linux/drivers/net/hyperv/hyperv_net.h

1821 lines
44 KiB

hv_netvsc: untangle the pointer mess We have the following structures keeping netvsc adapter state: - struct net_device - struct net_device_context - struct netvsc_device - struct rndis_device - struct hv_device and there are pointers/dependencies between them: - struct net_device_context is contained in struct net_device - struct hv_device has driver_data pointer which points to 'struct net_device' OR 'struct netvsc_device' depending on driver's state (!). - struct net_device_context has a pointer to 'struct hv_device'. - struct netvsc_device has pointers to 'struct hv_device' and 'struct net_device_context'. - struct rndis_device has a pointer to 'struct netvsc_device'. Different functions get different structures as parameters and use these pointers for traveling. The problem is (in addition to keeping in mind this complex graph) that some of these structures (struct netvsc_device and struct rndis_device) are being removed and re-created on mtu change (as we implement it as re-creation of hyper-v device) so our travel using these pointers is dangerous. Simplify this to a the following: - add struct netvsc_device pointer to struct net_device_context (which is a part of struct net_device and thus never disappears) - remove struct hv_device and struct net_device_context pointers from struct netvsc_device - replace pointer to 'struct netvsc_device' with pointer to 'struct net_device'. - always keep 'struct net_device' in hv_device driver_data. We'll end up with the following 'circular' structure: net_device: [net_device_context] -> netvsc_device -> rndis_device -> net_device -> hv_device -> net_device On MTU change we'll be removing the 'netvsc_device -> rndis_device' branch and re-creating it making the synchronization easier. There is one additional redundant pointer left, it is struct net_device link in struct netvsc_device, it is going to be removed in a separate commit. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-13 13:55:22 +02:00
net: netvsc: Update default VMBus channels 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 <ernis@linux.microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux@outlook.com> Link: https://patch.msgid.link/1724735791-22815-1-git-send-email-ernis@linux.microsoft.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-08-26 22:16:31 -07:00
hv_netvsc: Preserve contiguous PFN grouping in the page buffer array 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: <stable@vger.kernel.org> # 6.1.x Signed-off-by: Michael Kelley <mhklinux@outlook.com> Link: https://patch.msgid.link/20250513000604.1396-4-mhklinux@outlook.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-05-12 17:06:02 -07:00
hv_netvsc: add support for vlans in AF_PACKET mode Vlan tagged packets are getting dropped when used with DPDK that uses the AF_PACKET interface on a hyperV guest. The packet layer uses the tpacket interface to communicate the vlans information to the upper layers. On Rx path, these drivers can read the vlan info from the tpacket header but on the Tx path, this information is still within the packet frame and requires the paravirtual drivers to push this back into the NDIS header which is then used by the host OS to form the packet. This transition from the packet frame to NDIS header is currently missing hence causing the host OS to drop the all vlan tagged packets sent by the drivers that use AF_PACKET (ETH_P_ALL) such as DPDK. Here is an overview of the changes in the vlan header in the packet path: The RX path (userspace handles everything): 1. RX VLAN packet is stripped by HOST OS and placed in NDIS header 2. Guest Kernel RX hv_netvsc packets and moves VLAN info from NDIS header into kernel SKB 3. Kernel shares packets with user space application with PACKET_MMAP. The SKB VLAN info is copied to tpacket layer and indication set TP_STATUS_VLAN_VALID. 4. The user space application will re-insert the VLAN info into the frame The TX path: 1. The user space application has the VLAN info in the frame. 2. Guest kernel gets packets from the application with PACKET_MMAP. 3. The kernel later sends the frame to the hv_netvsc driver. The only way to send VLANs is when the SKB is setup & the VLAN is stripped from the frame. 4. TX VLAN is re-inserted by HOST OS based on the NDIS header. If it sees a VLAN in the frame the packet is dropped. Cc: xe-linux-external@cisco.com Cc: Sriram Krishnan <srirakr2@cisco.com> Signed-off-by: Sriram Krishnan <srirakr2@cisco.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-22 21:08:44 +05:30
hv_netvsc: untangle the pointer mess We have the following structures keeping netvsc adapter state: - struct net_device - struct net_device_context - struct netvsc_device - struct rndis_device - struct hv_device and there are pointers/dependencies between them: - struct net_device_context is contained in struct net_device - struct hv_device has driver_data pointer which points to 'struct net_device' OR 'struct netvsc_device' depending on driver's state (!). - struct net_device_context has a pointer to 'struct hv_device'. - struct netvsc_device has pointers to 'struct hv_device' and 'struct net_device_context'. - struct rndis_device has a pointer to 'struct netvsc_device'. Different functions get different structures as parameters and use these pointers for traveling. The problem is (in addition to keeping in mind this complex graph) that some of these structures (struct netvsc_device and struct rndis_device) are being removed and re-created on mtu change (as we implement it as re-creation of hyper-v device) so our travel using these pointers is dangerous. Simplify this to a the following: - add struct netvsc_device pointer to struct net_device_context (which is a part of struct net_device and thus never disappears) - remove struct hv_device and struct net_device_context pointers from struct netvsc_device - replace pointer to 'struct netvsc_device' with pointer to 'struct net_device'. - always keep 'struct net_device' in hv_device driver_data. We'll end up with the following 'circular' structure: net_device: [net_device_context] -> netvsc_device -> rndis_device -> net_device -> hv_device -> net_device On MTU change we'll be removing the 'netvsc_device -> rndis_device' branch and re-creating it making the synchronization easier. There is one additional redundant pointer left, it is struct net_device link in struct netvsc_device, it is going to be removed in a separate commit. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-13 13:55:22 +02:00
hv_netvsc: Fix panic during namespace deletion with VF 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] <TASK> [ 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 <haiyangz@microsoft.com> Link: https://patch.msgid.link/1754511711-11188-1-git-send-email-haiyangz@linux.microsoft.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-08-06 13:21:51 -07:00
hv_netvsc: Fix panic during namespace deletion with VF 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] <TASK> [ 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 <haiyangz@microsoft.com> Link: https://patch.msgid.link/1754511711-11188-1-git-send-email-haiyangz@linux.microsoft.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2025-08-06 13:21:51 -07:00