Merge tag 'for-linus-6.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - some cleanups in the Xen blkback driver

 - fix potential sleeps under lock in various Xen drivers

* tag 'for-linus-6.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/blkback: move blkif_get_x86_*_req() into blkback.c
  xen/blkback: simplify free_persistent_gnts() interface
  xen/blkback: remove stale prototype
  xen/blkback: fix white space code style issues
  xen/pvcalls: don't call bind_evtchn_to_irqhandler() under lock
  xen/scsiback: don't call scsiback_free_translation_entry() under lock
  xen/pciback: don't call pcistub_device_put() under lock

drivers/block/xen-blkback/blkback.c

@@ -239,9 +239,9 @@ static void put_persistent_gnt(struct xen_blkif_ring *ring,
 	atomic_dec(&ring->persistent_gnt_in_use);
 }
 
-static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *root,
-                                 unsigned int num)
+static void free_persistent_gnts(struct xen_blkif_ring *ring)
 {
+	struct rb_root *root = &ring->persistent_gnts;
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
@@ -249,6 +249,9 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro
 	int segs_to_unmap = 0;
 	struct gntab_unmap_queue_data unmap_data;
 
+	if (RB_EMPTY_ROOT(root))
+		return;
+
 	unmap_data.pages = pages;
 	unmap_data.unmap_ops = unmap;
 	unmap_data.kunmap_ops = NULL;
@@ -277,9 +280,11 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro
 
 		rb_erase(&persistent_gnt->node, root);
 		kfree(persistent_gnt);
-		num--;
+		ring->persistent_gnt_c--;
 	}
-	BUG_ON(num != 0);
+
+	BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
+	BUG_ON(ring->persistent_gnt_c != 0);
 }
 
 void xen_blkbk_unmap_purged_grants(struct work_struct *work)
@@ -631,12 +636,7 @@ int xen_blkif_schedule(void *arg)
 void xen_blkbk_free_caches(struct xen_blkif_ring *ring)
 {
 	/* Free all persistent grant pages */
-	if (!RB_EMPTY_ROOT(&ring->persistent_gnts))
-		free_persistent_gnts(ring, &ring->persistent_gnts,
-			ring->persistent_gnt_c);
-
-	BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
-	ring->persistent_gnt_c = 0;
+	free_persistent_gnts(ring);
 
 	/* Since we are shutting down remove all pages from the buffer */
 	gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */);
@@ -891,7 +891,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 out:
 	for (i = last_map; i < num; i++) {
 		/* Don't zap current batch's valid persistent grants. */
-		if(i >= map_until)
+		if (i >= map_until)
 			pages[i]->persistent_gnt = NULL;
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 	}
@@ -1072,7 +1072,111 @@ static void end_block_io_op(struct bio *bio)
 	bio_put(bio);
 }
 
+static void blkif_get_x86_32_req(struct blkif_request *dst,
+				 const struct blkif_x86_32_request *src)
+{
+	unsigned int i, n;
+
+	dst->operation = READ_ONCE(src->operation);
+
+	switch (dst->operation) {
+	case BLKIF_OP_READ:
+	case BLKIF_OP_WRITE:
+	case BLKIF_OP_WRITE_BARRIER:
+	case BLKIF_OP_FLUSH_DISKCACHE:
+		dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments);
+		dst->u.rw.handle = src->u.rw.handle;
+		dst->u.rw.id = src->u.rw.id;
+		dst->u.rw.sector_number = src->u.rw.sector_number;
+		n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST,
+			  dst->u.rw.nr_segments);
+		for (i = 0; i < n; i++)
+			dst->u.rw.seg[i] = src->u.rw.seg[i];
+		break;
+
+	case BLKIF_OP_DISCARD:
+		dst->u.discard.flag = src->u.discard.flag;
+		dst->u.discard.id = src->u.discard.id;
+		dst->u.discard.sector_number = src->u.discard.sector_number;
+		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
+		break;
+
+	case BLKIF_OP_INDIRECT:
+		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
+		dst->u.indirect.nr_segments =
+			READ_ONCE(src->u.indirect.nr_segments);
+		dst->u.indirect.handle = src->u.indirect.handle;
+		dst->u.indirect.id = src->u.indirect.id;
+		dst->u.indirect.sector_number = src->u.indirect.sector_number;
+		n = min(MAX_INDIRECT_PAGES,
+			INDIRECT_PAGES(dst->u.indirect.nr_segments));
+		for (i = 0; i < n; i++)
+			dst->u.indirect.indirect_grefs[i] =
+				src->u.indirect.indirect_grefs[i];
+		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;
+	}
+}
+
+static void blkif_get_x86_64_req(struct blkif_request *dst,
+				 const struct blkif_x86_64_request *src)
+{
+	unsigned int i, n;
+
+	dst->operation = READ_ONCE(src->operation);
+
+	switch (dst->operation) {
+	case BLKIF_OP_READ:
+	case BLKIF_OP_WRITE:
+	case BLKIF_OP_WRITE_BARRIER:
+	case BLKIF_OP_FLUSH_DISKCACHE:
+		dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments);
+		dst->u.rw.handle = src->u.rw.handle;
+		dst->u.rw.id = src->u.rw.id;
+		dst->u.rw.sector_number = src->u.rw.sector_number;
+		n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST,
+			  dst->u.rw.nr_segments);
+		for (i = 0; i < n; i++)
+			dst->u.rw.seg[i] = src->u.rw.seg[i];
+		break;
+
+	case BLKIF_OP_DISCARD:
+		dst->u.discard.flag = src->u.discard.flag;
+		dst->u.discard.id = src->u.discard.id;
+		dst->u.discard.sector_number = src->u.discard.sector_number;
+		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
+		break;
+
+	case BLKIF_OP_INDIRECT:
+		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
+		dst->u.indirect.nr_segments =
+			READ_ONCE(src->u.indirect.nr_segments);
+		dst->u.indirect.handle = src->u.indirect.handle;
+		dst->u.indirect.id = src->u.indirect.id;
+		dst->u.indirect.sector_number = src->u.indirect.sector_number;
+		n = min(MAX_INDIRECT_PAGES,
+			INDIRECT_PAGES(dst->u.indirect.nr_segments));
+		for (i = 0; i < n; i++)
+			dst->u.indirect.indirect_grefs[i] =
+				src->u.indirect.indirect_grefs[i];
+		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;
+	}
+}
 
 /*
  * Function to copy the from the ring buffer the 'struct blkif_request'

drivers/block/xen-blkback/common.h

@@ -296,7 +296,7 @@ struct xen_blkif_ring {
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
 	wait_queue_head_t	shutdown_wq;
-	struct xen_blkif 	*blkif;
+	struct xen_blkif	*blkif;
 };
 
 struct xen_blkif {
@@ -315,7 +315,7 @@ struct xen_blkif {
 	atomic_t		drain;
 
 	struct work_struct	free_work;
-	unsigned int 		nr_ring_pages;
+	unsigned int		nr_ring_pages;
 	bool			multi_ref;
 	/* All rings for this device. */
 	struct xen_blkif_ring	*rings;
@@ -329,7 +329,7 @@ struct seg_buf {
 };
 
 struct grant_page {
-	struct page 		*page;
+	struct page		*page;
 	struct persistent_gnt	*persistent_gnt;
 	grant_handle_t		handle;
 	grant_ref_t		gref;
@@ -384,7 +384,6 @@ void xen_blkif_xenbus_fini(void);
 
 irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
 int xen_blkif_schedule(void *arg);
-int xen_blkif_purge_persistent(void *arg);
 void xen_blkbk_free_caches(struct xen_blkif_ring *ring);
 
 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
@@ -395,100 +394,4 @@ int xen_blkbk_barrier(struct xenbus_transaction xbt,
 struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
 void xen_blkbk_unmap_purged_grants(struct work_struct *work);
 
-static inline void blkif_get_x86_32_req(struct blkif_request *dst,
-					struct blkif_x86_32_request *src)
-{
-	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
-	dst->operation = READ_ONCE(src->operation);
-	switch (dst->operation) {
-	case BLKIF_OP_READ:
-	case BLKIF_OP_WRITE:
-	case BLKIF_OP_WRITE_BARRIER:
-	case BLKIF_OP_FLUSH_DISKCACHE:
-		dst->u.rw.nr_segments = src->u.rw.nr_segments;
-		dst->u.rw.handle = src->u.rw.handle;
-		dst->u.rw.id = src->u.rw.id;
-		dst->u.rw.sector_number = src->u.rw.sector_number;
-		barrier();
-		if (n > dst->u.rw.nr_segments)
-			n = dst->u.rw.nr_segments;
-		for (i = 0; i < n; i++)
-			dst->u.rw.seg[i] = src->u.rw.seg[i];
-		break;
-	case BLKIF_OP_DISCARD:
-		dst->u.discard.flag = src->u.discard.flag;
-		dst->u.discard.id = src->u.discard.id;
-		dst->u.discard.sector_number = src->u.discard.sector_number;
-		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
-		break;
-	case BLKIF_OP_INDIRECT:
-		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
-		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
-		dst->u.indirect.handle = src->u.indirect.handle;
-		dst->u.indirect.id = src->u.indirect.id;
-		dst->u.indirect.sector_number = src->u.indirect.sector_number;
-		barrier();
-		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
-		for (i = 0; i < j; i++)
-			dst->u.indirect.indirect_grefs[i] =
-				src->u.indirect.indirect_grefs[i];
-		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;
-	}
-}
-
-static inline void blkif_get_x86_64_req(struct blkif_request *dst,
-					struct blkif_x86_64_request *src)
-{
-	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
-	dst->operation = READ_ONCE(src->operation);
-	switch (dst->operation) {
-	case BLKIF_OP_READ:
-	case BLKIF_OP_WRITE:
-	case BLKIF_OP_WRITE_BARRIER:
-	case BLKIF_OP_FLUSH_DISKCACHE:
-		dst->u.rw.nr_segments = src->u.rw.nr_segments;
-		dst->u.rw.handle = src->u.rw.handle;
-		dst->u.rw.id = src->u.rw.id;
-		dst->u.rw.sector_number = src->u.rw.sector_number;
-		barrier();
-		if (n > dst->u.rw.nr_segments)
-			n = dst->u.rw.nr_segments;
-		for (i = 0; i < n; i++)
-			dst->u.rw.seg[i] = src->u.rw.seg[i];
-		break;
-	case BLKIF_OP_DISCARD:
-		dst->u.discard.flag = src->u.discard.flag;
-		dst->u.discard.id = src->u.discard.id;
-		dst->u.discard.sector_number = src->u.discard.sector_number;
-		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
-		break;
-	case BLKIF_OP_INDIRECT:
-		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
-		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
-		dst->u.indirect.handle = src->u.indirect.handle;
-		dst->u.indirect.id = src->u.indirect.id;
-		dst->u.indirect.sector_number = src->u.indirect.sector_number;
-		barrier();
-		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
-		for (i = 0; i < j; i++)
-			dst->u.indirect.indirect_grefs[i] =
-				src->u.indirect.indirect_grefs[i];
-		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;
-	}
-}
-
 #endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */

drivers/xen/pvcalls-front.c

@@ -227,22 +227,30 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
 
 static void free_active_ring(struct sock_mapping *map);
 
-static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
-				   struct sock_mapping *map)
+static void pvcalls_front_destroy_active(struct pvcalls_bedata *bedata,
+					 struct sock_mapping *map)
 {
 	int i;
 
 	unbind_from_irqhandler(map->active.irq, map);
 
-	spin_lock(&bedata->socket_lock);
-	if (!list_empty(&map->list))
-		list_del_init(&map->list);
-	spin_unlock(&bedata->socket_lock);
+	if (bedata) {
+		spin_lock(&bedata->socket_lock);
+		if (!list_empty(&map->list))
+			list_del_init(&map->list);
+		spin_unlock(&bedata->socket_lock);
+	}
 
 	for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
 		gnttab_end_foreign_access(map->active.ring->ref[i], NULL);
 	gnttab_end_foreign_access(map->active.ref, NULL);
 	free_active_ring(map);
+}
+
+static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
+				   struct sock_mapping *map)
+{
+	pvcalls_front_destroy_active(bedata, map);
 
 	kfree(map);
 }
@@ -433,19 +441,18 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
-
-	spin_lock(&bedata->socket_lock);
-	ret = get_request(bedata, &req_id);
+	ret = create_active(map, &evtchn);
 	if (ret < 0) {
-		spin_unlock(&bedata->socket_lock);
 		free_active_ring(map);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
-	ret = create_active(map, &evtchn);
+
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
 		spin_unlock(&bedata->socket_lock);
-		free_active_ring(map);
+		pvcalls_front_destroy_active(NULL, map);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
@@ -821,28 +828,27 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
-	spin_lock(&bedata->socket_lock);
-	ret = get_request(bedata, &req_id);
+	ret = create_active(map2, &evtchn);
 	if (ret < 0) {
-		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
-			  (void *)&map->passive.flags);
-		spin_unlock(&bedata->socket_lock);
 		free_active_ring(map2);
 		kfree(map2);
+		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
+			  (void *)&map->passive.flags);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
 
-	ret = create_active(map2, &evtchn);
+	spin_lock(&bedata->socket_lock);
+	ret = get_request(bedata, &req_id);
 	if (ret < 0) {
-		free_active_ring(map2);
-		kfree(map2);
 		clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT,
 			  (void *)&map->passive.flags);
 		spin_unlock(&bedata->socket_lock);
+		pvcalls_front_free_map(bedata, map2);
 		pvcalls_exit_sock(sock);
 		return ret;
 	}
+
 	list_add_tail(&map2->list, &bedata->socket_mappings);
 
 	req = RING_GET_REQUEST(&bedata->ring, req_id);

drivers/xen/xen-pciback/pci_stub.c

@@ -194,8 +194,6 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
 	struct pci_dev *pci_dev = NULL;
 	unsigned long flags;
 
-	pcistub_device_get(psdev);
-
 	spin_lock_irqsave(&psdev->lock, flags);
 	if (!psdev->pdev) {
 		psdev->pdev = pdev;
@@ -203,8 +201,8 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
 	}
 	spin_unlock_irqrestore(&psdev->lock, flags);
 
-	if (!pci_dev)
-		pcistub_device_put(psdev);
+	if (pci_dev)
+		pcistub_device_get(psdev);
 
 	return pci_dev;
 }

drivers/xen/xen-scsiback.c

@@ -1010,12 +1010,6 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info,
 	return err;
 }
 
-static void __scsiback_del_translation_entry(struct v2p_entry *entry)
-{
-	list_del(&entry->l);
-	kref_put(&entry->kref, scsiback_free_translation_entry);
-}
-
 /*
   Delete the translation entry specified
 */
@@ -1024,18 +1018,20 @@ static int scsiback_del_translation_entry(struct vscsibk_info *info,
 {
 	struct v2p_entry *entry;
 	unsigned long flags;
-	int ret = 0;
 
 	spin_lock_irqsave(&info->v2p_lock, flags);
 	/* Find out the translation entry specified */
 	entry = scsiback_chk_translation_entry(info, v);
 	if (entry)
-		__scsiback_del_translation_entry(entry);
-	else
-		ret = -ENOENT;
+		list_del(&entry->l);
 
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
-	return ret;
+
+	if (!entry)
+		return -ENOENT;
+
+	kref_put(&entry->kref, scsiback_free_translation_entry);
+	return 0;
 }
 
 static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
@@ -1239,14 +1235,19 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info)
 {
 	struct v2p_entry *entry, *tmp;
 	struct list_head *head = &(info->v2p_entry_lists);
+	struct list_head tmp_list;
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->v2p_lock, flags);
 
-	list_for_each_entry_safe(entry, tmp, head, l)
-		__scsiback_del_translation_entry(entry);
+	list_cut_before(&tmp_list, head, head);
 
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, &tmp_list, l) {
+		list_del(&entry->l);
+		kref_put(&entry->kref, scsiback_free_translation_entry);
+	}
 }
 
 static void scsiback_remove(struct xenbus_device *dev)