Merge tag 'hyperv-next-signed-20260421' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull Hyper-V updates from Wei Liu:

 - Fix cross-compilation for hv tools (Aditya Garg)

 - Fix vmemmap_shift exceeding MAX_FOLIO_ORDER in mshv_vtl (Naman Jain)

 - Limit channel interrupt scan to relid high water mark (Michael
   Kelley)

 - Export hv_vmbus_exists() and use it in pci-hyperv (Dexuan Cui)

 - Fix cleanup and shutdown issues for MSHV (Jork Loeser)

 - Introduce more tracing support for MSHV (Stanislav Kinsburskii)

* tag 'hyperv-next-signed-20260421' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  x86/hyperv: Skip LP/VP creation on kexec
  x86/hyperv: move stimer cleanup to hv_machine_shutdown()
  Drivers: hv: vmbus: fix hyperv_cpuhp_online variable shadowing
  mshv: Add tracepoint for GPA intercept handling
  mshv_vtl: Fix vmemmap_shift exceeding MAX_FOLIO_ORDER
  tools: hv: Fix cross-compilation
  Drivers: hv: vmbus: Export hv_vmbus_exists() and use it in pci-hyperv
  mshv: Introduce tracing support
  Drivers: hv: vmbus: Limit channel interrupt scan to relid high water mark

Author: torvalds

arch/x86/kernel/cpu/mshyperv.c

@@ -237,8 +237,12 @@ void hv_remove_crash_handler(void)
 #ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
 {
-	if (kexec_in_progress && hv_kexec_handler)
-		hv_kexec_handler();
+	if (kexec_in_progress) {
+		hv_stimer_global_cleanup();
+
+		if (hv_kexec_handler)
+			hv_kexec_handler();
+	}
 
 	/*
 	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
@@ -427,13 +431,20 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 #ifdef CONFIG_X86_64
+	/* If AP LPs exist, we are in a kexec'd kernel and VPs already exist */
+	if (num_present_cpus() == 1 || hv_lp_exists(1))
+		return;
+
 	for_each_present_cpu(i) {
 		if (i == 0)
 			continue;
 		ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
 		BUG_ON(ret);
 	}
 
+	ret = hv_call_notify_all_processors_started();
+	WARN_ON(ret);
+
 	for_each_present_cpu(i) {
 		if (i == 0)
 			continue;

drivers/hv/Makefile

@@ -16,6 +16,7 @@ hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_utils_transport.o
 mshv_root-y := mshv_root_main.o mshv_synic.o mshv_eventfd.o mshv_irq.o \
 	       mshv_root_hv_call.o mshv_portid_table.o mshv_regions.o
 mshv_root-$(CONFIG_DEBUG_FS) += mshv_debugfs.o
+mshv_root-$(CONFIG_TRACEPOINTS) += mshv_trace.o
 mshv_vtl-y := mshv_vtl_main.o
 
 # Code that must be built-in

drivers/hv/channel_mgmt.c

@@ -384,8 +384,18 @@ static void free_channel(struct vmbus_channel *channel)
 
 void vmbus_channel_map_relid(struct vmbus_channel *channel)
 {
-	if (WARN_ON(channel->offermsg.child_relid >= MAX_CHANNEL_RELIDS))
+	u32 new_relid = channel->offermsg.child_relid;
+
+	if (WARN_ON(new_relid >= MAX_CHANNEL_RELIDS))
 		return;
+
+	/*
+	 * This function is always called in the tasklet for the connect CPU.
+	 * So updating the relid hiwater mark does not need to be atomic.
+	 */
+	if (new_relid > READ_ONCE(vmbus_connection.relid_hiwater))
+		WRITE_ONCE(vmbus_connection.relid_hiwater, new_relid);
+
 	/*
 	 * The mapping of the channel's relid is visible from the CPUs that
 	 * execute vmbus_chan_sched() by the time that vmbus_chan_sched() will
@@ -411,9 +421,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
 	 *      of the VMBus driver and vmbus_chan_sched() can not run before
 	 *      vmbus_bus_resume() has completed execution (cf. resume_noirq).
 	 */
-	virt_store_mb(
-		vmbus_connection.channels[channel->offermsg.child_relid],
-		channel);
+	virt_store_mb(vmbus_connection.channels[new_relid], channel);
 }
 
 void vmbus_channel_unmap_relid(struct vmbus_channel *channel)

drivers/hv/hv_proc.c

@@ -239,3 +239,50 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hv_call_create_vp);
+
+int hv_call_notify_all_processors_started(void)
+{
+	struct hv_input_notify_partition_event *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	local_irq_save(irq_flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(input, 0, sizeof(*input));
+	input->event = HV_PARTITION_ALL_LOGICAL_PROCESSORS_STARTED;
+	status = hv_do_hypercall(HVCALL_NOTIFY_PARTITION_EVENT,
+				 input, NULL);
+	local_irq_restore(irq_flags);
+
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		ret = hv_result_to_errno(status);
+	}
+	return ret;
+}
+
+bool hv_lp_exists(u32 lp_index)
+{
+	struct hv_input_get_logical_processor_run_time *input;
+	struct hv_output_get_logical_processor_run_time *output;
+	unsigned long flags;
+	u64 status;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	input->lp_index = lp_index;
+	status = hv_do_hypercall(HVCALL_GET_LOGICAL_PROCESSOR_RUN_TIME,
+				 input, output);
+	local_irq_restore(flags);
+
+	if (!hv_result_success(status) &&
+	    hv_result(status) != HV_STATUS_INVALID_LP_INDEX) {
+		hv_status_err(status, "\n");
+		BUG();
+	}
+
+	return hv_result_success(status);
+}

drivers/hv/hyperv_vmbus.h

@@ -276,8 +276,9 @@ struct vmbus_connection {
 	struct list_head chn_list;
 	struct mutex channel_mutex;
 
-	/* Array of channels */
+	/* Array of channel pointers, indexed by relid */
 	struct vmbus_channel **channels;
+	u32 relid_hiwater;
 
 	/*
 	 * An offer message is handled first on the work_queue, and then

drivers/hv/mshv_eventfd.c

@@ -733,6 +733,14 @@ static int mshv_assign_ioeventfd(struct mshv_partition *pt,
 	ret = mshv_register_doorbell(pt->pt_id, ioeventfd_mmio_write,
 				     (void *)pt, p->iovntfd_addr,
 				     p->iovntfd_datamatch, doorbell_flags);
+
+	trace_mshv_assign_ioeventfd(pt->pt_id, p->iovntfd_addr,
+				    p->iovntfd_length,
+				    p->iovntfd_datamatch,
+				    p->iovntfd_wildcard,
+				    p->iovntfd_eventfd,
+				    ret);
+
 	if (ret < 0)
 		goto unlock_fail;
 
@@ -780,6 +788,12 @@ static int mshv_deassign_ioeventfd(struct mshv_partition *pt,
 		    p->iovntfd_datamatch != args->datamatch)
 			continue;
 
+		trace_mshv_deassign_ioeventfd(pt->pt_id, p->iovntfd_addr,
+					      p->iovntfd_length,
+					      p->iovntfd_datamatch,
+					      p->iovntfd_wildcard,
+					      p->iovntfd_eventfd);
+
 		hlist_del_rcu(&p->iovntfd_hnode);
 		synchronize_rcu();
 		ioeventfd_release(p, pt->pt_id);

drivers/hv/mshv_irq.c

@@ -71,6 +71,10 @@ int mshv_update_routing_table(struct mshv_partition *partition,
 	mutex_unlock(&partition->pt_irq_lock);
 
 	synchronize_srcu_expedited(&partition->pt_irq_srcu);
+
+	trace_mshv_update_routing_table(partition->pt_id,
+					old, new, numents);
+
 	new = old;
 
 out:

drivers/hv/mshv_root.h

@@ -17,6 +17,7 @@
 #include <linux/build_bug.h>
 #include <linux/mmu_notifier.h>
 #include <uapi/linux/mshv.h>
+#include "mshv_trace.h"
 
 /*
  * Hypervisor must be between these version numbers (inclusive)

drivers/hv/mshv_root_hv_call.c

@@ -45,8 +45,7 @@ int hv_call_withdraw_memory(u64 count, int node, u64 partition_id)
 	struct hv_output_withdraw_memory *output_page;
 	struct page *page;
 	u16 completed;
-	unsigned long remaining = count;
-	u64 status;
+	u64 status, withdrawn = 0;
 	int i;
 	unsigned long flags;
 
@@ -55,15 +54,15 @@ int hv_call_withdraw_memory(u64 count, int node, u64 partition_id)
 		return -ENOMEM;
 	output_page = page_address(page);
 
-	while (remaining) {
+	while (withdrawn < count) {
 		local_irq_save(flags);
 
 		input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
 
 		memset(input_page, 0, sizeof(*input_page));
 		input_page->partition_id = partition_id;
 		status = hv_do_rep_hypercall(HVCALL_WITHDRAW_MEMORY,
-					     min(remaining, HV_WITHDRAW_BATCH_SIZE),
+					     min(count - withdrawn, HV_WITHDRAW_BATCH_SIZE),
 					     0, input_page, output_page);
 
 		local_irq_restore(flags);
@@ -79,10 +78,12 @@ int hv_call_withdraw_memory(u64 count, int node, u64 partition_id)
 			break;
 		}
 
-		remaining -= completed;
+		withdrawn += completed;
 	}
 	free_page((unsigned long)output_page);
 
+	trace_mshv_hvcall_withdraw_memory(partition_id, withdrawn, status);
+
 	return hv_result_to_errno(status);
 }
 
@@ -126,6 +127,8 @@ int hv_call_create_partition(u64 flags,
 		ret = hv_deposit_memory(hv_current_partition_id, status);
 	} while (!ret);
 
+	trace_mshv_hvcall_create_partition(flags, ret ? ret : *partition_id);
+
 	return ret;
 }
 
@@ -153,6 +156,8 @@ int hv_call_initialize_partition(u64 partition_id)
 		ret = hv_deposit_memory(partition_id, status);
 	} while (!ret);
 
+	trace_mshv_hvcall_initialize_partition(partition_id, status);
+
 	return ret;
 }
 
@@ -165,6 +170,8 @@ int hv_call_finalize_partition(u64 partition_id)
 	status = hv_do_fast_hypercall8(HVCALL_FINALIZE_PARTITION,
 				       *(u64 *)&input);
 
+	trace_mshv_hvcall_finalize_partition(partition_id, status);
+
 	return hv_result_to_errno(status);
 }
 
@@ -176,6 +183,8 @@ int hv_call_delete_partition(u64 partition_id)
 	input.partition_id = partition_id;
 	status = hv_do_fast_hypercall8(HVCALL_DELETE_PARTITION, *(u64 *)&input);
 
+	trace_mshv_hvcall_delete_partition(partition_id, status);
+
 	return hv_result_to_errno(status);
 }
 
@@ -573,6 +582,9 @@ static int hv_call_map_vp_state_page(u64 partition_id, u32 vp_index, u32 type,
 		ret = hv_deposit_memory(partition_id, status);
 	} while (!ret);
 
+	trace_mshv_hvcall_map_vp_state_page(partition_id, vp_index,
+					    type, status);
+
 	return ret;
 }