vdpa net devices Rx filter change notification with Shadow VQ
v4 cover vdpa net devices Rx filter change notification with Shadow VQ
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support advanced configurations.
Rx filtering event is issues by qemu when device's MAC address changed once and the previous one has not been queried by external agents.
Shadow VirtQueue (SVQ) already makes possible tracking the state of virtqueues, effectively intercepting them so qemu can track what regions of memory are dirty because device action and needs migration. However, this does not solve networking device state seen by the driver because CVQ messages, like changes on MAC addresses from the driver.
This series uses SVQ infrastructure to intercept networking control messages used by the device. This way, qemu is able to update VirtIONet device model and react to them. In particular, this series enables rx filter change notification.
This is a prerequisite to achieve net vdpa device with CVQ live migration. It's a stripped down version of [1], with error paths checked and no migration enabled.
First nine patches reorder and clean code base so its easier to apply later ones. No functional change should be noticed from these changes.
Patches from 11 to 14 enable SVQ API to make other parts of qemu to interact with it. In particular, they will be used by vhost-vdpa net to handle CVQ messages.
Patches 15 to 17 enable the update of the virtio-net device model for each CVQ message acknowledged by the device.
Last patches enable x-svq parameter, forbidding device migration since it is not restored in the destination's vdpa device yet. This will be added in later series, using this work.
Comments are welcome.
v4:
- Add a timeout to vhost_svq_poll to not hold BQL forever
v3:
- Replace SVQElement with SVQDescState
v2:
- (Comments from series [1]).
- Active poll for CVQ answer instead of relay on async used callback
- Do not offer a new buffer to device but reuse qemu's
- Use vhost_svq_add instead of not needed vhost_svq_inject
- Delete used and detach callbacks, not needed anymore
- Embed members of SVQElement in VirtQueueElement
- Reuse the same buffers for all CVQ commands
[1] https://patchwork.kernel.org/project/qemu-devel/cover/[email protected]/
Eugenio Pérez (19):
vhost: move descriptor translation to vhost_svq_vring_write_descs
virtio-net: Expose MAC_TABLE_ENTRIES
virtio-net: Expose ctrl virtqueue logic
vhost: Reorder vhost_svq_kick
vhost: Move vhost_svq_kick call to vhost_svq_add
vhost: Check for queue full at vhost_svq_add
vhost: Decouple vhost_svq_add from VirtQueueElement
vhost: Add SVQDescState
vhost: Track number of descs in SVQDescState
vhost: add vhost_svq_push_elem
vhost: Expose vhost_svq_add
vhost: add vhost_svq_poll
vhost: Add svq avail_handler callback
vdpa: Export vhost_vdpa_dma_map and unmap calls
vdpa: manual forward CVQ buffers
vdpa: Buffer CVQ support on shadow virtqueue
vdpa: Extract get features part from vhost_vdpa_get_max_queue_pairs
vdpa: Add device migration blocker
vdpa: Add x-svq to NetdevVhostVDPAOptions
qapi/net.json | 9 +- hw/virtio/vhost-shadow-virtqueue.h | 52 ++++- include/hw/virtio/vhost-vdpa.h | 8 + include/hw/virtio/virtio-net.h | 7 + hw/net/virtio-net.c | 85 ++++--- hw/virtio/vhost-shadow-virtqueue.c | 207 ++++++++++++----- hw/virtio/vhost-vdpa.c | 25 +- net/vhost-vdpa.c | 357 +++++++++++++++++++++++++++-- 8 files changed, 632 insertions(+), 118 deletions(-)
Signature · 1 line
2.31.1
PATCH v4 1/19 vhost: move descriptor translation to vhost_svq_vring_write_descs
It's done for both in and out descriptors so it's better placed here.
--- hw/virtio/vhost-shadow-virtqueue.c | 38 +++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 11 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +27 -11
@@ -122,17 +122,35 @@ static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq,return true; } -static void vhost_vring_write_descs (VhostShadowVirtqueue *svq,hwaddr *sg, -const struct iovec *iovec,size_t num, -bool more_descs,bool write) +/** +* Write descriptors to SVQ vring +* +* @svq: The shadow virtqueue +* @sg: Cache for hwaddr +* @iovec: The iovec from the guest +* @num: iovec length +* @more_descs: True if more descriptors come in the chain +* @write: True if they are writeable descriptors +* +* Return true if success, false otherwise and print error. +*/ +static bool vhost_svq_vring_write_descs (VhostShadowVirtqueue *svq,hwaddr *sg, +const struct iovec *iovec,size_t num, +bool more_descs,bool write) {uint16_t i = svq->free_head, last = svq->free_head;unsigned n;uint16_t flags = write ?cpu_to_le16 (VRING_DESC_F_WRITE ) :0 ;vring_desc_t *descs = svq->vring.desc; +bool ok;if (num ==0 ) { -return ; +return true; + } + + ok =vhost_svq_translate_addr (svq, sg, iovec, num); +if (unlikely (!ok)) { +return false; }for (n =0 ; n < num; n++) {
@@ -150,6 +168,7 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, } svq->free_head =le16_to_cpu (svq->desc_next[last]); +return true; } static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
@@ -169,21 +188,18 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,return false; } - ok =vhost_svq_translate_addr (svq, sgs, elem->out_sg, elem->out_num); + ok =vhost_svq_vring_write_descs (svq, sgs, elem->out_sg, elem->out_num, + elem->in_num >0 , false);if (unlikely (!ok)) {return false; } -vhost_vring_write_descs (svq, sgs, elem->out_sg, elem->out_num, - elem->in_num >0 , false); - - ok =vhost_svq_translate_addr (svq, sgs, elem->in_sg, elem->in_num); + ok =vhost_svq_vring_write_descs (svq, sgs, elem->in_sg, elem->in_num, false, + true);if (unlikely (!ok)) {return false; } -vhost_vring_write_descs (svq, sgs, elem->in_sg, elem->in_num, false, true); -/* * Put the entry in the available array (but don't update avail->idx until * they do sync).
Signature · 1 line
2.31.1
PATCH v4 2/19 virtio-net: Expose MAC_TABLE_ENTRIES
In reply to Eugenio Pérezvhost-vdpa control virtqueue needs to know the maximum entries supported by the virtio-net device, so we know if it is possible to apply the filter.
--- include/hw/virtio/virtio-net.h | 3 +++ hw/net/virtio-net.c | 1 - 2 files changed, 3 insertions(+), 1 deletion(-)
include/hw/virtio/virtio-net.h +3 -0
@@ -35,6 +35,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET)* and latency. */ #define TX_BURST 256 +/* Maximum VIRTIO_NET_CTRL_MAC_TABLE_SET unicast + multicast entries. */ +#define MAC_TABLE_ENTRIES 64 + typedef struct virtio_net_conf { uint32_t txtimer;
hw/net/virtio-net.c +0 -1
@@ -49,7 +49,6 @@#define VIRTIO_NET_VM_VERSION 11 -#define MAC_TABLE_ENTRIES 64#define MAX_VLAN (1 << 12)/* Per 802.1Q definition */ /* previously fixed value */
Signature · 1 line
2.31.1
PATCH v4 3/19 virtio-net: Expose ctrl virtqueue logic
In reply to Eugenio PérezThis allows external vhost-net devices to modify the state of the VirtIO device model once the vhost-vdpa device has acknowledged the control commands.
--- include/hw/virtio/virtio-net.h | 4 ++ hw/net/virtio-net.c | 84 ++++++++++++++++++++-------------- 2 files changed, 53 insertions(+), 35 deletions(-)
include/hw/virtio/virtio-net.h +4 -0
@@ -221,6 +221,10 @@ struct VirtIONet {struct EBPFRSSContext ebpf_rss; }; +size_t virtio_net_handle_ctrl_iov (VirtIODevice *vdev, +const struct iovec *in_sg,unsigned in_num, +const struct iovec *out_sg, +unsigned out_num);void virtio_net_set_netclient_name (VirtIONet *n,const char *name,const char *type);
hw/net/virtio-net.c +49 -35
106 lines not on this page · raw message
Signature · 1 line
2.31.1
PATCH v4 4/19 vhost: Reorder vhost_svq_kick
In reply to Eugenio PérezFuture code needs to call it from vhost_svq_add.
No functional change intended.
--- hw/virtio/vhost-shadow-virtqueue.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +14 -14
@@ -215,6 +215,20 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,return true; } +static void vhost_svq_kick (VhostShadowVirtqueue *svq) +{ +/* +* We need to expose the available array entries before checking the used +* flags +*/ +smp_mb (); +if (svq->vring.used->flags &VRING_USED_F_NO_NOTIFY ) { +return ; + } + +event_notifier_set (&svq->hdev_kick); +} +/** * Add an element to a SVQ. *
@@ -235,20 +249,6 @@ static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem)return true; } -static void vhost_svq_kick (VhostShadowVirtqueue *svq) -{ -/* -* We need to expose the available array entries before checking the used -* flags -*/ -smp_mb (); -if (svq->vring.used->flags &VRING_USED_F_NO_NOTIFY ) { -return ; - } - -event_notifier_set (&svq->hdev_kick); -} -/** * Forward available buffers. *
Signature · 1 line
2.31.1
PATCH v4 5/19 vhost: Move vhost_svq_kick call to vhost_svq_add
In reply to Eugenio PérezThe series needs to expose vhost_svq_add with full functionality, including kick
--- hw/virtio/vhost-shadow-virtqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
hw/virtio/vhost-shadow-virtqueue.c +1 -1
@@ -246,6 +246,7 @@ static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem) } svq->ring_id_maps[qemu_head] = elem; +vhost_svq_kick (svq);return true; }
@@ -306,7 +307,6 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)/* VQ is broken, just return and ignore any other kicks */ return ; } -vhost_svq_kick (svq); }virtio_queue_set_notification (svq->vq, true);
Signature · 1 line
2.31.1
PATCH v4 6/19 vhost: Check for queue full at vhost_svq_add
In reply to Eugenio PérezThe series need to expose vhost_svq_add with full functionality, including checking for full queue.
--- hw/virtio/vhost-shadow-virtqueue.c | 59 +++++++++++++++++------------- 1 file changed, 33 insertions(+), 26 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +33 -26
@@ -233,21 +233,29 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq)* Add an element to a SVQ. * * The caller must check that there is enough slots for the new element. It -* takes ownership of the element: In case of failure, it is free and the SVQ -* is considered broken. +* takes ownership of the element: In case of failure not ENOSPC, it is free. +* +* Return -EINVAL if element is invalid, -ENOSPC if dev queue is full */ -static bool vhost_svq_add (VhostShadowVirtqueue *svq,VirtQueueElement *elem) +static int vhost_svq_add (VhostShadowVirtqueue *svq,VirtQueueElement *elem) {unsigned qemu_head; -bool ok =vhost_svq_add_split (svq, elem, &qemu_head); +unsigned ndescs = elem->in_num + elem->out_num; +bool ok; + +if (unlikely (ndescs >vhost_svq_available_slots (svq))) { +return -ENOSPC ; + } + + ok =vhost_svq_add_split (svq, elem, &qemu_head);if (unlikely (!ok)) {g_free (elem); -return false; +return -EINVAL ; } svq->ring_id_maps[qemu_head] = elem;vhost_svq_kick (svq); -return true; +return 0 ; }/**
@@ -274,7 +282,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)while (true) {VirtQueueElement *elem; -bool ok; +int r;if (svq->next_guest_avail_elem) { elem =g_steal_pointer (&svq->next_guest_avail_elem);
@@ -286,25 +294,24 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)break ; } -if (elem->out_num + elem->in_num >vhost_svq_available_slots (svq)) { -/* -* This condition is possible since a contiguous buffer in GPA -* does not imply a contiguous buffer in qemu's VA -* scatter-gather segments. If that happens, the buffer exposed -* to the device needs to be a chain of descriptors at this -* moment. -* -* SVQ cannot hold more available buffers if we are here: -* queue the current guest descriptor and ignore further kicks -* until some elements are used. -*/ - svq->next_guest_avail_elem = elem; -return ; - } - - ok =vhost_svq_add (svq, elem); -if (unlikely (!ok)) { -/* VQ is broken, just return and ignore any other kicks */ + r =vhost_svq_add (svq, elem); +if (unlikely (r !=0 )) { +if (r == -ENOSPC ) { +/* +* This condition is possible since a contiguous buffer in +* GPA does not imply a contiguous buffer in qemu's VA +* scatter-gather segments. If that happens, the buffer +* exposed to the device needs to be a chain of descriptors +* at this moment. +* +* SVQ cannot hold more available buffers if we are here: +* queue the current guest descriptor and ignore kicks +* until some elements are used. +*/ + svq->next_guest_avail_elem = elem; + } + +/* VQ is full or broken, just return and ignore kicks */ return ; } }
Signature · 1 line
2.31.1
PATCH v4 7/19 vhost: Decouple vhost_svq_add from VirtQueueElement
In reply to Eugenio PérezVirtQueueElement comes from the guest, but we're heading SVQ to be able to modify the element presented to the device without the guest's knowledge.
To do so, make SVQ accept sg buffers directly, instead of using VirtQueueElement.
Add vhost_svq_add_element to maintain element convenience.
--- hw/virtio/vhost-shadow-virtqueue.c | 33 ++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 11 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +22 -11
@@ -172,30 +172,31 @@ static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg, }static bool vhost_svq_add_split (VhostShadowVirtqueue *svq, -VirtQueueElement *elem,unsigned *head) +const struct iovec *out_sg,size_t out_num, +const struct iovec *in_sg,size_t in_num, +unsigned *head) {unsigned avail_idx;vring_avail_t *avail = svq->vring.avail;bool ok; - g_autofree hwaddr *sgs = g_new(hwaddr, MAX(elem->out_num, elem->in_num)); + g_autofree hwaddr *sgs = g_new(hwaddr, MAX(out_num, in_num)); *head = svq->free_head;/* We need some descriptors here */ -if (unlikely (!elem->out_num && !elem->in_num)) { +if (unlikely (!out_num && !in_num)) {qemu_log_mask (LOG_GUEST_ERROR ,"Guest provided element with no descriptors" );return false; } - ok =vhost_svq_vring_write_descs (svq, sgs, elem->out_sg, elem->out_num, - elem->in_num >0 , false); + ok =vhost_svq_vring_write_descs (svq, sgs, out_sg, out_num, in_num >0 , + false);if (unlikely (!ok)) {return false; } - ok =vhost_svq_vring_write_descs (svq, sgs, elem->in_sg, elem->in_num, false, - true); + ok =vhost_svq_vring_write_descs (svq, sgs, in_sg, in_num, false, true);if (unlikely (!ok)) {return false; }
@@ -237,17 +238,19 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq)* * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full */ -static int vhost_svq_add (VhostShadowVirtqueue *svq,VirtQueueElement *elem) +static int vhost_svq_add (VhostShadowVirtqueue *svq,const struct iovec *out_sg, +size_t out_num,const struct iovec *in_sg, +size_t in_num,VirtQueueElement *elem) {unsigned qemu_head; -unsigned ndescs = elem->in_num + elem->out_num; +unsigned ndescs = in_num + out_num;bool ok;if (unlikely (ndescs >vhost_svq_available_slots (svq))) {return -ENOSPC ; } - ok =vhost_svq_add_split (svq, elem, &qemu_head); + ok =vhost_svq_add_split (svq, out_sg, out_num, in_sg, in_num, &qemu_head);if (unlikely (!ok)) {g_free (elem);return -EINVAL ;
@@ -258,6 +261,14 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem)return 0 ; } +/* Convenience wrapper to add a guest's element to SVQ */ +static int vhost_svq_add_element (VhostShadowVirtqueue *svq, +VirtQueueElement *elem) +{ +return vhost_svq_add (svq, elem->out_sg, elem->out_num, elem->in_sg, + elem->in_num, elem); +} +/** * Forward available buffers. *
@@ -294,7 +305,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)break ; } - r =vhost_svq_add (svq, elem); + r =vhost_svq_add_element (svq, elem);if (unlikely (r !=0 )) {if (r == -ENOSPC ) {/*
Signature · 1 line
2.31.1
PATCH v4 8/19 vhost: Add SVQDescState
In reply to Eugenio PérezThis will allow SVQ to add context to the different queue elements.
This patch only store the actual element, no functional change intended.
--- hw/virtio/vhost-shadow-virtqueue.h | 8 ++++++-- hw/virtio/vhost-shadow-virtqueue.c | 16 ++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-)
hw/virtio/vhost-shadow-virtqueue.h +6 -2
@@ -15,6 +15,10 @@#include "standard-headers/linux/vhost_types.h" #include "hw/virtio/vhost-iova-tree.h" +typedef struct SVQDescState { +VirtQueueElement *elem; +}SVQDescState ; +/* Shadow virtqueue to relay notifications */ typedef struct VhostShadowVirtqueue { /* Shadow vring */
@@ -47,8 +51,8 @@ typedef struct VhostShadowVirtqueue {/* IOVA mapping */ VhostIOVATree *iova_tree; -/* Map for use the guest's descriptors */ -VirtQueueElement **ring_id_maps; +/* SVQ vring descriptors state */ +SVQDescState *desc_state;/* Next VirtQueue element that guest made available */ VirtQueueElement *next_guest_avail_elem;
hw/virtio/vhost-shadow-virtqueue.c +8 -8
@@ -256,7 +256,7 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,return -EINVAL ; } - svq->ring_id_maps[qemu_head] = elem; + svq->desc_state[qemu_head].elem = elem;vhost_svq_kick (svq);return 0 ; }
@@ -410,21 +410,21 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,return NULL ; } -if (unlikely (!svq->ring_id_maps[used_elem.id])) { +if (unlikely (!svq->desc_state[used_elem.id].elem)) {qemu_log_mask (LOG_GUEST_ERROR ,"Device %s says index %u is used, but it was not available" , svq->vdev->name, used_elem.id);return NULL ; } - num = svq->ring_id_maps[used_elem.id]->in_num + - svq->ring_id_maps[used_elem.id]->out_num; + num = svq->desc_state[used_elem.id].elem->in_num + + svq->desc_state[used_elem.id].elem->out_num; last_used_chain =vhost_svq_last_desc_of_chain (svq, num, used_elem.id); svq->desc_next[last_used_chain] = svq->free_head; svq->free_head = used_elem.id; *len = used_elem.len; -return g_steal_pointer (&svq->ring_id_maps[used_elem.id]); +return g_steal_pointer (&svq->desc_state[used_elem.id].elem); } static void vhost_svq_flush(VhostShadowVirtqueue *svq,
@@ -594,7 +594,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev,memset (svq->vring.desc,0 , driver_size); svq->vring.used =qemu_memalign (qemu_real_host_page_size (), device_size);memset (svq->vring.used,0 , device_size); - svq->ring_id_maps = g_new0(VirtQueueElement *, svq->vring.num); + svq->desc_state =g_new0 (SVQDescState, svq->vring.num); svq->desc_next =g_new0 (uint16_t, svq->vring.num);for (unsigned i =0 ; i < svq->vring.num -1 ; i++) { svq->desc_next[i] =cpu_to_le16 (i +1 );
@@ -619,7 +619,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)for (unsigned i =0 ; i < svq->vring.num; ++i) { g_autofree VirtQueueElement *elem = NULL; - elem =g_steal_pointer (&svq->ring_id_maps[i]); + elem =g_steal_pointer (&svq->desc_state[i].elem);if (elem) {virtqueue_detach_element (svq->vq, elem,0 ); }
@@ -631,7 +631,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq) } svq->vq =NULL ;g_free (svq->desc_next); -g_free (svq->ring_id_maps); +g_free (svq->desc_state);qemu_vfree (svq->vring.desc);qemu_vfree (svq->vring.used); }
Signature · 1 line
2.31.1
PATCH v4 9/19 vhost: Track number of descs in SVQDescState
In reply to Eugenio PérezA guest's buffer continuos on GPA may need multiple descriptors on qemu's VA, so SVQ should track its length sepparatedly.
--- hw/virtio/vhost-shadow-virtqueue.h | 6 ++++++ hw/virtio/vhost-shadow-virtqueue.c | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-)
hw/virtio/vhost-shadow-virtqueue.h +6 -0
@@ -17,6 +17,12 @@typedef struct SVQDescState {VirtQueueElement *elem; + +/* +* Number of descriptors exposed to the device. May or may not match +* guest's +*/ +unsigned int ndescs; }SVQDescState ;/* Shadow virtqueue to relay notifications */
hw/virtio/vhost-shadow-virtqueue.c +2 -2
@@ -257,6 +257,7 @@ static int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg, } svq->desc_state[qemu_head].elem = elem; + svq->desc_state[qemu_head].ndescs = ndescs;vhost_svq_kick (svq);return 0 ; }
@@ -417,8 +418,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,return NULL ; } - num = svq->desc_state[used_elem.id].elem->in_num + - svq->desc_state[used_elem.id].elem->out_num; + num = svq->desc_state[used_elem.id].ndescs; last_used_chain =vhost_svq_last_desc_of_chain (svq, num, used_elem.id); svq->desc_next[last_used_chain] = svq->free_head; svq->free_head = used_elem.id;
Signature · 1 line
2.31.1
PATCH v4 10/19 vhost: add vhost_svq_push_elem
In reply to Eugenio PérezThis function allows external SVQ users to return guest's available buffers.
--- hw/virtio/vhost-shadow-virtqueue.h | 3 +++ hw/virtio/vhost-shadow-virtqueue.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+)
hw/virtio/vhost-shadow-virtqueue.h +3 -0
@@ -84,6 +84,9 @@ typedef struct VhostShadowVirtqueue {bool vhost_svq_valid_features (uint64_t features,Error **errp); +void vhost_svq_push_elem (VhostShadowVirtqueue *svq, +const VirtQueueElement *elem,uint32_t len); +void vhost_svq_set_svq_kick_fd (VhostShadowVirtqueue *svq,int svq_kick_fd);void vhost_svq_set_svq_call_fd (VhostShadowVirtqueue *svq,int call_fd); void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq,
hw/virtio/vhost-shadow-virtqueue.c +16 -0
@@ -427,6 +427,22 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,return g_steal_pointer (&svq->desc_state[used_elem.id].elem); } +/** +* Push an element to SVQ, returning it to the guest. +*/ +void vhost_svq_push_elem (VhostShadowVirtqueue *svq, +const VirtQueueElement *elem,uint32_t len) +{ +virtqueue_push (svq->vq, elem, len); +if (svq->next_guest_avail_elem) { +/* +* Avail ring was full when vhost_svq_flush was called, so it's a +* good moment to make more descriptors available if possible. +*/ +vhost_handle_guest_kick (svq); + } +} +static void vhost_svq_flush (VhostShadowVirtqueue *svq,bool check_for_avail_queue) {
Signature · 1 line
2.31.1
PATCH v4 11/19 vhost: Expose vhost_svq_add
In reply to Eugenio PérezThis allows external parts of SVQ to forward custom buffers to the device.
--- hw/virtio/vhost-shadow-virtqueue.h | 3 +++ hw/virtio/vhost-shadow-virtqueue.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-)
hw/virtio/vhost-shadow-virtqueue.h +3 -0
@@ -86,6 +86,9 @@ bool vhost_svq_valid_features(uint64_t features, Error **errp);void vhost_svq_push_elem (VhostShadowVirtqueue *svq,const VirtQueueElement *elem,uint32_t len); +int vhost_svq_add (VhostShadowVirtqueue *svq,const struct iovec *out_sg, +size_t out_num,const struct iovec *in_sg,size_t in_num, +VirtQueueElement *elem);void vhost_svq_set_svq_kick_fd (VhostShadowVirtqueue *svq,int svq_kick_fd);void vhost_svq_set_svq_call_fd (VhostShadowVirtqueue *svq,int call_fd);
hw/virtio/vhost-shadow-virtqueue.c +3 -3
@@ -238,9 +238,9 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq)* * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full */ -static int vhost_svq_add (VhostShadowVirtqueue *svq,const struct iovec *out_sg, -size_t out_num,const struct iovec *in_sg, -size_t in_num,VirtQueueElement *elem) +int vhost_svq_add (VhostShadowVirtqueue *svq,const struct iovec *out_sg, +size_t out_num,const struct iovec *in_sg,size_t in_num, +VirtQueueElement *elem) {unsigned qemu_head;unsigned ndescs = in_num + out_num;
Signature · 1 line
2.31.1
PATCH v4 12/19 vhost: add vhost_svq_poll
In reply to Eugenio PérezIt allows the Shadow Control VirtQueue to wait for the device to use the available buffers.
--- hw/virtio/vhost-shadow-virtqueue.h | 1 + hw/virtio/vhost-shadow-virtqueue.c | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+)
hw/virtio/vhost-shadow-virtqueue.h +1 -0
@@ -89,6 +89,7 @@ void vhost_svq_push_elem(VhostShadowVirtqueue *svq,int vhost_svq_add (VhostShadowVirtqueue *svq,const struct iovec *out_sg,size_t out_num,const struct iovec *in_sg,size_t in_num,VirtQueueElement *elem); +size_t vhost_svq_poll (VhostShadowVirtqueue *svq);void vhost_svq_set_svq_kick_fd (VhostShadowVirtqueue *svq,int svq_kick_fd);void vhost_svq_set_svq_call_fd (VhostShadowVirtqueue *svq,int call_fd);
hw/virtio/vhost-shadow-virtqueue.c +27 -0
@@ -484,6 +484,33 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq, }while (!vhost_svq_enable_notification (svq)); } +/** +* Poll the SVQ for one device used buffer. +* +* This function race with main event loop SVQ polling, so extra +* synchronization is needed. +* +* Return the length written by the device. +*/ +size_t vhost_svq_poll (VhostShadowVirtqueue *svq) +{ +int64_t start_us =g_get_monotonic_time (); +do { +uint32_t len; +VirtQueueElement *elem =vhost_svq_get_buf (svq, &len); +if (elem) { +return len; + } + +if (unlikely (g_get_monotonic_time () - start_us >10e6 )) { +return 0 ; + } + +/* Make sure we read new used_idx */ +smp_rmb (); + }while (true); +} +/** * Forward used buffers. *
Signature · 1 line
2.31.1
PATCH v4 13/19 vhost: Add svq avail_handler callback
In reply to Eugenio PérezThis allows external handlers to be aware of new buffers that the guest places in the virtqueue.
When this callback is defined the ownership of the guest's virtqueue element is transferred to the callback. This means that if the user wants to forward the descriptor it needs to manually inject it. The callback is also free to process the command by itself and use the element with svq_push.
--- hw/virtio/vhost-shadow-virtqueue.h | 31 +++++++++++++++++++++++++++++- hw/virtio/vhost-shadow-virtqueue.c | 14 ++++++++++++-- hw/virtio/vhost-vdpa.c | 3 ++- 3 files changed, 44 insertions(+), 4 deletions(-)
hw/virtio/vhost-shadow-virtqueue.h +30 -1
@@ -25,6 +25,27 @@ typedef struct SVQDescState {unsigned int ndescs; } SVQDescState; +typedef struct VhostShadowVirtqueue VhostShadowVirtqueue ; + +/** +* Callback to handle an avail buffer. +* +* @svq: Shadow virtqueue +* @elem: Element placed in the queue by the guest +* @vq_callback_opaque: Opaque +* +* Returns 0 if the vq is running as expected. +* +* Note that ownership of elem is transferred to the callback. +*/ +typedef int (*VirtQueueAvailCallback )(VhostShadowVirtqueue *svq, +VirtQueueElement *elem, +void *vq_callback_opaque); + +typedef struct VhostShadowVirtqueueOps { +VirtQueueAvailCallback avail_handler; +}VhostShadowVirtqueueOps ; +/* Shadow virtqueue to relay notifications */ typedef struct VhostShadowVirtqueue { /* Shadow vring */
@@ -69,6 +90,12 @@ typedef struct VhostShadowVirtqueue {*/ uint16_t *desc_next; +/* Caller callbacks */ +const VhostShadowVirtqueueOps *ops; + +/* Caller callbacks opaque */ +void *ops_opaque; +/* Next head to expose to the device */ uint16_t shadow_avail_idx;
@@ -102,7 +129,9 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev, VirtQueue *vq);void vhost_svq_stop (VhostShadowVirtqueue *svq); -VhostShadowVirtqueue *vhost_svq_new (VhostIOVATree *iova_tree); +VhostShadowVirtqueue *vhost_svq_new (VhostIOVATree *iova_tree, +const VhostShadowVirtqueueOps *ops, +void *ops_opaque);void vhost_svq_free (gpointer vq);G_DEFINE_AUTOPTR_CLEANUP_FUNC (VhostShadowVirtqueue, vhost_svq_free);
hw/virtio/vhost-shadow-virtqueue.c +12 -2
@@ -306,7 +306,11 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)break ; } - r =vhost_svq_add_element (svq, elem); +if (svq->ops) { + r = svq->ops->avail_handler (svq, elem, svq->ops_opaque); + }else { + r =vhost_svq_add_element (svq, elem); + }if (unlikely (r !=0 )) {if (r == -ENOSPC ) {/*
@@ -684,12 +688,16 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)* shadow methods and file descriptors. * * @iova_tree: Tree to perform descriptors translations +* @ops: SVQ owner callbacks +* @ops_opaque: ops opaque pointer * * Returns the new virtqueue or NULL. * * In case of error, reason is reported through error_report. */ -VhostShadowVirtqueue *vhost_svq_new (VhostIOVATree *iova_tree) +VhostShadowVirtqueue *vhost_svq_new (VhostIOVATree *iova_tree, +const VhostShadowVirtqueueOps *ops, +void *ops_opaque) { g_autofree VhostShadowVirtqueue *svq = g_new0(VhostShadowVirtqueue, 1);int r;
@@ -711,6 +719,8 @@ VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree)event_notifier_init_fd (&svq->svq_kick,VHOST_FILE_UNBIND );event_notifier_set_handler (&svq->hdev_call, vhost_svq_handle_call); svq->iova_tree = iova_tree; + svq->ops = ops; + svq->ops_opaque = ops_opaque;return g_steal_pointer (&svq); err_init_hdev_call:
hw/virtio/vhost-vdpa.c +2 -1
@@ -418,8 +418,9 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v, shadow_vqs =g_ptr_array_new_full (hdev->nvqs, vhost_svq_free);for (unsigned n =0 ; n < hdev->nvqs; ++n) { -g_autoptr (VhostShadowVirtqueue) svq =vhost_svq_new (v->iova_tree); +g_autoptr (VhostShadowVirtqueue) svq; + svq =vhost_svq_new (v->iova_tree,NULL ,NULL );if (unlikely (!svq)) {error_setg (errp,"Cannot create svq %u" , n);return -1 ;
Signature · 1 line
2.31.1
PATCH v4 14/19 vdpa: Export vhost_vdpa_dma_map and unmap calls
In reply to Eugenio PérezShadow CVQ will copy buffers on qemu VA, so we avoid TOCTOU attacks from the guest that could set a different state in qemu device model and vdpa device.
To do so, it needs to be able to map these new buffers to the device.
--- include/hw/virtio/vhost-vdpa.h | 4 ++++ hw/virtio/vhost-vdpa.c | 7 +++---- 2 files changed, 7 insertions(+), 4 deletions(-)
include/hw/virtio/vhost-vdpa.h +4 -0
@@ -39,4 +39,8 @@ typedef struct vhost_vdpa { VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX]; } VhostVDPA; +int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly); +int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova,hwaddr size); +#endif
hw/virtio/vhost-vdpa.c +3 -4
@@ -71,8 +71,8 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,return false; } -static int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, -void *vaddr,bool readonly) +int vhost_vdpa_dma_map (struct vhost_vdpa *v,hwaddr iova,hwaddr size, +void *vaddr,bool readonly) {struct vhost_msg_v2 msg = {};int fd = v->device_fd;
@@ -97,8 +97,7 @@ static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,return ret; } -static int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova, -hwaddr size) +int vhost_vdpa_dma_unmap (struct vhost_vdpa *v,hwaddr iova,hwaddr size) {struct vhost_msg_v2 msg = {};int fd = v->device_fd;
Signature · 1 line
2.31.1
PATCH v4 15/19 vdpa: manual forward CVQ buffers
In reply to Eugenio PérezDo a simple forwarding of CVQ buffers, the same work SVQ could do but through callbacks. No functional change intended.
--- include/hw/virtio/vhost-vdpa.h | 3 ++ hw/virtio/vhost-vdpa.c | 3 +- net/vhost-vdpa.c | 58 ++++++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 1 deletion(-)
include/hw/virtio/vhost-vdpa.h +3 -0
@@ -15,6 +15,7 @@#include <gmodule.h> #include "hw/virtio/vhost-iova-tree.h" +#include "hw/virtio/vhost-shadow-virtqueue.h" #include "hw/virtio/virtio.h" #include "standard-headers/linux/vhost_types.h"
@@ -35,6 +36,8 @@ typedef struct vhost_vdpa {/* IOVA mapping used by the Shadow Virtqueue */ VhostIOVATree *iova_tree;GPtrArray *shadow_vqs; +const VhostShadowVirtqueueOps *shadow_vq_ops; +void *shadow_vq_ops_opaque;struct vhost_dev *dev;VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX ]; } VhostVDPA;
hw/virtio/vhost-vdpa.c +2 -1
@@ -419,7 +419,8 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v,for (unsigned n =0 ; n < hdev->nvqs; ++n) {g_autoptr (VhostShadowVirtqueue) svq; - svq =vhost_svq_new (v->iova_tree,NULL ,NULL ); + svq =vhost_svq_new (v->iova_tree, v->shadow_vq_ops, + v->shadow_vq_ops_opaque);if (unlikely (!svq)) {error_setg (errp,"Cannot create svq %u" , n);return -1 ;
net/vhost-vdpa.c +58 -0
81 lines not on this page · raw message
Signature · 1 line
2.31.1
PATCH v4 16/19 vdpa: Buffer CVQ support on shadow virtqueue
In reply to Eugenio PérezIntroduce the control virtqueue support for vDPA shadow virtqueue. This is needed for advanced networking features like rx filtering.
Virtio-net control VQ copies the descriptors to qemu's VA, so we avoid TOCTOU with the guest's or device's memory every time there is a device model change. Otherwise, the guest could change the memory content in the time between qemu and the device read it.
To demonstrate command handling, VIRTIO_NET_F_CTRL_MACADDR is implemented. If the virtio-net driver changes MAC the virtio-net device model will be updated with the new one, and a rx filtering change event will be raised.
More cvq commands could be added here straightforwardly but they have not been tested.
--- net/vhost-vdpa.c | 211 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 204 insertions(+), 7 deletions(-)
net/vhost-vdpa.c +204 -7
@@ -33,6 +33,9 @@ typedef struct VhostVDPAState {NetClientState nc;struct vhost_vdpa vhost_vdpa;VHostNetState *vhost_net; + +/* Control commands shadow buffers */ +void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;bool started; } VhostVDPAState;
@@ -131,6 +134,8 @@ static void vhost_vdpa_cleanup(NetClientState *nc) {VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +qemu_vfree (s->cvq_cmd_out_buffer); +qemu_vfree (s->cvq_cmd_in_buffer);if (s->vhost_net) {vhost_net_cleanup (s->vhost_net);g_free (s->vhost_net);
@@ -190,24 +195,191 @@ static NetClientInfo net_vhost_vdpa_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; +static void vhost_vdpa_cvq_unmap_buf (struct vhost_vdpa *v,void *addr) +{ +VhostIOVATree *tree = v->iova_tree; +DMAMap needle = { +/* +* No need to specify size or to look for more translations since +* this contiguous chunk was allocated by us. +*/ + .translated_addr = (hwaddr )(uintptr_t )addr, + }; +const DMAMap *map =vhost_iova_tree_find_iova (tree, &needle); +int r; + +if (unlikely (!map)) { +error_report ("Cannot locate expected map" ); +return ; + } + + r =vhost_vdpa_dma_unmap (v, map->iova, map->size +1 ); +if (unlikely (r !=0 )) { +error_report ("Device cannot unmap: %s(%d)" ,g_strerror (r), r); + } + +vhost_iova_tree_remove (tree, map); +} + +static size_t vhost_vdpa_net_cvq_cmd_len (void ) +{ +/* +* MAC_TABLE_SET is the ctrl command that produces the longer out buffer. +* In buffer is always 1 byte, so it should fit here +*/ +return sizeof (struct virtio_net_ctrl_hdr ) + +2 *sizeof (struct virtio_net_ctrl_mac ) + +MAC_TABLE_ENTRIES *ETH_ALEN ; +} + +static size_t vhost_vdpa_net_cvq_cmd_page_len (void ) +{ +return ROUND_UP (vhost_vdpa_net_cvq_cmd_len (),qemu_real_host_page_size ()); +} + +/** Copy and map a guest buffer. */ +static bool vhost_vdpa_cvq_map_buf (struct vhost_vdpa *v, +const struct iovec *out_data, +size_t out_num,size_t data_len,void *buf, +size_t *written,bool write) +{ +DMAMap map = {}; +int r; + +if (unlikely (!data_len)) { +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid legnth of %s buffer\n" , + __func__, write ?"in" :"out" ); +return false; + } + + *written =iov_to_buf (out_data, out_num,0 , buf, data_len); + map.translated_addr = (hwaddr )(uintptr_t )buf; + map.size =vhost_vdpa_net_cvq_cmd_page_len () -1 ; + map.perm = write ?IOMMU_RW :IOMMU_RO , + r =vhost_iova_tree_map_alloc (v->iova_tree, &map); +if (unlikely (r !=IOVA_OK )) { +error_report ("Cannot map injected element" ); +return false; + } + + r =vhost_vdpa_dma_map (v, map.iova,vhost_vdpa_net_cvq_cmd_page_len (), buf, + !write); +if (unlikely (r <0 )) { + goto dma_map_err; + } + +return true; + +dma_map_err: +vhost_iova_tree_remove (v->iova_tree, &map); +return false; +} +/** -* Forward buffer for the moment. +* Copy the guest element into a dedicated buffer suitable to be sent to NIC +* +* @iov: [0] is the out buffer, [1] is the in one +*/ +static bool vhost_vdpa_net_cvq_map_elem (VhostVDPAState *s, +VirtQueueElement *elem, +struct iovec *iov) +{ +size_t in_copied; +bool ok; + + iov[0 ].iov_base = s->cvq_cmd_out_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa, elem->out_sg, elem->out_num, +vhost_vdpa_net_cvq_cmd_len (), iov[0 ].iov_base, + &iov[0 ].iov_len, false); +if (unlikely (!ok)) { +return false; + } + + iov[1 ].iov_base = s->cvq_cmd_in_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa,NULL ,0 , +sizeof (virtio_net_ctrl_ack), iov[1 ].iov_base, + &in_copied, true); +if (unlikely (!ok)) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, s->cvq_cmd_out_buffer); +return false; + } + + iov[1 ].iov_len =sizeof (virtio_net_ctrl_ack); +return true; +} + +/** +* Do not forward commands not supported by SVQ. Otherwise, the device could +* accept it and qemu would not know how to update the device model. +*/ +static bool vhost_vdpa_net_cvq_validate_cmd (const struct iovec *out, +size_t out_num) +{ +struct virtio_net_ctrl_hdr ctrl; +size_t n; + + n =iov_to_buf (out, out_num,0 , &ctrl,sizeof (ctrl)); +if (unlikely (n <sizeof (ctrl))) { +qemu_log_mask (LOG_GUEST_ERROR , +"%s: invalid legnth of out buffer %zu\n" , __func__, n); +return false; + } + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : +switch (ctrl.cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : +return true; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid mac cmd %u\n" , + __func__, ctrl.cmd); + }; +break ; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid control class %u\n" , + __func__, ctrl.class); + }; + +return false; +} + +/** +* Validate and copy control virtqueue commands. +* +* Following QEMU guidelines, we offer a copy of the buffers to the device to +* prevent TOCTOU bugs. */ static int vhost_vdpa_net_handle_ctrl_avail (VhostShadowVirtqueue *svq,VirtQueueElement *elem,void *opaque) { -unsigned int n = elem->out_num + elem->in_num; - g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); +VhostVDPAState *s = opaque;size_t in_len, dev_written;virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +/* out and in buffers sent to the device */ +struct iovec dev_buffers[2 ] = { + { .iov_base = s->cvq_cmd_out_buffer }, + { .iov_base = s->cvq_cmd_in_buffer }, + }; +/* in buffer used for device model */ +const struct iovec in = { + .iov_base = &status, + .iov_len =sizeof (status), + };int r; +bool ok; -memcpy (dev_buffers, elem->out_sg, elem->out_num); -memcpy (dev_buffers + elem->out_num, elem->in_sg, elem->in_num); + ok =vhost_vdpa_net_cvq_map_elem (s, elem, dev_buffers); +if (unlikely (!ok)) { + goto out; + } - r =vhost_svq_add (svq, &dev_buffers[0 ], elem->out_num, &dev_buffers[1 ], - elem->in_num, elem); + ok =vhost_vdpa_net_cvq_validate_cmd (&dev_buffers[0 ],1 ); +if (unlikely (!ok)) { + goto out; + } + + r =vhost_svq_add (svq, &dev_buffers[0 ],1 , &dev_buffers[1 ],1 , elem);if (unlikely (r !=0 )) {if (unlikely (r == -ENOSPC )) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
@@ -224,6 +396,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, dev_written =vhost_svq_poll (svq);if (unlikely (dev_written <sizeof (status))) {error_report ("Insufficient written data (%zu)" , dev_written); + goto out; + } + +memcpy (&status, dev_buffers[1 ].iov_base,sizeof (status)); +if (status !=VIRTIO_NET_OK ) { + goto out; + } + + status =VIRTIO_NET_ERR ; +virtio_net_handle_ctrl_iov (svq->vdev, &in,1 , dev_buffers,1 ); +if (status !=VIRTIO_NET_OK ) { +error_report ("Bad CVQ processing in model" ); } out:
@@ -234,6 +418,12 @@ out: }vhost_svq_push_elem (svq, elem,MIN (in_len,sizeof (status)));g_free (elem); +if (dev_buffers[0 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[0 ].iov_base); + } +if (dev_buffers[1 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[1 ].iov_base); + }return r; }
@@ -266,6 +456,13 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.device_fd = vdpa_device_fd; s->vhost_vdpa.index = queue_pair_index;if (!is_datapath) { + s->cvq_cmd_out_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_out_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->cvq_cmd_in_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_in_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; s->vhost_vdpa.shadow_vq_ops_opaque = s; }
Signature · 1 line
2.31.1
Re: [PATCH v4 16/19] vdpa: Buffer CVQ support on shadow virtqueue
Quoted 213 lines · Eugenio Pérez
Introduce the control virtqueue support for vDPA shadow virtqueue. This is needed for advanced networking features like rx filtering.
Virtio-net control VQ copies the descriptors to qemu's VA, so we avoid TOCTOU with the guest's or device's memory every time there is a device model change. Otherwise, the guest could change the memory content in the time between qemu and the device read it.
To demonstrate command handling,
VIRTIO_NET_F_CTRL_MACADDRis implemented. If the virtio-net driver changes MAC the virtio-net device model will be updated with the new one, and a rx filtering change event will be raised.More cvq commands could be added here straightforwardly but they have not been tested.
Signed-off-by Eugenio Pérez <[email protected]>--- net/vhost-vdpa.c | 211 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 204 insertions(+), 7 deletions(-)net/vhost-vdpa.c +159
-3@@ -33,6 +33,9 @@ typedef struct VhostVDPAState {NetClientState nc;struct vhost_vdpa vhost_vdpa;VHostNetState *vhost_net; + +/* Control commands shadow buffers */ +void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;bool started; } VhostVDPAState;@@ -131,6 +134,8 @@ static void vhost_vdpa_cleanup(NetClientState *nc) {VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +qemu_vfree (s->cvq_cmd_out_buffer); +qemu_vfree (s->cvq_cmd_in_buffer);if (s->vhost_net) {vhost_net_cleanup (s->vhost_net);g_free (s->vhost_net);@@ -190,24 +195,191 @@ static NetClientInfo net_vhost_vdpa_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; +static void vhost_vdpa_cvq_unmap_buf (struct vhost_vdpa *v,void *addr) +{ +VhostIOVATree *tree = v->iova_tree; +DMAMap needle = { +/* +* No need to specify size or to look for more translations since +* this contiguous chunk was allocated by us. +*/ + .translated_addr = (hwaddr )(uintptr_t )addr, + }; +const DMAMap *map =vhost_iova_tree_find_iova (tree, &needle); +int r; + +if (unlikely (!map)) { +error_report ("Cannot locate expected map" ); +return ; + } + + r =vhost_vdpa_dma_unmap (v, map->iova, map->size +1 ); +if (unlikely (r !=0 )) { +error_report ("Device cannot unmap: %s(%d)" ,g_strerror (r), r); + } + +vhost_iova_tree_remove (tree, map); +} + +static size_t vhost_vdpa_net_cvq_cmd_len (void ) +{ +/* +* MAC_TABLE_SET is the ctrl command that produces the longer out buffer. +* In buffer is always 1 byte, so it should fit here +*/ +return sizeof (struct virtio_net_ctrl_hdr ) + +2 *sizeof (struct virtio_net_ctrl_mac ) + +MAC_TABLE_ENTRIES *ETH_ALEN ; +} + +static size_t vhost_vdpa_net_cvq_cmd_page_len (void ) +{ +return ROUND_UP (vhost_vdpa_net_cvq_cmd_len (),qemu_real_host_page_size ()); +} + +/** Copy and map a guest buffer. */ +static bool vhost_vdpa_cvq_map_buf (struct vhost_vdpa *v, +const struct iovec *out_data, +size_t out_num,size_t data_len,void *buf, +size_t *written,bool write) +{ +DMAMap map = {}; +int r; + +if (unlikely (!data_len)) { +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid legnth of %s buffer\n" , + __func__, write ?"in" :"out" ); +return false; + } + + *written =iov_to_buf (out_data, out_num,0 , buf, data_len); + map.translated_addr = (hwaddr )(uintptr_t )buf; + map.size =vhost_vdpa_net_cvq_cmd_page_len () -1 ; + map.perm = write ?IOMMU_RW :IOMMU_RO , + r =vhost_iova_tree_map_alloc (v->iova_tree, &map); +if (unlikely (r !=IOVA_OK )) { +error_report ("Cannot map injected element" ); +return false; + } + + r =vhost_vdpa_dma_map (v, map.iova,vhost_vdpa_net_cvq_cmd_page_len (), buf, + !write); +if (unlikely (r <0 )) { + goto dma_map_err; + } + +return true; + +dma_map_err: +vhost_iova_tree_remove (v->iova_tree, &map); +return false; +} +/** -* Forward buffer for the moment. +* Copy the guest element into a dedicated buffer suitable to be sent to NIC +* +* @iov: [0] is the out buffer, [1] is the in one +*/ +static bool vhost_vdpa_net_cvq_map_elem (VhostVDPAState *s, +VirtQueueElement *elem, +struct iovec *iov) +{ +size_t in_copied; +bool ok; + + iov[0 ].iov_base = s->cvq_cmd_out_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa, elem->out_sg, elem->out_num, +vhost_vdpa_net_cvq_cmd_len (), iov[0 ].iov_base, + &iov[0 ].iov_len, false); +if (unlikely (!ok)) { +return false; + } + + iov[1 ].iov_base = s->cvq_cmd_in_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa,NULL ,0 , +sizeof (virtio_net_ctrl_ack), iov[1 ].iov_base, + &in_copied, true); +if (unlikely (!ok)) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, s->cvq_cmd_out_buffer); +return false; + } + + iov[1 ].iov_len =sizeof (virtio_net_ctrl_ack); +return true; +} + +/** +* Do not forward commands not supported by SVQ. Otherwise, the device could +* accept it and qemu would not know how to update the device model. +*/ +static bool vhost_vdpa_net_cvq_validate_cmd (const struct iovec *out, +size_t out_num) +{ +struct virtio_net_ctrl_hdr ctrl; +size_t n; + + n =iov_to_buf (out, out_num,0 , &ctrl,sizeof (ctrl)); +if (unlikely (n <sizeof (ctrl))) { +qemu_log_mask (LOG_GUEST_ERROR , +"%s: invalid legnth of out buffer %zu\n" , __func__, n); +return false; + } + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : +switch (ctrl.cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : +return true; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid mac cmd %u\n" , + __func__, ctrl.cmd); + }; +break ; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid control class %u\n" , + __func__, ctrl.class); + }; + +return false; +} + +/** +* Validate and copy control virtqueue commands. +* +* Following QEMU guidelines, we offer a copy of the buffers to the device to +* prevent TOCTOU bugs. */ static int vhost_vdpa_net_handle_ctrl_avail (VhostShadowVirtqueue *svq,VirtQueueElement *elem,void *opaque) { -unsigned int n = elem->out_num + elem->in_num; - g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); +VhostVDPAState *s = opaque;size_t in_len, dev_written;virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +/* out and in buffers sent to the device */
net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 369
Quoted 10 lines
net/vhost-vdpa.c +9
-0+struct iovec dev_buffers[2 ] = { + { .iov_base = s->cvq_cmd_out_buffer }, + { .iov_base = s->cvq_cmd_in_buffer }, + }; +/* in buffer used for device model */ +const struct iovec in = { + .iov_base = &status, + .iov_len =sizeof (status), + };int r;
I got this:
FAILED: libcommon.fa.p/net_vhost-vdpa.c.o
cc -m64 -mcx16 -Ilibcommon.fa.p -I../dtc/libfdt -I../slirp -I../slirp/src -I/usr/include/capstone -I/usr/include/pixman-1 -I/usr/include/libpng16 -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -I/usr/include/gio-unix-2.0 -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -isystem /home/devel/git/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/devel/git/qemu -iquote /home/devel/git/qemu/include -iquote /home/devel/git/qemu/tcg/i386 -pthread -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -Wstrict-prototypes -Wredundant-decls -Wundef -Wwrite-strings -Wmissing-prototypes -fno-strict-aliasing -fno-common -fwrapv -Wold-style-declaration -Wold-style-definition -Wtype-limits -Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers -Wempty-body -Wnested-externs -Wendif-labels -Wexpansion-to-defined -Wimplicit-fallthrough=2 -Wno-missing-include-dirs -Wno-shift-negative-value -Wno-psabi -fstack-protector-strong -fPIE -D_DEFAULT_SOURCE -D_XOPEN_SOURCE=600 -DNCURSES_WIDECHAR=1 -MD -MQ libcommon.fa.p/net_vhost-vdpa.c.o -MF libcommon.fa.p/net_vhost-vdpa.c.o.d -o libcommon.fa.p/net_vhost-vdpa.c.o -c ../net/vhost-vdpa.c ../net/vhost-vdpa.c: In function ‘vhost_vdpa_net_handle_ctrl_avail’:../net/vhost-vdpa.c:427:12: error: ‘r’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
427 | return r;
| ^
cc1: all warnings being treated as errors
net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 372
Quoted 5 lines
net/vhost-vdpa.c +2
-2+bool ok; -memcpy (dev_buffers, elem->out_sg, elem->out_num); -memcpy (dev_buffers + elem->out_num, elem->in_sg, elem->in_num); + ok =vhost_vdpa_net_cvq_map_elem (s, elem, dev_buffers);
I think it's good idea to let this function return int instead of a boolean.
Thanks
Quoted 61 lines
net/vhost-vdpa.c +34
-2+if (unlikely (!ok)) { + goto out; + } - r =vhost_svq_add (svq, &dev_buffers[0 ], elem->out_num, &dev_buffers[1 ], - elem->in_num, elem); + ok =vhost_vdpa_net_cvq_validate_cmd (&dev_buffers[0 ],1 ); +if (unlikely (!ok)) { + goto out; + } + + r =vhost_svq_add (svq, &dev_buffers[0 ],1 , &dev_buffers[1 ],1 , elem);if (unlikely (r !=0 )) {if (unlikely (r == -ENOSPC )) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",@@ -224,6 +396,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, dev_written =vhost_svq_poll (svq);if (unlikely (dev_written <sizeof (status))) {error_report ("Insufficient written data (%zu)" , dev_written); + goto out; + } + +memcpy (&status, dev_buffers[1 ].iov_base,sizeof (status)); +if (status !=VIRTIO_NET_OK ) { + goto out; + } + + status =VIRTIO_NET_ERR ; +virtio_net_handle_ctrl_iov (svq->vdev, &in,1 , dev_buffers,1 ); +if (status !=VIRTIO_NET_OK ) { +error_report ("Bad CVQ processing in model" ); } out:@@ -234,6 +418,12 @@ out: }vhost_svq_push_elem (svq, elem,MIN (in_len,sizeof (status)));g_free (elem); +if (dev_buffers[0 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[0 ].iov_base); + } +if (dev_buffers[1 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[1 ].iov_base); + }return r; }@@ -266,6 +456,13 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.device_fd = vdpa_device_fd; s->vhost_vdpa.index = queue_pair_index;if (!is_datapath) { + s->cvq_cmd_out_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_out_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->cvq_cmd_in_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_in_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; s->vhost_vdpa.shadow_vq_ops_opaque = s; }
Re: [PATCH v4 16/19] vdpa: Buffer CVQ support on shadow virtqueue
Quoted 249 lines · Jason Wang
Quoted 213 lines · Eugenio Pérez
Introduce the control virtqueue support for vDPA shadow virtqueue. This is needed for advanced networking features like rx filtering.
Virtio-net control VQ copies the descriptors to qemu's VA, so we avoid TOCTOU with the guest's or device's memory every time there is a device model change. Otherwise, the guest could change the memory content in the time between qemu and the device read it.
To demonstrate command handling,
VIRTIO_NET_F_CTRL_MACADDRis implemented. If the virtio-net driver changes MAC the virtio-net device model will be updated with the new one, and a rx filtering change event will be raised.More cvq commands could be added here straightforwardly but they have not been tested.
Signed-off-by Eugenio Pérez <[email protected]>--- net/vhost-vdpa.c | 211 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 204 insertions(+), 7 deletions(-)net/vhost-vdpa.c +159
-3@@ -33,6 +33,9 @@ typedef struct VhostVDPAState {NetClientState nc;struct vhost_vdpa vhost_vdpa;VHostNetState *vhost_net; + +/* Control commands shadow buffers */ +void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;bool started; } VhostVDPAState;@@ -131,6 +134,8 @@ static void vhost_vdpa_cleanup(NetClientState *nc) {VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +qemu_vfree (s->cvq_cmd_out_buffer); +qemu_vfree (s->cvq_cmd_in_buffer);if (s->vhost_net) {vhost_net_cleanup (s->vhost_net);g_free (s->vhost_net);@@ -190,24 +195,191 @@ static NetClientInfo net_vhost_vdpa_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; +static void vhost_vdpa_cvq_unmap_buf (struct vhost_vdpa *v,void *addr) +{ +VhostIOVATree *tree = v->iova_tree; +DMAMap needle = { +/* +* No need to specify size or to look for more translations since +* this contiguous chunk was allocated by us. +*/ + .translated_addr = (hwaddr )(uintptr_t )addr, + }; +const DMAMap *map =vhost_iova_tree_find_iova (tree, &needle); +int r; + +if (unlikely (!map)) { +error_report ("Cannot locate expected map" ); +return ; + } + + r =vhost_vdpa_dma_unmap (v, map->iova, map->size +1 ); +if (unlikely (r !=0 )) { +error_report ("Device cannot unmap: %s(%d)" ,g_strerror (r), r); + } + +vhost_iova_tree_remove (tree, map); +} + +static size_t vhost_vdpa_net_cvq_cmd_len (void ) +{ +/* +* MAC_TABLE_SET is the ctrl command that produces the longer out buffer. +* In buffer is always 1 byte, so it should fit here +*/ +return sizeof (struct virtio_net_ctrl_hdr ) + +2 *sizeof (struct virtio_net_ctrl_mac ) + +MAC_TABLE_ENTRIES *ETH_ALEN ; +} + +static size_t vhost_vdpa_net_cvq_cmd_page_len (void ) +{ +return ROUND_UP (vhost_vdpa_net_cvq_cmd_len (),qemu_real_host_page_size ()); +} + +/** Copy and map a guest buffer. */ +static bool vhost_vdpa_cvq_map_buf (struct vhost_vdpa *v, +const struct iovec *out_data, +size_t out_num,size_t data_len,void *buf, +size_t *written,bool write) +{ +DMAMap map = {}; +int r; + +if (unlikely (!data_len)) { +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid legnth of %s buffer\n" , + __func__, write ?"in" :"out" ); +return false; + } + + *written =iov_to_buf (out_data, out_num,0 , buf, data_len); + map.translated_addr = (hwaddr )(uintptr_t )buf; + map.size =vhost_vdpa_net_cvq_cmd_page_len () -1 ; + map.perm = write ?IOMMU_RW :IOMMU_RO , + r =vhost_iova_tree_map_alloc (v->iova_tree, &map); +if (unlikely (r !=IOVA_OK )) { +error_report ("Cannot map injected element" ); +return false; + } + + r =vhost_vdpa_dma_map (v, map.iova,vhost_vdpa_net_cvq_cmd_page_len (), buf, + !write); +if (unlikely (r <0 )) { + goto dma_map_err; + } + +return true; + +dma_map_err: +vhost_iova_tree_remove (v->iova_tree, &map); +return false; +} +/** -* Forward buffer for the moment. +* Copy the guest element into a dedicated buffer suitable to be sent to NIC +* +* @iov: [0] is the out buffer, [1] is the in one +*/ +static bool vhost_vdpa_net_cvq_map_elem (VhostVDPAState *s, +VirtQueueElement *elem, +struct iovec *iov) +{ +size_t in_copied; +bool ok; + + iov[0 ].iov_base = s->cvq_cmd_out_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa, elem->out_sg, elem->out_num, +vhost_vdpa_net_cvq_cmd_len (), iov[0 ].iov_base, + &iov[0 ].iov_len, false); +if (unlikely (!ok)) { +return false; + } + + iov[1 ].iov_base = s->cvq_cmd_in_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa,NULL ,0 , +sizeof (virtio_net_ctrl_ack), iov[1 ].iov_base, + &in_copied, true); +if (unlikely (!ok)) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, s->cvq_cmd_out_buffer); +return false; + } + + iov[1 ].iov_len =sizeof (virtio_net_ctrl_ack); +return true; +} + +/** +* Do not forward commands not supported by SVQ. Otherwise, the device could +* accept it and qemu would not know how to update the device model. +*/ +static bool vhost_vdpa_net_cvq_validate_cmd (const struct iovec *out, +size_t out_num) +{ +struct virtio_net_ctrl_hdr ctrl; +size_t n; + + n =iov_to_buf (out, out_num,0 , &ctrl,sizeof (ctrl)); +if (unlikely (n <sizeof (ctrl))) { +qemu_log_mask (LOG_GUEST_ERROR , +"%s: invalid legnth of out buffer %zu\n" , __func__, n); +return false; + } + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : +switch (ctrl.cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : +return true; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid mac cmd %u\n" , + __func__, ctrl.cmd); + }; +break ; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid control class %u\n" , + __func__, ctrl.class); + }; + +return false; +} + +/** +* Validate and copy control virtqueue commands. +* +* Following QEMU guidelines, we offer a copy of the buffers to the device to +* prevent TOCTOU bugs. */ static int vhost_vdpa_net_handle_ctrl_avail (VhostShadowVirtqueue *svq,VirtQueueElement *elem,void *opaque) { -unsigned int n = elem->out_num + elem->in_num; - g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); +VhostVDPAState *s = opaque;size_t in_len, dev_written;virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +/* out and in buffers sent to the device */ net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 369
Quoted 10 lines
net/vhost-vdpa.c +9
-0+struct iovec dev_buffers[2 ] = { + { .iov_base = s->cvq_cmd_out_buffer }, + { .iov_base = s->cvq_cmd_in_buffer }, + }; +/* in buffer used for device model */ +const struct iovec in = { + .iov_base = &status, + .iov_len =sizeof (status), + };int r;I got this:
FAILED:
libcommon.fa.p/net_vhost-vdpa.c.o
cc -m64 -mcx16 -Ilibcommon.fa.p -I../dtc/libfdt -I../slirp(quoted diff) +0
-6-I../slirp/src -I/usr/include/capstone -I/usr/include/pixman-1 -I/usr/include/libpng16 -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -I/usr/include/gio-unix-2.0 -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -isystem /home/devel/git/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/devel/git/qemu -iquote
/home/devel/git/qemu/include-iquote/home/devel/git/qemu/tcg/i386(quoted diff) +0
-10-pthread -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -Wstrict-prototypes -Wredundant-decls -Wundef -Wwrite-strings -Wmissing-prototypes -fno-strict-aliasing -fno-common -fwrapv -Wold-style-declaration -Wold-style-definition -Wtype-limits -Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers -Wempty-body -Wnested-externs -Wendif-labels -Wexpansion-to-defined -Wimplicit-fallthrough=2 -Wno-missing-include-dirs -Wno-shift-negative-value -Wno-psabi -fstack-protector-strong -fPIE -D_DEFAULT_SOURCE -D_XOPEN_SOURCE=600 -DNCURSES_WIDECHAR=1 -MD -MQ libcommon.fa.p/net_vhost-vdpa.c.o -MF
Quoted 9 lines
libcommon.fa.p/net_vhost-vdpa.c.o.d -o
libcommon.fa.p/net_vhost-vdpa.c.o-c../net/vhost-vdpa.c../net/vhost-vdpa.c: In function ‘vhost_vdpa_net_handle_ctrl_avail’:../net/vhost-vdpa.c:427:12: error: ‘r’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
427 | return r;
| ^
cc1: all warnings being treated as errors
Sorry, I rebase with these applied (or half applied) [1].
I'll send a new version based on the current master in a moment.
Thanks!
[1] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg01986.html
Quoted 75 lines
net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 372
Quoted 6 lines
net/vhost-vdpa.c +2
-2+bool ok; -memcpy (dev_buffers, elem->out_sg, elem->out_num); -memcpy (dev_buffers + elem->out_num, elem->in_sg, elem->in_num); + ok =vhost_vdpa_net_cvq_map_elem (s, elem, dev_buffers);I think it's good idea to let this function return int instead of a boolean.
Thanks
Quoted 61 lines
net/vhost-vdpa.c +34
-2+if (unlikely (!ok)) { + goto out; + } - r =vhost_svq_add (svq, &dev_buffers[0 ], elem->out_num, &dev_buffers[1 ], - elem->in_num, elem); + ok =vhost_vdpa_net_cvq_validate_cmd (&dev_buffers[0 ],1 ); +if (unlikely (!ok)) { + goto out; + } + + r =vhost_svq_add (svq, &dev_buffers[0 ],1 , &dev_buffers[1 ],1 , elem);if (unlikely (r !=0 )) {if (unlikely (r == -ENOSPC )) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",@@ -224,6 +396,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, dev_written =vhost_svq_poll (svq);if (unlikely (dev_written <sizeof (status))) {error_report ("Insufficient written data (%zu)" , dev_written); + goto out; + } + +memcpy (&status, dev_buffers[1 ].iov_base,sizeof (status)); +if (status !=VIRTIO_NET_OK ) { + goto out; + } + + status =VIRTIO_NET_ERR ; +virtio_net_handle_ctrl_iov (svq->vdev, &in,1 , dev_buffers,1 ); +if (status !=VIRTIO_NET_OK ) { +error_report ("Bad CVQ processing in model" ); } out:@@ -234,6 +418,12 @@ out: }vhost_svq_push_elem (svq, elem,MIN (in_len,sizeof (status)));g_free (elem); +if (dev_buffers[0 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[0 ].iov_base); + } +if (dev_buffers[1 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[1 ].iov_base); + }return r; }@@ -266,6 +456,13 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.device_fd = vdpa_device_fd; s->vhost_vdpa.index = queue_pair_index;if (!is_datapath) { + s->cvq_cmd_out_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_out_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->cvq_cmd_in_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_in_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; s->vhost_vdpa.shadow_vq_ops_opaque = s; }
Re: [PATCH v4 16/19] vdpa: Buffer CVQ support on shadow virtqueue
Quoted 263 lines · Eugenio Perez Martin
Quoted 249 lines · Jason Wang
Quoted 213 lines · Eugenio Pérez
Introduce the control virtqueue support for vDPA shadow virtqueue. This is needed for advanced networking features like rx filtering.
Virtio-net control VQ copies the descriptors to qemu's VA, so we avoid TOCTOU with the guest's or device's memory every time there is a device model change. Otherwise, the guest could change the memory content in the time between qemu and the device read it.
To demonstrate command handling,
VIRTIO_NET_F_CTRL_MACADDRis implemented. If the virtio-net driver changes MAC the virtio-net device model will be updated with the new one, and a rx filtering change event will be raised.More cvq commands could be added here straightforwardly but they have not been tested.
Signed-off-by Eugenio Pérez <[email protected]>--- net/vhost-vdpa.c | 211 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 204 insertions(+), 7 deletions(-)net/vhost-vdpa.c +159
-3@@ -33,6 +33,9 @@ typedef struct VhostVDPAState {NetClientState nc;struct vhost_vdpa vhost_vdpa;VHostNetState *vhost_net; + +/* Control commands shadow buffers */ +void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;bool started; } VhostVDPAState;@@ -131,6 +134,8 @@ static void vhost_vdpa_cleanup(NetClientState *nc) {VhostVDPAState *s =DO_UPCAST (VhostVDPAState, nc, nc); +qemu_vfree (s->cvq_cmd_out_buffer); +qemu_vfree (s->cvq_cmd_in_buffer);if (s->vhost_net) {vhost_net_cleanup (s->vhost_net);g_free (s->vhost_net);@@ -190,24 +195,191 @@ static NetClientInfo net_vhost_vdpa_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; +static void vhost_vdpa_cvq_unmap_buf (struct vhost_vdpa *v,void *addr) +{ +VhostIOVATree *tree = v->iova_tree; +DMAMap needle = { +/* +* No need to specify size or to look for more translations since +* this contiguous chunk was allocated by us. +*/ + .translated_addr = (hwaddr )(uintptr_t )addr, + }; +const DMAMap *map =vhost_iova_tree_find_iova (tree, &needle); +int r; + +if (unlikely (!map)) { +error_report ("Cannot locate expected map" ); +return ; + } + + r =vhost_vdpa_dma_unmap (v, map->iova, map->size +1 ); +if (unlikely (r !=0 )) { +error_report ("Device cannot unmap: %s(%d)" ,g_strerror (r), r); + } + +vhost_iova_tree_remove (tree, map); +} + +static size_t vhost_vdpa_net_cvq_cmd_len (void ) +{ +/* +* MAC_TABLE_SET is the ctrl command that produces the longer out buffer. +* In buffer is always 1 byte, so it should fit here +*/ +return sizeof (struct virtio_net_ctrl_hdr ) + +2 *sizeof (struct virtio_net_ctrl_mac ) + +MAC_TABLE_ENTRIES *ETH_ALEN ; +} + +static size_t vhost_vdpa_net_cvq_cmd_page_len (void ) +{ +return ROUND_UP (vhost_vdpa_net_cvq_cmd_len (),qemu_real_host_page_size ()); +} + +/** Copy and map a guest buffer. */ +static bool vhost_vdpa_cvq_map_buf (struct vhost_vdpa *v, +const struct iovec *out_data, +size_t out_num,size_t data_len,void *buf, +size_t *written,bool write) +{ +DMAMap map = {}; +int r; + +if (unlikely (!data_len)) { +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid legnth of %s buffer\n" , + __func__, write ?"in" :"out" ); +return false; + } + + *written =iov_to_buf (out_data, out_num,0 , buf, data_len); + map.translated_addr = (hwaddr )(uintptr_t )buf; + map.size =vhost_vdpa_net_cvq_cmd_page_len () -1 ; + map.perm = write ?IOMMU_RW :IOMMU_RO , + r =vhost_iova_tree_map_alloc (v->iova_tree, &map); +if (unlikely (r !=IOVA_OK )) { +error_report ("Cannot map injected element" ); +return false; + } + + r =vhost_vdpa_dma_map (v, map.iova,vhost_vdpa_net_cvq_cmd_page_len (), buf, + !write); +if (unlikely (r <0 )) { + goto dma_map_err; + } + +return true; + +dma_map_err: +vhost_iova_tree_remove (v->iova_tree, &map); +return false; +} +/** -* Forward buffer for the moment. +* Copy the guest element into a dedicated buffer suitable to be sent to NIC +* +* @iov: [0] is the out buffer, [1] is the in one +*/ +static bool vhost_vdpa_net_cvq_map_elem (VhostVDPAState *s, +VirtQueueElement *elem, +struct iovec *iov) +{ +size_t in_copied; +bool ok; + + iov[0 ].iov_base = s->cvq_cmd_out_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa, elem->out_sg, elem->out_num, +vhost_vdpa_net_cvq_cmd_len (), iov[0 ].iov_base, + &iov[0 ].iov_len, false); +if (unlikely (!ok)) { +return false; + } + + iov[1 ].iov_base = s->cvq_cmd_in_buffer; + ok =vhost_vdpa_cvq_map_buf (&s->vhost_vdpa,NULL ,0 , +sizeof (virtio_net_ctrl_ack), iov[1 ].iov_base, + &in_copied, true); +if (unlikely (!ok)) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, s->cvq_cmd_out_buffer); +return false; + } + + iov[1 ].iov_len =sizeof (virtio_net_ctrl_ack); +return true; +} + +/** +* Do not forward commands not supported by SVQ. Otherwise, the device could +* accept it and qemu would not know how to update the device model. +*/ +static bool vhost_vdpa_net_cvq_validate_cmd (const struct iovec *out, +size_t out_num) +{ +struct virtio_net_ctrl_hdr ctrl; +size_t n; + + n =iov_to_buf (out, out_num,0 , &ctrl,sizeof (ctrl)); +if (unlikely (n <sizeof (ctrl))) { +qemu_log_mask (LOG_GUEST_ERROR , +"%s: invalid legnth of out buffer %zu\n" , __func__, n); +return false; + } + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : +switch (ctrl.cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : +return true; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid mac cmd %u\n" , + __func__, ctrl.cmd); + }; +break ; +default : +qemu_log_mask (LOG_GUEST_ERROR ,"%s: invalid control class %u\n" , + __func__, ctrl.class); + }; + +return false; +} + +/** +* Validate and copy control virtqueue commands. +* +* Following QEMU guidelines, we offer a copy of the buffers to the device to +* prevent TOCTOU bugs. */ static int vhost_vdpa_net_handle_ctrl_avail (VhostShadowVirtqueue *svq,VirtQueueElement *elem,void *opaque) { -unsigned int n = elem->out_num + elem->in_num; - g_autofree struct iovec *dev_buffers = g_new(struct iovec, n); +VhostVDPAState *s = opaque;size_t in_len, dev_written;virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +/* out and in buffers sent to the device */ net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 369
Quoted 10 lines
net/vhost-vdpa.c +9
-0+struct iovec dev_buffers[2 ] = { + { .iov_base = s->cvq_cmd_out_buffer }, + { .iov_base = s->cvq_cmd_in_buffer }, + }; +/* in buffer used for device model */ +const struct iovec in = { + .iov_base = &status, + .iov_len =sizeof (status), + };int r;I got this:
FAILED:
libcommon.fa.p/net_vhost-vdpa.c.o
cc -m64 -mcx16 -Ilibcommon.fa.p -I../dtc/libfdt -I../slirp(quoted diff) +0
-6-I../slirp/src -I/usr/include/capstone -I/usr/include/pixman-1 -I/usr/include/libpng16 -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -I/usr/include/gio-unix-2.0 -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -isystem /home/devel/git/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/devel/git/qemu -iquote
/home/devel/git/qemu/include-iquote/home/devel/git/qemu/tcg/i386(quoted diff) +0
-10-pthread -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -Wstrict-prototypes -Wredundant-decls -Wundef -Wwrite-strings -Wmissing-prototypes -fno-strict-aliasing -fno-common -fwrapv -Wold-style-declaration -Wold-style-definition -Wtype-limits -Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers -Wempty-body -Wnested-externs -Wendif-labels -Wexpansion-to-defined -Wimplicit-fallthrough=2 -Wno-missing-include-dirs -Wno-shift-negative-value -Wno-psabi -fstack-protector-strong -fPIE -D_DEFAULT_SOURCE -D_XOPEN_SOURCE=600 -DNCURSES_WIDECHAR=1 -MD -MQ libcommon.fa.p/net_vhost-vdpa.c.o -MFQuoted 9 lines
libcommon.fa.p/net_vhost-vdpa.c.o.d -o
libcommon.fa.p/net_vhost-vdpa.c.o-c../net/vhost-vdpa.c../net/vhost-vdpa.c: In function ‘vhost_vdpa_net_handle_ctrl_avail’:../net/vhost-vdpa.c:427:12: error: ‘r’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
427 | return r;
| ^
cc1: all warnings being treated as errorsSorry, I rebase with these applied (or half applied) [1].
Quoted 2 lines
I'll send a new version based on the current master in a moment.
So that was not the issue. With --enable-debug, the optimization prevents that analysis from running in my compiler.
However, if I enable it there are other areas using uninitialized variables:../tests/fp/berkeley-testfloat-3/source/slowfloat.c:1016:14: error:
'uiZ' may be used uninitialized in this function [-Werror=maybe-uninitialized]
return uZ.f;
I'll send a new version. I'll add a warning in the cover letter for these unmerged fixes anyway.
Thanks!
Quoted 79 lines
Thanks!
[1] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg01986.html
Quoted 75 lines
net/vhost-vdpa.c static NetClientInfo net_vhost_vdpa_info = { · line 372
Quoted 6 lines
net/vhost-vdpa.c +2
-2+bool ok; -memcpy (dev_buffers, elem->out_sg, elem->out_num); -memcpy (dev_buffers + elem->out_num, elem->in_sg, elem->in_num); + ok =vhost_vdpa_net_cvq_map_elem (s, elem, dev_buffers);I think it's good idea to let this function return int instead of a boolean.
Thanks
Quoted 61 lines
net/vhost-vdpa.c +34
-2+if (unlikely (!ok)) { + goto out; + } - r =vhost_svq_add (svq, &dev_buffers[0 ], elem->out_num, &dev_buffers[1 ], - elem->in_num, elem); + ok =vhost_vdpa_net_cvq_validate_cmd (&dev_buffers[0 ],1 ); +if (unlikely (!ok)) { + goto out; + } + + r =vhost_svq_add (svq, &dev_buffers[0 ],1 , &dev_buffers[1 ],1 , elem);if (unlikely (r !=0 )) {if (unlikely (r == -ENOSPC )) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",@@ -224,6 +396,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, dev_written =vhost_svq_poll (svq);if (unlikely (dev_written <sizeof (status))) {error_report ("Insufficient written data (%zu)" , dev_written); + goto out; + } + +memcpy (&status, dev_buffers[1 ].iov_base,sizeof (status)); +if (status !=VIRTIO_NET_OK ) { + goto out; + } + + status =VIRTIO_NET_ERR ; +virtio_net_handle_ctrl_iov (svq->vdev, &in,1 , dev_buffers,1 ); +if (status !=VIRTIO_NET_OK ) { +error_report ("Bad CVQ processing in model" ); } out:@@ -234,6 +418,12 @@ out: }vhost_svq_push_elem (svq, elem,MIN (in_len,sizeof (status)));g_free (elem); +if (dev_buffers[0 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[0 ].iov_base); + } +if (dev_buffers[1 ].iov_base) { +vhost_vdpa_cvq_unmap_buf (&s->vhost_vdpa, dev_buffers[1 ].iov_base); + }return r; }@@ -266,6 +456,13 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.device_fd = vdpa_device_fd; s->vhost_vdpa.index = queue_pair_index;if (!is_datapath) { + s->cvq_cmd_out_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_out_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->cvq_cmd_in_buffer =qemu_memalign (qemu_real_host_page_size (), +vhost_vdpa_net_cvq_cmd_page_len ()); +memset (s->cvq_cmd_in_buffer,0 ,vhost_vdpa_net_cvq_cmd_page_len ()); + s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; s->vhost_vdpa.shadow_vq_ops_opaque = s; }
PATCH v4 17/19 vdpa: Extract get features part from vhost_vdpa_get_max_queue_pairs
In reply to Eugenio PérezTo know the device features is needed for CVQ SVQ, so SVQ knows if it can handle all commands or not. Extract from vhost_vdpa_get_max_queue_pairs so we can reuse it.
--- net/vhost-vdpa.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)
net/vhost-vdpa.c +20 -10
@@ -474,20 +474,24 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,return nc; } -static int vhost_vdpa_get_max_queue_pairs (int fd,int *has_cvq,Error **errp) +static int vhost_vdpa_get_features (int fd,uint64_t *features,Error **errp) +{ +int ret =ioctl (fd,VHOST_GET_FEATURES , features); +if (unlikely (ret <0 )) { +error_setg_errno (errp, errno, +"Fail to query features from vhost-vDPA device" ); + } +return ret; +} + +static int vhost_vdpa_get_max_queue_pairs (int fd,uint64_t features, +int *has_cvq,Error **errp) {unsigned long config_size = offsetof(struct vhost_vdpa_config , buf); g_autofree struct vhost_vdpa_config *config = NULL;__virtio16 *max_queue_pairs; -uint64_t features;int ret; - ret =ioctl (fd,VHOST_GET_FEATURES , &features); -if (ret) { -error_setg (errp,"Fail to query features from vhost-vDPA device" ); -return ret; - } -if (features & (1 <<VIRTIO_NET_F_CTRL_VQ )) { *has_cvq =1 ; }else {
@@ -517,10 +521,11 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) {const NetdevVhostVDPAOptions *opts; +uint64_t features;int vdpa_device_fd; g_autofree NetClientState **ncs = NULL;NetClientState *nc; -int queue_pairs, i, has_cvq =0 ; +int queue_pairs, r, i, has_cvq =0 ;assert (netdev->type ==NET_CLIENT_DRIVER_VHOST_VDPA ); opts = &netdev->u.vhost_vdpa;
@@ -534,7 +539,12 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,return -errno; } - queue_pairs =vhost_vdpa_get_max_queue_pairs (vdpa_device_fd, + r =vhost_vdpa_get_features (vdpa_device_fd, &features, errp); +if (unlikely (r <0 )) { +return r; + } + + queue_pairs =vhost_vdpa_get_max_queue_pairs (vdpa_device_fd, features, &has_cvq, errp);if (queue_pairs <0 ) {qemu_close (vdpa_device_fd);
Signature · 1 line
2.31.1
PATCH v4 18/19 vdpa: Add device migration blocker
In reply to Eugenio PérezSince the vhost-vdpa device is exposing _F_LOG, adding a migration blocker if it uses CVQ.
--- include/hw/virtio/vhost-vdpa.h | 1 + hw/virtio/vhost-vdpa.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+)
include/hw/virtio/vhost-vdpa.h +1 -0
@@ -35,6 +35,7 @@ typedef struct vhost_vdpa {bool shadow_vqs_enabled;/* IOVA mapping used by the Shadow Virtqueue */ VhostIOVATree *iova_tree; +Error *migration_blocker;GPtrArray *shadow_vqs;const VhostShadowVirtqueueOps *shadow_vq_ops;void *shadow_vq_ops_opaque;
hw/virtio/vhost-vdpa.c +14 -0
@@ -20,6 +20,7 @@#include "hw/virtio/vhost-shadow-virtqueue.h" #include "hw/virtio/vhost-vdpa.h" #include "exec/address-spaces.h" +#include "migration/blocker.h" #include "qemu/cutils.h" #include "qemu/main-loop.h" #include "cpu.h"
@@ -1022,6 +1023,13 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)return true; } +if (v->migration_blocker) { +int r =migrate_add_blocker (v->migration_blocker, &err); +if (unlikely (r <0 )) { + goto err_migration_blocker; + } + } +for (i =0 ; i < v->shadow_vqs->len; ++i) {VirtQueue *vq =virtio_get_queue (dev->vdev, dev->vq_index + i);VhostShadowVirtqueue *svq =g_ptr_array_index (v->shadow_vqs, i);
@@ -1064,6 +1072,9 @@ err:vhost_svq_stop (svq); } +err_migration_blocker: +error_reportf_err (err,"Cannot setup SVQ %u: " , i); +return false; }
@@ -1083,6 +1094,9 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev) } } +if (v->migration_blocker) { +migrate_del_blocker (v->migration_blocker); + }return true; }
Signature · 1 line
2.31.1
Re: [PATCH v4 18/19] vdpa: Add device migration blocker
Quoted 48 lines · Eugenio Pérez
Since the vhost-vdpa device is exposing
_F_LOG, adding a migration blocker if it uses CVQ.Signed-off-by Eugenio Pérez <[email protected]>--- include/hw/virtio/vhost-vdpa.h | 1 + hw/virtio/vhost-vdpa.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+)include/hw/virtio/vhost-vdpa.h +1
-0@@ -35,6 +35,7 @@ typedef struct vhost_vdpa {bool shadow_vqs_enabled;/* IOVA mapping used by the Shadow Virtqueue */ VhostIOVATree *iova_tree; +Error *migration_blocker;GPtrArray *shadow_vqs;const VhostShadowVirtqueueOps *shadow_vq_ops;void *shadow_vq_ops_opaque;hw/virtio/vhost-vdpa.c +8
-0@@ -20,6 +20,7 @@#include "hw/virtio/vhost-shadow-virtqueue.h" #include "hw/virtio/vhost-vdpa.h" #include "exec/address-spaces.h" +#include "migration/blocker.h" #include "qemu/cutils.h" #include "qemu/main-loop.h" #include "cpu.h" @@ -1022,6 +1023,13 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)return true; } +if (v->migration_blocker) { +int r =migrate_add_blocker (v->migration_blocker, &err); +if (unlikely (r <0 )) { + goto err_migration_blocker; + } + } +for (i =0 ; i < v->shadow_vqs->len; ++i) {VirtQueue *vq =virtio_get_queue (dev->vdev, dev->vq_index + i);VhostShadowVirtqueue *svq =g_ptr_array_index (v->shadow_vqs, i);
hw/virtio/vhost-vdpa.c err: · line 1076
Quoted 5 lines
hw/virtio/vhost-vdpa.c +2
-0@@ -1064,6 +1072,9 @@ err:vhost_svq_stop (svq); } +err_migration_blocker: +error_reportf_err (err,"Cannot setup SVQ %u: " , i);
So I got this:
FAILED: libqemu-x86_64-softmmu.fa.p/hw_virtio_vhost-vdpa.c.o
cc -m64 -mcx16 -Ilibqemu-x86_64-softmmu.fa.p -I. -I.. -Itarget/i386 -I../target/i386 -Iqapi -Itrace -Iui -Iui/shader -I/usr/include/pixman-1 -I/usr/include/capstone -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -isystem /home/devel/git/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/devel/git/qemu -iquote /home/devel/git/qemu/include -iquote /home/devel/git/qemu/tcg/i386 -pthread -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -Wstrict-prototypes -Wredundant-decls -Wundef -Wwrite-strings -Wmissing-prototypes -fno-strict-aliasing -fno-common -fwrapv -Wold-style-declaration -Wold-style-definition -Wtype-limits -Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers -Wempty-body -Wnested-externs -Wendif-labels -Wexpansion-to-defined -Wimplicit-fallthrough=2 -Wno-missing-include-dirs -Wno-shift-negative-value -Wno-psabi -fstack-protector-strong -fPIE -isystem../linux-headers -isystemlinux-headers -DNEED_CPU_H '-DCONFIG_TARGET="x86_64-softmmu-config-target.h"' '-DCONFIG_DEVICES="x86_64-softmmu-config-devices.h"' -MD -MQ libqemu-x86_64-softmmu.fa.p/hw_virtio_vhost-vdpa.c.o -MF libqemu-x86_64-softmmu.fa.p/hw_virtio_vhost-vdpa.c.o.d -o libqemu-x86_64-softmmu.fa.p/hw_virtio_vhost-vdpa.c.o -c ../hw/virtio/vhost-vdpa.c ../hw/virtio/vhost-vdpa.c: In function ‘vhost_vdpa_dev_start’:../hw/virtio/vhost-vdpa.c:1076:5: error: ‘i’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
1076 | error_reportf_err(err, "Cannot setup SVQ %u: ", i);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~../hw/virtio/vhost-vdpa.c:1020:14: note: ‘i’ was declared here
1020 | unsigned i;
| ^
cc1: all warnings being treated as errors
And this error is kind of duplicated with the one that is reported in label "err" above.
Thanks
Quoted 14 lines
hw/virtio/vhost-vdpa.c +4
-0+return false; }@@ -1083,6 +1094,9 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev) } } +if (v->migration_blocker) { +migrate_del_blocker (v->migration_blocker); + }return true; }
PATCH v4 19/19 vdpa: Add x-svq to NetdevVhostVDPAOptions
In reply to Eugenio PérezFinally offering the possibility to enable SVQ from the command line.
--- qapi/net.json | 9 +++++- net/vhost-vdpa.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 77 insertions(+), 4 deletions(-)
qapi/net.json +8 -1
@@ -445,12 +445,19 @@ # @queues: number of queues to be created for multiqueue vhost-vdpa # (default: 1) # +# @x-svq: Start device with (experimental) shadow virtqueue. (Since 7.1) +# (default: false) +# +# Features: +# @unstable: Member @x-svq is experimental. +# # Since: 5.1 ## { 'struct': 'NetdevVhostVDPAOptions', 'data': { '*vhostdev': 'str', - '*queues': 'int' } } + '*queues': 'int', + '*x-svq': {'type': 'bool', 'features' : [ 'unstable'] } } } ## # @NetdevVmnetHostOptions:
net/vhost-vdpa.c +69 -3
143 lines not on this page · raw message
Signature · 1 line
2.31.1