From 50764fc8a382dc17ccc06c0ba29184d0fd73016e Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Thu, 10 Sep 2015 13:37:10 +0200 Subject: [PATCH 01/18] virtio: right size for virtio_queue_get_avail_size Being working on dataplane I notice something strange: virtio_queue_get_avail_size() used a 64bit size index for the calculation of the available ring size. It is quite strange but it did work with the old calculation of the avail ring, at most with performance penalty, and I wonder where I missed something. This patch let use a 16bit size as defined in virtio_ring.h Signed-off-by: Pierre Morel Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 0832db9935..730c7f01d9 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -1460,7 +1460,7 @@ hwaddr virtio_queue_get_desc_size(VirtIODevice *vdev, int n) hwaddr virtio_queue_get_avail_size(VirtIODevice *vdev, int n) { return offsetof(VRingAvail, ring) + - sizeof(uint64_t) * vdev->vq[n].vring.num; + sizeof(uint16_t) * vdev->vq[n].vring.num; } hwaddr virtio_queue_get_used_size(VirtIODevice *vdev, int n) From 1f8828ef573c83365b4a87a776daf8bcef1caa21 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 11 Sep 2015 16:01:56 +0800 Subject: [PATCH 02/18] virtio-net: unbreak self announcement and guest offloads after migration After commit 019a3edbb25f1571e876f8af1ce4c55412939e5d ("virtio: make features 64bit wide"). Device's guest_features was actually set after vdc->load(). This breaks the assumption that device specific load() function can check guest_features. For virtio-net, self announcement and guest offloads won't work after migration. Fixing this by defer them to virtio_net_load() where guest_features were guaranteed to be set. Other virtio devices looks fine. Fixes: 019a3edbb25f1571e876f8af1ce4c55412939e5d ("virtio: make features 64bit wide") Cc: qemu-stable@nongnu.org Cc: Gerd Hoffmann Signed-off-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- hw/net/virtio-net.c | 40 +++++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 17 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index f72eebff2b..2775e6a03e 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -1458,11 +1458,33 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id) { VirtIONet *n = opaque; VirtIODevice *vdev = VIRTIO_DEVICE(n); + int ret; if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION) return -EINVAL; - return virtio_load(vdev, f, version_id); + ret = virtio_load(vdev, f, version_id); + if (ret) { + return ret; + } + + if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { + n->curr_guest_offloads = qemu_get_be64(f); + } else { + n->curr_guest_offloads = virtio_net_supported_guest_offloads(n); + } + + if (peer_has_vnet_hdr(n)) { + virtio_net_apply_guest_offloads(n); + } + + if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) && + virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) { + n->announce_counter = SELF_ANNOUNCE_ROUNDS; + timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL)); + } + + return 0; } static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, @@ -1559,16 +1581,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, } } - if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { - n->curr_guest_offloads = qemu_get_be64(f); - } else { - n->curr_guest_offloads = virtio_net_supported_guest_offloads(n); - } - - if (peer_has_vnet_hdr(n)) { - virtio_net_apply_guest_offloads(n); - } - virtio_net_set_queues(n); /* Find the first multicast entry in the saved MAC filter */ @@ -1586,12 +1598,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, qemu_get_subqueue(n->nic, i)->link_down = link_down; } - if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) && - virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) { - n->announce_counter = SELF_ANNOUNCE_ROUNDS; - timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL)); - } - return 0; } From 0b7783a79ef73a06f3a67b68e72d109afe975b77 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Fri, 11 Sep 2015 17:14:23 -0300 Subject: [PATCH 03/18] q35: Move options common to all classes to pc_q35_machine_options() The existing default_machine_opts, default_display, no_floppy, and no_tco settings will still apply to future machine classes. So it makes sense to move them to pc_q35_machine_options() instead of keeping them in a version-specific machine_options function. Signed-off-by: Eduardo Habkost Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/i386/pc_q35.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 11601ab005..966eedb91f 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -364,6 +364,10 @@ static void pc_q35_machine_options(MachineClass *m) m->desc = "Standard PC (Q35 + ICH9, 2009)"; m->hot_add_cpu = pc_hot_add_cpu; m->units_per_default_bus = 1; + m->default_machine_opts = "firmware=bios-256k.bin"; + m->default_display = "std"; + m->no_floppy = 1; + m->no_tco = 0; } static void pc_q35_2_4_machine_options(MachineClass *m) @@ -371,10 +375,6 @@ static void pc_q35_2_4_machine_options(MachineClass *m) PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_options(m); pcmc->broken_reserved_end = true; - m->default_machine_opts = "firmware=bios-256k.bin"; - m->default_display = "std"; - m->no_floppy = 1; - m->no_tco = 0; m->alias = "q35"; } From 254bdb1cbfd467ff9897c75a28a472e4381ce4cf Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Fri, 11 Sep 2015 17:14:24 -0300 Subject: [PATCH 04/18] q35: Move options common to all classes to pc_i440fx_machine_options() The existing default_machine_opts and default_display settings will still apply to future machine classes. So it makes sense to move them to pc_i440fx_machine_options() instead of keeping them in a version-specific machine_options function. Signed-off-by: Eduardo Habkost Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/i386/pc_piix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 3f925b26db..2d9df7c117 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -460,6 +460,8 @@ static void pc_i440fx_machine_options(MachineClass *m) m->family = "pc_piix"; m->desc = "Standard PC (i440FX + PIIX, 1996)"; m->hot_add_cpu = pc_hot_add_cpu; + m->default_machine_opts = "firmware=bios-256k.bin"; + m->default_display = "std"; } static void pc_i440fx_2_4_machine_options(MachineClass *m) @@ -467,8 +469,6 @@ static void pc_i440fx_2_4_machine_options(MachineClass *m) PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_machine_options(m); pcmc->broken_reserved_end = true; - m->default_machine_opts = "firmware=bios-256k.bin"; - m->default_display = "std"; m->alias = "pc"; m->is_default = 1; } From 87e896abe6d926caba19a9b8a83936fca2137f05 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Fri, 11 Sep 2015 17:14:25 -0300 Subject: [PATCH 05/18] pc: Introduce pc-*-2.5 machine classes Signed-off-by: Eduardo Habkost Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/i386/pc_piix.c | 18 +++++++++++++++--- hw/i386/pc_q35.c | 14 ++++++++++++-- include/hw/compat.h | 3 +++ include/hw/i386/pc.h | 4 ++++ 4 files changed, 34 insertions(+), 5 deletions(-) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 2d9df7c117..3ffb05f93e 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -464,13 +464,25 @@ static void pc_i440fx_machine_options(MachineClass *m) m->default_display = "std"; } +static void pc_i440fx_2_5_machine_options(MachineClass *m) +{ + pc_i440fx_machine_options(m); + m->alias = "pc"; + m->is_default = 1; +} + +DEFINE_I440FX_MACHINE(v2_5, "pc-i440fx-2.5", NULL, + pc_i440fx_2_5_machine_options); + + static void pc_i440fx_2_4_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_i440fx_machine_options(m); + pc_i440fx_2_5_machine_options(m); + m->alias = NULL; + m->is_default = 0; pcmc->broken_reserved_end = true; - m->alias = "pc"; - m->is_default = 1; + SET_MACHINE_COMPAT(m, PC_COMPAT_2_4); } DEFINE_I440FX_MACHINE(v2_4, "pc-i440fx-2.4", NULL, diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 966eedb91f..1b7d3b644e 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -370,12 +370,22 @@ static void pc_q35_machine_options(MachineClass *m) m->no_tco = 0; } +static void pc_q35_2_5_machine_options(MachineClass *m) +{ + pc_q35_machine_options(m); + m->alias = "q35"; +} + +DEFINE_Q35_MACHINE(v2_5, "pc-q35-2.5", NULL, + pc_q35_2_5_machine_options); + static void pc_q35_2_4_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_machine_options(m); + pc_q35_2_5_machine_options(m); + m->alias = NULL; pcmc->broken_reserved_end = true; - m->alias = "q35"; + SET_MACHINE_COMPAT(m, PC_COMPAT_2_4); } DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL, diff --git a/include/hw/compat.h b/include/hw/compat.h index 94c8097d0c..095de5d12f 100644 --- a/include/hw/compat.h +++ b/include/hw/compat.h @@ -1,6 +1,9 @@ #ifndef HW_COMPAT_H #define HW_COMPAT_H +#define HW_COMPAT_2_4 \ + /* empty */ + #define HW_COMPAT_2_3 \ {\ .driver = "virtio-blk-pci",\ diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 3e002c9da6..6896328aa0 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -291,7 +291,11 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t); int e820_get_num_entries(void); bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); +#define PC_COMPAT_2_4 \ + HW_COMPAT_2_4 + #define PC_COMPAT_2_3 \ + PC_COMPAT_2_4 \ HW_COMPAT_2_3 \ {\ .driver = TYPE_X86_CPU,\ From 46c5d0823d0186daf4064065bf739858dadfcf8c Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Fri, 11 Sep 2015 15:16:41 +0200 Subject: [PATCH 06/18] virtio: ring sizes vs. reset We allow guests to change the size of the virtqueue rings by supplying a number of buffers that is different from the number of buffers the device was initialized with. Current code has some problems, however, since reset does not reset the ringsizes to the default values (as this is not saved anywhere). Let's extend the core code to keep track of the default ringsizes and migrate them once the guest changed them for any of the virtqueues for a device. Reviewed-by: Jason Wang Signed-off-by: Cornelia Huck Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 730c7f01d9..7504f8b33a 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -60,6 +60,7 @@ typedef struct VRingUsed typedef struct VRing { unsigned int num; + unsigned int num_default; unsigned int align; hwaddr desc; hwaddr avail; @@ -633,6 +634,7 @@ void virtio_reset(void *opaque) vdev->vq[i].signalled_used = 0; vdev->vq[i].signalled_used_valid = false; vdev->vq[i].notification = true; + vdev->vq[i].vring.num = vdev->vq[i].vring.num_default; } } @@ -964,6 +966,7 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size, abort(); vdev->vq[i].vring.num = queue_size; + vdev->vq[i].vring.num_default = queue_size; vdev->vq[i].vring.align = VIRTIO_PCI_VRING_ALIGN; vdev->vq[i].handle_output = handle_output; @@ -977,6 +980,7 @@ void virtio_del_queue(VirtIODevice *vdev, int n) } vdev->vq[n].vring.num = 0; + vdev->vq[n].vring.num_default = 0; } void virtio_irq(VirtQueue *vq) @@ -1056,6 +1060,19 @@ static bool virtio_virtqueue_needed(void *opaque) return virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1); } +static bool virtio_ringsize_needed(void *opaque) +{ + VirtIODevice *vdev = opaque; + int i; + + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + if (vdev->vq[i].vring.num != vdev->vq[i].vring.num_default) { + return true; + } + } + return false; +} + static void put_virtqueue_state(QEMUFile *f, void *pv, size_t size) { VirtIODevice *vdev = pv; @@ -1104,6 +1121,52 @@ static const VMStateDescription vmstate_virtio_virtqueues = { } }; +static void put_ringsize_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIODevice *vdev = pv; + int i; + + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + qemu_put_be32(f, vdev->vq[i].vring.num_default); + } +} + +static int get_ringsize_state(QEMUFile *f, void *pv, size_t size) +{ + VirtIODevice *vdev = pv; + int i; + + for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { + vdev->vq[i].vring.num_default = qemu_get_be32(f); + } + return 0; +} + +static VMStateInfo vmstate_info_ringsize = { + .name = "ringsize_state", + .get = get_ringsize_state, + .put = put_ringsize_state, +}; + +static const VMStateDescription vmstate_virtio_ringsize = { + .name = "virtio/ringsize", + .version_id = 1, + .minimum_version_id = 1, + .needed = &virtio_ringsize_needed, + .fields = (VMStateField[]) { + { + .name = "ringsize", + .version_id = 0, + .field_exists = NULL, + .size = 0, + .info = &vmstate_info_ringsize, + .flags = VMS_SINGLE, + .offset = 0, + }, + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_virtio_device_endian = { .name = "virtio/device_endian", .version_id = 1, @@ -1138,6 +1201,7 @@ static const VMStateDescription vmstate_virtio = { &vmstate_virtio_device_endian, &vmstate_virtio_64bit_features, &vmstate_virtio_virtqueues, + &vmstate_virtio_ringsize, NULL } }; From 79cd0c80f82215a32890e3d30ff621b32ece5156 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Fri, 11 Sep 2015 15:16:42 +0200 Subject: [PATCH 07/18] virtio-ccw: support ring size changes Wire up changing the ring size for virtio-1 devices. Signed-off-by: Cornelia Huck Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/s390x/virtio-ccw.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index d36373e88a..85e2a5d29e 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -307,11 +307,18 @@ static int virtio_ccw_set_vqs(SubchDev *sch, VqInfoBlock *info, if (!desc) { virtio_queue_set_vector(vdev, index, VIRTIO_NO_VECTOR); } else { - /* Fail if we don't have a big enough queue. */ - /* TODO: Add interface to handle vring.num changing */ - if (virtio_queue_get_num(vdev, index) > num) { + if (info) { + /* virtio-1 allows changing the ring size. */ + if (virtio_queue_get_num(vdev, index) < num) { + /* Fail if we exceed the maximum number. */ + return -EINVAL; + } + virtio_queue_set_num(vdev, index, num); + } else if (virtio_queue_get_num(vdev, index) > num) { + /* Fail if we don't have a big enough queue. */ return -EINVAL; } + /* We ignore possible increased num for legacy for compatibility. */ virtio_queue_set_vector(vdev, index, index); } /* tell notify handler in case of config change */ From b4f8f9df152fca0e79b7a3ca40a3eea700a40855 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Fri, 11 Sep 2015 15:16:43 +0200 Subject: [PATCH 08/18] virtio-ccw: feature bits > 31 handling We currently switch off the VERSION_1 feature bit if the guest has not negotiated at least revision 1. As no feature bits beyond 31 are valid however unless VERSION_1 has been negotiated, make sure that legacy guests never see a feature bit beyond 31. Reviewed-by: David Hildenbrand Signed-off-by: Cornelia Huck Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/s390x/virtio-ccw.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index 85e2a5d29e..eed7b3e0f6 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -468,15 +468,12 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) NULL); if (features.index == 0) { features.features = (uint32_t)vdev->host_features; - } else if (features.index == 1) { - features.features = (uint32_t)(vdev->host_features >> 32); + } else if ((features.index == 1) && (dev->revision >= 1)) { /* - * Don't offer version 1 to the guest if it did not - * negotiate at least revision 1. + * Only offer feature bits beyond 31 if the guest has + * negotiated at least revision 1. */ - if (dev->revision <= 0) { - features.features &= ~(1 << (VIRTIO_F_VERSION_1 - 32)); - } + features.features = (uint32_t)(vdev->host_features >> 32); } else { /* Return zeroes if the guest supports more feature bits. */ features.features = 0; @@ -515,14 +512,12 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) virtio_set_features(vdev, (vdev->guest_features & 0xffffffff00000000ULL) | features.features); - } else if (features.index == 1) { + } else if ((features.index == 1) && (dev->revision >= 1)) { /* - * The guest should not set version 1 if it didn't - * negotiate a revision >= 1. + * If the guest did not negotiate at least revision 1, + * we did not offer it any feature bits beyond 31. Such a + * guest passing us any bit here is therefore buggy. */ - if (dev->revision <= 0) { - features.features &= ~(1 << (VIRTIO_F_VERSION_1 - 32)); - } virtio_set_features(vdev, (vdev->guest_features & 0x00000000ffffffffULL) | ((uint64_t)features.features << 32)); From 542571d523268357fd8f5b1a523ba2a6191c4c18 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Fri, 11 Sep 2015 15:16:44 +0200 Subject: [PATCH 09/18] virtio-ccw: enable virtio-1 Let's enable revision 1 for virtio-ccw devices. We can always offer VERSION_1 as drivers in legacy mode won't be able to see it anyway. We have to introduce a way to set a lower maximum revision for a device to accommodate the following cases: - compat machines (to enforce legacy only) - virtio-blk with scsi support (version 1 + scsi is fenced by common code, with a user-configured max revision of 0 we can allow scsi via not offering VERSION_1) Signed-off-by: Cornelia Huck Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/s390x/s390-virtio-ccw.c | 20 ++++++++++++++++++++ hw/s390x/virtio-ccw.c | 30 ++++++++++++++++++++++++++++-- hw/s390x/virtio-ccw.h | 6 ++++-- 3 files changed, 52 insertions(+), 4 deletions(-) diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 36f78b417c..c53ebc1ae1 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -242,6 +242,26 @@ static const TypeInfo ccw_machine_info = { .driver = TYPE_S390_SKEYS,\ .property = "migration-enabled",\ .value = "off",\ + },{\ + .driver = "virtio-blk-ccw",\ + .property = "max_revision",\ + .value = "0",\ + },{\ + .driver = "virtio-balloon-ccw",\ + .property = "max_revision",\ + .value = "0",\ + },{\ + .driver = "virtio-serial-ccw",\ + .property = "max_revision",\ + .value = "0",\ + },{\ + .driver = "virtio-9p-ccw",\ + .property = "max_revision",\ + .value = "0",\ + },{\ + .driver = "virtio-rng-ccw",\ + .property = "max_revision",\ + .value = "0",\ }, static void ccw_machine_2_4_class_init(ObjectClass *oc, void *data) diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index eed7b3e0f6..fb103b78ac 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -467,7 +467,13 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) MEMTXATTRS_UNSPECIFIED, NULL); if (features.index == 0) { - features.features = (uint32_t)vdev->host_features; + if (dev->revision >= 1) { + /* Don't offer legacy features for modern devices. */ + features.features = (uint32_t) + (vdev->host_features & ~VIRTIO_LEGACY_FEATURES); + } else { + features.features = (uint32_t)vdev->host_features; + } } else if ((features.index == 1) && (dev->revision >= 1)) { /* * Only offer feature bits beyond 31 if the guest has @@ -768,7 +774,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) * need to fetch it here. Nothing to do for now, though. */ if (dev->revision >= 0 || - revinfo.revision > virtio_ccw_rev_max(vdev)) { + revinfo.revision > virtio_ccw_rev_max(dev)) { ret = -ENOSYS; break; } @@ -1541,6 +1547,10 @@ static void virtio_ccw_device_plugged(DeviceState *d, Error **errp) sch->id.cu_model = virtio_bus_get_vdev_id(&dev->bus); + if (dev->max_rev >= 1) { + virtio_add_feature(&vdev->host_features, VIRTIO_F_VERSION_1); + } + css_generate_sch_crws(sch->cssid, sch->ssid, sch->schid, d->hotplugged, 1); } @@ -1557,6 +1567,8 @@ static Property virtio_ccw_net_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1584,6 +1596,8 @@ static Property virtio_ccw_blk_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1611,6 +1625,8 @@ static Property virtio_ccw_serial_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1638,6 +1654,8 @@ static Property virtio_ccw_balloon_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1665,6 +1683,8 @@ static Property virtio_ccw_scsi_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1691,6 +1711,8 @@ static const TypeInfo virtio_ccw_scsi = { #ifdef CONFIG_VHOST_SCSI static Property vhost_ccw_scsi_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1729,6 +1751,8 @@ static Property virtio_ccw_rng_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; @@ -1882,6 +1906,8 @@ static Property virtio_ccw_9p_properties[] = { DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id), DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags, VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev, + VIRTIO_CCW_MAX_REV), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h index 692ddd7318..7ab8367baa 100644 --- a/hw/s390x/virtio-ccw.h +++ b/hw/s390x/virtio-ccw.h @@ -88,6 +88,7 @@ struct VirtioCcwDevice { SubchDev *sch; char *bus_id; int revision; + uint32_t max_rev; VirtioBusState bus; bool ioeventfd_started; bool ioeventfd_disabled; @@ -102,9 +103,10 @@ struct VirtioCcwDevice { }; /* The maximum virtio revision we support. */ -static inline int virtio_ccw_rev_max(VirtIODevice *vdev) +#define VIRTIO_CCW_MAX_REV 1 +static inline int virtio_ccw_rev_max(VirtioCcwDevice *dev) { - return 0; + return dev->max_rev; } /* virtual css bus type */ From 7305483a3d113456681ba6c6e8dd41513decd5f6 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 23 Sep 2015 12:19:55 +0800 Subject: [PATCH 10/18] vhost-user: use VHOST_USER_XXX macro for switch statement So that we could let vhost_user_call to handle extented requests, such as VHOST_USER_GET/SET_PROTOCOL_FEATURES, instead of invoking vhost_user_read/write and constructing the msg again by ourself. Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Marcel Apfelbaum Tested-by: Marcel Apfelbaum --- hw/virtio/vhost-user.c | 38 ++++++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 16 deletions(-) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index e7ab8293d1..13677ac118 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -193,27 +193,33 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); - msg_request = vhost_user_request_translate(request); + /* only translate vhost ioctl requests */ + if (request > VHOST_USER_MAX) { + msg_request = vhost_user_request_translate(request); + } else { + msg_request = request; + } + msg.request = msg_request; msg.flags = VHOST_USER_VERSION; msg.size = 0; - switch (request) { - case VHOST_GET_FEATURES: + switch (msg_request) { + case VHOST_USER_GET_FEATURES: need_reply = 1; break; - case VHOST_SET_FEATURES: - case VHOST_SET_LOG_BASE: + case VHOST_USER_SET_FEATURES: + case VHOST_USER_SET_LOG_BASE: msg.u64 = *((__u64 *) arg); msg.size = sizeof(m.u64); break; - case VHOST_SET_OWNER: - case VHOST_RESET_OWNER: + case VHOST_USER_SET_OWNER: + case VHOST_USER_RESET_OWNER: break; - case VHOST_SET_MEM_TABLE: + case VHOST_USER_SET_MEM_TABLE: for (i = 0; i < dev->mem->nregions; ++i) { struct vhost_memory_region *reg = dev->mem->regions + i; ram_addr_t ram_addr; @@ -246,30 +252,30 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, break; - case VHOST_SET_LOG_FD: + case VHOST_USER_SET_LOG_FD: fds[fd_num++] = *((int *) arg); break; - case VHOST_SET_VRING_NUM: - case VHOST_SET_VRING_BASE: + case VHOST_USER_SET_VRING_NUM: + case VHOST_USER_SET_VRING_BASE: memcpy(&msg.state, arg, sizeof(struct vhost_vring_state)); msg.size = sizeof(m.state); break; - case VHOST_GET_VRING_BASE: + case VHOST_USER_GET_VRING_BASE: memcpy(&msg.state, arg, sizeof(struct vhost_vring_state)); msg.size = sizeof(m.state); need_reply = 1; break; - case VHOST_SET_VRING_ADDR: + case VHOST_USER_SET_VRING_ADDR: memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr)); msg.size = sizeof(m.addr); break; - case VHOST_SET_VRING_KICK: - case VHOST_SET_VRING_CALL: - case VHOST_SET_VRING_ERR: + case VHOST_USER_SET_VRING_KICK: + case VHOST_USER_SET_VRING_CALL: + case VHOST_USER_SET_VRING_ERR: file = arg; msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK; msg.size = sizeof(m.u64); From dcb10c000cdd4d14f5ac4f07b04fb666494ef4a8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 23 Sep 2015 12:19:56 +0800 Subject: [PATCH 11/18] vhost-user: add protocol feature negotiation Support a separate bitmask for vhost-user protocol features, and messages to get/set protocol features. Invoke them at init. No features are defined yet. [ leverage vhost_user_call for request handling -- Yuanhan Liu ] Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Marcel Apfelbaum Tested-by: Marcel Apfelbaum --- docs/specs/vhost-user.txt | 37 +++++++++++++++++++++++++++++++++++++ hw/net/vhost_net.c | 2 ++ hw/virtio/vhost-user.c | 31 +++++++++++++++++++++++++++++++ include/hw/virtio/vhost.h | 1 + 4 files changed, 71 insertions(+) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index 650bb18186..70da3b197e 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -113,6 +113,7 @@ message replies. Most of the requests don't require replies. Here is a list of the ones that do: * VHOST_GET_FEATURES + * VHOST_GET_PROTOCOL_FEATURES * VHOST_GET_VRING_BASE There are several messages that the master sends with file descriptors passed @@ -127,6 +128,13 @@ in the ancillary data: If Master is unable to send the full message or receives a wrong reply it will close the connection. An optional reconnection mechanism can be implemented. +Any protocol extensions are gated by protocol feature bits, +which allows full backwards compatibility on both master +and slave. +As older slaves don't support negotiating protocol features, +a feature bit was dedicated for this purpose: +#define VHOST_USER_F_PROTOCOL_FEATURES 30 + Message types ------------- @@ -138,6 +146,8 @@ Message types Slave payload: u64 Get from the underlying vhost implementation the features bitmask. + Feature bit VHOST_USER_F_PROTOCOL_FEATURES signals slave support for + VHOST_USER_GET_PROTOCOL_FEATURES and VHOST_USER_SET_PROTOCOL_FEATURES. * VHOST_USER_SET_FEATURES @@ -146,6 +156,33 @@ Message types Master payload: u64 Enable features in the underlying vhost implementation using a bitmask. + Feature bit VHOST_USER_F_PROTOCOL_FEATURES signals slave support for + VHOST_USER_GET_PROTOCOL_FEATURES and VHOST_USER_SET_PROTOCOL_FEATURES. + + * VHOST_USER_GET_PROTOCOL_FEATURES + + Id: 15 + Equivalent ioctl: VHOST_GET_FEATURES + Master payload: N/A + Slave payload: u64 + + Get the protocol feature bitmask from the underlying vhost implementation. + Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in + VHOST_USER_GET_FEATURES. + Note: slave that reported VHOST_USER_F_PROTOCOL_FEATURES must support + this message even before VHOST_USER_SET_FEATURES was called. + + * VHOST_USER_SET_PROTOCOL_FEATURES + + Id: 16 + Ioctl: VHOST_SET_FEATURES + Master payload: u64 + + Enable protocol features in the underlying vhost implementation. + Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in + VHOST_USER_GET_FEATURES. + Note: slave that reported VHOST_USER_F_PROTOCOL_FEATURES must support + this message even before VHOST_USER_SET_FEATURES was called. * VHOST_USER_SET_OWNER diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 1d76b94c84..9d32d76abb 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -152,8 +152,10 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) net->dev.backend_features = qemu_has_vnet_hdr(options->net_backend) ? 0 : (1ULL << VHOST_NET_F_VIRTIO_NET_HDR); net->backend = r; + net->dev.protocol_features = 0; } else { net->dev.backend_features = 0; + net->dev.protocol_features = 0; net->backend = -1; } net->nc = options->net_backend; diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 13677ac118..7fe35c6500 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -24,6 +24,8 @@ #include #define VHOST_MEMORY_MAX_NREGIONS 8 +#define VHOST_USER_F_PROTOCOL_FEATURES 30 +#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x0ULL typedef enum VhostUserRequest { VHOST_USER_NONE = 0, @@ -41,6 +43,8 @@ typedef enum VhostUserRequest { VHOST_USER_SET_VRING_KICK = 12, VHOST_USER_SET_VRING_CALL = 13, VHOST_USER_SET_VRING_ERR = 14, + VHOST_USER_GET_PROTOCOL_FEATURES = 15, + VHOST_USER_SET_PROTOCOL_FEATURES = 16, VHOST_USER_MAX } VhostUserRequest; @@ -206,11 +210,13 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, switch (msg_request) { case VHOST_USER_GET_FEATURES: + case VHOST_USER_GET_PROTOCOL_FEATURES: need_reply = 1; break; case VHOST_USER_SET_FEATURES: case VHOST_USER_SET_LOG_BASE: + case VHOST_USER_SET_PROTOCOL_FEATURES: msg.u64 = *((__u64 *) arg); msg.size = sizeof(m.u64); break; @@ -308,6 +314,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, switch (msg_request) { case VHOST_USER_GET_FEATURES: + case VHOST_USER_GET_PROTOCOL_FEATURES: if (msg.size != sizeof(m.u64)) { error_report("Received bad msg size."); return -1; @@ -333,10 +340,34 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, static int vhost_user_init(struct vhost_dev *dev, void *opaque) { + unsigned long long features; + int err; + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); dev->opaque = opaque; + err = vhost_user_call(dev, VHOST_USER_GET_FEATURES, &features); + if (err < 0) { + return err; + } + + if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) { + dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES; + + err = vhost_user_call(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &features); + if (err < 0) { + return err; + } + + dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK; + err = vhost_user_call(dev, VHOST_USER_SET_PROTOCOL_FEATURES, + &dev->protocol_features); + if (err < 0) { + return err; + } + } + return 0; } diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index dd510509eb..6467c73ecf 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -47,6 +47,7 @@ struct vhost_dev { unsigned long long features; unsigned long long acked_features; unsigned long long backend_features; + unsigned long long protocol_features; bool started; bool log_enabled; unsigned long long log_size; From d1f8b30ec8dde0318fd1b98d24a64926feae9625 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 23 Sep 2015 12:19:57 +0800 Subject: [PATCH 12/18] vhost: rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE Quote from Michael: We really should rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE. Suggested-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Marcel Apfelbaum Tested-by: Marcel Apfelbaum --- docs/specs/vhost-user.txt | 4 ++-- hw/net/vhost_net.c | 2 +- hw/virtio/vhost-user.c | 6 +++--- linux-headers/linux/vhost.h | 2 +- tests/vhost-user-test.c | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index 70da3b197e..ccbbcbb70e 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -194,10 +194,10 @@ Message types as an owner of the session. This can be used on the Slave as a "session start" flag. - * VHOST_USER_RESET_OWNER + * VHOST_USER_RESET_DEVICE Id: 4 - Equivalent ioctl: VHOST_RESET_OWNER + Equivalent ioctl: VHOST_RESET_DEVICE Master payload: N/A Issued when a new connection is about to be closed. The Master will no diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 9d32d76abb..b7d29b7cf4 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -287,7 +287,7 @@ static void vhost_net_stop_one(struct vhost_net *net, } else if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { for (file.index = 0; file.index < net->dev.nvqs; ++file.index) { const VhostOps *vhost_ops = net->dev.vhost_ops; - int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_OWNER, + int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_DEVICE, NULL); assert(r >= 0); } diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 7fe35c6500..9cb2f52eb7 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -32,7 +32,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_FEATURES = 1, VHOST_USER_SET_FEATURES = 2, VHOST_USER_SET_OWNER = 3, - VHOST_USER_RESET_OWNER = 4, + VHOST_USER_RESET_DEVICE = 4, VHOST_USER_SET_MEM_TABLE = 5, VHOST_USER_SET_LOG_BASE = 6, VHOST_USER_SET_LOG_FD = 7, @@ -98,7 +98,7 @@ static unsigned long int ioctl_to_vhost_user_request[VHOST_USER_MAX] = { VHOST_GET_FEATURES, /* VHOST_USER_GET_FEATURES */ VHOST_SET_FEATURES, /* VHOST_USER_SET_FEATURES */ VHOST_SET_OWNER, /* VHOST_USER_SET_OWNER */ - VHOST_RESET_OWNER, /* VHOST_USER_RESET_OWNER */ + VHOST_RESET_DEVICE, /* VHOST_USER_RESET_DEVICE */ VHOST_SET_MEM_TABLE, /* VHOST_USER_SET_MEM_TABLE */ VHOST_SET_LOG_BASE, /* VHOST_USER_SET_LOG_BASE */ VHOST_SET_LOG_FD, /* VHOST_USER_SET_LOG_FD */ @@ -222,7 +222,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, break; case VHOST_USER_SET_OWNER: - case VHOST_USER_RESET_OWNER: + case VHOST_USER_RESET_DEVICE: break; case VHOST_USER_SET_MEM_TABLE: diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index ead86db91a..14a01602f8 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -78,7 +78,7 @@ struct vhost_memory { #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) /* Give up ownership, and reset the device to default values. * Allows subsequent call to VHOST_OWNER_SET to succeed. */ -#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) +#define VHOST_RESET_DEVICE _IO(VHOST_VIRTIO, 0x02) /* Set up/modify memory layout */ #define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory) diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c index 75fedf0977..e301db79b9 100644 --- a/tests/vhost-user-test.c +++ b/tests/vhost-user-test.c @@ -58,7 +58,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_FEATURES = 1, VHOST_USER_SET_FEATURES = 2, VHOST_USER_SET_OWNER = 3, - VHOST_USER_RESET_OWNER = 4, + VHOST_USER_RESET_DEVICE = 4, VHOST_USER_SET_MEM_TABLE = 5, VHOST_USER_SET_LOG_BASE = 6, VHOST_USER_SET_LOG_FD = 7, From e2051e9e004649b53af4db34f78c689fb44e075b Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 23 Sep 2015 12:19:58 +0800 Subject: [PATCH 13/18] vhost-user: add VHOST_USER_GET_QUEUE_NUM message This is for querying how many queues the backend supports if it has mq support(when VHOST_USER_PROTOCOL_F_MQ flag is set from the quried protocol features). vhost_net_get_max_queues() is the interface to export that value, and to tell if the backend supports # of queues user requested, which is done in the following patch. Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Tested-by: Marcel Apfelbaum --- docs/specs/vhost-user.txt | 11 +++++++++++ hw/net/vhost_net.c | 12 ++++++++++++ hw/virtio/vhost-user.c | 15 ++++++++++++++- include/hw/virtio/vhost.h | 1 + include/net/vhost_net.h | 1 + 5 files changed, 39 insertions(+), 1 deletion(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index ccbbcbb70e..43db9b4100 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -301,3 +301,14 @@ Message types Bits (0-7) of the payload contain the vring index. Bit 8 is the invalid FD flag. This flag is set when there is no file descriptor in the ancillary data. + + * VHOST_USER_GET_QUEUE_NUM + + Id: 17 + Equivalent ioctl: N/A + Master payload: N/A + Slave payload: u64 + + Query how many queues the backend supports. This request should be + sent only when VHOST_USER_PROTOCOL_F_MQ is set in quried protocol + features by VHOST_USER_GET_PROTOCOL_FEATURES. diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index b7d29b7cf4..f663e5a505 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -122,6 +122,11 @@ void vhost_net_ack_features(struct vhost_net *net, uint64_t features) vhost_ack_features(&net->dev, vhost_net_get_feature_bits(net), features); } +uint64_t vhost_net_get_max_queues(VHostNetState *net) +{ + return net->dev.max_queues; +} + static int vhost_net_get_fd(NetClientState *backend) { switch (backend->info->type) { @@ -144,6 +149,8 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) goto fail; } + net->dev.max_queues = 1; + if (backend_kernel) { r = vhost_net_get_fd(options->net_backend); if (r < 0) { @@ -414,6 +421,11 @@ VHostNetState *get_vhost_net(NetClientState *nc) return vhost_net; } #else +uint64_t vhost_net_get_max_queues(VHostNetState *net) +{ + return 1; +} + struct vhost_net *vhost_net_init(VhostNetOptions *options) { error_report("vhost-net support is not compiled in"); diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 9cb2f52eb7..694fde5bf6 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -25,7 +25,9 @@ #define VHOST_MEMORY_MAX_NREGIONS 8 #define VHOST_USER_F_PROTOCOL_FEATURES 30 -#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x0ULL +#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x1ULL + +#define VHOST_USER_PROTOCOL_F_MQ 0 typedef enum VhostUserRequest { VHOST_USER_NONE = 0, @@ -45,6 +47,7 @@ typedef enum VhostUserRequest { VHOST_USER_SET_VRING_ERR = 14, VHOST_USER_GET_PROTOCOL_FEATURES = 15, VHOST_USER_SET_PROTOCOL_FEATURES = 16, + VHOST_USER_GET_QUEUE_NUM = 17, VHOST_USER_MAX } VhostUserRequest; @@ -211,6 +214,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, switch (msg_request) { case VHOST_USER_GET_FEATURES: case VHOST_USER_GET_PROTOCOL_FEATURES: + case VHOST_USER_GET_QUEUE_NUM: need_reply = 1; break; @@ -315,6 +319,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, switch (msg_request) { case VHOST_USER_GET_FEATURES: case VHOST_USER_GET_PROTOCOL_FEATURES: + case VHOST_USER_GET_QUEUE_NUM: if (msg.size != sizeof(m.u64)) { error_report("Received bad msg size."); return -1; @@ -366,6 +371,14 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque) if (err < 0) { return err; } + + /* query the max queues we support if backend supports Multiple Queue */ + if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) { + err = vhost_user_call(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues); + if (err < 0) { + return err; + } + } } return 0; diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index 6467c73ecf..c3758f3c78 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -48,6 +48,7 @@ struct vhost_dev { unsigned long long acked_features; unsigned long long backend_features; unsigned long long protocol_features; + unsigned long long max_queues; bool started; bool log_enabled; unsigned long long log_size; diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h index 840d4b16e2..8db723e54b 100644 --- a/include/net/vhost_net.h +++ b/include/net/vhost_net.h @@ -13,6 +13,7 @@ typedef struct VhostNetOptions { void *opaque; } VhostNetOptions; +uint64_t vhost_net_get_max_queues(VHostNetState *net); struct vhost_net *vhost_net_init(VhostNetOptions *options); int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, int total_queues); From fc57fd9900dc6344b8833e7641f63cddc6840301 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 23 Sep 2015 12:19:59 +0800 Subject: [PATCH 14/18] vhost: introduce vhost_backend_get_vq_index method Minusing the idx with the base(dev->vq_index) for vhost-kernel, and then adding it back for vhost-user doesn't seem right. Here introduces a new method vhost_backend_get_vq_index() for getting the right vq index for following vhost messages calls. Suggested-by: Jason Wang Signed-off-by: Yuanhan Liu Reviewed-by: Jason Wang Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Tested-by: Marcel Apfelbaum --- hw/virtio/vhost-backend.c | 10 +++++++++- hw/virtio/vhost-user.c | 12 ++++++++++-- hw/virtio/vhost.c | 15 ++++++--------- include/hw/virtio/vhost-backend.h | 2 ++ 4 files changed, 27 insertions(+), 12 deletions(-) diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 4d68a27658..72d1392b35 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -42,11 +42,19 @@ static int vhost_kernel_cleanup(struct vhost_dev *dev) return close(fd); } +static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx) +{ + assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + + return idx - dev->vq_index; +} + static const VhostOps kernel_ops = { .backend_type = VHOST_BACKEND_TYPE_KERNEL, .vhost_call = vhost_kernel_call, .vhost_backend_init = vhost_kernel_init, - .vhost_backend_cleanup = vhost_kernel_cleanup + .vhost_backend_cleanup = vhost_kernel_cleanup, + .vhost_backend_get_vq_index = vhost_kernel_get_vq_index, }; int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 694fde5bf6..5018fd6422 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -393,9 +393,17 @@ static int vhost_user_cleanup(struct vhost_dev *dev) return 0; } +static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx) +{ + assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + + return idx; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, .vhost_call = vhost_user_call, .vhost_backend_init = vhost_user_init, - .vhost_backend_cleanup = vhost_user_cleanup - }; + .vhost_backend_cleanup = vhost_user_cleanup, + .vhost_backend_get_vq_index = vhost_user_get_vq_index, +}; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index a08c36bb45..7a7812d33f 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -719,7 +719,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, { hwaddr s, l, a; int r; - int vhost_vq_index = idx - dev->vq_index; + int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx); struct vhost_vring_file file = { .index = vhost_vq_index }; @@ -728,7 +728,6 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, }; struct VirtQueue *vvq = virtio_get_queue(vdev, idx); - assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); vq->num = state.num = virtio_queue_get_num(vdev, idx); r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_NUM, &state); @@ -822,12 +821,12 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned idx) { - int vhost_vq_index = idx - dev->vq_index; + int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx); struct vhost_vring_state state = { .index = vhost_vq_index, }; int r; - assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs); + r = dev->vhost_ops->vhost_call(dev, VHOST_GET_VRING_BASE, &state); if (r < 0) { fprintf(stderr, "vhost VQ %d ring restore failed: %d\n", idx, r); @@ -1066,17 +1065,15 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, { struct VirtQueue *vvq = virtio_get_queue(vdev, n); int r, index = n - hdev->vq_index; + struct vhost_vring_file file; - assert(n >= hdev->vq_index && n < hdev->vq_index + hdev->nvqs); - - struct vhost_vring_file file = { - .index = index - }; if (mask) { file.fd = event_notifier_get_fd(&hdev->vqs[index].masked_notifier); } else { file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq)); } + + file.index = hdev->vhost_ops->vhost_backend_get_vq_index(hdev, n); r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_VRING_CALL, &file); assert(r >= 0); } diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index e472f29714..e1dfc6dd73 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -24,12 +24,14 @@ typedef int (*vhost_call)(struct vhost_dev *dev, unsigned long int request, void *arg); typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque); typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev); +typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx); typedef struct VhostOps { VhostBackendType backend_type; vhost_call vhost_call; vhost_backend_init vhost_backend_init; vhost_backend_cleanup vhost_backend_cleanup; + vhost_backend_get_vq_index vhost_backend_get_vq_index; } VhostOps; extern const VhostOps user_ops; From b931bfbf042983f311b3b09894d8030b2755a638 Mon Sep 17 00:00:00 2001 From: Changchun Ouyang Date: Wed, 23 Sep 2015 12:20:00 +0800 Subject: [PATCH 15/18] vhost-user: add multiple queue support This patch is initially based a patch from Nikolay Nikolaev. This patch adds vhost-user multiple queue support, by creating a nc and vhost_net pair for each queue. Qemu exits if find that the backend can't support the number of requested queues (by providing queues=# option). The max number is queried by a new message, VHOST_USER_GET_QUEUE_NUM, and is sent only when protocol feature VHOST_USER_PROTOCOL_F_MQ is present first. The max queue check is done at vhost-user initiation stage. We initiate one queue first, which, in the meantime, also gets the max_queues the backend supports. In older version, it was reported that some messages are sent more times than necessary. Here we came an agreement with Michael that we could categorize vhost user messages to 2 types: non-vring specific messages, which should be sent only once, and vring specific messages, which should be sent per queue. Here I introduced a helper function vhost_user_one_time_request(), which lists following messages as non-vring specific messages: VHOST_USER_SET_OWNER VHOST_USER_RESET_DEVICE VHOST_USER_SET_MEM_TABLE VHOST_USER_GET_QUEUE_NUM For above messages, we simply ignore them when they are not sent the first time. Signed-off-by: Nikolay Nikolaev Signed-off-by: Changchun Ouyang Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Jason Wang Tested-by: Marcel Apfelbaum --- docs/specs/vhost-user.txt | 15 ++++ hw/net/vhost_net.c | 10 +-- hw/virtio/vhost-user.c | 22 ++++++ hw/virtio/vhost.c | 5 +- net/vhost-user.c | 143 +++++++++++++++++++++++++------------- qapi-schema.json | 6 +- qemu-options.hx | 5 +- 7 files changed, 148 insertions(+), 58 deletions(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index 43db9b4100..cfc9d411ff 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -135,6 +135,21 @@ As older slaves don't support negotiating protocol features, a feature bit was dedicated for this purpose: #define VHOST_USER_F_PROTOCOL_FEATURES 30 +Multiple queue support +---------------------- + +Multiple queue is treated as a protocol extension, hence the slave has to +implement protocol features first. The multiple queues feature is supported +only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set: +#define VHOST_USER_PROTOCOL_F_MQ 0 + +The max number of queues the slave supports can be queried with message +VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of +requested queues is bigger than that. + +As all queues share one connection, the master uses a unique index for each +queue in the sent message to identify a specified queue. + Message types ------------- diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index f663e5a505..ad82b5cce6 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -148,8 +148,11 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) fprintf(stderr, "vhost-net requires net backend to be setup\n"); goto fail; } + net->nc = options->net_backend; net->dev.max_queues = 1; + net->dev.nvqs = 2; + net->dev.vqs = net->vqs; if (backend_kernel) { r = vhost_net_get_fd(options->net_backend); @@ -164,11 +167,10 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) net->dev.backend_features = 0; net->dev.protocol_features = 0; net->backend = -1; - } - net->nc = options->net_backend; - net->dev.nvqs = 2; - net->dev.vqs = net->vqs; + /* vhost-user needs vq_index to initiate a specific queue pair */ + net->dev.vq_index = net->nc->queue_index * net->dev.nvqs; + } r = vhost_dev_init(&net->dev, options->opaque, options->backend_type); diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 5018fd6422..e42fde68d6 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -187,6 +187,19 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg, 0 : -1; } +static bool vhost_user_one_time_request(VhostUserRequest request) +{ + switch (request) { + case VHOST_USER_SET_OWNER: + case VHOST_USER_RESET_DEVICE: + case VHOST_USER_SET_MEM_TABLE: + case VHOST_USER_GET_QUEUE_NUM: + return true; + default: + return false; + } +} + static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, void *arg) { @@ -207,6 +220,15 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, msg_request = request; } + /* + * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE, + * we just need send it once in the first time. For later such + * request, we just ignore it. + */ + if (vhost_user_one_time_request(msg_request) && dev->vq_index != 0) { + return 0; + } + msg.request = msg_request; msg.flags = VHOST_USER_VERSION; msg.size = 0; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7a7812d33f..c0ed5b263f 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -874,8 +874,9 @@ static void vhost_eventfd_del(MemoryListener *listener, static int vhost_virtqueue_init(struct vhost_dev *dev, struct vhost_virtqueue *vq, int n) { + int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, n); struct vhost_vring_file file = { - .index = n, + .index = vhost_vq_index, }; int r = event_notifier_init(&vq->masked_notifier, 0); if (r < 0) { @@ -926,7 +927,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, } for (i = 0; i < hdev->nvqs; ++i) { - r = vhost_virtqueue_init(hdev, hdev->vqs + i, i); + r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i); if (r < 0) { goto fail_vq; } diff --git a/net/vhost-user.c b/net/vhost-user.c index 93dcecd664..8f354eb9b0 100644 --- a/net/vhost-user.c +++ b/net/vhost-user.c @@ -14,6 +14,7 @@ #include "sysemu/char.h" #include "qemu/config-file.h" #include "qemu/error-report.h" +#include "qmp-commands.h" typedef struct VhostUserState { NetClientState nc; @@ -39,37 +40,77 @@ static int vhost_user_running(VhostUserState *s) return (s->vhost_net) ? 1 : 0; } -static int vhost_user_start(VhostUserState *s) +static void vhost_user_stop(int queues, NetClientState *ncs[]) { - VhostNetOptions options; + VhostUserState *s; + int i; - if (vhost_user_running(s)) { - return 0; + for (i = 0; i < queues; i++) { + assert (ncs[i]->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + + s = DO_UPCAST(VhostUserState, nc, ncs[i]); + if (!vhost_user_running(s)) { + continue; + } + + if (s->vhost_net) { + vhost_net_cleanup(s->vhost_net); + s->vhost_net = NULL; + } } - - options.backend_type = VHOST_BACKEND_TYPE_USER; - options.net_backend = &s->nc; - options.opaque = s->chr; - - s->vhost_net = vhost_net_init(&options); - - return vhost_user_running(s) ? 0 : -1; } -static void vhost_user_stop(VhostUserState *s) +static int vhost_user_start(int queues, NetClientState *ncs[]) { - if (vhost_user_running(s)) { - vhost_net_cleanup(s->vhost_net); + VhostNetOptions options; + VhostUserState *s; + int max_queues; + int i; + + options.backend_type = VHOST_BACKEND_TYPE_USER; + + for (i = 0; i < queues; i++) { + assert (ncs[i]->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + + s = DO_UPCAST(VhostUserState, nc, ncs[i]); + if (vhost_user_running(s)) { + continue; + } + + options.net_backend = ncs[i]; + options.opaque = s->chr; + s->vhost_net = vhost_net_init(&options); + if (!s->vhost_net) { + error_report("failed to init vhost_net for queue %d\n", i); + goto err; + } + + if (i == 0) { + max_queues = vhost_net_get_max_queues(s->vhost_net); + if (queues > max_queues) { + error_report("you are asking more queues than " + "supported: %d\n", max_queues); + goto err; + } + } } - s->vhost_net = 0; + return 0; + +err: + vhost_user_stop(i + 1, ncs); + return -1; } static void vhost_user_cleanup(NetClientState *nc) { VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc); - vhost_user_stop(s); + if (s->vhost_net) { + vhost_net_cleanup(s->vhost_net); + s->vhost_net = NULL; + } + qemu_purge_queued_packets(nc); } @@ -95,59 +136,61 @@ static NetClientInfo net_vhost_user_info = { .has_ufo = vhost_user_has_ufo, }; -static void net_vhost_link_down(VhostUserState *s, bool link_down) -{ - s->nc.link_down = link_down; - - if (s->nc.peer) { - s->nc.peer->link_down = link_down; - } - - if (s->nc.info->link_status_changed) { - s->nc.info->link_status_changed(&s->nc); - } - - if (s->nc.peer && s->nc.peer->info->link_status_changed) { - s->nc.peer->info->link_status_changed(s->nc.peer); - } -} - static void net_vhost_user_event(void *opaque, int event) { - VhostUserState *s = opaque; + const char *name = opaque; + NetClientState *ncs[MAX_QUEUE_NUM]; + VhostUserState *s; + Error *err = NULL; + int queues; + queues = qemu_find_net_clients_except(name, ncs, + NET_CLIENT_OPTIONS_KIND_NIC, + MAX_QUEUE_NUM); + s = DO_UPCAST(VhostUserState, nc, ncs[0]); switch (event) { case CHR_EVENT_OPENED: - vhost_user_start(s); - net_vhost_link_down(s, false); + if (vhost_user_start(queues, ncs) < 0) { + exit(1); + } + qmp_set_link(name, true, &err); error_report("chardev \"%s\" went up", s->chr->label); break; case CHR_EVENT_CLOSED: - net_vhost_link_down(s, true); - vhost_user_stop(s); + qmp_set_link(name, true, &err); + vhost_user_stop(queues, ncs); error_report("chardev \"%s\" went down", s->chr->label); break; } + + if (err) { + error_report_err(err); + } } static int net_vhost_user_init(NetClientState *peer, const char *device, - const char *name, CharDriverState *chr) + const char *name, CharDriverState *chr, + int queues) { NetClientState *nc; VhostUserState *s; + int i; - nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name); + for (i = 0; i < queues; i++) { + nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name); - snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user to %s", - chr->label); + snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s", + i, chr->label); - s = DO_UPCAST(VhostUserState, nc, nc); + /* We don't provide a receive callback */ + nc->receive_disabled = 1; + nc->queue_index = i; - /* We don't provide a receive callback */ - s->nc.receive_disabled = 1; - s->chr = chr; + s = DO_UPCAST(VhostUserState, nc, nc); + s->chr = chr; + } - qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s); + qemu_chr_add_handlers(chr, NULL, NULL, net_vhost_user_event, (void*)name); return 0; } @@ -226,6 +269,7 @@ static int net_vhost_check_net(void *opaque, QemuOpts *opts, Error **errp) int net_init_vhost_user(const NetClientOptions *opts, const char *name, NetClientState *peer, Error **errp) { + int queues; const NetdevVhostUserOptions *vhost_user_opts; CharDriverState *chr; @@ -243,6 +287,7 @@ int net_init_vhost_user(const NetClientOptions *opts, const char *name, return -1; } + queues = vhost_user_opts->has_queues ? vhost_user_opts->queues : 1; - return net_vhost_user_init(peer, "vhost_user", name, chr); + return net_vhost_user_init(peer, "vhost_user", name, chr, queues); } diff --git a/qapi-schema.json b/qapi-schema.json index 527690dfe0..582a817215 100644 --- a/qapi-schema.json +++ b/qapi-schema.json @@ -2481,12 +2481,16 @@ # # @vhostforce: #optional vhost on for non-MSIX virtio guests (default: false). # +# @queues: #optional number of queues to be created for multiqueue vhost-user +# (default: 1) (Since 2.5) +# # Since 2.1 ## { 'struct': 'NetdevVhostUserOptions', 'data': { 'chardev': 'str', - '*vhostforce': 'bool' } } + '*vhostforce': 'bool', + '*queues': 'int' } } ## # @NetClientOptions diff --git a/qemu-options.hx b/qemu-options.hx index 7e147b8aac..328404ca18 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -1990,13 +1990,14 @@ The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single netdev. @code{-net} and @code{-device} with parameter @option{vlan} create the required hub automatically. -@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off] +@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n] Establish a vhost-user netdev, backed by a chardev @var{id}. The chardev should be a unix domain socket backed one. The vhost-user uses a specifically defined protocol to pass vhost ioctl replacement messages to an application on the other end of the socket. On non-MSIX guests, the feature can be forced with -@var{vhostforce}. +@var{vhostforce}. Use 'queues=@var{n}' to specify the number of queues to +be created for multiqueue vhost-user. Example: @example From 7263a0ad7899994b719ebed736a1119cc2e08110 Mon Sep 17 00:00:00 2001 From: Changchun Ouyang Date: Wed, 23 Sep 2015 12:20:01 +0800 Subject: [PATCH 16/18] vhost-user: add a new message to disable/enable a specific virt queue. Add a new message, VHOST_USER_SET_VRING_ENABLE, to enable or disable a specific virt queue, which is similar to attach/detach queue for tap device. virtio driver on guest doesn't have to use max virt queue pair, it could enable any number of virt queue ranging from 1 to max virt queue pair. Signed-off-by: Changchun Ouyang Signed-off-by: Yuanhan Liu Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Yuanhan Liu Reviewed-by: Jason Wang Tested-by: Marcel Apfelbaum --- docs/specs/vhost-user.txt | 12 +++++++++++- hw/net/vhost_net.c | 18 ++++++++++++++++++ hw/net/virtio-net.c | 8 ++++++++ hw/virtio/vhost-user.c | 19 +++++++++++++++++++ include/hw/virtio/vhost-backend.h | 2 ++ include/net/vhost_net.h | 2 ++ 6 files changed, 60 insertions(+), 1 deletion(-) diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index cfc9d411ff..4eadad1d6b 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -148,7 +148,9 @@ VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of requested queues is bigger than that. As all queues share one connection, the master uses a unique index for each -queue in the sent message to identify a specified queue. +queue in the sent message to identify a specified queue. One queue pair +is enabled initially. More queues are enabled dynamically, by sending +message VHOST_USER_SET_VRING_ENABLE. Message types ------------- @@ -327,3 +329,11 @@ Message types Query how many queues the backend supports. This request should be sent only when VHOST_USER_PROTOCOL_F_MQ is set in quried protocol features by VHOST_USER_GET_PROTOCOL_FEATURES. + + * VHOST_USER_SET_VRING_ENABLE + + Id: 18 + Equivalent ioctl: N/A + Master payload: vring state description + + Signal slave to enable or disable corresponding vring. diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index ad82b5cce6..2bce89129d 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -422,6 +422,19 @@ VHostNetState *get_vhost_net(NetClientState *nc) return vhost_net; } + +int vhost_set_vring_enable(NetClientState *nc, int enable) +{ + VHostNetState *net = get_vhost_net(nc); + const VhostOps *vhost_ops = net->dev.vhost_ops; + + if (vhost_ops->vhost_backend_set_vring_enable) { + return vhost_ops->vhost_backend_set_vring_enable(&net->dev, enable); + } + + return 0; +} + #else uint64_t vhost_net_get_max_queues(VHostNetState *net) { @@ -472,4 +485,9 @@ VHostNetState *get_vhost_net(NetClientState *nc) { return 0; } + +int vhost_set_vring_enable(NetClientState *nc, int enable) +{ + return 0; +} #endif diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 2775e6a03e..d388c5571d 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -406,6 +406,10 @@ static int peer_attach(VirtIONet *n, int index) return 0; } + if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + vhost_set_vring_enable(nc->peer, 1); + } + if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { return 0; } @@ -421,6 +425,10 @@ static int peer_detach(VirtIONet *n, int index) return 0; } + if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + vhost_set_vring_enable(nc->peer, 0); + } + if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { return 0; } diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index e42fde68d6..b11c0d21a0 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -48,6 +48,7 @@ typedef enum VhostUserRequest { VHOST_USER_GET_PROTOCOL_FEATURES = 15, VHOST_USER_SET_PROTOCOL_FEATURES = 16, VHOST_USER_GET_QUEUE_NUM = 17, + VHOST_USER_SET_VRING_ENABLE = 18, VHOST_USER_MAX } VhostUserRequest; @@ -290,6 +291,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, case VHOST_USER_SET_VRING_NUM: case VHOST_USER_SET_VRING_BASE: + case VHOST_USER_SET_VRING_ENABLE: memcpy(&msg.state, arg, sizeof(struct vhost_vring_state)); msg.size = sizeof(m.state); break; @@ -406,6 +408,22 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque) return 0; } +static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable) +{ + struct vhost_vring_state state = { + .index = dev->vq_index, + .num = enable, + }; + + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); + + if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) { + return -1; + } + + return vhost_user_call(dev, VHOST_USER_SET_VRING_ENABLE, &state); +} + static int vhost_user_cleanup(struct vhost_dev *dev) { assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); @@ -428,4 +446,5 @@ const VhostOps user_ops = { .vhost_backend_init = vhost_user_init, .vhost_backend_cleanup = vhost_user_cleanup, .vhost_backend_get_vq_index = vhost_user_get_vq_index, + .vhost_backend_set_vring_enable = vhost_user_set_vring_enable, }; diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index e1dfc6dd73..3a0f6e2dc2 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -25,6 +25,7 @@ typedef int (*vhost_call)(struct vhost_dev *dev, unsigned long int request, typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque); typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev); typedef int (*vhost_backend_get_vq_index)(struct vhost_dev *dev, int idx); +typedef int (*vhost_backend_set_vring_enable)(struct vhost_dev *dev, int enable); typedef struct VhostOps { VhostBackendType backend_type; @@ -32,6 +33,7 @@ typedef struct VhostOps { vhost_backend_init vhost_backend_init; vhost_backend_cleanup vhost_backend_cleanup; vhost_backend_get_vq_index vhost_backend_get_vq_index; + vhost_backend_set_vring_enable vhost_backend_set_vring_enable; } VhostOps; extern const VhostOps user_ops; diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h index 8db723e54b..0188c4d02d 100644 --- a/include/net/vhost_net.h +++ b/include/net/vhost_net.h @@ -28,4 +28,6 @@ bool vhost_net_virtqueue_pending(VHostNetState *net, int n); void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev, int idx, bool mask); VHostNetState *get_vhost_net(NetClientState *nc); + +int vhost_set_vring_enable(NetClientState * nc, int enable); #endif From 9cc3b73cd8a88e16756f5d14fa87e156a4ce1e8d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 22 Sep 2015 11:56:47 +0200 Subject: [PATCH 17/18] MAINTAINERS: add more devices to the PC section For chipset devices, I can co-maintain it with Michael. Cc: Michael S. Tsirkin Signed-off-by: Paolo Bonzini Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 71c652be98..583d4af59b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -601,6 +601,25 @@ F: hw/acpi/piix4.c F: hw/acpi/ich9.c F: include/hw/acpi/ich9.h F: include/hw/acpi/piix.h +F: hw/misc/sga.c + +PC Chipset +M: Michael S. Tsirkin +M: Paolo Bonzini +S: Support +F: hw/char/debugcon.c +F: hw/char/parallel.c +F: hw/char/serial* +F: hw/dma/i8257* +F: hw/i2c/pm_smbus.c +F: hw/intc/apic* +F: hw/intc/ioapic* +F: hw/intc/i8259* +F: hw/misc/debugexit.c +F: hw/misc/pc-testdev.c +F: hw/timer/hpet* +F: hw/timer/i8254* +F: hw/timer/mc146818rtc* Xtensa Machines From f178bc6b68e6c65cda7354ec4a671860b3123f7a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 22 Sep 2015 11:56:48 +0200 Subject: [PATCH 18/18] MAINTAINERS: add more devices to the PCI section Cc: Michael S. Tsirkin Signed-off-by: Paolo Bonzini Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 583d4af59b..b2e5fbd8e5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -672,7 +672,9 @@ PCI M: Michael S. Tsirkin S: Supported F: include/hw/pci/* +F: hw/misc/pci-testdev.c F: hw/pci/* +F: hw/pci-bridge/* ACPI/SMBIOS M: Michael S. Tsirkin