public inbox for [email protected]
 help / color / mirror / Atom feed
From: Josh Triplett <[email protected]>
To: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH WIP 2/3] fs: openat2: Extend open_how to allow userspace-selected fds
Date: Wed, 4 Mar 2020 06:53:39 -0800	[thread overview]
Message-ID: <97dea7c8933ced47208899335fef5b41c13d2ae1.1583333579.git.josh@joshtriplett.org> (raw)
In-Reply-To: <20200304143548.GA407676@localhost>

Inspired by the X protocol's handling of XIDs, allow userspace to select
the file descriptor opened by openat2, so that it can use the resulting
file descriptor in subsequent system calls without waiting for the
response to openat2.

In io_uring, this allows sequences like openat2/read/close without
waiting for the openat2 to complete. Multiple such sequences can
overlap, as long as each uses a distinct file descriptor.

Add a new O_SPECIFIC_FD open flag to enable this behavior, only accepted
by openat2 for now (ignored by open/openat like all unknown flags). Add
an fd field to struct open_how (along with appropriate padding, and
verify that the padding is 0 to allow replacing the padding with a field
in the future).

The file table has a corresponding new function
get_specific_unused_fd_flags, which gets the specified file descriptor
if O_SPECIFIC_FD is set (and the fd isn't -1); otherwise it falls back
to get_unused_fd_flags, to simplify callers.

The specified file descriptor must not already be open; if it is,
get_specific_unused_fd_flags will fail with -EBUSY. This helps catch
userspace errors.

When O_SPECIFIC_FD is set, and fd is not -1, openat2 will use the
specified file descriptor rather than finding the lowest available one.

Test program:

    #include <err.h>
    #include <fcntl.h>
    #include <stdio.h>
    #include <unistd.h>

    int main(void)
    {
        struct open_how how = { .flags = O_RDONLY | O_SPECIFIC_FD, .fd = 42 };
        int fd = openat2(AT_FDCWD, "/dev/null", &how, sizeof(how));
        if (fd < 0)
            err(1, "openat2");
        printf("fd=%d\n", fd); // prints fd=42
        return 0;
    }

Signed-off-by: Josh Triplett <[email protected]>
---
 fs/fcntl.c                       |  2 +-
 fs/file.c                        | 33 ++++++++++++++++++++++++++++++++
 fs/io_uring.c                    |  2 +-
 fs/open.c                        |  6 ++++--
 include/linux/fcntl.h            |  5 +++--
 include/linux/file.h             |  1 +
 include/uapi/asm-generic/fcntl.h |  4 ++++
 include/uapi/linux/openat2.h     |  2 ++
 8 files changed, 49 insertions(+), 6 deletions(-)

diff --git a/fs/fcntl.c b/fs/fcntl.c
index 9bc167562ee8..1396bf8d9357 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -1031,7 +1031,7 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+	BUILD_BUG_ON(22 - 1 /* for O_RDONLY being 0 */ !=
 		HWEIGHT32(
 			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
 			__FMODE_EXEC | __FMODE_NONOTIFY));
diff --git a/fs/file.c b/fs/file.c
index 1b79d4ddedb2..185c54732b4a 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -562,6 +562,39 @@ void put_unused_fd(unsigned int fd)
 
 EXPORT_SYMBOL(put_unused_fd);
 
+int get_specific_unused_fd_flags(unsigned int fd, unsigned flags)
+{
+	int ret;
+	struct fdtable *fdt;
+	struct files_struct *files = current->files;
+
+	if (!(flags & O_SPECIFIC_FD) || fd == -1)
+		return get_unused_fd_flags(flags);
+
+	if (fd >= rlimit(RLIMIT_NOFILE))
+		return -EBADF;
+
+	spin_lock(&files->file_lock);
+	ret = expand_files(files, fd);
+	if (unlikely(ret < 0))
+		goto out_unlock;
+	fdt = files_fdtable(files);
+	if (fdt->fd[fd]) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	__set_open_fd(fd, fdt);
+	if (flags & O_CLOEXEC)
+		__set_close_on_exec(fd, fdt);
+	else
+		__clear_close_on_exec(fd, fdt);
+	ret = fd;
+
+out_unlock:
+	spin_unlock(&files->file_lock);
+	return ret;
+}
+
 /*
  * Install a file pointer in the fd array.
  *
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6a595c13e108..c25d56554d00 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2635,7 +2635,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
 	if (ret)
 		goto err;
 
-	ret = get_unused_fd_flags(req->open.how.flags);
+	ret = get_specific_unused_fd_flags(req->open.how.fd, req->open.how.flags);
 	if (ret < 0)
 		goto err;
 
diff --git a/fs/open.c b/fs/open.c
index 0788b3715731..570166eb11eb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -961,7 +961,7 @@ EXPORT_SYMBOL(open_with_fake_path);
 inline struct open_how build_open_how(int flags, umode_t mode)
 {
 	struct open_how how = {
-		.flags = flags & VALID_OPEN_FLAGS,
+		.flags = flags & VALID_OPEN_FLAGS & ~O_SPECIFIC_FD,
 		.mode = mode & S_IALLUGO,
 	};
 
@@ -1144,7 +1144,7 @@ static long do_sys_openat2(int dfd, const char __user *filename,
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
 
-	fd = get_unused_fd_flags(how->flags);
+	fd = get_specific_unused_fd_flags(how->fd, how->flags);
 	if (fd >= 0) {
 		struct file *f = do_filp_open(dfd, tmp, &op);
 		if (IS_ERR(f)) {
@@ -1194,6 +1194,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename,
 	err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize);
 	if (err)
 		return err;
+	if (tmp.pad != 0)
+		return -EINVAL;
 
 	/* O_LARGEFILE is only allowed for non-O_PATH. */
 	if (!(tmp.flags & O_PATH) && force_o_largefile())
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 7bcdcf4f6ab2..728849bcd8fa 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -10,7 +10,7 @@
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
 	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
-	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
+	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_SPECIFIC_FD)
 
 /* List of all valid flags for the how->upgrade_mask argument: */
 #define VALID_UPGRADE_FLAGS \
@@ -23,7 +23,8 @@
 
 /* List of all open_how "versions". */
 #define OPEN_HOW_SIZE_VER0	24 /* sizeof first published struct */
-#define OPEN_HOW_SIZE_LATEST	OPEN_HOW_SIZE_VER0
+#define OPEN_HOW_SIZE_VER1	32 /* added fd and pad */
+#define OPEN_HOW_SIZE_LATEST	OPEN_HOW_SIZE_VER1
 
 #ifndef force_o_largefile
 #define force_o_largefile() (!IS_ENABLED(CONFIG_ARCH_32BIT_OFF_T))
diff --git a/include/linux/file.h b/include/linux/file.h
index 358202f5951e..1fe67d8009ee 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -89,6 +89,7 @@ extern void set_min_fd(unsigned int min_fd);
 extern unsigned int get_min_fd(void);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
+extern int get_specific_unused_fd_flags(unsigned int fd, unsigned flags);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..d3de5b8b3955 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -89,6 +89,10 @@
 #define __O_TMPFILE	020000000
 #endif
 
+#ifndef O_SPECIFIC_FD
+#define O_SPECIFIC_FD	01000000000	/* open as specified fd */
+#endif
+
 /* a horrid kludge trying to make sure that this will fail on old kernels */
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
 #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      
diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h
index 58b1eb711360..50d1206b64c2 100644
--- a/include/uapi/linux/openat2.h
+++ b/include/uapi/linux/openat2.h
@@ -20,6 +20,8 @@ struct open_how {
 	__u64 flags;
 	__u64 mode;
 	__u64 resolve;
+	__s32 fd;
+	__u32 pad; /* Must be 0 in the current version */
 };
 
 /* how->resolve flags for openat2(2). */
-- 
2.25.1


  parent reply	other threads:[~2020-03-04 14:53 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-04 14:35 [PATCH WIP 0/3] Support userspace-selected fds Josh Triplett
2020-03-04 14:53 ` [PATCH WIP 1/3] fs: Support setting a minimum fd for "lowest available fd" allocation Josh Triplett
2020-03-04 14:53 ` Josh Triplett [this message]
2020-03-04 14:53 ` [PATCH WIP 3/3] fs: pipe2: Support O_SPECIFIC_FD Josh Triplett

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=97dea7c8933ced47208899335fef5b41c13d2ae1.1583333579.git.josh@joshtriplett.org \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox