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
  ...

12 files changed, 355 insertions, 320 deletions

diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 804734058c77..02c0078d3787 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/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)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index d028e9acdf1c..86169a24b0d8 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -8,6 +8,7 @@
 #include <asm/tlb.h>
 #include <asm/nospec-branch.h>
 #include <asm/mmu_context.h>
+#include <linux/build_bug.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -19,13 +20,16 @@
  * This is the main reason why we're doing stable VA mappings for RT
  * services.
  *
- * This flag is used in conjunction with a chicken bit called
- * "efi=old_map" which can be used as a fallback to the old runtime
- * services mapping method in case there's some b0rkage with a
- * particular EFI implementation (haha, it is hard to hold up the
- * sarcasm here...).
+ * SGI UV1 machines are known to be incompatible with this scheme, so we
+ * provide an opt-out for these machines via a DMI quirk that sets the
+ * attribute below.
  */
-#define EFI_OLD_MEMMAP		EFI_ARCH_1
+#define EFI_UV1_MEMMAP         EFI_ARCH_1
+
+static inline bool efi_have_uv1_memmap(void)
+{
+	return IS_ENABLED(CONFIG_X86_UV) && efi_enabled(EFI_UV1_MEMMAP);
+}
 
 #define EFI32_LOADER_SIGNATURE	"EL32"
 #define EFI64_LOADER_SIGNATURE	"EL64"
@@ -34,10 +38,46 @@
 
 #define ARCH_EFI_IRQ_FLAGS_MASK	X86_EFLAGS_IF
 
-#ifdef CONFIG_X86_32
+/*
+ * The EFI services are called through variadic functions in many cases. These
+ * functions are implemented in assembler and support only a fixed number of
+ * arguments. The macros below allows us to check at build time that we don't
+ * try to call them with too many arguments.
+ *
+ * __efi_nargs() will return the number of arguments if it is 7 or less, and
+ * cause a BUILD_BUG otherwise. The limitations of the C preprocessor make it
+ * impossible to calculate the exact number of arguments beyond some
+ * pre-defined limit. The maximum number of arguments currently supported by
+ * any of the thunks is 7, so this is good enough for now and can be extended
+ * in the obvious way if we ever need more.
+ */
 
-extern asmlinkage unsigned long efi_call_phys(void *, ...);
+#define __efi_nargs(...) __efi_nargs_(__VA_ARGS__)
+#define __efi_nargs_(...) __efi_nargs__(0, ##__VA_ARGS__,	\
+	__efi_arg_sentinel(7), __efi_arg_sentinel(6),		\
+	__efi_arg_sentinel(5), __efi_arg_sentinel(4),		\
+	__efi_arg_sentinel(3), __efi_arg_sentinel(2),		\
+	__efi_arg_sentinel(1), __efi_arg_sentinel(0))
+#define __efi_nargs__(_0, _1, _2, _3, _4, _5, _6, _7, n, ...)	\
+	__take_second_arg(n,					\
+		({ BUILD_BUG_ON_MSG(1, "__efi_nargs limit exceeded"); 8; }))
+#define __efi_arg_sentinel(n) , n
 
+/*
+ * __efi_nargs_check(f, n, ...) will cause a BUILD_BUG if the ellipsis
+ * represents more than n arguments.
+ */
+
+#define __efi_nargs_check(f, n, ...)					\
+	__efi_nargs_check_(f, __efi_nargs(__VA_ARGS__), n)
+#define __efi_nargs_check_(f, p, n) __efi_nargs_check__(f, p, n)
+#define __efi_nargs_check__(f, p, n) ({					\
+	BUILD_BUG_ON_MSG(						\
+		(p) > (n),						\
+		#f " called with too many arguments (" #p ">" #n ")");	\
+})
+
+#ifdef CONFIG_X86_32
 #define arch_efi_call_virt_setup()					\
 ({									\
 	kernel_fpu_begin();						\
@@ -51,13 +91,7 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...);
 })
 
 
-/*
- * Wrap all the virtual calls in a way that forces the parameters on the stack.
- */
-#define arch_efi_call_virt(p, f, args...)				\
-({									\
-	((efi_##f##_t __attribute__((regparm(0)))*) p->f)(args);	\
-})
+#define arch_efi_call_virt(p, f, args...)	p->f(args)
 
 #define efi_ioremap(addr, size, type, attr)	ioremap_cache(addr, size)
 
@@ -65,9 +99,12 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...);
 
 #define EFI_LOADER_SIGNATURE	"EL64"
 
-extern asmlinkage u64 efi_call(void *fp, ...);
+extern asmlinkage u64 __efi_call(void *fp, ...);
 
-#define efi_call_phys(f, args...)		efi_call((f), args)
+#define efi_call(...) ({						\
+	__efi_nargs_check(efi_call, 7, __VA_ARGS__);			\
+	__efi_call(__VA_ARGS__);					\
+})
 
 /*
  * struct efi_scratch - Scratch space used while switching to/from efi_mm
@@ -85,7 +122,7 @@ struct efi_scratch {
 	kernel_fpu_begin();						\
 	firmware_restrict_branch_speculation_start();			\
 									\
-	if (!efi_enabled(EFI_OLD_MEMMAP))				\
+	if (!efi_have_uv1_memmap())					\
 		efi_switch_mm(&efi_mm);					\
 })
 
@@ -94,7 +131,7 @@ struct efi_scratch {
 
 #define arch_efi_call_virt_teardown()					\
 ({									\
-	if (!efi_enabled(EFI_OLD_MEMMAP))				\
+	if (!efi_have_uv1_memmap())					\
 		efi_switch_mm(efi_scratch.prev_mm);			\
 									\
 	firmware_restrict_branch_speculation_end();			\
@@ -121,8 +158,6 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 extern struct efi_scratch efi_scratch;
 extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int __init efi_memblock_x86_reserve_range(void);
-extern pgd_t * __init efi_call_phys_prolog(void);
-extern void __init efi_call_phys_epilog(pgd_t *save_pgd);
 extern void __init efi_print_memmap(void);
 extern void __init efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
@@ -140,6 +175,8 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_switch_mm(struct mm_struct *mm);
 extern void efi_recover_from_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
+extern pgd_t * __init efi_uv1_memmap_phys_prolog(void);
+extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd);
 
 struct efi_setup_data {
 	u64 fw_vendor;
@@ -152,93 +189,144 @@ struct efi_setup_data {
 extern u64 efi_setup;
 
 #ifdef CONFIG_EFI
+extern efi_status_t __efi64_thunk(u32, ...);
 
-static inline bool efi_is_native(void)
+#define efi64_thunk(...) ({						\
+	__efi_nargs_check(efi64_thunk, 6, __VA_ARGS__);			\
+	__efi64_thunk(__VA_ARGS__);					\
+})
+
+static inline bool efi_is_mixed(void)
 {
-	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+		return false;
+	return IS_ENABLED(CONFIG_X86_64) && !efi_enabled(EFI_64BIT);
 }
 
 static inline bool efi_runtime_supported(void)
 {
-	if (efi_is_native())
-		return true;
-
-	if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP))
+	if (IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT))
 		return true;
 
-	return false;
+	return IS_ENABLED(CONFIG_EFI_MIXED);
 }
 
 extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 
 extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 
-#ifdef CONFIG_EFI_MIXED
 extern void efi_thunk_runtime_setup(void);
-extern efi_status_t efi_thunk_set_virtual_address_map(
-	void *phys_set_virtual_address_map,
-	unsigned long memory_map_size,
-	unsigned long descriptor_size,
-	u32 descriptor_version,
-	efi_memory_desc_t *virtual_map);
-#else
-static inline void efi_thunk_runtime_setup(void) {}
-static inline efi_status_t efi_thunk_set_virtual_address_map(
-	void *phys_set_virtual_address_map,
-	unsigned long memory_map_size,
-	unsigned long descriptor_size,
-	u32 descriptor_version,
-	efi_memory_desc_t *virtual_map)
-{
-	return EFI_SUCCESS;
-}
-#endif /* CONFIG_EFI_MIXED */
-
+efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
+					 unsigned long descriptor_size,
+					 u32 descriptor_version,
+					 efi_memory_desc_t *virtual_map);
 
 /* arch specific definitions used by the stub code */
 
-struct efi_config {
-	u64 image_handle;
-	u64 table;
-	u64 runtime_services;
-	u64 boot_services;
-	u64 text_output;
-	efi_status_t (*call)(unsigned long, ...);
-	bool is64;
-} __packed;
-
-__pure const struct efi_config *__efi_early(void);
+__attribute_const__ bool efi_is_64bit(void);
 
-static inline bool efi_is_64bit(void)
+static inline bool efi_is_native(void)
 {
 	if (!IS_ENABLED(CONFIG_X86_64))
-		return false;
-
+		return true;
 	if (!IS_ENABLED(CONFIG_EFI_MIXED))
 		return true;
+	return efi_is_64bit();
+}
+
+#define efi_mixed_mode_cast(attr)					\
+	__builtin_choose_expr(						\
+		__builtin_types_compatible_p(u32, __typeof__(attr)),	\
+			(unsigned long)(attr), (attr))
 
-	return __efi_early()->is64;
+#define efi_table_attr(inst, attr)					\
+	(efi_is_native()						\
+		? inst->attr						\
+		: (__typeof__(inst->attr))				\
+			efi_mixed_mode_cast(inst->mixed_mode.attr))
+
+/*
+ * The following macros allow translating arguments if necessary from native to
+ * mixed mode. The use case for this is to initialize the upper 32 bits of
+ * output parameters, and where the 32-bit method requires a 64-bit argument,
+ * which must be split up into two arguments to be thunked properly.
+ *
+ * As examples, the AllocatePool boot service returns the address of the
+ * allocation, but it will not set the high 32 bits of the address. To ensure
+ * that the full 64-bit address is initialized, we zero-init the address before
+ * calling the thunk.
+ *
+ * The FreePages boot service takes a 64-bit physical address even in 32-bit
+ * mode. For the thunk to work correctly, a native 64-bit call of
+ * 	free_pages(addr, size)
+ * must be translated to
+ * 	efi64_thunk(free_pages, addr & U32_MAX, addr >> 32, size)
+ * so that the two 32-bit halves of addr get pushed onto the stack separately.
+ */
+
+static inline void *efi64_zero_upper(void *p)
+{
+	((u32 *)p)[1] = 0;
+	return p;
 }
 
-#define efi_table_attr(table, attr, instance)				\
-	(efi_is_64bit() ?						\
-		((table##_64_t *)(unsigned long)instance)->attr :	\
-		((table##_32_t *)(unsigned long)instance)->attr)
+#define __efi64_argmap_free_pages(addr, size)				\
+	((addr), 0, (size))
+
+#define __efi64_argmap_get_memory_map(mm_size, mm, key, size, ver)	\
+	((mm_size), (mm), efi64_zero_upper(key), efi64_zero_upper(size), (ver))
+
+#define __efi64_argmap_allocate_pool(type, size, buffer)		\
+	((type), (size), efi64_zero_upper(buffer))
 
-#define efi_call_proto(protocol, f, instance, ...)			\
-	__efi_early()->call(efi_table_attr(protocol, f, instance),	\
-		instance, ##__VA_ARGS__)
+#define __efi64_argmap_handle_protocol(handle, protocol, interface)	\
+	((handle), (protocol), efi64_zero_upper(interface))
 
-#define efi_call_early(f, ...)						\
-	__efi_early()->call(efi_table_attr(efi_boot_services, f,	\
-		__efi_early()->boot_services), __VA_ARGS__)
+#define __efi64_argmap_locate_protocol(protocol, reg, interface)	\
+	((protocol), (reg), efi64_zero_upper(interface))
 
-#define __efi_call_early(f, ...)					\
-	__efi_early()->call((unsigned long)f, __VA_ARGS__);
+/* PCI I/O */
+#define __efi64_argmap_get_location(protocol, seg, bus, dev, func)	\
+	((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus),	\
+	 efi64_zero_upper(dev), efi64_zero_upper(func))
+
+/*
+ * The macros below handle the plumbing for the argument mapping. To add a
+ * mapping for a specific EFI method, simply define a macro
+ * __efi64_argmap_<method name>, following the examples above.
+ */
 
-#define efi_call_runtime(f, ...)					\
-	__efi_early()->call(efi_table_attr(efi_runtime_services, f,	\
-		__efi_early()->runtime_services), __VA_ARGS__)
+#define __efi64_thunk_map(inst, func, ...)				\
+	efi64_thunk(inst->mixed_mode.func,				\
+		__efi64_argmap(__efi64_argmap_ ## func(__VA_ARGS__),	\
+			       (__VA_ARGS__)))
+
+#define __efi64_argmap(mapped, args)					\
+	__PASTE(__efi64_argmap__, __efi_nargs(__efi_eat mapped))(mapped, args)
+#define __efi64_argmap__0(mapped, args) __efi_eval mapped
+#define __efi64_argmap__1(mapped, args) __efi_eval args
+
+#define __efi_eat(...)
+#define __efi_eval(...) __VA_ARGS__
+
+/* The three macros below handle dispatching via the thunk if needed */
+
+#define efi_call_proto(inst, func, ...)					\
+	(efi_is_native()						\
+		? inst->func(inst, ##__VA_ARGS__)			\
+		: __efi64_thunk_map(inst, func, inst, ##__VA_ARGS__))
+
+#define efi_bs_call(func, ...)						\
+	(efi_is_native()						\
+		? efi_system_table()->boottime->func(__VA_ARGS__)	\
+		: __efi64_thunk_map(efi_table_attr(efi_system_table(),	\
+				boottime), func, __VA_ARGS__))
+
+#define efi_rt_call(func, ...)						\
+	(efi_is_native()						\
+		? efi_system_table()->runtime->func(__VA_ARGS__)	\
+		: __efi64_thunk_map(efi_table_attr(efi_system_table(),	\
+				runtime), func, __VA_ARGS__))
 
 extern bool efi_reboot_required(void);
 extern bool efi_is_table_address(unsigned long phys_addr);
diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h
new file mode 100644
index 000000000000..9c2447b3555d
--- /dev/null
+++ b/arch/x86/include/asm/memtype.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_MEMTYPE_H
+#define _ASM_X86_MEMTYPE_H
+
+#include <linux/types.h>
+#include <asm/pgtable_types.h>
+
+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 memtype_reserve(u64 start, u64 end,
+		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
+extern int memtype_free(u64 start, u64 end);
+
+extern int memtype_kernel_map_sync(u64 base, unsigned long size,
+		enum page_cache_mode pcm);
+
+extern int memtype_reserve_io(resource_size_t start, resource_size_t end,
+			enum page_cache_mode *pcm);
+
+extern void memtype_free_io(resource_size_t start, resource_size_t end);
+
+extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+
+#endif /* _ASM_X86_MEMTYPE_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5f33924e200f..b243234e90cb 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/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()
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index dbff1456d215..829df26fd7a3 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/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)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
deleted file mode 100644
index 92015c65fa2a..000000000000
--- a/arch/x86/include/asm/pat.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_PAT_H
-#define _ASM_X86_PAT_H
-
-#include <linux/types.h>
-#include <asm/pgtable_types.h>
-
-bool pat_enabled(void);
-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,
-		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
-extern int free_memtype(u64 start, u64 end);
-
-extern int kernel_map_sync_memtype(u64 base, unsigned long size,
-		enum page_cache_mode pcm);
-
-int io_reserve_memtype(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);
-
-bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
-
-#endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731fdcb6..c1fdd43fe187 100644
--- a/arch/x86/include/asm/pci.h
+++ b/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 {
diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h
new file mode 100644
index 000000000000..b6355416a15a
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_32_areas.h
@@ -0,0 +1,53 @@
+#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 */
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 0416d42e5bdd..5356a46b0373 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -1,6 +1,6 @@
 /* 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 */
diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h
new file mode 100644
index 000000000000..d34cce1b995c
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_areas.h
@@ -0,0 +1,16 @@
+#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 */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b5e49e6bac63..ea7400726d7a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/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];
 
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
new file mode 100644
index 000000000000..29837740b520
--- /dev/null
+++ b/arch/x86/include/asm/vmalloc.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_VMALLOC_H
+#define _ASM_X86_VMALLOC_H
+
+#include <asm/pgtable_areas.h>
+
+#endif /* _ASM_X86_VMALLOC_H */