linux-toradex.git/fs/binfmt_elf_fdpic.c, branch v6.14-rc4

fs: don't block write during exec on pre-content watched files

2024-12-11T16:45:18+00:00

Commit 2a010c412853 ("fs: don't block i_writecount during exec") removed
the legacy behavior of getting ETXTBSY on attempt to open and executable
file for write while it is being executed.

This commit was reverted because an application that depends on this
legacy behavior was broken by the change.

We need to allow HSM writing into executable files while executed to
fill their content on-the-fly.

To that end, disable the ETXTBSY legacy behavior for files that are
watched by pre-content events.

This change is not expected to cause regressions with existing systems
which do not have any pre-content event listeners.

Signed-off-by: Amir Goldstein 
Acked-by: Christian Brauner 
Signed-off-by: Jan Kara 
Link: https://patch.msgid.link/20241128142532.465176-1-amir73il@gmail.com

Revert "fs: don't block i_writecount during exec"

2024-11-27T11:51:30+00:00

This reverts commit 2a010c41285345da60cece35575b4e0af7e7bf44.

Rui Ueyama  writes:

> I'm the creator and the maintainer of the mold linker
> (https://github.com/rui314/mold). Recently, we discovered that mold
> started causing process crashes in certain situations due to a change
> in the Linux kernel. Here are the details:
>
> - In general, overwriting an existing file is much faster than
> creating an empty file and writing to it on Linux, so mold attempts to
> reuse an existing executable file if it exists.
>
> - If a program is running, opening the executable file for writing
> previously failed with ETXTBSY. If that happens, mold falls back to
> creating a new file.
>
> - However, the Linux kernel recently changed the behavior so that
> writing to an executable file is now always permitted
> (https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2a010c412853).
>
> That caused mold to write to an executable file even if there's a
> process running that file. Since changes to mmap'ed files are
> immediately visible to other processes, any processes running that
> file would almost certainly crash in a very mysterious way.
> Identifying the cause of these random crashes took us a few days.
>
> Rejecting writes to an executable file that is currently running is a
> well-known behavior, and Linux had operated that way for a very long
> time. So, I don’t believe relying on this behavior was our mistake;
> rather, I see this as a regression in the Linux kernel.

Quoting myself from commit 2a010c412853 ("fs: don't block i_writecount during exec")

> Yes, someone in userspace could potentially be relying on this. It's not
> completely out of the realm of possibility but let's find out if that's
> actually the case and not guess.

It seems we found out that someone is relying on this obscure behavior.
So revert the change.

Link: https://github.com/rui314/mold/issues/1361
Link: https://lore.kernel.org/r/4a2bc207-76be-4715-8e12-7fc45a76a125@leemhuis.info
Cc: 
Signed-off-by: Christian Brauner

binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4

2024-10-17T17:38:49+00:00

AT_HWCAP3 and AT_HWCAP4 were recently defined for use on PowerPC in commit
3281366a8e79 ("uapi/auxvec: Define AT_HWCAP3 and AT_HWCAP4 aux vector,
entries"). Since we want to start using AT_HWCAP3 on arm64 add support for
exposing both these new hwcaps via binfmt_elf.

Signed-off-by: Mark Brown 
Acked-by: Kees Cook 
Reviewed-by: Anshuman Khandual 
Link: https://lore.kernel.org/r/20241004-arm64-elf-hwcap3-v2-1-799d1daad8b0@kernel.org
Signed-off-by: Catalin Marinas

binfmt_elf_fdpic: fix AUXV size calculation when ELF_HWCAP2 is defined

2024-08-26T20:00:38+00:00

create_elf_fdpic_tables() does not correctly account the space for the
AUX vector when an architecture has ELF_HWCAP2 defined. Prior to the
commit 10e29251be0e ("binfmt_elf_fdpic: fix /proc//auxv") it
resulted in the last entry of the AUX vector being set to zero, but with
that change it results in a kernel BUG.

Fix that by adding one to the number of AUXV entries (nitems) when
ELF_HWCAP2 is defined.

Fixes: 10e29251be0e ("binfmt_elf_fdpic: fix /proc//auxv")
Cc: stable@vger.kernel.org
Reported-by: Greg Ungerer 
Closes: https://lore.kernel.org/lkml/5b51975f-6d0b-413c-8b38-39a6a45e8821@westnet.com.au/
Signed-off-by: Max Filippov 
Tested-by: Greg Ungerer 
Link: https://lore.kernel.org/r/20240826032745.3423812-1-jcmvbkbc@gmail.com
Signed-off-by: Kees Cook

fs: don't block i_writecount during exec

2024-06-03T13:52:10+00:00

Back in 2021 we already discussed removing deny_write_access() for
executables. Back then I was hesistant because I thought that this might
cause issues in userspace. But even back then I had started taking some
notes on what could potentially depend on this and I didn't come up with
a lot so I've changed my mind and I would like to try this.

Here are some of the notes that I took:

(1) The deny_write_access() mechanism is causing really pointless issues
such as [1]. If a thread in a thread-group opens a file writable,
then writes some stuff, then closing the file descriptor and then
calling execve() they can fail the execve() with ETXTBUSY because
another thread in the thread-group could have concurrently called
fork(). Multi-threaded libraries such as go suffer from this.

(2) There are userspace attacks that rely on overwriting the binary of a
running process. These attacks are _mitigated_ but _not at all
prevented_ from ocurring by the deny_write_access() mechanism.

I'll go over some details. The clearest example of such attacks was
the attack against runC in CVE-2019-5736 (cf. [3]).

An attack could compromise the runC host binary from inside a
_privileged_ runC container. The malicious binary could then be used
to take over the host.

(It is crucial to note that this attack is _not_ possible with
unprivileged containers. IOW, the setup here is already insecure.)

The attack can be made when attaching to a running container or when
starting a container running a specially crafted image. For example,
when runC attaches to a container the attacker can trick it into
executing itself.

This could be done by replacing the target binary inside the
container with a custom binary pointing back at the runC binary
itself. As an example, if the target binary was /bin/bash, this
could be replaced with an executable script specifying the
interpreter path #!/proc/self/exe.

As such when /bin/bash is executed inside the container, instead the
target of /proc/self/exe will be executed. That magic link will
point to the runc binary on the host. The attacker can then proceed
to write to the target of /proc/self/exe to try and overwrite the
runC binary on the host.

However, this will not succeed because of deny_write_access(). Now,
one might think that this would prevent the attack but it doesn't.

To overcome this, the attacker has multiple ways:
* Open a file descriptor to /proc/self/exe using the O_PATH flag and
then proceed to reopen the binary as O_WRONLY through
/proc/self/fd/ and try to write to it in a busy loop from a
separate process. Ultimately it will succeed when the runC binary
exits. After this the runC binary is compromised and can be used
to attack other containers or the host itself.
* Use a malicious shared library annotating a function in there with
the constructor attribute making the malicious function run as an
initializor. The malicious library will then open /proc/self/exe
for creating a new entry under /proc/self/fd/. It'll then call
exec to a) force runC to exit and b) hand the file descriptor off
to a program that then reopens /proc/self/fd/ for writing
(which is now possible because runC has exited) and overwriting
that binary.

To sum up: the deny_write_access() mechanism doesn't prevent such
attacks in insecure setups. It just makes them minimally harder.
That's all.

The only way back then to prevent this is to create a temporary copy
of the calling binary itself when it starts or attaches to
containers. So what I did back then for LXC (and Aleksa for runC)
was to create an anonymous, in-memory file using the memfd_create()
system call and to copy itself into the temporary in-memory file,
which is then sealed to prevent further modifications. This sealed,
in-memory file copy is then executed instead of the original on-disk
binary.

Any compromising write operations from a privileged container to the
host binary will then write to the temporary in-memory binary and
not to the host binary on-disk, preserving the integrity of the host
binary. Also as the temporary, in-memory binary is sealed, writes to
this will also fail.

The point is that deny_write_access() is uselss to prevent these
attacks.

(3) Denying write access to an inode because it's currently used in an
exec path could easily be done on an LSM level. It might need an
additional hook but that should be about it.

(4) The MAP_DENYWRITE flag for mmap() has been deprecated a long time
ago so while we do protect the main executable the bigger portion of
the things you'd think need protecting such as the shared libraries
aren't. IOW, we let anyone happily overwrite shared libraries.

(5) We removed all remaining uses of VM_DENYWRITE in [2]. That means:
(5.1) We removed the legacy uselib() protection for preventing
overwriting of shared libraries. Nobody cared in 3 years.
(5.2) We allow write access to the elf interpreter after exec
completed treating it on a par with shared libraries.

Yes, someone in userspace could potentially be relying on this. It's not
completely out of the realm of possibility but let's find out if that's
actually the case and not guess.

Link: https://github.com/golang/go/issues/22315 [1]
Link: 49624efa65ac ("Merge tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux") [2]
Link: https://unit42.paloaltonetworks.com/breaking-docker-via-runc-explaining-cve-2019-5736 [3]
Link: https://lwn.net/Articles/866493
Link: https://github.com/golang/go/issues/22220
Link: https://github.com/golang/go/blob/5bf8c0cf09ee5c7e5a37ab90afcce154ab716a97/src/cmd/go/internal/work/buildid.go#L724
Link: https://github.com/golang/go/blob/5bf8c0cf09ee5c7e5a37ab90afcce154ab716a97/src/cmd/go/internal/work/exec.go#L1493
Link: https://github.com/golang/go/blob/5bf8c0cf09ee5c7e5a37ab90afcce154ab716a97/src/cmd/go/internal/script/cmds.go#L457
Link: https://github.com/golang/go/blob/5bf8c0cf09ee5c7e5a37ab90afcce154ab716a97/src/cmd/go/internal/test/test.go#L1557
Link: https://github.com/golang/go/blob/5bf8c0cf09ee5c7e5a37ab90afcce154ab716a97/src/os/exec/lp_linux_test.go#L61
Link: https://github.com/buildkite/agent/pull/2736
Link: https://github.com/rust-lang/rust/issues/114554
Link: https://bugs.openjdk.org/browse/JDK-8068370
Link: https://github.com/dotnet/runtime/issues/58964
Link: https://lore.kernel.org/r/20240531-vfs-i_writecount-v1-1-a17bea7ee36b@kernel.org
Reviewed-by: Josef Bacik
Signed-off-by: Christian Brauner

binfmt_elf_fdpic: fix /proc//auxv

2024-04-24T22:55:28+00:00

Althought FDPIC linux kernel provides /proc//auxv files they are
empty because there's no code that initializes mm->saved_auxv in the
FDPIC ELF loader.

Synchronize FDPIC ELF aux vector setup with ELF. Replace entry-by-entry
aux vector copying to userspace with initialization of mm->saved_auxv
first and then copying it to userspace as a whole.

Signed-off-by: Max Filippov 
Link: https://lore.kernel.org/r/20240322195418.2160164-1-jcmvbkbc@gmail.com
Signed-off-by: Kees Cook

binfmt: replace deprecated strncpy

2024-03-22T03:20:52+00:00

strncpy() is deprecated for use on NUL-terminated destination strings
[1] and as such we should prefer more robust and less ambiguous string
interfaces.

There is a _nearly_ identical implementation of fill_psinfo present in
binfmt_elf.c -- except that one uses get_task_comm over strncpy(). Let's
mirror that in binfmt_elf_fdpic.c

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings [1]
Link: https://github.com/KSPP/linux/issues/90
Cc:  
Signed-off-by: Justin Stitt 
Link: https://lore.kernel.org/r/20240321-strncpy-fs-binfmt_elf_fdpic-c-v2-1-0b6daec6cc56@google.com
Signed-off-by: Kees Cook

fs: binfmt_elf_efpic: don't use missing interpreter's properties

2024-02-05T16:15:11+00:00

Static FDPIC executable may get an executable stack even when it has
non-executable GNU_STACK segment. This happens when STACK segment has rw
permissions, but does not specify stack size. In that case FDPIC loader
uses permissions of the interpreter's stack, and for static executables
with no interpreter it results in choosing the arch-default permissions
for the stack.

Fix that by using the interpreter's properties only when the interpreter
is actually used.

Signed-off-by: Max Filippov 
Link: https://lore.kernel.org/r/20240118150637.660461-1-jcmvbkbc@gmail.com
Signed-off-by: Kees Cook

Merge tag 'execve-v6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

2023-10-31T05:28:19+00:00

Pull execve updates from Kees Cook:

 - Support non-BSS ELF segments with zero filesz

   Eric Biederman and I refactored ELF segment loading to handle the
   case where a segment has a smaller filesz than memsz. Traditionally
   linkers only did this for .bss and it was always the last segment. As
   a result, the kernel only handled this case when it was the last
   segment. We've had two recent cases where linkers were trying to use
   these kinds of segments for other reasons, and the were in the middle
   of the segment list. There was no good reason for the kernel not to
   support this, and the refactor actually ends up making things more
   readable too.

 - Enable namespaced binfmt_misc

   Christian Brauner has made it possible to use binfmt_misc with mount
   namespaces. This means some traditionally root-only interfaces (for
   adding/removing formats) are now more exposed (but believed to be
   safe).

 - Remove struct tag 'dynamic' from ELF UAPI

   Alejandro Colomar noticed that the ELF UAPI has been polluting the
   struct namespace with an unused and overly generic tag named
   "dynamic" for no discernible reason for many many years. After
   double-checking various distro source repositories, it has been
   removed.

 - Clean up binfmt_elf_fdpic debug output (Greg Ungerer)

* tag 'execve-v6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  binfmt_misc: enable sandboxed mounts
  binfmt_misc: cleanup on filesystem umount
  binfmt_elf_fdpic: clean up debug warnings
  mm: Remove unused vm_brk()
  binfmt_elf: Only report padzero() errors when PROT_WRITE
  binfmt_elf: Use elf_load() for library
  binfmt_elf: Use elf_load() for interpreter
  binfmt_elf: elf_bss no longer used by load_elf_binary()
  binfmt_elf: Support segments with 0 filesz and misaligned starts
  elf, uapi: Remove struct tag 'dynamic'

binfmt_elf_fdpic: clean up debug warnings

2023-10-04T02:48:44+00:00

The binfmt_elf_fdpic loader has some debug trace that can be enabled at
build time. The recent 64-bit additions cause some warnings if that
debug is enabled, such as:

    fs/binfmt_elf_fdpic.c: In function ‘elf_fdpic_map_file’:
    fs/binfmt_elf_fdpic.c:46:33: warning: format ‘%x’ expects argument of type ‘unsigned int’, but argument 3 has type ‘Elf64_Addr’ {aka ‘long long unsigned int’} [-Wformat=]
       46 | #define kdebug(fmt, ...) printk("FDPIC "fmt"\n" ,##__VA_ARGS__ )
          |                                 ^~~~~~~~
    ./include/linux/printk.h:427:25: note: in definition of macro ‘printk_index_wrap’
      427 |                 _p_func(_fmt, ##__VA_ARGS__);                           \
          |                         ^~~~

Cast values to the largest possible type (which is equivilent to unsigned
long long in this case) and use appropriate format specifiers to match.

Fixes: b922bf04d2c1 ("binfmt_elf_fdpic: support 64-bit systems")
Signed-off-by: Greg Ungerer 
Link: https://lore.kernel.org/r/20230927132933.3290734-1-gerg@kernel.org
Signed-off-by: Kees Cook