1 files changed, 132 insertions, 70 deletions

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 69591dc7bad2..a53af6fe81a6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -36,6 +36,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/dma-map-ops.h>
 #include <linux/pci.h>
+#include <linux/export.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
@@ -57,6 +58,18 @@ int vmbus_irq;
 int vmbus_interrupt;
 
 /*
+ * If the Confidential VMBus is used, the data on the "wire" is not
+ * visible to either the host or the hypervisor.
+ */
+static bool is_confidential;
+
+bool vmbus_is_confidential(void)
+{
+	return is_confidential;
+}
+EXPORT_SYMBOL_GPL(vmbus_is_confidential);
+
+/*
  * The panic notifier below is responsible solely for unloading the
  * vmbus connection, which is necessary in a panic event.
  *
@@ -1045,12 +1058,9 @@ static void vmbus_onmessage_work(struct work_struct *work)
 	kfree(ctx);
 }
 
-void vmbus_on_msg_dpc(unsigned long data)
+static void __vmbus_on_msg_dpc(void *message_page_addr)
 {
-	struct hv_per_cpu_context *hv_cpu = (void *)data;
-	void *page_addr = hv_cpu->synic_message_page;
-	struct hv_message msg_copy, *msg = (struct hv_message *)page_addr +
-				  VMBUS_MESSAGE_SINT;
+	struct hv_message msg_copy, *msg;
 	struct vmbus_channel_message_header *hdr;
 	enum vmbus_channel_message_type msgtype;
 	const struct vmbus_channel_message_table_entry *entry;
@@ -1058,6 +1068,10 @@ void vmbus_on_msg_dpc(unsigned long data)
 	__u8 payload_size;
 	u32 message_type;
 
+	if (!message_page_addr)
+		return;
+	msg = (struct hv_message *)message_page_addr + VMBUS_MESSAGE_SINT;
+
 	/*
 	 * 'enum vmbus_channel_message_type' is supposed to always be 'u32' as
 	 * it is being used in 'struct vmbus_channel_message_header' definition
@@ -1183,6 +1197,14 @@ msg_handled:
 	vmbus_signal_eom(msg, message_type);
 }
 
+void vmbus_on_msg_dpc(unsigned long data)
+{
+	struct hv_per_cpu_context *hv_cpu = (void *)data;
+
+	__vmbus_on_msg_dpc(hv_cpu->hyp_synic_message_page);
+	__vmbus_on_msg_dpc(hv_cpu->para_synic_message_page);
+}
+
 #ifdef CONFIG_PM_SLEEP
 /*
  * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
@@ -1221,21 +1243,19 @@ static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
 #endif /* CONFIG_PM_SLEEP */
 
 /*
- * Schedule all channels with events pending
+ * Schedule all channels with events pending.
+ * The event page can be directly checked to get the id of
+ * the channel that has the interrupt pending.
  */
-static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
+static void vmbus_chan_sched(void *event_page_addr)
 {
 	unsigned long *recv_int_page;
 	u32 maxbits, relid;
+	union hv_synic_event_flags *event;
 
-	/*
-	 * The event page can be directly checked to get the id of
-	 * the channel that has the interrupt pending.
-	 */
-	void *page_addr = hv_cpu->synic_event_page;
-	union hv_synic_event_flags *event
-		= (union hv_synic_event_flags *)page_addr +
-					 VMBUS_MESSAGE_SINT;
+	if (!event_page_addr)
+		return;
+	event = (union hv_synic_event_flags *)event_page_addr + VMBUS_MESSAGE_SINT;
 
 	maxbits = HV_EVENT_FLAGS_COUNT;
 	recv_int_page = event->flags;
@@ -1243,6 +1263,11 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 	if (unlikely(!recv_int_page))
 		return;
 
+	/*
+	 * Suggested-by: Michael Kelley <mhklinux@outlook.com>
+	 * One possible optimization would be to keep track of the largest relID that's in use,
+	 * and only scan up to that relID.
+	 */
 	for_each_set_bit(relid, recv_int_page, maxbits) {
 		void (*callback_fn)(void *context);
 		struct vmbus_channel *channel;
@@ -1306,29 +1331,39 @@ sched_unlock_rcu:
 	}
 }
 
-static void vmbus_isr(void)
+static void vmbus_message_sched(struct hv_per_cpu_context *hv_cpu, void *message_page_addr)
 {
-	struct hv_per_cpu_context *hv_cpu
-		= this_cpu_ptr(hv_context.cpu_context);
-	void *page_addr;
 	struct hv_message *msg;
 
-	vmbus_chan_sched(hv_cpu);
-
-	page_addr = hv_cpu->synic_message_page;
-	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
+	if (!message_page_addr)
+		return;
+	msg = (struct hv_message *)message_page_addr + VMBUS_MESSAGE_SINT;
 
 	/* Check if there are actual msgs to be processed */
 	if (msg->header.message_type != HVMSG_NONE) {
 		if (msg->header.message_type == HVMSG_TIMER_EXPIRED) {
 			hv_stimer0_isr();
 			vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
-		} else
+		} else {
 			tasklet_schedule(&hv_cpu->msg_dpc);
+		}
 	}
+}
+
+void vmbus_isr(void)
+{
+	struct hv_per_cpu_context *hv_cpu
+		= this_cpu_ptr(hv_context.cpu_context);
+
+	vmbus_chan_sched(hv_cpu->hyp_synic_event_page);
+	vmbus_chan_sched(hv_cpu->para_synic_event_page);
+
+	vmbus_message_sched(hv_cpu, hv_cpu->hyp_synic_message_page);
+	vmbus_message_sched(hv_cpu, hv_cpu->para_synic_message_page);
 
 	add_interrupt_randomness(vmbus_interrupt);
 }
+EXPORT_SYMBOL_FOR_MODULES(vmbus_isr, "mshv_vtl");
 
 static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id)
 {
@@ -1343,6 +1378,59 @@ static void vmbus_percpu_work(struct work_struct *work)
 	hv_synic_init(cpu);
 }
 
+static int vmbus_alloc_synic_and_connect(void)
+{
+	int ret, cpu;
+	struct work_struct __percpu *works;
+	int hyperv_cpuhp_online;
+
+	ret = hv_synic_alloc();
+	if (ret < 0)
+		goto err_alloc;
+
+	works = alloc_percpu(struct work_struct);
+	if (!works) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	/*
+	 * Initialize the per-cpu interrupt state and stimer state.
+	 * Then connect to the host.
+	 */
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct work_struct *work = per_cpu_ptr(works, cpu);
+
+		INIT_WORK(work, vmbus_percpu_work);
+		schedule_work_on(cpu, work);
+	}
+
+	for_each_online_cpu(cpu)
+		flush_work(per_cpu_ptr(works, cpu));
+
+	/* Register the callbacks for possible CPU online/offline'ing */
+	ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
+						   hv_synic_init, hv_synic_cleanup);
+	cpus_read_unlock();
+	free_percpu(works);
+	if (ret < 0)
+		goto err_alloc;
+	hyperv_cpuhp_online = ret;
+
+	ret = vmbus_connect();
+	if (ret)
+		goto err_connect;
+	return 0;
+
+err_connect:
+	cpuhp_remove_state(hyperv_cpuhp_online);
+	return -ENODEV;
+err_alloc:
+	hv_synic_free();
+	return -ENOMEM;
+}
+
 /*
  * vmbus_bus_init -Main vmbus driver initialization routine.
  *
@@ -1353,8 +1441,7 @@ static void vmbus_percpu_work(struct work_struct *work)
  */
 static int vmbus_bus_init(void)
 {
-	int ret, cpu;
-	struct work_struct __percpu *works;
+	int ret;
 
 	ret = hv_init();
 	if (ret != 0) {
@@ -1389,41 +1476,15 @@ static int vmbus_bus_init(void)
 		}
 	}
 
-	ret = hv_synic_alloc();
-	if (ret)
-		goto err_alloc;
-
-	works = alloc_percpu(struct work_struct);
-	if (!works) {
-		ret = -ENOMEM;
-		goto err_alloc;
-	}
-
 	/*
-	 * Initialize the per-cpu interrupt state and stimer state.
-	 * Then connect to the host.
+	 * Cache the value as getting it involves a VM exit on x86(_64), and
+	 * doing that on each VP while initializing SynIC's wastes time.
 	 */
-	cpus_read_lock();
-	for_each_online_cpu(cpu) {
-		struct work_struct *work = per_cpu_ptr(works, cpu);
-
-		INIT_WORK(work, vmbus_percpu_work);
-		schedule_work_on(cpu, work);
-	}
-
-	for_each_online_cpu(cpu)
-		flush_work(per_cpu_ptr(works, cpu));
-
-	/* Register the callbacks for possible CPU online/offline'ing */
-	ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
-						   hv_synic_init, hv_synic_cleanup);
-	cpus_read_unlock();
-	free_percpu(works);
-	if (ret < 0)
-		goto err_alloc;
-	hyperv_cpuhp_online = ret;
-
-	ret = vmbus_connect();
+	is_confidential = ms_hyperv.confidential_vmbus_available;
+	if (is_confidential)
+		pr_info("Establishing connection to the confidential VMBus\n");
+	hv_para_set_sint_proxy(!is_confidential);
+	ret = vmbus_alloc_synic_and_connect();
 	if (ret)
 		goto err_connect;
 
@@ -1439,9 +1500,6 @@ static int vmbus_bus_init(void)
 	return 0;
 
 err_connect:
-	cpuhp_remove_state(hyperv_cpuhp_online);
-err_alloc:
-	hv_synic_free();
 	if (vmbus_irq == -1) {
 		hv_remove_vmbus_handler();
 	} else {
@@ -2798,10 +2856,10 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 */
 	cpu = smp_processor_id();
 	hv_stimer_cleanup(cpu);
-	hv_synic_disable_regs(cpu);
+	hv_hyp_synic_disable_regs(cpu);
 };
 
-static int hv_synic_suspend(void)
+static int hv_synic_suspend(void *data)
 {
 	/*
 	 * When we reach here, all the non-boot CPUs have been offlined.
@@ -2823,14 +2881,14 @@ static int hv_synic_suspend(void)
 	 * interrupts-disabled context.
 	 */
 
-	hv_synic_disable_regs(0);
+	hv_hyp_synic_disable_regs(0);
 
 	return 0;
 }
 
-static void hv_synic_resume(void)
+static void hv_synic_resume(void *data)
 {
-	hv_synic_enable_regs(0);
+	hv_hyp_synic_enable_regs(0);
 
 	/*
 	 * Note: we don't need to call hv_stimer_init(0), because the timer
@@ -2840,11 +2898,15 @@ static void hv_synic_resume(void)
 }
 
 /* The callbacks run only on CPU0, with irqs_disabled. */
-static struct syscore_ops hv_synic_syscore_ops = {
+static const struct syscore_ops hv_synic_syscore_ops = {
 	.suspend = hv_synic_suspend,
 	.resume = hv_synic_resume,
 };
 
+static struct syscore hv_synic_syscore = {
+	.ops = &hv_synic_syscore_ops,
+};
+
 static int __init hv_acpi_init(void)
 {
 	int ret;
@@ -2887,7 +2949,7 @@ static int __init hv_acpi_init(void)
 	hv_setup_kexec_handler(hv_kexec_handler);
 	hv_setup_crash_handler(hv_crash_handler);
 
-	register_syscore_ops(&hv_synic_syscore_ops);
+	register_syscore(&hv_synic_syscore);
 
 	return 0;
 
@@ -2901,7 +2963,7 @@ static void __exit vmbus_exit(void)
 {
 	int cpu;
 
-	unregister_syscore_ops(&hv_synic_syscore_ops);
+	unregister_syscore(&hv_synic_syscore);
 
 	hv_remove_kexec_handler();
 	hv_remove_crash_handler();