Merge tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull Intel TDX support from Borislav Petkov:
 "Intel Trust Domain Extensions (TDX) support.

  This is the Intel version of a confidential computing solution called
  Trust Domain Extensions (TDX). This series adds support to run the
  kernel as part of a TDX guest. It provides similar guest protections
  to AMD's SEV-SNP like guest memory and register state encryption,
  memory integrity protection and a lot more.

  Design-wise, it differs from AMD's solution considerably: it uses a
  software module which runs in a special CPU mode called (Secure
  Arbitration Mode) SEAM. As the name suggests, this module serves as
  sort of an arbiter which the confidential guest calls for services it
  needs during its lifetime.

  Just like AMD's SNP set, this series reworks and streamlines certain
  parts of x86 arch code so that this feature can be properly
  accomodated"

* tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  x86/tdx: Fix RETs in TDX asm
  x86/tdx: Annotate a noreturn function
  x86/mm: Fix spacing within memory encryption features message
  x86/kaslr: Fix build warning in KASLR code in boot stub
  Documentation/x86: Document TDX kernel architecture
  ACPICA: Avoid cache flush inside virtual machines
  x86/tdx/ioapic: Add shared bit for IOAPIC base address
  x86/mm: Make DMA memory shared for TD guest
  x86/mm/cpa: Add support for TDX shared memory
  x86/tdx: Make pages shared in ioremap()
  x86/topology: Disable CPU online/offline control for TDX guests
  x86/boot: Avoid #VE during boot for TDX platforms
  x86/boot: Set CR0.NE early and keep it set during the boot
  x86/acpi/x86/boot: Add multiprocessor wake-up support
  x86/boot: Add a trampoline for booting APs via firmware handoff
  x86/tdx: Wire up KVM hypercalls
  x86/tdx: Port I/O: Add early boot support
  x86/tdx: Port I/O: Add runtime hypercalls
  x86/boot: Port I/O: Add decompression-time support for TDX
  x86/boot: Port I/O: Allow to hook up alternative helpers
  ...

4 files changed, 69 insertions, 5 deletions

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)