Skip to contentSkip to conversation

hv_netvsc: Advertise the SR-IOV capability for CoCo VMs

PATCH Applied Dexuan Cui 4 participants 4 messages Aug 28 – Sep 2

Subsystems (4)
lore
Share & tools
lore

Dexuan Cui

author maintainer
#0 lore raw

PATCH 1/1 hv_netvsc: Advertise the SR-IOV capability for CoCo VMs

This basically reverts the Feb 2021 change:
commit 96854bbda24f ("hv_netvsc: Restrict configurations on isolated guests")

In Feb 2021, PCI device assignment for CoCo VMs on Hyper-V was not
supported: if the host offered a PCI VF NIC device to the VM, the VM couldn't handle it properly, so the 2021 commit was made to tell the host "I'm unable to handle SR-IOV NICs, so please don't offer a VF to me". If the host offers a VF NIC to the VM anyway, the change to netvsc_receive_inband() ignores the VF NIC.

Since Mar 2023, the VM is able to support PCI device assignment due to commit 2c6ba4216844 ("PCI: hv: Enable PCI pass-thru devices in Confidential VMs") and related commits, so hv_netvsc can functionally work with a VF NIC, but we haven't advertised the SR-IOV capability because the MANA NIC driver (drivers/net/ethernet/microsoft/mana/) hadn't been hardened, so a malicious MANA NIC might be able to attack the VM.

Recently, we have finished hardening the MANA driver, so we can safely use the MANA NIC in a CoCo VM now. Note: currently the MANA driver in a CoCo VM still uses bounce buffering (i.e. shared decrypted memory) for DMA. In the future, it will be able to use private encrypted memory for DMA with the help of TDISP.

Now, advertises the SR-IOV capability for CoCo VMs.

Note: for MANA to work properly for CoCo VMs, the following earlier commits are also required:
commit 2e2a83b4998a ("net: mana: Validate the packet length reported by the NIC") commit c72a0f09c57f ("net: mana: Sync page pool RX frags for CPU")

Note: the host might offer a VF NIC device that's not MANA -- in that case, if the corresponding VF NIC driver isn't hardened for CoCo VMs, the driver should be blacklisted in CoCo VMs.

---
 drivers/net/hyperv/netvsc.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)
drivers/net/hyperv/netvsc.c +2 -8
index 5cd084e5696c..fc6548b16c91 100644
@@ -625,10 +625,7 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;
 
 	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) {
-		if (hv_is_isolation_supported())
-			netdev_info(ndev, "SR-IOV not advertised by guests on the host supporting isolation\n");
-		else
-			init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
+		init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
 
 		/* Teaming bit is needed to receive link speed updates */
 		init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1;
@@ -1665,10 +1662,7 @@ static void netvsc_receive_inband(struct net_device *ndev,
 		break;
 
 	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
-		if (hv_is_isolation_supported())
-			netdev_err(ndev, "Ignore VF_ASSOCIATION msg from the host supporting isolation\n");
-		else
-			netvsc_send_vf(ndev, nvmsg, msglen);
+		netvsc_send_vf(ndev, nvmsg, msglen);
 		break;
 	}
 }
Signature · 1 line
2.34.1
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 48 lines

-----Original Message-----
From: Dexuan Cui <[email protected]>
Sent: Friday, August 28, 2026 5:23 PM
To: KY Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; [email protected]; Dexuan Cui <[email protected]>; Long Li <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]
Cc: [email protected]
Subject: [PATCH net-next] hv_netvsc: Advertise the SR-IOV capability for CoCo VMs

This basically reverts the Feb 2021 change:
commit 96854bbda24f ("hv_netvsc: Restrict configurations on isolated guests")

In Feb 2021, PCI device assignment for CoCo VMs on Hyper-V was not
supported: if the host offered a PCI VF NIC device to the VM, the VM couldn't handle it properly, so the 2021 commit was made to tell the host "I'm unable to handle SR-IOV NICs, so please don't offer a VF to me". If the host offers a VF NIC to the VM anyway, the change to netvsc_receive_inband() ignores the VF NIC.

Since Mar 2023, the VM is able to support PCI device assignment due to commit 2c6ba4216844 ("PCI: hv: Enable PCI pass-thru devices in Confidential VMs")
and related commits, so hv_netvsc can functionally work with a VF NIC, but we haven't advertised the SR-IOV capability because the MANA NIC driver (drivers/net/ethernet/microsoft/mana/) hadn't been hardened, so a malicious MANA NIC might be able to attack the VM.

Recently, we have finished hardening the MANA driver, so we can safely use the MANA NIC in a CoCo VM now. Note: currently the MANA driver in a CoCo VM still uses bounce buffering (i.e. shared decrypted memory) for DMA. In the future, it will be able to use private encrypted memory for DMA with the help of TDISP.

Now, advertises the SR-IOV capability for CoCo VMs.

Note: for MANA to work properly for CoCo VMs, the following earlier commits are also required:
commit 2e2a83b4998a ("net: mana: Validate the packet length reported by the NIC")
commit c72a0f09c57f ("net: mana: Sync page pool RX frags for CPU")

Quoted 5 lines

Note: the host might offer a VF NIC device that's not MANA -- in that case, if the corresponding VF NIC driver isn't hardened for CoCo VMs, the driver should be blacklisted in CoCo VMs.

Reviewed-by on v1 1/1
#2 lore raw
In reply to Dexuan Cui

From: Dexuan Cui <[email protected]> Sent: Friday, August 28, 2026 2:23 PM

Quoted 58 lines

This basically reverts the Feb 2021 change:
commit 96854bbda24f ("hv_netvsc: Restrict configurations on isolated guests")

In Feb 2021, PCI device assignment for CoCo VMs on Hyper-V was not
supported: if the host offered a PCI VF NIC device to the VM, the VM couldn't handle it properly, so the 2021 commit was made to tell the host "I'm unable to handle SR-IOV NICs, so please don't offer a VF to me". If the host offers a VF NIC to the VM anyway, the change to netvsc_receive_inband() ignores the VF NIC.

Since Mar 2023, the VM is able to support PCI device assignment due to commit 2c6ba4216844 ("PCI: hv: Enable PCI pass-thru devices in Confidential VMs") and related commits, so hv_netvsc can functionally work with a VF NIC, but we haven't advertised the SR-IOV capability because the MANA NIC driver (drivers/net/ethernet/microsoft/mana/) hadn't been hardened, so a malicious MANA NIC might be able to attack the VM.

Recently, we have finished hardening the MANA driver, so we can safely use the MANA NIC in a CoCo VM now. Note: currently the MANA driver in a CoCo VM still uses bounce buffering (i.e. shared decrypted memory) for DMA. In the future, it will be able to use private encrypted memory for DMA with the help of TDISP.

Now, advertises the SR-IOV capability for CoCo VMs.

Note: for MANA to work properly for CoCo VMs, the following earlier commits are also required:
commit 2e2a83b4998a ("net: mana: Validate the packet length reported by the NIC") commit c72a0f09c57f ("net: mana: Sync page pool RX frags for CPU")

Note: the host might offer a VF NIC device that's not MANA -- in that case, if the corresponding VF NIC driver isn't hardened for CoCo VMs, the driver should be blacklisted in CoCo VMs.

---
 drivers/net/hyperv/netvsc.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)
drivers/net/hyperv/netvsc.c +1 -4
index 5cd084e5696c..fc6548b16c91 100644
@@ -625,10 +625,7 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;
 
 	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) {
-		if (hv_is_isolation_supported())
-			netdev_info(ndev, "SR-IOV not advertised by guests on the host supporting isolation\n");
-		else
-			init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
+		init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
 
 		/* Teaming bit is needed to receive link speed updates */
 		init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1;
@@ -1665,10 +1662,7 @@ static void netvsc_receive_inband(struct net_device *ndev,
 		break;

drivers/net/hyperv/netvsc.c static void netvsc_receive_inband(struct net_device *ndev, · line 1668

Quoted 10 lines
drivers/net/hyperv/netvsc.c +1 -4
 
 	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
-		if (hv_is_isolation_supported())
-			netdev_err(ndev, "Ignore VF_ASSOCIATION msg from the host supporting isolation\n");
-		else
-			netvsc_send_vf(ndev, nvmsg, msglen);
+		netvsc_send_vf(ndev, nvmsg, msglen);
 		break;
 	}
 }

Nice to see this getting enabled!

#3 lore raw
In reply to Dexuan Cui
This patch was applied to netdev/net-next.git (main) by David S. Miller <[email protected]>:

Hello:

This patch was applied to netdev/net-next.git (main) by David S. Miller <[email protected]>:

Quoted 11 lines · On Fri, 28 Aug 2026 14:23:25 -0700 you wrote:

This basically reverts the Feb 2021 change:
commit 96854bbda24f ("hv_netvsc: Restrict configurations on isolated guests")

In Feb 2021, PCI device assignment for CoCo VMs on Hyper-V was not
supported: if the host offered a PCI VF NIC device to the VM, the VM couldn't handle it properly, so the 2021 commit was made to tell the host "I'm unable to handle SR-IOV NICs, so please don't offer a VF to me". If the host offers a VF NIC to the VM anyway, the change to netvsc_receive_inband() ignores the VF NIC.

[...]

Here is the summary with links:
- [net-next] hv_netvsc: Advertise the SR-IOV capability for CoCo VMs

    https://git.kernel.org/netdev/net-next/c/d0ec95a8a4e7

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html