This patch series introduces support for Virtual Trust Level (VTL)
in Hyper-V systems. It provide a foundation for the implementation
of Hyper-V VSM support in the Linux kernel, providing a secure
platform for the development and deployment of applications.
Virtual Secure Mode (VSM) is a critical aspect of the security
infrastructure in Hyper-V systems. It provides a set of hypervisor
capabilities and enlightenments that enable the creation and
management of new security boundaries within operating system
software. The VSM achieves and maintains isolation through Virtual
Trust Levels, which are hierarchical, with higher levels being more
privileged than lower levels. Please refer to this link for further
information: https://learn.microsoft.com/en-us/virtualization/hyper-v-on-windows/tlfs/vsm
This patch series adds the initialization of the x86 platform for VTL
systems. This also adds the VTL early bootup code for initializing
and bringing up secondary cpus to targeted VTL context. In VTL, AP
has to start directly in the 64-bit mode, bypassing the usual
16-bit -> 32-bit -> 64-bit mode transition sequence that occurs after
waking up an AP with SIPI whose vector points to the 16-bit AP
startup trampoline code.
Currently only VTL level supprted is '2'. This patch series is tested
extensively on VTL2 systems.
[V4]
- Move HYPERV_VTL_MODE definition from arch/x86/Kconfig to drivers/hv/Kconfig
- Move Kconfig changes before its getting used
- Replace initial_stack with current->thread.sp as per recent upstream changes
[V3]
- Break in to 5 patches
- hv_init_vp_context_t -> hv_init_vp_context
- HYPERV_VTL -> HYPERV_VTL_MODE
- Modify description of HYPERV_VTL_MODE
- VTL 0 and VTL 2 -> VTL0 and VTL2
- Remove casting for this_cpu_ptr pointer
[V2]
- Remove the code for reserve 1 IRQ.
- boot_cpu_has -> cpu_feature_enabled.
- Improved commit message for 0002 patch.
- Improved Kconfig flag description for HYPERV_VTL.
- Removed hv_result as a wrapper around hv_do_hypercall().
- The value of output[0] copied to a local variable before returning.
Saurabh Sengar (5):
x86/init: Make get/set_rtc_noop() public
x86/hyperv: Add VTL specific structs and hypercalls
x86/hyperv: Make hv_get_nmi_reason public
x86/Kconfig: Add HYPERV_VTL_MODE
x86/hyperv: VTL support for Hyper-V
arch/x86/hyperv/Makefile | 1 +
arch/x86/hyperv/hv_vtl.c | 227 +++++++++++++++++++++++++++++
arch/x86/include/asm/hyperv-tlfs.h | 75 ++++++++++
arch/x86/include/asm/mshyperv.h | 15 ++
arch/x86/include/asm/x86_init.h | 2 +
arch/x86/kernel/cpu/mshyperv.c | 6 +-
arch/x86/kernel/x86_init.c | 4 +-
drivers/hv/Kconfig | 24 +++
include/asm-generic/hyperv-tlfs.h | 4 +
9 files changed, 351 insertions(+), 7 deletions(-)
create mode 100644 arch/x86/hyperv/hv_vtl.c
--
2.34.1
Virtual Trust Levels (VTL) helps enable Hyper-V Virtual Secure Mode (VSM)
feature. VSM is a set of hypervisor capabilities and enlightenments
offered to host and guest partitions which enable the creation and
management of new security boundaries within operating system software.
VSM achieves and maintains isolation through VTLs.
Add early initialization for Virtual Trust Levels (VTL). This includes
initializing the x86 platform for VTL and enabling boot support for
secondary CPUs to start in targeted VTL context. For now, only enable
the code for targeted VTL level as 2.
When starting an AP at a VTL other than VTL0, the AP must start directly
in 64-bit mode, bypassing the usual 16-bit -> 32-bit -> 64-bit mode
transition sequence that occurs after waking up an AP with SIPI whose
vector points to the 16-bit AP startup trampoline code.
Signed-off-by: Saurabh Sengar <[email protected]>
---
[V4]
- replace initial_stack with current->thread.sp as per recent upstream changes
arch/x86/hyperv/Makefile | 1 +
arch/x86/hyperv/hv_vtl.c | 227 ++++++++++++++++++++++++++++++++
arch/x86/include/asm/mshyperv.h | 10 ++
arch/x86/kernel/cpu/mshyperv.c | 1 +
4 files changed, 239 insertions(+)
create mode 100644 arch/x86/hyperv/hv_vtl.c
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 5d2de10809ae..3a1548054b48 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o
obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o
+obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o
ifdef CONFIG_X86_64
obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
new file mode 100644
index 000000000000..1ba5d3b99b16
--- /dev/null
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023, Microsoft Corporation.
+ *
+ * Author:
+ * Saurabh Sengar <[email protected]>
+ */
+
+#include <asm/apic.h>
+#include <asm/boot.h>
+#include <asm/desc.h>
+#include <asm/i8259.h>
+#include <asm/mshyperv.h>
+#include <asm/realmode.h>
+
+extern struct boot_params boot_params;
+static struct real_mode_header hv_vtl_real_mode_header;
+
+void __init hv_vtl_init_platform(void)
+{
+ pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+ x86_init.timers.timer_init = x86_init_noop;
+
+ x86_platform.get_wallclock = get_rtc_noop;
+ x86_platform.set_wallclock = set_rtc_noop;
+ x86_platform.get_nmi_reason = hv_get_nmi_reason;
+
+ x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT;
+ x86_platform.legacy.rtc = 0;
+ x86_platform.legacy.warm_reset = 0;
+ x86_platform.legacy.reserve_bios_regions = 0;
+ x86_platform.legacy.devices.pnpbios = 0;
+}
+
+static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
+{
+ return ((u64)desc->base3 << 32) | ((u64)desc->base2 << 24) |
+ (desc->base1 << 16) | desc->base0;
+}
+
+static inline u32 hv_vtl_system_desc_limit(struct ldttss_desc *desc)
+{
+ return ((u32)desc->limit1 << 16) | (u32)desc->limit0;
+}
+
+typedef void (*secondary_startup_64_fn)(void*, void*);
+static void hv_vtl_ap_entry(void)
+{
+ ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params);
+}
+
+static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored)
+{
+ u64 status;
+ int ret = 0;
+ struct hv_enable_vp_vtl *input;
+ unsigned long irq_flags;
+
+ struct desc_ptr gdt_ptr;
+ struct desc_ptr idt_ptr;
+
+ struct ldttss_desc *tss;
+ struct ldttss_desc *ldt;
+ struct desc_struct *gdt;
+
+ u64 rsp = current->thread.sp;
+ u64 rip = (u64)&hv_vtl_ap_entry;
+
+ native_store_gdt(&gdt_ptr);
+ store_idt(&idt_ptr);
+
+ gdt = (struct desc_struct *)((void *)(gdt_ptr.address));
+ tss = (struct ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+ ldt = (struct ldttss_desc *)(gdt + GDT_ENTRY_LDT);
+
+ local_irq_save(irq_flags);
+
+ input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ memset(input, 0, sizeof(*input));
+
+ input->partition_id = HV_PARTITION_ID_SELF;
+ input->vp_index = target_vp_index;
+ input->target_vtl.target_vtl = HV_VTL_MGMT;
+
+ /*
+ * The x86_64 Linux kernel follows the 16-bit -> 32-bit -> 64-bit
+ * mode transition sequence after waking up an AP with SIPI whose
+ * vector points to the 16-bit AP startup trampoline code. Here in
+ * VTL2, we can't perform that sequence as the AP has to start in
+ * the 64-bit mode.
+ *
+ * To make this happen, we tell the hypervisor to load a valid 64-bit
+ * context (most of which is just magic numbers from the CPU manual)
+ * so that AP jumps right to the 64-bit entry of the kernel, and the
+ * control registers are loaded with values that let the AP fetch the
+ * code and data and carry on with work it gets assigned.
+ */
+
+ input->vp_context.rip = rip;
+ input->vp_context.rsp = rsp;
+ input->vp_context.rflags = 0x0000000000000002;
+ input->vp_context.efer = __rdmsr(MSR_EFER);
+ input->vp_context.cr0 = native_read_cr0();
+ input->vp_context.cr3 = __native_read_cr3();
+ input->vp_context.cr4 = native_read_cr4();
+ input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT);
+ input->vp_context.idtr.limit = idt_ptr.size;
+ input->vp_context.idtr.base = idt_ptr.address;
+ input->vp_context.gdtr.limit = gdt_ptr.size;
+ input->vp_context.gdtr.base = gdt_ptr.address;
+
+ /* Non-system desc (64bit), long, code, present */
+ input->vp_context.cs.selector = __KERNEL_CS;
+ input->vp_context.cs.base = 0;
+ input->vp_context.cs.limit = 0xffffffff;
+ input->vp_context.cs.attributes = 0xa09b;
+ /* Non-system desc (64bit), data, present, granularity, default */
+ input->vp_context.ss.selector = __KERNEL_DS;
+ input->vp_context.ss.base = 0;
+ input->vp_context.ss.limit = 0xffffffff;
+ input->vp_context.ss.attributes = 0xc093;
+
+ /* System desc (128bit), present, LDT */
+ input->vp_context.ldtr.selector = GDT_ENTRY_LDT * 8;
+ input->vp_context.ldtr.base = hv_vtl_system_desc_base(ldt);
+ input->vp_context.ldtr.limit = hv_vtl_system_desc_limit(ldt);
+ input->vp_context.ldtr.attributes = 0x82;
+
+ /* System desc (128bit), present, TSS, 0x8b - busy, 0x89 -- default */
+ input->vp_context.tr.selector = GDT_ENTRY_TSS * 8;
+ input->vp_context.tr.base = hv_vtl_system_desc_base(tss);
+ input->vp_context.tr.limit = hv_vtl_system_desc_limit(tss);
+ input->vp_context.tr.attributes = 0x8b;
+
+ status = hv_do_hypercall(HVCALL_ENABLE_VP_VTL, input, NULL);
+
+ if (!hv_result_success(status) &&
+ hv_result(status) != HV_STATUS_VTL_ALREADY_ENABLED) {
+ pr_err("HVCALL_ENABLE_VP_VTL failed for VP : %d ! [Err: %#llx\n]",
+ target_vp_index, status);
+ ret = -EINVAL;
+ goto free_lock;
+ }
+
+ status = hv_do_hypercall(HVCALL_START_VP, input, NULL);
+
+ if (!hv_result_success(status)) {
+ pr_err("HVCALL_START_VP failed for VP : %d ! [Err: %#llx]\n",
+ target_vp_index, status);
+ ret = -EINVAL;
+ }
+
+free_lock:
+ local_irq_restore(irq_flags);
+
+ return ret;
+}
+
+static int hv_vtl_apicid_to_vp_id(u32 apic_id)
+{
+ u64 control;
+ u64 status;
+ unsigned long irq_flags;
+ struct hv_get_vp_from_apic_id_in *input;
+ u32 *output, ret;
+
+ local_irq_save(irq_flags);
+
+ input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ memset(input, 0, sizeof(*input));
+ input->partition_id = HV_PARTITION_ID_SELF;
+ input->apic_ids[0] = apic_id;
+
+ output = (u32 *)input;
+
+ control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
+ status = hv_do_hypercall(control, input, output);
+ ret = output[0];
+
+ local_irq_restore(irq_flags);
+
+ if (!hv_result_success(status)) {
+ pr_err("failed to get vp id from apic id %d, status %#llx\n",
+ apic_id, status);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
+static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
+{
+ int vp_id;
+
+ pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
+ vp_id = hv_vtl_apicid_to_vp_id(apicid);
+
+ if (vp_id < 0) {
+ pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
+ return -EINVAL;
+ }
+ if (vp_id > ms_hyperv.max_vp_index) {
+ pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
+ return -EINVAL;
+ }
+
+ return hv_vtl_bringup_vcpu(vp_id, start_eip);
+}
+
+static int __init hv_vtl_early_init(void)
+{
+ /*
+ * `boot_cpu_has` returns the runtime feature support,
+ * and here is the earliest it can be used.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVE))
+ panic("XSAVE has to be disabled as it is not supported by this module.\n"
+ "Please add 'noxsave' to the kernel command line.\n");
+
+ real_mode_header = &hv_vtl_real_mode_header;
+ apic->wakeup_secondary_cpu_64 = hv_vtl_wakeup_secondary_cpu;
+
+ return 0;
+}
+early_initcall(hv_vtl_early_init);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 71ed240ef66d..de4ad38f7d74 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -19,6 +19,10 @@
*/
#define HV_IOAPIC_BASE_ADDRESS 0xfec00000
+#define HV_VTL_NORMAL 0x0
+#define HV_VTL_SECURE 0x1
+#define HV_VTL_MGMT 0x2
+
union hv_ghcb;
DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
@@ -276,6 +280,12 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
#endif /* CONFIG_HYPERV */
+#ifdef CONFIG_HYPERV_VTL_MODE
+void __init hv_vtl_init_platform(void);
+#else
+static inline void __init hv_vtl_init_platform(void) {}
+#endif
+
#include <asm-generic/mshyperv.h>
#endif
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 5ee02af57dac..5180e3c50184 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -519,6 +519,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ hv_vtl_init_platform();
#endif
/*
* TSC should be marked as unstable only after Hyper-V
--
2.34.1
Add structs and hypercalls required to enable VTL support on x86.
Signed-off-by: Saurabh Sengar <[email protected]>
Reviewed-by: Michael Kelley <[email protected]>
---
arch/x86/include/asm/hyperv-tlfs.h | 75 ++++++++++++++++++++++++++++++
include/asm-generic/hyperv-tlfs.h | 4 ++
2 files changed, 79 insertions(+)
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 0b73a809e9e1..0b0b4e9a4318 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -713,6 +713,81 @@ union hv_msi_entry {
} __packed;
};
+struct hv_x64_segment_register {
+ __u64 base;
+ __u32 limit;
+ __u16 selector;
+ union {
+ struct {
+ __u16 segment_type : 4;
+ __u16 non_system_segment : 1;
+ __u16 descriptor_privilege_level : 2;
+ __u16 present : 1;
+ __u16 reserved : 4;
+ __u16 available : 1;
+ __u16 _long : 1;
+ __u16 _default : 1;
+ __u16 granularity : 1;
+ } __packed;
+ __u16 attributes;
+ };
+} __packed;
+
+struct hv_x64_table_register {
+ __u16 pad[3];
+ __u16 limit;
+ __u64 base;
+} __packed;
+
+struct hv_init_vp_context {
+ u64 rip;
+ u64 rsp;
+ u64 rflags;
+
+ struct hv_x64_segment_register cs;
+ struct hv_x64_segment_register ds;
+ struct hv_x64_segment_register es;
+ struct hv_x64_segment_register fs;
+ struct hv_x64_segment_register gs;
+ struct hv_x64_segment_register ss;
+ struct hv_x64_segment_register tr;
+ struct hv_x64_segment_register ldtr;
+
+ struct hv_x64_table_register idtr;
+ struct hv_x64_table_register gdtr;
+
+ u64 efer;
+ u64 cr0;
+ u64 cr3;
+ u64 cr4;
+ u64 msr_cr_pat;
+} __packed;
+
+union hv_input_vtl {
+ u8 as_uint8;
+ struct {
+ u8 target_vtl: 4;
+ u8 use_target_vtl: 1;
+ u8 reserved_z: 3;
+ };
+} __packed;
+
+struct hv_enable_vp_vtl {
+ u64 partition_id;
+ u32 vp_index;
+ union hv_input_vtl target_vtl;
+ u8 mbz0;
+ u16 mbz1;
+ struct hv_init_vp_context vp_context;
+} __packed;
+
+struct hv_get_vp_from_apic_id_in {
+ u64 partition_id;
+ union hv_input_vtl target_vtl;
+ u8 res[7];
+ u32 apic_ids[];
+} __packed;
+
#include <asm-generic/hyperv-tlfs.h>
#endif
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index b870983596b9..87258341fd7c 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -146,6 +146,7 @@ union hv_reference_tsc_msr {
/* Declare the various hypercall operations. */
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
+#define HVCALL_ENABLE_VP_VTL 0x000f
#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
#define HVCALL_SEND_IPI 0x000b
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
@@ -165,6 +166,8 @@ union hv_reference_tsc_msr {
#define HVCALL_MAP_DEVICE_INTERRUPT 0x007c
#define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d
#define HVCALL_RETARGET_INTERRUPT 0x007e
+#define HVCALL_START_VP 0x0099
+#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a
#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
#define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db
@@ -218,6 +221,7 @@ enum HV_GENERIC_SET_FORMAT {
#define HV_STATUS_INVALID_PORT_ID 17
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+#define HV_STATUS_VTL_ALREADY_ENABLED 134
/*
* The Hyper-V TimeRefCount register and the TSC
--
2.34.1
From: Saurabh Sengar <[email protected]> Sent: Tuesday, April 4, 2023 2:01 AM
>
> Virtual Trust Levels (VTL) helps enable Hyper-V Virtual Secure Mode (VSM)
> feature. VSM is a set of hypervisor capabilities and enlightenments
> offered to host and guest partitions which enable the creation and
> management of new security boundaries within operating system software.
> VSM achieves and maintains isolation through VTLs.
>
> Add early initialization for Virtual Trust Levels (VTL). This includes
> initializing the x86 platform for VTL and enabling boot support for
> secondary CPUs to start in targeted VTL context. For now, only enable
> the code for targeted VTL level as 2.
>
> When starting an AP at a VTL other than VTL0, the AP must start directly
> in 64-bit mode, bypassing the usual 16-bit -> 32-bit -> 64-bit mode
> transition sequence that occurs after waking up an AP with SIPI whose
> vector points to the 16-bit AP startup trampoline code.
>
> Signed-off-by: Saurabh Sengar <[email protected]>
> ---
> [V4]
> - replace initial_stack with current->thread.sp as per recent upstream changes
>
> arch/x86/hyperv/Makefile | 1 +
> arch/x86/hyperv/hv_vtl.c | 227 ++++++++++++++++++++++++++++++++
> arch/x86/include/asm/mshyperv.h | 10 ++
> arch/x86/kernel/cpu/mshyperv.c | 1 +
> 4 files changed, 239 insertions(+)
> create mode 100644 arch/x86/hyperv/hv_vtl.c
>
Reviewed-by: Michael Kelley <[email protected]>
On Tue, Apr 04, 2023 at 02:01:01AM -0700, Saurabh Sengar wrote:
> Add structs and hypercalls required to enable VTL support on x86.
>
> Signed-off-by: Saurabh Sengar <[email protected]>
> Reviewed-by: Michael Kelley <[email protected]>
> ---
> arch/x86/include/asm/hyperv-tlfs.h | 75 ++++++++++++++++++++++++++++++
> include/asm-generic/hyperv-tlfs.h | 4 ++
> 2 files changed, 79 insertions(+)
>
> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
> index 0b73a809e9e1..0b0b4e9a4318 100644
> --- a/arch/x86/include/asm/hyperv-tlfs.h
> +++ b/arch/x86/include/asm/hyperv-tlfs.h
> @@ -713,6 +713,81 @@ union hv_msi_entry {
> } __packed;
> };
>
> +struct hv_x64_segment_register {
> + __u64 base;
Ideally they arch-size types naming should be consistent: either with underscores or
without.
The majority of cases in this file are without underscores.
Reviewed-by: Stanislav Kinsburskii <[email protected]>
> + __u32 limit;
> + __u16 selector;
> + union {
> + struct {
> + __u16 segment_type : 4;
> + __u16 non_system_segment : 1;
> + __u16 descriptor_privilege_level : 2;
> + __u16 present : 1;
> + __u16 reserved : 4;
> + __u16 available : 1;
> + __u16 _long : 1;
> + __u16 _default : 1;
> + __u16 granularity : 1;
> + } __packed;
> + __u16 attributes;
> + };
> +} __packed;
> +
> +struct hv_x64_table_register {
> + __u16 pad[3];
> + __u16 limit;
> + __u64 base;
> +} __packed;
> +
> +struct hv_init_vp_context {
> + u64 rip;
> + u64 rsp;
> + u64 rflags;
> +
> + struct hv_x64_segment_register cs;
> + struct hv_x64_segment_register ds;
> + struct hv_x64_segment_register es;
> + struct hv_x64_segment_register fs;
> + struct hv_x64_segment_register gs;
> + struct hv_x64_segment_register ss;
> + struct hv_x64_segment_register tr;
> + struct hv_x64_segment_register ldtr;
> +
> + struct hv_x64_table_register idtr;
> + struct hv_x64_table_register gdtr;
> +
> + u64 efer;
> + u64 cr0;
> + u64 cr3;
> + u64 cr4;
> + u64 msr_cr_pat;
> +} __packed;
> +
> +union hv_input_vtl {
> + u8 as_uint8;
> + struct {
> + u8 target_vtl: 4;
> + u8 use_target_vtl: 1;
> + u8 reserved_z: 3;
> + };
> +} __packed;
> +
> +struct hv_enable_vp_vtl {
> + u64 partition_id;
> + u32 vp_index;
> + union hv_input_vtl target_vtl;
> + u8 mbz0;
> + u16 mbz1;
> + struct hv_init_vp_context vp_context;
> +} __packed;
> +
> +struct hv_get_vp_from_apic_id_in {
> + u64 partition_id;
> + union hv_input_vtl target_vtl;
> + u8 res[7];
> + u32 apic_ids[];
> +} __packed;
> +
> #include <asm-generic/hyperv-tlfs.h>
>
> #endif
> diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
> index b870983596b9..87258341fd7c 100644
> --- a/include/asm-generic/hyperv-tlfs.h
> +++ b/include/asm-generic/hyperv-tlfs.h
> @@ -146,6 +146,7 @@ union hv_reference_tsc_msr {
> /* Declare the various hypercall operations. */
> #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
> #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
> +#define HVCALL_ENABLE_VP_VTL 0x000f
> #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
> #define HVCALL_SEND_IPI 0x000b
> #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
> @@ -165,6 +166,8 @@ union hv_reference_tsc_msr {
> #define HVCALL_MAP_DEVICE_INTERRUPT 0x007c
> #define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d
> #define HVCALL_RETARGET_INTERRUPT 0x007e
> +#define HVCALL_START_VP 0x0099
> +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a
> #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
> #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
> #define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db
> @@ -218,6 +221,7 @@ enum HV_GENERIC_SET_FORMAT {
> #define HV_STATUS_INVALID_PORT_ID 17
> #define HV_STATUS_INVALID_CONNECTION_ID 18
> #define HV_STATUS_INSUFFICIENT_BUFFERS 19
> +#define HV_STATUS_VTL_ALREADY_ENABLED 134
>
> /*
> * The Hyper-V TimeRefCount register and the TSC
> --
> 2.34.1
On Tue, Apr 04, 2023 at 02:01:04AM -0700, Saurabh Sengar wrote:
> Virtual Trust Levels (VTL) helps enable Hyper-V Virtual Secure Mode (VSM)
> feature. VSM is a set of hypervisor capabilities and enlightenments
> offered to host and guest partitions which enable the creation and
> management of new security boundaries within operating system software.
> VSM achieves and maintains isolation through VTLs.
>
> Add early initialization for Virtual Trust Levels (VTL). This includes
> initializing the x86 platform for VTL and enabling boot support for
> secondary CPUs to start in targeted VTL context. For now, only enable
> the code for targeted VTL level as 2.
>
> When starting an AP at a VTL other than VTL0, the AP must start directly
> in 64-bit mode, bypassing the usual 16-bit -> 32-bit -> 64-bit mode
> transition sequence that occurs after waking up an AP with SIPI whose
> vector points to the 16-bit AP startup trampoline code.
>
> Signed-off-by: Saurabh Sengar <[email protected]>
> ---
> [V4]
> - replace initial_stack with current->thread.sp as per recent upstream changes
>
> arch/x86/hyperv/Makefile | 1 +
> arch/x86/hyperv/hv_vtl.c | 227 ++++++++++++++++++++++++++++++++
> arch/x86/include/asm/mshyperv.h | 10 ++
> arch/x86/kernel/cpu/mshyperv.c | 1 +
> 4 files changed, 239 insertions(+)
> create mode 100644 arch/x86/hyperv/hv_vtl.c
>
> diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
> index 5d2de10809ae..3a1548054b48 100644
> --- a/arch/x86/hyperv/Makefile
> +++ b/arch/x86/hyperv/Makefile
> @@ -1,6 +1,7 @@
> # SPDX-License-Identifier: GPL-2.0-only
> obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o
> obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o
> +obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o
>
> ifdef CONFIG_X86_64
> obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o
> diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
> new file mode 100644
> index 000000000000..1ba5d3b99b16
> --- /dev/null
> +++ b/arch/x86/hyperv/hv_vtl.c
> @@ -0,0 +1,227 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2023, Microsoft Corporation.
> + *
> + * Author:
> + * Saurabh Sengar <[email protected]>
> + */
> +
> +#include <asm/apic.h>
> +#include <asm/boot.h>
> +#include <asm/desc.h>
> +#include <asm/i8259.h>
> +#include <asm/mshyperv.h>
> +#include <asm/realmode.h>
> +
> +extern struct boot_params boot_params;
> +static struct real_mode_header hv_vtl_real_mode_header;
> +
> +void __init hv_vtl_init_platform(void)
> +{
> + pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
> +
> + x86_init.irqs.pre_vector_init = x86_init_noop;
> + x86_init.timers.timer_init = x86_init_noop;
> +
> + x86_platform.get_wallclock = get_rtc_noop;
> + x86_platform.set_wallclock = set_rtc_noop;
Nit: this code is VTL feature and hypevisor specific.
Defining vtl_get_rtc_noop instead of exporting get_rtc_noop would allow to make
this series less intrusive to the rest of x86 generic code.
Reviewed-by: Stanislav Kinsburskii <[email protected]>
> + x86_platform.get_nmi_reason = hv_get_nmi_reason;
> +
> + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT;
> + x86_platform.legacy.rtc = 0;
> + x86_platform.legacy.warm_reset = 0;
> + x86_platform.legacy.reserve_bios_regions = 0;
> + x86_platform.legacy.devices.pnpbios = 0;
> +}
> +
> +static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
> +{
> + return ((u64)desc->base3 << 32) | ((u64)desc->base2 << 24) |
> + (desc->base1 << 16) | desc->base0;
> +}
> +
> +static inline u32 hv_vtl_system_desc_limit(struct ldttss_desc *desc)
> +{
> + return ((u32)desc->limit1 << 16) | (u32)desc->limit0;
> +}
> +
> +typedef void (*secondary_startup_64_fn)(void*, void*);
> +static void hv_vtl_ap_entry(void)
> +{
> + ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params);
> +}
> +
> +static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored)
> +{
> + u64 status;
> + int ret = 0;
> + struct hv_enable_vp_vtl *input;
> + unsigned long irq_flags;
> +
> + struct desc_ptr gdt_ptr;
> + struct desc_ptr idt_ptr;
> +
> + struct ldttss_desc *tss;
> + struct ldttss_desc *ldt;
> + struct desc_struct *gdt;
> +
> + u64 rsp = current->thread.sp;
> + u64 rip = (u64)&hv_vtl_ap_entry;
> +
> + native_store_gdt(&gdt_ptr);
> + store_idt(&idt_ptr);
> +
> + gdt = (struct desc_struct *)((void *)(gdt_ptr.address));
> + tss = (struct ldttss_desc *)(gdt + GDT_ENTRY_TSS);
> + ldt = (struct ldttss_desc *)(gdt + GDT_ENTRY_LDT);
> +
> + local_irq_save(irq_flags);
> +
> + input = *this_cpu_ptr(hyperv_pcpu_input_arg);
> + memset(input, 0, sizeof(*input));
> +
> + input->partition_id = HV_PARTITION_ID_SELF;
> + input->vp_index = target_vp_index;
> + input->target_vtl.target_vtl = HV_VTL_MGMT;
> +
> + /*
> + * The x86_64 Linux kernel follows the 16-bit -> 32-bit -> 64-bit
> + * mode transition sequence after waking up an AP with SIPI whose
> + * vector points to the 16-bit AP startup trampoline code. Here in
> + * VTL2, we can't perform that sequence as the AP has to start in
> + * the 64-bit mode.
> + *
> + * To make this happen, we tell the hypervisor to load a valid 64-bit
> + * context (most of which is just magic numbers from the CPU manual)
> + * so that AP jumps right to the 64-bit entry of the kernel, and the
> + * control registers are loaded with values that let the AP fetch the
> + * code and data and carry on with work it gets assigned.
> + */
> +
> + input->vp_context.rip = rip;
> + input->vp_context.rsp = rsp;
> + input->vp_context.rflags = 0x0000000000000002;
> + input->vp_context.efer = __rdmsr(MSR_EFER);
> + input->vp_context.cr0 = native_read_cr0();
> + input->vp_context.cr3 = __native_read_cr3();
> + input->vp_context.cr4 = native_read_cr4();
> + input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT);
> + input->vp_context.idtr.limit = idt_ptr.size;
> + input->vp_context.idtr.base = idt_ptr.address;
> + input->vp_context.gdtr.limit = gdt_ptr.size;
> + input->vp_context.gdtr.base = gdt_ptr.address;
> +
> + /* Non-system desc (64bit), long, code, present */
> + input->vp_context.cs.selector = __KERNEL_CS;
> + input->vp_context.cs.base = 0;
> + input->vp_context.cs.limit = 0xffffffff;
> + input->vp_context.cs.attributes = 0xa09b;
> + /* Non-system desc (64bit), data, present, granularity, default */
> + input->vp_context.ss.selector = __KERNEL_DS;
> + input->vp_context.ss.base = 0;
> + input->vp_context.ss.limit = 0xffffffff;
> + input->vp_context.ss.attributes = 0xc093;
> +
> + /* System desc (128bit), present, LDT */
> + input->vp_context.ldtr.selector = GDT_ENTRY_LDT * 8;
> + input->vp_context.ldtr.base = hv_vtl_system_desc_base(ldt);
> + input->vp_context.ldtr.limit = hv_vtl_system_desc_limit(ldt);
> + input->vp_context.ldtr.attributes = 0x82;
> +
> + /* System desc (128bit), present, TSS, 0x8b - busy, 0x89 -- default */
> + input->vp_context.tr.selector = GDT_ENTRY_TSS * 8;
> + input->vp_context.tr.base = hv_vtl_system_desc_base(tss);
> + input->vp_context.tr.limit = hv_vtl_system_desc_limit(tss);
> + input->vp_context.tr.attributes = 0x8b;
> +
> + status = hv_do_hypercall(HVCALL_ENABLE_VP_VTL, input, NULL);
> +
> + if (!hv_result_success(status) &&
> + hv_result(status) != HV_STATUS_VTL_ALREADY_ENABLED) {
> + pr_err("HVCALL_ENABLE_VP_VTL failed for VP : %d ! [Err: %#llx\n]",
> + target_vp_index, status);
> + ret = -EINVAL;
> + goto free_lock;
> + }
> +
> + status = hv_do_hypercall(HVCALL_START_VP, input, NULL);
> +
> + if (!hv_result_success(status)) {
> + pr_err("HVCALL_START_VP failed for VP : %d ! [Err: %#llx]\n",
> + target_vp_index, status);
> + ret = -EINVAL;
> + }
> +
> +free_lock:
> + local_irq_restore(irq_flags);
> +
> + return ret;
> +}
> +
> +static int hv_vtl_apicid_to_vp_id(u32 apic_id)
> +{
> + u64 control;
> + u64 status;
> + unsigned long irq_flags;
> + struct hv_get_vp_from_apic_id_in *input;
> + u32 *output, ret;
> +
> + local_irq_save(irq_flags);
> +
> + input = *this_cpu_ptr(hyperv_pcpu_input_arg);
> + memset(input, 0, sizeof(*input));
> + input->partition_id = HV_PARTITION_ID_SELF;
> + input->apic_ids[0] = apic_id;
> +
> + output = (u32 *)input;
> +
> + control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
> + status = hv_do_hypercall(control, input, output);
> + ret = output[0];
> +
> + local_irq_restore(irq_flags);
> +
> + if (!hv_result_success(status)) {
> + pr_err("failed to get vp id from apic id %d, status %#llx\n",
> + apic_id, status);
> + return -EINVAL;
> + }
> +
> + return ret;
> +}
> +
> +static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
> +{
> + int vp_id;
> +
> + pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
> + vp_id = hv_vtl_apicid_to_vp_id(apicid);
> +
> + if (vp_id < 0) {
> + pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
> + return -EINVAL;
> + }
> + if (vp_id > ms_hyperv.max_vp_index) {
> + pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
> + return -EINVAL;
> + }
> +
> + return hv_vtl_bringup_vcpu(vp_id, start_eip);
> +}
> +
> +static int __init hv_vtl_early_init(void)
> +{
> + /*
> + * `boot_cpu_has` returns the runtime feature support,
> + * and here is the earliest it can be used.
> + */
> + if (cpu_feature_enabled(X86_FEATURE_XSAVE))
> + panic("XSAVE has to be disabled as it is not supported by this module.\n"
> + "Please add 'noxsave' to the kernel command line.\n");
> +
> + real_mode_header = &hv_vtl_real_mode_header;
> + apic->wakeup_secondary_cpu_64 = hv_vtl_wakeup_secondary_cpu;
> +
> + return 0;
> +}
> +early_initcall(hv_vtl_early_init);
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 71ed240ef66d..de4ad38f7d74 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -19,6 +19,10 @@
> */
> #define HV_IOAPIC_BASE_ADDRESS 0xfec00000
>
> +#define HV_VTL_NORMAL 0x0
> +#define HV_VTL_SECURE 0x1
> +#define HV_VTL_MGMT 0x2
> +
> union hv_ghcb;
>
> DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
> @@ -276,6 +280,12 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
> #endif /* CONFIG_HYPERV */
>
>
> +#ifdef CONFIG_HYPERV_VTL_MODE
> +void __init hv_vtl_init_platform(void);
> +#else
> +static inline void __init hv_vtl_init_platform(void) {}
> +#endif
> +
> #include <asm-generic/mshyperv.h>
>
> #endif
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index 5ee02af57dac..5180e3c50184 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -519,6 +519,7 @@ static void __init ms_hyperv_init_platform(void)
>
> /* Register Hyper-V specific clocksource */
> hv_init_clocksource();
> + hv_vtl_init_platform();
> #endif
> /*
> * TSC should be marked as unstable only after Hyper-V
> --
> 2.34.1
From: Stanislav Kinsburskii <[email protected]> Sent: Thursday, April 6, 2023 7:08 AM
>
> On Tue, Apr 04, 2023 at 02:01:04AM -0700, Saurabh Sengar wrote:
[snip]
> > --- /dev/null
> > +++ b/arch/x86/hyperv/hv_vtl.c
> > @@ -0,0 +1,227 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Copyright (c) 2023, Microsoft Corporation.
> > + *
> > + * Author:
> > + * Saurabh Sengar <[email protected]>
> > + */
> > +
> > +#include <asm/apic.h>
> > +#include <asm/boot.h>
> > +#include <asm/desc.h>
> > +#include <asm/i8259.h>
> > +#include <asm/mshyperv.h>
> > +#include <asm/realmode.h>
> > +
> > +extern struct boot_params boot_params;
> > +static struct real_mode_header hv_vtl_real_mode_header;
> > +
> > +void __init hv_vtl_init_platform(void)
> > +{
> > + pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
> > +
> > + x86_init.irqs.pre_vector_init = x86_init_noop;
> > + x86_init.timers.timer_init = x86_init_noop;
> > +
> > + x86_platform.get_wallclock = get_rtc_noop;
> > + x86_platform.set_wallclock = set_rtc_noop;
>
> Nit: this code is VTL feature and hypevisor specific.
> Defining vtl_get_rtc_noop instead of exporting get_rtc_noop would allow to make
> this series less intrusive to the rest of x86 generic code.
>
> Reviewed-by: Stanislav Kinsburskii <[email protected]>
>
Saurabh's initial version of the code did define its own version of
get/set_rtc_noop(). I had suggested that he use the existing functions
from x86 generic code, and KY had also commented about re-using
existing code wherever possible. :-) My suggestion was partly because
the VTL code is already re-using x86_init_noop(), and then just to avoid
code duplication. Admittedly, there's not much code being duplicated
in these stub functions. I slightly prefer re-using the existing functions,
but don't feel strongly about it.
Michael
On Thu, Apr 06, 2023 at 06:51:13AM -0700, Stanislav Kinsburskii wrote:
> On Tue, Apr 04, 2023 at 02:01:01AM -0700, Saurabh Sengar wrote:
> > Add structs and hypercalls required to enable VTL support on x86.
> >
> > Signed-off-by: Saurabh Sengar <[email protected]>
> > Reviewed-by: Michael Kelley <[email protected]>
> > ---
> > arch/x86/include/asm/hyperv-tlfs.h | 75 ++++++++++++++++++++++++++++++
> > include/asm-generic/hyperv-tlfs.h | 4 ++
> > 2 files changed, 79 insertions(+)
> >
> > diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
> > index 0b73a809e9e1..0b0b4e9a4318 100644
> > --- a/arch/x86/include/asm/hyperv-tlfs.h
> > +++ b/arch/x86/include/asm/hyperv-tlfs.h
> > @@ -713,6 +713,81 @@ union hv_msi_entry {
> > } __packed;
> > };
> >
> > +struct hv_x64_segment_register {
> > + __u64 base;
>
> Ideally they arch-size types naming should be consistent: either with underscores or
> without.
> The majority of cases in this file are without underscores.
Although I am fine either way, I think in a non-uapi file "without underscore" is prefered.
I can change this in next version.
Regards,
Saurabh
>
> Reviewed-by: Stanislav Kinsburskii <[email protected]>
>
> > + __u32 limit;
> > + __u16 selector;
> > + union {
> > + struct {
> > + __u16 segment_type : 4;
> > + __u16 non_system_segment : 1;
> > + __u16 descriptor_privilege_level : 2;
> > + __u16 present : 1;
> > + __u16 reserved : 4;
> > + __u16 available : 1;
> > + __u16 _long : 1;
> > + __u16 _default : 1;
> > + __u16 granularity : 1;
> > + } __packed;
> > + __u16 attributes;
> > + };
> > +} __packed;
> > +
> > +struct hv_x64_table_register {
> > + __u16 pad[3];
> > + __u16 limit;
> > + __u64 base;
> > +} __packed;
> > +
> > +struct hv_init_vp_context {
> > + u64 rip;
> > + u64 rsp;
> > + u64 rflags;
> > +
> > + struct hv_x64_segment_register cs;
> > + struct hv_x64_segment_register ds;
> > + struct hv_x64_segment_register es;
> > + struct hv_x64_segment_register fs;
> > + struct hv_x64_segment_register gs;
> > + struct hv_x64_segment_register ss;
> > + struct hv_x64_segment_register tr;
> > + struct hv_x64_segment_register ldtr;
> > +
> > + struct hv_x64_table_register idtr;
> > + struct hv_x64_table_register gdtr;
> > +
> > + u64 efer;
> > + u64 cr0;
> > + u64 cr3;
> > + u64 cr4;
> > + u64 msr_cr_pat;
> > +} __packed;
> > +
> > +union hv_input_vtl {
> > + u8 as_uint8;
> > + struct {
> > + u8 target_vtl: 4;
> > + u8 use_target_vtl: 1;
> > + u8 reserved_z: 3;
> > + };
> > +} __packed;
> > +
> > +struct hv_enable_vp_vtl {
> > + u64 partition_id;
> > + u32 vp_index;
> > + union hv_input_vtl target_vtl;
> > + u8 mbz0;
> > + u16 mbz1;
> > + struct hv_init_vp_context vp_context;
> > +} __packed;
> > +
> > +struct hv_get_vp_from_apic_id_in {
> > + u64 partition_id;
> > + union hv_input_vtl target_vtl;
> > + u8 res[7];
> > + u32 apic_ids[];
> > +} __packed;
> > +
> > #include <asm-generic/hyperv-tlfs.h>
> >
> > #endif
> > diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
> > index b870983596b9..87258341fd7c 100644
> > --- a/include/asm-generic/hyperv-tlfs.h
> > +++ b/include/asm-generic/hyperv-tlfs.h
> > @@ -146,6 +146,7 @@ union hv_reference_tsc_msr {
> > /* Declare the various hypercall operations. */
> > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
> > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
> > +#define HVCALL_ENABLE_VP_VTL 0x000f
> > #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
> > #define HVCALL_SEND_IPI 0x000b
> > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
> > @@ -165,6 +166,8 @@ union hv_reference_tsc_msr {
> > #define HVCALL_MAP_DEVICE_INTERRUPT 0x007c
> > #define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d
> > #define HVCALL_RETARGET_INTERRUPT 0x007e
> > +#define HVCALL_START_VP 0x0099
> > +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a
> > #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
> > #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
> > #define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db
> > @@ -218,6 +221,7 @@ enum HV_GENERIC_SET_FORMAT {
> > #define HV_STATUS_INVALID_PORT_ID 17
> > #define HV_STATUS_INVALID_CONNECTION_ID 18
> > #define HV_STATUS_INSUFFICIENT_BUFFERS 19
> > +#define HV_STATUS_VTL_ALREADY_ENABLED 134
> >
> > /*
> > * The Hyper-V TimeRefCount register and the TSC
> > --
> > 2.34.1
On Fri, Apr 07, 2023 at 08:56:29PM +0000, Michael Kelley (LINUX) wrote:
> From: Stanislav Kinsburskii <[email protected]> Sent: Thursday, April 6, 2023 7:08 AM
> >
> > On Tue, Apr 04, 2023 at 02:01:04AM -0700, Saurabh Sengar wrote:
>
> [snip]
>
> > > --- /dev/null
> > > +++ b/arch/x86/hyperv/hv_vtl.c
> > > @@ -0,0 +1,227 @@
> > > +// SPDX-License-Identifier: GPL-2.0
> > > +/*
> > > + * Copyright (c) 2023, Microsoft Corporation.
> > > + *
> > > + * Author:
> > > + * Saurabh Sengar <[email protected]>
> > > + */
> > > +
> > > +#include <asm/apic.h>
> > > +#include <asm/boot.h>
> > > +#include <asm/desc.h>
> > > +#include <asm/i8259.h>
> > > +#include <asm/mshyperv.h>
> > > +#include <asm/realmode.h>
> > > +
> > > +extern struct boot_params boot_params;
> > > +static struct real_mode_header hv_vtl_real_mode_header;
> > > +
> > > +void __init hv_vtl_init_platform(void)
> > > +{
> > > + pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
> > > +
> > > + x86_init.irqs.pre_vector_init = x86_init_noop;
> > > + x86_init.timers.timer_init = x86_init_noop;
> > > +
> > > + x86_platform.get_wallclock = get_rtc_noop;
> > > + x86_platform.set_wallclock = set_rtc_noop;
> >
> > Nit: this code is VTL feature and hypevisor specific.
> > Defining vtl_get_rtc_noop instead of exporting get_rtc_noop would allow to make
> > this series less intrusive to the rest of x86 generic code.
> >
> > Reviewed-by: Stanislav Kinsburskii <[email protected]>
> >
>
> Saurabh's initial version of the code did define its own version of
> get/set_rtc_noop(). I had suggested that he use the existing functions
> from x86 generic code, and KY had also commented about re-using
> existing code wherever possible. :-) My suggestion was partly because
> the VTL code is already re-using x86_init_noop(), and then just to avoid
> code duplication. Admittedly, there's not much code being duplicated
> in these stub functions. I slightly prefer re-using the existing functions,
> but don't feel strongly about it.
Thank you, Stanislav and Michael, for your comments.
Since the function is not doing anything significant, I think it's best to
minimize its effect on x86 generic code in this series.
I would like to redefine these functions in VTL code. Unless there are
compelling reasons against it, I plan to incorporate this change in the next
version.
- Saurabh
> Michael
> -----Original Message-----
> From: Saurabh Singh Sengar <[email protected]>
> Sent: Saturday, April 8, 2023 9:58 AM
> To: Stanislav Kinsburskii <[email protected]>
> Cc: [email protected]; [email protected]; [email protected];
> [email protected]; [email protected]; [email protected]; KY
> Srinivasan <[email protected]>; Haiyang Zhang
> <[email protected]>; [email protected]; Dexuan Cui
> <[email protected]>; [email protected]; Tianyu Lan
> <[email protected]>; Michael Kelley (LINUX)
> <[email protected]>; [email protected]; linux-
> [email protected]; [email protected]; [email protected];
> [email protected]
> Subject: [EXTERNAL] Re: [PATCH v4 2/5] x86/hyperv: Add VTL specific structs
> and hypercalls
>
> On Thu, Apr 06, 2023 at 06:51:13AM -0700, Stanislav Kinsburskii wrote:
> > On Tue, Apr 04, 2023 at 02:01:01AM -0700, Saurabh Sengar wrote:
> > > Add structs and hypercalls required to enable VTL support on x86.
> > >
> > > Signed-off-by: Saurabh Sengar <[email protected]>
> > > Reviewed-by: Michael Kelley <[email protected]>
> > > ---
> > > arch/x86/include/asm/hyperv-tlfs.h | 75
> > > ++++++++++++++++++++++++++++++ include/asm-generic/hyperv-tlfs.h |
> > > 4 ++
> > > 2 files changed, 79 insertions(+)
> > >
> > > diff --git a/arch/x86/include/asm/hyperv-tlfs.h
> > > b/arch/x86/include/asm/hyperv-tlfs.h
> > > index 0b73a809e9e1..0b0b4e9a4318 100644
> > > --- a/arch/x86/include/asm/hyperv-tlfs.h
> > > +++ b/arch/x86/include/asm/hyperv-tlfs.h
> > > @@ -713,6 +713,81 @@ union hv_msi_entry {
> > > } __packed;
> > > };
> > >
> > > +struct hv_x64_segment_register {
> > > + __u64 base;
> >
> > Ideally they arch-size types naming should be consistent: either with
> > underscores or without.
> > The majority of cases in this file are without underscores.
>
> Although I am fine either way, I think in a non-uapi file "without underscore"
> is prefered.
> I can change this in next version.
After reconsidering, I believe it would be wise to consult the "x86 maintainers" regarding this matter.
Hence, I intend to send the next version without this change.
- Saurabh
>
> Regards,
> Saurabh
>
>
> >
> > Reviewed-by: Stanislav Kinsburskii <[email protected]>
> >
> > > + __u32 limit;
> > > + __u16 selector;
> > > + union {
> > > + struct {
> > > + __u16 segment_type : 4;
> > > + __u16 non_system_segment : 1;
> > > + __u16 descriptor_privilege_level : 2;
> > > + __u16 present : 1;
> > > + __u16 reserved : 4;
> > > + __u16 available : 1;
> > > + __u16 _long : 1;
> > > + __u16 _default : 1;
> > > + __u16 granularity : 1;
> > > + } __packed;
> > > + __u16 attributes;
> > > + };
> > > +} __packed;
> > > +
> > > +struct hv_x64_table_register {
> > > + __u16 pad[3];
> > > + __u16 limit;
> > > + __u64 base;
> > > +} __packed;
> > > +
> > > +struct hv_init_vp_context {
> > > + u64 rip;
> > > + u64 rsp;
> > > + u64 rflags;
> > > +
> > > + struct hv_x64_segment_register cs;
> > > + struct hv_x64_segment_register ds;
> > > + struct hv_x64_segment_register es;
> > > + struct hv_x64_segment_register fs;
> > > + struct hv_x64_segment_register gs;
> > > + struct hv_x64_segment_register ss;
> > > + struct hv_x64_segment_register tr;
> > > + struct hv_x64_segment_register ldtr;
> > > +
> > > + struct hv_x64_table_register idtr;
> > > + struct hv_x64_table_register gdtr;
> > > +
> > > + u64 efer;
> > > + u64 cr0;
> > > + u64 cr3;
> > > + u64 cr4;
> > > + u64 msr_cr_pat;
> > > +} __packed;
> > > +
> > > +union hv_input_vtl {
> > > + u8 as_uint8;
> > > + struct {
> > > + u8 target_vtl: 4;
> > > + u8 use_target_vtl: 1;
> > > + u8 reserved_z: 3;
> > > + };
> > > +} __packed;
> > > +
> > > +struct hv_enable_vp_vtl {
> > > + u64 partition_id;
> > > + u32 vp_index;
> > > + union hv_input_vtl target_vtl;
> > > + u8 mbz0;
> > > + u16 mbz1;
> > > + struct hv_init_vp_context vp_context;
> > > +} __packed;
> > > +
> > > +struct hv_get_vp_from_apic_id_in {
> > > + u64 partition_id;
> > > + union hv_input_vtl target_vtl;
> > > + u8 res[7];
> > > + u32 apic_ids[];
> > > +} __packed;
> > > +
> > > #include <asm-generic/hyperv-tlfs.h>
> > >
> > > #endif
> > > diff --git a/include/asm-generic/hyperv-tlfs.h
> > > b/include/asm-generic/hyperv-tlfs.h
> > > index b870983596b9..87258341fd7c 100644
> > > --- a/include/asm-generic/hyperv-tlfs.h
> > > +++ b/include/asm-generic/hyperv-tlfs.h
> > > @@ -146,6 +146,7 @@ union hv_reference_tsc_msr {
> > > /* Declare the various hypercall operations. */
> > > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
> > > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
> > > +#define HVCALL_ENABLE_VP_VTL 0x000f
> > > #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
> > > #define HVCALL_SEND_IPI 0x000b
> > > #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
> > > @@ -165,6 +166,8 @@ union hv_reference_tsc_msr {
> > > #define HVCALL_MAP_DEVICE_INTERRUPT 0x007c
> > > #define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d
> > > #define HVCALL_RETARGET_INTERRUPT 0x007e
> > > +#define HVCALL_START_VP 0x0099
> > > +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a
> > > #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
> #define
> > > HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define
> > > HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db @@ -
> 218,6
> > > +221,7 @@ enum HV_GENERIC_SET_FORMAT {
> > > #define HV_STATUS_INVALID_PORT_ID 17
> > > #define HV_STATUS_INVALID_CONNECTION_ID 18
> > > #define HV_STATUS_INSUFFICIENT_BUFFERS 19
> > > +#define HV_STATUS_VTL_ALREADY_ENABLED 134
> > >
> > > /*
> > > * The Hyper-V TimeRefCount register and the TSC
> > > --
> > > 2.34.1