- 15 Nov, 2019 40 commits
-
-
Julian Wiedmann authored
Current code processes each (VLAN) device twice - once to inspect the IPv4 mcast addresses, and then a second time to walk the IPv6 mcast addresses. Unify all this into a single helper, thus removing some checks and a duplicated VLAN lookup. Signed-off-by:
Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Julian Wiedmann authored
Trust the IPv4/IPv6 code to properly remove its mcast addresses when a VLAN device is unregistered, and then also trigger an RX modeset whenever it's needed. Signed-off-by:
-
Julian Wiedmann authored
Push the inet6_dev locking down into the helper that actually needs it for walking the mc_list. Signed-off-by:
-
Julian Wiedmann authored
qeth_core_free_card() is meant to be the counterpart of qeth_alloc_card() - but unfortunately was also picked as the place to free the QDIO queues. This gets messy when qeth_core_probe_device() fails during qeth_add_dbf_entry(). At this point the card->qdio.state is not initialized yet, so qeth_free_qdio_queues() ends up operating on uninitialized data. Luckily for now, the whole qeth_card struct is zero-allocated and the value of the QETH_QDIO_UNINITIALIZED enum is 0 as well. So there's no real impact from this bug at the moment, it's just really fragile. Clean this up by moving the qeth_free_qdio_queues() call up one level in the hierarchy. This way it doesn't get called from the error path. Signed-off-by:
-
Julian Wiedmann authored
When current code fails to allocate an skb in the RX path, it drops the whole RX buffer. Considering the large number of packets that a single RX buffer might contain, this is quite drastic. Skip over the packet instead, and try to extract the next packet from the RX buffer. Signed-off-by:
-
Julian Wiedmann authored
Packets with an unexpected HW format are currently first extracted from the RX buffer, passed upwards to the layer-specific driver and only then finally dropped. Enhance the RX path so that we can drop such packets before even allocating an skb. For this, add some additional logic so that when a packet is meant to be dropped, we can still walk along the packet's data chunks in the RX buffer. This allows us to extract the following packet(s) from the buffer. Signed-off-by:
-
Julian Wiedmann authored
Each RX buffer may contain up to 64KB worth of data. In case the device needs to discard a packet _after_ already having reserved space for it in the buffer, the whole buffer gets set to ERROR state. As the buffer might contain any number of good packets, this can result in collateral packet loss. qeth can provide relief by enabling per-frame invalidation. The RX buffer is then presented as usual, we just need to spot & drop any individual packet that was flagged as invalid. Signed-off-by:
-
Julian Wiedmann authored
Where available, use the fine-grained counters in rtnl_link_stats64 to indicate different RX error causes. For drop reasons, use driver-private ethtool counters. In particular this patch allows us to keep track of driver-side drops due to unknown/unsupported HW descriptor format. Signed-off-by:
-
David S. Miller authored
Stefano Garzarella says: ==================== vsock: add multi-transports support Most of the patches are reviewed by Dexuan, Stefan, and Jorgen. The following patches need reviews: - [11/15] vsock: add multi-transports support - [12/15] vsock/vmci: register vmci_transport only when VMCI guest/host are active - [15/15] vhost/vsock: refuse CID assigned to the guest->host transport RFC: https://patchwork.ozlabs.org/cover/1168442/ v1: https://patchwork.ozlabs.org/cover/1181986/ v1 -> v2: - Patch 11: + vmci_transport: sent reset when vsock_assign_transport() fails [Jorgen] + fixed loopback in the guests, checking if the remote_addr is the same of transport_g2h->get_local_cid() + virtio_transport_common: updated space available while creating the new child socket during a connection request - Patch 12: + removed 'features' variable in vmci_transport_init() [Stefan] + added a flag to register only once the host [Jorgen] - Added patch 15 to refuse CID assigned to the guest->host transport in the vhost_transport This series adds the multi-transports support to vsock, following this proposal: https://www.spinics.net/lists/netdev/msg575792.html With the multi-transports support, we can use VSOCK with nested VMs (using also different hypervisors) loading both guest->host and host->guest transports at the same time. Before this series, vmci_transport supported this behavior but only using VMware hypervisor on L0, L1, etc. The first 9 patches are cleanups and preparations, maybe some of these can go regardless of this series. Patch 10 changes the hvs_remote_addr_init(). setting the VMADDR_CID_HOST as remote CID instead of VMADDR_CID_ANY to make the choice of transport to be used work properly. Patch 11 adds multi-transports support. Patch 12 changes a little bit the vmci_transport and the vmci driver to register the vmci_transport only when there are active host/guest. Patch 13 prevents the transport modules unloading while sockets are assigned to them. Patch 14 fixes an issue in the bind() logic discoverable only with the new multi-transport support. Patch 15 refuses CID assigned to the guest->host transport in the vhost_transport. I've tested this series with nested KVM (vsock-transport [L0,L1], virtio-transport[L1,L2]) and with VMware (L0) + KVM (L1) (vmci-transport [L0,L1], vhost-transport [L1], virtio-transport[L2]). Dexuan successfully tested the RFC series on HyperV with a Linux guest. ==================== Signed-off-by: -
Stefano Garzarella authored
In a nested VM environment, we have to refuse to assign to a nested guest the same CID assigned to our guest->host transport. In this way, the user can use the local CID for loopback. Signed-off-by:
Stefano Garzarella <sgarzare@redhat.com> Signed-off-by:
-
Stefano Garzarella authored
When we are looking for a socket bound to a specific address, we also have to take into account the CID. This patch is useful with multi-transports support because it allows the binding of the same port with different CID, and it prevents a connection to a wrong socket bound to the same port, but with different CID. Reviewed-by:
Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by:
Jorgen Hansen <jhansen@vmware.com> Signed-off-by:
-
Stefano Garzarella authored
This patch adds 'module' member in the 'struct vsock_transport' in order to get/put the transport module. This prevents the module unloading while sockets are assigned to it. We increase the module refcnt when a socket is assigned to a transport, and we decrease the module refcnt when the socket is destructed. Reviewed-by:
-
Stefano Garzarella authored
To allow other transports to be loaded with vmci_transport, we register the vmci_transport as G2H or H2G only when a VMCI guest or host is active. To do that, this patch adds a callback registered in the vmci driver that will be called when the host or guest becomes active. This callback will register the vmci_transport in the VSOCK core. Cc: Jorgen Hansen <jhansen@vmware.com> Signed-off-by:
-
Stefano Garzarella authored
This patch adds the support of multiple transports in the VSOCK core. With the multi-transports support, we can use vsock with nested VMs (using also different hypervisors) loading both guest->host and host->guest transports at the same time. Major changes: - vsock core module can be loaded regardless of the transports - vsock_core_init() and vsock_core_exit() are renamed to vsock_core_register() and vsock_core_unregister() - vsock_core_register() has a feature parameter (H2G, G2H, DGRAM) to identify which directions the transport can handle and if it's support DGRAM (only vmci) - each stream socket is assigned to a transport when the remote CID is set (during the connect() or when we receive a connection request on a listener socket). The remote CID is used to decide which transport to use: - remote CID <= VMADDR_CID_HOST will use guest->host transport; - remote CID == local_cid (guest->host transport) will use guest->host transport for loopback (host->guest transports don't support loopback); - remote CID > VMADDR_CID_HOST will use host->guest transport; - listener sockets are not bound to any transports since no transport operations are done on it. In this way we can create a listener socket, also if the transports are not loaded or with VMADDR_CID_ANY to listen on all transports. - DGRAM sockets are handled as before, since only the vmci_transport provides this feature. Signed-off-by: -
Stefano Garzarella authored
Remote peer is always the host, so we set VMADDR_CID_HOST as remote CID instead of VMADDR_CID_ANY. Reviewed-by:
Dexuan Cui <decui@microsoft.com> Reviewed-by:
-
Stefano Garzarella authored
vsock_insert_unbound() was called only when 'sock' parameter of __vsock_create() was not null. This only happened when __vsock_create() was called by vsock_create(). In order to simplify the multi-transports support, this patch moves vsock_insert_unbound() at the end of vsock_create(). Reviewed-by:
-
Stefano Garzarella authored
All transports call __vsock_create() with the same parameters, most of them depending on the parent socket. In order to simplify the VSOCK core APIs exposed to the transports, this patch adds the vsock_create_connected() callable from transports to create a new socket when a connection request is received. We also unexported the __vsock_create(). Suggested-by:
-
Stefano Garzarella authored
virtio_transport and vmci_transport handle the buffer_size sockopts in a very similar way. In order to support multiple transports, this patch moves this handling in the core to allow the user to change the options also if the socket is not yet assigned to any transport. This patch also adds the '.notify_buffer_size' callback in the 'struct virtio_transport' in order to inform the transport, when the buffer_size is changed by the user. It is also useful to limit the 'buffer_size' requested (e.g. virtio transports). Acked-by:
-
Stefano Garzarella authored
Since now the 'struct vsock_sock' object contains a pointer to the transport, this patch adds a parameter to the vsock_core_get_transport() to return the right transport assigned to the socket. This patch modifies also the virtio_transport_get_ops(), that uses the vsock_core_get_transport(), adding the 'struct vsock_sock *' parameter. Reviewed-by:
-
Stefano Garzarella authored
We are going to add 'struct vsock_sock *' parameter to virtio_transport_get_ops(). In some cases, like in the virtio_transport_reset_no_sock(), we don't have any socket assigned to the packet received, so we can't use the virtio_transport_get_ops(). In order to allow virtio_transport_reset_no_sock() to use the '.send_pkt' callback from the 'vhost_transport' or 'virtio_transport', we add the 'struct virtio_transport *' to it and to its caller: virtio_transport_recv_pkt(). We moved the 'vhost_transport' and 'virtio_transport' definition, to pass their address to the virtio_transport_recv_pkt(). Reviewed-by:
-
Stefano Garzarella authored
As a preparation to support multiple transports, this patch adds the 'transport' member at the 'struct vsock_sock'. This new field is initialized during the creation in the __vsock_create() function. This patch also renames the global 'transport' pointer to 'transport_single', since for now we're only supporting a single transport registered at run-time. Reviewed-by:
-
Stefano Garzarella authored
This header file now only includes the "uapi/linux/vm_sockets.h". We can include directly it when needed. Reviewed-by:
-
Stefano Garzarella authored
vm_sockets_get_local_cid() is only used in virtio_transport_common.c. We can replace it calling the virtio_transport_get_ops() and using the get_local_cid() callback registered by the transport. Reviewed-by:
-
Stefano Garzarella authored
The VSOCK_DEFAULT_CONNECT_TIMEOUT definition was introduced with commit d021c344 ("VSOCK: Introduce VM Sockets"), but it is never used in the net/vmw_vsock/vmci_transport.c. VSOCK_DEFAULT_CONNECT_TIMEOUT is used and defined in net/vmw_vsock/af_vsock.c Cc: Jorgen Hansen <jhansen@vmware.com> Reviewed-by:
-
David S. Miller authored
Sunil Goutham says: ==================== octeontx2-af: Debugfs support and updates to parser profile This patchset adds debugfs support to dump various HW state machine info which helps in debugging issues. Info includes - Current queue context, stats, resource utilization etc - MCAM entry utilization, miss and pkt drop counter - CGX ingress and egress stats - Current RVU block allocation status - etc. Rest patches has changes wrt - Updated packet parsing profile for parsing more protocols. - RSS algorithms to include inner protocols while generating hash - Handle current version of silicon's limitations wrt shaping, coloring and fixed mapping of transmit limiter queue's configuration. - Enable broadcast packet replication to PF and it's VFs. - Support for configurable NDC cache waymask - etc Changes from v1: Removed inline keyword for newly introduced APIs in few patches. - Suggested by David Miller. ==================== Signed-off-by: -
Subbaraya Sundeep authored
Traffic for a CGX mapped NIXLF can be stopped by disabling entries in NPC MCAM or by configuring CGX and mailbox messages exist for the two options. If traffic is stopped at CGX then VFs of that PF are also effected hence CGX traffic should be started/stopped by tracking all the users of it. This patch implements that CGX users tracking. CGX is also configured along with NPC if required. Also removed a check which mandates even number of LBK VFs. Signed-off-by:
Subbaraya Sundeep <sbhatta@marvell.com> Signed-off-by:
Sunil Goutham <sgoutham@marvell.com> Signed-off-by:
-
Sunil Goutham authored
A config option is added to disable caching of dynamic entries like SQEs and stack pages. Also locks down all HW contexts in NDC, preventing them from being evicted. This option is useful when the queue count is large and there are huge NDC cache misses. It's trade off between SQ context misses and dynamically changing entries like SQE and stack page pointers. Signed-off-by:
-
Geetha sowjanya authored
Each of the NIX/NPA LFs can choose which ways of their respective NDC caches should be used to cache their contexts. This enables flexible configurations like disabling caching for a LF, limiting it's context to a certain set of ways etc etc. Separate way_mask for NIX-TX and NIX-RX is not supported. Signed-off-by:
Geetha sowjanya <gakula@marvell.com> Signed-off-by:
-
Sunil Goutham authored
Ingress packet replication support has been added to 96xx B0 silicon. This patch enables using that feature to replicate ingress broadcast packets to PF and it's VFs. Also fixed below issues - VFs can also install NPC MCAM entry to forward broadcast pkts. Otherwise, unless PF's interface is UP, VFs will not receive bcast packets. - NPC MCAM entry is disabled when PF and all it's VFs are down. - Few corner cases in installing multicast entry list. Signed-off-by:
-
Sunil Goutham authored
CN96xx initial silicon doesn't support all features pertaining to NIX transmit scheduling and shaping. - It supports a fixed topology of 1:1 mapped transmit limiters at all levels. - Supports DWRR only at SMQ/MDQ and TL1. - Doesn't support shaping and coloring. This patch adds HW capability structure by which each variant and skew of silicon can be differentiated by their supported features. And adds support for A0 silicon's transmit scheduler capabilities or rather limitations. Signed-off-by:
-
Kiran Kumar K authored
This patch adds support for few more RSS key types for flow key algorithm to compute rss hash index. Following flow key types have been added. - Tunnel types like NVGRE, VXLAN, GENEVE. - L2 offload type ETH_DMAC, Here we will consider only DMAC 6 bytes. - And extension header IPV6_EXT (1 byte followed by IPV6 header - Hashing inner protocol fields for inner DMAC, IPv4/v6, TCP, UDP, SCTP. Signed-off-by:
Kiran Kumar K <kirankumark@marvell.com> Signed-off-by:
-
Nithin Dabilpuram authored
Writing into NPC MCAM1 and MCAM0 registers are suppressed if they happened to form a reserved combination. Hence clear and disable MCAM entries before update. For HRM: [CAM(1)]<n>=1, [CAM(0)]<n>=1: Reserved. The reserved combination is not allowed. Hardware suppresses any write to CAM(0) or CAM(1) that would result in the reserved combination for any CAM bit. Signed-off-by:
Nithin Dabilpuram <ndabilpuram@marvell.com> Signed-off-by:
-
Hao Zheng authored
Updated NPC KPU packet parsing profile with support for following - Fragmentation support for IPv4 IPv6 outer header - NIX instruction header support - QinQ with TPID of 0x8100 as non inner most vlan tag, as legacy network equipments still generate QinQ packets with this configuration. - To better support RSS for tunnelled packets, udp based tunnel protocols such as vxlan, vxlan-gpe, geneve and gtpu are now captured into a separate layer E. Consequently, the inner packet headers are pushed one layer down to LF, LG, and LH accordingly. - Support for rfc7510 mpls in udp. Up to 4 MPLS labels can be parsed and captured in one layer LE. - Parser support for DSA, extended DSA and eDSA tags right after ethernet header by Marvell SOHO and Falcon switches. For extended DSA and eDSA tags, a special PKIND of 62 is used, as these tags don't contain a tpid field. - Higig2 protocol header parsing support, added a NPC_LT_LA_HIGIG2_ETHER for a combined header of HIGIG2 and Ethernet. Add a NPC_LT_LA_IH_NIX_HIGIG2_ETHER for a combined header of nix_ih, HIGIG2 and Ethernet on egress side. Also added 2 upper flags in LA to indicate the presence of nix_ih and HIGIG2. Other changes include - IPv4.TTL==0 IPv6.HLIM==0 check - Per RFC 1858, mark fragment offset == 1 as error - TCP invalid flags check - Separate error codes for outer and inner IPv4 checksum errors. - Fix a parser error when KPU parses incoming IPSec ESP and AH packets - NPC vtag capture/strip hardware expect tag pointer to point to tpid/ethertype instead of tci. So move lb_ptr to point to tpid/ethertype. - Fix npc parser error when parsing udp packets that don't have any payload. - For a single MCAM entry to match on packets with one or stacked vlan tags combine NPC_LT_LB_STAG and NPC_LT_LB_QINQ to NPC_LT_LB_STAG_QINQ. - NVGRE to have a separate ltype LD_NVGRE instead of combined with LD_GRE. - Reserve top LD/LTYPEs to support custom KPU profile fields. Signed-off-by:
Hao Zheng <haoz@marvell.com> Signed-off-by:
-
Subbaraya Sundeep authored
For every mailbox handler added to rvu, we are adding a function declaration in rvu header file. Cleaned this up by adding a macro to generate these declarations automatically. Signed-off-by:
-
Geetha sowjanya authored
If mailbox client has a bounce buffer or a intermediate buffer where mbox messages are framed then copy them from there to HW buffer. If 'mbase' and 'hw_mbase' are not same then assume 'mbase' points to bounce buffer. This patch also adds msg_size field to mbox header to copy only valid data instead of whole buffer. Signed-off-by:
-
Sunil Goutham authored
Added a new mailbox API which goes through all responses to check their IDs and response codes. Also added logic to prevent queuing multiple works to process the same mailbox message. This scenario happens when AF is processing a PF's request and menawhile PF sends ACK to AF sent UP message, then mbox_hdr->num_msgs in the PF->AF DOWN mbox region will be nonzero and AF will end up processing PF's request again. This is fixed by taking a backup of num_msgs counter and clearing the same in the mbox region before scheduling work. Signed-off-by:
-
Sunil Goutham authored
Added support to display current NPC MCAM entries and counter's allocation status ín debugfs. cat /sys/kernel/debug/octeontx2/npc/mcam_info' will dump following info - MCAM Rx and Tx keysize - Total MCAM entries and counters - Current available count - Count of number of MCAM entries and counters allocated by a RVU PF/VF device. Also, one NPC MCAM counter (last one) is reserved and mapped to NPC RX_INTF's MISS_ACTION to count dropped packets due to no MCAM entry match. This pkt drop counter can be checked via debugfs. Signed-off-by:
-
Linu Cherian authored
A CGX port is shared by a RVU PF and it's VFs. These per CGX port level NIX Rx/Tx counters are cumilative stats of all NIXLFs sharing this port. These stats when compared to CGX Rx/Tx stats helps in identifying pkts dropped within the system, if any. Signed-off-by:
Linu Cherian <lcherian@marvell.com> Signed-off-by:
-
Prakash Brahmajyosyula authored
This patch adds CGX LMAC physical interface or serdes Rx/Tx packet stats to debugfs. 'cat cgx<idx>/lmac<idx>/stats' dumps the current interface link status and Rx/Tx stats. Stats include pkt received/transmitted, dropped, pause frames etc etc. Signed-off-by:
Prakash Brahmajyosyula <bprakash@marvell.com> Signed-off-by:
-
Prakash Brahmajyosyula authored
NDC is a data cache unit which caches NPA and NIX block's aura/pool/RQ/SQ/CQ/etc contexts to reduce number of costly DRAM accesses. This patch adds support to dump cache's performance stats like cache line hit/miss counters, average cycles taken for accessing cached and non-cached data. This will help in checking if NPA/NIX context reads/writes are having NDC cache misses which inturn might effect performance. Also changed NDC enums to reflect correct NDC hardware instance. Signed-off-by:
-
