[PATCH v18 0/9] mm: introduce memfd_secret system call to create "secret" memory areas

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SECRETMEM_H
+#define _LINUX_SECRETMEM_H
+
+#ifdef CONFIG_SECRETMEM
+
+bool vma_is_secretmem(struct vm_area_struct *vma);
+bool page_is_secretmem(struct page *page);
+
+#else
+
+static inline bool vma_is_secretmem(struct vm_area_struct *vma)
+{
+	return false;
+}
+
+static inline bool page_is_secretmem(struct page *page)
+{
+	return false;
+}
+
+#endif /* CONFIG_SECRETMEM */
+
+#endif /* _LINUX_SECRETMEM_H */

@@ -97,5 +97,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define Z3FOLD_MAGIC		0x33
 #define PPC_CMM_MAGIC		0xc7571590
+#define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 
 #endif /* __LINUX_MAGIC_H__ */

@@ -352,6 +352,8 @@ COND_SYSCALL(pkey_mprotect);
 COND_SYSCALL(pkey_alloc);
 COND_SYSCALL(pkey_free);
 
+/* memfd_secret */
+COND_SYSCALL(memfd_secret);
 
 /*
  * Architecture specific weak syscall entries.

@@ -872,4 +872,7 @@ config MAPPING_DIRTY_HELPERS
 config KMAP_LOCAL
 	bool
 
+config SECRETMEM
+	def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
 endmenu

@@ -120,3 +120,4 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
+obj-$(CONFIG_SECRETMEM) += secretmem.o

@@ -10,6 +10,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/secretmem.h>
 
 #include <linux/sched/signal.h>
 #include <linux/rwsem.h>

@@ -758,6 +759,9 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	struct follow_page_context ctx = { NULL };
 	struct page *page;
 
+	if (vma_is_secretmem(vma))
+		return NULL;
+
 	page = follow_page_mask(vma, address, foll_flags, &ctx);
 	if (ctx.pgmap)
 		put_dev_pagemap(ctx.pgmap);

@@ -891,6 +895,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
 		return -EOPNOTSUPP;
 
+	if (vma_is_secretmem(vma))
+		return -EFAULT;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))

@@ -2030,6 +2037,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
+		if (page_is_secretmem(page))
+			goto pte_unmap;
+
 		head = try_grab_compound_head(page, 1, flags);
 		if (!head)
 			goto pte_unmap;

@@ -23,6 +23,7 @@
 #include <linux/hugetlb.h>
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h>
+#include <linux/secretmem.h>
 
 #include "internal.h"
 

@@ -503,7 +504,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma))
+	    vma_is_dax(vma) || vma_is_secretmem(vma))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 

@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2021
+ *
+ * Author: Mike Rapoport <rppt@linux.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/swap.h>
+#include <linux/mount.h>
+#include <linux/memfd.h>
+#include <linux/bitops.h>
+#include <linux/printk.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/pseudo_fs.h>
+#include <linux/secretmem.h>
+#include <linux/set_memory.h>
+#include <linux/sched/signal.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "secretmem: " fmt
+
+/*
+ * Define mode and flag masks to allow validation of the system call
+ * parameters.
+ */
+#define SECRETMEM_MODE_MASK	(0x0)
+#define SECRETMEM_FLAGS_MASK	SECRETMEM_MODE_MASK
+
+static bool secretmem_enable __ro_after_init;
+module_param_named(enable, secretmem_enable, bool, 0400);
+MODULE_PARM_DESC(secretmem_enable,
+		 "Enable secretmem and memfd_secret(2) system call");
+
+static vm_fault_t secretmem_fault(struct vm_fault *vmf)
+{
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	pgoff_t offset = vmf->pgoff;
+	gfp_t gfp = vmf->gfp_mask;
+	unsigned long addr;
+	struct page *page;
+	int err;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return vmf_error(-EINVAL);
+
+retry:
+	page = find_lock_page(mapping, offset);
+	if (!page) {
+		page = alloc_page(gfp | __GFP_ZERO);
+		if (!page)
+			return VM_FAULT_OOM;
+
+		err = set_direct_map_invalid_noflush(page, 1);
+		if (err) {
+			put_page(page);
+			return vmf_error(err);
+		}
+
+		__SetPageUptodate(page);
+		err = add_to_page_cache_lru(page, mapping, offset, gfp);
+		if (unlikely(err)) {
+			put_page(page);
+			/*
+			 * If a split of large page was required, it
+			 * already happened when we marked the page invalid
+			 * which guarantees that this call won't fail
+			 */
+			set_direct_map_default_noflush(page, 1);
+			if (err == -EEXIST)
+				goto retry;
+
+			return vmf_error(err);
+		}
+
+		addr = (unsigned long)page_address(page);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	}
+
+	vmf->page = page;
+	return VM_FAULT_LOCKED;
+}
+
+static const struct vm_operations_struct secretmem_vm_ops = {
+	.fault = secretmem_fault,
+};
+
+static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	unsigned long len = vma->vm_end - vma->vm_start;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
+		return -EAGAIN;
+
+	vma->vm_flags |= VM_LOCKED | VM_DONTDUMP;
+	vma->vm_ops = &secretmem_vm_ops;
+
+	return 0;
+}
+
+bool vma_is_secretmem(struct vm_area_struct *vma)
+{
+	return vma->vm_ops == &secretmem_vm_ops;
+}
+
+static const struct file_operations secretmem_fops = {
+	.mmap		= secretmem_mmap,
+};
+
+static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
+{
+	return false;
+}
+
+static int secretmem_migratepage(struct address_space *mapping,
+				 struct page *newpage, struct page *page,
+				 enum migrate_mode mode)
+{
+	return -EBUSY;
+}
+
+static void secretmem_freepage(struct page *page)
+{
+	set_direct_map_default_noflush(page, 1);
+	clear_highpage(page);
+}
+
+static const struct address_space_operations secretmem_aops = {
+	.freepage	= secretmem_freepage,
+	.migratepage	= secretmem_migratepage,
+	.isolate_page	= secretmem_isolate_page,
+};
+
+bool page_is_secretmem(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+
+	if (!mapping)
+		return false;
+
+	return mapping->a_ops == &secretmem_aops;
+}
+
+static struct vfsmount *secretmem_mnt;
+
+static struct file *secretmem_file_create(unsigned long flags)
+{
+	struct file *file = ERR_PTR(-ENOMEM);
+	struct inode *inode;
+
+	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
+				 O_RDWR, &secretmem_fops);
+	if (IS_ERR(file))
+		goto err_free_inode;
+
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_unevictable(inode->i_mapping);
+
+	inode->i_mapping->a_ops = &secretmem_aops;
+
+	/* pretend we are a normal file with zero size */
+	inode->i_mode |= S_IFREG;
+	inode->i_size = 0;
+
+	return file;
+
+err_free_inode:
+	iput(inode);
+	return file;
+}
+
+SYSCALL_DEFINE1(memfd_secret, unsigned long, flags)
+{
+	struct file *file;
+	int fd, err;
+
+	/* make sure local flags do not confict with global fcntl.h */
+	BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC);
+
+	if (!secretmem_enable)
+		return -ENOSYS;
+
+	if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC))
+		return -EINVAL;
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	file = secretmem_file_create(flags);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_put_fd;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	fd_install(fd, file);
+	return fd;
+
+err_put_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+static int secretmem_init_fs_context(struct fs_context *fc)
+{
+	return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type secretmem_fs = {
+	.name		= "secretmem",
+	.init_fs_context = secretmem_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+static int secretmem_init(void)
+{
+	int ret = 0;
+
+	if (!secretmem_enable)
+		return ret;
+
+	secretmem_mnt = kern_mount(&secretmem_fs);
+	if (IS_ERR(secretmem_mnt))
+		ret = PTR_ERR(secretmem_mnt);
+
+	return ret;
+}
+fs_initcall(secretmem_init);

@@ -133,8 +133,8 @@ static __always_inline void __flush_icache_all(void)
 
 int set_memory_valid(unsigned long addr, int numpages, int enable);
 
-int set_direct_map_invalid_noflush(struct page *page);
-int set_direct_map_default_noflush(struct page *page);
+int set_direct_map_invalid_noflush(struct page *page, int numpages);
+int set_direct_map_default_noflush(struct page *page, int numpages);
 bool kernel_page_present(struct page *page);
 
 #include <asm-generic/cacheflush.h>

@@ -148,34 +148,36 @@ int set_memory_valid(unsigned long addr, int numpages, int enable)
 					__pgprot(PTE_VALID));
 }
 
-int set_direct_map_invalid_noflush(struct page *page)
+int set_direct_map_invalid_noflush(struct page *page, int numpages)
 {
 	struct page_change_data data = {
 		.set_mask = __pgprot(0),
 		.clear_mask = __pgprot(PTE_VALID),
 	};
+	unsigned long size = PAGE_SIZE * numpages;
 
 	if (!debug_pagealloc_enabled() && !rodata_full)
 		return 0;
 
 	return apply_to_page_range(&init_mm,
 				   (unsigned long)page_address(page),
-				   PAGE_SIZE, change_page_range, &data);
+				   size, change_page_range, &data);
 }
 
-int set_direct_map_default_noflush(struct page *page)
+int set_direct_map_default_noflush(struct page *page, int numpages)
 {
 	struct page_change_data data = {
 		.set_mask = __pgprot(PTE_VALID | PTE_WRITE),
 		.clear_mask = __pgprot(PTE_RDONLY),
 	};
+	unsigned long size = PAGE_SIZE * numpages;
 
 	if (!debug_pagealloc_enabled() && !rodata_full)
 		return 0;
 
 	return apply_to_page_range(&init_mm,
 				   (unsigned long)page_address(page),
-				   PAGE_SIZE, change_page_range, &data);
+				   size, change_page_range, &data);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC

@@ -26,8 +26,8 @@ static inline void protect_kernel_text_data(void) {}
 static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
-int set_direct_map_invalid_noflush(struct page *page);
-int set_direct_map_default_noflush(struct page *page);
+int set_direct_map_invalid_noflush(struct page *page, int numpages);
+int set_direct_map_default_noflush(struct page *page, int numpages);
 bool kernel_page_present(struct page *page);
 
 #endif /* __ASSEMBLY__ */

@@ -156,11 +156,11 @@ int set_memory_nx(unsigned long addr, int numpages)
 	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_EXEC));
 }
 
-int set_direct_map_invalid_noflush(struct page *page)
+int set_direct_map_invalid_noflush(struct page *page, int numpages)
 {
 	int ret;
 	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
+	unsigned long end = start + PAGE_SIZE * numpages;
 	struct pageattr_masks masks = {
 		.set_mask = __pgprot(0),
 		.clear_mask = __pgprot(_PAGE_PRESENT)

@@ -173,11 +173,11 @@ int set_direct_map_invalid_noflush(struct page *page)
 	return ret;
 }
 
-int set_direct_map_default_noflush(struct page *page)
+int set_direct_map_default_noflush(struct page *page, int numpages)
 {
 	int ret;
 	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
+	unsigned long end = start + PAGE_SIZE * numpages;
 	struct pageattr_masks masks = {
 		.set_mask = PAGE_KERNEL,
 		.clear_mask = __pgprot(0)

@@ -80,8 +80,8 @@ int set_pages_wb(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);
+int set_direct_map_invalid_noflush(struct page *page, int numpages);
+int set_direct_map_default_noflush(struct page *page, int numpages);
 bool kernel_page_present(struct page *page);
 
 extern int kernel_set_to_readonly;

@@ -2184,14 +2184,14 @@ 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)
+int set_direct_map_invalid_noflush(struct page *page, int numpages)
 {
-	return __set_pages_np(page, 1);
+	return __set_pages_np(page, numpages);
 }
 
-int set_direct_map_default_noflush(struct page *page)
+int set_direct_map_default_noflush(struct page *page, int numpages)
 {
-	return __set_pages_p(page, 1);
+	return __set_pages_p(page, numpages);
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC

@@ -15,11 +15,11 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
 #ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP
-static inline int set_direct_map_invalid_noflush(struct page *page)
+static inline int set_direct_map_invalid_noflush(struct page *page, int numpages)
 {
 	return 0;
 }
-static inline int set_direct_map_default_noflush(struct page *page)
+static inline int set_direct_map_default_noflush(struct page *page, int numpages)
 {
 	return 0;
 }

@@ -86,7 +86,7 @@ static inline void hibernate_restore_unprotect_page(void *page_address) {}
 static inline void hibernate_map_page(struct page *page)
 {
 	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
-		int ret = set_direct_map_default_noflush(page);
+		int ret = set_direct_map_default_noflush(page, 1);
 
 		if (ret)
 			pr_warn_once("Failed to remap page\n");

@@ -99,7 +99,7 @@ static inline void hibernate_unmap_page(struct page *page)
 {
 	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
 		unsigned long addr = (unsigned long)page_address(page);
-		int ret  = set_direct_map_invalid_noflush(page);
+		int ret = set_direct_map_invalid_noflush(page, 1);
 
 		if (ret)
 			pr_warn_once("Failed to remap page\n");

@@ -2195,13 +2195,14 @@ struct vm_struct *remove_vm_area(const void *addr)
 }
 
 static inline void set_area_direct_map(const struct vm_struct *area,
-				       int (*set_direct_map)(struct page *page))
+				       int (*set_direct_map)(struct page *page,
+							     int numpages))
 {
 	int i;
 
 	for (i = 0; i < area->nr_pages; i++)
 		if (page_address(area->pages[i]))
-			set_direct_map(area->pages[i]);
+			set_direct_map(area->pages[i], 1);
 }
 
 /* Handle removing and resetting vm mappings related to the vm_struct. */

@@ -25,8 +25,8 @@ config RISCV
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MMIOWB
 	select ARCH_HAS_PTE_SPECIAL
-	select ARCH_HAS_SET_DIRECT_MAP
-	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP if MMU
+	select ARCH_HAS_SET_MEMORY if MMU
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT

@@ -3,5 +3,4 @@ generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += set_memory.h
 generic-y += user.h

@@ -131,12 +131,6 @@ static __always_inline void __flush_icache_all(void)
 	dsb(ish);
 }
 
-int set_memory_valid(unsigned long addr, int numpages, int enable);
-
-int set_direct_map_invalid_noflush(struct page *page, int numpages);
-int set_direct_map_default_noflush(struct page *page, int numpages);
-bool kernel_page_present(struct page *page);
-
 #include <asm-generic/cacheflush.h>
 
 #endif /* __ASM_CACHEFLUSH_H */

@@ -8,7 +8,7 @@
 #ifndef __ASM_KFENCE_H
 #define __ASM_KFENCE_H
 
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
 
 static inline bool arch_kfence_init_pool(void) { return true; }
 

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARM64_SET_MEMORY_H
+#define _ASM_ARM64_SET_MEMORY_H
+
+#include <asm-generic/set_memory.h>
+
+bool can_set_direct_map(void);
+#define can_set_direct_map can_set_direct_map
+
+int set_memory_valid(unsigned long addr, int numpages, int enable);
+
+int set_direct_map_invalid_noflush(struct page *page, int numpages);
+int set_direct_map_default_noflush(struct page *page, int numpages);
+bool kernel_page_present(struct page *page);
+
+#endif /* _ASM_ARM64_SET_MEMORY_H */

@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/page-flags.h>
+#include <linux/set_memory.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>

@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/set_memory.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>

@@ -492,7 +493,7 @@ static void __init map_mem(pgd_t *pgdp)
 	int flags = 0;
 	u64 i;
 
-	if (rodata_full || crash_mem_map || debug_pagealloc_enabled())
+	if (can_set_direct_map() || crash_mem_map)
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*

@@ -1470,8 +1471,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	 * KFENCE requires linear map to be mapped at page granularity, so that
 	 * it is possible to protect/unprotect single pages in the KFENCE pool.
 	 */
-	if (rodata_full || debug_pagealloc_enabled() ||
-	    IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),

@@ -19,6 +19,11 @@ struct page_change_data {
 
 bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED);
 
+bool can_set_direct_map(void)
+{
+	return rodata_full || debug_pagealloc_enabled();
+}
+
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
 {
 	struct page_change_data *cdata = data;

@@ -156,7 +161,7 @@ int set_direct_map_invalid_noflush(struct page *page, int numpages)
 	};
 	unsigned long size = PAGE_SIZE * numpages;
 
-	if (!debug_pagealloc_enabled() && !rodata_full)
+	if (!can_set_direct_map())
 		return 0;
 
 	return apply_to_page_range(&init_mm,

@@ -172,7 +177,7 @@ int set_direct_map_default_noflush(struct page *page, int numpages)
 	};
 	unsigned long size = PAGE_SIZE * numpages;
 
-	if (!debug_pagealloc_enabled() && !rodata_full)
+	if (!can_set_direct_map())
 		return 0;
 
 	return apply_to_page_range(&init_mm,

@@ -183,7 +188,7 @@ int set_direct_map_default_noflush(struct page *page, int numpages)
 #ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
-	if (!debug_pagealloc_enabled() && !rodata_full)
+	if (!can_set_direct_map())
 		return;
 
 	set_memory_valid((unsigned long)page_address(page), numpages, enable);

@@ -208,7 +213,7 @@ bool kernel_page_present(struct page *page)
 	pte_t *ptep;
 	unsigned long addr = (unsigned long)page_address(page);
 
-	if (!debug_pagealloc_enabled() && !rodata_full)
+	if (!can_set_direct_map())
 		return true;
 
 	pgdp = pgd_offset_k(addr);

@@ -28,7 +28,19 @@ static inline bool kernel_page_present(struct page *page)
 {
 	return true;
 }
+#else /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
+/*
+ * Some architectures, e.g. ARM64 can disable direct map modifications at
+ * boot time. Let them overrive this query.
+ */
+#ifndef can_set_direct_map
+static inline bool can_set_direct_map(void)
+{
+	return true;
+}
+#define can_set_direct_map can_set_direct_map
 #endif
+#endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifndef set_mce_nospec
 static inline int set_mce_nospec(unsigned long pfn, bool unmap)

@@ -49,9 +49,6 @@ static inline unsigned int pe_order(enum page_entry_size pe_size)
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 #define PG_PMD_NR	(PMD_SIZE >> PAGE_SHIFT)
 
-/* The order of a PMD entry */
-#define PMD_ORDER	(PMD_SHIFT - PAGE_SHIFT)
-
 static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
 
 static int __init init_dax_wait_table(void)

@@ -98,7 +95,7 @@ static bool dax_is_locked(void *entry)
 static unsigned int dax_entry_order(void *entry)
 {
 	if (xa_to_value(entry) & DAX_PMD)
-		return PMD_ORDER;
+		return PMD_PAGE_ORDER;
 	return 0;
 }
 

@@ -1471,7 +1468,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
-	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
+	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_PAGE_ORDER);
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool sync;

@@ -1530,7 +1527,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * entry is already in the array, for instance), it will return
 	 * VM_FAULT_FALLBACK.
 	 */
-	entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
+	entry = grab_mapping_entry(&xas, mapping, PMD_PAGE_ORDER);
 	if (xa_is_internal(entry)) {
 		result = xa_to_internal(entry);
 		goto fallback;

@@ -1696,7 +1693,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 	if (order == 0)
 		ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
 #ifdef CONFIG_FS_DAX_PMD
-	else if (order == PMD_ORDER)
+	else if (order == PMD_PAGE_ORDER)
 		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
 #endif
 	else

@@ -28,6 +28,9 @@
 #define USER_PGTABLES_CEILING	0UL
 #endif
 
+/* Number of base pages in a second level leaf page */
+#define PMD_PAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
+
 /*
  * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD]
  *

@@ -353,6 +353,9 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
 extern void mlock_vma_page(struct page *page);
 extern unsigned int munlock_vma_page(struct page *page);
 
+extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
+			      unsigned long len);
+
 /*
  * Clear the page's PageMlocked().  This can be useful in a situation where
  * we want to unconditionally remove a page from the pagecache -- e.g.,

@@ -1346,9 +1346,8 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 	return hint;
 }
 
-static inline int mlock_future_check(struct mm_struct *mm,
-				     unsigned long flags,
-				     unsigned long len)
+int mlock_future_check(struct mm_struct *mm, unsigned long flags,
+		       unsigned long len)
 {
 	unsigned long locked, lock_limit;
 

@@ -21,4 +21,5 @@ va_128TBswitch
 map_fixed_noreplace
 write_to_hugetlbfs
 hmm-tests
+memfd_secret
 local_config.*

@@ -34,6 +34,7 @@ TEST_GEN_FILES += khugepaged
 TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_hugetlb
 TEST_GEN_FILES += map_populate
+TEST_GEN_FILES += memfd_secret
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += mlock2-tests
 TEST_GEN_FILES += mremap_dontunmap

@@ -133,7 +134,7 @@ warn_32bit_failure:
 endif
 endif
 
-$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
+$(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap
 
 $(OUTPUT)/gup_test: ../../../../mm/gup_test.h
 

@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2020
+ *
+ * Author: Mike Rapoport <rppt@linux.ibm.com>
+ */
+
+#define _GNU_SOURCE
+#include <sys/uio.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <sys/types.h>
+#include <sys/ptrace.h>
+#include <sys/syscall.h>
+#include <sys/resource.h>
+#include <sys/capability.h>
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+
+#include "../kselftest.h"
+
+#define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__)
+#define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__)
+#define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__)
+
+#ifdef __NR_memfd_secret
+
+#define PATTERN	0x55
+
+static const int prot = PROT_READ | PROT_WRITE;
+static const int mode = MAP_SHARED;
+
+static unsigned long page_size;
+static unsigned long mlock_limit_cur;
+static unsigned long mlock_limit_max;
+
+static int memfd_secret(unsigned long flags)
+{
+	return syscall(__NR_memfd_secret, flags);
+}
+
+static void test_file_apis(int fd)
+{
+	char buf[64];
+
+	if ((read(fd, buf, sizeof(buf)) >= 0) ||
+	    (write(fd, buf, sizeof(buf)) >= 0) ||
+	    (pread(fd, buf, sizeof(buf), 0) >= 0) ||
+	    (pwrite(fd, buf, sizeof(buf), 0) >= 0))
+		fail("unexpected file IO\n");
+	else
+		pass("file IO is blocked as expected\n");
+}
+
+static void test_mlock_limit(int fd)
+{
+	size_t len;
+	char *mem;
+
+	len = mlock_limit_cur;
+	mem = mmap(NULL, len, prot, mode, fd, 0);
+	if (mem == MAP_FAILED) {
+		fail("unable to mmap secret memory\n");
+		return;
+	}
+	munmap(mem, len);
+
+	len = mlock_limit_max * 2;
+	mem = mmap(NULL, len, prot, mode, fd, 0);
+	if (mem != MAP_FAILED) {
+		fail("unexpected mlock limit violation\n");
+		munmap(mem, len);
+		return;
+	}
+
+	pass("mlock limit is respected\n");
+}
+
+static void try_process_vm_read(int fd, int pipefd[2])
+{
+	struct iovec liov, riov;
+	char buf[64];
+	char *mem;
+
+	if (read(pipefd[0], &mem, sizeof(mem)) < 0) {
+		fail("pipe write: %s\n", strerror(errno));
+		exit(KSFT_FAIL);
+	}
+
+	liov.iov_len = riov.iov_len = sizeof(buf);
+	liov.iov_base = buf;
+	riov.iov_base = mem;
+
+	if (process_vm_readv(getppid(), &liov, 1, &riov, 1, 0) < 0) {
+		if (errno == ENOSYS)
+			exit(KSFT_SKIP);
+		exit(KSFT_PASS);
+	}
+
+	exit(KSFT_FAIL);
+}
+
+static void try_ptrace(int fd, int pipefd[2])
+{
+	pid_t ppid = getppid();
+	int status;
+	char *mem;
+	long ret;
+
+	if (read(pipefd[0], &mem, sizeof(mem)) < 0) {
+		perror("pipe write");
+		exit(KSFT_FAIL);
+	}
+
+	ret = ptrace(PTRACE_ATTACH, ppid, 0, 0);
+	if (ret) {
+		perror("ptrace_attach");
+		exit(KSFT_FAIL);
+	}
+
+	ret = waitpid(ppid, &status, WUNTRACED);
+	if ((ret != ppid) || !(WIFSTOPPED(status))) {
+		fprintf(stderr, "weird waitppid result %ld stat %x\n",
+			ret, status);
+		exit(KSFT_FAIL);
+	}
+
+	if (ptrace(PTRACE_PEEKDATA, ppid, mem, 0))
+		exit(KSFT_PASS);
+
+	exit(KSFT_FAIL);
+}
+
+static void check_child_status(pid_t pid, const char *name)
+{
+	int status;
+
+	waitpid(pid, &status, 0);
+
+	if (WIFEXITED(status) && WEXITSTATUS(status) == KSFT_SKIP) {
+		skip("%s is not supported\n", name);
+		return;
+	}
+
+	if ((WIFEXITED(status) && WEXITSTATUS(status) == KSFT_PASS) ||
+	    WIFSIGNALED(status)) {
+		pass("%s is blocked as expected\n", name);
+		return;
+	}
+
+	fail("%s: unexpected memory access\n", name);
+}
+
+static void test_remote_access(int fd, const char *name,
+			       void (*func)(int fd, int pipefd[2]))
+{
+	int pipefd[2];
+	pid_t pid;
+	char *mem;
+
+	if (pipe(pipefd)) {
+		fail("pipe failed: %s\n", strerror(errno));
+		return;
+	}
+
+	pid = fork();
+	if (pid < 0) {
+		fail("fork failed: %s\n", strerror(errno));
+		return;
+	}
+
+	if (pid == 0) {
+		func(fd, pipefd);
+		return;
+	}
+
+	mem = mmap(NULL, page_size, prot, mode, fd, 0);
+	if (mem == MAP_FAILED) {
+		fail("Unable to mmap secret memory\n");
+		return;
+	}
+
+	ftruncate(fd, page_size);
+	memset(mem, PATTERN, page_size);
+
+	if (write(pipefd[1], &mem, sizeof(mem)) < 0) {
+		fail("pipe write: %s\n", strerror(errno));
+		return;
+	}
+
+	check_child_status(pid, name);
+}
+
+static void test_process_vm_read(int fd)
+{
+	test_remote_access(fd, "process_vm_read", try_process_vm_read);
+}
+
+static void test_ptrace(int fd)
+{
+	test_remote_access(fd, "ptrace", try_ptrace);
+}
+
+static int set_cap_limits(rlim_t max)
+{
+	struct rlimit new;
+	cap_t cap = cap_init();
+
+	new.rlim_cur = max;
+	new.rlim_max = max;
+	if (setrlimit(RLIMIT_MEMLOCK, &new)) {
+		perror("setrlimit() returns error");
+		return -1;
+	}
+
+	/* drop capabilities including CAP_IPC_LOCK */
+	if (cap_set_proc(cap)) {
+		perror("cap_set_proc() returns error");
+		return -2;
+	}
+
+	return 0;
+}
+
+static void prepare(void)
+{
+	struct rlimit rlim;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+	if (!page_size)
+		ksft_exit_fail_msg("Failed to get page size %s\n",
+				   strerror(errno));
+
+	if (getrlimit(RLIMIT_MEMLOCK, &rlim))
+		ksft_exit_fail_msg("Unable to detect mlock limit: %s\n",
+				   strerror(errno));
+
+	mlock_limit_cur = rlim.rlim_cur;
+	mlock_limit_max = rlim.rlim_max;
+
+	printf("page_size: %ld, mlock.soft: %ld, mlock.hard: %ld\n",
+	       page_size, mlock_limit_cur, mlock_limit_max);
+
+	if (page_size > mlock_limit_cur)
+		mlock_limit_cur = page_size;
+	if (page_size > mlock_limit_max)
+		mlock_limit_max = page_size;
+
+	if (set_cap_limits(mlock_limit_max))
+		ksft_exit_fail_msg("Unable to set mlock limit: %s\n",
+				   strerror(errno));
+}
+
+#define NUM_TESTS 4
+
+int main(int argc, char *argv[])
+{
+	int fd;
+
+	prepare();
+
+	ksft_print_header();
+	ksft_set_plan(NUM_TESTS);
+
+	fd = memfd_secret(0);
+	if (fd < 0) {
+		if (errno == ENOSYS)
+			ksft_exit_skip("memfd_secret is not supported\n");
+		else
+			ksft_exit_fail_msg("memfd_secret failed: %s\n",
+					   strerror(errno));
+	}
+
+	test_mlock_limit(fd);
+	test_file_apis(fd);
+	test_process_vm_read(fd);
+	test_ptrace(fd);
+
+	close(fd);
+
+	ksft_exit(!ksft_get_fail_cnt());
+}
+
+#else /* __NR_memfd_secret */
+
+int main(int argc, char *argv[])
+{
+	printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_memfd_secret */