Introduce percpu-op.h API. It uses rseq internally as fast-path if invoked from the right CPU, else cpu_opv as slow-path if called from the wrong CPU or if rseq fails.

This allows acting on per-cpu data from various CPUs transparently from user-space: cpu_opv will take care of migrating the thread to the requested CPU. Use-cases such as rebalancing memory across per-cpu memory pools, or migrating tasks for a user-space scheduler, are thus facilitated. This also handles debugger single-stepping.

The use from userspace is, e.g. for a counter increment:

int cpu, ret;

cpu = percpu_current_cpu(); ret = percpu_addv(&data->c[cpu].count, 1, cpu); if (unlikely(ret)) { perror("percpu_addv"); return -1; } return 0;

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com CC: Shuah Khan shuah@kernel.org CC: Russell King linux@arm.linux.org.uk CC: Catalin Marinas catalin.marinas@arm.com CC: Will Deacon will.deacon@arm.com CC: Thomas Gleixner tglx@linutronix.de CC: Paul Turner pjt@google.com CC: Peter Zijlstra peterz@infradead.org CC: Andy Lutomirski luto@amacapital.net CC: Andi Kleen andi@firstfloor.org CC: Dave Watson davejwatson@fb.com CC: Chris Lameter cl@linux.com CC: Ingo Molnar mingo@redhat.com CC: "H. Peter Anvin" hpa@zytor.com CC: Ben Maurer bmaurer@fb.com CC: Steven Rostedt rostedt@goodmis.org CC: "Paul E. McKenney" paulmck@linux.vnet.ibm.com CC: Josh Triplett josh@joshtriplett.org CC: Linus Torvalds torvalds@linux-foundation.org CC: Andrew Morton akpm@linux-foundation.org CC: Boqun Feng boqun.feng@gmail.com CC: linux-kselftest@vger.kernel.org CC: linux-api@vger.kernel.org --- tools/testing/selftests/cpu-opv/percpu-op.h | 151 ++++++++++++++++++++++++++++ 1 file changed, 151 insertions(+) create mode 100644 tools/testing/selftests/cpu-opv/percpu-op.h

diff --git a/tools/testing/selftests/cpu-opv/percpu-op.h b/tools/testing/selftests/cpu-opv/percpu-op.h new file mode 100644 index 000000000000..918171e585d7 --- /dev/null +++ b/tools/testing/selftests/cpu-opv/percpu-op.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * percpu-op.h + * + * (C) Copyright 2017-2018 - Mathieu Desnoyers mathieu.desnoyers@efficios.com + */ + +#ifndef PERCPU_OP_H +#define PERCPU_OP_H + +#include <stdint.h> +#include <stdbool.h> +#include <errno.h> +#include <stdlib.h> +#include "rseq.h" +#include "cpu-op.h" + +static inline uint32_t percpu_current_cpu(void) +{ + return rseq_current_cpu(); +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, + int cpu) +{ + int ret; + + ret = rseq_cmpeqv_storev(v, expect, newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_storev(v, expect, newv, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + int ret; + + ret = rseq_cmpnev_storeoffp_load(v, expectnot, voffp, load, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpnev_storeoffp_load(v, expectnot, voffp, + load, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_addv(intptr_t *v, intptr_t count, int cpu) +{ + if (rseq_unlikely(rseq_addv(v, count, cpu))) + return cpu_op_addv(v, count, cpu); + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_storev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + int ret; + + ret = rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, + newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_storev_storev(v, expect, v2, newv2, + newv, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_storev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + int ret; + + ret = rseq_cmpeqv_trystorev_storev_release(v, expect, v2, newv2, + newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_storev_storev_release(v, expect, v2, newv2, + newv, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + int ret; + + ret = rseq_cmpeqv_cmpeqv_storev(v, expect, v2, expect2, newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_cmpeqv_storev(v, expect, v2, expect2, + newv, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_memcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + int ret; + + ret = rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len, + newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_memcpy_storev(v, expect, dst, src, len, + newv, cpu); + } + return 0; +} + +static inline __attribute__((always_inline)) +int percpu_cmpeqv_memcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + int ret; + + ret = rseq_cmpeqv_trymemcpy_storev_release(v, expect, dst, src, len, + newv, cpu); + if (rseq_unlikely(ret)) { + if (ret > 0) + return ret; + return cpu_op_cmpeqv_memcpy_storev_release(v, expect, dst, src, + len, newv, cpu); + } + return 0; +} + +#endif /* PERCPU_OP_H_ */