Merge tag 'hyperv-fixes-signed-20220407' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv fixes from Wei Liu:

 - Correctly propagate coherence information for VMbus devices (Michael
   Kelley)

 - Disable balloon and memory hot-add on ARM64 temporarily (Boqun Feng)

 - Use barrier to prevent reording when reading ring buffer (Michael
   Kelley)

 - Use virt_store_mb in favour of smp_store_mb (Andrea Parri)

 - Fix VMbus device object initialization (Andrea Parri)

 - Deactivate sysctl_record_panic_msg on isolated guest (Andrea Parri)

 - Fix a crash when unloading VMbus module (Guilherme G. Piccoli)

* tag 'hyperv-fixes-signed-20220407' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  Drivers: hv: vmbus: Replace smp_store_mb() with virt_store_mb()
  Drivers: hv: balloon: Disable balloon and hot-add accordingly
  Drivers: hv: balloon: Support status report for larger page sizes
  Drivers: hv: vmbus: Prevent load re-ordering when reading ring buffer
  PCI: hv: Propagate coherence from VMbus device to PCI device
  Drivers: hv: vmbus: Propagate VMbus coherence to each VMbus device
  Drivers: hv: vmbus: Fix potential crash on module unload
  Drivers: hv: vmbus: Fix initialization of device object in vmbus_device_register()
  Drivers: hv: vmbus: Deactivate sysctl_record_panic_msg by default in isolated guests

6 files changed, 131 insertions, 20 deletions

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 26d269ba947c..85a2142c9384 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
 	 * execute:
 	 *
 	 *  (a) In the "normal (i.e., not resuming from hibernation)" path,
-	 *      the full barrier in smp_store_mb() guarantees that the store
+	 *      the full barrier in virt_store_mb() guarantees that the store
 	 *      is propagated to all CPUs before the add_channel_work work
 	 *      is queued.  In turn, add_channel_work is queued before the
 	 *      channel's ring buffer is allocated/initialized and the
@@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
 	 *      recv_int_page before retrieving the channel pointer from the
 	 *      array of channels.
 	 *
-	 *  (b) In the "resuming from hibernation" path, the smp_store_mb()
+	 *  (b) In the "resuming from hibernation" path, the virt_store_mb()
 	 *      guarantees that the store is propagated to all CPUs before
 	 *      the VMBus connection is marked as ready for the resume event
 	 *      (cf. check_ready_for_resume_event()).  The interrupt handler
 	 *      of the VMBus driver and vmbus_chan_sched() can not run before
 	 *      vmbus_bus_resume() has completed execution (cf. resume_noirq).
 	 */
-	smp_store_mb(
+	virt_store_mb(
 		vmbus_connection.channels[channel->offermsg.child_relid],
 		channel);
 }
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 439f99b8b5de..3248b48f37f6 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
+#include <linux/count_zeros.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memory.h>
 #include <linux/notifier.h>
@@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm)
 	struct dm_status status;
 	unsigned long now = jiffies;
 	unsigned long last_post = last_post_time;
+	unsigned long num_pages_avail, num_pages_committed;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
@@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm)
 	 * num_pages_onlined) as committed to the host, otherwise it can try
 	 * asking us to balloon them out.
 	 */
-	status.num_avail = si_mem_available();
-	status.num_committed = vm_memory_committed() +
+	num_pages_avail = si_mem_available();
+	num_pages_committed = vm_memory_committed() +
 		dm->num_pages_ballooned +
 		(dm->num_pages_added > dm->num_pages_onlined ?
 		 dm->num_pages_added - dm->num_pages_onlined : 0) +
 		compute_balloon_floor();
 
-	trace_balloon_status(status.num_avail, status.num_committed,
+	trace_balloon_status(num_pages_avail, num_pages_committed,
 			     vm_memory_committed(), dm->num_pages_ballooned,
 			     dm->num_pages_added, dm->num_pages_onlined);
+
+	/* Convert numbers of pages into numbers of HV_HYP_PAGEs. */
+	status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE;
+	status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE;
+
 	/*
 	 * If our transaction ID is no longer current, just don't
 	 * send the status. This can happen if we were interrupted
@@ -1653,6 +1660,38 @@ static void disable_page_reporting(void)
 	}
 }
 
+static int ballooning_enabled(void)
+{
+	/*
+	 * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE),
+	 * since currently it's unclear to us whether an unballoon request can
+	 * make sure all page ranges are guest page size aligned.
+	 */
+	if (PAGE_SIZE != HV_HYP_PAGE_SIZE) {
+		pr_info("Ballooning disabled because page size is not 4096 bytes\n");
+		return 0;
+	}
+
+	return 1;
+}
+
+static int hot_add_enabled(void)
+{
+	/*
+	 * Disable hot add on ARM64, because we currently rely on
+	 * memory_add_physaddr_to_nid() to get a node id of a hot add range,
+	 * however ARM64's memory_add_physaddr_to_nid() always return 0 and
+	 * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for
+	 * add_memory().
+	 */
+	if (IS_ENABLED(CONFIG_ARM64)) {
+		pr_info("Memory hot add disabled on ARM64\n");
+		return 0;
+	}
+
+	return 1;
+}
+
 static int balloon_connect_vsp(struct hv_device *dev)
 {
 	struct dm_version_request version_req;
@@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev)
 	 * currently still requires the bits to be set, so we have to add code
 	 * to fail the host's hot-add and balloon up/down requests, if any.
 	 */
-	cap_msg.caps.cap_bits.balloon = 1;
-	cap_msg.caps.cap_bits.hot_add = 1;
+	cap_msg.caps.cap_bits.balloon = ballooning_enabled();
+	cap_msg.caps.cap_bits.hot_add = hot_add_enabled();
 
 	/*
 	 * Specify our alignment requirements as it relates
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index c1dd21d0d7ef..ae68298c0dca 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -20,6 +20,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query)
 }
 EXPORT_SYMBOL_GPL(hv_query_ext_cap);
 
+void hv_setup_dma_ops(struct device *dev, bool coherent)
+{
+	/*
+	 * Hyper-V does not offer a vIOMMU in the guest
+	 * VM, so pass 0/NULL for the IOMMU settings
+	 */
+	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+}
+EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
+
 bool hv_is_hibernation_supported(void)
 {
 	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 71efacb90965..3d215d9dec43 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
 {
 	u32 priv_read_loc = rbi->priv_read_index;
-	u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+	u32 write_loc;
+
+	/*
+	 * The Hyper-V host writes the packet data, then uses
+	 * store_release() to update the write_index.  Use load_acquire()
+	 * here to prevent loads of the packet data from being re-ordered
+	 * before the read of the write_index and potentially getting
+	 * stale data.
+	 */
+	write_loc = virt_load_acquire(&rbi->ring_buffer->write_index);
 
 	if (write_loc >= priv_read_loc)
 		return write_loc - priv_read_loc;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 60ee8b329f9e..14de17087864 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 
 	/*
 	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
-	 * the notification here.
+	 * doing hv_kmsg_dump() with kmsg data later, don't do the notification
+	 * here.
 	 */
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
 	    && hyperv_report_reg()) {
@@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 
 	/*
 	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
-	 * the notification here.
+	 * doing hv_kmsg_dump() with kmsg data later, don't do the notification
+	 * here.
 	 */
 	if (hyperv_report_reg())
 		hyperv_report_panic(regs, val, true);
@@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device)
 }
 
 /*
+ * vmbus_dma_configure -- Configure DMA coherence for VMbus device
+ */
+static int vmbus_dma_configure(struct device *child_device)
+{
+	/*
+	 * On ARM64, propagate the DMA coherence setting from the top level
+	 * VMbus ACPI device to the child VMbus device being added here.
+	 * On x86/x64 coherence is assumed and these calls have no effect.
+	 */
+	hv_setup_dma_ops(child_device,
+		device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT);
+	return 0;
+}
+
+/*
  * vmbus_remove - Remove a vmbus device
  */
 static void vmbus_remove(struct device *child_device)
@@ -1040,6 +1055,7 @@ static struct bus_type  hv_bus = {
 	.remove =		vmbus_remove,
 	.probe =		vmbus_probe,
 	.uevent =		vmbus_uevent,
+	.dma_configure =	vmbus_dma_configure,
 	.dev_groups =		vmbus_dev_groups,
 	.drv_groups =		vmbus_drv_groups,
 	.bus_groups =		vmbus_bus_groups,
@@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void)
 	if (ret)
 		goto err_connect;
 
+	if (hv_is_isolation_supported())
+		sysctl_record_panic_msg = 0;
+
 	/*
 	 * Only register if the crash MSRs are available
 	 */
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		u64 hyperv_crash_ctl;
 		/*
-		 * Sysctl registration is not fatal, since by default
-		 * reporting is enabled.
+		 * Panic message recording (sysctl_record_panic_msg)
+		 * is enabled by default in non-isolated guests and
+		 * disabled by default in isolated guests; the panic
+		 * message recording won't be available in isolated
+		 * guests should the following registration fail.
 		 */
 		hv_ctl_table_hdr = register_sysctl_table(hv_root_table);
 		if (!hv_ctl_table_hdr)
@@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	child_device_obj->device.parent = &hv_acpi_dev->dev;
 	child_device_obj->device.release = vmbus_device_release;
 
+	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
+	child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
+	dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
+
 	/*
 	 * Register with the LDM. This will kick off the driver/device
 	 * binding...which will eventually call vmbus_match() and vmbus_probe()
@@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	}
 	hv_debug_add_dev_dir(child_device_obj);
 
-	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
-	child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
-	dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
 	return 0;
 
 err_kset_unregister:
@@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 	hv_acpi_dev = device;
 
+	/*
+	 * Older versions of Hyper-V for ARM64 fail to include the _CCA
+	 * method on the top level VMbus device in the DSDT. But devices
+	 * are hardware coherent in all current Hyper-V use cases, so fix
+	 * up the ACPI device to behave as if _CCA is present and indicates
+	 * hardware coherence.
+	 */
+	ACPI_COMPANION_SET(&device->dev, device);
+	if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) &&
+	    device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) {
+		pr_info("No ACPI _CCA found; assuming coherent device I/O\n");
+		device->flags.cca_seen = true;
+		device->flags.coherent_dma = true;
+	}
+
 	result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
 					vmbus_walk_resources, NULL);
 
@@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void)
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		kmsg_dump_unregister(&hv_kmsg_dumper);
 		unregister_die_notifier(&hyperv_die_block);
-		atomic_notifier_chain_unregister(&panic_notifier_list,
-						 &hyperv_panic_block);
 	}
 
+	/*
+	 * The panic notifier is always registered, hence we should
+	 * also unconditionally unregister it here as well.
+	 */
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &hyperv_panic_block);
+
 	free_page((unsigned long)hv_panic_page);
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 558b35aba610..d270a204324e 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev,
 	hbus->bridge->domain_nr = dom;
 #ifdef CONFIG_X86
 	hbus->sysdata.domain = dom;
+#elif defined(CONFIG_ARM64)
+	/*
+	 * Set the PCI bus parent to be the corresponding VMbus
+	 * device. Then the VMbus device will be assigned as the
+	 * ACPI companion in pcibios_root_bridge_prepare() and
+	 * pci_dma_configure() will propagate device coherence
+	 * information to devices created on the bus.
+	 */
+	hbus->sysdata.parent = hdev->device.parent;
 #endif
 
 	hbus->hdev = hdev;