From cadb72854b44f53c07ea60d7a6149ccac5928a82 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 27 Oct 2020 12:02:15 -0400 Subject: [PATCH 02/18] libvhost-user: handle endianness as mandated by the spec RH-Author: Claudio Imbrenda Message-id: <20201027120217.2997314-2-cimbrend@redhat.com> Patchwork-id: 98723 O-Subject: [RHEL8.4 qemu-kvm PATCH 1/3] libvhost-user: handle endianness as mandated by the spec Bugzilla: 1857733 RH-Acked-by: Stefan Hajnoczi RH-Acked-by: Thomas Huth RH-Acked-by: Dr. David Alan Gilbert RH-Acked-by: Cornelia Huck From: Marc Hartmayer Since virtio existed even before it got standardized, the virtio standard defines the following types of virtio devices: + legacy device (pre-virtio 1.0) + non-legacy or VIRTIO 1.0 device + transitional device (which can act both as legacy and non-legacy) Virtio 1.0 defines the fields of the virtqueues as little endian, while legacy uses guest's native endian [1]. Currently libvhost-user does not handle virtio endianness at all, i.e. it works only if the native endianness matches with whatever is actually needed. That means things break spectacularly on big-endian targets. Let us handle virtio endianness for non-legacy as required by the virtio specification [1] and fence legacy virtio, as there is no safe way to figure out the needed endianness conversions for all cases. The fencing of legacy virtio devices is done in `vu_set_features_exec`. [1] https://docs.oasis-open.org/virtio/virtio/v1.1/cs01/virtio-v1.1-cs01.html#x1-210003 Reviewed-by: Michael S. Tsirkin Signed-off-by: Marc Hartmayer Message-id: 20200901150019.29229-3-mhartmay@linux.ibm.com Signed-off-by: Stefan Hajnoczi (cherry picked from commit 2ffc54708087c6e524297957be2fc5d543abb767) Signed-off-by: Danilo C. L. de Paula --- contrib/libvhost-user/libvhost-user.c | 77 +++++++++++++++------------ 1 file changed, 43 insertions(+), 34 deletions(-) diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c index b89bf185013..b8350b067e3 100644 --- a/contrib/libvhost-user/libvhost-user.c +++ b/contrib/libvhost-user/libvhost-user.c @@ -42,6 +42,7 @@ #include "qemu/atomic.h" #include "qemu/osdep.h" +#include "qemu/bswap.h" #include "qemu/memfd.h" #include "libvhost-user.h" @@ -522,6 +523,14 @@ vu_set_features_exec(VuDev *dev, VhostUserMsg *vmsg) DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64); dev->features = vmsg->payload.u64; + if (!vu_has_feature(dev, VIRTIO_F_VERSION_1)) { + /* + * We only support devices conforming to VIRTIO 1.0 or + * later + */ + vu_panic(dev, "virtio legacy devices aren't supported by libvhost-user"); + return false; + } if (!(dev->features & VHOST_USER_F_PROTOCOL_FEATURES)) { vu_set_enable_all_rings(dev, true); @@ -886,7 +895,7 @@ vu_set_vring_addr_exec(VuDev *dev, VhostUserMsg *vmsg) return false; } - vq->used_idx = vq->vring.used->idx; + vq->used_idx = lduw_le_p(&vq->vring.used->idx); if (vq->last_avail_idx != vq->used_idx) { bool resume = dev->iface->queue_is_processed_in_order && @@ -998,7 +1007,7 @@ vu_check_queue_inflights(VuDev *dev, VuVirtq *vq) return 0; } - vq->used_idx = vq->vring.used->idx; + vq->used_idx = lduw_le_p(&vq->vring.used->idx); vq->resubmit_num = 0; vq->resubmit_list = NULL; vq->counter = 0; @@ -1737,13 +1746,13 @@ vu_queue_started(const VuDev *dev, const VuVirtq *vq) static inline uint16_t vring_avail_flags(VuVirtq *vq) { - return vq->vring.avail->flags; + return lduw_le_p(&vq->vring.avail->flags); } static inline uint16_t vring_avail_idx(VuVirtq *vq) { - vq->shadow_avail_idx = vq->vring.avail->idx; + vq->shadow_avail_idx = lduw_le_p(&vq->vring.avail->idx); return vq->shadow_avail_idx; } @@ -1751,7 +1760,7 @@ vring_avail_idx(VuVirtq *vq) static inline uint16_t vring_avail_ring(VuVirtq *vq, int i) { - return vq->vring.avail->ring[i]; + return lduw_le_p(&vq->vring.avail->ring[i]); } static inline uint16_t @@ -1839,12 +1848,12 @@ virtqueue_read_next_desc(VuDev *dev, struct vring_desc *desc, int i, unsigned int max, unsigned int *next) { /* If this descriptor says it doesn't chain, we're done. */ - if (!(desc[i].flags & VRING_DESC_F_NEXT)) { + if (!(lduw_le_p(&desc[i].flags) & VRING_DESC_F_NEXT)) { return VIRTQUEUE_READ_DESC_DONE; } /* Check they're not leading us off end of descriptors. */ - *next = desc[i].next; + *next = lduw_le_p(&desc[i].next); /* Make sure compiler knows to grab that: we don't want it changing! */ smp_wmb(); @@ -1887,8 +1896,8 @@ vu_queue_get_avail_bytes(VuDev *dev, VuVirtq *vq, unsigned int *in_bytes, } desc = vq->vring.desc; - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - if (desc[i].len % sizeof(struct vring_desc)) { + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_INDIRECT) { + if (ldl_le_p(&desc[i].len) % sizeof(struct vring_desc)) { vu_panic(dev, "Invalid size for indirect buffer table"); goto err; } @@ -1901,8 +1910,8 @@ vu_queue_get_avail_bytes(VuDev *dev, VuVirtq *vq, unsigned int *in_bytes, /* loop over the indirect descriptor table */ indirect = 1; - desc_addr = desc[i].addr; - desc_len = desc[i].len; + desc_addr = ldq_le_p(&desc[i].addr); + desc_len = ldl_le_p(&desc[i].len); max = desc_len / sizeof(struct vring_desc); read_len = desc_len; desc = vu_gpa_to_va(dev, &read_len, desc_addr); @@ -1929,10 +1938,10 @@ vu_queue_get_avail_bytes(VuDev *dev, VuVirtq *vq, unsigned int *in_bytes, goto err; } - if (desc[i].flags & VRING_DESC_F_WRITE) { - in_total += desc[i].len; + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_WRITE) { + in_total += ldl_le_p(&desc[i].len); } else { - out_total += desc[i].len; + out_total += ldl_le_p(&desc[i].len); } if (in_total >= max_in_bytes && out_total >= max_out_bytes) { goto done; @@ -2047,7 +2056,7 @@ vring_used_flags_set_bit(VuVirtq *vq, int mask) flags = (uint16_t *)((char*)vq->vring.used + offsetof(struct vring_used, flags)); - *flags |= mask; + stw_le_p(flags, lduw_le_p(flags) | mask); } static inline void @@ -2057,7 +2066,7 @@ vring_used_flags_unset_bit(VuVirtq *vq, int mask) flags = (uint16_t *)((char*)vq->vring.used + offsetof(struct vring_used, flags)); - *flags &= ~mask; + stw_le_p(flags, lduw_le_p(flags) & ~mask); } static inline void @@ -2067,7 +2076,7 @@ vring_set_avail_event(VuVirtq *vq, uint16_t val) return; } - *((uint16_t *) &vq->vring.used->ring[vq->vring.num]) = val; + stw_le_p(&vq->vring.used->ring[vq->vring.num], val); } void @@ -2156,14 +2165,14 @@ vu_queue_map_desc(VuDev *dev, VuVirtq *vq, unsigned int idx, size_t sz) struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE]; int rc; - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - if (desc[i].len % sizeof(struct vring_desc)) { + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_INDIRECT) { + if (ldl_le_p(&desc[i].len) % sizeof(struct vring_desc)) { vu_panic(dev, "Invalid size for indirect buffer table"); } /* loop over the indirect descriptor table */ - desc_addr = desc[i].addr; - desc_len = desc[i].len; + desc_addr = ldq_le_p(&desc[i].addr); + desc_len = ldl_le_p(&desc[i].len); max = desc_len / sizeof(struct vring_desc); read_len = desc_len; desc = vu_gpa_to_va(dev, &read_len, desc_addr); @@ -2185,10 +2194,10 @@ vu_queue_map_desc(VuDev *dev, VuVirtq *vq, unsigned int idx, size_t sz) /* Collect all the descriptors */ do { - if (desc[i].flags & VRING_DESC_F_WRITE) { + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_WRITE) { virtqueue_map_desc(dev, &in_num, iov + out_num, VIRTQUEUE_MAX_SIZE - out_num, true, - desc[i].addr, desc[i].len); + ldq_le_p(&desc[i].addr), ldl_le_p(&desc[i].len)); } else { if (in_num) { vu_panic(dev, "Incorrect order for descriptors"); @@ -2196,7 +2205,7 @@ vu_queue_map_desc(VuDev *dev, VuVirtq *vq, unsigned int idx, size_t sz) } virtqueue_map_desc(dev, &out_num, iov, VIRTQUEUE_MAX_SIZE, false, - desc[i].addr, desc[i].len); + ldq_le_p(&desc[i].addr), ldl_le_p(&desc[i].len)); } /* If we've got too many, that implies a descriptor loop. */ @@ -2392,14 +2401,14 @@ vu_log_queue_fill(VuDev *dev, VuVirtq *vq, max = vq->vring.num; i = elem->index; - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - if (desc[i].len % sizeof(struct vring_desc)) { + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_INDIRECT) { + if (ldl_le_p(&desc[i].len) % sizeof(struct vring_desc)) { vu_panic(dev, "Invalid size for indirect buffer table"); } /* loop over the indirect descriptor table */ - desc_addr = desc[i].addr; - desc_len = desc[i].len; + desc_addr = ldq_le_p(&desc[i].addr); + desc_len = ldl_le_p(&desc[i].len); max = desc_len / sizeof(struct vring_desc); read_len = desc_len; desc = vu_gpa_to_va(dev, &read_len, desc_addr); @@ -2425,9 +2434,9 @@ vu_log_queue_fill(VuDev *dev, VuVirtq *vq, return; } - if (desc[i].flags & VRING_DESC_F_WRITE) { - min = MIN(desc[i].len, len); - vu_log_write(dev, desc[i].addr, min); + if (lduw_le_p(&desc[i].flags) & VRING_DESC_F_WRITE) { + min = MIN(ldl_le_p(&desc[i].len), len); + vu_log_write(dev, ldq_le_p(&desc[i].addr), min); len -= min; } @@ -2452,15 +2461,15 @@ vu_queue_fill(VuDev *dev, VuVirtq *vq, idx = (idx + vq->used_idx) % vq->vring.num; - uelem.id = elem->index; - uelem.len = len; + stl_le_p(&uelem.id, elem->index); + stl_le_p(&uelem.len, len); vring_used_write(dev, vq, &uelem, idx); } static inline void vring_used_idx_set(VuDev *dev, VuVirtq *vq, uint16_t val) { - vq->vring.used->idx = val; + stw_le_p(&vq->vring.used->idx, val); vu_log_write(dev, vq->vring.log_guest_addr + offsetof(struct vring_used, idx), sizeof(vq->vring.used->idx)); -- 2.27.0