1 files changed, 81 insertions, 60 deletions

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index a8ad728354cb..b14c5f9e0ef2 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -45,8 +45,8 @@ int hv_init(void)
  * This involves a hypercall.
  */
 int hv_post_message(union hv_connection_id connection_id,
-		  enum hv_message_type message_type,
-		  void *payload, size_t payload_size)
+			enum hv_message_type message_type,
+			void *payload, size_t payload_size)
 {
 	struct hv_input_post_message *aligned_msg;
 	unsigned long flags;
@@ -85,8 +85,10 @@ int hv_post_message(union hv_connection_id connection_id,
 		else
 			status = HV_STATUS_INVALID_PARAMETER;
 	} else {
-		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
-				aligned_msg, NULL);
+		u64 control = HVCALL_POST_MESSAGE;
+
+		control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
+		status = hv_do_hypercall(control, aligned_msg, NULL);
 	}
 
 	local_irq_restore(flags);
@@ -111,7 +113,7 @@ int hv_synic_alloc(void)
 
 	hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask),
 					 GFP_KERNEL);
-	if (hv_context.hv_numa_map == NULL) {
+	if (!hv_context.hv_numa_map) {
 		pr_err("Unable to allocate NUMA map\n");
 		goto err;
 	}
@@ -120,11 +122,11 @@ int hv_synic_alloc(void)
 		hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);
 
 		tasklet_init(&hv_cpu->msg_dpc,
-			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
+			     vmbus_on_msg_dpc, (unsigned long)hv_cpu);
 
 		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
 			hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
-			if (hv_cpu->post_msg_page == NULL) {
+			if (!hv_cpu->post_msg_page) {
 				pr_err("Unable to allocate post msg page\n");
 				goto err;
 			}
@@ -144,17 +146,17 @@ int hv_synic_alloc(void)
 		 * Synic message and event pages are allocated by paravisor.
 		 * Skip these pages allocation here.
 		 */
-		if (!ms_hyperv.paravisor_present && !hv_root_partition) {
+		if (!ms_hyperv.paravisor_present && !hv_root_partition()) {
 			hv_cpu->synic_message_page =
 				(void *)get_zeroed_page(GFP_ATOMIC);
-			if (hv_cpu->synic_message_page == NULL) {
+			if (!hv_cpu->synic_message_page) {
 				pr_err("Unable to allocate SYNIC message page\n");
 				goto err;
 			}
 
 			hv_cpu->synic_event_page =
 				(void *)get_zeroed_page(GFP_ATOMIC);
-			if (hv_cpu->synic_event_page == NULL) {
+			if (!hv_cpu->synic_event_page) {
 				pr_err("Unable to allocate SYNIC event page\n");
 
 				free_page((unsigned long)hv_cpu->synic_message_page);
@@ -203,14 +205,13 @@ err:
 	return ret;
 }
 
-
 void hv_synic_free(void)
 {
 	int cpu, ret;
 
 	for_each_present_cpu(cpu) {
-		struct hv_per_cpu_context *hv_cpu
-			= per_cpu_ptr(hv_context.cpu_context, cpu);
+		struct hv_per_cpu_context *hv_cpu =
+			per_cpu_ptr(hv_context.cpu_context, cpu);
 
 		/* It's better to leak the page if the encryption fails. */
 		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
@@ -262,8 +263,8 @@ void hv_synic_free(void)
  */
 void hv_synic_enable_regs(unsigned int cpu)
 {
-	struct hv_per_cpu_context *hv_cpu
-		= per_cpu_ptr(hv_context.cpu_context, cpu);
+	struct hv_per_cpu_context *hv_cpu =
+		per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sint shared_sint;
@@ -273,12 +274,12 @@ void hv_synic_enable_regs(unsigned int cpu)
 	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
 	simp.simp_enabled = 1;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
-		hv_cpu->synic_message_page
-			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
+		hv_cpu->synic_message_page =
+			(void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
 		if (!hv_cpu->synic_message_page)
 			pr_err("Fail to map synic message page.\n");
 	} else {
@@ -292,12 +293,12 @@ void hv_synic_enable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
 	siefp.siefp_enabled = 1;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
-		hv_cpu->synic_event_page
-			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
+		hv_cpu->synic_event_page =
+			(void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
 		if (!hv_cpu->synic_event_page)
 			pr_err("Fail to map synic event page.\n");
 	} else {
@@ -314,17 +315,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 
 	shared_sint.vector = vmbus_interrupt;
 	shared_sint.masked = false;
-
-	/*
-	 * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
-	 * it doesn't provide a recommendation flag and AEOI must be disabled.
-	 */
-#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
-	shared_sint.auto_eoi =
-			!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
-#else
-	shared_sint.auto_eoi = 0;
-#endif
+	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
@@ -343,13 +334,10 @@ int hv_synic_init(unsigned int cpu)
 	return 0;
 }
 
-/*
- * hv_synic_cleanup - Cleanup routine for hv_synic_init().
- */
 void hv_synic_disable_regs(unsigned int cpu)
 {
-	struct hv_per_cpu_context *hv_cpu
-		= per_cpu_ptr(hv_context.cpu_context, cpu);
+	struct hv_per_cpu_context *hv_cpu =
+		per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
@@ -371,7 +359,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	 * addresses.
 	 */
 	simp.simp_enabled = 0;
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		iounmap(hv_cpu->synic_message_page);
 		hv_cpu->synic_message_page = NULL;
 	} else {
@@ -383,7 +371,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
 	siefp.siefp_enabled = 0;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		iounmap(hv_cpu->synic_event_page);
 		hv_cpu->synic_event_page = NULL;
 	} else {
@@ -437,10 +425,47 @@ retry:
 	return pending;
 }
 
+static int hv_pick_new_cpu(struct vmbus_channel *channel)
+{
+	int ret = -EBUSY;
+	int start;
+	int cpu;
+
+	lockdep_assert_cpus_held();
+	lockdep_assert_held(&vmbus_connection.channel_mutex);
+
+	/*
+	 * We can't assume that the relevant interrupts will be sent before
+	 * the cpu is offlined on older versions of hyperv.
+	 */
+	if (vmbus_proto_version < VERSION_WIN10_V5_3)
+		return -EBUSY;
+
+	start = get_random_u32_below(nr_cpu_ids);
+
+	for_each_cpu_wrap(cpu, cpu_online_mask, start) {
+		if (channel->target_cpu == cpu ||
+		    channel->target_cpu == VMBUS_CONNECT_CPU)
+			continue;
+
+		ret = vmbus_channel_set_cpu(channel, cpu);
+		if (!ret)
+			break;
+	}
+
+	if (ret)
+		ret = vmbus_channel_set_cpu(channel, VMBUS_CONNECT_CPU);
+
+	return ret;
+}
+
+/*
+ * hv_synic_cleanup - Cleanup routine for hv_synic_init().
+ */
 int hv_synic_cleanup(unsigned int cpu)
 {
 	struct vmbus_channel *channel, *sc;
-	bool channel_found = false;
+	int ret = 0;
 
 	if (vmbus_connection.conn_state != CONNECTED)
 		goto always_cleanup;
@@ -457,38 +482,34 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	/*
 	 * Search for channels which are bound to the CPU we're about to
-	 * cleanup.  In case we find one and vmbus is still connected, we
-	 * fail; this will effectively prevent CPU offlining.
-	 *
-	 * TODO: Re-bind the channels to different CPUs.
+	 * cleanup.
 	 */
 	mutex_lock(&vmbus_connection.channel_mutex);
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		if (channel->target_cpu == cpu) {
-			channel_found = true;
-			break;
+			ret = hv_pick_new_cpu(channel);
+			if (ret) {
+				mutex_unlock(&vmbus_connection.channel_mutex);
+				return ret;
+			}
 		}
 		list_for_each_entry(sc, &channel->sc_list, sc_list) {
 			if (sc->target_cpu == cpu) {
-				channel_found = true;
-				break;
+				ret = hv_pick_new_cpu(sc);
+				if (ret) {
+					mutex_unlock(&vmbus_connection.channel_mutex);
+					return ret;
+				}
 			}
 		}
-		if (channel_found)
-			break;
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
-	if (channel_found)
-		return -EBUSY;
-
 	/*
-	 * channel_found == false means that any channels that were previously
-	 * assigned to the CPU have been reassigned elsewhere with a call of
-	 * vmbus_send_modifychannel().  Scan the event flags page looking for
-	 * bits that are set and waiting with a timeout for vmbus_chan_sched()
-	 * to process such bits.  If bits are still set after this operation
-	 * and VMBus is connected, fail the CPU offlining operation.
+	 * Scan the event flags page looking for bits that are set and waiting
+	 * with a timeout for vmbus_chan_sched() to process such bits. If bits
+	 * are still set after this operation and VMBus is connected, fail the
+	 * CPU offlining operation.
 	 */
 	if (vmbus_proto_version >= VERSION_WIN10_V4_1 && hv_synic_event_pending())
 		return -EBUSY;
@@ -498,5 +519,5 @@ always_cleanup:
 
 	hv_synic_disable_regs(cpu);
 
-	return 0;
+	return ret;
 }