lwn.git/drivers/net/ethernet/amazon, branch v6.11-rc1

net: ena: Fix redundant device NUMA node override

2024-05-30T02:01:34+00:00

The driver overrides the NUMA node id of the device regardless of whether it knows its correct value (often setting it to -1 even though the node id is advertised in 'struct device'). This can lead to suboptimal configurations. This patch fixes this behavior and makes the shared memory allocation functions use the NUMA node id advertised by the underlying device. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Shay Agroskin Link: https://lore.kernel.org/r/20240528170912.1204417-1-shayagr@amazon.com Signed-off-by: Jakub Kicinski

net: ena: Change initial rx_usec interval

2024-05-13T21:42:04+00:00

For the purpose of obtaining better CPU utilization, minimum rx moderation interval is set to 20 usec. Signed-off-by: Osama Abboud Signed-off-by: David Arinzon Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240512134637.25299-6-darinzon@amazon.com Signed-off-by: Jakub Kicinski

net: ena: Changes around strscpy calls

2024-05-13T21:42:04+00:00

strscpy copies as much of the string as possible, meaning that the destination string will be truncated in case of no space. As this is a non-critical error in our case, adding a debug level print for indication. This patch also removes a -1 which was added to ensure enough space for NUL, but strscpy destination string is guaranteed to be NUL-terminted, therefore, the -1 is not needed. Signed-off-by: David Arinzon Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240512134637.25299-5-darinzon@amazon.com Signed-off-by: Jakub Kicinski

net: ena: Add validation for completion descriptors consistency

2024-05-13T21:42:04+00:00

Validate that `first` flag is set only for the first descriptor in multi-buffer packets. In case of an invalid descriptor, a reset will occur. A new reset reason for RX data corruption has been added. Signed-off-by: Shahar Itzko Signed-off-by: David Arinzon Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240512134637.25299-4-darinzon@amazon.com Signed-off-by: Jakub Kicinski

net: ena: Reduce holes in ena_com structures

2024-05-13T21:42:04+00:00

This patch makes two changes in order to fill holes and reduce ther overall size of the structures ena_com_dev and ena_com_rx_ctx. Signed-off-by: Shahar Itzko Signed-off-by: David Arinzon Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240512134637.25299-3-darinzon@amazon.com Signed-off-by: Jakub Kicinski

net: ena: Add a counter for driver's reset failures

2024-05-13T21:42:04+00:00

This patch adds a counter to the ena_adapter struct in order to keep track of reset failures. The counter is incremented every time either ena_restore_device() or ena_destroy_device() fail. Signed-off-by: Osama Abboud Signed-off-by: David Arinzon Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240512134637.25299-2-darinzon@amazon.com Signed-off-by: Jakub Kicinski

net: annotate writes on dev->mtu from ndo_change_mtu()

2024-05-07T23:19:14+00:00

Simon reported that ndo_change_mtu() methods were never updated to use WRITE_ONCE(dev->mtu, new_mtu) as hinted in commit 501a90c94510 ("inet: protect against too small mtu values.") We read dev->mtu without holding RTNL in many places, with READ_ONCE() annotations. It is time to take care of ndo_change_mtu() methods to use corresponding WRITE_ONCE() Signed-off-by: Eric Dumazet Reported-by: Simon Horman Closes: https://lore.kernel.org/netdev/20240505144608.GB67882@kernel.org/ Reviewed-by: Jacob Keller Reviewed-by: Sabrina Dubroca Reviewed-by: Simon Horman Acked-by: Shannon Nelson Link: https://lore.kernel.org/r/20240506102812.3025432-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net: ena: Set tx_info->xdpf value to NULL

2024-04-11T09:21:02+00:00

The patch mentioned in the `Fixes` tag removed the explicit assignment of tx_info->xdpf to NULL with the justification that there's no need to set tx_info->xdpf to NULL and tx_info->num_of_bufs to 0 in case of a mapping error. Both values won't be used once the mapping function returns an error, and their values would be overridden by the next transmitted packet. While both values do indeed get overridden in the next transmission call, the value of tx_info->xdpf is also used to check whether a TX descriptor's transmission has been completed (i.e. a completion for it was polled). An example scenario: 1. Mapping failed, tx_info->xdpf wasn't set to NULL 2. A VF reset occurred leading to IO resource destruction and a call to ena_free_tx_bufs() function 3. Although the descriptor whose mapping failed was freed by the transmission function, it still passes the check if (!tx_info->skb) (skb and xdp_frame are in a union) 4. The xdp_frame associated with the descriptor is freed twice This patch returns the assignment of NULL to tx_info->xdpf to make the cleaning function knows that the descriptor is already freed. Fixes: 504fd6a5390c ("net: ena: fix DMA mapping function issues in XDP") Signed-off-by: Shay Agroskin Signed-off-by: David Arinzon Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni

net: ena: Fix incorrect descriptor free behavior

2024-04-11T09:21:02+00:00

ENA has two types of TX queues: - queues which only process TX packets arriving from the network stack - queues which only process TX packets forwarded to it by XDP_REDIRECT or XDP_TX instructions The ena_free_tx_bufs() cycles through all descriptors in a TX queue and unmaps + frees every descriptor that hasn't been acknowledged yet by the device (uncompleted TX transactions). The function assumes that the processed TX queue is necessarily from the first category listed above and ends up using napi_consume_skb() for descriptors belonging to an XDP specific queue. This patch solves a bug in which, in case of a VF reset, the descriptors aren't freed correctly, leading to crashes. Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action") Signed-off-by: Shay Agroskin Signed-off-by: David Arinzon Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni

net: ena: Wrong missing IO completions check order

2024-04-11T09:21:01+00:00

Missing IO completions check is called every second (HZ jiffies). This commit fixes several issues with this check: 1. Duplicate queues check: Max of 4 queues are scanned on each check due to monitor budget. Once reaching the budget, this check exits under the assumption that the next check will continue to scan the remainder of the queues, but in practice, next check will first scan the last already scanned queue which is not necessary and may cause the full queue scan to last a couple of seconds longer. The fix is to start every check with the next queue to scan. For example, on 8 IO queues: Bug: [0,1,2,3], [3,4,5,6], [6,7] Fix: [0,1,2,3], [4,5,6,7] 2. Unbalanced queues check: In case the number of active IO queues is not a multiple of budget, there will be checks which don't utilize the full budget because the full scan exits when reaching the last queue id. The fix is to run every TX completion check with exact queue budget regardless of the queue id. For example, on 7 IO queues: Bug: [0,1,2,3], [4,5,6], [0,1,2,3] Fix: [0,1,2,3], [4,5,6,0], [1,2,3,4] The budget may be lowered in case the number of IO queues is less than the budget (4) to make sure there are no duplicate queues on the same check. For example, on 3 IO queues: Bug: [0,1,2,0], [1,2,0,1] Fix: [0,1,2], [0,1,2] Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Amit Bernstein Signed-off-by: David Arinzon Reviewed-by: Shannon Nelson Signed-off-by: Paolo Abeni