Re: [PATCH v4 for 4.14 1/3] membarrier: Provide register expedited private command

[Mathieu Desnoyers <mathieu.desnoyers@efficios.com>]

----- On Sep 26, 2017, at 1:51 PM, Mathieu Desnoyers mathieu.desnoyers@efficios.com wrote:

> Provide a new command allowing processes to register their intent to use
> the private expedited command.
> 

I missed a few maintainers that should have been CC'd. Adding them now.
This patch is aimed to go through Paul E. McKenney's tree.

Thanks,

Mathieu

> This allows PowerPC to skip the full memory barrier in switch_mm(), and
> only issue the barrier when scheduling into a task belonging to a
> process that has registered to use expedited private.
> 
> Processes are now required to register before using
> MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM.
> 
> Changes since v1:
> - Use test_ti_thread_flag(next, ...) instead of test_thread_flag() in
>  powerpc membarrier_arch_sched_in(), given that we want to specifically
>  check the next thread state.
> - Add missing ARCH_HAS_MEMBARRIER_HOOKS in Kconfig.
> - Use task_thread_info() to pass thread_info from task to
>  *_ti_thread_flag().
> 
> Changes since v2:
> - Move membarrier_arch_sched_in() call to finish_task_switch().
> - Check for NULL t->mm in membarrier_arch_fork().
> - Use membarrier_sched_in() in generic code, which invokes the
>  arch-specific membarrier_arch_sched_in(). This fixes allnoconfig
>  build on PowerPC.
> - Move asm/membarrier.h include under CONFIG_MEMBARRIER, fixing
>  allnoconfig build on PowerPC.
> - Build and runtime tested on PowerPC.
> 
> Changes since v3:
> - Simply rely on copy_mm() to copy the membarrier_private_expedited mm
>  field on fork.
> - powerpc: test thread flag instead of reading
>  membarrier_private_expedited in membarrier_arch_fork().
> - powerpc: skip memory barrier in membarrier_arch_sched_in() if coming
>  from kernel thread, since mmdrop() implies a full barrier.
> - Set membarrier_private_expedited to 1 only after arch registration
>  code, thus eliminating a race where concurrent commands could succeed
>  when they should fail if issued concurrently with process
>  registration.
> - Use READ_ONCE() for membarrier_private_expedited field access in
>  membarrier_private_expedited. Matches WRITE_ONCE() performed in
>  process registration.
> 
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> CC: Peter Zijlstra <peterz@infradead.org>
> CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> CC: Boqun Feng <boqun.feng@gmail.com>
> CC: Andrew Hunter <ahh@google.com>
> CC: Maged Michael <maged.michael@gmail.com>
> CC: gromer@google.com
> CC: Avi Kivity <avi@scylladb.com>
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> CC: Paul Mackerras <paulus@samba.org>
> CC: Michael Ellerman <mpe@ellerman.id.au>
> CC: Dave Watson <davejwatson@fb.com>
> CC: Alan Stern <stern@rowland.harvard.edu>
> CC: Will Deacon <will.deacon@arm.com>
> CC: Andy Lutomirski <luto@kernel.org>
> CC: linux-arch@vger.kernel.org
> ---
> MAINTAINERS                            |  2 ++
> arch/powerpc/Kconfig                   |  1 +
> arch/powerpc/include/asm/membarrier.h  | 44 +++++++++++++++++++++++++++
> arch/powerpc/include/asm/thread_info.h |  3 ++
> arch/powerpc/kernel/Makefile           |  2 ++
> arch/powerpc/kernel/membarrier.c       | 45 ++++++++++++++++++++++++++++
> fs/exec.c                              |  1 +
> include/linux/mm_types.h               |  3 ++
> include/linux/sched/mm.h               | 55 ++++++++++++++++++++++++++++++++++
> include/uapi/linux/membarrier.h        | 23 +++++++++-----
> init/Kconfig                           |  3 ++
> kernel/fork.c                          |  2 ++
> kernel/sched/core.c                    | 11 +------
> kernel/sched/membarrier.c              | 25 +++++++++++++---
> 14 files changed, 199 insertions(+), 21 deletions(-)
> create mode 100644 arch/powerpc/include/asm/membarrier.h
> create mode 100644 arch/powerpc/kernel/membarrier.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 6671f375f7fc..f11d8aece00d 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -8816,6 +8816,8 @@ L:	linux-kernel@vger.kernel.org
> S:	Supported
> F:	kernel/sched/membarrier.c
> F:	include/uapi/linux/membarrier.h
> +F:	arch/powerpc/kernel/membarrier.c
> +F:	arch/powerpc/include/asm/membarrier.h
> 
> MEMORY MANAGEMENT
> L:	linux-mm@kvack.org
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 809c468edab1..6f44c5f74f71 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -138,6 +138,7 @@ config PPC
> 	select ARCH_HAS_ELF_RANDOMIZE
> 	select ARCH_HAS_FORTIFY_SOURCE
> 	select ARCH_HAS_GCOV_PROFILE_ALL
> +	select ARCH_HAS_MEMBARRIER_HOOKS
> 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
> 	select ARCH_HAS_SG_CHAIN
> 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
> diff --git a/arch/powerpc/include/asm/membarrier.h
> b/arch/powerpc/include/asm/membarrier.h
> new file mode 100644
> index 000000000000..588154c1cf57
> --- /dev/null
> +++ b/arch/powerpc/include/asm/membarrier.h
> @@ -0,0 +1,44 @@
> +#ifndef _ASM_POWERPC_MEMBARRIER_H
> +#define _ASM_POWERPC_MEMBARRIER_H
> +
> +static inline void membarrier_arch_sched_in(struct task_struct *prev,
> +		struct task_struct *next)
> +{
> +	/*
> +	 * Only need the full barrier when switching between processes.
> +	 * Barrier when switching from kernel to userspace is not
> +	 * required here, given that it is implied by mmdrop(). Barrier
> +	 * when switching from userspace to kernel is not needed after
> +	 * store to rq->curr.
> +	 */
> +	if (likely(!test_ti_thread_flag(task_thread_info(next),
> +			TIF_MEMBARRIER_PRIVATE_EXPEDITED)
> +			|| !prev->mm || prev->mm == next->mm))
> +		return;
> +
> +	/*
> +	 * The membarrier system call requires a full memory barrier
> +	 * after storing to rq->curr, before going back to user-space.
> +	 */
> +	smp_mb();
> +}
> +static inline void membarrier_arch_fork(struct task_struct *t,
> +		unsigned long clone_flags)
> +{
> +	/*
> +	 * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
> +	 * fork is protected by siglock. membarrier_arch_fork is called
> +	 * with siglock held.
> +	 */
> +	if (test_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED))
> +		set_ti_thread_flag(task_thread_info(t),
> +				TIF_MEMBARRIER_PRIVATE_EXPEDITED);
> +}
> +static inline void membarrier_arch_execve(struct task_struct *t)
> +{
> +	clear_ti_thread_flag(task_thread_info(t),
> +			TIF_MEMBARRIER_PRIVATE_EXPEDITED);
> +}
> +void membarrier_arch_register_private_expedited(struct task_struct *t);
> +
> +#endif /* _ASM_POWERPC_MEMBARRIER_H */
> diff --git a/arch/powerpc/include/asm/thread_info.h
> b/arch/powerpc/include/asm/thread_info.h
> index a941cc6fc3e9..2a208487724b 100644
> --- a/arch/powerpc/include/asm/thread_info.h
> +++ b/arch/powerpc/include/asm/thread_info.h
> @@ -100,6 +100,7 @@ static inline struct thread_info *current_thread_info(void)
> #if defined(CONFIG_PPC64)
> #define TIF_ELF2ABI		18	/* function descriptors must die! */
> #endif
> +#define TIF_MEMBARRIER_PRIVATE_EXPEDITED	19	/* membarrier */
> 
> /* as above, but as bit values */
> #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
> @@ -119,6 +120,8 @@ static inline struct thread_info *current_thread_info(void)
> #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
> #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
> #define _TIF_NOHZ		(1<<TIF_NOHZ)
> +#define _TIF_MEMBARRIER_PRIVATE_EXPEDITED \
> +				(1<<TIF_MEMBARRIER_PRIVATE_EXPEDITED)
> #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
> 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
> 				 _TIF_NOHZ)
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index 91960f83039c..2dd4b9e3313a 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -135,6 +135,8 @@ endif
> obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
> obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
> 
> +obj-$(CONFIG_MEMBARRIER)	+= membarrier.o
> +
> # Disable GCOV & sanitizers in odd or sensitive code
> GCOV_PROFILE_prom_init.o := n
> UBSAN_SANITIZE_prom_init.o := n
> diff --git a/arch/powerpc/kernel/membarrier.c b/arch/powerpc/kernel/membarrier.c
> new file mode 100644
> index 000000000000..b0d79a5f5981
> --- /dev/null
> +++ b/arch/powerpc/kernel/membarrier.c
> @@ -0,0 +1,45 @@
> +/*
> + * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> + *
> + * membarrier system call - PowerPC architecture code
> + *
> + * 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/sched/mm.h>
> +#include <linux/sched/signal.h>
> +#include <linux/thread_info.h>
> +#include <linux/spinlock.h>
> +#include <linux/rcupdate.h>
> +
> +void membarrier_arch_register_private_expedited(struct task_struct *p)
> +{
> +	struct task_struct *t;
> +
> +	if (get_nr_threads(p) == 1) {
> +		set_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED);
> +		return;
> +	}
> +	/*
> +	 * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
> +	 * fork is protected by siglock.
> +	 */
> +	spin_lock(&p->sighand->siglock);
> +	for_each_thread(p, t)
> +		set_ti_thread_flag(task_thread_info(t),
> +				TIF_MEMBARRIER_PRIVATE_EXPEDITED);
> +	spin_unlock(&p->sighand->siglock);
> +	/*
> +	 * Ensure all future scheduler executions will observe the new
> +	 * thread flag state for this process.
> +	 */
> +	synchronize_sched();
> +}
> diff --git a/fs/exec.c b/fs/exec.c
> index ac34d9724684..b2448f2731b3 100644
> --- a/fs/exec.c
> +++ b/fs/exec.c
> @@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename
> *filename,
> 	/* execve succeeded */
> 	current->fs->in_exec = 0;
> 	current->in_execve = 0;
> +	membarrier_execve(current);
> 	acct_update_integrals(current);
> 	task_numa_free(current);
> 	free_bprm(bprm);
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 46f4ecf5479a..5e0fe8ce053b 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -445,6 +445,9 @@ struct mm_struct {
> 	unsigned long flags; /* Must use atomic bitops to access the bits */
> 
> 	struct core_state *core_state; /* coredumping support */
> +#ifdef CONFIG_MEMBARRIER
> +	int membarrier_private_expedited;
> +#endif
> #ifdef CONFIG_AIO
> 	spinlock_t			ioctx_lock;
> 	struct kioctx_table __rcu	*ioctx_table;
> diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
> index 3a19c253bdb1..d3b81e48784d 100644
> --- a/include/linux/sched/mm.h
> +++ b/include/linux/sched/mm.h
> @@ -205,4 +205,59 @@ static inline void memalloc_noreclaim_restore(unsigned int
> flags)
> 	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
> }
> 
> +#ifdef CONFIG_MEMBARRIER
> +
> +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_HOOKS
> +#include <asm/membarrier.h>
> +#else
> +static inline void membarrier_arch_sched_in(struct task_struct *prev,
> +		struct task_struct *next)
> +{
> +}
> +static inline void membarrier_arch_fork(struct task_struct *t,
> +		unsigned long clone_flags)
> +{
> +}
> +static inline void membarrier_arch_execve(struct task_struct *t)
> +{
> +}
> +static inline void membarrier_arch_register_private_expedited(
> +		struct task_struct *p)
> +{
> +}
> +#endif
> +
> +static inline void membarrier_sched_in(struct task_struct *prev,
> +		struct task_struct *next)
> +{
> +	membarrier_arch_sched_in(prev, next);
> +}
> +static inline void membarrier_fork(struct task_struct *t,
> +		unsigned long clone_flags)
> +{
> +	/*
> +	 * Prior copy_mm() copies the membarrier_private_expedited field
> +	 * from current->mm to t->mm.
> +	 */
> +	membarrier_arch_fork(t, clone_flags);
> +}
> +static inline void membarrier_execve(struct task_struct *t)
> +{
> +	t->mm->membarrier_private_expedited = 0;
> +	membarrier_arch_execve(t);
> +}
> +#else
> +static inline void membarrier_sched_in(struct task_struct *prev,
> +		struct task_struct *next)
> +{
> +}
> +static inline void membarrier_fork(struct task_struct *t,
> +		unsigned long clone_flags)
> +{
> +}
> +static inline void membarrier_execve(struct task_struct *t)
> +{
> +}
> +#endif
> +
> #endif /* _LINUX_SCHED_MM_H */
> diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
> index 6d47b3249d8a..4e01ad7ffe98 100644
> --- a/include/uapi/linux/membarrier.h
> +++ b/include/uapi/linux/membarrier.h
> @@ -52,21 +52,30 @@
>  *                          (non-running threads are de facto in such a
>  *                          state). This only covers threads from the
>  *                          same processes as the caller thread. This
> - *                          command returns 0. The "expedited" commands
> - *                          complete faster than the non-expedited ones,
> - *                          they never block, but have the downside of
> - *                          causing extra overhead.
> + *                          command returns 0 on success. The
> + *                          "expedited" commands complete faster than
> + *                          the non-expedited ones, they never block,
> + *                          but have the downside of causing extra
> + *                          overhead. A process needs to register its
> + *                          intent to use the private expedited command
> + *                          prior to using it, otherwise this command
> + *                          returns -EPERM.
> + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
> + *                          Register the process intent to use
> + *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always
> + *                          returns 0.
>  *
>  * Command to be passed to the membarrier system call. The commands need to
>  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
>  * the value 0.
>  */
> enum membarrier_cmd {
> -	MEMBARRIER_CMD_QUERY			= 0,
> -	MEMBARRIER_CMD_SHARED			= (1 << 0),
> +	MEMBARRIER_CMD_QUERY				= 0,
> +	MEMBARRIER_CMD_SHARED				= (1 << 0),
> 	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
> 	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
> -	MEMBARRIER_CMD_PRIVATE_EXPEDITED	= (1 << 3),
> +	MEMBARRIER_CMD_PRIVATE_EXPEDITED		= (1 << 3),
> +	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED	= (1 << 4),
> };
> 
> #endif /* _UAPI_LINUX_MEMBARRIER_H */
> diff --git a/init/Kconfig b/init/Kconfig
> index 78cb2461012e..a3dc6a66f0d1 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1400,6 +1400,9 @@ config MEMBARRIER
> 
> 	  If unsure, say Y.
> 
> +config ARCH_HAS_MEMBARRIER_HOOKS
> +	bool
> +
> config EMBEDDED
> 	bool "Embedded system"
> 	option allnoconfig_y
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 10646182440f..bd4a93915e08 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(
> 	 */
> 	copy_seccomp(p);
> 
> +	membarrier_fork(p, clone_flags);
> +
> 	/*
> 	 * Process group and session signals need to be delivered to just the
> 	 * parent before the fork or both the parent and the child after the
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 18a6966567da..b9d731283946 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2643,17 +2643,8 @@ static struct rq *finish_task_switch(struct task_struct
> *prev)
> 	 */
> 	prev_state = prev->state;
> 	vtime_task_switch(prev);
> +	membarrier_sched_in(prev, current);
> 	perf_event_task_sched_in(prev, current);
> -	/*
> -	 * The membarrier system call requires a full memory barrier
> -	 * after storing to rq->curr, before going back to user-space.
> -	 *
> -	 * TODO: This smp_mb__after_unlock_lock can go away if PPC end
> -	 * up adding a full barrier to switch_mm(), or we should figure
> -	 * out if a smp_mb__after_unlock_lock is really the proper API
> -	 * to use.
> -	 */
> -	smp_mb__after_unlock_lock();
> 	finish_lock_switch(rq, prev);
> 	finish_arch_post_lock_switch();
> 
> diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
> index a92fddc22747..f06949a279ca 100644
> --- a/kernel/sched/membarrier.c
> +++ b/kernel/sched/membarrier.c
> @@ -26,21 +26,25 @@
>  * except MEMBARRIER_CMD_QUERY.
>  */
> #define MEMBARRIER_CMD_BITMASK	\
> -	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
> +	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED	\
> +	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
> 
> static void ipi_mb(void *info)
> {
> 	smp_mb();	/* IPIs should be serializing but paranoid. */
> }
> 
> -static void membarrier_private_expedited(void)
> +static int membarrier_private_expedited(void)
> {
> 	int cpu;
> 	bool fallback = false;
> 	cpumask_var_t tmpmask;
> 
> +	if (!READ_ONCE(current->mm->membarrier_private_expedited))
> +		return -EPERM;
> +
> 	if (num_online_cpus() == 1)
> -		return;
> +		return 0;
> 
> 	/*
> 	 * Matches memory barriers around rq->curr modification in
> @@ -94,6 +98,17 @@ static void membarrier_private_expedited(void)
> 	 * rq->curr modification in scheduler.
> 	 */
> 	smp_mb();	/* exit from system call is not a mb */
> +	return 0;
> +}
> +
> +static void membarrier_register_private_expedited(void)
> +{
> +	struct task_struct *p = current;
> +
> +	if (READ_ONCE(p->mm->membarrier_private_expedited))
> +		return;
> +	membarrier_arch_register_private_expedited(p);
> +	WRITE_ONCE(p->mm->membarrier_private_expedited, 1);
> }
> 
> /**
> @@ -144,7 +159,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
> 			synchronize_sched();
> 		return 0;
> 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
> -		membarrier_private_expedited();
> +		return membarrier_private_expedited();
> +	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
> +		membarrier_register_private_expedited();
> 		return 0;
> 	default:
> 		return -EINVAL;
> --
> 2.11.0

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com