Merge tag 'hyperv-next-signed-20250123' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Introduce a new set of Hyper-V headers in include/hyperv and replace
   the old hyperv-tlfs.h with the new headers (Nuno Das Neves)

 - Fixes for the Hyper-V VTL mode (Roman Kisel)

 - Fixes for cpu mask usage in Hyper-V code (Michael Kelley)

 - Document the guest VM hibernation behaviour (Michael Kelley)

 - Miscellaneous fixes and cleanups (Jacob Pan, John Starks, Naman Jain)

* tag 'hyperv-next-signed-20250123' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  Documentation: hyperv: Add overview of guest VM hibernation
  hyperv: Do not overlap the hvcall IO areas in hv_vtl_apicid_to_vp_id()
  hyperv: Do not overlap the hvcall IO areas in get_vtl()
  hyperv: Enable the hypercall output page for the VTL mode
  hv_balloon: Fallback to generic_online_page() for non-HV hot added mem
  Drivers: hv: vmbus: Log on missing offers if any
  Drivers: hv: vmbus: Wait for boot-time offers during boot and resume
  uio_hv_generic: Add a check for HV_NIC for send, receive buffers setup
  iommu/hyper-v: Don't assume cpu_possible_mask is dense
  Drivers: hv: Don't assume cpu_possible_mask is dense
  x86/hyperv: Don't assume cpu_possible_mask is dense
  hyperv: Remove the now unused hyperv-tlfs.h files
  hyperv: Switch from hyperv-tlfs.h to hyperv/hvhdk.h
  hyperv: Add new Hyper-V headers in include/hyperv
  hyperv: Clean up unnecessary #includes
  hyperv: Move hv_connection_id to hyperv-tlfs.h

11 files changed, 139 insertions, 108 deletions

diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index b39dee7b93af..f00019b078a7 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -23,7 +23,7 @@
 #include <linux/acpi.h>
 #include <linux/hyperv.h>
 #include <clocksource/hyperv_timer.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
 
 static struct clock_event_device __percpu *hv_clock_event;
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 3c6011a48dab..6e084c207414 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -944,16 +944,6 @@ void vmbus_initiate_unload(bool crash)
 		vmbus_wait_for_unload();
 }
 
-static void check_ready_for_resume_event(void)
-{
-	/*
-	 * If all the old primary channels have been fixed up, then it's safe
-	 * to resume.
-	 */
-	if (atomic_dec_and_test(&vmbus_connection.nr_chan_fixup_on_resume))
-		complete(&vmbus_connection.ready_for_resume_event);
-}
-
 static void vmbus_setup_channel_state(struct vmbus_channel *channel,
 				      struct vmbus_channel_offer_channel *offer)
 {
@@ -1109,8 +1099,6 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 
 		/* Add the channel back to the array of channels. */
 		vmbus_channel_map_relid(oldchannel);
-		check_ready_for_resume_event();
-
 		mutex_unlock(&vmbus_connection.channel_mutex);
 		return;
 	}
@@ -1296,13 +1284,28 @@ EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister);
 
 /*
  * vmbus_onoffers_delivered -
- * This is invoked when all offers have been delivered.
+ * The CHANNELMSG_ALLOFFERS_DELIVERED message arrives after all
+ * boot-time offers are delivered. A boot-time offer is for the primary
+ * channel for any virtual hardware configured in the VM at the time it boots.
+ * Boot-time offers include offers for physical devices assigned to the VM
+ * via Hyper-V's Discrete Device Assignment (DDA) functionality that are
+ * handled as virtual PCI devices in Linux (e.g., NVMe devices and GPUs).
+ * Boot-time offers do not include offers for VMBus sub-channels. Because
+ * devices can be hot-added to the VM after it is booted, additional channel
+ * offers that aren't boot-time offers can be received at any time after the
+ * all-offers-delivered message.
  *
- * Nothing to do here.
+ * SR-IOV NIC Virtual Functions (VFs) assigned to a VM are not considered
+ * to be assigned to the VM at boot-time, and offers for VFs may occur after
+ * the all-offers-delivered message. VFs are optional accelerators to the
+ * synthetic VMBus NIC and are effectively hot-added only after the VMBus
+ * NIC channel is opened (once it knows the guest can support it, via the
+ * sriov bit in the netvsc protocol).
  */
 static void vmbus_onoffers_delivered(
 			struct vmbus_channel_message_header *hdr)
 {
+	complete(&vmbus_connection.all_offers_delivered_event);
 }
 
 /*
@@ -1578,7 +1581,8 @@ void vmbus_onmessage(struct vmbus_channel_message_header *hdr)
 }
 
 /*
- * vmbus_request_offers - Send a request to get all our pending offers.
+ * vmbus_request_offers - Send a request to get all our pending offers
+ * and wait for all boot-time offers to arrive.
  */
 int vmbus_request_offers(void)
 {
@@ -1596,6 +1600,10 @@ int vmbus_request_offers(void)
 
 	msg->msgtype = CHANNELMSG_REQUESTOFFERS;
 
+	/*
+	 * This REQUESTOFFERS message will result in the host sending an all
+	 * offers delivered message after all the boot-time offers are sent.
+	 */
 	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header),
 			     true);
 
@@ -1607,6 +1615,29 @@ int vmbus_request_offers(void)
 		goto cleanup;
 	}
 
+	/*
+	 * Wait for the host to send all boot-time offers.
+	 * Keeping it as a best-effort mechanism, where a warning is
+	 * printed if a timeout occurs, and execution is resumed.
+	 */
+	if (!wait_for_completion_timeout(&vmbus_connection.all_offers_delivered_event,
+					 secs_to_jiffies(60))) {
+		pr_warn("timed out waiting for all boot-time offers to be delivered.\n");
+	}
+
+	/*
+	 * Flush handling of offer messages (which may initiate work on
+	 * other work queues).
+	 */
+	flush_workqueue(vmbus_connection.work_queue);
+
+	/*
+	 * Flush workqueue for processing the incoming offers. Subchannel
+	 * offers and their processing can happen later, so there is no need to
+	 * flush that workqueue here.
+	 */
+	flush_workqueue(vmbus_connection.handle_primary_chan_wq);
+
 cleanup:
 	kfree(msginfo);
 
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index f001ae880e1d..8351360bba16 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -34,8 +34,8 @@ struct vmbus_connection vmbus_connection = {
 
 	.ready_for_suspend_event = COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
-	.ready_for_resume_event	= COMPLETION_INITIALIZER(
-				  vmbus_connection.ready_for_resume_event),
+	.all_offers_delivered_event = COMPLETION_INITIALIZER(
+				  vmbus_connection.all_offers_delivered_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index a99112e6f0b8..fec2f18679e3 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -28,7 +28,7 @@
 #include <linux/sizes.h>
 
 #include <linux/hyperv.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 
 #include <asm/mshyperv.h>
 
@@ -766,16 +766,18 @@ static void hv_online_page(struct page *pg, unsigned int order)
 	struct hv_hotadd_state *has;
 	unsigned long pfn = page_to_pfn(pg);
 
-	guard(spinlock_irqsave)(&dm_device.ha_lock);
-	list_for_each_entry(has, &dm_device.ha_region_list, list) {
-		/* The page belongs to a different HAS. */
-		if (pfn < has->start_pfn ||
-		    (pfn + (1UL << order) > has->end_pfn))
-			continue;
+	scoped_guard(spinlock_irqsave, &dm_device.ha_lock) {
+		list_for_each_entry(has, &dm_device.ha_region_list, list) {
+			/* The page belongs to a different HAS. */
+			if (pfn < has->start_pfn ||
+				(pfn + (1UL << order) > has->end_pfn))
+				continue;
 
-		hv_bring_pgs_online(has, pfn, 1UL << order);
-		break;
+			hv_bring_pgs_online(has, pfn, 1UL << order);
+			return;
+		}
 	}
+	generic_online_page(pg, order);
 }
 
 static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
@@ -1586,7 +1588,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 		return -ENOSPC;
 	}
 
-	hint->type = HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD;
+	hint->heat_type = HV_EXTMEM_HEAT_HINT_COLD_DISCARD;
 	hint->reserved = 0;
 	for_each_sg(sgl, sg, nents, i) {
 		union hv_gpa_page_range *range;
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 7a35c82976e0..af5d1dc451f6 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/dma-map-ops.h>
 #include <linux/set_memory.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
 
 /*
@@ -278,6 +278,11 @@ static void hv_kmsg_dump_register(void)
 	}
 }
 
+static inline bool hv_output_page_exists(void)
+{
+	return hv_root_partition || IS_ENABLED(CONFIG_HYPERV_VTL_MODE);
+}
+
 int __init hv_common_init(void)
 {
 	int i;
@@ -340,19 +345,19 @@ int __init hv_common_init(void)
 	BUG_ON(!hyperv_pcpu_input_arg);
 
 	/* Allocate the per-CPU state for output arg for root */
-	if (hv_root_partition) {
+	if (hv_output_page_exists()) {
 		hyperv_pcpu_output_arg = alloc_percpu(void *);
 		BUG_ON(!hyperv_pcpu_output_arg);
 	}
 
-	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
+	hv_vp_index = kmalloc_array(nr_cpu_ids, sizeof(*hv_vp_index),
 				    GFP_KERNEL);
 	if (!hv_vp_index) {
 		hv_common_free();
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < num_possible_cpus(); i++)
+	for (i = 0; i < nr_cpu_ids; i++)
 		hv_vp_index[i] = VP_INVAL;
 
 	return 0;
@@ -435,7 +440,7 @@ int hv_common_cpu_init(unsigned int cpu)
 	void **inputarg, **outputarg;
 	u64 msr_vp_index;
 	gfp_t flags;
-	int pgcount = hv_root_partition ? 2 : 1;
+	const int pgcount = hv_output_page_exists() ? 2 : 1;
 	void *mem;
 	int ret;
 
@@ -453,7 +458,7 @@ int hv_common_cpu_init(unsigned int cpu)
 		if (!mem)
 			return -ENOMEM;
 
-		if (hv_root_partition) {
+		if (hv_output_page_exists()) {
 			outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
 			*outputarg = (char *)mem + HV_HYP_PAGE_SIZE;
 		}
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 7400a5a4d2bd..62795f6cbb00 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -27,7 +27,7 @@
 #include <linux/connector.h>
 #include <linux/workqueue.h>
 #include <linux/hyperv.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 
 #include "hyperv_vmbus.h"
 #include "hv_utils_transport.h"
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index bde637a96c37..2e7f537d53cf 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -12,7 +12,7 @@
 #include <linux/connector.h>
 #include <linux/workqueue.h>
 #include <linux/hyperv.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 
 #include "hyperv_vmbus.h"
 #include "hv_utils_transport.h"
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 52cb744b4d7f..29780f3a7478 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -15,10 +15,10 @@
 #include <linux/list.h>
 #include <linux/bitops.h>
 #include <asm/sync_bitops.h>
-#include <asm/hyperv-tlfs.h>
 #include <linux/atomic.h>
 #include <linux/hyperv.h>
 #include <linux/interrupt.h>
+#include <hyperv/hvhdk.h>
 
 #include "hv_trace.h"
 
@@ -287,18 +287,10 @@ struct vmbus_connection {
 	struct completion ready_for_suspend_event;
 
 	/*
-	 * The number of primary channels that should be "fixed up"
-	 * upon resume: these channels are re-offered upon resume, and some
-	 * fields of the channel offers (i.e. child_relid and connection_id)
-	 * can change, so the old offermsg must be fixed up, before the resume
-	 * callbacks of the VSC drivers start to further touch the channels.
+	 * Completed once the host has offered all boot-time channels.
+	 * Note that some channels may still be under process on a workqueue.
 	 */
-	atomic_t nr_chan_fixup_on_resume;
-	/*
-	 * vmbus_bus_resume() waits for "nr_chan_fixup_on_resume" to
-	 * drop to zero.
-	 */
-	struct completion ready_for_resume_event;
+	struct completion all_offers_delivered_event;
 };
 
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2892b8da20a5..0f6cd44fff29 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2427,11 +2427,6 @@ static int vmbus_bus_suspend(struct device *dev)
 	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
 		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
 
-	if (atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0) {
-		pr_err("Can not suspend due to a previous failed resuming\n");
-		return -EBUSY;
-	}
-
 	mutex_lock(&vmbus_connection.channel_mutex);
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
@@ -2456,22 +2451,18 @@ static int vmbus_bus_suspend(struct device *dev)
 			pr_err("Sub-channel not deleted!\n");
 			WARN_ON_ONCE(1);
 		}
-
-		atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume);
 	}
 
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
 	vmbus_initiate_unload(false);
 
-	/* Reset the event for the next resume. */
-	reinit_completion(&vmbus_connection.ready_for_resume_event);
-
 	return 0;
 }
 
 static int vmbus_bus_resume(struct device *dev)
 {
+	struct vmbus_channel *channel;
 	struct vmbus_channel_msginfo *msginfo;
 	size_t msgsize;
 	int ret;
@@ -2502,13 +2493,23 @@ static int vmbus_bus_resume(struct device *dev)
 	if (ret != 0)
 		return ret;
 
-	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0);
-
 	vmbus_request_offers();
 
-	if (wait_for_completion_timeout(
-		&vmbus_connection.ready_for_resume_event, secs_to_jiffies(10)) == 0)
-		pr_err("Some vmbus device is missing after suspending?\n");
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (channel->offermsg.child_relid != INVALID_RELID)
+			continue;
+
+		/* hvsock channels are not expected to be present. */
+		if (is_hvsock_channel(channel))
+			continue;
+
+		pr_err("channel %pUl/%pUl not present after resume.\n",
+		       &channel->offermsg.offer.if_type,
+		       &channel->offermsg.offer.if_instance);
+		/* ToDo: Cleanup these channels here */
+	}
+	mutex_unlock(&vmbus_connection.channel_mutex);
 
 	/* Reset the event for the next suspend. */
 	reinit_completion(&vmbus_connection.ready_for_suspend_event);
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index 8a5c17b97310..2a86aa5d54c6 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -164,8 +164,8 @@ static int __init hyperv_prepare_irq_remapping(void)
 	 * max cpu affinity for IOAPIC irqs. Scan cpu 0-255 and set cpu
 	 * into ioapic_max_cpumask if its APIC ID is less than 256.
 	 */
-	for (i = min_t(unsigned int, num_possible_cpus() - 1, 255); i >= 0; i--)
-		if (cpu_physical_id(i) < 256)
+	for (i = min_t(unsigned int, nr_cpu_ids - 1, 255); i >= 0; i--)
+		if (cpu_possible(i) && cpu_physical_id(i) < 256)
 			cpumask_set_cpu(i, &ioapic_max_cpumask);
 
 	return 0;
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 3976360d0096..1b19b5647495 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -296,51 +296,51 @@ hv_uio_probe(struct hv_device *dev,
 	pdata->info.mem[MON_PAGE_MAP].size = PAGE_SIZE;
 	pdata->info.mem[MON_PAGE_MAP].memtype = UIO_MEM_LOGICAL;
 
-	pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE);
-	if (pdata->recv_buf == NULL) {
-		ret = -ENOMEM;
-		goto fail_free_ring;
+	if (channel->device_id == HV_NIC) {
+		pdata->recv_buf = vzalloc(RECV_BUFFER_SIZE);
+		if (!pdata->recv_buf) {
+			ret = -ENOMEM;
+			goto fail_free_ring;
+		}
+
+		ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
+					    RECV_BUFFER_SIZE, &pdata->recv_gpadl);
+		if (ret) {
+			if (!pdata->recv_gpadl.decrypted)
+				vfree(pdata->recv_buf);
+			goto fail_close;
+		}
+
+		/* put Global Physical Address Label in name */
+		snprintf(pdata->recv_name, sizeof(pdata->recv_name),
+			 "recv:%u", pdata->recv_gpadl.gpadl_handle);
+		pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name;
+		pdata->info.mem[RECV_BUF_MAP].addr = (uintptr_t)pdata->recv_buf;
+		pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE;
+		pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
+
+		pdata->send_buf = vzalloc(SEND_BUFFER_SIZE);
+		if (!pdata->send_buf) {
+			ret = -ENOMEM;
+			goto fail_close;
+		}
+
+		ret = vmbus_establish_gpadl(channel, pdata->send_buf,
+					    SEND_BUFFER_SIZE, &pdata->send_gpadl);
+		if (ret) {
+			if (!pdata->send_gpadl.decrypted)
+				vfree(pdata->send_buf);
+			goto fail_close;
+		}
+
+		snprintf(pdata->send_name, sizeof(pdata->send_name),
+			 "send:%u", pdata->send_gpadl.gpadl_handle);
+		pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name;
+		pdata->info.mem[SEND_BUF_MAP].addr = (uintptr_t)pdata->send_buf;
+		pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE;
+		pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
 	}
 
-	ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
-				    RECV_BUFFER_SIZE, &pdata->recv_gpadl);
-	if (ret) {
-		if (!pdata->recv_gpadl.decrypted)
-			vfree(pdata->recv_buf);
-		goto fail_close;
-	}
-
-	/* put Global Physical Address Label in name */
-	snprintf(pdata->recv_name, sizeof(pdata->recv_name),
-		 "recv:%u", pdata->recv_gpadl.gpadl_handle);
-	pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name;
-	pdata->info.mem[RECV_BUF_MAP].addr
-		= (uintptr_t)pdata->recv_buf;
-	pdata->info.mem[RECV_BUF_MAP].size = RECV_BUFFER_SIZE;
-	pdata->info.mem[RECV_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
-
-	pdata->send_buf = vzalloc(SEND_BUFFER_SIZE);
-	if (pdata->send_buf == NULL) {
-		ret = -ENOMEM;
-		goto fail_close;
-	}
-
-	ret = vmbus_establish_gpadl(channel, pdata->send_buf,
-				    SEND_BUFFER_SIZE, &pdata->send_gpadl);
-	if (ret) {
-		if (!pdata->send_gpadl.decrypted)
-			vfree(pdata->send_buf);
-		goto fail_close;
-	}
-
-	snprintf(pdata->send_name, sizeof(pdata->send_name),
-		 "send:%u", pdata->send_gpadl.gpadl_handle);
-	pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name;
-	pdata->info.mem[SEND_BUF_MAP].addr
-		= (uintptr_t)pdata->send_buf;
-	pdata->info.mem[SEND_BUF_MAP].size = SEND_BUFFER_SIZE;
-	pdata->info.mem[SEND_BUF_MAP].memtype = UIO_MEM_VIRTUAL;
-
 	pdata->info.priv = pdata;
 	pdata->device = dev;