Date:   Mon, 30 Jan 2023 05:26:29 +0000
In-Reply-To: <20221202061347.1070246-2-chao.p.peng@linux.intel.com> (message
 from Chao Peng on Fri,  2 Dec 2022 14:13:39 +0800)
Mime-Version: 1.0
Message-ID: <diqzzga0fv96.fsf@ackerleytng-cloudtop-sg.c.googlers.com>
Subject: Re: [PATCH v10 1/9] mm: Introduce memfd_restricted system call to
 create restricted user memory
From:   Ackerley Tng <ackerleytng@google.com>
To:     Chao Peng <chao.p.peng@linux.intel.com>
Cc:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
        linux-arch@vger.kernel.org, linux-api@vger.kernel.org,
        linux-doc@vger.kernel.org, qemu-devel@nongnu.org,
        pbonzini@redhat.com, corbet@lwn.net, seanjc@google.com,
        vkuznets@redhat.com, wanpengli@tencent.com, jmattson@google.com,
        joro@8bytes.org, tglx@linutronix.de, mingo@redhat.com,
        bp@alien8.de, arnd@arndb.de, naoya.horiguchi@nec.com,
        linmiaohe@huawei.com, x86@kernel.org, hpa@zytor.com,
        hughd@google.com, jlayton@kernel.org, bfields@fieldses.org,
        akpm@linux-foundation.org, shuah@kernel.org, rppt@kernel.org,
        steven.price@arm.com, mail@maciej.szmigiero.name, vbabka@suse.cz,
        vannapurve@google.com, yu.c.zhang@linux.intel.com,
        chao.p.peng@linux.intel.com, kirill.shutemov@linux.intel.com,
        luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
        ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
        ddutile@redhat.com, dhildenb@redhat.com, qperret@google.com,
        tabba@google.com, michael.roth@amd.com, mhocko@suse.com,
        wei.w.wang@intel.com
Content-Type: text/plain; charset="UTF-8"; format=flowed; delsp=yes
Precedence: bulk


> +static int restrictedmem_getattr(struct user_namespace *mnt_userns,
> +				 const struct path *path, struct kstat *stat,
> +				 u32 request_mask, unsigned int query_flags)
> +{
> +	struct inode *inode = d_inode(path->dentry);
> +	struct restrictedmem_data *data = inode->i_mapping->private_data;
> +	struct file *memfd = data->memfd;
> +
> +	return memfd->f_inode->i_op->getattr(mnt_userns, path, stat,
> +					     request_mask, query_flags);

Instead of calling shmem's getattr() with path, we should be using the
the memfd's path.

Otherwise, shmem's getattr() will use restrictedmem's inode instead of
shmem's inode. The private fields will be of the wrong type, and the
host will crash when shmem_is_huge() does SHMEM_SB(inode->i_sb)->huge),
since inode->i_sb->s_fs_info is NULL for the restrictedmem's superblock.

Here's the patch:

diff --git a/mm/restrictedmem.c b/mm/restrictedmem.c
index 37191cd9eed1..06b72d593bd8 100644
--- a/mm/restrictedmem.c
+++ b/mm/restrictedmem.c
@@ -84,7 +84,7 @@ static int restrictedmem_getattr(struct user_namespace  
*mnt_userns,
  	struct restrictedmem *rm = inode->i_mapping->private_data;
  	struct file *memfd = rm->memfd;

-	return memfd->f_inode->i_op->getattr(mnt_userns, path, stat,
+	return memfd->f_inode->i_op->getattr(mnt_userns, &memfd->f_path, stat,
  					     request_mask, query_flags);
  }

> +}
> +
> +static int restrictedmem_setattr(struct user_namespace *mnt_userns,
> +				 struct dentry *dentry, struct iattr *attr)
> +{
> +	struct inode *inode = d_inode(dentry);
> +	struct restrictedmem_data *data = inode->i_mapping->private_data;
> +	struct file *memfd = data->memfd;
> +	int ret;
> +
> +	if (attr->ia_valid & ATTR_SIZE) {
> +		if (memfd->f_inode->i_size)
> +			return -EPERM;
> +
> +		if (!PAGE_ALIGNED(attr->ia_size))
> +			return -EINVAL;
> +	}
> +
> +	ret = memfd->f_inode->i_op->setattr(mnt_userns,
> +					    file_dentry(memfd), attr);
> +	return ret;
> +}
> +
> +static const struct inode_operations restrictedmem_iops = {
> +	.getattr = restrictedmem_getattr,
> +	.setattr = restrictedmem_setattr,
> +};