Message ID | 20200507143201.31080-3-eric.auger@redhat.com |
---|---|
State | New |
Headers | show |
Series | VIRTIO-IOMMU probe request support and MSI bypass on ARM | expand |
Hi, Eric, On Thu, May 07, 2020 at 04:31:58PM +0200, Eric Auger wrote: [...] > @@ -452,17 +520,33 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) > case VIRTIO_IOMMU_T_UNMAP: > tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); > break; > + case VIRTIO_IOMMU_T_PROBE: > + { > + struct virtio_iommu_req_tail *ptail; > + uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail)); > + > + ptail = (struct virtio_iommu_req_tail *) > + (buf + s->config.probe_size); > + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); > + > + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, > + buf, s->config.probe_size + sizeof(tail)); > + g_free(buf); > + assert(sz == s->config.probe_size + sizeof(tail)); > + goto push; > + } > default: > tail.status = VIRTIO_IOMMU_S_UNSUPP; > } > - qemu_mutex_unlock(&s->mutex); > > out: > sz = iov_from_buf(elem->in_sg, elem->in_num, 0, > &tail, sizeof(tail)); > assert(sz == sizeof(tail)); > > - virtqueue_push(vq, elem, sizeof(tail)); > +push: > + qemu_mutex_unlock(&s->mutex); I think we can't move this unlock to here because otherwise "goto out" could potentially try to unlock it without locked first. Thanks, > + virtqueue_push(vq, elem, sz); > virtio_notify(vdev, vq); > g_free(elem); > }
Hi Peter, On 5/7/20 9:40 PM, Peter Xu wrote: > Hi, Eric, > > On Thu, May 07, 2020 at 04:31:58PM +0200, Eric Auger wrote: > > [...] > >> @@ -452,17 +520,33 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) >> case VIRTIO_IOMMU_T_UNMAP: >> tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); >> break; >> + case VIRTIO_IOMMU_T_PROBE: >> + { >> + struct virtio_iommu_req_tail *ptail; >> + uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail)); >> + >> + ptail = (struct virtio_iommu_req_tail *) >> + (buf + s->config.probe_size); >> + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); >> + >> + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, >> + buf, s->config.probe_size + sizeof(tail)); >> + g_free(buf); >> + assert(sz == s->config.probe_size + sizeof(tail)); >> + goto push; >> + } >> default: >> tail.status = VIRTIO_IOMMU_S_UNSUPP; >> } >> - qemu_mutex_unlock(&s->mutex); >> >> out: >> sz = iov_from_buf(elem->in_sg, elem->in_num, 0, >> &tail, sizeof(tail)); >> assert(sz == sizeof(tail)); >> >> - virtqueue_push(vq, elem, sizeof(tail)); >> +push: >> + qemu_mutex_unlock(&s->mutex); > > I think we can't move this unlock to here because otherwise "goto out" could > potentially try to unlock it without locked first. Thanks, You're right. I will revisit that. Thanks! Eric > >> + virtqueue_push(vq, elem, sz); >> virtio_notify(vdev, vq); >> g_free(elem); >> } >
On Thu, May 07, 2020 at 04:31:58PM +0200, Eric Auger wrote: > +static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep, > + uint8_t *buf, size_t free) > +{ > + struct virtio_iommu_probe_resv_mem prop = {}; > + size_t size = sizeof(prop), length = size - sizeof(prop.head), total; > + int i; > + > + total = size * s->nb_reserved_regions; > + > + if (total > free) { > + return -ENOSPC; > + } > + > + for (i = 0; i < s->nb_reserved_regions; i++) { > + prop.head.type = VIRTIO_IOMMU_PROBE_T_RESV_MEM; cpu_to_le16 > + prop.head.length = cpu_to_le64(length); same here > + prop.subtype = cpu_to_le64(s->reserved_regions[i].type); and subtype is a byte > + prop.start = cpu_to_le64(s->reserved_regions[i].low); > + prop.end = cpu_to_le64(s->reserved_regions[i].high); > + > + memcpy(buf, &prop, size); > + > + trace_virtio_iommu_fill_resv_property(ep, prop.subtype, > + prop.start, prop.end); > + buf += size; > + } > + return total; > +} > + > +/** > + * virtio_iommu_probe - Fill the probe request buffer with > + * the properties the device is able to return and add a NONE > + * property at the end. > + */ > +static int virtio_iommu_probe(VirtIOIOMMU *s, > + struct virtio_iommu_req_probe *req, > + uint8_t *buf) > +{ > + uint32_t ep_id = le32_to_cpu(req->endpoint); I think we should check that the endpoint ID is sane even if we're not using it at the moment (it is a SHOULD in the spec, and the page size mask patch will need the ep anyway). > + struct virtio_iommu_probe_property last = {}; > + size_t free = VIOMMU_PROBE_SIZE - sizeof(last); last isn't needed, you can fill the whole probe buffer with valid properties > + ssize_t count; > + > + count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free); > + if (count < 0) { > + return VIRTIO_IOMMU_S_INVAL; indentation? Thanks, Jean > + } > + buf += count; > + free -= count; > + > + /* Fill the rest with zeroes */ > + memset(buf, 0, free); > + > + return VIRTIO_IOMMU_S_OK; > +} > + > static int virtio_iommu_iov_to_req(struct iovec *iov, > unsigned int iov_cnt, > void *req, size_t req_sz) > @@ -407,6 +464,17 @@ virtio_iommu_handle_req(detach) > virtio_iommu_handle_req(map) > virtio_iommu_handle_req(unmap) > > +static int virtio_iommu_handle_probe(VirtIOIOMMU *s, > + struct iovec *iov, > + unsigned int iov_cnt, > + uint8_t *buf) > +{ > + struct virtio_iommu_req_probe req; > + int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); > + > + return ret ? ret : virtio_iommu_probe(s, &req, buf); > +} > + > static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) > { > VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); > @@ -452,17 +520,33 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) > case VIRTIO_IOMMU_T_UNMAP: > tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); > break; > + case VIRTIO_IOMMU_T_PROBE: > + { > + struct virtio_iommu_req_tail *ptail; > + uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail)); > + > + ptail = (struct virtio_iommu_req_tail *) > + (buf + s->config.probe_size); > + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); > + > + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, > + buf, s->config.probe_size + sizeof(tail)); > + g_free(buf); > + assert(sz == s->config.probe_size + sizeof(tail)); > + goto push; > + } > default: > tail.status = VIRTIO_IOMMU_S_UNSUPP; > } > - qemu_mutex_unlock(&s->mutex); > > out: > sz = iov_from_buf(elem->in_sg, elem->in_num, 0, > &tail, sizeof(tail)); > assert(sz == sizeof(tail)); > > - virtqueue_push(vq, elem, sizeof(tail)); > +push: > + qemu_mutex_unlock(&s->mutex); > + virtqueue_push(vq, elem, sz); > virtio_notify(vdev, vq); > g_free(elem); > } > @@ -667,6 +751,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) > s->config.page_size_mask = TARGET_PAGE_MASK; > s->config.input_range.end = -1UL; > s->config.domain_range.end = 32; > + s->config.probe_size = VIOMMU_PROBE_SIZE; > > virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX); > virtio_add_feature(&s->features, VIRTIO_RING_F_INDIRECT_DESC); > @@ -676,6 +761,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) > virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP); > virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS); > virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO); > + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); > > qemu_mutex_init(&s->mutex); > > diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events > index e83500bee9..5550475691 100644 > --- a/hw/virtio/trace-events > +++ b/hw/virtio/trace-events > @@ -73,3 +73,4 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d" > virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d" > virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d" > virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64 > +virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64 > -- > 2.20.1 >
Hi Jean, On 5/8/20 11:26 AM, Jean-Philippe Brucker wrote: > On Thu, May 07, 2020 at 04:31:58PM +0200, Eric Auger wrote: >> +static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep, >> + uint8_t *buf, size_t free) >> +{ >> + struct virtio_iommu_probe_resv_mem prop = {}; >> + size_t size = sizeof(prop), length = size - sizeof(prop.head), total; >> + int i; >> + >> + total = size * s->nb_reserved_regions; >> + >> + if (total > free) { >> + return -ENOSPC; >> + } >> + >> + for (i = 0; i < s->nb_reserved_regions; i++) { >> + prop.head.type = VIRTIO_IOMMU_PROBE_T_RESV_MEM; > > cpu_to_le16 > >> + prop.head.length = cpu_to_le64(length); > > same here > >> + prop.subtype = cpu_to_le64(s->reserved_regions[i].type); > > and subtype is a byte All fixed. Thanks for spotting this. > >> + prop.start = cpu_to_le64(s->reserved_regions[i].low); >> + prop.end = cpu_to_le64(s->reserved_regions[i].high); >> + >> + memcpy(buf, &prop, size); >> + >> + trace_virtio_iommu_fill_resv_property(ep, prop.subtype, >> + prop.start, prop.end); >> + buf += size; >> + } >> + return total; >> +} >> + >> +/** >> + * virtio_iommu_probe - Fill the probe request buffer with >> + * the properties the device is able to return and add a NONE >> + * property at the end. >> + */ >> +static int virtio_iommu_probe(VirtIOIOMMU *s, >> + struct virtio_iommu_req_probe *req, >> + uint8_t *buf) >> +{ >> + uint32_t ep_id = le32_to_cpu(req->endpoint); > > I think we should check that the endpoint ID is sane even if we're not > using it at the moment (it is a SHOULD in the spec, and the page size mask > patch will need the ep anyway). OK > >> + struct virtio_iommu_probe_property last = {}; >> + size_t free = VIOMMU_PROBE_SIZE - sizeof(last); > > last isn't needed, you can fill the whole probe buffer with valid > properties yep. This is a reminder from none prop. > >> + ssize_t count; >> + >> + count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free); >> + if (count < 0) { >> + return VIRTIO_IOMMU_S_INVAL; > > indentation? yes. Thank you for the review Eric > > Thanks, > Jean > >> + } >> + buf += count; >> + free -= count; >> + >> + /* Fill the rest with zeroes */ >> + memset(buf, 0, free); >> + >> + return VIRTIO_IOMMU_S_OK; >> +} >> + >> static int virtio_iommu_iov_to_req(struct iovec *iov, >> unsigned int iov_cnt, >> void *req, size_t req_sz) >> @@ -407,6 +464,17 @@ virtio_iommu_handle_req(detach) >> virtio_iommu_handle_req(map) >> virtio_iommu_handle_req(unmap) >> >> +static int virtio_iommu_handle_probe(VirtIOIOMMU *s, >> + struct iovec *iov, >> + unsigned int iov_cnt, >> + uint8_t *buf) >> +{ >> + struct virtio_iommu_req_probe req; >> + int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); >> + >> + return ret ? ret : virtio_iommu_probe(s, &req, buf); >> +} >> + >> static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) >> { >> VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); >> @@ -452,17 +520,33 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) >> case VIRTIO_IOMMU_T_UNMAP: >> tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); >> break; >> + case VIRTIO_IOMMU_T_PROBE: >> + { >> + struct virtio_iommu_req_tail *ptail; >> + uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail)); >> + >> + ptail = (struct virtio_iommu_req_tail *) >> + (buf + s->config.probe_size); >> + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); >> + >> + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, >> + buf, s->config.probe_size + sizeof(tail)); >> + g_free(buf); >> + assert(sz == s->config.probe_size + sizeof(tail)); >> + goto push; >> + } >> default: >> tail.status = VIRTIO_IOMMU_S_UNSUPP; >> } >> - qemu_mutex_unlock(&s->mutex); >> >> out: >> sz = iov_from_buf(elem->in_sg, elem->in_num, 0, >> &tail, sizeof(tail)); >> assert(sz == sizeof(tail)); >> >> - virtqueue_push(vq, elem, sizeof(tail)); >> +push: >> + qemu_mutex_unlock(&s->mutex); >> + virtqueue_push(vq, elem, sz); >> virtio_notify(vdev, vq); >> g_free(elem); >> } >> @@ -667,6 +751,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) >> s->config.page_size_mask = TARGET_PAGE_MASK; >> s->config.input_range.end = -1UL; >> s->config.domain_range.end = 32; >> + s->config.probe_size = VIOMMU_PROBE_SIZE; >> >> virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX); >> virtio_add_feature(&s->features, VIRTIO_RING_F_INDIRECT_DESC); >> @@ -676,6 +761,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) >> virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP); >> virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS); >> virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO); >> + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); >> >> qemu_mutex_init(&s->mutex); >> >> diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events >> index e83500bee9..5550475691 100644 >> --- a/hw/virtio/trace-events >> +++ b/hw/virtio/trace-events >> @@ -73,3 +73,4 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d" >> virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d" >> virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d" >> virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64 >> +virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64 >> -- >> 2.20.1 >> >
diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h index e653004d7c..49eb105cd8 100644 --- a/include/hw/virtio/virtio-iommu.h +++ b/include/hw/virtio/virtio-iommu.h @@ -53,6 +53,8 @@ typedef struct VirtIOIOMMU { GHashTable *as_by_busptr; IOMMUPciBus *iommu_pcibus_by_bus_num[PCI_BUS_MAX]; PCIBus *primary_bus; + ReservedRegion *reserved_regions; + uint32_t nb_reserved_regions; GTree *domains; QemuMutex mutex; GTree *endpoints; diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index 22ba8848c2..95059eff70 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -38,6 +38,7 @@ /* Max size */ #define VIOMMU_DEFAULT_QUEUE_SIZE 256 +#define VIOMMU_PROBE_SIZE 512 typedef struct VirtIOIOMMUDomain { uint32_t id; @@ -378,6 +379,62 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s, return ret; } +static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep, + uint8_t *buf, size_t free) +{ + struct virtio_iommu_probe_resv_mem prop = {}; + size_t size = sizeof(prop), length = size - sizeof(prop.head), total; + int i; + + total = size * s->nb_reserved_regions; + + if (total > free) { + return -ENOSPC; + } + + for (i = 0; i < s->nb_reserved_regions; i++) { + prop.head.type = VIRTIO_IOMMU_PROBE_T_RESV_MEM; + prop.head.length = cpu_to_le64(length); + prop.subtype = cpu_to_le64(s->reserved_regions[i].type); + prop.start = cpu_to_le64(s->reserved_regions[i].low); + prop.end = cpu_to_le64(s->reserved_regions[i].high); + + memcpy(buf, &prop, size); + + trace_virtio_iommu_fill_resv_property(ep, prop.subtype, + prop.start, prop.end); + buf += size; + } + return total; +} + +/** + * virtio_iommu_probe - Fill the probe request buffer with + * the properties the device is able to return and add a NONE + * property at the end. + */ +static int virtio_iommu_probe(VirtIOIOMMU *s, + struct virtio_iommu_req_probe *req, + uint8_t *buf) +{ + uint32_t ep_id = le32_to_cpu(req->endpoint); + struct virtio_iommu_probe_property last = {}; + size_t free = VIOMMU_PROBE_SIZE - sizeof(last); + ssize_t count; + + count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free); + if (count < 0) { + return VIRTIO_IOMMU_S_INVAL; + } + buf += count; + free -= count; + + /* Fill the rest with zeroes */ + memset(buf, 0, free); + + return VIRTIO_IOMMU_S_OK; +} + static int virtio_iommu_iov_to_req(struct iovec *iov, unsigned int iov_cnt, void *req, size_t req_sz) @@ -407,6 +464,17 @@ virtio_iommu_handle_req(detach) virtio_iommu_handle_req(map) virtio_iommu_handle_req(unmap) +static int virtio_iommu_handle_probe(VirtIOIOMMU *s, + struct iovec *iov, + unsigned int iov_cnt, + uint8_t *buf) +{ + struct virtio_iommu_req_probe req; + int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req)); + + return ret ? ret : virtio_iommu_probe(s, &req, buf); +} + static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) { VirtIOIOMMU *s = VIRTIO_IOMMU(vdev); @@ -452,17 +520,33 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq) case VIRTIO_IOMMU_T_UNMAP: tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt); break; + case VIRTIO_IOMMU_T_PROBE: + { + struct virtio_iommu_req_tail *ptail; + uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail)); + + ptail = (struct virtio_iommu_req_tail *) + (buf + s->config.probe_size); + ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf); + + sz = iov_from_buf(elem->in_sg, elem->in_num, 0, + buf, s->config.probe_size + sizeof(tail)); + g_free(buf); + assert(sz == s->config.probe_size + sizeof(tail)); + goto push; + } default: tail.status = VIRTIO_IOMMU_S_UNSUPP; } - qemu_mutex_unlock(&s->mutex); out: sz = iov_from_buf(elem->in_sg, elem->in_num, 0, &tail, sizeof(tail)); assert(sz == sizeof(tail)); - virtqueue_push(vq, elem, sizeof(tail)); +push: + qemu_mutex_unlock(&s->mutex); + virtqueue_push(vq, elem, sz); virtio_notify(vdev, vq); g_free(elem); } @@ -667,6 +751,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) s->config.page_size_mask = TARGET_PAGE_MASK; s->config.input_range.end = -1UL; s->config.domain_range.end = 32; + s->config.probe_size = VIOMMU_PROBE_SIZE; virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX); virtio_add_feature(&s->features, VIRTIO_RING_F_INDIRECT_DESC); @@ -676,6 +761,7 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO); + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); qemu_mutex_init(&s->mutex); diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index e83500bee9..5550475691 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -73,3 +73,4 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d" virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d" virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d" virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64 +virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64