3 files changed, 62 insertions, 25 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d8dbeac8b206..ff253648706f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -958,8 +958,12 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params)
 {
+	unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	int ret;
 
+	if (WARN_ON_ONCE(end > PHYSMEM_END))
+		return -ERANGE;
+
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 37db264866b6..230f1dee4f09 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
  */
 static __initdata struct kaslr_memory_region {
 	unsigned long *base;
+	unsigned long *end;
 	unsigned long size_tb;
 } kaslr_regions[] = {
-	{ &page_offset_base, 0 },
-	{ &vmalloc_base, 0 },
-	{ &vmemmap_base, 0 },
+	{
+		.base	= &page_offset_base,
+		.end	= &physmem_end,
+	},
+	{
+		.base	= &vmalloc_base,
+	},
+	{
+		.base	= &vmemmap_base,
+	},
 };
 
+/* The end of the possible address space for physical memory */
+unsigned long physmem_end __ro_after_init;
+
 /* Get size in bytes used by the memory region */
 static inline unsigned long get_padding(struct kaslr_memory_region *region)
 {
@@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void)
 	BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
 	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
+	/* Preset the end of the possible address space for physical memory */
+	physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
 	if (!kaslr_memory_enabled())
 		return;
 
@@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void)
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
+		/* Calculate the end of the region */
+		vaddr += get_padding(&kaslr_regions[i]);
 		/*
-		 * Jump the region and add a minimum padding based on
-		 * randomization alignment.
+		 * KASLR trims the maximum possible size of the
+		 * direct-map. Update the physmem_end boundary.
+		 * No rounding required as the region starts
+		 * PUD aligned and size is in units of TB.
 		 */
-		vaddr += get_padding(&kaslr_regions[i]);
+		if (kaslr_regions[i].end)
+			*kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
+
+		/* Add a minimum padding based on randomization alignment. */
 		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 2e69abf4f852..851ec8f1363a 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -241,7 +241,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
  *
  * Returns a pointer to a PTE on success, or NULL on failure.
  */
-static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	pmd_t *pmd;
@@ -251,10 +251,15 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	if (!pmd)
 		return NULL;
 
-	/* We can't do anything sensible if we hit a large mapping. */
+	/* Large PMD mapping found */
 	if (pmd_leaf(*pmd)) {
-		WARN_ON(1);
-		return NULL;
+		/* Clear the PMD if we hit a large mapping from the first round */
+		if (late_text) {
+			set_pmd(pmd, __pmd(0));
+		} else {
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
 	}
 
 	if (pmd_none(*pmd)) {
@@ -283,7 +288,7 @@ static void __init pti_setup_vsyscall(void)
 	if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
 		return;
 
-	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false);
 	if (WARN_ON(!target_pte))
 		return;
 
@@ -301,7 +306,7 @@ enum pti_clone_level {
 
 static void
 pti_clone_pgtable(unsigned long start, unsigned long end,
-		  enum pti_clone_level level)
+		  enum pti_clone_level level, bool late_text)
 {
 	unsigned long addr;
 
@@ -374,14 +379,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			 */
 			*target_pmd = *pmd;
 
-			addr += PMD_SIZE;
+			addr = round_up(addr + 1, PMD_SIZE);
 
 		} else if (level == PTI_CLONE_PTE) {
 
 			/* Walk the page-table down to the pte level */
 			pte = pte_offset_kernel(pmd, addr);
 			if (pte_none(*pte)) {
-				addr += PAGE_SIZE;
+				addr = round_up(addr + 1, PAGE_SIZE);
 				continue;
 			}
 
@@ -390,7 +395,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 				return;
 
 			/* Allocate PTE in the user page-table */
-			target_pte = pti_user_pagetable_walk_pte(addr);
+			target_pte = pti_user_pagetable_walk_pte(addr, late_text);
 			if (WARN_ON(!target_pte))
 				return;
 
@@ -401,7 +406,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			/* Clone the PTE */
 			*target_pte = *pte;
 
-			addr += PAGE_SIZE;
+			addr = round_up(addr + 1, PAGE_SIZE);
 
 		} else {
 			BUG();
@@ -452,7 +457,7 @@ static void __init pti_clone_user_shared(void)
 		phys_addr_t pa = per_cpu_ptr_to_phys((void *)va);
 		pte_t *target_pte;
 
-		target_pte = pti_user_pagetable_walk_pte(va);
+		target_pte = pti_user_pagetable_walk_pte(va, false);
 		if (WARN_ON(!target_pte))
 			return;
 
@@ -475,7 +480,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD, false);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -492,11 +497,11 @@ static void __init pti_setup_espfix64(void)
 /*
  * Clone the populated PMDs of the entry text and force it RO.
  */
-static void pti_clone_entry_text(void)
+static void pti_clone_entry_text(bool late)
 {
 	pti_clone_pgtable((unsigned long) __entry_text_start,
 			  (unsigned long) __entry_text_end,
-			  PTI_CLONE_PMD);
+			  PTI_LEVEL_KERNEL_IMAGE, late);
 }
 
 /*
@@ -571,7 +576,7 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false);
 
 	/*
 	 * pti_clone_pgtable() will set the global bit in any PMDs
@@ -638,8 +643,15 @@ void __init pti_init(void)
 
 	/* Undo all global bits from the init pagetables in head_64.S: */
 	pti_set_kernel_image_nonglobal();
+
 	/* Replace some of the global bits just for shared entry text: */
-	pti_clone_entry_text();
+	/*
+	 * This is very early in boot. Device and Late initcalls can do
+	 * modprobe before free_initmem() and mark_readonly(). This
+	 * pti_clone_entry_text() allows those user-mode-helpers to function,
+	 * but notably the text is still RW.
+	 */
+	pti_clone_entry_text(false);
 	pti_setup_espfix64();
 	pti_setup_vsyscall();
 }
@@ -656,10 +668,11 @@ void pti_finalize(void)
 	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 	/*
-	 * We need to clone everything (again) that maps parts of the
-	 * kernel image.
+	 * This is after free_initmem() (all initcalls are done) and we've done
+	 * mark_readonly(). Text is now NX which might've split some PMDs
+	 * relative to the early clone.
 	 */
-	pti_clone_entry_text();
+	pti_clone_entry_text(true);
 	pti_clone_kernel_text();
 
 	debug_checkwx_user();