kernel/linux.git/drivers/net/hyperv/hyperv_net.h, branch v6.12.80

hv_netvsc: Fix panic during namespace deletion with VF

2025-08-20T16:30:55+00:00

commit 33caa208dba6fa639e8a92fd0c8320b652e5550c upstream. The existing code move the VF NIC to new namespace when NETDEV_REGISTER is received on netvsc NIC. During deletion of the namespace, default_device_exit_batch() >> default_device_exit_net() is called. When netvsc NIC is moved back and registered to the default namespace, it automatically brings VF NIC back to the default namespace. This will cause the default_device_exit_net() >> for_each_netdev_safe loop unable to detect the list end, and hit NULL ptr: [ 231.449420] mana 7870:00:00.0 enP30832s1: Moved VF to namespace with: eth0 [ 231.449656] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 231.450246] #PF: supervisor read access in kernel mode [ 231.450579] #PF: error_code(0x0000) - not-present page [ 231.450916] PGD 17b8a8067 P4D 0 [ 231.451163] Oops: Oops: 0000 [#1] SMP NOPTI [ 231.451450] CPU: 82 UID: 0 PID: 1394 Comm: kworker/u768:1 Not tainted 6.16.0-rc4+ #3 VOLUNTARY [ 231.452042] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 11/21/2024 [ 231.452692] Workqueue: netns cleanup_net [ 231.452947] RIP: 0010:default_device_exit_batch+0x16c/0x3f0 [ 231.453326] Code: c0 0c f5 b3 e8 d5 db fe ff 48 85 c0 74 15 48 c7 c2 f8 fd ca b2 be 10 00 00 00 48 8d 7d c0 e8 7b 77 25 00 49 8b 86 28 01 00 00 <48> 8b 50 10 4c 8b 2a 4c 8d 62 f0 49 83 ed 10 4c 39 e0 0f 84 d6 00 [ 231.454294] RSP: 0018:ff75fc7c9bf9fd00 EFLAGS: 00010246 [ 231.454610] RAX: 0000000000000000 RBX: 0000000000000002 RCX: 61c8864680b583eb [ 231.455094] RDX: ff1fa9f71462d800 RSI: ff75fc7c9bf9fd38 RDI: 0000000030766564 [ 231.455686] RBP: ff75fc7c9bf9fd78 R08: 0000000000000000 R09: 0000000000000000 [ 231.456126] R10: 0000000000000001 R11: 0000000000000004 R12: ff1fa9f70088e340 [ 231.456621] R13: ff1fa9f70088e340 R14: ffffffffb3f50c20 R15: ff1fa9f7103e6340 [ 231.457161] FS: 0000000000000000(0000) GS:ff1faa6783a08000(0000) knlGS:0000000000000000 [ 231.457707] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 231.458031] CR2: 0000000000000010 CR3: 0000000179ab2006 CR4: 0000000000b73ef0 [ 231.458434] Call Trace: [ 231.458600] [ 231.458777] ops_undo_list+0x100/0x220 [ 231.459015] cleanup_net+0x1b8/0x300 [ 231.459285] process_one_work+0x184/0x340 To fix it, move the ns change to a workqueue, and take rtnl_lock to avoid changing the netdev list when default_device_exit_net() is using it. Cc: stable@vger.kernel.org Fixes: 4c262801ea60 ("hv_netvsc: Fix VF namespace also in synthetic NIC NETDEV_REGISTER event") Signed-off-by: Haiyang Zhang Link: https://patch.msgid.link/1754511711-11188-1-git-send-email-haiyangz@linux.microsoft.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman

hv_netvsc: Remove rmsg_pgcnt

2025-05-22T12:29:47+00:00

commit 5bbc644bbf4e97a05bc0cb052189004588ff8a09 upstream. init_page_array() now always creates a single page buffer array entry for the rndis message, even if the rndis message crosses a page boundary. As such, the number of page buffer array entries used for the rndis message must no longer be tracked -- it is always just 1. Remove the rmsg_pgcnt field and use "1" where the value is needed. Cc: # 6.1.x Signed-off-by: Michael Kelley Link: https://patch.msgid.link/20250513000604.1396-5-mhklinux@outlook.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman

hv_netvsc: Preserve contiguous PFN grouping in the page buffer array

2025-05-22T12:29:47+00:00

commit 41a6328b2c55276f89ea3812069fd7521e348bbf upstream. Starting with commit dca5161f9bd0 ("hv_netvsc: Check status in SEND_RNDIS_PKT completion message") in the 6.3 kernel, the Linux driver for Hyper-V synthetic networking (netvsc) occasionally reports "nvsp_rndis_pkt_complete error status: 2".[1] This error indicates that Hyper-V has rejected a network packet transmit request from the guest, and the outgoing network packet is dropped. Higher level network protocols presumably recover and resend the packet so there is no functional error, but performance is slightly impacted. Commit dca5161f9bd0 is not the cause of the error -- it only added reporting of an error that was already happening without any notice. The error has presumably been present since the netvsc driver was originally introduced into Linux. The root cause of the problem is that the netvsc driver in Linux may send an incorrectly formatted VMBus message to Hyper-V when transmitting the network packet. The incorrect formatting occurs when the rndis header of the VMBus message crosses a page boundary due to how the Linux skb head memory is aligned. In such a case, two PFNs are required to describe the location of the rndis header, even though they are contiguous in guest physical address (GPA) space. Hyper-V requires that two rndis header PFNs be in a single "GPA range" data struture, but current netvsc code puts each PFN in its own GPA range, which Hyper-V rejects as an error. The incorrect formatting occurs only for larger packets that netvsc must transmit via a VMBus "GPA Direct" message. There's no problem when netvsc transmits a smaller packet by copying it into a pre- allocated send buffer slot because the pre-allocated slots don't have page crossing issues. After commit 14ad6ed30a10 ("net: allow small head cache usage with large MAX_SKB_FRAGS values") in the 6.14-rc4 kernel, the error occurs much more frequently in VMs with 16 or more vCPUs. It may occur every few seconds, or even more frequently, in an ssh session that outputs a lot of text. Commit 14ad6ed30a10 subtly changes how skb head memory is allocated, making it much more likely that the rndis header will cross a page boundary when the vCPU count is 16 or more. The changes in commit 14ad6ed30a10 are perfectly valid -- they just had the side effect of making the netvsc bug more prominent. Current code in init_page_array() creates a separate page buffer array entry for each PFN required to identify the data to be transmitted. Contiguous PFNs get separate entries in the page buffer array, and any information about contiguity is lost. Fix the core issue by having init_page_array() construct the page buffer array to represent contiguous ranges rather than individual pages. When these ranges are subsequently passed to netvsc_build_mpb_array(), it can build GPA ranges that contain multiple PFNs, as required to avoid the error "nvsp_rndis_pkt_complete error status: 2". If instead the network packet is sent by copying into a pre-allocated send buffer slot, the copy proceeds using the contiguous ranges rather than individual pages, but the result of the copying is the same. Also fix rndis_filter_send_request() to construct a contiguous range, since it has its own page buffer array. This change has a side benefit in CoCo VMs in that netvsc_dma_map() calls dma_map_single() on each contiguous range instead of on each page. This results in fewer calls to dma_map_single() but on larger chunks of memory, which should reduce contention on the swiotlb. Since the page buffer array now contains one entry for each contiguous range instead of for each individual page, the number of entries in the array can be reduced, saving 208 bytes of stack space in netvsc_xmit() when MAX_SKG_FRAGS has the default value of 17. [1] https://bugzilla.kernel.org/show_bug.cgi?id=217503 Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217503 Cc: # 6.1.x Signed-off-by: Michael Kelley Link: https://patch.msgid.link/20250513000604.1396-4-mhklinux@outlook.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman

net: netvsc: Update default VMBus channels

2024-08-29T00:18:32+00:00

Change VMBus channels macro (VRSS_CHANNEL_DEFAULT) in Linux netvsc from 8 to 16 to align with Azure Windows VM and improve networking throughput. For VMs having less than 16 vCPUS, the channels depend on number of vCPUs. For greater than 16 vCPUs, set the channels to maximum of VRSS_CHANNEL_DEFAULT and number of physical cores / 2 which is returned by netif_get_num_default_rss_queues() as a way to optimize CPU resource utilization and scale for high-end processors with many cores. Maximum number of channels are by default set to 64. Based on this change the channel creation would change as follows: ----------------------------------------------------------------- | No. of vCPU | dev_info->num_chn | channels created | ----------------------------------------------------------------- | 1-16 | 16 | vCPU | | >16 | max(16,#cores/2) | min(64 , max(16,#cores/2)) | ----------------------------------------------------------------- Performance tests showed significant improvement in throughput: - 0.54% for 16 vCPUs - 0.83% for 32 vCPUs - 0.86% for 48 vCPUs - 9.72% for 64 vCPUs - 13.57% for 96 vCPUs Signed-off-by: Erni Sri Satya Vennela Reviewed-by: Haiyang Zhang Reviewed-by: Shradha Gupta Reviewed-by: Michael Kelley Link: https://patch.msgid.link/1724735791-22815-1-git-send-email-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski

eth: add missing xdp.h includes in drivers

2023-08-03T15:38:07+00:00

Handful of drivers currently expect to get xdp.h by virtue of including netdevice.h. This will soon no longer be the case so add explicit includes. Reviewed-by: Wei Fang Reviewed-by: Gerhard Engleder Signed-off-by: Jakub Kicinski Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230803010230.1755386-2-kuba@kernel.org Signed-off-by: Martin KaFai Lau

hv_netvsc: Allocate rx indirection table size dynamically

2023-06-07T08:46:49+00:00

Allocate the size of rx indirection table dynamically in netvsc from the value of size provided by OID_GEN_RECEIVE_SCALE_CAPABILITIES query instead of using a constant value of ITAB_NUM. Signed-off-by: Shradha Gupta Reviewed-by: Haiyang Zhang Tested-on: Ubuntu22 (azure VM, SKU size: Standard_F72s_v2) Testcases: 1. ethtool -x eth0 output 2. LISA testcase:PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-Synthetic 3. LISA testcase:PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-SRIOV Reviewed-by: Simon Horman Signed-off-by: David S. Miller

hv_netvsc: Remove second mapping of send and recv buffers

2023-04-17T19:19:04+00:00

With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), creating a second kernel virtual mapping for shared memory is no longer necessary. Everything needed for the transition to shared is handled by set_memory_decrypted(). As such, remove the code to create and manage the second mapping for the pre-allocated send and recv buffers. This mapping is the last user of hv_map_memory()/hv_unmap_memory(), so delete these functions as well. Finally, hv_map_memory() is the last user of vmap_pfn() in Hyper-V guest code, so remove the Kconfig selection of VMAP_PFN. Signed-off-by: Michael Kelley Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1679838727-87310-11-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu

hv_netvsc: Fix race between VF offering and VF association message from host

2022-10-07T07:43:58+00:00

During vm boot, there might be possibility that vf registration call comes before the vf association from host to vm. And this might break netvsc vf path, To prevent the same block vf registration until vf bind message comes from host. Cc: stable@vger.kernel.org Fixes: 00d7ddba11436 ("hv_netvsc: pair VF based on serial number") Reviewed-by: Haiyang Zhang Signed-off-by: Gaurav Kohli Signed-off-by: David S. Miller

hv_netvsc: Add support for XDP_REDIRECT

2022-04-12T01:25:47+00:00

Handle XDP_REDIRECT action in netvsc driver. Also, transparently pass ndo_xdp_xmit to VF when available. Signed-off-by: Haiyang Zhang Link: https://lore.kernel.org/r/1649362894-20077-1-git-send-email-haiyangz@microsoft.com Signed-off-by: Jakub Kicinski

net: netvsc: Add Isolation VM support for netvsc driver

2021-12-20T18:01:09+00:00

In Isolation VM, all shared memory with host needs to mark visible to host via hvcall. vmbus_establish_gpadl() has already done it for netvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_ pagebuffer() stills need to be handled. Use DMA API to map/umap these memory during sending/receiving packet and Hyper-V swiotlb bounce buffer dma address will be returned. The swiotlb bounce buffer has been masked to be visible to host during boot up. rx/tx ring buffer is allocated via vzalloc() and they need to be mapped into unencrypted address space(above vTOM) before sharing with host and accessing. Add hv_map/unmap_memory() to map/umap rx /tx ring buffer. Signed-off-by: Tianyu Lan Reviewed-by: Haiyang Zhang Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20211213071407.314309-6-ltykernel@gmail.com Signed-off-by: Wei Liu