Merge pull request #1 from LIS/master

make repo current

hv-rhel5.x/hv/hyperv_vmbus.h

@@ -44,12 +44,31 @@ enum hv_cpuid_function {
 	 * HVCPUID_INTERFACE
 	 */
 	HVCPUID_VERSION			= 0x40000002,
-	HVCPUID_FEATURES			= 0x40000003,
+	HVCPUID_FEATURES		= 0x40000003,
 	HVCPUID_ENLIGHTENMENT_INFO	= 0x40000004,
-	HVCPUID_IMPLEMENTATION_LIMITS		= 0x40000005,
+	HVCPUID_IMPLEMENTATION_LIMITS	= 0x40000005,
 };
 
-#define  HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE   0x400
+/*
+ * Feature identification. EDX bits which identify miscellaneous
+ * features that are available to the partition. Defined in
+ * section 3.4 of the HV Top Level Functional spec.
+ */
+#define HV_FEATURE_MWAIT_INSTRUCTION_AVAILABLE            0x1
+#define HV_FEATURE_GUEST_DEBUGGING_SUPPORT                0x2
+#define HV_FEATURE_PERFORMANCE_MONITOR_SUPPORT            0x4
+#define HV_FEATURE_PHYSICAL_CPU_DYNAMIC_PARTITIONING      0x8
+#define HV_FEATURE_HYPERCALL_PARAMETER_BLOCK_XMM_REGISTER 0x10
+#define HV_FEATURE_VIRTUAL_GUEST_IDLE_STATE               0x20
+#define HV_FEATURE_HYPERVISOR_SLEEP_STATE                 0x40
+#define HV_FEATURE_QUERY_NUMA_DISTANCE                    0x80
+#define HV_FEATURE_DETERMINE_TIMER_FREQUENCIES            0x100
+#define HV_FEATURE_SYNTHETIC_MACHINE_CHECK                0x200
+#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE              0x400
+#define HV_FEATURE_DEBUG_MSG_AVAILABLE                    0x800
+#define HV_FEATURE_NPIPE_1_AVAILABLE                      0x1000
+#define HV_FEATURE_DISABLE_HYPERVISOR_AVAILABLE           0x200
+/* Bits 14 - 31 reserved */
 
 #define HV_X64_MSR_CRASH_P0   0x40000100
 #define HV_X64_MSR_CRASH_P1   0x40000101

hv-rhel5.x/hv/include/asm/mshyperv.h

@@ -7,6 +7,7 @@
 
 struct ms_hyperv_info {
 	u32 features;
+	u32 misc_features;
 	u32 hints;
 };
 

hv-rhel5.x/hv/vmbus_drv.c

@@ -55,10 +55,7 @@ bool using_null_legacy_pic = false;
 EXPORT_SYMBOL(using_null_legacy_pic);
 
 
-struct ms_hyperv_info ms_hyperv = {
-	.features = HV_X64_MSR_TIME_REF_COUNT_AVAILABLE |
-		    HV_X64_MSR_SYNTIMER_AVAILABLE,
-};
+struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL(ms_hyperv);
 
 #endif
@@ -819,7 +816,9 @@ static int vmbus_bus_init(int irq)
 
 
 #if defined(RHEL_RELEASE_VERSION) && (RHEL_RELEASE_CODE < 1540)
-	ms_hyperv.features |= HV_X64_MSR_TIME_REF_COUNT_AVAILABLE;
+	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
+	ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 #endif
 
 	/*

hv-rhel6.x/hv/channel_mgmt.c

@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include "include/linux/hyperv.h"
 
 #include "hyperv_vmbus.h"
@@ -477,6 +478,17 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
                    cpumask_of_node(primary->numa_node));
 
 	cur_cpu = -1;
+
+	/*
+	 * Normally Hyper-V host doesn't create more subchannels than there
+	 * are VCPUs on the node but it is possible when not all present VCPUs
+	 * on the node are initialized by guest. Clear the alloced_cpus_in_node
+	 * to start over.
+	 */
+	if (cpumask_equal(&primary->alloced_cpus_in_node,
+			  cpumask_of_node(primary->numa_node)))
+		cpumask_clear(&primary->alloced_cpus_in_node);
+
 	while (true) {
 		cur_cpu = cpumask_next(cur_cpu, &available_mask);
 		if (cur_cpu >= nr_cpu_ids) {
@@ -506,6 +518,40 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 	channel->target_vp = hv_context.vp_index[cur_cpu];
 }
 
+static void vmbus_wait_for_unload(void)
+{
+	int cpu = smp_processor_id();
+	void *page_addr = hv_context.synic_message_page[cpu];
+	struct hv_message *msg = (struct hv_message *)page_addr +
+				  VMBUS_MESSAGE_SINT;
+	struct vmbus_channel_message_header *hdr;
+	bool unloaded = false;
+
+	while (1) {
+		if (msg->header.message_type == HVMSG_NONE) {
+			mdelay(10);
+			continue;
+		}
+
+		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+			unloaded = true;
+
+		msg->header.message_type = HVMSG_NONE;
+		/*
+		 * header.message_type needs to be written before we do
+		 * wrmsrl() below.
+		 */
+		mb();
+
+		if (msg->header.message_flags.msg_pending)
+			wrmsrl(HV_X64_MSR_EOM, 0);
+
+		if (unloaded)
+			break;
+	}
+}
+
 /*
  * vmbus_unload_response - Handler for the unload response.
  */
@@ -531,7 +577,14 @@ void vmbus_initiate_unload(void)
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
 
-	wait_for_completion(&vmbus_connection.unload_event);
+	/*
+	 * vmbus_initiate_unload() is also called on crash and the crash can be
+	 * happening in an interrupt context, where scheduling is impossible.
+	 */
+	if (!in_interrupt())
+		wait_for_completion(&vmbus_connection.unload_event);
+	else
+		vmbus_wait_for_unload();
 }
 
 /*

hv-rhel6.x/hv/connection.c

@@ -82,13 +82,23 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+
 	/*
-	 * We want all channel messages to be delivered on CPU 0.
-	 * This has been the behavior pre-win8. This is not a
-	 * perf issue and having all channel messages delivered on
-	 * CPU 0 would be OK.
+	 * For Win8 and below, we want all channel messages to be delivered 
+	 * on CPU 0. This is not a perf issue and having all channel messages
+	 * delivered on CPU 0 would be OK.
+	 *
+	 * For Win 8.1 and above, we want messages delivered on current 
+	 * CPU, as this is necessary when a connection already exists.
+	 * For example, in the case of a crash kernel coming up.
 	 */
-	msg->target_vcpu = 0;
+	if (version >= VERSION_WIN8_1) {
+		msg->target_vcpu = hv_context.vp_index[get_cpu()];
+		put_cpu();
+	}
+	else {
+		msg->target_vcpu = 0;
+	}
 
 	/*
 	 * Add to list before we send the request since we may

hv-rhel6.x/hv/hv.c

@@ -342,18 +342,24 @@ void hv_cleanup(void)
 		hv_context.hypercall_page = NULL;
 	}
 #ifdef CONFIG_X86_64
-       /*
-        * Cleanup the TSC page based CS.
-        */
-       if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-               clocksource_change_rating(&hyperv_cs_tsc, 10);
-               clocksource_unregister(&hyperv_cs_tsc);
+	/*
+	 * Cleanup the TSC page based CS.
+	 */
+	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
+		/*
+		 * Crash can happen in an interrupt context and unregistering
+		 * a clocksource is impossible and redundant in this case.
+		 */
+		if (!oops_in_progress) {
+			clocksource_change_rating(&hyperv_cs_tsc, 10);
+			clocksource_unregister(&hyperv_cs_tsc);
+		}
 
-               hypercall_msr.as_uint64 = 0;
-               wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-               vfree(hv_context.tsc_page);
-               hv_context.tsc_page = NULL;
-       }
+		hypercall_msr.as_uint64 = 0;
+		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
+		vfree(hv_context.tsc_page);
+		hv_context.tsc_page = NULL;
+	}
 #endif
 
 }