Merge branch 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull EFI updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Cleanup of the GOP [graphics output] handling code in the EFI stub

   - Complete refactoring of the mixed mode handling in the x86 EFI stub

   - Overhaul of the x86 EFI boot/runtime code

   - Increase robustness for mixed mode code

   - Add the ability to disable DMA at the root port level in the EFI
     stub

   - Get rid of RWX mappings in the EFI memory map and page tables,
     where possible

   - Move the support code for the old EFI memory mapping style into its
     only user, the SGI UV1+ support code.

   - plus misc fixes, updates, smaller cleanups.

  ... and due to interactions with the RWX changes, another round of PAT
  cleanups make a guest appearance via the EFI tree - with no side
  effects intended"

* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
  efi/x86: Disable instrumentation in the EFI runtime handling code
  efi/libstub/x86: Fix EFI server boot failure
  efi/x86: Disallow efi=old_map in mixed mode
  x86/boot/compressed: Relax sed symbol type regex for LLVM ld.lld
  efi/x86: avoid KASAN false positives when accessing the 1: 1 mapping
  efi: Fix handling of multiple efi_fake_mem= entries
  efi: Fix efi_memmap_alloc() leaks
  efi: Add tracking for dynamically allocated memmaps
  efi: Add a flags parameter to efi_memory_map
  efi: Fix comment for efi_mem_type() wrt absent physical addresses
  efi/arm: Defer probe of PCIe backed efifb on DT systems
  efi/x86: Limit EFI old memory map to SGI UV machines
  efi/x86: Avoid RWX mappings for all of DRAM
  efi/x86: Don't map the entire kernel text RW for mixed mode
  x86/mm: Fix NX bit clearing issue in kernel_map_pages_in_pgd
  efi/libstub/x86: Fix unused-variable warning
  efi/libstub/x86: Use mandatory 16-byte stack alignment in mixed mode
  efi/libstub/x86: Use const attribute for efi_is_64bit()
  efi: Allow disabling PCI busmastering on bridges during boot
  efi/x86: Allow translating 64-bit arguments for mixed mode calls
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1165,10 +1165,10 @@
 
 	efi=		[EFI]
 			Format: { "old_map", "nochunk", "noruntime", "debug",
-				  "nosoftreserve" }
+				  "nosoftreserve", "disable_early_pci_dma",
+				  "no_disable_early_pci_dma" }
 			old_map [X86-64]: switch to the old ioremap-based EFI
-			runtime services mapping. 32-bit still uses this one by
-			default.
+			runtime services mapping. [Needs CONFIG_X86_UV=y]
 			nochunk: disable reading files in "chunks" in the EFI
 			boot stub, as chunking can cause problems with some
 			firmware implementations.
@@ -1180,6 +1180,10 @@
 			claim. Specify efi=nosoftreserve to disable this
 			reservation and treat the memory by its base type
 			(i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
+			disable_early_pci_dma: Disable the busmaster bit on all
+			PCI bridges while in the EFI boot stub
+			no_disable_early_pci_dma: Leave the busmaster bit set
+			on all PCI bridges while in the EFI boot stub
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of

arch/alpha/include/asm/vmalloc.h

+#ifndef _ASM_ALPHA_VMALLOC_H
+#define _ASM_ALPHA_VMALLOC_H
+
+#endif /* _ASM_ALPHA_VMALLOC_H */

arch/arc/include/asm/vmalloc.h

+#ifndef _ASM_ARC_VMALLOC_H
+#define _ASM_ARC_VMALLOC_H
+
+#endif /* _ASM_ARC_VMALLOC_H */

arch/arm/include/asm/efi.h

@@ -50,19 +50,16 @@ void efi_virtmap_unload(void);
 
 /* arch specific definitions used by the stub code */
 
-#define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
-#define __efi_call_early(f, ...)	f(__VA_ARGS__)
-#define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
-#define efi_is_64bit()			(false)
+#define efi_bs_call(func, ...)	efi_system_table()->boottime->func(__VA_ARGS__)
+#define efi_rt_call(func, ...)	efi_system_table()->runtime->func(__VA_ARGS__)
+#define efi_is_native()		(true)
 
-#define efi_table_attr(table, attr, instance)				\
-	((table##_t *)instance)->attr
+#define efi_table_attr(inst, attr)	(inst->attr)
 
-#define efi_call_proto(protocol, f, instance, ...)			\
-	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
+#define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
 
-struct screen_info *alloc_screen_info(efi_system_table_t *sys_table_arg);
-void free_screen_info(efi_system_table_t *sys_table, struct screen_info *si);
+struct screen_info *alloc_screen_info(void);
+void free_screen_info(struct screen_info *si);
 
 static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 {

arch/arm/include/asm/vmalloc.h

+#ifndef _ASM_ARM_VMALLOC_H
+#define _ASM_ARM_VMALLOC_H
+
+#endif /* _ASM_ARM_VMALLOC_H */

arch/arm64/include/asm/efi.h

@@ -93,21 +93,17 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1));
 }
 
-#define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
-#define __efi_call_early(f, ...)	f(__VA_ARGS__)
-#define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
-#define efi_is_64bit()			(true)
+#define efi_bs_call(func, ...)	efi_system_table()->boottime->func(__VA_ARGS__)
+#define efi_rt_call(func, ...)	efi_system_table()->runtime->func(__VA_ARGS__)
+#define efi_is_native()		(true)
 
-#define efi_table_attr(table, attr, instance)				\
-	((table##_t *)instance)->attr
+#define efi_table_attr(inst, attr)	(inst->attr)
 
-#define efi_call_proto(protocol, f, instance, ...)			\
-	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
+#define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
 
 #define alloc_screen_info(x...)		&screen_info
 
-static inline void free_screen_info(efi_system_table_t *sys_table_arg,
-				    struct screen_info *si)
+static inline void free_screen_info(struct screen_info *si)
 {
 }
 

arch/arm64/include/asm/vmalloc.h

+#ifndef _ASM_ARM64_VMALLOC_H
+#define _ASM_ARM64_VMALLOC_H
+
+#endif /* _ASM_ARM64_VMALLOC_H */

arch/c6x/include/asm/vmalloc.h

+#ifndef _ASM_C6X_VMALLOC_H
+#define _ASM_C6X_VMALLOC_H
+
+#endif /* _ASM_C6X_VMALLOC_H */

arch/csky/include/asm/vmalloc.h

+#ifndef _ASM_CSKY_VMALLOC_H
+#define _ASM_CSKY_VMALLOC_H
+
+#endif /* _ASM_CSKY_VMALLOC_H */

arch/h8300/include/asm/vmalloc.h

+#ifndef _ASM_H8300_VMALLOC_H
+#define _ASM_H8300_VMALLOC_H
+
+#endif /* _ASM_H8300_VMALLOC_H */

arch/hexagon/include/asm/vmalloc.h

+#ifndef _ASM_HEXAGON_VMALLOC_H
+#define _ASM_HEXAGON_VMALLOC_H
+
+#endif /* _ASM_HEXAGON_VMALLOC_H */

arch/ia64/include/asm/vmalloc.h

+#ifndef _ASM_IA64_VMALLOC_H
+#define _ASM_IA64_VMALLOC_H
+
+#endif /* _ASM_IA64_VMALLOC_H */

arch/m68k/include/asm/vmalloc.h

+#ifndef _ASM_M68K_VMALLOC_H
+#define _ASM_M68K_VMALLOC_H
+
+#endif /* _ASM_M68K_VMALLOC_H */

arch/microblaze/include/asm/vmalloc.h

+#ifndef _ASM_MICROBLAZE_VMALLOC_H
+#define _ASM_MICROBLAZE_VMALLOC_H
+
+#endif /* _ASM_MICROBLAZE_VMALLOC_H */

arch/mips/include/asm/vmalloc.h

+#ifndef _ASM_MIPS_VMALLOC_H
+#define _ASM_MIPS_VMALLOC_H
+
+#endif /* _ASM_MIPS_VMALLOC_H */

arch/nds32/include/asm/vmalloc.h

+#ifndef _ASM_NDS32_VMALLOC_H
+#define _ASM_NDS32_VMALLOC_H
+
+#endif /* _ASM_NDS32_VMALLOC_H */

arch/nios2/include/asm/vmalloc.h

+#ifndef _ASM_NIOS2_VMALLOC_H
+#define _ASM_NIOS2_VMALLOC_H
+
+#endif /* _ASM_NIOS2_VMALLOC_H */

arch/openrisc/include/asm/vmalloc.h

+#ifndef _ASM_OPENRISC_VMALLOC_H
+#define _ASM_OPENRISC_VMALLOC_H
+
+#endif /* _ASM_OPENRISC_VMALLOC_H */

arch/parisc/include/asm/vmalloc.h

+#ifndef _ASM_PARISC_VMALLOC_H
+#define _ASM_PARISC_VMALLOC_H
+
+#endif /* _ASM_PARISC_VMALLOC_H */

arch/powerpc/include/asm/vmalloc.h

+#ifndef _ASM_POWERPC_VMALLOC_H
+#define _ASM_POWERPC_VMALLOC_H
+
+#endif /* _ASM_POWERPC_VMALLOC_H */

arch/riscv/include/asm/vmalloc.h

+#ifndef _ASM_RISCV_VMALLOC_H
+#define _ASM_RISCV_VMALLOC_H
+
+#endif /* _ASM_RISCV_VMALLOC_H */

arch/s390/include/asm/vmalloc.h

+#ifndef _ASM_S390_VMALLOC_H
+#define _ASM_S390_VMALLOC_H
+
+#endif /* _ASM_S390_VMALLOC_H */

arch/sh/include/asm/vmalloc.h

+#ifndef _ASM_SH_VMALLOC_H
+#define _ASM_SH_VMALLOC_H
+
+#endif /* _ASM_SH_VMALLOC_H */

arch/sparc/include/asm/vmalloc.h

+#ifndef _ASM_SPARC_VMALLOC_H
+#define _ASM_SPARC_VMALLOC_H
+
+#endif /* _ASM_SPARC_VMALLOC_H */

arch/um/include/asm/vmalloc.h

+#ifndef _ASM_UM_VMALLOC_H
+#define _ASM_UM_VMALLOC_H
+
+#endif /* _ASM_UM_VMALLOC_H */

arch/unicore32/include/asm/vmalloc.h

+#ifndef _ASM_UNICORE32_VMALLOC_H
+#define _ASM_UNICORE32_VMALLOC_H
+
+#endif /* _ASM_UNICORE32_VMALLOC_H */

arch/x86/Kconfig

@@ -1513,7 +1513,7 @@ config X86_CPA_STATISTICS
 	bool "Enable statistic for Change Page Attribute"
 	depends on DEBUG_FS
 	---help---
-	  Expose statistics about the Change Page Attribute mechanims, which
+	  Expose statistics about the Change Page Attribute mechanism, which
 	  helps to determine the effectiveness of preserving large and huge
 	  page mappings when mapping protections are changed.
 
@@ -1992,11 +1992,12 @@ config EFI
 	  platforms.
 
 config EFI_STUB
-       bool "EFI stub support"
-       depends on EFI && !X86_USE_3DNOW
-       select RELOCATABLE
-       ---help---
-          This kernel feature allows a bzImage to be loaded directly
+	bool "EFI stub support"
+	depends on EFI && !X86_USE_3DNOW
+	depends on $(cc-option,-mabi=ms) || X86_32
+	select RELOCATABLE
+	---help---
+	  This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
 
 	  See Documentation/admin-guide/efi-stub.rst for more information.

arch/x86/boot/Makefile

@@ -88,7 +88,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@

arch/x86/boot/compressed/Makefile

@@ -89,7 +89,7 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
+vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o \
 	$(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 

arch/x86/boot/compressed/eboot.h

@@ -12,22 +12,20 @@
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
 
-typedef struct {
-	u32 get_mode;
-	u32 set_mode;
-	u32 blt;
-} efi_uga_draw_protocol_32_t;
+typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t;
 
-typedef struct {
-	u64 get_mode;
-	u64 set_mode;
-	u64 blt;
-} efi_uga_draw_protocol_64_t;
-
-typedef struct {
-	void *get_mode;
-	void *set_mode;
-	void *blt;
-} efi_uga_draw_protocol_t;
+union efi_uga_draw_protocol {
+	struct {
+		efi_status_t (__efiapi *get_mode)(efi_uga_draw_protocol_t *,
+						  u32*, u32*, u32*, u32*);
+		void *set_mode;
+		void *blt;
+	};
+	struct {
+		u32 get_mode;
+		u32 set_mode;
+		u32 blt;
+	} mixed_mode;
+};
 
 #endif /* BOOT_COMPRESSED_EBOOT_H */

arch/x86/boot/compressed/efi_stub_32.S

-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * EFI call stub for IA32.
- *
- * This stub allows us to make EFI calls in physical mode with interrupts
- * turned off. Note that this implementation is different from the one in
- * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical
- * mode at this point.
- */
-
-#include <linux/linkage.h>
-#include <asm/page_types.h>
-
-/*
- * efi_call_phys(void *, ...) is a function with variable parameters.
- * All the callers of this function assure that all the parameters are 4-bytes.
- */
-
-/*
- * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save.
- * So we'd better save all of them at the beginning of this function and restore
- * at the end no matter how many we use, because we can not assure EFI runtime
- * service functions will comply with gcc calling convention, too.
- */
-
-.text
-SYM_FUNC_START(efi_call_phys)
-	/*
-	 * 0. The function can only be called in Linux kernel. So CS has been
-	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
-	 * the values of these registers are the same. And, the corresponding
-	 * GDT entries are identical. So I will do nothing about segment reg
-	 * and GDT, but change GDT base register in prelog and epilog.
-	 */
-
-	/*
-	 * 1. Because we haven't been relocated by this point we need to
-	 * use relative addressing.
-	 */
-	call	1f
-1:	popl	%edx
-	subl	$1b, %edx
-
-	/*
-	 * 2. Now on the top of stack is the return
-	 * address in the caller of efi_call_phys(), then parameter 1,
-	 * parameter 2, ..., param n. To make things easy, we save the return
-	 * address of efi_call_phys in a global variable.
-	 */
-	popl	%ecx
-	movl	%ecx, saved_return_addr(%edx)
-	/* get the function pointer into ECX*/
-	popl	%ecx
-	movl	%ecx, efi_rt_function_ptr(%edx)
-
-	/*
-	 * 3. Call the physical function.
-	 */
-	call	*%ecx
-
-	/*
-	 * 4. Balance the stack. And because EAX contain the return value,
-	 * we'd better not clobber it. We need to calculate our address
-	 * again because %ecx and %edx are not preserved across EFI function
-	 * calls.
-	 */
-	call	1f
-1:	popl	%edx
-	subl	$1b, %edx
-
-	movl	efi_rt_function_ptr(%edx), %ecx
-	pushl	%ecx
-
-	/*
-	 * 10. Push the saved return address onto the stack and return.
-	 */
-	movl	saved_return_addr(%edx), %ecx
-	pushl	%ecx
-	ret
-SYM_FUNC_END(efi_call_phys)
-.previous
-
-.data
-saved_return_addr:
-	.long 0
-efi_rt_function_ptr:
-	.long 0

arch/x86/boot/compressed/efi_stub_64.S

-#include <asm/segment.h>
-#include <asm/msr.h>
-#include <asm/processor-flags.h>
-
-#include "../../platform/efi/efi_stub_64.S"

arch/x86/boot/compressed/efi_thunk_64.S

@@ -10,7 +10,7 @@
  * needs to be able to service interrupts.
  *
  * On the plus side, we don't have to worry about mangling 64-bit
- * addresses into 32-bits because we're executing with an identify
+ * addresses into 32-bits because we're executing with an identity
  * mapped pagetable and haven't transitioned to 64-bit virtual addresses
  * yet.
  */
@@ -23,16 +23,13 @@
 
 	.code64
 	.text
-SYM_FUNC_START(efi64_thunk)
+SYM_FUNC_START(__efi64_thunk)
 	push	%rbp
 	push	%rbx
 
-	subq	$8, %rsp
-	leaq	efi_exit32(%rip), %rax
-	movl	%eax, 4(%rsp)
-	leaq	efi_gdt64(%rip), %rax
-	movl	%eax, (%rsp)
-	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
+	leaq	1f(%rip), %rbp
+	leaq	efi_gdt64(%rip), %rbx
+	movl	%ebx, 2(%rbx)		/* Fixup the gdt base address */
 
 	movl	%ds, %eax
 	push	%rax
@@ -48,15 +45,10 @@ SYM_FUNC_START(efi64_thunk)
 	movl	%esi, 0x0(%rsp)
 	movl	%edx, 0x4(%rsp)
 	movl	%ecx, 0x8(%rsp)
-	movq	%r8, %rsi
-	movl	%esi, 0xc(%rsp)
-	movq	%r9, %rsi
-	movl	%esi,  0x10(%rsp)
+	movl	%r8d, 0xc(%rsp)
+	movl	%r9d, 0x10(%rsp)
 
-	sgdt	save_gdt(%rip)
-
-	leaq	1f(%rip), %rbx
-	movq	%rbx, func_rt_ptr(%rip)
+	sgdt	0x14(%rsp)
 
 	/*
 	 * Switch to gdt with 32-bit segments. This is the firmware GDT
@@ -71,9 +63,9 @@ SYM_FUNC_START(efi64_thunk)
 	pushq	%rax
 	lretq
 
-1:	addq	$32, %rsp
-
-	lgdt	save_gdt(%rip)
+1:	lgdt	0x14(%rsp)
+	addq	$32, %rsp
+	movq	%rdi, %rax
 
 	pop	%rbx
 	movl	%ebx, %ss
@@ -85,26 +77,13 @@ SYM_FUNC_START(efi64_thunk)
 	/*
 	 * Convert 32-bit status code into 64-bit.
 	 */
-	test	%rax, %rax
-	jz	1f
-	movl	%eax, %ecx
-	andl	$0x0fffffff, %ecx
-	andl	$0xf0000000, %eax
-	shl	$32, %rax
-	or	%rcx, %rax
-1:
-	addq	$8, %rsp
+	roll	$1, %eax
+	rorq	$1, %rax
+
 	pop	%rbx
 	pop	%rbp
 	ret
-SYM_FUNC_END(efi64_thunk)
-
-SYM_FUNC_START_LOCAL(efi_exit32)
-	movq	func_rt_ptr(%rip), %rax
-	push	%rax
-	mov	%rdi, %rax
-	ret
-SYM_FUNC_END(efi_exit32)
+SYM_FUNC_END(__efi64_thunk)
 
 	.code32
 /*
@@ -144,9 +123,7 @@ SYM_FUNC_START_LOCAL(efi_enter32)
 	 */
 	cli
 
-	movl	56(%esp), %eax
-	movl	%eax, 2(%eax)
-	lgdtl	(%eax)
+	lgdtl	(%ebx)
 
 	movl	%cr4, %eax
 	btsl	$(X86_CR4_PAE_BIT), %eax
@@ -163,9 +140,8 @@ SYM_FUNC_START_LOCAL(efi_enter32)
 	xorl	%eax, %eax
 	lldt	%ax
 
-	movl	60(%esp), %eax
 	pushl	$__KERNEL_CS
-	pushl	%eax
+	pushl	%ebp
 
 	/* Enable paging */
 	movl	%cr0, %eax
@@ -181,13 +157,6 @@ SYM_DATA_START(efi32_boot_gdt)
 	.quad	0
 SYM_DATA_END(efi32_boot_gdt)
 
-SYM_DATA_START_LOCAL(save_gdt)
-	.word	0
-	.quad	0
-SYM_DATA_END(save_gdt)
-
-SYM_DATA_LOCAL(func_rt_ptr, .quad 0)
-
 SYM_DATA_START(efi_gdt64)
 	.word	efi_gdt64_end - efi_gdt64
 	.long	0			/* Filled out by user */

arch/x86/boot/compressed/head_32.S

@@ -145,67 +145,16 @@ SYM_FUNC_START(startup_32)
 SYM_FUNC_END(startup_32)
 
 #ifdef CONFIG_EFI_STUB
-/*
- * We don't need the return address, so set up the stack so efi_main() can find
- * its arguments.
- */
-SYM_FUNC_START(efi_pe_entry)
-	add	$0x4, %esp
-
-	call	1f
-1:	popl	%esi
-	subl	$1b, %esi
-
-	popl	%ecx
-	movl	%ecx, efi32_config(%esi)	/* Handle */
-	popl	%ecx
-	movl	%ecx, efi32_config+8(%esi)	/* EFI System table pointer */
-
-	/* Relocate efi_config->call() */
-	leal	efi32_config(%esi), %eax
-	add	%esi, 40(%eax)
-	pushl	%eax
-
-	call	make_boot_params
-	cmpl	$0, %eax
-	je	fail
-	movl	%esi, BP_code32_start(%eax)
-	popl	%ecx
-	pushl	%eax
-	pushl	%ecx
-	jmp	2f		/* Skip efi_config initialization */
-SYM_FUNC_END(efi_pe_entry)
-
 SYM_FUNC_START(efi32_stub_entry)
+SYM_FUNC_START_ALIAS(efi_stub_entry)
 	add	$0x4, %esp
-	popl	%ecx
-	popl	%edx
-
-	call	1f
-1:	popl	%esi
-	subl	$1b, %esi
-
-	movl	%ecx, efi32_config(%esi)	/* Handle */
-	movl	%edx, efi32_config+8(%esi)	/* EFI System table pointer */
-
-	/* Relocate efi_config->call() */
-	leal	efi32_config(%esi), %eax
-	add	%esi, 40(%eax)
-	pushl	%eax
-2:
 	call	efi_main
-	cmpl	$0, %eax
 	movl	%eax, %esi
-	jne	2f
-fail:
-	/* EFI init failed, so hang. */
-	hlt
-	jmp	fail
-2:
 	movl	BP_code32_start(%esi), %eax
 	leal	startup_32(%eax), %eax
 	jmp	*%eax
 SYM_FUNC_END(efi32_stub_entry)
+SYM_FUNC_END_ALIAS(efi_stub_entry)
 #endif
 
 	.text
@@ -262,15 +211,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	jmp	*%eax
 SYM_FUNC_END(.Lrelocated)
 
-#ifdef CONFIG_EFI_STUB
-	.data
-efi32_config:
-	.fill 5,8,0
-	.long efi_call_phys
-	.long 0
-	.byte 0
-#endif
-
 /*
  * Stack and heap for uncompression
  */

arch/x86/boot/compressed/head_64.S

@@ -208,10 +208,12 @@ SYM_FUNC_START(startup_32)
 	pushl	$__KERNEL_CS
 	leal	startup_64(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
-	movl	efi32_config(%ebp), %ebx
-	cmp	$0, %ebx
+	movl	efi32_boot_args(%ebp), %edi
+	cmp	$0, %edi
 	jz	1f
-	leal	handover_entry(%ebp), %eax
+	leal	efi64_stub_entry(%ebp), %eax
+	movl	%esi, %edx
+	movl	efi32_boot_args+4(%ebp), %esi
 1:
 #endif
 	pushl	%eax
@@ -232,17 +234,14 @@ SYM_FUNC_START(efi32_stub_entry)
 	popl	%edx
 	popl	%esi
 
-	leal	(BP_scratch+4)(%esi), %esp
 	call	1f
 1:	pop	%ebp
 	subl	$1b, %ebp
 
-	movl	%ecx, efi32_config(%ebp)
-	movl	%edx, efi32_config+8(%ebp)
+	movl	%ecx, efi32_boot_args(%ebp)
+	movl	%edx, efi32_boot_args+4(%ebp)
 	sgdtl	efi32_boot_gdt(%ebp)
-
-	leal	efi32_config(%ebp), %eax
-	movl	%eax, efi_config(%ebp)
+	movb	$0, efi_is64(%ebp)
 
 	/* Disable paging */
 	movl	%cr0, %eax
@@ -450,70 +449,17 @@ trampoline_return:
 SYM_CODE_END(startup_64)
 
 #ifdef CONFIG_EFI_STUB
-
-/* The entry point for the PE/COFF executable is efi_pe_entry. */
-SYM_FUNC_START(efi_pe_entry)
-	movq	%rcx, efi64_config(%rip)	/* Handle */
-	movq	%rdx, efi64_config+8(%rip) /* EFI System table pointer */
-
-	leaq	efi64_config(%rip), %rax
-	movq	%rax, efi_config(%rip)
-
-	call	1f
-1:	popq	%rbp
-	subq	$1b, %rbp
-
-	/*
-	 * Relocate efi_config->call().
-	 */
-	addq	%rbp, efi64_config+40(%rip)
-
-	movq	%rax, %rdi
-	call	make_boot_params
-	cmpq	$0,%rax
-	je	fail
-	mov	%rax, %rsi
-	leaq	startup_32(%rip), %rax
-	movl	%eax, BP_code32_start(%rsi)
-	jmp	2f		/* Skip the relocation */
-
-handover_entry:
-	call	1f
-1:	popq	%rbp
-	subq	$1b, %rbp
-
-	/*
-	 * Relocate efi_config->call().
-	 */
-	movq	efi_config(%rip), %rax
-	addq	%rbp, 40(%rax)
-2:
-	movq	efi_config(%rip), %rdi
+	.org 0x390
+SYM_FUNC_START(efi64_stub_entry)
+SYM_FUNC_START_ALIAS(efi_stub_entry)
+	and	$~0xf, %rsp			/* realign the stack */
 	call	efi_main
 	movq	%rax,%rsi
-	cmpq	$0,%rax
-	jne	2f
-fail:
-	/* EFI init failed, so hang. */
-	hlt
-	jmp	fail
-2:
 	movl	BP_code32_start(%esi), %eax
 	leaq	startup_64(%rax), %rax
 	jmp	*%rax
-SYM_FUNC_END(efi_pe_entry)
-
-	.org 0x390
-SYM_FUNC_START(efi64_stub_entry)
-	movq	%rdi, efi64_config(%rip)	/* Handle */
-	movq	%rsi, efi64_config+8(%rip) /* EFI System table pointer */
-
-	leaq	efi64_config(%rip), %rax
-	movq	%rax, efi_config(%rip)
-
-	movq	%rdx, %rsi
-	jmp	handover_entry
 SYM_FUNC_END(efi64_stub_entry)
+SYM_FUNC_END_ALIAS(efi_stub_entry)
 #endif
 
 	.text
@@ -682,24 +628,11 @@ SYM_DATA_START_LOCAL(gdt)
 	.quad   0x0000000000000000	/* TS continued */
 SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
 
-#ifdef CONFIG_EFI_STUB
-SYM_DATA_LOCAL(efi_config, .quad 0)
-
 #ifdef CONFIG_EFI_MIXED
-SYM_DATA_START(efi32_config)
-	.fill	5,8,0
-	.quad	efi64_thunk
-	.byte	0
-SYM_DATA_END(efi32_config)
+SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0)
+SYM_DATA(efi_is64, .byte 1)
 #endif
 
-SYM_DATA_START(efi64_config)
-	.fill	5,8,0
-	.quad	efi_call
-	.byte	1
-SYM_DATA_END(efi64_config)
-#endif /* CONFIG_EFI_STUB */
-
 /*
  * Stack and heap for uncompression
  */

arch/x86/include/asm/cpu_entry_area.h

@@ -6,6 +6,7 @@
 #include <linux/percpu-defs.h>
 #include <asm/processor.h>
 #include <asm/intel_ds.h>
+#include <asm/pgtable_areas.h>
 
 #ifdef CONFIG_X86_64
 
@@ -134,15 +135,6 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
-/* Single page reserved for the readonly IDT mapping: */
-#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
-#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
-
-#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
-
-#define CPU_ENTRY_AREA_MAP_SIZE			\
-	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
-
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
 static inline struct entry_stack *cpu_entry_stack(int cpu)

arch/x86/include/asm/pat.h → arch/x86/include/asm/memtype.h

 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_PAT_H
-#define _ASM_X86_PAT_H
+#ifndef _ASM_X86_MEMTYPE_H
+#define _ASM_X86_MEMTYPE_H
 
 #include <linux/types.h>
 #include <asm/pgtable_types.h>
 
-bool pat_enabled(void);
-void pat_disable(const char *reason);
+extern bool pat_enabled(void);
+extern void pat_disable(const char *reason);
 extern void pat_init(void);
 extern void init_cache_modes(void);
 
-extern int reserve_memtype(u64 start, u64 end,
+extern int memtype_reserve(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
-extern int free_memtype(u64 start, u64 end);
+extern int memtype_free(u64 start, u64 end);
 
-extern int kernel_map_sync_memtype(u64 base, unsigned long size,
+extern int memtype_kernel_map_sync(u64 base, unsigned long size,
 		enum page_cache_mode pcm);
 
-int io_reserve_memtype(resource_size_t start, resource_size_t end,
+extern int memtype_reserve_io(resource_size_t start, resource_size_t end,
 			enum page_cache_mode *pcm);
 
-void io_free_memtype(resource_size_t start, resource_size_t end);
+extern void memtype_free_io(resource_size_t start, resource_size_t end);
 
-bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
 
-#endif /* _ASM_X86_PAT_H */
+#endif /* _ASM_X86_MEMTYPE_H */

arch/x86/include/asm/mmu_context.h

@@ -69,14 +69,6 @@ struct ldt_struct {
 	int			slot;
 };
 
-/* This is a multiple of PAGE_SIZE. */
-#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
-
-static inline void *ldt_slot_va(int slot)
-{
-	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
-}
-
 /*
  * Used for LDT copy/destruction.
  */
@@ -99,87 +91,21 @@ static inline void destroy_context_ldt(struct mm_struct *mm) { }
 static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
 #endif
 
-static inline void load_mm_ldt(struct mm_struct *mm)
-{
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
-
-	/* READ_ONCE synchronizes with smp_store_release */
-	ldt = READ_ONCE(mm->context.ldt);
-
-	/*
-	 * Any change to mm->context.ldt is followed by an IPI to all
-	 * CPUs with the mm active.  The LDT will not be freed until
-	 * after the IPI is handled by all such CPUs.  This means that,
-	 * if the ldt_struct changes before we return, the values we see
-	 * will be safe, and the new values will be loaded before we run
-	 * any user code.
-	 *
-	 * NB: don't try to convert this to use RCU without extreme care.
-	 * We would still need IRQs off, because we don't want to change
-	 * the local LDT after an IPI loaded a newer value than the one
-	 * that we can see.
-	 */
-
-	if (unlikely(ldt)) {
-		if (static_cpu_has(X86_FEATURE_PTI)) {
-			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
-				/*
-				 * Whoops -- either the new LDT isn't mapped
-				 * (if slot == -1) or is mapped into a bogus
-				 * slot (if slot > 1).
-				 */
-				clear_LDT();
-				return;
-			}
-
-			/*
-			 * If page table isolation is enabled, ldt->entries
-			 * will not be mapped in the userspace pagetables.
-			 * Tell the CPU to access the LDT through the alias
-			 * at ldt_slot_va(ldt->slot).
-			 */
-			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
-		} else {
-			set_ldt(ldt->entries, ldt->nr_entries);
-		}
-	} else {
-		clear_LDT();
-	}
+extern void load_mm_ldt(struct mm_struct *mm);
+extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next);
 #else
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
 	clear_LDT();
-#endif
 }
-
 static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 {
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-	/*
-	 * Load the LDT if either the old or new mm had an LDT.
-	 *
-	 * An mm will never go from having an LDT to not having an LDT.  Two
-	 * mms never share an LDT, so we don't gain anything by checking to
-	 * see whether the LDT changed.  There's also no guarantee that
-	 * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL,
-	 * then prev->context.ldt will also be non-NULL.
-	 *
-	 * If we really cared, we could optimize the case where prev == next
-	 * and we're exiting lazy mode.  Most of the time, if this happens,
-	 * we don't actually need to reload LDTR, but modify_ldt() is mostly
-	 * used by legacy code and emulators where we don't need this level of
-	 * performance.
-	 *
-	 * This uses | instead of || because it generates better code.
-	 */
-	if (unlikely((unsigned long)prev->context.ldt |
-		     (unsigned long)next->context.ldt))
-		load_mm_ldt(next);
-#endif
-
 	DEBUG_LOCKS_WARN_ON(preemptible());
 }
+#endif
 
-void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
+extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
 /*
  * Init a new mm.  Used on mm copies, like at fork()

arch/x86/include/asm/mtrr.h

@@ -24,7 +24,7 @@
 #define _ASM_X86_MTRR_H
 
 #include <uapi/asm/mtrr.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 
 
 /*
@@ -86,7 +86,7 @@ static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 }
 static inline void mtrr_bp_init(void)
 {
-	pat_disable("MTRRs disabled, skipping PAT initialization too.");
+	pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel.");
 }
 
 #define mtrr_ap_init() do {} while (0)

arch/x86/include/asm/pci.h

@@ -9,7 +9,7 @@
 #include <linux/scatterlist.h>
 #include <linux/numa.h>
 #include <asm/io.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/x86_init.h>
 
 struct pci_sysdata {

arch/x86/include/asm/pgtable_32_areas.h

+#ifndef _ASM_X86_PGTABLE_32_AREAS_H
+#define _ASM_X86_PGTABLE_32_AREAS_H
+
+#include <asm/cpu_entry_area.h>
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET	(8 * 1024 * 1024)
+
+#ifndef __ASSEMBLY__
+extern bool __vmalloc_start_set; /* set once high_memory is set */
+#endif
+
+#define VMALLOC_START	((unsigned long)high_memory + VMALLOC_OFFSET)
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+
+#define CPU_ENTRY_AREA_PAGES		(NR_CPUS * DIV_ROUND_UP(sizeof(struct cpu_entry_area), PAGE_SIZE))
+
+/* The +1 is for the readonly IDT page: */
+#define CPU_ENTRY_AREA_BASE	\
+	((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
+
+#define LDT_BASE_ADDR		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
+
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PMD_SIZE)
+
+#define PKMAP_BASE		\
+	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
+
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
+#else
+# define VMALLOC_END	(LDT_BASE_ADDR - 2 * PAGE_SIZE)
+#endif
+
+#define MODULES_VADDR	VMALLOC_START
+#define MODULES_END	VMALLOC_END
+#define MODULES_LEN	(MODULES_VADDR - MODULES_END)
+
+#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
+
+#endif /* _ASM_X86_PGTABLE_32_AREAS_H */

arch/x86/include/asm/pgtable_32_types.h

 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_PGTABLE_32_DEFS_H
-#define _ASM_X86_PGTABLE_32_DEFS_H
+#ifndef _ASM_X86_PGTABLE_32_TYPES_H
+#define _ASM_X86_PGTABLE_32_TYPES_H
 
 /*
  * The Linux x86 paging architecture is 'compile-time dual-mode', it
@@ -20,55 +20,4 @@
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-/* Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8MB value just means that there will be a 8MB "hole" after the
- * physical memory until the kernel virtual memory starts.  That means that
- * any out-of-bounds memory accesses will hopefully be caught.
- * The vmalloc() routines leaves a hole of 4kB between each vmalloced
- * area for the same reason. ;)
- */
-#define VMALLOC_OFFSET	(8 * 1024 * 1024)
-
-#ifndef __ASSEMBLY__
-extern bool __vmalloc_start_set; /* set once high_memory is set */
-#endif
-
-#define VMALLOC_START	((unsigned long)high_memory + VMALLOC_OFFSET)
-#ifdef CONFIG_X86_PAE
-#define LAST_PKMAP 512
-#else
-#define LAST_PKMAP 1024
-#endif
-
-/*
- * This is an upper bound on sizeof(struct cpu_entry_area) / PAGE_SIZE.
- * Define this here and validate with BUILD_BUG_ON() in cpu_entry_area.c
- * to avoid include recursion hell.
- */
-#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 43)
-
-/* The +1 is for the readonly IDT page: */
-#define CPU_ENTRY_AREA_BASE	\
-	((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
-
-#define LDT_BASE_ADDR		\
-	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
-
-#define LDT_END_ADDR		(LDT_BASE_ADDR + PMD_SIZE)
-
-#define PKMAP_BASE		\
-	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
-
-#ifdef CONFIG_HIGHMEM
-# define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
-#else
-# define VMALLOC_END	(LDT_BASE_ADDR - 2 * PAGE_SIZE)
-#endif
-
-#define MODULES_VADDR	VMALLOC_START
-#define MODULES_END	VMALLOC_END
-#define MODULES_LEN	(MODULES_VADDR - MODULES_END)
-
-#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
-
-#endif /* _ASM_X86_PGTABLE_32_DEFS_H */
+#endif /* _ASM_X86_PGTABLE_32_TYPES_H */

arch/x86/include/asm/pgtable_areas.h

+#ifndef _ASM_X86_PGTABLE_AREAS_H
+#define _ASM_X86_PGTABLE_AREAS_H
+
+#ifdef CONFIG_X86_32
+# include <asm/pgtable_32_areas.h>
+#endif
+
+/* Single page reserved for the readonly IDT mapping: */
+#define CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE		(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
+
+#endif /* _ASM_X86_PGTABLE_AREAS_H */

arch/x86/include/asm/pgtable_types.h

@@ -110,11 +110,6 @@
 
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
-#define _PAGE_TABLE_NOENC	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\
-				 _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE_NOENC	(_PAGE_PRESENT | _PAGE_RW |		\
-				 _PAGE_ACCESSED | _PAGE_DIRTY)
-
 /*
  * Set of bits not changed in pte_modify.  The pte's
  * protection key is treated like _PAGE_RW, for
@@ -136,80 +131,93 @@
  */
 #ifndef __ASSEMBLY__
 enum page_cache_mode {
-	_PAGE_CACHE_MODE_WB = 0,
-	_PAGE_CACHE_MODE_WC = 1,
+	_PAGE_CACHE_MODE_WB       = 0,
+	_PAGE_CACHE_MODE_WC       = 1,
 	_PAGE_CACHE_MODE_UC_MINUS = 2,
-	_PAGE_CACHE_MODE_UC = 3,
-	_PAGE_CACHE_MODE_WT = 4,
-	_PAGE_CACHE_MODE_WP = 5,
-	_PAGE_CACHE_MODE_NUM = 8
+	_PAGE_CACHE_MODE_UC       = 3,
+	_PAGE_CACHE_MODE_WT       = 4,
+	_PAGE_CACHE_MODE_WP       = 5,
+
+	_PAGE_CACHE_MODE_NUM      = 8
 };
 #endif
 
-#define _PAGE_CACHE_MASK	(_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)
-#define _PAGE_NOCACHE		(cachemode2protval(_PAGE_CACHE_MODE_UC))
-#define _PAGE_CACHE_WP		(cachemode2protval(_PAGE_CACHE_MODE_WP))
+#define _PAGE_ENC		(_AT(pteval_t, sme_me_mask))
 
-#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
-				 _PAGE_ACCESSED | _PAGE_NX)
-
-#define PAGE_SHARED_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_RW |	\
-					 _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY_NOEXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_COPY_EXEC		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED)
-#define PAGE_COPY		PAGE_COPY_NOEXEC
-#define PAGE_READONLY		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED)
-
-#define __PAGE_KERNEL_EXEC						\
-	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
-#define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
-
-#define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
-#define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
-#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_NOCACHE)
-#define __PAGE_KERNEL_VVAR		(__PAGE_KERNEL_RO | _PAGE_USER)
-#define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
-#define __PAGE_KERNEL_WP		(__PAGE_KERNEL | _PAGE_CACHE_WP)
-
-#define __PAGE_KERNEL_IO		(__PAGE_KERNEL)
-#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE)
+#define _PAGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
 
-#ifndef __ASSEMBLY__
+#define _PAGE_NOCACHE		(cachemode2protval(_PAGE_CACHE_MODE_UC))
+#define _PAGE_CACHE_WP		(cachemode2protval(_PAGE_CACHE_MODE_WP))
 
-#define _PAGE_ENC	(_AT(pteval_t, sme_me_mask))
+#define __PP _PAGE_PRESENT
+#define __RW _PAGE_RW
+#define _USR _PAGE_USER
+#define ___A _PAGE_ACCESSED
+#define ___D _PAGE_DIRTY
+#define ___G _PAGE_GLOBAL
+#define __NX _PAGE_NX
+
+#define _ENC _PAGE_ENC
+#define __WP _PAGE_CACHE_WP
+#define __NC _PAGE_NOCACHE
+#define _PSE _PAGE_PSE
+
+#define pgprot_val(x)		((x).pgprot)
+#define __pgprot(x)		((pgprot_t) { (x) } )
+#define __pg(x)			__pgprot(x)
+
+#define _PAGE_PAT_LARGE		(_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
+
+#define PAGE_NONE	     __pg(   0|   0|   0|___A|   0|   0|   0|___G)
+#define PAGE_SHARED	     __pg(__PP|__RW|_USR|___A|__NX|   0|   0|   0)
+#define PAGE_SHARED_EXEC     __pg(__PP|__RW|_USR|___A|   0|   0|   0|   0)
+#define PAGE_COPY_NOEXEC     __pg(__PP|   0|_USR|___A|__NX|   0|   0|   0)
+#define PAGE_COPY_EXEC	     __pg(__PP|   0|_USR|___A|   0|   0|   0|   0)
+#define PAGE_COPY	     __pg(__PP|   0|_USR|___A|__NX|   0|   0|   0)
+#define PAGE_READONLY	     __pg(__PP|   0|_USR|___A|__NX|   0|   0|   0)
+#define PAGE_READONLY_EXEC   __pg(__PP|   0|_USR|___A|   0|   0|   0|   0)
+
+#define __PAGE_KERNEL		 (__PP|__RW|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_EXEC	 (__PP|__RW|   0|___A|   0|___D|   0|___G)
+#define _KERNPG_TABLE_NOENC	 (__PP|__RW|   0|___A|   0|___D|   0|   0)
+#define _KERNPG_TABLE		 (__PP|__RW|   0|___A|   0|___D|   0|   0| _ENC)
+#define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
+#define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
+#define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_RX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
+#define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
+#define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
+#define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW|   0|___A|   0|___D|_PSE|___G)
+#define __PAGE_KERNEL_WP	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __WP)
+
+
+#define __PAGE_KERNEL_IO		__PAGE_KERNEL
+#define __PAGE_KERNEL_IO_NOCACHE	__PAGE_KERNEL_NOCACHE
 
-#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
-			 _PAGE_DIRTY | _PAGE_ENC)
-#define _PAGE_TABLE	(_KERNPG_TABLE | _PAGE_USER)
 
-#define __PAGE_KERNEL_ENC	(__PAGE_KERNEL | _PAGE_ENC)
-#define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _PAGE_ENC)
+#ifndef __ASSEMBLY__
 
-#define __PAGE_KERNEL_NOENC	(__PAGE_KERNEL)
-#define __PAGE_KERNEL_NOENC_WP	(__PAGE_KERNEL_WP)
+#define __PAGE_KERNEL_ENC	(__PAGE_KERNEL    | _ENC)
+#define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _ENC)
+#define __PAGE_KERNEL_NOENC	(__PAGE_KERNEL    |    0)
+#define __PAGE_KERNEL_NOENC_WP	(__PAGE_KERNEL_WP |    0)
 
-#define default_pgprot(x)	__pgprot((x) & __default_kernel_pte_mask)
+#define __pgprot_mask(x)	__pgprot((x) & __default_kernel_pte_mask)
 
-#define PAGE_KERNEL		default_pgprot(__PAGE_KERNEL | _PAGE_ENC)
-#define PAGE_KERNEL_NOENC	default_pgprot(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO		default_pgprot(__PAGE_KERNEL_RO | _PAGE_ENC)
-#define PAGE_KERNEL_EXEC	default_pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_EXEC_NOENC	default_pgprot(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX		default_pgprot(__PAGE_KERNEL_RX | _PAGE_ENC)
-#define PAGE_KERNEL_NOCACHE	default_pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
-#define PAGE_KERNEL_LARGE	default_pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
-#define PAGE_KERNEL_LARGE_EXEC	default_pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_VVAR	default_pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
+#define PAGE_KERNEL		__pgprot_mask(__PAGE_KERNEL            | _ENC)
+#define PAGE_KERNEL_NOENC	__pgprot_mask(__PAGE_KERNEL            |    0)
+#define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
+#define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
+#define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
+#define PAGE_KERNEL_RX		__pgprot_mask(__PAGE_KERNEL_RX         | _ENC)
+#define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
+#define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
+#define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
+#define PAGE_KERNEL_VVAR	__pgprot_mask(__PAGE_KERNEL_VVAR       | _ENC)
 
-#define PAGE_KERNEL_IO		default_pgprot(__PAGE_KERNEL_IO)
-#define PAGE_KERNEL_IO_NOCACHE	default_pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#define PAGE_KERNEL_IO		__pgprot_mask(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE	__pgprot_mask(__PAGE_KERNEL_IO_NOCACHE)
 
 #endif	/* __ASSEMBLY__ */
 
@@ -449,9 +457,6 @@ static inline pteval_t pte_flags(pte_t pte)
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
-#define pgprot_val(x)	((x).pgprot)
-#define __pgprot(x)	((pgprot_t) { (x) } )
-
 extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM];
 extern uint8_t __pte2cachemode_tbl[8];
 

arch/x86/include/asm/vmalloc.h

+#ifndef _ASM_X86_VMALLOC_H
+#define _ASM_X86_VMALLOC_H
+
+#include <asm/pgtable_areas.h>
+
+#endif /* _ASM_X86_VMALLOC_H */

arch/x86/kernel/cpu/common.c

@@ -49,7 +49,7 @@
 #include <asm/cpu.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
 #include <asm/intel-family.h>

arch/x86/kernel/cpu/mtrr/generic.c

@@ -15,7 +15,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 
 #include "mtrr.h"
 

arch/x86/kernel/cpu/mtrr/mtrr.c

@@ -52,7 +52,7 @@
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 
 #include "mtrr.h"
 

arch/x86/kernel/cpu/scattered.c

@@ -4,7 +4,7 @@
  */
 #include <linux/cpu.h>
 
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 

arch/x86/kernel/cpu/topology.c

@@ -7,7 +7,7 @@
 
 #include <linux/cpu.h>
 #include <asm/apic.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/processor.h>
 
 #include "cpu.h"

arch/x86/kernel/kexec-bzimage64.c

@@ -177,7 +177,7 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	 * acpi_rsdp=<addr> on kernel command line to make second kernel boot
 	 * without efi.
 	 */
-	if (efi_enabled(EFI_OLD_MEMMAP))
+	if (efi_have_uv1_memmap())
 		return 0;
 
 	params->secure_boot = boot_params.secure_boot;

arch/x86/kernel/ldt.c

@@ -28,6 +28,89 @@
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
+#include <asm/pgtable_areas.h>
+
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+}
+
+void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* READ_ONCE synchronizes with smp_store_release */
+	ldt = READ_ONCE(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt)) {
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+				/*
+				 * Whoops -- either the new LDT isn't mapped
+				 * (if slot == -1) or is mapped into a bogus
+				 * slot (if slot > 1).
+				 */
+				clear_LDT();
+				return;
+			}
+
+			/*
+			 * If page table isolation is enabled, ldt->entries
+			 * will not be mapped in the userspace pagetables.
+			 * Tell the CPU to access the LDT through the alias
+			 * at ldt_slot_va(ldt->slot).
+			 */
+			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+		} else {
+			set_ldt(ldt->entries, ldt->nr_entries);
+		}
+	} else {
+		clear_LDT();
+	}
+}
+
+void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
+{
+	/*
+	 * Load the LDT if either the old or new mm had an LDT.
+	 *
+	 * An mm will never go from having an LDT to not having an LDT.  Two
+	 * mms never share an LDT, so we don't gain anything by checking to
+	 * see whether the LDT changed.  There's also no guarantee that
+	 * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL,
+	 * then prev->context.ldt will also be non-NULL.
+	 *
+	 * If we really cared, we could optimize the case where prev == next
+	 * and we're exiting lazy mode.  Most of the time, if this happens,
+	 * we don't actually need to reload LDTR, but modify_ldt() is mostly
+	 * used by legacy code and emulators where we don't need this level of
+	 * performance.
+	 *
+	 * This uses | instead of || because it generates better code.
+	 */
+	if (unlikely((unsigned long)prev->context.ldt |
+		     (unsigned long)next->context.ldt))
+		load_mm_ldt(next);
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
 
 static void refresh_ldt_segments(void)
 {

arch/x86/kernel/setup.c

@@ -42,6 +42,7 @@
 #include <asm/proto.h>
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
+#include <linux/vmalloc.h>
 
 /*
  * max_low_pfn_mapped: highest directly mapped pfn < 4 GB

arch/x86/kernel/x86_init.c

@@ -20,7 +20,7 @@
 #include <asm/irq.h>
 #include <asm/io_apic.h>
 #include <asm/hpet.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/tsc.h>
 #include <asm/iommu.h>
 #include <asm/mach_traps.h>

arch/x86/kvm/mmu/mmu.c

@@ -40,7 +40,7 @@
 #include <linux/kthread.h>
 
 #include <asm/page.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/cmpxchg.h>
 #include <asm/e820/api.h>
 #include <asm/io.h>

arch/x86/mm/Makefile

@@ -12,8 +12,10 @@ CFLAGS_REMOVE_mem_encrypt.o		= -pg
 CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 endif
 
-obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
+obj-y				:=  init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
+				    pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o
+
+obj-y				+= pat/
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -23,8 +25,6 @@ CFLAGS_mem_encrypt_identity.o	:= $(nostackp)
 
 CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
 
-obj-$(CONFIG_X86_PAT)		+= pat_interval.o
-
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o

arch/x86/mm/fault.c

@@ -29,6 +29,7 @@
 #include <asm/efi.h>			/* efi_recover_from_page_fault()*/
 #include <asm/desc.h>			/* store_idt(), ...		*/
 #include <asm/cpu_entry_area.h>		/* exception stack		*/
+#include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>

arch/x86/mm/init_32.c

@@ -52,6 +52,7 @@
 #include <asm/page_types.h>
 #include <asm/cpu_entry_area.h>
 #include <asm/init.h>
+#include <asm/pgtable_areas.h>
 
 #include "mm_internal.h"
 

arch/x86/mm/iomap_32.c

@@ -4,7 +4,7 @@
  */
 
 #include <asm/iomap.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <linux/export.h>
 #include <linux/highmem.h>
 
@@ -26,7 +26,7 @@ int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
 	if (!is_io_mapping_possible(base, size))
 		return -EINVAL;
 
-	ret = io_reserve_memtype(base, base + size, &pcm);
+	ret = memtype_reserve_io(base, base + size, &pcm);
 	if (ret)
 		return ret;
 
@@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(iomap_create_wc);
 
 void iomap_free(resource_size_t base, unsigned long size)
 {
-	io_free_memtype(base, base + size);
+	memtype_free_io(base, base + size);
 }
 EXPORT_SYMBOL_GPL(iomap_free);
 

arch/x86/mm/ioremap.c

@@ -24,7 +24,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/setup.h>
 
 #include "physaddr.h"
@@ -196,10 +196,10 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
 	phys_addr &= PHYSICAL_PAGE_MASK;
 	size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
-	retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
+	retval = memtype_reserve(phys_addr, (u64)phys_addr + size,
 						pcm, &new_pcm);
 	if (retval) {
-		printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
+		printk(KERN_ERR "ioremap memtype_reserve failed %d\n", retval);
 		return NULL;
 	}
 
@@ -255,7 +255,7 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
 	area->phys_addr = phys_addr;
 	vaddr = (unsigned long) area->addr;
 
-	if (kernel_map_sync_memtype(phys_addr, size, pcm))
+	if (memtype_kernel_map_sync(phys_addr, size, pcm))
 		goto err_free_area;
 
 	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
@@ -275,7 +275,7 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
 err_free_area:
 	free_vm_area(area);
 err_free_memtype:
-	free_memtype(phys_addr, phys_addr + size);
+	memtype_free(phys_addr, phys_addr + size);
 	return NULL;
 }
 
@@ -451,7 +451,7 @@ void iounmap(volatile void __iomem *addr)
 		return;
 	}
 
-	free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p));
+	memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p));
 
 	/* Finally remove it */
 	o = remove_vm_area((void __force *)addr);

arch/x86/mm/pat/Makefile

+# SPDX-License-Identifier: GPL-2.0
+
+obj-y				:= set_memory.o memtype.o
+
+obj-$(CONFIG_X86_PAT)		+= memtype_interval.o

arch/x86/mm/pat_internal.h → arch/x86/mm/pat/memtype.h

 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PAT_INTERNAL_H_
-#define __PAT_INTERNAL_H_
+#ifndef __MEMTYPE_H_
+#define __MEMTYPE_H_
 
 extern int pat_debug_enable;
 
@@ -29,13 +29,13 @@ static inline char *cattr_name(enum page_cache_mode pcm)
 }
 
 #ifdef CONFIG_X86_PAT
-extern int memtype_check_insert(struct memtype *new,
+extern int memtype_check_insert(struct memtype *entry_new,
 				enum page_cache_mode *new_type);
 extern struct memtype *memtype_erase(u64 start, u64 end);
 extern struct memtype *memtype_lookup(u64 addr);
-extern int memtype_copy_nth_element(struct memtype *out, loff_t pos);
+extern int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos);
 #else
-static inline int memtype_check_insert(struct memtype *new,
+static inline int memtype_check_insert(struct memtype *entry_new,
 				       enum page_cache_mode *new_type)
 { return 0; }
 static inline struct memtype *memtype_erase(u64 start, u64 end)
@@ -46,4 +46,4 @@ static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos)
 { return 0; }
 #endif
 
-#endif /* __PAT_INTERNAL_H_ */
+#endif /* __MEMTYPE_H_ */

arch/x86/mm/pat_interval.c → arch/x86/mm/pat/memtype_interval.c

@@ -16,34 +16,36 @@
 #include <linux/gfp.h>
 
 #include <asm/pgtable.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 
-#include "pat_internal.h"
+#include "memtype.h"
 
 /*
  * The memtype tree keeps track of memory type for specific
  * physical memory areas. Without proper tracking, conflicting memory
  * types in different mappings can cause CPU cache corruption.
  *
- * The tree is an interval tree (augmented rbtree) with tree ordered
- * on starting address. Tree can contain multiple entries for
+ * The tree is an interval tree (augmented rbtree) which tree is ordered
+ * by the starting address. The tree can contain multiple entries for
  * different regions which overlap. All the aliases have the same
- * cache attributes of course.
+ * cache attributes of course, as enforced by the PAT logic.
  *
  * memtype_lock protects the rbtree.
  */
-static inline u64 memtype_interval_start(struct memtype *memtype)
+
+static inline u64 interval_start(struct memtype *entry)
 {
-	return memtype->start;
+	return entry->start;
 }
 
-static inline u64 memtype_interval_end(struct memtype *memtype)
+static inline u64 interval_end(struct memtype *entry)
 {
-	return memtype->end - 1;
+	return entry->end - 1;
 }
+
 INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
-		     memtype_interval_start, memtype_interval_end,
-		     static, memtype_interval)
+		     interval_start, interval_end,
+		     static, interval)
 
 static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED;
 
@@ -54,19 +56,20 @@ enum {
 
 static struct memtype *memtype_match(u64 start, u64 end, int match_type)
 {
-	struct memtype *match;
+	struct memtype *entry_match;
 
-	match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
-	while (match != NULL && match->start < end) {
+	entry_match = interval_iter_first(&memtype_rbroot, start, end-1);
+
+	while (entry_match != NULL && entry_match->start < end) {
 		if ((match_type == MEMTYPE_EXACT_MATCH) &&
-		    (match->start == start) && (match->end == end))
-			return match;
+		    (entry_match->start == start) && (entry_match->end == end))
+			return entry_match;
 
 		if ((match_type == MEMTYPE_END_MATCH) &&
-		    (match->start < start) && (match->end == end))
-			return match;
+		    (entry_match->start < start) && (entry_match->end == end))
+			return entry_match;
 
-		match = memtype_interval_iter_next(match, start, end-1);
+		entry_match = interval_iter_next(entry_match, start, end-1);
 	}
 
 	return NULL; /* Returns NULL if there is no match */
@@ -76,25 +79,25 @@ static int memtype_check_conflict(u64 start, u64 end,
 				  enum page_cache_mode reqtype,
 				  enum page_cache_mode *newtype)
 {
-	struct memtype *match;
+	struct memtype *entry_match;
 	enum page_cache_mode found_type = reqtype;
 
-	match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
-	if (match == NULL)
+	entry_match = interval_iter_first(&memtype_rbroot, start, end-1);
+	if (entry_match == NULL)
 		goto success;
 
-	if (match->type != found_type && newtype == NULL)
+	if (entry_match->type != found_type && newtype == NULL)
 		goto failure;
 
-	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
-	found_type = match->type;
+	dprintk("Overlap at 0x%Lx-0x%Lx\n", entry_match->start, entry_match->end);
+	found_type = entry_match->type;
 
-	match = memtype_interval_iter_next(match, start, end-1);
-	while (match) {
-		if (match->type != found_type)
+	entry_match = interval_iter_next(entry_match, start, end-1);
+	while (entry_match) {
+		if (entry_match->type != found_type)
 			goto failure;
 
-		match = memtype_interval_iter_next(match, start, end-1);
+		entry_match = interval_iter_next(entry_match, start, end-1);
 	}
 success:
 	if (newtype)
@@ -105,29 +108,29 @@ static int memtype_check_conflict(u64 start, u64 end,
 failure:
 	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
 		current->comm, current->pid, start, end,
-		cattr_name(found_type), cattr_name(match->type));
+		cattr_name(found_type), cattr_name(entry_match->type));
+
 	return -EBUSY;
 }
 
-int memtype_check_insert(struct memtype *new,
-			 enum page_cache_mode *ret_type)
+int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_type)
 {
 	int err = 0;
 
-	err = memtype_check_conflict(new->start, new->end, new->type, ret_type);
+	err = memtype_check_conflict(entry_new->start, entry_new->end, entry_new->type, ret_type);
 	if (err)
 		return err;
 
 	if (ret_type)
-		new->type = *ret_type;
+		entry_new->type = *ret_type;
 
-	memtype_interval_insert(new, &memtype_rbroot);
+	interval_insert(entry_new, &memtype_rbroot);
 	return 0;
 }
 
 struct memtype *memtype_erase(u64 start, u64 end)
 {
-	struct memtype *data;
+	struct memtype *entry_old;
 
 	/*
 	 * Since the memtype_rbroot tree allows overlapping ranges,
@@ -136,47 +139,53 @@ struct memtype *memtype_erase(u64 start, u64 end)
 	 * it then checks with END_MATCH, i.e. shrink the size of a node
 	 * from the end for the mremap case.
 	 */
-	data = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
-	if (!data) {
-		data = memtype_match(start, end, MEMTYPE_END_MATCH);
-		if (!data)
+	entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
+	if (!entry_old) {
+		entry_old = memtype_match(start, end, MEMTYPE_END_MATCH);
+		if (!entry_old)
 			return ERR_PTR(-EINVAL);
 	}
 
-	if (data->start == start) {
+	if (entry_old->start == start) {
 		/* munmap: erase this node */
-		memtype_interval_remove(data, &memtype_rbroot);
+		interval_remove(entry_old, &memtype_rbroot);
 	} else {
 		/* mremap: update the end value of this node */
-		memtype_interval_remove(data, &memtype_rbroot);
-		data->end = start;
-		memtype_interval_insert(data, &memtype_rbroot);
+		interval_remove(entry_old, &memtype_rbroot);
+		entry_old->end = start;
+		interval_insert(entry_old, &memtype_rbroot);
+
 		return NULL;
 	}
 
-	return data;
+	return entry_old;
 }
 
 struct memtype *memtype_lookup(u64 addr)
 {
-	return memtype_interval_iter_first(&memtype_rbroot, addr,
-					   addr + PAGE_SIZE-1);
+	return interval_iter_first(&memtype_rbroot, addr, addr + PAGE_SIZE-1);
 }
 
-#if defined(CONFIG_DEBUG_FS)
-int memtype_copy_nth_element(struct memtype *out, loff_t pos)
+/*
+ * Debugging helper, copy the Nth entry of the tree into a
+ * a copy for printout. This allows us to print out the tree
+ * via debugfs, without holding the memtype_lock too long:
+ */
+#ifdef CONFIG_DEBUG_FS
+int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos)
 {
-	struct memtype *match;
+	struct memtype *entry_match;
 	int i = 1;
 
-	match = memtype_interval_iter_first(&memtype_rbroot, 0, ULONG_MAX);
-	while (match && pos != i) {
-		match = memtype_interval_iter_next(match, 0, ULONG_MAX);
+	entry_match = interval_iter_first(&memtype_rbroot, 0, ULONG_MAX);
+
+	while (entry_match && pos != i) {
+		entry_match = interval_iter_next(entry_match, 0, ULONG_MAX);
 		i++;
 	}
 
-	if (match) { /* pos == i */
-		*out = *match;
+	if (entry_match) { /* pos == i */
+		*entry_out = *entry_match;
 		return 0;
 	} else {
 		return 1;

arch/x86/mm/pageattr.c → arch/x86/mm/pat/set_memory.c

@@ -24,10 +24,10 @@
 #include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/set_memory.h>
 
-#include "mm_internal.h"
+#include "../mm_internal.h"
 
 /*
  * The current flushing context - we pass it instead of 5 arguments:
@@ -331,7 +331,7 @@ static void cpa_flush_all(unsigned long cache)
 	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
 }
 
-void __cpa_flush_tlb(void *data)
+static void __cpa_flush_tlb(void *data)
 {
 	struct cpa_data *cpa = data;
 	unsigned int i;
@@ -1801,7 +1801,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 	/*
 	 * for now UC MINUS. see comments in ioremap()
 	 */
-	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+	ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 			      _PAGE_CACHE_MODE_UC_MINUS, NULL);
 	if (ret)
 		goto out_err;
@@ -1813,7 +1813,7 @@ int set_memory_uc(unsigned long addr, int numpages)
 	return 0;
 
 out_free:
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 out_err:
 	return ret;
 }
@@ -1839,14 +1839,14 @@ int set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
 
-	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+	ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 		_PAGE_CACHE_MODE_WC, NULL);
 	if (ret)
 		return ret;
 
 	ret = _set_memory_wc(addr, numpages);
 	if (ret)
-		free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+		memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
 	return ret;
 }
@@ -1873,7 +1873,7 @@ int set_memory_wb(unsigned long addr, int numpages)
 	if (ret)
 		return ret;
 
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 	return 0;
 }
 EXPORT_SYMBOL(set_memory_wb);
@@ -2014,7 +2014,7 @@ static int _set_pages_array(struct page **pages, int numpages,
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
-		if (reserve_memtype(start, end, new_type, NULL))
+		if (memtype_reserve(start, end, new_type, NULL))
 			goto err_out;
 	}
 
@@ -2040,7 +2040,7 @@ static int _set_pages_array(struct page **pages, int numpages,
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
-		free_memtype(start, end);
+		memtype_free(start, end);
 	}
 	return -EINVAL;
 }
@@ -2089,7 +2089,7 @@ int set_pages_array_wb(struct page **pages, int numpages)
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
-		free_memtype(start, end);
+		memtype_free(start, end);
 	}
 
 	return 0;
@@ -2215,7 +2215,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(0),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
 		.flags = 0,
 	};
 
@@ -2224,12 +2224,6 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 	if (!(__supported_pte_mask & _PAGE_NX))
 		goto out;
 
-	if (!(page_flags & _PAGE_NX))
-		cpa.mask_clr = __pgprot(_PAGE_NX);
-
-	if (!(page_flags & _PAGE_RW))
-		cpa.mask_clr = __pgprot(_PAGE_RW);
-
 	if (!(page_flags & _PAGE_ENC))
 		cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);
 
@@ -2281,5 +2275,5 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
  * be exposed to the rest of the kernel. Include these directly here.
  */
 #ifdef CONFIG_CPA_DEBUG
-#include "pageattr-test.c"
+#include "cpa-test.c"
 #endif

arch/x86/mm/pgtable_32.c

@@ -18,6 +18,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/io.h>
+#include <linux/vmalloc.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 

arch/x86/mm/physaddr.c

@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 
 #include <asm/page.h>
+#include <linux/vmalloc.h>
 
 #include "physaddr.h"
 

arch/x86/pci/i386.c

@@ -34,7 +34,7 @@
 #include <linux/errno.h>
 #include <linux/memblock.h>
 
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/e820/api.h>
 #include <asm/pci_x86.h>
 #include <asm/io_apic.h>

arch/x86/platform/efi/Makefile

 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y
-OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y
+KASAN_SANITIZE := n
+GCOV_PROFILE := n
 
 obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o

arch/x86/platform/efi/efi_32.c

@@ -66,9 +66,17 @@ void __init efi_map_region(efi_memory_desc_t *md)
 void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
 void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
 
-pgd_t * __init efi_call_phys_prolog(void)
+efi_status_t efi_call_svam(efi_set_virtual_address_map_t *__efiapi *,
+			   u32, u32, u32, void *);
+
+efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size,
+						unsigned long descriptor_size,
+						u32 descriptor_version,
+						efi_memory_desc_t *virtual_map)
 {
 	struct desc_ptr gdt_descr;
+	efi_status_t status;
+	unsigned long flags;
 	pgd_t *save_pgd;
 
 	/* Current pgd is swapper_pg_dir, we'll restore it later: */
@@ -80,14 +88,18 @@ pgd_t * __init efi_call_phys_prolog(void)
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
-	return save_pgd;
-}
+	/* Disable interrupts around EFI calls: */
+	local_irq_save(flags);
+	status = efi_call_svam(&efi.systab->runtime->set_virtual_address_map,
+			       memory_map_size, descriptor_size,
+			       descriptor_version, virtual_map);
+	local_irq_restore(flags);
 
-void __init efi_call_phys_epilog(pgd_t *save_pgd)
-{
 	load_fixmap_gdt(0);
 	load_cr3(save_pgd);
 	__flush_tlb_all();
+
+	return status;
 }
 
 void __init efi_runtime_update_mappings(void)

arch/x86/platform/efi/efi_stub_32.S

@@ -7,118 +7,43 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/init.h>
 #include <asm/page_types.h>
 
-/*
- * efi_call_phys(void *, ...) is a function with variable parameters.
- * All the callers of this function assure that all the parameters are 4-bytes.
- */
-
-/*
- * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save.
- * So we'd better save all of them at the beginning of this function and restore
- * at the end no matter how many we use, because we can not assure EFI runtime
- * service functions will comply with gcc calling convention, too.
- */
+	__INIT
+SYM_FUNC_START(efi_call_svam)
+	push	8(%esp)
+	push	8(%esp)
+	push	%ecx
+	push	%edx
 
-.text
-SYM_FUNC_START(efi_call_phys)
 	/*
-	 * 0. The function can only be called in Linux kernel. So CS has been
-	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
-	 * the values of these registers are the same. And, the corresponding
-	 * GDT entries are identical. So I will do nothing about segment reg
-	 * and GDT, but change GDT base register in prolog and epilog.
-	 */
-
-	/*
-	 * 1. Now I am running with EIP = <physical address> + PAGE_OFFSET.
-	 * But to make it smoothly switch from virtual mode to flat mode.
-	 * The mapping of lower virtual memory has been created in prolog and
-	 * epilog.
+	 * Switch to the flat mapped alias of this routine, by jumping to the
+	 * address of label '1' after subtracting PAGE_OFFSET from it.
 	 */
 	movl	$1f, %edx
 	subl	$__PAGE_OFFSET, %edx
 	jmp	*%edx
 1:
 
-	/*
-	 * 2. Now on the top of stack is the return
-	 * address in the caller of efi_call_phys(), then parameter 1,
-	 * parameter 2, ..., param n. To make things easy, we save the return
-	 * address of efi_call_phys in a global variable.
-	 */
-	popl	%edx
-	movl	%edx, saved_return_addr
-	/* get the function pointer into ECX*/
-	popl	%ecx
-	movl	%ecx, efi_rt_function_ptr
-	movl	$2f, %edx
-	subl	$__PAGE_OFFSET, %edx
-	pushl	%edx
-
-	/*
-	 * 3. Clear PG bit in %CR0.
-	 */
+	/* disable paging */
 	movl	%cr0, %edx
 	andl	$0x7fffffff, %edx
 	movl	%edx, %cr0
-	jmp	1f
-1:
 
-	/*
-	 * 4. Adjust stack pointer.
-	 */
+	/* convert the stack pointer to a flat mapped address */
 	subl	$__PAGE_OFFSET, %esp
 
-	/*
-	 * 5. Call the physical function.
-	 */
-	jmp	*%ecx
+	/* call the EFI routine */
+	call	*(%eax)
 
-2:
-	/*
-	 * 6. After EFI runtime service returns, control will return to
-	 * following instruction. We'd better readjust stack pointer first.
-	 */
-	addl	$__PAGE_OFFSET, %esp
+	/* convert ESP back to a kernel VA, and pop the outgoing args */
+	addl	$__PAGE_OFFSET + 16, %esp
 
-	/*
-	 * 7. Restore PG bit
-	 */
+	/* re-enable paging */
 	movl	%cr0, %edx
 	orl	$0x80000000, %edx
 	movl	%edx, %cr0
-	jmp	1f
-1:
-	/*
-	 * 8. Now restore the virtual mode from flat mode by
-	 * adding EIP with PAGE_OFFSET.
-	 */
-	movl	$1f, %edx
-	jmp	*%edx
-1:
-
-	/*
-	 * 9. Balance the stack. And because EAX contain the return value,
-	 * we'd better not clobber it.
-	 */
-	leal	efi_rt_function_ptr, %edx
-	movl	(%edx), %ecx
-	pushl	%ecx
 
-	/*
-	 * 10. Push the saved return address onto the stack and return.
-	 */
-	leal	saved_return_addr, %edx
-	movl	(%edx), %ecx
-	pushl	%ecx
 	ret
-SYM_FUNC_END(efi_call_phys)
-.previous
-
-.data
-saved_return_addr:
-	.long 0
-efi_rt_function_ptr:
-	.long 0
+SYM_FUNC_END(efi_call_svam)

arch/x86/platform/efi/efi_stub_64.S

@@ -8,41 +8,12 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/segment.h>
-#include <asm/msr.h>
-#include <asm/processor-flags.h>
-#include <asm/page_types.h>
+#include <asm/nospec-branch.h>
 
-#define SAVE_XMM			\
-	mov %rsp, %rax;			\
-	subq $0x70, %rsp;		\
-	and $~0xf, %rsp;		\
-	mov %rax, (%rsp);		\
-	mov %cr0, %rax;			\
-	clts;				\
-	mov %rax, 0x8(%rsp);		\
-	movaps %xmm0, 0x60(%rsp);	\
-	movaps %xmm1, 0x50(%rsp);	\
-	movaps %xmm2, 0x40(%rsp);	\
-	movaps %xmm3, 0x30(%rsp);	\
-	movaps %xmm4, 0x20(%rsp);	\
-	movaps %xmm5, 0x10(%rsp)
-
-#define RESTORE_XMM			\
-	movaps 0x60(%rsp), %xmm0;	\
-	movaps 0x50(%rsp), %xmm1;	\
-	movaps 0x40(%rsp), %xmm2;	\
-	movaps 0x30(%rsp), %xmm3;	\
-	movaps 0x20(%rsp), %xmm4;	\
-	movaps 0x10(%rsp), %xmm5;	\
-	mov 0x8(%rsp), %rsi;		\
-	mov %rsi, %cr0;			\
-	mov (%rsp), %rsp
-
-SYM_FUNC_START(efi_call)
+SYM_FUNC_START(__efi_call)
 	pushq %rbp
 	movq %rsp, %rbp
-	SAVE_XMM
+	and $~0xf, %rsp
 	mov 16(%rbp), %rax
 	subq $48, %rsp
 	mov %r9, 32(%rsp)
@@ -50,9 +21,7 @@ SYM_FUNC_START(efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	call *%rdi
-	addq $48, %rsp
-	RESTORE_XMM
-	popq %rbp
+	CALL_NOSPEC %rdi
+	leave
 	ret
-SYM_FUNC_END(efi_call)
+SYM_FUNC_END(__efi_call)

arch/x86/platform/efi/efi_thunk_64.S

@@ -25,15 +25,16 @@
 
 	.text
 	.code64
-SYM_FUNC_START(efi64_thunk)
+SYM_CODE_START(__efi64_thunk)
 	push	%rbp
 	push	%rbx
 
 	/*
 	 * Switch to 1:1 mapped 32-bit stack pointer.
 	 */
-	movq	%rsp, efi_saved_sp(%rip)
+	movq	%rsp, %rax
 	movq	efi_scratch(%rip), %rsp
+	push	%rax
 
 	/*
 	 * Calculate the physical address of the kernel text.
@@ -41,113 +42,31 @@ SYM_FUNC_START(efi64_thunk)
 	movq	$__START_KERNEL_map, %rax
 	subq	phys_base(%rip), %rax
 
-	/*
-	 * Push some physical addresses onto the stack. This is easier
-	 * to do now in a code64 section while the assembler can address
-	 * 64-bit values. Note that all the addresses on the stack are
-	 * 32-bit.
-	 */
-	subq	$16, %rsp
-	leaq	efi_exit32(%rip), %rbx
-	subq	%rax, %rbx
-	movl	%ebx, 8(%rsp)
-
-	leaq	__efi64_thunk(%rip), %rbx
+	leaq	1f(%rip), %rbp
+	leaq	2f(%rip), %rbx
+	subq	%rax, %rbp
 	subq	%rax, %rbx
-	call	*%rbx
-
-	movq	efi_saved_sp(%rip), %rsp
-	pop	%rbx
-	pop	%rbp
-	retq
-SYM_FUNC_END(efi64_thunk)
 
-/*
- * We run this function from the 1:1 mapping.
- *
- * This function must be invoked with a 1:1 mapped stack.
- */
-SYM_FUNC_START_LOCAL(__efi64_thunk)
-	movl	%ds, %eax
-	push	%rax
-	movl	%es, %eax
-	push	%rax
-	movl	%ss, %eax
-	push	%rax
-
-	subq	$32, %rsp
-	movl	%esi, 0x0(%rsp)
-	movl	%edx, 0x4(%rsp)
-	movl	%ecx, 0x8(%rsp)
-	movq	%r8, %rsi
-	movl	%esi, 0xc(%rsp)
-	movq	%r9, %rsi
-	movl	%esi,  0x10(%rsp)
-
-	leaq	1f(%rip), %rbx
-	movq	%rbx, func_rt_ptr(%rip)
+	subq	$28, %rsp
+	movl	%ebx, 0x0(%rsp)		/* return address */
+	movl	%esi, 0x4(%rsp)
+	movl	%edx, 0x8(%rsp)
+	movl	%ecx, 0xc(%rsp)
+	movl	%r8d, 0x10(%rsp)
+	movl	%r9d, 0x14(%rsp)
 
 	/* Switch to 32-bit descriptor */
 	pushq	$__KERNEL32_CS
-	leaq	efi_enter32(%rip), %rax
-	pushq	%rax
+	pushq	%rdi			/* EFI runtime service address */
 	lretq
 
-1:	addq	$32, %rsp
-
+1:	movq	24(%rsp), %rsp
 	pop	%rbx
-	movl	%ebx, %ss
-	pop	%rbx
-	movl	%ebx, %es
-	pop	%rbx
-	movl	%ebx, %ds
-
-	/*
-	 * Convert 32-bit status code into 64-bit.
-	 */
-	test	%rax, %rax
-	jz	1f
-	movl	%eax, %ecx
-	andl	$0x0fffffff, %ecx
-	andl	$0xf0000000, %eax
-	shl	$32, %rax
-	or	%rcx, %rax
-1:
-	ret
-SYM_FUNC_END(__efi64_thunk)
-
-SYM_FUNC_START_LOCAL(efi_exit32)
-	movq	func_rt_ptr(%rip), %rax
-	push	%rax
-	mov	%rdi, %rax
-	ret
-SYM_FUNC_END(efi_exit32)
+	pop	%rbp
+	retq
 
 	.code32
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-SYM_FUNC_START_LOCAL(efi_enter32)
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %es
-	movl	%eax, %ss
-
-	call	*%edi
-
-	/* We must preserve return value */
-	movl	%eax, %edi
-
-	movl	72(%esp), %eax
-	pushl	$__KERNEL_CS
-	pushl	%eax
-
+2:	pushl	$__KERNEL_CS
+	pushl	%ebp
 	lret
-SYM_FUNC_END(efi_enter32)
-
-	.data
-	.balign	8
-func_rt_ptr:		.quad 0
-efi_saved_sp:		.quad 0
+SYM_CODE_END(__efi64_thunk)

arch/x86/platform/efi/quirks.c

@@ -244,7 +244,7 @@ EXPORT_SYMBOL_GPL(efi_query_variable_store);
  */
 void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 {
-	phys_addr_t new_phys, new_size;
+	struct efi_memory_map_data data = { 0 };
 	struct efi_mem_range mr;
 	efi_memory_desc_t md;
 	int num_entries;
@@ -272,24 +272,21 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 	num_entries = efi_memmap_split_count(&md, &mr.range);
 	num_entries += efi.memmap.nr_map;
 
-	new_size = efi.memmap.desc_size * num_entries;
-
-	new_phys = efi_memmap_alloc(num_entries);
-	if (!new_phys) {
+	if (efi_memmap_alloc(num_entries, &data) != 0) {
 		pr_err("Could not allocate boot services memmap\n");
 		return;
 	}
 
-	new = early_memremap(new_phys, new_size);
+	new = early_memremap(data.phys_map, data.size);
 	if (!new) {
 		pr_err("Failed to map new boot services memmap\n");
 		return;
 	}
 
 	efi_memmap_insert(&efi.memmap, new, &mr);
-	early_memunmap(new, new_size);
+	early_memunmap(new, data.size);
 
-	efi_memmap_install(new_phys, num_entries);
+	efi_memmap_install(&data);
 	e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
 	e820__update_table(e820_table);
 }
@@ -385,10 +382,10 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 
 	/*
 	 * To Do: Remove this check after adding functionality to unmap EFI boot
-	 * services code/data regions from direct mapping area because
-	 * "efi=old_map" maps EFI regions in swapper_pg_dir.
+	 * services code/data regions from direct mapping area because the UV1
+	 * memory map maps EFI regions in swapper_pg_dir.
 	 */
-	if (efi_enabled(EFI_OLD_MEMMAP))
+	if (efi_have_uv1_memmap())
 		return;
 
 	/*
@@ -396,7 +393,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 	 * EFI runtime calls, hence don't unmap EFI boot services code/data
 	 * regions.
 	 */
-	if (!efi_is_native())
+	if (efi_is_mixed())
 		return;
 
 	if (kernel_unmap_pages_in_pgd(pgd, pa, md->num_pages))
@@ -408,7 +405,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 
 void __init efi_free_boot_services(void)
 {
-	phys_addr_t new_phys, new_size;
+	struct efi_memory_map_data data = { 0 };
 	efi_memory_desc_t *md;
 	int num_entries = 0;
 	void *new, *new_md;
@@ -463,14 +460,12 @@ void __init efi_free_boot_services(void)
 	if (!num_entries)
 		return;
 
-	new_size = efi.memmap.desc_size * num_entries;
-	new_phys = efi_memmap_alloc(num_entries);
-	if (!new_phys) {
+	if (efi_memmap_alloc(num_entries, &data) != 0) {
 		pr_err("Failed to allocate new EFI memmap\n");
 		return;
 	}
 
-	new = memremap(new_phys, new_size, MEMREMAP_WB);
+	new = memremap(data.phys_map, data.size, MEMREMAP_WB);
 	if (!new) {
 		pr_err("Failed to map new EFI memmap\n");
 		return;
@@ -494,7 +489,7 @@ void __init efi_free_boot_services(void)
 
 	memunmap(new);
 
-	if (efi_memmap_install(new_phys, num_entries)) {
+	if (efi_memmap_install(&data) != 0) {
 		pr_err("Could not install new EFI memmap\n");
 		return;
 	}
@@ -559,7 +554,7 @@ int __init efi_reuse_config(u64 tables, int nr_tables)
 	return ret;
 }
 
-static const struct dmi_system_id sgi_uv1_dmi[] = {
+static const struct dmi_system_id sgi_uv1_dmi[] __initconst = {
 	{ NULL, "SGI UV1",
 		{	DMI_MATCH(DMI_PRODUCT_NAME,	"Stoutland Platform"),
 			DMI_MATCH(DMI_PRODUCT_VERSION,	"1.0"),
@@ -582,8 +577,15 @@ void __init efi_apply_memmap_quirks(void)
 	}
 
 	/* UV2+ BIOS has a fix for this issue.  UV1 still needs the quirk. */
-	if (dmi_check_system(sgi_uv1_dmi))
-		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+	if (dmi_check_system(sgi_uv1_dmi)) {
+		if (IS_ENABLED(CONFIG_X86_UV)) {
+			set_bit(EFI_UV1_MEMMAP, &efi.flags);
+		} else {
+			pr_warn("EFI runtime disabled, needs CONFIG_X86_UV=y on UV1\n");
+			clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+			efi_memmap_unmap();
+		}
+	}
 }
 
 /*
@@ -721,7 +723,7 @@ void efi_recover_from_page_fault(unsigned long phys_addr)
 	/*
 	 * Make sure that an efi runtime service caused the page fault.
 	 * "efi_mm" cannot be used to check if the page fault had occurred
-	 * in the firmware context because efi=old_map doesn't use efi_pgd.
+	 * in the firmware context because the UV1 memmap doesn't use efi_pgd.
 	 */
 	if (efi_rts_work.efi_rts_id == EFI_NONE)
 		return;

arch/x86/platform/uv/bios_uv.c

@@ -31,13 +31,16 @@ static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 		return BIOS_STATUS_UNIMPLEMENTED;
 
 	/*
-	 * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI
+	 * If EFI_UV1_MEMMAP is set, we need to fall back to using our old EFI
 	 * callback method, which uses efi_call() directly, with the kernel page tables:
 	 */
-	if (unlikely(efi_enabled(EFI_OLD_MEMMAP)))
+	if (unlikely(efi_enabled(EFI_UV1_MEMMAP))) {
+		kernel_fpu_begin();
 		ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5);
-	else
+		kernel_fpu_end();
+	} else {
 		ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+	}
 
 	return ret;
 }
@@ -214,3 +217,163 @@ int uv_bios_init(void)
 	pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision);
 	return 0;
 }
+
+static void __init early_code_mapping_set_exec(int executable)
+{
+	efi_memory_desc_t *md;
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return;
+
+	/* Make EFI service code area executable */
+	for_each_efi_memory_desc(md) {
+		if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+		    md->type == EFI_BOOT_SERVICES_CODE)
+			efi_set_executable(md, executable);
+	}
+}
+
+void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd)
+{
+	/*
+	 * After the lock is released, the original page table is restored.
+	 */
+	int pgd_idx, i;
+	int nr_pgds;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+
+	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+		pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
+
+		if (!pgd_present(*pgd))
+			continue;
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			p4d = p4d_offset(pgd,
+					 pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+			if (!p4d_present(*p4d))
+				continue;
+
+			pud = (pud_t *)p4d_page_vaddr(*p4d);
+			pud_free(&init_mm, pud);
+		}
+
+		p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		p4d_free(&init_mm, p4d);
+	}
+
+	kfree(save_pgd);
+
+	__flush_tlb_all();
+	early_code_mapping_set_exec(0);
+}
+
+pgd_t * __init efi_uv1_memmap_phys_prolog(void)
+{
+	unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+	pgd_t *save_pgd, *pgd_k, *pgd_efi;
+	p4d_t *p4d, *p4d_k, *p4d_efi;
+	pud_t *pud;
+
+	int pgd;
+	int n_pgds, i, j;
+
+	early_code_mapping_set_exec(1);
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
+	if (!save_pgd)
+		return NULL;
+
+	/*
+	 * Build 1:1 identity mapping for UV1 memmap usage. Note that
+	 * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+	 * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+	 * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+	 * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+	 * This means here we can only reuse the PMD tables of the direct mapping.
+	 */
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+		vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+		pgd_efi = pgd_offset_k(addr_pgd);
+		save_pgd[pgd] = *pgd_efi;
+
+		p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+		if (!p4d) {
+			pr_err("Failed to allocate p4d table!\n");
+			goto out;
+		}
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			addr_p4d = addr_pgd + i * P4D_SIZE;
+			p4d_efi = p4d + p4d_index(addr_p4d);
+
+			pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+			if (!pud) {
+				pr_err("Failed to allocate pud table!\n");
+				goto out;
+			}
+
+			for (j = 0; j < PTRS_PER_PUD; j++) {
+				addr_pud = addr_p4d + j * PUD_SIZE;
+
+				if (addr_pud > (max_pfn << PAGE_SHIFT))
+					break;
+
+				vaddr = (unsigned long)__va(addr_pud);
+
+				pgd_k = pgd_offset_k(vaddr);
+				p4d_k = p4d_offset(pgd_k, vaddr);
+				pud[j] = *pud_offset(p4d_k, vaddr);
+			}
+		}
+		pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX;
+	}
+
+	__flush_tlb_all();
+	return save_pgd;
+out:
+	efi_uv1_memmap_phys_epilog(save_pgd);
+	return NULL;
+}
+
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
+				 u32 type, u64 attribute)
+{
+	unsigned long last_map_pfn;
+
+	if (type == EFI_MEMORY_MAPPED_IO)
+		return ioremap(phys_addr, size);
+
+	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
+	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+		unsigned long top = last_map_pfn << PAGE_SHIFT;
+		efi_ioremap(top, size - (top - phys_addr), type, attribute);
+	}
+
+	if (!(attribute & EFI_MEMORY_WB))
+		efi_memory_uc((u64)(unsigned long)__va(phys_addr), size);
+
+	return (void __iomem *)__va(phys_addr);
+}
+
+static int __init arch_parse_efi_cmdline(char *str)
+{
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
+	if (!efi_is_mixed() && parse_option_str(str, "old_map"))
+		set_bit(EFI_UV1_MEMMAP, &efi.flags);
+
+	return 0;
+}
+early_param("efi", arch_parse_efi_cmdline);

arch/x86/xen/efi.c

@@ -31,7 +31,7 @@ static efi_system_table_t efi_systab_xen __initdata = {
 	.con_in_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
 	.con_in		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
 	.con_out_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
-	.con_out	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_out	= NULL, 		  /* Not used under Xen. */
 	.stderr_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
 	.stderr		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
 	.runtime	= (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR,

arch/x86/xen/mmu_pv.c

@@ -67,7 +67,7 @@
 #include <asm/linkage.h>
 #include <asm/page.h>
 #include <asm/init.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
 #include <asm/smp.h>
 #include <asm/tlb.h>
 

arch/xtensa/include/asm/vmalloc.h

+#ifndef _ASM_XTENSA_VMALLOC_H
+#define _ASM_XTENSA_VMALLOC_H
+
+#endif /* _ASM_XTENSA_VMALLOC_H */

drivers/firmware/efi/Kconfig

@@ -215,6 +215,28 @@ config EFI_RCI2_TABLE
 
 	  Say Y here for Dell EMC PowerEdge systems.
 
+config EFI_DISABLE_PCI_DMA
+       bool "Clear Busmaster bit on PCI bridges during ExitBootServices()"
+       help
+	  Disable the busmaster bit in the control register on all PCI bridges
+	  while calling ExitBootServices() and passing control to the runtime
+	  kernel. System firmware may configure the IOMMU to prevent malicious
+	  PCI devices from being able to attack the OS via DMA. However, since
+	  firmware can't guarantee that the OS is IOMMU-aware, it will tear
+	  down IOMMU configuration when ExitBootServices() is called. This
+	  leaves a window between where a hostile device could still cause
+	  damage before Linux configures the IOMMU again.
+
+	  If you say Y here, the EFI stub will clear the busmaster bit on all
+	  PCI bridges before ExitBootServices() is called. This will prevent
+	  any malicious PCI devices from being able to perform DMA until the
+	  kernel reenables busmastering after configuring the IOMMU.
+
+	  This option will cause failures with some poorly behaved hardware
+	  and should not be enabled without testing. The kernel commandline
+	  options "efi=disable_early_pci_dma" or "efi=no_disable_early_pci_dma"
+	  may be used to override this option.
+
 endmenu
 
 config UEFI_CPER