86_32_request_other other;
 	} u;
 } __attribute__((__packed__));
 
@@ -113,11 +120,19 @@ struct blkif_x86_64_request_discard {
 	uint64_t       nr_sectors;
 } __attribute__((__packed__));
 
+struct blkif_x86_64_request_other {
+	uint8_t        _pad1;
+	blkif_vdev_t   _pad2;
+	uint32_t       _pad3;        /* offsetof(blkif_..,u.discard.id)==8   */
+	uint64_t       id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_x86_64_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_64_request_rw rw;
 		struct blkif_x86_64_request_discard discard;
+		struct blkif_x86_64_request_other other;
 	} u;
 } __attribute__((__packed__));
 
@@ -172,7 +187,6 @@ struct persistent_gnt {
 	struct page *page;
 	grant_ref_t gnt;
 	grant_handle_t handle;
-	uint64_t dev_bus_addr;
 	struct rb_node node;
 };
 
@@ -208,13 +222,13 @@ struct xen_blkif {
 
 	/* statistics */
 	unsigned long		st_print;
-	int			st_rd_req;
-	int			st_wr_req;
-	int			st_oo_req;
-	int			st_f_req;
-	int			st_ds_req;
-	int			st_rd_sect;
-	int			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;
 
 	wait_queue_head_t	waiting_to_free;
 };
@@ -278,6 +292,11 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
 	default:
+		/*
+		 * Don't know how to translate this op. Only get the
+		 * ID so failure can be reported to the frontend.
+		 */
+		dst->u.other.id = src->u.other.id;
 		break;
 	}
 }
@@ -309,6 +328,11 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
 	default:
+		/*
+		 * Don't know how to translate this op. Only get the
+		 * ID so failure can be reported to the frontend.
+		 */
+		dst->u.other.id = src->u.other.id;
 		break;
 	}
 }

drivers/block/xen-blkback/xenbus.c

@@ -230,13 +230,13 @@ int __init xen_blkif_interface_init(void)
 	}								\
 	static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
 
-VBD_SHOW(oo_req,  "%d\n", be->blkif->st_oo_req);
-VBD_SHOW(rd_req,  "%d\n", be->blkif->st_rd_req);
-VBD_SHOW(wr_req,  "%d\n", be->blkif->st_wr_req);
-VBD_SHOW(f_req,  "%d\n", be->blkif->st_f_req);
-VBD_SHOW(ds_req,  "%d\n", be->blkif->st_ds_req);
-VBD_SHOW(rd_sect, "%d\n", be->blkif->st_rd_sect);
-VBD_SHOW(wr_sect, "%d\n", be->blkif->st_wr_sect);
+VBD_SHOW(oo_req,  "%llu\n", be->blkif->st_oo_req);
+VBD_SHOW(rd_req,  "%llu\n", be->blkif->st_rd_req);
+VBD_SHOW(wr_req,  "%llu\n", be->blkif->st_wr_req);
+VBD_SHOW(f_req,  "%llu\n", be->blkif->st_f_req);
+VBD_SHOW(ds_req,  "%llu\n", be->blkif->st_ds_req);
+VBD_SHOW(rd_sect, "%llu\n", be->blkif->st_rd_sect);
+VBD_SHOW(wr_sect, "%llu\n", be->blkif->st_wr_sect);
 
 static struct attribute *xen_vbdstat_attrs[] = {
 	&dev_attr_oo_req.attr,

drivers/block/xen-blkfront.c

@@ -44,7 +44,7 @@
 #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>
@@ -68,13 +68,12 @@ enum blkif_state {
 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];
 };
 
@@ -105,7 +104,7 @@ struct blkfront_info
 	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;
@@ -165,6 +164,69 @@ static int add_id_to_freelist(struct blkfront_info *info,
 	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[] = {
@@ -293,7 +355,6 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
 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;
@@ -306,7 +367,6 @@ static int blkif_queue_request(struct request *req)
 	 */
 	bool new_persistent_gnts;
 	grant_ref_t gref_head;
-	struct page *granted_page;
 	struct grant *gnt_list_entry = NULL;
 	struct scatterlist *sg;
 
@@ -370,41 +430,8 @@ static int blkif_queue_request(struct request *req)
 			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);
-
-				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);
-			}
+			gnt_list_entry = get_grant(&gref_head, info);
+			ref = gnt_list_entry->gref;
 
 			info->shadow[id].grants_used[i] = gnt_list_entry;
 
@@ -435,7 +462,6 @@ static int blkif_queue_request(struct request *req)
 				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,
@@ -790,9 +816,8 @@ static void blkif_restart_queue(struct work_struct *work)
 
 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;
 
 	/* Prevent new requests being issued until we fix things up. */
 	spin_lock_irq(&info->io_lock);
@@ -803,22 +828,20 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 		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) {
-			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
+	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));
-			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);
 		}
-		info->persistent_gnts_c = 0;
 	}
+	BUG_ON(info->persistent_gnts_c != 0);
 
 	/* No more gnttab callback work. */
 	gnttab_cancel_free_callback(&info->callback);
@@ -875,7 +898,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 	}
 	/* 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);
+		list_add(&s->grants_used[i]->node, &info->persistent_gnts);
 		info->persistent_gnts_c++;
 	}
 }
@@ -1013,6 +1036,12 @@ static int setup_blkring(struct xenbus_device *dev,
 
 	sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
 
+	/* Allocate memory for grants */
+	err = fill_grant_buffer(info, BLK_RING_SIZE *
+	                              BLKIF_MAX_SEGMENTS_PER_REQUEST);
+	if (err)
+		goto fail;
+
 	err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
 	if (err < 0) {
 		free_page((unsigned long)sring);
@@ -1171,7 +1200,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 	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);
@@ -1203,11 +1232,10 @@ static int blkif_recover(struct blkfront_info *info)
 	int j;
 
 	/* 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));
@@ -1236,7 +1264,7 @@ static int blkif_recover(struct blkfront_info *info)
 				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]),
+					pfn_to_mfn(copy[i].grants_used[j]->pfn),
 					0);
 		}
 		info->shadow[req->u.rw.id].req = *req;

include/xen/interface/io/blkif.h

@@ -138,11 +138,21 @@ struct blkif_request_discard {
 	uint8_t        _pad3;
 } __attribute__((__packed__));
 
+struct blkif_request_other {
+	uint8_t      _pad1;
+	blkif_vdev_t _pad2;        /* only for read/write requests         */
+#ifdef CONFIG_X86_64
+	uint32_t     _pad3;        /* offsetof(blkif_req..,u.other.id)==8*/
+#endif
+	uint64_t     id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_request_rw rw;
 		struct blkif_request_discard discard;
+		struct blkif_request_other other;
 	} u;
 } __attribute__((__packed__));