From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/drivers/vhost/vhost.c | 759 ++++++++++++++++++++++++++++++++-------------------------
1 files changed, 423 insertions(+), 336 deletions(-)
diff --git a/kernel/drivers/vhost/vhost.c b/kernel/drivers/vhost/vhost.c
index ee478b5..f41463a 100644
--- a/kernel/drivers/vhost/vhost.c
+++ b/kernel/drivers/vhost/vhost.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (C) 2009 Red Hat, Inc.
* Copyright (C) 2006 Rusty Russell IBM Corporation
*
@@ -6,8 +7,6 @@
* Inspiration, some code, and most witty comments come from
* Documentation/virtual/lguest/lguest.c, by Rusty Russell
*
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
* Generic code for virtio server in host kernel.
*/
@@ -15,7 +14,6 @@
#include <linux/vhost.h>
#include <linux/uio.h>
#include <linux/mm.h>
-#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/poll.h>
@@ -50,10 +48,6 @@
#define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
#define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
-
-INTERVAL_TREE_DEFINE(struct vhost_umem_node,
- rb, __u64, __subtree_last,
- START, LAST, static inline, vhost_umem_interval_tree);
#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
@@ -171,11 +165,16 @@
void *key)
{
struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);
+ struct vhost_work *work = &poll->work;
if (!(key_to_poll(key) & poll->mask))
return 0;
- vhost_poll_queue(poll);
+ if (!poll->dev->use_worker)
+ work->fn(work);
+ else
+ vhost_poll_queue(poll);
+
return 0;
}
@@ -205,7 +204,6 @@
int vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
__poll_t mask;
- int ret = 0;
if (poll->wqh)
return 0;
@@ -215,10 +213,10 @@
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
if (mask & EPOLLERR) {
vhost_poll_stop(poll);
- ret = -EINVAL;
+ return -EINVAL;
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL_GPL(vhost_poll_start);
@@ -300,6 +298,18 @@
__vhost_vq_meta_reset(d->vqs[i]);
}
+static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx)
+{
+ call_ctx->ctx = NULL;
+ memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
+}
+
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq)
+{
+ return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq);
+}
+EXPORT_SYMBOL_GPL(vhost_vq_is_setup);
+
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
@@ -321,13 +331,13 @@
vq->log_base = NULL;
vq->error_ctx = NULL;
vq->kick = NULL;
- vq->call_ctx = NULL;
vq->log_ctx = NULL;
vhost_disable_cross_endian(vq);
vhost_reset_is_le(vq);
vq->busyloop_timeout = 0;
vq->umem = NULL;
vq->iotlb = NULL;
+ vhost_vring_call_reset(&vq->call_ctx);
__vhost_vq_meta_reset(vq);
}
@@ -336,10 +346,8 @@
struct vhost_dev *dev = data;
struct vhost_work *work, *work_next;
struct llist_node *node;
- mm_segment_t oldfs = get_fs();
- set_fs(USER_DS);
- use_mm(dev->mm);
+ kthread_use_mm(dev->mm);
for (;;) {
/* mb paired w/ kthread_stop */
@@ -367,8 +375,7 @@
schedule();
}
}
- unuse_mm(dev->mm);
- set_fs(oldfs);
+ kthread_unuse_mm(dev->mm);
return 0;
}
@@ -431,9 +438,38 @@
}
EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
+static size_t vhost_get_avail_size(struct vhost_virtqueue *vq,
+ unsigned int num)
+{
+ size_t event __maybe_unused =
+ vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+
+ return sizeof(*vq->avail) +
+ sizeof(*vq->avail->ring) * num + event;
+}
+
+static size_t vhost_get_used_size(struct vhost_virtqueue *vq,
+ unsigned int num)
+{
+ size_t event __maybe_unused =
+ vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+
+ return sizeof(*vq->used) +
+ sizeof(*vq->used->ring) * num + event;
+}
+
+static size_t vhost_get_desc_size(struct vhost_virtqueue *vq,
+ unsigned int num)
+{
+ return sizeof(*vq->desc) * num;
+}
+
void vhost_dev_init(struct vhost_dev *dev,
struct vhost_virtqueue **vqs, int nvqs,
- int iov_limit, int weight, int byte_weight)
+ int iov_limit, int weight, int byte_weight,
+ bool use_worker,
+ int (*msg_handler)(struct vhost_dev *dev,
+ struct vhost_iotlb_msg *msg))
{
struct vhost_virtqueue *vq;
int i;
@@ -449,6 +485,8 @@
dev->iov_limit = iov_limit;
dev->weight = weight;
dev->byte_weight = byte_weight;
+ dev->use_worker = use_worker;
+ dev->msg_handler = msg_handler;
init_llist_head(&dev->work_list);
init_waitqueue_head(&dev->wait);
INIT_LIST_HEAD(&dev->read_list);
@@ -511,6 +549,36 @@
}
EXPORT_SYMBOL_GPL(vhost_dev_has_owner);
+static void vhost_attach_mm(struct vhost_dev *dev)
+{
+ /* No owner, become one */
+ if (dev->use_worker) {
+ dev->mm = get_task_mm(current);
+ } else {
+ /* vDPA device does not use worker thead, so there's
+ * no need to hold the address space for mm. This help
+ * to avoid deadlock in the case of mmap() which may
+ * held the refcnt of the file and depends on release
+ * method to remove vma.
+ */
+ dev->mm = current->mm;
+ mmgrab(dev->mm);
+ }
+}
+
+static void vhost_detach_mm(struct vhost_dev *dev)
+{
+ if (!dev->mm)
+ return;
+
+ if (dev->use_worker)
+ mmput(dev->mm);
+ else
+ mmdrop(dev->mm);
+
+ dev->mm = NULL;
+}
+
/* Caller should have device mutex */
long vhost_dev_set_owner(struct vhost_dev *dev)
{
@@ -523,21 +591,24 @@
goto err_mm;
}
- /* No owner, become one */
- dev->mm = get_task_mm(current);
+ vhost_attach_mm(dev);
+
dev->kcov_handle = kcov_common_handle();
- worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
- if (IS_ERR(worker)) {
- err = PTR_ERR(worker);
- goto err_worker;
+ if (dev->use_worker) {
+ worker = kthread_create(vhost_worker, dev,
+ "vhost-%d", current->pid);
+ if (IS_ERR(worker)) {
+ err = PTR_ERR(worker);
+ goto err_worker;
+ }
+
+ dev->worker = worker;
+ wake_up_process(worker); /* avoid contributing to loadavg */
+
+ err = vhost_attach_cgroups(dev);
+ if (err)
+ goto err_cgroup;
}
-
- dev->worker = worker;
- wake_up_process(worker); /* avoid contributing to loadavg */
-
- err = vhost_attach_cgroups(dev);
- if (err)
- goto err_cgroup;
err = vhost_dev_alloc_iovecs(dev);
if (err)
@@ -545,33 +616,37 @@
return 0;
err_cgroup:
- kthread_stop(worker);
- dev->worker = NULL;
+ if (dev->worker) {
+ kthread_stop(dev->worker);
+ dev->worker = NULL;
+ }
err_worker:
- if (dev->mm)
- mmput(dev->mm);
- dev->mm = NULL;
+ vhost_detach_mm(dev);
dev->kcov_handle = 0;
err_mm:
return err;
}
EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
-struct vhost_umem *vhost_dev_reset_owner_prepare(void)
+static struct vhost_iotlb *iotlb_alloc(void)
{
- return kvzalloc(sizeof(struct vhost_umem), GFP_KERNEL);
+ return vhost_iotlb_alloc(max_iotlb_entries,
+ VHOST_IOTLB_FLAG_RETIRE);
+}
+
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void)
+{
+ return iotlb_alloc();
}
EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
/* Caller should have device mutex */
-void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem)
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *umem)
{
int i;
vhost_dev_cleanup(dev);
- /* Restore memory to default empty mapping. */
- INIT_LIST_HEAD(&umem->umem_list);
dev->umem = umem;
/* We don't need VQ locks below since vhost_dev_cleanup makes sure
* VQs aren't running.
@@ -593,28 +668,6 @@
}
}
EXPORT_SYMBOL_GPL(vhost_dev_stop);
-
-static void vhost_umem_free(struct vhost_umem *umem,
- struct vhost_umem_node *node)
-{
- vhost_umem_interval_tree_remove(node, &umem->umem_tree);
- list_del(&node->link);
- kfree(node);
- umem->numem--;
-}
-
-static void vhost_umem_clean(struct vhost_umem *umem)
-{
- struct vhost_umem_node *node, *tmp;
-
- if (!umem)
- return;
-
- list_for_each_entry_safe(node, tmp, &umem->umem_list, link)
- vhost_umem_free(umem, node);
-
- kvfree(umem);
-}
static void vhost_clear_msg(struct vhost_dev *dev)
{
@@ -644,8 +697,8 @@
eventfd_ctx_put(dev->vqs[i]->error_ctx);
if (dev->vqs[i]->kick)
fput(dev->vqs[i]->kick);
- if (dev->vqs[i]->call_ctx)
- eventfd_ctx_put(dev->vqs[i]->call_ctx);
+ if (dev->vqs[i]->call_ctx.ctx)
+ eventfd_ctx_put(dev->vqs[i]->call_ctx.ctx);
vhost_vq_reset(dev, dev->vqs[i]);
}
vhost_dev_free_iovecs(dev);
@@ -653,9 +706,9 @@
eventfd_ctx_put(dev->log_ctx);
dev->log_ctx = NULL;
/* No one will access memory at this point */
- vhost_umem_clean(dev->umem);
+ vhost_iotlb_free(dev->umem);
dev->umem = NULL;
- vhost_umem_clean(dev->iotlb);
+ vhost_iotlb_free(dev->iotlb);
dev->iotlb = NULL;
vhost_clear_msg(dev);
wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
@@ -665,9 +718,7 @@
dev->worker = NULL;
dev->kcov_handle = 0;
}
- if (dev->mm)
- mmput(dev->mm);
- dev->mm = NULL;
+ vhost_detach_mm(dev);
}
EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
@@ -680,7 +731,7 @@
a + (unsigned long)log_base > ULONG_MAX)
return false;
- return access_ok(VERIFY_WRITE, log_base + a,
+ return access_ok(log_base + a,
(sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
}
@@ -697,27 +748,26 @@
}
/* Caller should have vq mutex and device mutex. */
-static bool vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
+static bool vq_memory_access_ok(void __user *log_base, struct vhost_iotlb *umem,
int log_all)
{
- struct vhost_umem_node *node;
+ struct vhost_iotlb_map *map;
if (!umem)
return false;
- list_for_each_entry(node, &umem->umem_list, link) {
- unsigned long a = node->userspace_addr;
+ list_for_each_entry(map, &umem->list, link) {
+ unsigned long a = map->addr;
- if (vhost_overflow(node->userspace_addr, node->size))
+ if (vhost_overflow(map->addr, map->size))
return false;
- if (!access_ok(VERIFY_WRITE, (void __user *)a,
- node->size))
+ if (!access_ok((void __user *)a, map->size))
return false;
else if (log_all && !log_access_ok(log_base,
- node->start,
- node->size))
+ map->start,
+ map->size))
return false;
}
return true;
@@ -727,17 +777,17 @@
u64 addr, unsigned int size,
int type)
{
- const struct vhost_umem_node *node = vq->meta_iotlb[type];
+ const struct vhost_iotlb_map *map = vq->meta_iotlb[type];
- if (!node)
+ if (!map)
return NULL;
- return (void *)(uintptr_t)(node->userspace_addr + addr - node->start);
+ return (void __user *)(uintptr_t)(map->addr + addr - map->start);
}
/* Can we switch to this memory table? */
/* Caller should have device mutex but not vq mutex */
-static bool memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
+static bool memory_access_ok(struct vhost_dev *d, struct vhost_iotlb *umem,
int log_all)
{
int i;
@@ -871,7 +921,7 @@
* not happen in this case.
*/
static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
- void *addr, unsigned int size,
+ void __user *addr, unsigned int size,
int type)
{
void __user *uaddr = vhost_vq_meta_fetch(vq,
@@ -884,7 +934,7 @@
#define vhost_put_user(vq, x, ptr) \
({ \
- int ret = -EFAULT; \
+ int ret; \
if (!vq->iotlb) { \
ret = __put_user(x, ptr); \
} else { \
@@ -898,6 +948,34 @@
} \
ret; \
})
+
+static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
+{
+ return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
+ vhost_avail_event(vq));
+}
+
+static inline int vhost_put_used(struct vhost_virtqueue *vq,
+ struct vring_used_elem *head, int idx,
+ int count)
+{
+ return vhost_copy_to_user(vq, vq->used->ring + idx, head,
+ count * sizeof(*head));
+}
+
+static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
+
+{
+ return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
+ &vq->used->flags);
+}
+
+static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
+
+{
+ return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
+ &vq->used->idx);
+}
#define vhost_get_user(vq, x, ptr, type) \
({ \
@@ -937,45 +1015,41 @@
mutex_unlock(&d->vqs[i]->mutex);
}
-static int vhost_new_umem_range(struct vhost_umem *umem,
- u64 start, u64 size, u64 end,
- u64 userspace_addr, int perm)
+static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
+ __virtio16 *idx)
{
- struct vhost_umem_node *tmp, *node;
-
- if (!size)
- return -EFAULT;
-
- node = kmalloc(sizeof(*node), GFP_ATOMIC);
- if (!node)
- return -ENOMEM;
-
- if (umem->numem == max_iotlb_entries) {
- tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link);
- vhost_umem_free(umem, tmp);
- }
-
- node->start = start;
- node->size = size;
- node->last = end;
- node->userspace_addr = userspace_addr;
- node->perm = perm;
- INIT_LIST_HEAD(&node->link);
- list_add_tail(&node->link, &umem->umem_list);
- vhost_umem_interval_tree_insert(node, &umem->umem_tree);
- umem->numem++;
-
- return 0;
+ return vhost_get_avail(vq, *idx, &vq->avail->idx);
}
-static void vhost_del_umem_range(struct vhost_umem *umem,
- u64 start, u64 end)
+static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
+ __virtio16 *head, int idx)
{
- struct vhost_umem_node *node;
+ return vhost_get_avail(vq, *head,
+ &vq->avail->ring[idx & (vq->num - 1)]);
+}
- while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
- start, end)))
- vhost_umem_free(umem, node);
+static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
+ __virtio16 *flags)
+{
+ return vhost_get_avail(vq, *flags, &vq->avail->flags);
+}
+
+static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
+ __virtio16 *event)
+{
+ return vhost_get_avail(vq, *event, vhost_used_event(vq));
+}
+
+static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
+ __virtio16 *idx)
+{
+ return vhost_get_used(vq, *idx, &vq->used->idx);
+}
+
+static inline int vhost_get_desc(struct vhost_virtqueue *vq,
+ struct vring_desc *desc, int idx)
+{
+ return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
}
static void vhost_iotlb_notify_vq(struct vhost_dev *d,
@@ -1008,10 +1082,10 @@
return false;
if ((access & VHOST_ACCESS_RO) &&
- !access_ok(VERIFY_READ, (void __user *)a, size))
+ !access_ok((void __user *)a, size))
return false;
if ((access & VHOST_ACCESS_WO) &&
- !access_ok(VERIFY_WRITE, (void __user *)a, size))
+ !access_ok((void __user *)a, size))
return false;
return true;
}
@@ -1034,9 +1108,9 @@
break;
}
vhost_vq_meta_reset(dev);
- if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
- msg->iova + msg->size - 1,
- msg->uaddr, msg->perm)) {
+ if (vhost_iotlb_add_range(dev->iotlb, msg->iova,
+ msg->iova + msg->size - 1,
+ msg->uaddr, msg->perm)) {
ret = -ENOMEM;
break;
}
@@ -1048,8 +1122,8 @@
break;
}
vhost_vq_meta_reset(dev);
- vhost_del_umem_range(dev->iotlb, msg->iova,
- msg->iova + msg->size - 1);
+ vhost_iotlb_del_range(dev->iotlb, msg->iova,
+ msg->iova + msg->size - 1);
break;
default:
ret = -EINVAL;
@@ -1095,7 +1169,12 @@
ret = -EINVAL;
goto done;
}
- if (vhost_process_iotlb_msg(dev, &msg)) {
+
+ if (dev->msg_handler)
+ ret = dev->msg_handler(dev, &msg);
+ else
+ ret = vhost_process_iotlb_msg(dev, &msg);
+ if (ret) {
ret = -EFAULT;
goto done;
}
@@ -1217,59 +1296,58 @@
}
static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
- struct vring_desc __user *desc,
- struct vring_avail __user *avail,
- struct vring_used __user *used)
+ vring_desc_t __user *desc,
+ vring_avail_t __user *avail,
+ vring_used_t __user *used)
{
- size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+ /* If an IOTLB device is present, the vring addresses are
+ * GIOVAs. Access validation occurs at prefetch time. */
+ if (vq->iotlb)
+ return true;
- return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
- access_ok(VERIFY_READ, avail,
- sizeof *avail + num * sizeof *avail->ring + s) &&
- access_ok(VERIFY_WRITE, used,
- sizeof *used + num * sizeof *used->ring + s);
+ return access_ok(desc, vhost_get_desc_size(vq, num)) &&
+ access_ok(avail, vhost_get_avail_size(vq, num)) &&
+ access_ok(used, vhost_get_used_size(vq, num));
}
static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
- const struct vhost_umem_node *node,
+ const struct vhost_iotlb_map *map,
int type)
{
int access = (type == VHOST_ADDR_USED) ?
VHOST_ACCESS_WO : VHOST_ACCESS_RO;
- if (likely(node->perm & access))
- vq->meta_iotlb[type] = node;
+ if (likely(map->perm & access))
+ vq->meta_iotlb[type] = map;
}
static bool iotlb_access_ok(struct vhost_virtqueue *vq,
int access, u64 addr, u64 len, int type)
{
- const struct vhost_umem_node *node;
- struct vhost_umem *umem = vq->iotlb;
+ const struct vhost_iotlb_map *map;
+ struct vhost_iotlb *umem = vq->iotlb;
u64 s = 0, size, orig_addr = addr, last = addr + len - 1;
if (vhost_vq_meta_fetch(vq, addr, len, type))
return true;
while (len > s) {
- node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
- addr,
- last);
- if (node == NULL || node->start > addr) {
+ map = vhost_iotlb_itree_first(umem, addr, last);
+ if (map == NULL || map->start > addr) {
vhost_iotlb_miss(vq, addr, access);
return false;
- } else if (!(node->perm & access)) {
+ } else if (!(map->perm & access)) {
/* Report the possible access violation by
* request another translation from userspace.
*/
return false;
}
- size = node->size - addr + node->start;
+ size = map->size - addr + map->start;
if (orig_addr == addr && size >= len)
- vhost_vq_meta_update(vq, node, type);
+ vhost_vq_meta_update(vq, map, type);
s += size;
addr += size;
@@ -1278,26 +1356,22 @@
return true;
}
-int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
+int vq_meta_prefetch(struct vhost_virtqueue *vq)
{
- size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
unsigned int num = vq->num;
if (!vq->iotlb)
return 1;
- return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
- num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
- iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
- sizeof *vq->avail +
- num * sizeof(*vq->avail->ring) + s,
+ return iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->desc,
+ vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
+ iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->avail,
+ vhost_get_avail_size(vq, num),
VHOST_ADDR_AVAIL) &&
- iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
- sizeof *vq->used +
- num * sizeof(*vq->used->ring) + s,
- VHOST_ADDR_USED);
+ iotlb_access_ok(vq, VHOST_MAP_WO, (u64)(uintptr_t)vq->used,
+ vhost_get_used_size(vq, num), VHOST_ADDR_USED);
}
-EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);
+EXPORT_SYMBOL_GPL(vq_meta_prefetch);
/* Can we log writes? */
/* Caller should have device mutex but not vq mutex */
@@ -1307,18 +1381,28 @@
}
EXPORT_SYMBOL_GPL(vhost_log_access_ok);
+static bool vq_log_used_access_ok(struct vhost_virtqueue *vq,
+ void __user *log_base,
+ bool log_used,
+ u64 log_addr)
+{
+ /* If an IOTLB device is present, log_addr is a GIOVA that
+ * will never be logged by log_used(). */
+ if (vq->iotlb)
+ return true;
+
+ return !log_used || log_access_ok(log_base, log_addr,
+ vhost_get_used_size(vq, vq->num));
+}
+
/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static bool vq_log_access_ok(struct vhost_virtqueue *vq,
void __user *log_base)
{
- size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
-
return vq_memory_access_ok(log_base, vq->umem,
vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
- (!vq->log_used || log_access_ok(log_base, vq->log_addr,
- sizeof *vq->used +
- vq->num * sizeof *vq->used->ring + s));
+ vq_log_used_access_ok(vq, log_base, vq->log_used, vq->log_addr);
}
/* Can we start vq? */
@@ -1328,33 +1412,15 @@
if (!vq_log_access_ok(vq, vq->log_base))
return false;
- /* Access validation occurs at prefetch time with IOTLB */
- if (vq->iotlb)
- return true;
-
return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
}
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
-
-static struct vhost_umem *vhost_umem_alloc(void)
-{
- struct vhost_umem *umem = kvzalloc(sizeof(*umem), GFP_KERNEL);
-
- if (!umem)
- return NULL;
-
- umem->umem_tree = RB_ROOT_CACHED;
- umem->numem = 0;
- INIT_LIST_HEAD(&umem->umem_list);
-
- return umem;
-}
static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
struct vhost_memory mem, *newmem;
struct vhost_memory_region *region;
- struct vhost_umem *newumem, *oldumem;
+ struct vhost_iotlb *newumem, *oldumem;
unsigned long size = offsetof(struct vhost_memory, regions);
int i;
@@ -1371,12 +1437,12 @@
memcpy(newmem, &mem, size);
if (copy_from_user(newmem->regions, m->regions,
- mem.nregions * sizeof *m->regions)) {
+ flex_array_size(newmem, regions, mem.nregions))) {
kvfree(newmem);
return -EFAULT;
}
- newumem = vhost_umem_alloc();
+ newumem = iotlb_alloc();
if (!newumem) {
kvfree(newmem);
return -ENOMEM;
@@ -1385,13 +1451,12 @@
for (region = newmem->regions;
region < newmem->regions + mem.nregions;
region++) {
- if (vhost_new_umem_range(newumem,
- region->guest_phys_addr,
- region->memory_size,
- region->guest_phys_addr +
- region->memory_size - 1,
- region->userspace_addr,
- VHOST_ACCESS_RW))
+ if (vhost_iotlb_add_range(newumem,
+ region->guest_phys_addr,
+ region->guest_phys_addr +
+ region->memory_size - 1,
+ region->userspace_addr,
+ VHOST_MAP_RW))
goto err;
}
@@ -1409,15 +1474,112 @@
}
kvfree(newmem);
- vhost_umem_clean(oldumem);
+ vhost_iotlb_free(oldumem);
return 0;
err:
- vhost_umem_clean(newumem);
+ vhost_iotlb_free(newumem);
kvfree(newmem);
return -EFAULT;
}
+static long vhost_vring_set_num(struct vhost_dev *d,
+ struct vhost_virtqueue *vq,
+ void __user *argp)
+{
+ struct vhost_vring_state s;
+
+ /* Resizing ring with an active backend?
+ * You don't want to do that. */
+ if (vq->private_data)
+ return -EBUSY;
+
+ if (copy_from_user(&s, argp, sizeof s))
+ return -EFAULT;
+
+ if (!s.num || s.num > 0xffff || (s.num & (s.num - 1)))
+ return -EINVAL;
+ vq->num = s.num;
+
+ return 0;
+}
+
+static long vhost_vring_set_addr(struct vhost_dev *d,
+ struct vhost_virtqueue *vq,
+ void __user *argp)
+{
+ struct vhost_vring_addr a;
+
+ if (copy_from_user(&a, argp, sizeof a))
+ return -EFAULT;
+ if (a.flags & ~(0x1 << VHOST_VRING_F_LOG))
+ return -EOPNOTSUPP;
+
+ /* For 32bit, verify that the top 32bits of the user
+ data are set to zero. */
+ if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
+ (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
+ (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr)
+ return -EFAULT;
+
+ /* Make sure it's safe to cast pointers to vring types. */
+ BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
+ BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
+ if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
+ (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
+ (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1)))
+ return -EINVAL;
+
+ /* We only verify access here if backend is configured.
+ * If it is not, we don't as size might not have been setup.
+ * We will verify when backend is configured. */
+ if (vq->private_data) {
+ if (!vq_access_ok(vq, vq->num,
+ (void __user *)(unsigned long)a.desc_user_addr,
+ (void __user *)(unsigned long)a.avail_user_addr,
+ (void __user *)(unsigned long)a.used_user_addr))
+ return -EINVAL;
+
+ /* Also validate log access for used ring if enabled. */
+ if (!vq_log_used_access_ok(vq, vq->log_base,
+ a.flags & (0x1 << VHOST_VRING_F_LOG),
+ a.log_guest_addr))
+ return -EINVAL;
+ }
+
+ vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
+ vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
+ vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
+ vq->log_addr = a.log_guest_addr;
+ vq->used = (void __user *)(unsigned long)a.used_user_addr;
+
+ return 0;
+}
+
+static long vhost_vring_set_num_addr(struct vhost_dev *d,
+ struct vhost_virtqueue *vq,
+ unsigned int ioctl,
+ void __user *argp)
+{
+ long r;
+
+ mutex_lock(&vq->mutex);
+
+ switch (ioctl) {
+ case VHOST_SET_VRING_NUM:
+ r = vhost_vring_set_num(d, vq, argp);
+ break;
+ case VHOST_SET_VRING_ADDR:
+ r = vhost_vring_set_addr(d, vq, argp);
+ break;
+ default:
+ BUG();
+ }
+
+ mutex_unlock(&vq->mutex);
+
+ return r;
+}
long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
{
struct file *eventfp, *filep = NULL;
@@ -1427,7 +1589,6 @@
struct vhost_virtqueue *vq;
struct vhost_vring_state s;
struct vhost_vring_file f;
- struct vhost_vring_addr a;
u32 idx;
long r;
@@ -1440,26 +1601,14 @@
idx = array_index_nospec(idx, d->nvqs);
vq = d->vqs[idx];
+ if (ioctl == VHOST_SET_VRING_NUM ||
+ ioctl == VHOST_SET_VRING_ADDR) {
+ return vhost_vring_set_num_addr(d, vq, ioctl, argp);
+ }
+
mutex_lock(&vq->mutex);
switch (ioctl) {
- case VHOST_SET_VRING_NUM:
- /* Resizing ring with an active backend?
- * You don't want to do that. */
- if (vq->private_data) {
- r = -EBUSY;
- break;
- }
- if (copy_from_user(&s, argp, sizeof s)) {
- r = -EFAULT;
- break;
- }
- if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
- r = -EINVAL;
- break;
- }
- vq->num = s.num;
- break;
case VHOST_SET_VRING_BASE:
/* Moving base with an active backend?
* You don't want to do that. */
@@ -1485,68 +1634,12 @@
if (copy_to_user(argp, &s, sizeof s))
r = -EFAULT;
break;
- case VHOST_SET_VRING_ADDR:
- if (copy_from_user(&a, argp, sizeof a)) {
- r = -EFAULT;
- break;
- }
- if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
- r = -EOPNOTSUPP;
- break;
- }
- /* For 32bit, verify that the top 32bits of the user
- data are set to zero. */
- if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
- (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
- (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
- r = -EFAULT;
- break;
- }
-
- /* Make sure it's safe to cast pointers to vring types. */
- BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
- BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
- if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
- (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
- (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) {
- r = -EINVAL;
- break;
- }
-
- /* We only verify access here if backend is configured.
- * If it is not, we don't as size might not have been setup.
- * We will verify when backend is configured. */
- if (vq->private_data) {
- if (!vq_access_ok(vq, vq->num,
- (void __user *)(unsigned long)a.desc_user_addr,
- (void __user *)(unsigned long)a.avail_user_addr,
- (void __user *)(unsigned long)a.used_user_addr)) {
- r = -EINVAL;
- break;
- }
-
- /* Also validate log access for used ring if enabled. */
- if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
- !log_access_ok(vq->log_base, a.log_guest_addr,
- sizeof *vq->used +
- vq->num * sizeof *vq->used->ring)) {
- r = -EINVAL;
- break;
- }
- }
-
- vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
- vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
- vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
- vq->log_addr = a.log_guest_addr;
- vq->used = (void __user *)(unsigned long)a.used_user_addr;
- break;
case VHOST_SET_VRING_KICK:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
- eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
+ eventfp = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_fget(f.fd);
if (IS_ERR(eventfp)) {
r = PTR_ERR(eventfp);
break;
@@ -1562,19 +1655,20 @@
r = -EFAULT;
break;
}
- ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
+ ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd);
if (IS_ERR(ctx)) {
r = PTR_ERR(ctx);
break;
}
- swap(ctx, vq->call_ctx);
+
+ swap(ctx, vq->call_ctx.ctx);
break;
case VHOST_SET_VRING_ERR:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
- ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
+ ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd);
if (IS_ERR(ctx)) {
r = PTR_ERR(ctx);
break;
@@ -1625,10 +1719,10 @@
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
{
- struct vhost_umem *niotlb, *oiotlb;
+ struct vhost_iotlb *niotlb, *oiotlb;
int i;
- niotlb = vhost_umem_alloc();
+ niotlb = iotlb_alloc();
if (!niotlb)
return -ENOMEM;
@@ -1644,7 +1738,7 @@
mutex_unlock(&vq->mutex);
}
- vhost_umem_clean(oiotlb);
+ vhost_iotlb_free(oiotlb);
return 0;
}
@@ -1699,7 +1793,7 @@
r = get_user(fd, (int __user *)argp);
if (r < 0)
break;
- ctx = fd == -1 ? NULL : eventfd_ctx_fdget(fd);
+ ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd);
if (IS_ERR(ctx)) {
r = PTR_ERR(ctx);
break;
@@ -1724,7 +1818,7 @@
/* TODO: This is really inefficient. We need something like get_user()
* (instruction directly accesses the data, with an exception table entry
- * returning -EFAULT). See Documentation/x86/exception-tables.txt.
+ * returning -EFAULT). See Documentation/x86/exception-tables.rst.
*/
static int set_bit_to_user(int nr, void __user *addr)
{
@@ -1734,15 +1828,14 @@
int bit = nr + (log % PAGE_SIZE) * 8;
int r;
- r = get_user_pages_fast(log, 1, 1, &page);
+ r = pin_user_pages_fast(log, 1, FOLL_WRITE, &page);
if (r < 0)
return r;
BUG_ON(r != 1);
base = kmap_atomic(page);
set_bit(bit, base);
kunmap_atomic(base);
- set_page_dirty_lock(page);
- put_page(page);
+ unpin_user_pages_dirty_lock(&page, 1, true);
return 0;
}
@@ -1774,8 +1867,8 @@
static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
{
- struct vhost_umem *umem = vq->umem;
- struct vhost_umem_node *u;
+ struct vhost_iotlb *umem = vq->umem;
+ struct vhost_iotlb_map *u;
u64 start, end, l, min;
int r;
bool hit = false;
@@ -1785,16 +1878,15 @@
/* More than one GPAs can be mapped into a single HVA. So
* iterate all possible umems here to be safe.
*/
- list_for_each_entry(u, &umem->umem_list, link) {
- if (u->userspace_addr > hva - 1 + len ||
- u->userspace_addr - 1 + u->size < hva)
+ list_for_each_entry(u, &umem->list, link) {
+ if (u->addr > hva - 1 + len ||
+ u->addr - 1 + u->size < hva)
continue;
- start = max(u->userspace_addr, hva);
- end = min(u->userspace_addr - 1 + u->size,
- hva - 1 + len);
+ start = max(u->addr, hva);
+ end = min(u->addr - 1 + u->size, hva - 1 + len);
l = end - start + 1;
r = log_write(vq->log_base,
- u->start + start - u->userspace_addr,
+ u->start + start - u->addr,
l);
if (r < 0)
return r;
@@ -1814,7 +1906,7 @@
static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
{
- struct iovec iov[64];
+ struct iovec *iov = vq->log_iov;
int i, ret;
if (!vq->iotlb)
@@ -1874,8 +1966,7 @@
static int vhost_update_used_flags(struct vhost_virtqueue *vq)
{
void __user *used;
- if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
- &vq->used->flags) < 0)
+ if (vhost_put_used_flags(vq))
return -EFAULT;
if (unlikely(vq->log_used)) {
/* Make sure the flag is seen before log. */
@@ -1892,8 +1983,7 @@
static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
{
- if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
- vhost_avail_event(vq)))
+ if (vhost_put_avail_event(vq))
return -EFAULT;
if (unlikely(vq->log_used)) {
void __user *used;
@@ -1925,11 +2015,11 @@
goto err;
vq->signalled_used_valid = false;
if (!vq->iotlb &&
- !access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) {
+ !access_ok(&vq->used->idx, sizeof vq->used->idx)) {
r = -EFAULT;
goto err;
}
- r = vhost_get_used(vq, last_used_idx, &vq->used->idx);
+ r = vhost_get_used_idx(vq, &last_used_idx);
if (r) {
vq_err(vq, "Can't access used idx at %p\n",
&vq->used->idx);
@@ -1947,9 +2037,9 @@
static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
struct iovec iov[], int iov_size, int access)
{
- const struct vhost_umem_node *node;
+ const struct vhost_iotlb_map *map;
struct vhost_dev *dev = vq->dev;
- struct vhost_umem *umem = dev->iotlb ? dev->iotlb : dev->umem;
+ struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
struct iovec *_iov;
u64 s = 0;
int ret = 0;
@@ -1961,25 +2051,24 @@
break;
}
- node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
- addr, addr + len - 1);
- if (node == NULL || node->start > addr) {
+ map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+ if (map == NULL || map->start > addr) {
if (umem != dev->iotlb) {
ret = -EFAULT;
break;
}
ret = -EAGAIN;
break;
- } else if (!(node->perm & access)) {
+ } else if (!(map->perm & access)) {
ret = -EPERM;
break;
}
_iov = iov + ret;
- size = node->size - addr + node->start;
+ size = map->size - addr + map->start;
_iov->iov_len = min((u64)len - s, size);
_iov->iov_base = (void __user *)(unsigned long)
- (node->userspace_addr + addr - node->start);
+ (map->addr + addr - map->start);
s += size;
addr += size;
++ret;
@@ -2035,11 +2124,6 @@
return ret;
}
iov_iter_init(&from, READ, vq->indirect, ret, len);
-
- /* We will use the result as an address to read from, so most
- * architectures only need a compiler barrier here. */
- read_barrier_depends();
-
count = len / sizeof desc;
/* Buffers are chained via a 16 bit next field, so
* we can have at most 2^16 of these. */
@@ -2128,7 +2212,7 @@
last_avail_idx = vq->last_avail_idx;
if (vq->avail_idx == vq->last_avail_idx) {
- if (unlikely(vhost_get_avail(vq, avail_idx, &vq->avail->idx))) {
+ if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
vq_err(vq, "Failed to access avail idx at %p\n",
&vq->avail->idx);
return -EFAULT;
@@ -2155,8 +2239,7 @@
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
- if (unlikely(vhost_get_avail(vq, ring_head,
- &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
+ if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) {
vq_err(vq, "Failed to read head: idx %d address %p\n",
last_avail_idx,
&vq->avail->ring[last_avail_idx % vq->num]);
@@ -2191,8 +2274,7 @@
i, vq->num, head);
return -EINVAL;
}
- ret = vhost_copy_from_user(vq, &desc, vq->desc + i,
- sizeof desc);
+ ret = vhost_get_desc(vq, &desc, i);
if (unlikely(ret)) {
vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
i, vq->desc + i);
@@ -2279,22 +2361,13 @@
struct vring_used_elem *heads,
unsigned count)
{
- struct vring_used_elem __user *used;
+ vring_used_elem_t __user *used;
u16 old, new;
int start;
start = vq->last_used_idx & (vq->num - 1);
used = vq->used->ring + start;
- if (count == 1) {
- if (vhost_put_user(vq, heads[0].id, &used->id)) {
- vq_err(vq, "Failed to write used id");
- return -EFAULT;
- }
- if (vhost_put_user(vq, heads[0].len, &used->len)) {
- vq_err(vq, "Failed to write used len");
- return -EFAULT;
- }
- } else if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) {
+ if (vhost_put_used(vq, heads, start, count)) {
vq_err(vq, "Failed to write used");
return -EFAULT;
}
@@ -2336,8 +2409,7 @@
/* Make sure buffer is written before we update index. */
smp_wmb();
- if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
- &vq->used->idx)) {
+ if (vhost_put_used_idx(vq)) {
vq_err(vq, "Failed to increment used idx");
return -EFAULT;
}
@@ -2370,7 +2442,7 @@
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
__virtio16 flags;
- if (vhost_get_avail(vq, flags, &vq->avail->flags)) {
+ if (vhost_get_avail_flags(vq, &flags)) {
vq_err(vq, "Failed to get flags");
return true;
}
@@ -2384,7 +2456,7 @@
if (unlikely(!v))
return true;
- if (vhost_get_avail(vq, event, vhost_used_event(vq))) {
+ if (vhost_get_used_event(vq, &event)) {
vq_err(vq, "Failed to get used event idx");
return true;
}
@@ -2395,8 +2467,8 @@
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
/* Signal the Guest tell them we used something up. */
- if (vq->call_ctx && vhost_notify(dev, vq))
- eventfd_signal(vq->call_ctx, 1);
+ if (vq->call_ctx.ctx && vhost_notify(dev, vq))
+ eventfd_signal(vq->call_ctx.ctx, 1);
}
EXPORT_SYMBOL_GPL(vhost_signal);
@@ -2429,7 +2501,7 @@
if (vq->avail_idx != vq->last_avail_idx)
return false;
- r = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
+ r = vhost_get_avail_idx(vq, &avail_idx);
if (unlikely(r))
return false;
vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
@@ -2465,7 +2537,7 @@
/* They could have slipped one in as we were doing that: make
* sure it's written, then check again. */
smp_mb();
- r = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
+ r = vhost_get_avail_idx(vq, &avail_idx);
if (r) {
vq_err(vq, "Failed to check avail idx at %p: %d\n",
&vq->avail->idx, r);
@@ -2487,7 +2559,7 @@
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
r = vhost_update_used_flags(vq);
if (r)
- vq_err(vq, "Failed to enable notification at %p: %d\n",
+ vq_err(vq, "Failed to disable notification at %p: %d\n",
&vq->used->flags, r);
}
}
@@ -2536,6 +2608,21 @@
}
EXPORT_SYMBOL_GPL(vhost_dequeue_msg);
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features)
+{
+ struct vhost_virtqueue *vq;
+ int i;
+
+ mutex_lock(&dev->mutex);
+ for (i = 0; i < dev->nvqs; ++i) {
+ vq = dev->vqs[i];
+ mutex_lock(&vq->mutex);
+ vq->acked_backend_features = features;
+ mutex_unlock(&vq->mutex);
+ }
+ mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(vhost_set_backend_features);
static int __init vhost_init(void)
{
--
Gitblit v1.6.2