hyperv: Add new Hyper-V headers in include/hyperv

These headers contain definitions for regular Hyper-V guests (as in
hyperv-tlfs.h), as well as interfaces for more privileged guests like
the root partition (aka Dom0).

These files are derived from headers exported from Hyper-V, rather than
being derived from the TLFS document. (Although, to preserve
compatibility with existing Linux code, some definitions are copied
directly from hyperv-tlfs.h too).

The new files follow a naming convention according to their original
use:
- hdk "host development kit"
- gdk "guest development kit"
With postfix "_mini" implying userspace-only headers, and "_ext" for
extended hypercalls.

The use of multiple files and their original names is primarily to
keep the provenance of exactly where they came from in Hyper-V
code, which is helpful for manual maintenance and extension
of these definitions. Microsoft maintainers importing new definitions
should take care to put them in the right file. However, Linux kernel
code that uses any of the definitions need not be aware of the multiple
files or assign any meaning to the new names. Linux kernel code should
always just include hvhdk.h

Note the new headers contain both arm64 and x86_64 definitions. Some are
guarded by #ifdefs, and some are instead prefixed with the architecture,
e.g. hv_x64_*. These conventions are kept from Hyper-V code as another
tactic to simplify the process of importing and maintaining the
definitions, rather than splitting them up into their own files in
arch/x86/ and arch/arm64/.

These headers are a step toward importing headers directly from Hyper-V
in the future, similar to Xen public files in include/xen/interface/.

Signed-off-by: Nuno Das Neves <[email protected]>
Reviewed-by: Easwar Hariharan <[email protected]>
Reviewed-by: Michael Kelley <[email protected]>
Signed-off-by: Roman Kisel <[email protected]>
Link: https://lore.kernel.org/r/1732577084-2122-4-git-send-email-nunodasneves@linux.microsoft.com
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Wei Liu <[email protected]>

Author: NunoDasNeves

MAINTAINERS

@@ -10695,6 +10695,11 @@ F:	drivers/video/fbdev/hyperv_fb.c
 F:	include/asm-generic/hyperv-tlfs.h
 F:	include/asm-generic/mshyperv.h
 F:	include/clocksource/hyperv_timer.h
+F:	include/hyperv/hvgdk.h
+F:	include/hyperv/hvgdk_ext.h
+F:	include/hyperv/hvgdk_mini.h
+F:	include/hyperv/hvhdk.h
+F:	include/hyperv/hvhdk_mini.h
 F:	include/linux/hyperv.h
 F:	include/net/mana
 F:	include/uapi/linux/hyperv.h

include/hyperv/hvgdk.h

@@ -0,0 +1,308 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the Microsoft Hypervisor.
+ */
+#ifndef _HV_HVGDK_H
+#define _HV_HVGDK_H
+
+#include "hvgdk_mini.h"
+#include "hvgdk_ext.h"
+
+/*
+ * The guest OS needs to register the guest ID with the hypervisor.
+ * The guest ID is a 64 bit entity and the structure of this ID is
+ * specified in the Hyper-V TLFS specification.
+ *
+ * While the current guideline does not specify how Linux guest ID(s)
+ * need to be generated, our plan is to publish the guidelines for
+ * Linux and other guest operating systems that currently are hosted
+ * on Hyper-V. The implementation here conforms to this yet
+ * unpublished guidelines.
+ *
+ * Bit(s)
+ * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
+ * 62:56 - Os Type; Linux is 0x100
+ * 55:48 - Distro specific identification
+ * 47:16 - Linux kernel version number
+ * 15:0  - Distro specific identification
+ */
+
+#define HV_LINUX_VENDOR_ID              0x8100
+
+/* HV_VMX_ENLIGHTENED_VMCS */
+struct hv_enlightened_vmcs {
+	u32 revision_id;
+	u32 abort;
+
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+
+	u16 padding16_1;
+
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+
+	u64 host_cr0;
+	u64 host_cr3;
+	u64 host_cr4;
+
+	u64 host_ia32_sysenter_esp;
+	u64 host_ia32_sysenter_eip;
+	u64 host_rip;
+	u32 host_ia32_sysenter_cs;
+
+	u32 pin_based_vm_exec_control;
+	u32 vm_exit_controls;
+	u32 secondary_vm_exec_control;
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+
+	u64 guest_es_base;
+	u64 guest_cs_base;
+	u64 guest_ss_base;
+	u64 guest_ds_base;
+	u64 guest_fs_base;
+	u64 guest_gs_base;
+	u64 guest_ldtr_base;
+	u64 guest_tr_base;
+	u64 guest_gdtr_base;
+	u64 guest_idtr_base;
+
+	u64 padding64_1[3];
+
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+
+	u64 cr3_target_value0;
+	u64 cr3_target_value1;
+	u64 cr3_target_value2;
+	u64 cr3_target_value3;
+
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+
+	u32 cr3_target_count;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_msr_load_count;
+
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 vmcs_link_pointer;
+
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+
+	u64 guest_pending_dbg_exceptions;
+	u64 guest_sysenter_esp;
+	u64 guest_sysenter_eip;
+
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+
+	u64 cr0_guest_host_mask;
+	u64 cr4_guest_host_mask;
+	u64 cr0_read_shadow;
+	u64 cr4_read_shadow;
+	u64 guest_cr0;
+	u64 guest_cr3;
+	u64 guest_cr4;
+	u64 guest_dr7;
+
+	u64 host_fs_base;
+	u64 host_gs_base;
+	u64 host_tr_base;
+	u64 host_gdtr_base;
+	u64 host_idtr_base;
+	u64 host_rsp;
+
+	u64 ept_pointer;
+
+	u16 virtual_processor_id;
+	u16 padding16_2[3];
+
+	u64 padding64_2[5];
+	u64 guest_physical_address;
+
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+
+	u64 exit_qualification;
+	u64 exit_io_instruction_ecx;
+	u64 exit_io_instruction_esi;
+	u64 exit_io_instruction_edi;
+	u64 exit_io_instruction_eip;
+
+	u64 guest_linear_address;
+	u64 guest_rsp;
+	u64 guest_rflags;
+
+	u32 guest_interruptibility_info;
+	u32 cpu_based_vm_exec_control;
+	u32 exception_bitmap;
+	u32 vm_entry_controls;
+	u32 vm_entry_intr_info_field;
+	u32 vm_entry_exception_error_code;
+	u32 vm_entry_instruction_len;
+	u32 tpr_threshold;
+
+	u64 guest_rip;
+
+	u32 hv_clean_fields;
+	u32 padding32_1;
+	u32 hv_synthetic_controls;
+	struct {
+		u32 nested_flush_hypercall:1;
+		u32 msr_bitmap:1;
+		u32 reserved:30;
+	}  __packed hv_enlightenments_control;
+	u32 hv_vp_id;
+	u32 padding32_2;
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 padding64_4[4];
+	u64 guest_bndcfgs;
+	u64 guest_ia32_perf_global_ctrl;
+	u64 guest_ia32_s_cet;
+	u64 guest_ssp;
+	u64 guest_ia32_int_ssp_table_addr;
+	u64 guest_ia32_lbr_ctl;
+	u64 padding64_5[2];
+	u64 xss_exit_bitmap;
+	u64 encls_exiting_bitmap;
+	u64 host_ia32_perf_global_ctrl;
+	u64 tsc_multiplier;
+	u64 host_ia32_s_cet;
+	u64 host_ssp;
+	u64 host_ia32_int_ssp_table_addr;
+	u64 padding64_6;
+} __packed;
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE			0
+
+
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP		BIT(0)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP		BIT(1)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2		BIT(2)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1		BIT(3)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC		BIT(4)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT		BIT(5)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY		BIT(6)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN		BIT(7)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR			BIT(8)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT		BIT(9)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC		BIT(10)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1		BIT(11)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2		BIT(12)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER		BIT(13)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1		BIT(14)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL	BIT(15)
+
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL			0xFFFF
+
+/*
+ * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by
+ * pairing it with architecturally impossible exit reasons.  Bit 28 is set only
+ * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit
+ * is pending.  I.e. it will never be set by hardware for non-SMI exits (there
+ * are only three), nor will it ever be set unless the VMM is an STM.
+ */
+#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH		0x10000031
+
+/*
+ * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose
+ * SVM enlightenments to guests. This is documented in the TLFS doc.
+ * Note on naming: SVM_NESTED_ENLIGHTENED_VMCB_FIELDS
+ */
+struct hv_vmcb_enlightenments {
+	struct __packed hv_enlightenments_control {
+		u32 nested_flush_hypercall : 1;
+		u32 msr_bitmap : 1;
+		u32 enlightened_npt_tlb: 1;
+		u32 reserved : 29;
+	} __packed hv_enlightenments_control;
+	u32 hv_vp_id;
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 reserved;
+} __packed;
+
+/*
+ * Hyper-V uses the software reserved clean bit in VMCB.
+ */
+#define HV_VMCB_NESTED_ENLIGHTENMENTS		31
+
+/* Synthetic VM-Exit */
+#define HV_SVM_EXITCODE_ENL			0xf0000000
+#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH	(1)
+
+/* VM_PARTITION_ASSIST_PAGE */
+struct hv_partition_assist_pg {
+	u32 tlb_lock_count;
+};
+
+/* Define connection identifier type. */
+union hv_connection_id {
+	u32 asu32;
+	struct {
+		u32 id : 24;
+		u32 reserved : 8;
+	} __packed u;
+};
+
+struct hv_input_unmap_gpa_pages {
+	u64 target_partition_id;
+	u64 target_gpa_base;
+	u32 unmap_flags;
+	u32 padding;
+} __packed;
+
+#endif /* #ifndef _HV_HVGDK_H */

include/hyperv/hvgdk_ext.h

@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the Microsoft Hypervisor.
+ */
+#ifndef _HV_HVGDK_EXT_H
+#define _HV_HVGDK_EXT_H
+
+#include "hvgdk_mini.h"
+
+/* Extended hypercalls */
+#define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001
+#define HV_EXT_CALL_MEMORY_HEAT_HINT		0x8003
+
+/* Extended hypercalls */
+enum {		/* HV_EXT_CALL */
+	HV_EXTCALL_QUERY_CAPABILITIES = 0x8001,
+	HV_EXTCALL_MEMORY_HEAT_HINT   = 0x8003,
+};
+
+/* HV_EXT_OUTPUT_QUERY_CAPABILITIES */
+#define HV_EXT_CAPABILITY_MEMORY_COLD_DISCARD_HINT BIT(8)
+
+enum {		/* HV_EXT_MEMORY_HEAT_HINT_TYPE */
+	HV_EXTMEM_HEAT_HINT_COLD = 0,
+	HV_EXTMEM_HEAT_HINT_HOT = 1,
+	HV_EXTMEM_HEAT_HINT_COLD_DISCARD = 2,
+	HV_EXTMEM_HEAT_HINT_MAX
+};
+
+/*
+ * The whole argument should fit in a page to be able to pass to the hypervisor
+ * in one hypercall.
+ */
+#define HV_MEMORY_HINT_MAX_GPA_PAGE_RANGES  \
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_memory_hint)) / \
+		sizeof(union hv_gpa_page_range))
+
+/* HvExtCallMemoryHeatHint hypercall */
+#define HV_EXT_MEMORY_HEAT_HINT_TYPE_COLD_DISCARD	2
+struct hv_memory_hint {		/* HV_EXT_INPUT_MEMORY_HEAT_HINT */
+	u64 heat_type : 2;	/* HV_EXTMEM_HEAT_HINT_* */
+	u64 reserved : 62;
+	union hv_gpa_page_range ranges[];
+} __packed;
+
+#endif /* _HV_HVGDK_EXT_H */