All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: viro@zeniv.linux.org.uk
Cc: Avi Kivity <avi@scylladb.com>,
	linux-aio@kvack.org, linux-fsdevel@vger.kernel.org,
	linux-api@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH 7/7] aio: implement io_pgetevents
Date: Sun, 15 Apr 2018 17:01:08 +0200	[thread overview]
Message-ID: <20180415150108.1341-8-hch@lst.de> (raw)
In-Reply-To: <20180415150108.1341-1-hch@lst.de>

This is the io_getevents equivalent of ppoll/pselect and allows to
properly mix signals and aio completions (especially with IOCB_CMD_POLL)
and atomically executes the following sequence:

	sigset_t origmask;

	pthread_sigmask(SIG_SETMASK, &sigmask, &origmask);
	ret = io_getevents(ctx, min_nr, nr, events, timeout);
	pthread_sigmask(SIG_SETMASK, &origmask, NULL);

Note that unlike many other signal related calls we do not pass a sigmask
size, as that would get us to 7 arguments, which aren't easily supported
by the syscall infrastructure.  It seems a lot less painful to just add a
new syscall variant in the unlikely case we're going to increase the
sigset size.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 arch/x86/entry/syscalls/syscall_32.tbl |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl |   1 +
 fs/aio.c                               | 114 ++++++++++++++++++++++---
 include/linux/compat.h                 |   7 ++
 include/linux/syscalls.h               |   6 ++
 include/uapi/asm-generic/unistd.h      |   4 +-
 include/uapi/linux/aio_abi.h           |   6 ++
 kernel/sys_ni.c                        |   2 +
 8 files changed, 130 insertions(+), 11 deletions(-)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c58f75b088c5..99b6f7a36178 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -391,3 +391,4 @@
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
 384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+385	i386	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183e2f85..e995cd2b4e65 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -339,6 +339,7 @@
 330	common	pkey_alloc		sys_pkey_alloc
 331	common	pkey_free		sys_pkey_free
 332	common	statx			sys_statx
+333	common	io_pgetevents		sys_io_pgetevents
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/aio.c b/fs/aio.c
index de56496ba86c..5cfeb5bc3a7d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1303,10 +1303,6 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 		wait_event_interruptible_hrtimeout(ctx->wait,
 				aio_read_events(ctx, min_nr, nr, event, &ret),
 				until);
-
-	if (!ret && signal_pending(current))
-		ret = -EINTR;
-
 	return ret;
 }
 
@@ -1913,13 +1909,60 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 		struct timespec __user *, timeout)
 {
 	struct timespec64	ts;
+	int			ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
 
-	if (timeout) {
-		if (unlikely(get_timespec64(&ts, timeout)))
+SYSCALL_DEFINE6(io_pgetevents,
+		aio_context_t, ctx_id,
+		long, min_nr,
+		long, nr,
+		struct io_event __user *, events,
+		struct timespec __user *, timeout,
+		const struct __aio_sigset __user *, usig)
+{
+	struct __aio_sigset	ksig = { NULL, };
+	sigset_t		ksigmask, sigsaved;
+	struct timespec64	ts;
+	int ret;
+
+	if (timeout && unlikely(get_timespec64(&ts, timeout)))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
+
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ksigmask, ksig.sigmask, sizeof(ksigmask)))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT
@@ -1930,13 +1973,64 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
 		       struct compat_timespec __user *, timeout)
 {
 	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+	return ret;
+}
+
 
-	if (timeout) {
-		if (compat_get_timespec64(&t, timeout))
+struct __compat_aio_sigset {
+	compat_sigset_t __user	*sigmask;
+	compat_size_t		sigsetsize;
+};
+
+COMPAT_SYSCALL_DEFINE6(io_pgetevents,
+		compat_aio_context_t, ctx_id,
+		compat_long_t, min_nr,
+		compat_long_t, nr,
+		struct io_event __user *, events,
+		struct compat_timespec __user *, timeout,
+		const struct __compat_aio_sigset __user *, usig)
+{
+	struct __compat_aio_sigset ksig = { NULL, };
+	sigset_t ksigmask, sigsaved;
+	struct timespec64 t;
+	int ret;
+
+	if (timeout && compat_get_timespec64(&t, timeout))
+		return -EFAULT;
+
+	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+		return -EFAULT;
+
+	if (ksig.sigmask) {
+		if (ksig.sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (get_compat_sigset(&ksigmask, ksig.sigmask))
 			return -EFAULT;
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
 
+	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	if (signal_pending(current)) {
+		if (ksig.sigmask) {
+			current->saved_sigmask = sigsaved;
+			set_restore_sigmask();
+		}
+		if (!ret)
+			ret = -ERESTARTNOHAND;
+	} else {
+		if (ksig.sigmask)
+			sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 	}
 
-	return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+	return ret;
 }
 #endif
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f188eab10570..fdd068f192c1 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -310,6 +310,7 @@ extern int put_compat_rusage(const struct rusage *,
 			     struct compat_rusage __user *);
 
 struct compat_siginfo;
+struct __compat_aio_sigset;
 
 struct compat_dirent {
 	u32		d_ino;
@@ -528,6 +529,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
 					compat_long_t nr,
 					struct io_event __user *events,
 					struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+					compat_long_t min_nr,
+					compat_long_t nr,
+					struct io_event __user *events,
+					struct compat_timespec __user *timeout,
+					const struct __compat_aio_sigset __user *usig);
 
 /* fs/cookies.c */
 asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b961184f597a..c40cf5ec24c9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -264,6 +264,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
 				long nr,
 				struct io_event __user *events,
 				struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+				long min_nr,
+				long nr,
+				struct io_event __user *events,
+				struct timespec __user *timeout,
+				const struct __aio_sigset *sig);
 
 /* fs/xattr.c */
 asmlinkage long sys_setxattr(const char __user *path, const char __user *name,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8bcb186c6f67..42990676a55e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 
 #undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc70ddf..2c0a3415beee 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,6 +29,7 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
+#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -108,5 +109,10 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
+struct __aio_sigset {
+	sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 #endif /* __LINUX__AIO_ABI_H */
 
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 6cafc008f6db..7571cf9d7424 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -33,7 +33,9 @@ COND_SYSCALL(io_submit);
 COND_SYSCALL_COMPAT(io_submit);
 COND_SYSCALL(io_cancel);
 COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents);
 COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents);
 
 /* fs/xattr.c */
 
-- 
2.17.0


  parent reply	other threads:[~2018-04-15 15:02 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-15 15:01 io_pgetevents & aio fsync V3 Christoph Hellwig
2018-04-15 15:01 ` [PATCH 1/7] aio: don't print the page size at boot time Christoph Hellwig
2018-04-15 15:01 ` [PATCH 2/7] aio: remove an outdated BUG_ON and comment in aio_complete Christoph Hellwig
2018-04-15 15:01   ` Christoph Hellwig
2018-04-24 21:27   ` Darrick J. Wong
2018-04-24 21:27     ` Darrick J. Wong
2018-04-15 15:01 ` [PATCH 3/7] aio: sanitize ki_list handling Christoph Hellwig
2018-04-15 15:01   ` Christoph Hellwig
2018-04-15 15:01 ` [PATCH 4/7] aio: remove the extra get_file/fput pair in io_submit_one Christoph Hellwig
2018-04-26 15:41   ` Darrick J. Wong
2018-04-26 15:41     ` Darrick J. Wong
2018-04-15 15:01 ` [PATCH 5/7] aio: refactor read/write iocb setup Christoph Hellwig
2018-04-15 15:01   ` Christoph Hellwig
2018-04-15 15:01 ` [PATCH 6/7] aio: implement IOCB_CMD_FSYNC and IOCB_CMD_FDSYNC Christoph Hellwig
2018-04-15 15:01   ` Christoph Hellwig
2018-04-15 15:01 ` Christoph Hellwig [this message]
2018-05-02 21:14 io_pgetevents & aio fsync V4 Christoph Hellwig
2018-05-02 21:14 ` [PATCH 7/7] aio: implement io_pgetevents Christoph Hellwig
2018-05-18  8:28   ` James Hogan
2018-05-18  8:57     ` Christoph Hellwig
2018-07-04 14:21   ` Adrian Reber
2018-07-04 14:21     ` Adrian Reber
2018-07-08 20:44     ` Christoph Hellwig
2018-07-08 20:44       ` Christoph Hellwig
2018-07-09 17:20       ` Stephan Müller
2018-07-09 19:21       ` Stephan Müller
2018-07-10 12:51         ` Christoph Hellwig
2018-07-10 12:51           ` Christoph Hellwig
2018-07-10 12:51           ` Christoph Hellwig
2018-07-10  5:11       ` Andrei Vagin
2018-07-10  5:11         ` Andrei Vagin

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=20180415150108.1341-8-hch@lst.de \
    --to=hch@lst.de \
    --cc=avi@scylladb.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.