* [PATCH v9 1/5] mseal: Wire up mseal syscall
2024-02-14 15:11 [PATCH v9 0/5] Introduce mseal jeffxu
@ 2024-02-14 15:11 ` jeffxu
2024-02-14 15:11 ` [PATCH v9 2/5] mseal: add " jeffxu
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: jeffxu @ 2024-02-14 15:11 UTC (permalink / raw)
To: akpm, keescook, jannh, sroettger, willy, gregkh, torvalds,
usama.anjum, corbet, Liam.Howlett, surenb, merimus, rdunlap
Cc: jeffxu, jorgelo, groeck, linux-kernel, linux-kselftest, linux-mm,
pedro.falcato, dave.hansen, linux-hardening, deraadt,
=David.Laight, Jeff Xu
From: Jeff Xu <jeffxu@chromium.org>
Wire up mseal syscall for all architectures.
Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/arm64/include/asm/unistd.h | 2 +-
arch/arm64/include/asm/unistd32.h | 2 ++
arch/m68k/kernel/syscalls/syscall.tbl | 1 +
arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n32.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n64.tbl | 1 +
arch/mips/kernel/syscalls/syscall_o32.tbl | 1 +
arch/parisc/kernel/syscalls/syscall.tbl | 1 +
arch/powerpc/kernel/syscalls/syscall.tbl | 1 +
arch/s390/kernel/syscalls/syscall.tbl | 1 +
arch/sh/kernel/syscalls/syscall.tbl | 1 +
arch/sparc/kernel/syscalls/syscall.tbl | 1 +
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/xtensa/kernel/syscalls/syscall.tbl | 1 +
include/uapi/asm-generic/unistd.h | 5 ++++-
kernel/sys_ni.c | 1 +
19 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 8ff110826ce2..d8f96362e9f8 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -501,3 +501,4 @@
569 common lsm_get_self_attr sys_lsm_get_self_attr
570 common lsm_set_self_attr sys_lsm_set_self_attr
571 common lsm_list_modules sys_lsm_list_modules
+572 common mseal sys_mseal
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index b6c9e01e14f5..2ed7d229c8f9 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -475,3 +475,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 491b2b9bd553..1346579f802f 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 462
+#define __NR_compat_syscalls 463
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 7118282d1c79..266b96acc014 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -929,6 +929,8 @@ __SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
#define __NR_lsm_list_modules 461
__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+#define __NR_mseal 462
+__SYSCALL(__NR_mseal, sys_mseal)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7fd43fd4c9f2..22a3cbd4c602 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -461,3 +461,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index b00ab2cabab9..2b81a6bd78b2 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -467,3 +467,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 83cfc9eb6b88..cc869f5d5693 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -400,3 +400,4 @@
459 n32 lsm_get_self_attr sys_lsm_get_self_attr
460 n32 lsm_set_self_attr sys_lsm_set_self_attr
461 n32 lsm_list_modules sys_lsm_list_modules
+462 n32 mseal sys_mseal
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 532b855df589..1464c6be6eb3 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -376,3 +376,4 @@
459 n64 lsm_get_self_attr sys_lsm_get_self_attr
460 n64 lsm_set_self_attr sys_lsm_set_self_attr
461 n64 lsm_list_modules sys_lsm_list_modules
+462 n64 mseal sys_mseal
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index f45c9530ea93..008ebe60263e 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -449,3 +449,4 @@
459 o32 lsm_get_self_attr sys_lsm_get_self_attr
460 o32 lsm_set_self_attr sys_lsm_set_self_attr
461 o32 lsm_list_modules sys_lsm_list_modules
+462 o32 mseal sys_mseal
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b236a84c4e12..b13c21373974 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -460,3 +460,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 17173b82ca21..3656f1ca7a21 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -548,3 +548,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 095bb86339a7..bd0fee24ad10 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -464,3 +464,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal sys_mseal
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 86fe269f0220..bbf83a2db986 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -464,3 +464,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b23d59313589..ac6c281ccfe0 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -507,3 +507,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 5f8591ce7f25..7fd1f57ad3d3 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -466,3 +466,4 @@
459 i386 lsm_get_self_attr sys_lsm_get_self_attr
460 i386 lsm_set_self_attr sys_lsm_set_self_attr
461 i386 lsm_list_modules sys_lsm_list_modules
+462 i386 mseal sys_mseal
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 7e8d46f4147f..52df0dec70da 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -383,6 +383,7 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index dd116598fb25..67083fc1b2f5 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -432,3 +432,4 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 75f00965ab15..d983c48a3b6a 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
#define __NR_lsm_list_modules 461
__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+#define __NR_mseal 462
+__SYSCALL(__NR_mseal, sys_mseal)
+
#undef __NR_syscalls
-#define __NR_syscalls 462
+#define __NR_syscalls 463
/*
* 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index faad00cce269..d7eee421d4bc 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -196,6 +196,7 @@ COND_SYSCALL(migrate_pages);
COND_SYSCALL(move_pages);
COND_SYSCALL(set_mempolicy_home_node);
COND_SYSCALL(cachestat);
+COND_SYSCALL(mseal);
COND_SYSCALL(perf_event_open);
COND_SYSCALL(accept4);
--
2.43.0.687.g38aa6559b0-goog
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v9 2/5] mseal: add mseal syscall
2024-02-14 15:11 [PATCH v9 0/5] Introduce mseal jeffxu
2024-02-14 15:11 ` [PATCH v9 1/5] mseal: Wire up mseal syscall jeffxu
@ 2024-02-14 15:11 ` jeffxu
2024-02-14 15:11 ` [PATCH v9 3/5] selftest mm/mseal memory sealing jeffxu
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: jeffxu @ 2024-02-14 15:11 UTC (permalink / raw)
To: akpm, keescook, jannh, sroettger, willy, gregkh, torvalds,
usama.anjum, corbet, Liam.Howlett, surenb, merimus, rdunlap
Cc: jeffxu, jorgelo, groeck, linux-kernel, linux-kselftest, linux-mm,
pedro.falcato, dave.hansen, linux-hardening, deraadt,
=David.Laight, Jeff Xu
From: Jeff Xu <jeffxu@chromium.org>
The new mseal() is an syscall on 64 bit CPU, and with
following signature:
int mseal(void addr, size_t len, unsigned long flags)
addr/len: memory range.
flags: reserved.
mseal() blocks following operations for the given memory range.
1> Unmapping, moving to another location, and shrinking the size,
via munmap() and mremap(), can leave an empty space, therefore can
be replaced with a VMA with a new set of attributes.
2> Moving or expanding a different VMA into the current location,
via mremap().
3> Modifying a VMA via mmap(MAP_FIXED).
4> Size expansion, via mremap(), does not appear to pose any specific
risks to sealed VMAs. It is included anyway because the use case is
unclear. In any case, users can rely on merging to expand a sealed VMA.
5> mprotect() and pkey_mprotect().
6> Some destructive madvice() behaviors (e.g. MADV_DONTNEED) for anonymous
memory, when users don't have write permission to the memory. Those
behaviors can alter region contents by discarding pages, effectively a
memset(0) for anonymous memory.
Following input during RFC are incooperated into this patch:
Jann Horn: raising awareness and providing valuable insights on the
destructive madvise operations.
Linus Torvalds: assisting in defining system call signature and scope.
Liam R. Howlett: perf optimization.
Theo de Raadt: sharing the experiences and insight gained from
implementing mimmutable() in OpenBSD.
Finally, the idea that inspired this patch comes from Stephen Röttger’s
work in Chrome V8 CFI.
Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
include/linux/syscalls.h | 1 +
mm/Makefile | 4 +
mm/internal.h | 37 +++++
mm/madvise.c | 12 ++
mm/mmap.c | 31 +++-
mm/mprotect.c | 10 ++
mm/mremap.c | 31 ++++
mm/mseal.c | 307 +++++++++++++++++++++++++++++++++++++++
8 files changed, 432 insertions(+), 1 deletion(-)
create mode 100644 mm/mseal.c
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 77eb9b0e7685..abdf93951405 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -821,6 +821,7 @@ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags);
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,
unsigned long flags);
+asmlinkage long sys_mseal(unsigned long start, size_t len, unsigned long flags);
asmlinkage long sys_mbind(unsigned long start, unsigned long len,
unsigned long mode,
const unsigned long __user *nmask,
diff --git a/mm/Makefile b/mm/Makefile
index e4b5b75aaec9..cbae83f74642 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -43,6 +43,10 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH
mmu-$(CONFIG_MMU) += process_vm_access.o
endif
+ifdef CONFIG_64BIT
+mmu-$(CONFIG_MMU) += mseal.o
+endif
+
obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
maccess.o page-writeback.o folio-compat.o \
readahead.o swap.o truncate.o vmscan.o shrinker.o \
diff --git a/mm/internal.h b/mm/internal.h
index f309a010d50f..ca42acee3a3f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1221,6 +1221,43 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn,
unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
int priority);
+#ifdef CONFIG_64BIT
+/* VM is sealed, in vm_flags */
+#define VM_SEALED _BITUL(63)
+#endif
+
+#ifdef CONFIG_64BIT
+static inline int can_do_mseal(unsigned long flags)
+{
+ if (flags)
+ return -EINVAL;
+
+ return 0;
+}
+
+bool can_modify_mm(struct mm_struct *mm, unsigned long start,
+ unsigned long end);
+bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
+ unsigned long end, int behavior);
+#else
+static inline int can_do_mseal(unsigned long flags)
+{
+ return -EPERM;
+}
+
+static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start,
+ unsigned long end)
+{
+ return true;
+}
+
+static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
+ unsigned long end, int behavior)
+{
+ return true;
+}
+#endif
+
#ifdef CONFIG_SHRINKER_DEBUG
static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
struct shrinker *shrinker, const char *fmt, va_list ap)
diff --git a/mm/madvise.c b/mm/madvise.c
index cfa5e7288261..8cd916a9ee1d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1394,6 +1394,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
* -EIO - an I/O error occurred while paging in data.
* -EBADF - map exists, but area maps something that isn't a file.
* -EAGAIN - a kernel resource was temporarily unavailable.
+ * -EPERM - memory is sealed.
*/
int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
{
@@ -1437,10 +1438,21 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh
start = untagged_addr_remote(mm, start);
end = start + len;
+ /*
+ * Check if the address range is sealed for do_madvise().
+ * can_modify_mm_madv assumes we have acquired the lock on MM.
+ */
+ if (!can_modify_mm_madv(mm, start, end, behavior)) {
+ error = -EPERM;
+ goto out;
+ }
+
blk_start_plug(&plug);
error = madvise_walk_vmas(mm, start, end, behavior,
madvise_vma_behavior);
blk_finish_plug(&plug);
+
+out:
if (write)
mmap_write_unlock(mm);
else
diff --git a/mm/mmap.c b/mm/mmap.c
index d89770eaab6b..d495fac95550 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1261,6 +1261,16 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
return -EEXIST;
}
+ /*
+ * addr is returned from get_unmapped_area,
+ * There are two cases:
+ * 1> MAP_FIXED == false
+ * unallocated memory, no need to check sealing.
+ * 1> MAP_FIXED == true
+ * sealing is checked inside mmap_region when
+ * do_vmi_munmap is called.
+ */
+
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(mm);
if (pkey < 0)
@@ -2681,6 +2691,14 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
if (end == start)
return -EINVAL;
+ /*
+ * Check if memory is sealed before arch_unmap.
+ * Prevent unmapping a sealed VMA.
+ * can_modify_mm assumes we have acquired the lock on MM.
+ */
+ if (!can_modify_mm(mm, start, end))
+ return -EPERM;
+
/* arch_unmap() might do unmaps itself. */
arch_unmap(mm, start, end);
@@ -2743,7 +2761,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
}
/* Unmap any existing mapping in the area */
- if (do_vmi_munmap(&vmi, mm, addr, len, uf, false))
+ error = do_vmi_munmap(&vmi, mm, addr, len, uf, false);
+ if (error == -EPERM)
+ return error;
+ else if (error)
return -ENOMEM;
/*
@@ -3104,6 +3125,14 @@ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
{
struct mm_struct *mm = vma->vm_mm;
+ /*
+ * Check if memory is sealed before arch_unmap.
+ * Prevent unmapping a sealed VMA.
+ * can_modify_mm assumes we have acquired the lock on MM.
+ */
+ if (!can_modify_mm(mm, start, end))
+ return -EPERM;
+
arch_unmap(mm, start, end);
return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock);
}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 81991102f785..5f0f716bf4ae 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -32,6 +32,7 @@
#include <linux/sched/sysctl.h>
#include <linux/userfaultfd_k.h>
#include <linux/memory-tiers.h>
+#include <uapi/linux/mman.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -743,6 +744,15 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
}
}
+ /*
+ * checking if memory is sealed.
+ * can_modify_mm assumes we have acquired the lock on MM.
+ */
+ if (!can_modify_mm(current->mm, start, end)) {
+ error = -EPERM;
+ goto out;
+ }
+
prev = vma_prev(&vmi);
if (start > vma->vm_start)
prev = vma;
diff --git a/mm/mremap.c b/mm/mremap.c
index 38d98465f3d8..d69b438dcf83 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -902,7 +902,25 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
if ((mm->map_count + 2) >= sysctl_max_map_count - 3)
return -ENOMEM;
+ /*
+ * In mremap_to().
+ * Move a VMA to another location, check if src addr is sealed.
+ *
+ * Place can_modify_mm here because mremap_to()
+ * does its own checking for address range, and we only
+ * check the sealing after passing those checks.
+ *
+ * can_modify_mm assumes we have acquired the lock on MM.
+ */
+ if (!can_modify_mm(mm, addr, addr + old_len))
+ return -EPERM;
+
if (flags & MREMAP_FIXED) {
+ /*
+ * In mremap_to().
+ * VMA is moved to dst address, and munmap dst first.
+ * do_munmap will check if dst is sealed.
+ */
ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
if (ret)
goto out;
@@ -1061,6 +1079,19 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
goto out;
}
+ /*
+ * Below is shrink/expand case (not mremap_to())
+ * Check if src address is sealed, if so, reject.
+ * In other words, prevent shrinking or expanding a sealed VMA.
+ *
+ * Place can_modify_mm here so we can keep the logic related to
+ * shrink/expand together.
+ */
+ if (!can_modify_mm(mm, addr, addr + old_len)) {
+ ret = -EPERM;
+ goto out;
+ }
+
/*
* Always allow a shrinking remap: that just unmaps
* the unnecessary pages..
diff --git a/mm/mseal.c b/mm/mseal.c
new file mode 100644
index 000000000000..daadac4b8125
--- /dev/null
+++ b/mm/mseal.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implement mseal() syscall.
+ *
+ * Copyright (c) 2023,2024 Google, Inc.
+ *
+ * Author: Jeff Xu <jeffxu@chromium.org>
+ */
+
+#include <linux/mempolicy.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/mm_inline.h>
+#include <linux/mmu_context.h>
+#include <linux/syscalls.h>
+#include <linux/sched.h>
+#include "internal.h"
+
+static inline bool vma_is_sealed(struct vm_area_struct *vma)
+{
+ return (vma->vm_flags & VM_SEALED);
+}
+
+static inline void set_vma_sealed(struct vm_area_struct *vma)
+{
+ vm_flags_set(vma, VM_SEALED);
+}
+
+/*
+ * check if a vma is sealed for modification.
+ * return true, if modification is allowed.
+ */
+static bool can_modify_vma(struct vm_area_struct *vma)
+{
+ if (vma_is_sealed(vma))
+ return false;
+
+ return true;
+}
+
+static bool is_madv_discard(int behavior)
+{
+ return behavior &
+ (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED |
+ MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK);
+}
+
+static bool is_ro_anon(struct vm_area_struct *vma)
+{
+ /* check anonymous mapping. */
+ if (vma->vm_file || vma->vm_flags & VM_SHARED)
+ return false;
+
+ /*
+ * check for non-writable:
+ * PROT=RO or PKRU is not writeable.
+ */
+ if (!(vma->vm_flags & VM_WRITE) ||
+ !arch_vma_access_permitted(vma, true, false, false))
+ return true;
+
+ return false;
+}
+
+/*
+ * Check if the vmas of a memory range are allowed to be modified.
+ * the memory ranger can have a gap (unallocated memory).
+ * return true, if it is allowed.
+ */
+bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+ struct vm_area_struct *vma;
+
+ VMA_ITERATOR(vmi, mm, start);
+
+ /* going through each vma to check. */
+ for_each_vma_range(vmi, vma, end) {
+ if (!can_modify_vma(vma))
+ return false;
+ }
+
+ /* Allow by default. */
+ return true;
+}
+
+/*
+ * Check if the vmas of a memory range are allowed to be modified by madvise.
+ * the memory ranger can have a gap (unallocated memory).
+ * return true, if it is allowed.
+ */
+bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end,
+ int behavior)
+{
+ struct vm_area_struct *vma;
+
+ VMA_ITERATOR(vmi, mm, start);
+
+ if (!is_madv_discard(behavior))
+ return true;
+
+ /* going through each vma to check. */
+ for_each_vma_range(vmi, vma, end)
+ if (is_ro_anon(vma) && !can_modify_vma(vma))
+ return false;
+
+ /* Allow by default. */
+ return true;
+}
+
+static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
+ struct vm_area_struct **prev, unsigned long start,
+ unsigned long end, vm_flags_t newflags)
+{
+ int ret = 0;
+ vm_flags_t oldflags = vma->vm_flags;
+
+ if (newflags == oldflags)
+ goto out;
+
+ vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags);
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto out;
+ }
+
+ set_vma_sealed(vma);
+out:
+ *prev = vma;
+ return ret;
+}
+
+/*
+ * Check for do_mseal:
+ * 1> start is part of a valid vma.
+ * 2> end is part of a valid vma.
+ * 3> No gap (unallocated address) between start and end.
+ * 4> map is sealable.
+ */
+static int check_mm_seal(unsigned long start, unsigned long end)
+{
+ struct vm_area_struct *vma;
+ unsigned long nstart = start;
+
+ VMA_ITERATOR(vmi, current->mm, start);
+
+ /* going through each vma to check. */
+ for_each_vma_range(vmi, vma, end) {
+ if (vma->vm_start > nstart)
+ /* unallocated memory found. */
+ return -ENOMEM;
+
+ if (vma->vm_end >= end)
+ return 0;
+
+ nstart = vma->vm_end;
+ }
+
+ return -ENOMEM;
+}
+
+/*
+ * Apply sealing.
+ */
+static int apply_mm_seal(unsigned long start, unsigned long end)
+{
+ unsigned long nstart;
+ struct vm_area_struct *vma, *prev;
+
+ VMA_ITERATOR(vmi, current->mm, start);
+
+ vma = vma_iter_load(&vmi);
+ /*
+ * Note: check_mm_seal should already checked ENOMEM case.
+ * so vma should not be null, same for the other ENOMEM cases.
+ */
+ prev = vma_prev(&vmi);
+ if (start > vma->vm_start)
+ prev = vma;
+
+ nstart = start;
+ for_each_vma_range(vmi, vma, end) {
+ int error;
+ unsigned long tmp;
+ vm_flags_t newflags;
+
+ newflags = vma->vm_flags | VM_SEALED;
+ tmp = vma->vm_end;
+ if (tmp > end)
+ tmp = end;
+ error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags);
+ if (error)
+ return error;
+ nstart = vma_iter_end(&vmi);
+ }
+
+ return 0;
+}
+
+/*
+ * mseal(2) seals the VM's meta data from
+ * selected syscalls.
+ *
+ * addr/len: VM address range.
+ *
+ * The address range by addr/len must meet:
+ * start (addr) must be in a valid VMA.
+ * end (addr + len) must be in a valid VMA.
+ * no gap (unallocated memory) between start and end.
+ * start (addr) must be page aligned.
+ *
+ * len: len will be page aligned implicitly.
+ *
+ * Below VMA operations are blocked after sealing.
+ * 1> Unmapping, moving to another location, and shrinking
+ * the size, via munmap() and mremap(), can leave an empty
+ * space, therefore can be replaced with a VMA with a new
+ * set of attributes.
+ * 2> Moving or expanding a different vma into the current location,
+ * via mremap().
+ * 3> Modifying a VMA via mmap(MAP_FIXED).
+ * 4> Size expansion, via mremap(), does not appear to pose any
+ * specific risks to sealed VMAs. It is included anyway because
+ * the use case is unclear. In any case, users can rely on
+ * merging to expand a sealed VMA.
+ * 5> mprotect and pkey_mprotect.
+ * 6> Some destructive madvice() behavior (e.g. MADV_DONTNEED)
+ * for anonymous memory, when users don't have write permission to the
+ * memory. Those behaviors can alter region contents by discarding pages,
+ * effectively a memset(0) for anonymous memory.
+ *
+ * flags: reserved.
+ *
+ * return values:
+ * zero: success.
+ * -EINVAL:
+ * invalid input flags.
+ * start address is not page aligned.
+ * Address arange (start + len) overflow.
+ * -ENOMEM:
+ * addr is not a valid address (not allocated).
+ * end (start + len) is not a valid address.
+ * a gap (unallocated memory) between start and end.
+ * -EPERM:
+ * - In 32 bit architecture, sealing is not supported.
+ * Note:
+ * user can call mseal(2) multiple times, adding a seal on an
+ * already sealed memory is a no-action (no error).
+ *
+ * unseal() is not supported.
+ */
+static int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
+{
+ size_t len;
+ int ret = 0;
+ unsigned long end;
+ struct mm_struct *mm = current->mm;
+
+ ret = can_do_mseal(flags);
+ if (ret)
+ return ret;
+
+ start = untagged_addr(start);
+ if (!PAGE_ALIGNED(start))
+ return -EINVAL;
+
+ len = PAGE_ALIGN(len_in);
+ /* Check to see whether len was rounded up from small -ve to zero. */
+ if (len_in && !len)
+ return -EINVAL;
+
+ end = start + len;
+ if (end < start)
+ return -EINVAL;
+
+ if (end == start)
+ return 0;
+
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
+ /*
+ * First pass, this helps to avoid
+ * partial sealing in case of error in input address range,
+ * e.g. ENOMEM error.
+ */
+ ret = check_mm_seal(start, end);
+ if (ret)
+ goto out;
+
+ /*
+ * Second pass, this should success, unless there are errors
+ * from vma_modify_flags, e.g. merge/split error, or process
+ * reaching the max supported VMAs, however, those cases shall
+ * be rare.
+ */
+ ret = apply_mm_seal(start, end);
+
+out:
+ mmap_write_unlock(current->mm);
+ return ret;
+}
+
+SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long,
+ flags)
+{
+ return do_mseal(start, len, flags);
+}
--
2.43.0.687.g38aa6559b0-goog
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v9 3/5] selftest mm/mseal memory sealing
2024-02-14 15:11 [PATCH v9 0/5] Introduce mseal jeffxu
2024-02-14 15:11 ` [PATCH v9 1/5] mseal: Wire up mseal syscall jeffxu
2024-02-14 15:11 ` [PATCH v9 2/5] mseal: add " jeffxu
@ 2024-02-14 15:11 ` jeffxu
2024-02-14 15:11 ` [PATCH v9 4/5] mseal:add documentation jeffxu
2024-02-14 15:11 ` [PATCH v9 5/5] selftest mm/mseal read-only elf memory segment jeffxu
4 siblings, 0 replies; 6+ messages in thread
From: jeffxu @ 2024-02-14 15:11 UTC (permalink / raw)
To: akpm, keescook, jannh, sroettger, willy, gregkh, torvalds,
usama.anjum, corbet, Liam.Howlett, surenb, merimus, rdunlap
Cc: jeffxu, jorgelo, groeck, linux-kernel, linux-kselftest, linux-mm,
pedro.falcato, dave.hansen, linux-hardening, deraadt,
=David.Laight, Jeff Xu
From: Jeff Xu <jeffxu@chromium.org>
selftest for memory sealing change in mmap() and mseal().
Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
tools/testing/selftests/mm/.gitignore | 1 +
tools/testing/selftests/mm/Makefile | 1 +
tools/testing/selftests/mm/mseal_test.c | 1836 +++++++++++++++++++++++
3 files changed, 1838 insertions(+)
create mode 100644 tools/testing/selftests/mm/mseal_test.c
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 4ff10ea61461..76474c51c786 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -46,3 +46,4 @@ gup_longterm
mkdirty
va_high_addr_switch
hugetlb_fault_after_madv
+mseal_test
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 2453add65d12..ba36a5c2b1fc 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -59,6 +59,7 @@ TEST_GEN_FILES += mlock2-tests
TEST_GEN_FILES += mrelease_test
TEST_GEN_FILES += mremap_dontunmap
TEST_GEN_FILES += mremap_test
+TEST_GEN_FILES += mseal_test
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += pagemap_ioctl
TEST_GEN_FILES += thuge-gen
diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c
new file mode 100644
index 000000000000..06c780d1d8e5
--- /dev/null
+++ b/tools/testing/selftests/mm/mseal_test.c
@@ -0,0 +1,1836 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/mman.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <stdbool.h>
+#include "../kselftest.h"
+#include <syscall.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <sys/ioctl.h>
+#include <sys/vfs.h>
+#include <sys/stat.h>
+
+/*
+ * need those definition for manually build using gcc.
+ * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 mseal_test.c -o mseal_test
+ */
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS 0x1
+#endif
+
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE 0x2
+#endif
+
+#ifndef PKEY_BITS_PER_KEY
+#define PKEY_BITS_PER_PKEY 2
+#endif
+
+#ifndef PKEY_MASK
+#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)
+#endif
+
+#define FAIL_TEST_IF_FALSE(c) do {\
+ if (!(c)) {\
+ ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\
+ goto test_end;\
+ } \
+ } \
+ while (0)
+
+#define SKIP_TEST_IF_FALSE(c) do {\
+ if (!(c)) {\
+ ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\
+ goto test_end;\
+ } \
+ } \
+ while (0)
+
+
+#define TEST_END_CHECK() {\
+ ksft_test_result_pass("%s\n", __func__);\
+ return;\
+test_end:\
+ return;\
+}
+
+#ifndef u64
+#define u64 unsigned long long
+#endif
+
+static unsigned long get_vma_size(void *addr, int *prot)
+{
+ FILE *maps;
+ char line[256];
+ int size = 0;
+ uintptr_t addr_start, addr_end;
+ char protstr[5];
+ *prot = 0;
+
+ maps = fopen("/proc/self/maps", "r");
+ if (!maps)
+ return 0;
+
+ while (fgets(line, sizeof(line), maps)) {
+ if (sscanf(line, "%lx-%lx %4s", &addr_start, &addr_end, &protstr) == 3) {
+ if (addr_start == (uintptr_t) addr) {
+ size = addr_end - addr_start;
+ if (protstr[0] == 'r')
+ *prot |= 0x4;
+ if (protstr[1] == 'w')
+ *prot |= 0x2;
+ if (protstr[2] == 'x')
+ *prot |= 0x1;
+ break;
+ }
+ }
+ }
+ fclose(maps);
+ return size;
+}
+
+/*
+ * define sys_xyx to call syscall directly.
+ */
+static int sys_mseal(void *start, size_t len)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_mseal, start, len, 0);
+ return sret;
+}
+
+static int sys_mprotect(void *ptr, size_t size, unsigned long prot)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_mprotect, ptr, size, prot);
+ return sret;
+}
+
+static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+ unsigned long pkey)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey);
+ return sret;
+}
+
+static void *sys_mmap(void *addr, unsigned long len, unsigned long prot,
+ unsigned long flags, unsigned long fd, unsigned long offset)
+{
+ void *sret;
+
+ errno = 0;
+ sret = (void *) syscall(__NR_mmap, addr, len, prot,
+ flags, fd, offset);
+ return sret;
+}
+
+static int sys_munmap(void *ptr, size_t size)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_munmap, ptr, size);
+ return sret;
+}
+
+static int sys_madvise(void *start, size_t len, int types)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_madvise, start, len, types);
+ return sret;
+}
+
+static int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
+{
+ int ret = syscall(__NR_pkey_alloc, flags, init_val);
+
+ return ret;
+}
+
+static unsigned int __read_pkey_reg(void)
+{
+ unsigned int pkey_reg = 0;
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+ unsigned int eax, edx;
+ unsigned int ecx = 0;
+
+ asm volatile(".byte 0x0f,0x01,0xee\n\t"
+ : "=a" (eax), "=d" (edx)
+ : "c" (ecx));
+ pkey_reg = eax;
+#endif
+ return pkey_reg;
+}
+
+static void __write_pkey_reg(u64 pkey_reg)
+{
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+ unsigned int eax = pkey_reg;
+ unsigned int ecx = 0;
+ unsigned int edx = 0;
+
+ asm volatile(".byte 0x0f,0x01,0xef\n\t"
+ : : "a" (eax), "c" (ecx), "d" (edx));
+ assert(pkey_reg == __read_pkey_reg());
+#endif
+}
+
+static unsigned long pkey_bit_position(int pkey)
+{
+ return pkey * PKEY_BITS_PER_PKEY;
+}
+
+static u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
+{
+ unsigned long shift = pkey_bit_position(pkey);
+
+ /* mask out bits from pkey in old value */
+ reg &= ~((u64)PKEY_MASK << shift);
+ /* OR in new bits for pkey */
+ reg |= (flags & PKEY_MASK) << shift;
+ return reg;
+}
+
+static void set_pkey(int pkey, unsigned long pkey_value)
+{
+ unsigned long mask = (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE);
+ u64 new_pkey_reg;
+
+ assert(!(pkey_value & ~mask));
+ new_pkey_reg = set_pkey_bits(__read_pkey_reg(), pkey, pkey_value);
+ __write_pkey_reg(new_pkey_reg);
+}
+
+static void setup_single_address(int size, void **ptrOut)
+{
+ void *ptr;
+
+ ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ assert(ptr != (void *)-1);
+ *ptrOut = ptr;
+}
+
+static void setup_single_address_rw(int size, void **ptrOut)
+{
+ void *ptr;
+ unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE;
+
+ ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0);
+ assert(ptr != (void *)-1);
+ *ptrOut = ptr;
+}
+
+static void clean_single_address(void *ptr, int size)
+{
+ int ret;
+
+ ret = munmap(ptr, size);
+ assert(!ret);
+}
+
+static void seal_single_address(void *ptr, int size)
+{
+ int ret;
+
+ ret = sys_mseal(ptr, size);
+ assert(!ret);
+}
+
+bool seal_support(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+
+ ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (ptr == (void *) -1)
+ return false;
+
+ ret = sys_mseal(ptr, page_size);
+ if (ret < 0)
+ return false;
+
+ return true;
+}
+
+bool pkey_supported(void)
+{
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+ int pkey = sys_pkey_alloc(0, 0);
+
+ if (pkey > 0)
+ return true;
+#endif
+ return false;
+}
+
+static void test_seal_addseal(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_unmapped_start(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* munmap 2 pages from ptr. */
+ ret = sys_munmap(ptr, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mprotect will fail because 2 pages from ptr are unmapped. */
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* mseal will fail because 2 pages from ptr are unmapped. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ ret = sys_mseal(ptr + 2 * page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_unmapped_middle(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* munmap 2 pages from ptr + page. */
+ ret = sys_munmap(ptr + page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mprotect will fail, since middle 2 pages are unmapped. */
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* mseal will fail as well. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* we still can add seal to the first page and last page*/
+ ret = sys_mseal(ptr, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_mseal(ptr + 3 * page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_unmapped_end(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* unmap last 2 pages. */
+ ret = sys_munmap(ptr + 2 * page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mprotect will fail since last 2 pages are unmapped. */
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* mseal will fail as well. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* The first 2 pages is not sealed, and can add seals */
+ ret = sys_mseal(ptr, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_multiple_vmas(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split the vma into 3. */
+ ret = sys_mprotect(ptr + page_size, 2 * page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mprotect will get applied to all 4 pages - 3 VMAs. */
+ ret = sys_mprotect(ptr, size, PROT_READ);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* use mprotect to split the vma into 3. */
+ ret = sys_mprotect(ptr + page_size, 2 * page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mseal get applied to all 4 pages - 3 VMAs. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_split_start(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split at middle */
+ ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal the first page, this will split the VMA */
+ ret = sys_mseal(ptr, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* add seal to the remain 3 pages */
+ ret = sys_mseal(ptr + page_size, 3 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_split_end(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split at middle */
+ ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal the last page */
+ ret = sys_mseal(ptr + 3 * page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* Adding seals to the first 3 pages */
+ ret = sys_mseal(ptr, 3 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_invalid_input(void)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(8 * page_size, &ptr);
+ clean_single_address(ptr + 4 * page_size, 4 * page_size);
+
+ /* invalid flag */
+ ret = syscall(__NR_mseal, ptr, size, 0x20);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* unaligned address */
+ ret = sys_mseal(ptr + 1, 2 * page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* length too big */
+ ret = sys_mseal(ptr, 5 * page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* length overflow */
+ ret = sys_mseal(ptr, UINT64_MAX/page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* start is not in a valid VMA */
+ ret = sys_mseal(ptr - page_size, 5 * page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_zero_length(void)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ ret = sys_mprotect(ptr, 0, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal 0 length will be OK, same as mprotect */
+ ret = sys_mseal(ptr, 0);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* verify the 4 pages are not sealed by previous call. */
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_zero_address(void)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ int prot;
+
+ /* use mmap to change protection. */
+ ptr = sys_mmap(0, size, PROT_NONE,
+ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ FAIL_TEST_IF_FALSE(ptr == 0);
+
+ size = get_vma_size(ptr, &prot);
+ FAIL_TEST_IF_FALSE(size == 4 * page_size);
+
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* verify the 4 pages are sealed by previous call. */
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_twice(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+
+ setup_single_address(size, &ptr);
+
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* apply the same seal will be OK. idempotent. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal)
+ seal_single_address(ptr, size);
+
+ ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_start_mprotect(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal)
+ seal_single_address(ptr, page_size);
+
+ /* the first page is sealed. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* pages after the first page is not sealed. */
+ ret = sys_mprotect(ptr + page_size, page_size * 3,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_end_mprotect(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal)
+ seal_single_address(ptr + page_size, 3 * page_size);
+
+ /* first page is not sealed */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* last 3 page are sealed */
+ ret = sys_mprotect(ptr + page_size, page_size * 3,
+ PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_unalign_len(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal)
+ seal_single_address(ptr, page_size * 2 - 1);
+
+ /* 2 pages are sealed. */
+ ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_mprotect(ptr + page_size * 2, page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_unalign_len_variant_2(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+ if (seal)
+ seal_single_address(ptr, page_size * 2 + 1);
+
+ /* 3 pages are sealed. */
+ ret = sys_mprotect(ptr, page_size * 3, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_mprotect(ptr + page_size * 3, page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_two_vma(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split */
+ ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal)
+ seal_single_address(ptr, page_size * 4);
+
+ ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_mprotect(ptr + page_size * 2, page_size * 2,
+ PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_two_vma_with_split(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split as two vma. */
+ ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mseal can apply across 2 vma, also split them. */
+ if (seal)
+ seal_single_address(ptr + page_size, page_size * 2);
+
+ /* the first page is not sealed. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* the second page is sealed. */
+ ret = sys_mprotect(ptr + page_size, page_size, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* the third page is sealed. */
+ ret = sys_mprotect(ptr + 2 * page_size, page_size,
+ PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* the fouth page is not sealed. */
+ ret = sys_mprotect(ptr + 3 * page_size, page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_partial_mprotect(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* seal one page. */
+ if (seal)
+ seal_single_address(ptr, page_size);
+
+ /* mprotect first 2 page will fail, since the first page are sealed. */
+ ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_two_vma_with_gap(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* use mprotect to split. */
+ ret = sys_mprotect(ptr + 3 * page_size, page_size,
+ PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* use munmap to free two pages in the middle */
+ ret = sys_munmap(ptr + page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* mprotect will fail, because there is a gap in the address. */
+ /* notes, internally mprotect still updated the first page. */
+ ret = sys_mprotect(ptr, 4 * page_size, PROT_READ);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* mseal will fail as well. */
+ ret = sys_mseal(ptr, 4 * page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* the first page is not sealed. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ);
+ FAIL_TEST_IF_FALSE(ret == 0);
+
+ /* the last page is not sealed. */
+ ret = sys_mprotect(ptr + 3 * page_size, page_size, PROT_READ);
+ FAIL_TEST_IF_FALSE(ret == 0);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_split(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal all 4 pages. */
+ if (seal) {
+ ret = sys_mseal(ptr, 4 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* mprotect is sealed. */
+ ret = sys_mprotect(ptr, 2 * page_size, PROT_READ);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+
+ ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mprotect_merge(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split one page. */
+ ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal first two pages. */
+ if (seal) {
+ ret = sys_mseal(ptr, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* 2 pages are sealed. */
+ ret = sys_mprotect(ptr, 2 * page_size, PROT_READ);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* last 2 pages are not sealed. */
+ ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ);
+ FAIL_TEST_IF_FALSE(ret == 0);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_munmap(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* 4 pages are sealed. */
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+/*
+ * allocate 4 pages,
+ * use mprotect to split it as two VMAs
+ * seal the whole range
+ * munmap will fail on both
+ */
+static void test_seal_munmap_two_vma(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ /* use mprotect to split */
+ ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ ret = sys_munmap(ptr, page_size * 2);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr + page_size, page_size * 2);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+/*
+ * allocate a VMA with 4 pages.
+ * munmap the middle 2 pages.
+ * seal the whole 4 pages, will fail.
+ * munmap the first page will be OK.
+ * munmap the last page will be OK.
+ */
+static void test_seal_munmap_vma_with_gap(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ ret = sys_munmap(ptr + page_size, page_size * 2);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal) {
+ /* can't have gap in the middle. */
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+ }
+
+ ret = sys_munmap(ptr, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr + page_size * 2, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_munmap_start_freed(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ int prot;
+
+ setup_single_address(size, &ptr);
+
+ /* unmap the first page. */
+ ret = sys_munmap(ptr, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal the last 3 pages. */
+ if (seal) {
+ ret = sys_mseal(ptr + page_size, 3 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* unmap from the first page. */
+ ret = sys_munmap(ptr, size);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == page_size * 3);
+ } else {
+ /* note: this will be OK, even the first page is */
+ /* already unmapped. */
+ FAIL_TEST_IF_FALSE(!ret);
+
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 0);
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_munmap_end_freed(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+ /* unmap last page. */
+ ret = sys_munmap(ptr + page_size * 3, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal the first 3 pages. */
+ if (seal) {
+ ret = sys_mseal(ptr, 3 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* unmap all pages. */
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_munmap_middle_freed(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ int prot;
+
+ setup_single_address(size, &ptr);
+ /* unmap 2 pages in the middle. */
+ ret = sys_munmap(ptr + page_size, page_size * 2);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* seal the first page. */
+ if (seal) {
+ ret = sys_mseal(ptr, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* munmap all 4 pages. */
+ ret = sys_munmap(ptr, size);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ size = get_vma_size(ptr, &prot);
+ FAIL_TEST_IF_FALSE(size == page_size);
+
+ size = get_vma_size(ptr + page_size * 3, &prot);
+ FAIL_TEST_IF_FALSE(size == page_size);
+ } else {
+ FAIL_TEST_IF_FALSE(!ret);
+
+ size = get_vma_size(ptr, &prot);
+ FAIL_TEST_IF_FALSE(size == 0);
+
+ size = get_vma_size(ptr + page_size * 3, &prot);
+ FAIL_TEST_IF_FALSE(size == 0);
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_shrink(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* shrink from 4 pages to 2 pages. */
+ ret2 = mremap(ptr, size, 2 * page_size, 0, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_expand(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+ /* ummap last 2 pages. */
+ ret = sys_munmap(ptr + 2 * page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal) {
+ ret = sys_mseal(ptr, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* expand from 2 page to 4 pages. */
+ ret2 = mremap(ptr, 2 * page_size, 4 * page_size, 0, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 == ptr);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_move(bool seal)
+{
+ void *ptr, *newPtr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+ setup_single_address(size, &newPtr);
+ clean_single_address(newPtr, size);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* move from ptr to fixed address. */
+ ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mmap_overwrite_prot(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* use mmap to change protection. */
+ ret2 = sys_mmap(ptr, size, PROT_NONE,
+ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == ptr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mmap_expand(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 12 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+ /* ummap last 4 pages. */
+ ret = sys_munmap(ptr + 8 * page_size, 4 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal) {
+ ret = sys_mseal(ptr, 8 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* use mmap to expand. */
+ ret2 = sys_mmap(ptr, size, PROT_READ,
+ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == ptr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mmap_shrink(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 12 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* use mmap to shrink. */
+ ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ,
+ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == ptr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_shrink_fixed(bool seal)
+{
+ void *ptr;
+ void *newAddr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+ setup_single_address(size, &newAddr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* mremap to move and shrink to fixed address */
+ ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED,
+ newAddr);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == newAddr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_expand_fixed(bool seal)
+{
+ void *ptr;
+ void *newAddr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(page_size, &ptr);
+ setup_single_address(size, &newAddr);
+
+ if (seal) {
+ ret = sys_mseal(newAddr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* mremap to move and expand to fixed address */
+ ret2 = mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED,
+ newAddr);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == newAddr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_move_fixed(bool seal)
+{
+ void *ptr;
+ void *newAddr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+ setup_single_address(size, &newAddr);
+
+ if (seal) {
+ ret = sys_mseal(newAddr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* mremap to move to fixed address */
+ ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else
+ FAIL_TEST_IF_FALSE(ret2 == newAddr);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_move_fixed_zero(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /*
+ * MREMAP_FIXED can move the mapping to zero address
+ */
+ ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED,
+ 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 == 0);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_move_dontunmap(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* mremap to move, and don't unmap src addr. */
+ ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_mremap_move_dontunmap_anyaddr(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ void *ret2;
+
+ setup_single_address(size, &ptr);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /*
+ * The 0xdeaddead should not have effect on dest addr
+ * when MREMAP_DONTUNMAP is set.
+ */
+ ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP,
+ 0xdeaddead);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+ } else {
+ FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED);
+ FAIL_TEST_IF_FALSE((long)ret2 != 0xdeaddead);
+
+ }
+
+ TEST_END_CHECK();
+}
+
+
+static void test_seal_merge_and_split(void)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size;
+ int ret;
+ int prot;
+
+ /* (24 RO) */
+ setup_single_address(24 * page_size, &ptr);
+
+ /* use mprotect(NONE) to set out boundary */
+ /* (1 NONE) (22 RO) (1 NONE) */
+ ret = sys_mprotect(ptr, page_size, PROT_NONE);
+ FAIL_TEST_IF_FALSE(!ret);
+ ret = sys_mprotect(ptr + 23 * page_size, page_size, PROT_NONE);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 22 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 4);
+
+ /* use mseal to split from beginning */
+ /* (1 NONE) (1 RO_SEAL) (21 RO) (1 NONE) */
+ ret = sys_mseal(ptr + page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+ size = get_vma_size(ptr + 2 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 21 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ /* use mseal to split from the end. */
+ /* (1 NONE) (1 RO_SEAL) (20 RO) (1 RO_SEAL) (1 NONE) */
+ ret = sys_mseal(ptr + 22 * page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + 22 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+ size = get_vma_size(ptr + 2 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 20 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ /* merge with prev. */
+ /* (1 NONE) (2 RO_SEAL) (19 RO) (1 RO_SEAL) (1 NONE) */
+ ret = sys_mseal(ptr + 2 * page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 2 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ /* merge with after. */
+ /* (1 NONE) (2 RO_SEAL) (18 RO) (2 RO_SEALS) (1 NONE) */
+ ret = sys_mseal(ptr + 21 * page_size, page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + 21 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 2 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ /* split and merge from prev */
+ /* (1 NONE) (3 RO_SEAL) (17 RO) (2 RO_SEALS) (1 NONE) */
+ ret = sys_mseal(ptr + 2 * page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + 1 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 3 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+ ret = sys_munmap(ptr + page_size, page_size);
+ FAIL_TEST_IF_FALSE(ret < 0);
+ ret = sys_mprotect(ptr + 2 * page_size, page_size, PROT_NONE);
+ FAIL_TEST_IF_FALSE(ret < 0);
+
+ /* split and merge from next */
+ /* (1 NONE) (3 RO_SEAL) (16 RO) (3 RO_SEALS) (1 NONE) */
+ ret = sys_mseal(ptr + 20 * page_size, 2 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+ size = get_vma_size(ptr + 20 * page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 3 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ /* merge from middle of prev and middle of next. */
+ /* (1 NONE) (22 RO_SEAL) (1 NONE) */
+ ret = sys_mseal(ptr + 2 * page_size, 20 * page_size);
+ FAIL_TEST_IF_FALSE(!ret);
+ size = get_vma_size(ptr + page_size, &prot);
+ FAIL_TEST_IF_FALSE(size == 22 * page_size);
+ FAIL_TEST_IF_FALSE(prot == 0x4);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_discard_ro_anon_on_rw(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address_rw(size, &ptr);
+ FAIL_TEST_IF_FALSE(ptr != (void *)-1);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* sealing doesn't take effect on RW memory. */
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* base seal still apply. */
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_discard_ro_anon_on_pkey(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ int pkey;
+
+ SKIP_TEST_IF_FALSE(pkey_supported());
+
+ setup_single_address_rw(size, &ptr);
+ FAIL_TEST_IF_FALSE(ptr != (void *)-1);
+
+ pkey = sys_pkey_alloc(0, 0);
+ FAIL_TEST_IF_FALSE(pkey > 0);
+
+ ret = sys_mprotect_pkey((void *)ptr, size, PROT_READ | PROT_WRITE, pkey);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* sealing doesn't take effect if PKRU allow write. */
+ set_pkey(pkey, 0);
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* sealing will take effect if PKRU deny write. */
+ set_pkey(pkey, PKEY_DISABLE_WRITE);
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ /* base seal still apply. */
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_discard_ro_anon_on_filebacked(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ int fd;
+ unsigned long mapflags = MAP_PRIVATE;
+
+ fd = memfd_create("test", 0);
+ FAIL_TEST_IF_FALSE(fd > 0);
+
+ ret = fallocate(fd, 0, 0, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0);
+ FAIL_TEST_IF_FALSE(ptr != MAP_FAILED);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* sealing doesn't apply for file backed mapping. */
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+ close(fd);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_discard_ro_anon_on_shared(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+ unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED;
+
+ ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0);
+ FAIL_TEST_IF_FALSE(ptr != (void *)-1);
+
+ if (seal) {
+ ret = sys_mseal(ptr, size);
+ FAIL_TEST_IF_FALSE(!ret);
+ }
+
+ /* sealing doesn't apply for shared mapping. */
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+static void test_seal_discard_ro_anon(bool seal)
+{
+ void *ptr;
+ unsigned long page_size = getpagesize();
+ unsigned long size = 4 * page_size;
+ int ret;
+
+ setup_single_address(size, &ptr);
+
+ if (seal)
+ seal_single_address(ptr, size);
+
+ ret = sys_madvise(ptr, size, MADV_DONTNEED);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ ret = sys_munmap(ptr, size);
+ if (seal)
+ FAIL_TEST_IF_FALSE(ret < 0);
+ else
+ FAIL_TEST_IF_FALSE(!ret);
+
+ TEST_END_CHECK();
+}
+
+int main(int argc, char **argv)
+{
+ bool test_seal = seal_support();
+
+ ksft_print_header();
+
+ if (!test_seal)
+ ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n");
+
+ if (!pkey_supported())
+ ksft_print_msg("PKEY not supported\n");
+
+ ksft_set_plan(80);
+
+ test_seal_addseal();
+ test_seal_unmapped_start();
+ test_seal_unmapped_middle();
+ test_seal_unmapped_end();
+ test_seal_multiple_vmas();
+ test_seal_split_start();
+ test_seal_split_end();
+ test_seal_invalid_input();
+ test_seal_zero_length();
+ test_seal_twice();
+
+ test_seal_mprotect(false);
+ test_seal_mprotect(true);
+
+ test_seal_start_mprotect(false);
+ test_seal_start_mprotect(true);
+
+ test_seal_end_mprotect(false);
+ test_seal_end_mprotect(true);
+
+ test_seal_mprotect_unalign_len(false);
+ test_seal_mprotect_unalign_len(true);
+
+ test_seal_mprotect_unalign_len_variant_2(false);
+ test_seal_mprotect_unalign_len_variant_2(true);
+
+ test_seal_mprotect_two_vma(false);
+ test_seal_mprotect_two_vma(true);
+
+ test_seal_mprotect_two_vma_with_split(false);
+ test_seal_mprotect_two_vma_with_split(true);
+
+ test_seal_mprotect_partial_mprotect(false);
+ test_seal_mprotect_partial_mprotect(true);
+
+ test_seal_mprotect_two_vma_with_gap(false);
+ test_seal_mprotect_two_vma_with_gap(true);
+
+ test_seal_mprotect_merge(false);
+ test_seal_mprotect_merge(true);
+
+ test_seal_mprotect_split(false);
+ test_seal_mprotect_split(true);
+
+ test_seal_munmap(false);
+ test_seal_munmap(true);
+ test_seal_munmap_two_vma(false);
+ test_seal_munmap_two_vma(true);
+ test_seal_munmap_vma_with_gap(false);
+ test_seal_munmap_vma_with_gap(true);
+
+ test_munmap_start_freed(false);
+ test_munmap_start_freed(true);
+ test_munmap_middle_freed(false);
+ test_munmap_middle_freed(true);
+ test_munmap_end_freed(false);
+ test_munmap_end_freed(true);
+
+ test_seal_mremap_shrink(false);
+ test_seal_mremap_shrink(true);
+ test_seal_mremap_expand(false);
+ test_seal_mremap_expand(true);
+ test_seal_mremap_move(false);
+ test_seal_mremap_move(true);
+
+ test_seal_mremap_shrink_fixed(false);
+ test_seal_mremap_shrink_fixed(true);
+ test_seal_mremap_expand_fixed(false);
+ test_seal_mremap_expand_fixed(true);
+ test_seal_mremap_move_fixed(false);
+ test_seal_mremap_move_fixed(true);
+ test_seal_mremap_move_dontunmap(false);
+ test_seal_mremap_move_dontunmap(true);
+ test_seal_mremap_move_fixed_zero(false);
+ test_seal_mremap_move_fixed_zero(true);
+ test_seal_mremap_move_dontunmap_anyaddr(false);
+ test_seal_mremap_move_dontunmap_anyaddr(true);
+ test_seal_discard_ro_anon(false);
+ test_seal_discard_ro_anon(true);
+ test_seal_discard_ro_anon_on_rw(false);
+ test_seal_discard_ro_anon_on_rw(true);
+ test_seal_discard_ro_anon_on_shared(false);
+ test_seal_discard_ro_anon_on_shared(true);
+ test_seal_discard_ro_anon_on_filebacked(false);
+ test_seal_discard_ro_anon_on_filebacked(true);
+ test_seal_mmap_overwrite_prot(false);
+ test_seal_mmap_overwrite_prot(true);
+ test_seal_mmap_expand(false);
+ test_seal_mmap_expand(true);
+ test_seal_mmap_shrink(false);
+ test_seal_mmap_shrink(true);
+
+ test_seal_merge_and_split();
+ test_seal_zero_address();
+
+ test_seal_discard_ro_anon_on_pkey(false);
+ test_seal_discard_ro_anon_on_pkey(true);
+
+ ksft_finished();
+ return 0;
+}
--
2.43.0.687.g38aa6559b0-goog
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v9 4/5] mseal:add documentation
2024-02-14 15:11 [PATCH v9 0/5] Introduce mseal jeffxu
` (2 preceding siblings ...)
2024-02-14 15:11 ` [PATCH v9 3/5] selftest mm/mseal memory sealing jeffxu
@ 2024-02-14 15:11 ` jeffxu
2024-02-14 15:11 ` [PATCH v9 5/5] selftest mm/mseal read-only elf memory segment jeffxu
4 siblings, 0 replies; 6+ messages in thread
From: jeffxu @ 2024-02-14 15:11 UTC (permalink / raw)
To: akpm, keescook, jannh, sroettger, willy, gregkh, torvalds,
usama.anjum, corbet, Liam.Howlett, surenb, merimus, rdunlap
Cc: jeffxu, jorgelo, groeck, linux-kernel, linux-kselftest, linux-mm,
pedro.falcato, dave.hansen, linux-hardening, deraadt,
=David.Laight, Jeff Xu
From: Jeff Xu <jeffxu@chromium.org>
Add documentation for mseal().
Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
Documentation/userspace-api/index.rst | 1 +
Documentation/userspace-api/mseal.rst | 199 ++++++++++++++++++++++++++
2 files changed, 200 insertions(+)
create mode 100644 Documentation/userspace-api/mseal.rst
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 09f61bd2ac2e..178f6a1d79cb 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -26,6 +26,7 @@ place where this information is gathered.
iommu
iommufd
media/index
+ mseal
netlink/index
sysfs-platform_profile
vduse
diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
new file mode 100644
index 000000000000..4132eec995a3
--- /dev/null
+++ b/Documentation/userspace-api/mseal.rst
@@ -0,0 +1,199 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+Introduction of mseal
+=====================
+
+:Author: Jeff Xu <jeffxu@chromium.org>
+
+Modern CPUs support memory permissions such as RW and NX bits. The memory
+permission feature improves security stance on memory corruption bugs, i.e.
+the attacker can’t just write to arbitrary memory and point the code to it,
+the memory has to be marked with X bit, or else an exception will happen.
+
+Memory sealing additionally protects the mapping itself against
+modifications. This is useful to mitigate memory corruption issues where a
+corrupted pointer is passed to a memory management system. For example,
+such an attacker primitive can break control-flow integrity guarantees
+since read-only memory that is supposed to be trusted can become writable
+or .text pages can get remapped. Memory sealing can automatically be
+applied by the runtime loader to seal .text and .rodata pages and
+applications can additionally seal security critical data at runtime.
+
+A similar feature already exists in the XNU kernel with the
+VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2].
+
+User API
+========
+mseal()
+-----------
+The mseal() syscall has the following signature:
+
+``int mseal(void addr, size_t len, unsigned long flags)``
+
+**addr/len**: virtual memory address range.
+
+The address range set by ``addr``/``len`` must meet:
+ - The start address must be in an allocated VMA.
+ - The start address must be page aligned.
+ - The end address (``addr`` + ``len``) must be in an allocated VMA.
+ - no gap (unallocated memory) between start and end address.
+
+The ``len`` will be paged aligned implicitly by the kernel.
+
+**flags**: reserved for future use.
+
+**return values**:
+
+- ``0``: Success.
+
+- ``-EINVAL``:
+ - Invalid input ``flags``.
+ - The start address (``addr``) is not page aligned.
+ - Address range (``addr`` + ``len``) overflow.
+
+- ``-ENOMEM``:
+ - The start address (``addr``) is not allocated.
+ - The end address (``addr`` + ``len``) is not allocated.
+ - A gap (unallocated memory) between start and end address.
+
+- ``-EPERM``:
+ - sealing is supported only on 64-bit CPUs, 32-bit is not supported.
+
+- For above error cases, users can expect the given memory range is
+ unmodified, i.e. no partial update.
+
+- There might be other internal errors/cases not listed here, e.g.
+ error during merging/splitting VMAs, or the process reaching the max
+ number of supported VMAs. In those cases, partial updates to the given
+ memory range could happen. However, those cases should be rare.
+
+**Blocked operations after sealing**:
+ Unmapping, moving to another location, and shrinking the size,
+ via munmap() and mremap(), can leave an empty space, therefore
+ can be replaced with a VMA with a new set of attributes.
+
+ Moving or expanding a different VMA into the current location,
+ via mremap().
+
+ Modifying a VMA via mmap(MAP_FIXED).
+
+ Size expansion, via mremap(), does not appear to pose any
+ specific risks to sealed VMAs. It is included anyway because
+ the use case is unclear. In any case, users can rely on
+ merging to expand a sealed VMA.
+
+ mprotect() and pkey_mprotect().
+
+ Some destructive madvice() behaviors (e.g. MADV_DONTNEED)
+ for anonymous memory, when users don't have write permission to the
+ memory. Those behaviors can alter region contents by discarding pages,
+ effectively a memset(0) for anonymous memory.
+
+ Kernel will return -EPERM for blocked operations.
+
+ For blocked operations, one can expect the given address is unmodified,
+ i.e. no partial update. Note, this is different from existing mm
+ system call behaviors, where partial updates are made till an error is
+ found and returned to userspace. To give an example:
+
+ Assume following code sequence:
+
+ - ptr = mmap(null, 8192, PROT_NONE);
+ - munmap(ptr + 4096, 4096);
+ - ret1 = mprotect(ptr, 8192, PROT_READ);
+ - mseal(ptr, 4096);
+ - ret2 = mprotect(ptr, 8192, PROT_NONE);
+
+ ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ.
+
+ ret2 will be -EPERM, the page remains to be PROT_READ.
+
+**Note**:
+
+- mseal() only works on 64-bit CPUs, not 32-bit CPU.
+
+- users can call mseal() multiple times, mseal() on an already sealed memory
+ is a no-action (not error).
+
+- munseal() is not supported.
+
+Use cases:
+==========
+- glibc:
+ The dynamic linker, during loading ELF executables, can apply sealing to
+ non-writable memory segments.
+
+- Chrome browser: protect some security sensitive data-structures.
+
+Notes on which memory to seal:
+==============================
+
+It might be important to note that sealing changes the lifetime of a mapping,
+i.e. the sealed mapping won’t be unmapped till the process terminates or the
+exec system call is invoked. Applications can apply sealing to any virtual
+memory region from userspace, but it is crucial to thoroughly analyze the
+mapping's lifetime prior to apply the sealing.
+
+For example:
+
+- aio/shm
+
+ aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in
+ shm.c. The lifetime of those mapping are not tied to the lifetime of the
+ process. If those memories are sealed from userspace, then munmap() will fail,
+ causing leaks in VMA address space during the lifetime of the process.
+
+- Brk (heap)
+
+ Currently, userspace applications can seal parts of the heap by calling
+ malloc() and mseal().
+ let's assume following calls from user space:
+
+ - ptr = malloc(size);
+ - mprotect(ptr, size, RO);
+ - mseal(ptr, size);
+ - free(ptr);
+
+ Technically, before mseal() is added, the user can change the protection of
+ the heap by calling mprotect(RO). As long as the user changes the protection
+ back to RW before free(), the memory range can be reused.
+
+ Adding mseal() into the picture, however, the heap is then sealed partially,
+ the user can still free it, but the memory remains to be RO. If the address
+ is re-used by the heap manager for another malloc, the process might crash
+ soon after. Therefore, it is important not to apply sealing to any memory
+ that might get recycled.
+
+ Furthermore, even if the application never calls the free() for the ptr,
+ the heap manager may invoke the brk system call to shrink the size of the
+ heap. In the kernel, the brk-shrink will call munmap(). Consequently,
+ depending on the location of the ptr, the outcome of brk-shrink is
+ nondeterministic.
+
+
+Additional notes:
+=================
+As Jann Horn pointed out in [3], there are still a few ways to write
+to RO memory, which is, in a way, by design. Those cases are not covered
+by mseal(). If applications want to block such cases, sandbox tools (such as
+seccomp, LSM, etc) might be considered.
+
+Those cases are:
+
+- Write to read-only memory through /proc/self/mem interface.
+- Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
+- userfaultfd.
+
+The idea that inspired this patch comes from Stephen Röttger’s work in V8
+CFI [4]. Chrome browser in ChromeOS will be the first user of this API.
+
+Reference:
+==========
+[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
+
+[2] https://man.openbsd.org/mimmutable.2
+
+[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
+
+[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
--
2.43.0.687.g38aa6559b0-goog
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v9 5/5] selftest mm/mseal read-only elf memory segment
2024-02-14 15:11 [PATCH v9 0/5] Introduce mseal jeffxu
` (3 preceding siblings ...)
2024-02-14 15:11 ` [PATCH v9 4/5] mseal:add documentation jeffxu
@ 2024-02-14 15:11 ` jeffxu
4 siblings, 0 replies; 6+ messages in thread
From: jeffxu @ 2024-02-14 15:11 UTC (permalink / raw)
To: akpm, keescook, jannh, sroettger, willy, gregkh, torvalds,
usama.anjum, corbet, Liam.Howlett, surenb, merimus, rdunlap
Cc: jeffxu, jorgelo, groeck, linux-kernel, linux-kselftest, linux-mm,
pedro.falcato, dave.hansen, linux-hardening, deraadt,
=David.Laight, Jeff Xu
From: Jeff Xu <jeffxu@chromium.org>
Sealing read-only of elf mapping so it can't be changed by mprotect.
Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
tools/testing/selftests/mm/.gitignore | 1 +
tools/testing/selftests/mm/Makefile | 1 +
tools/testing/selftests/mm/seal_elf.c | 183 ++++++++++++++++++++++++++
3 files changed, 185 insertions(+)
create mode 100644 tools/testing/selftests/mm/seal_elf.c
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 76474c51c786..eff280b17a6e 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -47,3 +47,4 @@ mkdirty
va_high_addr_switch
hugetlb_fault_after_madv
mseal_test
+seal_elf
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index ba36a5c2b1fc..a0a12626cd19 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -60,6 +60,7 @@ TEST_GEN_FILES += mrelease_test
TEST_GEN_FILES += mremap_dontunmap
TEST_GEN_FILES += mremap_test
TEST_GEN_FILES += mseal_test
+TEST_GEN_FILES += seal_elf
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += pagemap_ioctl
TEST_GEN_FILES += thuge-gen
diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c
new file mode 100644
index 000000000000..61a2f1c94e02
--- /dev/null
+++ b/tools/testing/selftests/mm/seal_elf.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/mman.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <stdbool.h>
+#include "../kselftest.h"
+#include <syscall.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <sys/ioctl.h>
+#include <sys/vfs.h>
+#include <sys/stat.h>
+
+/*
+ * need those definition for manually build using gcc.
+ * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 seal_elf.c -o seal_elf
+ */
+#define FAIL_TEST_IF_FALSE(c) do {\
+ if (!(c)) {\
+ ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\
+ goto test_end;\
+ } \
+ } \
+ while (0)
+
+#define SKIP_TEST_IF_FALSE(c) do {\
+ if (!(c)) {\
+ ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\
+ goto test_end;\
+ } \
+ } \
+ while (0)
+
+
+#define TEST_END_CHECK() {\
+ ksft_test_result_pass("%s\n", __func__);\
+ return;\
+test_end:\
+ return;\
+}
+
+#ifndef u64
+#define u64 unsigned long long
+#endif
+
+/*
+ * define sys_xyx to call syscall directly.
+ */
+static int sys_mseal(void *start, size_t len)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_mseal, start, len, 0);
+ return sret;
+}
+
+static void *sys_mmap(void *addr, unsigned long len, unsigned long prot,
+ unsigned long flags, unsigned long fd, unsigned long offset)
+{
+ void *sret;
+
+ errno = 0;
+ sret = (void *) syscall(__NR_mmap, addr, len, prot,
+ flags, fd, offset);
+ return sret;
+}
+
+inline int sys_mprotect(void *ptr, size_t size, unsigned long prot)
+{
+ int sret;
+
+ errno = 0;
+ sret = syscall(__NR_mprotect, ptr, size, prot);
+ return sret;
+}
+
+static bool seal_support(void)
+{
+ int ret;
+ void *ptr;
+ unsigned long page_size = getpagesize();
+
+ ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (ptr == (void *) -1)
+ return false;
+
+ ret = sys_mseal(ptr, page_size);
+ if (ret < 0)
+ return false;
+
+ return true;
+}
+
+const char somestr[4096] = {"READONLY"};
+
+static void test_seal_elf(void)
+{
+ int ret;
+ FILE *maps;
+ char line[512];
+ int size = 0;
+ uintptr_t addr_start, addr_end;
+ char prot[5];
+ char filename[256];
+ unsigned long page_size = getpagesize();
+ unsigned long long ptr = (unsigned long long) somestr;
+ char *somestr2 = (char *)somestr;
+
+ /*
+ * Modify the protection of readonly somestr
+ */
+ if (((unsigned long long)ptr % page_size) != 0)
+ ptr = (unsigned long long)ptr & ~(page_size - 1);
+
+ ksft_print_msg("somestr = %s\n", somestr);
+ ksft_print_msg("change protection to rw\n");
+ ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE);
+ FAIL_TEST_IF_FALSE(!ret);
+ *somestr2 = 'A';
+ ksft_print_msg("somestr is modified to: %s\n", somestr);
+ ret = sys_mprotect((void *)ptr, page_size, PROT_READ);
+ FAIL_TEST_IF_FALSE(!ret);
+
+ maps = fopen("/proc/self/maps", "r");
+ FAIL_TEST_IF_FALSE(maps);
+
+ /*
+ * apply sealing to elf binary
+ */
+ while (fgets(line, sizeof(line), maps)) {
+ if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]",
+ &addr_start, &addr_end, &prot, &filename) == 4) {
+ if (strlen(filename)) {
+ /*
+ * seal the mapping if read only.
+ */
+ if (strstr(prot, "r-")) {
+ ret = sys_mseal((void *)addr_start, addr_end - addr_start);
+ FAIL_TEST_IF_FALSE(!ret);
+ ksft_print_msg("sealed: %lx-%lx %s %s\n",
+ addr_start, addr_end, prot, filename);
+ if ((uintptr_t) somestr >= addr_start &&
+ (uintptr_t) somestr <= addr_end)
+ ksft_print_msg("mapping for somestr found\n");
+ }
+ }
+ }
+ }
+ fclose(maps);
+
+ ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE);
+ FAIL_TEST_IF_FALSE(ret < 0);
+ ksft_print_msg("somestr is sealed, mprotect is rejected\n");
+
+ TEST_END_CHECK();
+}
+
+int main(int argc, char **argv)
+{
+ bool test_seal = seal_support();
+
+ ksft_print_header();
+ ksft_print_msg("pid=%d\n", getpid());
+
+ if (!test_seal)
+ ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n");
+
+ ksft_set_plan(1);
+
+ test_seal_elf();
+
+ ksft_finished();
+ return 0;
+}
--
2.43.0.687.g38aa6559b0-goog
^ permalink raw reply related [flat|nested] 6+ messages in thread