kernel.git/drivers/net/ethernet/google, branch linux-5.12.y

gve: Fix swapped vars when fetching max queues

2021-07-14T15:00:04Z

[ Upstream commit 1db1a862a08f85edc36aad091236ac9b818e949e ] Fixes: 893ce44df565 ("gve: Add basic driver framework for Compute Engine Virtual NIC") Signed-off-by: Bailey Forrest Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Correct SKB queue index validation.

2021-06-03T07:09:48Z

[ Upstream commit fbd4a28b4fa66faaa7f510c0adc531d37e0a7848 ] SKBs with skb_get_queue_mapping(skb) == tx_cfg.num_queues should also be considered invalid. Fixes: f5cedc84a30d ("gve: Add transmit and receive support") Signed-off-by: David Awogbemila Acked-by: Willem de Brujin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Upgrade memory barrier in poll routine

2021-06-03T07:09:48Z

[ Upstream commit f81781835f0adfae8d701545386030d223efcd6f ] As currently written, if the driver checks for more work (via gve_tx_poll or gve_rx_poll) before the device posts work and the irq doorbell is not unmasked (via iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, ...)) before the device attempts to raise an interrupt, an interrupt is lost and this could potentially lead to the traffic being completely halted. For example, if a tx queue has already been stopped, the driver won't get the chance to complete work and egress will be halted. We need a full memory barrier in the poll routine to ensure that the irq doorbell is unmasked before the driver checks for more work. Fixes: f5cedc84a30d ("gve: Add transmit and receive support") Signed-off-by: Catherine Sullivan Signed-off-by: David Awogbemila Acked-by: Willem de Brujin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Add NULL pointer checks when freeing irqs.

2021-06-03T07:09:48Z

[ Upstream commit 5218e919c8d06279884aa0baf76778a6817d5b93 ] When freeing notification blocks, we index priv->msix_vectors. If we failed to allocate priv->msix_vectors (see abort_with_msix_vectors) this could lead to a NULL pointer dereference if the driver is unloaded. Fixes: 893ce44df565 ("gve: Add basic driver framework for Compute Engine Virtual NIC") Signed-off-by: David Awogbemila Acked-by: Willem de Brujin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Update mgmt_msix_idx if num_ntfy changes

2021-06-03T07:09:47Z

[ Upstream commit e96b491a0ffa35a8a9607c193fa4d894ca9fb32f ] If we do not get the expected number of vectors from pci_enable_msix_range, we update priv->num_ntfy_blks but not priv->mgmt_msix_idx. This patch fixes this so that priv->mgmt_msix_idx is updated accordingly. Fixes: f5cedc84a30d ("gve: Add transmit and receive support") Signed-off-by: David Awogbemila Acked-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Check TX QPL was actually assigned

2021-06-03T07:09:47Z

[ Upstream commit 5aec55b46c6238506cdf0c60cd0e42ab77a1e5e0 ] Correctly check the TX QPL was assigned and unassigned if other steps in the allocation fail. Fixes: f5cedc84a30d (gve: Add transmit and receive support) Signed-off-by: Catherine Sullivan Signed-off-by: David Awogbemila Acked-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin

gve: Add support for raw addressing in the tx path

2020-12-09T00:06:28Z

During TX, skbs' data addresses are dma_map'ed and passed to the NIC. This means that the device can perform DMA directly from these addresses and the driver does not have to copy the buffer content into pre-allocated buffers/qpls (as in qpl mode). Reviewed-by: Yangchun Fu Signed-off-by: Catherine Sullivan Signed-off-by: David Awogbemila Signed-off-by: David S. Miller

gve: Rx Buffer Recycling

2020-12-09T00:06:28Z

This patch lets the driver reuse buffers that have been freed by the networking stack. In the raw addressing case, this allows the driver avoid allocating new buffers. In the qpl case, the driver can avoid copies. This patch separates the page refcount tracking mechanism into a function gve_rx_can_recycle_buffer which uses get_page - this will be changed in a future patch to entirely eliminate the use of get_page in tracking page refcounts. Signed-off-by: David Awogbemila Signed-off-by: David S. Miller

gve: Add support for raw addressing to the rx path

2020-12-09T00:06:28Z

Add support to use raw dma addresses in the rx path. Due to this new support we can alloc a new buffer instead of making a copy. RX buffers are handed to the networking stack and are re-allocated as needed, avoiding the need to use skb_copy_to_linear_data() as in "qpl" mode. Reviewed-by: Yangchun Fu Signed-off-by: Catherine Sullivan Signed-off-by: David Awogbemila Signed-off-by: David S. Miller

gve: Add support for raw addressing device option

2020-12-09T00:06:28Z

Add support to describe device for parsing device options. As the first device option, add raw addressing. "Raw Addressing" mode (as opposed to the current "qpl" mode) is an operational mode which allows the driver avoid bounce buffer copies which it currently performs using pre-allocated qpls (queue_page_lists) when sending and receiving packets. For egress packets, the provided skb data addresses will be dma_map'ed and passed to the device, allowing the NIC can perform DMA directly - the driver will not have to copy the buffer content into pre-allocated buffers/qpls (as in qpl mode). For ingress packets, copies are also eliminated as buffers are handed to the networking stack and then recycled or re-allocated as necessary, avoiding the use of skb_copy_to_linear_data(). This patch only introduces the option to the driver. Subsequent patches will add the ingress and egress functionality. Reviewed-by: Yangchun Fu Signed-off-by: Catherine Sullivan Signed-off-by: David Awogbemila Signed-off-by: David S. Miller