From ba3f5839fbeb3f9e65070d90aa4e66008bbea80f Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 11 Jul 2021 19:50:04 -0700 Subject: [PATCH 01/15] asm-generic/hyperv: Add missing #include of nmi.h The recent move of hv_do_rep_hypercall() to this file adds a reference to touch_nmi_watchdog(). Its function definition is included indirectly when compiled on x86, but not when compiled on ARM64. So add the explicit #include. No functional change. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1626058204-2106-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/asm-generic/mshyperv.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 9a000ba2bb75..2ccb40670552 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include From c445535c3efbfb8cb42d098e624d46ab149664b7 Mon Sep 17 00:00:00 2001 From: Ani Sinha Date: Tue, 13 Jul 2021 08:35:21 +0530 Subject: [PATCH 02/15] x86/hyperv: fix for unwanted manipulation of sched_clock when TSC marked unstable Marking TSC as unstable has a side effect of marking sched_clock as unstable when TSC is still being used as the sched_clock. This is not desirable. Hyper-V ultimately uses a paravirtualized clock source that provides a stable scheduler clock even on systems without TscInvariant CPU capability. Hence, mark_tsc_unstable() call should be called _after_ scheduler clock has been changed to the paravirtualized clocksource. This will prevent any unwanted manipulation of the sched_clock. Only TSC will be correctly marked as unstable. Signed-off-by: Ani Sinha Reviewed-by: Michael Kelley Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20210713030522.1714803-1-ani@anisinha.ca Signed-off-by: Wei Liu --- arch/x86/kernel/cpu/mshyperv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index cc8f1773deca..8bd1c01c3310 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -375,8 +375,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) { 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 +435,13 @@ 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) From afca4d95dd7d7936d46a0ff02169cc40f534a6a3 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 14 Jul 2021 11:34:45 -0700 Subject: [PATCH 03/15] Drivers: hv: Make portions of Hyper-V init code be arch neutral The code to allocate and initialize the hv_vp_index array is architecture neutral. Similarly, the code to allocate and populate the hypercall input and output arg pages is architecture neutral. Move both sets of code out from arch/x86 and into utility functions in drivers/hv/hv_common.c that can be shared by Hyper-V initialization on ARM64. No functional changes. However, the allocation of the hypercall input and output arg pages is done differently so that the size is always the Hyper-V page size, even if not the same as the guest page size (such as with ARM64's 64K page size). Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1626287687-2045-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 91 +++------------------ arch/x86/include/asm/mshyperv.h | 4 - arch/x86/kernel/cpu/mshyperv.c | 3 - drivers/hv/hv_common.c | 138 ++++++++++++++++++++++++++++++++ include/asm-generic/mshyperv.h | 10 +++ 5 files changed, 158 insertions(+), 88 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6952e219cba3..5cc0c0f30e75 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -39,48 +39,17 @@ 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; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; - void **input_arg; - struct page *pg; + int ret; - /* 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; - - 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; @@ -198,25 +167,8 @@ 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; - } - - local_irq_restore(flags); - - free_pages((unsigned long)pg, hv_root_partition ? 1 : 0); + hv_common_cpu_die(cpu); if (hv_vp_assist_page && hv_vp_assist_page[cpu]) wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0); @@ -368,7 +320,7 @@ 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 +332,14 @@ 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 +437,8 @@ 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(); } /* 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 8bd1c01c3310..40d3656d5461 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -36,10 +36,7 @@ /* 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); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 7f42da98d377..e836002bc0ce 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -15,9 +15,147 @@ #include #include #include +#include +#include #include #include +/* + * hv_root_partition and ms_hyperv are defined here with other Hyper-V + * specific globals so they are shared across all architectures and are + * built only when CONFIG_HYPERV is defined. But on x86, + * ms_hyperv_init_platform() is built even when CONFIG_HYPERV is not + * defined, and it uses these two variables. So mark them as __weak + * here, allowing for an overriding definition in the module containing + * ms_hyperv_init_platform(). + */ +bool __weak hv_root_partition; +EXPORT_SYMBOL_GPL(hv_root_partition); + +struct ms_hyperv_info __weak ms_hyperv; +EXPORT_SYMBOL_GPL(ms_hyperv); + +u32 *hv_vp_index; +EXPORT_SYMBOL_GPL(hv_vp_index); + +u32 hv_max_vp_index; +EXPORT_SYMBOL_GPL(hv_max_vp_index); + +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); + +/* + * Hyper-V specific initialization and shutdown code that is + * common across all architectures. Called from architecture + * specific initialization functions. + */ + +void __init hv_common_free(void) +{ + kfree(hv_vp_index); + hv_vp_index = NULL; + + free_percpu(hyperv_pcpu_output_arg); + hyperv_pcpu_output_arg = NULL; + + free_percpu(hyperv_pcpu_input_arg); + hyperv_pcpu_input_arg = NULL; +} + +int __init hv_common_init(void) +{ + int i; + + /* + * 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); + + /* 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); + } + + hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), + GFP_KERNEL); + if (!hv_vp_index) { + hv_common_free(); + return -ENOMEM; + } + + for (i = 0; i < num_possible_cpus(); i++) + hv_vp_index[i] = VP_INVAL; + + return 0; +} + +/* + * Hyper-V specific initialization and die code for + * individual CPUs that is common across all architectures. + * Called by the CPU hotplug mechanism. + */ + +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; + + /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ + flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL; + + inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); + *inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags); + if (!(*inputarg)) + return -ENOMEM; + + if (hv_root_partition) { + outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE; + } + + msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); + + hv_vp_index[cpu] = msr_vp_index; + + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + + return 0; +} + +int hv_common_cpu_die(unsigned int cpu) +{ + unsigned long flags; + void **inputarg, **outputarg; + void *mem; + + local_irq_save(flags); + + inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); + mem = *inputarg; + *inputarg = NULL; + + if (hv_root_partition) { + outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *outputarg = NULL; + } + + local_irq_restore(flags); + + kfree(mem); + + return 0; +} /* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */ bool hv_query_ext_cap(u64 cap_query) diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 2ccb40670552..60cdff3e2252 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -39,6 +39,9 @@ struct ms_hyperv_info { }; extern struct ms_hyperv_info ms_hyperv; +extern void __percpu **hyperv_pcpu_input_arg; +extern void __percpu **hyperv_pcpu_output_arg; + extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr); extern u64 hv_do_fast_hypercall8(u16 control, u64 input8); @@ -152,6 +155,8 @@ void hv_remove_crash_handler(void); extern int vmbus_interrupt; extern int vmbus_irq; +extern bool hv_root_partition; + #if IS_ENABLED(CONFIG_HYPERV) /* * Hypervisor's notion of virtual processor ID is different from @@ -165,6 +170,11 @@ extern u32 hv_max_vp_index; /* Sentinel value for an uninitialized entry in hv_vp_index array */ #define VP_INVAL U32_MAX +int __init hv_common_init(void); +void __init hv_common_free(void); +int hv_common_cpu_init(unsigned int cpu); +int hv_common_cpu_die(unsigned int cpu); + void *hv_alloc_hyperv_page(void); void *hv_alloc_hyperv_zeroed_page(void); void hv_free_hyperv_page(unsigned long addr); From 9d7cf2c9675838c12cd5cf5a4ebe2ba41bd78a44 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 14 Jul 2021 11:34:46 -0700 Subject: [PATCH 04/15] Drivers: hv: Add arch independent default functions for some Hyper-V handlers Architecture independent Hyper-V code calls various arch-specific handlers when needed. To aid in supporting multiple architectures, provide weak defaults that can be overridden by arch-specific implementations where appropriate. But when arch-specific overrides aren't needed or haven't been implemented yet for a particular architecture, these stubs reduce the amount of clutter under arch/. No functional change. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1626287687-2045-3-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 2 -- arch/x86/kernel/cpu/mshyperv.c | 6 ----- drivers/hv/hv_common.c | 49 ++++++++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+), 8 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 5cc0c0f30e75..e87a0293b705 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -468,7 +468,6 @@ 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) { @@ -542,4 +541,3 @@ 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/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 40d3656d5461..0b647965e039 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -62,14 +62,12 @@ 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 @@ -104,25 +102,21 @@ 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) diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index e836002bc0ce..fe333f410d1d 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -202,3 +203,51 @@ bool hv_query_ext_cap(u64 cap_query) return hv_extended_cap & cap_query; } EXPORT_SYMBOL_GPL(hv_query_ext_cap); + +/* These __weak functions provide default "no-op" behavior and + * may be overridden by architecture specific versions. Architectures + * for which the default "no-op" behavior is sufficient can leave + * them unimplemented and not be cluttered with a bunch of stub + * functions in arch-specific code. + */ + +bool __weak hv_is_isolation_supported(void) +{ + return false; +} +EXPORT_SYMBOL_GPL(hv_is_isolation_supported); + +void __weak hv_setup_vmbus_handler(void (*handler)(void)) +{ +} +EXPORT_SYMBOL_GPL(hv_setup_vmbus_handler); + +void __weak hv_remove_vmbus_handler(void) +{ +} +EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler); + +void __weak hv_setup_kexec_handler(void (*handler)(void)) +{ +} +EXPORT_SYMBOL_GPL(hv_setup_kexec_handler); + +void __weak hv_remove_kexec_handler(void) +{ +} +EXPORT_SYMBOL_GPL(hv_remove_kexec_handler); + +void __weak hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)) +{ +} +EXPORT_SYMBOL_GPL(hv_setup_crash_handler); + +void __weak hv_remove_crash_handler(void) +{ +} +EXPORT_SYMBOL_GPL(hv_remove_crash_handler); + +void __weak hyperv_cleanup(void) +{ +} +EXPORT_SYMBOL_GPL(hyperv_cleanup); From 6dc77fa5ac2cf26f846a51492dbe42526e26d0f2 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 14 Jul 2021 11:34:47 -0700 Subject: [PATCH 05/15] Drivers: hv: Move Hyper-V misc functionality to arch-neutral code The check for whether hibernation is possible, and the enabling of Hyper-V panic notification during kexec, are both architecture neutral. Move the code from under arch/x86 and into drivers/hv/hv_common.c where it can also be used for ARM64. No functional change. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1626287687-2045-4-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 8 +------- arch/x86/kernel/cpu/mshyperv.c | 11 ----------- drivers/hv/hv_common.c | 18 ++++++++++++++++++ 3 files changed, 19 insertions(+), 18 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e87a0293b705..6f247e7e07eb 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -7,10 +7,10 @@ * Author : K. Y. Srinivasan */ -#include #include #include #include +#include #include #include #include @@ -523,12 +523,6 @@ 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)) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 0b647965e039..30baae031481 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -326,16 +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) { diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index fe333f410d1d..46658de78050 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -13,9 +13,11 @@ */ #include +#include #include #include #include +#include #include #include #include @@ -70,6 +72,16 @@ int __init hv_common_init(void) { int i; + /* + * 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; + /* * Allocate the per-CPU state for the hypercall input arg. * If this allocation fails, we will not be able to setup @@ -204,6 +216,12 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +bool hv_is_hibernation_supported(void) +{ + return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); +} +EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); + /* These __weak functions provide default "no-op" behavior and * may be overridden by architecture specific versions. Architectures * for which the default "no-op" behavior is sufficient can leave From 5f92b45c3b67e3d222caf10e2eb898af31756b67 Mon Sep 17 00:00:00 2001 From: Ani Sinha Date: Fri, 16 Jul 2021 19:02:45 +0530 Subject: [PATCH 06/15] x86/hyperv: add comment describing TSC_INVARIANT_CONTROL MSR setting bit 0 Commit dce7cd62754b5 ("x86/hyperv: Allow guests to enable InvariantTSC") added the support for HV_X64_MSR_TSC_INVARIANT_CONTROL. Setting bit 0 of this synthetic MSR will allow hyper-v guests to report invariant TSC CPU feature through CPUID. This comment adds this explanation to the code and mentions where the Intel's generic platform init code reads this feature bit from CPUID. The comment will help developers understand how the two parts of the initialization (hyperV specific and non-hyperV specific generic hw init) are related. Signed-off-by: Ani Sinha Reviewed-by: Vitaly Kuznetsov Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210716133245.3272672-1-ani@anisinha.ca Signed-off-by: Wei Liu --- arch/x86/kernel/cpu/mshyperv.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 30baae031481..6b5835a087a3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -353,6 +353,15 @@ 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); } From 31e5e64694cf9879e63b2802007fa934f4131126 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 13 Jul 2021 17:01:46 -0700 Subject: [PATCH 07/15] drivers: hv: Decouple Hyper-V clock/timer code from VMbus drivers Hyper-V clock/timer code in hyperv_timer.c is mostly independent from other VMbus drivers, but building for ARM64 without hyperv_timer.c shows some remaining entanglements. A default implementation of hv_read_reference_counter can just read a Hyper-V synthetic register and be independent of hyperv_timer.c, so move this code out and into hv_common.c. Then it can be used by the timesync driver even if hyperv_timer.c isn't built on a particular architecture. If hyperv_timer.c *is* built, it can override with a faster implementation. Also provide stubs for stimer functions called by the VMbus driver when hyperv_timer.c isn't built. No functional changes. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1626220906-22629-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/clocksource/hyperv_timer.c | 3 --- drivers/hv/hv_common.c | 14 ++++++++++++++ drivers/hv/hv_util.c | 5 ----- include/asm-generic/mshyperv.h | 2 ++ include/clocksource/hyperv_timer.h | 11 +++++++++-- 5 files changed, 25 insertions(+), 10 deletions(-) diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index d6ece7bbce89..ff188ab68496 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -361,9 +361,6 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); * Hyper-V and 32-bit x86. The TSC reference page version is preferred. */ -u64 (*hv_read_reference_counter)(void); -EXPORT_SYMBOL_GPL(hv_read_reference_counter); - static union { struct ms_hyperv_tsc_page page; u8 reserved[PAGE_SIZE]; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 46658de78050..c0d9048a4112 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -222,6 +222,20 @@ bool hv_is_hibernation_supported(void) } EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); +/* + * Default function to read the Hyper-V reference counter, independent + * of whether Hyper-V enlightened clocks/timers are being used. But on + * architectures where it is used, Hyper-V enlightenment code in + * hyperv_timer.c may override this function. + */ +static u64 __hv_read_ref_counter(void) +{ + return hv_get_register(HV_REGISTER_TIME_REF_COUNT); +} + +u64 (*hv_read_reference_counter)(void) = __hv_read_ref_counter; +EXPORT_SYMBOL_GPL(hv_read_reference_counter); + /* These __weak functions provide default "no-op" behavior and * may be overridden by architecture specific versions. Architectures * for which the default "no-op" behavior is sufficient can leave diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 136576cba26f..835e6039c186 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include "hyperv_vmbus.h" @@ -735,10 +734,6 @@ static struct ptp_clock *hv_ptp_clock; static int hv_timesync_init(struct hv_util_service *srv) { - /* TimeSync requires Hyper-V clocksource. */ - if (!hv_read_reference_counter) - return -ENODEV; - spin_lock_init(&host_ts.lock); INIT_WORK(&adj_time_work, hv_set_host_time); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 60cdff3e2252..c1ab6a6e72b5 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -167,6 +167,8 @@ extern bool hv_root_partition; extern u32 *hv_vp_index; extern u32 hv_max_vp_index; +extern u64 (*hv_read_reference_counter)(void); + /* Sentinel value for an uninitialized entry in hv_vp_index array */ #define VP_INVAL U32_MAX diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index b6774aa5a4b8..b3f5d73ae1d6 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -20,6 +20,8 @@ #define HV_MAX_MAX_DELTA_TICKS 0xffffffff #define HV_MIN_DELTA_TICKS 1 +#ifdef CONFIG_HYPERV_TIMER + /* Routines called by the VMbus driver */ extern int hv_stimer_alloc(bool have_percpu_irqs); extern int hv_stimer_cleanup(unsigned int cpu); @@ -28,8 +30,6 @@ extern void hv_stimer_legacy_cleanup(unsigned int cpu); extern void hv_stimer_global_cleanup(void); extern void hv_stimer0_isr(void); -#ifdef CONFIG_HYPERV_TIMER -extern u64 (*hv_read_reference_counter)(void); extern void hv_init_clocksource(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); @@ -100,6 +100,13 @@ static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, { return U64_MAX; } + +static inline int hv_stimer_cleanup(unsigned int cpu) { return 0; } +static inline void hv_stimer_legacy_init(unsigned int cpu, int sint) {} +static inline void hv_stimer_legacy_cleanup(unsigned int cpu) {} +static inline void hv_stimer_global_cleanup(void) {} +static inline void hv_stimer0_isr(void) {} + #endif /* CONFIG_HYPERV_TIMER */ #endif From 63fb60c2fcc94d595a184fa187bdfb25e5ecd4a2 Mon Sep 17 00:00:00 2001 From: Sonia Sharma Date: Wed, 21 Jul 2021 14:41:03 -0700 Subject: [PATCH 08/15] hv: hyperv.h: Remove unused inline functions There are some unused inline functions in hyper.h. Remove those unused functions. Signed-off-by: Sonia Sharma Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1626903663-23615-1-git-send-email-sosha@linux.microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2e859d2f9609..ddc8713ce57b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -538,12 +538,6 @@ struct vmbus_channel_rescind_offer { u32 child_relid; } __packed; -static inline u32 -hv_ringbuffer_pending_size(const struct hv_ring_buffer_info *rbi) -{ - return rbi->ring_buffer->pending_send_sz; -} - /* * Request Offer -- no parameters, SynIC message contains the partition ID * Set Snoop -- no parameters, SynIC message contains the partition ID @@ -1092,16 +1086,6 @@ static inline void set_channel_pending_send_size(struct vmbus_channel *c, c->outbound.ring_buffer->pending_send_sz = size; } -static inline void set_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = true; -} - -static inline void clear_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = false; -} - void vmbus_onmessage(struct vmbus_channel_message_header *hdr); int vmbus_request_offers(void); From e5d9b714fe40270222a7de9dcd1cf62dad63eeef Mon Sep 17 00:00:00 2001 From: Praveen Kumar Date: Sat, 31 Jul 2021 17:35:19 +0530 Subject: [PATCH 09/15] x86/hyperv: fix root partition faults when writing to VP assist page MSR For root partition the VP assist pages are pre-determined by the hypervisor. The root kernel is not allowed to change them to different locations. And thus, we are getting below stack as in current implementation root is trying to perform write to specific MSR. [ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to write 0x0000000145ac5001) at rIP: 0xffffffff810c1084 (native_write_msr+0x4/0x30) [ 2.784867] Call Trace: [ 2.791507] hv_cpu_init+0xf1/0x1c0 [ 2.798144] ? hyperv_report_panic+0xd0/0xd0 [ 2.804806] cpuhp_invoke_callback+0x11a/0x440 [ 2.811465] ? hv_resume+0x90/0x90 [ 2.818137] cpuhp_issue_call+0x126/0x130 [ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0 [ 2.831427] ? hyperv_report_panic+0xd0/0xd0 [ 2.838075] ? hyperv_report_panic+0xd0/0xd0 [ 2.844723] ? hv_resume+0x90/0x90 [ 2.851375] __cpuhp_setup_state+0x3d/0x90 [ 2.858030] hyperv_init+0x14e/0x410 [ 2.864689] ? enable_IR_x2apic+0x190/0x1a0 [ 2.871349] apic_intr_mode_init+0x8b/0x100 [ 2.878017] x86_late_time_init+0x20/0x30 [ 2.884675] start_kernel+0x459/0x4fb [ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb Since the hypervisor already provides the VP assist pages for root partition, we need to memremap the memory from hypervisor for root kernel to use. The mapping is done in hv_cpu_init during bringup and is unmapped in hv_cpu_die during teardown. Signed-off-by: Praveen Kumar Reviewed-by: Sunil Muthuswamy Link: https://lore.kernel.org/r/20210731120519.17154-1-kumarpraveen@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 64 ++++++++++++++++++++---------- arch/x86/include/asm/hyperv-tlfs.h | 9 +++++ 2 files changed, 53 insertions(+), 20 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6f247e7e07eb..708a2712a516 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -44,6 +44,7 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page); static int hv_cpu_init(unsigned int cpu) { + union hv_vp_assist_msr_contents msr = { 0 }; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; int ret; @@ -54,25 +55,34 @@ static int hv_cpu_init(unsigned int cpu) 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; @@ -170,8 +180,22 @@ static int hv_cpu_die(unsigned int cpu) hv_common_cpu_die(cpu); - if (hv_vp_assist_page && hv_vp_assist_page[cpu]) - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0); + 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); + } if (hv_reenlightenment_cb == NULL) return 0; 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; From 57d276bbbd322409bb6f7c6446187a29953f8ded Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 4 Aug 2021 08:52:35 -0700 Subject: [PATCH 10/15] arm64: hyperv: Add Hyper-V hypercall and register access utilities hyperv-tlfs.h defines Hyper-V interfaces from the Hyper-V Top Level Functional Spec (TLFS), and #includes the architecture-independent part of hyperv-tlfs.h in include/asm-generic. The published TLFS is distinctly oriented to x86/x64, so the ARM64-specific hyperv-tlfs.h includes information for ARM64 that is not yet formally published. The TLFS is available here: docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs mshyperv.h defines Linux-specific structures and routines for interacting with Hyper-V on ARM64, and #includes the architecture- independent part of mshyperv.h in include/asm-generic. Use these definitions to provide utility functions to make Hyper-V hypercalls and to get and set Hyper-V provided registers associated with a virtual processor. Signed-off-by: Michael Kelley Reviewed-by: Sunil Muthuswamy Acked-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1628092359-61351-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- MAINTAINERS | 3 + arch/arm64/Kbuild | 1 + arch/arm64/hyperv/Makefile | 2 + arch/arm64/hyperv/hv_core.c | 129 +++++++++++++++++++++++++++ arch/arm64/include/asm/hyperv-tlfs.h | 69 ++++++++++++++ arch/arm64/include/asm/mshyperv.h | 54 +++++++++++ 6 files changed, 258 insertions(+) create mode 100644 arch/arm64/hyperv/Makefile create mode 100644 arch/arm64/hyperv/hv_core.c create mode 100644 arch/arm64/include/asm/hyperv-tlfs.h create mode 100644 arch/arm64/include/asm/mshyperv.h diff --git a/MAINTAINERS b/MAINTAINERS index a61f4f3b78a9..4f84a8616b87 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8594,6 +8594,9 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git F: Documentation/ABI/stable/sysfs-bus-vmbus F: Documentation/ABI/testing/debugfs-hyperv F: Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst +F: arch/arm64/hyperv +F: arch/arm64/include/asm/hyperv-tlfs.h +F: arch/arm64/include/asm/mshyperv.h F: arch/x86/hyperv F: arch/x86/include/asm/hyperv-tlfs.h F: arch/x86/include/asm/mshyperv.h diff --git a/arch/arm64/Kbuild b/arch/arm64/Kbuild index 7b393cfec071..ea7ab4ca81f9 100644 --- a/arch/arm64/Kbuild +++ b/arch/arm64/Kbuild @@ -2,4 +2,5 @@ obj-y += kernel/ mm/ net/ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_XEN) += xen/ +obj-$(subst m,y,$(CONFIG_HYPERV)) += hyperv/ obj-$(CONFIG_CRYPTO) += crypto/ diff --git a/arch/arm64/hyperv/Makefile b/arch/arm64/hyperv/Makefile new file mode 100644 index 000000000000..1697d30ff106 --- /dev/null +++ b/arch/arm64/hyperv/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y := hv_core.o diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c new file mode 100644 index 000000000000..4c5dc0f51b12 --- /dev/null +++ b/arch/arm64/hyperv/hv_core.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Low level utility routines for interacting with Hyper-V. + * + * Copyright (C) 2021, Microsoft, Inc. + * + * Author : Michael Kelley + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * hv_do_hypercall- Invoke the specified hypercall + */ +u64 hv_do_hypercall(u64 control, void *input, void *output) +{ + struct arm_smccc_res res; + u64 input_address; + u64 output_address; + + input_address = input ? virt_to_phys(input) : 0; + output_address = output ? virt_to_phys(output) : 0; + + arm_smccc_1_1_hvc(HV_FUNC_ID, control, + input_address, output_address, &res); + return res.a0; +} +EXPORT_SYMBOL_GPL(hv_do_hypercall); + +/* + * hv_do_fast_hypercall8 -- Invoke the specified hypercall + * with arguments in registers instead of physical memory. + * Avoids the overhead of virt_to_phys for simple hypercalls. + */ + +u64 hv_do_fast_hypercall8(u16 code, u64 input) +{ + struct arm_smccc_res res; + u64 control; + + control = (u64)code | HV_HYPERCALL_FAST_BIT; + + arm_smccc_1_1_hvc(HV_FUNC_ID, control, input, &res); + return res.a0; +} +EXPORT_SYMBOL_GPL(hv_do_fast_hypercall8); + +/* + * Set a single VP register to a 64-bit value. + */ +void hv_set_vpreg(u32 msr, u64 value) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_hvc(HV_FUNC_ID, + HVCALL_SET_VP_REGISTERS | HV_HYPERCALL_FAST_BIT | + HV_HYPERCALL_REP_COMP_1, + HV_PARTITION_ID_SELF, + HV_VP_INDEX_SELF, + msr, + 0, + value, + 0, + &res); + + /* + * Something is fundamentally broken in the hypervisor if + * setting a VP register fails. There's really no way to + * continue as a guest VM, so panic. + */ + BUG_ON(!hv_result_success(res.a0)); +} +EXPORT_SYMBOL_GPL(hv_set_vpreg); + +/* + * Get the value of a single VP register. One version + * returns just 64 bits and another returns the full 128 bits. + * The two versions are separate to avoid complicating the + * calling sequence for the more frequently used 64 bit version. + */ + +void hv_get_vpreg_128(u32 msr, struct hv_get_vp_registers_output *result) +{ + struct arm_smccc_1_2_regs args; + struct arm_smccc_1_2_regs res; + + args.a0 = HV_FUNC_ID; + args.a1 = HVCALL_GET_VP_REGISTERS | HV_HYPERCALL_FAST_BIT | + HV_HYPERCALL_REP_COMP_1; + args.a2 = HV_PARTITION_ID_SELF; + args.a3 = HV_VP_INDEX_SELF; + args.a4 = msr; + + /* + * Use the SMCCC 1.2 interface because the results are in registers + * beyond X0-X3. + */ + arm_smccc_1_2_hvc(&args, &res); + + /* + * Something is fundamentally broken in the hypervisor if + * getting a VP register fails. There's really no way to + * continue as a guest VM, so panic. + */ + BUG_ON(!hv_result_success(res.a0)); + + result->as64.low = res.a6; + result->as64.high = res.a7; +} +EXPORT_SYMBOL_GPL(hv_get_vpreg_128); + +u64 hv_get_vpreg(u32 msr) +{ + struct hv_get_vp_registers_output output; + + hv_get_vpreg_128(msr, &output); + + return output.as64.low; +} +EXPORT_SYMBOL_GPL(hv_get_vpreg); diff --git a/arch/arm64/include/asm/hyperv-tlfs.h b/arch/arm64/include/asm/hyperv-tlfs.h new file mode 100644 index 000000000000..4d964a7f02ee --- /dev/null +++ b/arch/arm64/include/asm/hyperv-tlfs.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file contains definitions from the Hyper-V Hypervisor Top-Level + * Functional Specification (TLFS): + * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs + * + * Copyright (C) 2021, Microsoft, Inc. + * + * Author : Michael Kelley + */ + +#ifndef _ASM_HYPERV_TLFS_H +#define _ASM_HYPERV_TLFS_H + +#include + +/* + * All data structures defined in the TLFS that are shared between Hyper-V + * and a guest VM use Little Endian byte ordering. This matches the default + * byte ordering of Linux running on ARM64, so no special handling is required. + */ + +/* + * These Hyper-V registers provide information equivalent to the CPUID + * instruction on x86/x64. + */ +#define HV_REGISTER_HYPERVISOR_VERSION 0x00000100 /*CPUID 0x40000002 */ +#define HV_REGISTER_FEATURES 0x00000200 /*CPUID 0x40000003 */ +#define HV_REGISTER_ENLIGHTENMENTS 0x00000201 /*CPUID 0x40000004 */ + +/* + * Group C Features. See the asm-generic version of hyperv-tlfs.h + * for a description of Feature Groups. + */ + +/* Crash MSRs available */ +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(8) + +/* STIMER direct mode is available */ +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(13) + +/* + * Synthetic register definitions equivalent to MSRs on x86/x64 + */ +#define HV_REGISTER_CRASH_P0 0x00000210 +#define HV_REGISTER_CRASH_P1 0x00000211 +#define HV_REGISTER_CRASH_P2 0x00000212 +#define HV_REGISTER_CRASH_P3 0x00000213 +#define HV_REGISTER_CRASH_P4 0x00000214 +#define HV_REGISTER_CRASH_CTL 0x00000215 + +#define HV_REGISTER_GUEST_OSID 0x00090002 +#define HV_REGISTER_VP_INDEX 0x00090003 +#define HV_REGISTER_TIME_REF_COUNT 0x00090004 +#define HV_REGISTER_REFERENCE_TSC 0x00090017 + +#define HV_REGISTER_SINT0 0x000A0000 +#define HV_REGISTER_SCONTROL 0x000A0010 +#define HV_REGISTER_SIEFP 0x000A0012 +#define HV_REGISTER_SIMP 0x000A0013 +#define HV_REGISTER_EOM 0x000A0014 + +#define HV_REGISTER_STIMER0_CONFIG 0x000B0000 +#define HV_REGISTER_STIMER0_COUNT 0x000B0001 + +#include + +#endif diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h new file mode 100644 index 000000000000..20070a847304 --- /dev/null +++ b/arch/arm64/include/asm/mshyperv.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Linux-specific definitions for managing interactions with Microsoft's + * Hyper-V hypervisor. The definitions in this file are specific to + * the ARM64 architecture. See include/asm-generic/mshyperv.h for + * definitions are that architecture independent. + * + * Definitions that are specified in the Hyper-V Top Level Functional + * Spec (TLFS) should not go in this file, but should instead go in + * hyperv-tlfs.h. + * + * Copyright (C) 2021, Microsoft, Inc. + * + * Author : Michael Kelley + */ + +#ifndef _ASM_MSHYPERV_H +#define _ASM_MSHYPERV_H + +#include +#include +#include + +/* + * Declare calls to get and set Hyper-V VP register values on ARM64, which + * requires a hypercall. + */ + +void hv_set_vpreg(u32 reg, u64 value); +u64 hv_get_vpreg(u32 reg); +void hv_get_vpreg_128(u32 reg, struct hv_get_vp_registers_output *result); + +static inline void hv_set_register(unsigned int reg, u64 value) +{ + hv_set_vpreg(reg, value); +} + +static inline u64 hv_get_register(unsigned int reg) +{ + return hv_get_vpreg(reg); +} + +/* SMCCC hypercall parameters */ +#define HV_SMCCC_FUNC_NUMBER 1 +#define HV_FUNC_ID ARM_SMCCC_CALL_VAL( \ + ARM_SMCCC_STD_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + HV_SMCCC_FUNC_NUMBER) + +#include + +#endif From 512c1117fb2eeb944df1b88bff6e0c002990b369 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 4 Aug 2021 08:52:36 -0700 Subject: [PATCH 11/15] arm64: hyperv: Add panic handler Add a function to inform Hyper-V about a guest panic. This code is built only when CONFIG_HYPERV is enabled. Signed-off-by: Michael Kelley Reviewed-by: Sunil Muthuswamy Reviewed-by: Boqun Feng Acked-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1628092359-61351-3-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/arm64/hyperv/hv_core.c | 52 +++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/arch/arm64/hyperv/hv_core.c b/arch/arm64/hyperv/hv_core.c index 4c5dc0f51b12..b54c34793701 100644 --- a/arch/arm64/hyperv/hv_core.c +++ b/arch/arm64/hyperv/hv_core.c @@ -127,3 +127,55 @@ u64 hv_get_vpreg(u32 msr) return output.as64.low; } EXPORT_SYMBOL_GPL(hv_get_vpreg); + +/* + * hyperv_report_panic - report a panic to Hyper-V. This function uses + * the older version of the Hyper-V interface that admittedly doesn't + * pass enough information to be useful beyond just recording the + * occurrence of a panic. The parallel hv_kmsg_dump() uses the + * new interface that allows reporting 4 Kbytes of data, which is much + * more useful. Hyper-V on ARM64 always supports the newer interface, but + * we retain support for the older version because the sysadmin is allowed + * to disable the newer version via sysctl in case of information security + * concerns about the more verbose version. + */ +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) +{ + static bool panic_reported; + u64 guest_id; + + /* Don't report a panic to Hyper-V if we're not going to panic */ + if (in_die && !panic_on_oops) + return; + + /* + * We prefer to report panic on 'die' chain as we have proper + * registers to report, but if we miss it (e.g. on BUG()) we need + * to report it on 'panic'. + * + * Calling code in the 'die' and 'panic' paths ensures that only + * one CPU is running this code, so no atomicity is needed. + */ + if (panic_reported) + return; + panic_reported = true; + + guest_id = hv_get_vpreg(HV_REGISTER_GUEST_OSID); + + /* + * Hyper-V provides the ability to store only 5 values. + * Pick the passed in error value, the guest_id, the PC, + * and the SP. + */ + hv_set_vpreg(HV_REGISTER_CRASH_P0, err); + hv_set_vpreg(HV_REGISTER_CRASH_P1, guest_id); + hv_set_vpreg(HV_REGISTER_CRASH_P2, regs->pc); + hv_set_vpreg(HV_REGISTER_CRASH_P3, regs->sp); + hv_set_vpreg(HV_REGISTER_CRASH_P4, 0); + + /* + * Let Hyper-V know there is crash data available + */ + hv_set_vpreg(HV_REGISTER_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY); +} +EXPORT_SYMBOL_GPL(hyperv_report_panic); From 9bbb888824e38cc2e9118ed351fe3d22403a73e1 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 4 Aug 2021 08:52:37 -0700 Subject: [PATCH 12/15] arm64: hyperv: Initialize hypervisor on boot Add ARM64-specific code to initialize the Hyper-V hypervisor when booting as a guest VM. This code is built only when CONFIG_HYPERV is enabled. Signed-off-by: Michael Kelley Acked-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1628092359-61351-4-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/arm64/hyperv/Makefile | 2 +- arch/arm64/hyperv/mshyperv.c | 87 ++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/hyperv/mshyperv.c diff --git a/arch/arm64/hyperv/Makefile b/arch/arm64/hyperv/Makefile index 1697d30ff106..87c31c001da9 100644 --- a/arch/arm64/hyperv/Makefile +++ b/arch/arm64/hyperv/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := hv_core.o +obj-y := hv_core.o mshyperv.o diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c new file mode 100644 index 000000000000..bbbe351e9045 --- /dev/null +++ b/arch/arm64/hyperv/mshyperv.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Core routines for interacting with Microsoft's Hyper-V hypervisor, + * including hypervisor initialization. + * + * Copyright (C) 2021, Microsoft, Inc. + * + * Author : Michael Kelley + */ + +#include +#include +#include +#include +#include +#include +#include + +static bool hyperv_initialized; + +static int __init hyperv_init(void) +{ + struct hv_get_vp_registers_output result; + u32 a, b, c, d; + u64 guest_id; + int ret; + + /* + * Allow for a kernel built with CONFIG_HYPERV to be running in + * a non-Hyper-V environment, including on DT instead of ACPI. + * In such cases, do nothing and return success. + */ + if (acpi_disabled) + return 0; + + if (strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8)) + return 0; + + /* Setup the guest ID */ + guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); + hv_set_vpreg(HV_REGISTER_GUEST_OSID, guest_id); + + /* Get the features and hints from Hyper-V */ + hv_get_vpreg_128(HV_REGISTER_FEATURES, &result); + ms_hyperv.features = result.as32.a; + ms_hyperv.priv_high = result.as32.b; + ms_hyperv.misc_features = result.as32.c; + + hv_get_vpreg_128(HV_REGISTER_ENLIGHTENMENTS, &result); + ms_hyperv.hints = result.as32.a; + + pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints, + ms_hyperv.misc_features); + + /* Get information about the Hyper-V host version */ + hv_get_vpreg_128(HV_REGISTER_HYPERVISOR_VERSION, &result); + a = result.as32.a; + b = result.as32.b; + c = result.as32.c; + d = result.as32.d; + pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n", + b >> 16, b & 0xFFFF, a, d & 0xFFFFFF, c, d >> 24); + + ret = hv_common_init(); + if (ret) + return ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/hyperv_init:online", + hv_common_cpu_init, hv_common_cpu_die); + if (ret < 0) { + hv_common_free(); + return ret; + } + + hyperv_initialized = true; + return 0; +} + +early_initcall(hyperv_init); + +bool hv_is_hyperv_initialized(void) +{ + return hyperv_initialized; +} +EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); From 9b16c2132f34316bf0b59d24357a788cc1e9e352 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 4 Aug 2021 08:52:38 -0700 Subject: [PATCH 13/15] arm64: efi: Export screen_info The Hyper-V frame buffer driver may be built as a module, and it needs access to screen_info. So export screen_info. Signed-off-by: Michael Kelley Acked-by: Ard Biesheuvel Acked-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1628092359-61351-5-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/arm64/kernel/efi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index fa02efb28e88..e1be6c429810 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -55,6 +55,7 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md) /* we will fill this structure from the stub, so don't put it in .bss */ struct screen_info screen_info __section(".data"); +EXPORT_SYMBOL(screen_info); int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { From 7aff79e297ee1aa0126924921fd87a4ae59d2467 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 4 Aug 2021 08:52:39 -0700 Subject: [PATCH 14/15] Drivers: hv: Enable Hyper-V code to be built on ARM64 Update drivers/hv/Kconfig so CONFIG_HYPERV can be selected on ARM64, causing the Hyper-V specific code to be built. Exclude the Hyper-V enlightened clocks/timers code from being built for ARM64. Signed-off-by: Michael Kelley Reviewed-by: Boqun Feng Acked-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1628092359-61351-6-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/Kconfig | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 66c794d92391..d1123ceb38f3 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -4,15 +4,16 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on X86 && ACPI && X86_LOCAL_APIC && HYPERVISOR_GUEST + depends on ACPI && ((X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \ + || (ARM64 && !CPU_BIG_ENDIAN)) select PARAVIRT - select X86_HV_CALLBACK_VECTOR + select X86_HV_CALLBACK_VECTOR if X86 help Select this option to run Linux as a Hyper-V client operating system. config HYPERV_TIMER - def_bool HYPERV + def_bool HYPERV && X86 config HYPERV_UTILS tristate "Microsoft Hyper-V Utilities driver" From 9d68cd9120e4e3af38f843e165631c323b86b4e4 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 25 Aug 2021 15:38:57 +0200 Subject: [PATCH 15/15] hv_utils: Set the maximum packet size for VSS driver to the length of the receive buffer Commit adae1e931acd ("Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer") introduced a notion of maximum packet size and for KVM and FCOPY drivers set it to the length of the receive buffer. VSS driver wasn't updated, this means that the maximum packet size is now VMBUS_DEFAULT_MAX_PKT_SIZE (4k). Apparently, this is not enough. I'm observing a packet of 6304 bytes which is being truncated to 4096. When VSS driver tries to read next packet from ring buffer it starts from the wrong offset and receives garbage. Set the maximum packet size to 'HV_HYP_PAGE_SIZE * 2' in VSS driver. This matches the length of the receive buffer and is in line with other utils drivers. Fixes: adae1e931acd ("Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer") Signed-off-by: Vitaly Kuznetsov Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210825133857.847866-1-vkuznets@redhat.com Signed-off-by: Wei Liu --- drivers/hv/hv_snapshot.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 2267bd4c3472..6018b9d1b1fb 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -375,6 +375,7 @@ hv_vss_init(struct hv_util_service *srv) } recv_buffer = srv->recv_buffer; vss_transaction.recv_channel = srv->channel; + vss_transaction.recv_channel->max_pkt_size = HV_HYP_PAGE_SIZE * 2; /* * When this driver loads, the user level daemon that