LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Peter Zijlstra <peterz@infradead.org>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	Boqun Feng <boqun.feng@gmail.com>
Cc: linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>,
	Andy Lutomirski <luto@amacapital.net>,
	Dave Watson <davejwatson@fb.com>, Paul Turner <pjt@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Russell King <linux@arm.linux.org.uk>,
	Ingo Molnar <mingo@redhat.com>, "H . Peter Anvin" <hpa@zytor.com>,
	Andi Kleen <andi@firstfloor.org>, Chris Lameter <cl@linux.com>,
	Ben Maurer <bmaurer@fb.com>, Steven Rostedt <rostedt@goodmis.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Joel Fernandes <joelaf@google.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Shuah Khan <shuah@kernel.org>,
	linux-kselftest@vger.kernel.org
Subject: [RFC PATCH for 4.21 13/16] cpu-opv/selftests: Provide percpu_op API
Date: Thu,  1 Nov 2018 10:58:41 +0100
Message-ID: <20181101095844.24462-14-mathieu.desnoyers@efficios.com> (raw)
In-Reply-To: <20181101095844.24462-1-mathieu.desnoyers@efficios.com>

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_ */
-- 
2.11.0


  parent reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-01  9:58 [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2) Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 01/16] rseq/selftests: Expose reference counter to coexist with glibc (v2) Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 02/16] rseq/selftests: Adapt number of threads to the number of detected cpus Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 03/16] mm: Replace BUG_ON() by WARN_ON() in vm_unmap_ram() Mathieu Desnoyers
2018-11-01 12:21   ` Thomas Gleixner
2018-11-01 18:46     ` Steven Rostedt
2018-11-01 19:57       ` Mathieu Desnoyers
2018-11-01 22:00         ` Linus Torvalds
2018-11-01 22:17           ` Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 04/16] mm: Introduce vm_map_user_ram, vm_unmap_user_ram (v2) Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 05/16] mm: Provide is_vma_noncached Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 06/16] cpu_opv: Provide cpu_opv system call (v9) Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 07/16] cpu_opv: limit amount of virtual address space used by cpu_opv Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 08/16] x86: Wire up cpu_opv system call Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 09/16] powerpc: " Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 10/16] arm: " Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 11/16] cpu-opv/selftests: Provide cpu-op library Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 12/16] cpu-opv/selftests: Provide basic test Mathieu Desnoyers
2018-11-01  9:58 ` Mathieu Desnoyers [this message]
2018-11-01  9:58 ` [RFC PATCH for 4.21 14/16] cpu-opv/selftests: Provide basic percpu ops test Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore Mathieu Desnoyers
2018-11-01 15:33 ` [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2) Linus Torvalds
  -- strict thread matches above, loose matches on Subject: below --
2018-10-10 19:19 [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 13/16] cpu-opv/selftests: Provide percpu_op API Mathieu Desnoyers

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181101095844.24462-14-mathieu.desnoyers@efficios.com \
    --to=mathieu.desnoyers@efficios.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=bmaurer@fb.com \
    --cc=boqun.feng@gmail.com \
    --cc=catalin.marinas@arm.com \
    --cc=cl@linux.com \
    --cc=davejwatson@fb.com \
    --cc=hpa@zytor.com \
    --cc=joelaf@google.com \
    --cc=josh@joshtriplett.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux@arm.linux.org.uk \
    --cc=luto@amacapital.net \
    --cc=mingo@redhat.com \
    --cc=mtk.manpages@gmail.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=rostedt@goodmis.org \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox