From: Mike Rapoport <rppt@xxxxxxxxxxxxx>
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 secretmem feature is off by default and the user must explicitly enable
it at the boot time.
Once secretmem is enabled, the user will be able to 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 file descriptor based memory has several advantages over the
"traditional" mm interfaces, such as mlock(), mprotect(), madvise(). It
paves the way for VMMs to remove the secret memory range from the process;
there may be situations where sharing is useful and file descriptor based
approach allows to seal the operations.
As secret memory implementation is not an extension of tmpfs or hugetlbfs,
usage of a dedicated system call rather than hooking new functionality into
memfd_create(2) emphasises that memfd_secret(2) has different semantics and
allows better upwards compatibility.
The secret memory remains accessible in the process context using uaccess
primitives, but it is not exposed to the kernel otherwise; secret memory
areas are removed from the direct map and functions in the
follow_page()/get_user_page() family will refuse to return a page that
belongs to the secret memory area.
Once there will be a use case that will require exposing secretmem to the
kernel it will be an opt-in request in the system call flags so that user
would have to decide what data can be exposed to the kernel.
Removing of the pages from the direct map may cause its fragmentation on
architectures that use large pages to map the physical memory which affects
the system performance. However, the original Kconfig text for
CONFIG_DIRECT_GBPAGES said that gigabyte pages in the direct map "... can
improve the kernel's performance a tiny bit ..." (commit 00d1c5e05736
("x86: add gbpages switches")) and the recent report [1] showed that "...
although 1G mappings are a good default choice, there is no compelling
evidence that it must be the only choice". Hence, it is sufficient to have
secretmem disabled by default with the ability of a system administrator to
enable it at boot time.
The secretmem mappings are locked in memory so they cannot exceed
RLIMIT_MEMLOCK. Since these mappings are already locked an attempt to
mlock() secretmem range would fail and mlockall() will ignore secretmem
mappings.
Pages in the secretmem regions are unevictable and unmovable to avoid
accidental exposure of the sensitive data via swap or during page
migration.
A page that was a part of the secret memory area is cleared when it is
freed to ensure the data is not exposed to the next user of that page.
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);
[1] https://lore.kernel.org/linux-mm/213b4567-46ce-f116-9cdf-bbd0c884eb3c@xxxxxxxxxxxxxxx/
Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Acked-by: Hagen Paul Pfeifer <hagen@xxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christopher Lameter <cl@xxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Elena Reshetova <elena.reshetova@xxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: James Bottomley <jejb@xxxxxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx>
Cc: Palmer Dabbelt <palmerdabbelt@xxxxxxxxxx>
Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tycho Andersen <tycho@xxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
---
---
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/mlock.c | 3 +-
mm/secretmem.c | 246 +++++++++++++++++++++++++++++++++++++
8 files changed, 289 insertions(+), 1 deletion(-)
create mode 100644 include/linux/secretmem.h
create mode 100644 mm/secretmem.c
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 19aa806890d5..e9a2011ee4a2 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -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.
diff --git a/mm/Kconfig b/mm/Kconfig
index 24c045b24b95..5f8243442f66 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -872,4 +872,7 @@ config MAPPING_DIRTY_HELPERS
config KMAP_LOCAL
bool
+config SECRETMEM
+ def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 72227b24a616..b2a564eec27f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -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
diff --git a/mm/gup.c b/mm/gup.c
index e4c224cd9661..3e086b073624 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>
@@ -759,6 +760,9 @@ 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);
@@ -892,6 +896,9 @@ 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))
@@ -2031,6 +2038,9 @@ 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/mlock.c b/mm/mlock.c
index 73960bb3464d..127e72dcac3d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -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;
diff --git a/mm/secretmem.c b/mm/secretmem.c
new file mode 100644
index 000000000000..fa6738e860c2
--- /dev/null
+++ b/mm/secretmem.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2021
+ *
+ * Author: Mike Rapoport <rppt@xxxxxxxxxxxxx>
+ */
+
+#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);
--
2.28.0
