[PATCH v2] posix-timers: add multi_clock_gettime system call

From: Sagi Maimon
Date: Mon Nov 27 2023 - 10:39:14 EST


Some user space applications need to read some clocks.
Each read requires moving from user space to kernel space.
This asymmetry causes the measured offset to have a significant error.

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@xxxxxxxxx>
---
Addressed comments from:
- Richard Cochran : https://www.spinics.net/lists/netdev/msg951723.html

Changes since version 1:
- Change multi PHC ioctl implamantation into systemcall.

arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
include/linux/posix-timers.h | 24 ++++++++++
include/linux/syscalls.h | 3 +-
include/uapi/asm-generic/unistd.h | 12 ++++-
kernel/sys_ni.c | 1 +
kernel/time/posix-timers.c | 62 ++++++++++++++++++++++++++
7 files changed, 102 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c8fac5205803..070efd266e7e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -461,3 +461,4 @@
454 i386 futex_wake sys_futex_wake
455 i386 futex_wait sys_futex_wait
456 i386 futex_requeue sys_futex_requeue
+457 i386 multi_clock_gettime sys_multi_clock_gettime32
\ No newline at end of file
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..f790330244bb 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/posix-timers.h b/include/linux/posix-timers.h
index d607f51404fc..426a45441ab5 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -260,4 +260,28 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new);

void posixtimer_rearm(struct kernel_siginfo *info);
+
+#define MULTI_PTP_MAX_CLOCKS 12 /* 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. */
+ const 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];
+};
+
+struct __ptp_multi_clock_get32 {
+ unsigned int n_clocks; /* Desired number of clocks. */
+ unsigned int n_samples; /* Desired number of measurements per clock. */
+ const 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 old_timespec32 ts[MULTI_PTP_MAX_SAMPLES][MULTI_PTP_MAX_CLOCKS];
+};
+
#endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..afcf68e83d63 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1161,7 +1161,8 @@ 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);
+asmlinkage long sys_multi_clock_gettime32(struct __ptp_multi_clock_get32 __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..3ebcaa052650 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,18 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
#define __NR_futex_requeue 456
__SYSCALL(__NR_futex_requeue, sys_futex_requeue)

+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_multi_clock_gettime 457
+__SC_3264(__NR_multi_clock_gettime, sys_multi_clock_gettime32, sys_multi_clock_gettime)
+#endif
+
+#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32
+#define __NR_multi_clock_gettime64 458
+__SYSCALL(__NR_multi_clock_gettime64, sys_multi_clock_gettime)
+#endif
+
#undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 459

/*
* 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..8ed1c22f40ac 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -335,6 +335,7 @@ COND_SYSCALL(ppoll_time32);
COND_SYSCALL_COMPAT(ppoll_time32);
COND_SYSCALL(utimensat_time32);
COND_SYSCALL(clock_adjtime32);
+COND_SYSCALL(multi_clock_gettime32);

/*
* The syscalls below are not found in include/uapi/asm-generic/unistd.h
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b924f0f096fa..517558af2479 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1426,6 +1426,68 @@ 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;
+ int error;
+ unsigned int i, j;
+
+ 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;
+}
+
+SYSCALL_DEFINE1(multi_clock_gettime32, struct __ptp_multi_clock_get32 __user *, ptp_multi_clk_get)
+{
+ const struct k_clock *kc;
+ struct timespec64 kernel_tp;
+ struct __ptp_multi_clock_get multi_clk_get;
+ int error;
+ unsigned int i, j;
+
+ 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_old_timespec32(&kernel_tp, (struct old_timespec32 __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