From: Mike Rapoport rppt@linux.ibm.com

It will be used by the upcoming secret memory implementation.

Signed-off-by: Mike Rapoport rppt@linux.ibm.com --- mm/internal.h | 3 +++ mm/mmap.c | 5 ++--- 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h index c43ccdddb0f6..ae146a260b14 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -348,6 +348,9 @@ 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., diff --git a/mm/mmap.c b/mm/mmap.c index 61f72b09d990..c481f088bd50 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1348,9 +1348,8 @@ 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;

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 where flags supplied as a parameter to this system call will define the desired protection mode for the memory associated with that file descriptor.

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.

Currently there are two protection modes:

* exclusive - the memory area is unmapped from the kernel direct map and it is present only in the page tables of the owning mm. * uncached - the memory area is present only in the page tables of the owning mm and it is mapped there as uncached.

The "exclusive" mode is enabled implicitly and it is the default mode for memfd_secret().

The "uncached" mode requires architecture support and an architecture should opt-in for this mode using HAVE_SECRETMEM_UNCACHED configuration option.

For instance, the following example will create an uncached mapping (error handling is omitted):

fd = memfd_secret(SECRETMEM_UNCACHED); 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/Kconfig | 7 + arch/x86/Kconfig | 1 + include/linux/secretmem.h | 24 +++ include/uapi/linux/magic.h | 1 + include/uapi/linux/secretmem.h | 8 + kernel/sys_ni.c | 2 + mm/Kconfig | 3 + mm/Makefile | 1 + mm/gup.c | 10 ++ mm/secretmem.c | 283 +++++++++++++++++++++++++++++++++ 10 files changed, 340 insertions(+) create mode 100644 include/linux/secretmem.h create mode 100644 include/uapi/linux/secretmem.h create mode 100644 mm/secretmem.c

diff --git a/arch/Kconfig b/arch/Kconfig index e175529bfb12..0b54b9d8a21f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1041,6 +1041,13 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config HAVE_ARCH_PFN_VALID bool

+config HAVE_SECRETMEM_UNCACHED + bool + help + An architecture can select this if its semantics of non-cached + mappings can be used to prevent speculative loads and it is + useful for secret protection. + source "kernel/gcov/Kconfig"

source "scripts/gcc-plugins/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 34d5fb82f674..907e24ae7698 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -224,6 +224,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO + select HAVE_SECRETMEM_UNCACHED select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING select NEED_SG_DMA_LENGTH 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/include/uapi/linux/secretmem.h b/include/uapi/linux/secretmem.h new file mode 100644 index 000000000000..7cf9492c70d2 --- /dev/null +++ b/include/uapi/linux/secretmem.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SECRETMEM_H +#define _UAPI_LINUX_SECRETMEM_H + +/* secretmem operation modes */ +#define SECRETMEM_UNCACHED 0x1 + +#endif /* _UAPI_LINUX_SECRETMEM_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..4be4c9ecac45 --- /dev/null +++ b/mm/secretmem.c @@ -0,0 +1,283 @@ +// 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/secretmem.h> +#include <uapi/linux/magic.h> + +#include <asm/tlbflush.h> + +#include "internal.h" + +#undef pr_fmt +#define pr_fmt(fmt) "secretmem: " fmt + +/* + * Secret memory areas are always exclusive to owning mm and they are + * removed from the direct map. + */ +#ifdef CONFIG_HAVE_SECRETMEM_UNCACHED +#define SECRETMEM_MODE_MASK (SECRETMEM_UNCACHED) +#else +#define SECRETMEM_MODE_MASK (0x0) +#endif + +#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) +{ + struct secretmem_ctx *ctx = file->private_data; + 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; + + if (ctx->mode & SECRETMEM_UNCACHED) + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + 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);

From: Mike Rapoport rppt@linux.ibm.com

Account memory consumed by secretmem to memcg. The accounting is updated when the memory is actually allocated and freed.

Signed-off-by: Mike Rapoport rppt@linux.ibm.com Acked-by: Roman Gushchin guro@fb.com --- mm/filemap.c | 3 ++- mm/secretmem.c | 36 +++++++++++++++++++++++++++++++++++- 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c index 249cf489f5df..cf7f1dc9f4b8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -42,6 +42,7 @@ #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> +#include <linux/secretmem.h> #include "internal.h"

#define CREATE_TRACE_POINTS @@ -844,7 +845,7 @@ static noinline int __add_to_page_cache_locked(struct page *page, page->mapping = mapping; page->index = offset;

- if (!huge) { + if (!huge && !page_is_secretmem(page)) { error = mem_cgroup_charge(page, current->mm, gfp); if (error) goto error; diff --git a/mm/secretmem.c b/mm/secretmem.c index d4c44fc568a4..abf6ecdf70cb 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -18,6 +18,7 @@ #include <linux/memblock.h> #include <linux/pseudo_fs.h> #include <linux/secretmem.h> +#include <linux/memcontrol.h> #include <linux/set_memory.h> #include <linux/sched/signal.h>

@@ -50,6 +51,32 @@ struct secretmem_ctx {

static struct cma *secretmem_cma;

+static int secretmem_account_pages(struct page *page, gfp_t gfp, int order) +{ + int err; + + err = memcg_kmem_charge_page(page, gfp, order); + if (err) + return err; + + /* + * seceremem caches are unreclaimable kernel allocations, so treat + * them as unreclaimable slab memory for VM statistics purposes + */ + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B, + PAGE_SIZE << order); + + return 0; +} + +static void secretmem_unaccount_pages(struct page *page, int order) +{ + + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B, + -PAGE_SIZE << order); + memcg_kmem_uncharge_page(page, order); +} + static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp) { unsigned long nr_pages = (1 << PMD_PAGE_ORDER); @@ -62,10 +89,14 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp) if (!page) return -ENOMEM;

- err = set_direct_map_invalid_noflush(page, nr_pages); + err = secretmem_account_pages(page, gfp, PMD_PAGE_ORDER); if (err) goto err_cma_release;

+ err = set_direct_map_invalid_noflush(page, nr_pages); + if (err) + goto err_memcg_uncharge; + addr = (unsigned long)page_address(page); err = gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE); if (err) @@ -82,6 +113,8 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp) * won't fail */ set_direct_map_default_noflush(page, nr_pages); +err_memcg_uncharge: + secretmem_unaccount_pages(page, PMD_PAGE_ORDER); err_cma_release: cma_release(secretmem_cma, page, nr_pages); return err; @@ -312,6 +345,7 @@ static void secretmem_cleanup_chunk(struct gen_pool *pool, int i;

set_direct_map_default_noflush(page, nr_pages); + secretmem_unaccount_pages(page, PMD_PAGE_ORDER);

for (i = 0; i < nr_pages; i++) clear_highpage(page + i);

From: Mike Rapoport rppt@linux.ibm.com

Wire up memfd_secret system call on architectures that define ARCH_HAS_SET_DIRECT_MAP, namely arm64, risc-v and x86.

Signed-off-by: Mike Rapoport rppt@linux.ibm.com Acked-by: Palmer Dabbelt palmerdabbelt@google.com Acked-by: Arnd Bergmann arnd@arndb.de --- arch/arm64/include/uapi/asm/unistd.h | 1 + arch/riscv/include/asm/unistd.h | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 6 +++++- scripts/checksyscalls.sh | 4 ++++ 7 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h index f83a70e07df8..ce2ee8f1e361 100644 --- a/arch/arm64/include/uapi/asm/unistd.h +++ b/arch/arm64/include/uapi/asm/unistd.h @@ -20,5 +20,6 @@ #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS #define __ARCH_WANT_SYS_CLONE3 +#define __ARCH_WANT_MEMFD_SECRET

#include <asm-generic/unistd.h> diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h index 977ee6181dab..6c316093a1e5 100644 --- a/arch/riscv/include/asm/unistd.h +++ b/arch/riscv/include/asm/unistd.h @@ -9,6 +9,7 @@ */

#define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_MEMFD_SECRET

#include <uapi/asm/unistd.h>

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c52ab1c4a755..109e6681b8fa 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -446,3 +446,4 @@ 439 i386 faccessat2 sys_faccessat2 440 i386 process_madvise sys_process_madvise 441 i386 watch_mount sys_watch_mount +442 i386 memfd_secret sys_memfd_secret diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f3270a9ef467..742cf17d7725 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -363,6 +363,7 @@ 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise 441 common watch_mount sys_watch_mount +442 common memfd_secret sys_memfd_secret

# # Due to a historical design error, certain syscalls are numbered differently diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 6d55324363ab..f9d93fbf9b69 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1010,6 +1010,7 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig, asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags); asmlinkage long sys_watch_mount(int dfd, const char __user *path, unsigned int at_flags, int watch_fd, int watch_id); +asmlinkage long sys_memfd_secret(unsigned long flags);

/* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 5df46517260e..51151888f330 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -861,9 +861,13 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_watch_mount 441 __SYSCALL(__NR_watch_mount, sys_watch_mount) +#ifdef __ARCH_WANT_MEMFD_SECRET +#define __NR_memfd_secret 442 +__SYSCALL(__NR_memfd_secret, sys_memfd_secret) +#endif

#undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 443

/* * 32 bit systems traditionally used different diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh index a18b47695f55..b7609958ee36 100755 --- a/scripts/checksyscalls.sh +++ b/scripts/checksyscalls.sh @@ -40,6 +40,10 @@ cat << EOF #define __IGNORE_setrlimit /* setrlimit */ #endif

+#ifndef __ARCH_WANT_MEMFD_SECRET +#define __IGNORE_memfd_secret +#endif + /* Missing flags argument */ #define __IGNORE_renameat /* renameat2 */

From: Mike Rapoport rppt@linux.ibm.com

The test verifies that file descriptor created with memfd_secret does not allow read/write operations, that secret memory mappings respect RLIMIT_MEMLOCK and that remote accesses with process_vm_read() and ptrace() to the secret memory fail.

Signed-off-by: Mike Rapoport rppt@linux.ibm.com --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 3 +- tools/testing/selftests/vm/memfd_secret.c | 298 ++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests | 17 ++ 4 files changed, 318 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/vm/memfd_secret.c

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 9a35c3f6a557..c8deddc81e7a 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -21,4 +21,5 @@ va_128TBswitch map_fixed_noreplace write_to_hugetlbfs hmm-tests +memfd_secret local_config.* diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 62fb15f286ee..9ab98946fbf2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -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 @@ -129,7 +130,7 @@ 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

diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c new file mode 100644 index 000000000000..79578dfd13e6 --- /dev/null +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -0,0 +1,298 @@ +// 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 + +#include <linux/secretmem.h> + +#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 */ diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index e953f3cd9664..95a67382f132 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -346,4 +346,21 @@ else exitcode=1 fi

+echo "running memfd_secret test" +echo "------------------------------------" +./memfd_secret +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else + echo "[FAIL]" + exitcode=1 +fi + +exit $exitcode + exit $exitcode