vhost: factor out IOTLB

This patch factors out IOTLB into a dedicated module in order to be
reused by other modules like vringh. User may choose to enable the
automatic retiring by specifying VHOST_IOTLB_FLAG_RETIRE flag to fit
for the case of vhost device IOTLB implementation.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20200326140125.19794-4-jasowang@redhat.comSigned-off-by: Michael S. Tsirkin <mst@redhat.com>

MAINTAINERS

@@ -17766,6 +17766,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git
 S:	Maintained
 F:	drivers/vhost/
 F:	include/uapi/linux/vhost.h
+F:	include/linux/vhost_iotlb.h
 
 VIRTIO INPUT DRIVER
 M:	Gerd Hoffmann <kraxel@redhat.com>

drivers/vhost/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
+config VHOST_IOTLB
+	tristate
+	help
+	  Generic IOTLB implementation for vhost and vringh.
+
 config VHOST_RING
 	tristate
 	help
@@ -67,4 +72,5 @@ config VHOST_CROSS_ENDIAN_LEGACY
 	  adds some overhead, it is disabled by default.
 
 	  If unsure, say "N".
+
 endif

drivers/vhost/Makefile

@@ -11,3 +11,6 @@ vhost_vsock-y := vsock.o
 obj-$(CONFIG_VHOST_RING) += vringh.o
 
 obj-$(CONFIG_VHOST)	+= vhost.o
+
+obj-$(CONFIG_VHOST_IOTLB) += vhost_iotlb.o
+vhost_iotlb-y := iotlb.o

drivers/vhost/iotlb.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Red Hat, Inc.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ * IOTLB implementation for vhost.
+ */
+#include <linux/slab.h>
+#include <linux/vhost_iotlb.h>
+#include <linux/module.h>
+
+#define MOD_VERSION  "0.1"
+#define MOD_DESC     "VHOST IOTLB"
+#define MOD_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define MOD_LICENSE  "GPL v2"
+
+#define START(map) ((map)->start)
+#define LAST(map) ((map)->last)
+
+INTERVAL_TREE_DEFINE(struct vhost_iotlb_map,
+		     rb, __u64, __subtree_last,
+		     START, LAST, static inline, vhost_iotlb_itree);
+
+/**
+ * vhost_iotlb_map_free - remove a map node and free it
+ * @iotlb: the IOTLB
+ * @map: the map that want to be remove and freed
+ */
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map)
+{
+	vhost_iotlb_itree_remove(map, &iotlb->root);
+	list_del(&map->link);
+	kfree(map);
+	iotlb->nmaps--;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_map_free);
+
+/**
+ * vhost_iotlb_add_range - add a new range to vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ * @addr: the address that is mapped to @start
+ * @perm: access permission of this range
+ *
+ * Returns an error last is smaller than start or memory allocation
+ * fails
+ */
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
+			  u64 start, u64 last,
+			  u64 addr, unsigned int perm)
+{
+	struct vhost_iotlb_map *map;
+
+	if (last < start)
+		return -EFAULT;
+
+	if (iotlb->limit &&
+	    iotlb->nmaps == iotlb->limit &&
+	    iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) {
+		map = list_first_entry(&iotlb->list, typeof(*map), link);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+
+	map = kmalloc(sizeof(*map), GFP_ATOMIC);
+	if (!map)
+		return -ENOMEM;
+
+	map->start = start;
+	map->size = last - start + 1;
+	map->last = last;
+	map->addr = addr;
+	map->perm = perm;
+
+	iotlb->nmaps++;
+	vhost_iotlb_itree_insert(map, &iotlb->root);
+
+	INIT_LIST_HEAD(&map->link);
+	list_add_tail(&map->link, &iotlb->list);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range);
+
+/**
+ * vring_iotlb_del_range - delete overlapped ranges from vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ */
+void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	struct vhost_iotlb_map *map;
+
+	while ((map = vhost_iotlb_itree_iter_first(&iotlb->root,
+						   start, last)))
+		vhost_iotlb_map_free(iotlb, map);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_del_range);
+
+/**
+ * vhost_iotlb_alloc - add a new vhost IOTLB
+ * @limit: maximum number of IOTLB entries
+ * @flags: VHOST_IOTLB_FLAG_XXX
+ *
+ * Returns an error is memory allocation fails
+ */
+struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags)
+{
+	struct vhost_iotlb *iotlb = kzalloc(sizeof(*iotlb), GFP_KERNEL);
+
+	if (!iotlb)
+		return NULL;
+
+	iotlb->root = RB_ROOT_CACHED;
+	iotlb->limit = limit;
+	iotlb->nmaps = 0;
+	iotlb->flags = flags;
+	INIT_LIST_HEAD(&iotlb->list);
+
+	return iotlb;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_alloc);
+
+/**
+ * vhost_iotlb_reset - reset vhost IOTLB (free all IOTLB entries)
+ * @iotlb: the IOTLB to be reset
+ */
+void vhost_iotlb_reset(struct vhost_iotlb *iotlb)
+{
+	vhost_iotlb_del_range(iotlb, 0ULL, 0ULL - 1);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_reset);
+
+/**
+ * vhost_iotlb_free - reset and free vhost IOTLB
+ * @iotlb: the IOTLB to be freed
+ */
+void vhost_iotlb_free(struct vhost_iotlb *iotlb)
+{
+	if (iotlb) {
+		vhost_iotlb_reset(iotlb);
+		kfree(iotlb);
+	}
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_free);
+
+/**
+ * vhost_iotlb_itree_first - return the first overlapped range
+ * @iotlb: the IOTLB
+ * @start: start of IOVA range
+ * @end: end of IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_first(&iotlb->root, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first);
+
+/**
+ * vhost_iotlb_itree_first - return the next overlapped range
+ * @iotlb: the IOTLB
+ * @start: start of IOVA range
+ * @end: end of IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_next(map, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_next);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_DESCRIPTION(MOD_DESC);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_LICENSE(MOD_LICENSE);

drivers/vhost/net.c

@@ -1587,7 +1587,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	struct socket *tx_sock = NULL;
 	struct socket *rx_sock = NULL;
 	long err;
-	struct vhost_umem *umem;
+	struct vhost_iotlb *umem;
 
 	mutex_lock(&n->dev.mutex);
 	err = vhost_dev_check_owner(&n->dev);

drivers/vhost/vhost.h

@@ -12,6 +12,7 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/atomic.h>
+#include <linux/vhost_iotlb.h>
 
 struct vhost_work;
 typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -52,27 +53,6 @@ struct vhost_log {
 	u64 len;
 };
 
-#define START(node) ((node)->start)
-#define LAST(node) ((node)->last)
-
-struct vhost_umem_node {
-	struct rb_node rb;
-	struct list_head link;
-	__u64 start;
-	__u64 last;
-	__u64 size;
-	__u64 userspace_addr;
-	__u32 perm;
-	__u32 flags_padding;
-	__u64 __subtree_last;
-};
-
-struct vhost_umem {
-	struct rb_root_cached umem_tree;
-	struct list_head umem_list;
-	int numem;
-};
-
 enum vhost_uaddr_type {
 	VHOST_ADDR_DESC = 0,
 	VHOST_ADDR_AVAIL = 1,
@@ -90,7 +70,7 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
-	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
+	const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
 	struct eventfd_ctx *call_ctx;
 	struct eventfd_ctx *error_ctx;
@@ -128,8 +108,8 @@ struct vhost_virtqueue {
 	struct iovec *indirect;
 	struct vring_used_elem *heads;
 	/* Protected by virtqueue mutex. */
-	struct vhost_umem *umem;
-	struct vhost_umem *iotlb;
+	struct vhost_iotlb *umem;
+	struct vhost_iotlb *iotlb;
 	void *private_data;
 	u64 acked_features;
 	u64 acked_backend_features;
@@ -164,8 +144,8 @@ struct vhost_dev {
 	struct eventfd_ctx *log_ctx;
 	struct llist_head work_list;
 	struct task_struct *worker;
-	struct vhost_umem *umem;
-	struct vhost_umem *iotlb;
+	struct vhost_iotlb *umem;
+	struct vhost_iotlb *iotlb;
 	spinlock_t iotlb_lock;
 	struct list_head read_list;
 	struct list_head pending_list;
@@ -186,8 +166,8 @@ void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
-struct vhost_umem *vhost_dev_reset_owner_prepare(void);
-void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void);
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *iotlb);
 void vhost_dev_cleanup(struct vhost_dev *);
 void vhost_dev_stop(struct vhost_dev *);
 long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
@@ -233,6 +213,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 			     struct iov_iter *from);
 int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
 
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map);
+
 #define vq_err(vq, fmt, ...) do {                                  \
 		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
 		if ((vq)->error_ctx)                               \

include/linux/vhost_iotlb.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VHOST_IOTLB_H
+#define _LINUX_VHOST_IOTLB_H
+
+#include <linux/interval_tree_generic.h>
+
+struct vhost_iotlb_map {
+	struct rb_node rb;
+	struct list_head link;
+	u64 start;
+	u64 last;
+	u64 size;
+	u64 addr;
+#define VHOST_MAP_RO 0x1
+#define VHOST_MAP_WO 0x2
+#define VHOST_MAP_RW 0x3
+	u32 perm;
+	u32 flags_padding;
+	u64 __subtree_last;
+};
+
+#define VHOST_IOTLB_FLAG_RETIRE 0x1
+
+struct vhost_iotlb {
+	struct rb_root_cached root;
+	struct list_head list;
+	unsigned int limit;
+	unsigned int nmaps;
+	unsigned int flags;
+};
+
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
+			  u64 addr, unsigned int perm);
+void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);
+
+struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags);
+void vhost_iotlb_free(struct vhost_iotlb *iotlb);
+void vhost_iotlb_reset(struct vhost_iotlb *iotlb);
+
+struct vhost_iotlb_map *
+vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last);
+struct vhost_iotlb_map *
+vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last);
+
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map);
+#endif