IronPort-SDR: MoD+9Yv2wQf2rhjlhIylaQBKErd+zeo1XgTDdHlsHEIRuzxkhGhJlJWuxnVaL/jMHOhzSefFJK
 lk/Y0DOMJlQwU9ReoYAQ8vKoyyr18vc1az8aFyiuSHniAAMIBOhg53IsU7ParOYc28qpCNtsj7
 bV4Yt1aAgQp57g0i1izRepRm2t/SpKP/Rtuhqp5waxRH/ozu/TYNCxM2GZkoAbzo18bEHI2Wa6
 n7sZut+7Pl/vhgUIbplErPyDR67lNpbaUBxRY6IKk93OrMylCo6hqUQLV9qNCAUxA6kh2Ot1/E
 MepyAA6jKxCRmya6ybeH/2Q+
IronPort-SDR: lqQCbEA7coEE2+3vKaJOxIckrPPfyJc7yLqPNBH3c2Bi9nOc8iYaso8+du9bKXVJR/AGxw9v5j
 bSrGVZC1e7d/UcUyxjZizBwjZT2OWfx0BoWR4FVodaPh+bda4V5YjBErGWyFOl9ic471sybozL
 2dqdooc5a37emcSJdMB77iKKPEKhVguCPcDvUmdkjmjA4sOuvZ/pw6z9nd/QSi7DVYdKxO+1W5
 n79oxfco+Rz8BWpRtE1x4g4j/DXd6HSpj0G5aWKKbLE+tNq1E983RhOHItUiwUUTIjKyKyTw21
 ktY=
WDCIronportException: Internal
From:   Alistair Francis <alistair.francis@opensource.wdc.com>
To:     linux-kernel@vger.kernel.org
Cc:     tglx@linutronix.de, arnd@arndb.de, namhyung@kernel.org,
        peterz@infradead.org, alistair23@gmail.com, jolsa@redhat.com,
        dave@stgolabs.net, mingo@redhat.com, dvhart@infradead.org,
        acme@kernel.org, linux-perf-users@vger.kernel.org,
        mark.rutland@arm.com, alexander.shishkin@linux.intel.com,
        Alistair Francis <alistair.francis@wdc.com>
Subject: [PATCH v3 3/6] uapi: futex: Add a futex syscall
Date:   Fri, 26 Nov 2021 16:00:21 +1000
Message-Id: <20211126060024.3290177-3-alistair.francis@opensource.wdc.com>
In-Reply-To: <20211126060024.3290177-1-alistair.francis@opensource.wdc.com>
References: <20211126060024.3290177-1-alistair.francis@opensource.wdc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

From: Alistair Francis <alistair.francis@wdc.com>

This commit adds two futex syscall wrappers that are exposed to
userspace.

Neither the kernel or glibc currently expose a futex wrapper, so
userspace is left performing raw syscalls. This has mostly been because
the overloading of one of the arguments makes it impossible to provide a
single type safe function.

Until recently the single syscall has worked fine. With the introduction
of a 64-bit time_t futex call on 32-bit architectures, this has become
more complex. The logic of handling the two possible futex syscalls is
complex and often implemented incorrectly.

This patch adds two futux syscall functions that correctly handle the
time_t complexity for userspace.

This idea is based on previous discussions:
https://lore.kernel.org/lkml/CAK8P3a3x_EyCiPDpMK54y=3DRtm-Wb08ym2TNiuAZgX=
hYrThcWTw@mail.gmail.com/

Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 include/uapi/linux/futex_syscall.h | 89 ++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)
 create mode 100644 include/uapi/linux/futex_syscall.h

diff --git a/include/uapi/linux/futex_syscall.h b/include/uapi/linux/fute=
x_syscall.h
new file mode 100644
index 000000000000..e0305c581142
--- /dev/null
+++ b/include/uapi/linux/futex_syscall.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Futex syscall helper functions
+ *
+ * Copyright (C) 2021 Western Digital.  All Rights Reserved.
+ *
+ * Author: Alistair Francis <alistair.francis@wdc.com>
+ */
+#ifndef _UAPI_LINUX_FUTEX_SYSCALL_H
+#define _UAPI_LINUX_FUTEX_SYSCALL_H
+
+#include <asm/unistd.h>
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/time_types.h>
+#include <stdint.h>
+#include <sys/syscall.h>
+
+/**
+ * futex_syscall_timeout() - __NR_futex/__NR_futex_time64 syscall wrappe=
r
+ * @uaddr:  address of first futex
+ * @op:   futex op code
+ * @val:  typically expected value of uaddr, but varies by op
+ * @timeout:  an absolute struct timespec
+ * @uaddr2: address of second futex for some ops
+ * @val3: varies by op
+ */
+static inline int
+__kernel_futex_syscall_timeout(volatile uint32_t *uaddr, int op, uint32_=
t val,
+		      struct timespec *timeout, volatile uint32_t *uaddr2, int val3)
+{
+#if defined(__NR_futex_time64)
+	if (sizeof(*timeout) !=3D sizeof(struct __kernel_old_timespec)) {
+		int ret =3D syscall(__NR_futex_time64, uaddr, op, val, timeout, uaddr2=
, val3);
+
+		if (ret =3D=3D 0 || errno !=3D ENOSYS)
+			return ret;
+	}
+#endif
+
+#if defined(__NR_futex)
+	if (sizeof(*timeout) =3D=3D sizeof(struct __kernel_old_timespec))
+		return syscall(__NR_futex, uaddr, op, val, timeout, uaddr2, val3);
+
+	if (timeout && timeout->tv_sec =3D=3D (long)timeout->tv_sec) {
+		struct __kernel_old_timespec ts_old;
+
+		ts_old.tv_sec =3D (__kernel_long_t) timeout->tv_sec;
+		ts_old.tv_nsec =3D (__kernel_long_t) timeout->tv_nsec;
+
+		return syscall(__NR_futex, uaddr, op, val, &ts_old, uaddr2, val3);
+	} else if (!timeout) {
+		return syscall(__NR_futex, uaddr, op, val, NULL, uaddr2, val3);
+	}
+#endif
+
+	errno =3D ENOSYS;
+	return -1;
+}
+
+/**
+ * futex_syscall_nr_requeue() - __NR_futex/__NR_futex_time64 syscall wra=
pper
+ * @uaddr:  address of first futex
+ * @op:   futex op code
+ * @val:  typically expected value of uaddr, but varies by op
+ * @nr_requeue:  an op specific meaning
+ * @uaddr2: address of second futex for some ops
+ * @val3: varies by op
+ */
+static inline int
+__kernel_futex_syscall_nr_requeue(volatile uint32_t *uaddr, int op, uint=
32_t val,
+			 uint32_t nr_requeue, volatile uint32_t *uaddr2, int val3)
+{
+#if defined(__NR_futex_time64)
+	int ret =3D  syscall(__NR_futex_time64, uaddr, op, val, nr_requeue, uad=
dr2, val3);
+
+	if (ret =3D=3D 0 || errno !=3D ENOSYS)
+		return ret;
+#endif
+
+#if defined(__NR_futex)
+	return syscall(__NR_futex, uaddr, op, val, nr_requeue, uaddr2, val3);
+#endif
+
+	errno =3D ENOSYS;
+	return -1;
+}
+
+#endif /* _UAPI_LINUX_FUTEX_SYSCALL_H */
--=20
2.31.1