Merge tag 'hyperv-next-signed-20221208' of...

Merge tag 'hyperv-next-signed-20221208' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Drop unregister syscore from hyperv_cleanup to avoid hang (Gaurav
   Kohli)

 - Clean up panic path for Hyper-V framebuffer (Guilherme G. Piccoli)

 - Allow IRQ remapping to work without x2apic (Nuno Das Neves)

 - Fix comments (Olaf Hering)

 - Expand hv_vp_assist_page definition (Saurabh Sengar)

 - Improvement to page reporting (Shradha Gupta)

 - Make sure TSC clocksource works when Linux runs as the root partition
   (Stanislav Kinsburskiy)

* tag 'hyperv-next-signed-20221208' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  x86/hyperv: Remove unregister syscore call from Hyper-V cleanup
  iommu/hyper-v: Allow hyperv irq remapping without x2apic
  clocksource: hyper-v: Add TSC page support for root partition
  clocksource: hyper-v: Use TSC PFN getter to map vvar page
  clocksource: hyper-v: Introduce TSC PFN getter
  clocksource: hyper-v: Introduce a pointer to TSC page
  x86/hyperv: Expand definition of struct hv_vp_assist_page
  PCI: hv: update comment in x86 specific hv_arch_irq_unmask
  hv: fix comment typo in vmbus_channel/low_latency
  drivers: hv, hyperv_fb: Untangle and refactor Hyper-V panic notifiers
  video: hyperv_fb: Avoid taking busy spinlock on panic path
  hv_balloon: Add support for configurable order free page reporting
  mm/page_reporting: Add checks for page_reporting_order param

arch/x86/entry/vdso/vma.c

@@ -210,11 +210,10 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 					pgprot_decrypted(vma->vm_page_prot));
 		}
 	} else if (sym_offset == image->sym_hvclock_page) {
-		struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
+		pfn = hv_get_tsc_pfn();
 
-		if (tsc_pg && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
-			return vmf_insert_pfn(vma, vmf->address,
-					virt_to_phys(tsc_pg) >> PAGE_SHIFT);
+		if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
+			return vmf_insert_pfn(vma, vmf->address, pfn);
 	} else if (sym_offset == image->sym_timens_page) {
 		struct page *timens_page = find_timens_vvar_page(vma);
 

arch/x86/hyperv/hv_init.c

@@ -462,6 +462,8 @@ void __init hyperv_init(void)
 		BUG_ON(!src);
 		memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE);
 		memunmap(src);
+
+		hv_remap_tsc_clocksource();
 	} else {
 		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -535,8 +537,6 @@ void hyperv_cleanup(void)
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	union hv_reference_tsc_msr tsc_msr;
 
-	unregister_syscore_ops(&hv_syscore_ops);
-
 	/* Reset our OS id */
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);

arch/x86/include/asm/hyperv-tlfs.h

@@ -374,11 +374,20 @@ struct hv_nested_enlightenments_control {
 struct hv_vp_assist_page {
 	__u32 apic_assist;
 	__u32 reserved1;
-	__u64 vtl_control[3];
+	__u32 vtl_entry_reason;
+	__u32 vtl_reserved;
+	__u64 vtl_ret_x64rax;
+	__u64 vtl_ret_x64rcx;
 	struct hv_nested_enlightenments_control nested_control;
 	__u8 enlighten_vmentry;
 	__u8 reserved2[7];
 	__u64 current_nested_vmcs;
+	__u8 synthetic_time_unhalted_timer_expired;
+	__u8 reserved3[7];
+	__u8 virtualization_fault_information[40];
+	__u8 reserved4[8];
+	__u8 intercept_message[256];
+	__u8 vtl_ret_actions[256];
 } __packed;
 
 struct hv_enlightened_vmcs {

arch/x86/kernel/cpu/mshyperv.c

@@ -475,6 +475,12 @@ static bool __init ms_hyperv_x2apic_available(void)
  * (logically) generates MSIs directly to the system APIC irq domain.
  * There is no HPET, and PCI MSI/MSI-X interrupts are remapped by the
  * pci-hyperv host bridge.
+ *
+ * Note: for a Hyper-V root partition, this will always return false.
+ * The hypervisor doesn't expose these HYPERV_CPUID_VIRT_STACK_* cpuids by
+ * default, they are implemented as intercepts by the Windows Hyper-V stack.
+ * Even a nested root partition (L2 root) will not get them because the
+ * nested (L1) hypervisor filters them out.
  */
 static bool __init ms_hyperv_msi_ext_dest_id(void)
 {

drivers/clocksource/hyperv_timer.c

@@ -367,9 +367,18 @@ static union {
 	u8 reserved[PAGE_SIZE];
 } tsc_pg __aligned(PAGE_SIZE);
 
+static struct ms_hyperv_tsc_page *tsc_page = &tsc_pg.page;
+static unsigned long tsc_pfn;
+
+unsigned long hv_get_tsc_pfn(void)
+{
+	return tsc_pfn;
+}
+EXPORT_SYMBOL_GPL(hv_get_tsc_pfn);
+
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
-	return &tsc_pg.page;
+	return tsc_page;
 }
 EXPORT_SYMBOL_GPL(hv_get_tsc_page);
 
@@ -407,13 +416,12 @@ static void suspend_hv_clock_tsc(struct clocksource *arg)
 
 static void resume_hv_clock_tsc(struct clocksource *arg)
 {
-	phys_addr_t phys_addr = virt_to_phys(&tsc_pg);
 	union hv_reference_tsc_msr tsc_msr;
 
 	/* Re-enable the TSC page */
 	tsc_msr.as_uint64 = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr.enable = 1;
-	tsc_msr.pfn = HVPFN_DOWN(phys_addr);
+	tsc_msr.pfn = tsc_pfn;
 	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr.as_uint64);
 }
 
@@ -497,14 +505,10 @@ static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
 static bool __init hv_init_tsc_clocksource(void)
 {
 	union hv_reference_tsc_msr tsc_msr;
-	phys_addr_t	phys_addr;
 
 	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
 		return false;
 
-	if (hv_root_partition)
-		return false;
-
 	/*
 	 * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
 	 * handles frequency and offset changes due to live migration,
@@ -522,18 +526,30 @@ static bool __init hv_init_tsc_clocksource(void)
 	}
 
 	hv_read_reference_counter = read_hv_clock_tsc;
-	phys_addr = virt_to_phys(hv_get_tsc_page());
 
 	/*
-	 * The Hyper-V TLFS specifies to preserve the value of reserved
-	 * bits in registers. So read the existing value, preserve the
-	 * low order 12 bits, and add in the guest physical address
-	 * (which already has at least the low 12 bits set to zero since
-	 * it is page aligned). Also set the "enable" bit, which is bit 0.
+	 * TSC page mapping works differently in root compared to guest.
+	 * - In guest partition the guest PFN has to be passed to the
+	 *   hypervisor.
+	 * - In root partition it's other way around: it has to map the PFN
+	 *   provided by the hypervisor.
+	 *   But it can't be mapped right here as it's too early and MMU isn't
+	 *   ready yet. So, we only set the enable bit here and will remap the
+	 *   page later in hv_remap_tsc_clocksource().
+	 *
+	 * It worth mentioning, that TSC clocksource read function
+	 * (read_hv_clock_tsc) has a MSR-based fallback mechanism, used when
+	 * TSC page is zeroed (which is the case until the PFN is remapped) and
+	 * thus TSC clocksource will work even without the real TSC page
+	 * mapped.
 	 */
 	tsc_msr.as_uint64 = hv_get_register(HV_REGISTER_REFERENCE_TSC);
+	if (hv_root_partition)
+		tsc_pfn = tsc_msr.pfn;
+	else
+		tsc_pfn = HVPFN_DOWN(virt_to_phys(tsc_page));
 	tsc_msr.enable = 1;
-	tsc_msr.pfn = HVPFN_DOWN(phys_addr);
+	tsc_msr.pfn = tsc_pfn;
 	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr.as_uint64);
 
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
@@ -566,3 +582,20 @@ void __init hv_init_clocksource(void)
 	hv_sched_clock_offset = hv_read_reference_counter();
 	hv_setup_sched_clock(read_hv_sched_clock_msr);
 }
+
+void __init hv_remap_tsc_clocksource(void)
+{
+	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+		return;
+
+	if (!hv_root_partition) {
+		WARN(1, "%s: attempt to remap TSC page in guest partition\n",
+		     __func__);
+		return;
+	}
+
+	tsc_page = memremap(tsc_pfn << HV_HYP_PAGE_SHIFT, sizeof(tsc_pg),
+			    MEMREMAP_WB);
+	if (!tsc_page)
+		pr_err("Failed to remap Hyper-V TSC page.\n");
+}

drivers/hv/hv_balloon.c

@@ -469,12 +469,16 @@ static bool do_hot_add;
  * the specified number of seconds.
  */
 static uint pressure_report_delay = 45;
+extern unsigned int page_reporting_order;
+#define HV_MAX_FAILURES	2
 
 /*
  * The last time we posted a pressure report to host.
  */
 static unsigned long last_post_time;
 
+static int hv_hypercall_multi_failure;
+
 module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
 
@@ -579,6 +583,10 @@ static struct hv_dynmem_device dm_device;
 
 static void post_status(struct hv_dynmem_device *dm);
 
+static void enable_page_reporting(void);
+
+static void disable_page_reporting(void);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static inline bool has_pfn_is_backed(struct hv_hotadd_state *has,
 				     unsigned long pfn)
@@ -1418,6 +1426,18 @@ static int dm_thread_func(void *dm_dev)
 		 */
 		reinit_completion(&dm_device.config_event);
 		post_status(dm);
+		/*
+		 * disable free page reporting if multiple hypercall
+		 * failure flag set. It is not done in the page_reporting
+		 * callback context as that causes a deadlock between
+		 * page_reporting_process() and page_reporting_unregister()
+		 */
+		if (hv_hypercall_multi_failure >= HV_MAX_FAILURES) {
+			pr_err("Multiple failures in cold memory discard hypercall, disabling page reporting\n");
+			disable_page_reporting();
+			/* Reset the flag after disabling reporting */
+			hv_hypercall_multi_failure = 0;
+		}
 	}
 
 	return 0;
@@ -1593,20 +1613,20 @@ static void balloon_onchannelcallback(void *context)
 
 }
 
-/* Hyper-V only supports reporting 2MB pages or higher */
-#define HV_MIN_PAGE_REPORTING_ORDER	9
-#define HV_MIN_PAGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << HV_MIN_PAGE_REPORTING_ORDER)
+#define HV_LARGE_REPORTING_ORDER	9
+#define HV_LARGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << \
+		HV_LARGE_REPORTING_ORDER)
 static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 		    struct scatterlist *sgl, unsigned int nents)
 {
 	unsigned long flags;
 	struct hv_memory_hint *hint;
-	int i;
+	int i, order;
 	u64 status;
 	struct scatterlist *sg;
 
 	WARN_ON_ONCE(nents > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
-	WARN_ON_ONCE(sgl->length < HV_MIN_PAGE_REPORTING_LEN);
+	WARN_ON_ONCE(sgl->length < (HV_HYP_PAGE_SIZE << page_reporting_order));
 	local_irq_save(flags);
 	hint = *(struct hv_memory_hint **)this_cpu_ptr(hyperv_pcpu_input_arg);
 	if (!hint) {
@@ -1621,21 +1641,53 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 
 		range = &hint->ranges[i];
 		range->address_space = 0;
-		/* page reporting only reports 2MB pages or higher */
-		range->page.largepage = 1;
-		range->page.additional_pages =
-			(sg->length / HV_MIN_PAGE_REPORTING_LEN) - 1;
-		range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB;
-		range->base_large_pfn =
-			page_to_hvpfn(sg_page(sg)) >> HV_MIN_PAGE_REPORTING_ORDER;
+		order = get_order(sg->length);
+		/*
+		 * Hyper-V expects the additional_pages field in the units
+		 * of one of these 3 sizes, 4Kbytes, 2Mbytes or 1Gbytes.
+		 * This is dictated by the values of the fields page.largesize
+		 * and page_size.
+		 * This code however, only uses 4Kbytes and 2Mbytes units
+		 * and not 1Gbytes unit.
+		 */
+
+		/* page reporting for pages 2MB or higher */
+		if (order >= HV_LARGE_REPORTING_ORDER ) {
+			range->page.largepage = 1;
+			range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB;
+			range->base_large_pfn = page_to_hvpfn(
+					sg_page(sg)) >> HV_LARGE_REPORTING_ORDER;
+			range->page.additional_pages =
+				(sg->length / HV_LARGE_REPORTING_LEN) - 1;
+		} else {
+			/* Page reporting for pages below 2MB */
+			range->page.basepfn = page_to_hvpfn(sg_page(sg));
+			range->page.largepage = false;
+			range->page.additional_pages =
+				(sg->length / HV_HYP_PAGE_SIZE) - 1;
+		}
+
 	}
 
 	status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0,
 				     hint, NULL);
 	local_irq_restore(flags);
-	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+	if (!hv_result_success(status)) {
+
 		pr_err("Cold memory discard hypercall failed with status %llx\n",
-			status);
+				status);
+		if (hv_hypercall_multi_failure > 0)
+			hv_hypercall_multi_failure++;
+
+		if (hv_result(status) == HV_STATUS_INVALID_PARAMETER) {
+			pr_err("Underlying Hyper-V does not support order less than 9. Hypercall failed\n");
+			pr_err("Defaulting to page_reporting_order %d\n",
+					pageblock_order);
+			page_reporting_order = pageblock_order;
+			hv_hypercall_multi_failure++;
+			return -EINVAL;
+		}
+
 		return -EINVAL;
 	}
 
@@ -1646,12 +1698,6 @@ static void enable_page_reporting(void)
 {
 	int ret;
 
-	/* Essentially, validating 'PAGE_REPORTING_MIN_ORDER' is big enough. */
-	if (pageblock_order < HV_MIN_PAGE_REPORTING_ORDER) {
-		pr_debug("Cold memory discard is only supported on 2MB pages and above\n");
-		return;
-	}
-
 	if (!hv_query_ext_cap(HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT)) {
 		pr_debug("Cold memory discard hint not supported by Hyper-V\n");
 		return;
@@ -1659,12 +1705,18 @@ static void enable_page_reporting(void)
 
 	BUILD_BUG_ON(PAGE_REPORTING_CAPACITY > HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES);
 	dm_device.pr_dev_info.report = hv_free_page_report;
+	/*
+	 * We let the page_reporting_order parameter decide the order
+	 * in the page_reporting code
+	 */
+	dm_device.pr_dev_info.order = 0;
 	ret = page_reporting_register(&dm_device.pr_dev_info);
 	if (ret < 0) {
 		dm_device.pr_dev_info.report = NULL;
 		pr_err("Failed to enable cold memory discard: %d\n", ret);
 	} else {
-		pr_info("Cold memory discard hint enabled\n");
+		pr_info("Cold memory discard hint enabled with order %d\n",
+				page_reporting_order);
 	}
 }
 

drivers/hv/ring_buffer.c

@@ -280,6 +280,19 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 	ring_info->pkt_buffer_size = 0;
 }
 
+/*
+ * Check if the ring buffer spinlock is available to take or not; used on
+ * atomic contexts, like panic path (see the Hyper-V framebuffer driver).
+ */
+
+bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rinfo = &channel->outbound;
+
+	return spin_is_locked(&rinfo->ring_lock);
+}
+EXPORT_SYMBOL_GPL(hv_ringbuffer_spinlock_busy);
+
 /* Write to the ring buffer. */
 int hv_ringbuffer_write(struct vmbus_channel *channel,
 			const struct kvec *kv_list, u32 kv_count,

drivers/hv/vmbus_drv.c

@@ -25,7 +25,6 @@
 #include <linux/sched/task_stack.h>
 
 #include <linux/delay.h>
-#include <linux/notifier.h>
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/screen_info.h>
@@ -68,53 +67,74 @@ static int hyperv_report_reg(void)
 	return !sysctl_record_panic_msg || !hv_panic_page;
 }
 
-static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
+/*
+ * The panic notifier below is responsible solely for unloading the
+ * vmbus connection, which is necessary in a panic event.
+ *
+ * Notice an intrincate relation of this notifier with Hyper-V
+ * framebuffer panic notifier exists - we need vmbus connection alive
+ * there in order to succeed, so we need to order both with each other
+ * [see hvfb_on_panic()] - this is done using notifiers' priorities.
+ */
+static int hv_panic_vmbus_unload(struct notifier_block *nb, unsigned long val,
 			      void *args)
 {
-	struct pt_regs *regs;
-
 	vmbus_initiate_unload(true);
-
-	/*
-	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * 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()) {
-		regs = current_pt_regs();
-		hyperv_report_panic(regs, val, false);
-	}
 	return NOTIFY_DONE;
 }
+static struct notifier_block hyperv_panic_vmbus_unload_block = {
+	.notifier_call	= hv_panic_vmbus_unload,
+	.priority	= INT_MIN + 1, /* almost the latest one to execute */
+};
+
+static int hv_die_panic_notify_crash(struct notifier_block *self,
+				     unsigned long val, void *args);
+
+static struct notifier_block hyperv_die_report_block = {
+	.notifier_call = hv_die_panic_notify_crash,
+};
+static struct notifier_block hyperv_panic_report_block = {
+	.notifier_call = hv_die_panic_notify_crash,
+};
 
-static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
-			    void *args)
+/*
+ * The following callback works both as die and panic notifier; its
+ * goal is to provide panic information to the hypervisor unless the
+ * kmsg dumper is used [see hv_kmsg_dump()], which provides more
+ * information but isn't always available.
+ *
+ * Notice that both the panic/die report notifiers are registered only
+ * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set.
+ */
+static int hv_die_panic_notify_crash(struct notifier_block *self,
+				     unsigned long val, void *args)
 {
-	struct die_args *die = args;
-	struct pt_regs *regs = die->regs;
+	struct pt_regs *regs;
+	bool is_die;
 
-	/* Don't notify Hyper-V if the die event is other than oops */
-	if (val != DIE_OOPS)
-		return NOTIFY_DONE;
+	/* Don't notify Hyper-V unless we have a die oops event or panic. */
+	if (self == &hyperv_panic_report_block) {
+		is_die = false;
+		regs = current_pt_regs();
+	} else { /* die event */
+		if (val != DIE_OOPS)
+			return NOTIFY_DONE;
+
+		is_die = true;
+		regs = ((struct die_args *)args)->regs;
+	}
 
 	/*
-	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * doing hv_kmsg_dump() with kmsg data later, don't do the notification
-	 * here.
+	 * Hyper-V should be notified only once about a panic/die. If we will
+	 * be calling hv_kmsg_dump() later with kmsg data, don't do the
+	 * notification here.
 	 */
 	if (hyperv_report_reg())
-		hyperv_report_panic(regs, val, true);
+		hyperv_report_panic(regs, val, is_die);
+
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block hyperv_die_block = {
-	.notifier_call = hyperv_die_event,
-};
-static struct notifier_block hyperv_panic_block = {
-	.notifier_call = hyperv_panic_event,
-};
-
 static const char *fb_mmio_name = "fb_range";
 static struct resource *fb_mmio;
 static struct resource *hyperv_mmio;
@@ -1538,16 +1558,17 @@ static int vmbus_bus_init(void)
 		if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG)
 			hv_kmsg_dump_register();
 
-		register_die_notifier(&hyperv_die_block);
+		register_die_notifier(&hyperv_die_report_block);
+		atomic_notifier_chain_register(&panic_notifier_list,
+						&hyperv_panic_report_block);
 	}
 
 	/*
-	 * Always register the panic notifier because we need to unload
-	 * the VMbus channel connection to prevent any VMbus
-	 * activity after the VM panics.
+	 * Always register the vmbus unload panic notifier because we
+	 * need to shut the VMbus channel connection on panic.
 	 */
 	atomic_notifier_chain_register(&panic_notifier_list,
-			       &hyperv_panic_block);
+			       &hyperv_panic_vmbus_unload_block);
 
 	vmbus_request_offers();
 
@@ -2800,15 +2821,17 @@ 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);
+		unregister_die_notifier(&hyperv_die_report_block);
+		atomic_notifier_chain_unregister(&panic_notifier_list,
+						&hyperv_panic_report_block);
 	}
 
 	/*
-	 * The panic notifier is always registered, hence we should
+	 * The vmbus 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);
+					&hyperv_panic_vmbus_unload_block);
 
 	free_page((unsigned long)hv_panic_page);
 	unregister_sysctl_table(hv_ctl_table_hdr);

drivers/iommu/Kconfig

@@ -474,13 +474,13 @@ config QCOM_IOMMU
 	  Support for IOMMU on certain Qualcomm SoCs.
 
 config HYPERV_IOMMU
-	bool "Hyper-V x2APIC IRQ Handling"
+	bool "Hyper-V IRQ Handling"
 	depends on HYPERV && X86
 	select IOMMU_API
 	default HYPERV
 	help
-	  Stub IOMMU driver to handle IRQs as to allow Hyper-V Linux
-	  guests to run with x2APIC mode enabled.
+	  Stub IOMMU driver to handle IRQs to support Hyper-V Linux
+	  guest and root partitions.
 
 config VIRTIO_IOMMU
 	tristate "Virtio IOMMU driver"

drivers/iommu/hyperv-iommu.c

@@ -122,9 +122,12 @@ static int __init hyperv_prepare_irq_remapping(void)
 	const char *name;
 	const struct irq_domain_ops *ops;
 
+	/*
+	 * For a Hyper-V root partition, ms_hyperv_msi_ext_dest_id()
+	 * will always return false.
+	 */
 	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) ||
-	    x86_init.hyper.msi_ext_dest_id() ||
-	    !x2apic_supported())
+	    x86_init.hyper.msi_ext_dest_id())
 		return -ENODEV;
 
 	if (hv_root_partition) {
@@ -170,7 +173,9 @@ static int __init hyperv_prepare_irq_remapping(void)
 
 static int __init hyperv_enable_irq_remapping(void)
 {
-	return IRQ_REMAP_X2APIC_MODE;
+	if (x2apic_supported())
+		return IRQ_REMAP_X2APIC_MODE;
+	return IRQ_REMAP_XAPIC_MODE;
 }
 
 struct irq_remap_ops hyperv_irq_remap_ops = {

drivers/pci/controller/pci-hyperv.c

@@ -735,9 +735,9 @@ static void hv_arch_irq_unmask(struct irq_data *data)
 	 * during hibernation does not matter (at this time all the devices
 	 * have been frozen). Note: the correct affinity info is still updated
 	 * into the irqdata data structure in migrate_one_irq() ->
-	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
-	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
-	 * the interrupt with the correct affinity.
+	 * irq_do_set_affinity(), so later when the VM resumes,
+	 * hv_pci_restore_msi_state() is able to correctly restore the
+	 * interrupt with the correct affinity.
 	 */
 	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
 		dev_err(&hbus->hdev->device,

drivers/video/fbdev/hyperv_fb.c

@@ -780,12 +780,18 @@ static void hvfb_ondemand_refresh_throttle(struct hvfb_par *par,
 static int hvfb_on_panic(struct notifier_block *nb,
 			 unsigned long e, void *p)
 {
+	struct hv_device *hdev;
 	struct hvfb_par *par;
 	struct fb_info *info;
 
 	par = container_of(nb, struct hvfb_par, hvfb_panic_nb);
-	par->synchronous_fb = true;
 	info = par->info;
+	hdev = device_to_hv_device(info->device);
+
+	if (hv_ringbuffer_spinlock_busy(hdev->channel))
+		return NOTIFY_DONE;
+
+	par->synchronous_fb = true;
 	if (par->need_docopy)
 		hvfb_docopy(par, 0, dio_fb_size);
 	synthvid_update(info, 0, 0, INT_MAX, INT_MAX);
@@ -1208,7 +1214,15 @@ static int hvfb_probe(struct hv_device *hdev,
 	par->fb_ready = true;
 
 	par->synchronous_fb = false;
+
+	/*
+	 * We need to be sure this panic notifier runs _before_ the
+	 * vmbus disconnect, so order it by priority. It must execute
+	 * before the function hv_panic_vmbus_unload() [drivers/hv/vmbus_drv.c],
+	 * which is almost at the end of list, with priority = INT_MIN + 1.
+	 */
 	par->hvfb_panic_nb.notifier_call = hvfb_on_panic;
+	par->hvfb_panic_nb.priority = INT_MIN + 10,
 	atomic_notifier_chain_register(&panic_notifier_list,
 				       &par->hvfb_panic_nb);
 

include/clocksource/hyperv_timer.h

@@ -31,7 +31,9 @@ extern void hv_stimer_global_cleanup(void);
 extern void hv_stimer0_isr(void);
 
 extern void hv_init_clocksource(void);
+extern void hv_remap_tsc_clocksource(void);
 
+extern unsigned long hv_get_tsc_pfn(void);
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 
 static inline notrace u64
@@ -90,6 +92,11 @@ hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 }
 
 #else /* CONFIG_HYPERV_TIMER */
+static inline unsigned long hv_get_tsc_pfn(void)
+{
+	return 0;
+}
+
 static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return NULL;

include/linux/hyperv.h

@@ -969,7 +969,7 @@ struct vmbus_channel {
 	 * mechanism improves throughput by:
 	 *
 	 * A) Making the host more efficient - each time it wakes up,
-	 *    potentially it will process morev number of packets. The
+	 *    potentially it will process more number of packets. The
 	 *    monitor latency allows a batch to build up.
 	 * B) By deferring the hypercall to signal, we will also minimize
 	 *    the interrupts.
@@ -1341,6 +1341,8 @@ struct hv_ring_buffer_debug_info {
 int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
 				struct hv_ring_buffer_debug_info *debug_info);
 
+bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel);
+
 /* Vmbus interface */
 #define vmbus_driver_register(driver)	\
 	__vmbus_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)

mm/page_reporting.c

@@ -11,10 +11,42 @@
 #include "page_reporting.h"
 #include "internal.h"
 
-unsigned int page_reporting_order = MAX_ORDER;
-module_param(page_reporting_order, uint, 0644);
+/* Initialize to an unsupported value */
+unsigned int page_reporting_order = -1;
+
+static int page_order_update_notify(const char *val, const struct kernel_param *kp)
+{
+	/*
+	 * If param is set beyond this limit, order is set to default
+	 * pageblock_order value
+	 */
+	return  param_set_uint_minmax(val, kp, 0, MAX_ORDER-1);
+}
+
+static const struct kernel_param_ops page_reporting_param_ops = {
+	.set = &page_order_update_notify,
+	/*
+	 * For the get op, use param_get_int instead of param_get_uint.
+	 * This is to make sure that when unset the initialized value of
+	 * -1 is shown correctly
+	 */
+	.get = &param_get_int,
+};
+
+module_param_cb(page_reporting_order, &page_reporting_param_ops,
+			&page_reporting_order, 0644);
 MODULE_PARM_DESC(page_reporting_order, "Set page reporting order");
 
+/*
+ * This symbol is also a kernel parameter. Export the page_reporting_order
+ * symbol so that other drivers can access it to control order values without
+ * having to introduce another configurable parameter. Only one driver can
+ * register with the page_reporting driver for the service, so we have just
+ * one control parameter for the use case(which can be accessed in both
+ * drivers)
+ */
+EXPORT_SYMBOL_GPL(page_reporting_order);
+
 #define PAGE_REPORTING_DELAY	(2 * HZ)
 static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly;
 
@@ -330,10 +362,18 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
 	}
 
 	/*
-	 * Update the page reporting order if it's specified by driver.
-	 * Otherwise, it falls back to @pageblock_order.
+	 * If the page_reporting_order value is not set, we check if
+	 * an order is provided from the driver that is performing the
+	 * registration. If that is not provided either, we default to
+	 * pageblock_order.
 	 */
-	page_reporting_order = prdev->order ? : pageblock_order;
+
+	if (page_reporting_order == -1) {
+		if (prdev->order > 0 && prdev->order <= MAX_ORDER)
+			page_reporting_order = prdev->order;
+		else
+			page_reporting_order = pageblock_order;
+	}
 
 	/* initialize state and work structures */
 	atomic_set(&prdev->state, PAGE_REPORTING_IDLE);