14 files changed, 212 insertions, 195 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 428048e73bd2..8d3a00e5c528 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -34,7 +34,7 @@ obj-y				+= pat/
 CFLAGS_physaddr.o		:= -fno-stack-protector
 CFLAGS_mem_encrypt_identity.o	:= -fno-stack-protector
 
-CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
+CFLAGS_fault.o := -I $(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index b522933bfa56..51986e8a9d35 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -164,13 +164,6 @@ static bool ex_handler_uaccess(const struct exception_table_entry *fixup,
 	return ex_handler_default(fixup, regs);
 }
 
-static bool ex_handler_copy(const struct exception_table_entry *fixup,
-			    struct pt_regs *regs, int trapnr)
-{
-	WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
-	return ex_handler_fault(fixup, regs, trapnr);
-}
-
 static bool ex_handler_msr(const struct exception_table_entry *fixup,
 			   struct pt_regs *regs, bool wrmsr, bool safe, int reg)
 {
@@ -341,8 +334,6 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_fault(e, regs, trapnr);
 	case EX_TYPE_UACCESS:
 		return ex_handler_uaccess(e, regs, trapnr, fault_addr);
-	case EX_TYPE_COPY:
-		return ex_handler_copy(e, regs, trapnr);
 	case EX_TYPE_CLEAR_FS:
 		return ex_handler_clear_fs(e, regs);
 	case EX_TYPE_FPU_RESTORE:
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 622d12ec7f08..e6c469b323cc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,7 @@
 #include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
 #include <linux/mm_types.h>
 #include <linux/mm.h>			/* find_and_lock_vma() */
+#include <linux/vmalloc.h>
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
@@ -514,18 +515,19 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 
 	if (error_code & X86_PF_INSTR) {
 		unsigned int level;
+		bool nx, rw;
 		pgd_t *pgd;
 		pte_t *pte;
 
 		pgd = __va(read_cr3_pa());
 		pgd += pgd_index(address);
 
-		pte = lookup_address_in_pgd(pgd, address, &level);
+		pte = lookup_address_in_pgd_attr(pgd, address, &level, &nx, &rw);
 
-		if (pte && pte_present(*pte) && !pte_exec(*pte))
+		if (pte && pte_present(*pte) && (!pte_exec(*pte) || nx))
 			pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
 				from_kuid(&init_user_ns, current_uid()));
-		if (pte && pte_present(*pte) && pte_exec(*pte) &&
+		if (pte && pte_present(*pte) && pte_exec(*pte) && !nx &&
 				(pgd_flags(*pgd) & _PAGE_USER) &&
 				(__read_cr4() & X86_CR4_SMEP))
 			pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
@@ -723,39 +725,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
 	WARN_ON_ONCE(user_mode(regs));
 
 	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
-		/*
-		 * Any interrupt that takes a fault gets the fixup. This makes
-		 * the below recursive fault logic only apply to a faults from
-		 * task context.
-		 */
-		if (in_interrupt())
-			return;
-
-		/*
-		 * Per the above we're !in_interrupt(), aka. task context.
-		 *
-		 * In this case we need to make sure we're not recursively
-		 * faulting through the emulate_vsyscall() logic.
-		 */
-		if (current->thread.sig_on_uaccess_err && signal) {
-			sanitize_error_code(address, &error_code);
-
-			set_signal_archinfo(address, error_code);
-
-			if (si_code == SEGV_PKUERR) {
-				force_sig_pkuerr((void __user *)address, pkey);
-			} else {
-				/* XXX: hwpoison faults will set the wrong code. */
-				force_sig_fault(signal, si_code, (void __user *)address);
-			}
-		}
-
-		/*
-		 * Barring that, we can do the fixup and be happy.
-		 */
+	if (fixup_exception(regs, X86_TRAP_PF, error_code, address))
 		return;
-	}
 
 	/*
 	 * AMD erratum #91 manifests as a spurious page fault on a PREFETCH
@@ -865,14 +836,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 
 static void
 __bad_area(struct pt_regs *regs, unsigned long error_code,
-	   unsigned long address, u32 pkey, int si_code)
+	   unsigned long address, struct mm_struct *mm,
+	   struct vm_area_struct *vma, u32 pkey, int si_code)
 {
-	struct mm_struct *mm = current->mm;
 	/*
 	 * Something tried to access memory that isn't in our memory map..
 	 * Fix it, but check if it's kernel or user first..
 	 */
-	mmap_read_unlock(mm);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
 }
@@ -896,7 +870,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code,
 
 static noinline void
 bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
-		      unsigned long address, struct vm_area_struct *vma)
+		      unsigned long address, struct mm_struct *mm,
+		      struct vm_area_struct *vma)
 {
 	/*
 	 * This OSPKE check is not strictly necessary at runtime.
@@ -926,9 +901,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
 		 */
 		u32 pkey = vma_pkey(vma);
 
-		__bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
+		__bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR);
 	} else {
-		__bad_area(regs, error_code, address, 0, SEGV_ACCERR);
+		__bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR);
 	}
 }
 
@@ -1356,8 +1331,9 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto lock_mmap;
 
 	if (unlikely(access_error(error_code, vma))) {
-		vma_end_read(vma);
-		goto lock_mmap;
+		bad_area_access_error(regs, error_code, address, NULL, vma);
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return;
 	}
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
 	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
@@ -1393,7 +1369,7 @@ retry:
 	 * we can handle it..
 	 */
 	if (unlikely(access_error(error_code, vma))) {
-		bad_area_access_error(regs, error_code, address, vma);
+		bad_area_access_error(regs, error_code, address, mm, vma);
 		return;
 	}
 
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 5804bbae4f01..807a5859a3c4 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,41 +19,14 @@
 #include <asm/tlbflush.h>
 #include <asm/elf.h>
 
-/*
- * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pmd_huge(pmd_t pmd)
-{
-	return !pmd_none(pmd) &&
-		(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-}
-
-/*
- * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pud_huge(pud_t pud)
-{
-#if CONFIG_PGTABLE_LEVELS > 2
-	return !pud_none(pud) &&
-		(pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-#else
-	return 0;
-#endif
-}
-
 #ifdef CONFIG_HUGETLB_PAGE
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
+	struct vm_unmapped_area_info info = {};
 
-	info.flags = 0;
 	info.length = len;
 	info.low_limit = get_mmap_base(1);
 
@@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
 
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
 	return vm_unmapped_area(&info);
 }
 
@@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info;
+	struct vm_unmapped_area_info info = {};
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
@@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
 
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);
 
 	/*
@@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	}
 
 get_unmapped_area:
-	if (mm->get_unmapped_area == arch_get_unmapped_area)
+	if (!test_bit(MMF_TOPDOWN, &mm->flags))
 		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 				pgoff, flags);
 	else
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a204a332c71f..968d7005f4a7 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
-		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		/* if this is already a gbpage, this portion is already mapped */
-		if (pud_leaf(*pud))
-			continue;
-
-		/* Is using a gbpage allowed? */
-		use_gbpage = info->direct_gbpages;
-
-		/* Don't use gbpage if it maps more than the requested region. */
-		/* at the begining: */
-		use_gbpage &= ((addr & ~PUD_MASK) == 0);
-		/* ... or at the end: */
-		use_gbpage &= ((next & ~PUD_MASK) == 0);
-
-		/* Never overwrite existing mappings */
-		use_gbpage &= !pud_present(*pud);
-
-		if (use_gbpage) {
+		if (info->direct_gbpages) {
 			pud_t pudval;
 
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 679893ea5e68..eb503f53c319 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
 #include <linux/swapops.h>
 #include <linux/kmemleak.h>
 #include <linux/sched/task.h>
+#include <linux/execmem.h>
 
 #include <asm/set_memory.h>
 #include <asm/cpu_device_id.h>
@@ -261,21 +262,17 @@ static void __init probe_page_size_mask(void)
 	}
 }
 
-#define INTEL_MATCH(_model) { .vendor  = X86_VENDOR_INTEL,	\
-			      .family  = 6,			\
-			      .model = _model,			\
-			    }
 /*
  * INVLPG may not properly flush Global entries
  * on these CPUs when PCIDs are enabled.
  */
 static const struct x86_cpu_id invlpg_miss_ids[] = {
-	INTEL_MATCH(INTEL_FAM6_ALDERLAKE   ),
-	INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
-	INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ),
-	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE  ),
-	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
-	INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+	X86_MATCH_VFM(INTEL_ALDERLAKE,	    0),
+	X86_MATCH_VFM(INTEL_ALDERLAKE_L,    0),
+	X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE,	    0),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_P,   0),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,   0),
 	{}
 };
 
@@ -990,53 +987,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-/*
- * Calculate the precise size of the DMA zone (first 16 MB of RAM),
- * and pass it to the MM layer - to help it set zone watermarks more
- * accurately.
- *
- * Done on 64-bit systems only for the time being, although 32-bit systems
- * might benefit from this as well.
- */
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
-	u64 nr_pages = 0, nr_free_pages = 0;
-	unsigned long start_pfn, end_pfn;
-	phys_addr_t start_addr, end_addr;
-	int i;
-	u64 u;
-
-	/*
-	 * Iterate over all memory ranges (free and reserved ones alike),
-	 * to calculate the total number of pages in the first 16 MB of RAM:
-	 */
-	nr_pages = 0;
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-		start_pfn = min(start_pfn, MAX_DMA_PFN);
-		end_pfn   = min(end_pfn,   MAX_DMA_PFN);
-
-		nr_pages += end_pfn - start_pfn;
-	}
-
-	/*
-	 * Iterate over free memory ranges to calculate the number of free
-	 * pages in the DMA zone, while not counting potential partial
-	 * pages at the beginning or the end of the range:
-	 */
-	nr_free_pages = 0;
-	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
-		start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
-		end_pfn   = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
-
-		if (start_pfn < end_pfn)
-			nr_free_pages += end_pfn - start_pfn;
-	}
-
-	set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
-
 void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
@@ -1099,3 +1049,31 @@ unsigned long arch_max_swapfile_size(void)
 	return pages;
 }
 #endif
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	unsigned long start, offset = 0;
+
+	if (kaslr_enabled())
+		offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+	start = MODULES_VADDR + offset;
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.flags	= EXECMEM_KASAN_SHADOW,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = MODULE_ALIGN,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 6f3b3e028718..0a120d85d7bb 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -102,6 +102,13 @@ void __init mem_encrypt_setup_arch(void)
 	phys_addr_t total_mem = memblock_phys_mem_size();
 	unsigned long size;
 
+	/*
+	 * Do RMP table fixups after the e820 tables have been setup by
+	 * e820__memory_setup().
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+		snp_fixup_e820_tables();
+
 	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 70b91de2e053..422602f6039b 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -492,6 +492,24 @@ void __init sme_early_init(void)
 	 */
 	if (sev_status & MSR_AMD64_SEV_ENABLED)
 		ia32_disable();
+
+	/*
+	 * Override init functions that scan the ROM region in SEV-SNP guests,
+	 * as this memory is not pre-validated and would thus cause a crash.
+	 */
+	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+		x86_init.mpparse.find_mptable = x86_init_noop;
+		x86_init.pci.init_irq = x86_init_noop;
+		x86_init.resources.probe_roms = x86_init_noop;
+
+		/*
+		 * DMI setup behavior for SEV-SNP guests depends on
+		 * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+		 * parsed yet. snp_dmi_setup() will run after that
+		 * parsing has happened.
+		 */
+		x86_init.resources.dmi_setup = snp_dmi_setup;
+	}
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c90c20904a60..a2cabb1c81e1 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
 void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	if (mmap_is_legacy())
-		mm->get_unmapped_area = arch_get_unmapped_area;
+		clear_bit(MMF_TOPDOWN, &mm->flags);
 	else
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		set_bit(MMF_TOPDOWN, &mm->flags);
 
 	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
 			arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 65e9a6e391c0..ce84ba86e69e 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -929,6 +929,8 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 
+#endif
+
 static int __init cmp_memblk(const void *a, const void *b)
 {
 	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
@@ -1001,5 +1003,3 @@ int __init numa_fill_memblks(u64 start, u64 end)
 	}
 	return 0;
 }
-
-#endif
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 104544359d69..65fda406e6f2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,8 @@
 
 #include <linux/memblock.h>
 #include <linux/init.h>
+#include <linux/vmalloc.h>
+#include <asm/pgtable_areas.h>
 
 #include "numa_internal.h"
 
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0d72183b5dd0..bdc2a240c2aa 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -39,6 +39,7 @@
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
 
@@ -947,6 +948,61 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
+static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
+		resource_size_t *phys)
+{
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+
+	if (follow_pte(vma, vma->vm_start, &ptep, &ptl))
+		return -EINVAL;
+
+	pte = ptep_get(ptep);
+
+	/* Never return PFNs of anon folios in COW mappings. */
+	if (vm_normal_folio(vma, vma->vm_start, pte)) {
+		pte_unmap_unlock(ptep, ptl);
+		return -EINVAL;
+	}
+
+	*prot = pgprot_val(pte_pgprot(pte));
+	*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+		pgprot_t *pgprot)
+{
+	unsigned long prot;
+
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+	/*
+	 * We need the starting PFN and cachemode used for track_pfn_remap()
+	 * that covered the whole VMA. For most mappings, we can obtain that
+	 * information from the page tables. For COW mappings, we might now
+	 * suddenly have anon folios mapped and follow_phys() will fail.
+	 *
+	 * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+	 * detect the PFN. If we need the cachemode as well, we're out of luck
+	 * for now and have to fail fork().
+	 */
+	if (!follow_phys(vma, &prot, paddr)) {
+		if (pgprot)
+			*pgprot = __pgprot(prot);
+		return 0;
+	}
+	if (is_cow_mapping(vma->vm_flags)) {
+		if (pgprot)
+			return -EINVAL;
+		*paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
 /*
  * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
@@ -957,20 +1013,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 int track_pfn_copy(struct vm_area_struct *vma)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (vma->vm_flags & VM_PAT) {
-		/*
-		 * reserve the whole chunk covered by vma. We need the
-		 * starting address and protection from pte.
-		 */
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, &pgprot))
 			return -EINVAL;
-		}
-		pgprot = __pgprot(prot);
+		/* reserve the whole chunk covered by vma. */
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
@@ -1045,7 +1094,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		 unsigned long size, bool mm_wr_locked)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 
 	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
@@ -1053,11 +1101,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	/* free the chunk starting from pfn or the whole chunk */
 	paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	if (!paddr && !size) {
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, NULL))
 			return;
-		}
-
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 80c9037ffadf..19fdfbb171ed 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
  * Validate strict W^X semantics.
  */
 static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start,
-				  unsigned long pfn, unsigned long npg)
+				  unsigned long pfn, unsigned long npg,
+				  bool nx, bool rw)
 {
 	unsigned long end;
 
@@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
 	if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
 		return new;
 
+	/* Non-leaf translation entries can disable writing or execution. */
+	if (!rw || nx)
+		return new;
+
 	end = start + npg * PAGE_SIZE - 1;
 	WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n",
 		  (unsigned long long)pgprot_val(old),
@@ -657,20 +662,26 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
 
 /*
  * Lookup the page table entry for a virtual address in a specific pgd.
- * Return a pointer to the entry and the level of the mapping.
+ * Return a pointer to the entry, the level of the mapping, and the effective
+ * NX and RW bits of all page table levels.
  */
-pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
-			     unsigned int *level)
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw)
 {
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	*level = PG_LEVEL_NONE;
+	*nx = false;
+	*rw = true;
 
 	if (pgd_none(*pgd))
 		return NULL;
 
+	*nx |= pgd_flags(*pgd) & _PAGE_NX;
+	*rw &= pgd_flags(*pgd) & _PAGE_RW;
+
 	p4d = p4d_offset(pgd, address);
 	if (p4d_none(*p4d))
 		return NULL;
@@ -679,6 +690,9 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (p4d_leaf(*p4d) || !p4d_present(*p4d))
 		return (pte_t *)p4d;
 
+	*nx |= p4d_flags(*p4d) & _PAGE_NX;
+	*rw &= p4d_flags(*p4d) & _PAGE_RW;
+
 	pud = pud_offset(p4d, address);
 	if (pud_none(*pud))
 		return NULL;
@@ -687,6 +701,9 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (pud_leaf(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 
+	*nx |= pud_flags(*pud) & _PAGE_NX;
+	*rw &= pud_flags(*pud) & _PAGE_RW;
+
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
 		return NULL;
@@ -695,12 +712,27 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (pmd_leaf(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	*nx |= pmd_flags(*pmd) & _PAGE_NX;
+	*rw &= pmd_flags(*pmd) & _PAGE_RW;
+
 	*level = PG_LEVEL_4K;
 
 	return pte_offset_kernel(pmd, address);
 }
 
 /*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+			     unsigned int *level)
+{
+	bool nx, rw;
+
+	return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw);
+}
+
+/*
  * Lookup the page table entry for a virtual address. Return a pointer
  * to the entry and the level of the mapping.
  *
@@ -715,13 +747,16 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 EXPORT_SYMBOL_GPL(lookup_address);
 
 static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
-				  unsigned int *level)
+				  unsigned int *level, bool *nx, bool *rw)
 {
-	if (cpa->pgd)
-		return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
-					       address, level);
+	pgd_t *pgd;
+
+	if (!cpa->pgd)
+		pgd = pgd_offset_k(address);
+	else
+		pgd = cpa->pgd + pgd_index(address);
 
-	return lookup_address(address, level);
+	return lookup_address_in_pgd_attr(pgd, address, level, nx, rw);
 }
 
 /*
@@ -849,12 +884,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	pgprot_t old_prot, new_prot, req_prot, chk_prot;
 	pte_t new_pte, *tmp;
 	enum pg_level level;
+	bool nx, rw;
 
 	/*
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = _lookup_address_cpa(cpa, address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (tmp != kpte)
 		return 1;
 
@@ -965,7 +1001,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
 				      psize, CPA_DETECT);
 
-	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages);
+	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages,
+			      nx, rw);
 
 	/*
 	 * If there is a conflict, split the large page.
@@ -1046,6 +1083,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned int i, level;
 	pgprot_t ref_prot;
+	bool nx, rw;
 	pte_t *tmp;
 
 	spin_lock(&pgd_lock);
@@ -1053,7 +1091,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = _lookup_address_cpa(cpa, address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -1594,10 +1632,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	int do_split, err;
 	unsigned int level;
 	pte_t *kpte, old_pte;
+	bool nx, rw;
 
 	address = __cpa_addr(cpa, cpa->curpage);
 repeat:
-	kpte = _lookup_address_cpa(cpa, address, &level);
+	kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (!kpte)
 		return __cpa_process_fault(cpa, address, primary);
 
@@ -1619,7 +1658,8 @@ repeat:
 		new_prot = static_protections(new_prot, address, pfn, 1, 0,
 					      CPA_PROTECT);
 
-		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1);
+		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1,
+				      nx, rw);
 
 		new_prot = pgprot_clear_protnone_bits(new_prot);
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d007591b8059..93e54ba91fbf 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
 			 pmd_t *pmdp)
 {
+	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
+
 	/*
 	 * No flush is necessary. Once an invalid PTE is established, the PTE's
 	 * access and dirty bits cannot be updated.
@@ -731,7 +733,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 		return 0;
 
 	/* Bail out if we are we on a populated non-leaf entry: */
-	if (pud_present(*pud) && !pud_huge(*pud))
+	if (pud_present(*pud) && !pud_leaf(*pud))
 		return 0;
 
 	set_pte((pte_t *)pud, pfn_pte(
@@ -760,7 +762,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 	}
 
 	/* Bail out if we are we on a populated non-leaf entry: */
-	if (pmd_present(*pmd) && !pmd_huge(*pmd))
+	if (pmd_present(*pmd) && !pmd_leaf(*pmd))
 		return 0;
 
 	set_pte((pte_t *)pmd, pfn_pte(