Hi,
So as discussed, this is one possible prctl interface for
task isolation.
Is this something that is desired? If not, what is the
proper way for the interface to be?
(addition of a new capability CAP_TASK_ISOLATION,
for permissions is still missing, should be done
in the next versions).
Thanks.
add prctl interface for task isolation
Add a new extensible interface for task isolation,
and allow userspace to quiesce the CPU.
This means putting the system into a quiet state by
completing all workqueue items, idle all subsystems
that need it and put the cpu into NOHZ mode.
Suggested-by: Christopher Lameter <cl@xxxxxxxxx>
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Index: linux-2.6-vmstat2/include/uapi/linux/prctl.h
===================================================================
--- linux-2.6-vmstat2.orig/include/uapi/linux/prctl.h
+++ linux-2.6-vmstat2/include/uapi/linux/prctl.h
@@ -247,4 +247,10 @@ struct prctl_mm_map {
#define PR_SET_IO_FLUSHER 57
#define PR_GET_IO_FLUSHER 58
+/* Task isolation control */
+#define PR_TASK_ISOLATION_FEATURES 59
+#define PR_TASK_ISOLATION_GET 60
+#define PR_TASK_ISOLATION_SET 61
+#define PR_TASK_ISOLATION_REQUEST 62
+
#endif /* _LINUX_PRCTL_H */
Index: linux-2.6-vmstat2/kernel/sys.c
===================================================================
--- linux-2.6-vmstat2.orig/kernel/sys.c
+++ linux-2.6-vmstat2/kernel/sys.c
@@ -58,6 +58,7 @@
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
+#include <linux/isolation.h>
#include <linux/rcupdate.h>
#include <linux/uidgid.h>
#include <linux/cred.h>
@@ -2530,6 +2531,25 @@ SYSCALL_DEFINE5(prctl, int, option, unsi
error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
break;
+ case PR_TASK_ISOLATION_FEATURES: {
+ struct isolation_features ifeat;
+
+ memset(&ifeat, 0, sizeof(ifeat));
+
+ prctl_task_isolation_features(&ifeat);
+ if (copy_to_user((char __user *)arg2, &ifeat, sizeof(ifeat)))
+ return -EFAULT;
+ break;
+ }
+ case PR_TASK_ISOLATION_SET:
+ error = prctl_task_isolation_set(arg2, arg3, arg4, arg5);
+ break;
+ case PR_TASK_ISOLATION_GET:
+ error = prctl_task_isolation_get(arg2, arg3, arg4, arg5);
+ break;
+ case PR_TASK_ISOLATION_REQUEST:
+ error = prctl_task_isolation_request(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
Index: linux-2.6-vmstat2/Documentation/userspace-api/task_isolation.rst
===================================================================
--- /dev/null
+++ linux-2.6-vmstat2/Documentation/userspace-api/task_isolation.rst
@@ -0,0 +1,99 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Task isolation CPU interface
+============================
+
+The kernel might perform a number of activities in the background,
+on a given CPU, in the form of workqueues or interrupts.
+
+This interface allows userspace to indicate to the kernel when
+its running latency critical code (and what is the behaviour
+on activities that would interrupt the CPU).
+
+This allows the system to take preventive measures to avoid
+deferred actions and create a OS noise free environment for
+the application.
+
+The task isolation mode is a bitmap specifying which individual
+features the application desires to be enabled.
+
+Each individual feature can be configured via
+
+ prctl(PR_TASK_ISOLATION_SET, ISOL_F_featurename, params...)
+
+Enablement of the set of features is requested via
+
+ prctl(PR_TASK_ISOLATION_REQUEST, ISOL_F_featurename, 0, 0, 0)
+
+PR_TASK_ISO_feature (both GET/SET) are supported if the flags
+field of struct isolation_features contains bit number ISOL_F_featurename
+set (see "Example" section below).
+
+In summary, the usual flow is
+
+ # Determine the supported features
+ prctl(PR_TASK_ISOLATION_FEATURES, ifeat, 0, 0, 0);
+
+ # Configure the desired features, based on ifeat
+ if ((ifeat & PR_TASK_ISO_feature1) == ISOL_F_feature1) {
+ prctl(PR_TASK_ISOLATION_SET, ISOL_F_feature1, params...)
+ featuremask |= ISOL_F_feature1
+ }
+
+ if ((ifeat & ISOL_F_feature2) == ISOL_F_feature2) {
+ prctl(PR_TASK_ISOLATION_SET, ISOL_F_feature2, params...)
+ featuremask |= ISOL_F_feature2
+ }
+
+ ...
+
+ # Enable isolation (feature set in bitmask), with each
+ # feature configured as above
+ prctl(PR_TASK_ISOLATION_REQUEST, featuremask, 0, 0, 0)
+
+Usage
+=====
+``PR_TASK_ISOLATION_FEATURES``:
+ Returns the supported features. Features are defined
+ at include/uapi/linux/isolation.h.
+
+ Usage::
+
+ prctl(PR_TASK_ISOLATION_FEATURES, ifeat, 0, 0, 0);
+
+ The 'ifeat' argument is a pointer to a struct isolation_features:
+
+ struct isolation_features {
+ __u32 flags;
+ __u32 pad[3];
+ };
+
+ Where flags contains bits set for the features the kernel supports.
+
+``PR_TASK_ISOLATION_SET``:
+ Configures task isolation features. Each individual feature is
+ configured separately via
+
+ prctl(PR_TASK_ISOLATION_SET, PR_TASK_ISO_feature, params...)
+
+``PR_TASK_ISOLATION_GET``:
+ Retrieves the currently configured task isolation mode parameters
+ for feature PR_TASK_ISO_feature (arg1).
+
+ prctl(PR_TASK_ISOLATION_SET, PR_TASK_ISO_feature, params...)
+
+``PR_TASK_ISOLATION_REQUEST``:
+ Enter task isolation, with features in featuremask enabled.
+ supported. This will quiesce any pending activity
+ on the CPU, and enable mode specific configurations.
+
+Feature list
+============
+
+Example
+=======
+
+The ``samples/task_isolation/`` directory contains a sample
+application.
+
Index: linux-2.6-vmstat2/include/uapi/linux/isolation.h
===================================================================
--- /dev/null
+++ linux-2.6-vmstat2/include/uapi/linux/isolation.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _UAPI_LINUX_ISOL_H
+#define _UAPI_LINUX_ISOL_H
+
+/* For PR_TASK_ISOLATION_FEATURES */
+struct isolation_features {
+ __u32 flags;
+ __u32 pad[3];
+};
+
+/* Isolation features */
+#define ISOL_F_QUIESCE 0x1
+
+#endif /* _UAPI_LINUX_ISOL_H */
+
Index: linux-2.6-vmstat2/kernel/isolation.c
===================================================================
--- /dev/null
+++ linux-2.6-vmstat2/kernel/isolation.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implementation of task isolation.
+ *
+ * Authors:
+ * Chris Metcalf <cmetcalf@xxxxxxxxxxxx>
+ * Alex Belits <abelits@xxxxxxxxxxx>
+ * Yuri Norov <ynorov@xxxxxxxxxxx>
+ */
+
+#include <linux/sched.h>
+#include <linux/isolation.h>
+#include <linux/vmstat.h>
+
+void prctl_task_isolation_features(struct isolation_features *ifeat)
+{
+ ifeat->flags = ISOL_F_QUIESCE;
+}
+
+int prctl_task_isolation_get(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ return 0;
+}
+
+int prctl_task_isolation_set(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ return 0;
+}
+
+int prctl_task_isolation_request(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ int ret;
+ int cpu = raw_smp_processor_id();
+
+ ret = user_quiet_vmstat(cpu);
+
+ return ret;
+}
Index: linux-2.6-vmstat2/samples/task_isolation/task_isolation.c
===================================================================
--- /dev/null
+++ linux-2.6-vmstat2/samples/task_isolation/task_isolation.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/mman.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+void main(void)
+{
+ int ret;
+ void *buf = malloc(4096);
+
+ struct isolation_features ifeat;
+ struct isolation_control icontrol;
+ unsigned long fmask = 0;
+
+ memset(ifeat, 0, sizeof(struct isolation_features));
+
+ memset(buf, 1, 4096);
+ ret = mlock(buf, 4096);
+ if (ret) {
+ perror("mlock");
+ exit(0);
+ }
+
+ ret = prctl(PR_TASK_ISOLATION_FEATURES, &ifeat, 0, 0, 0);
+ if (ret == -1) {
+ perror("prctl");
+ exit(0);
+ }
+
+#ifdef ISOL_F_QUIESCE
+ /* enable ISOL_F_QUIESCE */
+ if (!(ifeat.flags & ISOL_F_QUIESCE)) {
+ printf("ISOL_F_QUIESCE not set!\n");
+ exit(0);
+ }
+ fmask = fmask | ISOL_F_QUIESCE;
+#endif
+
+ /* busy loop */
+ while (ret != 0)
+ memset(buf, 0, 10);
+
+}
+
Index: linux-2.6-vmstat2/include/linux/isolation.h
===================================================================
--- /dev/null
+++ linux-2.6-vmstat2/include/linux/isolation.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LINUX_ISOL_H
+#define __LINUX_ISOL_H
+
+#include <uapi/linux/isolation.h>
+
+void prctl_task_isolation_features(struct isolation_features *ifeat);
+
+int prctl_task_isolation_get(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5);
+
+int prctl_task_isolation_set(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5);
+
+int prctl_task_isolation_request(unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5);
+#endif /* __LINUX_ISOL_H */
Index: linux-2.6-vmstat2/kernel/Makefile
===================================================================
--- linux-2.6-vmstat2.orig/kernel/Makefile
+++ linux-2.6-vmstat2/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y = fork.o exec_domain.o panic.o
extable.o params.o \
kthread.o sys_ni.o nsproxy.o \
notifier.o ksysfs.o cred.o reboot.o \
- async.o range.o smpboot.o ucount.o regset.o
+ async.o range.o smpboot.o ucount.o regset.o isolation.o
obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o
obj-$(CONFIG_MODULES) += kmod.o
Index: linux-2.6-vmstat2/include/linux/vmstat.h
===================================================================
--- linux-2.6-vmstat2.orig/include/linux/vmstat.h
+++ linux-2.6-vmstat2/include/linux/vmstat.h
@@ -290,6 +290,7 @@ void refresh_zone_stat_thresholds(void);
struct ctl_table;
int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp,
loff_t *ppos);
+int user_quiet_vmstat(int cpu);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
Index: linux-2.6-vmstat2/mm/vmstat.c
===================================================================
--- linux-2.6-vmstat2.orig/mm/vmstat.c
+++ linux-2.6-vmstat2/mm/vmstat.c
@@ -1936,6 +1936,16 @@ void quiet_vmstat(void)
refresh_cpu_vm_stats(false);
}
+int user_quiet_vmstat(int cpu)
+{
+ if (need_update(cpu) == true)
+ refresh_cpu_vm_stats(false);
+
+ flush_delayed_work(per_cpu_ptr(&vmstat_work, cpu));
+
+ return 0;
+}
+
/*
* Shepherd worker thread that checks the
* differentials of processors that have their worker
