Merge tag 'hyperv-next-signed-20210831' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - make Hyper-V code arch-agnostic (Michael Kelley)

 - fix sched_clock behaviour on Hyper-V (Ani Sinha)

 - fix a fault when Linux runs as the root partition on MSHV (Praveen
   Kumar)

 - fix VSS driver (Vitaly Kuznetsov)

 - cleanup (Sonia Sharma)

* tag 'hyperv-next-signed-20210831' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  hv_utils: Set the maximum packet size for VSS driver to the length of the receive buffer
  Drivers: hv: Enable Hyper-V code to be built on ARM64
  arm64: efi: Export screen_info
  arm64: hyperv: Initialize hypervisor on boot
  arm64: hyperv: Add panic handler
  arm64: hyperv: Add Hyper-V hypercall and register access utilities
  x86/hyperv: fix root partition faults when writing to VP assist page MSR
  hv: hyperv.h: Remove unused inline functions
  drivers: hv: Decouple Hyper-V clock/timer code from VMbus drivers
  x86/hyperv: add comment describing TSC_INVARIANT_CONTROL MSR setting bit 0
  Drivers: hv: Move Hyper-V misc functionality to arch-neutral code
  Drivers: hv: Add arch independent default functions for some Hyper-V handlers
  Drivers: hv: Make portions of Hyper-V init code be arch neutral
  x86/hyperv: fix for unwanted manipulation of sched_clock when TSC marked unstable
  asm-generic/hyperv: Add missing #include of nmi.h

4 files changed, 80 insertions, 136 deletions

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 6952e219cba3..708a2712a516 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -7,10 +7,10 @@
  * Author : K. Y. Srinivasan <kys@microsoft.com>
  */
 
-#include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/types.h>
 #include <linux/bitfield.h>
+#include <linux/io.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
@@ -39,71 +39,50 @@ EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 /* Storage to save the hypercall page temporarily for hibernation */
 static void *hv_hypercall_pg_saved;
 
-u32 *hv_vp_index;
-EXPORT_SYMBOL_GPL(hv_vp_index);
-
 struct hv_vp_assist_page **hv_vp_assist_page;
 EXPORT_SYMBOL_GPL(hv_vp_assist_page);
 
-void  __percpu **hyperv_pcpu_input_arg;
-EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
-
-void  __percpu **hyperv_pcpu_output_arg;
-EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
-
-u32 hv_max_vp_index;
-EXPORT_SYMBOL_GPL(hv_max_vp_index);
-
 static int hv_cpu_init(unsigned int cpu)
 {
-	u64 msr_vp_index;
+	union hv_vp_assist_msr_contents msr = { 0 };
 	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
-	void **input_arg;
-	struct page *pg;
-
-	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
-	pg = alloc_pages(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL, hv_root_partition ? 1 : 0);
-	if (unlikely(!pg))
-		return -ENOMEM;
-
-	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-	*input_arg = page_address(pg);
-	if (hv_root_partition) {
-		void **output_arg;
-
-		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
-		*output_arg = page_address(pg + 1);
-	}
-
-	msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX);
-
-	hv_vp_index[smp_processor_id()] = msr_vp_index;
+	int ret;
 
-	if (msr_vp_index > hv_max_vp_index)
-		hv_max_vp_index = msr_vp_index;
+	ret = hv_common_cpu_init(cpu);
+	if (ret)
+		return ret;
 
 	if (!hv_vp_assist_page)
 		return 0;
 
-	/*
-	 * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section
-	 * 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure
-	 * we always write the EOI MSR in hv_apic_eoi_write() *after* the
-	 * EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may
-	 * not be stopped in the case of CPU offlining and the VM will hang.
-	 */
 	if (!*hvp) {
-		*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
-	}
-
-	if (*hvp) {
-		u64 val;
-
-		val = vmalloc_to_pfn(*hvp);
-		val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
-			HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
-
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
+		if (hv_root_partition) {
+			/*
+			 * For root partition we get the hypervisor provided VP assist
+			 * page, instead of allocating a new page.
+			 */
+			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+			*hvp = memremap(msr.pfn <<
+					HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
+					PAGE_SIZE, MEMREMAP_WB);
+		} else {
+			/*
+			 * The VP assist page is an "overlay" page (see Hyper-V TLFS's
+			 * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
+			 * out to make sure we always write the EOI MSR in
+			 * hv_apic_eoi_write() *after* the EOI optimization is disabled
+			 * in hv_cpu_die(), otherwise a CPU may not be stopped in the
+			 * case of CPU offlining and the VM will hang.
+			 */
+			*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+			if (*hvp)
+				msr.pfn = vmalloc_to_pfn(*hvp);
+		}
+		WARN_ON(!(*hvp));
+		if (*hvp) {
+			msr.enable = 1;
+			wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		}
 	}
 
 	return 0;
@@ -198,29 +177,26 @@ static int hv_cpu_die(unsigned int cpu)
 {
 	struct hv_reenlightenment_control re_ctrl;
 	unsigned int new_cpu;
-	unsigned long flags;
-	void **input_arg;
-	void *pg;
 
-	local_irq_save(flags);
-	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-	pg = *input_arg;
-	*input_arg = NULL;
-
-	if (hv_root_partition) {
-		void **output_arg;
-
-		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
-		*output_arg = NULL;
+	hv_common_cpu_die(cpu);
+
+	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
+		union hv_vp_assist_msr_contents msr = { 0 };
+		if (hv_root_partition) {
+			/*
+			 * For root partition the VP assist page is mapped to
+			 * hypervisor provided page, and thus we unmap the
+			 * page here and nullify it, so that in future we have
+			 * correct page address mapped in hv_cpu_init.
+			 */
+			memunmap(hv_vp_assist_page[cpu]);
+			hv_vp_assist_page[cpu] = NULL;
+			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+			msr.enable = 0;
+		}
+		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 	}
 
-	local_irq_restore(flags);
-
-	free_pages((unsigned long)pg, hv_root_partition ? 1 : 0);
-
-	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
-
 	if (hv_reenlightenment_cb == NULL)
 		return 0;
 
@@ -368,7 +344,7 @@ void __init hyperv_init(void)
 {
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
-	int cpuhp, i;
+	int cpuhp;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
@@ -380,36 +356,14 @@ void __init hyperv_init(void)
 	if ((ms_hyperv.features & required_msrs) != required_msrs)
 		return;
 
-	/*
-	 * Allocate the per-CPU state for the hypercall input arg.
-	 * If this allocation fails, we will not be able to setup
-	 * (per-CPU) hypercall input page and thus this failure is
-	 * fatal on Hyper-V.
-	 */
-	hyperv_pcpu_input_arg = alloc_percpu(void  *);
-
-	BUG_ON(hyperv_pcpu_input_arg == NULL);
-
-	/* Allocate the per-CPU state for output arg for root */
-	if (hv_root_partition) {
-		hyperv_pcpu_output_arg = alloc_percpu(void *);
-		BUG_ON(hyperv_pcpu_output_arg == NULL);
-	}
-
-	/* Allocate percpu VP index */
-	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
-				    GFP_KERNEL);
-	if (!hv_vp_index)
+	if (hv_common_init())
 		return;
 
-	for (i = 0; i < num_possible_cpus(); i++)
-		hv_vp_index[i] = VP_INVAL;
-
 	hv_vp_assist_page = kcalloc(num_possible_cpus(),
 				    sizeof(*hv_vp_assist_page), GFP_KERNEL);
 	if (!hv_vp_assist_page) {
 		ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
-		goto free_vp_index;
+		goto common_free;
 	}
 
 	cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
@@ -507,9 +461,8 @@ remove_cpuhp_state:
 free_vp_assist_page:
 	kfree(hv_vp_assist_page);
 	hv_vp_assist_page = NULL;
-free_vp_index:
-	kfree(hv_vp_index);
-	hv_vp_index = NULL;
+common_free:
+	hv_common_free();
 }
 
 /*
@@ -539,7 +492,6 @@ void hyperv_cleanup(void)
 	hypercall_msr.as_uint64 = 0;
 	wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
 }
-EXPORT_SYMBOL_GPL(hyperv_cleanup);
 
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
 {
@@ -595,12 +547,6 @@ bool hv_is_hyperv_initialized(void)
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
 
-bool hv_is_hibernation_supported(void)
-{
-	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
-}
-EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
-
 enum hv_isolation_type hv_get_isolation_type(void)
 {
 	if (!(ms_hyperv.priv_high & HV_ISOLATION))
@@ -613,4 +559,3 @@ bool hv_is_isolation_supported(void)
 {
 	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
 }
-EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index f1366ce609e3..2322d6bd5883 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -288,6 +288,15 @@ union hv_x64_msr_hypercall_contents {
 	} __packed;
 };
 
+union hv_vp_assist_msr_contents {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:11;
+		u64 pfn:52;
+	} __packed;
+};
+
 struct hv_reenlightenment_control {
 	__u64 vector:8;
 	__u64 reserved1:8;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 67ff0d637e55..adccbc209169 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -36,8 +36,6 @@ void hyperv_vector_handler(struct pt_regs *regs);
 extern int hyperv_init_cpuhp;
 
 extern void *hv_hypercall_pg;
-extern void  __percpu  **hyperv_pcpu_input_arg;
-extern void  __percpu  **hyperv_pcpu_output_arg;
 
 extern u64 hv_current_partition_id;
 
@@ -170,8 +168,6 @@ int hyperv_fill_flush_guest_mapping_list(
 		struct hv_guest_mapping_flush_list *flush,
 		u64 start_gfn, u64 end_gfn);
 
-extern bool hv_root_partition;
-
 #ifdef CONFIG_X86_64
 void hv_apic_init(void);
 void __init hv_init_spinlocks(void);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c890d67a64ad..e095c28d27ae 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,7 +17,6 @@
 #include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/i8253.h>
-#include <linux/panic_notifier.h>
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
@@ -36,10 +35,7 @@
 
 /* Is Linux running as the root partition? */
 bool hv_root_partition;
-EXPORT_SYMBOL_GPL(hv_root_partition);
-
 struct ms_hyperv_info ms_hyperv;
-EXPORT_SYMBOL_GPL(ms_hyperv);
 
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
@@ -65,14 +61,12 @@ void hv_setup_vmbus_handler(void (*handler)(void))
 {
 	vmbus_handler = handler;
 }
-EXPORT_SYMBOL_GPL(hv_setup_vmbus_handler);
 
 void hv_remove_vmbus_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	vmbus_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler);
 
 /*
  * Routines to do per-architecture handling of stimer0
@@ -107,25 +101,21 @@ void hv_setup_kexec_handler(void (*handler)(void))
 {
 	hv_kexec_handler = handler;
 }
-EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);
 
 void hv_remove_kexec_handler(void)
 {
 	hv_kexec_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);
 
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs))
 {
 	hv_crash_handler = handler;
 }
-EXPORT_SYMBOL_GPL(hv_setup_crash_handler);
 
 void hv_remove_crash_handler(void)
 {
 	hv_crash_handler = NULL;
 }
-EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
 
 #ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
@@ -335,16 +325,6 @@ static void __init ms_hyperv_init_platform(void)
 			ms_hyperv.nested_features);
 	}
 
-	/*
-	 * Hyper-V expects to get crash register data or kmsg when
-	 * crash enlightment is available and system crashes. Set
-	 * crash_kexec_post_notifiers to be true to make sure that
-	 * calling crash enlightment interface before running kdump
-	 * kernel.
-	 */
-	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
-		crash_kexec_post_notifiers = true;
-
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
@@ -373,10 +353,17 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
+		/*
+		 * Writing to synthetic MSR 0x40000118 updates/changes the
+		 * guest visible CPUIDs. Setting bit 0 of this MSR  enables
+		 * guests to report invariant TSC feature through CPUID
+		 * instruction, CPUID 0x800000007/EDX, bit 8. See code in
+		 * early_init_intel() where this bit is examined. The
+		 * setting of this MSR bit should happen before init_intel()
+		 * is called.
+		 */
 		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-	} else {
-		mark_tsc_unstable("running on Hyper-V");
 	}
 
 	/*
@@ -437,6 +424,13 @@ static void __init ms_hyperv_init_platform(void)
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
 #endif
+	/*
+	 * TSC should be marked as unstable only after Hyper-V
+	 * clocksource has been initialized. This ensures that the
+	 * stability of the sched_clock is not altered.
+	 */
+	if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+		mark_tsc_unstable("running on Hyper-V");
 }
 
 static bool __init ms_hyperv_x2apic_available(void)