Expose a new system call allowing threads to register a userspace memory area where to store the current CPU number. Scheduler migration sets the TIF_NOTIFY_RESUME flag on the current thread. Upon return to user-space, a notify-resume handler updates the current CPU value within that user-space memory area.
This getcpu cache is an alternative to the sched_getcpu() vdso which has a few benefits: - It is faster to do a memory read that to call a vDSO, - This cache value can be read from within an inline assembly, which makes it a useful building block for restartable sequences. This approach is inspired by Paul Turner and Andrew Hunter's work on percpu atomics, which lets the kernel handle restart of critical sections: Ref.: * https://lkml.org/lkml/2015/6/24/665 * https://lwn.net/Articles/650333/ * http://www.linuxplumbersconf.org/2013/ocw/system/presentations/1695/original/LPC%20-%20PerCpu%20Atomics.pdf Benchmarking sched_getcpu() vs tls cache approach. Getting the current CPU number: - With Linux vdso: 12.7 ns - With TLS-cached cpu number: 0.3 ns Signed-off-by: Mathieu Desnoyers <[email protected]> CC: Paul Turner <[email protected]> CC: Andrew Hunter <[email protected]> CC: Peter Zijlstra <[email protected]> CC: Ingo Molnar <[email protected]> CC: Ben Maurer <[email protected]> CC: Steven Rostedt <[email protected]> CC: "Paul E. McKenney" <[email protected]> CC: Josh Triplett <[email protected]> CC: Lai Jiangshan <[email protected]> CC: Linus Torvalds <[email protected]> CC: Andrew Morton <[email protected]> CC: [email protected] --- arch/x86/kernel/signal.c | 2 ++ arch/x86/syscalls/syscall_64.tbl | 1 + fs/exec.c | 1 + include/linux/sched.h | 27 +++++++++++++++ include/uapi/asm-generic/unistd.h | 4 ++- init/Kconfig | 9 +++++ kernel/Makefile | 1 + kernel/fork.c | 2 ++ kernel/getcpu-cache.c | 70 +++++++++++++++++++++++++++++++++++++++ kernel/sched/core.c | 3 ++ kernel/sched/sched.h | 2 ++ kernel/sys_ni.c | 3 ++ 12 files changed, 124 insertions(+), 1 deletion(-) create mode 100644 kernel/getcpu-cache.c diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e504246..157cec0 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -750,6 +750,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + if (getcpu_cache_active(current)) + getcpu_cache_handle_notify_resume(current); } if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) fire_user_return_notifiers(); diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 8d656fb..cfcf8e7 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -329,6 +329,7 @@ 320 common kexec_file_load sys_kexec_file_load 321 common bpf sys_bpf 322 64 execveat stub_execveat +323 common getcpu_cache sys_getcpu_cache # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/exec.c b/fs/exec.c index c7f9b73..20ef2e6 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1555,6 +1555,7 @@ static int do_execveat_common(int fd, struct filename *filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; + getcpu_cache_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/include/linux/sched.h b/include/linux/sched.h index a419b65..0654cc2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1710,6 +1710,9 @@ struct task_struct { #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; #endif +#ifdef CONFIG_GETCPU_CACHE + int32_t __user *getcpu_cache; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ @@ -3090,4 +3093,28 @@ static inline unsigned long rlimit_max(unsigned int limit) return task_rlimit_max(current, limit); } +#ifdef CONFIG_GETCPU_CACHE +void getcpu_cache_fork(struct task_struct *t); +void getcpu_cache_execve(struct task_struct *t); +void getcpu_cache_handle_notify_resume(struct task_struct *t); +static inline bool getcpu_cache_active(struct task_struct *t) +{ + return t->getcpu_cache; +} +#else +static inline void getcpu_cache_fork(struct task_struct *t) +{ +} +static inline void getcpu_cache_execve(struct task_struct *t) +{ +} +static inline void getcpu_cache_handle_notify_resume(struct task_struct *t) +{ +} +static inline bool getcpu_cache_active(struct task_struct *t) +{ + return false; +} +#endif + #endif diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index e016bd9..f82b70d 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -709,9 +709,11 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 281 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) +#define __NR_getcpu_cache 282 +__SYSCALL(__NR_getcpu_cache, sys_getcpu_cache) #undef __NR_syscalls -#define __NR_syscalls 282 +#define __NR_syscalls 283 /* * All syscalls below here should go away really, diff --git a/init/Kconfig b/init/Kconfig index f5dbc6d..fac919b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1559,6 +1559,15 @@ config PCI_QUIRKS bugs/quirks. Disable this only if your target machine is unaffected by PCI quirks. +config GETCPU_CACHE + bool "Enable getcpu_cache() system call" if EXPERT + default y + help + Enable the getcpu_cache() system call which provides a + user-space cache for the current CPU number value. + + If unsure, say Y. + config EMBEDDED bool "Embedded system" option allnoconfig_y diff --git a/kernel/Makefile b/kernel/Makefile index 1408b33..3350ba1 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o +obj-$(CONFIG_GETCPU_CACHE) += getcpu-cache.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/fork.c b/kernel/fork.c index cf65139..334e62d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1549,6 +1549,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, cgroup_post_fork(p); if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); + if (!(clone_flags & CLONE_THREAD)) + getcpu_cache_fork(p); perf_event_fork(p); trace_task_newtask(p, clone_flags); diff --git a/kernel/getcpu-cache.c b/kernel/getcpu-cache.c new file mode 100644 index 0000000..b4e5c77 --- /dev/null +++ b/kernel/getcpu-cache.c @@ -0,0 +1,70 @@ +/* + * Copyright (C) 2015 Mathieu Desnoyers <[email protected]> + * + * getcpu_cache system call + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> + +/* + * This resume handler should always be executed between a migration + * triggered by preemption and return to user-space. + */ +void getcpu_cache_handle_notify_resume(struct task_struct *t) +{ + int32_t __user *gcp = t->getcpu_cache; + + if (gcp == NULL) + return; + if (unlikely(t->flags & PF_EXITING)) + return; + /* + * access_ok() of gcp_user has already been checked by + * sys_getcpu_cache(). + */ + if (__put_user(raw_smp_processor_id(), gcp)) + force_sig(SIGSEGV, current); +} + +/* + * If parent process has a getcpu_cache, the child inherits. Only + * applies when forking a process, not a thread. + */ +void getcpu_cache_fork(struct task_struct *t) +{ + t->getcpu_cache = current->getcpu_cache; +} + +void getcpu_cache_execve(struct task_struct *t) +{ + t->getcpu_cache = NULL; +} + +/* + * sys_getcpu_cache - setup getcpu cache for caller thread + */ +SYSCALL_DEFINE2(getcpu_cache, int32_t __user *, gcp, int, flags) +{ + if (flags) + return -EINVAL; + if (gcp != NULL && !access_ok(VERIFY_WRITE, gcp, sizeof(int32_t))) + return -EFAULT; + current->getcpu_cache = gcp; + /* Will update *gcp on resume */ + if (gcp) + set_thread_flag(TIF_NOTIFY_RESUME); + return 0; +} diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 62671f5..a9009d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1823,6 +1823,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->numa_group = NULL; #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_GETCPU_CACHE + p->getcpu_cache = NULL; +#endif } #ifdef CONFIG_NUMA_BALANCING diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index dc0f435..bf3e346 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -921,6 +921,8 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { set_task_rq(p, cpu); #ifdef CONFIG_SMP + if (getcpu_cache_active(p)) + set_tsk_thread_flag(p, TIF_NOTIFY_RESUME); /* * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be * successfuly executed on another CPU. We must ensure that updates of diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 5adcb0a..3691dc8 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -229,3 +229,6 @@ cond_syscall(sys_bpf); /* execveat */ cond_syscall(sys_execveat); + +/* current CPU number cache */ +cond_syscall(sys_getcpu_cache); -- 2.1.4 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
