summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/Kconfig15
-rw-r--r--arch/x86/boot/boot.h37
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/head_64.S27
-rw-r--r--arch/x86/boot/compressed/misc.c12
-rw-r--r--arch/x86/boot/compressed/misc.h4
-rw-r--r--arch/x86/boot/compressed/pgtable.h2
-rw-r--r--arch/x86/boot/compressed/tdcall.S3
-rw-r--r--arch/x86/boot/compressed/tdx.c77
-rw-r--r--arch/x86/boot/compressed/tdx.h13
-rw-r--r--arch/x86/boot/cpuflags.c3
-rw-r--r--arch/x86/boot/cpuflags.h1
-rw-r--r--arch/x86/boot/io.h41
-rw-r--r--arch/x86/boot/main.c4
-rw-r--r--arch/x86/coco/Makefile2
-rw-r--r--arch/x86/coco/core.c22
-rw-r--r--arch/x86/coco/tdx/Makefile3
-rw-r--r--arch/x86/coco/tdx/tdcall.S205
-rw-r--r--arch/x86/coco/tdx/tdx.c692
-rw-r--r--arch/x86/include/asm/acenv.h14
-rw-r--r--arch/x86/include/asm/apic.h7
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/idtentry.h4
-rw-r--r--arch/x86/include/asm/io.h42
-rw-r--r--arch/x86/include/asm/kvm_para.h22
-rw-r--r--arch/x86/include/asm/mem_encrypt.h6
-rw-r--r--arch/x86/include/asm/realmode.h1
-rw-r--r--arch/x86/include/asm/shared/io.h34
-rw-r--r--arch/x86/include/asm/shared/tdx.h40
-rw-r--r--arch/x86/include/asm/tdx.h91
-rw-r--r--arch/x86/kernel/acpi/boot.c93
-rw-r--r--arch/x86/kernel/apic/apic.c10
-rw-r--r--arch/x86/kernel/apic/io_apic.c18
-rw-r--r--arch/x86/kernel/asm-offsets.c17
-rw-r--r--arch/x86/kernel/head64.c7
-rw-r--r--arch/x86/kernel/head_64.S28
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/process.c4
-rw-r--r--arch/x86/kernel/smpboot.c12
-rw-r--r--arch/x86/kernel/traps.c143
-rw-r--r--arch/x86/lib/kaslr.c2
-rw-r--r--arch/x86/mm/ioremap.c5
-rw-r--r--arch/x86/mm/mem_encrypt.c9
-rw-r--r--arch/x86/realmode/rm/header.S1
-rw-r--r--arch/x86/realmode/rm/trampoline_64.S57
-rw-r--r--arch/x86/realmode/rm/trampoline_common.S12
-rw-r--r--arch/x86/realmode/rm/wakemain.c4
-rw-r--r--arch/x86/virt/vmx/tdx/tdxcall.S96
49 files changed, 1835 insertions, 120 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4bed3abf444d..d90a33e96517 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -878,6 +878,21 @@ config ACRN_GUEST
IOT with small footprint and real-time features. More details can be
found in https://projectacrn.org/.
+config INTEL_TDX_GUEST
+ bool "Intel TDX (Trust Domain Extensions) - Guest Support"
+ depends on X86_64 && CPU_SUP_INTEL
+ depends on X86_X2APIC
+ select ARCH_HAS_CC_PLATFORM
+ select X86_MEM_ENCRYPT
+ select X86_MCE
+ help
+ Support running as a guest under Intel TDX. Without this support,
+ the guest kernel can not boot or run under TDX.
+ TDX includes memory encryption and integrity capabilities
+ which protect the confidentiality and integrity of guest
+ memory contents and CPU state. TDX guests are protected from
+ some attacks from the VMM.
+
endif #HYPERVISOR_GUEST
source "arch/x86/Kconfig.cpu"
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 34c9dbb6a47d..b42b91606ca8 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -26,6 +26,7 @@
#include "bitops.h"
#include "ctype.h"
#include "cpuflags.h"
+#include "io.h"
/* Useful macros */
#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
@@ -35,44 +36,10 @@ extern struct boot_params boot_params;
#define cpu_relax() asm volatile("rep; nop")
-/* Basic port I/O */
-static inline void outb(u8 v, u16 port)
-{
- asm volatile("outb %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u8 inb(u16 port)
-{
- u8 v;
- asm volatile("inb %1,%0" : "=a" (v) : "dN" (port));
- return v;
-}
-
-static inline void outw(u16 v, u16 port)
-{
- asm volatile("outw %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u16 inw(u16 port)
-{
- u16 v;
- asm volatile("inw %1,%0" : "=a" (v) : "dN" (port));
- return v;
-}
-
-static inline void outl(u32 v, u16 port)
-{
- asm volatile("outl %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u32 inl(u16 port)
-{
- u32 v;
- asm volatile("inl %1,%0" : "=a" (v) : "dN" (port));
- return v;
-}
-
static inline void io_delay(void)
{
const u16 DELAY_PORT = 0x80;
- asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT));
+ outb(0, DELAY_PORT);
}
/* These functions are used to reference data in other segments. */
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e69c3d2e0628..19e1905dcbf6 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -101,6 +101,7 @@ ifdef CONFIG_X86_64
endif
vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
+vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o
vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4cd661165d4a..d33f060900d2 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32)
pushl %eax
/* Enter paged protected Mode, activating Long Mode */
- movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
+ movl $CR0_STATE, %eax
movl %eax, %cr0
/* Jump from 32bit compatibility mode into 64bit mode. */
@@ -649,12 +649,28 @@ SYM_CODE_START(trampoline_32bit_src)
movl $MSR_EFER, %ecx
rdmsr
btsl $_EFER_LME, %eax
+ /* Avoid writing EFER if no change was made (for TDX guest) */
+ jc 1f
wrmsr
- popl %edx
+1: popl %edx
popl %ecx
+#ifdef CONFIG_X86_MCE
+ /*
+ * Preserve CR4.MCE if the kernel will enable #MC support.
+ * Clearing MCE may fault in some environments (that also force #MC
+ * support). Any machine check that occurs before #MC support is fully
+ * configured will crash the system regardless of the CR4.MCE value set
+ * here.
+ */
+ movl %cr4, %eax
+ andl $X86_CR4_MCE, %eax
+#else
+ movl $0, %eax
+#endif
+
/* Enable PAE and LA57 (if required) paging modes */
- movl $X86_CR4_PAE, %eax
+ orl $X86_CR4_PAE, %eax
testl %edx, %edx
jz 1f
orl $X86_CR4_LA57, %eax
@@ -668,8 +684,9 @@ SYM_CODE_START(trampoline_32bit_src)
pushl $__KERNEL_CS
pushl %eax
- /* Enable paging again */
- movl $(X86_CR0_PG | X86_CR0_PE), %eax
+ /* Enable paging again. */
+ movl %cr0, %eax
+ btsl $X86_CR0_PG_BIT, %eax
movl %eax, %cr0
lret
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index ca6820f99b40..cf690d8712f4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -48,6 +48,8 @@ void *memmove(void *dest, const void *src, size_t n);
*/
struct boot_params *boot_params;
+struct port_io_ops pio_ops;
+
memptr free_mem_ptr;
memptr free_mem_end_ptr;
@@ -374,6 +376,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
lines = boot_params->screen_info.orig_video_lines;
cols = boot_params->screen_info.orig_video_cols;
+ init_default_io_ops();
+
+ /*
+ * Detect TDX guest environment.
+ *
+ * It has to be done before console_init() in order to use
+ * paravirtualized port I/O operations if needed.
+ */
+ early_tdx_detect();
+
console_init();
/*
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 4ca2857ea041..4910bf230d7b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -22,17 +22,19 @@
#include <linux/linkage.h>
#include <linux/screen_info.h>
#include <linux/elf.h>
-#include <linux/io.h>
#include <asm/page.h>
#include <asm/boot.h>
#include <asm/bootparam.h>
#include <asm/desc_defs.h>
+#include "tdx.h"
+
#define BOOT_CTYPE_H
#include <linux/acpi.h>
#define BOOT_BOOT_H
#include "../ctype.h"
+#include "../io.h"
#include "efi.h"
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index 6ff7e81b5628..cc9b2529a086 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -6,7 +6,7 @@
#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0
#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE 0x70
+#define TRAMPOLINE_32BIT_CODE_SIZE 0x80
#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE
diff --git a/arch/x86/boot/compressed/tdcall.S b/arch/x86/boot/compressed/tdcall.S
new file mode 100644
index 000000000000..46d0495e0d3a
--- /dev/null
+++ b/arch/x86/boot/compressed/tdcall.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "../../coco/tdx/tdcall.S"
diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c
new file mode 100644
index 000000000000..918a7606f53c
--- /dev/null
+++ b/arch/x86/boot/compressed/tdx.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../cpuflags.h"
+#include "../string.h"
+#include "../io.h"
+#include "error.h"
+
+#include <vdso/limits.h>
+#include <uapi/asm/vmx.h>
+
+#include <asm/shared/tdx.h>
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void)
+{
+ error("TDVMCALL failed. TDX module bug?");
+}
+
+static inline unsigned int tdx_io_in(int size, u16 port)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = EXIT_REASON_IO_INSTRUCTION,
+ .r12 = size,
+ .r13 = 0,
+ .r14 = port,
+ };
+
+ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+ return UINT_MAX;
+
+ return args.r11;
+}
+
+static inline void tdx_io_out(int size, u16 port, u32 value)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = EXIT_REASON_IO_INSTRUCTION,
+ .r12 = size,
+ .r13 = 1,
+ .r14 = port,
+ .r15 = value,
+ };
+
+ __tdx_hypercall(&args, 0);
+}
+
+static inline u8 tdx_inb(u16 port)
+{
+ return tdx_io_in(1, port);
+}
+
+static inline void tdx_outb(u8 value, u16 port)
+{
+ tdx_io_out(1, port, value);
+}
+
+static inline void tdx_outw(u16 value, u16 port)
+{
+ tdx_io_out(2, port, value);
+}
+
+void early_tdx_detect(void)
+{
+ u32 eax, sig[3];
+
+ cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]);
+
+ if (memcmp(TDX_IDENT, sig, sizeof(sig)))
+ return;
+
+ /* Use hypercalls instead of I/O instructions */
+ pio_ops.f_inb = tdx_inb;
+ pio_ops.f_outb = tdx_outb;
+ pio_ops.f_outw = tdx_outw;
+}
diff --git a/arch/x86/boot/compressed/tdx.h b/arch/x86/boot/compressed/tdx.h
new file mode 100644
index 000000000000..9055482cd35c
--- /dev/null
+++ b/arch/x86/boot/compressed/tdx.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_COMPRESSED_TDX_H
+#define BOOT_COMPRESSED_TDX_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+void early_tdx_detect(void);
+#else
+static inline void early_tdx_detect(void) { };
+#endif
+
+#endif /* BOOT_COMPRESSED_TDX_H */
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index a0b75f73dc63..a83d67ec627d 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -71,8 +71,7 @@ int has_eflag(unsigned long mask)
# define EBX_REG "=b"
#endif
-static inline void cpuid_count(u32 id, u32 count,
- u32 *a, u32 *b, u32 *c, u32 *d)
+void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d)
{
asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t"
"cpuid \n\t"
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 2e20814d3ce3..475b8fde90f7 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -17,5 +17,6 @@ extern u32 cpu_vendor[3];
int has_eflag(unsigned long mask);
void get_cpuflags(void);
+void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d);
#endif
diff --git a/arch/x86/boot/io.h b/arch/x86/boot/io.h
new file mode 100644
index 000000000000..110880907f87
--- /dev/null
+++ b/arch/x86/boot/io.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_IO_H
+#define BOOT_IO_H
+
+#include <asm/shared/io.h>
+
+#undef inb
+#undef inw
+#undef inl
+#undef outb
+#undef outw
+#undef outl
+
+struct port_io_ops {
+ u8 (*f_inb)(u16 port);
+ void (*f_outb)(u8 v, u16 port);
+ void (*f_outw)(u16 v, u16 port);
+};
+
+extern struct port_io_ops pio_ops;
+
+/*
+ * Use the normal I/O instructions by default.
+ * TDX guests override these to use hypercalls.
+ */
+static inline void init_default_io_ops(void)
+{
+ pio_ops.f_inb = __inb;
+ pio_ops.f_outb = __outb;
+ pio_ops.f_outw = __outw;
+}
+
+/*
+ * Redirect port I/O operations via pio_ops callbacks.
+ * TDX guests override these callbacks with TDX-specific helpers.
+ */
+#define inb pio_ops.f_inb
+#define outb pio_ops.f_outb
+#define outw pio_ops.f_outw
+
+#endif
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index e3add857c2c9..1202d4f8a390 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -17,6 +17,8 @@
struct boot_params boot_params __attribute__((aligned(16)));
+struct port_io_ops pio_ops;
+
char *HEAP = _end;
char *heap_end = _end; /* Default end of heap = no heap */
@@ -133,6 +135,8 @@ static void init_heap(void)
void main(void)
{
+ init_default_io_ops();
+
/* First, copy the boot header into the "zeropage" */
copy_boot_params();
diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile
index c1ead00017a7..c816acf78b6a 100644
--- a/arch/x86/coco/Makefile
+++ b/arch/x86/coco/Makefile
@@ -4,3 +4,5 @@ KASAN_SANITIZE_core.o := n
CFLAGS_core.o += -fno-stack-protector
obj-y += core.o
+
+obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index dafd4881ce29..49b44f881484 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,15 @@ static u64 cc_mask __ro_after_init;
static bool intel_cc_platform_has(enum cc_attr attr)
{
- return false;
+ switch (attr) {
+ case CC_ATTR_GUEST_UNROLL_STRING_IO:
+ case CC_ATTR_HOTPLUG_DISABLED:
+ case CC_ATTR_GUEST_MEM_ENCRYPT:
+ case CC_ATTR_MEM_ENCRYPT:
+ return true;
+ default:
+ return false;
+ }
}
/*
@@ -90,9 +98,18 @@ EXPORT_SYMBOL_GPL(cc_platform_has);
u64 cc_mkenc(u64 val)
{
+ /*
+ * Both AMD and Intel use a bit in the page table to indicate
+ * encryption status of the page.
+ *
+ * - for AMD, bit *set* means the page is encrypted
+ * - for Intel *clear* means encrypted.
+ */
switch (vendor) {
case CC_VENDOR_AMD:
return val | cc_mask;
+ case CC_VENDOR_INTEL:
+ return val & ~cc_mask;
default:
return val;
}
@@ -100,9 +117,12 @@ u64 cc_mkenc(u64 val)
u64 cc_mkdec(u64 val)
{
+ /* See comment in cc_mkenc() */
switch (vendor) {
case CC_VENDOR_AMD:
return val & ~cc_mask;
+ case CC_VENDOR_INTEL:
+ return val | cc_mask;
default:
return val;
}
diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile
new file mode 100644
index 000000000000..46c55998557d
--- /dev/null
+++ b/arch/x86/coco/tdx/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += tdx.o tdcall.o
diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S
new file mode 100644
index 000000000000..f9eb1134f22d
--- /dev/null
+++ b/arch/x86/coco/tdx/tdcall.S
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <asm/frame.h>
+#include <asm/unwind_hints.h>
+
+#include <linux/linkage.h>
+#include <linux/bits.h>
+#include <linux/errno.h>
+
+#include "../../virt/vmx/tdx/tdxcall.S"
+
+/*
+ * Bitmasks of exposed registers (with VMM).
+ */
+#define TDX_R10 BIT(10)
+#define TDX_R11 BIT(11)
+#define TDX_R12 BIT(12)
+#define TDX_R13 BIT(13)
+#define TDX_R14 BIT(14)
+#define TDX_R15 BIT(15)
+
+/*
+ * These registers are clobbered to hold arguments for each
+ * TDVMCALL. They are safe to expose to the VMM.
+ * Each bit in this mask represents a register ID. Bit field
+ * details can be found in TDX GHCI specification, section
+ * titled "TDCALL [TDG.VP.VMCALL] leaf".
+ */
+#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \
+ TDX_R12 | TDX_R13 | \
+ TDX_R14 | TDX_R15 )
+
+/*
+ * __tdx_module_call() - Used by TDX guests to request services from
+ * the TDX module (does not include VMM services) using TDCALL instruction.
+ *
+ * Transforms function call register arguments into the TDCALL register ABI.
+ * After TDCALL operation, TDX module output is saved in @out (if it is
+ * provided by the user).
+ *
+ *-------------------------------------------------------------------------
+ * TDCALL ABI:
+ *-------------------------------------------------------------------------
+ * Input Registers:
+ *
+ * RAX - TDCALL Leaf number.
+ * RCX,RDX,R8-R9 - TDCALL Leaf specific input registers.
+ *
+ * Output Registers:
+ *
+ * RAX - TDCALL instruction error code.
+ * RCX,RDX,R8-R11 - TDCALL Leaf specific output registers.
+ *
+ *-------------------------------------------------------------------------
+ *
+ * __tdx_module_call() function ABI:
+ *
+ * @fn (RDI) - TDCALL Leaf ID, moved to RAX
+ * @rcx (RSI) - Input parameter 1, moved to RCX
+ * @rdx (RDX) - Input parameter 2, moved to RDX
+ * @r8 (RCX) - Input parameter 3, moved to R8
+ * @r9 (R8) - Input parameter 4, moved to R9
+ *
+ * @out (R9) - struct tdx_module_output pointer
+ * stored temporarily in R12 (not
+ * shared with the TDX module). It
+ * can be NULL.
+ *
+ * Return status of TDCALL via RAX.
+ */
+SYM_FUNC_START(__tdx_module_call)
+ FRAME_BEGIN
+ TDX_MODULE_CALL host=0
+ FRAME_END
+ RET
+SYM_FUNC_END(__tdx_module_call)
+
+/*
+ * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf
+ * of TDCALL instruction
+ *
+ * Transforms values in function call argument struct tdx_hypercall_args @args
+ * into the TDCALL register ABI. After TDCALL operation, VMM output is saved
+ * back in @args.
+ *
+ *-------------------------------------------------------------------------
+ * TD VMCALL ABI:
+ *-------------------------------------------------------------------------
+ *
+ * Input Registers:
+ *
+ * RAX - TDCALL instruction leaf number (0 - TDG.VP.VMCALL)
+ * RCX - BITMAP which controls which part of TD Guest GPR
+ * is passed as-is to the VMM and back.
+ * R10 - Set 0 to indicate TDCALL follows standard TDX ABI
+ * specification. Non zero value indicates vendor
+ * specific ABI.
+ * R11 - VMCALL sub function number
+ * RBX, RBP, RDI, RSI - Used to pass VMCALL sub function specific arguments.
+ * R8-R9, R12-R15 - Same as above.
+ *
+ * Output Registers:
+ *
+ * RAX - TDCALL instruction status (Not related to hypercall
+ * output).
+ * R10 - Hypercall output error code.
+ * R11-R15 - Hypercall sub function specific output values.
+ *
+ *-------------------------------------------------------------------------
+ *
+ * __tdx_hypercall() function ABI:
+ *
+ * @args (RDI) - struct tdx_hypercall_args for input and output
+ * @flags (RSI) - TDX_HCALL_* flags
+ *
+ * On successful completion, return the hypercall error code.
+ */
+SYM_FUNC_START(__tdx_hypercall)
+ FRAME_BEGIN
+
+ /* Save callee-saved GPRs as mandated by the x86_64 ABI */
+ push %r15
+ push %r14
+ push %r13
+ push %r12
+
+ /* Mangle function call ABI into TDCALL ABI: */
+ /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */
+ xor %eax, %eax
+
+ /* Copy hypercall registers from arg struct: */
+ movq TDX_HYPERCALL_r10(%rdi), %r10
+ movq TDX_HYPERCALL_r11(%rdi), %r11
+ movq TDX_HYPERCALL_r12(%rdi), %r12
+ movq TDX_HYPERCALL_r13(%rdi), %r13
+ movq TDX_HYPERCALL_r14(%rdi), %r14
+ movq TDX_HYPERCALL_r15(%rdi), %r15
+
+ movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx
+
+ /*
+ * For the idle loop STI needs to be called directly before the TDCALL
+ * that enters idle (EXIT_REASON_HLT case). STI instruction enables
+ * interrupts only one instruction later. If there is a window between
+ * STI and the instruction that emulates the HALT state, there is a
+ * chance for interrupts to happen in this window, which can delay the
+ * HLT operation indefinitely. Since this is the not the desired
+ * result, conditionally call STI before TDCALL.
+ */
+ testq $TDX_HCALL_ISSUE_STI, %rsi
+ jz .Lskip_sti
+ sti
+.Lskip_sti:
+ tdcall
+
+ /*
+ * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that
+ * something has gone horribly wrong with the TDX module.
+ *
+ * The return status of the hypercall operation is in a separate
+ * register (in R10). Hypercall errors are a part of normal operation
+ * and are handled by callers.
+ */
+ testq %rax, %rax
+ jne .Lpanic
+
+ /* TDVMCALL leaf return code is in R10 */
+ movq %r10, %rax
+
+ /* Copy hypercall result registers to arg struct if needed */
+ testq $TDX_HCALL_HAS_OUTPUT, %rsi
+ jz .Lout
+
+ movq %r10, TDX_HYPERCALL_r10(%rdi)
+ movq %r11, TDX_HYPERCALL_r11(%rdi)
+ movq %r12, TDX_HYPERCALL_r12(%rdi)
+ movq %r13, TDX_HYPERCALL_r13(%rdi)
+ movq %r14, TDX_HYPERCALL_r14(%rdi)
+ movq %r15, TDX_HYPERCALL_r15(%rdi)
+.Lout:
+ /*
+ * Zero out registers exposed to the VMM to avoid speculative execution
+ * with VMM-controlled values. This needs to include all registers
+ * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15
+ * context will be restored.
+ */
+ xor %r10d, %r10d
+ xor %r11d, %r11d
+
+ /* Restore callee-saved GPRs as mandated by the x86_64 ABI */
+ pop %r12
+ pop %r13
+ pop %r14
+ pop %r15
+
+ FRAME_END
+
+ RET
+.Lpanic:
+ call __tdx_hypercall_failed
+ /* __tdx_hypercall_failed never returns */
+ REACHABLE
+ jmp .Lpanic
+SYM_FUNC_END(__tdx_hypercall)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
new file mode 100644
index 000000000000..03deb4d6920d
--- /dev/null
+++ b/arch/x86/coco/tdx/tdx.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2022 Intel Corporation */
+
+#undef pr_fmt
+#define pr_fmt(fmt) "tdx: " fmt
+
+#include <linux/cpufeature.h>
+#include <asm/coco.h>
+#include <asm/tdx.h>
+#include <asm/vmx.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <asm/pgtable.h>
+
+/* TDX module Call Leaf IDs */
+#define TDX_GET_INFO 1
+#define TDX_GET_VEINFO 3
+#define TDX_ACCEPT_PAGE 6
+
+/* TDX hypercall Leaf IDs */
+#define TDVMCALL_MAP_GPA 0x10001
+
+/* MMIO direction */
+#define EPT_READ 0
+#define EPT_WRITE 1
+
+/* Port I/O direction */
+#define PORT_READ 0
+#define PORT_WRITE 1
+
+/* See Exit Qualification for I/O Instructions in VMX documentation */
+#define VE_IS_IO_IN(e) ((e) & BIT(3))
+#define VE_GET_IO_SIZE(e) (((e) & GENMASK(2, 0)) + 1)
+#define VE_GET_PORT_NUM(e) ((e) >> 16)
+#define VE_IS_IO_STRING(e) ((e) & BIT(4))
+
+/*
+ * Wrapper for standard use of __tdx_hypercall with no output aside from
+ * return code.
+ */
+static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = fn,
+ .r12 = r12,
+ .r13 = r13,
+ .r14 = r14,
+ .r15 = r15,
+ };
+
+ return __tdx_hypercall(&args, 0);
+}
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void)
+{
+ panic("TDVMCALL failed. TDX module bug?");
+}
+
+/*
+ * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined
+ * independently from but are currently matched 1:1 with VMX EXIT_REASONs.
+ * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and
+ * guest sides of these calls.
+ */
+static u64 hcall_func(u64 exit_reason)
+{
+ return exit_reason;
+}
+
+#ifdef CONFIG_KVM_GUEST
+long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2,
+ unsigned long p3, unsigned long p4)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = nr,
+ .r11 = p1,
+ .r12 = p2,
+ .r13 = p3,
+ .r14 = p4,
+ };
+
+ return __tdx_hypercall(&args, 0);
+}
+EXPORT_SYMBOL_GPL(tdx_kvm_hypercall);
+#endif
+
+/*
+ * Used for TDX guests to make calls directly to the TD module. This
+ * should only be used for calls that have no legitimate reason to fail
+ * or where the kernel can not survive the call failing.
+ */
+static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
+ struct tdx_module_output *out)
+{
+ if (__tdx_module_call(fn, rcx, rdx, r8, r9, out))
+ panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
+}
+
+static u64 get_cc_mask(void)
+{
+ struct tdx_module_output out;
+ unsigned int gpa_width;
+
+ /*
+ * TDINFO TDX module call is used to get the TD execution environment
+ * information like GPA width, number of available vcpus, debug mode
+ * information, etc. More details about the ABI can be found in TDX
+ * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL
+ * [TDG.VP.INFO].
+ *
+ * The GPA width that comes out of this call is critical. TDX guests
+ * can not meaningfully run without it.
+ */
+ tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
+
+ gpa_width = out.rcx & GENMASK(5, 0);
+
+ /*
+ * The highest bit of a guest physical address is the "sharing" bit.
+ * Set it for shared pages and clear it for private pages.
+ */
+ return BIT_ULL(gpa_width - 1);
+}
+
+static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_HLT),
+ .r12 = irq_disabled,
+ };
+
+ /*
+ * Emulate HLT operation via hypercall. More info about ABI
+ * can be found in TDX Guest-Host-Communication Interface
+ * (GHCI), section 3.8 TDG.VP.VMCALL<Instruction.HLT>.
+ *
+ * The VMM uses the "IRQ disabled" param to understand IRQ
+ * enabled status (RFLAGS.IF) of the TD guest and to determine
+ * whether or not it should schedule the halted vCPU if an
+ * IRQ becomes pending. E.g. if IRQs are disabled, the VMM
+ * can keep the vCPU in virtual HLT, even if an IRQ is
+ * pending, without hanging/breaking the guest.
+ */
+ return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
+}
+
+static bool handle_halt(void)
+{
+ /*
+ * Since non safe halt is mainly used in CPU offlining
+ * and the guest will always stay in the halt state, don't
+ * call the STI instruction (set do_sti as false).
+ */
+ const bool irq_disabled = irqs_disabled();
+ const bool do_sti = false;
+
+ if (__halt(irq_disabled, do_sti))
+ return false;
+
+ return true;
+}
+
+void __cpuidle tdx_safe_halt(void)
+{
+ /*
+ * For do_sti=true case, __tdx_hypercall() function enables
+ * interrupts using the STI instruction before the TDCALL. So
+ * set irq_disabled as false.
+ */
+ const bool irq_disabled = false;
+ const bool do_sti = true;
+
+ /*
+ * Use WARN_ONCE() to report the failure.
+ */
+ if (__halt(irq_disabled, do_sti))
+ WARN_ONCE(1, "HLT instruction emulation failed\n");
+}
+
+static bool read_msr(struct pt_regs *regs)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_MSR_READ),
+ .r12 = regs->cx,
+ };
+
+ /*
+ * Emulate the MSR read via hypercall. More info about ABI
+ * can be found in TDX Guest-Host-Communication Interface
+ * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>".
+ */
+ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+ return false;
+
+ regs->ax = lower_32_bits(args.r11);
+ regs->dx = upper_32_bits(args.r11);
+ return true;
+}
+
+static bool write_msr(struct pt_regs *regs)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_MSR_WRITE),
+ .r12 = regs->cx,
+ .r13 = (u64)regs->dx << 32 | regs->ax,
+ };
+
+ /*
+ * Emulate the MSR write via hypercall. More info about ABI
+ * can be found in TDX Guest-Host-Communication Interface
+ * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>".
+ */
+ return !__tdx_hypercall(&args, 0);
+}
+
+static bool handle_cpuid(struct pt_regs *regs)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_CPUID),
+ .r12 = regs->ax,
+ .r13 = regs->cx,
+ };
+
+ /*
+ * Only allow VMM to control range reserved for hypervisor
+ * communication.
+ *
+ * Return all-zeros for any CPUID outside the range. It matches CPU
+ * behaviour for non-supported leaf.
+ */
+ if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) {
+ regs->ax = regs->bx = regs->cx = regs->dx = 0;
+ return true;
+ }
+
+ /*
+ * Emulate the CPUID instruction via a hypercall. More info about
+ * ABI can be found in TDX Guest-Host-Communication Interface
+ * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>".
+ */
+ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+ return false;
+
+ /*
+ * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of
+ * EAX, EBX, ECX, EDX registers after the CPUID instruction execution.
+ * So copy the register contents back to pt_regs.
+ */
+ regs->ax = args.r12;
+ regs->bx = args.r13;
+ regs->cx = args.r14;
+ regs->dx = args.r15;
+
+ return true;
+}
+
+static bool mmio_read(int size, unsigned long addr, unsigned long *val)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_EPT_VIOLATION),
+ .r12 = size,
+ .r13 = EPT_READ,
+ .r14 = addr,
+ .r15 = *val,
+ };
+
+ if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+ return false;
+ *val = args.r11;
+ return true;
+}
+
+static bool mmio_write(int size, unsigned long addr, unsigned long val)
+{
+ return !_tdx_hypercall(hcall_func(EXIT_REASON_EPT_VIOLATION), size,
+ EPT_WRITE, addr, val);
+}
+
+static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+{
+ char buffer[MAX_INSN_SIZE];
+ unsigned long *reg, val;
+ struct insn insn = {};
+ enum mmio_type mmio;
+ int size, extend_size;
+ u8 extend_val = 0;
+
+ /* Only in-kernel MMIO is supported */
+ if (WARN_ON_ONCE(user_mode(regs)))
+ return false;
+
+ if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE))
+ return false;
+
+ if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64))
+ return false;
+
+ mmio = insn_decode_mmio(&insn, &size);
+ if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+ return false;
+
+ if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ reg = insn_get_modrm_reg_ptr(&insn, regs);
+ if (!reg)
+ return false;
+ }
+
+ ve->instr_len = insn.length;
+
+ /* Handle writes first */
+ switch (mmio) {
+ case MMIO_WRITE:
+ memcpy(&val, reg, size);
+ return mmio_write(size, ve->gpa, val);
+ case MMIO_WRITE_IMM:
+ val = insn.immediate.value;
+ return mmio_write(size, ve->gpa, val);
+ case MMIO_READ:
+ case MMIO_READ_ZERO_EXTEND:
+ case MMIO_READ_SIGN_EXTEND:
+ /* Reads are handled below */
+ break;
+ case MMIO_MOVS:
+ case MMIO_DECODE_FAILED:
+ /*
+ * MMIO was accessed with an instruction that could not be
+ * decoded or handled properly. It was likely not using io.h
+ * helpers or accessed MMIO accidentally.
+ */
+ return false;
+ default:
+ WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?");
+ return false;
+ }
+
+ /* Handle reads */
+ if (!mmio_read(size, ve->gpa, &val))
+ return false;
+
+ switch (mmio) {
+ case MMIO_READ:
+ /* Zero-extend for 32-bit operation */
+ extend_size = size == 4 ? sizeof(*reg) : 0;
+ break;
+ case MMIO_READ_ZERO_EXTEND:
+ /* Zero extend based on operand size */
+ extend_size = insn.opnd_bytes;
+ break;
+ case MMIO_READ_SIGN_EXTEND:
+ /* Sign extend based on operand size */
+ extend_size = insn.opnd_bytes;
+ if (size == 1 && val & BIT(7))
+ extend_val = 0xFF;
+ else if (size > 1 && val & BIT(15))
+ extend_val = 0xFF;
+ break;
+ default:
+ /* All other cases has to be covered with the first switch() */
+ WARN_ON_ONCE(1);
+ return false;
+ }
+
+ if (extend_size)
+ memset(reg, extend_val, extend_size);
+ memcpy(reg, &val, size);
+ return true;
+}
+
+static bool handle_in(struct pt_regs *regs, int size, int port)
+{
+ struct tdx_hypercall_args args = {
+ .r10 = TDX_HYPERCALL_STANDARD,
+ .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
+ .r12 = size,
+ .r13 = PORT_READ,
+ .r14 = port,
+ };
+ u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+ bool success;
+
+ /*
+ * Emulate the I/O read via hypercall. More info about ABI can be found
+ * in TDX Guest-Host-Communication Interface (GHCI) section titled
+ * "TDG.VP.VMCALL<Instruction.IO>".
+ */
+ success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT);
+
+ /* Update part of the register affected by the emulated instruction */
+ regs->ax &= ~mask;
+ if (success)
+ regs->ax |= args.r11 & mask;
+
+ return success;
+}
+
+static bool handle_out(struct pt_regs *regs, int size, int port)
+{
+ u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+
+ /*
+ * Emulate the I/O write via hypercall. More info about ABI can be found
+ * in TDX Guest-Host-Communication Interface (GHCI) section titled
+ * "TDG.VP.VMCALL<Instruction.IO>".
+ */
+ return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size,
+ PORT_WRITE, port, regs->ax & mask);
+}
+
+/*
+ * Emulate I/O using hypercall.
+ *
+ * Assumes the IO instruction was using ax, which is enforced
+ * by the standard io.h macros.
+ *
+ * Return True on success or False on failure.
+ */
+static bool handle_io(struct pt_regs *regs, u32 exit_qual)
+{
+ int size, port;
+ bool in;
+
+ if (VE_IS_IO_STRING(exit_qual))
+ return false;
+
+ in = VE_IS_IO_IN(exit_qual);
+ size = VE_GET_IO_SIZE(exit_qual);
+ port = VE_GET_PORT_NUM(exit_qual);
+
+
+ if (in)
+ return handle_in(regs, size, port);
+ else
+ return handle_out(regs, size, port);
+}
+
+/*
+ * Early #VE exception handler. Only handles a subset of port I/O.
+ * Intended only for earlyprintk. If failed, return false.
+ */
+__init bool tdx_early_handle_ve(struct pt_regs *regs)
+{
+ struct ve_info ve;
+
+ tdx_get_ve_info(&ve);
+
+ if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION)
+ return false;
+
+ return handle_io(regs, ve.exit_qual);
+}
+
+void tdx_get_ve_info(struct ve_info *ve)
+{
+ struct tdx_module_output out;
+
+ /*
+ * Called during #VE handling to retrieve the #VE info from the
+ * TDX module.
+ *
+ * This has to be called early in #VE handling. A "nested" #VE which
+ * occurs before this will raise a #DF and is not recoverable.
+ *
+ * The call retrieves the #VE info from the TDX module, which also
+ * clears the "#VE valid" flag. This must be done before anything else
+ * because any #VE that occurs while the valid flag is set will lead to
+ * #DF.
+ *
+ * Note, the TDX module treats virtual NMIs as inhibited if the #VE
+ * valid flag is set. It means that NMI=>#VE will not result in a #DF.
+ */
+ tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out);
+
+ /* Transfer the output parameters */
+ ve->exit_reason = out.rcx;
+ ve->exit_qual = out.rdx;
+ ve->gla = out.r8;
+ ve->gpa = out.r9;
+ ve->instr_len = lower_32_bits(out.r10);
+ ve->instr_info = upper_32_bits(out.r10);
+}
+
+/* Handle the user initiated #VE */
+static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
+{
+ switch (ve->exit_reason) {
+ case EXIT_REASON_CPUID:
+ return handle_cpuid(regs);
+ default:
+ pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+ return false;
+ }
+}
+
+/* Handle the kernel #VE */
+static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
+{
+ switch (ve->exit_reason) {
+ case EXIT_REASON_HLT:
+ return handle_halt();
+ case EXIT_REASON_MSR_READ:
+ return read_msr(regs);
+ case EXIT_REASON_MSR_WRITE:
+ return write_msr(regs);
+ case EXIT_REASON_CPUID:
+ return handle_cpuid(regs);
+ case EXIT_REASON_EPT_VIOLATION:
+ return handle_mmio(regs, ve);
+ case EXIT_REASON_IO_INSTRUCTION:
+ return handle_io(regs, ve->exit_qual);
+ default:
+ pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+ return false;
+ }
+}
+
+bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve)
+{
+ bool ret;
+
+ if (user_mode(regs))
+ ret = virt_exception_user(regs, ve);
+ else
+ ret = virt_exception_kernel(regs, ve);
+
+ /* After successful #VE handling, move the IP */
+ if (ret)
+ regs->ip += ve->instr_len;
+
+ return ret;
+}
+
+static bool tdx_tlb_flush_required(bool private)
+{
+ /*
+ * TDX guest is responsible for flushing TLB on private->shared
+ * transition. VMM is responsible for flushing on shared->private.
+ *
+ * The VMM _can't_ flush private addresses as it can't generate PAs
+ * with the guest's HKID. Shared memory isn't subject to integrity
+ * checking, i.e. the VMM doesn't need to flush for its own protection.
+ *
+ * There's no need to flush when converting from shared to private,
+ * as flushing is the VMM's responsibility in this case, e.g. it must
+ * flush to avoid integrity failures in the face of a buggy or
+ * malicious guest.
+ */
+ return !private;
+}
+
+static bool tdx_cache_flush_required(void)
+{
+ /*
+ * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence.
+ * TDX doesn't have such capability.
+ *
+ * Flush cache unconditionally.
+ */
+ return true;
+}
+
+static bool try_accept_one(phys_addr_t *start, unsigned long len,
+ enum pg_level pg_level)
+{
+ unsigned long accept_size = page_level_size(pg_level);
+ u64 tdcall_rcx;
+ u8 page_size;
+
+ if (!IS_ALIGNED(*start, accept_size))
+ return false;
+
+ if (len < accept_size)
+ return false;
+
+ /*
+ * Pass the page physical address to the TDX module to accept the
+ * pending, private page.
+ *
+ * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G.
+ */
+ switch (pg_level) {
+ case PG_LEVEL_4K:
+ page_size = 0;
+ break;
+ case PG_LEVEL_2M:
+ page_size = 1;
+ break;
+ case PG_LEVEL_1G:
+ page_size = 2;
+ break;
+ default:
+ return false;
+ }
+
+ tdcall_rcx = *start | page_size;
+ if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL))
+ return false;
+
+ *start += accept_size;
+ return true;
+}
+
+/*
+ * Inform the VMM of the guest's intent for this physical page: shared with
+ * the VMM or private to the guest. The VMM is expected to change its mapping
+ * of the page in response.
+ */
+static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
+{
+ phys_addr_t start = __pa(vaddr);
+ phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE);
+
+ if (!enc) {
+ /* Set the shared (decrypted) bits: */
+ start |= cc_mkdec(0);
+ end |= cc_mkdec(0);
+ }
+
+ /*
+ * Notify the VMM about page mapping conversion. More info about ABI
+ * can be found in TDX Guest-Host-Communication Interface (GHCI),
+ * section "TDG.VP.VMCALL<MapGPA>"
+ */
+ if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0))
+ return false;
+
+ /* private->shared conversion requires only MapGPA call */
+ if (!enc)
+ return true;
+
+ /*
+ * For shared->private conversion, accept the page using
+ * TDX_ACCEPT_PAGE TDX module call.
+ */
+ while (start < end) {
+ unsigned long len = end - start;
+
+ /*
+ * Try larger accepts first. It gives chance to VMM to keep
+ * 1G/2M SEPT entries where possible and speeds up process by
+ * cutting number of hypercalls (if successful).
+ */
+
+ if (try_accept_one(&start, len, PG_LEVEL_1G))
+ continue;
+
+ if (try_accept_one(&start, len, PG_LEVEL_2M))
+ continue;
+
+ if (!try_accept_one(&start, len, PG_LEVEL_4K))
+ return false;
+ }
+
+ return true;
+}
+
+void __init tdx_early_init(void)
+{
+ u64 cc_mask;
+ u32 eax, sig[3];
+
+ cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]);
+
+ if (memcmp(TDX_IDENT, sig, sizeof(sig)))
+ return;
+
+ setup_force_cpu_cap(X86_FEATURE_TDX_GUEST);
+
+ cc_set_vendor(CC_VENDOR_INTEL);
+ cc_mask = get_cc_mask();
+ cc_set_mask(cc_mask);
+
+ /*
+ * All bits above GPA width are reserved and kernel treats shared bit
+ * as flag, not as part of physical address.
+ *
+ * Adjust physical mask to only cover valid GPA bits.
+ */
+ physical_mask &= cc_mask - 1;
+
+ x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
+ x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;
+ x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed;
+
+ pr_info("Guest detected\n");
+}
diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h
index 9aff97f0de7f..d937c55e717e 100644
--- a/arch/x86/include/asm/acenv.h
+++ b/arch/x86/include/asm/acenv.h
@@ -13,7 +13,19 @@
/* Asm macros */
-#define ACPI_FLUSH_CPU_CACHE() wbinvd()
+/*
+ * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states.
+ * It is required to prevent data loss.
+ *
+ * While running inside virtual machine, the kernel can bypass cache flushing.
+ * Changing sleep state in a virtual machine doesn't affect the host system
+ * sleep state and cannot lead to data loss.
+ */
+#define ACPI_FLUSH_CPU_CACHE() \
+do { \
+ if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) \
+ wbinvd(); \
+} while (0)
int __acpi_acquire_global_lock(unsigned int *lock);
int __acpi_release_global_lock(unsigned int *lock);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 48067af94678..bd8ae0a7010a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -328,6 +328,8 @@ struct apic {
/* wakeup_secondary_cpu */
int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+ /* wakeup secondary CPU using 64-bit wakeup point */
+ int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
void (*inquire_remote_apic)(int apicid);
@@ -488,6 +490,11 @@ static inline unsigned int read_apic_id(void)
return apic->get_apic_id(reg);
}
+#ifdef CONFIG_X86_64
+typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip);
+extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler);
+#endif
+
extern int default_apic_id_valid(u32 apicid);
extern int default_acpi_madt_oem_check(char *, char *);
extern void default_setup_apic_routing(void);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 73e643ae94b6..20df73b51025 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -238,6 +238,7 @@
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */
#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */
+#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 1231d63f836d..b37de8268c9a 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -68,6 +68,12 @@
# define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31))
#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+# define DISABLE_TDX_GUEST 0
+#else
+# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -79,7 +85,7 @@
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
#define DISABLED_MASK7 (DISABLE_PTI)
-#define DISABLED_MASK8 0
+#define DISABLED_MASK8 (DISABLE_TDX_GUEST)
#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 7924f27f5c8b..72184b0b2219 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -632,6 +632,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback);
DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap);
#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception);
+#endif
+
/* Device interrupts common/spurious */
DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt);
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e9736af126b2..1870b99c3356 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -44,6 +44,7 @@
#include <asm/page.h>
#include <asm/early_ioremap.h>
#include <asm/pgtable_types.h>
+#include <asm/shared/io.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
@@ -256,37 +257,23 @@ static inline void slow_down_io(void)
#endif
#define BUILDIO(bwl, bw, type) \
-static inline void out##bwl(unsigned type value, int port) \
-{ \
- asm volatile("out" #bwl " %" #bw "0, %w1" \
- : : "a"(value), "Nd"(port)); \
-} \
- \
-static inline unsigned type in##bwl(int port) \
-{ \
- unsigned type value; \
- asm volatile("in" #bwl " %w1, %" #bw "0" \
- : "=a"(value) : "Nd"(port)); \
- return value; \
-} \
- \
-static inline void out##bwl##_p(unsigned type value, int port) \
+static inline void out##bwl##_p(type value, u16 port) \
{ \
out##bwl(value, port); \
slow_down_io(); \
} \
\
-static inline unsigned type in##bwl##_p(int port) \
+static inline type in##bwl##_p(u16 port) \
{ \
- unsigned type value = in##bwl(port); \
+ type value = in##bwl(port); \
slow_down_io(); \
return value; \
} \
\
-static inline void outs##bwl(int port, const void *addr, unsigned long count) \
+static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \
{ \
if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \
- unsigned type *value = (unsigned type *)addr; \
+ type *value = (type *)addr; \
while (count) { \
out##bwl(*value, port); \
value++; \
@@ -299,10 +286,10 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \
} \
} \
\
-static inline void ins##bwl(int port, void *addr, unsigned long count) \
+static inline void ins##bwl(u16 port, void *addr, unsigned long count) \
{ \
if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \
- unsigned type *value = (unsigned type *)addr; \
+ type *value = (type *)addr; \
while (count) { \
*value = in##bwl(port); \
value++; \
@@ -315,13 +302,11 @@ static inline void ins##bwl(int port, void *addr, unsigned long count) \
} \
}
-BUILDIO(b, b, char)
-BUILDIO(w, w, short)
-BUILDIO(l, , int)
+BUILDIO(b, b, u8)
+BUILDIO(w, w, u16)
+BUILDIO(l, , u32)
+#undef BUILDIO
-#define inb inb
-#define inw inw
-#define inl inl
#define inb_p inb_p
#define inw_p inw_p
#define inl_p inl_p
@@ -329,9 +314,6 @@ BUILDIO(l, , int)
#define insw insw
#define insl insl
-#define outb outb
-#define outw outw
-#define outl outl
#define outb_p outb_p
#define outw_p outw_p
#define outl_p outl_p
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 56935ebb1dfe..57bc74e112f2 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,6 +7,8 @@
#include <linux/interrupt.h>
#include <uapi/asm/kvm_para.h>
+#include <asm/tdx.h>
+
#ifdef CONFIG_KVM_GUEST
bool kvm_check_and_clear_guest_paused(void);
#else
@@ -32,6 +34,10 @@ static inline bool kvm_check_and_clear_guest_paused(void)
static inline long kvm_hypercall0(unsigned int nr)
{
long ret;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return tdx_kvm_hypercall(nr, 0, 0, 0, 0);
+
asm volatile(KVM_HYPERCALL
: "=a"(ret)
: "a"(nr)
@@ -42,6 +48,10 @@ static inline long kvm_hypercall0(unsigned int nr)
static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
{
long ret;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return tdx_kvm_hypercall(nr, p1, 0, 0, 0);
+
asm volatile(KVM_HYPERCALL
: "=a"(ret)
: "a"(nr), "b"(p1)
@@ -53,6 +63,10 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
unsigned long p2)
{
long ret;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return tdx_kvm_hypercall(nr, p1, p2, 0, 0);
+
asm volatile(KVM_HYPERCALL
: "=a"(ret)
: "a"(nr), "b"(p1), "c"(p2)
@@ -64,6 +78,10 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
unsigned long p2, unsigned long p3)
{
long ret;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return tdx_kvm_hypercall(nr, p1, p2, p3, 0);
+
asm volatile(KVM_HYPERCALL
: "=a"(ret)
: "a"(nr), "b"(p1), "c"(p2), "d"(p3)
@@ -76,6 +94,10 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
unsigned long p4)
{
long ret;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return tdx_kvm_hypercall(nr, p1, p2, p3, p4);
+
asm volatile(KVM_HYPERCALL
: "=a"(ret)
: "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index e2c6f433ed10..88ceaf3648b3 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -49,9 +49,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages,
void __init mem_encrypt_free_decrypted_mem(void);
-/* Architecture __weak replacement functions */
-void __init mem_encrypt_init(void);
-
void __init sev_es_init_vc_handling(void);
#define __bss_decrypted __section(".bss..decrypted")
@@ -89,6 +86,9 @@ static inline void mem_encrypt_free_decrypted_mem(void) { }
#endif /* CONFIG_AMD_MEM_ENCRYPT */
+/* Architecture __weak replacement functions */
+void __init mem_encrypt_init(void);
+
/*
* The __sme_pa() and __sme_pa_nodebug() macros are meant for use when
* writing to or comparing values from the cr3 register. Having the
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 331474b150f1..fd6f6e5b755a 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -25,6 +25,7 @@ struct real_mode_header {
u32 sev_es_trampoline_start;
#endif
#ifdef CONFIG_X86_64
+ u32 trampoline_start64;
u32 trampoline_pgd;
#endif
/* ACPI S3 wakeup */
diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h
new file mode 100644
index 000000000000..c0ef921c0586
--- /dev/null
+++ b/arch/x86/include/asm/shared/io.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SHARED_IO_H
+#define _ASM_X86_SHARED_IO_H
+
+#include <linux/types.h>
+
+#define BUILDIO(bwl, bw, type) \
+static inline void __out##bwl(type value, u16 port) \
+{ \
+ asm volatile("out" #bwl " %" #bw "0, %w1" \
+ : : "a"(value), "Nd"(port)); \
+} \
+ \
+static inline type __in##bwl(u16 port) \
+{ \
+ type value; \
+ asm volatile("in" #bwl " %w1, %" #bw "0" \
+ : "=a"(value) : "Nd"(port)); \
+ return value; \
+}
+
+BUILDIO(b, b, u8)
+BUILDIO(w, w, u16)
+BUILDIO(l, , u32)
+#undef BUILDIO
+
+#define inb __inb
+#define inw __inw
+#define inl __inl
+#define outb __outb
+#define outw __outw
+#define outl __outl
+
+#endif
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
new file mode 100644
index 000000000000..e53f26228fbb
--- /dev/null
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SHARED_TDX_H
+#define _ASM_X86_SHARED_TDX_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define TDX_HYPERCALL_STANDARD 0
+
+#define TDX_HCALL_HAS_OUTPUT BIT(0)
+#define TDX_HCALL_ISSUE_STI BIT(1)
+
+#define TDX_CPUID_LEAF_ID 0x21
+#define TDX_IDENT "IntelTDX "
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Used in __tdx_hypercall() to pass down and get back registers' values of
+ * the TDCALL instruction when requesting services from the VMM.
+ *
+ * This is a software only structure and not part of the TDX module/VMM ABI.
+ */
+struct tdx_hypercall_args {
+ u64 r10;
+ u64 r11;
+ u64 r12;
+ u64 r13;
+ u64 r14;
+ u64 r15;
+};
+
+/* Used to request services from the VMM */
+u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags);
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void);
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_X86_SHARED_TDX_H */
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
new file mode 100644
index 000000000000..020c81a7c729
--- /dev/null
+++ b/arch/x86/include/asm/tdx.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2022 Intel Corporation */
+#ifndef _ASM_X86_TDX_H
+#define _ASM_X86_TDX_H
+
+#include <linux/init.h>
+#include <linux/bits.h>
+#include <asm/ptrace.h>
+#include <asm/shared/tdx.h>
+
+/*
+ * SW-defined error codes.
+ *
+ * Bits 47:40 == 0xFF indicate Reserved status code class that never used by
+ * TDX module.
+ */
+#define TDX_ERROR _BITUL(63)
+#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40))
+#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000))
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Used to gather the output registers values of the TDCALL and SEAMCALL
+ * instructions when requesting services from the TDX module.
+ *
+ * This is a software only structure and not part of the TDX module/VMM ABI.
+ */
+struct tdx_module_output {
+ u64 rcx;
+ u64 rdx;
+ u64 r8;
+ u64 r9;
+ u64 r10;
+ u64 r11;
+};
+
+/*
+ * Used by the #VE exception handler to gather the #VE exception
+ * info from the TDX module. This is a software only structure
+ * and not part of the TDX module/VMM ABI.
+ */
+struct ve_info {
+ u64 exit_reason;
+ u64 exit_qual;
+ /* Guest Linear (virtual) Address */
+ u64 gla;
+ /* Guest Physical Address */
+ u64 gpa;
+ u32 instr_len;
+ u32 instr_info;
+};
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+
+void __init tdx_early_init(void);
+
+/* Used to communicate with the TDX module */
+u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
+ struct tdx_module_output *out);
+
+void tdx_get_ve_info(struct ve_info *ve);
+
+bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve);
+
+void tdx_safe_halt(void);
+
+bool tdx_early_handle_ve(struct pt_regs *regs);
+
+#else
+
+static inline void tdx_early_init(void) { };
+static inline void tdx_safe_halt(void) { };
+
+static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; }
+
+#endif /* CONFIG_INTEL_TDX_GUEST */
+
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST)
+long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2,
+ unsigned long p3, unsigned long p4);
+#else
+static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1,
+ unsigned long p2, unsigned long p3,
+ unsigned long p4)
+{
+ return -ENODEV;
+}
+#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_X86_TDX_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 0d01e7f5078c..6d2c50819501 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -65,6 +65,13 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
static bool acpi_support_online_capable;
#endif
+#ifdef CONFIG_X86_64
+/* Physical address of the Multiprocessor Wakeup Structure mailbox */
+static u64 acpi_mp_wake_mailbox_paddr;
+/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
+static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox;
+#endif
+
#ifdef CONFIG_X86_IO_APIC
/*
* Locks related to IOAPIC hotplug
@@ -336,7 +343,60 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e
return 0;
}
-#endif /*CONFIG_X86_LOCAL_APIC */
+#ifdef CONFIG_X86_64
+static int acpi_wakeup_cpu(int apicid, unsigned long start_ip)
+{
+ /*
+ * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
+ *
+ * Wakeup of secondary CPUs is fully serialized in the core code.
+ * No need to protect acpi_mp_wake_mailbox from concurrent accesses.
+ */
+ if (!acpi_mp_wake_mailbox) {
+ acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr,
+ sizeof(*acpi_mp_wake_mailbox),
+ MEMREMAP_WB);
+ }
+
+ /*
+ * Mailbox memory is shared between the firmware and OS. Firmware will
+ * listen on mailbox command address, and once it receives the wakeup
+ * command, the CPU associated with the given apicid will be booted.
+ *
+ * The value of 'apic_id' and 'wakeup_vector' must be visible to the
+ * firmware before the wakeup command is visible. smp_store_release()
+ * ensures ordering and visibility.
+ */
+ acpi_mp_wake_mailbox->apic_id = apicid;
+ acpi_mp_wake_mailbox->wakeup_vector = start_ip;
+ smp_store_release(&acpi_mp_wake_mailbox->command,
+ ACPI_MP_WAKE_COMMAND_WAKEUP);
+
+ /*
+ * Wait for the CPU to wake up.
+ *
+ * The CPU being woken up is essentially in a spin loop waiting to be
+ * woken up. It should not take long for it wake up and acknowledge by
+ * zeroing out ->command.
+ *
+ * ACPI specification doesn't provide any guidance on how long kernel
+ * has to wait for a wake up acknowledgement. It also doesn't provide
+ * a way to cancel a wake up request if it takes too long.
+ *
+ * In TDX environment, the VMM has control over how long it takes to
+ * wake up secondary. It can postpone scheduling secondary vCPU
+ * indefinitely. Giving up on wake up request and reporting error opens
+ * possible attack vector for VMM: it can wake up a secondary CPU when
+ * kernel doesn't expect it. Wait until positive result of the wake up
+ * request.
+ */
+ while (READ_ONCE(acpi_mp_wake_mailbox->command))
+ cpu_relax();
+
+ return 0;
+}
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
@@ -1083,6 +1143,29 @@ static int __init acpi_parse_madt_lapic_entries(void)
}
return 0;
}
+
+#ifdef CONFIG_X86_64
+static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+ const unsigned long end)
+{
+ struct acpi_madt_multiproc_wakeup *mp_wake;
+
+ if (!IS_ENABLED(CONFIG_SMP))
+ return -ENODEV;
+
+ mp_wake = (struct acpi_madt_multiproc_wakeup *)header;
+ if (BAD_MADT_ENTRY(mp_wake, end))
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(&header->common);
+
+ acpi_mp_wake_mailbox_paddr = mp_wake->base_address;
+
+ acpi_wake_cpu_handler_update(acpi_wakeup_cpu);
+
+ return 0;
+}
+#endif /* CONFIG_X86_64 */
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
@@ -1278,6 +1361,14 @@ static void __init acpi_process_madt(void)
smp_found_config = 1;
}
+
+#ifdef CONFIG_X86_64
+ /*
+ * Parse MADT MP Wake entry.
+ */
+ acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP,
+ acpi_parse_mp_wake, 1);
+#endif
}
if (error == -EINVAL) {
/*
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b70344bf6600..3c8f2c797a98 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2551,6 +2551,16 @@ u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid)
}
EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid);
+#ifdef CONFIG_X86_64
+void __init acpi_wake_cpu_handler_update(wakeup_cpu_handler handler)
+{
+ struct apic **drv;
+
+ for (drv = __apicdrivers; drv < __apicdrivers_end; drv++)
+ (*drv)->wakeup_secondary_cpu_64 = handler;
+}
+#endif
+
/*
* Override the generic EOI implementation with an optimized version.
* Only called during early boot when only one CPU is active and with
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c1bb384935b0..a868b76cd3d4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -65,6 +65,7 @@
#include <asm/irq_remapping.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
+#include <asm/pgtable.h>
#define for_each_ioapic(idx) \
for ((idx) = 0; (idx) < nr_ioapics; (idx)++)
@@ -2677,6 +2678,19 @@ static struct resource * __init ioapic_setup_resources(void)
return res;
}
+static void io_apic_set_fixmap(enum fixed_addresses idx, phys_addr_t phys)
+{
+ pgprot_t flags = FIXMAP_PAGE_NOCACHE;
+
+ /*
+ * Ensure fixmaps for IOAPIC MMIO respect memory encryption pgprot
+ * bits, just like normal ioremap():
+ */
+ flags = pgprot_decrypted(flags);
+
+ __set_fixmap(idx, phys, flags);
+}
+
void __init io_apic_init_mappings(void)
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
@@ -2709,7 +2723,7 @@ fake_ioapic_page:
__func__, PAGE_SIZE, PAGE_SIZE);
ioapic_phys = __pa(ioapic_phys);
}
- set_fixmap_nocache(idx, ioapic_phys);
+ io_apic_set_fixmap(idx, ioapic_phys);
apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n",
__fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK),
ioapic_phys);
@@ -2838,7 +2852,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base,
ioapics[idx].mp_config.flags = MPC_APIC_USABLE;
ioapics[idx].mp_config.apicaddr = address;
- set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+ io_apic_set_fixmap(FIX_IO_APIC_BASE_0 + idx, address);
if (bad_ioapic_register(idx)) {
clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
return -ENODEV;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 9fb0a2f8b62a..437308004ef2 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -18,6 +18,7 @@
#include <asm/bootparam.h>
#include <asm/suspend.h>
#include <asm/tlbflush.h>
+#include <asm/tdx.h>
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -66,6 +67,22 @@ static void __used common(void)
#endif
BLANK();
+ OFFSET(TDX_MODULE_rcx, tdx_module_output, rcx);
+ OFFSET(TDX_MODULE_rdx, tdx_module_output, rdx);
+ OFFSET(TDX_MODULE_r8, tdx_module_output, r8);
+ OFFSET(TDX_MODULE_r9, tdx_module_output, r9);
+ OFFSET(TDX_MODULE_r10, tdx_module_output, r10);
+ OFFSET(TDX_MODULE_r11, tdx_module_output, r11);
+
+ BLANK();
+ OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10);
+ OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11);
+ OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12);
+ OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13);
+ OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14);
+ OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15);
+
+ BLANK();
OFFSET(BP_scratch, boot_params, scratch);
OFFSET(BP_secure_boot, boot_params, secure_boot);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index c185f4831498..bd4a34100ed0 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -40,6 +40,7 @@
#include <asm/extable.h>
#include <asm/trapnr.h>
#include <asm/sev.h>
+#include <asm/tdx.h>
/*
* Manage page tables very early on.
@@ -417,6 +418,9 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr)
trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs))
return;
+ if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(regs))
+ return;
+
early_fixup_exception(regs, trapnr);
}
@@ -515,6 +519,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
idt_setup_early_handler();
+ /* Needed before cc_platform_has() can be used for TDX */
+ tdx_early_init();
+
copy_bootdata(__va(real_mode_data));
/*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7bac9a4bdf7c..92c4afa2b729 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -173,8 +173,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
addq $(init_top_pgt - __START_KERNEL_map), %rax
1:
+#ifdef CONFIG_X86_MCE
+ /*
+ * Preserve CR4.MCE if the kernel will enable #MC support.
+ * Clearing MCE may fault in some environments (that also force #MC
+ * support). Any machine check that occurs before #MC support is fully
+ * configured will crash the system regardless of the CR4.MCE value set
+ * here.
+ */
+ movq %cr4, %rcx
+ andl $X86_CR4_MCE, %ecx
+#else
+ movl $0, %ecx
+#endif
+
/* Enable PAE mode, PGE and LA57 */
- movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
#ifdef CONFIG_X86_5LEVEL
testl $1, __pgtable_l5_enabled(%rip)
jz 1f
@@ -280,13 +294,23 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
/* Setup EFER (Extended Feature Enable Register) */
movl $MSR_EFER, %ecx
rdmsr
+ /*
+ * Preserve current value of EFER for comparison and to skip
+ * EFER writes if no change was made (for TDX guest)
+ */
+ movl %eax, %edx
btsl $_EFER_SCE, %eax /* Enable System Call */
btl $20,%edi /* No Execute supported? */
jnc 1f
btsl $_EFER_NX, %eax
btsq $_PAGE_BIT_NX,early_pmd_flags(%rip)
-1: wrmsr /* Make changes effective */
+ /* Avoid writing EFER if no change was made (for TDX guest) */
+1: cmpl %edx, %eax
+ je 1f
+ xor %edx, %edx
+ wrmsr /* Make changes effective */
+1:
/* Setup cr0 */
movl $CR0_STATE, %eax
/* Make changes effective */
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 608eb63bf044..a58c6bc1cd68 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -69,6 +69,9 @@ static const __initconst struct idt_data early_idts[] = {
*/
INTG(X86_TRAP_PF, asm_exc_page_fault),
#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+ INTG(X86_TRAP_VE, asm_exc_virtualization_exception),
+#endif
};
/*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b370767f5b19..dbaf12c43fe1 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -46,6 +46,7 @@
#include <asm/proto.h>
#include <asm/frame.h>
#include <asm/unwind.h>
+#include <asm/tdx.h>
#include "process.h"
@@ -873,6 +874,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
} else if (prefer_mwait_c1_over_halt(c)) {
pr_info("using mwait in idle threads\n");
x86_idle = mwait_idle;
+ } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+ pr_info("using TDX aware idle routine\n");
+ x86_idle = tdx_safe_halt;
} else
x86_idle = default_idle;
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85d7b1c5eb70..66199f9574ef 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1083,6 +1083,11 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
unsigned long boot_error = 0;
unsigned long timeout;
+#ifdef CONFIG_X86_64
+ /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
+ if (apic->wakeup_secondary_cpu_64)
+ start_ip = real_mode_header->trampoline_start64;
+#endif
idle->thread.sp = (unsigned long)task_pt_regs(idle);
early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
initial_code = (unsigned long)start_secondary;
@@ -1124,11 +1129,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
/*
* Wake up a CPU in difference cases:
- * - Use the method in the APIC driver if it's defined
+ * - Use a method from the APIC driver if one defined, with wakeup
+ * straight to 64-bit mode preferred over wakeup to RM.
* Otherwise,
* - Use an INIT boot APIC message for APs or NMI for BSP.
*/
- if (apic->wakeup_secondary_cpu)
+ if (apic->wakeup_secondary_cpu_64)
+ boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+ else if (apic->wakeup_secondary_cpu)
boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
else
boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1563fb995005..a4e2efde5d1f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -62,6 +62,7 @@
#include <asm/insn.h>
#include <asm/insn-eval.h>
#include <asm/vdso.h>
+#include <asm/tdx.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -686,13 +687,40 @@ static bool try_fixup_enqcmd_gp(void)
#endif
}
+static bool gp_try_fixup_and_notify(struct pt_regs *regs, int trapnr,
+ unsigned long error_code, const char *str)
+{
+ if (fixup_exception(regs, trapnr, error_code, 0))
+ return true;
+
+ current->thread.error_code = error_code;
+ current->thread.trap_nr = trapnr;
+
+ /*
+ * To be potentially processing a kprobe fault and to trust the result
+ * from kprobe_running(), we have to be non-preemptible.
+ */
+ if (!preemptible() && kprobe_running() &&
+ kprobe_fault_handler(regs, trapnr))
+ return true;
+
+ return notify_die(DIE_GPF, str, regs, error_code, trapnr, SIGSEGV) == NOTIFY_STOP;
+}
+
+static void gp_user_force_sig_segv(struct pt_regs *regs, int trapnr,
+ unsigned long error_code, const char *str)
+{
+ current->thread.error_code = error_code;
+ current->thread.trap_nr = trapnr;
+ show_signal(current, SIGSEGV, "", str, regs, error_code);
+ force_sig(SIGSEGV);
+}
+
DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
{
char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR;
enum kernel_gp_hint hint = GP_NO_HINT;
- struct task_struct *tsk;
unsigned long gp_addr;
- int ret;
if (user_mode(regs) && try_fixup_enqcmd_gp())
return;
@@ -711,40 +739,18 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
return;
}
- tsk = current;
-
if (user_mode(regs)) {
if (fixup_iopl_exception(regs))
goto exit;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_nr = X86_TRAP_GP;
-
if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
goto exit;
- show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
- force_sig(SIGSEGV);
+ gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc);
goto exit;
}
- if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
- goto exit;
-
- tsk->thread.error_code = error_code;
- tsk->thread.trap_nr = X86_TRAP_GP;
-
- /*
- * To be potentially processing a kprobe fault and to trust the result
- * from kprobe_running(), we have to be non-preemptible.
- */
- if (!preemptible() &&
- kprobe_running() &&
- kprobe_fault_handler(regs, X86_TRAP_GP))
- goto exit;
-
- ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV);
- if (ret == NOTIFY_STOP)
+ if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc))
goto exit;
if (error_code)
@@ -1343,6 +1349,91 @@ DEFINE_IDTENTRY(exc_device_not_available)
}
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+
+#define VE_FAULT_STR "VE fault"
+
+static void ve_raise_fault(struct pt_regs *regs, long error_code)
+{
+ if (user_mode(regs)) {
+ gp_user_force_sig_segv(regs, X86_TRAP_VE, error_code, VE_FAULT_STR);
+ return;
+ }
+
+ if (gp_try_fixup_and_notify(regs, X86_TRAP_VE, error_code, VE_FAULT_STR))
+ return;
+
+ die_addr(VE_FAULT_STR, regs, error_code, 0);
+}
+
+/*
+ * Virtualization Exceptions (#VE) are delivered to TDX guests due to
+ * specific guest actions which may happen in either user space or the
+ * kernel:
+ *
+ * * Specific instructions (WBINVD, for example)
+ * * Specific MSR accesses
+ * * Specific CPUID leaf accesses
+ * * Access to specific guest physical addresses
+ *
+ * In the settings that Linux will run in, virtualization exceptions are
+ * never generated on accesses to normal, TD-private memory that has been
+ * accepted (by BIOS or with tdx_enc_status_changed()).
+ *
+ * Syscall entry code has a critical window where the kernel stack is not
+ * yet set up. Any exception in this window leads to hard to debug issues
+ * and can be exploited for privilege escalation. Exceptions in the NMI
+ * entry code also cause issues. Returning from the exception handler with
+ * IRET will re-enable NMIs and nested NMI will corrupt the NMI stack.
+ *
+ * For these reasons, the kernel avoids #VEs during the syscall gap and
+ * the NMI entry code. Entry code paths do not access TD-shared memory,
+ * MMIO regions, use #VE triggering MSRs, instructions, or CPUID leaves
+ * that might generate #VE. VMM can remove memory from TD at any point,
+ * but access to unaccepted (or missing) private memory leads to VM
+ * termination, not to #VE.
+ *
+ * Similarly to page faults and breakpoints, #VEs are allowed in NMI
+ * handlers once the kernel is ready to deal with nested NMIs.
+ *
+ * During #VE delivery, all interrupts, including NMIs, are blocked until
+ * TDGETVEINFO is called. It prevents #VE nesting until the kernel reads
+ * the VE info.
+ *
+ * If a guest kernel action which would normally cause a #VE occurs in
+ * the interrupt-disabled region before TDGETVEINFO, a #DF (fault
+ * exception) is delivered to the guest which will result in an oops.
+ *
+ * The entry code has been audited carefully for following these expectations.
+ * Changes in the entry code have to be audited for correctness vs. this
+ * aspect. Similarly to #PF, #VE in these places will expose kernel to
+ * privilege escalation or may lead to random crashes.
+ */
+DEFINE_IDTENTRY(exc_virtualization_exception)
+{
+ struct ve_info ve;
+
+ /*
+ * NMIs/Machine-checks/Interrupts will be in a disabled state
+ * till TDGETVEINFO TDCALL is executed. This ensures that VE
+ * info cannot be overwritten by a nested #VE.
+ */
+ tdx_get_ve_info(&ve);
+
+ cond_local_irq_enable(regs);
+
+ /*
+ * If tdx_handle_virt_exception() could not process
+ * it successfully, treat it as #GP(0) and handle it.
+ */
+ if (!tdx_handle_virt_exception(regs, &ve))
+ ve_raise_fault(regs, 0);
+
+ cond_local_irq_disable(regs);
+}
+
+#endif
+
#ifdef CONFIG_X86_32
DEFINE_IDTENTRY_SW(iret_error)
{
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 2b3eb8c948a3..a58f451a7dd3 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -11,7 +11,7 @@
#include <asm/msr.h>
#include <asm/archrandom.h>
#include <asm/e820/api.h>
-#include <asm/io.h>
+#include <asm/shared/io.h>
/*
* When built for the regular kernel, several functions need to be stubbed out
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 17a492c27306..1ad0228f8ceb 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -242,10 +242,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
* If the page being mapped is in memory and SEV is active then
* make sure the memory encryption attribute is enabled in the
* resulting mapping.
+ * In TDX guests, memory is marked private by default. If encryption
+ * is not requested (using encrypted), explicitly set decrypt
+ * attribute in all IOREMAPPED memory.
*/
prot = PAGE_KERNEL_IO;
if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted)
prot = pgprot_encrypted(prot);
+ else
+ prot = pgprot_decrypted(prot);
switch (pcm) {
case _PAGE_CACHE_MODE_UC:
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index f85868c031c6..11350e2fd736 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -42,7 +42,14 @@ bool force_dma_unencrypted(struct device *dev)
static void print_mem_encrypt_feature_info(void)
{
- pr_info("AMD Memory Encryption Features active:");
+ pr_info("Memory Encryption Features active:");
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+ pr_cont(" Intel TDX\n");
+ return;
+ }
+
+ pr_cont(" AMD");
/* Secure Memory Encryption */
if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S
index 8c1db5bf5d78..2eb62be6d256 100644
--- a/arch/x86/realmode/rm/header.S
+++ b/arch/x86/realmode/rm/header.S
@@ -24,6 +24,7 @@ SYM_DATA_START(real_mode_header)
.long pa_sev_es_trampoline_start
#endif
#ifdef CONFIG_X86_64
+ .long pa_trampoline_start64
.long pa_trampoline_pgd;
#endif
/* ACPI S3 wakeup */
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index cc8391f86cdb..e38d61d6562e 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -70,7 +70,7 @@ SYM_CODE_START(trampoline_start)
movw $__KERNEL_DS, %dx # Data segment descriptor
# Enable protected mode
- movl $X86_CR0_PE, %eax # protected mode (PE) bit
+ movl $(CR0_STATE & ~X86_CR0_PG), %eax
movl %eax, %cr0 # into protected mode
# flush prefetch and jump to startup_32
@@ -143,13 +143,24 @@ SYM_CODE_START(startup_32)
movl %eax, %cr3
# Set up EFER
+ movl $MSR_EFER, %ecx
+ rdmsr
+ /*
+ * Skip writing to EFER if the register already has desired
+ * value (to avoid #VE for the TDX guest).
+ */
+ cmp pa_tr_efer, %eax
+ jne .Lwrite_efer
+ cmp pa_tr_efer + 4, %edx
+ je .Ldone_efer
+.Lwrite_efer:
movl pa_tr_efer, %eax
movl pa_tr_efer + 4, %edx
- movl $MSR_EFER, %ecx
wrmsr
- # Enable paging and in turn activate Long Mode
- movl $(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax
+.Ldone_efer:
+ # Enable paging and in turn activate Long Mode.
+ movl $CR0_STATE, %eax
movl %eax, %cr0
/*
@@ -161,6 +172,19 @@ SYM_CODE_START(startup_32)
ljmpl $__KERNEL_CS, $pa_startup_64
SYM_CODE_END(startup_32)
+SYM_CODE_START(pa_trampoline_compat)
+ /*
+ * In compatibility mode. Prep ESP and DX for startup_32, then disable
+ * paging and complete the switch to legacy 32-bit mode.
+ */
+ movl $rm_stack_end, %esp
+ movw $__KERNEL_DS, %dx
+
+ movl $(CR0_STATE & ~X86_CR0_PG), %eax
+ movl %eax, %cr0
+ ljmpl $__KERNEL32_CS, $pa_startup_32
+SYM_CODE_END(pa_trampoline_compat)
+
.section ".text64","ax"
.code64
.balign 4
@@ -169,6 +193,20 @@ SYM_CODE_START(startup_64)
jmpq *tr_start(%rip)
SYM_CODE_END(startup_64)
+SYM_CODE_START(trampoline_start64)
+ /*
+ * APs start here on a direct transfer from 64-bit BIOS with identity
+ * mapped page tables. Load the kernel's GDT in order to gear down to
+ * 32-bit mode (to handle 4-level vs. 5-level paging), and to (re)load
+ * segment registers. Load the zero IDT so any fault triggers a
+ * shutdown instead of jumping back into BIOS.
+ */
+ lidt tr_idt(%rip)
+ lgdt tr_gdt64(%rip)
+
+ ljmpl *tr_compat(%rip)
+SYM_CODE_END(trampoline_start64)
+
.section ".rodata","a"
# Duplicate the global descriptor table
# so the kernel can live anywhere
@@ -182,6 +220,17 @@ SYM_DATA_START(tr_gdt)
.quad 0x00cf93000000ffff # __KERNEL_DS
SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end)
+SYM_DATA_START(tr_gdt64)
+ .short tr_gdt_end - tr_gdt - 1 # gdt limit
+ .long pa_tr_gdt
+ .long 0
+SYM_DATA_END(tr_gdt64)
+
+SYM_DATA_START(tr_compat)
+ .long pa_trampoline_compat
+ .short __KERNEL32_CS
+SYM_DATA_END(tr_compat)
+
.bss
.balign PAGE_SIZE
SYM_DATA(trampoline_pgd, .space PAGE_SIZE)
diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S
index 5033e640f957..4331c32c47f8 100644
--- a/arch/x86/realmode/rm/trampoline_common.S
+++ b/arch/x86/realmode/rm/trampoline_common.S
@@ -1,4 +1,14 @@
/* SPDX-License-Identifier: GPL-2.0 */
.section ".rodata","a"
.balign 16
-SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0)
+
+/*
+ * When a bootloader hands off to the kernel in 32-bit mode an
+ * IDT with a 2-byte limit and 4-byte base is needed. When a boot
+ * loader hands off to a kernel 64-bit mode the base address
+ * extends to 8-bytes. Reserve enough space for either scenario.
+ */
+SYM_DATA_START_LOCAL(tr_idt)
+ .short 0
+ .quad 0
+SYM_DATA_END(tr_idt)
diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c
index 1d6437e6d2ba..a6f4d8388ad8 100644
--- a/arch/x86/realmode/rm/wakemain.c
+++ b/arch/x86/realmode/rm/wakemain.c
@@ -62,8 +62,12 @@ static void send_morse(const char *pattern)
}
}
+struct port_io_ops pio_ops;
+
void main(void)
{
+ init_default_io_ops();
+
/* Kill machine if structures are wrong */
if (wakeup_header.real_magic != 0x12345678)
while (1)
diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S
new file mode 100644
index 000000000000..49a54356ae99
--- /dev/null
+++ b/arch/x86/virt/vmx/tdx/tdxcall.S
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/asm-offsets.h>
+#include <asm/tdx.h>
+
+/*
+ * TDCALL and SEAMCALL are supported in Binutils >= 2.36.
+ */
+#define tdcall .byte 0x66,0x0f,0x01,0xcc
+#define seamcall .byte 0x66,0x0f,0x01,0xcf
+
+/*
+ * TDX_MODULE_CALL - common helper macro for both
+ * TDCALL and SEAMCALL instructions.
+ *
+ * TDCALL - used by TDX guests to make requests to the
+ * TDX module and hypercalls to the VMM.
+ * SEAMCALL - used by TDX hosts to make requests to the
+ * TDX module.
+ */
+.macro TDX_MODULE_CALL host:req
+ /*
+ * R12 will be used as temporary storage for struct tdx_module_output
+ * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL
+ * services supported by this function, it can be reused.
+ */
+
+ /* Callee saved, so preserve it */
+ push %r12
+
+ /*
+ * Push output pointer to stack.
+ * After the operation, it will be fetched into R12 register.
+ */
+ push %r9
+
+ /* Mangle function call ABI into TDCALL/SEAMCALL ABI: */
+ /* Move Leaf ID to RAX */
+ mov %rdi, %rax
+ /* Move input 4 to R9 */
+ mov %r8, %r9
+ /* Move input 3 to R8 */
+ mov %rcx, %r8
+ /* Move input 1 to RCX */
+ mov %rsi, %rcx
+ /* Leave input param 2 in RDX */
+
+ .if \host
+ seamcall
+ /*
+ * SEAMCALL instruction is essentially a VMExit from VMX root
+ * mode to SEAM VMX root mode. VMfailInvalid (CF=1) indicates
+ * that the targeted SEAM firmware is not loaded or disabled,
+ * or P-SEAMLDR is busy with another SEAMCALL. %rax is not
+ * changed in this case.
+ *
+ * Set %rax to TDX_SEAMCALL_VMFAILINVALID for VMfailInvalid.
+ * This value will never be used as actual SEAMCALL error code as
+ * it is from the Reserved status code class.
+ */
+ jnc .Lno_vmfailinvalid
+ mov $TDX_SEAMCALL_VMFAILINVALID, %rax
+.Lno_vmfailinvalid:
+
+ .else
+ tdcall
+ .endif
+
+ /*
+ * Fetch output pointer from stack to R12 (It is used
+ * as temporary storage)
+ */
+ pop %r12
+
+ /*
+ * Since this macro can be invoked with NULL as an output pointer,
+ * check if caller provided an output struct before storing output
+ * registers.
+ *
+ * Update output registers, even if the call failed (RAX != 0).
+ * Other registers may contain details of the failure.
+ */
+ test %r12, %r12
+ jz .Lno_output_struct
+
+ /* Copy result registers to output struct: */
+ movq %rcx, TDX_MODULE_rcx(%r12)
+ movq %rdx, TDX_MODULE_rdx(%r12)
+ movq %r8, TDX_MODULE_r8(%r12)
+ movq %r9, TDX_MODULE_r9(%r12)
+ movq %r10, TDX_MODULE_r10(%r12)
+ movq %r11, TDX_MODULE_r11(%r12)
+
+.Lno_output_struct:
+ /* Restore the state of R12 register */
+ pop %r12
+.endm