Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 88 insertions, 116 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 428048e73b..8d3a00e5c5 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 b522933bfa..51986e8a9d 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 bba4e020dd..e6c469b323 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",
@@ -834,14 +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);
 }
@@ -865,7 +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.
@@ -895,9 +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);
 	}
 }
 
@@ -1325,8 +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)))
@@ -1362,7 +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 5804bbae4f..807a5859a3 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/init.c b/arch/x86/mm/init.c
index 679893ea5e..eb503f53c3 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/mmap.c b/arch/x86/mm/mmap.c
index c90c20904a..a2cabb1c81 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_32.c b/arch/x86/mm/numa_32.c
index 025fd7ea5d..65fda406e6 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #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 36b603d0cd..bdc2a240c2 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 +948,29 @@ 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)
 {
@@ -964,7 +988,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
 	 * 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, vma->vm_start, 0, &prot, paddr)) {
+	if (!follow_phys(vma, &prot, paddr)) {
 		if (pgprot)
 			*pgprot = __pgprot(prot);
 		return 0;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 103cbccf1d..93e54ba91f 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -733,7 +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(
@@ -762,7 +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(