If a user program uses userfaultfd on ranges of heap memory, it may
end up passing a tagged pointer to the kernel in the range.start
field of the UFFDIO_REGISTER ioctl. This can happen when using an
MTE-capable allocator, or on Android if using the Tagged Pointers
feature for MTE readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field
of struct uffd_msg. However, from the application's perspective,
the tagged address *is* the memory address, so if the application
is unaware of memory tags, it may get confused by receiving an
address that is, from its point of view, outside of the bounds of the
allocation. We observed this behavior in the kselftest for userfaultfd
[2] but other applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd
ioctls. Instead, let the system call fail. This will provide an
early indication of problems with tag-unaware userspace code instead
of letting the code get confused later, and is consistent with how
we decided to handle brk/mmap/mremap in commit dcde237319e6 ("mm:
Avoid creating virtual address aliases in brk()/mmap()/mremap()"),
as well as being consistent with the existing tagged address ABI
documentation relating to how ioctl arguments are handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd:
untag user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Signed-off-by: Peter Collingbourne <pcc@xxxxxxxxxx>
Reviewed-by: Andrey Konovalov <andreyknvl@xxxxxxxxx>
Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Cc: <stable@xxxxxxxxxxxxxxx> # 5.4
---
v4:
- document the changes more accurately
- fix new calls to validate_range
Documentation/arm64/tagged-address-abi.rst | 26 +++++++++++++++-------
fs/userfaultfd.c | 26 ++++++++++------------
2 files changed, 30 insertions(+), 22 deletions(-)
diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst
index 459e6b66ff68..0c9120ec58ae 100644
--- a/Documentation/arm64/tagged-address-abi.rst
+++ b/Documentation/arm64/tagged-address-abi.rst
@@ -45,14 +45,24 @@ how the user addresses are used by the kernel:
1. User addresses not accessed by the kernel but used for address space
management (e.g. ``mprotect()``, ``madvise()``). The use of valid
- tagged pointers in this context is allowed with the exception of
- ``brk()``, ``mmap()`` and the ``new_address`` argument to
- ``mremap()`` as these have the potential to alias with existing
- user addresses.
-
- NOTE: This behaviour changed in v5.6 and so some earlier kernels may
- incorrectly accept valid tagged pointers for the ``brk()``,
- ``mmap()`` and ``mremap()`` system calls.
+ tagged pointers in this context is allowed with these exceptions:
+
+ - ``brk()``, ``mmap()`` and the ``new_address`` argument to
+ ``mremap()`` as these have the potential to alias with existing
+ user addresses.
+
+ NOTE: This behaviour changed in v5.6 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for the ``brk()``,
+ ``mmap()`` and ``mremap()`` system calls.
+
+ - The ``range.start``, ``start`` and ``dst`` arguments to the
+ ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from
+ ``userfaultfd()``, as fault addresses subsequently obtained by reading
+ the file descriptor will be untagged, which may otherwise confuse
+ tag-unaware programs.
+
+ NOTE: This behaviour changed in v5.14 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for this system call.
2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
relaxation is disabled by default and the application thread needs to
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f6e0f0c0d0e5..5c2d806e6ae5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1236,23 +1236,21 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
}
static __always_inline int validate_range(struct mm_struct *mm,
- __u64 *start, __u64 len)
+ __u64 start, __u64 len)
{
__u64 task_size = mm->task_size;
- *start = untagged_addr(*start);
-
- if (*start & ~PAGE_MASK)
+ if (start & ~PAGE_MASK)
return -EINVAL;
if (len & ~PAGE_MASK)
return -EINVAL;
if (!len)
return -EINVAL;
- if (*start < mmap_min_addr)
+ if (start < mmap_min_addr)
return -EINVAL;
- if (*start >= task_size)
+ if (start >= task_size)
return -EINVAL;
- if (len > task_size - *start)
+ if (len > task_size - start)
return -EINVAL;
return 0;
}
@@ -1316,7 +1314,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vm_flags |= VM_UFFD_MINOR;
}
- ret = validate_range(mm, &uffdio_register.range.start,
+ ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
if (ret)
goto out;
@@ -1522,7 +1520,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
goto out;
- ret = validate_range(mm, &uffdio_unregister.start,
+ ret = validate_range(mm, uffdio_unregister.start,
uffdio_unregister.len);
if (ret)
goto out;
@@ -1671,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
+ ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
if (ret)
goto out;
@@ -1711,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
sizeof(uffdio_copy)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
+ ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
if (ret)
goto out;
/*
@@ -1768,7 +1766,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
sizeof(uffdio_zeropage)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
+ ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
if (ret)
goto out;
@@ -1818,7 +1816,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
sizeof(struct uffdio_writeprotect)))
return -EFAULT;
- ret = validate_range(ctx->mm, &uffdio_wp.range.start,
+ ret = validate_range(ctx->mm, uffdio_wp.range.start,
uffdio_wp.range.len);
if (ret)
return ret;
@@ -1866,7 +1864,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
sizeof(uffdio_continue) - (sizeof(__s64))))
goto out;
- ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+ ret = validate_range(ctx->mm, uffdio_continue.range.start,
uffdio_continue.range.len);
if (ret)
goto out;
--
2.32.0.93.g670b81a890-goog
