Hyper-V VMs can be replicated to another hosts and there is a feature to set different IP for replicas, it is called 'Failover TCP/IP'. When such guest starts Hyper-V host sends it KVP_OP_SET_IP_INFO message as soon as we finish negotiation procedure. The problem is that it can happen (and it actually happens) before userspace daemon connects and we reply with HV_E_FAIL to the message. As there are no repetitions we fail to set the requested IP.
Solve the issue by postponing our reply to the negotiation message till userspace daemon is connected. We can't wait too long as there is a host-side timeout (cca. 75 seconds) and if we fail to reply in this time frame the whole KVP service will become inactive. The solution is not ideal - if it takes userspace daemon more than 60 seconds to connect IP Failover will still fail but I don't see a solution with our current separation between kernel and userspace parts.
Other two modules (VSS and FCOPY) don't require such delay, leave them untouched.
Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: K. Y. Srinivasan kys@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Dexuan Cui decui@microsoft.com ---
This is cherry-picked from the mainline: 4dbfc2e ("Drivers: hv: kvp: fix IP Failover")
I added my Signed-off-by as I identified and tested the patches. If this is unnecessary, please feel free to remove it.
drivers/hv/hv_kvp.c | 31 +++++++++++++++++++++++++++++++ drivers/hv/hyperv_vmbus.h | 5 +++++ 2 files changed, 36 insertions(+)
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index cd3fb01..ff0a426 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -78,9 +78,11 @@ static void kvp_send_key(struct work_struct *dummy);
static void kvp_respond_to_host(struct hv_kvp_msg *msg, int error); static void kvp_timeout_func(struct work_struct *dummy); +static void kvp_host_handshake_func(struct work_struct *dummy); static void kvp_register(int);
static DECLARE_DELAYED_WORK(kvp_timeout_work, kvp_timeout_func); +static DECLARE_DELAYED_WORK(kvp_host_handshake_work, kvp_host_handshake_func); static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
static const char kvp_devname[] = "vmbus/hv_kvp"; @@ -131,6 +133,11 @@ static void kvp_timeout_func(struct work_struct *dummy) hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper); }
+static void kvp_host_handshake_func(struct work_struct *dummy) +{ + hv_poll_channel(kvp_transaction.recv_channel, hv_kvp_onchannelcallback); +} + static int kvp_handle_handshake(struct hv_kvp_msg *msg) { switch (msg->kvp_hdr.operation) { @@ -155,6 +162,12 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg) pr_debug("KVP: userspace daemon ver. %d registered\n", KVP_OP_REGISTER); kvp_register(dm_reg_value); + + /* + * If we're still negotiating with the host cancel the timeout + * work to not poll the channel twice. + */ + cancel_delayed_work_sync(&kvp_host_handshake_work); hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
return 0; @@ -595,7 +608,22 @@ void hv_kvp_onchannelcallback(void *context) struct icmsg_negotiate *negop = NULL; int util_fw_version; int kvp_srv_version; + static enum {NEGO_NOT_STARTED, + NEGO_IN_PROGRESS, + NEGO_FINISHED} host_negotiatied = NEGO_NOT_STARTED;
+ if (host_negotiatied == NEGO_NOT_STARTED && + kvp_transaction.state < HVUTIL_READY) { + /* + * If userspace daemon is not connected and host is asking + * us to negotiate we need to delay to not lose messages. + * This is important for Failover IP setting. + */ + host_negotiatied = NEGO_IN_PROGRESS; + schedule_delayed_work(&kvp_host_handshake_work, + HV_UTIL_NEGO_TIMEOUT * HZ); + return; + } if (kvp_transaction.state > HVUTIL_READY) return;
@@ -673,6 +701,8 @@ void hv_kvp_onchannelcallback(void *context) vmbus_sendpacket(channel, recv_buffer, recvlen, requestid, VM_PKT_DATA_INBAND, 0); + + host_negotiatied = NEGO_FINISHED; }
} @@ -711,6 +741,7 @@ hv_kvp_init(struct hv_util_service *srv) void hv_kvp_deinit(void) { kvp_transaction.state = HVUTIL_DEVICE_DYING; + cancel_delayed_work_sync(&kvp_host_handshake_work); cancel_delayed_work_sync(&kvp_timeout_work); cancel_work_sync(&kvp_sendkey_work); hvutil_transport_destroy(hvt); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 75e383e..15e0649 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -36,6 +36,11 @@ #define HV_UTIL_TIMEOUT 30
/* + * Timeout for guest-host handshake for services. + */ +#define HV_UTIL_NEGO_TIMEOUT 60 + +/* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent * is set by CPUID(HVCPUID_VERSION_FEATURES). */