From:   Chao Peng <chao.p.peng@linux.intel.com>
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
        qemu-devel@nongnu.org
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        Jonathan Corbet <corbet@lwn.net>,
        Sean Christopherson <seanjc@google.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
        Hugh Dickins <hughd@google.com>,
        Jeff Layton <jlayton@kernel.org>,
        "J . Bruce Fields" <bfields@fieldses.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Yu Zhang <yu.c.zhang@linux.intel.com>,
        Chao Peng <chao.p.peng@linux.intel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        luto@kernel.org, john.ji@intel.com, susie.li@intel.com,
        jun.nakajima@intel.com, dave.hansen@intel.com, ak@linux.intel.com,
        david@redhat.com
Subject: [PATCH v3 kvm/queue 02/16] mm/memfd: Introduce MFD_INACCESSIBLE flag
Date:   Thu, 23 Dec 2021 20:29:57 +0800
Message-Id: <20211223123011.41044-3-chao.p.peng@linux.intel.com>
In-Reply-To: <20211223123011.41044-1-chao.p.peng@linux.intel.com>
References: <20211223123011.41044-1-chao.p.peng@linux.intel.com>
Precedence: bulk

Introduce a new memfd_create() flag indicating the content of the
created memfd is inaccessible from userspace. It does this by force
setting F_SEAL_INACCESSIBLE seal when the file is created. It also set
F_SEAL_SEAL to prevent future sealing, which means, it can not coexist
with MFD_ALLOW_SEALING.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
 include/uapi/linux/memfd.h |  1 +
 mm/memfd.c                 | 12 +++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 7a8a26751c23..48750474b904 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -8,6 +8,7 @@
 #define MFD_CLOEXEC		0x0001U
 #define MFD_ALLOW_SEALING	0x0002U
 #define MFD_HUGETLB		0x0004U
+#define MFD_INACCESSIBLE	0x0008U
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
diff --git a/mm/memfd.c b/mm/memfd.c
index 9f80f162791a..c898a007fb76 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -245,7 +245,8 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
 #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
 
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | \
+		       MFD_INACCESSIBLE)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
@@ -267,6 +268,10 @@ SYSCALL_DEFINE2(memfd_create,
 			return -EINVAL;
 	}
 
+	/* Disallow sealing when MFD_INACCESSIBLE is set. */
+	if (flags & MFD_INACCESSIBLE && flags & MFD_ALLOW_SEALING)
+		return -EINVAL;
+
 	/* length includes terminating zero */
 	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
 	if (len <= 0)
@@ -315,6 +320,11 @@ SYSCALL_DEFINE2(memfd_create,
 		*file_seals &= ~F_SEAL_SEAL;
 	}
 
+	if (flags & MFD_INACCESSIBLE) {
+		file_seals = memfd_file_seals_ptr(file);
+		*file_seals &= F_SEAL_SEAL | F_SEAL_INACCESSIBLE;
+	}
+
 	fd_install(fd, file);
 	kfree(name);
 	return fd;
-- 
2.17.1