| Message ID | 20210112194143.1494-1-yuri.benditovich@daynix.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | Support for virtio-net hash reporting | expand |
On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich <yuri.benditovich@daynix.com> wrote: > > Existing TUN module is able to use provided "steering eBPF" to > calculate per-packet hash and derive the destination queue to > place the packet to. The eBPF uses mapped configuration data > containing a key for hash calculation and indirection table > with array of queues' indices. > > This series of patches adds support for virtio-net hash reporting > feature as defined in virtio specification. It extends the TUN module > and the "steering eBPF" as follows: > > Extended steering eBPF calculates the hash value and hash type, keeps > hash value in the skb->hash and returns index of destination virtqueue > and the type of the hash. TUN module keeps returned hash type in > (currently unused) field of the skb. > skb->__unused renamed to 'hash_report_type'. > > When TUN module is called later to allocate and fill the virtio-net > header and push it to destination virtqueue it populates the hash > and the hash type into virtio-net header. > > VHOST driver is made aware of respective virtio-net feature that > extends the virtio-net header to report the hash value and hash report > type. Comment from Willem de Bruijn: Skbuff fields are in short supply. I don't think we need to add one just for this narrow path entirely internal to the tun device. Instead, you could just run the flow_dissector in tun_put_user if the feature is negotiated. Indeed, the flow dissector seems more apt to me than BPF here. Note that the flow dissector internally can be overridden by a BPF program if the admin so chooses. This also hits on a deeper point with the choice of hash values, that I also noticed in my RFC patchset to implement the inverse [1][2]. It is much more detailed than skb->hash + skb->l4_hash currently offers, and that can be gotten for free from most hardware. In most practical cases, that information suffices. I added less specific fields VIRTIO_NET_HASH_REPORT_L4, VIRTIO_NET_HASH_REPORT_OTHER that work without explicit flow dissection. I understand that the existing fields are part of the standard. Just curious, what is their purpose beyond 4-tuple based flow hashing? [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=406859&state=* [2] https://github.com/wdebruij/linux/commit/0f77febf22cd6ffc242a575807fa8382a26e511e > > Yuri Benditovich (7): > skbuff: define field for hash report type > vhost: support for hash report virtio-net feature > tun: allow use of BPF_PROG_TYPE_SCHED_CLS program type > tun: free bpf_program by bpf_prog_put instead of bpf_prog_destroy > tun: add ioctl code TUNSETHASHPOPULATION > tun: populate hash in virtio-net header when needed > tun: report new tun feature IFF_HASH > > drivers/net/tun.c | 43 +++++++++++++++++++++++++++++++------ > drivers/vhost/net.c | 37 ++++++++++++++++++++++++------- > include/linux/skbuff.h | 7 +++++- > include/uapi/linux/if_tun.h | 2 ++ > 4 files changed, 74 insertions(+), 15 deletions(-) > > -- > 2.17.1 >
On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich <yuri.benditovich@daynix.com> wrote: > > On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich > <yuri.benditovich@daynix.com> wrote: > > > > Existing TUN module is able to use provided "steering eBPF" to > > calculate per-packet hash and derive the destination queue to > > place the packet to. The eBPF uses mapped configuration data > > containing a key for hash calculation and indirection table > > with array of queues' indices. > > > > This series of patches adds support for virtio-net hash reporting > > feature as defined in virtio specification. It extends the TUN module > > and the "steering eBPF" as follows: > > > > Extended steering eBPF calculates the hash value and hash type, keeps > > hash value in the skb->hash and returns index of destination virtqueue > > and the type of the hash. TUN module keeps returned hash type in > > (currently unused) field of the skb. > > skb->__unused renamed to 'hash_report_type'. > > > > When TUN module is called later to allocate and fill the virtio-net > > header and push it to destination virtqueue it populates the hash > > and the hash type into virtio-net header. > > > > VHOST driver is made aware of respective virtio-net feature that > > extends the virtio-net header to report the hash value and hash report > > type. > > Comment from Willem de Bruijn: > > Skbuff fields are in short supply. I don't think we need to add one > just for this narrow path entirely internal to the tun device. > We understand that and try to minimize the impact by using an already existing unused field of skb. > Instead, you could just run the flow_dissector in tun_put_user if the > feature is negotiated. Indeed, the flow dissector seems more apt to me > than BPF here. Note that the flow dissector internally can be > overridden by a BPF program if the admin so chooses. > When this set of patches is related to hash delivery in the virtio-net packet in general, it was prepared in context of RSS feature implementation as defined in virtio spec [1] In case of RSS it is not enough to run the flow_dissector in tun_put_user: in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, hash type and queue index according to the (mapped) parameters (key, hash types, indirection table) received from the guest. Our intention is to keep the hash and hash type in the skb to populate them into a virtio-net header later in tun_put_user. Note that in this case the type of calculated hash is selected not only from flow dissections but also from limitations provided by the guest. This is already implemented in qemu (for case of vhost=off), see [2] (virtio_net_process_rss) For case of vhost=on there are WIP for qemu to load eBPF and attach it to TUN. Note that exact way of selecting rx virtqueue depends on the guest, it could be automatic steering (typical for Linux VM), RSS (typical for Windows VM) or any other steering mechanism implemented in loadable TUN steering BPF with or without hash calculation. [1] https://github.com/oasis-tcs/virtio-spec/blob/master/content.tex#L3740 [2] https://github.com/qemu/qemu/blob/master/hw/net/virtio-net.c#L1591 > This also hits on a deeper point with the choice of hash values, that > I also noticed in my RFC patchset to implement the inverse [1][2]. It > is much more detailed than skb->hash + skb->l4_hash currently offers, > and that can be gotten for free from most hardware. Unfortunately in the case of RSS we can't get this hash from the hardware as this requires configuration of the NIC's hardware with key and hash types for Toeplitz hash calculation. > In most practical > cases, that information suffices. I added less specific fields > VIRTIO_NET_HASH_REPORT_L4, VIRTIO_NET_HASH_REPORT_OTHER that work > without explicit flow dissection. I understand that the existing > fields are part of the standard. Just curious, what is their purpose > beyond 4-tuple based flow hashing? The hash is used in combination with the indirection table to select destination rx virtqueue. The hash and hash type are to be reported in virtio-net header, if requested. For Windows VM - in case the device does not report the hash (even if it calculated it to schedule the packet to a proper queue), the driver must do that for each packet (this is a certification requirement). > > [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=406859&state=* > [2] https://github.com/wdebruij/linux/commit/0f77febf22cd6ffc242a575807fa8382a26e511e > > > > Yuri Benditovich (7): > > skbuff: define field for hash report type > > vhost: support for hash report virtio-net feature > > tun: allow use of BPF_PROG_TYPE_SCHED_CLS program type > > tun: free bpf_program by bpf_prog_put instead of bpf_prog_destroy > > tun: add ioctl code TUNSETHASHPOPULATION > > tun: populate hash in virtio-net header when needed > > tun: report new tun feature IFF_HASH > > > > drivers/net/tun.c | 43 +++++++++++++++++++++++++++++++------ > > drivers/vhost/net.c | 37 ++++++++++++++++++++++++------- > > include/linux/skbuff.h | 7 +++++- > > include/uapi/linux/if_tun.h | 2 ++ > > 4 files changed, 74 insertions(+), 15 deletions(-) > > > > -- > > 2.17.1 > >
On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich <yuri.benditovich@daynix.com> wrote: > > On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich > <yuri.benditovich@daynix.com> wrote: > > > > On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich > > <yuri.benditovich@daynix.com> wrote: > > > > > > Existing TUN module is able to use provided "steering eBPF" to > > > calculate per-packet hash and derive the destination queue to > > > place the packet to. The eBPF uses mapped configuration data > > > containing a key for hash calculation and indirection table > > > with array of queues' indices. > > > > > > This series of patches adds support for virtio-net hash reporting > > > feature as defined in virtio specification. It extends the TUN module > > > and the "steering eBPF" as follows: > > > > > > Extended steering eBPF calculates the hash value and hash type, keeps > > > hash value in the skb->hash and returns index of destination virtqueue > > > and the type of the hash. TUN module keeps returned hash type in > > > (currently unused) field of the skb. > > > skb->__unused renamed to 'hash_report_type'. > > > > > > When TUN module is called later to allocate and fill the virtio-net > > > header and push it to destination virtqueue it populates the hash > > > and the hash type into virtio-net header. > > > > > > VHOST driver is made aware of respective virtio-net feature that > > > extends the virtio-net header to report the hash value and hash report > > > type. > > > > Comment from Willem de Bruijn: > > > > Skbuff fields are in short supply. I don't think we need to add one > > just for this narrow path entirely internal to the tun device. > > > > We understand that and try to minimize the impact by using an already > existing unused field of skb. Not anymore. It was repurposed as a flags field very recently. This use case is also very narrow in scope. And a very short path from data producer to consumer. So I don't think it needs to claim scarce bits in the skb. tun_ebpf_select_queue stores the field, tun_put_user reads it and converts it to the virtio_net_hdr in the descriptor. tun_ebpf_select_queue is called from .ndo_select_queue. Storing the field in skb->cb is fragile, as in theory some code could overwrite that between field between ndo_select_queue and ndo_start_xmit/tun_net_xmit, from which point it is fully under tun control again. But in practice, I don't believe anything does. Alternatively an existing skb field that is used only on disjoint datapaths, such as ingress-only, could be viable. > > Instead, you could just run the flow_dissector in tun_put_user if the > > feature is negotiated. Indeed, the flow dissector seems more apt to me > > than BPF here. Note that the flow dissector internally can be > > overridden by a BPF program if the admin so chooses. > > > When this set of patches is related to hash delivery in the virtio-net > packet in general, > it was prepared in context of RSS feature implementation as defined in > virtio spec [1] > In case of RSS it is not enough to run the flow_dissector in tun_put_user: > in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, > hash type and queue index > according to the (mapped) parameters (key, hash types, indirection > table) received from the guest. TUNSETSTEERINGEBPF was added to support more diverse queue selection than the default in case of multiqueue tun. Not sure what the exact use cases are. But RSS is exactly the purpose of the flow dissector. It is used for that purpose in the software variant RPS. The flow dissector implements a superset of the RSS spec, and certainly computes a four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC has already computed a 4-tuple hash. What it does not give is a type indication, such as VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. In datapaths where the NIC has already computed the four-tuple hash and stored it in skb->hash --the common case for servers--, That type field is the only reason to have to compute again. > Our intention is to keep the hash and hash type in the skb to populate them > into a virtio-net header later in tun_put_user. > Note that in this case the type of calculated hash is selected not > only from flow dissections > but also from limitations provided by the guest. > > This is already implemented in qemu (for case of vhost=off), see [2] > (virtio_net_process_rss) > For case of vhost=on there are WIP for qemu to load eBPF and attach it to TUN. > Note that exact way of selecting rx virtqueue depends on the guest, > it could be automatic steering (typical for Linux VM), RSS (typical > for Windows VM) or > any other steering mechanism implemented in loadable TUN steering BPF with > or without hash calculation. > > [1] https://github.com/oasis-tcs/virtio-spec/blob/master/content.tex#L3740 > [2] https://github.com/qemu/qemu/blob/master/hw/net/virtio-net.c#L1591 > > > This also hits on a deeper point with the choice of hash values, that > > I also noticed in my RFC patchset to implement the inverse [1][2]. It > > is much more detailed than skb->hash + skb->l4_hash currently offers, > > and that can be gotten for free from most hardware. > > Unfortunately in the case of RSS we can't get this hash from the hardware as > this requires configuration of the NIC's hardware with key and hash types for > Toeplitz hash calculation. I don't understand. Toeplitz hash calculation is enabled by default for multiqueue devices, and many devices will pass the toeplitz hash along for free to avoid software flow dissection. > > In most practical > > cases, that information suffices. I added less specific fields > > VIRTIO_NET_HASH_REPORT_L4, VIRTIO_NET_HASH_REPORT_OTHER that work > > without explicit flow dissection. I understand that the existing > > fields are part of the standard. Just curious, what is their purpose > > beyond 4-tuple based flow hashing? > > The hash is used in combination with the indirection table to select > destination rx virtqueue. > The hash and hash type are to be reported in virtio-net header, if requested. > For Windows VM - in case the device does not report the hash (even if > it calculated it to > schedule the packet to a proper queue), the driver must do that for each packet > (this is a certification requirement). I understand the basics of RSS. My question is what the hash-type is intended to be used for by the guest. It is part of the virtio spec, so this point is somewhat moot: it has to be passed along with the hash value now. But it is not entirely moot. If most users are satisfied with knowing whether a hash is L4 or not, we could add two new types VIRTIO_NET_HASH_TYPE_L4 and VIRTIO_NET_HASH_TYPE_OTHER. And then pass the existing skb->hash as is, likely computed by the NIC. [1] https://patchwork.kernel.org/project/netdevbpf/patch/20201228162233.2032571-2-willemdebruijn.kernel@gmail.com/ > > > > [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=406859&state=* > > [2] https://github.com/wdebruij/linux/commit/0f77febf22cd6ffc242a575807fa8382a26e511e > > > > > > Yuri Benditovich (7): > > > skbuff: define field for hash report type > > > vhost: support for hash report virtio-net feature > > > tun: allow use of BPF_PROG_TYPE_SCHED_CLS program type > > > tun: free bpf_program by bpf_prog_put instead of bpf_prog_destroy > > > tun: add ioctl code TUNSETHASHPOPULATION > > > tun: populate hash in virtio-net header when needed > > > tun: report new tun feature IFF_HASH > > > > > > drivers/net/tun.c | 43 +++++++++++++++++++++++++++++++------ > > > drivers/vhost/net.c | 37 ++++++++++++++++++++++++------- > > > include/linux/skbuff.h | 7 +++++- > > > include/uapi/linux/if_tun.h | 2 ++ > > > 4 files changed, 74 insertions(+), 15 deletions(-) > > > > > > -- > > > 2.17.1 > > >
On 2021/1/13 上午7:47, Willem de Bruijn wrote: > On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich > <yuri.benditovich@daynix.com> wrote: >> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich >> <yuri.benditovich@daynix.com> wrote: >>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich >>> <yuri.benditovich@daynix.com> wrote: >>>> Existing TUN module is able to use provided "steering eBPF" to >>>> calculate per-packet hash and derive the destination queue to >>>> place the packet to. The eBPF uses mapped configuration data >>>> containing a key for hash calculation and indirection table >>>> with array of queues' indices. >>>> >>>> This series of patches adds support for virtio-net hash reporting >>>> feature as defined in virtio specification. It extends the TUN module >>>> and the "steering eBPF" as follows: >>>> >>>> Extended steering eBPF calculates the hash value and hash type, keeps >>>> hash value in the skb->hash and returns index of destination virtqueue >>>> and the type of the hash. TUN module keeps returned hash type in >>>> (currently unused) field of the skb. >>>> skb->__unused renamed to 'hash_report_type'. >>>> >>>> When TUN module is called later to allocate and fill the virtio-net >>>> header and push it to destination virtqueue it populates the hash >>>> and the hash type into virtio-net header. >>>> >>>> VHOST driver is made aware of respective virtio-net feature that >>>> extends the virtio-net header to report the hash value and hash report >>>> type. >>> Comment from Willem de Bruijn: >>> >>> Skbuff fields are in short supply. I don't think we need to add one >>> just for this narrow path entirely internal to the tun device. >>> >> We understand that and try to minimize the impact by using an already >> existing unused field of skb. > Not anymore. It was repurposed as a flags field very recently. > > This use case is also very narrow in scope. And a very short path from > data producer to consumer. So I don't think it needs to claim scarce > bits in the skb. > > tun_ebpf_select_queue stores the field, tun_put_user reads it and > converts it to the virtio_net_hdr in the descriptor. > > tun_ebpf_select_queue is called from .ndo_select_queue. Storing the > field in skb->cb is fragile, as in theory some code could overwrite > that between field between ndo_select_queue and > ndo_start_xmit/tun_net_xmit, from which point it is fully under tun > control again. But in practice, I don't believe anything does. > > Alternatively an existing skb field that is used only on disjoint > datapaths, such as ingress-only, could be viable. A question here. We had metadata support in XDP for cooperation between eBPF programs. Do we have something similar in the skb? E.g in the RSS, if we want to pass some metadata information between eBPF program and the logic that generates the vnet header (either hard logic in the kernel or another eBPF program). Is there any way that can avoid the possible conflicts of qdiscs? > >>> Instead, you could just run the flow_dissector in tun_put_user if the >>> feature is negotiated. Indeed, the flow dissector seems more apt to me >>> than BPF here. Note that the flow dissector internally can be >>> overridden by a BPF program if the admin so chooses. >>> >> When this set of patches is related to hash delivery in the virtio-net >> packet in general, >> it was prepared in context of RSS feature implementation as defined in >> virtio spec [1] >> In case of RSS it is not enough to run the flow_dissector in tun_put_user: >> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, >> hash type and queue index >> according to the (mapped) parameters (key, hash types, indirection >> table) received from the guest. > TUNSETSTEERINGEBPF was added to support more diverse queue selection > than the default in case of multiqueue tun. Not sure what the exact > use cases are. > > But RSS is exactly the purpose of the flow dissector. It is used for > that purpose in the software variant RPS. The flow dissector > implements a superset of the RSS spec, and certainly computes a > four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC > has already computed a 4-tuple hash. > > What it does not give is a type indication, such as > VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. > In datapaths where the NIC has already computed the four-tuple hash > and stored it in skb->hash --the common case for servers--, That type > field is the only reason to have to compute again. The problem is there's no guarantee that the packet comes from the NIC, it could be a simple VM2VM or host2VM packet. And even if the packet is coming from the NIC that calculates the hash there's no guarantee that it's the has that guest want (guest may use different RSS keys). Thanks > >> Our intention is to keep the hash and hash type in the skb to populate them >> into a virtio-net header later in tun_put_user. >> Note that in this case the type of calculated hash is selected not >> only from flow dissections >> but also from limitations provided by the guest. >> >> This is already implemented in qemu (for case of vhost=off), see [2] >> (virtio_net_process_rss) >> For case of vhost=on there are WIP for qemu to load eBPF and attach it to TUN. >> Note that exact way of selecting rx virtqueue depends on the guest, >> it could be automatic steering (typical for Linux VM), RSS (typical >> for Windows VM) or >> any other steering mechanism implemented in loadable TUN steering BPF with >> or without hash calculation. >> >> [1] https://github.com/oasis-tcs/virtio-spec/blob/master/content.tex#L3740 >> [2] https://github.com/qemu/qemu/blob/master/hw/net/virtio-net.c#L1591 >> >>> This also hits on a deeper point with the choice of hash values, that >>> I also noticed in my RFC patchset to implement the inverse [1][2]. It >>> is much more detailed than skb->hash + skb->l4_hash currently offers, >>> and that can be gotten for free from most hardware. >> Unfortunately in the case of RSS we can't get this hash from the hardware as >> this requires configuration of the NIC's hardware with key and hash types for >> Toeplitz hash calculation. > I don't understand. Toeplitz hash calculation is enabled by default > for multiqueue devices, and many devices will pass the toeplitz hash > along for free to avoid software flow dissection. > >>> In most practical >>> cases, that information suffices. I added less specific fields >>> VIRTIO_NET_HASH_REPORT_L4, VIRTIO_NET_HASH_REPORT_OTHER that work >>> without explicit flow dissection. I understand that the existing >>> fields are part of the standard. Just curious, what is their purpose >>> beyond 4-tuple based flow hashing? >> The hash is used in combination with the indirection table to select >> destination rx virtqueue. >> The hash and hash type are to be reported in virtio-net header, if requested. >> For Windows VM - in case the device does not report the hash (even if >> it calculated it to >> schedule the packet to a proper queue), the driver must do that for each packet >> (this is a certification requirement). > I understand the basics of RSS. My question is what the hash-type is > intended to be used for by the guest. It is part of the virtio spec, > so this point is somewhat moot: it has to be passed along with the > hash value now. > > But it is not entirely moot. If most users are satisfied with knowing > whether a hash is L4 or not, we could add two new types > VIRTIO_NET_HASH_TYPE_L4 and VIRTIO_NET_HASH_TYPE_OTHER. And then pass > the existing skb->hash as is, likely computed by the NIC. > > [1] https://patchwork.kernel.org/project/netdevbpf/patch/20201228162233.2032571-2-willemdebruijn.kernel@gmail.com/ > >>> [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=406859&state=* >>> [2] https://github.com/wdebruij/linux/commit/0f77febf22cd6ffc242a575807fa8382a26e511e >>>> Yuri Benditovich (7): >>>> skbuff: define field for hash report type >>>> vhost: support for hash report virtio-net feature >>>> tun: allow use of BPF_PROG_TYPE_SCHED_CLS program type >>>> tun: free bpf_program by bpf_prog_put instead of bpf_prog_destroy >>>> tun: add ioctl code TUNSETHASHPOPULATION >>>> tun: populate hash in virtio-net header when needed >>>> tun: report new tun feature IFF_HASH >>>> >>>> drivers/net/tun.c | 43 +++++++++++++++++++++++++++++++------ >>>> drivers/vhost/net.c | 37 ++++++++++++++++++++++++------- >>>> include/linux/skbuff.h | 7 +++++- >>>> include/uapi/linux/if_tun.h | 2 ++ >>>> 4 files changed, 74 insertions(+), 15 deletions(-) >>>> >>>> -- >>>> 2.17.1 >>>>
On Tue, Jan 12, 2021 at 11:11 PM Jason Wang <jasowang@redhat.com> wrote: > > > On 2021/1/13 上午7:47, Willem de Bruijn wrote: > > On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich > > <yuri.benditovich@daynix.com> wrote: > >> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich > >> <yuri.benditovich@daynix.com> wrote: > >>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich > >>> <yuri.benditovich@daynix.com> wrote: > >>>> Existing TUN module is able to use provided "steering eBPF" to > >>>> calculate per-packet hash and derive the destination queue to > >>>> place the packet to. The eBPF uses mapped configuration data > >>>> containing a key for hash calculation and indirection table > >>>> with array of queues' indices. > >>>> > >>>> This series of patches adds support for virtio-net hash reporting > >>>> feature as defined in virtio specification. It extends the TUN module > >>>> and the "steering eBPF" as follows: > >>>> > >>>> Extended steering eBPF calculates the hash value and hash type, keeps > >>>> hash value in the skb->hash and returns index of destination virtqueue > >>>> and the type of the hash. TUN module keeps returned hash type in > >>>> (currently unused) field of the skb. > >>>> skb->__unused renamed to 'hash_report_type'. > >>>> > >>>> When TUN module is called later to allocate and fill the virtio-net > >>>> header and push it to destination virtqueue it populates the hash > >>>> and the hash type into virtio-net header. > >>>> > >>>> VHOST driver is made aware of respective virtio-net feature that > >>>> extends the virtio-net header to report the hash value and hash report > >>>> type. > >>> Comment from Willem de Bruijn: > >>> > >>> Skbuff fields are in short supply. I don't think we need to add one > >>> just for this narrow path entirely internal to the tun device. > >>> > >> We understand that and try to minimize the impact by using an already > >> existing unused field of skb. > > Not anymore. It was repurposed as a flags field very recently. > > > > This use case is also very narrow in scope. And a very short path from > > data producer to consumer. So I don't think it needs to claim scarce > > bits in the skb. > > > > tun_ebpf_select_queue stores the field, tun_put_user reads it and > > converts it to the virtio_net_hdr in the descriptor. > > > > tun_ebpf_select_queue is called from .ndo_select_queue. Storing the > > field in skb->cb is fragile, as in theory some code could overwrite > > that between field between ndo_select_queue and > > ndo_start_xmit/tun_net_xmit, from which point it is fully under tun > > control again. But in practice, I don't believe anything does. > > > > Alternatively an existing skb field that is used only on disjoint > > datapaths, such as ingress-only, could be viable. > > > A question here. We had metadata support in XDP for cooperation between > eBPF programs. Do we have something similar in the skb? > > E.g in the RSS, if we want to pass some metadata information between > eBPF program and the logic that generates the vnet header (either hard > logic in the kernel or another eBPF program). Is there any way that can > avoid the possible conflicts of qdiscs? Not that I am aware of. The closest thing is cb[]. It'll have to aliase a field like that, that is known unused for the given path. One other approach that has been used within linear call stacks is out of band. Like percpu variables softnet_data.xmit.more and mirred_rec_level. But that is perhaps a bit overwrought for this use case. > > > >>> Instead, you could just run the flow_dissector in tun_put_user if the > >>> feature is negotiated. Indeed, the flow dissector seems more apt to me > >>> than BPF here. Note that the flow dissector internally can be > >>> overridden by a BPF program if the admin so chooses. > >>> > >> When this set of patches is related to hash delivery in the virtio-net > >> packet in general, > >> it was prepared in context of RSS feature implementation as defined in > >> virtio spec [1] > >> In case of RSS it is not enough to run the flow_dissector in tun_put_user: > >> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, > >> hash type and queue index > >> according to the (mapped) parameters (key, hash types, indirection > >> table) received from the guest. > > TUNSETSTEERINGEBPF was added to support more diverse queue selection > > than the default in case of multiqueue tun. Not sure what the exact > > use cases are. > > > > But RSS is exactly the purpose of the flow dissector. It is used for > > that purpose in the software variant RPS. The flow dissector > > implements a superset of the RSS spec, and certainly computes a > > four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC > > has already computed a 4-tuple hash. > > > > What it does not give is a type indication, such as > > VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. > > In datapaths where the NIC has already computed the four-tuple hash > > and stored it in skb->hash --the common case for servers--, That type > > field is the only reason to have to compute again. > > > The problem is there's no guarantee that the packet comes from the NIC, > it could be a simple VM2VM or host2VM packet. > > And even if the packet is coming from the NIC that calculates the hash > there's no guarantee that it's the has that guest want (guest may use > different RSS keys). Ah yes, of course. I would still revisit the need to store a detailed hash_type along with the hash, as as far I can tell that conveys no actionable information to the guest.
On 2021/1/13 下午10:33, Willem de Bruijn wrote: > On Tue, Jan 12, 2021 at 11:11 PM Jason Wang <jasowang@redhat.com> wrote: >> >> On 2021/1/13 上午7:47, Willem de Bruijn wrote: >>> On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich >>> <yuri.benditovich@daynix.com> wrote: >>>> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich >>>> <yuri.benditovich@daynix.com> wrote: >>>>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich >>>>> <yuri.benditovich@daynix.com> wrote: >>>>>> Existing TUN module is able to use provided "steering eBPF" to >>>>>> calculate per-packet hash and derive the destination queue to >>>>>> place the packet to. The eBPF uses mapped configuration data >>>>>> containing a key for hash calculation and indirection table >>>>>> with array of queues' indices. >>>>>> >>>>>> This series of patches adds support for virtio-net hash reporting >>>>>> feature as defined in virtio specification. It extends the TUN module >>>>>> and the "steering eBPF" as follows: >>>>>> >>>>>> Extended steering eBPF calculates the hash value and hash type, keeps >>>>>> hash value in the skb->hash and returns index of destination virtqueue >>>>>> and the type of the hash. TUN module keeps returned hash type in >>>>>> (currently unused) field of the skb. >>>>>> skb->__unused renamed to 'hash_report_type'. >>>>>> >>>>>> When TUN module is called later to allocate and fill the virtio-net >>>>>> header and push it to destination virtqueue it populates the hash >>>>>> and the hash type into virtio-net header. >>>>>> >>>>>> VHOST driver is made aware of respective virtio-net feature that >>>>>> extends the virtio-net header to report the hash value and hash report >>>>>> type. >>>>> Comment from Willem de Bruijn: >>>>> >>>>> Skbuff fields are in short supply. I don't think we need to add one >>>>> just for this narrow path entirely internal to the tun device. >>>>> >>>> We understand that and try to minimize the impact by using an already >>>> existing unused field of skb. >>> Not anymore. It was repurposed as a flags field very recently. >>> >>> This use case is also very narrow in scope. And a very short path from >>> data producer to consumer. So I don't think it needs to claim scarce >>> bits in the skb. >>> >>> tun_ebpf_select_queue stores the field, tun_put_user reads it and >>> converts it to the virtio_net_hdr in the descriptor. >>> >>> tun_ebpf_select_queue is called from .ndo_select_queue. Storing the >>> field in skb->cb is fragile, as in theory some code could overwrite >>> that between field between ndo_select_queue and >>> ndo_start_xmit/tun_net_xmit, from which point it is fully under tun >>> control again. But in practice, I don't believe anything does. >>> >>> Alternatively an existing skb field that is used only on disjoint >>> datapaths, such as ingress-only, could be viable. >> >> A question here. We had metadata support in XDP for cooperation between >> eBPF programs. Do we have something similar in the skb? >> >> E.g in the RSS, if we want to pass some metadata information between >> eBPF program and the logic that generates the vnet header (either hard >> logic in the kernel or another eBPF program). Is there any way that can >> avoid the possible conflicts of qdiscs? > Not that I am aware of. The closest thing is cb[]. > > It'll have to aliase a field like that, that is known unused for the given path. Right, we need to make sure cb is not used by other ones. I'm not sure how hard to achieve that consider Qemu installs the eBPF program but it doesn't deal with networking configurations. > > One other approach that has been used within linear call stacks is out > of band. Like percpu variables softnet_data.xmit.more and > mirred_rec_level. But that is perhaps a bit overwrought for this use > case. Yes, and if we go that way then eBPF turns out to be a burden since we need to invent helpers to access those auxiliary data structure. It would be better then to hard-coded the RSS in the kernel. > >>>>> Instead, you could just run the flow_dissector in tun_put_user if the >>>>> feature is negotiated. Indeed, the flow dissector seems more apt to me >>>>> than BPF here. Note that the flow dissector internally can be >>>>> overridden by a BPF program if the admin so chooses. >>>>> >>>> When this set of patches is related to hash delivery in the virtio-net >>>> packet in general, >>>> it was prepared in context of RSS feature implementation as defined in >>>> virtio spec [1] >>>> In case of RSS it is not enough to run the flow_dissector in tun_put_user: >>>> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, >>>> hash type and queue index >>>> according to the (mapped) parameters (key, hash types, indirection >>>> table) received from the guest. >>> TUNSETSTEERINGEBPF was added to support more diverse queue selection >>> than the default in case of multiqueue tun. Not sure what the exact >>> use cases are. >>> >>> But RSS is exactly the purpose of the flow dissector. It is used for >>> that purpose in the software variant RPS. The flow dissector >>> implements a superset of the RSS spec, and certainly computes a >>> four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC >>> has already computed a 4-tuple hash. >>> >>> What it does not give is a type indication, such as >>> VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. >>> In datapaths where the NIC has already computed the four-tuple hash >>> and stored it in skb->hash --the common case for servers--, That type >>> field is the only reason to have to compute again. >> >> The problem is there's no guarantee that the packet comes from the NIC, >> it could be a simple VM2VM or host2VM packet. >> >> And even if the packet is coming from the NIC that calculates the hash >> there's no guarantee that it's the has that guest want (guest may use >> different RSS keys). > Ah yes, of course. > > I would still revisit the need to store a detailed hash_type along with > the hash, as as far I can tell that conveys no actionable information > to the guest. Yes, need to figure out its usage. According to [1], it only mention that storing has type is a charge of driver. Maybe Yuri can answer this. Thanks [1] https://docs.microsoft.com/en-us/windows-hardware/drivers/network/indicating-rss-receive-data >
On Thu, Jan 14, 2021 at 5:39 AM Jason Wang <jasowang@redhat.com> wrote: > > > On 2021/1/13 下午10:33, Willem de Bruijn wrote: > > On Tue, Jan 12, 2021 at 11:11 PM Jason Wang <jasowang@redhat.com> wrote: > >> > >> On 2021/1/13 上午7:47, Willem de Bruijn wrote: > >>> On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich > >>> <yuri.benditovich@daynix.com> wrote: > >>>> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich > >>>> <yuri.benditovich@daynix.com> wrote: > >>>>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich > >>>>> <yuri.benditovich@daynix.com> wrote: > >>>>>> Existing TUN module is able to use provided "steering eBPF" to > >>>>>> calculate per-packet hash and derive the destination queue to > >>>>>> place the packet to. The eBPF uses mapped configuration data > >>>>>> containing a key for hash calculation and indirection table > >>>>>> with array of queues' indices. > >>>>>> > >>>>>> This series of patches adds support for virtio-net hash reporting > >>>>>> feature as defined in virtio specification. It extends the TUN module > >>>>>> and the "steering eBPF" as follows: > >>>>>> > >>>>>> Extended steering eBPF calculates the hash value and hash type, keeps > >>>>>> hash value in the skb->hash and returns index of destination virtqueue > >>>>>> and the type of the hash. TUN module keeps returned hash type in > >>>>>> (currently unused) field of the skb. > >>>>>> skb->__unused renamed to 'hash_report_type'. > >>>>>> > >>>>>> When TUN module is called later to allocate and fill the virtio-net > >>>>>> header and push it to destination virtqueue it populates the hash > >>>>>> and the hash type into virtio-net header. > >>>>>> > >>>>>> VHOST driver is made aware of respective virtio-net feature that > >>>>>> extends the virtio-net header to report the hash value and hash report > >>>>>> type. > >>>>> Comment from Willem de Bruijn: > >>>>> > >>>>> Skbuff fields are in short supply. I don't think we need to add one > >>>>> just for this narrow path entirely internal to the tun device. > >>>>> > >>>> We understand that and try to minimize the impact by using an already > >>>> existing unused field of skb. > >>> Not anymore. It was repurposed as a flags field very recently. > >>> > >>> This use case is also very narrow in scope. And a very short path from > >>> data producer to consumer. So I don't think it needs to claim scarce > >>> bits in the skb. > >>> > >>> tun_ebpf_select_queue stores the field, tun_put_user reads it and > >>> converts it to the virtio_net_hdr in the descriptor. > >>> > >>> tun_ebpf_select_queue is called from .ndo_select_queue. Storing the > >>> field in skb->cb is fragile, as in theory some code could overwrite > >>> that between field between ndo_select_queue and > >>> ndo_start_xmit/tun_net_xmit, from which point it is fully under tun > >>> control again. But in practice, I don't believe anything does. > >>> > >>> Alternatively an existing skb field that is used only on disjoint > >>> datapaths, such as ingress-only, could be viable. > >> > >> A question here. We had metadata support in XDP for cooperation between > >> eBPF programs. Do we have something similar in the skb? > >> > >> E.g in the RSS, if we want to pass some metadata information between > >> eBPF program and the logic that generates the vnet header (either hard > >> logic in the kernel or another eBPF program). Is there any way that can > >> avoid the possible conflicts of qdiscs? > > Not that I am aware of. The closest thing is cb[]. > > > > It'll have to aliase a field like that, that is known unused for the given path. > > > Right, we need to make sure cb is not used by other ones. I'm not sure > how hard to achieve that consider Qemu installs the eBPF program but it > doesn't deal with networking configurations. > > > > > > One other approach that has been used within linear call stacks is out > > of band. Like percpu variables softnet_data.xmit.more and > > mirred_rec_level. But that is perhaps a bit overwrought for this use > > case. > > > Yes, and if we go that way then eBPF turns out to be a burden since we > need to invent helpers to access those auxiliary data structure. It > would be better then to hard-coded the RSS in the kernel. > > > > > >>>>> Instead, you could just run the flow_dissector in tun_put_user if the > >>>>> feature is negotiated. Indeed, the flow dissector seems more apt to me > >>>>> than BPF here. Note that the flow dissector internally can be > >>>>> overridden by a BPF program if the admin so chooses. > >>>>> > >>>> When this set of patches is related to hash delivery in the virtio-net > >>>> packet in general, > >>>> it was prepared in context of RSS feature implementation as defined in > >>>> virtio spec [1] > >>>> In case of RSS it is not enough to run the flow_dissector in tun_put_user: > >>>> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, > >>>> hash type and queue index > >>>> according to the (mapped) parameters (key, hash types, indirection > >>>> table) received from the guest. > >>> TUNSETSTEERINGEBPF was added to support more diverse queue selection > >>> than the default in case of multiqueue tun. Not sure what the exact > >>> use cases are. > >>> > >>> But RSS is exactly the purpose of the flow dissector. It is used for > >>> that purpose in the software variant RPS. The flow dissector > >>> implements a superset of the RSS spec, and certainly computes a > >>> four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC > >>> has already computed a 4-tuple hash. > >>> > >>> What it does not give is a type indication, such as > >>> VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. > >>> In datapaths where the NIC has already computed the four-tuple hash > >>> and stored it in skb->hash --the common case for servers--, That type > >>> field is the only reason to have to compute again. > >> > >> The problem is there's no guarantee that the packet comes from the NIC, > >> it could be a simple VM2VM or host2VM packet. > >> > >> And even if the packet is coming from the NIC that calculates the hash > >> there's no guarantee that it's the has that guest want (guest may use > >> different RSS keys). > > Ah yes, of course. > > > > I would still revisit the need to store a detailed hash_type along with > > the hash, as as far I can tell that conveys no actionable information > > to the guest. > > > Yes, need to figure out its usage. According to [1], it only mention > that storing has type is a charge of driver. Maybe Yuri can answer this. > For the case of Windows VM we can't know how exactly the network stack uses provided hash data (including hash type). But: different releases of Windows enable different hash types (for example UDP hash is enabled only on Server 2016 and up). Indeed the Windows requires a little more from the network adapter/driver than Linux does. The addition of RSS support to virtio specification takes in account the widest set of requirements (i.e. Windows one), our initial impression is that this should be enough also for Linux. The NDIS specification in part of RSS is _mandatory_ and there are certification tests that check that the driver provides the hash data as expected. All the high-performance network adapters have such RSS functionality in the hardware. With pre-RSS QEMU (i.e. where the virtio-net device does not indicate the RSS support) the virtio-net driver for Windows does all the job related to RSS: - hash calculation - hash/hash_type delivery - reporting each packet on the correct CPU according to RSS settings With RSS support in QEMU all the packets always come on a proper CPU and the driver never needs to reschedule them. The driver still need to calculate the hash and report it to Windows. In this case we do the same job twice: the device (QEMU or eBPF) does calculate the hash and get proper queue/CPU to deliver the packet. But the hash is not delivered by the device, so the driver needs to recalculate it and report to the Windows. If we add HASH_REPORT support (current set of patches) and the device indicates this feature we can avoid hash recalculation in the driver assuming we receive the correct hash value and hash type. Otherwise the driver can't know which exactly hash the device has calculated. Please let me know if I did not answer the question. > Thanks > > [1] > https://docs.microsoft.com/en-us/windows-hardware/drivers/network/indicating-rss-receive-data > > > > >
On 2021/1/17 下午3:57, Yuri Benditovich wrote: > On Thu, Jan 14, 2021 at 5:39 AM Jason Wang <jasowang@redhat.com> wrote: >> >> On 2021/1/13 下午10:33, Willem de Bruijn wrote: >>> On Tue, Jan 12, 2021 at 11:11 PM Jason Wang <jasowang@redhat.com> wrote: >>>> On 2021/1/13 上午7:47, Willem de Bruijn wrote: >>>>> On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich >>>>> <yuri.benditovich@daynix.com> wrote: >>>>>> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich >>>>>> <yuri.benditovich@daynix.com> wrote: >>>>>>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich >>>>>>> <yuri.benditovich@daynix.com> wrote: >>>>>>>> Existing TUN module is able to use provided "steering eBPF" to >>>>>>>> calculate per-packet hash and derive the destination queue to >>>>>>>> place the packet to. The eBPF uses mapped configuration data >>>>>>>> containing a key for hash calculation and indirection table >>>>>>>> with array of queues' indices. >>>>>>>> >>>>>>>> This series of patches adds support for virtio-net hash reporting >>>>>>>> feature as defined in virtio specification. It extends the TUN module >>>>>>>> and the "steering eBPF" as follows: >>>>>>>> >>>>>>>> Extended steering eBPF calculates the hash value and hash type, keeps >>>>>>>> hash value in the skb->hash and returns index of destination virtqueue >>>>>>>> and the type of the hash. TUN module keeps returned hash type in >>>>>>>> (currently unused) field of the skb. >>>>>>>> skb->__unused renamed to 'hash_report_type'. >>>>>>>> >>>>>>>> When TUN module is called later to allocate and fill the virtio-net >>>>>>>> header and push it to destination virtqueue it populates the hash >>>>>>>> and the hash type into virtio-net header. >>>>>>>> >>>>>>>> VHOST driver is made aware of respective virtio-net feature that >>>>>>>> extends the virtio-net header to report the hash value and hash report >>>>>>>> type. >>>>>>> Comment from Willem de Bruijn: >>>>>>> >>>>>>> Skbuff fields are in short supply. I don't think we need to add one >>>>>>> just for this narrow path entirely internal to the tun device. >>>>>>> >>>>>> We understand that and try to minimize the impact by using an already >>>>>> existing unused field of skb. >>>>> Not anymore. It was repurposed as a flags field very recently. >>>>> >>>>> This use case is also very narrow in scope. And a very short path from >>>>> data producer to consumer. So I don't think it needs to claim scarce >>>>> bits in the skb. >>>>> >>>>> tun_ebpf_select_queue stores the field, tun_put_user reads it and >>>>> converts it to the virtio_net_hdr in the descriptor. >>>>> >>>>> tun_ebpf_select_queue is called from .ndo_select_queue. Storing the >>>>> field in skb->cb is fragile, as in theory some code could overwrite >>>>> that between field between ndo_select_queue and >>>>> ndo_start_xmit/tun_net_xmit, from which point it is fully under tun >>>>> control again. But in practice, I don't believe anything does. >>>>> >>>>> Alternatively an existing skb field that is used only on disjoint >>>>> datapaths, such as ingress-only, could be viable. >>>> A question here. We had metadata support in XDP for cooperation between >>>> eBPF programs. Do we have something similar in the skb? >>>> >>>> E.g in the RSS, if we want to pass some metadata information between >>>> eBPF program and the logic that generates the vnet header (either hard >>>> logic in the kernel or another eBPF program). Is there any way that can >>>> avoid the possible conflicts of qdiscs? >>> Not that I am aware of. The closest thing is cb[]. >>> >>> It'll have to aliase a field like that, that is known unused for the given path. >> >> Right, we need to make sure cb is not used by other ones. I'm not sure >> how hard to achieve that consider Qemu installs the eBPF program but it >> doesn't deal with networking configurations. >> >> >>> One other approach that has been used within linear call stacks is out >>> of band. Like percpu variables softnet_data.xmit.more and >>> mirred_rec_level. But that is perhaps a bit overwrought for this use >>> case. >> >> Yes, and if we go that way then eBPF turns out to be a burden since we >> need to invent helpers to access those auxiliary data structure. It >> would be better then to hard-coded the RSS in the kernel. >> >> >>>>>>> Instead, you could just run the flow_dissector in tun_put_user if the >>>>>>> feature is negotiated. Indeed, the flow dissector seems more apt to me >>>>>>> than BPF here. Note that the flow dissector internally can be >>>>>>> overridden by a BPF program if the admin so chooses. >>>>>>> >>>>>> When this set of patches is related to hash delivery in the virtio-net >>>>>> packet in general, >>>>>> it was prepared in context of RSS feature implementation as defined in >>>>>> virtio spec [1] >>>>>> In case of RSS it is not enough to run the flow_dissector in tun_put_user: >>>>>> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, >>>>>> hash type and queue index >>>>>> according to the (mapped) parameters (key, hash types, indirection >>>>>> table) received from the guest. >>>>> TUNSETSTEERINGEBPF was added to support more diverse queue selection >>>>> than the default in case of multiqueue tun. Not sure what the exact >>>>> use cases are. >>>>> >>>>> But RSS is exactly the purpose of the flow dissector. It is used for >>>>> that purpose in the software variant RPS. The flow dissector >>>>> implements a superset of the RSS spec, and certainly computes a >>>>> four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC >>>>> has already computed a 4-tuple hash. >>>>> >>>>> What it does not give is a type indication, such as >>>>> VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. >>>>> In datapaths where the NIC has already computed the four-tuple hash >>>>> and stored it in skb->hash --the common case for servers--, That type >>>>> field is the only reason to have to compute again. >>>> The problem is there's no guarantee that the packet comes from the NIC, >>>> it could be a simple VM2VM or host2VM packet. >>>> >>>> And even if the packet is coming from the NIC that calculates the hash >>>> there's no guarantee that it's the has that guest want (guest may use >>>> different RSS keys). >>> Ah yes, of course. >>> >>> I would still revisit the need to store a detailed hash_type along with >>> the hash, as as far I can tell that conveys no actionable information >>> to the guest. >> >> Yes, need to figure out its usage. According to [1], it only mention >> that storing has type is a charge of driver. Maybe Yuri can answer this. >> > For the case of Windows VM we can't know how exactly the network stack > uses provided hash data (including hash type). But: different releases > of Windows > enable different hash types (for example UDP hash is enabled only on > Server 2016 and up). > > Indeed the Windows requires a little more from the network adapter/driver > than Linux does. > > The addition of RSS support to virtio specification takes in account > the widest set of > requirements (i.e. Windows one), our initial impression is that this > should be enough also for Linux. > > The NDIS specification in part of RSS is _mandatory_ and there are > certification tests > that check that the driver provides the hash data as expected. All the > high-performance > network adapters have such RSS functionality in the hardware. > With pre-RSS QEMU (i.e. where the virtio-net device does not indicate > the RSS support) > the virtio-net driver for Windows does all the job related to RSS: > - hash calculation > - hash/hash_type delivery > - reporting each packet on the correct CPU according to RSS settings > > With RSS support in QEMU all the packets always come on a proper CPU and > the driver never needs to reschedule them. The driver still need to > calculate the > hash and report it to Windows. In this case we do the same job twice: the device > (QEMU or eBPF) does calculate the hash and get proper queue/CPU to deliver > the packet. But the hash is not delivered by the device, so the driver needs to > recalculate it and report to the Windows. > > If we add HASH_REPORT support (current set of patches) and the device > indicates this > feature we can avoid hash recalculation in the driver assuming we > receive the correct hash > value and hash type. Otherwise the driver can't know which exactly > hash the device has calculated. > > Please let me know if I did not answer the question. I think I get you. The hash type is also a kind of classification (e.g TCP or UDP). Any possibility that it can be deduced from the driver? (Or it could be too expensive to do that). Thanks > >> Thanks >> >> [1] >> https://docs.microsoft.com/en-us/windows-hardware/drivers/network/indicating-rss-receive-data >> >>
On Mon, Jan 18, 2021 at 4:46 AM Jason Wang <jasowang@redhat.com> wrote: > > > On 2021/1/17 下午3:57, Yuri Benditovich wrote: > > On Thu, Jan 14, 2021 at 5:39 AM Jason Wang <jasowang@redhat.com> wrote: > >> > >> On 2021/1/13 下午10:33, Willem de Bruijn wrote: > >>> On Tue, Jan 12, 2021 at 11:11 PM Jason Wang <jasowang@redhat.com> wrote: > >>>> On 2021/1/13 上午7:47, Willem de Bruijn wrote: > >>>>> On Tue, Jan 12, 2021 at 3:29 PM Yuri Benditovich > >>>>> <yuri.benditovich@daynix.com> wrote: > >>>>>> On Tue, Jan 12, 2021 at 9:49 PM Yuri Benditovich > >>>>>> <yuri.benditovich@daynix.com> wrote: > >>>>>>> On Tue, Jan 12, 2021 at 9:41 PM Yuri Benditovich > >>>>>>> <yuri.benditovich@daynix.com> wrote: > >>>>>>>> Existing TUN module is able to use provided "steering eBPF" to > >>>>>>>> calculate per-packet hash and derive the destination queue to > >>>>>>>> place the packet to. The eBPF uses mapped configuration data > >>>>>>>> containing a key for hash calculation and indirection table > >>>>>>>> with array of queues' indices. > >>>>>>>> > >>>>>>>> This series of patches adds support for virtio-net hash reporting > >>>>>>>> feature as defined in virtio specification. It extends the TUN module > >>>>>>>> and the "steering eBPF" as follows: > >>>>>>>> > >>>>>>>> Extended steering eBPF calculates the hash value and hash type, keeps > >>>>>>>> hash value in the skb->hash and returns index of destination virtqueue > >>>>>>>> and the type of the hash. TUN module keeps returned hash type in > >>>>>>>> (currently unused) field of the skb. > >>>>>>>> skb->__unused renamed to 'hash_report_type'. > >>>>>>>> > >>>>>>>> When TUN module is called later to allocate and fill the virtio-net > >>>>>>>> header and push it to destination virtqueue it populates the hash > >>>>>>>> and the hash type into virtio-net header. > >>>>>>>> > >>>>>>>> VHOST driver is made aware of respective virtio-net feature that > >>>>>>>> extends the virtio-net header to report the hash value and hash report > >>>>>>>> type. > >>>>>>> Comment from Willem de Bruijn: > >>>>>>> > >>>>>>> Skbuff fields are in short supply. I don't think we need to add one > >>>>>>> just for this narrow path entirely internal to the tun device. > >>>>>>> > >>>>>> We understand that and try to minimize the impact by using an already > >>>>>> existing unused field of skb. > >>>>> Not anymore. It was repurposed as a flags field very recently. > >>>>> > >>>>> This use case is also very narrow in scope. And a very short path from > >>>>> data producer to consumer. So I don't think it needs to claim scarce > >>>>> bits in the skb. > >>>>> > >>>>> tun_ebpf_select_queue stores the field, tun_put_user reads it and > >>>>> converts it to the virtio_net_hdr in the descriptor. > >>>>> > >>>>> tun_ebpf_select_queue is called from .ndo_select_queue. Storing the > >>>>> field in skb->cb is fragile, as in theory some code could overwrite > >>>>> that between field between ndo_select_queue and > >>>>> ndo_start_xmit/tun_net_xmit, from which point it is fully under tun > >>>>> control again. But in practice, I don't believe anything does. > >>>>> > >>>>> Alternatively an existing skb field that is used only on disjoint > >>>>> datapaths, such as ingress-only, could be viable. > >>>> A question here. We had metadata support in XDP for cooperation between > >>>> eBPF programs. Do we have something similar in the skb? > >>>> > >>>> E.g in the RSS, if we want to pass some metadata information between > >>>> eBPF program and the logic that generates the vnet header (either hard > >>>> logic in the kernel or another eBPF program). Is there any way that can > >>>> avoid the possible conflicts of qdiscs? > >>> Not that I am aware of. The closest thing is cb[]. > >>> > >>> It'll have to aliase a field like that, that is known unused for the given path. > >> > >> Right, we need to make sure cb is not used by other ones. I'm not sure > >> how hard to achieve that consider Qemu installs the eBPF program but it > >> doesn't deal with networking configurations. > >> > >> > >>> One other approach that has been used within linear call stacks is out > >>> of band. Like percpu variables softnet_data.xmit.more and > >>> mirred_rec_level. But that is perhaps a bit overwrought for this use > >>> case. > >> > >> Yes, and if we go that way then eBPF turns out to be a burden since we > >> need to invent helpers to access those auxiliary data structure. It > >> would be better then to hard-coded the RSS in the kernel. > >> > >> > >>>>>>> Instead, you could just run the flow_dissector in tun_put_user if the > >>>>>>> feature is negotiated. Indeed, the flow dissector seems more apt to me > >>>>>>> than BPF here. Note that the flow dissector internally can be > >>>>>>> overridden by a BPF program if the admin so chooses. > >>>>>>> > >>>>>> When this set of patches is related to hash delivery in the virtio-net > >>>>>> packet in general, > >>>>>> it was prepared in context of RSS feature implementation as defined in > >>>>>> virtio spec [1] > >>>>>> In case of RSS it is not enough to run the flow_dissector in tun_put_user: > >>>>>> in tun_ebpf_select_queue the TUN calls eBPF to calculate the hash, > >>>>>> hash type and queue index > >>>>>> according to the (mapped) parameters (key, hash types, indirection > >>>>>> table) received from the guest. > >>>>> TUNSETSTEERINGEBPF was added to support more diverse queue selection > >>>>> than the default in case of multiqueue tun. Not sure what the exact > >>>>> use cases are. > >>>>> > >>>>> But RSS is exactly the purpose of the flow dissector. It is used for > >>>>> that purpose in the software variant RPS. The flow dissector > >>>>> implements a superset of the RSS spec, and certainly computes a > >>>>> four-tuple for TCP/IPv6. In the case of RPS, it is skipped if the NIC > >>>>> has already computed a 4-tuple hash. > >>>>> > >>>>> What it does not give is a type indication, such as > >>>>> VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. > >>>>> In datapaths where the NIC has already computed the four-tuple hash > >>>>> and stored it in skb->hash --the common case for servers--, That type > >>>>> field is the only reason to have to compute again. > >>>> The problem is there's no guarantee that the packet comes from the NIC, > >>>> it could be a simple VM2VM or host2VM packet. > >>>> > >>>> And even if the packet is coming from the NIC that calculates the hash > >>>> there's no guarantee that it's the has that guest want (guest may use > >>>> different RSS keys). > >>> Ah yes, of course. > >>> > >>> I would still revisit the need to store a detailed hash_type along with > >>> the hash, as as far I can tell that conveys no actionable information > >>> to the guest. > >> > >> Yes, need to figure out its usage. According to [1], it only mention > >> that storing has type is a charge of driver. Maybe Yuri can answer this. > >> > > For the case of Windows VM we can't know how exactly the network stack > > uses provided hash data (including hash type). But: different releases > > of Windows > > enable different hash types (for example UDP hash is enabled only on > > Server 2016 and up). > > > > Indeed the Windows requires a little more from the network adapter/driver > > than Linux does. > > > > The addition of RSS support to virtio specification takes in account > > the widest set of > > requirements (i.e. Windows one), our initial impression is that this > > should be enough also for Linux. > > > > The NDIS specification in part of RSS is _mandatory_ and there are > > certification tests > > that check that the driver provides the hash data as expected. All the > > high-performance > > network adapters have such RSS functionality in the hardware. > > With pre-RSS QEMU (i.e. where the virtio-net device does not indicate > > the RSS support) > > the virtio-net driver for Windows does all the job related to RSS: > > - hash calculation > > - hash/hash_type delivery > > - reporting each packet on the correct CPU according to RSS settings > > > > With RSS support in QEMU all the packets always come on a proper CPU and > > the driver never needs to reschedule them. The driver still need to > > calculate the > > hash and report it to Windows. In this case we do the same job twice: the device > > (QEMU or eBPF) does calculate the hash and get proper queue/CPU to deliver > > the packet. But the hash is not delivered by the device, so the driver needs to > > recalculate it and report to the Windows. > > > > If we add HASH_REPORT support (current set of patches) and the device > > indicates this > > feature we can avoid hash recalculation in the driver assuming we > > receive the correct hash > > value and hash type. Otherwise the driver can't know which exactly > > hash the device has calculated. > > > > Please let me know if I did not answer the question. > > > I think I get you. The hash type is also a kind of classification (e.g > TCP or UDP). Any possibility that it can be deduced from the driver? (Or > it could be too expensive to do that). > The driver does it today (when the device does not offer any features) and of course can continue doing it. IMO if the device can't report the data according to the spec it should not indicate support for the respective feature (or fallback to vhost=off). Again, IMO if Linux does not need the exact hash_type we can use (for Linux) the way that Willem de Brujin suggested in his patchset: - just add VIRTIO_NET_HASH_REPORT_L4 to the spec - Linux can use MQ + hash delivery (and use VIRTIO_NET_HASH_REPORT_L4) - Linux can use (if makes sense) RSS with VIRTIO_NET_HASH_REPORT_L4 and eBPF - Windows gets what it needs + eBPF So, everyone has what they need at the respective cost. Regarding use of skb->cb for hash type: Currently, if I'm not mistaken, there are 2 bytes at the end of skb->cb: skb->cb is 48 bytes array There is skb_gso_cb (14 bytes) at offset SKB_GSO_CB_OFFSET(32) Is it possible to use one of these 2 bytes for hash_type? If yes, shall we extend the skb_gso_cb and place the 1-bytes hash_type in it or just emit compilation error if the skb_gso_cb grows beyond 15 bytes? > Thanks > > > > > >> Thanks > >> > >> [1] > >> https://docs.microsoft.com/en-us/windows-hardware/drivers/network/indicating-rss-receive-data > >> > >> >
> > >>>>> What it does not give is a type indication, such as > > >>>>> VIRTIO_NET_HASH_TYPE_TCPv6. I don't understand how this would be used. > > >>>>> In datapaths where the NIC has already computed the four-tuple hash > > >>>>> and stored it in skb->hash --the common case for servers--, That type > > >>>>> field is the only reason to have to compute again. > > >>>> The problem is there's no guarantee that the packet comes from the NIC, > > >>>> it could be a simple VM2VM or host2VM packet. > > >>>> > > >>>> And even if the packet is coming from the NIC that calculates the hash > > >>>> there's no guarantee that it's the has that guest want (guest may use > > >>>> different RSS keys). > > >>> Ah yes, of course. > > >>> > > >>> I would still revisit the need to store a detailed hash_type along with > > >>> the hash, as as far I can tell that conveys no actionable information > > >>> to the guest. > > >> > > >> Yes, need to figure out its usage. According to [1], it only mention > > >> that storing has type is a charge of driver. Maybe Yuri can answer this. > > >> > > > For the case of Windows VM we can't know how exactly the network stack > > > uses provided hash data (including hash type). But: different releases > > > of Windows > > > enable different hash types (for example UDP hash is enabled only on > > > Server 2016 and up). > > > > > > Indeed the Windows requires a little more from the network adapter/driver > > > than Linux does. > > > > > > The addition of RSS support to virtio specification takes in account > > > the widest set of > > > requirements (i.e. Windows one), our initial impression is that this > > > should be enough also for Linux. > > > > > > The NDIS specification in part of RSS is _mandatory_ and there are > > > certification tests > > > that check that the driver provides the hash data as expected. All the > > > high-performance > > > network adapters have such RSS functionality in the hardware. Thanks for the context. If Windows requires the driver to pass the hash-type along with the hash data, then indeed this will be needed. If it only requires the device to support a subset of of the possible types, chosen at init, that would be different and it would be cheaper for the driver to pass this config to the device one time. > > > With pre-RSS QEMU (i.e. where the virtio-net device does not indicate > > > the RSS support) > > > the virtio-net driver for Windows does all the job related to RSS: > > > - hash calculation > > > - hash/hash_type delivery > > > - reporting each packet on the correct CPU according to RSS settings > > > > > > With RSS support in QEMU all the packets always come on a proper CPU and > > > the driver never needs to reschedule them. The driver still need to > > > calculate the > > > hash and report it to Windows. In this case we do the same job twice: the device > > > (QEMU or eBPF) does calculate the hash and get proper queue/CPU to deliver > > > the packet. But the hash is not delivered by the device, so the driver needs to > > > recalculate it and report to the Windows. > > > > > > If we add HASH_REPORT support (current set of patches) and the device > > > indicates this > > > feature we can avoid hash recalculation in the driver assuming we > > > receive the correct hash > > > value and hash type. Otherwise the driver can't know which exactly > > > hash the device has calculated. > > > > > > Please let me know if I did not answer the question. > > > > > > I think I get you. The hash type is also a kind of classification (e.g > > TCP or UDP). Any possibility that it can be deduced from the driver? (Or > > it could be too expensive to do that). > > > The driver does it today (when the device does not offer any features) > and of course can continue doing it. > IMO if the device can't report the data according to the spec it > should not indicate support for the respective feature (or fallback to > vhost=off). > Again, IMO if Linux does not need the exact hash_type we can use (for > Linux) the way that Willem de Brujin suggested in his patchset: > - just add VIRTIO_NET_HASH_REPORT_L4 to the spec > - Linux can use MQ + hash delivery (and use VIRTIO_NET_HASH_REPORT_L4) > - Linux can use (if makes sense) RSS with VIRTIO_NET_HASH_REPORT_L4 and eBPF > - Windows gets what it needs + eBPF > So, everyone has what they need at the respective cost. > > Regarding use of skb->cb for hash type: > Currently, if I'm not mistaken, there are 2 bytes at the end of skb->cb: > skb->cb is 48 bytes array > There is skb_gso_cb (14 bytes) at offset SKB_GSO_CB_OFFSET(32) > Is it possible to use one of these 2 bytes for hash_type? > If yes, shall we extend the skb_gso_cb and place the 1-bytes hash_type > in it or just emit compilation error if the skb_gso_cb grows beyond 15 > bytes? Good catch on segmentation taking place between .ndo_select_queue and .ndo_start_xmit. That also means that whatever field in the skb is used, has to be copied to all segments in skb_segment. Which happens for cb. But this feature is completely unrelated to the skb_gso_cb type. Perhaps another field with a real type is more clear. For instance, an extension to the union with napi_id and sender_cpu, as neither is used in this egress path with .ndo_select_queue?