user/sven/linux.git/include/linux/netdevice.h, branch v6.12.7

net: fix races in netdev_tx_sent_queue()/dev_watchdog()

2024-10-21T10:54:25Z

Some workloads hit the infamous dev_watchdog() message: "NETDEV WATCHDOG: eth0 (xxxx): transmit queue XX timed out" It seems possible to hit this even for perfectly normal BQL enabled drivers: 1) Assume a TX queue was idle for more than dev->watchdog_timeo (5 seconds unless changed by the driver) 2) Assume a big packet is sent, exceeding current BQL limit. 3) Driver ndo_start_xmit() puts the packet in TX ring, and netdev_tx_sent_queue() is called. 4) QUEUE_STATE_STACK_XOFF could be set from netdev_tx_sent_queue() before txq->trans_start has been written. 5) txq->trans_start is written later, from netdev_start_xmit() if (rc == NETDEV_TX_OK) txq_trans_update(txq) dev_watchdog() running on another cpu could read the old txq->trans_start, and then see QUEUE_STATE_STACK_XOFF, because 5) did not happen yet. To solve the issue, write txq->trans_start right before one XOFF bit is set : - _QUEUE_STATE_DRV_XOFF from netif_tx_stop_queue() - __QUEUE_STATE_STACK_XOFF from netdev_tx_sent_queue() From dev_watchdog(), we have to read txq->state before txq->trans_start. Add memory barriers to enforce correct ordering. In the future, we could avoid writing over txq->trans_start for normal operations, and rename this field to txq->xoff_start_time. Fixes: bec251bc8b6a ("net: no longer stop all TX queues in dev_watchdog()") Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Reviewed-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20241015194118.3951657-1-edumazet@google.com Signed-off-by: Paolo Abeni

net: Fix gso_features_check to check for both dev->gso_{ipv4_,}max_size

2024-10-01T08:48:52Z

Commit 24ab059d2ebd ("net: check dev->gso_max_size in gso_features_check()") added a dev->gso_max_size test to gso_features_check() in order to fall back to GSO when needed. This was added as it was noticed that some drivers could misbehave if TSO packets get too big. However, the check doesn't respect dev->gso_ipv4_max_size limit. For instance, a device could be configured with BIG TCP for IPv4, but not IPv6. Therefore, add a netif_get_gso_max_size() equivalent to netif_get_gro_max_size() and use the helper to respect both limits before falling back to GSO engine. Fixes: 24ab059d2ebd ("net: check dev->gso_max_size in gso_features_check()") Signed-off-by: Daniel Borkmann Cc: Eric Dumazet Cc: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240923212242.15669-2-daniel@iogearbox.net Signed-off-by: Paolo Abeni

net: Add netif_get_gro_max_size helper for GRO

2024-10-01T08:48:51Z

Add a small netif_get_gro_max_size() helper which returns the maximum IPv4 or IPv6 GRO size of the netdevice. We later add a netif_get_gso_max_size() equivalent as well for GSO, so that these helpers can be used consistently instead of open-coded checks. Signed-off-by: Daniel Borkmann Cc: Eric Dumazet Cc: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240923212242.15669-1-daniel@iogearbox.net Signed-off-by: Paolo Abeni

netdev: support binding dma-buf to netdevice

2024-09-12T03:44:31Z

Add a netdev_dmabuf_binding struct which represents the dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to rx queues on the netdevice. On the binding, the dma_buf_attach & dma_buf_map_attachment will occur. The entries in the sg_table from mapping will be inserted into a genpool to make it ready for allocation. The chunks in the genpool are owned by a dmabuf_chunk_owner struct which holds the dma-buf offset of the base of the chunk and the dma_addr of the chunk. Both are needed to use allocations that come from this chunk. We create a new type that represents an allocation from the genpool: net_iov. We setup the net_iov allocation size in the genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally allocated by the page pool and given to the drivers. The user can unbind the dmabuf from the netdevice by closing the netlink socket that established the binding. We do this so that the binding is automatically unbound even if the userspace process crashes. The binding and unbinding leaves an indicator in struct netdev_rx_queue that the given queue is bound, and the binding is actuated by resetting the rx queue using the queue API. The netdev_dmabuf_binding struct is refcounted, and releases its resources only when all the refs are released. Signed-off-by: Willem de Bruijn Signed-off-by: Kaiyuan Zhang Signed-off-by: Mina Almasry Reviewed-by: Pavel Begunkov # excluding netlink Acked-by: Daniel Vetter Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-4-almasrymina@google.com Signed-off-by: Jakub Kicinski

Merge branch '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

2024-09-12T03:24:43Z

Tony Nguyen says: ==================== idpf: XDP chapter II: convert Tx completion to libeth Alexander Lobakin says: XDP for idpf is currently 5 chapters: * convert Rx to libeth; * convert Tx completion to libeth (this); * generic XDP and XSk code changes; * actual XDP for idpf via libeth_xdp; * XSk for idpf (^). Part II does the following: * adds generic libeth Tx completion routines; * converts idpf to use generic libeth Tx comp routines; * fixes Tx queue timeouts and robustifies Tx completion in general; * fixes Tx event/descriptor flushes (writebacks). Most idpf patches again remove more lines than adds. Generic Tx completion helpers and structs are needed as libeth_xdp (Ch. III) makes use of them. WB_ON_ITR is needed since XDPSQs don't want to work without it at all. Tx queue timeouts fixes are needed since without them, it's way easier to catch a Tx timeout event when WB_ON_ITR is enabled. * '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue: idpf: enable WB_ON_ITR idpf: fix netdev Tx queue stop/wake idpf: refactor Tx completion routines netdevice: add netdev_tx_reset_subqueue() shorthand idpf: convert to libeth Tx buffer completion libeth: add Tx buffer completion helpers ==================== Link: https://patch.msgid.link/20240909205323.3110312-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski

net: remove dev_pick_tx_cpu_id()

2024-09-09T23:53:38Z

dev_pick_tx_cpu_id() has been introduced with two users by commit a4ea8a3dacc3 ("net: Add generic ndo_select_queue functions"). The use in AF_PACKET has been removed in 2019 by commit b71b5837f871 ("packet: rework packet_pick_tx_queue() to use common code selection") The other user was a Netlogic XLP driver, removed in 2021 by commit 47ac6f567c28 ("staging: Remove Netlogic XLP network driver"). It's relatively unlikely that any modern driver will need an .ndo_select_queue implementation which picks purely based on CPU ID and skips XPS, delete dev_pick_tx_cpu_id() Found by code inspection. Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240906161059.715546-1-kuba@kernel.org Signed-off-by: Jakub Kicinski

netdevice: add netdev_tx_reset_subqueue() shorthand

2024-09-09T20:15:37Z

Add a shorthand similar to other net*_subqueue() helpers for resetting the queue by its index w/o obtaining &netdev_tx_queue beforehand manually. Reviewed-by: Przemek Kitszel Signed-off-by: Alexander Lobakin Signed-off-by: Tony Nguyen

net: napi: Prevent overflow of napi_defer_hard_irqs

2024-09-06T01:42:56Z

In commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature") napi_defer_irqs was added to net_device and napi_defer_irqs_count was added to napi_struct, both as type int. This value never goes below zero, so there is not reason for it to be a signed int. Change the type for both from int to u32, and add an overflow check to sysfs to limit the value to S32_MAX. The limit of S32_MAX was chosen because the practical limit before this patch was S32_MAX (anything larger was an overflow) and thus there are no behavioral changes introduced. If the extra bit is needed in the future, the limit can be raised. Before this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' $ cat /sys/class/net/eth4/napi_defer_hard_irqs -2147483647 After this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' bash: line 0: echo: write error: Numerical result out of range Similarly, /sys/class/net/XXXXX/tx_queue_len is defined as unsigned: include/linux/netdevice.h: unsigned int tx_queue_len; And has an overflow check: dev_change_tx_queue_len(..., unsigned long new_len): if (new_len != (unsigned int)new_len) return -ERANGE; Suggested-by: Jakub Kicinski Signed-off-by: Joe Damato Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240904153431.307932-1-jdamato@fastly.com Signed-off-by: Jakub Kicinski

netdev_features: convert NETIF_F_FCOE_MTU to dev->fcoe_mtu

2024-09-03T09:36:43Z

Ability to handle maximum FCoE frames of 2158 bytes can never be changed and thus more of an attribute, not a toggleable feature. Move it from netdev_features_t to "cold" priv flags (bitfield bool) and free yet another feature bit. Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni

netdev_features: convert NETIF_F_NETNS_LOCAL to dev->netns_local

2024-09-03T09:36:43Z

"Interface can't change network namespaces" is rather an attribute, not a feature, and it can't be changed via Ethtool. Make it a "cold" private flag instead of a netdev_feature and free one more bit. Signed-off-by: Alexander Lobakin Signed-off-by: Paolo Abeni