netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sagi Maimon <maimon.sagi@gmail.com>
To: richardcochran@gmail.com, luto@kernel.org, datglx@linutronix.de,
	mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
	x86@kernel.org, hpa@zytor.com, arnd@arndb.de,
	geert@linux-m68k.org, peterz@infradead.org, hannes@cmpxchg.org,
	sohil.mehta@intel.com, rick.p.edgecombe@intel.com,
	nphamcs@gmail.com, palmer@sifive.com, maimon.sagi@gmail.com,
	keescook@chromium.org, legion@kernel.org, mark.rutland@arm.com
Cc: linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	linux-arch@vger.kernel.org, netdev@vger.kernel.org
Subject: [PATCH v3] posix-timers: add multi_clock_gettime system call
Date: Thu, 28 Dec 2023 14:24:11 +0200	[thread overview]
Message-ID: <20231228122411.3189-1-maimon.sagi@gmail.com> (raw)

Some user space applications need to read some clocks.
Each read requires moving from user space to kernel space.
The syscall overhead causes unpredictable delay between N clocks reads
Removing this delay causes better synchronization between N clocks.

Introduce a new system call multi_clock_gettime, which can be used to measure
the offset between multiple clocks, from variety of types: PHC, virtual PHC
and various system clocks (CLOCK_REALTIME, CLOCK_MONOTONIC, etc).
The offset includes the total time that the driver needs to read the clock
timestamp.

New system call allows the reading of a list of clocks - up to PTP_MAX_CLOCKS.
Supported clocks IDs: PHC, virtual PHC and various system clocks.
Up to PTP_MAX_SAMPLES times (per clock) in a single system call read.
The system call returns n_clocks timestamps for each measurement:
- clock 0 timestamp
- ...
- clock n timestamp

Signed-off-by: Sagi Maimon <maimon.sagi@gmail.com>
---
 Addressed comments from:
 - Thomas Gleixner : https://www.spinics.net/lists/netdev/msg959514.html
          
 Changes since version 2:
 - Change multi PHC syscall to fit the Y2038 safe variant.
 - Define the syscall data structure under uapi directory, so it will be known in user space.
 
 arch/x86/entry/syscalls/syscall_64.tbl |  1 +
 include/linux/syscalls.h               |  2 +-
 include/uapi/asm-generic/unistd.h      |  4 +++-
 include/uapi/linux/multi_clock.h       | 21 ++++++++++++++++
 kernel/time/posix-timers.c             | 33 ++++++++++++++++++++++++++
 5 files changed, 59 insertions(+), 2 deletions(-)
 create mode 100644 include/uapi/linux/multi_clock.h

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..9cdeb0bf49db 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,7 @@
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
+457	common	multi_clock_gettime	sys_multi_clock_gettime
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..b59fa776ab76 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1161,7 +1161,7 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
 			unsigned long prot, unsigned long flags,
 			unsigned long fd, unsigned long pgoff);
 asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
-
+asmlinkage long sys_multi_clock_gettime(struct __ptp_multi_clock_get __user * ptp_multi_clk_get);
 
 /*
  * Not a real system call, but a placeholder for syscalls which are
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 756b013fb832..beb3e0052d3c 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -828,9 +828,11 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_multi_clock_gettime 457
+__SYSCALL(__NR_multi_clock_gettime, sys_multi_clock_gettime)
 
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 458
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/multi_clock.h b/include/uapi/linux/multi_clock.h
new file mode 100644
index 000000000000..07099045ec32
--- /dev/null
+++ b/include/uapi/linux/multi_clock.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_MULTI_CLOCK_H
+#define _UAPI_MULTI_CLOCK_H
+
+#include <linux/types.h>
+#include <linux/time_types.h>
+
+#define MULTI_PTP_MAX_CLOCKS 5 /* Max number of clocks */
+#define MULTI_PTP_MAX_SAMPLES 10 /* Max allowed offset measurement samples. */
+
+struct __ptp_multi_clock_get {
+	unsigned int n_clocks; /* Desired number of clocks. */
+	unsigned int n_samples; /* Desired number of measurements per clock. */
+	clockid_t clkid_arr[MULTI_PTP_MAX_CLOCKS]; /* list of clock IDs */
+	/*
+	 * Array of list of n_clocks clocks time samples n_samples times.
+	 */
+	struct  __kernel_timespec ts[MULTI_PTP_MAX_SAMPLES][MULTI_PTP_MAX_CLOCKS];
+};
+
+#endif /* _UAPI_MULTI_CLOCK_H */
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b924f0f096fa..80cbce59d4f4 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -31,6 +31,7 @@
 #include <linux/compat.h>
 #include <linux/nospec.h>
 #include <linux/time_namespace.h>
+#include <linux/multi_clock.h>
 
 #include "timekeeping.h"
 #include "posix-timers.h"
@@ -1426,6 +1427,38 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
 
 #endif
 
+SYSCALL_DEFINE1(multi_clock_gettime, struct __ptp_multi_clock_get __user *, ptp_multi_clk_get)
+{
+	const struct k_clock *kc;
+	struct timespec64 kernel_tp;
+	struct __ptp_multi_clock_get multi_clk_get;
+	unsigned int i, j;
+	int error;
+
+	if (copy_from_user(&multi_clk_get, ptp_multi_clk_get, sizeof(multi_clk_get)))
+		return -EFAULT;
+
+	if (multi_clk_get.n_samples > MULTI_PTP_MAX_SAMPLES)
+		return -EINVAL;
+	if (multi_clk_get.n_clocks > MULTI_PTP_MAX_CLOCKS)
+		return -EINVAL;
+
+	for (j = 0; j < multi_clk_get.n_samples; j++) {
+		for (i = 0; i < multi_clk_get.n_clocks; i++) {
+			kc = clockid_to_kclock(multi_clk_get.clkid_arr[i]);
+			if (!kc)
+				return -EINVAL;
+			error = kc->clock_get_timespec(multi_clk_get.clkid_arr[i], &kernel_tp);
+			if (!error && put_timespec64(&kernel_tp, (struct __kernel_timespec __user *)
+						     &ptp_multi_clk_get->ts[j][i]))
+				error = -EFAULT;
+		}
+	}
+
+	return error;
+}
+
+
 static const struct k_clock clock_realtime = {
 	.clock_getres		= posix_get_hrtimer_res,
 	.clock_get_timespec	= posix_get_realtime_timespec,
-- 
2.26.3


             reply	other threads:[~2023-12-28 12:24 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-28 12:24 Sagi Maimon [this message]
2023-12-29  3:21 ` [PATCH v3] posix-timers: add multi_clock_gettime system call kernel test robot
2023-12-29  4:03 ` kernel test robot
2023-12-29 15:26 ` Arnd Bergmann
2023-12-31 16:00   ` Sagi Maimon
2024-01-02 11:29     ` Arnd Bergmann
2024-01-07 14:05       ` Sagi Maimon
2024-01-11  7:31       ` Richard Cochran
2024-01-15 15:49         ` Sagi Maimon
2024-01-15 23:41           ` Richard Cochran

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=20231228122411.3189-1-maimon.sagi@gmail.com \
    --to=maimon.sagi@gmail.com \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=datglx@linutronix.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=geert@linux-m68k.org \
    --cc=hannes@cmpxchg.org \
    --cc=hpa@zytor.com \
    --cc=keescook@chromium.org \
    --cc=legion@kernel.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=nphamcs@gmail.com \
    --cc=palmer@sifive.com \
    --cc=peterz@infradead.org \
    --cc=richardcochran@gmail.com \
    --cc=rick.p.edgecombe@intel.com \
    --cc=sohil.mehta@intel.com \
    --cc=x86@kernel.org \
    /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;
as well as URLs for NNTP newsgroup(s).