diff options
Diffstat (limited to 'drivers/vhost/vringh.c')
| -rw-r--r-- | drivers/vhost/vringh.c | 807 |
1 files changed, 648 insertions, 159 deletions
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 5174ebac288d..925858cc6096 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1,8 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Helpers for the host side of a virtio ring. * * Since these may be in userspace, we use (inline) accessors. */ +#include <linux/compiler.h> #include <linux/module.h> #include <linux/vringh.h> #include <linux/virtio_ring.h> @@ -11,6 +13,12 @@ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/export.h> +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) +#include <linux/bvec.h> +#include <linux/highmem.h> +#include <linux/vhost_iotlb.h> +#endif +#include <uapi/linux/virtio_config.h> static __printf(1,2) __cold void vringh_bad(const char *fmt, ...) { @@ -28,13 +36,14 @@ static __printf(1,2) __cold void vringh_bad(const char *fmt, ...) /* Returns vring->num if empty, -ve on error. */ static inline int __vringh_get_head(const struct vringh *vrh, - int (*getu16)(u16 *val, const u16 *p), + int (*getu16)(const struct vringh *vrh, + u16 *val, const __virtio16 *p), u16 *last_avail_idx) { u16 avail_idx, i, head; int err; - err = getu16(&avail_idx, &vrh->vring.avail->idx); + err = getu16(vrh, &avail_idx, &vrh->vring.avail->idx); if (err) { vringh_bad("Failed to access avail idx at %p", &vrh->vring.avail->idx); @@ -49,7 +58,7 @@ static inline int __vringh_get_head(const struct vringh *vrh, i = *last_avail_idx & (vrh->vring.num - 1); - err = getu16(&head, &vrh->vring.avail->ring[i]); + err = getu16(vrh, &head, &vrh->vring.avail->ring[i]); if (err) { vringh_bad("Failed to read head: idx %d address %p", *last_avail_idx, &vrh->vring.avail->ring[i]); @@ -66,10 +75,40 @@ static inline int __vringh_get_head(const struct vringh *vrh, return head; } +/** + * vringh_kiov_advance - skip bytes from vring_kiov + * @iov: an iov passed to vringh_getdesc_*() (updated as we consume) + * @len: the maximum length to advance + */ +void vringh_kiov_advance(struct vringh_kiov *iov, size_t len) +{ + while (len && iov->i < iov->used) { + size_t partlen = min(iov->iov[iov->i].iov_len, len); + + iov->consumed += partlen; + iov->iov[iov->i].iov_len -= partlen; + iov->iov[iov->i].iov_base += partlen; + + if (!iov->iov[iov->i].iov_len) { + /* Fix up old iov element then increment. */ + iov->iov[iov->i].iov_len = iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + + iov->consumed = 0; + iov->i++; + } + + len -= partlen; + } +} +EXPORT_SYMBOL(vringh_kiov_advance); + /* Copy some bytes to/from the iovec. Returns num copied. */ -static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, +static inline ssize_t vringh_iov_xfer(struct vringh *vrh, + struct vringh_kiov *iov, void *ptr, size_t len, - int (*xfer)(void *addr, void *ptr, + int (*xfer)(const struct vringh *vrh, + void *addr, void *ptr, size_t len)) { int err, done = 0; @@ -78,7 +117,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, size_t partlen; partlen = min(iov->iov[iov->i].iov_len, len); - err = xfer(iov->iov[iov->i].iov_base, ptr, partlen); + err = xfer(vrh, iov->iov[iov->i].iov_base, ptr, partlen); if (err) return err; done += partlen; @@ -92,7 +131,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov, /* Fix up old iov element then increment. */ iov->iov[iov->i].iov_len = iov->consumed; iov->iov[iov->i].iov_base -= iov->consumed; - + iov->consumed = 0; iov->i++; } @@ -144,28 +183,32 @@ static inline bool no_range_check(struct vringh *vrh, u64 addr, size_t *len, } /* No reason for this code to be inline. */ -static int move_to_indirect(int *up_next, u16 *i, void *addr, +static int move_to_indirect(const struct vringh *vrh, + int *up_next, u16 *i, void *addr, const struct vring_desc *desc, struct vring_desc **descs, int *desc_max) { + u32 len; + /* Indirect tables can't have indirect. */ if (*up_next != -1) { vringh_bad("Multilevel indirect %u->%u", *up_next, *i); return -EINVAL; } - if (unlikely(desc->len % sizeof(struct vring_desc))) { + len = vringh32_to_cpu(vrh, desc->len); + if (unlikely(len % sizeof(struct vring_desc))) { vringh_bad("Strange indirect len %u", desc->len); return -EINVAL; } /* We will check this when we follow it! */ - if (desc->flags & VRING_DESC_F_NEXT) - *up_next = desc->next; + if (desc->flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT)) + *up_next = vringh16_to_cpu(vrh, desc->next); else *up_next = -2; *descs = addr; - *desc_max = desc->len / sizeof(struct vring_desc); + *desc_max = len / sizeof(struct vring_desc); /* Now, start at the first indirect. */ *i = 0; @@ -182,9 +225,9 @@ static int resize_iovec(struct vringh_kiov *iov, gfp_t gfp) flag = (iov->max_num & VRINGH_IOV_ALLOCATED); if (flag) - new = krealloc(iov->iov, new_num * sizeof(struct iovec), gfp); + new = krealloc_array(iov->iov, new_num, sizeof(*new), gfp); else { - new = kmalloc(new_num * sizeof(struct iovec), gfp); + new = kmalloc_array(new_num, sizeof(*new), gfp); if (new) { memcpy(new, iov->iov, iov->max_num * sizeof(struct iovec)); @@ -219,7 +262,8 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src, u64 addr, struct vringh_range *r), struct vringh_range *range, - int (*copy)(void *dst, const void *src, size_t len)) + int (*copy)(const struct vringh *vrh, + void *dst, const void *src, size_t len)) { size_t part, len = sizeof(struct vring_desc); @@ -233,7 +277,7 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src, if (!rcheck(vrh, addr, &part, range, getrange)) return -EINVAL; - err = copy(dst, src, part); + err = copy(vrh, dst, src, part); if (err) return err; @@ -254,9 +298,10 @@ __vringh_iov(struct vringh *vrh, u16 i, struct vringh_range *)), bool (*getrange)(struct vringh *, u64, struct vringh_range *), gfp_t gfp, - int (*copy)(void *dst, const void *src, size_t len)) + int (*copy)(const struct vringh *vrh, + void *dst, const void *src, size_t len)) { - int err, count = 0, up_next, desc_max; + int err, count = 0, indirect_count = 0, up_next, desc_max; struct vring_desc desc, *descs; struct vringh_range range = { -1ULL, 0 }, slowrange; bool slow = false; @@ -266,13 +311,14 @@ __vringh_iov(struct vringh *vrh, u16 i, desc_max = vrh->vring.num; up_next = -1; + /* You must want something! */ + if (WARN_ON(!riov && !wiov)) + return -EINVAL; + if (riov) - riov->i = riov->used = 0; - else if (wiov) - wiov->i = wiov->used = 0; - else - /* You must want something! */ - BUG(); + riov->i = riov->used = riov->consumed = 0; + if (wiov) + wiov->i = wiov->used = wiov->consumed = 0; for (;;) { void *addr; @@ -283,43 +329,51 @@ __vringh_iov(struct vringh *vrh, u16 i, err = slow_copy(vrh, &desc, &descs[i], rcheck, getrange, &slowrange, copy); else - err = copy(&desc, &descs[i], sizeof(desc)); + err = copy(vrh, &desc, &descs[i], sizeof(desc)); if (unlikely(err)) goto fail; - if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) { + if (unlikely(desc.flags & + cpu_to_vringh16(vrh, VRING_DESC_F_INDIRECT))) { + u64 a = vringh64_to_cpu(vrh, desc.addr); + /* Make sure it's OK, and get offset. */ - len = desc.len; - if (!rcheck(vrh, desc.addr, &len, &range, getrange)) { + len = vringh32_to_cpu(vrh, desc.len); + if (!rcheck(vrh, a, &len, &range, getrange)) { err = -EINVAL; goto fail; } - if (unlikely(len != desc.len)) { + if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) { slow = true; /* We need to save this range to use offset */ slowrange = range; } - addr = (void *)(long)(desc.addr + range.offset); - err = move_to_indirect(&up_next, &i, addr, &desc, + addr = (void *)(long)(a + range.offset); + err = move_to_indirect(vrh, &up_next, &i, addr, &desc, &descs, &desc_max); if (err) goto fail; continue; } - if (count++ == vrh->vring.num) { + if (up_next == -1) + count++; + else + indirect_count++; + + if (count > vrh->vring.num || indirect_count > desc_max) { vringh_bad("Descriptor loop in %p", descs); err = -ELOOP; goto fail; } - if (desc.flags & VRING_DESC_F_WRITE) + if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_WRITE)) iov = wiov; else { iov = riov; - if (unlikely(wiov && wiov->i)) { + if (unlikely(wiov && wiov->used)) { vringh_bad("Readable desc %p after writable", &descs[i]); err = -EINVAL; @@ -336,12 +390,14 @@ __vringh_iov(struct vringh *vrh, u16 i, again: /* Make sure it's OK, and get offset. */ - len = desc.len; - if (!rcheck(vrh, desc.addr, &len, &range, getrange)) { + len = vringh32_to_cpu(vrh, desc.len); + if (!rcheck(vrh, vringh64_to_cpu(vrh, desc.addr), &len, &range, + getrange)) { err = -EINVAL; goto fail; } - addr = (void *)(unsigned long)(desc.addr + range.offset); + addr = (void *)(unsigned long)(vringh64_to_cpu(vrh, desc.addr) + + range.offset); if (unlikely(iov->used == (iov->max_num & ~VRINGH_IOV_ALLOCATED))) { err = resize_iovec(iov, gfp); @@ -353,20 +409,23 @@ __vringh_iov(struct vringh *vrh, u16 i, iov->iov[iov->used].iov_len = len; iov->used++; - if (unlikely(len != desc.len)) { - desc.len -= len; - desc.addr += len; + if (unlikely(len != vringh32_to_cpu(vrh, desc.len))) { + desc.len = cpu_to_vringh32(vrh, + vringh32_to_cpu(vrh, desc.len) - len); + desc.addr = cpu_to_vringh64(vrh, + vringh64_to_cpu(vrh, desc.addr) + len); goto again; } - if (desc.flags & VRING_DESC_F_NEXT) { - i = desc.next; + if (desc.flags & cpu_to_vringh16(vrh, VRING_DESC_F_NEXT)) { + i = vringh16_to_cpu(vrh, desc.next); } else { /* Just in case we need to finish traversing above. */ if (unlikely(up_next > 0)) { i = return_from_indirect(vrh, &up_next, &descs, &desc_max); slow = false; + indirect_count = 0; } else break; } @@ -387,8 +446,10 @@ fail: static inline int __vringh_complete(struct vringh *vrh, const struct vring_used_elem *used, unsigned int num_used, - int (*putu16)(u16 *p, u16 val), - int (*putused)(struct vring_used_elem *dst, + int (*putu16)(const struct vringh *vrh, + __virtio16 *p, u16 val), + int (*putused)(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned num)) { @@ -404,12 +465,12 @@ static inline int __vringh_complete(struct vringh *vrh, /* Compiler knows num_used == 1 sometimes, hence extra check */ if (num_used > 1 && unlikely(off + num_used >= vrh->vring.num)) { u16 part = vrh->vring.num - off; - err = putused(&used_ring->ring[off], used, part); + err = putused(vrh, &used_ring->ring[off], used, part); if (!err) - err = putused(&used_ring->ring[0], used + part, + err = putused(vrh, &used_ring->ring[0], used + part, num_used - part); } else - err = putused(&used_ring->ring[off], used, num_used); + err = putused(vrh, &used_ring->ring[off], used, num_used); if (err) { vringh_bad("Failed to write %u used entries %u at %p", @@ -420,7 +481,7 @@ static inline int __vringh_complete(struct vringh *vrh, /* Make sure buffer is written before we update index. */ virtio_wmb(vrh->weak_barriers); - err = putu16(&vrh->vring.used->idx, used_idx + num_used); + err = putu16(vrh, &vrh->vring.used->idx, used_idx + num_used); if (err) { vringh_bad("Failed to update used index at %p", &vrh->vring.used->idx); @@ -433,7 +494,9 @@ static inline int __vringh_complete(struct vringh *vrh, static inline int __vringh_need_notify(struct vringh *vrh, - int (*getu16)(u16 *val, const u16 *p)) + int (*getu16)(const struct vringh *vrh, + u16 *val, + const __virtio16 *p)) { bool notify; u16 used_event; @@ -447,7 +510,7 @@ static inline int __vringh_need_notify(struct vringh *vrh, /* Old-style, without event indices. */ if (!vrh->event_indices) { u16 flags; - err = getu16(&flags, &vrh->vring.avail->flags); + err = getu16(vrh, &flags, &vrh->vring.avail->flags); if (err) { vringh_bad("Failed to get flags at %p", &vrh->vring.avail->flags); @@ -457,7 +520,7 @@ static inline int __vringh_need_notify(struct vringh *vrh, } /* Modern: we know when other side wants to know. */ - err = getu16(&used_event, &vring_used_event(&vrh->vring)); + err = getu16(vrh, &used_event, &vring_used_event(&vrh->vring)); if (err) { vringh_bad("Failed to get used event idx at %p", &vring_used_event(&vrh->vring)); @@ -478,20 +541,22 @@ static inline int __vringh_need_notify(struct vringh *vrh, } static inline bool __vringh_notify_enable(struct vringh *vrh, - int (*getu16)(u16 *val, const u16 *p), - int (*putu16)(u16 *p, u16 val)) + int (*getu16)(const struct vringh *vrh, + u16 *val, const __virtio16 *p), + int (*putu16)(const struct vringh *vrh, + __virtio16 *p, u16 val)) { u16 avail; if (!vrh->event_indices) { /* Old-school; update flags. */ - if (putu16(&vrh->vring.used->flags, 0) != 0) { + if (putu16(vrh, &vrh->vring.used->flags, 0) != 0) { vringh_bad("Clearing used flags %p", &vrh->vring.used->flags); return true; } } else { - if (putu16(&vring_avail_event(&vrh->vring), + if (putu16(vrh, &vring_avail_event(&vrh->vring), vrh->last_avail_idx) != 0) { vringh_bad("Updating avail event index %p", &vring_avail_event(&vrh->vring)); @@ -503,7 +568,7 @@ static inline bool __vringh_notify_enable(struct vringh *vrh, * sure it's written, then check again. */ virtio_mb(vrh->weak_barriers); - if (getu16(&avail, &vrh->vring.avail->idx) != 0) { + if (getu16(vrh, &avail, &vrh->vring.avail->idx) != 0) { vringh_bad("Failed to check avail idx at %p", &vrh->vring.avail->idx); return true; @@ -516,11 +581,13 @@ static inline bool __vringh_notify_enable(struct vringh *vrh, } static inline void __vringh_notify_disable(struct vringh *vrh, - int (*putu16)(u16 *p, u16 val)) + int (*putu16)(const struct vringh *vrh, + __virtio16 *p, u16 val)) { if (!vrh->event_indices) { /* Old-school; update flags. */ - if (putu16(&vrh->vring.used->flags, VRING_USED_F_NO_NOTIFY)) { + if (putu16(vrh, &vrh->vring.used->flags, + VRING_USED_F_NO_NOTIFY)) { vringh_bad("Setting used flags %p", &vrh->vring.used->flags); } @@ -528,23 +595,29 @@ static inline void __vringh_notify_disable(struct vringh *vrh, } /* Userspace access helpers: in this case, addresses are really userspace. */ -static inline int getu16_user(u16 *val, const u16 *p) +static inline int getu16_user(const struct vringh *vrh, u16 *val, const __virtio16 *p) { - return get_user(*val, (__force u16 __user *)p); + __virtio16 v = 0; + int rc = get_user(v, (__force __virtio16 __user *)p); + *val = vringh16_to_cpu(vrh, v); + return rc; } -static inline int putu16_user(u16 *p, u16 val) +static inline int putu16_user(const struct vringh *vrh, __virtio16 *p, u16 val) { - return put_user(val, (__force u16 __user *)p); + __virtio16 v = cpu_to_vringh16(vrh, val); + return put_user(v, (__force __virtio16 __user *)p); } -static inline int copydesc_user(void *dst, const void *src, size_t len) +static inline int copydesc_user(const struct vringh *vrh, + void *dst, const void *src, size_t len) { return copy_from_user(dst, (__force void __user *)src, len) ? -EFAULT : 0; } -static inline int putused_user(struct vring_used_elem *dst, +static inline int putused_user(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned int num) { @@ -552,13 +625,15 @@ static inline int putused_user(struct vring_used_elem *dst, sizeof(*dst) * num) ? -EFAULT : 0; } -static inline int xfer_from_user(void *src, void *dst, size_t len) +static inline int xfer_from_user(const struct vringh *vrh, void *src, + void *dst, size_t len) { return copy_from_user(dst, (__force void __user *)src, len) ? -EFAULT : 0; } -static inline int xfer_to_user(void *dst, void *src, size_t len) +static inline int xfer_to_user(const struct vringh *vrh, + void *dst, void *src, size_t len) { return copy_to_user((__force void __user *)dst, src, len) ? -EFAULT : 0; @@ -570,18 +645,18 @@ static inline int xfer_to_user(void *dst, void *src, size_t len) * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid: you should check pointers * yourself! */ -int vringh_init_user(struct vringh *vrh, u32 features, +int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - 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) { /* Sane power of 2 please! */ if (!num || num > 0xffff || (num & (num - 1))) { @@ -589,6 +664,7 @@ int vringh_init_user(struct vringh *vrh, u32 features, return -EINVAL; } + vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1)); vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX)); vrh->weak_barriers = weak_barriers; vrh->completed = 0; @@ -618,7 +694,10 @@ EXPORT_SYMBOL(vringh_init_user); * *head will be vrh->vring.num. You may be able to ignore an invalid * descriptor, but there's not much you can do with an invalid ring. * - * Note that you may need to clean up riov and wiov, even on error! + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_iov_cleanup() to release the memory, even on error! */ int vringh_getdesc_user(struct vringh *vrh, struct vringh_iov *riov, @@ -679,7 +758,7 @@ EXPORT_SYMBOL(vringh_getdesc_user); */ ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len) { - return vringh_iov_xfer((struct vringh_kiov *)riov, + return vringh_iov_xfer(NULL, (struct vringh_kiov *)riov, dst, len, xfer_from_user); } EXPORT_SYMBOL(vringh_iov_pull_user); @@ -687,7 +766,7 @@ EXPORT_SYMBOL(vringh_iov_pull_user); /** * vringh_iov_push_user - copy bytes into vring_iov. * @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume) - * @dst: the place to copy. + * @src: the place to copy from. * @len: the maximum length to copy. * * Returns the bytes copied <= len or a negative errno. @@ -695,28 +774,12 @@ EXPORT_SYMBOL(vringh_iov_pull_user); ssize_t vringh_iov_push_user(struct vringh_iov *wiov, const void *src, size_t len) { - return vringh_iov_xfer((struct vringh_kiov *)wiov, + return vringh_iov_xfer(NULL, (struct vringh_kiov *)wiov, (void *)src, len, xfer_to_user); } EXPORT_SYMBOL(vringh_iov_push_user); /** - * vringh_abandon_user - we've decided not to handle the descriptor(s). - * @vrh: the vring. - * @num: the number of descriptors to put back (ie. num - * vringh_get_user() to undo). - * - * The next vringh_get_user() will return the old descriptor(s) again. - */ -void vringh_abandon_user(struct vringh *vrh, unsigned int num) -{ - /* We only update vring_avail_event(vr) when we want to be notified, - * so we haven't changed that yet. */ - vrh->last_avail_idx -= num; -} -EXPORT_SYMBOL(vringh_abandon_user); - -/** * vringh_complete_user - we've finished with descriptor, publish it. * @vrh: the vring. * @head: the head as filled in by vringh_getdesc_user. @@ -729,8 +792,8 @@ int vringh_complete_user(struct vringh *vrh, u16 head, u32 len) { struct vring_used_elem used; - used.id = head; - used.len = len; + used.id = cpu_to_vringh32(vrh, head); + used.len = cpu_to_vringh32(vrh, len); return __vringh_complete(vrh, &used, 1, putu16_user, putused_user); } EXPORT_SYMBOL(vringh_complete_user); @@ -792,25 +855,28 @@ int vringh_need_notify_user(struct vringh *vrh) EXPORT_SYMBOL(vringh_need_notify_user); /* Kernelspace access helpers. */ -static inline int getu16_kern(u16 *val, const u16 *p) +static inline int getu16_kern(const struct vringh *vrh, + u16 *val, const __virtio16 *p) { - *val = ACCESS_ONCE(*p); + *val = vringh16_to_cpu(vrh, READ_ONCE(*p)); return 0; } -static inline int putu16_kern(u16 *p, u16 val) +static inline int putu16_kern(const struct vringh *vrh, __virtio16 *p, u16 val) { - ACCESS_ONCE(*p) = val; + WRITE_ONCE(*p, cpu_to_vringh16(vrh, val)); return 0; } -static inline int copydesc_kern(void *dst, const void *src, size_t len) +static inline int copydesc_kern(const struct vringh *vrh, + void *dst, const void *src, size_t len) { memcpy(dst, src, len); return 0; } -static inline int putused_kern(struct vring_used_elem *dst, +static inline int putused_kern(const struct vringh *vrh, + struct vring_used_elem *dst, const struct vring_used_elem *src, unsigned int num) { @@ -818,25 +884,19 @@ static inline int putused_kern(struct vring_used_elem *dst, return 0; } -static inline int xfer_kern(void *src, void *dst, size_t len) -{ - memcpy(dst, src, len); - return 0; -} - /** * vringh_init_kern - initialize a vringh for a kernelspace vring. * @vrh: the vringh to initialize. * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid. */ -int vringh_init_kern(struct vringh *vrh, u32 features, +int vringh_init_kern(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, struct vring_desc *desc, struct vring_avail *avail, @@ -848,6 +908,7 @@ int vringh_init_kern(struct vringh *vrh, u32 features, return -EINVAL; } + vrh->little_endian = (features & (1ULL << VIRTIO_F_VERSION_1)); vrh->event_indices = (features & (1 << VIRTIO_RING_F_EVENT_IDX)); vrh->weak_barriers = weak_barriers; vrh->completed = 0; @@ -876,7 +937,10 @@ EXPORT_SYMBOL(vringh_init_kern); * *head will be vrh->vring.num. You may be able to ignore an invalid * descriptor, but there's not much you can do with an invalid ring. * - * Note that you may need to clean up riov and wiov, even on error! + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_kiov_cleanup() to release the memory, even on error! */ int vringh_getdesc_kern(struct vringh *vrh, struct vringh_kiov *riov, @@ -905,51 +969,6 @@ int vringh_getdesc_kern(struct vringh *vrh, EXPORT_SYMBOL(vringh_getdesc_kern); /** - * vringh_iov_pull_kern - copy bytes from vring_iov. - * @riov: the riov as passed to vringh_getdesc_kern() (updated as we consume) - * @dst: the place to copy. - * @len: the maximum length to copy. - * - * Returns the bytes copied <= len or a negative errno. - */ -ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len) -{ - return vringh_iov_xfer(riov, dst, len, xfer_kern); -} -EXPORT_SYMBOL(vringh_iov_pull_kern); - -/** - * vringh_iov_push_kern - copy bytes into vring_iov. - * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume) - * @dst: the place to copy. - * @len: the maximum length to copy. - * - * Returns the bytes copied <= len or a negative errno. - */ -ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, - const void *src, size_t len) -{ - return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern); -} -EXPORT_SYMBOL(vringh_iov_push_kern); - -/** - * vringh_abandon_kern - we've decided not to handle the descriptor(s). - * @vrh: the vring. - * @num: the number of descriptors to put back (ie. num - * vringh_get_kern() to undo). - * - * The next vringh_get_kern() will return the old descriptor(s) again. - */ -void vringh_abandon_kern(struct vringh *vrh, unsigned int num) -{ - /* We only update vring_avail_event(vr) when we want to be notified, - * so we haven't changed that yet. */ - vrh->last_avail_idx -= num; -} -EXPORT_SYMBOL(vringh_abandon_kern); - -/** * vringh_complete_kern - we've finished with descriptor, publish it. * @vrh: the vring. * @head: the head as filled in by vringh_getdesc_kern. @@ -962,8 +981,8 @@ int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len) { struct vring_used_elem used; - used.id = head; - used.len = len; + used.id = cpu_to_vringh32(vrh, head); + used.len = cpu_to_vringh32(vrh, len); return __vringh_complete(vrh, &used, 1, putu16_kern, putused_kern); } @@ -1007,4 +1026,474 @@ int vringh_need_notify_kern(struct vringh *vrh) } EXPORT_SYMBOL(vringh_need_notify_kern); +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) + +struct iotlb_vec { + union { + struct iovec *iovec; + struct bio_vec *bvec; + } iov; + size_t count; +}; + +static int iotlb_translate(const struct vringh *vrh, + u64 addr, u64 len, u64 *translated, + struct iotlb_vec *ivec, u32 perm) +{ + struct vhost_iotlb_map *map; + struct vhost_iotlb *iotlb = vrh->iotlb; + int ret = 0; + u64 s = 0, last = addr + len - 1; + + spin_lock(vrh->iotlb_lock); + + while (len > s) { + uintptr_t io_addr; + size_t io_len; + u64 size; + + if (unlikely(ret >= ivec->count)) { + ret = -ENOBUFS; + break; + } + + map = vhost_iotlb_itree_first(iotlb, addr, last); + if (!map || map->start > addr) { + ret = -EINVAL; + break; + } else if (!(map->perm & perm)) { + ret = -EPERM; + break; + } + + size = map->size - addr + map->start; + io_len = min(len - s, size); + io_addr = map->addr - map->start + addr; + + if (vrh->use_va) { + struct iovec *iovec = ivec->iov.iovec; + + iovec[ret].iov_len = io_len; + iovec[ret].iov_base = (void __user *)io_addr; + } else { + u64 pfn = io_addr >> PAGE_SHIFT; + struct bio_vec *bvec = ivec->iov.bvec; + + bvec_set_page(&bvec[ret], pfn_to_page(pfn), io_len, + io_addr & (PAGE_SIZE - 1)); + } + + s += size; + addr += size; + ++ret; + } + + spin_unlock(vrh->iotlb_lock); + + if (translated) + *translated = min(len, s); + + return ret; +} + +#define IOTLB_IOV_STRIDE 16 + +static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, + void *src, size_t len) +{ + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; + u64 total_translated = 0; + + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + + while (total_translated < len) { + struct iov_iter iter; + u64 translated; + int ret; + size_t size; + + ret = iotlb_translate(vrh, (u64)(uintptr_t)src, + len - total_translated, &translated, + &ivec, VHOST_MAP_RO); + if (ret == -ENOBUFS) + ret = IOTLB_IOV_STRIDE; + else if (ret < 0) + return ret; + + if (vrh->use_va) { + iov_iter_init(&iter, ITER_SOURCE, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_SOURCE, ivec.iov.bvec, ret, + translated); + } + + size = copy_from_iter(dst, translated, &iter); + if (size != translated) + return -EFAULT; + + src += translated; + dst += translated; + total_translated += translated; + } + + return total_translated; +} + +static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, + void *src, size_t len) +{ + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; + u64 total_translated = 0; + + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + + while (total_translated < len) { + struct iov_iter iter; + u64 translated; + int ret; + size_t size; + + ret = iotlb_translate(vrh, (u64)(uintptr_t)dst, + len - total_translated, &translated, + &ivec, VHOST_MAP_WO); + if (ret == -ENOBUFS) + ret = IOTLB_IOV_STRIDE; + else if (ret < 0) + return ret; + + if (vrh->use_va) { + iov_iter_init(&iter, ITER_DEST, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_DEST, ivec.iov.bvec, ret, + translated); + } + + size = copy_to_iter(src, translated, &iter); + if (size != translated) + return -EFAULT; + + src += translated; + dst += translated; + total_translated += translated; + } + + return total_translated; +} + +static inline int getu16_iotlb(const struct vringh *vrh, + u16 *val, const __virtio16 *p) +{ + struct iotlb_vec ivec; + union { + struct iovec iovec[1]; + struct bio_vec bvec[1]; + } iov; + __virtio16 tmp; + int ret; + + ivec.iov.iovec = iov.iovec; + ivec.count = 1; + + /* Atomic read is needed for getu16 */ + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); + if (ret < 0) + return ret; + + if (vrh->use_va) { + ret = __get_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + __virtio16 *from = bvec_kmap_local(&ivec.iov.bvec[0]); + + tmp = READ_ONCE(*from); + kunmap_local(from); + } + + *val = vringh16_to_cpu(vrh, tmp); + + return 0; +} + +static inline int putu16_iotlb(const struct vringh *vrh, + __virtio16 *p, u16 val) +{ + struct iotlb_vec ivec; + union { + struct iovec iovec; + struct bio_vec bvec; + } iov; + __virtio16 tmp; + int ret; + + ivec.iov.iovec = &iov.iovec; + ivec.count = 1; + + /* Atomic write is needed for putu16 */ + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); + if (ret < 0) + return ret; + + tmp = cpu_to_vringh16(vrh, val); + + if (vrh->use_va) { + ret = __put_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + __virtio16 *to = bvec_kmap_local(&ivec.iov.bvec[0]); + + WRITE_ONCE(*to, tmp); + kunmap_local(to); + } + + return 0; +} + +static inline int copydesc_iotlb(const struct vringh *vrh, + void *dst, const void *src, size_t len) +{ + int ret; + + ret = copy_from_iotlb(vrh, dst, (void *)src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int xfer_from_iotlb(const struct vringh *vrh, void *src, + void *dst, size_t len) +{ + int ret; + + ret = copy_from_iotlb(vrh, dst, src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int xfer_to_iotlb(const struct vringh *vrh, + void *dst, void *src, size_t len) +{ + int ret; + + ret = copy_to_iotlb(vrh, dst, src, len); + if (ret != len) + return -EFAULT; + + return 0; +} + +static inline int putused_iotlb(const struct vringh *vrh, + struct vring_used_elem *dst, + const struct vring_used_elem *src, + unsigned int num) +{ + int size = num * sizeof(*dst); + int ret; + + ret = copy_to_iotlb(vrh, dst, (void *)src, num * sizeof(*dst)); + if (ret != size) + return -EFAULT; + + return 0; +} + +/** + * vringh_init_iotlb - initialize a vringh for a ring with IOTLB. + * @vrh: the vringh to initialize. + * @features: the feature bits for this ring. + * @num: the number of elements. + * @weak_barriers: true if we only need memory barriers, not I/O. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. + * + * Returns an error if num is invalid. + */ +int vringh_init_iotlb(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used) +{ + vrh->use_va = false; + + return vringh_init_kern(vrh, features, num, weak_barriers, + desc, avail, used); +} +EXPORT_SYMBOL(vringh_init_iotlb); + +/** + * vringh_init_iotlb_va - initialize a vringh for a ring with IOTLB containing + * user VA. + * @vrh: the vringh to initialize. + * @features: the feature bits for this ring. + * @num: the number of elements. + * @weak_barriers: true if we only need memory barriers, not I/O. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. + * + * Returns an error if num is invalid. + */ +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used) +{ + vrh->use_va = true; + + return vringh_init_kern(vrh, features, num, weak_barriers, + desc, avail, used); +} +EXPORT_SYMBOL(vringh_init_iotlb_va); + +/** + * vringh_set_iotlb - initialize a vringh for a ring with IOTLB. + * @vrh: the vring + * @iotlb: iotlb associated with this vring + * @iotlb_lock: spinlock to synchronize the iotlb accesses + */ +void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb, + spinlock_t *iotlb_lock) +{ + vrh->iotlb = iotlb; + vrh->iotlb_lock = iotlb_lock; +} +EXPORT_SYMBOL(vringh_set_iotlb); + +/** + * vringh_getdesc_iotlb - get next available descriptor from ring with + * IOTLB. + * @vrh: the kernelspace vring. + * @riov: where to put the readable descriptors (or NULL) + * @wiov: where to put the writable descriptors (or NULL) + * @head: head index we received, for passing to vringh_complete_iotlb(). + * @gfp: flags for allocating larger riov/wiov. + * + * Returns 0 if there was no descriptor, 1 if there was, or -errno. + * + * Note that on error return, you can tell the difference between an + * invalid ring and a single invalid descriptor: in the former case, + * *head will be vrh->vring.num. You may be able to ignore an invalid + * descriptor, but there's not much you can do with an invalid ring. + * + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_kiov_cleanup() to release the memory, even on error! + */ +int vringh_getdesc_iotlb(struct vringh *vrh, + struct vringh_kiov *riov, + struct vringh_kiov *wiov, + u16 *head, + gfp_t gfp) +{ + int err; + + err = __vringh_get_head(vrh, getu16_iotlb, &vrh->last_avail_idx); + if (err < 0) + return err; + + /* Empty... */ + if (err == vrh->vring.num) + return 0; + + *head = err; + err = __vringh_iov(vrh, *head, riov, wiov, no_range_check, NULL, + gfp, copydesc_iotlb); + if (err) + return err; + + return 1; +} +EXPORT_SYMBOL(vringh_getdesc_iotlb); + +/** + * vringh_iov_pull_iotlb - copy bytes from vring_iov. + * @vrh: the vring. + * @riov: the riov as passed to vringh_getdesc_iotlb() (updated as we consume) + * @dst: the place to copy. + * @len: the maximum length to copy. + * + * Returns the bytes copied <= len or a negative errno. + */ +ssize_t vringh_iov_pull_iotlb(struct vringh *vrh, + struct vringh_kiov *riov, + void *dst, size_t len) +{ + return vringh_iov_xfer(vrh, riov, dst, len, xfer_from_iotlb); +} +EXPORT_SYMBOL(vringh_iov_pull_iotlb); + +/** + * vringh_iov_push_iotlb - copy bytes into vring_iov. + * @vrh: the vring. + * @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume) + * @src: the place to copy from. + * @len: the maximum length to copy. + * + * Returns the bytes copied <= len or a negative errno. + */ +ssize_t vringh_iov_push_iotlb(struct vringh *vrh, + struct vringh_kiov *wiov, + const void *src, size_t len) +{ + return vringh_iov_xfer(vrh, wiov, (void *)src, len, xfer_to_iotlb); +} +EXPORT_SYMBOL(vringh_iov_push_iotlb); + +/** + * vringh_complete_iotlb - we've finished with descriptor, publish it. + * @vrh: the vring. + * @head: the head as filled in by vringh_getdesc_iotlb. + * @len: the length of data we have written. + * + * You should check vringh_need_notify_iotlb() after one or more calls + * to this function. + */ +int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len) +{ + struct vring_used_elem used; + + used.id = cpu_to_vringh32(vrh, head); + used.len = cpu_to_vringh32(vrh, len); + + return __vringh_complete(vrh, &used, 1, putu16_iotlb, putused_iotlb); +} +EXPORT_SYMBOL(vringh_complete_iotlb); + +/** + * vringh_need_notify_iotlb - must we tell the other side about used buffers? + * @vrh: the vring we've called vringh_complete_iotlb() on. + * + * Returns -errno or 0 if we don't need to tell the other side, 1 if we do. + */ +int vringh_need_notify_iotlb(struct vringh *vrh) +{ + return __vringh_need_notify(vrh, getu16_iotlb); +} +EXPORT_SYMBOL(vringh_need_notify_iotlb); + +#endif + +MODULE_DESCRIPTION("host side of a virtio ring"); MODULE_LICENSE("GPL"); |