[PATCH v3 00/20] Merge text_poke fixes and executable lockdowns

@@ -50,7 +50,12 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	jmp.offset = jump_entry_target(entry) -
 		     (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 
-	if (early_boot_irqs_disabled)
+	/*
+	 * As long as only a single processor is running and the code is still
+	 * not marked as RO, text_poke_early() can be used; Checking that
+	 * system_state is SYSTEM_BOOTING guarantees it.
+	 */
+	if (system_state == SYSTEM_BOOTING)
 		poker = text_poke_early;
 
 	if (type == JUMP_LABEL_JMP) {

@@ -1021,6 +1021,9 @@ static inline void __meminit init_trampoline_default(void)
 	/* Default trampoline pgd value */
 	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
+
+void __init poking_init(void);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else

@@ -39,5 +39,7 @@ extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */

@@ -678,6 +678,9 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	return addr;
 }
 
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
 static void *__text_poke(void *addr, const void *opcode, size_t len)
 {
 	unsigned long flags;

@@ -53,6 +53,7 @@
 #include <asm/init.h>
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
+#include <asm/text-patching.h>
 
 #include "mm_internal.h"
 

@@ -1383,6 +1384,41 @@ unsigned long memory_block_size_bytes(void)
 	return memory_block_size_probed;
 }
 
+/*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	poking_mm = copy_init_mm();
+	BUG_ON(!poking_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	poking_addr = TASK_UNMAPPED_BASE;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		poking_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.

@@ -496,6 +496,8 @@ void __init __weak thread_stack_cache_init(void)
 
 void __init __weak mem_encrypt_init(void) { }
 
+void __init __weak poking_init(void) { }
+
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 

@@ -730,6 +732,7 @@ asmlinkage __visible void __init start_kernel(void)
 	taskstats_init_early();
 	delayacct_init();
 
+	poking_init();
 	check_bugs();
 
 	acpi_subsystem_init();

@@ -742,6 +742,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
+	unsigned long npages;
 	unsigned long size;
 	unsigned long retq;
 	unsigned long *ptr;

@@ -774,6 +775,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		return 0;
 
 	*tramp_size = size + RET_SIZE + sizeof(void *);
+	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);

@@ -818,6 +820,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
+	/*
+	 * Module allocation needs to be completed by making the page
+	 * executable. The page is still writable, which is a security hazard,
+	 * but anyhow ftrace breaks W^X completely.
+	 */
+	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
 	tramp_free(trampoline, *tramp_size);

@@ -431,8 +431,20 @@ void *alloc_insn_page(void)
 	void *page;
 
 	page = module_alloc(PAGE_SIZE);
-	if (page)
-		set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+	if (!page)
+		return NULL;
+
+	/*
+	 * First make the page read-only, and only then make it executable to
+	 * prevent it from being W+X in between.
+	 */
+	set_memory_ro((unsigned long)page, 1);
+
+	/*
+	 * TODO: Once additional kernel code protection mechanisms are set, ensure
+	 * that the page was not maliciously altered and it is still zeroed.
+	 */
+	set_memory_x((unsigned long)page, 1);
 
 	return page;
 }

@@ -440,8 +452,12 @@ void *alloc_insn_page(void)
 /* Recover page to RW mode before releasing it */
 void free_insn_page(void *page)
 {
-	set_memory_nx((unsigned long)page & PAGE_MASK, 1);
-	set_memory_rw((unsigned long)page & PAGE_MASK, 1);
+	/*
+	 * First make the page non-executable, and only then make it writable to
+	 * prevent it from being W+X in between.
+	 */
+	set_memory_nx((unsigned long)page, 1);
+	set_memory_rw((unsigned long)page, 1);
 	module_memfree(page);
 }
 

@@ -692,10 +692,6 @@ static inline void *alloc_tramp(unsigned long size)
 }
 static inline void tramp_free(void *tramp, int size)
 {
-	int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	set_memory_nx((unsigned long)tramp, npages);
-	set_memory_rw((unsigned long)tramp, npages);
 	module_memfree(tramp);
 }
 #else

@@ -820,6 +816,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
+	set_vm_flush_reset_perms(trampoline);
+
 	/*
 	 * Module allocation needs to be completed by making the page
 	 * executable. The page is still writable, which is a security hazard,

@@ -809,6 +809,11 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note that the caller must ensure that if the modified code is part of a
+ * module, the module would not be removed during poking. This can be achieved
+ * by registering a module notifier, and ordering module removal and patching
+ * trough a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {

@@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Work queue for freeing init sections in success case */
+static struct work_struct init_free_wq;
+static struct llist_head init_free_list;
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*

@@ -1949,6 +1953,8 @@ void module_enable_ro(const struct module *mod, bool after_init)
 	if (!rodata_enabled)
 		return;
 
+	set_vm_flush_reset_perms(mod->core_layout.base);
+	set_vm_flush_reset_perms(mod->init_layout.base);
 	frob_text(&mod->core_layout, set_memory_ro);
 	frob_text(&mod->core_layout, set_memory_x);
 

@@ -1972,15 +1978,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-static void module_disable_nx(const struct module *mod)
-{
-	frob_rodata(&mod->core_layout, set_memory_x);
-	frob_ro_after_init(&mod->core_layout, set_memory_x);
-	frob_writable_data(&mod->core_layout, set_memory_x);
-	frob_rodata(&mod->init_layout, set_memory_x);
-	frob_writable_data(&mod->init_layout, set_memory_x);
-}
-
 /* Iterate through all modules and set each module's text as RW */
 void set_all_modules_text_rw(void)
 {

@@ -2024,23 +2021,8 @@ void set_all_modules_text_ro(void)
 	}
 	mutex_unlock(&module_mutex);
 }
-
-static void disable_ro_nx(const struct module_layout *layout)
-{
-	if (rodata_enabled) {
-		frob_text(layout, set_memory_rw);
-		frob_rodata(layout, set_memory_rw);
-		frob_ro_after_init(layout, set_memory_rw);
-	}
-	frob_rodata(layout, set_memory_x);
-	frob_ro_after_init(layout, set_memory_x);
-	frob_writable_data(layout, set_memory_x);
-}
-
 #else
-static void disable_ro_nx(const struct module_layout *layout) { }
 static void module_enable_nx(const struct module *mod) { }
-static void module_disable_nx(const struct module *mod) { }
 #endif
 
 #ifdef CONFIG_LIVEPATCH

@@ -2120,6 +2102,11 @@ static void free_module_elf(struct module *mod)
 
 void __weak module_memfree(void *module_region)
 {
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
 	vfree(module_region);
 }
 

@@ -2171,7 +2158,6 @@ static void free_module(struct module *mod)
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	kfree(mod->args);

@@ -2181,7 +2167,6 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
-	disable_ro_nx(&mod->core_layout);
 	module_memfree(mod->core_layout.base);
 }
 

@@ -3424,17 +3409,34 @@ static void do_mod_ctors(struct module *mod)
 
 /* For freeing module_init on success, in case kallsyms traversing */
 struct mod_initfree {
-	struct rcu_head rcu;
+	struct llist_node node;
 	void *module_init;
 };
 
-static void do_free_init(struct rcu_head *head)
+static void do_free_init(struct work_struct *w)
 {
-	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
-	module_memfree(m->module_init);
-	kfree(m);
+	struct llist_node *pos, *n, *list;
+	struct mod_initfree *initfree;
+
+	list = llist_del_all(&init_free_list);
+
+	synchronize_rcu();
+
+	llist_for_each_safe(pos, n, list) {
+		initfree = container_of(pos, struct mod_initfree, node);
+		module_memfree(initfree->module_init);
+		kfree(initfree);
+	}
 }
 
+static int __init modules_wq_init(void)
+{
+	INIT_WORK(&init_free_wq, do_free_init);
+	init_llist_head(&init_free_list);
+	return 0;
+}
+module_init(modules_wq_init);
+
 /*
  * This is where the real work happens.
  *

@@ -3511,7 +3513,6 @@ static noinline int do_init_module(struct module *mod)
 #endif
 	module_enable_ro(mod, true);
 	mod_tree_remove_init(mod);
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	mod->init_layout.base = NULL;
 	mod->init_layout.size = 0;

@@ -3522,14 +3523,18 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path, so use actual RCU here.
+	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * work and call synchronize_rcu() in a work queue.
+	 *
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
 	 * rcu_barrier()
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	if (llist_add(&freeinit->node, &init_free_list))
+		schedule_work(&init_free_wq);
+
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 

@@ -3826,10 +3831,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* we can't deallocate the module until we clear memory protection */
-	module_disable_ro(mod);
-	module_disable_nx(mod);
-
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);

@@ -434,6 +434,7 @@ void *alloc_insn_page(void)
 	if (!page)
 		return NULL;
 
+	set_vm_flush_reset_perms(page);
 	/*
 	 * First make the page read-only, and only then make it executable to
 	 * prevent it from being W+X in between.

@@ -452,12 +453,6 @@ void *alloc_insn_page(void)
 /* Recover page to RW mode before releasing it */
 void free_insn_page(void *page)
 {
-	/*
-	 * First make the page non-executable, and only then make it writable to
-	 * prevent it from being W+X in between.
-	 */
-	set_memory_nx((unsigned long)page, 1);
-	set_memory_rw((unsigned long)page, 1);
 	module_memfree(page);
 }
 

@@ -20,6 +20,7 @@
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
 
 #include <net/sch_generic.h>
 

@@ -483,7 +484,6 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */

@@ -681,27 +681,17 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	fp->undo_set_mem = 1;
+	set_vm_flush_reset_perms(fp);
 	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-	if (fp->undo_set_mem)
-		set_memory_rw((unsigned long)fp, fp->pages);
-}
-
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
+	set_vm_flush_reset_perms(hdr);
 	set_memory_ro((unsigned long)hdr, hdr->pages);
 	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-	set_memory_rw((unsigned long)hdr, hdr->pages);
-}
-
 static inline struct bpf_binary_header *
 bpf_jit_binary_hdr(const struct bpf_prog *fp)
 {

@@ -736,7 +726,6 @@ void __bpf_prog_free(struct bpf_prog *fp);
 
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
-	bpf_prog_unlock_ro(fp);
 	__bpf_prog_free(fp);
 }
 

@@ -804,7 +804,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		bpf_jit_binary_unlock_ro(hdr);
 		bpf_jit_binary_free(hdr);
 
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));

@@ -18,7 +18,7 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.

@@ -37,7 +37,7 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;

@@ -264,7 +264,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-void *text_poke_early(void *addr, const void *opcode, size_t len);
+void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Are we looking at a near JMP with a 1 or 4-byte displacement.

@@ -666,8 +666,8 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-void *__init_or_module text_poke_early(void *addr, const void *opcode,
-				       size_t len)
+void __init_or_module text_poke_early(void *addr, const void *opcode,
+				      size_t len)
 {
 	unsigned long flags;
 

@@ -690,7 +690,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 		 * that causes hangs on some VIA CPUs.
 		 */
 	}
-	return addr;
 }
 
 __ro_after_init struct mm_struct *poking_mm;

@@ -892,7 +891,7 @@ int poke_int3_handler(struct pt_regs *regs)
  *	  replacing opcode
  *	- sync cores
  */
-void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
 	unsigned char int3 = 0xcc;
 

@@ -934,7 +933,5 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	 * the writing of the new instruction.
 	 */
 	bp_patching_in_progress = false;
-
-	return addr;
 }
 

@@ -21,6 +21,11 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+/*
+ * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
+ * vfree_atomic().
+ */
+#define VM_FLUSH_RESET_PERMS	0x00000100      /* Reset direct map and flush TLB on unmap */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*

@@ -135,6 +140,14 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
 
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+	struct vm_struct *vm = find_vm_area(addr);
+
+	if (vm)
+		vm->flags |= VM_FLUSH_RESET_PERMS;
+}
+
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
 			struct page **pages);
 #ifdef CONFIG_MMU

@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/set_memory.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/list.h>

@@ -1055,24 +1056,9 @@ static void vb_free(const void *addr, unsigned long size)
 		spin_unlock(&vb->lock);
 }
 
-/**
- * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
- *
- * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
- * to amortize TLB flushing overheads. What this means is that any page you
- * have now, may, in a former life, have been mapped into kernel virtual
- * address by the vmap layer and so there might be some CPUs with TLB entries
- * still referencing that page (additional to the regular 1:1 kernel mapping).
- *
- * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
- * be sure that none of the pages we have control over will have any aliases
- * from the vmap layer.
- */
-void vm_unmap_aliases(void)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
 {
-	unsigned long start = ULONG_MAX, end = 0;
 	int cpu;
-	int flush = 0;
 
 	if (unlikely(!vmap_initialized))
 		return;

@@ -1109,6 +1095,27 @@ void vm_unmap_aliases(void)
 		flush_tlb_kernel_range(start, end);
 	mutex_unlock(&vmap_purge_lock);
 }
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush = 0;
+
+	_vm_unmap_aliases(start, end, flush);
+}
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /**

@@ -1494,6 +1501,72 @@ struct vm_struct *remove_vm_area(const void *addr)
 	return NULL;
 }
 
+static inline void set_area_direct_map(const struct vm_struct *area,
+				       int (*set_direct_map)(struct page *page))
+{
+	int i;
+
+	for (i = 0; i < area->nr_pages; i++)
+		if (page_address(area->pages[i]))
+			set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+	int i;
+
+	/*
+	 * The below block can be removed when all architectures that have
+	 * direct map permissions also have set_direct_map_() implementations.
+	 * This is concerned with resetting the direct map any an vm alias with
+	 * execute permissions, without leaving a RW+X window.
+	 */
+	if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		set_memory_nx(addr, area->nr_pages);
+		set_memory_rw(addr, area->nr_pages);
+	}
+
+	remove_vm_area(area->addr);
+
+	/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+	if (!flush_reset)
+		return;
+
+	/*
+	 * If not deallocating pages, just do the flush of the VM area and
+	 * return.
+	 */
+	if (!deallocate_pages) {
+		vm_unmap_aliases();
+		return;
+	}
+
+	/*
+	 * If execution gets here, flush the vm mapping and reset the direct
+	 * map. Find the start and end range of the direct mappings to make sure
+	 * the vm_unmap_aliases() flush includes the direct map.
+	 */
+	for (i = 0; i < area->nr_pages; i++) {
+		if (page_address(area->pages[i])) {
+			start = min(addr, start);
+			end = max(addr, end);
+		}
+	}
+
+	/*
+	 * Set direct map to something invalid so that it won't be cached if
+	 * there are any accesses after the TLB flush, then flush the TLB and
+	 * reset the direct map permissions to the default.
+	 */
+	set_area_direct_map(area, set_direct_map_invalid_noflush);
+	_vm_unmap_aliases(start, end, 1);
+	set_area_direct_map(area, set_direct_map_default_noflush);
+}
+
 static void __vunmap(const void *addr, int deallocate_pages)
 {
 	struct vm_struct *area;

@@ -1515,7 +1588,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	remove_vm_area(addr);
+	vm_remove_mappings(area, deallocate_pages);
+
 	if (deallocate_pages) {
 		int i;
 

@@ -1925,8 +1999,9 @@ EXPORT_SYMBOL(vzalloc_node);
 
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
-			      NUMA_NO_NODE, __builtin_return_address(0));
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)

@@ -2257,7 +2257,6 @@ int set_direct_map_default_noflush(struct page *page)
 	return __set_pages_p(page, 1);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))

@@ -2302,11 +2301,8 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-
 #endif /* CONFIG_HIBERNATION */
 
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
 {

@@ -2642,37 +2642,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
-extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static inline bool debug_pagealloc_enabled(void)
 {
-	return _debug_pagealloc_enabled;
+	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled;
 }
 
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
 {
-	if (!debug_pagealloc_enabled())
-		return;
-
 	__kernel_map_pages(page, numpages, enable);
 }
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
-#else	/* CONFIG_DEBUG_PAGEALLOC */
+#else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
-static inline bool debug_pagealloc_enabled(void)
-{
-	return false;
-}
-#endif	/* CONFIG_DEBUG_PAGEALLOC */
+#endif	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);

@@ -1334,8 +1334,9 @@ static inline void do_copy_page(long *dst, long *src)
  * safe_copy_page - Copy a page in a safe way.
  *
  * Check if the page we are going to copy is marked as present in the kernel
- * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
- * and in that case kernel_page_present() always returns 'true').
+ * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
+ * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
+ * always returns 'true'.
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {

@@ -1074,7 +1074,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	arch_free_page(page, order);
 	kernel_poison_pages(page, 1 << order, 0);
-	kernel_map_pages(page, 1 << order, 0);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 0);
+
 	kasan_free_nondeferred_pages(page, order);
 
 	return true;

@@ -1944,7 +1946,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	kernel_map_pages(page, 1 << order, 1);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 1);
 	kernel_poison_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 	set_page_owner(page, order, gfp_flags);

@@ -249,6 +249,10 @@ config ARCH_HAS_FORTIFY_SOURCE
 config ARCH_HAS_SET_MEMORY
 	bool
 
+# Select if arch has all set_direct_map_invalid/default() functions
+config ARCH_HAS_SET_DIRECT_MAP
+	bool
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
        bool

@@ -66,6 +66,7 @@ config X86
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE

@@ -85,6 +85,9 @@ int set_pages_nx(struct page *page, int numpages);
 int set_pages_ro(struct page *page, int numpages);
 int set_pages_rw(struct page *page, int numpages);
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);

@@ -2209,8 +2209,6 @@ int set_pages_rw(struct page *page, int numpages)
 	return set_memory_rw(addr, numpages);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-
 static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);

@@ -2249,6 +2247,17 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_pages_np(page, 1);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_pages_p(page, 1);
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))

@@ -2282,7 +2291,6 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 }
 
 #ifdef CONFIG_HIBERNATION
-
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;

@@ -10,6 +10,16 @@
 
 #ifdef CONFIG_ARCH_HAS_SET_MEMORY
 #include <asm/set_memory.h>
+#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP
+static inline int set_direct_map_invalid_noflush(struct page *page)
+{
+	return 0;
+}
+static inline int set_direct_map_default_noflush(struct page *page)
+{
+	return 0;
+}
+#endif
 #else
 static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }