diff mbox series

[v11,4/9] mm: introduce memfd_secret system call to create "secret" memory areas

Message ID 20201124092556.12009-5-rppt@kernel.org (mailing list archive)
State New, archived
Headers show
Series mm: introduce memfd_secret system call to create "secret" memory areas | expand

Commit Message

Mike Rapoport Nov. 24, 2020, 9:25 a.m. UTC
From: Mike Rapoport <rppt@linux.ibm.com>

Introduce "memfd_secret" system call with the ability to create memory
areas visible only in the context of the owning process and not mapped not
only to other processes but in the kernel page tables as well.

The user will create a file descriptor using the memfd_secret() system
call. The memory areas created by mmap() calls from this file descriptor
will be unmapped from the kernel direct map and they will be only mapped in
the page table of the owning mm.

The secret memory remains accessible in the process context using uaccess
primitives, but it is not accessible using direct/linear map addresses.

Functions in the follow_page()/get_user_page() family will refuse to return
a page that belongs to the secret memory area.

A page that was a part of the secret memory area is cleared when it is
freed.

The following example demonstrates creation of a secret mapping (error
handling is omitted):

	fd = memfd_secret(0);
	ftruncate(fd, MAP_SIZE);
	ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Hagen Paul Pfeifer <hagen@jauu.net>
---
 arch/x86/Kconfig           |   2 +-
 include/linux/secretmem.h  |  24 ++++
 include/uapi/linux/magic.h |   1 +
 kernel/sys_ni.c            |   2 +
 mm/Kconfig                 |   3 +
 mm/Makefile                |   1 +
 mm/gup.c                   |  10 ++
 mm/secretmem.c             | 273 +++++++++++++++++++++++++++++++++++++
 8 files changed, 315 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/secretmem.h
 create mode 100644 mm/secretmem.c

Comments

Catalin Marinas Nov. 24, 2020, 10:59 a.m. UTC | #1
Hi Mike,

On Tue, Nov 24, 2020 at 11:25:51AM +0200, Mike Rapoport wrote:
> +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;
> +	vm_fault_t ret = 0;
> +	unsigned long addr;
> +	struct page *page;
> +	int err;
> +
> +	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
> +		return vmf_error(-EINVAL);
> +
> +	page = find_get_page(mapping, offset);
> +	if (!page) {
> +
> +		page = secretmem_alloc_page(vmf->gfp_mask);
> +		if (!page)
> +			return vmf_error(-ENOMEM);
> +
> +		err = add_to_page_cache(page, mapping, offset, vmf->gfp_mask);
> +		if (unlikely(err))
> +			goto err_put_page;
> +
> +		err = set_direct_map_invalid_noflush(page, 1);
> +		if (err)
> +			goto err_del_page_cache;

On arm64, set_direct_map_default_noflush() returns 0 if !rodata_full but
no pgtable changes happen since the linear map can be a mix of small and
huge pages. The arm64 implementation doesn't break large mappings. I
presume we don't want to tell the user that the designated memory is
"secret" but the kernel silently ignored it.

We could change the arm64 set_direct_map* to return an error, however, I
think it would be pretty unexpected for the user to get a fault when
trying to access it. It may be better to return a -ENOSYS or something
on the actual syscall if the fault-in wouldn't be allowed later.

Alternatively, we could make the linear map always use pages on arm64,
irrespective of other config or cmdline options (maybe not justified
unless we have clear memsecret users). Yet another idea is to get
set_direct_map* to break pmd/pud mappings into pte but that's not always
possible without a stop_machine() and potentially disabling the MMU.

> +
> +		addr = (unsigned long)page_address(page);
> +		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> +
> +		__SetPageUptodate(page);
> +
> +		ret = VM_FAULT_LOCKED;
> +	}
> +
> +	vmf->page = page;
> +	return ret;
> +
> +err_del_page_cache:
> +	delete_from_page_cache(page);
> +err_put_page:
> +	put_page(page);
> +	return vmf_error(err);
> +}
Mike Rapoport Nov. 24, 2020, 4:49 p.m. UTC | #2
On Tue, Nov 24, 2020 at 10:59:48AM +0000, Catalin Marinas wrote:
> Hi Mike,
> 
> On Tue, Nov 24, 2020 at 11:25:51AM +0200, Mike Rapoport wrote:
> > +static vm_fault_t secretmem_fault(struct vm_fault *vmf)
> > +{
> > +	struct address_space *mapping = vmf->vma->vm_file->f_mapping;

...

> > +
> > +		err = set_direct_map_invalid_noflush(page, 1);
> > +		if (err)
> > +			goto err_del_page_cache;
> 
> On arm64, set_direct_map_default_noflush() returns 0 if !rodata_full but
> no pgtable changes happen since the linear map can be a mix of small and
> huge pages. The arm64 implementation doesn't break large mappings. I
> presume we don't want to tell the user that the designated memory is
> "secret" but the kernel silently ignored it.
> 
> We could change the arm64 set_direct_map* to return an error, however, I
> think it would be pretty unexpected for the user to get a fault when
> trying to access it. It may be better to return a -ENOSYS or something
> on the actual syscall if the fault-in wouldn't be allowed later.
> 
> Alternatively, we could make the linear map always use pages on arm64,
> irrespective of other config or cmdline options (maybe not justified
> unless we have clear memsecret users). Yet another idea is to get
> set_direct_map* to break pmd/pud mappings into pte but that's not always
> possible without a stop_machine() and potentially disabling the MMU.

My preference would be to check at secretmem initialization if
set_direct_map_*() actually do anything and then return an error from
the syscall if they are essentially nop.

I'll update the patches with something like this in v12.

> -- 
> Catalin
diff mbox series

Patch

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 34d5fb82f674..7d781fea79c2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -41,7 +41,7 @@  config FORCE_DYNAMIC_FTRACE
 	 in order to test the non static function tracing in the
 	 generic code, as other architectures still use it. But we
 	 only need to keep it around for x86_64. No need to keep it
-	 for x86_32. For x86_32, force DYNAMIC_FTRACE. 
+	 for x86_32. For x86_32, force DYNAMIC_FTRACE.
 #
 # Arch settings
 #
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
new file mode 100644
index 000000000000..70e7db9f94fe
--- /dev/null
+++ b/include/linux/secretmem.h
@@ -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 */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index f3956fc11de6..35687dcb1a42 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.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__ */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 2dd6cbb8cabc..805fd7a668be 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -353,6 +353,8 @@  COND_SYSCALL(pkey_mprotect);
 COND_SYSCALL(pkey_alloc);
 COND_SYSCALL(pkey_free);
 
+/* memfd_secret */
+COND_SYSCALL(memfd_secret);
 
 /*
  * Architecture specific weak syscall entries.
diff --git a/mm/Kconfig b/mm/Kconfig
index c89c5444924b..d8d170fa5210 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -884,4 +884,7 @@  config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config SECRETMEM
+	def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 6eeb4b29efb8..dfda14c48a75 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -121,3 +121,4 @@  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
diff --git a/mm/gup.c b/mm/gup.c
index 5ec98de1e5de..71164fa83114 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -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>
@@ -793,6 +794,9 @@  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);
@@ -923,6 +927,9 @@  static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
 		return -EFAULT;
 
+	if (vma_is_secretmem(vma))
+		return -EFAULT;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
@@ -2196,6 +2203,9 @@  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;
diff --git a/mm/secretmem.c b/mm/secretmem.c
new file mode 100644
index 000000000000..781aaaca8c70
--- /dev/null
+++ b/mm/secretmem.c
@@ -0,0 +1,273 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2020
+ *
+ * Author: Mike Rapoport <rppt@linux.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/fs.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
+
+struct secretmem_ctx {
+	unsigned int mode;
+};
+
+static struct page *secretmem_alloc_page(gfp_t gfp)
+{
+	/*
+	 * FIXME: use a cache of large pages to reduce the direct map
+	 * fragmentation
+	 */
+	return alloc_page(gfp);
+}
+
+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;
+	vm_fault_t ret = 0;
+	unsigned long addr;
+	struct page *page;
+	int err;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return vmf_error(-EINVAL);
+
+	page = find_get_page(mapping, offset);
+	if (!page) {
+
+		page = secretmem_alloc_page(vmf->gfp_mask);
+		if (!page)
+			return vmf_error(-ENOMEM);
+
+		err = add_to_page_cache(page, mapping, offset, vmf->gfp_mask);
+		if (unlikely(err))
+			goto err_put_page;
+
+		err = set_direct_map_invalid_noflush(page, 1);
+		if (err)
+			goto err_del_page_cache;
+
+		addr = (unsigned long)page_address(page);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+		__SetPageUptodate(page);
+
+		ret = VM_FAULT_LOCKED;
+	}
+
+	vmf->page = page;
+	return ret;
+
+err_del_page_cache:
+	delete_from_page_cache(page);
+err_put_page:
+	put_page(page);
+	return vmf_error(err);
+}
+
+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_ops = &secretmem_vm_ops;
+	vma->vm_flags |= VM_LOCKED;
+
+	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 secretmem_ctx *ctx;
+	struct inode *inode;
+
+	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		goto err_free_inode;
+
+	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
+				 O_RDWR, &secretmem_fops);
+	if (IS_ERR(file))
+		goto err_free_ctx;
+
+	mapping_set_unevictable(inode->i_mapping);
+
+	inode->i_mapping->private_data = ctx;
+	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;
+
+	file->private_data = ctx;
+
+	ctx->mode = flags & SECRETMEM_MODE_MASK;
+
+	return file;
+
+err_free_ctx:
+	kfree(ctx);
+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 (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 void secretmem_evict_inode(struct inode *inode)
+{
+	struct secretmem_ctx *ctx = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kfree(ctx);
+}
+
+static const struct super_operations secretmem_super_ops = {
+	.evict_inode = secretmem_evict_inode,
+};
+
+static int secretmem_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx = init_pseudo(fc, SECRETMEM_MAGIC);
+
+	if (!ctx)
+		return -ENOMEM;
+	ctx->ops = &secretmem_super_ops;
+
+	return 0;
+}
+
+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;
+
+	secretmem_mnt = kern_mount(&secretmem_fs);
+	if (IS_ERR(secretmem_mnt))
+		ret = PTR_ERR(secretmem_mnt);
+
+	return ret;
+}
+fs_initcall(secretmem_init);