[PATCH v2] mm: Split critical region in remap_file_pages() and invoke LSMs in between

[Liam R. Howlett]

* Roberto Sassu <roberto.sassu at huaweicloud.com> [241018 12:15]:
> From: "Kirill A. Shutemov" <kirill.shutemov at linux.intel.com>
> 
> Commit ea7e2d5e49c0 ("mm: call the security_mmap_file() LSM hook in
> remap_file_pages()") fixed a security issue, it added an LSM check when
> trying to remap file pages, so that LSMs have the opportunity to evaluate
> such action like for other memory operations such as mmap() and mprotect().
> 
> However, that commit called security_mmap_file() inside the mmap_lock lock,
> while the other calls do it before taking the lock, after commit
> 8b3ec6814c83 ("take security_mmap_file() outside of ->mmap_sem").
> 
> This caused lock inversion issue with IMA which was taking the mmap_lock
> and i_mutex lock in the opposite way when the remap_file_pages() system
> call was called.
> 
> Solve the issue by splitting the critical region in remap_file_pages() in
> two regions: the first takes a read lock of mmap_lock, retrieves the VMA
> and the file descriptor associated, and calculates the 'prot' and 'flags'
> variables; the second takes a write lock on mmap_lock, checks that the VMA
> flags and the VMA file descriptor are the same as the ones obtained in the
> first critical region (otherwise the system call fails), and calls
> do_mmap().
> 
> In between, after releasing the read lock and before taking the write lock,
> call security_mmap_file(), and solve the lock inversion issue.
> 
> Cc: stable at vger.kernel.org # v6.12-rcx
> Fixes: ea7e2d5e49c0 ("mm: call the security_mmap_file() LSM hook in remap_file_pages()")
> Reported-by: syzbot+1cd571a672400ef3a930 at syzkaller.appspotmail.com
> Closes: https://lore.kernel.org/linux-security-module/66f7b10e.050a0220.46d20.0036.GAE@google.com/
> Reviewed-by: Roberto Sassu <roberto.sassu at huawei.com>
> Reviewed-by: Jann Horn <jannh at google.com>
> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes at oracle.com>
> Tested-by: Roberto Sassu <roberto.sassu at huawei.com>
> Tested-by: syzbot+1cd571a672400ef3a930 at syzkaller.appspotmail.com
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>

You really need to be in that list of people :)

Please add your own signed-off-by.

Besides the missing SOB, it looks good.

Reviewed-by: Liam R. Howlett <Liam.Howlett at Oracle.com>

> ---
>  mm/mmap.c | 69 +++++++++++++++++++++++++++++++++++++++++--------------
>  1 file changed, 52 insertions(+), 17 deletions(-)
> 
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 9c0fb43064b5..f731dd69e162 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1640,6 +1640,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
>  	unsigned long populate = 0;
>  	unsigned long ret = -EINVAL;
>  	struct file *file;
> +	vm_flags_t vm_flags;
>  
>  	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
>  		     current->comm, current->pid);
> @@ -1656,12 +1657,60 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
>  	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
>  		return ret;
>  
> -	if (mmap_write_lock_killable(mm))
> +	if (mmap_read_lock_killable(mm))
>  		return -EINTR;
>  
> +	/*
> +	 * Look up VMA under read lock first so we can perform the security
> +	 * without holding locks (which can be problematic). We reacquire a
> +	 * write lock later and check nothing changed underneath us.
> +	 */
>  	vma = vma_lookup(mm, start);
>  
> -	if (!vma || !(vma->vm_flags & VM_SHARED))
> +	if (!vma || !(vma->vm_flags & VM_SHARED)) {
> +		mmap_read_unlock(mm);
> +		return -EINVAL;
> +	}
> +
> +	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
> +	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
> +	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
> +
> +	flags &= MAP_NONBLOCK;
> +	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
> +	if (vma->vm_flags & VM_LOCKED)
> +		flags |= MAP_LOCKED;
> +
> +	/* Save vm_flags used to calculate prot and flags, and recheck later. */
> +	vm_flags = vma->vm_flags;
> +	file = get_file(vma->vm_file);
> +
> +	mmap_read_unlock(mm);
> +
> +	/* Call outside mmap_lock to be consistent with other callers. */
> +	ret = security_mmap_file(file, prot, flags);
> +	if (ret) {
> +		fput(file);
> +		return ret;
> +	}
> +
> +	ret = -EINVAL;
> +
> +	/* OK security check passed, take write lock + let it rip. */
> +	if (mmap_write_lock_killable(mm)) {
> +		fput(file);
> +		return -EINTR;
> +	}
> +
> +	vma = vma_lookup(mm, start);
> +
> +	if (!vma)
> +		goto out;
> +
> +	/* Make sure things didn't change under us. */
> +	if (vma->vm_flags != vm_flags)
> +		goto out;
> +	if (vma->vm_file != file)
>  		goto out;
>  
>  	if (start + size > vma->vm_end) {
> @@ -1689,25 +1738,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
>  			goto out;
>  	}
>  
> -	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
> -	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
> -	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
> -
> -	flags &= MAP_NONBLOCK;
> -	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
> -	if (vma->vm_flags & VM_LOCKED)
> -		flags |= MAP_LOCKED;
> -
> -	file = get_file(vma->vm_file);
> -	ret = security_mmap_file(vma->vm_file, prot, flags);
> -	if (ret)
> -		goto out_fput;
>  	ret = do_mmap(vma->vm_file, start, size,
>  			prot, flags, 0, pgoff, &populate, NULL);
> -out_fput:
> -	fput(file);
>  out:
>  	mmap_write_unlock(mm);
> +	fput(file);
>  	if (populate)
>  		mm_populate(ret, populate);
>  	if (!IS_ERR_VALUE(ret))
> -- 
> 2.34.1
>