diff options
| -rw-r--r-- | Documentation/scheduler/index.rst | 1 | ||||
| -rw-r--r-- | Documentation/scheduler/membarrier.rst | 39 | ||||
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | kernel/sched/core.c | 7 | ||||
| -rw-r--r-- | kernel/sched/membarrier.c | 8 |
5 files changed, 51 insertions, 5 deletions
diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst index 3170747226f6..43bd8a145b7a 100644 --- a/Documentation/scheduler/index.rst +++ b/Documentation/scheduler/index.rst @@ -7,6 +7,7 @@ Scheduler completion + membarrier sched-arch sched-bwc sched-deadline diff --git a/Documentation/scheduler/membarrier.rst b/Documentation/scheduler/membarrier.rst new file mode 100644 index 000000000000..2387804b1c63 --- /dev/null +++ b/Documentation/scheduler/membarrier.rst @@ -0,0 +1,39 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +membarrier() System Call +======================== + +MEMBARRIER_CMD_{PRIVATE,GLOBAL}_EXPEDITED - Architecture requirements +===================================================================== + +Memory barriers before updating rq->curr +---------------------------------------- + +The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED +require each architecture to have a full memory barrier after coming from +user-space, before updating rq->curr. This barrier is implied by the sequence +rq_lock(); smp_mb__after_spinlock() in __schedule(). The barrier matches a full +barrier in the proximity of the membarrier system call exit, cf. +membarrier_{private,global}_expedited(). + +Memory barriers after updating rq->curr +--------------------------------------- + +The commands MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_GLOBAL_EXPEDITED +require each architecture to have a full memory barrier after updating rq->curr, +before returning to user-space. The schemes providing this barrier on the various +architectures are as follows. + + - alpha, arc, arm, hexagon, mips rely on the full barrier implied by + spin_unlock() in finish_lock_switch(). + + - arm64 relies on the full barrier implied by switch_to(). + + - powerpc, riscv, s390, sparc, x86 rely on the full barrier implied by + switch_mm(), if mm is not NULL; they rely on the full barrier implied + by mmdrop(), otherwise. On powerpc and riscv, switch_mm() relies on + membarrier_arch_switch_mm(). + +The barrier matches a full barrier in the proximity of the membarrier system call +entry, cf. membarrier_{private,global}_expedited(). diff --git a/MAINTAINERS b/MAINTAINERS index 2450e88d3e2c..78c835cc69c9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14039,6 +14039,7 @@ M: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> M: "Paul E. McKenney" <paulmck@kernel.org> L: linux-kernel@vger.kernel.org S: Supported +F: Documentation/scheduler/membarrier.rst F: arch/*/include/asm/membarrier.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c4ca8085885a..a972628e7756 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6638,7 +6638,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * if (signal_pending_state()) if (p->state & @state) * * Also, the membarrier system call requires a full memory barrier - * after coming from user-space, before storing to rq->curr. + * after coming from user-space, before storing to rq->curr; this + * barrier matches a full barrier in the proximity of the membarrier + * system call exit. */ rq_lock(rq, &rf); smp_mb__after_spinlock(); @@ -6716,6 +6718,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * architectures where spin_unlock is a full barrier, * - switch_to() for arm64 (weakly-ordered, spin_unlock * is a RELEASE barrier), + * + * The barrier matches a full barrier in the proximity of + * the membarrier system call entry. */ ++*switch_count; diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 2ad881d07752..f3d91628d6b8 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -251,7 +251,7 @@ static int membarrier_global_expedited(void) return 0; /* - * Matches memory barriers around rq->curr modification in + * Matches memory barriers after rq->curr modification in * scheduler. */ smp_mb(); /* system call entry is not a mb. */ @@ -300,7 +300,7 @@ static int membarrier_global_expedited(void) /* * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers around + * waiting for the last IPI. Matches memory barriers before * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ @@ -339,7 +339,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) return 0; /* - * Matches memory barriers around rq->curr modification in + * Matches memory barriers after rq->curr modification in * scheduler. */ smp_mb(); /* system call entry is not a mb. */ @@ -415,7 +415,7 @@ out: /* * Memory barrier on the caller thread _after_ we finished - * waiting for the last IPI. Matches memory barriers around + * waiting for the last IPI. Matches memory barriers before * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ |