[PATCH 1/5] WIP: Add syscall unlinkat_s (currently x86* only)

[Alexander Holler <holler@ahsoftware.de>]

Signed-off-by: Alexander Holler <holler@ahsoftware.de>
---
 arch/x86/syscalls/syscall_32.tbl      |  1 +
 arch/x86/syscalls/syscall_64.tbl      |  1 +
 fs/namei.c                            | 38 ++++++++++++++++++++++++++++++-----
 include/asm-generic/audit_dir_write.h |  1 +
 include/linux/fs.h                    |  1 +
 include/linux/syscalls.h              |  1 +
 include/uapi/asm-generic/unistd.h     |  4 +++-
 tools/perf/builtin-trace.c            |  2 ++
 8 files changed, 43 insertions(+), 6 deletions(-)

diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 9fe1b5d..7a3d530 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -364,3 +364,4 @@
 355	i386	getrandom		sys_getrandom
 356	i386	memfd_create		sys_memfd_create
 357	i386	bpf			sys_bpf
+359	i386	unlinkat_s		sys_unlinkat_s
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 281150b..97eaf01 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -328,6 +328,7 @@
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
+322	common	unlinkat_s		sys_unlinkat_s
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/namei.c b/fs/namei.c
index db5fe86..1ad3724 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3717,7 +3717,7 @@ EXPORT_SYMBOL(vfs_unlink);
  * writeout happening, and we don't want to prevent access to the directory
  * while waiting on the I/O.
  */
-static long do_unlinkat(int dfd, const char __user *pathname)
+static long do_unlinkat(int dfd, const char __user *pathname, bool secure)
 {
 	int error;
 	struct filename *name;
@@ -3759,8 +3759,25 @@ exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-	if (inode)
-		iput(inode);	/* truncate the inode here */
+	if (inode) {
+		// TODO:
+		// if (inode is file and 's' flag is set)
+		// 	secure = true;
+		if (!secure)
+			iput(inode);	/* truncate the inode here */
+		else {
+			struct super_block *sb = inode->i_sb;
+			if (sb->s_op->set_secure_delete)
+				sb->s_op->set_secure_delete(sb, true);
+			// TODO: We should fail if secure isn't supported,
+			// look up how that's possible here.
+			iput(inode);	/* truncate the inode here */
+			// TODO: check if sb is still valid after the inode is gone
+			sync_filesystem(sb);
+			if (sb->s_op->set_secure_delete)
+				sb->s_op->set_secure_delete(sb, false);
+		}
+	}
 	inode = NULL;
 	if (delegated_inode) {
 		error = break_deleg_wait(&delegated_inode);
@@ -3796,12 +3813,23 @@ SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
 	if (flag & AT_REMOVEDIR)
 		return do_rmdir(dfd, pathname);
 
-	return do_unlinkat(dfd, pathname);
+	return do_unlinkat(dfd, pathname, false);
 }
 
 SYSCALL_DEFINE1(unlink, const char __user *, pathname)
 {
-	return do_unlinkat(AT_FDCWD, pathname);
+	return do_unlinkat(AT_FDCWD, pathname, false);
+}
+
+SYSCALL_DEFINE3(unlinkat_s, int, dfd, const char __user *, pathname, int, flag)
+{
+	if ((flag & ~AT_REMOVEDIR) != 0)
+		return -EINVAL;
+
+	if (flag & AT_REMOVEDIR)
+		return do_rmdir(dfd, pathname);
+
+	return do_unlinkat(dfd, pathname, true);
 }
 
 int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
diff --git a/include/asm-generic/audit_dir_write.h b/include/asm-generic/audit_dir_write.h
index 7b61db4..5282aba 100644
--- a/include/asm-generic/audit_dir_write.h
+++ b/include/asm-generic/audit_dir_write.h
@@ -29,4 +29,5 @@ __NR_unlinkat,
 __NR_renameat,
 __NR_linkat,
 __NR_symlinkat,
+__NR_unlinkat_s,
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9ab779e..039e969 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1594,6 +1594,7 @@ struct super_operations {
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 	long (*nr_cached_objects)(struct super_block *, int);
 	long (*free_cached_objects)(struct super_block *, long, int);
+	void (*set_secure_delete) (struct super_block *, bool);
 };
 
 /*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index bda9b81..b88019b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -877,4 +877,5 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
 asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+asmlinkage long sys_unlinkat_s(int dfd, const char __user * pathname, int flag);
 #endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 22749c1..2ba072e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -707,9 +707,11 @@ __SYSCALL(__NR_getrandom, sys_getrandom)
 __SYSCALL(__NR_memfd_create, sys_memfd_create)
 #define __NR_bpf 280
 __SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_unlinkat_s 281
+__SYSCALL(__NR_unlinkat_s, sys_unlinkat_s)
 
 #undef __NR_syscalls
-#define __NR_syscalls 281
+#define __NR_syscalls 282
 
 /*
  * All syscalls below here should go away really,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index fb12645..1507335 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1110,6 +1110,8 @@ static struct syscall_fmt {
 	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
 	{ .name	    = "unlinkat",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
+	{ .name	    = "unlinkat_s",   .errmsg = true,
+	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
 	{ .name	    = "utimensat",  .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
 	{ .name	    = "write",	    .errmsg = true,
-- 
2.1.0