From a6c76bb08dc7f7ff2b1c381002eb6c7211746182 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 1 Feb 2021 15:48:11 +0100 Subject: x86/hyperv: Load/save the Isolation Configuration leaf If bit 22 of Group B Features is set, the guest has access to the Isolation Configuration CPUID leaf. On x86, the first four bits of EAX in this leaf provide the isolation type of the partition; we entail three isolation types: 'SNP' (hardware-based isolation), 'VBS' (software-based isolation), and 'NONE' (no isolation). Signed-off-by: Andrea Parri (Microsoft) Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Arnd Bergmann Cc: x86@kernel.org Cc: linux-arch@vger.kernel.org Link: https://lore.kernel.org/r/20210201144814.2701-2-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 15 +++++++++++++++ arch/x86/include/asm/hyperv-tlfs.h | 15 +++++++++++++++ arch/x86/kernel/cpu/mshyperv.c | 9 +++++++++ 3 files changed, 39 insertions(+) (limited to 'arch') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6375967a8244..6608d50d7aaa 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -555,3 +556,17 @@ bool hv_is_hibernation_supported(void) return 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.features_b & HV_ISOLATION)) + return HV_ISOLATION_TYPE_NONE; + return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b); +} +EXPORT_SYMBOL_GPL(hv_get_isolation_type); + +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 6bf42aed387e..6aed936e5e96 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -22,6 +22,7 @@ #define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 #define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 #define HYPERV_CPUID_NESTED_FEATURES 0x4000000A +#define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C #define HYPERV_CPUID_VIRT_STACK_INTERFACE 0x40000081 #define HYPERV_VS_INTERFACE_EAX_SIGNATURE 0x31235356 /* "VS#1" */ @@ -122,6 +123,20 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */ +#define HV_PARAVISOR_PRESENT BIT(0) + +/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */ +#define HV_ISOLATION_TYPE GENMASK(3, 0) +#define HV_SHARED_GPA_BOUNDARY_ACTIVE BIT(5) +#define HV_SHARED_GPA_BOUNDARY_BITS GENMASK(11, 6) + +enum hv_isolation_type { + HV_ISOLATION_TYPE_NONE = 0, + HV_ISOLATION_TYPE_VBS = 1, + HV_ISOLATION_TYPE_SNP = 2 +}; + /* Hyper-V specific model specific registers (MSRs) */ /* MSR used to identify the guest OS. */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 43b54bef5448..fc6cb84c9fe5 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -243,6 +243,7 @@ static void __init ms_hyperv_init_platform(void) * Extract the features and hints */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES); ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); @@ -277,6 +278,14 @@ static void __init ms_hyperv_init_platform(void) x86_platform.calibrate_cpu = hv_get_tsc_khz; } + if (ms_hyperv.features_b & HV_ISOLATION) { + ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG); + ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG); + + pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", + ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); + } + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { ms_hyperv.nested_features = cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); -- cgit v1.2.3 From e997720202b363ba8000d769f114e3c2c5822227 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:21 +0000 Subject: x86/hyperv: detect if Linux is the root partition For now we can use the privilege flag to check. Stash the value to be used later. Put in a bunch of defines for future use when we want to have more fine-grained detection. Signed-off-by: Wei Liu Reviewed-by: Pavel Tatashin Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-3-wei.liu@kernel.org --- arch/x86/include/asm/hyperv-tlfs.h | 10 ++++++++++ arch/x86/include/asm/mshyperv.h | 2 ++ arch/x86/kernel/cpu/mshyperv.c | 20 ++++++++++++++++++++ 3 files changed, 32 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 6aed936e5e96..e3a6a723d661 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -21,6 +21,7 @@ #define HYPERV_CPUID_FEATURES 0x40000003 #define HYPERV_CPUID_ENLIGHTMENT_INFO 0x40000004 #define HYPERV_CPUID_IMPLEMENT_LIMITS 0x40000005 +#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES 0x40000007 #define HYPERV_CPUID_NESTED_FEATURES 0x4000000A #define HYPERV_CPUID_ISOLATION_CONFIG 0x4000000C @@ -111,6 +112,15 @@ /* Recommend using enlightened VMCS */ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +/* + * CPU management features identification. + * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. + */ +#define HV_X64_START_LOGICAL_PROCESSOR BIT(0) +#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR BIT(1) +#define HV_X64_PERFORMANCE_COUNTER_SYNC BIT(2) +#define HV_X64_RESERVED_IDENTITY_BIT BIT(31) + /* * Virtual processor will never share a physical core with another virtual * processor, except for virtual processors that are reported as sibling SMT diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 30f76b966857..4014a1ca2fae 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -239,6 +239,8 @@ 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 fc6cb84c9fe5..39a4b4509b87 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -32,6 +32,10 @@ #include #include +/* 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); @@ -256,6 +260,22 @@ static void __init ms_hyperv_init_platform(void) pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); + /* + * Check CPU management privilege. + * + * To mirror what Windows does we should extract CPU management + * features and use the ReservedIdentityBit to detect if Linux is the + * root partition. But that requires negotiating CPU management + * interface (a process to be finalized). + * + * For now, use the privilege flag as the indicator for running as + * root. + */ + if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) { + hv_root_partition = true; + pr_info("Hyper-V: running as root partition\n"); + } + /* * Extract host information. */ -- cgit v1.2.3 From 5d0f077e0f413b7eca827b16ea8bfc4569e3946c Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:24 +0000 Subject: x86/hyperv: allocate output arg pages if required When Linux runs as the root partition, it will need to make hypercalls which return data from the hypervisor. Allocate pages for storing results when Linux runs as the root partition. Signed-off-by: Lillian Grassin-Drake Co-Developed-by: Lillian Grassin-Drake Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-6-wei.liu@kernel.org --- arch/x86/hyperv/hv_init.c | 35 ++++++++++++++++++++++++++++++----- arch/x86/include/asm/mshyperv.h | 1 + 2 files changed, 31 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6608d50d7aaa..a73f4db31870 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -45,6 +45,9 @@ 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); @@ -77,12 +80,19 @@ static int hv_cpu_init(unsigned int cpu) void **input_arg; struct page *pg; - input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ - pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL); + 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); + } hv_get_vp_index(msr_vp_index); @@ -209,14 +219,23 @@ static int hv_cpu_die(unsigned int cpu) unsigned int new_cpu; unsigned long flags; void **input_arg; - void *input_pg = NULL; + void *pg; local_irq_save(flags); input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - input_pg = *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_page((unsigned long)input_pg); + + 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); @@ -369,6 +388,12 @@ void __init hyperv_init(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); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 4014a1ca2fae..ef06cdac8444 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -78,6 +78,7 @@ extern int hyperv_init_cpuhp; extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; +extern void __percpu **hyperv_pcpu_output_arg; static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { -- cgit v1.2.3 From 99a0f46af6a7715147e81c558d558021aad4e207 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:25 +0000 Subject: x86/hyperv: extract partition ID from Microsoft Hypervisor if necessary We will need the partition ID for executing some hypercalls later. Signed-off-by: Lillian Grassin-Drake Co-Developed-by: Sunil Muthuswamy Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-7-wei.liu@kernel.org --- arch/x86/hyperv/hv_init.c | 26 ++++++++++++++++++++++++++ arch/x86/include/asm/mshyperv.h | 2 ++ include/asm-generic/hyperv-tlfs.h | 6 ++++++ 3 files changed, 34 insertions(+) (limited to 'arch') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a73f4db31870..612c555fb9aa 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -29,6 +29,8 @@ #include int hyperv_init_cpuhp; +u64 hv_current_partition_id = ~0ull; +EXPORT_SYMBOL_GPL(hv_current_partition_id); void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -354,6 +356,24 @@ static void __init hv_stimer_setup_percpu_clockev(void) old_setup_percpu_clockev(); } +static void __init hv_get_partition_id(void) +{ + struct hv_get_partition_id *output_page; + u64 status; + unsigned long flags; + + local_irq_save(flags); + output_page = *this_cpu_ptr(hyperv_pcpu_output_arg); + status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page); + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) { + /* No point in proceeding if this failed */ + pr_err("Failed to get partition ID: %lld\n", status); + BUG(); + } + hv_current_partition_id = output_page->partition_id; + local_irq_restore(flags); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -454,6 +474,12 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); hyperv_init_cpuhp = cpuhp; + + if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID) + hv_get_partition_id(); + + BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull); + return; remove_cpuhp_state: diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ef06cdac8444..b8324202d850 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -80,6 +80,8 @@ 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; + static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { u64 input_address = input ? virt_to_phys(input) : 0; diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index e232ddcb0a2d..ba96bcb5c657 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -142,6 +142,7 @@ struct ms_hyperv_tsc_page { #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 #define HVCALL_SEND_IPI_EX 0x0015 +#define HVCALL_GET_PARTITION_ID 0x0046 #define HVCALL_GET_VP_REGISTERS 0x0050 #define HVCALL_SET_VP_REGISTERS 0x0051 #define HVCALL_POST_MESSAGE 0x005c @@ -408,6 +409,11 @@ struct hv_tlb_flush_ex { u64 gva_list[]; } __packed; +/* HvGetPartitionId hypercall (output only) */ +struct hv_get_partition_id { + u64 partition_id; +} __packed; + /* HvRetargetDeviceInterrupt hypercall */ union hv_msi_entry { u64 as_uint64; -- cgit v1.2.3 From 80f73c9f7468b15484e3ee4a29870fc9fa0419cc Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:26 +0000 Subject: x86/hyperv: handling hypercall page setup for root When Linux is running as the root partition, the hypercall page will have already been setup by Hyper-V. Copy the content over to the allocated page. Add checks to hv_suspend & co to bail early because they are not supported in this setup yet. Signed-off-by: Lillian Grassin-Drake Signed-off-by: Sunil Muthuswamy Signed-off-by: Nuno Das Neves Co-Developed-by: Lillian Grassin-Drake Co-Developed-by: Sunil Muthuswamy Co-Developed-by: Nuno Das Neves Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-8-wei.liu@kernel.org --- arch/x86/hyperv/hv_init.c | 37 ++++++++++++++++++++++++++++++++++--- 1 file changed, 34 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 612c555fb9aa..aeea8fbf3c23 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -27,6 +27,7 @@ #include #include #include +#include int hyperv_init_cpuhp; u64 hv_current_partition_id = ~0ull; @@ -286,6 +287,9 @@ static int hv_suspend(void) union hv_x64_msr_hypercall_contents hypercall_msr; int ret; + if (hv_root_partition) + return -EPERM; + /* * Reset the hypercall page as it is going to be invalidated * accross hibernation. Setting hv_hypercall_pg to NULL ensures @@ -454,8 +458,35 @@ void __init hyperv_init(void) rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); hypercall_msr.enable = 1; - hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); - wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + if (hv_root_partition) { + struct page *pg; + void *src, *dst; + + /* + * For the root partition, the hypervisor will set up its + * hypercall page. The hypervisor guarantees it will not show + * up in the root's address space. The root can't change the + * location of the hypercall page. + * + * Order is important here. We must enable the hypercall page + * so it is populated with code, then copy the code to an + * executable page. + */ + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + pg = vmalloc_to_page(hv_hypercall_pg); + dst = kmap(pg); + src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE, + MEMREMAP_WB); + BUG_ON(!(src && dst)); + memcpy(dst, src, HV_HYP_PAGE_SIZE); + memunmap(src); + kunmap(pg); + } else { + hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + } /* * hyperv_init() is called before LAPIC is initialized: see @@ -604,7 +635,7 @@ EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); bool hv_is_hibernation_supported(void) { - return acpi_sleep_state_supported(ACPI_STATE_S4); + return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); } EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); -- cgit v1.2.3 From 86b5ec3552f3c09694e6f7934834b0a2a3aeebbe Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:28 +0000 Subject: x86/hyperv: provide a bunch of helper functions They are used to deposit pages into Microsoft Hypervisor and bring up logical and virtual processors. Signed-off-by: Lillian Grassin-Drake Signed-off-by: Sunil Muthuswamy Signed-off-by: Nuno Das Neves Co-Developed-by: Lillian Grassin-Drake Co-Developed-by: Sunil Muthuswamy Co-Developed-by: Nuno Das Neves Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-10-wei.liu@kernel.org --- arch/x86/hyperv/Makefile | 2 +- arch/x86/hyperv/hv_proc.c | 219 ++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/mshyperv.h | 4 + include/asm-generic/hyperv-tlfs.h | 67 ++++++++++++ 4 files changed, 291 insertions(+), 1 deletion(-) create mode 100644 arch/x86/hyperv/hv_proc.c (limited to 'arch') diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 89b1f74d3225..565358020921 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := hv_init.o mmu.o nested.o -obj-$(CONFIG_X86_64) += hv_apic.o +obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o ifdef CONFIG_X86_64 obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c new file mode 100644 index 000000000000..60461e598239 --- /dev/null +++ b/arch/x86/hyperv/hv_proc.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * See struct hv_deposit_memory. The first u64 is partition ID, the rest + * are GPAs. + */ +#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1) + +/* Deposits exact number of pages. Must be called with interrupts enabled. */ +int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages) +{ + struct page **pages, *page; + int *counts; + int num_allocations; + int i, j, page_count; + int order; + u64 status; + int ret; + u64 base_pfn; + struct hv_deposit_memory *input_page; + unsigned long flags; + + if (num_pages > HV_DEPOSIT_MAX) + return -E2BIG; + if (!num_pages) + return 0; + + /* One buffer for page pointers and counts */ + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + pages = page_address(page); + + counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL); + if (!counts) { + free_page((unsigned long)pages); + return -ENOMEM; + } + + /* Allocate all the pages before disabling interrupts */ + i = 0; + + while (num_pages) { + /* Find highest order we can actually allocate */ + order = 31 - __builtin_clz(num_pages); + + while (1) { + pages[i] = alloc_pages_node(node, GFP_KERNEL, order); + if (pages[i]) + break; + if (!order) { + ret = -ENOMEM; + num_allocations = i; + goto err_free_allocations; + } + --order; + } + + split_page(pages[i], order); + counts[i] = 1 << order; + num_pages -= counts[i]; + i++; + } + num_allocations = i; + + local_irq_save(flags); + + input_page = *this_cpu_ptr(hyperv_pcpu_input_arg); + + input_page->partition_id = partition_id; + + /* Populate gpa_page_list - these will fit on the input page */ + for (i = 0, page_count = 0; i < num_allocations; ++i) { + base_pfn = page_to_pfn(pages[i]); + for (j = 0; j < counts[i]; ++j, ++page_count) + input_page->gpa_page_list[page_count] = base_pfn + j; + } + status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY, + page_count, 0, input_page, NULL); + local_irq_restore(flags); + + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) { + pr_err("Failed to deposit pages: %lld\n", status); + ret = status; + goto err_free_allocations; + } + + ret = 0; + goto free_buf; + +err_free_allocations: + for (i = 0; i < num_allocations; ++i) { + base_pfn = page_to_pfn(pages[i]); + for (j = 0; j < counts[i]; ++j) + __free_page(pfn_to_page(base_pfn + j)); + } + +free_buf: + free_page((unsigned long)pages); + kfree(counts); + return ret; +} + +int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) +{ + struct hv_add_logical_processor_in *input; + struct hv_add_logical_processor_out *output; + u64 status; + unsigned long flags; + int ret = 0; + int pxm = node_to_pxm(node); + + /* + * When adding a logical processor, the hypervisor may return + * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more + * pages and retry. + */ + do { + local_irq_save(flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + /* We don't do anything with the output right now */ + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + input->lp_index = lp_index; + input->apic_id = apic_id; + input->flags = 0; + input->proximity_domain_info.domain_id = pxm; + input->proximity_domain_info.flags.reserved = 0; + input->proximity_domain_info.flags.proximity_info_valid = 1; + input->proximity_domain_info.flags.proximity_preferred = 1; + status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR, + input, output); + local_irq_restore(flags); + + status &= HV_HYPERCALL_RESULT_MASK; + + if (status != HV_STATUS_INSUFFICIENT_MEMORY) { + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: cpu %u apic ID %u, %lld\n", __func__, + lp_index, apic_id, status); + ret = status; + } + break; + } + ret = hv_call_deposit_pages(node, hv_current_partition_id, 1); + } while (!ret); + + return ret; +} + +int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) +{ + struct hv_create_vp *input; + u64 status; + unsigned long irq_flags; + int ret = 0; + int pxm = node_to_pxm(node); + + /* Root VPs don't seem to need pages deposited */ + if (partition_id != hv_current_partition_id) { + /* The value 90 is empirically determined. It may change. */ + ret = hv_call_deposit_pages(node, partition_id, 90); + if (ret) + return ret; + } + + do { + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + + input->partition_id = partition_id; + input->vp_index = vp_index; + input->flags = flags; + input->subnode_type = HvSubnodeAny; + if (node != NUMA_NO_NODE) { + input->proximity_domain_info.domain_id = pxm; + input->proximity_domain_info.flags.reserved = 0; + input->proximity_domain_info.flags.proximity_info_valid = 1; + input->proximity_domain_info.flags.proximity_preferred = 1; + } else { + input->proximity_domain_info.as_uint64 = 0; + } + status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); + local_irq_restore(irq_flags); + + status &= HV_HYPERCALL_RESULT_MASK; + + if (status != HV_STATUS_INSUFFICIENT_MEMORY) { + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: vcpu %u, lp %u, %lld\n", __func__, + vp_index, flags, status); + ret = status; + } + break; + } + ret = hv_call_deposit_pages(node, partition_id, 1); + + } while (!ret); + + return ret; +} + diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index b8324202d850..f9119781f2bb 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -82,6 +82,10 @@ extern void __percpu **hyperv_pcpu_output_arg; extern u64 hv_current_partition_id; +int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages); +int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id); +int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags); + static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { u64 input_address = input ? virt_to_phys(input) : 0; diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index ba96bcb5c657..562a29981632 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -143,6 +143,8 @@ struct ms_hyperv_tsc_page { #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 #define HVCALL_SEND_IPI_EX 0x0015 #define HVCALL_GET_PARTITION_ID 0x0046 +#define HVCALL_DEPOSIT_MEMORY 0x0048 +#define HVCALL_CREATE_VP 0x004e #define HVCALL_GET_VP_REGISTERS 0x0050 #define HVCALL_SET_VP_REGISTERS 0x0051 #define HVCALL_POST_MESSAGE 0x005c @@ -150,6 +152,7 @@ struct ms_hyperv_tsc_page { #define HVCALL_POST_DEBUG_DATA 0x0069 #define HVCALL_RETRIEVE_DEBUG_DATA 0x006a #define HVCALL_RESET_DEBUG_SESSION 0x006b +#define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 #define HVCALL_RETARGET_INTERRUPT 0x007e #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 @@ -414,6 +417,70 @@ struct hv_get_partition_id { u64 partition_id; } __packed; +/* HvDepositMemory hypercall */ +struct hv_deposit_memory { + u64 partition_id; + u64 gpa_page_list[]; +} __packed; + +struct hv_proximity_domain_flags { + u32 proximity_preferred : 1; + u32 reserved : 30; + u32 proximity_info_valid : 1; +} __packed; + +/* Not a union in windows but useful for zeroing */ +union hv_proximity_domain_info { + struct { + u32 domain_id; + struct hv_proximity_domain_flags flags; + }; + u64 as_uint64; +} __packed; + +struct hv_lp_startup_status { + u64 hv_status; + u64 substatus1; + u64 substatus2; + u64 substatus3; + u64 substatus4; + u64 substatus5; + u64 substatus6; +} __packed; + +/* HvAddLogicalProcessor hypercall */ +struct hv_add_logical_processor_in { + u32 lp_index; + u32 apic_id; + union hv_proximity_domain_info proximity_domain_info; + u64 flags; +} __packed; + +struct hv_add_logical_processor_out { + struct hv_lp_startup_status startup_status; +} __packed; + +enum HV_SUBNODE_TYPE +{ + HvSubnodeAny = 0, + HvSubnodeSocket = 1, + HvSubnodeAmdNode = 2, + HvSubnodeL3 = 3, + HvSubnodeCount = 4, + HvSubnodeInvalid = -1 +}; + +/* HvCreateVp hypercall */ +struct hv_create_vp { + u64 partition_id; + u32 vp_index; + u8 padding[3]; + u8 subnode_type; + u64 subnode_id; + union hv_proximity_domain_info proximity_domain_info; + u64 flags; +} __packed; + /* HvRetargetDeviceInterrupt hypercall */ union hv_msi_entry { u64 as_uint64; -- cgit v1.2.3 From 333abaf5abb396820c4c7c26a8eecc7523c99184 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:29 +0000 Subject: x86/hyperv: implement and use hv_smp_prepare_cpus Microsoft Hypervisor requires the root partition to make a few hypercalls to setup application processors before they can be used. Signed-off-by: Lillian Grassin-Drake Signed-off-by: Sunil Muthuswamy Co-Developed-by: Lillian Grassin-Drake Co-Developed-by: Sunil Muthuswamy Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-11-wei.liu@kernel.org --- arch/x86/kernel/cpu/mshyperv.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 39a4b4509b87..e88bc296afca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -31,6 +31,7 @@ #include #include #include +#include /* Is Linux running as the root partition? */ bool hv_root_partition; @@ -230,6 +231,32 @@ static void __init hv_smp_prepare_boot_cpu(void) hv_init_spinlocks(); #endif } + +static void __init hv_smp_prepare_cpus(unsigned int max_cpus) +{ +#ifdef CONFIG_X86_64 + int i; + int ret; +#endif + + native_smp_prepare_cpus(max_cpus); + +#ifdef CONFIG_X86_64 + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); + BUG_ON(ret); + } + + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_create_vp(numa_cpu_node(i), hv_current_partition_id, i, i); + BUG_ON(ret); + } +#endif +} #endif static void __init ms_hyperv_init_platform(void) @@ -395,6 +422,8 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; + if (hv_root_partition) + smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus; # endif /* -- cgit v1.2.3 From d589ae61bc27b2b9aaac0bf20a9077b6fbda32b6 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:30 +0000 Subject: asm-generic/hyperv: update hv_msi_entry We will soon need to access fields inside the MSI address and MSI data fields. Introduce hv_msi_address_register and hv_msi_data_register. Fix up one user of hv_msi_entry in mshyperv.h. No functional change expected. Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-12-wei.liu@kernel.org --- arch/x86/include/asm/mshyperv.h | 4 ++-- include/asm-generic/hyperv-tlfs.h | 28 ++++++++++++++++++++++++++-- 2 files changed, 28 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index f9119781f2bb..7bd4022da061 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -259,8 +259,8 @@ static inline void hv_apic_init(void) {} static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, struct msi_desc *msi_desc) { - msi_entry->address = msi_desc->msg.address_lo; - msi_entry->data = msi_desc->msg.data; + msi_entry->address.as_uint32 = msi_desc->msg.address_lo; + msi_entry->data.as_uint32 = msi_desc->msg.data; } #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 562a29981632..8ac797e6a91a 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -481,12 +481,36 @@ struct hv_create_vp { u64 flags; } __packed; +union hv_msi_address_register { + u32 as_uint32; + struct { + u32 reserved1:2; + u32 destination_mode:1; + u32 redirection_hint:1; + u32 reserved2:8; + u32 destination_id:8; + u32 msi_base:12; + }; +} __packed; + +union hv_msi_data_register { + u32 as_uint32; + struct { + u32 vector:8; + u32 delivery_mode:3; + u32 reserved1:3; + u32 level_assert:1; + u32 trigger_mode:1; + u32 reserved2:16; + }; +} __packed; + /* HvRetargetDeviceInterrupt hypercall */ union hv_msi_entry { u64 as_uint64; struct { - u32 address; - u32 data; + union hv_msi_address_register address; + union hv_msi_data_register data; } __packed; }; -- cgit v1.2.3 From 466a9c3f88d04152ca83e840ca940c5f700402ac Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:33 +0000 Subject: asm-generic/hyperv: import data structures for mapping device interrupts Signed-off-by: Sunil Muthuswamy Co-Developed-by: Sunil Muthuswamy Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-15-wei.liu@kernel.org --- arch/x86/include/asm/hyperv-tlfs.h | 13 +++++++++++++ include/asm-generic/hyperv-tlfs.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index e3a6a723d661..e6cd3fee562b 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -548,6 +548,19 @@ struct hv_partition_assist_pg { u32 tlb_lock_count; }; +enum hv_interrupt_type { + HV_X64_INTERRUPT_TYPE_FIXED = 0x0000, + HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY = 0x0001, + HV_X64_INTERRUPT_TYPE_SMI = 0x0002, + HV_X64_INTERRUPT_TYPE_REMOTEREAD = 0x0003, + HV_X64_INTERRUPT_TYPE_NMI = 0x0004, + HV_X64_INTERRUPT_TYPE_INIT = 0x0005, + HV_X64_INTERRUPT_TYPE_SIPI = 0x0006, + HV_X64_INTERRUPT_TYPE_EXTINT = 0x0007, + HV_X64_INTERRUPT_TYPE_LOCALINT0 = 0x0008, + HV_X64_INTERRUPT_TYPE_LOCALINT1 = 0x0009, + HV_X64_INTERRUPT_TYPE_MAXIMUM = 0x000A, +}; #include diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 20457a85c046..83448e837ded 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -153,6 +153,8 @@ struct ms_hyperv_tsc_page { #define HVCALL_RETRIEVE_DEBUG_DATA 0x006a #define HVCALL_RESET_DEBUG_SESSION 0x006b #define HVCALL_ADD_LOGICAL_PROCESSOR 0x0076 +#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c +#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d #define HVCALL_RETARGET_INTERRUPT 0x007e #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 @@ -703,4 +705,38 @@ union hv_device_id { } acpi; } __packed; +enum hv_interrupt_trigger_mode { + HV_INTERRUPT_TRIGGER_MODE_EDGE = 0, + HV_INTERRUPT_TRIGGER_MODE_LEVEL = 1, +}; + +struct hv_device_interrupt_descriptor { + u32 interrupt_type; + u32 trigger_mode; + u32 vector_count; + u32 reserved; + struct hv_device_interrupt_target target; +} __packed; + +struct hv_input_map_device_interrupt { + u64 partition_id; + u64 device_id; + u64 flags; + struct hv_interrupt_entry logical_interrupt_entry; + struct hv_device_interrupt_descriptor interrupt_descriptor; +} __packed; + +struct hv_output_map_device_interrupt { + struct hv_interrupt_entry interrupt_entry; +} __packed; + +struct hv_input_unmap_device_interrupt { + u64 partition_id; + u64 device_id; + struct hv_interrupt_entry interrupt_entry; +} __packed; + +#define HV_SOURCE_SHADOW_NONE 0x0 +#define HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE 0x1 + #endif -- cgit v1.2.3 From e39397d1fd6851bef4dfb63a631b8e15d1f43329 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:34 +0000 Subject: x86/hyperv: implement an MSI domain for root partition When Linux runs as the root partition on Microsoft Hypervisor, its interrupts are remapped. Linux will need to explicitly map and unmap interrupts for hardware. Implement an MSI domain to issue the correct hypercalls. And initialize this irq domain as the default MSI irq domain. Signed-off-by: Sunil Muthuswamy Co-Developed-by: Sunil Muthuswamy Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-16-wei.liu@kernel.org --- arch/x86/hyperv/Makefile | 2 +- arch/x86/hyperv/hv_init.c | 9 + arch/x86/hyperv/irqdomain.c | 360 ++++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/mshyperv.h | 2 + 4 files changed, 372 insertions(+), 1 deletion(-) create mode 100644 arch/x86/hyperv/irqdomain.c (limited to 'arch') diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 565358020921..48e2c51464e8 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y := hv_init.o mmu.o nested.o +obj-y := hv_init.o mmu.o nested.o irqdomain.o obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o ifdef CONFIG_X86_64 diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index aeea8fbf3c23..b81047dec1da 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -511,6 +511,15 @@ void __init hyperv_init(void) BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull); +#ifdef CONFIG_PCI_MSI + /* + * If we're running as root, we want to create our own PCI MSI domain. + * We can't set this in hv_pci_init because that would be too late. + */ + if (hv_root_partition) + x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain; +#endif + return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c new file mode 100644 index 000000000000..bddcf1d6860d --- /dev/null +++ b/arch/x86/hyperv/irqdomain.c @@ -0,0 +1,360 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Irqdomain for Linux to run as the root partition on Microsoft Hypervisor. + * + * Authors: + * Sunil Muthuswamy + * Wei Liu + */ + +#include +#include +#include + +static int hv_map_interrupt(union hv_device_id device_id, bool level, + int cpu, int vector, struct hv_interrupt_entry *entry) +{ + struct hv_input_map_device_interrupt *input; + struct hv_output_map_device_interrupt *output; + struct hv_device_interrupt_descriptor *intr_desc; + unsigned long flags; + u64 status; + int nr_bank, var_size; + + local_irq_save(flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + intr_desc = &input->interrupt_descriptor; + memset(input, 0, sizeof(*input)); + input->partition_id = hv_current_partition_id; + input->device_id = device_id.as_uint64; + intr_desc->interrupt_type = HV_X64_INTERRUPT_TYPE_FIXED; + intr_desc->vector_count = 1; + intr_desc->target.vector = vector; + + if (level) + intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_LEVEL; + else + intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_EDGE; + + intr_desc->target.vp_set.valid_bank_mask = 0; + intr_desc->target.vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(intr_desc->target.vp_set), cpumask_of(cpu)); + if (nr_bank < 0) { + local_irq_restore(flags); + pr_err("%s: unable to generate VP set\n", __func__); + return EINVAL; + } + intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; + + /* + * var-sized hypercall, var-size starts after vp_mask (thus + * vp_set.format does not count, but vp_set.valid_bank_mask + * does). + */ + var_size = nr_bank + 1; + + status = hv_do_rep_hypercall(HVCALL_MAP_DEVICE_INTERRUPT, 0, var_size, + input, output); + *entry = output->interrupt_entry; + + local_irq_restore(flags); + + if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) + pr_err("%s: hypercall failed, status %lld\n", __func__, status); + + return status & HV_HYPERCALL_RESULT_MASK; +} + +static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) +{ + unsigned long flags; + struct hv_input_unmap_device_interrupt *input; + struct hv_interrupt_entry *intr_entry; + u64 status; + + local_irq_save(flags); + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + + memset(input, 0, sizeof(*input)); + intr_entry = &input->interrupt_entry; + input->partition_id = hv_current_partition_id; + input->device_id = id; + *intr_entry = *old_entry; + + status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL); + local_irq_restore(flags); + + return status & HV_HYPERCALL_RESULT_MASK; +} + +#ifdef CONFIG_PCI_MSI +struct rid_data { + struct pci_dev *bridge; + u32 rid; +}; + +static int get_rid_cb(struct pci_dev *pdev, u16 alias, void *data) +{ + struct rid_data *rd = data; + u8 bus = PCI_BUS_NUM(rd->rid); + + if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus) { + rd->bridge = pdev; + rd->rid = alias; + } + + return 0; +} + +static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev) +{ + union hv_device_id dev_id; + struct rid_data data = { + .bridge = NULL, + .rid = PCI_DEVID(dev->bus->number, dev->devfn) + }; + + pci_for_each_dma_alias(dev, get_rid_cb, &data); + + dev_id.as_uint64 = 0; + dev_id.device_type = HV_DEVICE_TYPE_PCI; + dev_id.pci.segment = pci_domain_nr(dev->bus); + + dev_id.pci.bdf.bus = PCI_BUS_NUM(data.rid); + dev_id.pci.bdf.device = PCI_SLOT(data.rid); + dev_id.pci.bdf.function = PCI_FUNC(data.rid); + dev_id.pci.source_shadow = HV_SOURCE_SHADOW_NONE; + + if (data.bridge) { + int pos; + + /* + * Microsoft Hypervisor requires a bus range when the bridge is + * running in PCI-X mode. + * + * To distinguish conventional vs PCI-X bridge, we can check + * the bridge's PCI-X Secondary Status Register, Secondary Bus + * Mode and Frequency bits. See PCI Express to PCI/PCI-X Bridge + * Specification Revision 1.0 5.2.2.1.3. + * + * Value zero means it is in conventional mode, otherwise it is + * in PCI-X mode. + */ + + pos = pci_find_capability(data.bridge, PCI_CAP_ID_PCIX); + if (pos) { + u16 status; + + pci_read_config_word(data.bridge, pos + + PCI_X_BRIDGE_SSTATUS, &status); + + if (status & PCI_X_SSTATUS_FREQ) { + /* Non-zero, PCI-X mode */ + u8 sec_bus, sub_bus; + + dev_id.pci.source_shadow = HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE; + + pci_read_config_byte(data.bridge, PCI_SECONDARY_BUS, &sec_bus); + dev_id.pci.shadow_bus_range.secondary_bus = sec_bus; + pci_read_config_byte(data.bridge, PCI_SUBORDINATE_BUS, &sub_bus); + dev_id.pci.shadow_bus_range.subordinate_bus = sub_bus; + } + } + } + + return dev_id; +} + +static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector, + struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id = hv_build_pci_dev_id(dev); + + return hv_map_interrupt(device_id, false, cpu, vector, entry); +} + +static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg) +{ + /* High address is always 0 */ + msg->address_hi = 0; + msg->address_lo = entry->msi_entry.address.as_uint32; + msg->data = entry->msi_entry.data.as_uint32; +} + +static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry); +static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct msi_desc *msidesc; + struct pci_dev *dev; + struct hv_interrupt_entry out_entry, *stored_entry; + struct irq_cfg *cfg = irqd_cfg(data); + cpumask_t *affinity; + int cpu; + u64 status; + + msidesc = irq_data_get_msi_desc(data); + dev = msi_desc_to_pci_dev(msidesc); + + if (!cfg) { + pr_debug("%s: cfg is NULL", __func__); + return; + } + + affinity = irq_data_get_effective_affinity_mask(data); + cpu = cpumask_first_and(affinity, cpu_online_mask); + + if (data->chip_data) { + /* + * This interrupt is already mapped. Let's unmap first. + * + * We don't use retarget interrupt hypercalls here because + * Microsoft Hypervisor doens't allow root to change the vector + * or specify VPs outside of the set that is initially used + * during mapping. + */ + stored_entry = data->chip_data; + data->chip_data = NULL; + + status = hv_unmap_msi_interrupt(dev, stored_entry); + + kfree(stored_entry); + + if (status != HV_STATUS_SUCCESS) { + pr_debug("%s: failed to unmap, status %lld", __func__, status); + return; + } + } + + stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC); + if (!stored_entry) { + pr_debug("%s: failed to allocate chip data\n", __func__); + return; + } + + status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry); + if (status != HV_STATUS_SUCCESS) { + kfree(stored_entry); + return; + } + + *stored_entry = out_entry; + data->chip_data = stored_entry; + entry_to_msi_msg(&out_entry, msg); + + return; +} + +static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry) +{ + return hv_unmap_interrupt(hv_build_pci_dev_id(dev).as_uint64, old_entry); +} + +static void hv_teardown_msi_irq_common(struct pci_dev *dev, struct msi_desc *msidesc, int irq) +{ + u64 status; + struct hv_interrupt_entry old_entry; + struct irq_desc *desc; + struct irq_data *data; + struct msi_msg msg; + + desc = irq_to_desc(irq); + if (!desc) { + pr_debug("%s: no irq desc\n", __func__); + return; + } + + data = &desc->irq_data; + if (!data) { + pr_debug("%s: no irq data\n", __func__); + return; + } + + if (!data->chip_data) { + pr_debug("%s: no chip data\n!", __func__); + return; + } + + old_entry = *(struct hv_interrupt_entry *)data->chip_data; + entry_to_msi_msg(&old_entry, &msg); + + kfree(data->chip_data); + data->chip_data = NULL; + + status = hv_unmap_msi_interrupt(dev, &old_entry); + + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: hypercall failed, status %lld\n", __func__, status); + return; + } +} + +static void hv_msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + int i; + struct msi_desc *entry; + struct pci_dev *pdev; + + if (WARN_ON_ONCE(!dev_is_pci(dev))) + return; + + pdev = to_pci_dev(dev); + + for_each_pci_msi_entry(entry, pdev) { + if (entry->irq) { + for (i = 0; i < entry->nvec_used; i++) { + hv_teardown_msi_irq_common(pdev, entry, entry->irq + i); + irq_domain_free_irqs(entry->irq + i, 1); + } + } + } +} + +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip hv_pci_msi_controller = { + .name = "HV-PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = hv_irq_compose_msi_msg, + .irq_set_affinity = msi_domain_set_affinity, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static struct msi_domain_ops pci_msi_domain_ops = { + .domain_free_irqs = hv_msi_domain_free_irqs, + .msi_prepare = pci_msi_prepare, +}; + +static struct msi_domain_info hv_pci_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &hv_pci_msi_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; + +struct irq_domain * __init hv_create_pci_msi_domain(void) +{ + struct irq_domain *d = NULL; + struct fwnode_handle *fn; + + fn = irq_domain_alloc_named_fwnode("HV-PCI-MSI"); + if (fn) + d = pci_msi_create_irq_domain(fn, &hv_pci_msi_domain_info, x86_vector_domain); + + /* No point in going further if we can't get an irq domain */ + BUG_ON(!d); + + return d; +} + +#endif /* CONFIG_PCI_MSI */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 7bd4022da061..4533773115ea 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -263,6 +263,8 @@ static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, msi_entry->data.as_uint32 = msi_desc->msg.data; } +struct irq_domain *hv_create_pci_msi_domain(void); + #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} -- cgit v1.2.3 From fb5ef35165a37ca63ef0227657eabd06f0a39cf9 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Wed, 3 Feb 2021 15:04:35 +0000 Subject: iommu/hyperv: setup an IO-APIC IRQ remapping domain for root partition Just like MSI/MSI-X, IO-APIC interrupts are remapped by Microsoft Hypervisor when Linux runs as the root partition. Implement an IRQ domain to handle mapping and unmapping of IO-APIC interrupts. Signed-off-by: Wei Liu Acked-by: Joerg Roedel Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210203150435.27941-17-wei.liu@kernel.org --- arch/x86/hyperv/irqdomain.c | 25 ++++++ arch/x86/include/asm/mshyperv.h | 4 + drivers/iommu/hyperv-iommu.c | 177 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 203 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index bddcf1d6860d..4421a8d92e23 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -358,3 +358,28 @@ struct irq_domain * __init hv_create_pci_msi_domain(void) } #endif /* CONFIG_PCI_MSI */ + +int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id; + + device_id.as_uint64 = 0; + device_id.device_type = HV_DEVICE_TYPE_IOAPIC; + device_id.ioapic.ioapic_id = (u8)ioapic_id; + + return hv_unmap_interrupt(device_id.as_uint64, entry); +} +EXPORT_SYMBOL_GPL(hv_unmap_ioapic_interrupt); + +int hv_map_ioapic_interrupt(int ioapic_id, bool level, int cpu, int vector, + struct hv_interrupt_entry *entry) +{ + union hv_device_id device_id; + + device_id.as_uint64 = 0; + device_id.device_type = HV_DEVICE_TYPE_IOAPIC; + device_id.ioapic.ioapic_id = (u8)ioapic_id; + + return hv_map_interrupt(device_id, level, cpu, vector, entry); +} +EXPORT_SYMBOL_GPL(hv_map_ioapic_interrupt); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 4533773115ea..ccf60a809a17 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -265,6 +265,10 @@ static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, struct irq_domain *hv_create_pci_msi_domain(void); +int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, + struct hv_interrupt_entry *entry); +int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); + #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline void hyperv_setup_mmu_ops(void) {} diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 1d21a0b5f724..e285a220c913 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "irq_remapping.h" @@ -115,30 +116,43 @@ static const struct irq_domain_ops hyperv_ir_domain_ops = { .free = hyperv_irq_remapping_free, }; +static const struct irq_domain_ops hyperv_root_ir_domain_ops; static int __init hyperv_prepare_irq_remapping(void) { struct fwnode_handle *fn; int i; + const char *name; + const struct irq_domain_ops *ops; if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) || x86_init.hyper.msi_ext_dest_id() || !x2apic_supported()) return -ENODEV; - fn = irq_domain_alloc_named_id_fwnode("HYPERV-IR", 0); + if (hv_root_partition) { + name = "HYPERV-ROOT-IR"; + ops = &hyperv_root_ir_domain_ops; + } else { + name = "HYPERV-IR"; + ops = &hyperv_ir_domain_ops; + } + + fn = irq_domain_alloc_named_id_fwnode(name, 0); if (!fn) return -ENOMEM; ioapic_ir_domain = irq_domain_create_hierarchy(arch_get_ir_parent_domain(), - 0, IOAPIC_REMAPPING_ENTRY, fn, - &hyperv_ir_domain_ops, NULL); + 0, IOAPIC_REMAPPING_ENTRY, fn, ops, NULL); if (!ioapic_ir_domain) { irq_domain_free_fwnode(fn); return -ENOMEM; } + if (hv_root_partition) + return 0; /* The rest is only relevant to guests */ + /* * Hyper-V doesn't provide irq remapping function for * IO-APIC and so IO-APIC only accepts 8-bit APIC ID. @@ -166,4 +180,161 @@ struct irq_remap_ops hyperv_irq_remap_ops = { .enable = hyperv_enable_irq_remapping, }; +/* IRQ remapping domain when Linux runs as the root partition */ +struct hyperv_root_ir_data { + u8 ioapic_id; + bool is_level; + struct hv_interrupt_entry entry; +}; + +static void +hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) +{ + u64 status; + u32 vector; + struct irq_cfg *cfg; + int ioapic_id; + struct cpumask *affinity; + int cpu; + struct hv_interrupt_entry entry; + struct hyperv_root_ir_data *data = irq_data->chip_data; + struct IO_APIC_route_entry e; + + cfg = irqd_cfg(irq_data); + affinity = irq_data_get_effective_affinity_mask(irq_data); + cpu = cpumask_first_and(affinity, cpu_online_mask); + + vector = cfg->vector; + ioapic_id = data->ioapic_id; + + if (data->entry.source == HV_DEVICE_TYPE_IOAPIC + && data->entry.ioapic_rte.as_uint64) { + entry = data->entry; + + status = hv_unmap_ioapic_interrupt(ioapic_id, &entry); + + if (status != HV_STATUS_SUCCESS) + pr_debug("%s: unexpected unmap status %lld\n", __func__, status); + + data->entry.ioapic_rte.as_uint64 = 0; + data->entry.source = 0; /* Invalid source */ + } + + + status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu, + vector, &entry); + + if (status != HV_STATUS_SUCCESS) { + pr_err("%s: map hypercall failed, status %lld\n", __func__, status); + return; + } + + data->entry = entry; + + /* Turn it into an IO_APIC_route_entry, and generate MSI MSG. */ + e.w1 = entry.ioapic_rte.low_uint32; + e.w2 = entry.ioapic_rte.high_uint32; + + memset(msg, 0, sizeof(*msg)); + msg->arch_data.vector = e.vector; + msg->arch_data.delivery_mode = e.delivery_mode; + msg->arch_addr_lo.dest_mode_logical = e.dest_mode_logical; + msg->arch_addr_lo.dmar_format = e.ir_format; + msg->arch_addr_lo.dmar_index_0_14 = e.ir_index_0_14; +} + +static int hyperv_root_ir_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = data->parent_data; + struct irq_cfg *cfg = irqd_cfg(data); + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + send_cleanup_vector(cfg); + + return 0; +} + +static struct irq_chip hyperv_root_ir_chip = { + .name = "HYPERV-ROOT-IR", + .irq_ack = apic_ack_irq, + .irq_set_affinity = hyperv_root_ir_set_affinity, + .irq_compose_msi_msg = hyperv_root_ir_compose_msi_msg, +}; + +static int hyperv_root_irq_remapping_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *arg) +{ + struct irq_alloc_info *info = arg; + struct irq_data *irq_data; + struct hyperv_root_ir_data *data; + int ret = 0; + + if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1) + return -EINVAL; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) { + irq_domain_free_irqs_common(domain, virq, nr_irqs); + return -ENOMEM; + } + + irq_data = irq_domain_get_irq_data(domain, virq); + if (!irq_data) { + kfree(data); + irq_domain_free_irqs_common(domain, virq, nr_irqs); + return -EINVAL; + } + + data->ioapic_id = info->devid; + data->is_level = info->ioapic.is_level; + + irq_data->chip = &hyperv_root_ir_chip; + irq_data->chip_data = data; + + return 0; +} + +static void hyperv_root_irq_remapping_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data; + struct hyperv_root_ir_data *data; + struct hv_interrupt_entry *e; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + e = &data->entry; + + if (e->source == HV_DEVICE_TYPE_IOAPIC + && e->ioapic_rte.as_uint64) + hv_unmap_ioapic_interrupt(data->ioapic_id, + &data->entry); + + kfree(data); + } + } + + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops hyperv_root_ir_domain_ops = { + .select = hyperv_irq_remapping_select, + .alloc = hyperv_root_irq_remapping_alloc, + .free = hyperv_root_irq_remapping_free, +}; + #endif -- cgit v1.2.3