Merge branch 'x86/mm' into x86/core, to resolve conflicts

 Conflicts:
	arch/x86/mm/numa.c
	arch/x86/mm/pgtable.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

25 files changed, 130 insertions, 331 deletions

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 6d20a6ce0507..fa8858546d5e 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -15,10 +15,6 @@ config AS_SHA256_NI
 	def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
 	help
 	  Supported by binutils >= 2.24 and LLVM integrated assembler
-config AS_TPAUSE
-	def_bool $(as-instr,tpause %ecx)
-	help
-	  Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7
 
 config AS_GFNI
 	def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index ce857ef54cf1..dd2b129b0418 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,29 +25,31 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-static __always_inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
+static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx));
 }
 
-static __always_inline void __monitorx(const void *eax, unsigned long ecx,
-			      unsigned long edx)
+static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitorx %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfa;"
+	/* "monitorx %eax, %ecx, %edx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfa"
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
 
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -76,13 +78,12 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
  * EAX                     (logical) address to monitor
  * ECX                     #GP if not zero
  */
-static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
-				     unsigned long ecx)
+static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
 	/* No MDS buffer clear as this is AMD/HYGON only */
 
-	/* "mwaitx %eax, %ebx, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb;"
+	/* "mwaitx %eax, %ebx, %ecx" */
+	asm volatile(".byte 0x0f, 0x01, 0xfb"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
@@ -95,12 +96,11 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
  * executing mwait, it would otherwise go unnoticed and the next tick
  * would not be reprogrammed accordingly before mwait ever wakes up.
  */
-static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
 	mds_idle_clear_cpu_buffers();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+
+	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -113,16 +113,13 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  * New with Core Duo processors, MWAIT can take some hints based on CPU
  * capability.
  */
-static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
-		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
-			mb();
-			clflush((void *)&current_thread_info()->flags);
-			mb();
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 
 		if (!need_resched()) {
 			if (ecx & 1) {
@@ -144,16 +141,9 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
  */
 static inline void __tpause(u32 ecx, u32 edx, u32 eax)
 {
-	/* "tpause %ecx, %edx, %eax;" */
-	#ifdef CONFIG_AS_TPAUSE
-	asm volatile("tpause %%ecx\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#else
-	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#endif
+	/* "tpause %ecx" */
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+		     :: "c" (ecx), "d" (edx), "a" (eax));
 }
 
 #endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index a9b62e0e6f79..623f1e9f493e 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -73,7 +73,6 @@ extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
 extern void find_low_pfn_range(void);
-extern void setup_bootmem_allocator(void);
 
 #endif	/* !__ASSEMBLER__ */
 
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 66425424ce91..54690bd4ddbe 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -18,8 +18,6 @@ typedef union {
 } pte_t;
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	0
-
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 9d5b257d44e3..580b09bf6a45 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -27,9 +27,7 @@ typedef union {
 } pmd_t;
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
-
-#define ARCH_PAGE_TABLE_SYNC_MASK	(SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
+#define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7bd6bd6df4a1..5ddba366d3b4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -292,13 +292,6 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
 	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
-#define p4d_leaf p4d_leaf
-static inline bool p4d_leaf(p4d_t p4d)
-{
-	/* No 512 GiB pages yet */
-	return 0;
-}
-
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 #define pmd_leaf pmd_leaf
@@ -1472,9 +1465,6 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
 }
 
-#define pgd_leaf	pgd_leaf
-static inline bool pgd_leaf(pgd_t pgd) { return false; }
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 5bb782d856f2..e83721db18c9 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -46,8 +46,6 @@ extern unsigned int ptrs_per_p4d;
 
 #endif	/* !__ASSEMBLER__ */
 
-#define SHARED_KERNEL_PMD	0
-
 #ifdef CONFIG_X86_5LEVEL
 
 /*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9e6180777565..1871e833ecc7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -901,13 +901,10 @@ static __init bool prefer_mwait_c1_over_halt(void)
 static __cpuidle void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
-		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
-			mb(); /* quirk */
-			clflush((void *)&current_thread_info()->flags);
-			mb(); /* quirk */
-		}
+		const void *addr = &current_thread_info()->flags;
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 		if (!need_resched()) {
 			__sti_mwait(0, 0);
 			raw_local_irq_disable();
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 3faa60f13a61..cebe5812d78d 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -47,7 +47,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 296d294142c8..697432f63c59 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,7 +13,6 @@
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
-#include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
@@ -1496,8 +1495,6 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 
 	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
-	prefetchw(&current->mm->mmap_lock);
-
 	/*
 	 * KVM uses #PF vector to deliver 'page not present' events to guests
 	 * (asynchronous page fault mechanism). The event happens when a
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ad662cc4605c..d467f89191cd 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -612,7 +612,6 @@ void __init find_low_pfn_range(void)
 		highmem_pfn_init();
 }
 
-#ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
@@ -633,12 +632,6 @@ void __init initmem_init(void)
 	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
 			pages_to_mb(max_low_pfn));
 
-	setup_bootmem_allocator();
-}
-#endif /* !CONFIG_NUMA */
-
-void __init setup_bootmem_allocator(void)
-{
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7c4f6f591f2b..b7655396f4e0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -805,12 +805,17 @@ kernel_physical_mapping_change(unsigned long paddr_start,
 }
 
 #ifndef CONFIG_NUMA
-void __init initmem_init(void)
+static inline void x86_numa_init(void)
 {
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
 }
 #endif
 
+void __init initmem_init(void)
+{
+	x86_numa_init();
+}
+
 void __init paging_init(void)
 {
 	sparse_init();
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 3f37b5c80bb3..097aadc250f7 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -25,4 +25,8 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
 
 extern unsigned long tlb_single_page_flush_ceiling;
 
+#ifdef CONFIG_NUMA
+void __init x86_numa_init(void);
+#endif
+
 #endif	/* __X86_MM_INTERNAL_H */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fed02d1073c7..c24890c40138 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -18,9 +18,10 @@
 #include <asm/e820/api.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
+#include <asm/numa.h>
 #include <asm/amd/nb.h>
 
-#include "numa_internal.h"
+#include "mm_internal.h"
 
 int numa_off;
 
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
deleted file mode 100644
index 65fda406e6f2..000000000000
--- a/arch/x86/mm/numa_32.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
- * August 2002: added remote node KVA remap - Martin J. Bligh 
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.          
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/memblock.h>
-#include <linux/init.h>
-#include <linux/vmalloc.h>
-#include <asm/pgtable_areas.h>
-
-#include "numa_internal.h"
-
-extern unsigned long highend_pfn, highstart_pfn;
-
-void __init initmem_init(void)
-{
-	x86_numa_init();
-
-#ifdef CONFIG_HIGHMEM
-	highstart_pfn = highend_pfn = max_pfn;
-	if (max_pfn > max_low_pfn)
-		highstart_pfn = max_low_pfn;
-	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
-	       pages_to_mb(highend_pfn - highstart_pfn));
-	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
-#else
-	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
-#endif
-	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
-			pages_to_mb(max_low_pfn));
-	printk(KERN_DEBUG "max_low_pfn = %lx, highstart_pfn = %lx\n",
-			max_low_pfn, highstart_pfn);
-
-	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
-			(ulong) pfn_to_kaddr(max_low_pfn));
-
-	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
-			(ulong) pfn_to_kaddr(highstart_pfn));
-
-	__vmalloc_start_set = true;
-	setup_bootmem_allocator();
-}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
deleted file mode 100644
index 59d80160fa5a..000000000000
--- a/arch/x86/mm/numa_64.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Generic VM initialization for x86-64 NUMA setups.
- * Copyright 2002,2003 Andi Kleen, SuSE Labs.
- */
-#include <linux/memblock.h>
-
-#include "numa_internal.h"
-
-void __init initmem_init(void)
-{
-	x86_numa_init();
-}
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
deleted file mode 100644
index 11e1ff370c10..000000000000
--- a/arch/x86/mm/numa_internal.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __X86_MM_NUMA_INTERNAL_H
-#define __X86_MM_NUMA_INTERNAL_H
-
-#include <linux/types.h>
-#include <asm/numa.h>
-
-void __init x86_numa_init(void);
-
-#endif	/* __X86_MM_NUMA_INTERNAL_H */
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 72d8cbc61158..c97b6598f187 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -38,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
@@ -773,38 +774,14 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 	return vma_prot;
 }
 
-#ifdef CONFIG_STRICT_DEVMEM
-/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	return 1;
-}
-#else
-/* This check is needed to avoid cache aliasing when PAT is enabled */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	u64 from = ((u64)pfn) << PAGE_SHIFT;
-	u64 to = from + size;
-	u64 cursor = from;
-
-	if (!pat_enabled())
-		return 1;
-
-	while (cursor < to) {
-		if (!devmem_is_allowed(pfn))
-			return 0;
-		cursor += PAGE_SIZE;
-		pfn++;
-	}
-	return 1;
-}
-#endif /* CONFIG_STRICT_DEVMEM */
-
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
 	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
 
+	if (!pat_enabled())
+		return 1;
+
 	if (!range_is_allowed(pfn, size))
 		return 0;
 
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index def3d9284254..30ab4aced761 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -889,7 +889,7 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
 	/* change init_mm */
 	set_pte_atomic(kpte, pte);
 #ifdef CONFIG_X86_32
-	if (!SHARED_KERNEL_PMD) {
+	{
 		struct page *page;
 
 		list_for_each_entry(page, &pgd_list, lru) {
@@ -1293,7 +1293,7 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
 	/* Queue the page table to be freed after TLB flush */
 	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
 
-	if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+	if (IS_ENABLED(CONFIG_X86_32)) {
 		struct page *page;
 
 		/* Update all PGD tables to use the same large page */
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index e62af72923e8..7c253deb46e9 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -69,12 +69,6 @@ static inline void pgd_list_del(pgd_t *pgd)
 	list_del(&ptdesc->pt_list);
 }
 
-#define UNSHARED_PTRS_PER_PGD				\
-	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
-#define MAX_UNSHARED_PTRS_PER_PGD			\
-	MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
-
-
 static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
 {
 	virt_to_ptdesc(pgd)->pt_mm = mm;
@@ -87,29 +81,19 @@ struct mm_struct *pgd_page_get_mm(struct page *page)
 
 static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 {
-	/* If the pgd points to a shared pagetable level (either the
-	   ptes in non-PAE, or shared PMD in PAE), then just copy the
-	   references from swapper_pg_dir. */
-	if (CONFIG_PGTABLE_LEVELS == 2 ||
-	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
-	    CONFIG_PGTABLE_LEVELS >= 4) {
+	/* PAE preallocates all its PMDs.  No cloning needed. */
+	if (!IS_ENABLED(CONFIG_X86_PAE))
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
-	}
 
-	/* list required to sync kernel mapping updates */
-	if (!SHARED_KERNEL_PMD) {
-		pgd_set_mm(pgd, mm);
-		pgd_list_add(pgd);
-	}
+	/* List used to sync kernel mapping updates */
+	pgd_set_mm(pgd, mm);
+	pgd_list_add(pgd);
 }
 
 static void pgd_dtor(pgd_t *pgd)
 {
-	if (SHARED_KERNEL_PMD)
-		return;
-
 	spin_lock(&pgd_lock);
 	pgd_list_del(pgd);
 	spin_unlock(&pgd_lock);
@@ -133,15 +117,15 @@ static void pgd_dtor(pgd_t *pgd)
  * processor notices the update.  Since this is expensive, and
  * all 4 top-level entries are used almost immediately in a
  * new process's life, we just pre-populate them here.
- *
- * Also, if we're in a paravirt environment where the kernel pmd is
- * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
- * and initialize the kernel pmds here.
  */
-#define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
-#define MAX_PREALLOCATED_PMDS	MAX_UNSHARED_PTRS_PER_PGD
+#define PREALLOCATED_PMDS	PTRS_PER_PGD
 
 /*
+ * "USER_PMDS" are the PMDs for the user copy of the page tables when
+ * PTI is enabled. They do not exist when PTI is disabled.  Note that
+ * this is distinct from the user _portion_ of the kernel page tables
+ * which always exists.
+ *
  * We allocate separate PMDs for the kernel part of the user page-table
  * when PTI is enabled. We need them to map the per-process LDT into the
  * user-space page-table.
@@ -170,7 +154,6 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
-#define MAX_PREALLOCATED_PMDS	0
 #define PREALLOCATED_USER_PMDS	 0
 #define MAX_PREALLOCATED_USER_PMDS 0
 #endif	/* CONFIG_X86_PAE */
@@ -319,68 +302,15 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 {
 }
 #endif
-/*
- * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
- * assumes that pgd should be in one page.
- *
- * But kernel with PAE paging that is not running as a Xen domain
- * only needs to allocate 32 bytes for pgd instead of one page.
- */
-#ifdef CONFIG_X86_PAE
-
-#include <linux/slab.h>
-
-#define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
-#define PGD_ALIGN	32
-
-static struct kmem_cache *pgd_cache;
-
-void __init pgtable_cache_init(void)
-{
-	/*
-	 * When PAE kernel is running as a Xen domain, it does not use
-	 * shared kernel pmd. And this requires a whole page for pgd.
-	 */
-	if (!SHARED_KERNEL_PMD)
-		return;
-
-	/*
-	 * when PAE kernel is not running as a Xen domain, it uses
-	 * shared kernel pmd. Shared kernel pmd does not require a whole
-	 * page for pgd. We are able to just allocate a 32-byte for pgd.
-	 * During boot time, we create a 32-byte slab for pgd table allocation.
-	 */
-	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
-				      SLAB_PANIC, NULL);
-}
 
 static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
 	/*
-	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
-	 * We allocate one page for pgd.
-	 */
-	if (!SHARED_KERNEL_PMD)
-		return __pgd_alloc(mm, pgd_allocation_order());
-
-	/*
-	 * Now PAE kernel is not running as a Xen domain. We can allocate
-	 * a 32-byte slab for pgd to save memory space.
+	 * PTI and Xen need a whole page for the PAE PGD
+	 * even though the hardware only needs 32 bytes.
+	 *
+	 * For simplicity, allocate a page for all users.
 	 */
-	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
-}
-
-static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	if (!SHARED_KERNEL_PMD)
-		__pgd_free(mm, pgd);
-	else
-		kmem_cache_free(pgd_cache, pgd);
-}
-#else
-
-static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
-{
 	return __pgd_alloc(mm, pgd_allocation_order());
 }
 
@@ -388,13 +318,12 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	__pgd_free(mm, pgd);
 }
-#endif /* CONFIG_X86_PAE */
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
-	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
+	pmd_t *pmds[PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc(mm);
 
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5f0d579932c6..190299834011 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -185,7 +185,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 
 		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
 	}
-	BUILD_BUG_ON(pgd_leaf(*pgd) != 0);
+	BUILD_BUG_ON(pgd_leaf(*pgd));
 
 	return p4d_offset(pgd, address);
 }
@@ -206,7 +206,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	if (!p4d)
 		return NULL;
 
-	BUILD_BUG_ON(p4d_leaf(*p4d) != 0);
+	BUILD_BUG_ON(p4d_leaf(*p4d));
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
 		if (WARN_ON_ONCE(!new_pud_page))
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 2ea8cec6cd49..5f75d63093c8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -215,16 +215,20 @@ static void clear_asid_other(void)
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
+struct new_asid {
+	unsigned int asid	: 16;
+	unsigned int need_flush : 1;
+};
 
-static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
-			    u16 *new_asid, bool *need_flush)
+static struct new_asid choose_new_asid(struct mm_struct *next, u64 next_tlb_gen)
 {
+	struct new_asid ns;
 	u16 asid;
 
 	if (!static_cpu_has(X86_FEATURE_PCID)) {
-		*new_asid = 0;
-		*need_flush = true;
-		return;
+		ns.asid = 0;
+		ns.need_flush = 1;
+		return ns;
 	}
 
 	/*
@@ -235,9 +239,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		u16 global_asid = mm_global_asid(next);
 
 		if (global_asid) {
-			*new_asid = global_asid;
-			*need_flush = false;
-			return;
+			ns.asid = global_asid;
+			ns.need_flush = 0;
+			return ns;
 		}
 	}
 
@@ -249,22 +253,23 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		    next->context.ctx_id)
 			continue;
 
-		*new_asid = asid;
-		*need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) <
-			       next_tlb_gen);
-		return;
+		ns.asid = asid;
+		ns.need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < next_tlb_gen);
+		return ns;
 	}
 
 	/*
 	 * We don't currently own an ASID slot on this CPU.
 	 * Allocate a slot.
 	 */
-	*new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
-	if (*new_asid >= TLB_NR_DYN_ASIDS) {
-		*new_asid = 0;
+	ns.asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
+	if (ns.asid >= TLB_NR_DYN_ASIDS) {
+		ns.asid = 0;
 		this_cpu_write(cpu_tlbstate.next_asid, 1);
 	}
-	*need_flush = true;
+	ns.need_flush = true;
+
+	return ns;
 }
 
 /*
@@ -781,9 +786,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
 	unsigned cpu = smp_processor_id();
 	unsigned long new_lam;
+	struct new_asid ns;
 	u64 next_tlb_gen;
-	bool need_flush;
-	u16 new_asid;
+
 
 	/* We don't want flush_tlb_func() to run concurrently with us. */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
@@ -855,7 +860,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		/* Check if the current mm is transitioning to a global ASID */
 		if (mm_needs_global_asid(next, prev_asid)) {
 			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
-			choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+			ns = choose_new_asid(next, next_tlb_gen);
 			goto reload_tlb;
 		}
 
@@ -890,8 +895,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 * TLB contents went out of date while we were in lazy
 		 * mode. Fall through to the TLB switching code below.
 		 */
-		new_asid = prev_asid;
-		need_flush = true;
+		ns.asid = prev_asid;
+		ns.need_flush = true;
 	} else {
 		/*
 		 * Apply process to process speculation vulnerability
@@ -912,21 +917,21 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
-		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+		ns = choose_new_asid(next, next_tlb_gen);
 	}
 
 reload_tlb:
 	new_lam = mm_lam_cr3_mask(next);
-	if (need_flush) {
-		VM_WARN_ON_ONCE(is_global_asid(new_asid));
-		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
+	if (ns.need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(ns.asid));
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, true);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
-		load_new_mm_cr3(next->pgd, new_asid, new_lam, false);
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, false);
 
 		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
@@ -935,7 +940,7 @@ reload_tlb:
 	barrier();
 
 	this_cpu_write(cpu_tlbstate.loaded_mm, next);
-	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, ns.asid);
 	cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next));
 
 	if (next != prev) {
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 169eed162a7f..48839958b0b1 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -61,29 +61,11 @@ static inline int page_is_allowed(unsigned long pfn)
 {
 	return devmem_is_allowed(pfn);
 }
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	u64 from = ((u64)pfn) << PAGE_SHIFT;
-	u64 to = from + size;
-	u64 cursor = from;
-
-	while (cursor < to) {
-		if (!devmem_is_allowed(pfn))
-			return 0;
-		cursor += PAGE_SIZE;
-		pfn++;
-	}
-	return 1;
-}
 #else
 static inline int page_is_allowed(unsigned long pfn)
 {
 	return 1;
 }
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
-	return 1;
-}
 #endif
 
 static inline bool should_stop_iteration(void)
diff --git a/include/linux/io.h b/include/linux/io.h
index 6a6bc4d46d0a..0642c7ee41db 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -183,4 +183,25 @@ static inline void arch_io_free_memtype_wc(resource_size_t base,
 int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start,
 				    resource_size_t size);
 
+#ifdef CONFIG_STRICT_DEVMEM
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	u64 from = ((u64)pfn) << PAGE_SHIFT;
+	u64 to = from + size;
+	u64 cursor = from;
+
+	while (cursor < to) {
+		if (!devmem_is_allowed(pfn))
+			return 0;
+		cursor += PAGE_SIZE;
+		pfn++;
+	}
+	return 1;
+}
+#else
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	return 1;
+}
+#endif
 #endif /* _LINUX_IO_H */
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 18d736640ece..0873b0e5f48b 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -682,7 +682,7 @@ int do_uring(unsigned long lam)
 		return 1;
 
 	if (fstat(file_fd, &st) < 0)
-		return 1;
+		goto cleanup;
 
 	off_t file_sz = st.st_size;
 
@@ -690,7 +690,7 @@ int do_uring(unsigned long lam)
 
 	fi = malloc(sizeof(*fi) + sizeof(struct iovec) * blocks);
 	if (!fi)
-		return 1;
+		goto cleanup;
 
 	fi->file_sz = file_sz;
 	fi->file_fd = file_fd;
@@ -698,7 +698,7 @@ int do_uring(unsigned long lam)
 	ring = malloc(sizeof(*ring));
 	if (!ring) {
 		free(fi);
-		return 1;
+		goto cleanup;
 	}
 
 	memset(ring, 0, sizeof(struct io_ring));
@@ -729,6 +729,8 @@ out:
 	}
 
 	free(fi);
+cleanup:
+	close(file_fd);
 
 	return ret;
 }
@@ -1189,6 +1191,7 @@ void *allocate_dsa_pasid(void)
 
 	wq = mmap(NULL, 0x1000, PROT_WRITE,
 			   MAP_SHARED | MAP_POPULATE, fd, 0);
+	close(fd);
 	if (wq == MAP_FAILED)
 		perror("mmap");