summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/.gitignore1
-rw-r--r--kernel/Kconfig.hz2
-rw-r--r--kernel/Makefile82
-rw-r--r--kernel/audit_tree.c20
-rw-r--r--kernel/audit_watch.c24
-rw-r--r--kernel/bounds.c6
-rw-r--r--kernel/cgroup.c1494
-rw-r--r--kernel/cgroup_freezer.c7
-rw-r--r--kernel/context_tracking.c10
-rw-r--r--kernel/cpu.c49
-rw-r--r--kernel/cpu/idle.c19
-rw-r--r--kernel/cpuset.c79
-rw-r--r--kernel/debug/debug_core.c32
-rw-r--r--kernel/debug/debug_core.h3
-rw-r--r--kernel/debug/kdb/kdb_debugger.c5
-rw-r--r--kernel/debug/kdb/kdb_main.c3
-rw-r--r--kernel/delayacct.c7
-rw-r--r--kernel/elfcore.c10
-rw-r--r--kernel/events/core.c232
-rw-r--r--kernel/events/internal.h35
-rw-r--r--kernel/events/ring_buffer.c127
-rw-r--r--kernel/events/uprobes.c255
-rw-r--r--kernel/exit.c1
-rw-r--r--kernel/extable.c4
-rw-r--r--kernel/fork.c33
-rw-r--r--kernel/freezer.c6
-rw-r--r--kernel/futex.c212
-rw-r--r--kernel/gcov/Kconfig30
-rw-r--r--kernel/gcov/Makefile32
-rw-r--r--kernel/gcov/base.c32
-rw-r--r--kernel/gcov/fs.c52
-rw-r--r--kernel/gcov/gcc_3_4.c115
-rw-r--r--kernel/gcov/gcc_4_7.c560
-rw-r--r--kernel/gcov/gcov.h65
-rw-r--r--kernel/hrtimer.c3
-rw-r--r--kernel/hung_task.c17
-rw-r--r--kernel/irq/chip.c2
-rw-r--r--kernel/irq/irqdomain.c13
-rw-r--r--kernel/irq/manage.c4
-rw-r--r--kernel/irq/pm.c2
-rw-r--r--kernel/irq/settings.h7
-rw-r--r--kernel/irq/spurious.c12
-rw-r--r--kernel/jump_label.c5
-rw-r--r--kernel/kexec.c7
-rw-r--r--kernel/kprobes.c4
-rw-r--r--kernel/kthread.c73
-rw-r--r--kernel/locking/Makefile25
-rw-r--r--kernel/locking/lglock.c (renamed from kernel/lglock.c)0
-rw-r--r--kernel/locking/lockdep.c (renamed from kernel/lockdep.c)12
-rw-r--r--kernel/locking/lockdep_internals.h (renamed from kernel/lockdep_internals.h)0
-rw-r--r--kernel/locking/lockdep_proc.c (renamed from kernel/lockdep_proc.c)15
-rw-r--r--kernel/locking/lockdep_states.h (renamed from kernel/lockdep_states.h)0
-rw-r--r--kernel/locking/mutex-debug.c (renamed from kernel/mutex-debug.c)7
-rw-r--r--kernel/locking/mutex-debug.h (renamed from kernel/mutex-debug.h)0
-rw-r--r--kernel/locking/mutex.c (renamed from kernel/mutex.c)2
-rw-r--r--kernel/locking/mutex.h (renamed from kernel/mutex.h)0
-rw-r--r--kernel/locking/percpu-rwsem.c165
-rw-r--r--kernel/locking/rtmutex-debug.c (renamed from kernel/rtmutex-debug.c)8
-rw-r--r--kernel/locking/rtmutex-debug.h (renamed from kernel/rtmutex-debug.h)0
-rw-r--r--kernel/locking/rtmutex-tester.c (renamed from kernel/rtmutex-tester.c)0
-rw-r--r--kernel/locking/rtmutex.c (renamed from kernel/rtmutex.c)166
-rw-r--r--kernel/locking/rtmutex.h (renamed from kernel/rtmutex.h)0
-rw-r--r--kernel/locking/rtmutex_common.h (renamed from kernel/rtmutex_common.h)23
-rw-r--r--kernel/locking/rwsem-spinlock.c296
-rw-r--r--kernel/locking/rwsem-xadd.c293
-rw-r--r--kernel/locking/rwsem.c (renamed from kernel/rwsem.c)0
-rw-r--r--kernel/locking/semaphore.c (renamed from kernel/semaphore.c)0
-rw-r--r--kernel/locking/spinlock.c (renamed from kernel/spinlock.c)0
-rw-r--r--kernel/locking/spinlock_debug.c302
-rw-r--r--kernel/modsign_certificate.S12
-rw-r--r--kernel/modsign_pubkey.c104
-rw-r--r--kernel/module-internal.h2
-rw-r--r--kernel/module.c167
-rw-r--r--kernel/module_signing.c11
-rw-r--r--kernel/padata.c9
-rw-r--r--kernel/panic.c4
-rw-r--r--kernel/params.c25
-rw-r--r--kernel/pid_namespace.c8
-rw-r--r--kernel/posix-cpu-timers.c327
-rw-r--r--kernel/power/Kconfig16
-rw-r--r--kernel/power/console.c1
-rw-r--r--kernel/power/qos.c26
-rw-r--r--kernel/power/snapshot.c11
-rw-r--r--kernel/power/user.c21
-rw-r--r--kernel/printk/printk.c45
-rw-r--r--kernel/ptrace.c3
-rw-r--r--kernel/rcu/Makefile6
-rw-r--r--kernel/rcu/rcu.h (renamed from kernel/rcu.h)12
-rw-r--r--kernel/rcu/srcu.c (renamed from kernel/srcu.c)57
-rw-r--r--kernel/rcu/tiny.c (renamed from kernel/rcutiny.c)37
-rw-r--r--kernel/rcu/tiny_plugin.h (renamed from kernel/rcutiny_plugin.h)0
-rw-r--r--kernel/rcu/torture.c (renamed from kernel/rcutorture.c)81
-rw-r--r--kernel/rcu/tree.c (renamed from kernel/rcutree.c)295
-rw-r--r--kernel/rcu/tree.h (renamed from kernel/rcutree.h)14
-rw-r--r--kernel/rcu/tree_plugin.h (renamed from kernel/rcutree_plugin.h)188
-rw-r--r--kernel/rcu/tree_trace.c (renamed from kernel/rcutree_trace.c)5
-rw-r--r--kernel/rcu/update.c (renamed from kernel/rcupdate.c)15
-rw-r--r--kernel/reboot.c2
-rw-r--r--kernel/sched/Makefile6
-rw-r--r--kernel/sched/clock.c78
-rw-r--r--kernel/sched/completion.c299
-rw-r--r--kernel/sched/core.c1536
-rw-r--r--kernel/sched/cpuacct.c18
-rw-r--r--kernel/sched/cpudeadline.c216
-rw-r--r--kernel/sched/cpudeadline.h33
-rw-r--r--kernel/sched/deadline.c1640
-rw-r--r--kernel/sched/debug.c70
-rw-r--r--kernel/sched/fair.c1651
-rw-r--r--kernel/sched/features.h19
-rw-r--r--kernel/sched/idle_task.c2
-rw-r--r--kernel/sched/rt.c38
-rw-r--r--kernel/sched/sched.h200
-rw-r--r--kernel/sched/stats.h46
-rw-r--r--kernel/sched/stop_task.c4
-rw-r--r--kernel/sched/wait.c (renamed from kernel/wait.c)127
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/smp.c19
-rw-r--r--kernel/softirq.c270
-rw-r--r--kernel/stop_machine.c303
-rw-r--r--kernel/sys.c1
-rw-r--r--kernel/sysctl.c38
-rw-r--r--kernel/sysctl_binary.c6
-rw-r--r--kernel/system_certificates.S20
-rw-r--r--kernel/system_keyring.c105
-rw-r--r--kernel/taskstats.c54
-rw-r--r--kernel/time/Kconfig2
-rw-r--r--kernel/time/alarmtimer.c4
-rw-r--r--kernel/time/clockevents.c2
-rw-r--r--kernel/time/clocksource.c52
-rw-r--r--kernel/time/ntp.c3
-rw-r--r--kernel/time/sched_clock.c114
-rw-r--r--kernel/time/tick-broadcast.c7
-rw-r--r--kernel/time/tick-common.c16
-rw-r--r--kernel/time/tick-internal.h7
-rw-r--r--kernel/time/tick-sched.c67
-rw-r--r--kernel/time/timekeeping.c58
-rw-r--r--kernel/time/timer_stats.c8
-rw-r--r--kernel/timer.c13
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/blktrace.c36
-rw-r--r--kernel/trace/ftrace.c440
-rw-r--r--kernel/trace/ring_buffer.c2
-rw-r--r--kernel/trace/trace.c142
-rw-r--r--kernel/trace/trace.h244
-rw-r--r--kernel/trace/trace_branch.c2
-rw-r--r--kernel/trace/trace_event_perf.c10
-rw-r--r--kernel/trace/trace_events.c84
-rw-r--r--kernel/trace/trace_events_filter.c230
-rw-r--r--kernel/trace/trace_events_trigger.c1437
-rw-r--r--kernel/trace/trace_export.c2
-rw-r--r--kernel/trace/trace_functions_graph.c82
-rw-r--r--kernel/trace/trace_kprobe.c838
-rw-r--r--kernel/trace/trace_mmiotrace.c4
-rw-r--r--kernel/trace/trace_output.c19
-rw-r--r--kernel/trace/trace_probe.c440
-rw-r--r--kernel/trace/trace_probe.h224
-rw-r--r--kernel/trace/trace_sched_switch.c4
-rw-r--r--kernel/trace/trace_sched_wakeup.c65
-rw-r--r--kernel/trace/trace_selftest.c33
-rw-r--r--kernel/trace/trace_stack.c2
-rw-r--r--kernel/trace/trace_stat.c41
-rw-r--r--kernel/trace/trace_syscalls.c38
-rw-r--r--kernel/trace/trace_uprobe.c488
-rw-r--r--kernel/up.c11
-rw-r--r--kernel/user.c4
-rw-r--r--kernel/user_namespace.c6
-rw-r--r--kernel/workqueue.c84
167 files changed, 13787 insertions, 4991 deletions
diff --git a/kernel/.gitignore b/kernel/.gitignore
index b3097bde4e9c..790d83c7d160 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -5,3 +5,4 @@ config_data.h
config_data.gz
timeconst.h
hz.bc
+x509_certificate_list
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
index 94fabd534b03..2a202a846757 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
default 1000 if HZ_1000
config SCHED_HRTICK
- def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
+ def_bool HIGH_RES_TIMERS
diff --git a/kernel/Makefile b/kernel/Makefile
index 1ce47553fb02..bc010ee272b6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -6,56 +6,44 @@ obj-y = fork.o exec_domain.o panic.o \
cpu.o exit.o itimer.o time.o softirq.o resource.o \
sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
signal.o sys.o kmod.o workqueue.o pid.o task_work.o \
- rcupdate.o extable.o params.o posix-timers.o \
- kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \
- hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
+ extable.o params.o posix-timers.o \
+ kthread.o sys_ni.o posix-cpu-timers.o \
+ hrtimer.o nsproxy.o \
notifier.o ksysfs.o cred.o reboot.o \
- async.o range.o groups.o lglock.o smpboot.o
+ async.o range.o groups.o smpboot.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
-CFLAGS_REMOVE_lockdep.o = -pg
-CFLAGS_REMOVE_lockdep_proc.o = -pg
-CFLAGS_REMOVE_mutex-debug.o = -pg
-CFLAGS_REMOVE_rtmutex-debug.o = -pg
CFLAGS_REMOVE_cgroup-debug.o = -pg
CFLAGS_REMOVE_irq_work.o = -pg
endif
obj-y += sched/
+obj-y += locking/
obj-y += power/
obj-y += printk/
obj-y += cpu/
obj-y += irq/
+obj-y += rcu/
obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
obj-$(CONFIG_FREEZER) += freezer.o
obj-$(CONFIG_PROFILING) += profile.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += time/
-obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
-obj-$(CONFIG_LOCKDEP) += lockdep.o
-ifeq ($(CONFIG_PROC_FS),y)
-obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
-endif
obj-$(CONFIG_FUTEX) += futex.o
ifeq ($(CONFIG_COMPAT),y)
obj-$(CONFIG_FUTEX) += futex_compat.o
endif
-obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
-obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
-obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
obj-$(CONFIG_SMP) += smp.o
ifneq ($(CONFIG_SMP),y)
obj-y += up.o
endif
-obj-$(CONFIG_SMP) += spinlock.o
-obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
-obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
obj-$(CONFIG_KEXEC) += kexec.o
@@ -81,12 +69,6 @@ obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
obj-$(CONFIG_SECCOMP) += seccomp.o
-obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
-obj-$(CONFIG_TREE_RCU) += rcutree.o
-obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
-obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
-obj-$(CONFIG_TINY_RCU) += rcutiny.o
-obj-$(CONFIG_TINY_PREEMPT_RCU) += rcutiny.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -141,19 +123,53 @@ targets += timeconst.h
$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
$(call if_changed,bc)
-ifeq ($(CONFIG_MODULE_SIG),y)
+###############################################################################
+#
+# Roll all the X.509 certificates that we can find together and pull them into
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
#
-# Pull the signing certificate and any extra certificates into the kernel
+# We look in the source root and the build root for all files whose name ends
+# in ".x509". Unfortunately, this will generate duplicate filenames, so we
+# have make canonicalise the pathnames and then sort them to discard the
+# duplicates.
#
+###############################################################################
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509
+X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+ $(or $(realpath $(CERT)),$(CERT))))
+X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw))
+
+ifeq ($(X509_CERTIFICATES),)
+$(warning *** No X.509 certificates found ***)
+endif
-quiet_cmd_touch = TOUCH $@
- cmd_touch = touch $@
+ifneq ($(wildcard $(obj)/.x509.list),)
+ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
+$(info X.509 certificate list changed)
+$(shell rm $(obj)/.x509.list)
+endif
+endif
+
+kernel/system_certificates.o: $(obj)/x509_certificate_list
+
+quiet_cmd_x509certs = CERTS $@
+ cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)")
-extra_certificates:
- $(call cmd,touch)
+targets += $(obj)/x509_certificate_list
+$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
+ $(call if_changed,x509certs)
-kernel/modsign_certificate.o: signing_key.x509 extra_certificates
+targets += $(obj)/.x509.list
+$(obj)/.x509.list:
+ @echo $(X509_CERTIFICATES) >$@
+endif
+
+clean-files := x509_certificate_list .x509.list
+ifeq ($(CONFIG_MODULE_SIG),y)
###############################################################################
#
# If module signing is requested, say by allyesconfig, but a key has not been
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307dc9453..67ccf0e7cca9 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -912,12 +912,13 @@ static void evict_chunk(struct audit_chunk *chunk)
}
static int audit_tree_handle_event(struct fsnotify_group *group,
+ struct inode *to_tell,
struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmonut_mark,
- struct fsnotify_event *event)
+ struct fsnotify_mark *vfsmount_mark,
+ u32 mask, void *data, int data_type,
+ const unsigned char *file_name)
{
- BUG();
- return -EOPNOTSUPP;
+ return 0;
}
static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group)
@@ -933,19 +934,8 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
BUG_ON(atomic_read(&entry->refcnt) < 1);
}
-static bool audit_tree_send_event(struct fsnotify_group *group, struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
- __u32 mask, void *data, int data_type)
-{
- return false;
-}
-
static const struct fsnotify_ops audit_tree_ops = {
.handle_event = audit_tree_handle_event,
- .should_send_event = audit_tree_send_event,
- .free_group_priv = NULL,
- .free_event_priv = NULL,
.freeing_mark = audit_tree_freeing_mark,
};
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 22831c4d369c..2596fac5dcb4 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -465,35 +465,27 @@ void audit_remove_watch_rule(struct audit_krule *krule)
}
}
-static bool audit_watch_should_send_event(struct fsnotify_group *group, struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
- __u32 mask, void *data, int data_type)
-{
- return true;
-}
-
/* Update watch data in audit rules based on fsnotify events. */
static int audit_watch_handle_event(struct fsnotify_group *group,
+ struct inode *to_tell,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
- struct fsnotify_event *event)
+ u32 mask, void *data, int data_type,
+ const unsigned char *dname)
{
struct inode *inode;
- __u32 mask = event->mask;
- const char *dname = event->file_name;
struct audit_parent *parent;
parent = container_of(inode_mark, struct audit_parent, mark);
BUG_ON(group != audit_watch_group);
- switch (event->data_type) {
+ switch (data_type) {
case (FSNOTIFY_EVENT_PATH):
- inode = event->path.dentry->d_inode;
+ inode = ((struct path *)data)->dentry->d_inode;
break;
case (FSNOTIFY_EVENT_INODE):
- inode = event->inode;
+ inode = (struct inode *)data;
break;
default:
BUG();
@@ -512,11 +504,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
}
static const struct fsnotify_ops audit_watch_fsnotify_ops = {
- .should_send_event = audit_watch_should_send_event,
.handle_event = audit_watch_handle_event,
- .free_group_priv = NULL,
- .freeing_mark = NULL,
- .free_event_priv = NULL,
};
static int __init audit_watch_init(void)
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 0c9b862292b2..9fd4246b04b8 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -10,6 +10,8 @@
#include <linux/mmzone.h>
#include <linux/kbuild.h>
#include <linux/page_cgroup.h>
+#include <linux/log2.h>
+#include <linux/spinlock_types.h>
void foo(void)
{
@@ -17,5 +19,9 @@ void foo(void)
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
+#ifdef CONFIG_SMP
+ DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+#endif
+ DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8bd9cfdc70d7..e2f46ba37f72 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -41,7 +41,6 @@
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
-#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
@@ -56,15 +55,20 @@
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/eventfd.h>
-#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
-#include <linux/file.h>
#include <linux/atomic.h>
/*
+ * pidlists linger the following amount before being destroyed. The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#define CGROUP_PIDLIST_DESTROY_DELAY HZ
+
+/*
* cgroup_mutex is the master lock. Any modification to cgroup or its
* hierarchy must be performed while holding it.
*
@@ -89,6 +93,33 @@ static DEFINE_MUTEX(cgroup_mutex);
static DEFINE_MUTEX(cgroup_root_mutex);
+#define cgroup_assert_mutex_or_rcu_locked() \
+ rcu_lockdep_assert(rcu_read_lock_held() || \
+ lockdep_is_held(&cgroup_mutex), \
+ "cgroup_mutex or RCU read lock required");
+
+#ifdef CONFIG_LOCKDEP
+#define cgroup_assert_mutex_or_root_locked() \
+ WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) && \
+ !lockdep_is_held(&cgroup_root_mutex)))
+#else
+#define cgroup_assert_mutex_or_root_locked() do { } while (0)
+#endif
+
+/*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions. Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
+/*
+ * pidlist destructions need to be flushed on cgroup destruction. Use a
+ * separate workqueue as flush domain.
+ */
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
/*
* Generate an array of cgroup subsystem pointers. At boot time, this is
* populated with the built in subsystems, and modular subsystems are
@@ -111,81 +142,6 @@ static struct cgroupfs_root cgroup_dummy_root;
/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
-/*
- * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
- */
-struct cfent {
- struct list_head node;
- struct dentry *dentry;
- struct cftype *type;
- struct cgroup_subsys_state *css;
-
- /* file xattrs */
- struct simple_xattrs xattrs;
-};
-
-/*
- * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
- * cgroup_subsys->use_id != 0.
- */
-#define CSS_ID_MAX (65535)
-struct css_id {
- /*
- * The css to which this ID points. This pointer is set to valid value
- * after cgroup is populated. If cgroup is removed, this will be NULL.
- * This pointer is expected to be RCU-safe because destroy()
- * is called after synchronize_rcu(). But for safe use, css_tryget()
- * should be used for avoiding race.
- */
- struct cgroup_subsys_state __rcu *css;
- /*
- * ID of this css.
- */
- unsigned short id;
- /*
- * Depth in hierarchy which this ID belongs to.
- */
- unsigned short depth;
- /*
- * ID is freed by RCU. (and lookup routine is RCU safe.)
- */
- struct rcu_head rcu_head;
- /*
- * Hierarchy of CSS ID belongs to.
- */
- unsigned short stack[0]; /* Array of Length (depth+1) */
-};
-
-/*
- * cgroup_event represents events which userspace want to receive.
- */
-struct cgroup_event {
- /*
- * css which the event belongs to.
- */
- struct cgroup_subsys_state *css;
- /*
- * Control file which the event associated.
- */
- struct cftype *cft;
- /*
- * eventfd to signal userspace about the event.
- */
- struct eventfd_ctx *eventfd;
- /*
- * Each of these stored in a list by the cgroup.
- */
- struct list_head list;
- /*
- * All fields below needed to unregister event when
- * userspace closes eventfd.
- */
- poll_table pt;
- wait_queue_head_t *wqh;
- wait_queue_t wait;
- struct work_struct remove;
-};
-
/* The list of hierarchy roots */
static LIST_HEAD(cgroup_roots);
@@ -223,6 +179,8 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
+static int cgroup_file_release(struct inode *inode, struct file *file);
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
/**
* cgroup_css - obtain a cgroup's css for the specified subsystem
@@ -285,16 +243,32 @@ static int notify_on_release(const struct cgroup *cgrp)
}
/**
+ * for_each_css - iterate all css's of a cgroup
+ * @css: the iteration cursor
+ * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
+ * @cgrp: the target cgroup to iterate css's of
+ *
+ * Should be called under cgroup_mutex.
+ */
+#define for_each_css(css, ssid, cgrp) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
+ if (!((css) = rcu_dereference_check( \
+ (cgrp)->subsys[(ssid)], \
+ lockdep_is_held(&cgroup_mutex)))) { } \
+ else
+
+/**
* for_each_subsys - iterate all loaded cgroup subsystems
* @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
*
- * Should be called under cgroup_mutex.
+ * Iterates through all loaded subsystems. Should be called under
+ * cgroup_mutex or cgroup_root_mutex.
*/
-#define for_each_subsys(ss, i) \
- for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- !((ss) = cgroup_subsys[i]); })) { } \
+#define for_each_subsys(ss, ssid) \
+ for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; }); \
+ (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
+ if (!((ss) = cgroup_subsys[(ssid)])) { } \
else
/**
@@ -309,10 +283,6 @@ static int notify_on_release(const struct cgroup *cgrp)
for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT && \
(((ss) = cgroup_subsys[i]) || true); (i)++)
-/* iterate each subsystem attached to a hierarchy */
-#define for_each_root_subsys(root, ss) \
- list_for_each_entry((ss), &(root)->subsys_list, sibling)
-
/* iterate across the active hierarchies */
#define for_each_active_root(root) \
list_for_each_entry((root), &cgroup_roots, root_list)
@@ -387,9 +357,6 @@ struct cgrp_cset_link {
static struct css_set init_css_set;
static struct cgrp_cset_link init_cgrp_cset_link;
-static int cgroup_init_idr(struct cgroup_subsys *ss,
- struct cgroup_subsys_state *css);
-
/*
* css_set_lock protects the list of css_set objects, and the chain of
* tasks off each css_set. Nests outside task->alloc_lock due to
@@ -841,8 +808,6 @@ static struct backing_dev_info cgroup_backing_dev_info = {
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
-static int alloc_css_id(struct cgroup_subsys_state *child_css);
-
static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
{
struct inode *inode = new_inode(sb);
@@ -891,11 +856,7 @@ static void cgroup_free_fn(struct work_struct *work)
*/
deactivate_super(cgrp->root->sb);
- /*
- * if we're getting rid of the cgroup, refcount should ensure
- * that there are no pidlists left.
- */
- BUG_ON(!list_empty(&cgrp->pidlists));
+ cgroup_pidlist_destroy_all(cgrp);
simple_xattrs_free(&cgrp->xattrs);
@@ -908,7 +869,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
INIT_WORK(&cgrp->destroy_work, cgroup_free_fn);
- schedule_work(&cgrp->destroy_work);
+ queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
}
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -918,6 +879,16 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
struct cgroup *cgrp = dentry->d_fsdata;
BUG_ON(!(cgroup_is_dead(cgrp)));
+
+ /*
+ * XXX: cgrp->id is only used to look up css's. As cgroup
+ * and css's lifetimes will be decoupled, it should be made
+ * per-subsystem and moved to css->id so that lookups are
+ * successful until the target css is released.
+ */
+ idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ cgrp->id = -1;
+
call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
} else {
struct cfent *cfe = __d_cfe(dentry);
@@ -932,11 +903,6 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
iput(inode);
}
-static int cgroup_delete(const struct dentry *d)
-{
- return 1;
-}
-
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
@@ -1073,7 +1039,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
cgroup_css(cgroup_dummy_top, ss));
cgroup_css(cgrp, ss)->cgroup = cgrp;
- list_move(&ss->sibling, &root->subsys_list);
ss->root = root;
if (ss->bind)
ss->bind(cgroup_css(cgrp, ss));
@@ -1092,7 +1057,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
RCU_INIT_POINTER(cgrp->subsys[i], NULL);
cgroup_subsys[i]->root = &cgroup_dummy_root;
- list_move(&ss->sibling, &cgroup_dummy_root.subsys_list);
/* subsystem is now free - drop reference on module */
module_put(ss->module);
@@ -1119,10 +1083,12 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
{
struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
struct cgroup_subsys *ss;
+ int ssid;
mutex_lock(&cgroup_root_mutex);
- for_each_root_subsys(root, ss)
- seq_printf(seq, ",%s", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->subsys_mask & (1 << ssid))
+ seq_printf(seq, ",%s", ss->name);
if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
seq_puts(seq, ",sane_behavior");
if (root->flags & CGRP_ROOT_NOPREFIX)
@@ -1385,8 +1351,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
cgrp->dummy_css.cgroup = cgrp;
- INIT_LIST_HEAD(&cgrp->event_list);
- spin_lock_init(&cgrp->event_list_lock);
simple_xattrs_init(&cgrp->xattrs);
}
@@ -1394,7 +1358,6 @@ static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
- INIT_LIST_HEAD(&root->subsys_list);
INIT_LIST_HEAD(&root->root_list);
root->number_of_cgroups = 1;
cgrp->root = root;
@@ -1523,7 +1486,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
{
static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
- .d_delete = cgroup_delete,
+ .d_delete = always_delete_dentry,
};
struct inode *inode =
@@ -1716,7 +1679,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
return ERR_PTR(ret);
}
-static void cgroup_kill_sb(struct super_block *sb) {
+static void cgroup_kill_sb(struct super_block *sb)
+{
struct cgroupfs_root *root = sb->s_fs_info;
struct cgroup *cgrp = &root->top_cgroup;
struct cgrp_cset_link *link, *tmp_link;
@@ -1999,8 +1963,8 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
bool threadgroup)
{
int retval, i, group_size;
- struct cgroup_subsys *ss, *failed_ss = NULL;
struct cgroupfs_root *root = cgrp->root;
+ struct cgroup_subsys_state *css, *failed_css = NULL;
/* threadgroup list cursor and array */
struct task_struct *leader = tsk;
struct task_and_cgroup *tc;
@@ -2073,13 +2037,11 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
/*
* step 1: check that we can legitimately attach to the cgroup.
*/
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss->can_attach) {
- retval = ss->can_attach(css, &tset);
+ for_each_css(css, i, cgrp) {
+ if (css->ss->can_attach) {
+ retval = css->ss->can_attach(css, &tset);
if (retval) {
- failed_ss = ss;
+ failed_css = css;
goto out_cancel_attach;
}
}
@@ -2115,12 +2077,9 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
/*
* step 4: do subsystem attach callbacks.
*/
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss->attach)
- ss->attach(css, &tset);
- }
+ for_each_css(css, i, cgrp)
+ if (css->ss->attach)
+ css->ss->attach(css, &tset);
/*
* step 5: success! and cleanup
@@ -2137,13 +2096,11 @@ out_put_css_set_refs:
}
out_cancel_attach:
if (retval) {
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss == failed_ss)
+ for_each_css(css, i, cgrp) {
+ if (css == failed_css)
break;
- if (ss->cancel_attach)
- ss->cancel_attach(css, &tset);
+ if (css->ss->cancel_attach)
+ css->ss->cancel_attach(css, &tset);
}
}
out_free_group_list:
@@ -2171,7 +2128,7 @@ retry_find_task:
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
- ret= -ESRCH;
+ ret = -ESRCH;
goto out_unlock_cgroup;
}
/*
@@ -2283,10 +2240,9 @@ static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
return 0;
}
-static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_release_agent_show(struct seq_file *seq, void *v)
{
- struct cgroup *cgrp = css->cgroup;
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
@@ -2296,174 +2252,129 @@ static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
return 0;
}
-static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
{
- seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup));
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+ seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
return 0;
}
/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64
-static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
+static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
{
- char buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- char *end;
+ struct cfent *cfe = __d_cfe(file->f_dentry);
+ struct cftype *cft = __d_cft(file->f_dentry);
+ struct cgroup_subsys_state *css = cfe->css;
+ size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1;
+ char *buf;
+ int ret;
- if (!nbytes)
- return -EINVAL;
- if (nbytes >= sizeof(buffer))
+ if (nbytes >= max_bytes)
return -E2BIG;
- if (copy_from_user(buffer, userbuf, nbytes))
- return -EFAULT;
- buffer[nbytes] = 0; /* nul-terminate */
- if (cft->write_u64) {
- u64 val = simple_strtoull(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_u64(css, cft, val);
+ buf = kmalloc(nbytes + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, userbuf, nbytes)) {
+ ret = -EFAULT;
+ goto out_free;
+ }
+
+ buf[nbytes] = '\0';
+
+ if (cft->write_string) {
+ ret = cft->write_string(css, cft, strstrip(buf));
+ } else if (cft->write_u64) {
+ unsigned long long v;
+ ret = kstrtoull(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_u64(css, cft, v);
+ } else if (cft->write_s64) {
+ long long v;
+ ret = kstrtoll(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_s64(css, cft, v);
+ } else if (cft->trigger) {
+ ret = cft->trigger(css, (unsigned int)cft->private);
} else {
- s64 val = simple_strtoll(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_s64(css, cft, val);
+ ret = -EINVAL;
}
- if (!retval)
- retval = nbytes;
- return retval;
+out_free:
+ kfree(buf);
+ return ret ?: nbytes;
}
-static ssize_t cgroup_write_string(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
+/*
+ * seqfile ops/methods for returning structured data. Currently just
+ * supports string->u64 maps, but can be extended in future.
+ */
+
+static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
- char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- size_t max_bytes = cft->max_write_len;
- char *buffer = local_buffer;
+ struct cftype *cft = seq_cft(seq);
- if (!max_bytes)
- max_bytes = sizeof(local_buffer) - 1;
- if (nbytes >= max_bytes)
- return -E2BIG;
- /* Allocate a dynamic buffer if we need one */
- if (nbytes >= sizeof(local_buffer)) {
- buffer = kmalloc(nbytes + 1, GFP_KERNEL);
- if (buffer == NULL)
- return -ENOMEM;
- }
- if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
- retval = -EFAULT;
- goto out;
+ if (cft->seq_start) {
+ return cft->seq_start(seq, ppos);
+ } else {
+ /*
+ * The same behavior and code as single_open(). Returns
+ * !NULL if pos is at the beginning; otherwise, NULL.
+ */
+ return NULL + !*ppos;
}
-
- buffer[nbytes] = 0; /* nul-terminate */
- retval = cft->write_string(css, cft, strstrip(buffer));
- if (!retval)
- retval = nbytes;
-out:
- if (buffer != local_buffer)
- kfree(buffer);
- return retval;
}
-static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
- size_t nbytes, loff_t *ppos)
+static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
+ struct cftype *cft = seq_cft(seq);
- if (cft->write)
- return cft->write(css, cft, file, buf, nbytes, ppos);
- if (cft->write_u64 || cft->write_s64)
- return cgroup_write_X64(css, cft, file, buf, nbytes, ppos);
- if (cft->write_string)
- return cgroup_write_string(css, cft, file, buf, nbytes, ppos);
- if (cft->trigger) {
- int ret = cft->trigger(css, (unsigned int)cft->private);
- return ret ? ret : nbytes;
+ if (cft->seq_next) {
+ return cft->seq_next(seq, v, ppos);
+ } else {
+ /*
+ * The same behavior and code as single_open(), always
+ * terminate after the initial read.
+ */
+ ++*ppos;
+ return NULL;
}
- return -EINVAL;
}
-static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
+static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- u64 val = cft->read_u64(css, cft);
- int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
+ struct cftype *cft = seq_cft(seq);
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+ if (cft->seq_stop)
+ cft->seq_stop(seq, v);
}
-static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
+static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- s64 val = cft->read_s64(css, cft);
- int len = sprintf(tmp, "%lld\n", (long long) val);
-
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
-}
+ struct cftype *cft = seq_cft(m);
+ struct cgroup_subsys_state *css = seq_css(m);
-static ssize_t cgroup_file_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
+ if (cft->seq_show)
+ return cft->seq_show(m, arg);
- if (cft->read)
- return cft->read(css, cft, file, buf, nbytes, ppos);
if (cft->read_u64)
- return cgroup_read_u64(css, cft, file, buf, nbytes, ppos);
- if (cft->read_s64)
- return cgroup_read_s64(css, cft, file, buf, nbytes, ppos);
- return -EINVAL;
-}
-
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
-static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
-{
- struct seq_file *sf = cb->state;
- return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
-}
-
-static int cgroup_seqfile_show(struct seq_file *m, void *arg)
-{
- struct cfent *cfe = m->private;
- struct cftype *cft = cfe->type;
- struct cgroup_subsys_state *css = cfe->css;
-
- if (cft->read_map) {
- struct cgroup_map_cb cb = {
- .fill = cgroup_map_add,
- .state = m,
- };
- return cft->read_map(css, cft, &cb);
- }
- return cft->read_seq_string(css, cft, m);
+ seq_printf(m, "%llu\n", cft->read_u64(css, cft));
+ else if (cft->read_s64)
+ seq_printf(m, "%lld\n", cft->read_s64(css, cft));
+ else
+ return -EINVAL;
+ return 0;
}
-static const struct file_operations cgroup_seqfile_operations = {
- .read = seq_read,
- .write = cgroup_file_write,
- .llseek = seq_lseek,
- .release = single_release,
+static struct seq_operations cgroup_seq_operations = {
+ .start = cgroup_seqfile_start,
+ .next = cgroup_seqfile_next,
+ .stop = cgroup_seqfile_stop,
+ .show = cgroup_seqfile_show,
};
static int cgroup_file_open(struct inode *inode, struct file *file)
@@ -2472,6 +2383,7 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
struct cftype *cft = __d_cft(file->f_dentry);
struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
struct cgroup_subsys_state *css;
+ struct cgroup_open_file *of;
int err;
err = generic_file_open(inode, file);
@@ -2501,30 +2413,26 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
WARN_ON_ONCE(cfe->css && cfe->css != css);
cfe->css = css;
- if (cft->read_map || cft->read_seq_string) {
- file->f_op = &cgroup_seqfile_operations;
- err = single_open(file, cgroup_seqfile_show, cfe);
- } else if (cft->open) {
- err = cft->open(inode, file);
+ of = __seq_open_private(file, &cgroup_seq_operations,
+ sizeof(struct cgroup_open_file));
+ if (of) {
+ of->cfe = cfe;
+ return 0;
}
- if (css->ss && err)
+ if (css->ss)
css_put(css);
- return err;
+ return -ENOMEM;
}
static int cgroup_file_release(struct inode *inode, struct file *file)
{
struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
struct cgroup_subsys_state *css = cfe->css;
- int ret = 0;
- if (cft->release)
- ret = cft->release(inode, file);
if (css->ss)
css_put(css);
- return ret;
+ return seq_release_private(inode, file);
}
/*
@@ -2635,7 +2543,7 @@ static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
}
static const struct file_operations cgroup_file_operations = {
- .read = cgroup_file_read,
+ .read = seq_read,
.write = cgroup_file_write,
.llseek = generic_file_llseek,
.open = cgroup_file_open,
@@ -2660,16 +2568,6 @@ static const struct inode_operations cgroup_dir_inode_operations = {
.removexattr = cgroup_removexattr,
};
-/*
- * Check if a file is a control file
- */
-static inline struct cftype *__file_cft(struct file *file)
-{
- if (file_inode(file)->i_fop != &cgroup_file_operations)
- return ERR_PTR(-EINVAL);
- return __d_cft(file->f_dentry);
-}
-
static int cgroup_create_file(struct dentry *dentry, umode_t mode,
struct super_block *sb)
{
@@ -2727,12 +2625,11 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
if (cft->mode)
return cft->mode;
- if (cft->read || cft->read_u64 || cft->read_s64 ||
- cft->read_map || cft->read_seq_string)
+ if (cft->read_u64 || cft->read_s64 || cft->seq_show)
mode |= S_IRUGO;
- if (cft->write || cft->write_u64 || cft->write_s64 ||
- cft->write_string || cft->trigger)
+ if (cft->write_u64 || cft->write_s64 || cft->write_string ||
+ cft->trigger)
mode |= S_IWUSR;
return mode;
@@ -3028,9 +2925,9 @@ static void cgroup_enable_task_cg_lists(void)
* @parent_css: css whose children to walk
*
* This function returns the next child of @parent_css and should be called
- * under RCU read lock. The only requirement is that @parent_css and
- * @pos_css are accessible. The next sibling is guaranteed to be returned
- * regardless of their states.
+ * under either cgroup_mutex or RCU read lock. The only requirement is
+ * that @parent_css and @pos_css are accessible. The next sibling is
+ * guaranteed to be returned regardless of their states.
*/
struct cgroup_subsys_state *
css_next_child(struct cgroup_subsys_state *pos_css,
@@ -3040,7 +2937,7 @@ css_next_child(struct cgroup_subsys_state *pos_css,
struct cgroup *cgrp = parent_css->cgroup;
struct cgroup *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutex_or_rcu_locked();
/*
* @pos could already have been removed. Once a cgroup is removed,
@@ -3087,10 +2984,10 @@ EXPORT_SYMBOL_GPL(css_next_child);
* to visit for pre-order traversal of @root's descendants. @root is
* included in the iteration and the first node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @root are accessible and @pos is a descendant of @root.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @root are accessible and @pos is a descendant of @root.
*/
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
@@ -3098,7 +2995,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit @root */
if (!pos)
@@ -3129,17 +3026,17 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre);
* is returned. This can be used during pre-order traversal to skip
* subtree of @pos.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct rightmost descendant as long as @pos is
- * accessible.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct rightmost descendant as
+ * long as @pos is accessible.
*/
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last, *tmp;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutex_or_rcu_locked();
do {
last = pos;
@@ -3175,10 +3072,11 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
* to visit for post-order traversal of @root's descendants. @root is
* included in the iteration and the last node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @cgroup are accessible and @pos is a descendant of @cgroup.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @cgroup are accessible and @pos is a descendant of
+ * @cgroup.
*/
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
@@ -3186,7 +3084,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutex_or_rcu_locked();
/* if first iteration, visit leftmost descendant which may be @root */
if (!pos)
@@ -3525,14 +3423,12 @@ struct cgroup_pidlist {
pid_t *list;
/* how many elements the above list has */
int length;
- /* how many files are using the current array */
- int use_count;
/* each of these stored in a list by its cgroup */
struct list_head links;
/* pointer to the cgroup we belong to, for list removal purposes */
struct cgroup *owner;
- /* protects the other fields */
- struct rw_semaphore rwsem;
+ /* for delayed destruction */
+ struct delayed_work destroy_dwork;
};
/*
@@ -3548,6 +3444,7 @@ static void *pidlist_allocate(int count)
else
return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
+
static void pidlist_free(void *p)
{
if (is_vmalloc_addr(p))
@@ -3557,6 +3454,47 @@ static void pidlist_free(void *p)
}
/*
+ * Used to destroy all pidlists lingering waiting for destroy timer. None
+ * should be left afterwards.
+ */
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+{
+ struct cgroup_pidlist *l, *tmp_l;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+ list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+ mutex_unlock(&cgrp->pidlist_mutex);
+
+ flush_workqueue(cgroup_pidlist_destroy_wq);
+ BUG_ON(!list_empty(&cgrp->pidlists));
+}
+
+static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
+ destroy_dwork);
+ struct cgroup_pidlist *tofree = NULL;
+
+ mutex_lock(&l->owner->pidlist_mutex);
+
+ /*
+ * Destroy iff we didn't get queued again. The state won't change
+ * as destroy_dwork can only be queued while locked.
+ */
+ if (!delayed_work_pending(dwork)) {
+ list_del(&l->links);
+ pidlist_free(l->list);
+ put_pid_ns(l->key.ns);
+ tofree = l;
+ }
+
+ mutex_unlock(&l->owner->pidlist_mutex);
+ kfree(tofree);
+}
+
+/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
* Returns the number of unique elements.
*/
@@ -3586,52 +3524,92 @@ after:
return dest;
}
+/*
+ * The two pid files - task and cgroup.procs - guaranteed that the result
+ * is sorted, which forced this whole pidlist fiasco. As pid order is
+ * different per namespace, each namespace needs differently sorted list,
+ * making it impossible to use, for example, single rbtree of member tasks
+ * sorted by task pointer. As pidlists can be fairly large, allocating one
+ * per open file is dangerous, so cgroup had to implement shared pool of
+ * pidlists keyed by cgroup and namespace.
+ *
+ * All this extra complexity was caused by the original implementation
+ * committing to an entirely unnecessary property. In the long term, we
+ * want to do away with it. Explicitly scramble sort order if
+ * sane_behavior so that no such expectation exists in the new interface.
+ *
+ * Scrambling is done by swapping every two consecutive bits, which is
+ * non-identity one-to-one mapping which disturbs sort order sufficiently.
+ */
+static pid_t pid_fry(pid_t pid)
+{
+ unsigned a = pid & 0x55555555;
+ unsigned b = pid & 0xAAAAAAAA;
+
+ return (a << 1) | (b >> 1);
+}
+
+static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
+{
+ if (cgroup_sane_behavior(cgrp))
+ return pid_fry(pid);
+ else
+ return pid;
+}
+
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
+static int fried_cmppid(const void *a, const void *b)
+{
+ return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
+}
+
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+ enum cgroup_filetype type)
+{
+ struct cgroup_pidlist *l;
+ /* don't need task_nsproxy() if we're looking at ourself */
+ struct pid_namespace *ns = task_active_pid_ns(current);
+
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ list_for_each_entry(l, &cgrp->pidlists, links)
+ if (l->key.type == type && l->key.ns == ns)
+ return l;
+ return NULL;
+}
+
/*
* find the appropriate pidlist for our purpose (given procs vs tasks)
* returns with the lock on that pidlist already held, and takes care
* of the use count, or returns NULL with no locks held if we're out of
* memory.
*/
-static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
- enum cgroup_filetype type)
+static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
+ enum cgroup_filetype type)
{
struct cgroup_pidlist *l;
- /* don't need task_nsproxy() if we're looking at ourself */
- struct pid_namespace *ns = task_active_pid_ns(current);
- /*
- * We can't drop the pidlist_mutex before taking the l->rwsem in case
- * the last ref-holder is trying to remove l from the list at the same
- * time. Holding the pidlist_mutex precludes somebody taking whichever
- * list we find out from under us - compare release_pid_array().
- */
- mutex_lock(&cgrp->pidlist_mutex);
- list_for_each_entry(l, &cgrp->pidlists, links) {
- if (l->key.type == type && l->key.ns == ns) {
- /* make sure l doesn't vanish out from under us */
- down_write(&l->rwsem);
- mutex_unlock(&cgrp->pidlist_mutex);
- return l;
- }
- }
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ l = cgroup_pidlist_find(cgrp, type);
+ if (l)
+ return l;
+
/* entry not found; create a new one */
l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
- if (!l) {
- mutex_unlock(&cgrp->pidlist_mutex);
+ if (!l)
return l;
- }
- init_rwsem(&l->rwsem);
- down_write(&l->rwsem);
+
+ INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
l->key.type = type;
- l->key.ns = get_pid_ns(ns);
+ /* don't need task_nsproxy() if we're looking at ourself */
+ l->key.ns = get_pid_ns(task_active_pid_ns(current));
l->owner = cgrp;
list_add(&l->links, &cgrp->pidlists);
- mutex_unlock(&cgrp->pidlist_mutex);
return l;
}
@@ -3648,6 +3626,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
struct task_struct *tsk;
struct cgroup_pidlist *l;
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
/*
* If cgroup gets more users after we read count, we won't have
* enough space - tough. This race is indistinguishable to the
@@ -3674,20 +3654,24 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
css_task_iter_end(&it);
length = n;
/* now sort & (if procs) strip out duplicates */
- sort(array, length, sizeof(pid_t), cmppid, NULL);
+ if (cgroup_sane_behavior(cgrp))
+ sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
+ else
+ sort(array, length, sizeof(pid_t), cmppid, NULL);
if (type == CGROUP_FILE_PROCS)
length = pidlist_uniq(array, length);
- l = cgroup_pidlist_find(cgrp, type);
+
+ l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
+ mutex_unlock(&cgrp->pidlist_mutex);
pidlist_free(array);
return -ENOMEM;
}
- /* store array, freeing old if necessary - lock already held */
+
+ /* store array, freeing old if necessary */
pidlist_free(l->list);
l->list = array;
l->length = length;
- l->use_count++;
- up_write(&l->rwsem);
*lp = l;
return 0;
}
@@ -3761,20 +3745,45 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup_pidlist *l = s->private;
+ struct cgroup_open_file *of = s->private;
+ struct cgroup *cgrp = seq_css(s)->cgroup;
+ struct cgroup_pidlist *l;
+ enum cgroup_filetype type = seq_cft(s)->private;
int index = 0, pid = *pos;
- int *iter;
+ int *iter, ret;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+
+ /*
+ * !NULL @of->priv indicates that this isn't the first start()
+ * after open. If the matching pidlist is around, we can use that.
+ * Look for it. Note that @of->priv can't be used directly. It
+ * could already have been destroyed.
+ */
+ if (of->priv)
+ of->priv = cgroup_pidlist_find(cgrp, type);
+
+ /*
+ * Either this is the first start() after open or the matching
+ * pidlist has been destroyed inbetween. Create a new one.
+ */
+ if (!of->priv) {
+ ret = pidlist_array_load(cgrp, type,
+ (struct cgroup_pidlist **)&of->priv);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+ l = of->priv;
- down_read(&l->rwsem);
if (pid) {
int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
- if (l->list[mid] == pid) {
+ if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
index = mid;
break;
- } else if (l->list[mid] <= pid)
+ } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
index = mid + 1;
else
end = mid;
@@ -3785,19 +3794,25 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
return NULL;
/* Update the abstract position to be the actual pid that we found */
iter = l->list + index;
- *pos = *iter;
+ *pos = cgroup_pid_fry(cgrp, *iter);
return iter;
}
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup_pidlist *l = s->private;
- up_read(&l->rwsem);
+ struct cgroup_open_file *of = s->private;
+ struct cgroup_pidlist *l = of->priv;
+
+ if (l)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
+ CGROUP_PIDLIST_DESTROY_DELAY);
+ mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup_pidlist *l = s->private;
+ struct cgroup_open_file *of = s->private;
+ struct cgroup_pidlist *l = of->priv;
pid_t *p = v;
pid_t *end = l->list + l->length;
/*
@@ -3808,7 +3823,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
if (p >= end) {
return NULL;
} else {
- *pos = *p;
+ *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
return p;
}
}
@@ -3829,92 +3844,6 @@ static const struct seq_operations cgroup_pidlist_seq_operations = {
.show = cgroup_pidlist_show,
};
-static void cgroup_release_pid_array(struct cgroup_pidlist *l)
-{
- /*
- * the case where we're the last user of this particular pidlist will
- * have us remove it from the cgroup's list, which entails taking the
- * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
- * pidlist_mutex, we have to take pidlist_mutex first.
- */
- mutex_lock(&l->owner->pidlist_mutex);
- down_write(&l->rwsem);
- BUG_ON(!l->use_count);
- if (!--l->use_count) {
- /* we're the last user if refcount is 0; remove and free */
- list_del(&l->links);
- mutex_unlock(&l->owner->pidlist_mutex);
- pidlist_free(l->list);
- put_pid_ns(l->key.ns);
- up_write(&l->rwsem);
- kfree(l);
- return;
- }
- mutex_unlock(&l->owner->pidlist_mutex);
- up_write(&l->rwsem);
-}
-
-static int cgroup_pidlist_release(struct inode *inode, struct file *file)
-{
- struct cgroup_pidlist *l;
- if (!(file->f_mode & FMODE_READ))
- return 0;
- /*
- * the seq_file will only be initialized if the file was opened for
- * reading; hence we check if it's not null only in that case.
- */
- l = ((struct seq_file *)file->private_data)->private;
- cgroup_release_pid_array(l);
- return seq_release(inode, file);
-}
-
-static const struct file_operations cgroup_pidlist_operations = {
- .read = seq_read,
- .llseek = seq_lseek,
- .write = cgroup_file_write,
- .release = cgroup_pidlist_release,
-};
-
-/*
- * The following functions handle opens on a file that displays a pidlist
- * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
- * in the cgroup.
- */
-/* helper function for the two below it */
-static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
-{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
- struct cgroup_pidlist *l;
- int retval;
-
- /* Nothing to do for write-only files */
- if (!(file->f_mode & FMODE_READ))
- return 0;
-
- /* have the array populated */
- retval = pidlist_array_load(cgrp, type, &l);
- if (retval)
- return retval;
- /* configure file information */
- file->f_op = &cgroup_pidlist_operations;
-
- retval = seq_open(file, &cgroup_pidlist_seq_operations);
- if (retval) {
- cgroup_release_pid_array(l);
- return retval;
- }
- ((struct seq_file *)file->private_data)->private = l;
- return 0;
-}
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
-}
-static int cgroup_procs_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
-}
-
static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -3949,202 +3878,6 @@ static void cgroup_dput(struct cgroup *cgrp)
deactivate_super(sb);
}
-/*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
-static void cgroup_event_remove(struct work_struct *work)
-{
- struct cgroup_event *event = container_of(work, struct cgroup_event,
- remove);
- struct cgroup_subsys_state *css = event->css;
-
- remove_wait_queue(event->wqh, &event->wait);
-
- event->cft->unregister_event(css, event->cft, event->eventfd);
-
- /* Notify userspace the event is going away. */
- eventfd_signal(event->eventfd, 1);
-
- eventfd_ctx_put(event->eventfd);
- kfree(event);
- css_put(css);
-}
-
-/*
- * Gets called on POLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
-static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
- int sync, void *key)
-{
- struct cgroup_event *event = container_of(wait,
- struct cgroup_event, wait);
- struct cgroup *cgrp = event->css->cgroup;
- unsigned long flags = (unsigned long)key;
-
- if (flags & POLLHUP) {
- /*
- * If the event has been detached at cgroup removal, we
- * can simply return knowing the other side will cleanup
- * for us.
- *
- * We can't race against event freeing since the other
- * side will require wqh->lock via remove_wait_queue(),
- * which we hold.
- */
- spin_lock(&cgrp->event_list_lock);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- /*
- * We are in atomic context, but cgroup_event_remove()
- * may sleep, so we have to call it in workqueue.
- */
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
- }
-
- return 0;
-}
-
-static void cgroup_event_ptable_queue_proc(struct file *file,
- wait_queue_head_t *wqh, poll_table *pt)
-{
- struct cgroup_event *event = container_of(pt,
- struct cgroup_event, pt);
-
- event->wqh = wqh;
- add_wait_queue(wqh, &event->wait);
-}
-
-/*
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
-static int cgroup_write_event_control(struct cgroup_subsys_state *dummy_css,
- struct cftype *cft, const char *buffer)
-{
- struct cgroup *cgrp = dummy_css->cgroup;
- struct cgroup_event *event;
- struct cgroup_subsys_state *cfile_css;
- unsigned int efd, cfd;
- struct fd efile;
- struct fd cfile;
- char *endp;
- int ret;
-
- efd = simple_strtoul(buffer, &endp, 10);
- if (*endp != ' ')
- return -EINVAL;
- buffer = endp + 1;
-
- cfd = simple_strtoul(buffer, &endp, 10);
- if ((*endp != ' ') && (*endp != '\0'))
- return -EINVAL;
- buffer = endp + 1;
-
- event = kzalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&event->list);
- init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
- init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
- INIT_WORK(&event->remove, cgroup_event_remove);
-
- efile = fdget(efd);
- if (!efile.file) {
- ret = -EBADF;
- goto out_kfree;
- }
-
- event->eventfd = eventfd_ctx_fileget(efile.file);
- if (IS_ERR(event->eventfd)) {
- ret = PTR_ERR(event->eventfd);
- goto out_put_efile;
- }
-
- cfile = fdget(cfd);
- if (!cfile.file) {
- ret = -EBADF;
- goto out_put_eventfd;
- }
-
- /* the process need read permission on control file */
- /* AV: shouldn't we check that it's been opened for read instead? */
- ret = inode_permission(file_inode(cfile.file), MAY_READ);
- if (ret < 0)
- goto out_put_cfile;
-
- event->cft = __file_cft(cfile.file);
- if (IS_ERR(event->cft)) {
- ret = PTR_ERR(event->cft);
- goto out_put_cfile;
- }
-
- if (!event->cft->ss) {
- ret = -EBADF;
- goto out_put_cfile;
- }
-
- /*
- * Determine the css of @cfile, verify it belongs to the same
- * cgroup as cgroup.event_control, and associate @event with it.
- * Remaining events are automatically removed on cgroup destruction
- * but the removal is asynchronous, so take an extra ref.
- */
- rcu_read_lock();
-
- ret = -EINVAL;
- event->css = cgroup_css(cgrp, event->cft->ss);
- cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, event->cft->ss);
- if (event->css && event->css == cfile_css && css_tryget(event->css))
- ret = 0;
-
- rcu_read_unlock();
- if (ret)
- goto out_put_cfile;
-
- if (!event->cft->register_event || !event->cft->unregister_event) {
- ret = -EINVAL;
- goto out_put_css;
- }
-
- ret = event->cft->register_event(event->css, event->cft,
- event->eventfd, buffer);
- if (ret)
- goto out_put_css;
-
- efile.file->f_op->poll(efile.file, &event->pt);
-
- spin_lock(&cgrp->event_list_lock);
- list_add(&event->list, &cgrp->event_list);
- spin_unlock(&cgrp->event_list_lock);
-
- fdput(cfile);
- fdput(efile);
-
- return 0;
-
-out_put_css:
- css_put(event->css);
-out_put_cfile:
- fdput(cfile);
-out_put_eventfd:
- eventfd_ctx_put(event->eventfd);
-out_put_efile:
- fdput(efile);
-out_kfree:
- kfree(event);
-
- return ret;
-}
-
static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -4164,17 +3897,15 @@ static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.procs",
- .open = cgroup_procs_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_PROCS,
.write_u64 = cgroup_procs_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
{
- .name = "cgroup.event_control",
- .write_string = cgroup_write_event_control,
- .mode = S_IWUGO,
- },
- {
.name = "cgroup.clone_children",
.flags = CFTYPE_INSANE,
.read_u64 = cgroup_clone_children_read,
@@ -4183,7 +3914,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.sane_behavior",
.flags = CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_sane_behavior_show,
+ .seq_show = cgroup_sane_behavior_show,
},
/*
@@ -4194,9 +3925,12 @@ static struct cftype cgroup_base_files[] = {
{
.name = "tasks",
.flags = CFTYPE_INSANE, /* use "procs" instead */
- .open = cgroup_tasks_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_TASKS,
.write_u64 = cgroup_tasks_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
{
@@ -4208,7 +3942,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "release_agent",
.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_release_agent_show,
+ .seq_show = cgroup_release_agent_show,
.write_string = cgroup_release_agent_write,
.max_write_len = PATH_MAX,
},
@@ -4240,21 +3974,6 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
goto err;
}
}
-
- /* This cgroup is ready now */
- for_each_root_subsys(cgrp->root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
- struct css_id *id = rcu_dereference_protected(css->id, true);
-
- /*
- * Update id->css pointer and make this css visible from
- * CSS ID functions. This pointer will be dereferened
- * from RCU-read-side without locks.
- */
- if (id)
- rcu_assign_pointer(id->css, css);
- }
-
return 0;
err:
cgroup_clear_dir(cgrp, subsys_mask);
@@ -4306,7 +4025,7 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
* css_put(). dput() requires process context which we don't have.
*/
INIT_WORK(&css->destroy_work, css_free_work_fn);
- schedule_work(&css->destroy_work);
+ queue_work(cgroup_destroy_wq, &css->destroy_work);
}
static void css_release(struct percpu_ref *ref)
@@ -4314,6 +4033,7 @@ static void css_release(struct percpu_ref *ref)
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
+ rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
@@ -4323,7 +4043,6 @@ static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss,
css->cgroup = cgrp;
css->ss = ss;
css->flags = 0;
- css->id = NULL;
if (cgrp->parent)
css->parent = cgroup_css(cgrp->parent, ss);
@@ -4369,6 +4088,62 @@ static void offline_css(struct cgroup_subsys_state *css)
RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
}
+/**
+ * create_css - create a cgroup_subsys_state
+ * @cgrp: the cgroup new css will be associated with
+ * @ss: the subsys of new css
+ *
+ * Create a new css associated with @cgrp - @ss pair. On success, the new
+ * css is online and installed in @cgrp with all interface files created.
+ * Returns 0 on success, -errno on failure.
+ */
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct cgroup *parent = cgrp->parent;
+ struct cgroup_subsys_state *css;
+ int err;
+
+ lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
+ lockdep_assert_held(&cgroup_mutex);
+
+ css = ss->css_alloc(cgroup_css(parent, ss));
+ if (IS_ERR(css))
+ return PTR_ERR(css);
+
+ err = percpu_ref_init(&css->refcnt, css_release);
+ if (err)
+ goto err_free;
+
+ init_css(css, ss, cgrp);
+
+ err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
+ if (err)
+ goto err_free;
+
+ err = online_css(css);
+ if (err)
+ goto err_free;
+
+ dget(cgrp->dentry);
+ css_get(css->parent);
+
+ if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
+ parent->parent) {
+ pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
+ current->comm, current->pid, ss->name);
+ if (!strcmp(ss->name, "memory"))
+ pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
+ ss->warned_broken_hierarchy = true;
+ }
+
+ return 0;
+
+err_free:
+ percpu_ref_cancel_init(&css->refcnt);
+ ss->css_free(css);
+ return err;
+}
+
/*
* cgroup_create - create a cgroup
* @parent: cgroup that will be parent of the new cgroup
@@ -4380,11 +4155,10 @@ static void offline_css(struct cgroup_subsys_state *css)
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
umode_t mode)
{
- struct cgroup_subsys_state *css_ar[CGROUP_SUBSYS_COUNT] = { };
struct cgroup *cgrp;
struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
- int err = 0;
+ int ssid, err = 0;
struct cgroup_subsys *ss;
struct super_block *sb = root->sb;
@@ -4440,29 +4214,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css;
-
- css = ss->css_alloc(cgroup_css(parent, ss));
- if (IS_ERR(css)) {
- err = PTR_ERR(css);
- goto err_free_all;
- }
- css_ar[ss->subsys_id] = css;
-
- err = percpu_ref_init(&css->refcnt, css_release);
- if (err)
- goto err_free_all;
-
- init_css(css, ss, cgrp);
-
- if (ss->use_id) {
- err = alloc_css_id(css);
- if (err)
- goto err_free_all;
- }
- }
-
/*
* Create directory. cgroup_create_file() returns with the new
* directory locked on success so that it can be populated without
@@ -4470,7 +4221,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
if (err < 0)
- goto err_free_all;
+ goto err_unlock;
lockdep_assert_held(&dentry->d_inode->i_mutex);
cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4479,59 +4230,34 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
root->number_of_cgroups++;
- /* each css holds a ref to the cgroup's dentry and the parent css */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- dget(dentry);
- css_get(css->parent);
- }
-
/* hold a ref to the parent's dentry */
dget(parent->dentry);
- /* creation succeeded, notify subsystems */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- err = online_css(css);
- if (err)
- goto err_destroy;
-
- if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
- parent->parent) {
- pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
- current->comm, current->pid, ss->name);
- if (!strcmp(ss->name, "memory"))
- pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
- ss->warned_broken_hierarchy = true;
- }
- }
-
+ /*
+ * @cgrp is now fully operational. If something fails after this
+ * point, it'll be released via the normal destruction path.
+ */
idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
if (err)
goto err_destroy;
- err = cgroup_populate_dir(cgrp, root->subsys_mask);
- if (err)
- goto err_destroy;
+ /* let's create and online css's */
+ for_each_subsys(ss, ssid) {
+ if (root->subsys_mask & (1 << ssid)) {
+ err = create_css(cgrp, ss);
+ if (err)
+ goto err_destroy;
+ }
+ }
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return 0;
-err_free_all:
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- if (css) {
- percpu_ref_cancel_init(&css->refcnt);
- ss->css_free(css);
- }
- }
+err_unlock:
mutex_unlock(&cgroup_mutex);
/* Release the reference count that we took on the superblock */
deactivate_super(sb);
@@ -4603,7 +4329,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
container_of(ref, struct cgroup_subsys_state, refcnt);
INIT_WORK(&css->destroy_work, css_killed_work_fn);
- schedule_work(&css->destroy_work);
+ queue_work(cgroup_destroy_wq, &css->destroy_work);
}
/**
@@ -4666,10 +4392,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
struct dentry *d = cgrp->dentry;
- struct cgroup_event *event, *tmp;
- struct cgroup_subsys *ss;
+ struct cgroup_subsys_state *css;
struct cgroup *child;
bool empty;
+ int ssid;
lockdep_assert_held(&d->d_inode->i_mutex);
lockdep_assert_held(&cgroup_mutex);
@@ -4705,8 +4431,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
* will be invoked to perform the rest of destruction once the
* percpu refs of all css's are confirmed to be killed.
*/
- for_each_root_subsys(cgrp->root, ss)
- kill_css(cgroup_css(cgrp, ss));
+ for_each_css(css, ssid, cgrp)
+ kill_css(css);
/*
* Mark @cgrp dead. This prevents further task migration and child
@@ -4741,18 +4467,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
dget(d);
cgroup_d_remove_dir(d);
- /*
- * Unregister events and notify userspace.
- * Notify userspace about cgroup removing only after rmdir of cgroup
- * directory to avoid race between userspace and kernelspace.
- */
- spin_lock(&cgrp->event_list_lock);
- list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
- list_del_init(&event->list);
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
-
return 0;
};
@@ -4775,14 +4489,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
/* delete this cgroup from parent->children */
list_del_rcu(&cgrp->sibling);
- /*
- * We should remove the cgroup object from idr before its grace
- * period starts, so we won't be looking up a cgroup while the
- * cgroup is being freed.
- */
- idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- cgrp->id = -1;
-
dput(d);
set_bit(CGRP_RELEASABLE, &parent->flags);
@@ -4831,7 +4537,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
cgroup_init_cftsets(ss);
/* Create the top cgroup state for this subsystem */
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
ss->root = &cgroup_dummy_root;
css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
/* We don't handle early failures gracefully */
@@ -4905,6 +4610,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
cgroup_init_cftsets(ss);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
cgroup_subsys[ss->subsys_id] = ss;
/*
@@ -4916,21 +4622,15 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
if (IS_ERR(css)) {
/* failure case - need to deassign the cgroup_subsys[] slot. */
cgroup_subsys[ss->subsys_id] = NULL;
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
return PTR_ERR(css);
}
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
ss->root = &cgroup_dummy_root;
/* our new subsystem will be attached to the dummy hierarchy. */
init_css(css, ss, cgroup_dummy_top);
- /* init_idr must be after init_css() because it sets css->id. */
- if (ss->use_id) {
- ret = cgroup_init_idr(ss, css);
- if (ret)
- goto err_unload;
- }
/*
* Now we need to entangle the css into the existing css_sets. unlike
@@ -4956,14 +4656,18 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
write_unlock(&css_set_lock);
ret = online_css(css);
- if (ret)
+ if (ret) {
+ ss->css_free(css);
goto err_unload;
+ }
/* success! */
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
return 0;
err_unload:
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
/* @ss can't be mounted here as try_module_get() would fail */
cgroup_unload_subsys(ss);
@@ -4982,6 +4686,7 @@ EXPORT_SYMBOL_GPL(cgroup_load_subsys);
void cgroup_unload_subsys(struct cgroup_subsys *ss)
{
struct cgrp_cset_link *link;
+ struct cgroup_subsys_state *css;
BUG_ON(ss->module == NULL);
@@ -4993,18 +4698,15 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
BUG_ON(ss->root != &cgroup_dummy_root);
mutex_lock(&cgroup_mutex);
+ mutex_lock(&cgroup_root_mutex);
- offline_css(cgroup_css(cgroup_dummy_top, ss));
-
- if (ss->use_id)
- idr_destroy(&ss->idr);
+ css = cgroup_css(cgroup_dummy_top, ss);
+ if (css)
+ offline_css(css);
/* deassign the subsys_id */
cgroup_subsys[ss->subsys_id] = NULL;
- /* remove subsystem from the dummy root's list of subsystems */
- list_del_init(&ss->sibling);
-
/*
* disentangle the css from all css_sets attached to the dummy
* top. as in loading, we need to pay our respects to the hashtable
@@ -5025,12 +4727,13 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
/*
* remove subsystem's css from the cgroup_dummy_top and free it -
* need to free before marking as null because ss->css_free needs
- * the cgrp->subsys pointer to find their state. note that this
- * also takes care of freeing the css_id.
+ * the cgrp->subsys pointer to find their state.
*/
- ss->css_free(cgroup_css(cgroup_dummy_top, ss));
+ if (css)
+ ss->css_free(css);
RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
+ mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
@@ -5097,8 +4800,6 @@ int __init cgroup_init(void)
for_each_builtin_subsys(ss, i) {
if (!ss->early_init)
cgroup_init_subsys(ss);
- if (ss->use_id)
- cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
}
/* allocate id for the dummy hierarchy */
@@ -5139,6 +4840,31 @@ out:
return err;
}
+static int __init cgroup_wq_init(void)
+{
+ /*
+ * There isn't much point in executing destruction path in
+ * parallel. Good chunk is serialized with cgroup_mutex anyway.
+ * Use 1 for @max_active.
+ *
+ * We would prefer to do this in cgroup_init() above, but that
+ * is called before init_workqueues(): so leave this until after.
+ */
+ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+ BUG_ON(!cgroup_destroy_wq);
+
+ /*
+ * Used to destroy pidlists and separate to serve as flush domain.
+ * Cap @max_active to 1 too.
+ */
+ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
+ 0, 1);
+ BUG_ON(!cgroup_pidlist_destroy_wq);
+
+ return 0;
+}
+core_initcall(cgroup_wq_init);
+
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
@@ -5178,11 +4904,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
for_each_active_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
- int count = 0;
+ int ssid, count = 0;
seq_printf(m, "%d:", root->hierarchy_id);
- for_each_root_subsys(root, ss)
- seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->subsys_mask & (1 << ssid))
+ seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
@@ -5518,196 +5245,21 @@ static int __init cgroup_disable(char *str)
}
__setup("cgroup_disable=", cgroup_disable);
-/*
- * Functons for CSS ID.
- */
-
-/* to get ID other than 0, this should be called when !cgroup_is_dead() */
-unsigned short css_id(struct cgroup_subsys_state *css)
-{
- struct css_id *cssid;
-
- /*
- * This css_id() can return correct value when somone has refcnt
- * on this or this is under rcu_read_lock(). Once css->id is allocated,
- * it's unchanged until freed.
- */
- cssid = rcu_dereference_raw(css->id);
-
- if (cssid)
- return cssid->id;
- return 0;
-}
-EXPORT_SYMBOL_GPL(css_id);
-
-/**
- * css_is_ancestor - test "root" css is an ancestor of "child"
- * @child: the css to be tested.
- * @root: the css supporsed to be an ancestor of the child.
- *
- * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
- * this function reads css->id, the caller must hold rcu_read_lock().
- * But, considering usual usage, the csses should be valid objects after test.
- * Assuming that the caller will do some action to the child if this returns
- * returns true, the caller must take "child";s reference count.
- * If "child" is valid object and this returns true, "root" is valid, too.
- */
-
-bool css_is_ancestor(struct cgroup_subsys_state *child,
- const struct cgroup_subsys_state *root)
-{
- struct css_id *child_id;
- struct css_id *root_id;
-
- child_id = rcu_dereference(child->id);
- if (!child_id)
- return false;
- root_id = rcu_dereference(root->id);
- if (!root_id)
- return false;
- if (child_id->depth < root_id->depth)
- return false;
- if (child_id->stack[root_id->depth] != root_id->id)
- return false;
- return true;
-}
-
-void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
-{
- struct css_id *id = rcu_dereference_protected(css->id, true);
-
- /* When this is called before css_id initialization, id can be NULL */
- if (!id)
- return;
-
- BUG_ON(!ss->use_id);
-
- rcu_assign_pointer(id->css, NULL);
- rcu_assign_pointer(css->id, NULL);
- spin_lock(&ss->id_lock);
- idr_remove(&ss->idr, id->id);
- spin_unlock(&ss->id_lock);
- kfree_rcu(id, rcu_head);
-}
-EXPORT_SYMBOL_GPL(free_css_id);
-
-/*
- * This is called by init or create(). Then, calls to this function are
- * always serialized (By cgroup_mutex() at create()).
- */
-
-static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
-{
- struct css_id *newid;
- int ret, size;
-
- BUG_ON(!ss->use_id);
-
- size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
- newid = kzalloc(size, GFP_KERNEL);
- if (!newid)
- return ERR_PTR(-ENOMEM);
-
- idr_preload(GFP_KERNEL);
- spin_lock(&ss->id_lock);
- /* Don't use 0. allocates an ID of 1-65535 */
- ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT);
- spin_unlock(&ss->id_lock);
- idr_preload_end();
-
- /* Returns error when there are no free spaces for new ID.*/
- if (ret < 0)
- goto err_out;
-
- newid->id = ret;
- newid->depth = depth;
- return newid;
-err_out:
- kfree(newid);
- return ERR_PTR(ret);
-
-}
-
-static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
- struct cgroup_subsys_state *rootcss)
-{
- struct css_id *newid;
-
- spin_lock_init(&ss->id_lock);
- idr_init(&ss->idr);
-
- newid = get_new_cssid(ss, 0);
- if (IS_ERR(newid))
- return PTR_ERR(newid);
-
- newid->stack[0] = newid->id;
- RCU_INIT_POINTER(newid->css, rootcss);
- RCU_INIT_POINTER(rootcss->id, newid);
- return 0;
-}
-
-static int alloc_css_id(struct cgroup_subsys_state *child_css)
-{
- struct cgroup_subsys_state *parent_css = css_parent(child_css);
- struct css_id *child_id, *parent_id;
- int i, depth;
-
- parent_id = rcu_dereference_protected(parent_css->id, true);
- depth = parent_id->depth + 1;
-
- child_id = get_new_cssid(child_css->ss, depth);
- if (IS_ERR(child_id))
- return PTR_ERR(child_id);
-
- for (i = 0; i < depth; i++)
- child_id->stack[i] = parent_id->stack[i];
- child_id->stack[depth] = child_id->id;
- /*
- * child_id->css pointer will be set after this cgroup is available
- * see cgroup_populate_dir()
- */
- rcu_assign_pointer(child_css->id, child_id);
-
- return 0;
-}
-
-/**
- * css_lookup - lookup css by id
- * @ss: cgroup subsys to be looked into.
- * @id: the id
- *
- * Returns pointer to cgroup_subsys_state if there is valid one with id.
- * NULL if not. Should be called under rcu_read_lock()
- */
-struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
-{
- struct css_id *cssid = NULL;
-
- BUG_ON(!ss->use_id);
- cssid = idr_find(&ss->idr, id);
-
- if (unlikely(!cssid))
- return NULL;
-
- return rcu_dereference(cssid->css);
-}
-EXPORT_SYMBOL_GPL(css_lookup);
-
/**
* css_from_dir - get corresponding css from the dentry of a cgroup dir
* @dentry: directory dentry of interest
* @ss: subsystem of interest
*
- * Must be called under RCU read lock. The caller is responsible for
- * pinning the returned css if it needs to be accessed outside the RCU
- * critical section.
+ * Must be called under cgroup_mutex or RCU read lock. The caller is
+ * responsible for pinning the returned css if it needs to be accessed
+ * outside the critical section.
*/
struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss)
{
struct cgroup *cgrp;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutex_or_rcu_locked();
/* is @dentry a cgroup dir? */
if (!dentry->d_inode ||
@@ -5730,9 +5282,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
{
struct cgroup *cgrp;
- rcu_lockdep_assert(rcu_read_lock_held() ||
- lockdep_is_held(&cgroup_mutex),
- "css_from_id() needs proper protection");
+ cgroup_assert_mutex_or_rcu_locked();
cgrp = idr_find(&ss->root->cgroup_idr, id);
if (cgrp)
@@ -5780,9 +5330,7 @@ static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
return count;
}
-static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft,
- struct seq_file *seq)
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
{
struct cgrp_cset_link *link;
struct css_set *cset;
@@ -5807,9 +5355,9 @@ static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
}
#define MAX_TASKS_SHOWN_PER_CSS 25
-static int cgroup_css_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
{
+ struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
read_lock(&css_set_lock);
@@ -5855,12 +5403,12 @@ static struct cftype debug_files[] = {
{
.name = "current_css_set_cg_links",
- .read_seq_string = current_css_set_cg_links_read,
+ .seq_show = current_css_set_cg_links_read,
},
{
.name = "cgroup_css_links",
- .read_seq_string = cgroup_css_links_read,
+ .seq_show = cgroup_css_links_read,
},
{
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index f0ff64d0ebaa..6c3154e477f6 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -301,10 +301,9 @@ out_unlock:
spin_unlock_irq(&freezer->lock);
}
-static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
- struct seq_file *m)
+static int freezer_read(struct seq_file *m, void *v)
{
- struct cgroup_subsys_state *pos;
+ struct cgroup_subsys_state *css = seq_css(m), *pos;
rcu_read_lock();
@@ -458,7 +457,7 @@ static struct cftype files[] = {
{
.name = "state",
.flags = CFTYPE_NOT_ON_ROOT,
- .read_seq_string = freezer_read,
+ .seq_show = freezer_read,
.write_string = freezer_write,
},
{
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 859c8dfd78a1..6cb20d2e7ee0 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -53,10 +53,10 @@ void context_tracking_user_enter(void)
/*
* Repeat the user_enter() check here because some archs may be calling
* this from asm and if no CPU needs context tracking, they shouldn't
- * go further. Repeat the check here until they support the static key
- * check.
+ * go further. Repeat the check here until they support the inline static
+ * key check.
*/
- if (!static_key_false(&context_tracking_enabled))
+ if (!context_tracking_is_enabled())
return;
/*
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
* instead of preempt_schedule() to exit user context if needed before
* calling the scheduler.
*/
-void __sched notrace preempt_schedule_context(void)
+asmlinkage void __sched notrace preempt_schedule_context(void)
{
enum ctx_state prev_ctx;
@@ -160,7 +160,7 @@ void context_tracking_user_exit(void)
{
unsigned long flags;
- if (!static_key_false(&context_tracking_enabled))
+ if (!context_tracking_is_enabled())
return;
if (in_interrupt())
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d7f07a2da5a6..deff2e693766 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -306,8 +306,28 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
__func__, cpu);
goto out_release;
}
+
+ /*
+ * By now we've cleared cpu_active_mask, wait for all preempt-disabled
+ * and RCU users of this state to go away such that all new such users
+ * will observe it.
+ *
+ * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
+ * not imply sync_sched(), so explicitly call both.
+ *
+ * Do sync before park smpboot threads to take care the rcu boost case.
+ */
+#ifdef CONFIG_PREEMPT
+ synchronize_sched();
+#endif
+ synchronize_rcu();
+
smpboot_park_threads(cpu);
+ /*
+ * So now all preempt/rcu users must observe !cpu_active().
+ */
+
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
@@ -420,11 +440,6 @@ int cpu_up(unsigned int cpu)
{
int err = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG
- int nid;
- pg_data_t *pgdat;
-#endif
-
if (!cpu_possible(cpu)) {
printk(KERN_ERR "can't online cpu %d because it is not "
"configured as may-hotadd at boot time\n", cpu);
@@ -435,27 +450,9 @@ int cpu_up(unsigned int cpu)
return -EINVAL;
}
-#ifdef CONFIG_MEMORY_HOTPLUG
- nid = cpu_to_node(cpu);
- if (!node_online(nid)) {
- err = mem_online_node(nid);
- if (err)
- return err;
- }
-
- pgdat = NODE_DATA(nid);
- if (!pgdat) {
- printk(KERN_ERR
- "Can't online cpu %d due to NULL pgdat\n", cpu);
- return -ENOMEM;
- }
-
- if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
- mutex_lock(&zonelists_mutex);
- build_all_zonelists(NULL, NULL);
- mutex_unlock(&zonelists_mutex);
- }
-#endif
+ err = try_online_node(cpu_to_node(cpu));
+ if (err)
+ return err;
cpu_maps_update_begin();
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a0bcb5..277f494c2a9a 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
- while (!need_resched())
+ while (!tif_need_resched())
cpu_relax();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
rcu_idle_exit();
@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
cpu_idle_poll();
} else {
- current_clr_polling();
- if (!need_resched()) {
+ if (!current_clr_polling_and_test()) {
stop_critical_timings();
rcu_idle_enter();
arch_cpu_idle();
@@ -103,10 +102,20 @@ static void cpu_idle_loop(void)
} else {
local_irq_enable();
}
- current_set_polling();
+ __current_set_polling();
}
arch_cpu_idle_exit();
}
+
+ /*
+ * Since we fell out of the loop above, we know
+ * TIF_NEED_RESCHED must be set, propagate it into
+ * PREEMPT_NEED_RESCHED.
+ *
+ * This is required because for polling idle loops we will
+ * not have had an IPI to fold the state for us.
+ */
+ preempt_set_need_resched();
tick_nohz_idle_exit();
schedule_preempt_disabled();
}
@@ -129,7 +138,7 @@ void cpu_startup_entry(enum cpuhp_state state)
*/
boot_init_stack_canary();
#endif
- current_set_polling();
+ __current_set_polling();
arch_cpu_idle_prepare();
cpu_idle_loop();
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6bf981e13c43..4410ac6a55f1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1033,8 +1033,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
need_loop = task_has_mempolicy(tsk) ||
!nodes_intersects(*newmems, tsk->mems_allowed);
- if (need_loop)
+ if (need_loop) {
+ local_irq_disable();
write_seqcount_begin(&tsk->mems_allowed_seq);
+ }
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -1042,8 +1044,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
tsk->mems_allowed = *newmems;
- if (need_loop)
+ if (need_loop) {
write_seqcount_end(&tsk->mems_allowed_seq);
+ local_irq_enable();
+ }
task_unlock(tsk);
}
@@ -1727,66 +1731,41 @@ out_unlock:
* used, list of ranges of sequential numbers, is variable length,
* and since these maps can change value dynamically, one could read
* gibberish by doing partial reads while a list was changing.
- * A single large read to a buffer that crosses a page boundary is
- * ok, because the result being copied to user land is not recomputed
- * across a page fault.
*/
-
-static size_t cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
+static int cpuset_common_seq_show(struct seq_file *sf, void *v)
{
- size_t count;
-
- mutex_lock(&callback_mutex);
- count = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
- mutex_unlock(&callback_mutex);
+ struct cpuset *cs = css_cs(seq_css(sf));
+ cpuset_filetype_t type = seq_cft(sf)->private;
+ ssize_t count;
+ char *buf, *s;
+ int ret = 0;
- return count;
-}
-
-static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs)
-{
- size_t count;
+ count = seq_get_buf(sf, &buf);
+ s = buf;
mutex_lock(&callback_mutex);
- count = nodelist_scnprintf(page, PAGE_SIZE, cs->mems_allowed);
- mutex_unlock(&callback_mutex);
-
- return count;
-}
-
-static ssize_t cpuset_common_file_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes,
- loff_t *ppos)
-{
- struct cpuset *cs = css_cs(css);
- cpuset_filetype_t type = cft->private;
- char *page;
- ssize_t retval = 0;
- char *s;
-
- if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
- return -ENOMEM;
-
- s = page;
switch (type) {
case FILE_CPULIST:
- s += cpuset_sprintf_cpulist(s, cs);
+ s += cpulist_scnprintf(s, count, cs->cpus_allowed);
break;
case FILE_MEMLIST:
- s += cpuset_sprintf_memlist(s, cs);
+ s += nodelist_scnprintf(s, count, cs->mems_allowed);
break;
default:
- retval = -EINVAL;
- goto out;
+ ret = -EINVAL;
+ goto out_unlock;
}
- *s++ = '\n';
- retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
-out:
- free_page((unsigned long)page);
- return retval;
+ if (s < buf + count - 1) {
+ *s++ = '\n';
+ seq_commit(sf, s - buf);
+ } else {
+ seq_commit(sf, -1);
+ }
+out_unlock:
+ mutex_unlock(&callback_mutex);
+ return ret;
}
static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -1843,7 +1822,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
static struct cftype files[] = {
{
.name = "cpus",
- .read = cpuset_common_file_read,
+ .seq_show = cpuset_common_seq_show,
.write_string = cpuset_write_resmask,
.max_write_len = (100U + 6 * NR_CPUS),
.private = FILE_CPULIST,
@@ -1851,7 +1830,7 @@ static struct cftype files[] = {
{
.name = "mems",
- .read = cpuset_common_file_read,
+ .seq_show = cpuset_common_seq_show,
.write_string = cpuset_write_resmask,
.max_write_len = (100U + 6 * MAX_NUMNODES),
.private = FILE_MEMLIST,
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0506d447aed2..7d2f35e5df2f 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -575,8 +575,12 @@ return_normal:
raw_spin_lock(&dbg_slave_lock);
#ifdef CONFIG_SMP
+ /* If send_ready set, slaves are already waiting */
+ if (ks->send_ready)
+ atomic_set(ks->send_ready, 1);
+
/* Signal the other CPUs to enter kgdb_wait() */
- if ((!kgdb_single_step) && kgdb_do_roundup)
+ else if ((!kgdb_single_step) && kgdb_do_roundup)
kgdb_roundup_cpus(flags);
#endif
@@ -678,11 +682,11 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
if (arch_kgdb_ops.enable_nmi)
arch_kgdb_ops.enable_nmi(0);
+ memset(ks, 0, sizeof(struct kgdb_state));
ks->cpu = raw_smp_processor_id();
ks->ex_vector = evector;
ks->signo = signo;
ks->err_code = ecode;
- ks->kgdb_usethreadid = 0;
ks->linux_regs = regs;
if (kgdb_reenter_check(ks))
@@ -732,6 +736,30 @@ int kgdb_nmicallback(int cpu, void *regs)
return 1;
}
+int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
+{
+#ifdef CONFIG_SMP
+ if (!kgdb_io_ready(0) || !send_ready)
+ return 1;
+
+ if (kgdb_info[cpu].enter_kgdb == 0) {
+ struct kgdb_state kgdb_var;
+ struct kgdb_state *ks = &kgdb_var;
+
+ memset(ks, 0, sizeof(struct kgdb_state));
+ ks->cpu = cpu;
+ ks->ex_vector = trapnr;
+ ks->signo = SIGTRAP;
+ ks->err_code = KGDB_KDB_REASON_SYSTEM_NMI;
+ ks->linux_regs = regs;
+ ks->send_ready = send_ready;
+ kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
+ return 0;
+ }
+#endif
+ return 1;
+}
+
static void kgdb_console_write(struct console *co, const char *s,
unsigned count)
{
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 2235967e78b0..572aa4f5677c 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -26,6 +26,7 @@ struct kgdb_state {
unsigned long threadid;
long kgdb_usethreadid;
struct pt_regs *linux_regs;
+ atomic_t *send_ready;
};
/* Exception state values */
@@ -74,11 +75,13 @@ extern int kdb_stub(struct kgdb_state *ks);
extern int kdb_parse(const char *cmdstr);
extern int kdb_common_init_state(struct kgdb_state *ks);
extern int kdb_common_deinit_state(void);
+#define KGDB_KDB_REASON_SYSTEM_NMI KDB_REASON_SYSTEM_NMI
#else /* ! CONFIG_KGDB_KDB */
static inline int kdb_stub(struct kgdb_state *ks)
{
return DBG_PASS_EVENT;
}
+#define KGDB_KDB_REASON_SYSTEM_NMI 0
#endif /* CONFIG_KGDB_KDB */
#endif /* _DEBUG_CORE_H_ */
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 328d18ef31e4..8859ca34dcfe 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -69,7 +69,10 @@ int kdb_stub(struct kgdb_state *ks)
if (atomic_read(&kgdb_setting_breakpoint))
reason = KDB_REASON_KEYBOARD;
- if (in_nmi())
+ if (ks->err_code == KDB_REASON_SYSTEM_NMI && ks->signo == SIGTRAP)
+ reason = KDB_REASON_SYSTEM_NMI;
+
+ else if (in_nmi())
reason = KDB_REASON_NMI;
for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) {
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 00eb8f7fbf41..0b097c8a1e50 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1200,6 +1200,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
instruction_pointer(regs));
kdb_dumpregs(regs);
break;
+ case KDB_REASON_SYSTEM_NMI:
+ kdb_printf("due to System NonMaskable Interrupt\n");
+ break;
case KDB_REASON_NMI:
kdb_printf("due to NonMaskable Interrupt @ "
kdb_machreg_fmt "\n",
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index d473988c1d0b..54996b71e66d 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -108,12 +108,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
struct timespec ts;
cputime_t utime, stime, stimescaled, utimescaled;
- /* Though tsk->delays accessed later, early exit avoids
- * unnecessary returning of other data
- */
- if (!tsk->delays)
- goto done;
-
tmp = (s64)d->cpu_run_real_total;
task_cputime(tsk, &utime, &stime);
cputime_to_timespec(utime + stime, &ts);
@@ -158,7 +152,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->freepages_count += tsk->delays->freepages_count;
spin_unlock_irqrestore(&tsk->delays->lock, flags);
-done:
return 0;
}
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
index ff915efef66d..e556751d15d9 100644
--- a/kernel/elfcore.c
+++ b/kernel/elfcore.c
@@ -1,23 +1,19 @@
#include <linux/elf.h>
#include <linux/fs.h>
#include <linux/mm.h>
-
-#include <asm/elf.h>
-
+#include <linux/binfmts.h>
Elf_Half __weak elf_core_extra_phdrs(void)
{
return 0;
}
-int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
- unsigned long limit)
+int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
return 1;
}
-int __weak elf_core_write_extra_data(struct file *file, size_t *size,
- unsigned long limit)
+int __weak elf_core_write_extra_data(struct coredump_params *cprm)
{
return 1;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 953c14348375..56003c6edfd3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
- PERF_FLAG_PID_CGROUP)
+ PERF_FLAG_PID_CGROUP |\
+ PERF_FLAG_FD_CLOEXEC)
/*
* branch priv levels that need permission checks
@@ -175,8 +176,8 @@ int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
static int max_samples_per_tick __read_mostly = DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS;
-static atomic_t perf_sample_allowed_ns __read_mostly =
- ATOMIC_INIT( DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100);
+static int perf_sample_allowed_ns __read_mostly =
+ DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100;
void update_perf_cpu_limits(void)
{
@@ -184,7 +185,7 @@ void update_perf_cpu_limits(void)
tmp *= sysctl_perf_cpu_time_max_percent;
do_div(tmp, 100);
- atomic_set(&perf_sample_allowed_ns, tmp);
+ ACCESS_ONCE(perf_sample_allowed_ns) = tmp;
}
static int perf_rotate_context(struct perf_cpu_context *cpuctx);
@@ -193,7 +194,7 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
@@ -228,14 +229,15 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
* we detect that events are taking too long.
*/
#define NR_ACCUMULATED_SAMPLES 128
-DEFINE_PER_CPU(u64, running_sample_length);
+static DEFINE_PER_CPU(u64, running_sample_length);
void perf_sample_event_took(u64 sample_len_ns)
{
u64 avg_local_sample_len;
u64 local_samples_len;
+ u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
- if (atomic_read(&perf_sample_allowed_ns) == 0)
+ if (allowed_ns == 0)
return;
/* decay the counter by 1 average sample */
@@ -251,7 +253,7 @@ void perf_sample_event_took(u64 sample_len_ns)
*/
avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
- if (avg_local_sample_len <= atomic_read(&perf_sample_allowed_ns))
+ if (avg_local_sample_len <= allowed_ns)
return;
if (max_samples_per_tick <= 1)
@@ -262,10 +264,9 @@ void perf_sample_event_took(u64 sample_len_ns)
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
printk_ratelimited(KERN_WARNING
- "perf samples too long (%lld > %d), lowering "
+ "perf samples too long (%lld > %lld), lowering "
"kernel.perf_event_max_sample_rate to %d\n",
- avg_local_sample_len,
- atomic_read(&perf_sample_allowed_ns),
+ avg_local_sample_len, allowed_ns,
sysctl_perf_event_sample_rate);
update_perf_cpu_limits();
@@ -899,6 +900,7 @@ static void unclone_ctx(struct perf_event_context *ctx)
put_ctx(ctx->parent_ctx);
ctx->parent_ctx = NULL;
}
+ ctx->generation++;
}
static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
@@ -1136,6 +1138,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
ctx->nr_events++;
if (event->attr.inherit_stat)
ctx->nr_stat++;
+
+ ctx->generation++;
}
/*
@@ -1201,6 +1205,9 @@ static void perf_event__header_size(struct perf_event *event)
if (sample_type & PERF_SAMPLE_DATA_SRC)
size += sizeof(data->data_src.val);
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ size += sizeof(data->txn);
+
event->header_size = size;
}
@@ -1310,6 +1317,8 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
*/
if (event->state > PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_OFF;
+
+ ctx->generation++;
}
static void perf_group_detach(struct perf_event *event)
@@ -1388,6 +1397,8 @@ event_sched_out(struct perf_event *event,
if (event->state != PERF_EVENT_STATE_ACTIVE)
return;
+ perf_pmu_disable(event->pmu);
+
event->state = PERF_EVENT_STATE_INACTIVE;
if (event->pending_disable) {
event->pending_disable = 0;
@@ -1404,6 +1415,8 @@ event_sched_out(struct perf_event *event,
ctx->nr_freq--;
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
+
+ perf_pmu_enable(event->pmu);
}
static void
@@ -1644,6 +1657,7 @@ event_sched_in(struct perf_event *event,
struct perf_event_context *ctx)
{
u64 tstamp = perf_event_time(event);
+ int ret = 0;
if (event->state <= PERF_EVENT_STATE_OFF)
return 0;
@@ -1666,10 +1680,13 @@ event_sched_in(struct perf_event *event,
*/
smp_wmb();
+ perf_pmu_disable(event->pmu);
+
if (event->pmu->add(event, PERF_EF_START)) {
event->state = PERF_EVENT_STATE_INACTIVE;
event->oncpu = -1;
- return -EAGAIN;
+ ret = -EAGAIN;
+ goto out;
}
event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1685,7 +1702,10 @@ event_sched_in(struct perf_event *event,
if (event->attr.exclusive)
cpuctx->exclusive = 1;
- return 0;
+out:
+ perf_pmu_enable(event->pmu);
+
+ return ret;
}
static int
@@ -2146,22 +2166,38 @@ static void ctx_sched_out(struct perf_event_context *ctx,
}
/*
- * Test whether two contexts are equivalent, i.e. whether they
- * have both been cloned from the same version of the same context
- * and they both have the same number of enabled events.
- * If the number of enabled events is the same, then the set
- * of enabled events should be the same, because these are both
- * inherited contexts, therefore we can't access individual events
- * in them directly with an fd; we can only enable/disable all
- * events via prctl, or enable/disable all events in a family
- * via ioctl, which will have the same effect on both contexts.
+ * Test whether two contexts are equivalent, i.e. whether they have both been
+ * cloned from the same version of the same context.
+ *
+ * Equivalence is measured using a generation number in the context that is
+ * incremented on each modification to it; see unclone_ctx(), list_add_event()
+ * and list_del_event().
*/
static int context_equiv(struct perf_event_context *ctx1,
struct perf_event_context *ctx2)
{
- return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
- && ctx1->parent_gen == ctx2->parent_gen
- && !ctx1->pin_count && !ctx2->pin_count;
+ /* Pinning disables the swap optimization */
+ if (ctx1->pin_count || ctx2->pin_count)
+ return 0;
+
+ /* If ctx1 is the parent of ctx2 */
+ if (ctx1 == ctx2->parent_ctx && ctx1->generation == ctx2->parent_gen)
+ return 1;
+
+ /* If ctx2 is the parent of ctx1 */
+ if (ctx1->parent_ctx == ctx2 && ctx1->parent_gen == ctx2->generation)
+ return 1;
+
+ /*
+ * If ctx1 and ctx2 have the same parent; we flatten the parent
+ * hierarchy, see perf_event_init_context().
+ */
+ if (ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx &&
+ ctx1->parent_gen == ctx2->parent_gen)
+ return 1;
+
+ /* Unmatched */
+ return 0;
}
static void __perf_event_sync_stat(struct perf_event *event,
@@ -2210,9 +2246,6 @@ static void __perf_event_sync_stat(struct perf_event *event,
perf_event_update_userpage(next_event);
}
-#define list_next_entry(pos, member) \
- list_entry(pos->member.next, typeof(*pos), member)
-
static void perf_event_sync_stat(struct perf_event_context *ctx,
struct perf_event_context *next_ctx)
{
@@ -2244,7 +2277,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
{
struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
struct perf_event_context *next_ctx;
- struct perf_event_context *parent;
+ struct perf_event_context *parent, *next_parent;
struct perf_cpu_context *cpuctx;
int do_switch = 1;
@@ -2256,10 +2289,18 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
return;
rcu_read_lock();
- parent = rcu_dereference(ctx->parent_ctx);
next_ctx = next->perf_event_ctxp[ctxn];
- if (parent && next_ctx &&
- rcu_dereference(next_ctx->parent_ctx) == parent) {
+ if (!next_ctx)
+ goto unlock;
+
+ parent = rcu_dereference(ctx->parent_ctx);
+ next_parent = rcu_dereference(next_ctx->parent_ctx);
+
+ /* If neither context have a parent context; they cannot be clones. */
+ if (!parent && !next_parent)
+ goto unlock;
+
+ if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
/*
* Looks like the two contexts are clones, so we might be
* able to optimize the context switch. We lock both
@@ -2287,6 +2328,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
raw_spin_unlock(&next_ctx->lock);
raw_spin_unlock(&ctx->lock);
}
+unlock:
rcu_read_unlock();
if (do_switch) {
@@ -2713,6 +2755,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
if (!event_filter_match(event))
continue;
+ perf_pmu_disable(event->pmu);
+
hwc = &event->hw;
if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2722,7 +2766,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
}
if (!event->attr.freq || !event->attr.sample_freq)
- continue;
+ goto next;
/*
* stop the event and update event->count
@@ -2744,6 +2788,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
perf_adjust_period(event, period, delta, false);
event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+ next:
+ perf_pmu_enable(event->pmu);
}
perf_pmu_enable(ctx->pmu);
@@ -3497,7 +3543,7 @@ static void perf_event_for_each(struct perf_event *event,
static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
struct perf_event_context *ctx = event->ctx;
- int ret = 0;
+ int ret = 0, active;
u64 value;
if (!is_sampling_event(event))
@@ -3521,6 +3567,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
event->attr.sample_period = value;
event->hw.sample_period = value;
}
+
+ active = (event->state == PERF_EVENT_STATE_ACTIVE);
+ if (active) {
+ perf_pmu_disable(ctx->pmu);
+ event->pmu->stop(event, PERF_EF_UPDATE);
+ }
+
+ local64_set(&event->hw.period_left, 0);
+
+ if (active) {
+ event->pmu->start(event, PERF_EF_RELOAD);
+ perf_pmu_enable(ctx->pmu);
+ }
+
unlock:
raw_spin_unlock_irq(&ctx->lock);
@@ -4572,6 +4632,9 @@ void perf_output_sample(struct perf_output_handle *handle,
if (sample_type & PERF_SAMPLE_DATA_SRC)
perf_output_put(handle, data->data_src.val);
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ perf_output_put(handle, data->txn);
+
if (!event->attr.watermark) {
int wakeup_events = event->attr.wakeup_events;
@@ -5100,27 +5163,26 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
unsigned int size;
char tmp[16];
char *buf = NULL;
- const char *name;
-
- memset(tmp, 0, sizeof(tmp));
+ char *name;
if (file) {
struct inode *inode;
dev_t dev;
+
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!buf) {
+ name = "//enomem";
+ goto cpy_name;
+ }
/*
- * d_path works from the end of the rb backwards, so we
+ * d_path() works from the end of the rb backwards, so we
* need to add enough zero bytes after the string to handle
* the 64bit alignment we do later.
*/
- buf = kzalloc(PATH_MAX + sizeof(u64), GFP_KERNEL);
- if (!buf) {
- name = strncpy(tmp, "//enomem", sizeof(tmp));
- goto got_name;
- }
- name = d_path(&file->f_path, buf, PATH_MAX);
+ name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
if (IS_ERR(name)) {
- name = strncpy(tmp, "//toolong", sizeof(tmp));
- goto got_name;
+ name = "//toolong";
+ goto cpy_name;
}
inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
@@ -5128,34 +5190,39 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
gen = inode->i_generation;
maj = MAJOR(dev);
min = MINOR(dev);
-
+ goto got_name;
} else {
- if (arch_vma_name(mmap_event->vma)) {
- name = strncpy(tmp, arch_vma_name(mmap_event->vma),
- sizeof(tmp) - 1);
- tmp[sizeof(tmp) - 1] = '\0';
- goto got_name;
- }
+ name = (char *)arch_vma_name(vma);
+ if (name)
+ goto cpy_name;
- if (!vma->vm_mm) {
- name = strncpy(tmp, "[vdso]", sizeof(tmp));
- goto got_name;
- } else if (vma->vm_start <= vma->vm_mm->start_brk &&
+ if (vma->vm_start <= vma->vm_mm->start_brk &&
vma->vm_end >= vma->vm_mm->brk) {
- name = strncpy(tmp, "[heap]", sizeof(tmp));
- goto got_name;
- } else if (vma->vm_start <= vma->vm_mm->start_stack &&
+ name = "[heap]";
+ goto cpy_name;
+ }
+ if (vma->vm_start <= vma->vm_mm->start_stack &&
vma->vm_end >= vma->vm_mm->start_stack) {
- name = strncpy(tmp, "[stack]", sizeof(tmp));
- goto got_name;
+ name = "[stack]";
+ goto cpy_name;
}
- name = strncpy(tmp, "//anon", sizeof(tmp));
- goto got_name;
+ name = "//anon";
+ goto cpy_name;
}
+cpy_name:
+ strlcpy(tmp, name, sizeof(tmp));
+ name = tmp;
got_name:
- size = ALIGN(strlen(name)+1, sizeof(u64));
+ /*
+ * Since our buffer works in 8 byte units we need to align our string
+ * size to a multiple of 8. However, we must guarantee the tail end is
+ * zero'd out to avoid leaking random bits to userspace.
+ */
+ size = strlen(name)+1;
+ while (!IS_ALIGNED(size, sizeof(u64)))
+ name[size++] = '\0';
mmap_event->file_name = name;
mmap_event->file_size = size;
@@ -5643,11 +5710,6 @@ static void swevent_hlist_put(struct perf_event *event)
{
int cpu;
- if (event->cpu != -1) {
- swevent_hlist_put_cpu(event, event->cpu);
- return;
- }
-
for_each_possible_cpu(cpu)
swevent_hlist_put_cpu(event, cpu);
}
@@ -5681,9 +5743,6 @@ static int swevent_hlist_get(struct perf_event *event)
int err;
int cpu, failed_cpu;
- if (event->cpu != -1)
- return swevent_hlist_get_cpu(event, event->cpu);
-
get_online_cpus();
for_each_possible_cpu(cpu) {
err = swevent_hlist_get_cpu(event, cpu);
@@ -6292,6 +6351,7 @@ type_show(struct device *dev, struct device_attribute *attr, char *page)
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
}
+static DEVICE_ATTR_RO(type);
static ssize_t
perf_event_mux_interval_ms_show(struct device *dev,
@@ -6336,17 +6396,19 @@ perf_event_mux_interval_ms_store(struct device *dev,
return count;
}
+static DEVICE_ATTR_RW(perf_event_mux_interval_ms);
-static struct device_attribute pmu_dev_attrs[] = {
- __ATTR_RO(type),
- __ATTR_RW(perf_event_mux_interval_ms),
- __ATTR_NULL,
+static struct attribute *pmu_dev_attrs[] = {
+ &dev_attr_type.attr,
+ &dev_attr_perf_event_mux_interval_ms.attr,
+ NULL,
};
+ATTRIBUTE_GROUPS(pmu_dev);
static int pmu_bus_running;
static struct bus_type pmu_bus = {
.name = "event_source",
- .dev_attrs = pmu_dev_attrs,
+ .dev_groups = pmu_dev_groups,
};
static void pmu_dev_release(struct device *dev)
@@ -6623,6 +6685,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
+ INIT_LIST_HEAD(&event->active_entry);
+ INIT_HLIST_NODE(&event->hlist_entry);
+
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
@@ -6933,6 +6998,7 @@ SYSCALL_DEFINE5(perf_event_open,
int event_fd;
int move_group = 0;
int err;
+ int f_flags = O_RDWR;
/* for future expandability... */
if (flags & ~PERF_FLAG_ALL)
@@ -6961,7 +7027,10 @@ SYSCALL_DEFINE5(perf_event_open,
if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
return -EINVAL;
- event_fd = get_unused_fd();
+ if (flags & PERF_FLAG_FD_CLOEXEC)
+ f_flags |= O_CLOEXEC;
+
+ event_fd = get_unused_fd_flags(f_flags);
if (event_fd < 0)
return event_fd;
@@ -7083,7 +7152,8 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
}
- event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+ event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+ f_flags);
if (IS_ERR(event_file)) {
err = PTR_ERR(event_file);
goto err_context;
@@ -7126,7 +7196,6 @@ SYSCALL_DEFINE5(perf_event_open,
}
perf_install_in_context(ctx, event, event->cpu);
- ++ctx->generation;
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
@@ -7209,7 +7278,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
perf_install_in_context(ctx, event, cpu);
- ++ctx->generation;
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index ca6599723be5..569b218782ad 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -82,16 +82,16 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
}
#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \
-static inline unsigned int \
+static inline unsigned long \
func_name(struct perf_output_handle *handle, \
- const void *buf, unsigned int len) \
+ const void *buf, unsigned long len) \
{ \
unsigned long size, written; \
\
do { \
- size = min_t(unsigned long, handle->size, len); \
- \
+ size = min(handle->size, len); \
written = memcpy_func(handle->addr, buf, size); \
+ written = size - written; \
\
len -= written; \
handle->addr += written; \
@@ -110,20 +110,37 @@ func_name(struct perf_output_handle *handle, \
return len; \
}
-static inline int memcpy_common(void *dst, const void *src, size_t n)
+static inline unsigned long
+memcpy_common(void *dst, const void *src, unsigned long n)
{
memcpy(dst, src, n);
- return n;
+ return 0;
}
DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
-#define MEMCPY_SKIP(dst, src, n) (n)
+static inline unsigned long
+memcpy_skip(void *dst, const void *src, unsigned long n)
+{
+ return 0;
+}
-DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+DEFINE_OUTPUT_COPY(__output_skip, memcpy_skip)
#ifndef arch_perf_out_copy_user
-#define arch_perf_out_copy_user __copy_from_user_inatomic
+#define arch_perf_out_copy_user arch_perf_out_copy_user
+
+static inline unsigned long
+arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
+{
+ unsigned long ret;
+
+ pagefault_disable();
+ ret = __copy_from_user_inatomic(dst, src, n);
+ pagefault_enable();
+
+ return ret;
+}
#endif
DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 9c2ddfbf4525..146a5792b1d2 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -12,40 +12,10 @@
#include <linux/perf_event.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
+#include <linux/circ_buf.h>
#include "internal.h"
-static bool perf_output_space(struct ring_buffer *rb, unsigned long tail,
- unsigned long offset, unsigned long head)
-{
- unsigned long sz = perf_data_size(rb);
- unsigned long mask = sz - 1;
-
- /*
- * check if user-writable
- * overwrite : over-write its own tail
- * !overwrite: buffer possibly drops events.
- */
- if (rb->overwrite)
- return true;
-
- /*
- * verify that payload is not bigger than buffer
- * otherwise masking logic may fail to detect
- * the "not enough space" condition
- */
- if ((head - offset) > sz)
- return false;
-
- offset = (offset - tail) & mask;
- head = (head - tail) & mask;
-
- if ((int)(head - offset) < 0)
- return false;
-
- return true;
-}
-
static void perf_output_wakeup(struct perf_output_handle *handle)
{
atomic_set(&handle->rb->poll, POLL_IN);
@@ -91,19 +61,20 @@ again:
*
* kernel user
*
- * READ ->data_tail READ ->data_head
- * smp_mb() (A) smp_rmb() (C)
- * WRITE $data READ $data
- * smp_wmb() (B) smp_mb() (D)
- * STORE ->data_head WRITE ->data_tail
+ * if (LOAD ->data_tail) { LOAD ->data_head
+ * (A) smp_rmb() (C)
+ * STORE $data LOAD $data
+ * smp_wmb() (B) smp_mb() (D)
+ * STORE ->data_head STORE ->data_tail
+ * }
*
* Where A pairs with D, and B pairs with C.
*
- * I don't think A needs to be a full barrier because we won't in fact
- * write data until we see the store from userspace. So we simply don't
- * issue the data WRITE until we observe it. Be conservative for now.
+ * In our case (A) is a control dependency that separates the load of
+ * the ->data_tail and the stores of $data. In case ->data_tail
+ * indicates there is no room in the buffer to store $data we do not.
*
- * OTOH, D needs to be a full barrier since it separates the data READ
+ * D needs to be a full barrier since it separates the data READ
* from the tail WRITE.
*
* For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -111,12 +82,12 @@ again:
*
* See perf_output_begin().
*/
- smp_wmb();
+ smp_wmb(); /* B, matches C */
rb->user_page->data_head = head;
/*
- * Now check if we missed an update, rely on the (compiler)
- * barrier in atomic_dec_and_test() to re-read rb->head.
+ * Now check if we missed an update -- rely on previous implied
+ * compiler barriers to force a re-read.
*/
if (unlikely(head != local_read(&rb->head))) {
local_inc(&rb->nest);
@@ -135,8 +106,7 @@ int perf_output_begin(struct perf_output_handle *handle,
{
struct ring_buffer *rb;
unsigned long tail, offset, head;
- int have_lost;
- struct perf_sample_data sample_data;
+ int have_lost, page_shift;
struct {
struct perf_event_header header;
u64 id;
@@ -151,57 +121,72 @@ int perf_output_begin(struct perf_output_handle *handle,
event = event->parent;
rb = rcu_dereference(event->rb);
- if (!rb)
+ if (unlikely(!rb))
goto out;
- handle->rb = rb;
- handle->event = event;
-
- if (!rb->nr_pages)
+ if (unlikely(!rb->nr_pages))
goto out;
+ handle->rb = rb;
+ handle->event = event;
+
have_lost = local_read(&rb->lost);
- if (have_lost) {
- lost_event.header.size = sizeof(lost_event);
- perf_event_header__init_id(&lost_event.header, &sample_data,
- event);
- size += lost_event.header.size;
+ if (unlikely(have_lost)) {
+ size += sizeof(lost_event);
+ if (event->attr.sample_id_all)
+ size += event->id_header_size;
}
perf_output_get_handle(handle);
do {
+ tail = ACCESS_ONCE(rb->user_page->data_tail);
+ offset = head = local_read(&rb->head);
+ if (!rb->overwrite &&
+ unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
+ goto fail;
+
/*
- * Userspace could choose to issue a mb() before updating the
- * tail pointer. So that all reads will be completed before the
- * write is issued.
+ * The above forms a control dependency barrier separating the
+ * @tail load above from the data stores below. Since the @tail
+ * load is required to compute the branch to fail below.
+ *
+ * A, matches D; the full memory barrier userspace SHOULD issue
+ * after reading the data and before storing the new tail
+ * position.
*
* See perf_output_put_handle().
*/
- tail = ACCESS_ONCE(rb->user_page->data_tail);
- smp_mb();
- offset = head = local_read(&rb->head);
+
head += size;
- if (unlikely(!perf_output_space(rb, tail, offset, head)))
- goto fail;
} while (local_cmpxchg(&rb->head, offset, head) != offset);
- if (head - local_read(&rb->wakeup) > rb->watermark)
+ /*
+ * We rely on the implied barrier() by local_cmpxchg() to ensure
+ * none of the data stores below can be lifted up by the compiler.
+ */
+
+ if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
local_add(rb->watermark, &rb->wakeup);
- handle->page = offset >> (PAGE_SHIFT + page_order(rb));
- handle->page &= rb->nr_pages - 1;
- handle->size = offset & ((PAGE_SIZE << page_order(rb)) - 1);
- handle->addr = rb->data_pages[handle->page];
- handle->addr += handle->size;
- handle->size = (PAGE_SIZE << page_order(rb)) - handle->size;
+ page_shift = PAGE_SHIFT + page_order(rb);
- if (have_lost) {
+ handle->page = (offset >> page_shift) & (rb->nr_pages - 1);
+ offset &= (1UL << page_shift) - 1;
+ handle->addr = rb->data_pages[handle->page] + offset;
+ handle->size = (1UL << page_shift) - offset;
+
+ if (unlikely(have_lost)) {
+ struct perf_sample_data sample_data;
+
+ lost_event.header.size = sizeof(lost_event);
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
lost_event.id = event->id;
lost_event.lost = local_xchg(&rb->lost, 0);
+ perf_event_header__init_id(&lost_event.header,
+ &sample_data, event);
perf_output_put(handle, lost_event);
perf_event__output_id_sample(event, handle, &sample_data);
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ad8e1bdca70e..307d87c0991a 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -35,6 +35,7 @@
#include <linux/kdebug.h> /* notifier mechanism */
#include "../../mm/internal.h" /* munlock_vma_page */
#include <linux/percpu-rwsem.h>
+#include <linux/task_work.h>
#include <linux/uprobes.h>
@@ -72,6 +73,17 @@ struct uprobe {
struct inode *inode; /* Also hold a ref to inode */
loff_t offset;
unsigned long flags;
+
+ /*
+ * The generic code assumes that it has two members of unknown type
+ * owned by the arch-specific code:
+ *
+ * insn - copy_insn() saves the original instruction here for
+ * arch_uprobe_analyze_insn().
+ *
+ * ixol - potentially modified instruction to execute out of
+ * line, copied to xol_area by xol_get_insn_slot().
+ */
struct arch_uprobe arch;
};
@@ -85,6 +97,29 @@ struct return_instance {
};
/*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
+ * On a breakpoint hit, thread contests for a slot. It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+ wait_queue_head_t wq; /* if all slots are busy */
+ atomic_t slot_count; /* number of in-use slots */
+ unsigned long *bitmap; /* 0 = free slot */
+ struct page *page;
+
+ /*
+ * We keep the vma's vm_start rather than a pointer to the vma
+ * itself. The probed process or a naughty kernel module could make
+ * the vma go away, and we must handle that reasonably gracefully.
+ */
+ unsigned long vaddr; /* Page(s) of instruction slots */
+};
+
+/*
* valid_vma: Verify if the specified vma is an executable vma
* Relax restrictions while unregistering: vm_flags might have
* changed after breakpoint was inserted.
@@ -244,12 +279,12 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
* the architecture. If an arch has variable length instruction and the
* breakpoint instruction is not of the smallest length instruction
* supported by that architecture then we need to modify is_trap_at_addr and
- * write_opcode accordingly. This would never be a problem for archs that
- * have fixed length instructions.
+ * uprobe_write_opcode accordingly. This would never be a problem for archs
+ * that have fixed length instructions.
*/
/*
- * write_opcode - write the opcode at a given virtual address.
+ * uprobe_write_opcode - write the opcode at a given virtual address.
* @mm: the probed process address space.
* @vaddr: the virtual address to store the opcode.
* @opcode: opcode to be written at @vaddr.
@@ -260,7 +295,7 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
* For mm @mm, write the opcode at @vaddr.
* Return 0 (success) or a negative errno.
*/
-static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
+int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
uprobe_opcode_t opcode)
{
struct page *old_page, *new_page;
@@ -314,7 +349,7 @@ put_old:
*/
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- return write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
+ return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
}
/**
@@ -329,7 +364,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- return write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+ return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
}
static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -503,9 +538,8 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
return ret;
}
-static int
-__copy_insn(struct address_space *mapping, struct file *filp, char *insn,
- unsigned long nbytes, loff_t offset)
+static int __copy_insn(struct address_space *mapping, struct file *filp,
+ void *insn, int nbytes, loff_t offset)
{
struct page *page;
@@ -527,28 +561,28 @@ __copy_insn(struct address_space *mapping, struct file *filp, char *insn,
static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
- struct address_space *mapping;
- unsigned long nbytes;
- int bytes;
+ struct address_space *mapping = uprobe->inode->i_mapping;
+ loff_t offs = uprobe->offset;
+ void *insn = &uprobe->arch.insn;
+ int size = sizeof(uprobe->arch.insn);
+ int len, err = -EIO;
- nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK);
- mapping = uprobe->inode->i_mapping;
-
- /* Instruction at end of binary; copy only available bytes */
- if (uprobe->offset + MAX_UINSN_BYTES > uprobe->inode->i_size)
- bytes = uprobe->inode->i_size - uprobe->offset;
- else
- bytes = MAX_UINSN_BYTES;
+ /* Copy only available bytes, -EIO if nothing was read */
+ do {
+ if (offs >= i_size_read(uprobe->inode))
+ break;
- /* Instruction at the page-boundary; copy bytes in second page */
- if (nbytes < bytes) {
- int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes,
- bytes - nbytes, uprobe->offset + nbytes);
+ len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK));
+ err = __copy_insn(mapping, filp, insn, len, offs);
if (err)
- return err;
- bytes = nbytes;
- }
- return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
+ break;
+
+ insn += len;
+ offs += len;
+ size -= len;
+ } while (size);
+
+ return err;
}
static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
@@ -569,14 +603,14 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
goto out;
ret = -ENOTSUPP;
- if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+ if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
goto out;
ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
if (ret)
goto out;
- /* write_opcode() assumes we don't cross page boundary */
+ /* uprobe_write_opcode() assumes we don't cross page boundary */
BUG_ON((uprobe->offset & ~PAGE_MASK) +
UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
@@ -1096,21 +1130,22 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
}
/* Slot allocation for XOL */
-static int xol_add_vma(struct xol_area *area)
+static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
{
- struct mm_struct *mm = current->mm;
int ret = -EALREADY;
down_write(&mm->mmap_sem);
if (mm->uprobes_state.xol_area)
goto fail;
- ret = -ENOMEM;
- /* Try to map as high as possible, this is only a hint. */
- area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
- if (area->vaddr & ~PAGE_MASK) {
- ret = area->vaddr;
- goto fail;
+ if (!area->vaddr) {
+ /* Try to map as high as possible, this is only a hint. */
+ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE,
+ PAGE_SIZE, 0, 0);
+ if (area->vaddr & ~PAGE_MASK) {
+ ret = area->vaddr;
+ goto fail;
+ }
}
ret = install_special_mapping(mm, area->vaddr, PAGE_SIZE,
@@ -1120,30 +1155,19 @@ static int xol_add_vma(struct xol_area *area)
smp_wmb(); /* pairs with get_xol_area() */
mm->uprobes_state.xol_area = area;
- ret = 0;
fail:
up_write(&mm->mmap_sem);
return ret;
}
-/*
- * get_xol_area - Allocate process's xol_area if necessary.
- * This area will be used for storing instructions for execution out of line.
- *
- * Returns the allocated area or NULL.
- */
-static struct xol_area *get_xol_area(void)
+static struct xol_area *__create_xol_area(unsigned long vaddr)
{
struct mm_struct *mm = current->mm;
- struct xol_area *area;
uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+ struct xol_area *area;
- area = mm->uprobes_state.xol_area;
- if (area)
- goto ret;
-
- area = kzalloc(sizeof(*area), GFP_KERNEL);
+ area = kmalloc(sizeof(*area), GFP_KERNEL);
if (unlikely(!area))
goto out;
@@ -1155,13 +1179,14 @@ static struct xol_area *get_xol_area(void)
if (!area->page)
goto free_bitmap;
- /* allocate first slot of task's xol_area for the return probes */
+ area->vaddr = vaddr;
+ init_waitqueue_head(&area->wq);
+ /* Reserve the 1st slot for get_trampoline_vaddr() */
set_bit(0, area->bitmap);
- copy_to_page(area->page, 0, &insn, UPROBE_SWBP_INSN_SIZE);
atomic_set(&area->slot_count, 1);
- init_waitqueue_head(&area->wq);
+ copy_to_page(area->page, 0, &insn, UPROBE_SWBP_INSN_SIZE);
- if (!xol_add_vma(area))
+ if (!xol_add_vma(mm, area))
return area;
__free_page(area->page);
@@ -1170,9 +1195,25 @@ static struct xol_area *get_xol_area(void)
free_area:
kfree(area);
out:
+ return NULL;
+}
+
+/*
+ * get_xol_area - Allocate process's xol_area if necessary.
+ * This area will be used for storing instructions for execution out of line.
+ *
+ * Returns the allocated area or NULL.
+ */
+static struct xol_area *get_xol_area(void)
+{
+ struct mm_struct *mm = current->mm;
+ struct xol_area *area;
+
+ if (!mm->uprobes_state.xol_area)
+ __create_xol_area(0);
+
area = mm->uprobes_state.xol_area;
- ret:
- smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */
+ smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */
return area;
}
@@ -1256,7 +1297,8 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
return 0;
/* Initialize the slot */
- copy_to_page(area->page, xol_vaddr, uprobe->arch.insn, MAX_UINSN_BYTES);
+ copy_to_page(area->page, xol_vaddr,
+ &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
/*
* We probably need flush_icache_user_range() but it needs vma.
* This should work on supported architectures too.
@@ -1345,14 +1387,6 @@ void uprobe_free_utask(struct task_struct *t)
}
/*
- * Called in context of a new clone/fork from copy_process.
- */
-void uprobe_copy_process(struct task_struct *t)
-{
- t->utask = NULL;
-}
-
-/*
* Allocate a uprobe_task object for the task if if necessary.
* Called when the thread hits a breakpoint.
*
@@ -1367,6 +1401,82 @@ static struct uprobe_task *get_utask(void)
return current->utask;
}
+static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask)
+{
+ struct uprobe_task *n_utask;
+ struct return_instance **p, *o, *n;
+
+ n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
+ if (!n_utask)
+ return -ENOMEM;
+ t->utask = n_utask;
+
+ p = &n_utask->return_instances;
+ for (o = o_utask->return_instances; o; o = o->next) {
+ n = kmalloc(sizeof(struct return_instance), GFP_KERNEL);
+ if (!n)
+ return -ENOMEM;
+
+ *n = *o;
+ atomic_inc(&n->uprobe->ref);
+ n->next = NULL;
+
+ *p = n;
+ p = &n->next;
+ n_utask->depth++;
+ }
+
+ return 0;
+}
+
+static void uprobe_warn(struct task_struct *t, const char *msg)
+{
+ pr_warn("uprobe: %s:%d failed to %s\n",
+ current->comm, current->pid, msg);
+}
+
+static void dup_xol_work(struct callback_head *work)
+{
+ if (current->flags & PF_EXITING)
+ return;
+
+ if (!__create_xol_area(current->utask->dup_xol_addr))
+ uprobe_warn(current, "dup xol area");
+}
+
+/*
+ * Called in context of a new clone/fork from copy_process.
+ */
+void uprobe_copy_process(struct task_struct *t, unsigned long flags)
+{
+ struct uprobe_task *utask = current->utask;
+ struct mm_struct *mm = current->mm;
+ struct xol_area *area;
+
+ t->utask = NULL;
+
+ if (!utask || !utask->return_instances)
+ return;
+
+ if (mm == t->mm && !(flags & CLONE_VFORK))
+ return;
+
+ if (dup_utask(t, utask))
+ return uprobe_warn(t, "dup ret instances");
+
+ /* The task can fork() after dup_xol_work() fails */
+ area = mm->uprobes_state.xol_area;
+ if (!area)
+ return uprobe_warn(t, "dup xol area");
+
+ if (mm == t->mm)
+ return;
+
+ t->utask->dup_xol_addr = area->vaddr;
+ init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+ task_work_add(t, &t->utask->dup_xol_work, true);
+}
+
/*
* Current area->vaddr notion assume the trampoline address is always
* equal area->vaddr.
@@ -1744,6 +1854,10 @@ static void handle_swbp(struct pt_regs *regs)
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /* Tracing handlers use ->utask to communicate with fetch methods */
+ if (!get_utask())
+ goto out;
+
handler_chain(uprobe, regs);
if (can_skip_sstep(uprobe, regs))
goto out;
@@ -1857,9 +1971,4 @@ static int __init init_uprobes(void)
return register_die_notifier(&uprobe_exception_nb);
}
-module_init(init_uprobes);
-
-static void __exit exit_uprobes(void)
-{
-}
-module_exit(exit_uprobes);
+__initcall(init_uprobes);
diff --git a/kernel/exit.c b/kernel/exit.c
index a949819055d5..1e77fc645317 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
__this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_group);
+ list_del_rcu(&p->thread_node);
}
/*
diff --git a/kernel/extable.c b/kernel/extable.c
index 832cb28105bb..763faf037ec1 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -61,7 +61,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
static inline int init_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_sinittext &&
- addr <= (unsigned long)_einittext)
+ addr < (unsigned long)_einittext)
return 1;
return 0;
}
@@ -69,7 +69,7 @@ static inline int init_kernel_text(unsigned long addr)
int core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
- addr <= (unsigned long)_etext)
+ addr < (unsigned long)_etext)
return 1;
if (system_state == SYSTEM_BOOTING &&
diff --git a/kernel/fork.c b/kernel/fork.c
index 086fe73ad6bd..2f11bbe376b0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -532,11 +532,12 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
mm->flags = (current->mm) ?
(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
- mm->nr_ptes = 0;
+ atomic_long_set(&mm->nr_ptes, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm_init_aio(mm);
mm_init_owner(mm, p);
+ clear_tlb_flush_pending(mm);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
@@ -560,7 +561,7 @@ static void check_mm(struct mm_struct *mm)
"mm:%p idx:%d val:%ld\n", mm, i, x);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
VM_BUG_ON(mm->pmd_huge_pte);
#endif
}
@@ -814,12 +815,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
-#ifdef CONFIG_NUMA_BALANCING
- mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
@@ -1037,6 +1035,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
@@ -1089,8 +1092,10 @@ static void rt_mutex_init_task(struct task_struct *p)
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&p->pi_waiters);
+ p->pi_waiters = RB_ROOT;
+ p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
@@ -1174,7 +1179,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
* do not allow it to share a thread group or signal handlers or
* parent with the forking task.
*/
- if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+ if (clone_flags & CLONE_SIGHAND) {
if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
(task_active_pid_ns(current) !=
current->nsproxy->pid_ns_for_children))
@@ -1313,7 +1318,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(p);
+ retval = sched_fork(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
@@ -1373,7 +1380,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
- uprobe_copy_process(p);
/*
* sigaltstack should be cleared when sharing the same VM
*/
@@ -1406,13 +1412,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->tgid = p->pid;
}
- p->pdeath_signal = 0;
- p->exit_state = 0;
-
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
+ p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
@@ -1475,6 +1479,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
atomic_inc(&current->signal->sigcnt);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
+ list_add_tail_rcu(&p->thread_node,
+ &p->signal->thread_head);
}
attach_pid(p, PIDTYPE_PID);
nr_threads++;
@@ -1490,6 +1496,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
+ uprobe_copy_process(p, clone_flags);
return p;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa197517..aa6a8aadb911 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt);
bool pm_freezing;
bool pm_nosig_freezing;
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
/* protects freezing and frozen transitions */
static DEFINE_SPINLOCK(freezer_lock);
diff --git a/kernel/futex.c b/kernel/futex.c
index c3a1a55a5214..44a1261cb9ff 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,101 @@
#include <linux/sched/rt.h>
#include <linux/hugetlb.h>
#include <linux/freezer.h>
+#include <linux/bootmem.h>
#include <asm/futex.h>
-#include "rtmutex_common.h"
+#include "locking/rtmutex_common.h"
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ * uval = *futex;
+ * *futex = newval;
+ * sys_futex(WAKE, futex);
+ * futex_wake(futex);
+ * if (queue_empty())
+ * return;
+ * if (uval == val)
+ * lock(hash_bucket(futex));
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ *
+ * waiters++;
+ * mb(); (A) <-- paired with -.
+ * |
+ * lock(hash_bucket(futex)); |
+ * |
+ * uval = *futex; |
+ * | *futex = newval;
+ * | sys_futex(WAKE, futex);
+ * | futex_wake(futex);
+ * |
+ * `-------> mb(); (B)
+ * if (uval == val)
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule(); if (waiters)
+ * lock(hash_bucket(futex));
+ * wake_waiters(futex);
+ * unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ * X = Y = 0
+ *
+ * w[X]=1 w[Y]=1
+ * MB MB
+ * r[Y]=y r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+int __read_mostly futex_cmpxchg_enabled;
/*
* Futex flags used to encode options to functions and preserve them across
@@ -149,9 +236,41 @@ static const struct futex_q futex_q_init = {
struct futex_hash_bucket {
spinlock_t lock;
struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
+
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+ atomic_inc(&key->private.mm->mm_count);
+ /*
+ * Ensure futex_get_mm() implies a full barrier such that
+ * get_futex_key() implies a full barrier. This is relied upon
+ * as full barrier (B), see the ordering comment above.
+ */
+ smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ /*
+ * Tasks trying to enter the critical region are most likely
+ * potential waiters that will be added to the plist. Ensure
+ * that wakers won't miss to-be-slept tasks in the window between
+ * the wait call and the actual plist_add.
+ */
+ if (spin_is_locked(&hb->lock))
+ return true;
+ smp_rmb(); /* Make sure we check the lock state first */
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+ return !plist_head_empty(&hb->chain);
+#else
+ return true;
+#endif
+}
/*
* We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +280,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
u32 hash = jhash2((u32*)&key->both.word,
(sizeof(key->both.word)+sizeof(key->both.ptr))/4,
key->both.offset);
- return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+ return &futex_queues[hash & (futex_hashsize - 1)];
}
/*
@@ -187,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- ihold(key->shared.inode);
+ ihold(key->shared.inode); /* implies MB (B) */
break;
case FUT_OFF_MMSHARED:
- atomic_inc(&key->private.mm->mm_count);
+ futex_get_mm(key); /* implies MB (B) */
break;
}
}
@@ -251,6 +370,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
return -EINVAL;
address -= key->both.offset;
+ if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
+ return -EFAULT;
+
/*
* PROCESS_PRIVATE futexes are fast.
* As the mm cannot disappear under us and the 'key' only needs
@@ -259,11 +381,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
* but access_ok() should be faster than find_vma()
*/
if (!fshared) {
- if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
- return -EFAULT;
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
return 0;
}
@@ -288,7 +408,7 @@ again:
put_page(page);
/* serialize against __split_huge_page_splitting() */
local_irq_disable();
- if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+ if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
page_head = compound_head(page);
/*
* page_head is valid pointer but we must pin
@@ -370,7 +490,7 @@ again:
key->shared.pgoff = basepage_index(page);
}
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
out:
unlock_page(page_head);
@@ -597,13 +717,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
{
struct futex_pi_state *pi_state = NULL;
struct futex_q *this, *next;
- struct plist_head *head;
struct task_struct *p;
pid_t pid = uval & FUTEX_TID_MASK;
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex(&this->key, key)) {
/*
* Another waiter already exists - bump up
@@ -985,7 +1102,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
int ret;
@@ -997,10 +1113,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
goto out;
hb = hash_futex(&key);
+
+ /* Make sure we really have tasks to wakeup */
+ if (!hb_waiters_pending(hb))
+ goto out_put_key;
+
spin_lock(&hb->lock);
- head = &hb->chain;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex (&this->key, &key)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1018,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
}
spin_unlock(&hb->lock);
+out_put_key:
put_futex_key(&key);
out:
return ret;
@@ -1033,7 +1154,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head;
struct futex_q *this, *next;
int ret, op_ret;
@@ -1081,9 +1201,7 @@ retry_private:
goto retry;
}
- head = &hb1->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (match_futex (&this->key, &key1)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1096,10 +1214,8 @@ retry_private:
}
if (op_ret > 0) {
- head = &hb2->chain;
-
op_ret = 0;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb2->chain, list) {
if (match_futex (&this->key, &key2)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1269,7 +1385,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
int drop_count = 0, task_count = 0, ret;
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head1;
struct futex_q *this, *next;
u32 curval2;
@@ -1392,8 +1507,7 @@ retry_private:
}
}
- head1 = &hb1->chain;
- plist_for_each_entry_safe(this, next, head1, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (task_count - nr_wake >= nr_requeue)
break;
@@ -1488,12 +1602,12 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
hb = hash_futex(&q->key);
q->lock_ptr = &hb->lock;
- spin_lock(&hb->lock);
+ spin_lock(&hb->lock); /* implies MB (A) */
return hb;
}
static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
__releases(&hb->lock)
{
spin_unlock(&hb->lock);
@@ -1866,7 +1980,7 @@ retry_private:
ret = get_futex_value_locked(&uval, uaddr);
if (ret) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = get_user(uval, uaddr);
if (ret)
@@ -1880,7 +1994,7 @@ retry_private:
}
if (uval != val) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = -EWOULDBLOCK;
}
@@ -2028,7 +2142,7 @@ retry_private:
* Task is exiting and we just wait for the
* exit to complete.
*/
- queue_unlock(&q, hb);
+ queue_unlock(hb);
put_futex_key(&q.key);
cond_resched();
goto retry;
@@ -2080,7 +2194,7 @@ retry_private:
goto out_put_key;
out_unlock_put_key:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
out_put_key:
put_futex_key(&q.key);
@@ -2090,7 +2204,7 @@ out:
return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
ret = fault_in_user_writeable(uaddr);
if (ret)
@@ -2112,7 +2226,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
u32 uval, vpid = task_pid_vnr(current);
int ret;
@@ -2152,9 +2265,7 @@ retry:
* Ok, other tasks may need to be woken up - check waiters
* and do the wakeup if necessary:
*/
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (!match_futex (&this->key, &key))
continue;
ret = wake_futex_pi(uaddr, uval, this);
@@ -2315,6 +2426,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
* code while we sleep on uaddr.
*/
debug_rt_mutex_init_waiter(&rt_waiter);
+ RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&rt_waiter.tree_entry);
rt_waiter.task = NULL;
ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
@@ -2733,8 +2846,21 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
static int __init futex_init(void)
{
u32 curval;
- int i;
+ unsigned int futex_shift;
+ unsigned long i;
+
+#if CONFIG_BASE_SMALL
+ futex_hashsize = 16;
+#else
+ futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
+ futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+ futex_hashsize, 0,
+ futex_hashsize < 256 ? HASH_SMALL : 0,
+ &futex_shift, NULL,
+ futex_hashsize, futex_hashsize);
+ futex_hashsize = 1UL << futex_shift;
/*
* This will fail and we want it. Some arch implementations do
* runtime detection of the futex_atomic_cmpxchg_inatomic()
@@ -2748,7 +2874,7 @@ static int __init futex_init(void)
if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
- for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+ for (i = 0; i < futex_hashsize; i++) {
plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index d4da55d1fb65..d04ce8ac4399 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -46,4 +46,34 @@ config GCOV_PROFILE_ALL
larger and run slower. Also be sure to exclude files from profiling
which are not linked to the kernel image to prevent linker errors.
+choice
+ prompt "Specify GCOV format"
+ depends on GCOV_KERNEL
+ default GCOV_FORMAT_AUTODETECT
+ ---help---
+ The gcov format is usually determined by the GCC version, but there are
+ exceptions where format changes are integrated in lower-version GCCs.
+ In such a case use this option to adjust the format used in the kernel
+ accordingly.
+
+ If unsure, choose "Autodetect".
+
+config GCOV_FORMAT_AUTODETECT
+ bool "Autodetect"
+ ---help---
+ Select this option to use the format that corresponds to your GCC
+ version.
+
+config GCOV_FORMAT_3_4
+ bool "GCC 3.4 format"
+ ---help---
+ Select this option to use the format defined by GCC 3.4.
+
+config GCOV_FORMAT_4_7
+ bool "GCC 4.7 format"
+ ---help---
+ Select this option to use the format defined by GCC 4.7.
+
+endchoice
+
endmenu
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index e97ca59e2520..52aa7e8de927 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -1,3 +1,33 @@
ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
-obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o
+# if-lt
+# Usage VAR := $(call if-lt, $(a), $(b))
+# Returns 1 if (a < b)
+if-lt = $(shell [ $(1) -lt $(2) ] && echo 1)
+
+ifeq ($(CONFIG_GCOV_FORMAT_3_4),y)
+ cc-ver := 0304
+else ifeq ($(CONFIG_GCOV_FORMAT_4_7),y)
+ cc-ver := 0407
+else
+# Use cc-version if available, otherwise set 0
+#
+# scripts/Kbuild.include, which contains cc-version function, is not included
+# during make clean "make -f scripts/Makefile.clean obj=kernel/gcov"
+# Meaning cc-ver is empty causing if-lt test to fail with
+# "/bin/sh: line 0: [: -lt: unary operator expected" error mesage.
+# This has no affect on the clean phase, but the error message could be
+# confusing/annoying. So this dummy workaround sets cc-ver to zero if cc-version
+# is not available. We can probably move if-lt to Kbuild.include, so it's also
+# not defined during clean or to include Kbuild.include in
+# scripts/Makefile.clean. But the following workaround seems least invasive.
+ cc-ver := $(if $(call cc-version),$(call cc-version),0)
+endif
+
+obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o
+
+ifeq ($(call if-lt, $(cc-ver), 0407),1)
+ obj-$(CONFIG_GCOV_KERNEL) += gcc_3_4.o
+else
+ obj-$(CONFIG_GCOV_KERNEL) += gcc_4_7.o
+endif
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 9b22d03cc581..f45b75b713c0 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -20,7 +20,6 @@
#include <linux/mutex.h>
#include "gcov.h"
-static struct gcov_info *gcov_info_head;
static int gcov_events_enabled;
static DEFINE_MUTEX(gcov_lock);
@@ -34,7 +33,7 @@ void __gcov_init(struct gcov_info *info)
mutex_lock(&gcov_lock);
if (gcov_version == 0) {
- gcov_version = info->version;
+ gcov_version = gcov_info_version(info);
/*
* Printing gcc's version magic may prove useful for debugging
* incompatibility reports.
@@ -45,8 +44,7 @@ void __gcov_init(struct gcov_info *info)
* Add new profiling data structure to list and inform event
* listener.
*/
- info->next = gcov_info_head;
- gcov_info_head = info;
+ gcov_info_link(info);
if (gcov_events_enabled)
gcov_event(GCOV_ADD, info);
mutex_unlock(&gcov_lock);
@@ -81,6 +79,12 @@ void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters)
}
EXPORT_SYMBOL(__gcov_merge_delta);
+void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_ior);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
@@ -91,13 +95,15 @@ EXPORT_SYMBOL(__gcov_merge_delta);
*/
void gcov_enable_events(void)
{
- struct gcov_info *info;
+ struct gcov_info *info = NULL;
mutex_lock(&gcov_lock);
gcov_events_enabled = 1;
+
/* Perform event callback for previously registered entries. */
- for (info = gcov_info_head; info; info = info->next)
+ while ((info = gcov_info_next(info)))
gcov_event(GCOV_ADD, info);
+
mutex_unlock(&gcov_lock);
}
@@ -112,25 +118,23 @@ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event,
void *data)
{
struct module *mod = data;
- struct gcov_info *info;
- struct gcov_info *prev;
+ struct gcov_info *info = NULL;
+ struct gcov_info *prev = NULL;
if (event != MODULE_STATE_GOING)
return NOTIFY_OK;
mutex_lock(&gcov_lock);
- prev = NULL;
+
/* Remove entries located in module from linked list. */
- for (info = gcov_info_head; info; info = info->next) {
+ while ((info = gcov_info_next(info))) {
if (within(info, mod->module_core, mod->core_size)) {
- if (prev)
- prev->next = info->next;
- else
- gcov_info_head = info->next;
+ gcov_info_unlink(prev, info);
if (gcov_events_enabled)
gcov_event(GCOV_REMOVE, info);
} else
prev = info;
}
+
mutex_unlock(&gcov_lock);
return NOTIFY_OK;
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 7a7d2ee96d42..15ff01a76379 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -75,7 +75,7 @@ static int __init gcov_persist_setup(char *str)
unsigned long val;
if (kstrtoul(str, 0, &val)) {
- pr_warning("invalid gcov_persist parameter '%s'\n", str);
+ pr_warn("invalid gcov_persist parameter '%s'\n", str);
return 0;
}
gcov_persist = val;
@@ -242,7 +242,7 @@ static struct gcov_node *get_node_by_name(const char *name)
list_for_each_entry(node, &all_head, all) {
info = get_node_info(node);
- if (info && (strcmp(info->filename, name) == 0))
+ if (info && (strcmp(gcov_info_filename(info), name) == 0))
return node;
}
@@ -279,7 +279,7 @@ static ssize_t gcov_seq_write(struct file *file, const char __user *addr,
seq = file->private_data;
info = gcov_iter_get_info(seq->private);
mutex_lock(&node_lock);
- node = get_node_by_name(info->filename);
+ node = get_node_by_name(gcov_info_filename(info));
if (node) {
/* Reset counts or remove node for unloaded modules. */
if (node->num_loaded == 0)
@@ -365,7 +365,7 @@ static const char *deskew(const char *basename)
*/
static void add_links(struct gcov_node *node, struct dentry *parent)
{
- char *basename;
+ const char *basename;
char *target;
int num;
int i;
@@ -376,14 +376,14 @@ static void add_links(struct gcov_node *node, struct dentry *parent)
if (!node->links)
return;
for (i = 0; i < num; i++) {
- target = get_link_target(get_node_info(node)->filename,
- &gcov_link[i]);
+ target = get_link_target(
+ gcov_info_filename(get_node_info(node)),
+ &gcov_link[i]);
if (!target)
goto out_err;
- basename = strrchr(target, '/');
- if (!basename)
+ basename = kbasename(target);
+ if (basename == target)
goto out_err;
- basename++;
node->links[i] = debugfs_create_symlink(deskew(basename),
parent, target);
if (!node->links[i])
@@ -450,7 +450,7 @@ static struct gcov_node *new_node(struct gcov_node *parent,
} else
node->dentry = debugfs_create_dir(node->name, parent->dentry);
if (!node->dentry) {
- pr_warning("could not create file\n");
+ pr_warn("could not create file\n");
kfree(node);
return NULL;
}
@@ -463,7 +463,7 @@ static struct gcov_node *new_node(struct gcov_node *parent,
err_nomem:
kfree(node);
- pr_warning("out of memory\n");
+ pr_warn("out of memory\n");
return NULL;
}
@@ -576,7 +576,7 @@ static void add_node(struct gcov_info *info)
struct gcov_node *parent;
struct gcov_node *node;
- filename = kstrdup(info->filename, GFP_KERNEL);
+ filename = kstrdup(gcov_info_filename(info), GFP_KERNEL);
if (!filename)
return;
parent = &root_node;
@@ -630,8 +630,8 @@ static void add_info(struct gcov_node *node, struct gcov_info *info)
*/
loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL);
if (!loaded_info) {
- pr_warning("could not add '%s' (out of memory)\n",
- info->filename);
+ pr_warn("could not add '%s' (out of memory)\n",
+ gcov_info_filename(info));
return;
}
memcpy(loaded_info, node->loaded_info,
@@ -644,8 +644,9 @@ static void add_info(struct gcov_node *node, struct gcov_info *info)
* data set replaces the copy of the last one.
*/
if (!gcov_info_is_compatible(node->unloaded_info, info)) {
- pr_warning("discarding saved data for %s "
- "(incompatible version)\n", info->filename);
+ pr_warn("discarding saved data for %s "
+ "(incompatible version)\n",
+ gcov_info_filename(info));
gcov_info_free(node->unloaded_info);
node->unloaded_info = NULL;
}
@@ -655,8 +656,8 @@ static void add_info(struct gcov_node *node, struct gcov_info *info)
* The initial one takes precedence.
*/
if (!gcov_info_is_compatible(node->loaded_info[0], info)) {
- pr_warning("could not add '%s' (incompatible "
- "version)\n", info->filename);
+ pr_warn("could not add '%s' (incompatible "
+ "version)\n", gcov_info_filename(info));
kfree(loaded_info);
return;
}
@@ -691,8 +692,9 @@ static void save_info(struct gcov_node *node, struct gcov_info *info)
else {
node->unloaded_info = gcov_info_dup(info);
if (!node->unloaded_info) {
- pr_warning("could not save data for '%s' "
- "(out of memory)\n", info->filename);
+ pr_warn("could not save data for '%s' "
+ "(out of memory)\n",
+ gcov_info_filename(info));
}
}
}
@@ -707,8 +709,8 @@ static void remove_info(struct gcov_node *node, struct gcov_info *info)
i = get_info_index(node, info);
if (i < 0) {
- pr_warning("could not remove '%s' (not found)\n",
- info->filename);
+ pr_warn("could not remove '%s' (not found)\n",
+ gcov_info_filename(info));
return;
}
if (gcov_persist)
@@ -735,7 +737,7 @@ void gcov_event(enum gcov_action action, struct gcov_info *info)
struct gcov_node *node;
mutex_lock(&node_lock);
- node = get_node_by_name(info->filename);
+ node = get_node_by_name(gcov_info_filename(info));
switch (action) {
case GCOV_ADD:
if (node)
@@ -747,8 +749,8 @@ void gcov_event(enum gcov_action action, struct gcov_info *info)
if (node)
remove_info(node, info);
else {
- pr_warning("could not remove '%s' (not found)\n",
- info->filename);
+ pr_warn("could not remove '%s' (not found)\n",
+ gcov_info_filename(info));
}
break;
}
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
index ae5bb4260033..27bc88a35013 100644
--- a/kernel/gcov/gcc_3_4.c
+++ b/kernel/gcov/gcc_3_4.c
@@ -21,6 +21,121 @@
#include <linux/vmalloc.h>
#include "gcov.h"
+#define GCOV_COUNTERS 5
+
+static struct gcov_info *gcov_info_head;
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @ident: object file-unique function identifier
+ * @checksum: function checksum
+ * @n_ctrs: number of values per counter type belonging to this function
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ */
+struct gcov_fn_info {
+ unsigned int ident;
+ unsigned int checksum;
+ unsigned int n_ctrs[0];
+};
+
+/**
+ * struct gcov_ctr_info - profiling data per counter type
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ * @merge: merge function for counter values of this type (unused)
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+ unsigned int num;
+ gcov_type *values;
+ void (*merge)(gcov_type *, unsigned int);
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: time stamp
+ * @filename: name of the associated gcov data file
+ * @n_functions: number of instrumented functions
+ * @functions: function data
+ * @ctr_mask: mask specifying which counter types are active
+ * @counts: counter data per counter type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+ unsigned int version;
+ struct gcov_info *next;
+ unsigned int stamp;
+ const char *filename;
+ unsigned int n_functions;
+ const struct gcov_fn_info *functions;
+ unsigned int ctr_mask;
+ struct gcov_ctr_info counts[0];
+};
+
+/**
+ * gcov_info_filename - return info filename
+ * @info: profiling data set
+ */
+const char *gcov_info_filename(struct gcov_info *info)
+{
+ return info->filename;
+}
+
+/**
+ * gcov_info_version - return info version
+ * @info: profiling data set
+ */
+unsigned int gcov_info_version(struct gcov_info *info)
+{
+ return info->version;
+}
+
+/**
+ * gcov_info_next - return next profiling data set
+ * @info: profiling data set
+ *
+ * Returns next gcov_info following @info or first gcov_info in the chain if
+ * @info is %NULL.
+ */
+struct gcov_info *gcov_info_next(struct gcov_info *info)
+{
+ if (!info)
+ return gcov_info_head;
+
+ return info->next;
+}
+
+/**
+ * gcov_info_link - link/add profiling data set to the list
+ * @info: profiling data set
+ */
+void gcov_info_link(struct gcov_info *info)
+{
+ info->next = gcov_info_head;
+ gcov_info_head = info;
+}
+
+/**
+ * gcov_info_unlink - unlink/remove profiling data set from the list
+ * @prev: previous profiling data set
+ * @info: profiling data set
+ */
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info)
+{
+ if (prev)
+ prev->next = info->next;
+ else
+ gcov_info_head = info->next;
+}
+
/* Symbolic links to be created for each profiling data file. */
const struct gcov_link gcov_link[] = {
{ OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
new file mode 100644
index 000000000000..2c6e4631c814
--- /dev/null
+++ b/kernel/gcov/gcc_4_7.c
@@ -0,0 +1,560 @@
+/*
+ * This code provides functions to handle gcc's profiling data format
+ * introduced with gcc 4.7.
+ *
+ * This file is based heavily on gcc_3_4.c file.
+ *
+ * For a better understanding, refer to gcc source:
+ * gcc/gcov-io.h
+ * libgcc/libgcov.c
+ *
+ * Uses gcc-internal data definitions.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include "gcov.h"
+
+#define GCOV_COUNTERS 8
+#define GCOV_TAG_FUNCTION_LENGTH 3
+
+static struct gcov_info *gcov_info_head;
+
+/**
+ * struct gcov_ctr_info - information about counters for a single function
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+ unsigned int num;
+ gcov_type *values;
+};
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @key: comdat key
+ * @ident: unique ident of function
+ * @lineno_checksum: function lineo_checksum
+ * @cfg_checksum: function cfg checksum
+ * @ctrs: instrumented counters
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ *
+ * Information about a single function. This uses the trailing array
+ * idiom. The number of counters is determined from the merge pointer
+ * array in gcov_info. The key is used to detect which of a set of
+ * comdat functions was selected -- it points to the gcov_info object
+ * of the object file containing the selected comdat function.
+ */
+struct gcov_fn_info {
+ const struct gcov_info *key;
+ unsigned int ident;
+ unsigned int lineno_checksum;
+ unsigned int cfg_checksum;
+ struct gcov_ctr_info ctrs[0];
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: uniquifying time stamp
+ * @filename: name of the associated gcov data file
+ * @merge: merge functions (null for unused counter type)
+ * @n_functions: number of instrumented functions
+ * @functions: pointer to pointers to function information
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+ unsigned int version;
+ struct gcov_info *next;
+ unsigned int stamp;
+ const char *filename;
+ void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int);
+ unsigned int n_functions;
+ struct gcov_fn_info **functions;
+};
+
+/**
+ * gcov_info_filename - return info filename
+ * @info: profiling data set
+ */
+const char *gcov_info_filename(struct gcov_info *info)
+{
+ return info->filename;
+}
+
+/**
+ * gcov_info_version - return info version
+ * @info: profiling data set
+ */
+unsigned int gcov_info_version(struct gcov_info *info)
+{
+ return info->version;
+}
+
+/**
+ * gcov_info_next - return next profiling data set
+ * @info: profiling data set
+ *
+ * Returns next gcov_info following @info or first gcov_info in the chain if
+ * @info is %NULL.
+ */
+struct gcov_info *gcov_info_next(struct gcov_info *info)
+{
+ if (!info)
+ return gcov_info_head;
+
+ return info->next;
+}
+
+/**
+ * gcov_info_link - link/add profiling data set to the list
+ * @info: profiling data set
+ */
+void gcov_info_link(struct gcov_info *info)
+{
+ info->next = gcov_info_head;
+ gcov_info_head = info;
+}
+
+/**
+ * gcov_info_unlink - unlink/remove profiling data set from the list
+ * @prev: previous profiling data set
+ * @info: profiling data set
+ */
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info)
+{
+ if (prev)
+ prev->next = info->next;
+ else
+ gcov_info_head = info->next;
+}
+
+/* Symbolic links to be created for each profiling data file. */
+const struct gcov_link gcov_link[] = {
+ { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */
+ { 0, NULL},
+};
+
+/*
+ * Determine whether a counter is active. Doesn't change at run-time.
+ */
+static int counter_active(struct gcov_info *info, unsigned int type)
+{
+ return info->merge[type] ? 1 : 0;
+}
+
+/* Determine number of active counters. Based on gcc magic. */
+static unsigned int num_counter_active(struct gcov_info *info)
+{
+ unsigned int i;
+ unsigned int result = 0;
+
+ for (i = 0; i < GCOV_COUNTERS; i++) {
+ if (counter_active(info, i))
+ result++;
+ }
+ return result;
+}
+
+/**
+ * gcov_info_reset - reset profiling data to zero
+ * @info: profiling data set
+ */
+void gcov_info_reset(struct gcov_info *info)
+{
+ struct gcov_ctr_info *ci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ ci_ptr = info->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(info, ct_idx))
+ continue;
+
+ memset(ci_ptr->values, 0,
+ sizeof(gcov_type) * ci_ptr->num);
+ ci_ptr++;
+ }
+ }
+}
+
+/**
+ * gcov_info_is_compatible - check if profiling data can be added
+ * @info1: first profiling data set
+ * @info2: second profiling data set
+ *
+ * Returns non-zero if profiling data can be added, zero otherwise.
+ */
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
+{
+ return (info1->stamp == info2->stamp);
+}
+
+/**
+ * gcov_info_add - add up profiling data
+ * @dest: profiling data set to which data is added
+ * @source: profiling data set which is added
+ *
+ * Adds profiling counts of @source to @dest.
+ */
+void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
+{
+ struct gcov_ctr_info *dci_ptr;
+ struct gcov_ctr_info *sci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ unsigned int val_idx;
+
+ for (fi_idx = 0; fi_idx < src->n_functions; fi_idx++) {
+ dci_ptr = dst->functions[fi_idx]->ctrs;
+ sci_ptr = src->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(src, ct_idx))
+ continue;
+
+ for (val_idx = 0; val_idx < sci_ptr->num; val_idx++)
+ dci_ptr->values[val_idx] +=
+ sci_ptr->values[val_idx];
+
+ dci_ptr++;
+ sci_ptr++;
+ }
+ }
+}
+
+/**
+ * gcov_info_dup - duplicate profiling data set
+ * @info: profiling data set to duplicate
+ *
+ * Return newly allocated duplicate on success, %NULL on error.
+ */
+struct gcov_info *gcov_info_dup(struct gcov_info *info)
+{
+ struct gcov_info *dup;
+ struct gcov_ctr_info *dci_ptr; /* dst counter info */
+ struct gcov_ctr_info *sci_ptr; /* src counter info */
+ unsigned int active;
+ unsigned int fi_idx; /* function info idx */
+ unsigned int ct_idx; /* counter type idx */
+ size_t fi_size; /* function info size */
+ size_t cv_size; /* counter values size */
+
+ dup = kmemdup(info, sizeof(*dup), GFP_KERNEL);
+ if (!dup)
+ return NULL;
+
+ dup->next = NULL;
+ dup->filename = NULL;
+ dup->functions = NULL;
+
+ dup->filename = kstrdup(info->filename, GFP_KERNEL);
+ if (!dup->filename)
+ goto err_free;
+
+ dup->functions = kcalloc(info->n_functions,
+ sizeof(struct gcov_fn_info *), GFP_KERNEL);
+ if (!dup->functions)
+ goto err_free;
+
+ active = num_counter_active(info);
+ fi_size = sizeof(struct gcov_fn_info);
+ fi_size += sizeof(struct gcov_ctr_info) * active;
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ dup->functions[fi_idx] = kzalloc(fi_size, GFP_KERNEL);
+ if (!dup->functions[fi_idx])
+ goto err_free;
+
+ *(dup->functions[fi_idx]) = *(info->functions[fi_idx]);
+
+ sci_ptr = info->functions[fi_idx]->ctrs;
+ dci_ptr = dup->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < active; ct_idx++) {
+
+ cv_size = sizeof(gcov_type) * sci_ptr->num;
+
+ dci_ptr->values = vmalloc(cv_size);
+
+ if (!dci_ptr->values)
+ goto err_free;
+
+ dci_ptr->num = sci_ptr->num;
+ memcpy(dci_ptr->values, sci_ptr->values, cv_size);
+
+ sci_ptr++;
+ dci_ptr++;
+ }
+ }
+
+ return dup;
+err_free:
+ gcov_info_free(dup);
+ return NULL;
+}
+
+/**
+ * gcov_info_free - release memory for profiling data set duplicate
+ * @info: profiling data set duplicate to free
+ */
+void gcov_info_free(struct gcov_info *info)
+{
+ unsigned int active;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ struct gcov_ctr_info *ci_ptr;
+
+ if (!info->functions)
+ goto free_info;
+
+ active = num_counter_active(info);
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ if (!info->functions[fi_idx])
+ continue;
+
+ ci_ptr = info->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++)
+ vfree(ci_ptr->values);
+
+ kfree(info->functions[fi_idx]);
+ }
+
+free_info:
+ kfree(info->functions);
+ kfree(info->filename);
+ kfree(info);
+}
+
+#define ITER_STRIDE PAGE_SIZE
+
+/**
+ * struct gcov_iterator - specifies current file position in logical records
+ * @info: associated profiling data
+ * @buffer: buffer containing file data
+ * @size: size of buffer
+ * @pos: current position in file
+ */
+struct gcov_iterator {
+ struct gcov_info *info;
+ void *buffer;
+ size_t size;
+ loff_t pos;
+};
+
+/**
+ * store_gcov_u32 - store 32 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't
+ * store anything.
+ */
+static size_t store_gcov_u32(void *buffer, size_t off, u32 v)
+{
+ u32 *data;
+
+ if (buffer) {
+ data = buffer + off;
+ *data = v;
+ }
+
+ return sizeof(*data);
+}
+
+/**
+ * store_gcov_u64 - store 64 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. 64 bit numbers are stored as two 32 bit numbers, the low part
+ * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store
+ * anything.
+ */
+static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
+{
+ u32 *data;
+
+ if (buffer) {
+ data = buffer + off;
+
+ data[0] = (v & 0xffffffffUL);
+ data[1] = (v >> 32);
+ }
+
+ return sizeof(*data) * 2;
+}
+
+/**
+ * convert_to_gcda - convert profiling data set to gcda file format
+ * @buffer: the buffer to store file data or %NULL if no data should be stored
+ * @info: profiling data set to be converted
+ *
+ * Returns the number of bytes that were/would have been stored into the buffer.
+ */
+static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
+{
+ struct gcov_fn_info *fi_ptr;
+ struct gcov_ctr_info *ci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ unsigned int cv_idx;
+ size_t pos = 0;
+
+ /* File header. */
+ pos += store_gcov_u32(buffer, pos, GCOV_DATA_MAGIC);
+ pos += store_gcov_u32(buffer, pos, info->version);
+ pos += store_gcov_u32(buffer, pos, info->stamp);
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ fi_ptr = info->functions[fi_idx];
+
+ /* Function record. */
+ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
+ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+
+ ci_ptr = fi_ptr->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(info, ct_idx))
+ continue;
+
+ /* Counter record. */
+ pos += store_gcov_u32(buffer, pos,
+ GCOV_TAG_FOR_COUNTER(ct_idx));
+ pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2);
+
+ for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) {
+ pos += store_gcov_u64(buffer, pos,
+ ci_ptr->values[cv_idx]);
+ }
+
+ ci_ptr++;
+ }
+ }
+
+ return pos;
+}
+
+/**
+ * gcov_iter_new - allocate and initialize profiling data iterator
+ * @info: profiling data set to be iterated
+ *
+ * Return file iterator on success, %NULL otherwise.
+ */
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
+{
+ struct gcov_iterator *iter;
+
+ iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL);
+ if (!iter)
+ goto err_free;
+
+ iter->info = info;
+ /* Dry-run to get the actual buffer size. */
+ iter->size = convert_to_gcda(NULL, info);
+ iter->buffer = vmalloc(iter->size);
+ if (!iter->buffer)
+ goto err_free;
+
+ convert_to_gcda(iter->buffer, info);
+
+ return iter;
+
+err_free:
+ kfree(iter);
+ return NULL;
+}
+
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+void gcov_iter_free(struct gcov_iterator *iter)
+{
+ vfree(iter->buffer);
+ kfree(iter);
+}
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
+{
+ return iter->info;
+}
+
+/**
+ * gcov_iter_start - reset file iterator to starting position
+ * @iter: file iterator
+ */
+void gcov_iter_start(struct gcov_iterator *iter)
+{
+ iter->pos = 0;
+}
+
+/**
+ * gcov_iter_next - advance file iterator to next logical record
+ * @iter: file iterator
+ *
+ * Return zero if new position is valid, non-zero if iterator has reached end.
+ */
+int gcov_iter_next(struct gcov_iterator *iter)
+{
+ if (iter->pos < iter->size)
+ iter->pos += ITER_STRIDE;
+
+ if (iter->pos >= iter->size)
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * gcov_iter_write - write data for current pos to seq_file
+ * @iter: file iterator
+ * @seq: seq_file handle
+ *
+ * Return zero on success, non-zero otherwise.
+ */
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
+{
+ size_t len;
+
+ if (iter->pos >= iter->size)
+ return -EINVAL;
+
+ len = ITER_STRIDE;
+ if (iter->pos + len > iter->size)
+ len = iter->size - iter->pos;
+
+ seq_write(seq, iter->buffer + iter->pos, len);
+
+ return 0;
+}
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
index 060073ebf7a6..92c8e22a29ed 100644
--- a/kernel/gcov/gcov.h
+++ b/kernel/gcov/gcov.h
@@ -21,7 +21,6 @@
* gcc and need to be kept as close to the original definition as possible to
* remain compatible.
*/
-#define GCOV_COUNTERS 5
#define GCOV_DATA_MAGIC ((unsigned int) 0x67636461)
#define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000)
#define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000)
@@ -34,60 +33,18 @@ typedef long gcov_type;
typedef long long gcov_type;
#endif
-/**
- * struct gcov_fn_info - profiling meta data per function
- * @ident: object file-unique function identifier
- * @checksum: function checksum
- * @n_ctrs: number of values per counter type belonging to this function
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time.
- */
-struct gcov_fn_info {
- unsigned int ident;
- unsigned int checksum;
- unsigned int n_ctrs[0];
-};
-
-/**
- * struct gcov_ctr_info - profiling data per counter type
- * @num: number of counter values for this type
- * @values: array of counter values for this type
- * @merge: merge function for counter values of this type (unused)
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the values array.
- */
-struct gcov_ctr_info {
- unsigned int num;
- gcov_type *values;
- void (*merge)(gcov_type *, unsigned int);
-};
+/* Opaque gcov_info. The gcov structures can change as for example in gcc 4.7 so
+ * we cannot use full definition here and they need to be placed in gcc specific
+ * implementation of gcov. This also means no direct access to the members in
+ * generic code and usage of the interface below.*/
+struct gcov_info;
-/**
- * struct gcov_info - profiling data per object file
- * @version: gcov version magic indicating the gcc version used for compilation
- * @next: list head for a singly-linked list
- * @stamp: time stamp
- * @filename: name of the associated gcov data file
- * @n_functions: number of instrumented functions
- * @functions: function data
- * @ctr_mask: mask specifying which counter types are active
- * @counts: counter data per counter type
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the next pointer.
- */
-struct gcov_info {
- unsigned int version;
- struct gcov_info *next;
- unsigned int stamp;
- const char *filename;
- unsigned int n_functions;
- const struct gcov_fn_info *functions;
- unsigned int ctr_mask;
- struct gcov_ctr_info counts[0];
-};
+/* Interface to access gcov_info data */
+const char *gcov_info_filename(struct gcov_info *info);
+unsigned int gcov_info_version(struct gcov_info *info);
+struct gcov_info *gcov_info_next(struct gcov_info *info);
+void gcov_info_link(struct gcov_info *info);
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info);
/* Base interface. */
enum gcov_action {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319bae3f7..09094361dce5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include <linux/freezer.h>
@@ -1610,7 +1611,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
unsigned long slack;
slack = current->timer_slack_ns;
- if (rt_task(current))
+ if (dl_task(current) || rt_task(current))
slack = 0;
hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 3e97fb126e6b..9328b80eaf14 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -16,11 +16,12 @@
#include <linux/export.h>
#include <linux/sysctl.h>
#include <linux/utsname.h>
+#include <trace/events/sched.h>
/*
* The number of tasks checked:
*/
-unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
/*
* Limit number of tasks checked in a batch.
@@ -92,6 +93,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
t->last_switch_count = switch_count;
return;
}
+
+ trace_sched_process_hang(t);
+
if (!sysctl_hung_task_warnings)
return;
sysctl_hung_task_warnings--;
@@ -203,6 +207,14 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
return ret;
}
+static atomic_t reset_hung_task = ATOMIC_INIT(0);
+
+void reset_hung_task_detector(void)
+{
+ atomic_set(&reset_hung_task, 1);
+}
+EXPORT_SYMBOL_GPL(reset_hung_task_detector);
+
/*
* kthread which checks for tasks stuck in D state
*/
@@ -216,6 +228,9 @@ static int watchdog(void *dummy)
while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
timeout = sysctl_hung_task_timeout_secs;
+ if (atomic_xchg(&reset_hung_task, 0))
+ continue;
+
check_hung_uninterruptible_tasks(timeout);
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a3bb14fbe5c6..dc04c166c54d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -214,7 +214,7 @@ void irq_enable(struct irq_desc *desc)
}
/**
- * irq_disable - Mark interupt disabled
+ * irq_disable - Mark interrupt disabled
* @desc: irq descriptor which should be disabled
*
* If the chip does not implement the irq_disable callback, we
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 706724e9835d..cf68bb36fe58 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -465,27 +465,26 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base,
}
EXPORT_SYMBOL_GPL(irq_create_strict_mappings);
-unsigned int irq_create_of_mapping(struct device_node *controller,
- const u32 *intspec, unsigned int intsize)
+unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data)
{
struct irq_domain *domain;
irq_hw_number_t hwirq;
unsigned int type = IRQ_TYPE_NONE;
unsigned int virq;
- domain = controller ? irq_find_host(controller) : irq_default_domain;
+ domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain;
if (!domain) {
pr_warn("no irq domain found for %s !\n",
- of_node_full_name(controller));
+ of_node_full_name(irq_data->np));
return 0;
}
/* If domain has no translation, then we assume interrupt line */
if (domain->ops->xlate == NULL)
- hwirq = intspec[0];
+ hwirq = irq_data->args[0];
else {
- if (domain->ops->xlate(domain, controller, intspec, intsize,
- &hwirq, &type))
+ if (domain->ops->xlate(domain, irq_data->np, irq_data->args,
+ irq_data->args_count, &hwirq, &type))
return 0;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 514bcfd855a8..481a13c43b17 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -786,7 +786,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
}
/*
- * Interrupts explicitely requested as threaded interupts want to be
+ * Interrupts explicitly requested as threaded interrupts want to be
* preemtible - many of them need to sleep and wait for slow busses to
* complete.
*/
@@ -956,7 +956,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
goto out_mput;
}
- sched_setscheduler(t, SCHED_FIFO, &param);
+ sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
/*
* We keep the reference to the task struct even if
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index cb228bf21760..abcd6ca86cb7 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@ static void resume_irqs(bool want_early)
bool is_early = desc->action &&
desc->action->flags & IRQF_EARLY_RESUME;
- if (is_early != want_early)
+ if (!is_early && want_early)
continue;
raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 1162f1030f18..3320b84cc60f 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,6 +14,7 @@ enum {
_IRQ_NO_BALANCING = IRQ_NO_BALANCING,
_IRQ_NESTED_THREAD = IRQ_NESTED_THREAD,
_IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID,
+ _IRQ_IS_POLLED = IRQ_IS_POLLED,
_IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
};
@@ -26,6 +27,7 @@ enum {
#define IRQ_NOAUTOEN GOT_YOU_MORON
#define IRQ_NESTED_THREAD GOT_YOU_MORON
#define IRQ_PER_CPU_DEVID GOT_YOU_MORON
+#define IRQ_IS_POLLED GOT_YOU_MORON
#undef IRQF_MODIFY_MASK
#define IRQF_MODIFY_MASK GOT_YOU_MORON
@@ -147,3 +149,8 @@ static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_NESTED_THREAD;
}
+
+static inline bool irq_settings_is_polled(struct irq_desc *desc)
+{
+ return desc->status_use_accessors & _IRQ_IS_POLLED;
+}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7b5f012bde9d..a1d8cc63b56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -67,8 +67,13 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
raw_spin_lock(&desc->lock);
- /* PER_CPU and nested thread interrupts are never polled */
- if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+ /*
+ * PER_CPU, nested thread interrupts and interrupts explicitely
+ * marked polled are excluded from polling.
+ */
+ if (irq_settings_is_per_cpu(desc) ||
+ irq_settings_is_nested_thread(desc) ||
+ irq_settings_is_polled(desc))
goto out;
/*
@@ -268,7 +273,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
void note_interrupt(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
- if (desc->istate & IRQS_POLL_INPROGRESS)
+ if (desc->istate & IRQS_POLL_INPROGRESS ||
+ irq_settings_is_polled(desc))
return;
/* we get here again via the threaded handler */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 297a9247a3b3..9019f15deab2 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,6 +58,7 @@ static void jump_label_update(struct static_key *key, int enable);
void static_key_slow_inc(struct static_key *key)
{
+ STATIC_KEY_CHECK_USE();
if (atomic_inc_not_zero(&key->enabled))
return;
@@ -103,12 +104,14 @@ static void jump_label_update_timeout(struct work_struct *work)
void static_key_slow_dec(struct static_key *key)
{
+ STATIC_KEY_CHECK_USE();
__static_key_slow_dec(key, 0, NULL);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
+ STATIC_KEY_CHECK_USE();
__static_key_slow_dec(&key->key, key->timeout, &key->work);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
@@ -116,6 +119,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
+ STATIC_KEY_CHECK_USE();
key->timeout = rl;
INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
}
@@ -212,6 +216,7 @@ void __init jump_label_init(void)
key->next = NULL;
#endif
}
+ static_key_initialized = true;
jump_label_unlock();
}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 2a74f307c5ec..9c970167e402 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
.name = "Crash kernel",
@@ -921,7 +924,7 @@ static int kimage_load_segment(struct kimage *image,
* reinitialize them.
*
* - A machine specific part that includes the syscall number
- * and the copies the image to it's final destination. And
+ * and then copies the image to it's final destination. And
* jumps into the image at entry.
*
* kexec does not sync, or unmount filesystems so if you need
@@ -1675,7 +1678,9 @@ int kernel_kexec(void)
} else
#endif
{
+ kexec_in_progress = true;
kernel_restart_prepare(NULL);
+ migrate_to_reboot_cpu();
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index a0d367a49122..ceeadfcabb76 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2066,7 +2066,7 @@ static int __init init_kprobes(void)
{
int i, err = 0;
unsigned long offset = 0, size = 0;
- char *modname, namebuf[128];
+ char *modname, namebuf[KSYM_NAME_LEN];
const char *symbol_name;
void *addr;
struct kprobe_blackpoint *kb;
@@ -2192,7 +2192,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
const char *sym = NULL;
unsigned int i = *(loff_t *) v;
unsigned long offset = 0;
- char *modname, namebuf[128];
+ char *modname, namebuf[KSYM_NAME_LEN];
head = &kprobe_table[i];
preempt_disable();
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 760e86df8c20..b5ae3ee860a9 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -33,7 +33,7 @@ struct kthread_create_info
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
- struct completion done;
+ struct completion *done;
struct list_head list;
};
@@ -178,6 +178,7 @@ static int kthread(void *_create)
struct kthread_create_info *create = _create;
int (*threadfn)(void *data) = create->threadfn;
void *data = create->data;
+ struct completion *done;
struct kthread self;
int ret;
@@ -187,10 +188,16 @@ static int kthread(void *_create)
init_completion(&self.parked);
current->vfork_done = &self.exited;
+ /* If user was SIGKILLed, I release the structure. */
+ done = xchg(&create->done, NULL);
+ if (!done) {
+ kfree(create);
+ do_exit(-EINTR);
+ }
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
- complete(&create->done);
+ complete(done);
schedule();
ret = -EINTR;
@@ -223,8 +230,15 @@ static void create_kthread(struct kthread_create_info *create)
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
if (pid < 0) {
+ /* If user was SIGKILLed, I release the structure. */
+ struct completion *done = xchg(&create->done, NULL);
+
+ if (!done) {
+ kfree(create);
+ return;
+ }
create->result = ERR_PTR(pid);
- complete(&create->done);
+ complete(done);
}
}
@@ -255,36 +269,59 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
const char namefmt[],
...)
{
- struct kthread_create_info create;
-
- create.threadfn = threadfn;
- create.data = data;
- create.node = node;
- init_completion(&create.done);
+ DECLARE_COMPLETION_ONSTACK(done);
+ struct task_struct *task;
+ struct kthread_create_info *create = kmalloc(sizeof(*create),
+ GFP_KERNEL);
+
+ if (!create)
+ return ERR_PTR(-ENOMEM);
+ create->threadfn = threadfn;
+ create->data = data;
+ create->node = node;
+ create->done = &done;
spin_lock(&kthread_create_lock);
- list_add_tail(&create.list, &kthread_create_list);
+ list_add_tail(&create->list, &kthread_create_list);
spin_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
- wait_for_completion(&create.done);
-
- if (!IS_ERR(create.result)) {
+ /*
+ * Wait for completion in killable state, for I might be chosen by
+ * the OOM killer while kthreadd is trying to allocate memory for
+ * new kernel thread.
+ */
+ if (unlikely(wait_for_completion_killable(&done))) {
+ /*
+ * If I was SIGKILLed before kthreadd (or new kernel thread)
+ * calls complete(), leave the cleanup of this structure to
+ * that thread.
+ */
+ if (xchg(&create->done, NULL))
+ return ERR_PTR(-ENOMEM);
+ /*
+ * kthreadd (or new kernel thread) will call complete()
+ * shortly.
+ */
+ wait_for_completion(&done);
+ }
+ task = create->result;
+ if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
va_list args;
va_start(args, namefmt);
- vsnprintf(create.result->comm, sizeof(create.result->comm),
- namefmt, args);
+ vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
va_end(args);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
*/
- sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
- set_cpus_allowed_ptr(create.result, cpu_all_mask);
+ sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
+ set_cpus_allowed_ptr(task, cpu_all_mask);
}
- return create.result;
+ kfree(create);
+ return task;
}
EXPORT_SYMBOL(kthread_create_on_node);
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
new file mode 100644
index 000000000000..baab8e5e7f66
--- /dev/null
+++ b/kernel/locking/Makefile
@@ -0,0 +1,25 @@
+
+obj-y += mutex.o semaphore.o rwsem.o lglock.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_lockdep.o = -pg
+CFLAGS_REMOVE_lockdep_proc.o = -pg
+CFLAGS_REMOVE_mutex-debug.o = -pg
+CFLAGS_REMOVE_rtmutex-debug.o = -pg
+endif
+
+obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+obj-$(CONFIG_LOCKDEP) += lockdep.o
+ifeq ($(CONFIG_PROC_FS),y)
+obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
+endif
+obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
+obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
+obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
+obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
diff --git a/kernel/lglock.c b/kernel/locking/lglock.c
index 86ae2aebf004..86ae2aebf004 100644
--- a/kernel/lglock.c
+++ b/kernel/locking/lglock.c
diff --git a/kernel/lockdep.c b/kernel/locking/lockdep.c
index e16c45b9ee77..eb8a54783fa0 100644
--- a/kernel/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
/*
* Is this the address of a static object:
*/
+#ifdef __KERNEL__
static int static_obj(void *obj)
{
unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
*/
return is_module_address(addr) || is_module_percpu_address(addr);
}
+#endif
/*
* To make lock name printouts unique, we calculate a unique
@@ -1232,7 +1234,7 @@ static int noop_count(struct lock_list *entry, void *data)
return 0;
}
-unsigned long __lockdep_count_forward_deps(struct lock_list *this)
+static unsigned long __lockdep_count_forward_deps(struct lock_list *this)
{
unsigned long count = 0;
struct lock_list *uninitialized_var(target_entry);
@@ -1258,7 +1260,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
return ret;
}
-unsigned long __lockdep_count_backward_deps(struct lock_list *this)
+static unsigned long __lockdep_count_backward_deps(struct lock_list *this)
{
unsigned long count = 0;
struct lock_list *uninitialized_var(target_entry);
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
+#ifdef __KERNEL__
void debug_show_all_locks(void)
{
struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
read_unlock(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
/*
* Careful: only use this function if you are sure that
@@ -4224,7 +4228,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
!rcu_lockdep_current_cpu_online()
? "RCU used illegally from offline CPU!\n"
- : rcu_is_cpu_idle()
+ : !rcu_is_watching()
? "RCU used illegally from idle CPU!\n"
: "",
rcu_scheduler_active, debug_locks);
@@ -4247,7 +4251,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
* So complain bitterly if someone does call rcu_read_lock(),
* rcu_read_lock_bh() and so on from extended quiescent states.
*/
- if (rcu_is_cpu_idle())
+ if (!rcu_is_watching())
printk("RCU used illegally from extended quiescent state!\n");
lockdep_print_held_locks(curr);
diff --git a/kernel/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 4f560cfedc8f..4f560cfedc8f 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
diff --git a/kernel/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b2c71c5873e4..ef43ac4bafb5 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -421,6 +421,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
seq_time(m, lt->min);
seq_time(m, lt->max);
seq_time(m, lt->total);
+ seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
}
static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
@@ -518,20 +519,20 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
}
if (i) {
seq_puts(m, "\n");
- seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
+ seq_line(m, '.', 0, 40 + 1 + 12 * (14 + 1));
seq_puts(m, "\n");
}
}
static void seq_header(struct seq_file *m)
{
- seq_printf(m, "lock_stat version 0.3\n");
+ seq_puts(m, "lock_stat version 0.4\n");
if (unlikely(!debug_locks))
seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n");
- seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
- seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
+ seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
+ seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s %14s %14s "
"%14s %14s\n",
"class name",
"con-bounces",
@@ -539,12 +540,14 @@ static void seq_header(struct seq_file *m)
"waittime-min",
"waittime-max",
"waittime-total",
+ "waittime-avg",
"acq-bounces",
"acquisitions",
"holdtime-min",
"holdtime-max",
- "holdtime-total");
- seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
+ "holdtime-total",
+ "holdtime-avg");
+ seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
seq_printf(m, "\n");
}
diff --git a/kernel/lockdep_states.h b/kernel/locking/lockdep_states.h
index 995b0cc2b84c..995b0cc2b84c 100644
--- a/kernel/lockdep_states.h
+++ b/kernel/locking/lockdep_states.h
diff --git a/kernel/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443fe1f48..faf6f5b53e77 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
return;
DEBUG_LOCKS_WARN_ON(lock->magic != lock);
- DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+ if (!lock->owner)
+ DEBUG_LOCKS_WARN_ON(!lock->owner);
+ else
+ DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
mutex_clear_owner(lock);
}
diff --git a/kernel/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..0799fd3e4cfa 100644
--- a/kernel/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
diff --git a/kernel/mutex.c b/kernel/locking/mutex.c
index d24105b1b794..4dd6e4c219de 100644
--- a/kernel/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1,5 +1,5 @@
/*
- * kernel/mutex.c
+ * kernel/locking/mutex.c
*
* Mutexes: blocking mutual exclusion locks
*
diff --git a/kernel/mutex.h b/kernel/locking/mutex.h
index 4115fbf83b12..4115fbf83b12 100644
--- a/kernel/mutex.h
+++ b/kernel/locking/mutex.h
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
new file mode 100644
index 000000000000..652a8ee8efe9
--- /dev/null
+++ b/kernel/locking/percpu-rwsem.c
@@ -0,0 +1,165 @@
+#include <linux/atomic.h>
+#include <linux/rwsem.h>
+#include <linux/percpu.h>
+#include <linux/wait.h>
+#include <linux/lockdep.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+int __percpu_init_rwsem(struct percpu_rw_semaphore *brw,
+ const char *name, struct lock_class_key *rwsem_key)
+{
+ brw->fast_read_ctr = alloc_percpu(int);
+ if (unlikely(!brw->fast_read_ctr))
+ return -ENOMEM;
+
+ /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
+ __init_rwsem(&brw->rw_sem, name, rwsem_key);
+ atomic_set(&brw->write_ctr, 0);
+ atomic_set(&brw->slow_read_ctr, 0);
+ init_waitqueue_head(&brw->write_waitq);
+ return 0;
+}
+
+void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
+{
+ free_percpu(brw->fast_read_ctr);
+ brw->fast_read_ctr = NULL; /* catch use after free bugs */
+}
+
+/*
+ * This is the fast-path for down_read/up_read, it only needs to ensure
+ * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the
+ * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
+ * serialize with the preempt-disabled section below.
+ *
+ * The nontrivial part is that we should guarantee acquire/release semantics
+ * in case when
+ *
+ * R_W: down_write() comes after up_read(), the writer should see all
+ * changes done by the reader
+ * or
+ * W_R: down_read() comes after up_write(), the reader should see all
+ * changes done by the writer
+ *
+ * If this helper fails the callers rely on the normal rw_semaphore and
+ * atomic_dec_and_test(), so in this case we have the necessary barriers.
+ *
+ * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or
+ * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
+ * reader inside the critical section. See the comments in down_write and
+ * up_write below.
+ */
+static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
+{
+ bool success = false;
+
+ preempt_disable();
+ if (likely(!atomic_read(&brw->write_ctr))) {
+ __this_cpu_add(*brw->fast_read_ctr, val);
+ success = true;
+ }
+ preempt_enable();
+
+ return success;
+}
+
+/*
+ * Like the normal down_read() this is not recursive, the writer can
+ * come after the first percpu_down_read() and create the deadlock.
+ *
+ * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep,
+ * percpu_up_read() does rwsem_release(). This pairs with the usage
+ * of ->rw_sem in percpu_down/up_write().
+ */
+void percpu_down_read(struct percpu_rw_semaphore *brw)
+{
+ might_sleep();
+ if (likely(update_fast_ctr(brw, +1))) {
+ rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_);
+ return;
+ }
+
+ down_read(&brw->rw_sem);
+ atomic_inc(&brw->slow_read_ctr);
+ /* avoid up_read()->rwsem_release() */
+ __up_read(&brw->rw_sem);
+}
+
+void percpu_up_read(struct percpu_rw_semaphore *brw)
+{
+ rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);
+
+ if (likely(update_fast_ctr(brw, -1)))
+ return;
+
+ /* false-positive is possible but harmless */
+ if (atomic_dec_and_test(&brw->slow_read_ctr))
+ wake_up_all(&brw->write_waitq);
+}
+
+static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
+{
+ unsigned int sum = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ sum += per_cpu(*brw->fast_read_ctr, cpu);
+ per_cpu(*brw->fast_read_ctr, cpu) = 0;
+ }
+
+ return sum;
+}
+
+/*
+ * A writer increments ->write_ctr to force the readers to switch to the
+ * slow mode, note the atomic_read() check in update_fast_ctr().
+ *
+ * After that the readers can only inc/dec the slow ->slow_read_ctr counter,
+ * ->fast_read_ctr is stable. Once the writer moves its sum into the slow
+ * counter it represents the number of active readers.
+ *
+ * Finally the writer takes ->rw_sem for writing and blocks the new readers,
+ * then waits until the slow counter becomes zero.
+ */
+void percpu_down_write(struct percpu_rw_semaphore *brw)
+{
+ /* tell update_fast_ctr() there is a pending writer */
+ atomic_inc(&brw->write_ctr);
+ /*
+ * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read
+ * so that update_fast_ctr() can't succeed.
+ *
+ * 2. Ensures we see the result of every previous this_cpu_add() in
+ * update_fast_ctr().
+ *
+ * 3. Ensures that if any reader has exited its critical section via
+ * fast-path, it executes a full memory barrier before we return.
+ * See R_W case in the comment above update_fast_ctr().
+ */
+ synchronize_sched_expedited();
+
+ /* exclude other writers, and block the new readers completely */
+ down_write(&brw->rw_sem);
+
+ /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */
+ atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr);
+
+ /* wait for all readers to complete their percpu_up_read() */
+ wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr));
+}
+
+void percpu_up_write(struct percpu_rw_semaphore *brw)
+{
+ /* release the lock, but the readers can't use the fast-path */
+ up_write(&brw->rw_sem);
+ /*
+ * Insert the barrier before the next fast-path in down_read,
+ * see W_R case in the comment above update_fast_ctr().
+ */
+ synchronize_sched_expedited();
+ /* the last writer unblocks update_fast_ctr() */
+ atomic_dec(&brw->write_ctr);
+}
diff --git a/kernel/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a323fa..49b2ed3dced8 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
#include <linux/kallsyms.h>
#include <linux/syscalls.h>
#include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
#include <linux/fs.h>
#include <linux/debug_locks.h>
@@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
void rt_mutex_debug_task_free(struct task_struct *task)
{
- DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+ DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
}
@@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
{
memset(waiter, 0x11, sizeof(*waiter));
- plist_node_init(&waiter->list_entry, MAX_PRIO);
- plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
waiter->deadlock_task_pid = NULL;
}
void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
{
put_pid(waiter->deadlock_task_pid);
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
memset(waiter, 0x22, sizeof(*waiter));
}
diff --git a/kernel/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d596d78..14193d596d78 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
diff --git a/kernel/rtmutex-tester.c b/kernel/locking/rtmutex-tester.c
index 1d96dd0d93c1..1d96dd0d93c1 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/locking/rtmutex-tester.c
diff --git a/kernel/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec1cb6a..2e960a2bab81 100644
--- a/kernel/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include "rtmutex_common.h"
@@ -91,10 +92,107 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
}
#endif
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+ struct rt_mutex_waiter *right)
+{
+ if (left->prio < right->prio)
+ return 1;
+
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+ * If left waiter has a dl_prio(), and we didn't return 1 above,
+ * then right waiter has a dl_prio() too.
+ */
+ if (dl_prio(left->prio))
+ return (left->task->dl.deadline < right->task->dl.deadline);
+
+ return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &lock->waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ lock->waiters_leftmost = &waiter->tree_entry;
+
+ rb_link_node(&waiter->tree_entry, parent, link);
+ rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->tree_entry))
+ return;
+
+ if (lock->waiters_leftmost == &waiter->tree_entry)
+ lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+ rb_erase(&waiter->tree_entry, &lock->waiters);
+ RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &task->pi_waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+ rb_link_node(&waiter->pi_tree_entry, parent, link);
+ rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+ return;
+
+ if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+ task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+ rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+ RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
/*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
*
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
* the waiter is not allowed to do priority boosting
*/
int rt_mutex_getprio(struct task_struct *task)
@@ -102,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task)
if (likely(!task_has_pi_waiters(task)))
return task->normal_prio;
- return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+ return min(task_top_pi_waiter(task)->prio,
task->normal_prio);
}
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+ if (likely(!task_has_pi_waiters(task)))
+ return NULL;
+
+ return task_top_pi_waiter(task)->task;
+}
+
/*
* Adjust the priority of a task, after its pi_waiters got modified.
*
@@ -115,7 +221,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
{
int prio = rt_mutex_getprio(task);
- if (task->prio != prio)
+ if (task->prio != prio || dl_prio(prio))
rt_mutex_setprio(task, prio);
}
@@ -233,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
* When deadlock detection is off then we check, if further
* priority adjustment is necessary.
*/
- if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+ if (!detect_deadlock && waiter->prio == task->prio)
goto out_unlock_pi;
lock = waiter->lock;
@@ -254,9 +360,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
top_waiter = rt_mutex_top_waiter(lock);
/* Requeue the waiter */
- plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->list_entry.prio = task->prio;
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
+ waiter->prio = task->prio;
+ rt_mutex_enqueue(lock, waiter);
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +386,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
- plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, top_waiter);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
} else if (top_waiter == waiter) {
/* Deboost the owner */
- plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
}
@@ -355,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
* 3) it is top waiter
*/
if (rt_mutex_has_waiters(lock)) {
- if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
if (!waiter || waiter != rt_mutex_top_waiter(lock))
return 0;
}
@@ -369,7 +473,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
/* remove the queued waiter. */
if (waiter) {
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
task->pi_blocked_on = NULL;
}
@@ -379,8 +483,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
*/
if (rt_mutex_has_waiters(lock)) {
top = rt_mutex_top_waiter(lock);
- top->pi_list_entry.prio = top->list_entry.prio;
- plist_add(&top->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, top);
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
@@ -416,13 +519,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
- plist_node_init(&waiter->list_entry, task->prio);
- plist_node_init(&waiter->pi_list_entry, task->prio);
+ waiter->prio = task->prio;
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_enqueue(lock, waiter);
task->pi_blocked_on = waiter;
@@ -433,8 +535,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
- plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, top_waiter);
+ rt_mutex_enqueue_pi(owner, waiter);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
@@ -486,7 +588,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
* boosted mode and go back to normal after releasing
* lock->wait_lock.
*/
- plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+ rt_mutex_dequeue_pi(current, waiter);
rt_mutex_set_owner(lock, NULL);
@@ -510,7 +612,7 @@ static void remove_waiter(struct rt_mutex *lock,
int chain_walk = 0;
raw_spin_lock_irqsave(&current->pi_lock, flags);
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(&current->pi_lock, flags);
@@ -521,13 +623,13 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, waiter);
if (rt_mutex_has_waiters(lock)) {
struct rt_mutex_waiter *next;
next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_enqueue_pi(owner, next);
}
__rt_mutex_adjust_prio(owner);
@@ -537,8 +639,6 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
- WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
if (!chain_walk)
return;
@@ -565,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
- if (!waiter || waiter->list_entry.prio == task->prio) {
+ if (!waiter || (waiter->prio == task->prio &&
+ !dl_prio(task->prio))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
@@ -638,6 +739,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
+ RB_CLEAR_NODE(&waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&waiter.tree_entry);
raw_spin_lock(&lock->wait_lock);
@@ -904,7 +1007,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
{
lock->owner = NULL;
raw_spin_lock_init(&lock->wait_lock);
- plist_head_init(&lock->wait_list);
+ lock->waiters = RB_ROOT;
+ lock->waiters_leftmost = NULL;
debug_rt_mutex_init(lock, name);
}
diff --git a/kernel/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd06421d..a1a1dd06421d 100644
--- a/kernel/rtmutex.h
+++ b/kernel/locking/rtmutex.h
diff --git a/kernel/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c85261b..7431a9c86f35 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
* This is the control structure for tasks blocked on a rt_mutex,
* which is allocated on the kernel stack on of the blocked task.
*
- * @list_entry: pi node to enqueue into the mutex waiters list
- * @pi_list_entry: pi node to enqueue into the mutex owner waiters list
+ * @tree_entry: pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree
* @task: task reference to the blocked task
*/
struct rt_mutex_waiter {
- struct plist_node list_entry;
- struct plist_node pi_list_entry;
+ struct rb_node tree_entry;
+ struct rb_node pi_tree_entry;
struct task_struct *task;
struct rt_mutex *lock;
#ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -54,14 +54,15 @@ struct rt_mutex_waiter {
struct pid *deadlock_task_pid;
struct rt_mutex *deadlock_lock;
#endif
+ int prio;
};
/*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
*/
static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
{
- return !plist_head_empty(&lock->wait_list);
+ return !RB_EMPTY_ROOT(&lock->waiters);
}
static inline struct rt_mutex_waiter *
@@ -69,8 +70,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
{
struct rt_mutex_waiter *w;
- w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
- list_entry);
+ w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+ tree_entry);
BUG_ON(w->lock != lock);
return w;
@@ -78,14 +79,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
static inline int task_has_pi_waiters(struct task_struct *p)
{
- return !plist_head_empty(&p->pi_waiters);
+ return !RB_EMPTY_ROOT(&p->pi_waiters);
}
static inline struct rt_mutex_waiter *
task_top_pi_waiter(struct task_struct *p)
{
- return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
- pi_list_entry);
+ return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+ pi_tree_entry);
}
/*
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
new file mode 100644
index 000000000000..9be8a9144978
--- /dev/null
+++ b/kernel/locking/rwsem-spinlock.c
@@ -0,0 +1,296 @@
+/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
+ * generic spinlock implementation
+ *
+ * Copyright (c) 2001 David Howells (dhowells@redhat.com).
+ * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ * - Derived also from comments by Linus
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+
+enum rwsem_waiter_type {
+ RWSEM_WAITING_FOR_WRITE,
+ RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+ struct list_head list;
+ struct task_struct *task;
+ enum rwsem_waiter_type type;
+};
+
+int rwsem_is_locked(struct rw_semaphore *sem)
+{
+ int ret = 1;
+ unsigned long flags;
+
+ if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
+ ret = (sem->activity != 0);
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ }
+ return ret;
+}
+EXPORT_SYMBOL(rwsem_is_locked);
+
+/*
+ * initialise the semaphore
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+ struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ /*
+ * Make sure we are not reinitializing a held semaphore:
+ */
+ debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+ lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+ sem->activity = 0;
+ raw_spin_lock_init(&sem->wait_lock);
+ INIT_LIST_HEAD(&sem->wait_list);
+}
+EXPORT_SYMBOL(__init_rwsem);
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here, then:
+ * - the 'active count' _reached_ zero
+ * - the 'waiting count' is non-zero
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if wakewrite is non-zero
+ */
+static inline struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
+{
+ struct rwsem_waiter *waiter;
+ struct task_struct *tsk;
+ int woken;
+
+ waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+
+ if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+ if (wakewrite)
+ /* Wake up a writer. Note that we do not grant it the
+ * lock - it will have to acquire it when it runs. */
+ wake_up_process(waiter->task);
+ goto out;
+ }
+
+ /* grant an infinite number of read locks to the front of the queue */
+ woken = 0;
+ do {
+ struct list_head *next = waiter->list.next;
+
+ list_del(&waiter->list);
+ tsk = waiter->task;
+ smp_mb();
+ waiter->task = NULL;
+ wake_up_process(tsk);
+ put_task_struct(tsk);
+ woken++;
+ if (next == &sem->wait_list)
+ break;
+ waiter = list_entry(next, struct rwsem_waiter, list);
+ } while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+ sem->activity += woken;
+
+ out:
+ return sem;
+}
+
+/*
+ * wake a single writer
+ */
+static inline struct rw_semaphore *
+__rwsem_wake_one_writer(struct rw_semaphore *sem)
+{
+ struct rwsem_waiter *waiter;
+
+ waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+ wake_up_process(waiter->task);
+
+ return sem;
+}
+
+/*
+ * get a read lock on the semaphore
+ */
+void __sched __down_read(struct rw_semaphore *sem)
+{
+ struct rwsem_waiter waiter;
+ struct task_struct *tsk;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+ sem->activity++;
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ goto out;
+ }
+
+ tsk = current;
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+ /* set up my own style of waitqueue */
+ waiter.task = tsk;
+ waiter.type = RWSEM_WAITING_FOR_READ;
+ get_task_struct(tsk);
+
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we don't need to touch the semaphore struct anymore */
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ /* wait to be given the lock */
+ for (;;) {
+ if (!waiter.task)
+ break;
+ schedule();
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ }
+
+ tsk->state = TASK_RUNNING;
+ out:
+ ;
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+ int ret = 0;
+
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+ /* granted */
+ sem->activity++;
+ ret = 1;
+ }
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return ret;
+}
+
+/*
+ * get a write lock on the semaphore
+ */
+void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+ struct rwsem_waiter waiter;
+ struct task_struct *tsk;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ /* set up my own style of waitqueue */
+ tsk = current;
+ waiter.task = tsk;
+ waiter.type = RWSEM_WAITING_FOR_WRITE;
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* wait for someone to release the lock */
+ for (;;) {
+ /*
+ * That is the key to support write lock stealing: allows the
+ * task already on CPU to get the lock soon rather than put
+ * itself into sleep and waiting for system woke it or someone
+ * else in the head of the wait list up.
+ */
+ if (sem->activity == 0)
+ break;
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ schedule();
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+ }
+ /* got the lock */
+ sem->activity = -1;
+ list_del(&waiter.list);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+void __sched __down_write(struct rw_semaphore *sem)
+{
+ __down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+int __down_write_trylock(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (sem->activity == 0) {
+ /* got the lock */
+ sem->activity = -1;
+ ret = 1;
+ }
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return ret;
+}
+
+/*
+ * release a read lock on the semaphore
+ */
+void __up_read(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+ sem = __rwsem_wake_one_writer(sem);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * release a write lock on the semaphore
+ */
+void __up_write(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ sem->activity = 0;
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 1);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - just wake up any readers at the front of the queue
+ */
+void __downgrade_write(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ sem->activity = 1;
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, 0);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
new file mode 100644
index 000000000000..19c5fa95e0b4
--- /dev/null
+++ b/kernel/locking/rwsem-xadd.c
@@ -0,0 +1,293 @@
+/* rwsem.c: R/W semaphores: contention handling functions
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ * Derived from arch/i386/kernel/semaphore.c
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
+ * and Michel Lespinasse <walken@google.com>
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/export.h>
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+ struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ /*
+ * Make sure we are not reinitializing a held semaphore:
+ */
+ debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+ lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+ sem->count = RWSEM_UNLOCKED_VALUE;
+ raw_spin_lock_init(&sem->wait_lock);
+ INIT_LIST_HEAD(&sem->wait_list);
+}
+
+EXPORT_SYMBOL(__init_rwsem);
+
+enum rwsem_waiter_type {
+ RWSEM_WAITING_FOR_WRITE,
+ RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+ struct list_head list;
+ struct task_struct *task;
+ enum rwsem_waiter_type type;
+};
+
+enum rwsem_wake_type {
+ RWSEM_WAKE_ANY, /* Wake whatever's at head of wait list */
+ RWSEM_WAKE_READERS, /* Wake readers only */
+ RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */
+};
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then:
+ * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
+ * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
+ * - there must be someone on the queue
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if downgrading is false
+ */
+static struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+{
+ struct rwsem_waiter *waiter;
+ struct task_struct *tsk;
+ struct list_head *next;
+ long oldcount, woken, loop, adjustment;
+
+ waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+ if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+ if (wake_type == RWSEM_WAKE_ANY)
+ /* Wake writer at the front of the queue, but do not
+ * grant it the lock yet as we want other writers
+ * to be able to steal it. Readers, on the other hand,
+ * will block as they will notice the queued writer.
+ */
+ wake_up_process(waiter->task);
+ goto out;
+ }
+
+ /* Writers might steal the lock before we grant it to the next reader.
+ * We prefer to do the first reader grant before counting readers
+ * so we can bail out early if a writer stole the lock.
+ */
+ adjustment = 0;
+ if (wake_type != RWSEM_WAKE_READ_OWNED) {
+ adjustment = RWSEM_ACTIVE_READ_BIAS;
+ try_reader_grant:
+ oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+ if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
+ /* A writer stole the lock. Undo our reader grant. */
+ if (rwsem_atomic_update(-adjustment, sem) &
+ RWSEM_ACTIVE_MASK)
+ goto out;
+ /* Last active locker left. Retry waking readers. */
+ goto try_reader_grant;
+ }
+ }
+
+ /* Grant an infinite number of read locks to the readers at the front
+ * of the queue. Note we increment the 'active part' of the count by
+ * the number of readers before waking any processes up.
+ */
+ woken = 0;
+ do {
+ woken++;
+
+ if (waiter->list.next == &sem->wait_list)
+ break;
+
+ waiter = list_entry(waiter->list.next,
+ struct rwsem_waiter, list);
+
+ } while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+ adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+ if (waiter->type != RWSEM_WAITING_FOR_WRITE)
+ /* hit end of list above */
+ adjustment -= RWSEM_WAITING_BIAS;
+
+ if (adjustment)
+ rwsem_atomic_add(adjustment, sem);
+
+ next = sem->wait_list.next;
+ loop = woken;
+ do {
+ waiter = list_entry(next, struct rwsem_waiter, list);
+ next = waiter->list.next;
+ tsk = waiter->task;
+ smp_mb();
+ waiter->task = NULL;
+ wake_up_process(tsk);
+ put_task_struct(tsk);
+ } while (--loop);
+
+ sem->wait_list.next = next;
+ next->prev = &sem->wait_list;
+
+ out:
+ return sem;
+}
+
+/*
+ * wait for the read lock to be granted
+ */
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+ long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+ struct rwsem_waiter waiter;
+ struct task_struct *tsk = current;
+
+ /* set up my own style of waitqueue */
+ waiter.task = tsk;
+ waiter.type = RWSEM_WAITING_FOR_READ;
+ get_task_struct(tsk);
+
+ raw_spin_lock_irq(&sem->wait_lock);
+ if (list_empty(&sem->wait_list))
+ adjustment += RWSEM_WAITING_BIAS;
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we're now waiting on the lock, but no longer actively locking */
+ count = rwsem_atomic_update(adjustment, sem);
+
+ /* If there are no active locks, wake the front queued process(es).
+ *
+ * If there are no writers and we are first in the queue,
+ * wake our own waiter to join the existing active readers !
+ */
+ if (count == RWSEM_WAITING_BIAS ||
+ (count > RWSEM_WAITING_BIAS &&
+ adjustment != -RWSEM_ACTIVE_READ_BIAS))
+ sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+ raw_spin_unlock_irq(&sem->wait_lock);
+
+ /* wait to be given the lock */
+ while (true) {
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ if (!waiter.task)
+ break;
+ schedule();
+ }
+
+ tsk->state = TASK_RUNNING;
+
+ return sem;
+}
+
+/*
+ * wait until we successfully acquire the write lock
+ */
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+ long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
+ struct rwsem_waiter waiter;
+ struct task_struct *tsk = current;
+
+ /* set up my own style of waitqueue */
+ waiter.task = tsk;
+ waiter.type = RWSEM_WAITING_FOR_WRITE;
+
+ raw_spin_lock_irq(&sem->wait_lock);
+ if (list_empty(&sem->wait_list))
+ adjustment += RWSEM_WAITING_BIAS;
+ list_add_tail(&waiter.list, &sem->wait_list);
+
+ /* we're now waiting on the lock, but no longer actively locking */
+ count = rwsem_atomic_update(adjustment, sem);
+
+ /* If there were already threads queued before us and there are no
+ * active writers, the lock must be read owned; so we try to wake
+ * any read locks that were queued ahead of us. */
+ if (count > RWSEM_WAITING_BIAS &&
+ adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
+ sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+
+ /* wait until we successfully acquire the lock */
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ while (true) {
+ if (!(count & RWSEM_ACTIVE_MASK)) {
+ /* Try acquiring the write lock. */
+ count = RWSEM_ACTIVE_WRITE_BIAS;
+ if (!list_is_singular(&sem->wait_list))
+ count += RWSEM_WAITING_BIAS;
+
+ if (sem->count == RWSEM_WAITING_BIAS &&
+ cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) ==
+ RWSEM_WAITING_BIAS)
+ break;
+ }
+
+ raw_spin_unlock_irq(&sem->wait_lock);
+
+ /* Block until there are no active lockers. */
+ do {
+ schedule();
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ } while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+
+ raw_spin_lock_irq(&sem->wait_lock);
+ }
+
+ list_del(&waiter.list);
+ raw_spin_unlock_irq(&sem->wait_lock);
+ tsk->state = TASK_RUNNING;
+
+ return sem;
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ /* do nothing if list empty */
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+ /* do nothing if list empty */
+ if (!list_empty(&sem->wait_list))
+ sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+
+ raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+ return sem;
+}
+
+EXPORT_SYMBOL(rwsem_down_read_failed);
+EXPORT_SYMBOL(rwsem_down_write_failed);
+EXPORT_SYMBOL(rwsem_wake);
+EXPORT_SYMBOL(rwsem_downgrade_wake);
diff --git a/kernel/rwsem.c b/kernel/locking/rwsem.c
index cfff1435bdfb..cfff1435bdfb 100644
--- a/kernel/rwsem.c
+++ b/kernel/locking/rwsem.c
diff --git a/kernel/semaphore.c b/kernel/locking/semaphore.c
index 6815171a4fff..6815171a4fff 100644
--- a/kernel/semaphore.c
+++ b/kernel/locking/semaphore.c
diff --git a/kernel/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9e..4b082b5cac9e 100644
--- a/kernel/spinlock.c
+++ b/kernel/locking/spinlock.c
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
new file mode 100644
index 000000000000..0374a596cffa
--- /dev/null
+++ b/kernel/locking/spinlock_debug.c
@@ -0,0 +1,302 @@
+/*
+ * Copyright 2005, Red Hat, Inc., Ingo Molnar
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the spinlock/rwlock implementations for
+ * DEBUG_SPINLOCK.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/nmi.h>
+#include <linux/interrupt.h>
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+
+void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
+ struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ /*
+ * Make sure we are not reinitializing a held lock:
+ */
+ debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+ lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+ lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+ lock->magic = SPINLOCK_MAGIC;
+ lock->owner = SPINLOCK_OWNER_INIT;
+ lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__raw_spin_lock_init);
+
+void __rwlock_init(rwlock_t *lock, const char *name,
+ struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ /*
+ * Make sure we are not reinitializing a held lock:
+ */
+ debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+ lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+ lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
+ lock->magic = RWLOCK_MAGIC;
+ lock->owner = SPINLOCK_OWNER_INIT;
+ lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__rwlock_init);
+
+static void spin_dump(raw_spinlock_t *lock, const char *msg)
+{
+ struct task_struct *owner = NULL;
+
+ if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
+ owner = lock->owner;
+ printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
+ msg, raw_smp_processor_id(),
+ current->comm, task_pid_nr(current));
+ printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
+ ".owner_cpu: %d\n",
+ lock, lock->magic,
+ owner ? owner->comm : "<none>",
+ owner ? task_pid_nr(owner) : -1,
+ lock->owner_cpu);
+ dump_stack();
+}
+
+static void spin_bug(raw_spinlock_t *lock, const char *msg)
+{
+ if (!debug_locks_off())
+ return;
+
+ spin_dump(lock, msg);
+}
+
+#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
+
+static inline void
+debug_spin_lock_before(raw_spinlock_t *lock)
+{
+ SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+ SPIN_BUG_ON(lock->owner == current, lock, "recursion");
+ SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+ lock, "cpu recursion");
+}
+
+static inline void debug_spin_lock_after(raw_spinlock_t *lock)
+{
+ lock->owner_cpu = raw_smp_processor_id();
+ lock->owner = current;
+}
+
+static inline void debug_spin_unlock(raw_spinlock_t *lock)
+{
+ SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+ SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked");
+ SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
+ SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+ lock, "wrong CPU");
+ lock->owner = SPINLOCK_OWNER_INIT;
+ lock->owner_cpu = -1;
+}
+
+static void __spin_lock_debug(raw_spinlock_t *lock)
+{
+ u64 i;
+ u64 loops = loops_per_jiffy * HZ;
+
+ for (i = 0; i < loops; i++) {
+ if (arch_spin_trylock(&lock->raw_lock))
+ return;
+ __delay(1);
+ }
+ /* lockup suspected: */
+ spin_dump(lock, "lockup suspected");
+#ifdef CONFIG_SMP
+ trigger_all_cpu_backtrace();
+#endif
+
+ /*
+ * The trylock above was causing a livelock. Give the lower level arch
+ * specific lock code a chance to acquire the lock. We have already
+ * printed a warning/backtrace at this point. The non-debug arch
+ * specific code might actually succeed in acquiring the lock. If it is
+ * not successful, the end-result is the same - there is no forward
+ * progress.
+ */
+ arch_spin_lock(&lock->raw_lock);
+}
+
+void do_raw_spin_lock(raw_spinlock_t *lock)
+{
+ debug_spin_lock_before(lock);
+ if (unlikely(!arch_spin_trylock(&lock->raw_lock)))
+ __spin_lock_debug(lock);
+ debug_spin_lock_after(lock);
+}
+
+int do_raw_spin_trylock(raw_spinlock_t *lock)
+{
+ int ret = arch_spin_trylock(&lock->raw_lock);
+
+ if (ret)
+ debug_spin_lock_after(lock);
+#ifndef CONFIG_SMP
+ /*
+ * Must not happen on UP:
+ */
+ SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+ return ret;
+}
+
+void do_raw_spin_unlock(raw_spinlock_t *lock)
+{
+ debug_spin_unlock(lock);
+ arch_spin_unlock(&lock->raw_lock);
+}
+
+static void rwlock_bug(rwlock_t *lock, const char *msg)
+{
+ if (!debug_locks_off())
+ return;
+
+ printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n",
+ msg, raw_smp_processor_id(), current->comm,
+ task_pid_nr(current), lock);
+ dump_stack();
+}
+
+#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
+
+#if 0 /* __write_lock_debug() can lock up - maybe this can too? */
+static void __read_lock_debug(rwlock_t *lock)
+{
+ u64 i;
+ u64 loops = loops_per_jiffy * HZ;
+ int print_once = 1;
+
+ for (;;) {
+ for (i = 0; i < loops; i++) {
+ if (arch_read_trylock(&lock->raw_lock))
+ return;
+ __delay(1);
+ }
+ /* lockup suspected: */
+ if (print_once) {
+ print_once = 0;
+ printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
+ "%s/%d, %p\n",
+ raw_smp_processor_id(), current->comm,
+ current->pid, lock);
+ dump_stack();
+ }
+ }
+}
+#endif
+
+void do_raw_read_lock(rwlock_t *lock)
+{
+ RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+ arch_read_lock(&lock->raw_lock);
+}
+
+int do_raw_read_trylock(rwlock_t *lock)
+{
+ int ret = arch_read_trylock(&lock->raw_lock);
+
+#ifndef CONFIG_SMP
+ /*
+ * Must not happen on UP:
+ */
+ RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+ return ret;
+}
+
+void do_raw_read_unlock(rwlock_t *lock)
+{
+ RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+ arch_read_unlock(&lock->raw_lock);
+}
+
+static inline void debug_write_lock_before(rwlock_t *lock)
+{
+ RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+ RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
+ RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+ lock, "cpu recursion");
+}
+
+static inline void debug_write_lock_after(rwlock_t *lock)
+{
+ lock->owner_cpu = raw_smp_processor_id();
+ lock->owner = current;
+}
+
+static inline void debug_write_unlock(rwlock_t *lock)
+{
+ RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+ RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
+ RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+ lock, "wrong CPU");
+ lock->owner = SPINLOCK_OWNER_INIT;
+ lock->owner_cpu = -1;
+}
+
+#if 0 /* This can cause lockups */
+static void __write_lock_debug(rwlock_t *lock)
+{
+ u64 i;
+ u64 loops = loops_per_jiffy * HZ;
+ int print_once = 1;
+
+ for (;;) {
+ for (i = 0; i < loops; i++) {
+ if (arch_write_trylock(&lock->raw_lock))
+ return;
+ __delay(1);
+ }
+ /* lockup suspected: */
+ if (print_once) {
+ print_once = 0;
+ printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
+ "%s/%d, %p\n",
+ raw_smp_processor_id(), current->comm,
+ current->pid, lock);
+ dump_stack();
+ }
+ }
+}
+#endif
+
+void do_raw_write_lock(rwlock_t *lock)
+{
+ debug_write_lock_before(lock);
+ arch_write_lock(&lock->raw_lock);
+ debug_write_lock_after(lock);
+}
+
+int do_raw_write_trylock(rwlock_t *lock)
+{
+ int ret = arch_write_trylock(&lock->raw_lock);
+
+ if (ret)
+ debug_write_lock_after(lock);
+#ifndef CONFIG_SMP
+ /*
+ * Must not happen on UP:
+ */
+ RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+ return ret;
+}
+
+void do_raw_write_unlock(rwlock_t *lock)
+{
+ debug_write_unlock(lock);
+ arch_write_unlock(&lock->raw_lock);
+}
diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S
deleted file mode 100644
index 4a9a86d12c8b..000000000000
--- a/kernel/modsign_certificate.S
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <linux/export.h>
-
-#define GLOBAL(name) \
- .globl VMLINUX_SYMBOL(name); \
- VMLINUX_SYMBOL(name):
-
- .section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
- .incbin "signing_key.x509"
- .incbin "extra_certificates"
-GLOBAL(modsign_certificate_list_end)
diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c
deleted file mode 100644
index 7cbd4507a7e6..000000000000
--- a/kernel/modsign_pubkey.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/* Public keys for module signature verification
- *
- * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cred.h>
-#include <linux/err.h>
-#include <keys/asymmetric-type.h>
-#include "module-internal.h"
-
-struct key *modsign_keyring;
-
-extern __initconst const u8 modsign_certificate_list[];
-extern __initconst const u8 modsign_certificate_list_end[];
-
-/*
- * We need to make sure ccache doesn't cache the .o file as it doesn't notice
- * if modsign.pub changes.
- */
-static __initconst const char annoy_ccache[] = __TIME__ "foo";
-
-/*
- * Load the compiled-in keys
- */
-static __init int module_verify_init(void)
-{
- pr_notice("Initialise module verification\n");
-
- modsign_keyring = keyring_alloc(".module_sign",
- KUIDT_INIT(0), KGIDT_INIT(0),
- current_cred(),
- ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
- KEY_USR_VIEW | KEY_USR_READ),
- KEY_ALLOC_NOT_IN_QUOTA, NULL);
- if (IS_ERR(modsign_keyring))
- panic("Can't allocate module signing keyring\n");
-
- return 0;
-}
-
-/*
- * Must be initialised before we try and load the keys into the keyring.
- */
-device_initcall(module_verify_init);
-
-/*
- * Load the compiled-in keys
- */
-static __init int load_module_signing_keys(void)
-{
- key_ref_t key;
- const u8 *p, *end;
- size_t plen;
-
- pr_notice("Loading module verification certificates\n");
-
- end = modsign_certificate_list_end;
- p = modsign_certificate_list;
- while (p < end) {
- /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
- * than 256 bytes in size.
- */
- if (end - p < 4)
- goto dodgy_cert;
- if (p[0] != 0x30 &&
- p[1] != 0x82)
- goto dodgy_cert;
- plen = (p[2] << 8) | p[3];
- plen += 4;
- if (plen > end - p)
- goto dodgy_cert;
-
- key = key_create_or_update(make_key_ref(modsign_keyring, 1),
- "asymmetric",
- NULL,
- p,
- plen,
- (KEY_POS_ALL & ~KEY_POS_SETATTR) |
- KEY_USR_VIEW,
- KEY_ALLOC_NOT_IN_QUOTA);
- if (IS_ERR(key))
- pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n",
- PTR_ERR(key));
- else
- pr_notice("MODSIGN: Loaded cert '%s'\n",
- key_ref_to_ptr(key)->description);
- p += plen;
- }
-
- return 0;
-
-dodgy_cert:
- pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n");
- return 0;
-}
-late_initcall(load_module_signing_keys);
diff --git a/kernel/module-internal.h b/kernel/module-internal.h
index 24f9247b7d02..915e123a430f 100644
--- a/kernel/module-internal.h
+++ b/kernel/module-internal.h
@@ -9,6 +9,4 @@
* 2 of the Licence, or (at your option) any later version.
*/
-extern struct key *modsign_keyring;
-
extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
diff --git a/kernel/module.c b/kernel/module.c
index dc582749fa13..d24fcf29cb64 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -378,23 +378,21 @@ static bool check_symbol(const struct symsearch *syms,
if (syms->licence == GPL_ONLY)
return false;
if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
- printk(KERN_WARNING "Symbol %s is being used "
- "by a non-GPL module, which will not "
- "be allowed in the future\n", fsa->name);
+ pr_warn("Symbol %s is being used by a non-GPL module, "
+ "which will not be allowed in the future\n",
+ fsa->name);
}
}
#ifdef CONFIG_UNUSED_SYMBOLS
if (syms->unused && fsa->warn) {
- printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
- "however this module is using it.\n", fsa->name);
- printk(KERN_WARNING
- "This symbol will go away in the future.\n");
- printk(KERN_WARNING
- "Please evalute if this is the right api to use and if "
- "it really is, submit a report the linux kernel "
- "mailinglist together with submitting your code for "
- "inclusion.\n");
+ pr_warn("Symbol %s is marked as UNUSED, however this module is "
+ "using it.\n", fsa->name);
+ pr_warn("This symbol will go away in the future.\n");
+ pr_warn("Please evalute if this is the right api to use and if "
+ "it really is, submit a report the linux kernel "
+ "mailinglist together with submitting your code for "
+ "inclusion.\n");
}
#endif
@@ -492,16 +490,15 @@ static int percpu_modalloc(struct module *mod, struct load_info *info)
return 0;
if (align > PAGE_SIZE) {
- printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
- mod->name, align, PAGE_SIZE);
+ pr_warn("%s: per-cpu alignment %li > %li\n",
+ mod->name, align, PAGE_SIZE);
align = PAGE_SIZE;
}
mod->percpu = __alloc_reserved_percpu(pcpusec->sh_size, align);
if (!mod->percpu) {
- printk(KERN_WARNING
- "%s: Could not allocate %lu bytes percpu data\n",
- mod->name, (unsigned long)pcpusec->sh_size);
+ pr_warn("%s: Could not allocate %lu bytes percpu data\n",
+ mod->name, (unsigned long)pcpusec->sh_size);
return -ENOMEM;
}
mod->percpu_size = pcpusec->sh_size;
@@ -644,8 +641,6 @@ static int module_unload_init(struct module *mod)
/* Hold reference count during initialization. */
__this_cpu_write(mod->refptr->incs, 1);
- /* Backwards compatibility macros put refcount during init. */
- mod->waiter = current;
return 0;
}
@@ -679,7 +674,7 @@ static int add_module_usage(struct module *a, struct module *b)
pr_debug("Allocating new usage for %s.\n", a->name);
use = kmalloc(sizeof(*use), GFP_ATOMIC);
if (!use) {
- printk(KERN_WARNING "%s: out of memory loading\n", a->name);
+ pr_warn("%s: out of memory loading\n", a->name);
return -ENOMEM;
}
@@ -771,16 +766,9 @@ static int __try_stop_module(void *_sref)
static int try_stop_module(struct module *mod, int flags, int *forced)
{
- if (flags & O_NONBLOCK) {
- struct stopref sref = { mod, flags, forced };
+ struct stopref sref = { mod, flags, forced };
- return stop_machine(__try_stop_module, &sref, NULL);
- } else {
- /* We don't need to stop the machine for this. */
- mod->state = MODULE_STATE_GOING;
- synchronize_sched();
- return 0;
- }
+ return stop_machine(__try_stop_module, &sref, NULL);
}
unsigned long module_refcount(struct module *mod)
@@ -813,21 +801,6 @@ EXPORT_SYMBOL(module_refcount);
/* This exists whether we can unload or not */
static void free_module(struct module *mod);
-static void wait_for_zero_refcount(struct module *mod)
-{
- /* Since we might sleep for some time, release the mutex first */
- mutex_unlock(&module_mutex);
- for (;;) {
- pr_debug("Looking at refcount...\n");
- set_current_state(TASK_UNINTERRUPTIBLE);
- if (module_refcount(mod) == 0)
- break;
- schedule();
- }
- current->state = TASK_RUNNING;
- mutex_lock(&module_mutex);
-}
-
SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
unsigned int, flags)
{
@@ -842,6 +815,9 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
return -EFAULT;
name[MODULE_NAME_LEN-1] = '\0';
+ if (!(flags & O_NONBLOCK))
+ pr_warn("waiting module removal not supported: please upgrade\n");
+
if (mutex_lock_interruptible(&module_mutex) != 0)
return -EINTR;
@@ -859,8 +835,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
/* Doing init or already dying? */
if (mod->state != MODULE_STATE_LIVE) {
- /* FIXME: if (force), slam module count and wake up
- waiter --RR */
+ /* FIXME: if (force), slam module count damn the torpedoes */
pr_debug("%s already dying\n", mod->name);
ret = -EBUSY;
goto out;
@@ -876,18 +851,11 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
}
}
- /* Set this up before setting mod->state */
- mod->waiter = current;
-
/* Stop the machine so refcounts can't move and disable module. */
ret = try_stop_module(mod, flags, &forced);
if (ret != 0)
goto out;
- /* Never wait if forced. */
- if (!forced && module_refcount(mod) != 0)
- wait_for_zero_refcount(mod);
-
mutex_unlock(&module_mutex);
/* Final destruction now no one is using it. */
if (mod->exit != NULL)
@@ -1005,9 +973,6 @@ void module_put(struct module *module)
__this_cpu_inc(module->refptr->decs);
trace_module_put(module, _RET_IP_);
- /* Maybe they're waiting for us to drop reference? */
- if (unlikely(!module_is_live(module)))
- wake_up_process(module->waiter);
preempt_enable();
}
}
@@ -1145,8 +1110,7 @@ static int try_to_force_load(struct module *mod, const char *reason)
{
#ifdef CONFIG_MODULE_FORCE_LOAD
if (!test_taint(TAINT_FORCED_MODULE))
- printk(KERN_WARNING "%s: %s: kernel tainted.\n",
- mod->name, reason);
+ pr_warn("%s: %s: kernel tainted.\n", mod->name, reason);
add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_NOW_UNRELIABLE);
return 0;
#else
@@ -1199,8 +1163,7 @@ static int check_version(Elf_Shdr *sechdrs,
goto bad_version;
}
- printk(KERN_WARNING "%s: no symbol version for %s\n",
- mod->name, symname);
+ pr_warn("%s: no symbol version for %s\n", mod->name, symname);
return 0;
bad_version:
@@ -1309,8 +1272,8 @@ resolve_symbol_wait(struct module *mod,
!IS_ERR(ksym = resolve_symbol(mod, info, name, owner))
|| PTR_ERR(ksym) != -EBUSY,
30 * HZ) <= 0) {
- printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n",
- mod->name, owner);
+ pr_warn("%s: gave up waiting for init of module %s.\n",
+ mod->name, owner);
}
return ksym;
}
@@ -1626,15 +1589,14 @@ static int mod_sysfs_init(struct module *mod)
struct kobject *kobj;
if (!module_sysfs_initialized) {
- printk(KERN_ERR "%s: module sysfs not initialized\n",
- mod->name);
+ pr_err("%s: module sysfs not initialized\n", mod->name);
err = -EINVAL;
goto out;
}
kobj = kset_find_obj(module_kset, mod->name);
if (kobj) {
- printk(KERN_ERR "%s: module is already loaded\n", mod->name);
+ pr_err("%s: module is already loaded\n", mod->name);
kobject_put(kobj);
err = -EINVAL;
goto out;
@@ -1961,8 +1923,7 @@ static int verify_export_symbols(struct module *mod)
for (i = 0; i < ARRAY_SIZE(arr); i++) {
for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
if (find_symbol(s->name, &owner, NULL, true, false)) {
- printk(KERN_ERR
- "%s: exports duplicate symbol %s"
+ pr_err("%s: exports duplicate symbol %s"
" (owned by %s)\n",
mod->name, s->name, module_name(owner));
return -ENOEXEC;
@@ -2013,8 +1974,8 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK)
break;
- printk(KERN_WARNING "%s: Unknown symbol %s (err %li)\n",
- mod->name, name, PTR_ERR(ksym));
+ pr_warn("%s: Unknown symbol %s (err %li)\n",
+ mod->name, name, PTR_ERR(ksym));
ret = PTR_ERR(ksym) ?: -ENOENT;
break;
@@ -2168,8 +2129,8 @@ static void set_license(struct module *mod, const char *license)
if (!license_is_gpl_compatible(license)) {
if (!test_taint(TAINT_PROPRIETARY_MODULE))
- printk(KERN_WARNING "%s: module license '%s' taints "
- "kernel.\n", mod->name, license);
+ pr_warn("%s: module license '%s' taints kernel.\n",
+ mod->name, license);
add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
LOCKDEP_NOW_UNRELIABLE);
}
@@ -2405,8 +2366,8 @@ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num)
return;
#ifdef CONFIG_DYNAMIC_DEBUG
if (ddebug_add_module(debug, num, debug->modname))
- printk(KERN_ERR "dynamic debug error adding module: %s\n",
- debug->modname);
+ pr_err("dynamic debug error adding module: %s\n",
+ debug->modname);
#endif
}
@@ -2619,8 +2580,7 @@ static int rewrite_section_headers(struct load_info *info, int flags)
Elf_Shdr *shdr = &info->sechdrs[i];
if (shdr->sh_type != SHT_NOBITS
&& info->len < shdr->sh_offset + shdr->sh_size) {
- printk(KERN_ERR "Module len %lu truncated\n",
- info->len);
+ pr_err("Module len %lu truncated\n", info->len);
return -ENOEXEC;
}
@@ -2682,15 +2642,14 @@ static struct module *setup_load_info(struct load_info *info, int flags)
info->index.mod = find_sec(info, ".gnu.linkonce.this_module");
if (!info->index.mod) {
- printk(KERN_WARNING "No module found in object\n");
+ pr_warn("No module found in object\n");
return ERR_PTR(-ENOEXEC);
}
/* This is temporary: point mod into copy of data. */
mod = (void *)info->sechdrs[info->index.mod].sh_addr;
if (info->index.sym == 0) {
- printk(KERN_WARNING "%s: module has no symbols (stripped?)\n",
- mod->name);
+ pr_warn("%s: module has no symbols (stripped?)\n", mod->name);
return ERR_PTR(-ENOEXEC);
}
@@ -2717,7 +2676,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
if (err)
return err;
} else if (!same_magic(modmagic, vermagic, info->index.vers)) {
- printk(KERN_ERR "%s: version magic '%s' should be '%s'\n",
+ pr_err("%s: version magic '%s' should be '%s'\n",
mod->name, modmagic, vermagic);
return -ENOEXEC;
}
@@ -2727,9 +2686,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
if (get_modinfo(info, "staging")) {
add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
- printk(KERN_WARNING "%s: module is from the staging directory,"
- " the quality is unknown, you have been warned.\n",
- mod->name);
+ pr_warn("%s: module is from the staging directory, the quality "
+ "is unknown, you have been warned.\n", mod->name);
}
/* Set up license info based on the info section */
@@ -2738,7 +2696,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
return 0;
}
-static void find_module_sections(struct module *mod, struct load_info *info)
+static int find_module_sections(struct module *mod, struct load_info *info)
{
mod->kp = section_objs(info, "__param",
sizeof(*mod->kp), &mod->num_kp);
@@ -2768,6 +2726,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
#ifdef CONFIG_CONSTRUCTORS
mod->ctors = section_objs(info, ".ctors",
sizeof(*mod->ctors), &mod->num_ctors);
+ if (!mod->ctors)
+ mod->ctors = section_objs(info, ".init_array",
+ sizeof(*mod->ctors), &mod->num_ctors);
+ else if (find_sec(info, ".init_array")) {
+ /*
+ * This shouldn't happen with same compiler and binutils
+ * building all parts of the module.
+ */
+ printk(KERN_WARNING "%s: has both .ctors and .init_array.\n",
+ mod->name);
+ return -EINVAL;
+ }
#endif
#ifdef CONFIG_TRACEPOINTS
@@ -2801,11 +2771,12 @@ static void find_module_sections(struct module *mod, struct load_info *info)
sizeof(*mod->extable), &mod->num_exentries);
if (section_addr(info, "__obsparm"))
- printk(KERN_WARNING "%s: Ignoring obsolete parameters\n",
- mod->name);
+ pr_warn("%s: Ignoring obsolete parameters\n", mod->name);
info->debug = section_objs(info, "__verbose",
sizeof(*info->debug), &info->num_debug);
+
+ return 0;
}
static int move_module(struct module *mod, struct load_info *info)
@@ -3078,11 +3049,10 @@ static int do_init_module(struct module *mod)
return ret;
}
if (ret > 0) {
- printk(KERN_WARNING
-"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n"
-"%s: loading module anyway...\n",
- __func__, mod->name, ret,
- __func__);
+ pr_warn("%s: '%s'->init suspiciously returned %d, it should "
+ "follow 0/-E convention\n"
+ "%s: loading module anyway...\n",
+ __func__, mod->name, ret, __func__);
dump_stack();
}
@@ -3205,10 +3175,8 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname)
{
/* Check for magic 'dyndbg' arg */
int ret = ddebug_dyndbg_module_param_cb(param, val, modname);
- if (ret != 0) {
- printk(KERN_WARNING "%s: unknown parameter '%s' ignored\n",
- modname, param);
- }
+ if (ret != 0)
+ pr_warn("%s: unknown parameter '%s' ignored\n", modname, param);
return 0;
}
@@ -3243,10 +3211,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
#ifdef CONFIG_MODULE_SIG
mod->sig_ok = info->sig_ok;
if (!mod->sig_ok) {
- printk_once(KERN_NOTICE
- "%s: module verification failed: signature and/or"
- " required key missing - tainting kernel\n",
- mod->name);
+ pr_notice_once("%s: module verification failed: signature "
+ "and/or required key missing - tainting "
+ "kernel\n", mod->name);
add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK);
}
#endif
@@ -3263,7 +3230,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
/* Now we've got everything in the final locations, we can
* find optional sections. */
- find_module_sections(mod, info);
+ err = find_module_sections(mod, info);
+ if (err)
+ goto free_unload;
err = check_module_license_and_versions(mod);
if (err)
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index f2970bddc5ea..be5b8fac4bd0 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -14,6 +14,7 @@
#include <crypto/public_key.h>
#include <crypto/hash.h>
#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
#include "module-internal.h"
/*
@@ -28,7 +29,7 @@
*/
struct module_signature {
u8 algo; /* Public-key crypto algorithm [enum pkey_algo] */
- u8 hash; /* Digest algorithm [enum pkey_hash_algo] */
+ u8 hash; /* Digest algorithm [enum hash_algo] */
u8 id_type; /* Key identifier type [enum pkey_id_type] */
u8 signer_len; /* Length of signer's name */
u8 key_id_len; /* Length of key identifier */
@@ -39,7 +40,7 @@ struct module_signature {
/*
* Digest the module contents.
*/
-static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
+static struct public_key_signature *mod_make_digest(enum hash_algo hash,
const void *mod,
unsigned long modlen)
{
@@ -54,7 +55,7 @@ static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
/* Allocate the hashing algorithm we're going to need and find out how
* big the hash operational data will be.
*/
- tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0);
+ tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0);
if (IS_ERR(tfm))
return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm);
@@ -157,7 +158,7 @@ static struct key *request_asymmetric_key(const char *signer, size_t signer_len,
pr_debug("Look up: \"%s\"\n", id);
- key = keyring_search(make_key_ref(modsign_keyring, 1),
+ key = keyring_search(make_key_ref(system_trusted_keyring, 1),
&key_type_asymmetric, id);
if (IS_ERR(key))
pr_warn("Request for unknown module key '%s' err %ld\n",
@@ -217,7 +218,7 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
return -ENOPKG;
if (ms.hash >= PKEY_HASH__LAST ||
- !pkey_hash_algo[ms.hash])
+ !hash_algo_name[ms.hash])
return -ENOPKG;
key = request_asymmetric_key(sig, ms.signer_len,
diff --git a/kernel/padata.c b/kernel/padata.c
index 07af2c95dcfe..2abd25d79cc8 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -46,6 +46,7 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
static int padata_cpu_hash(struct parallel_data *pd)
{
+ unsigned int seq_nr;
int cpu_index;
/*
@@ -53,10 +54,8 @@ static int padata_cpu_hash(struct parallel_data *pd)
* seq_nr mod. number of cpus in use.
*/
- spin_lock(&pd->seq_lock);
- cpu_index = pd->seq_nr % cpumask_weight(pd->cpumask.pcpu);
- pd->seq_nr++;
- spin_unlock(&pd->seq_lock);
+ seq_nr = atomic_inc_return(&pd->seq_nr);
+ cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu);
return padata_index_to_cpu(pd, cpu_index);
}
@@ -429,7 +428,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
padata_init_pqueues(pd);
padata_init_squeues(pd);
setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
- pd->seq_nr = 0;
+ atomic_set(&pd->seq_nr, -1);
atomic_set(&pd->reorder_objects, 0);
atomic_set(&pd->refcnt, 0);
pd->pinst = pinst;
diff --git a/kernel/panic.c b/kernel/panic.c
index b6c482ccc5db..6d6300375090 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
@@ -233,7 +233,7 @@ static const struct tnt tnts[] = {
*/
const char *print_tainted(void)
{
- static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ") + 1];
+ static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ")];
if (tainted_mask) {
char *s;
diff --git a/kernel/params.c b/kernel/params.c
index c00d5b502aa4..b00142e7f3ba 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -227,17 +227,10 @@ int parse_args(const char *doing,
}
/* Lazy bastard, eh? */
-#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \
+#define STANDARD_PARAM_DEF(name, type, format, strtolfn) \
int param_set_##name(const char *val, const struct kernel_param *kp) \
{ \
- tmptype l; \
- int ret; \
- \
- ret = strtolfn(val, 0, &l); \
- if (ret < 0 || ((type)l != l)) \
- return ret < 0 ? ret : -EINVAL; \
- *((type *)kp->arg) = l; \
- return 0; \
+ return strtolfn(val, 0, (type *)kp->arg); \
} \
int param_get_##name(char *buffer, const struct kernel_param *kp) \
{ \
@@ -253,13 +246,13 @@ int parse_args(const char *doing,
EXPORT_SYMBOL(param_ops_##name)
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8);
+STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16);
+STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16);
+STANDARD_PARAM_DEF(int, int, "%i", kstrtoint);
+STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint);
+STANDARD_PARAM_DEF(long, long, "%li", kstrtol);
+STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul);
int param_set_charp(const char *val, const struct kernel_param *kp)
{
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 42086551a24a..06c62de9c711 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -132,6 +132,12 @@ out:
return ERR_PTR(err);
}
+static void delayed_free_pidns(struct rcu_head *p)
+{
+ kmem_cache_free(pid_ns_cachep,
+ container_of(p, struct pid_namespace, rcu));
+}
+
static void destroy_pid_namespace(struct pid_namespace *ns)
{
int i;
@@ -140,7 +146,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
for (i = 0; i < PIDMAP_ENTRIES; i++)
kfree(ns->pidmap[i].page);
put_user_ns(ns->user_ns);
- kmem_cache_free(pid_ns_cachep, ns);
+ call_rcu(&ns->rcu, delayed_free_pidns);
}
struct pid_namespace *copy_pid_ns(unsigned long flags,
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c7f31aa272f7..3b8946416a5f 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -233,7 +233,8 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
/*
* Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
*/
static int cpu_clock_sample_group(const clockid_t which_clock,
struct task_struct *p,
@@ -260,30 +261,53 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
return 0;
}
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+ const clockid_t which_clock,
+ struct timespec *tp)
+{
+ int err = -EINVAL;
+ unsigned long long rtn;
+
+ if (CPUCLOCK_PERTHREAD(which_clock)) {
+ if (same_thread_group(tsk, current))
+ err = cpu_clock_sample(which_clock, tsk, &rtn);
+ } else {
+ unsigned long flags;
+ struct sighand_struct *sighand;
+
+ /*
+ * while_each_thread() is not yet entirely RCU safe,
+ * keep locking the group while sampling process
+ * clock for now.
+ */
+ sighand = lock_task_sighand(tsk, &flags);
+ if (!sighand)
+ return err;
+
+ if (tsk == current || thread_group_leader(tsk))
+ err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+ unlock_task_sighand(tsk, &flags);
+ }
+
+ if (!err)
+ sample_to_timespec(which_clock, rtn, tp);
+
+ return err;
+}
+
static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
{
const pid_t pid = CPUCLOCK_PID(which_clock);
- int error = -EINVAL;
- unsigned long long rtn;
+ int err = -EINVAL;
if (pid == 0) {
/*
* Special case constant value for our own clocks.
* We don't have to do any lookup to find ourselves.
*/
- if (CPUCLOCK_PERTHREAD(which_clock)) {
- /*
- * Sampling just ourselves we can do with no locking.
- */
- error = cpu_clock_sample(which_clock,
- current, &rtn);
- } else {
- read_lock(&tasklist_lock);
- error = cpu_clock_sample_group(which_clock,
- current, &rtn);
- read_unlock(&tasklist_lock);
- }
+ err = posix_cpu_clock_get_task(current, which_clock, tp);
} else {
/*
* Find the given PID, and validate that the caller
@@ -292,29 +316,12 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
struct task_struct *p;
rcu_read_lock();
p = find_task_by_vpid(pid);
- if (p) {
- if (CPUCLOCK_PERTHREAD(which_clock)) {
- if (same_thread_group(p, current)) {
- error = cpu_clock_sample(which_clock,
- p, &rtn);
- }
- } else {
- read_lock(&tasklist_lock);
- if (thread_group_leader(p) && p->sighand) {
- error =
- cpu_clock_sample_group(which_clock,
- p, &rtn);
- }
- read_unlock(&tasklist_lock);
- }
- }
+ if (p)
+ err = posix_cpu_clock_get_task(p, which_clock, tp);
rcu_read_unlock();
}
- if (error)
- return error;
- sample_to_timespec(which_clock, rtn, tp);
- return 0;
+ return err;
}
@@ -371,36 +378,40 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
*/
static int posix_cpu_timer_del(struct k_itimer *timer)
{
- struct task_struct *p = timer->it.cpu.task;
int ret = 0;
+ unsigned long flags;
+ struct sighand_struct *sighand;
+ struct task_struct *p = timer->it.cpu.task;
- if (likely(p != NULL)) {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
- /*
- * We raced with the reaping of the task.
- * The deletion should have cleared us off the list.
- */
- BUG_ON(!list_empty(&timer->it.cpu.entry));
- } else {
- spin_lock(&p->sighand->siglock);
- if (timer->it.cpu.firing)
- ret = TIMER_RETRY;
- else
- list_del(&timer->it.cpu.entry);
- spin_unlock(&p->sighand->siglock);
- }
- read_unlock(&tasklist_lock);
+ WARN_ON_ONCE(p == NULL);
- if (!ret)
- put_task_struct(p);
+ /*
+ * Protect against sighand release/switch in exit/exec and process/
+ * thread timer list entry concurrent read/writes.
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
+ /*
+ * We raced with the reaping of the task.
+ * The deletion should have cleared us off the list.
+ */
+ WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+ } else {
+ if (timer->it.cpu.firing)
+ ret = TIMER_RETRY;
+ else
+ list_del(&timer->it.cpu.entry);
+
+ unlock_task_sighand(p, &flags);
}
+ if (!ret)
+ put_task_struct(p);
+
return ret;
}
-static void cleanup_timers_list(struct list_head *head,
- unsigned long long curr)
+static void cleanup_timers_list(struct list_head *head)
{
struct cpu_timer_list *timer, *next;
@@ -414,16 +425,11 @@ static void cleanup_timers_list(struct list_head *head,
* time for later timer_gettime calls to return.
* This must be called with the siglock held.
*/
-static void cleanup_timers(struct list_head *head,
- cputime_t utime, cputime_t stime,
- unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
{
-
- cputime_t ptime = utime + stime;
-
- cleanup_timers_list(head, cputime_to_expires(ptime));
- cleanup_timers_list(++head, cputime_to_expires(utime));
- cleanup_timers_list(++head, sum_exec_runtime);
+ cleanup_timers_list(head);
+ cleanup_timers_list(++head);
+ cleanup_timers_list(++head);
}
/*
@@ -433,41 +439,14 @@ static void cleanup_timers(struct list_head *head,
*/
void posix_cpu_timers_exit(struct task_struct *tsk)
{
- cputime_t utime, stime;
-
add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
sizeof(unsigned long long));
- task_cputime(tsk, &utime, &stime);
- cleanup_timers(tsk->cpu_timers,
- utime, stime, tsk->se.sum_exec_runtime);
+ cleanup_timers(tsk->cpu_timers);
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
- struct signal_struct *const sig = tsk->signal;
- cputime_t utime, stime;
-
- task_cputime(tsk, &utime, &stime);
- cleanup_timers(tsk->signal->cpu_timers,
- utime + sig->utime, stime + sig->stime,
- tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
-}
-
-static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
-{
- struct cpu_timer_list *timer = &itimer->it.cpu;
-
- /*
- * That's all for this thread or process.
- * We leave our residual in expires to be reported.
- */
- put_task_struct(timer->task);
- timer->task = NULL;
- if (timer->expires < now) {
- timer->expires = 0;
- } else {
- timer->expires -= now;
- }
+ cleanup_timers(tsk->signal->cpu_timers);
}
static inline int expires_gt(cputime_t expires, cputime_t new_exp)
@@ -477,8 +456,7 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
/*
* Insert the timer on the appropriate list before any timers that
- * expire later. This must be called with the tasklist_lock held
- * for reading, interrupts disabled and p->sighand->siglock taken.
+ * expire later. This must be called with the sighand lock held.
*/
static void arm_timer(struct k_itimer *timer)
{
@@ -569,7 +547,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
/*
* Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
*/
static int cpu_timer_sample_group(const clockid_t which_clock,
struct task_struct *p,
@@ -608,7 +587,8 @@ static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
*/
static void posix_cpu_timer_kick_nohz(void)
{
- schedule_work(&nohz_kick_work);
+ if (context_tracking_is_enabled())
+ schedule_work(&nohz_kick_work);
}
bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
@@ -631,43 +611,39 @@ static inline void posix_cpu_timer_kick_nohz(void) { }
* If we return TIMER_RETRY, it's necessary to release the timer's lock
* and try again. (This happens when the timer is in the middle of firing.)
*/
-static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
struct itimerspec *new, struct itimerspec *old)
{
+ unsigned long flags;
+ struct sighand_struct *sighand;
struct task_struct *p = timer->it.cpu.task;
unsigned long long old_expires, new_expires, old_incr, val;
int ret;
- if (unlikely(p == NULL)) {
- /*
- * Timer refers to a dead task's clock.
- */
- return -ESRCH;
- }
+ WARN_ON_ONCE(p == NULL);
new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
- read_lock(&tasklist_lock);
/*
- * We need the tasklist_lock to protect against reaping that
- * clears p->sighand. If p has just been reaped, we can no
+ * Protect against sighand release/switch in exit/exec and p->cpu_timers
+ * and p->signal->cpu_timers read/write in arm_timer()
+ */
+ sighand = lock_task_sighand(p, &flags);
+ /*
+ * If p has just been reaped, we can no
* longer get any information about it at all.
*/
- if (unlikely(p->sighand == NULL)) {
- read_unlock(&tasklist_lock);
- put_task_struct(p);
- timer->it.cpu.task = NULL;
+ if (unlikely(sighand == NULL)) {
return -ESRCH;
}
/*
* Disarm any old timer after extracting its expiry time.
*/
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
ret = 0;
old_incr = timer->it.cpu.incr;
- spin_lock(&p->sighand->siglock);
old_expires = timer->it.cpu.expires;
if (unlikely(timer->it.cpu.firing)) {
timer->it.cpu.firing = -1;
@@ -724,12 +700,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
* disable this firing since we are already reporting
* it as an overrun (thanks to bump_cpu_timer above).
*/
- spin_unlock(&p->sighand->siglock);
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(p, &flags);
goto out;
}
- if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+ if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
new_expires += val;
}
@@ -743,9 +718,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
arm_timer(timer);
}
- spin_unlock(&p->sighand->siglock);
- read_unlock(&tasklist_lock);
-
+ unlock_task_sighand(p, &flags);
/*
* Install the new reload setting, and
* set up the signal and overrun bookkeeping.
@@ -787,7 +760,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
unsigned long long now;
struct task_struct *p = timer->it.cpu.task;
- int clear_dead;
+
+ WARN_ON_ONCE(p == NULL);
/*
* Easy part: convert the reload time.
@@ -800,52 +774,34 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
return;
}
- if (unlikely(p == NULL)) {
- /*
- * This task already died and the timer will never fire.
- * In this case, expires is actually the dead value.
- */
- dead:
- sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
- &itp->it_value);
- return;
- }
-
/*
* Sample the clock to take the difference with the expiry time.
*/
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
cpu_clock_sample(timer->it_clock, p, &now);
- clear_dead = p->exit_state;
} else {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
+ struct sighand_struct *sighand;
+ unsigned long flags;
+
+ /*
+ * Protect against sighand release/switch in exit/exec and
+ * also make timer sampling safe if it ends up calling
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
/*
* The process has been reaped.
* We can't even collect a sample any more.
* Call the timer disarmed, nothing else to do.
*/
- put_task_struct(p);
- timer->it.cpu.task = NULL;
timer->it.cpu.expires = 0;
- read_unlock(&tasklist_lock);
- goto dead;
+ sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+ &itp->it_value);
} else {
cpu_timer_sample_group(timer->it_clock, p, &now);
- clear_dead = (unlikely(p->exit_state) &&
- thread_group_empty(p));
+ unlock_task_sighand(p, &flags);
}
- read_unlock(&tasklist_lock);
- }
-
- if (unlikely(clear_dead)) {
- /*
- * We've noticed that the thread is dead, but
- * not yet reaped. Take this opportunity to
- * drop our task ref.
- */
- clear_dead_task(timer, now);
- goto dead;
}
if (now < timer->it.cpu.expires) {
@@ -1059,14 +1015,12 @@ static void check_process_timers(struct task_struct *tsk,
*/
void posix_cpu_timer_schedule(struct k_itimer *timer)
{
+ struct sighand_struct *sighand;
+ unsigned long flags;
struct task_struct *p = timer->it.cpu.task;
unsigned long long now;
- if (unlikely(p == NULL))
- /*
- * The task was cleaned up already, no future firings.
- */
- goto out;
+ WARN_ON_ONCE(p == NULL);
/*
* Fetch the current sample and update the timer's expiry time.
@@ -1074,49 +1028,45 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
cpu_clock_sample(timer->it_clock, p, &now);
bump_cpu_timer(timer, now);
- if (unlikely(p->exit_state)) {
- clear_dead_task(timer, now);
+ if (unlikely(p->exit_state))
+ goto out;
+
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (!sighand)
goto out;
- }
- read_lock(&tasklist_lock); /* arm_timer needs it. */
- spin_lock(&p->sighand->siglock);
} else {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
+ /*
+ * Protect arm_timer() and timer sampling in case of call to
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
/*
* The process has been reaped.
* We can't even collect a sample any more.
*/
- put_task_struct(p);
- timer->it.cpu.task = p = NULL;
timer->it.cpu.expires = 0;
- goto out_unlock;
+ goto out;
} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
- /*
- * We've noticed that the thread is dead, but
- * not yet reaped. Take this opportunity to
- * drop our task ref.
- */
- cpu_timer_sample_group(timer->it_clock, p, &now);
- clear_dead_task(timer, now);
- goto out_unlock;
+ unlock_task_sighand(p, &flags);
+ /* Optimizations: if the process is dying, no need to rearm */
+ goto out;
}
- spin_lock(&p->sighand->siglock);
cpu_timer_sample_group(timer->it_clock, p, &now);
bump_cpu_timer(timer, now);
- /* Leave the tasklist_lock locked for the call below. */
+ /* Leave the sighand locked for the call below. */
}
/*
* Now re-arm for the new expiry time.
*/
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
arm_timer(timer);
- spin_unlock(&p->sighand->siglock);
-
-out_unlock:
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(p, &flags);
+ /* Kick full dynticks CPUs in case they need to tick on the new timer */
+ posix_cpu_timer_kick_nohz();
out:
timer->it_overrun_last = timer->it_overrun;
timer->it_overrun = -1;
@@ -1200,7 +1150,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
struct k_itimer *timer, *next;
unsigned long flags;
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
/*
* The fast path checks that there are no expired thread or thread
@@ -1256,13 +1206,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
cpu_timer_fire(timer);
spin_unlock(&timer->it_lock);
}
-
- /*
- * In case some timers were rescheduled after the queue got emptied,
- * wake up full dynticks CPUs.
- */
- if (tsk->signal->cputimer.running)
- posix_cpu_timer_kick_nohz();
}
/*
@@ -1274,7 +1217,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
{
unsigned long long now;
- BUG_ON(clock_idx == CPUCLOCK_SCHED);
+ WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
if (oldval) {
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index d444c4e834f4..2fac9cc79b3d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -178,6 +178,22 @@ config PM_SLEEP_DEBUG
def_bool y
depends on PM_DEBUG && PM_SLEEP
+config DPM_WATCHDOG
+ bool "Device suspend/resume watchdog"
+ depends on PM_DEBUG && PSTORE
+ ---help---
+ Sets up a watchdog timer to capture drivers that are
+ locked up attempting to suspend/resume a device.
+ A detected lockup causes system panic with message
+ captured in pstore device for inspection in subsequent
+ boot session.
+
+config DPM_WATCHDOG_TIMEOUT
+ int "Watchdog timeout in seconds"
+ range 1 120
+ default 12
+ depends on DPM_WATCHDOG
+
config PM_TRACE
bool
help
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 463aa6736751..eacb8bd8cab4 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -81,6 +81,7 @@ void pm_vt_switch_unregister(struct device *dev)
list_for_each_entry(tmp, &pm_vt_switch_list, head) {
if (tmp->dev == dev) {
list_del(&tmp->head);
+ kfree(tmp);
break;
}
}
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index a394297f8b2f..8dff9b48075a 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -558,30 +558,12 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
if (count == sizeof(s32)) {
if (copy_from_user(&value, buf, sizeof(s32)))
return -EFAULT;
- } else if (count <= 11) { /* ASCII perhaps? */
- char ascii_value[11];
- unsigned long int ulval;
+ } else {
int ret;
- if (copy_from_user(ascii_value, buf, count))
- return -EFAULT;
-
- if (count > 10) {
- if (ascii_value[10] == '\n')
- ascii_value[10] = '\0';
- else
- return -EINVAL;
- } else {
- ascii_value[count] = '\0';
- }
- ret = kstrtoul(ascii_value, 16, &ulval);
- if (ret) {
- pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret);
- return -EINVAL;
- }
- value = (s32)lower_32_bits(ulval);
- } else {
- return -EINVAL;
+ ret = kstrtos32_from_user(buf, count, 16, &value);
+ if (ret)
+ return ret;
}
req = filp->private_data;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 98c3b34a4cff..d9f61a145802 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -637,7 +637,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
BUG_ON(!region);
} else
/* This allocation cannot fail */
- region = alloc_bootmem(sizeof(struct nosave_region));
+ region = memblock_virt_alloc(sizeof(struct nosave_region), 0);
region->start_pfn = start_pfn;
region->end_pfn = end_pfn;
list_add_tail(&region->list, &nosave_regions);
@@ -792,7 +792,8 @@ void free_basic_memory_bitmaps(void)
{
struct memory_bitmap *bm1, *bm2;
- BUG_ON(!(forbidden_pages_map && free_pages_map));
+ if (WARN_ON(!(forbidden_pages_map && free_pages_map)))
+ return;
bm1 = forbidden_pages_map;
bm2 = free_pages_map;
@@ -1402,7 +1403,11 @@ int hibernate_preallocate_memory(void)
* highmem and non-highmem zones separately.
*/
pages_highmem = preallocate_image_highmem(highmem / 2);
- alloc = (count - max_size) - pages_highmem;
+ alloc = count - max_size;
+ if (alloc > pages_highmem)
+ alloc -= pages_highmem;
+ else
+ alloc = 0;
pages = preallocate_image_memory(alloc, avail_normal);
if (pages < alloc) {
/* We have exhausted non-highmem pages, try highmem. */
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 957f06164ad1..98d357584cd6 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -36,9 +36,9 @@ static struct snapshot_data {
struct snapshot_handle handle;
int swap;
int mode;
- char frozen;
- char ready;
- char platform_support;
+ bool frozen;
+ bool ready;
+ bool platform_support;
bool free_bitmaps;
} snapshot_state;
@@ -70,6 +70,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
data->swap = swsusp_resume_device ?
swap_type_of(swsusp_resume_device, 0, NULL) : -1;
data->mode = O_RDONLY;
+ data->free_bitmaps = false;
error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
if (error)
pm_notifier_call_chain(PM_POST_HIBERNATION);
@@ -93,9 +94,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
if (error)
atomic_inc(&snapshot_device_available);
- data->frozen = 0;
- data->ready = 0;
- data->platform_support = 0;
+ data->frozen = false;
+ data->ready = false;
+ data->platform_support = false;
Unlock:
unlock_system_sleep();
@@ -229,7 +230,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
if (error)
thaw_processes();
else
- data->frozen = 1;
+ data->frozen = true;
break;
@@ -240,7 +241,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
free_basic_memory_bitmaps();
data->free_bitmaps = false;
thaw_processes();
- data->frozen = 0;
+ data->frozen = false;
break;
case SNAPSHOT_CREATE_IMAGE:
@@ -270,7 +271,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
case SNAPSHOT_FREE:
swsusp_free();
memset(&data->handle, 0, sizeof(struct snapshot_handle));
- data->ready = 0;
+ data->ready = false;
/*
* It is necessary to thaw kernel threads here, because
* SNAPSHOT_CREATE_IMAGE may be invoked directly after
@@ -334,7 +335,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
* PM_HIBERNATION_PREPARE
*/
error = suspend_devices_and_enter(PM_SUSPEND_MEM);
- data->ready = 0;
+ data->ready = false;
break;
case SNAPSHOT_PLATFORM_SUPPORT:
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b4e8500afdb3..f8b41bddc6dc 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -705,9 +705,9 @@ const struct file_operations kmsg_fops = {
#ifdef CONFIG_KEXEC
/*
- * This appends the listed symbols to /proc/vmcoreinfo
+ * This appends the listed symbols to /proc/vmcore
*
- * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to
+ * /proc/vmcore is used by various utilities, like crash and makedumpfile to
* obtain access to symbols that are otherwise very difficult to locate. These
* symbols are specifically used so that utilities can access and extract the
* dmesg log from a vmcore file after a crash.
@@ -757,14 +757,10 @@ void __init setup_log_buf(int early)
return;
if (early) {
- unsigned long mem;
-
- mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
- if (!mem)
- return;
- new_log_buf = __va(mem);
+ new_log_buf =
+ memblock_virt_alloc(new_log_buf_len, PAGE_SIZE);
} else {
- new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
+ new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, 0);
}
if (unlikely(!new_log_buf)) {
@@ -791,7 +787,7 @@ static bool __read_mostly ignore_loglevel;
static int __init ignore_loglevel_setup(char *str)
{
ignore_loglevel = 1;
- printk(KERN_INFO "debug: ignoring loglevel setting.\n");
+ pr_info("debug: ignoring loglevel setting.\n");
return 0;
}
@@ -820,9 +816,9 @@ static int __init boot_delay_setup(char *str)
pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
"HZ: %d, loops_per_msec: %llu\n",
boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
- return 1;
+ return 0;
}
-__setup("boot_delay=", boot_delay_setup);
+early_param("boot_delay", boot_delay_setup);
static void boot_delay_msec(int level)
{
@@ -2193,7 +2189,7 @@ static int __read_mostly keep_bootcon;
static int __init keep_bootcon_setup(char *str)
{
keep_bootcon = 1;
- printk(KERN_INFO "debug: skip boot console de-registration.\n");
+ pr_info("debug: skip boot console de-registration.\n");
return 0;
}
@@ -2241,7 +2237,7 @@ void register_console(struct console *newcon)
/* find the last or real console */
for_each_console(bcon) {
if (!(bcon->flags & CON_BOOT)) {
- printk(KERN_INFO "Too late to register bootconsole %s%d\n",
+ pr_info("Too late to register bootconsole %s%d\n",
newcon->name, newcon->index);
return;
}
@@ -2358,21 +2354,18 @@ void register_console(struct console *newcon)
* users know there might be something in the kernel's log buffer that
* went to the bootconsole (that they do not see on the real console)
*/
+ pr_info("%sconsole [%s%d] enabled\n",
+ (newcon->flags & CON_BOOT) ? "boot" : "" ,
+ newcon->name, newcon->index);
if (bcon &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
!keep_bootcon) {
- /* we need to iterate through twice, to make sure we print
- * everything out, before we unregister the console(s)
+ /* We need to iterate through all boot consoles, to make
+ * sure we print everything out, before we unregister them.
*/
- printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n",
- newcon->name, newcon->index);
for_each_console(bcon)
if (bcon->flags & CON_BOOT)
unregister_console(bcon);
- } else {
- printk(KERN_INFO "%sconsole [%s%d] enabled\n",
- (newcon->flags & CON_BOOT) ? "boot" : "" ,
- newcon->name, newcon->index);
}
}
EXPORT_SYMBOL(register_console);
@@ -2382,6 +2375,10 @@ int unregister_console(struct console *console)
struct console *a, *b;
int res;
+ pr_info("%sconsole [%s%d] disabled\n",
+ (console->flags & CON_BOOT) ? "boot" : "" ,
+ console->name, console->index);
+
res = _braille_unregister_console(console);
if (res)
return res;
@@ -2421,8 +2418,6 @@ static int __init printk_late_init(void)
for_each_console(con) {
if (!keep_bootcon && con->flags & CON_BOOT) {
- printk(KERN_INFO "turn off boot console %s%d\n",
- con->name, con->index);
unregister_console(con);
}
}
@@ -2449,7 +2444,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work)
if (pending & PRINTK_PENDING_SCHED) {
char *buf = __get_cpu_var(printk_sched_buf);
- printk(KERN_WARNING "[sched_delayed] %s", buf);
+ pr_warn("[sched_delayed] %s", buf);
}
if (pending & PRINTK_PENDING_WAKEUP)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index dd562e9aa2c8..1f4bcb3cc21c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -257,7 +257,8 @@ ok:
if (task->mm)
dumpable = get_dumpable(task->mm);
rcu_read_lock();
- if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+ if (dumpable != SUID_DUMP_USER &&
+ !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
rcu_read_unlock();
return -EPERM;
}
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
new file mode 100644
index 000000000000..01e9ec37a3e3
--- /dev/null
+++ b/kernel/rcu/Makefile
@@ -0,0 +1,6 @@
+obj-y += update.o srcu.o
+obj-$(CONFIG_RCU_TORTURE_TEST) += torture.o
+obj-$(CONFIG_TREE_RCU) += tree.o
+obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
+obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
+obj-$(CONFIG_TINY_RCU) += tiny.o
diff --git a/kernel/rcu.h b/kernel/rcu/rcu.h
index 77131966c4ad..79c3877e9c5b 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -96,19 +96,22 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-extern void kfree(const void *);
+void kfree(const void *);
static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
+ rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
kfree((void *)head - offset);
+ rcu_lock_release(&rcu_callback_map);
return 1;
} else {
RCU_TRACE(trace_rcu_invoke_callback(rn, head));
head->func(head);
+ rcu_lock_release(&rcu_callback_map);
return 0;
}
}
@@ -122,4 +125,11 @@ int rcu_jiffies_till_stall_check(void);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+/*
+ * Strings used in tracepoints need to be exported via the
+ * tracing system such that tools like perf and trace-cmd can
+ * translate the string address pointers to actual text.
+ */
+#define TPS(x) tracepoint_string(x)
+
#endif /* __LINUX_RCU_H */
diff --git a/kernel/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb8bfe3..3318d8284384 100644
--- a/kernel/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -363,6 +363,29 @@ static void srcu_flip(struct srcu_struct *sp)
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section. On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu(). It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
*/
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
void (*func)(struct rcu_head *head))
@@ -459,7 +482,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
* Note that it is illegal to call synchronize_srcu() from the corresponding
* SRCU read-side critical section; doing so will result in deadlock.
* However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu(). In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section. Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu(). This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
*/
void synchronize_srcu(struct srcu_struct *sp)
{
@@ -476,12 +522,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
*
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock. However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
*/
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
@@ -491,6 +533,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
*/
void srcu_barrier(struct srcu_struct *sp)
{
diff --git a/kernel/rcutiny.c b/kernel/rcu/tiny.c
index 9ed6075dc562..1254f312d024 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcu/tiny.c
@@ -35,6 +35,7 @@
#include <linux/time.h>
#include <linux/cpu.h>
#include <linux/prefetch.h>
+#include <linux/ftrace_event.h>
#ifdef CONFIG_RCU_TRACE
#include <trace/events/rcu.h>
@@ -42,7 +43,7 @@
#include "rcu.h"
-/* Forward declarations for rcutiny_plugin.h. */
+/* Forward declarations for tiny_plugin.h. */
struct rcu_ctrlblk;
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
static void rcu_process_callbacks(struct softirq_action *unused);
@@ -52,22 +53,23 @@ static void __call_rcu(struct rcu_head *head,
static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-#include "rcutiny_plugin.h"
+#include "tiny_plugin.h"
/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
static void rcu_idle_enter_common(long long newval)
{
if (newval) {
- RCU_TRACE(trace_rcu_dyntick("--=",
+ RCU_TRACE(trace_rcu_dyntick(TPS("--="),
rcu_dynticks_nesting, newval));
rcu_dynticks_nesting = newval;
return;
}
- RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval));
+ RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
+ rcu_dynticks_nesting, newval));
if (!is_idle_task(current)) {
- struct task_struct *idle = idle_task(smp_processor_id());
+ struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
- RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
+ RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
rcu_dynticks_nesting, newval));
ftrace_dump(DUMP_ALL);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -120,15 +122,15 @@ EXPORT_SYMBOL_GPL(rcu_irq_exit);
static void rcu_idle_exit_common(long long oldval)
{
if (oldval) {
- RCU_TRACE(trace_rcu_dyntick("++=",
+ RCU_TRACE(trace_rcu_dyntick(TPS("++="),
oldval, rcu_dynticks_nesting));
return;
}
- RCU_TRACE(trace_rcu_dyntick("End", oldval, rcu_dynticks_nesting));
+ RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
if (!is_idle_task(current)) {
- struct task_struct *idle = idle_task(smp_processor_id());
+ struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
- RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task",
+ RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
oldval, rcu_dynticks_nesting));
ftrace_dump(DUMP_ALL);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -174,18 +176,18 @@ void rcu_irq_enter(void)
}
EXPORT_SYMBOL_GPL(rcu_irq_enter);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
/*
* Test whether RCU thinks that the current CPU is idle.
*/
-int rcu_is_cpu_idle(void)
+bool notrace __rcu_is_watching(void)
{
- return !rcu_dynticks_nesting;
+ return rcu_dynticks_nesting;
}
-EXPORT_SYMBOL(rcu_is_cpu_idle);
+EXPORT_SYMBOL(__rcu_is_watching);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
/*
* Test whether the current CPU was interrupted from idle. Nested
@@ -273,7 +275,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
if (&rcp->rcucblist == rcp->donetail) {
RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1));
RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
- ACCESS_ONCE(rcp->rcucblist),
+ !!ACCESS_ONCE(rcp->rcucblist),
need_resched(),
is_idle_task(current),
false));
@@ -304,7 +306,8 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
RCU_TRACE(cb_count++);
}
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
- RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(),
+ RCU_TRACE(trace_rcu_batch_end(rcp->name,
+ cb_count, 0, need_resched(),
is_idle_task(current),
false));
}
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 280d06cae352..280d06cae352 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
diff --git a/kernel/rcutorture.c b/kernel/rcu/torture.c
index be63101c6175..732f8ae3086a 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcu/torture.c
@@ -52,6 +52,12 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
+MODULE_ALIAS("rcutorture");
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "rcutorture."
+
static int fqs_duration;
module_param(fqs_duration, int, 0444);
MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
@@ -133,8 +139,6 @@ MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
#define VERBOSE_PRINTK_ERRSTRING(s) \
do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
-static char printk_buf[4096];
-
static int nrealreaders;
static struct task_struct *writer_task;
static struct task_struct **fakewriter_tasks;
@@ -370,7 +374,7 @@ struct rcu_torture_ops {
void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
void (*cb_barrier)(void);
void (*fqs)(void);
- int (*stats)(char *page);
+ void (*stats)(char *page);
int irq_capable;
int can_boost;
const char *name;
@@ -572,21 +576,19 @@ static void srcu_torture_barrier(void)
srcu_barrier(&srcu_ctl);
}
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
{
- int cnt = 0;
int cpu;
int idx = srcu_ctl.completed & 0x1;
- cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+ page += sprintf(page, "%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
- cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+ page += sprintf(page, " %d(%lu,%lu)", cpu,
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
}
- cnt += sprintf(&page[cnt], "\n");
- return cnt;
+ sprintf(page, "\n");
}
static void srcu_torture_synchronize_expedited(void)
@@ -1046,10 +1048,9 @@ rcu_torture_reader(void *arg)
/*
* Create an RCU-torture statistics message in the specified buffer.
*/
-static int
+static void
rcu_torture_printk(char *page)
{
- int cnt = 0;
int cpu;
int i;
long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1065,8 +1066,8 @@ rcu_torture_printk(char *page)
if (pipesummary[i] != 0)
break;
}
- cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt],
+ page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page,
"rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
rcu_torture_current,
rcu_torture_current_version,
@@ -1074,53 +1075,52 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc),
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free));
- cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+ page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
atomic_read(&n_rcu_torture_mberror),
n_rcu_torture_boost_ktrerror,
n_rcu_torture_boost_rterror);
- cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+ page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
- cnt += sprintf(&page[cnt],
+ page += sprintf(page,
"onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
n_online_successes, n_online_attempts,
n_offline_successes, n_offline_attempts,
min_online, max_online,
min_offline, max_offline,
sum_online, sum_offline, HZ);
- cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+ page += sprintf(page, "barrier: %ld/%ld:%ld",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
n_rcu_torture_barrier_error != 0 ||
n_rcu_torture_boost_ktrerror != 0 ||
n_rcu_torture_boost_rterror != 0 ||
n_rcu_torture_boost_failure != 0 ||
i > 1) {
- cnt += sprintf(&page[cnt], "!!! ");
+ page += sprintf(page, "!!! ");
atomic_inc(&n_rcu_torture_error);
WARN_ON_ONCE(1);
}
- cnt += sprintf(&page[cnt], "Reader Pipe: ");
+ page += sprintf(page, "Reader Pipe: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Reader Batch: ");
+ page += sprintf(page, " %ld", pipesummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Reader Batch: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+ page += sprintf(page, " %ld", batchsummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Free-Block Circulation: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
- cnt += sprintf(&page[cnt], " %d",
+ page += sprintf(page, " %d",
atomic_read(&rcu_torture_wcount[i]));
}
- cnt += sprintf(&page[cnt], "\n");
+ page += sprintf(page, "\n");
if (cur_ops->stats)
- cnt += cur_ops->stats(&page[cnt]);
- return cnt;
+ cur_ops->stats(page);
}
/*
@@ -1134,10 +1134,17 @@ rcu_torture_printk(char *page)
static void
rcu_torture_stats_print(void)
{
- int cnt;
+ int size = nr_cpu_ids * 200 + 8192;
+ char *buf;
- cnt = rcu_torture_printk(printk_buf);
- pr_alert("%s", printk_buf);
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf) {
+ pr_err("rcu-torture: Out of memory, need: %d", size);
+ return;
+ }
+ rcu_torture_printk(buf);
+ pr_alert("%s", buf);
+ kfree(buf);
}
/*
@@ -1572,6 +1579,7 @@ static int rcu_torture_barrier_cbs(void *arg)
{
long myid = (long)arg;
bool lastphase = 0;
+ bool newphase;
struct rcu_head rcu;
init_rcu_head_on_stack(&rcu);
@@ -1579,10 +1587,11 @@ static int rcu_torture_barrier_cbs(void *arg)
set_user_nice(current, 19);
do {
wait_event(barrier_cbs_wq[myid],
- barrier_phase != lastphase ||
+ (newphase =
+ ACCESS_ONCE(barrier_phase)) != lastphase ||
kthread_should_stop() ||
fullstop != FULLSTOP_DONTSTOP);
- lastphase = barrier_phase;
+ lastphase = newphase;
smp_mb(); /* ensure barrier_phase load before ->call(). */
if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
break;
@@ -1619,7 +1628,7 @@ static int rcu_torture_barrier(void *arg)
if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
break;
n_barrier_attempts++;
- cur_ops->cb_barrier();
+ cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
n_rcu_torture_barrier_error++;
WARN_ON_ONCE(1);
diff --git a/kernel/rcutree.c b/kernel/rcu/tree.c
index 32618b3fe4e6..b3d116cd072d 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcu/tree.c
@@ -41,6 +41,7 @@
#include <linux/export.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
+#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
@@ -56,17 +57,16 @@
#include <linux/ftrace_event.h>
#include <linux/suspend.h>
-#include "rcutree.h"
+#include "tree.h"
#include <trace/events/rcu.h>
#include "rcu.h"
-/*
- * Strings used in tracepoints need to be exported via the
- * tracing system such that tools like perf and trace-cmd can
- * translate the string address pointers to actual text.
- */
-#define TPS(x) tracepoint_string(x)
+MODULE_ALIAS("rcutree");
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "rcutree."
/* Data structures. */
@@ -222,7 +222,7 @@ void rcu_note_context_switch(int cpu)
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
-DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
.dynticks = ATOMIC_INIT(1),
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
@@ -369,9 +369,13 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
bool user)
{
+ struct rcu_state *rsp;
+ struct rcu_data *rdp;
+
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
- struct task_struct *idle = idle_task(smp_processor_id());
+ struct task_struct *idle __maybe_unused =
+ idle_task(smp_processor_id());
trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
ftrace_dump(DUMP_ORIG);
@@ -379,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
+ for_each_rcu_flavor(rsp) {
+ rdp = this_cpu_ptr(rsp->rda);
+ do_nocb_deferred_wakeup(rdp);
+ }
rcu_prepare_for_idle(smp_processor_id());
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic_inc(); /* See above. */
@@ -407,14 +415,15 @@ static void rcu_eqs_enter(bool user)
long long oldval;
struct rcu_dynticks *rdtp;
- rdtp = &__get_cpu_var(rcu_dynticks);
+ rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
- else
+ rcu_eqs_enter_common(rdtp, oldval, user);
+ } else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_eqs_enter_common(rdtp, oldval, user);
+ }
}
/**
@@ -435,7 +444,7 @@ void rcu_idle_enter(void)
local_irq_save(flags);
rcu_eqs_enter(false);
- rcu_sysidle_enter(&__get_cpu_var(rcu_dynticks), 0);
+ rcu_sysidle_enter(this_cpu_ptr(&rcu_dynticks), 0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -478,7 +487,7 @@ void rcu_irq_exit(void)
struct rcu_dynticks *rdtp;
local_irq_save(flags);
- rdtp = &__get_cpu_var(rcu_dynticks);
+ rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting--;
WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
@@ -508,7 +517,8 @@ static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
rcu_cleanup_after_idle(smp_processor_id());
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
- struct task_struct *idle = idle_task(smp_processor_id());
+ struct task_struct *idle __maybe_unused =
+ idle_task(smp_processor_id());
trace_rcu_dyntick(TPS("Error on exit: not idle task"),
oldval, rdtp->dynticks_nesting);
@@ -528,14 +538,15 @@ static void rcu_eqs_exit(bool user)
struct rcu_dynticks *rdtp;
long long oldval;
- rdtp = &__get_cpu_var(rcu_dynticks);
+ rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(oldval < 0);
- if (oldval & DYNTICK_TASK_NEST_MASK)
+ if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
- else
+ } else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_eqs_exit_common(rdtp, oldval, user);
+ rcu_eqs_exit_common(rdtp, oldval, user);
+ }
}
/**
@@ -555,7 +566,7 @@ void rcu_idle_exit(void)
local_irq_save(flags);
rcu_eqs_exit(false);
- rcu_sysidle_exit(&__get_cpu_var(rcu_dynticks), 0);
+ rcu_sysidle_exit(this_cpu_ptr(&rcu_dynticks), 0);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
@@ -599,7 +610,7 @@ void rcu_irq_enter(void)
long long oldval;
local_irq_save(flags);
- rdtp = &__get_cpu_var(rcu_dynticks);
+ rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
@@ -620,7 +631,7 @@ void rcu_irq_enter(void)
*/
void rcu_nmi_enter(void)
{
- struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
if (rdtp->dynticks_nmi_nesting == 0 &&
(atomic_read(&rdtp->dynticks) & 0x1))
@@ -642,7 +653,7 @@ void rcu_nmi_enter(void)
*/
void rcu_nmi_exit(void)
{
- struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
if (rdtp->dynticks_nmi_nesting == 0 ||
--rdtp->dynticks_nmi_nesting != 0)
@@ -655,21 +666,34 @@ void rcu_nmi_exit(void)
}
/**
- * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
+ * __rcu_is_watching - are RCU read-side critical sections safe?
+ *
+ * Return true if RCU is watching the running CPU, which means that
+ * this CPU can safely enter RCU read-side critical sections. Unlike
+ * rcu_is_watching(), the caller of __rcu_is_watching() must have at
+ * least disabled preemption.
+ */
+bool notrace __rcu_is_watching(void)
+{
+ return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+}
+
+/**
+ * rcu_is_watching - see if RCU thinks that the current CPU is idle
*
* If the current CPU is in its idle loop and is neither in an interrupt
* or NMI handler, return true.
*/
-int rcu_is_cpu_idle(void)
+bool notrace rcu_is_watching(void)
{
int ret;
preempt_disable();
- ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
+ ret = __rcu_is_watching();
preempt_enable();
return ret;
}
-EXPORT_SYMBOL(rcu_is_cpu_idle);
+EXPORT_SYMBOL_GPL(rcu_is_watching);
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
@@ -701,9 +725,9 @@ bool rcu_lockdep_current_cpu_online(void)
bool ret;
if (in_nmi())
- return 1;
+ return true;
preempt_disable();
- rdp = &__get_cpu_var(rcu_sched_data);
+ rdp = this_cpu_ptr(&rcu_sched_data);
rnp = rdp->mynode;
ret = (rdp->grpmask & rnp->qsmaskinit) ||
!rcu_scheduler_fully_active;
@@ -723,7 +747,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
*/
static int rcu_is_cpu_rrupt_from_idle(void)
{
- return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
+ return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1;
}
/*
@@ -740,6 +764,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
}
/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
@@ -797,13 +827,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
*/
rcu_kick_nohz_cpu(rdp->cpu);
+ /*
+ * Alternatively, the CPU might be running in the kernel
+ * for an extended period of time without a quiescent state.
+ * Attempt to force the CPU through the scheduler to gain the
+ * needed quiescent state, but only if the grace period has gone
+ * on for an uncommonly long time. If there are many stuck CPUs,
+ * we will beat on the first one until it gets unstuck, then move
+ * to the next. Only do this for the primary flavor of RCU.
+ */
+ if (rdp->rsp == rcu_state &&
+ ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+ rdp->rsp->jiffies_resched += 5;
+ resched_cpu(rdp->cpu);
+ }
+
return 0;
}
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
- rsp->gp_start = jiffies;
- rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+ unsigned long j = ACCESS_ONCE(jiffies);
+ unsigned long j1;
+
+ rsp->gp_start = j;
+ smp_wmb(); /* Record start time before stall time. */
+ j1 = rcu_jiffies_till_stall_check();
+ rsp->jiffies_stall = j + j1;
+ rsp->jiffies_resched = j + j1 / 2;
}
/*
@@ -898,6 +949,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
force_quiescent_state(rsp); /* Kick them all. */
}
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
static void print_cpu_stall(struct rcu_state *rsp)
{
int cpu;
@@ -927,22 +984,60 @@ static void print_cpu_stall(struct rcu_state *rsp)
3 * rcu_jiffies_till_stall_check() + 3;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- set_need_resched(); /* kick ourselves to get things going. */
+ /*
+ * Attempt to revive the RCU machinery by forcing a context switch.
+ *
+ * A context switch would normally allow the RCU state machine to make
+ * progress and it could be we're stuck in kernel space without context
+ * switches for an entirely unreasonable amount of time.
+ */
+ resched_cpu(smp_processor_id());
}
static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
+ unsigned long completed;
+ unsigned long gpnum;
+ unsigned long gps;
unsigned long j;
unsigned long js;
struct rcu_node *rnp;
- if (rcu_cpu_stall_suppress)
+ if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
return;
j = ACCESS_ONCE(jiffies);
+
+ /*
+ * Lots of memory barriers to reject false positives.
+ *
+ * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
+ * then rsp->gp_start, and finally rsp->completed. These values
+ * are updated in the opposite order with memory barriers (or
+ * equivalent) during grace-period initialization and cleanup.
+ * Now, a false positive can occur if we get an new value of
+ * rsp->gp_start and a old value of rsp->jiffies_stall. But given
+ * the memory barriers, the only way that this can happen is if one
+ * grace period ends and another starts between these two fetches.
+ * Detect this by comparing rsp->completed with the previous fetch
+ * from rsp->gpnum.
+ *
+ * Given this check, comparisons of jiffies, rsp->jiffies_stall,
+ * and rsp->gp_start suffice to forestall false positives.
+ */
+ gpnum = ACCESS_ONCE(rsp->gpnum);
+ smp_rmb(); /* Pick up ->gpnum first... */
js = ACCESS_ONCE(rsp->jiffies_stall);
+ smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+ gps = ACCESS_ONCE(rsp->gp_start);
+ smp_rmb(); /* ...and finally ->gp_start before ->completed. */
+ completed = ACCESS_ONCE(rsp->completed);
+ if (ULONG_CMP_GE(completed, gpnum) ||
+ ULONG_CMP_LT(j, js) ||
+ ULONG_CMP_GE(gps, js))
+ return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
if (rcu_gp_in_progress(rsp) &&
- (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
+ (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
@@ -1071,8 +1166,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
* hold it, acquire the root rcu_node structure's lock in order to
* start one (if needed).
*/
- if (rnp != rnp_root)
+ if (rnp != rnp_root) {
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
+ }
/*
* Get a new grace-period number. If there really is no grace
@@ -1292,12 +1389,13 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
local_irq_restore(flags);
return;
}
+ smp_mb__after_unlock_lock();
__note_gp_changes(rsp, rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
- * Initialize a new grace period.
+ * Initialize a new grace period. Return 0 if no grace period required.
*/
static int rcu_gp_init(struct rcu_state *rsp)
{
@@ -1306,18 +1404,28 @@ static int rcu_gp_init(struct rcu_state *rsp)
rcu_bind_gp_kthread();
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
+ if (rsp->gp_flags == 0) {
+ /* Spurious wakeup, tell caller to go back to sleep. */
+ raw_spin_unlock_irq(&rnp->lock);
+ return 0;
+ }
rsp->gp_flags = 0; /* Clear all flags: New grace period. */
- if (rcu_gp_in_progress(rsp)) {
- /* Grace period already in progress, don't start another. */
+ if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
+ /*
+ * Grace period already in progress, don't start another.
+ * Not supposed to be able to happen.
+ */
raw_spin_unlock_irq(&rnp->lock);
return 0;
}
/* Advance to a new grace period and initialize state. */
+ record_gp_stall_check_time(rsp);
+ smp_wmb(); /* Record GP times before starting GP. */
rsp->gpnum++;
trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
- record_gp_stall_check_time(rsp);
raw_spin_unlock_irq(&rnp->lock);
/* Exclude any concurrent CPU-hotplug operations. */
@@ -1338,6 +1446,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
@@ -1366,7 +1475,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
/*
* Do one round of quiescent-state forcing.
*/
-int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
+static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
{
int fqs_state = fqs_state_in;
bool isidle = false;
@@ -1392,6 +1501,7 @@ int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
/* Clear flag to prevent immediate re-entry. */
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
raw_spin_unlock_irq(&rnp->lock);
}
@@ -1409,6 +1519,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
struct rcu_node *rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
if (gp_duration > rsp->gp_max)
rsp->gp_max = gp_duration;
@@ -1434,16 +1545,19 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
ACCESS_ONCE(rnp->completed) = rsp->gpnum;
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
__note_gp_changes(rsp, rnp, rdp);
+ /* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rcu_nocb_gp_set(rnp, nocb);
rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1451,8 +1565,12 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
rsp->fqs_state = RCU_GP_IDLE;
rdp = this_cpu_ptr(rsp->rda);
rcu_advance_cbs(rsp, rnp, rdp); /* Reduce false positives below. */
- if (cpu_needs_another_gp(rsp, rdp))
- rsp->gp_flags = 1;
+ if (cpu_needs_another_gp(rsp, rdp)) {
+ rsp->gp_flags = RCU_GP_FLAG_INIT;
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("newreq"));
+ }
raw_spin_unlock_irq(&rnp->lock);
}
@@ -1462,6 +1580,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
static int __noreturn rcu_gp_kthread(void *arg)
{
int fqs_state;
+ int gf;
unsigned long j;
int ret;
struct rcu_state *rsp = arg;
@@ -1471,14 +1590,20 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Handle grace-period start. */
for (;;) {
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("reqwait"));
wait_event_interruptible(rsp->gp_wq,
- rsp->gp_flags &
+ ACCESS_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
- if ((rsp->gp_flags & RCU_GP_FLAG_INIT) &&
- rcu_gp_init(rsp))
+ /* Locking provides needed memory barrier. */
+ if (rcu_gp_init(rsp))
break;
cond_resched();
flush_signals(current);
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
@@ -1488,25 +1613,42 @@ static int __noreturn rcu_gp_kthread(void *arg)
j = HZ;
jiffies_till_first_fqs = HZ;
}
+ ret = 0;
for (;;) {
- rsp->jiffies_force_qs = jiffies + j;
+ if (!ret)
+ rsp->jiffies_force_qs = jiffies + j;
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("fqswait"));
ret = wait_event_interruptible_timeout(rsp->gp_wq,
- (rsp->gp_flags & RCU_GP_FLAG_FQS) ||
+ ((gf = ACCESS_ONCE(rsp->gp_flags)) &
+ RCU_GP_FLAG_FQS) ||
(!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp)),
j);
+ /* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
- if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) {
+ if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
+ (gf & RCU_GP_FLAG_FQS)) {
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("fqsstart"));
fqs_state = rcu_gp_fqs(rsp, fqs_state);
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("fqsend"));
cond_resched();
} else {
/* Deal with stray signal. */
cond_resched();
flush_signals(current);
+ trace_rcu_grace_period(rsp->name,
+ ACCESS_ONCE(rsp->gpnum),
+ TPS("fqswaitsig"));
}
j = jiffies_till_next_fqs;
if (j > HZ) {
@@ -1554,6 +1696,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
return;
}
rsp->gp_flags = RCU_GP_FLAG_INIT;
+ trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+ TPS("newreq"));
/*
* We can't do wakeups while holding the rnp->lock, as that
@@ -1650,6 +1794,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
WARN_ON_ONCE(rnp_c->qsmask);
}
@@ -1679,6 +1824,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
rnp->completed == rnp->gpnum) {
@@ -1802,13 +1948,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
* Adopt the RCU callbacks from the specified rcu_state structure's
* orphanage. The caller must hold the ->orphan_lock.
*/
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
int i;
struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
- if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+ if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
@@ -1887,12 +2033,13 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
- rcu_adopt_orphan_cbs(rsp);
+ rcu_adopt_orphan_cbs(rsp, flags);
/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
mask = rdp->grpmask; /* rnp->grplo is constant. */
do {
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
if (rnp != rdp->mynode)
@@ -2103,6 +2250,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
cond_resched();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (!rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
@@ -2132,6 +2280,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
rnp = rcu_get_root(rsp);
if (rnp->qsmask == 0) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
}
}
@@ -2164,6 +2313,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave(&rnp_old->lock, flags);
+ smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
rsp->n_force_qs_lh++;
@@ -2204,6 +2354,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
/* If there are callbacks ready, invoke them. */
if (cpu_has_callbacks_ready_to_invoke(rdp))
invoke_rcu_callbacks(rsp, rdp);
+
+ /* Do any needed deferred wakeups of rcuo kthreads. */
+ do_nocb_deferred_wakeup(rdp);
}
/*
@@ -2255,7 +2408,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
* If called from an extended quiescent state, invoke the RCU
* core in order to force a re-evaluation of RCU's idleness.
*/
- if (rcu_is_cpu_idle() && cpu_online(smp_processor_id()))
+ if (!rcu_is_watching() && cpu_online(smp_processor_id()))
invoke_rcu_core();
/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
@@ -2279,6 +2432,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_node *rnp_root = rcu_get_root(rsp);
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
rcu_start_gp(rsp);
raw_spin_unlock(&rnp_root->lock);
} else {
@@ -2338,7 +2492,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
if (cpu != -1)
rdp = per_cpu_ptr(rsp->rda, cpu);
- offline = !__call_rcu_nocb(rdp, head, lazy);
+ offline = !__call_rcu_nocb(rdp, head, lazy, flags);
WARN_ON_ONCE(offline);
/* _call_rcu() is illegal on offline CPU; leak the callback. */
local_irq_restore(flags);
@@ -2658,6 +2812,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rsp, rdp);
+ /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+ if (rcu_nohz_full_cpu(rsp))
+ return 0;
+
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->qs_pending && !rdp->passed_quiesce) {
@@ -2691,6 +2849,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
return 1;
}
+ /* Does this CPU need a deferred NOCB wakeup? */
+ if (rcu_nocb_need_deferred_wakeup(rdp)) {
+ rdp->n_rp_nocb_defer_wakeup++;
+ return 1;
+ }
+
/* nothing to do */
rdp->n_rp_need_nothing++;
return 0;
@@ -2725,10 +2889,13 @@ static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
for_each_rcu_flavor(rsp) {
rdp = per_cpu_ptr(rsp->rda, cpu);
- if (rdp->qlen != rdp->qlen_lazy)
+ if (!rdp->nxtlist)
+ continue;
+ hc = true;
+ if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
al = false;
- if (rdp->nxtlist)
- hc = true;
+ break;
+ }
}
if (all_lazy)
*all_lazy = al;
@@ -3112,9 +3279,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = rcu_num_lvls - 1; i > 0; i--)
+ rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ for (i = rcu_num_lvls - 2; i >= 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
- rsp->levelspread[0] = rcu_fanout_leaf;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
@@ -3216,7 +3383,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
/*
* Compute the rcu_node tree geometry from kernel parameters. This cannot
- * replace the definitions in rcutree.h because those are needed to size
+ * replace the definitions in tree.h because those are needed to size
* the ->node array in the rcu_state structure.
*/
static void __init rcu_init_geometry(void)
@@ -3244,6 +3411,8 @@ static void __init rcu_init_geometry(void)
if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
+ pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+ rcu_fanout_leaf, nr_cpu_ids);
/*
* Compute number of nodes that can be handled an rcu_node tree
@@ -3295,8 +3464,8 @@ void __init rcu_init(void)
rcu_bootup_announce();
rcu_init_geometry();
- rcu_init_one(&rcu_sched_state, &rcu_sched_data);
rcu_init_one(&rcu_bh_state, &rcu_bh_data);
+ rcu_init_one(&rcu_sched_state, &rcu_sched_data);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
@@ -3311,4 +3480,4 @@ void __init rcu_init(void)
rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
}
-#include "rcutree_plugin.h"
+#include "tree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcu/tree.h
index 5f97eab602cd..8c19873f1ac9 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcu/tree.h
@@ -104,6 +104,8 @@ struct rcu_dynticks {
/* idle-period nonlazy_posted snapshot. */
unsigned long last_accelerate;
/* Last jiffy CBs were accelerated. */
+ unsigned long last_advance_all;
+ /* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
@@ -315,6 +317,7 @@ struct rcu_data {
unsigned long n_rp_cpu_needs_gp;
unsigned long n_rp_gp_completed;
unsigned long n_rp_gp_started;
+ unsigned long n_rp_nocb_defer_wakeup;
unsigned long n_rp_need_nothing;
/* 6) _rcu_barrier() and OOM callbacks. */
@@ -333,6 +336,7 @@ struct rcu_data {
int nocb_p_count_lazy; /* (approximate). */
wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
+ bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 8) RCU CPU stall data. */
@@ -451,6 +455,8 @@ struct rcu_state {
/* but in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
+ unsigned long jiffies_resched; /* Time at which to resched */
+ /* a reluctant CPU. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
const char *name; /* Name of structure. */
@@ -546,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy);
+ bool lazy, unsigned long flags);
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp);
+ struct rcu_data *rdp,
+ unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
static void rcu_kick_nohz_cpu(int cpu);
@@ -562,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj);
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
#endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcu/tree_plugin.h
index 130c97b027f2..6e2ef4b2b920 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -28,7 +28,7 @@
#include <linux/gfp.h>
#include <linux/oom.h>
#include <linux/smpboot.h>
-#include "time/tick-internal.h"
+#include "../time/tick-internal.h"
#define RCU_KTHREAD_PRIO 1
@@ -96,10 +96,15 @@ static void __init rcu_bootup_announce_oddness(void)
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
#ifdef CONFIG_RCU_NOCB_CPU_ALL
pr_info("\tOffload RCU callbacks from all CPUs\n");
- cpumask_setall(rcu_nocb_mask);
+ cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
if (have_rcu_nocb_mask) {
+ if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
+ pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+ cpumask_and(rcu_nocb_mask, cpu_possible_mask,
+ rcu_nocb_mask);
+ }
cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
if (rcu_nocb_poll)
@@ -199,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
t->rcu_blocked_node = rnp;
@@ -307,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}
@@ -356,10 +363,14 @@ void rcu_read_unlock_special(struct task_struct *t)
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
rcu_preempt_qs(smp_processor_id());
+ if (!t->rcu_read_unlock_special) {
+ local_irq_restore(flags);
+ return;
+ }
}
- /* Hardware IRQ handlers cannot block. */
- if (in_irq() || in_serving_softirq()) {
+ /* Hardware IRQ handlers cannot block, complain if they get here. */
+ if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
local_irq_restore(flags);
return;
}
@@ -376,6 +387,7 @@ void rcu_read_unlock_special(struct task_struct *t)
for (;;) {
rnp = t->rcu_blocked_node;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -600,6 +612,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
while (!list_empty(lp)) {
t = list_entry(lp->next, typeof(*t), rcu_node_entry);
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
list_del(&t->rcu_node_entry);
t->rcu_blocked_node = rnp_root;
list_add(&t->rcu_node_entry, lp_root);
@@ -624,6 +637,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
* in this case.
*/
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
if (rnp_root->boost_tasks != NULL &&
rnp_root->boost_tasks != rnp_root->gp_tasks &&
rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -660,7 +674,7 @@ static void rcu_preempt_check_callbacks(int cpu)
static void rcu_preempt_do_callbacks(void)
{
- rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+ rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
}
#endif /* #ifdef CONFIG_RCU_BOOST */
@@ -767,6 +781,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -774,14 +789,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- if (wake)
+ if (wake) {
+ smp_mb(); /* EGP done before wake_up(). */
wake_up(&sync_rcu_preempt_exp_wq);
+ }
break;
}
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock(&rnp->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
rnp->expmask &= ~mask;
}
}
@@ -801,6 +819,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
int must_wait = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (list_empty(&rnp->blkd_tasks)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else {
@@ -881,6 +900,7 @@ void synchronize_rcu_expedited(void)
/* Initialize ->expmask for all non-leaf rcu_node structures. */
rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->expmask = rnp->qsmaskinit;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
@@ -1128,7 +1148,7 @@ void exit_rcu(void)
#ifdef CONFIG_RCU_BOOST
-#include "rtmutex_common.h"
+#include "../locking/rtmutex_common.h"
#ifdef CONFIG_RCU_TRACE
@@ -1186,6 +1206,7 @@ static int rcu_boost(struct rcu_node *rnp)
return 0; /* Nothing left to boost. */
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
/*
* Recheck under the lock: all tasks in need of boosting
@@ -1332,7 +1353,7 @@ static void invoke_rcu_callbacks_kthread(void)
*/
static bool rcu_is_callbacks_kthread(void)
{
- return __get_cpu_var(rcu_cpu_kthread_task) == current;
+ return __this_cpu_read(rcu_cpu_kthread_task) == current;
}
#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1372,6 +1393,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
if (IS_ERR(t))
return PTR_ERR(t);
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
sp.sched_priority = RCU_BOOST_PRIO;
@@ -1382,8 +1404,8 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
static void rcu_kthread_do_work(void)
{
- rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
- rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+ rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
+ rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
rcu_preempt_do_callbacks();
}
@@ -1402,7 +1424,7 @@ static void rcu_cpu_kthread_park(unsigned int cpu)
static int rcu_cpu_kthread_should_run(unsigned int cpu)
{
- return __get_cpu_var(rcu_cpu_has_work);
+ return __this_cpu_read(rcu_cpu_has_work);
}
/*
@@ -1412,8 +1434,8 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
*/
static void rcu_cpu_kthread(unsigned int cpu)
{
- unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status);
- char work, *workp = &__get_cpu_var(rcu_cpu_has_work);
+ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
+ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
int spincnt;
for (spincnt = 0; spincnt < 10; spincnt++) {
@@ -1627,20 +1649,26 @@ module_param(rcu_idle_gp_delay, int, 0644);
static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
module_param(rcu_idle_lazy_gp_delay, int, 0644);
-extern int tick_nohz_enabled;
+extern int tick_nohz_active;
/*
- * Try to advance callbacks for all flavors of RCU on the current CPU.
- * Afterwards, if there are any callbacks ready for immediate invocation,
- * return true.
+ * Try to advance callbacks for all flavors of RCU on the current CPU, but
+ * only if it has been awhile since the last time we did so. Afterwards,
+ * if there are any callbacks ready for immediate invocation, return true.
*/
static bool rcu_try_advance_all_cbs(void)
{
bool cbs_ready = false;
struct rcu_data *rdp;
+ struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
struct rcu_node *rnp;
struct rcu_state *rsp;
+ /* Exit early if we advanced recently. */
+ if (jiffies == rdtp->last_advance_all)
+ return 0;
+ rdtp->last_advance_all = jiffies;
+
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
rnp = rdp->mynode;
@@ -1718,7 +1746,7 @@ static void rcu_prepare_for_idle(int cpu)
int tne;
/* Handle nohz enablement switches conservatively. */
- tne = ACCESS_ONCE(tick_nohz_enabled);
+ tne = ACCESS_ONCE(tick_nohz_active);
if (tne != rdtp->tick_nohz_enabled_snap) {
if (rcu_cpu_has_callbacks(cpu, NULL))
invoke_rcu_core(); /* force nohz to see update. */
@@ -1739,6 +1767,8 @@ static void rcu_prepare_for_idle(int cpu)
*/
if (rdtp->all_lazy &&
rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) {
+ rdtp->all_lazy = false;
+ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
invoke_rcu_core();
return;
}
@@ -1756,6 +1786,7 @@ static void rcu_prepare_for_idle(int cpu)
continue;
rnp = rdp->mynode;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_accelerate_cbs(rsp, rnp, rdp);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
@@ -1768,17 +1799,11 @@ static void rcu_prepare_for_idle(int cpu)
*/
static void rcu_cleanup_after_idle(int cpu)
{
- struct rcu_data *rdp;
- struct rcu_state *rsp;
if (rcu_is_nocb_cpu(cpu))
return;
- rcu_try_advance_all_cbs();
- for_each_rcu_flavor(rsp) {
- rdp = per_cpu_ptr(rsp->rda, cpu);
- if (cpu_has_callbacks_ready_to_invoke(rdp))
- invoke_rcu_core();
- }
+ if (rcu_try_advance_all_cbs())
+ invoke_rcu_core();
}
/*
@@ -1845,6 +1870,7 @@ static int rcu_oom_notify(struct notifier_block *self,
/* Wait for callbacks from earlier instance to complete. */
wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+ smp_mb(); /* Ensure callback reuse happens after callback invocation. */
/*
* Prevent premature wakeup: ensure that all increments happen
@@ -2094,7 +2120,8 @@ bool rcu_is_nocb_cpu(int cpu)
static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
struct rcu_head *rhp,
struct rcu_head **rhtp,
- int rhcount, int rhcount_lazy)
+ int rhcount, int rhcount_lazy,
+ unsigned long flags)
{
int len;
struct rcu_head **old_rhpp;
@@ -2108,15 +2135,29 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
/* If we are not being polled and there is a kthread, awaken it ... */
t = ACCESS_ONCE(rdp->nocb_kthread);
- if (rcu_nocb_poll | !t)
+ if (rcu_nocb_poll || !t) {
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeNotPoll"));
return;
+ }
len = atomic_long_read(&rdp->nocb_q_count);
if (old_rhpp == &rdp->nocb_head) {
- wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+ if (!irqs_disabled_flags(flags)) {
+ wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmpty"));
+ } else {
+ rdp->nocb_defer_wakeup = true;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmptyIsDeferred"));
+ }
rdp->qlen_last_fqs_check = 0;
} else if (len > rdp->qlen_last_fqs_check + qhimark) {
wake_up_process(t); /* ... or if many callbacks queued. */
rdp->qlen_last_fqs_check = LONG_MAX / 2;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
+ } else {
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
}
return;
}
@@ -2131,19 +2172,21 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
* "rcuo" kthread can find it.
*/
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
if (!rcu_is_nocb_cpu(rdp->cpu))
return 0;
- __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+ __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
if (__is_kfree_rcu_offset((unsigned long)rhp->func))
trace_rcu_kfree_callback(rdp->rsp->name, rhp,
(unsigned long)rhp->func,
- rdp->qlen_lazy, rdp->qlen);
+ -atomic_long_read(&rdp->nocb_q_count_lazy),
+ -atomic_long_read(&rdp->nocb_q_count));
else
trace_rcu_callback(rdp->rsp->name, rhp,
- rdp->qlen_lazy, rdp->qlen);
+ -atomic_long_read(&rdp->nocb_q_count_lazy),
+ -atomic_long_read(&rdp->nocb_q_count));
return 1;
}
@@ -2152,7 +2195,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
* not a no-CBs CPU.
*/
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
long ql = rsp->qlen;
long qll = rsp->qlen_lazy;
@@ -2166,14 +2210,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
/* First, enqueue the donelist, if any. This preserves CB ordering. */
if (rsp->orphan_donelist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
- rsp->orphan_donetail, ql, qll);
+ rsp->orphan_donetail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_donelist = NULL;
rsp->orphan_donetail = &rsp->orphan_donelist;
}
if (rsp->orphan_nxtlist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
- rsp->orphan_nxttail, ql, qll);
+ rsp->orphan_nxttail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2193,6 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
struct rcu_node *rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
c = rcu_start_future_gp(rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -2221,6 +2266,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
static int rcu_nocb_kthread(void *arg)
{
int c, cl;
+ bool firsttime = 1;
struct rcu_head *list;
struct rcu_head *next;
struct rcu_head **tail;
@@ -2229,14 +2275,28 @@ static int rcu_nocb_kthread(void *arg)
/* Each pass through this loop invokes one batch of callbacks */
for (;;) {
/* If not polling, wait for next batch of callbacks. */
- if (!rcu_nocb_poll)
+ if (!rcu_nocb_poll) {
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("Sleep"));
wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+ /* Memory barrier provide by xchg() below. */
+ } else if (firsttime) {
+ firsttime = 0;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("Poll"));
+ }
list = ACCESS_ONCE(rdp->nocb_head);
if (!list) {
+ if (!rcu_nocb_poll)
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WokeEmpty"));
schedule_timeout_interruptible(1);
flush_signals(current);
continue;
}
+ firsttime = 1;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WokeNonEmpty"));
/*
* Extract queued callbacks, update counts, and wait
@@ -2257,7 +2317,11 @@ static int rcu_nocb_kthread(void *arg)
next = list->next;
/* Wait for enqueuing to complete, if needed. */
while (next == NULL && &list->next != tail) {
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WaitQueue"));
schedule_timeout_interruptible(1);
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WokeQueue"));
next = list->next;
}
debug_rcu_head_unqueue(list);
@@ -2276,6 +2340,22 @@ static int rcu_nocb_kthread(void *arg)
return 0;
}
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+ if (!rcu_nocb_need_deferred_wakeup(rdp))
+ return;
+ ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+ wake_up(&rdp->nocb_wq);
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
/* Initialize per-rcu_data variables for no-CBs CPUs. */
static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
@@ -2331,13 +2411,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
}
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
return 0;
}
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
return 0;
}
@@ -2346,6 +2427,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
}
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
{
}
@@ -2795,3 +2885,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
}
#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ if (tick_nohz_full_cpu(smp_processor_id()) &&
+ (!rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+ return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+ return 0;
+}
diff --git a/kernel/rcutree_trace.c b/kernel/rcu/tree_trace.c
index cf6c17412932..4def475336d4 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -44,7 +44,7 @@
#include <linux/seq_file.h>
#define RCU_TREE_NONCORE
-#include "rcutree.h"
+#include "tree.h"
static int r_open(struct inode *inode, struct file *file,
const struct seq_operations *op)
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
rdp->n_rp_report_qs,
rdp->n_rp_cb_ready,
rdp->n_rp_cpu_needs_gp);
- seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+ seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
rdp->n_rp_gp_completed,
rdp->n_rp_gp_started,
+ rdp->n_rp_nocb_defer_wakeup,
rdp->n_rp_need_nothing);
}
diff --git a/kernel/rcupdate.c b/kernel/rcu/update.c
index b02a339836b4..802365ccd591 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcu/update.c
@@ -53,6 +53,12 @@
#include "rcu.h"
+MODULE_ALIAS("rcupdate");
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "rcupdate."
+
module_param(rcu_expedited, int, 0);
#ifdef CONFIG_PREEMPT_RCU
@@ -122,6 +128,11 @@ struct lockdep_map rcu_sched_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+ STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
int notrace debug_lockdep_rcu_enabled(void)
{
return rcu_scheduler_active && debug_locks &&
@@ -148,7 +159,7 @@ int rcu_read_lock_bh_held(void)
{
if (!debug_lockdep_rcu_enabled())
return 1;
- if (rcu_is_cpu_idle())
+ if (!rcu_is_watching())
return 0;
if (!rcu_lockdep_current_cpu_online())
return 0;
@@ -298,7 +309,7 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
#endif
int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
-int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
+static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_suppress, int, 0644);
module_param(rcu_cpu_stall_timeout, int, 0644);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b3474646..662c83fc16b7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_reboot_notifier);
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
{
/* The boot cpu is always logical cpu 0 */
int cpu = reboot_cpu;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 54adcf35f495..9a95c8c2af2a 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,8 +11,10 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
+obj-y += wait.o completion.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae1446461c..6bd6a6731b21 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
* at 0 on boot (but people really shouldn't rely on that).
*
* cpu_clock(i) -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
* local_clock() -- is cpu_clock() on the current cpu.
*
+ * sched_clock_cpu(i)
+ *
* How:
*
* The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
* Furthermore, explicit sleep and wakeup hooks allow us to account for time
* that is otherwise invisible (TSC gets stopped).
*
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
*/
#include <linux/spinlock.h>
#include <linux/hardirq.h>
@@ -66,6 +58,8 @@
#include <linux/percpu.h>
#include <linux/ktime.h>
#include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
/*
* Scheduler clock - returns current time in nanosec units.
@@ -82,7 +76,37 @@ EXPORT_SYMBOL_GPL(sched_clock);
__read_mostly int sched_clock_running;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+
+int sched_clock_stable(void)
+{
+ if (static_key_false(&__sched_clock_stable))
+ return false;
+ return true;
+}
+
+void set_sched_clock_stable(void)
+{
+ if (!sched_clock_stable())
+ static_key_slow_dec(&__sched_clock_stable);
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+ /* XXX worry about clock continuity */
+ if (sched_clock_stable())
+ static_key_slow_inc(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+ if (keventd_up())
+ schedule_work(&sched_clock_work);
+ else
+ __clear_sched_clock_stable(&sched_clock_work);
+}
struct sched_clock_data {
u64 tick_raw;
@@ -242,20 +266,20 @@ u64 sched_clock_cpu(int cpu)
struct sched_clock_data *scd;
u64 clock;
- WARN_ON_ONCE(!irqs_disabled());
-
- if (sched_clock_stable)
+ if (sched_clock_stable())
return sched_clock();
if (unlikely(!sched_clock_running))
return 0ull;
+ preempt_disable();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
+ preempt_enable();
return clock;
}
@@ -265,7 +289,7 @@ void sched_clock_tick(void)
struct sched_clock_data *scd;
u64 now, now_gtod;
- if (sched_clock_stable)
+ if (sched_clock_stable())
return;
if (unlikely(!sched_clock_running))
@@ -316,14 +340,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
*/
u64 cpu_clock(int cpu)
{
- u64 clock;
- unsigned long flags;
-
- local_irq_save(flags);
- clock = sched_clock_cpu(cpu);
- local_irq_restore(flags);
+ if (static_key_false(&__sched_clock_stable))
+ return sched_clock_cpu(cpu);
- return clock;
+ return sched_clock();
}
/*
@@ -335,14 +355,10 @@ u64 cpu_clock(int cpu)
*/
u64 local_clock(void)
{
- u64 clock;
- unsigned long flags;
+ if (static_key_false(&__sched_clock_stable))
+ return sched_clock_cpu(raw_smp_processor_id());
- local_irq_save(flags);
- clock = sched_clock_cpu(smp_processor_id());
- local_irq_restore(flags);
-
- return clock;
+ return sched_clock();
}
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +378,12 @@ u64 sched_clock_cpu(int cpu)
u64 cpu_clock(int cpu)
{
- return sched_clock_cpu(cpu);
+ return sched_clock();
}
u64 local_clock(void)
{
- return sched_clock_cpu(0);
+ return sched_clock();
}
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
new file mode 100644
index 000000000000..a63f4dc27909
--- /dev/null
+++ b/kernel/sched/completion.c
@@ -0,0 +1,299 @@
+/*
+ * Generic wait-for-completion handler;
+ *
+ * It differs from semaphores in that their default case is the opposite,
+ * wait_for_completion default blocks whereas semaphore default non-block. The
+ * interface also makes it easy to 'complete' multiple waiting threads,
+ * something which isn't entirely natural for semaphores.
+ *
+ * But more importantly, the primitive documents the usage. Semaphores would
+ * typically be used for exclusion which gives rise to priority inversion.
+ * Waiting for completion is a typically sync point, but not an exclusion point.
+ */
+
+#include <linux/sched.h>
+#include <linux/completion.h>
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x: holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete(struct completion *x)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
+ x->done++;
+ __wake_up_locked(&x->wait, TASK_NORMAL, 1);
+ spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x: holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete_all(struct completion *x)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
+ x->done += UINT_MAX/2;
+ __wake_up_locked(&x->wait, TASK_NORMAL, 0);
+ spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+do_wait_for_common(struct completion *x,
+ long (*action)(long), long timeout, int state)
+{
+ if (!x->done) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ __add_wait_queue_tail_exclusive(&x->wait, &wait);
+ do {
+ if (signal_pending_state(state, current)) {
+ timeout = -ERESTARTSYS;
+ break;
+ }
+ __set_current_state(state);
+ spin_unlock_irq(&x->wait.lock);
+ timeout = action(timeout);
+ spin_lock_irq(&x->wait.lock);
+ } while (!x->done && timeout);
+ __remove_wait_queue(&x->wait, &wait);
+ if (!x->done)
+ return timeout;
+ }
+ x->done--;
+ return timeout ?: 1;
+}
+
+static inline long __sched
+__wait_for_common(struct completion *x,
+ long (*action)(long), long timeout, int state)
+{
+ might_sleep();
+
+ spin_lock_irq(&x->wait.lock);
+ timeout = do_wait_for_common(x, action, timeout, state);
+ spin_unlock_irq(&x->wait.lock);
+ return timeout;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+ return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+ return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+ wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+ return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+ wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+ return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x: holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+ if (t == -ERESTARTSYS)
+ return t;
+ return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+ unsigned long timeout)
+{
+ return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+ if (t == -ERESTARTSYS)
+ return t;
+ return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be
+ * signaled or for a specified timeout to expire. It can be
+ * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_killable_timeout(struct completion *x,
+ unsigned long timeout)
+{
+ return wait_for_common(x, timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(wait_for_completion_killable_timeout);
+
+/**
+ * try_wait_for_completion - try to decrement a completion without blocking
+ * @x: completion structure
+ *
+ * Return: 0 if a decrement cannot be done without blocking
+ * 1 if a decrement succeeded.
+ *
+ * If a completion is being used as a counting completion,
+ * attempt to decrement the counter without blocking. This
+ * enables us to avoid waiting if the resource the completion
+ * is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+ unsigned long flags;
+ int ret = 1;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
+ if (!x->done)
+ ret = 0;
+ else
+ x->done--;
+ spin_unlock_irqrestore(&x->wait.lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ * completion_done - Test to see if a completion has any waiters
+ * @x: completion structure
+ *
+ * Return: 0 if there are waiters (wait_for_completion() in progress)
+ * 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+ unsigned long flags;
+ int ret = 1;
+
+ spin_lock_irqsave(&x->wait.lock, flags);
+ if (!x->done)
+ ret = 0;
+ spin_unlock_irqrestore(&x->wait.lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5ac63c9a995a..4d6964e49711 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -296,8 +296,6 @@ __read_mostly int scheduler_running;
*/
int sysctl_sched_rt_runtime = 950000;
-
-
/*
* __task_rq_lock - lock the rq @p resides on.
*/
@@ -513,12 +511,11 @@ static inline void init_hrtick(void)
* might also involve a cross-CPU call to trigger the scheduler on
* the target CPU.
*/
-#ifdef CONFIG_SMP
void resched_task(struct task_struct *p)
{
int cpu;
- assert_raw_spin_locked(&task_rq(p)->lock);
+ lockdep_assert_held(&task_rq(p)->lock);
if (test_tsk_need_resched(p))
return;
@@ -526,8 +523,10 @@ void resched_task(struct task_struct *p)
set_tsk_need_resched(p);
cpu = task_cpu(p);
- if (cpu == smp_processor_id())
+ if (cpu == smp_processor_id()) {
+ set_preempt_need_resched();
return;
+ }
/* NEED_RESCHED must be visible before we test polling */
smp_mb();
@@ -546,6 +545,7 @@ void resched_cpu(int cpu)
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
+#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
* In the semi idle case, use the nearest busy cpu for migrating timers
@@ -693,12 +693,6 @@ void sched_avg_update(struct rq *rq)
}
}
-#else /* !CONFIG_SMP */
-void resched_task(struct task_struct *p)
-{
- assert_raw_spin_locked(&task_rq(p)->lock);
- set_tsk_need_resched(p);
-}
#endif /* CONFIG_SMP */
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -767,14 +761,14 @@ static void set_load_weight(struct task_struct *p)
static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- sched_info_queued(p);
+ sched_info_queued(rq, p);
p->sched_class->enqueue_task(rq, p, flags);
}
static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq);
- sched_info_dequeued(p);
+ sched_info_dequeued(rq, p);
p->sched_class->dequeue_task(rq, p, flags);
}
@@ -903,7 +897,9 @@ static inline int normal_prio(struct task_struct *p)
{
int prio;
- if (task_has_rt_policy(p))
+ if (task_has_dl_policy(p))
+ prio = MAX_DL_PRIO-1;
+ else if (task_has_rt_policy(p))
prio = MAX_RT_PRIO-1 - p->rt_priority;
else
prio = __normal_prio(p);
@@ -949,7 +945,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
if (prev_class->switched_from)
prev_class->switched_from(rq, p);
p->sched_class->switched_to(rq, p);
- } else if (oldprio != p->prio)
+ } else if (oldprio != p->prio || dl_task(p))
p->sched_class->prio_changed(rq, p, oldprio);
}
@@ -987,7 +983,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
* ttwu() will sort out the placement.
*/
WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
- !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+ !(task_preempt_count(p) & PREEMPT_ACTIVE));
#ifdef CONFIG_LOCKDEP
/*
@@ -1017,6 +1013,108 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
__set_task_cpu(p, new_cpu);
}
+static void __migrate_swap_task(struct task_struct *p, int cpu)
+{
+ if (p->on_rq) {
+ struct rq *src_rq, *dst_rq;
+
+ src_rq = task_rq(p);
+ dst_rq = cpu_rq(cpu);
+
+ deactivate_task(src_rq, p, 0);
+ set_task_cpu(p, cpu);
+ activate_task(dst_rq, p, 0);
+ check_preempt_curr(dst_rq, p, 0);
+ } else {
+ /*
+ * Task isn't running anymore; make it appear like we migrated
+ * it before it went to sleep. This means on wakeup we make the
+ * previous cpu our targer instead of where it really is.
+ */
+ p->wake_cpu = cpu;
+ }
+}
+
+struct migration_swap_arg {
+ struct task_struct *src_task, *dst_task;
+ int src_cpu, dst_cpu;
+};
+
+static int migrate_swap_stop(void *data)
+{
+ struct migration_swap_arg *arg = data;
+ struct rq *src_rq, *dst_rq;
+ int ret = -EAGAIN;
+
+ src_rq = cpu_rq(arg->src_cpu);
+ dst_rq = cpu_rq(arg->dst_cpu);
+
+ double_raw_lock(&arg->src_task->pi_lock,
+ &arg->dst_task->pi_lock);
+ double_rq_lock(src_rq, dst_rq);
+ if (task_cpu(arg->dst_task) != arg->dst_cpu)
+ goto unlock;
+
+ if (task_cpu(arg->src_task) != arg->src_cpu)
+ goto unlock;
+
+ if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task)))
+ goto unlock;
+
+ if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
+ goto unlock;
+
+ __migrate_swap_task(arg->src_task, arg->dst_cpu);
+ __migrate_swap_task(arg->dst_task, arg->src_cpu);
+
+ ret = 0;
+
+unlock:
+ double_rq_unlock(src_rq, dst_rq);
+ raw_spin_unlock(&arg->dst_task->pi_lock);
+ raw_spin_unlock(&arg->src_task->pi_lock);
+
+ return ret;
+}
+
+/*
+ * Cross migrate two tasks
+ */
+int migrate_swap(struct task_struct *cur, struct task_struct *p)
+{
+ struct migration_swap_arg arg;
+ int ret = -EINVAL;
+
+ arg = (struct migration_swap_arg){
+ .src_task = cur,
+ .src_cpu = task_cpu(cur),
+ .dst_task = p,
+ .dst_cpu = task_cpu(p),
+ };
+
+ if (arg.src_cpu == arg.dst_cpu)
+ goto out;
+
+ /*
+ * These three tests are all lockless; this is OK since all of them
+ * will be re-checked with proper locks held further down the line.
+ */
+ if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
+ goto out;
+
+ if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task)))
+ goto out;
+
+ if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
+ goto out;
+
+ trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
+ ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
+
+out:
+ return ret;
+}
+
struct migration_arg {
struct task_struct *task;
int dest_cpu;
@@ -1236,9 +1334,9 @@ out:
* The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
*/
static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
{
- int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+ cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
/*
* In order not to call set_task_cpu() on a blocking task we need
@@ -1330,12 +1428,13 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
if (rq->idle_stamp) {
u64 delta = rq_clock(rq) - rq->idle_stamp;
- u64 max = 2*sysctl_sched_migration_cost;
+ u64 max = 2*rq->max_idle_balance_cost;
- if (delta > max)
+ update_avg(&rq->avg_idle, delta);
+
+ if (rq->avg_idle > max)
rq->avg_idle = max;
- else
- update_avg(&rq->avg_idle, delta);
+
rq->idle_stamp = 0;
}
#endif
@@ -1396,6 +1495,13 @@ static void sched_ttwu_pending(void)
void scheduler_ipi(void)
{
+ /*
+ * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
+ * TIF_NEED_RESCHED remotely (for the first time) will also send
+ * this IPI.
+ */
+ preempt_fold_need_resched();
+
if (llist_empty(&this_rq()->wake_list)
&& !tick_nohz_full_cpu(smp_processor_id())
&& !got_nohz_idle_kick())
@@ -1513,7 +1619,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
if (p->sched_class->task_waking)
p->sched_class->task_waking(p);
- cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
set_task_cpu(p, cpu);
@@ -1595,7 +1701,7 @@ int wake_up_state(struct task_struct *p, unsigned int state)
*
* __sched_fork() is basic setup used by init_idle() too:
*/
-static void __sched_fork(struct task_struct *p)
+static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
{
p->on_rq = 0;
@@ -1611,6 +1717,13 @@ static void __sched_fork(struct task_struct *p)
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
+ RB_CLEAR_NODE(&p->dl.rb_node);
+ hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ p->dl.dl_runtime = p->dl.runtime = 0;
+ p->dl.dl_deadline = p->dl.deadline = 0;
+ p->dl.dl_period = 0;
+ p->dl.flags = 0;
+
INIT_LIST_HEAD(&p->rt.run_list);
#ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1619,16 +1732,24 @@ static void __sched_fork(struct task_struct *p)
#ifdef CONFIG_NUMA_BALANCING
if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
- p->mm->numa_next_scan = jiffies;
- p->mm->numa_next_reset = jiffies;
+ p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
p->mm->numa_scan_seq = 0;
}
+ if (clone_flags & CLONE_VM)
+ p->numa_preferred_nid = current->numa_preferred_nid;
+ else
+ p->numa_preferred_nid = -1;
+
p->node_stamp = 0ULL;
p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
- p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
p->numa_work.next = &p->numa_work;
+ p->numa_faults = NULL;
+ p->numa_faults_buffer = NULL;
+
+ INIT_LIST_HEAD(&p->numa_entry);
+ p->numa_group = NULL;
#endif /* CONFIG_NUMA_BALANCING */
}
@@ -1654,12 +1775,12 @@ void set_numabalancing_state(bool enabled)
/*
* fork()/clone()-time setup:
*/
-void sched_fork(struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
int cpu = get_cpu();
- __sched_fork(p);
+ __sched_fork(clone_flags, p);
/*
* We mark the process as running here. This guarantees that
* nobody will actually run it, and a signal or other external
@@ -1676,7 +1797,7 @@ void sched_fork(struct task_struct *p)
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->policy = SCHED_NORMAL;
p->static_prio = NICE_TO_PRIO(0);
p->rt_priority = 0;
@@ -1693,8 +1814,14 @@ void sched_fork(struct task_struct *p)
p->sched_reset_on_fork = 0;
}
- if (!rt_prio(p->prio))
+ if (dl_prio(p->prio)) {
+ put_cpu();
+ return -EAGAIN;
+ } else if (rt_prio(p->prio)) {
+ p->sched_class = &rt_sched_class;
+ } else {
p->sched_class = &fair_sched_class;
+ }
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
@@ -1717,18 +1844,128 @@ void sched_fork(struct task_struct *p)
#if defined(CONFIG_SMP)
p->on_cpu = 0;
#endif
-#ifdef CONFIG_PREEMPT_COUNT
- /* Want to start with kernel preemption disabled. */
- task_thread_info(p)->preempt_count = 1;
-#endif
+ init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
put_cpu();
+ return 0;
+}
+
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+ if (runtime == RUNTIME_INF)
+ return 1ULL << 20;
+
+ /*
+ * Doing this here saves a lot of checks in all
+ * the calling paths, and returning zero seems
+ * safe for them anyway.
+ */
+ if (period == 0)
+ return 0;
+
+ return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ struct root_domain *rd = cpu_rq(i)->rd;
+ int cpus = 0;
+
+ for_each_cpu_and(i, rd->span, cpu_active_mask)
+ cpus++;
+
+ return cpus;
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+ return dl_b->bw != -1 &&
+ dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}
/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+ const struct sched_attr *attr)
+{
+
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+ u64 period = attr->sched_period;
+ u64 runtime = attr->sched_runtime;
+ u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+ int cpus, err = -1;
+
+ if (new_bw == p->dl.dl_bw)
+ return 0;
+
+ /*
+ * Either if a task, enters, leave, or stays -deadline but changes
+ * its parameters, we may need to update accordingly the total
+ * allocated bandwidth of the container.
+ */
+ raw_spin_lock(&dl_b->lock);
+ cpus = dl_bw_cpus(task_cpu(p));
+ if (dl_policy(policy) && !task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (dl_policy(policy) && task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ err = 0;
+ }
+ raw_spin_unlock(&dl_b->lock);
+
+ return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
+/*
* wake_up_new_task - wake up a newly created task for the first time.
*
* This function will do some initial scheduler statistics housekeeping
@@ -1747,7 +1984,7 @@ void wake_up_new_task(struct task_struct *p)
* - cpus_allowed can change in the fork path
* - any previously selected cpu might disappear through hotplug
*/
- set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
+ set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
/* Initialize new task's runnable average */
@@ -1838,7 +2075,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
trace_sched_switch(prev, next);
- sched_info_switch(prev, next);
+ sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
@@ -1890,6 +2127,11 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
if (mm)
mmdrop(mm);
if (unlikely(prev_state == TASK_DEAD)) {
+ task_numa_free(prev);
+
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
+
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
@@ -2073,7 +2315,7 @@ void sched_exec(void)
int dest_cpu;
raw_spin_lock_irqsave(&p->pi_lock, flags);
- dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
+ dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
if (dest_cpu == smp_processor_id())
goto unlock;
@@ -2140,6 +2382,20 @@ unsigned long long task_sched_runtime(struct task_struct *p)
struct rq *rq;
u64 ns = 0;
+#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
+ /*
+ * 64-bit doesn't need locks to atomically read a 64bit value.
+ * So we have a optimization chance when the task's delta_exec is 0.
+ * Reading ->on_cpu is racy, but this is ok.
+ *
+ * If we race with it leaving cpu, we'll take a lock. So we're correct.
+ * If we race with it entering cpu, unaccounted time is 0. This is
+ * indistinguishable from the read occurring a few cycles earlier.
+ */
+ if (!p->on_cpu)
+ return p->se.sum_exec_runtime;
+#endif
+
rq = task_rq_lock(p, &flags);
ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
task_rq_unlock(rq, p, &flags);
@@ -2169,7 +2425,7 @@ void scheduler_tick(void)
#ifdef CONFIG_SMP
rq->idle_balance = idle_cpu(cpu);
- trigger_load_balance(rq, cpu);
+ trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
}
@@ -2215,7 +2471,7 @@ notrace unsigned long get_parent_ip(unsigned long addr)
#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
defined(CONFIG_PREEMPT_TRACER))
-void __kprobes add_preempt_count(int val)
+void __kprobes preempt_count_add(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
/*
@@ -2224,7 +2480,7 @@ void __kprobes add_preempt_count(int val)
if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
return;
#endif
- preempt_count() += val;
+ __preempt_count_add(val);
#ifdef CONFIG_DEBUG_PREEMPT
/*
* Spinlock count overflowing soon?
@@ -2235,9 +2491,9 @@ void __kprobes add_preempt_count(int val)
if (preempt_count() == val)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
-EXPORT_SYMBOL(add_preempt_count);
+EXPORT_SYMBOL(preempt_count_add);
-void __kprobes sub_preempt_count(int val)
+void __kprobes preempt_count_sub(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
/*
@@ -2255,9 +2511,9 @@ void __kprobes sub_preempt_count(int val)
if (preempt_count() == val)
trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
- preempt_count() -= val;
+ __preempt_count_sub(val);
}
-EXPORT_SYMBOL(sub_preempt_count);
+EXPORT_SYMBOL(preempt_count_sub);
#endif
@@ -2287,10 +2543,10 @@ static inline void schedule_debug(struct task_struct *prev)
{
/*
* Test if we are atomic. Since do_exit() needs to call into
- * schedule() atomically, we ignore that path for now.
- * Otherwise, whine if we are scheduling when we should not be.
+ * schedule() atomically, we ignore that path. Otherwise whine
+ * if we are scheduling when we should not.
*/
- if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+ if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
__schedule_bug(prev);
rcu_sleep_check();
@@ -2430,6 +2686,7 @@ need_resched:
put_prev_task(rq, prev);
next = pick_next_task(rq);
clear_tsk_need_resched(prev);
+ clear_preempt_need_resched();
rq->skip_clock_update = 0;
if (likely(prev != next)) {
@@ -2520,9 +2777,9 @@ asmlinkage void __sched notrace preempt_schedule(void)
return;
do {
- add_preempt_count_notrace(PREEMPT_ACTIVE);
+ __preempt_count_add(PREEMPT_ACTIVE);
__schedule();
- sub_preempt_count_notrace(PREEMPT_ACTIVE);
+ __preempt_count_sub(PREEMPT_ACTIVE);
/*
* Check again in case we missed a preemption opportunity
@@ -2532,6 +2789,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
} while (need_resched());
}
EXPORT_SYMBOL(preempt_schedule);
+#endif /* CONFIG_PREEMPT */
/*
* this is the entry point to schedule() from kernel preemption
@@ -2541,20 +2799,19 @@ EXPORT_SYMBOL(preempt_schedule);
*/
asmlinkage void __sched preempt_schedule_irq(void)
{
- struct thread_info *ti = current_thread_info();
enum ctx_state prev_state;
/* Catch callers which need to be fixed */
- BUG_ON(ti->preempt_count || !irqs_disabled());
+ BUG_ON(preempt_count() || !irqs_disabled());
prev_state = exception_enter();
do {
- add_preempt_count(PREEMPT_ACTIVE);
+ __preempt_count_add(PREEMPT_ACTIVE);
local_irq_enable();
__schedule();
local_irq_disable();
- sub_preempt_count(PREEMPT_ACTIVE);
+ __preempt_count_sub(PREEMPT_ACTIVE);
/*
* Check again in case we missed a preemption opportunity
@@ -2566,8 +2823,6 @@ asmlinkage void __sched preempt_schedule_irq(void)
exception_exit(prev_state);
}
-#endif /* CONFIG_PREEMPT */
-
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
void *key)
{
@@ -2575,393 +2830,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
}
EXPORT_SYMBOL(default_wake_function);
-/*
- * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
- * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
- *
- * There are circumstances in which we can try to wake a task which has already
- * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
- * zero in this (rare) case, and we handle it by continuing to scan the queue.
- */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int wake_flags, void *key)
-{
- wait_queue_t *curr, *next;
-
- list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
- unsigned flags = curr->flags;
-
- if (curr->func(curr, mode, wake_flags, key) &&
- (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
- break;
- }
-}
-
-/**
- * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
- * @key: is directly passed to the wakeup function
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void __wake_up(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, void *key)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_common(q, mode, nr_exclusive, 0, key);
- spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL(__wake_up);
-
-/*
- * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
- */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
-{
- __wake_up_common(q, mode, nr, 0, NULL);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked);
-
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
-{
- __wake_up_common(q, mode, 1, 0, key);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key);
-
-/**
- * __wake_up_sync_key - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
- * @key: opaque value to be passed to wakeup targets
- *
- * The sync wakeup differs that the waker knows that it will schedule
- * away soon, so while the target thread will be woken up, it will not
- * be migrated to another CPU - ie. the two threads are 'synchronized'
- * with each other. This can prevent needless bouncing between CPUs.
- *
- * On UP it can prevent extra preemption.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, void *key)
-{
- unsigned long flags;
- int wake_flags = WF_SYNC;
-
- if (unlikely(!q))
- return;
-
- if (unlikely(nr_exclusive != 1))
- wake_flags = 0;
-
- spin_lock_irqsave(&q->lock, flags);
- __wake_up_common(q, mode, nr_exclusive, wake_flags, key);
- spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL_GPL(__wake_up_sync_key);
-
-/*
- * __wake_up_sync - see __wake_up_sync_key()
- */
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
-{
- __wake_up_sync_key(q, mode, nr_exclusive, NULL);
-}
-EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
-
-/**
- * complete: - signals a single thread waiting on this completion
- * @x: holds the state of this particular completion
- *
- * This will wake up a single thread waiting on this completion. Threads will be
- * awakened in the same order in which they were queued.
- *
- * See also complete_all(), wait_for_completion() and related routines.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete(struct completion *x)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&x->wait.lock, flags);
- x->done++;
- __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
- spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete);
-
-/**
- * complete_all: - signals all threads waiting on this completion
- * @x: holds the state of this particular completion
- *
- * This will wake up all threads waiting on this particular completion event.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete_all(struct completion *x)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&x->wait.lock, flags);
- x->done += UINT_MAX/2;
- __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
- spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete_all);
-
-static inline long __sched
-do_wait_for_common(struct completion *x,
- long (*action)(long), long timeout, int state)
-{
- if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
-
- __add_wait_queue_tail_exclusive(&x->wait, &wait);
- do {
- if (signal_pending_state(state, current)) {
- timeout = -ERESTARTSYS;
- break;
- }
- __set_current_state(state);
- spin_unlock_irq(&x->wait.lock);
- timeout = action(timeout);
- spin_lock_irq(&x->wait.lock);
- } while (!x->done && timeout);
- __remove_wait_queue(&x->wait, &wait);
- if (!x->done)
- return timeout;
- }
- x->done--;
- return timeout ?: 1;
-}
-
-static inline long __sched
-__wait_for_common(struct completion *x,
- long (*action)(long), long timeout, int state)
-{
- might_sleep();
-
- spin_lock_irq(&x->wait.lock);
- timeout = do_wait_for_common(x, action, timeout, state);
- spin_unlock_irq(&x->wait.lock);
- return timeout;
-}
-
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
-{
- return __wait_for_common(x, schedule_timeout, timeout, state);
-}
-
-static long __sched
-wait_for_common_io(struct completion *x, long timeout, int state)
-{
- return __wait_for_common(x, io_schedule_timeout, timeout, state);
-}
-
-/**
- * wait_for_completion: - waits for completion of a task
- * @x: holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout.
- *
- * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
- * and interrupt capability. Also see complete().
- */
-void __sched wait_for_completion(struct completion *x)
-{
- wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion);
-
-/**
- * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
- * @x: holds the state of this particular completion
- * @timeout: timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_timeout(struct completion *x, unsigned long timeout)
-{
- return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_timeout);
-
-/**
- * wait_for_completion_io: - waits for completion of a task
- * @x: holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout. The caller is accounted as waiting
- * for IO.
- */
-void __sched wait_for_completion_io(struct completion *x)
-{
- wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io);
-
-/**
- * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
- * @x: holds the state of this particular completion
- * @timeout: timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible. The caller is accounted as waiting for IO.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
-{
- return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io_timeout);
-
-/**
- * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
- * @x: holds the state of this particular completion
- *
- * This waits for completion of a specific task to be signaled. It is
- * interruptible.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_interruptible(struct completion *x)
-{
- long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
- if (t == -ERESTARTSYS)
- return t;
- return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible);
-
-/**
- * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
- * @x: holds the state of this particular completion
- * @timeout: timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. It is interruptible. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_interruptible_timeout(struct completion *x,
- unsigned long timeout)
-{
- return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
-
-/**
- * wait_for_completion_killable: - waits for completion of a task (killable)
- * @x: holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It can be
- * interrupted by a kill signal.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_killable(struct completion *x)
-{
- long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
- if (t == -ERESTARTSYS)
- return t;
- return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_killable);
-
-/**
- * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
- * @x: holds the state of this particular completion
- * @timeout: timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be
- * signaled or for a specified timeout to expire. It can be
- * interrupted by a kill signal. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_killable_timeout(struct completion *x,
- unsigned long timeout)
-{
- return wait_for_common(x, timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(wait_for_completion_killable_timeout);
-
-/**
- * try_wait_for_completion - try to decrement a completion without blocking
- * @x: completion structure
- *
- * Return: 0 if a decrement cannot be done without blocking
- * 1 if a decrement succeeded.
- *
- * If a completion is being used as a counting completion,
- * attempt to decrement the counter without blocking. This
- * enables us to avoid waiting if the resource the completion
- * is protecting is not available.
- */
-bool try_wait_for_completion(struct completion *x)
-{
- unsigned long flags;
- int ret = 1;
-
- spin_lock_irqsave(&x->wait.lock, flags);
- if (!x->done)
- ret = 0;
- else
- x->done--;
- spin_unlock_irqrestore(&x->wait.lock, flags);
- return ret;
-}
-EXPORT_SYMBOL(try_wait_for_completion);
-
-/**
- * completion_done - Test to see if a completion has any waiters
- * @x: completion structure
- *
- * Return: 0 if there are waiters (wait_for_completion() in progress)
- * 1 if there are no waiters.
- *
- */
-bool completion_done(struct completion *x)
-{
- unsigned long flags;
- int ret = 1;
-
- spin_lock_irqsave(&x->wait.lock, flags);
- if (!x->done)
- ret = 0;
- spin_unlock_irqrestore(&x->wait.lock, flags);
- return ret;
-}
-EXPORT_SYMBOL(completion_done);
-
static long __sched
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
{
@@ -3022,11 +2890,11 @@ EXPORT_SYMBOL(sleep_on_timeout);
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, on_rq, running;
+ int oldprio, on_rq, running, enqueue_flag = 0;
struct rq *rq;
const struct sched_class *prev_class;
- BUG_ON(prio < 0 || prio > MAX_PRIO);
+ BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p);
@@ -3049,6 +2917,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
}
trace_sched_pi_setprio(p, prio);
+ p->pi_top_task = rt_mutex_get_top_task(p);
oldprio = p->prio;
prev_class = p->sched_class;
on_rq = p->on_rq;
@@ -3058,23 +2927,49 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (running)
p->sched_class->put_prev_task(rq, p);
- if (rt_prio(prio))
+ /*
+ * Boosting condition are:
+ * 1. -rt task is running and holds mutex A
+ * --> -dl task blocks on mutex A
+ *
+ * 2. -dl task is running and holds mutex A
+ * --> -dl task blocks on mutex A and could preempt the
+ * running task
+ */
+ if (dl_prio(prio)) {
+ if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+ dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+ p->dl.dl_boosted = 1;
+ p->dl.dl_throttled = 0;
+ enqueue_flag = ENQUEUE_REPLENISH;
+ } else
+ p->dl.dl_boosted = 0;
+ p->sched_class = &dl_sched_class;
+ } else if (rt_prio(prio)) {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
+ if (oldprio < prio)
+ enqueue_flag = ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
- else
+ } else {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
p->sched_class = &fair_sched_class;
+ }
p->prio = prio;
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq)
- enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+ enqueue_task(rq, p, enqueue_flag);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
__task_rq_unlock(rq);
}
#endif
+
void set_user_nice(struct task_struct *p, long nice)
{
int old_prio, delta, on_rq;
@@ -3092,9 +2987,9 @@ void set_user_nice(struct task_struct *p, long nice)
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
* it wont have any effect on scheduling until the task is
- * SCHED_FIFO/SCHED_RR:
+ * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
*/
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
@@ -3249,22 +3144,95 @@ static struct task_struct *find_process_by_pid(pid_t pid)
return pid ? find_task_by_vpid(pid) : current;
}
-/* Actually do priority change: must hold rq lock. */
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ init_dl_task_timer(dl_se);
+ dl_se->dl_runtime = attr->sched_runtime;
+ dl_se->dl_deadline = attr->sched_deadline;
+ dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+ dl_se->flags = attr->sched_flags;
+ dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_throttled = 0;
+ dl_se->dl_new = 1;
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+ const struct sched_attr *attr)
{
+ int policy = attr->sched_policy;
+
+ if (policy == -1) /* setparam */
+ policy = p->policy;
+
p->policy = policy;
- p->rt_priority = prio;
+
+ if (dl_policy(policy))
+ __setparam_dl(p, attr);
+ else if (fair_policy(policy))
+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
+ /*
+ * __sched_setscheduler() ensures attr->sched_priority == 0 when
+ * !rt_policy. Always setting this ensures that things like
+ * getparam()/getattr() don't report silly values for !rt tasks.
+ */
+ p->rt_priority = attr->sched_priority;
+
p->normal_prio = normal_prio(p);
- /* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
- if (rt_prio(p->prio))
+
+ if (dl_prio(p->prio))
+ p->sched_class = &dl_sched_class;
+ else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
+
set_load_weight(p);
}
+static void
+__getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ attr->sched_priority = p->rt_priority;
+ attr->sched_runtime = dl_se->dl_runtime;
+ attr->sched_deadline = dl_se->dl_deadline;
+ attr->sched_period = dl_se->dl_period;
+ attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution (1us); we
+ * check sched_runtime only since it is always the smaller one.
+ */
+static bool
+__checkparam_dl(const struct sched_attr *attr)
+{
+ return attr && attr->sched_deadline != 0 &&
+ (attr->sched_period == 0 ||
+ (s64)(attr->sched_period - attr->sched_deadline) >= 0) &&
+ (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 &&
+ attr->sched_runtime >= (2 << (DL_SCALE - 1));
+}
+
/*
* check the target process has a UID that matches the current process's
*/
@@ -3281,10 +3249,12 @@ static bool check_same_owner(struct task_struct *p)
return match;
}
-static int __sched_setscheduler(struct task_struct *p, int policy,
- const struct sched_param *param, bool user)
+static int __sched_setscheduler(struct task_struct *p,
+ const struct sched_attr *attr,
+ bool user)
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
+ int policy = attr->sched_policy;
unsigned long flags;
const struct sched_class *prev_class;
struct rq *rq;
@@ -3298,31 +3268,40 @@ recheck:
reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
} else {
- reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
- policy &= ~SCHED_RESET_ON_FORK;
+ reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
- if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ if (policy != SCHED_DEADLINE &&
+ policy != SCHED_FIFO && policy != SCHED_RR &&
policy != SCHED_NORMAL && policy != SCHED_BATCH &&
policy != SCHED_IDLE)
return -EINVAL;
}
+ if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+ return -EINVAL;
+
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
* SCHED_BATCH and SCHED_IDLE is 0.
*/
- if (param->sched_priority < 0 ||
- (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
- (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+ if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+ (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
return -EINVAL;
- if (rt_policy(policy) != (param->sched_priority != 0))
+ if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+ (rt_policy(policy) != (attr->sched_priority != 0)))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (user && !capable(CAP_SYS_NICE)) {
+ if (fair_policy(policy)) {
+ if (attr->sched_nice < TASK_NICE(p) &&
+ !can_nice(p, attr->sched_nice))
+ return -EPERM;
+ }
+
if (rt_policy(policy)) {
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
@@ -3332,8 +3311,8 @@ recheck:
return -EPERM;
/* can't increase priority */
- if (param->sched_priority > p->rt_priority &&
- param->sched_priority > rlim_rtprio)
+ if (attr->sched_priority > p->rt_priority &&
+ attr->sched_priority > rlim_rtprio)
return -EPERM;
}
@@ -3381,14 +3360,21 @@ recheck:
/*
* If not changing anything there's no need to proceed further:
*/
- if (unlikely(policy == p->policy && (!rt_policy(policy) ||
- param->sched_priority == p->rt_priority))) {
+ if (unlikely(policy == p->policy)) {
+ if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+ goto change;
+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+ goto change;
+ if (dl_policy(policy))
+ goto change;
+
task_rq_unlock(rq, p, &flags);
return 0;
}
+change:
-#ifdef CONFIG_RT_GROUP_SCHED
if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
/*
* Do not allow realtime tasks into groups that have no runtime
* assigned.
@@ -3399,8 +3385,24 @@ recheck:
task_rq_unlock(rq, p, &flags);
return -EPERM;
}
- }
#endif
+#ifdef CONFIG_SMP
+ if (dl_bandwidth_enabled() && dl_policy(policy)) {
+ cpumask_t *span = rq->rd->span;
+
+ /*
+ * Don't allow tasks with an affinity mask smaller than
+ * the entire root_domain to become SCHED_DEADLINE. We
+ * will also fail if there's no bandwidth available.
+ */
+ if (!cpumask_subset(span, &p->cpus_allowed) ||
+ rq->rd->dl_bw.bw == 0) {
+ task_rq_unlock(rq, p, &flags);
+ return -EPERM;
+ }
+ }
+#endif
+ }
/* recheck policy now with rq lock held */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
@@ -3408,6 +3410,17 @@ recheck:
task_rq_unlock(rq, p, &flags);
goto recheck;
}
+
+ /*
+ * If setscheduling to SCHED_DEADLINE (or changing the parameters
+ * of a SCHED_DEADLINE task) we need to check if enough bandwidth
+ * is available.
+ */
+ if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+ task_rq_unlock(rq, p, &flags);
+ return -EBUSY;
+ }
+
on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
@@ -3419,7 +3432,7 @@ recheck:
oldprio = p->prio;
prev_class = p->sched_class;
- __setscheduler(rq, p, policy, param->sched_priority);
+ __setscheduler(rq, p, attr);
if (running)
p->sched_class->set_curr_task(rq);
@@ -3434,6 +3447,26 @@ recheck:
return 0;
}
+static int _sched_setscheduler(struct task_struct *p, int policy,
+ const struct sched_param *param, bool check)
+{
+ struct sched_attr attr = {
+ .sched_policy = policy,
+ .sched_priority = param->sched_priority,
+ .sched_nice = PRIO_TO_NICE(p->static_prio),
+ };
+
+ /*
+ * Fixup the legacy SCHED_RESET_ON_FORK hack
+ */
+ if (policy & SCHED_RESET_ON_FORK) {
+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ policy &= ~SCHED_RESET_ON_FORK;
+ attr.sched_policy = policy;
+ }
+
+ return __sched_setscheduler(p, &attr, check);
+}
/**
* sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
* @p: the task in question.
@@ -3447,10 +3480,16 @@ recheck:
int sched_setscheduler(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, true);
+ return _sched_setscheduler(p, policy, param, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
* @p: the task in question.
@@ -3467,7 +3506,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, false);
+ return _sched_setscheduler(p, policy, param, false);
}
static int
@@ -3492,6 +3531,79 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
return retval;
}
+/*
+ * Mimics kernel/events/core.c perf_copy_attr().
+ */
+static int sched_copy_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr)
+{
+ u32 size;
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+ return -EFAULT;
+
+ /*
+ * zero the full structure, so that a short copy will be nice.
+ */
+ memset(attr, 0, sizeof(*attr));
+
+ ret = get_user(size, &uattr->size);
+ if (ret)
+ return ret;
+
+ if (size > PAGE_SIZE) /* silly large */
+ goto err_size;
+
+ if (!size) /* abi compat */
+ size = SCHED_ATTR_SIZE_VER0;
+
+ if (size < SCHED_ATTR_SIZE_VER0)
+ goto err_size;
+
+ /*
+ * If we're handed a bigger struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. new
+ * user-space does not rely on any kernel feature
+ * extensions we dont know about yet.
+ */
+ if (size > sizeof(*attr)) {
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+
+ addr = (void __user *)uattr + sizeof(*attr);
+ end = (void __user *)uattr + size;
+
+ for (; addr < end; addr++) {
+ ret = get_user(val, addr);
+ if (ret)
+ return ret;
+ if (val)
+ goto err_size;
+ }
+ size = sizeof(*attr);
+ }
+
+ ret = copy_from_user(attr, uattr, size);
+ if (ret)
+ return -EFAULT;
+
+ /*
+ * XXX: do we want to be lenient like existing syscalls; or do we want
+ * to be strict and return an error on out-of-bounds values?
+ */
+ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+
+out:
+ return ret;
+
+err_size:
+ put_user(sizeof(*attr), &uattr->size);
+ ret = -E2BIG;
+ goto out;
+}
+
/**
* sys_sched_setscheduler - set/change the scheduler policy and RT priority
* @pid: the pid in question.
@@ -3523,6 +3635,33 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
}
/**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+{
+ struct sched_attr attr;
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0)
+ return -EINVAL;
+
+ if (sched_copy_attr(uattr, &attr))
+ return -EFAULT;
+
+ rcu_read_lock();
+ retval = -ESRCH;
+ p = find_process_by_pid(pid);
+ if (p != NULL)
+ retval = sched_setattr(p, &attr);
+ rcu_read_unlock();
+
+ return retval;
+}
+
+/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
*
@@ -3577,6 +3716,10 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
if (retval)
goto out_unlock;
+ if (task_has_dl_policy(p)) {
+ retval = -EINVAL;
+ goto out_unlock;
+ }
lp.sched_priority = p->rt_priority;
rcu_read_unlock();
@@ -3592,19 +3735,107 @@ out_unlock:
return retval;
}
+static int sched_read_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr,
+ unsigned int usize)
+{
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, usize))
+ return -EFAULT;
+
+ /*
+ * If we're handed a smaller struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. old
+ * user-space does not get uncomplete information.
+ */
+ if (usize < sizeof(*attr)) {
+ unsigned char *addr;
+ unsigned char *end;
+
+ addr = (void *)attr + usize;
+ end = (void *)attr + sizeof(*attr);
+
+ for (; addr < end; addr++) {
+ if (*addr)
+ goto err_size;
+ }
+
+ attr->size = usize;
+ }
+
+ ret = copy_to_user(uattr, attr, usize);
+ if (ret)
+ return -EFAULT;
+
+out:
+ return ret;
+
+err_size:
+ ret = -E2BIG;
+ goto out;
+}
+
+/**
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size)
+{
+ struct sched_attr attr = {
+ .size = sizeof(struct sched_attr),
+ };
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0 || size > PAGE_SIZE ||
+ size < SCHED_ATTR_SIZE_VER0)
+ return -EINVAL;
+
+ rcu_read_lock();
+ p = find_process_by_pid(pid);
+ retval = -ESRCH;
+ if (!p)
+ goto out_unlock;
+
+ retval = security_task_getscheduler(p);
+ if (retval)
+ goto out_unlock;
+
+ attr.sched_policy = p->policy;
+ if (p->sched_reset_on_fork)
+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ if (task_has_dl_policy(p))
+ __getparam_dl(p, &attr);
+ else if (task_has_rt_policy(p))
+ attr.sched_priority = p->rt_priority;
+ else
+ attr.sched_nice = TASK_NICE(p);
+
+ rcu_read_unlock();
+
+ retval = sched_read_attr(uattr, &attr, size);
+ return retval;
+
+out_unlock:
+ rcu_read_unlock();
+ return retval;
+}
+
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
cpumask_var_t cpus_allowed, new_mask;
struct task_struct *p;
int retval;
- get_online_cpus();
rcu_read_lock();
p = find_process_by_pid(pid);
if (!p) {
rcu_read_unlock();
- put_online_cpus();
return -ESRCH;
}
@@ -3638,8 +3869,26 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_unlock;
+
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
+
+ /*
+ * Since bandwidth control happens on root_domain basis,
+ * if admission test is enabled, we only admit -deadline
+ * tasks allowed to run on all the CPUs in the task's
+ * root_domain.
+ */
+#ifdef CONFIG_SMP
+ if (task_has_dl_policy(p)) {
+ const struct cpumask *span = task_rq(p)->rd->span;
+
+ if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+ retval = -EBUSY;
+ goto out_unlock;
+ }
+ }
+#endif
again:
retval = set_cpus_allowed_ptr(p, new_mask);
@@ -3661,7 +3910,6 @@ out_free_cpus_allowed:
free_cpumask_var(cpus_allowed);
out_put_task:
put_task_struct(p);
- put_online_cpus();
return retval;
}
@@ -3706,7 +3954,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
unsigned long flags;
int retval;
- get_online_cpus();
rcu_read_lock();
retval = -ESRCH;
@@ -3719,12 +3966,11 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
goto out_unlock;
raw_spin_lock_irqsave(&p->pi_lock, flags);
- cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+ cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out_unlock:
rcu_read_unlock();
- put_online_cpus();
return retval;
}
@@ -3794,16 +4040,11 @@ SYSCALL_DEFINE0(sched_yield)
return 0;
}
-static inline int should_resched(void)
-{
- return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
-}
-
static void __cond_resched(void)
{
- add_preempt_count(PREEMPT_ACTIVE);
+ __preempt_count_add(PREEMPT_ACTIVE);
__schedule();
- sub_preempt_count(PREEMPT_ACTIVE);
+ __preempt_count_sub(PREEMPT_ACTIVE);
}
int __sched _cond_resched(void)
@@ -3924,7 +4165,7 @@ again:
}
double_rq_lock(rq, p_rq);
- while (task_rq(p) != p_rq) {
+ if (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
@@ -4013,6 +4254,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
case SCHED_RR:
ret = MAX_USER_RT_PRIO-1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -4039,6 +4281,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
case SCHED_RR:
ret = 1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -4186,7 +4429,7 @@ void init_idle(struct task_struct *idle, int cpu)
raw_spin_lock_irqsave(&rq->lock, flags);
- __sched_fork(idle);
+ __sched_fork(0, idle);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
@@ -4212,7 +4455,7 @@ void init_idle(struct task_struct *idle, int cpu)
raw_spin_unlock_irqrestore(&rq->lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
- task_thread_info(idle)->preempt_count = 0;
+ init_idle_preempt_count(idle, cpu);
/*
* The idle tasks have their own, simple scheduling class:
@@ -4346,6 +4589,54 @@ fail:
return ret;
}
+#ifdef CONFIG_NUMA_BALANCING
+/* Migrate current task p to target_cpu */
+int migrate_task_to(struct task_struct *p, int target_cpu)
+{
+ struct migration_arg arg = { p, target_cpu };
+ int curr_cpu = task_cpu(p);
+
+ if (curr_cpu == target_cpu)
+ return 0;
+
+ if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p)))
+ return -EINVAL;
+
+ /* TODO: This is not properly updating schedstats */
+
+ trace_sched_move_numa(p, curr_cpu, target_cpu);
+ return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
+}
+
+/*
+ * Requeue a task on a given node and accurately track the number of NUMA
+ * tasks on the runqueues
+ */
+void sched_setnuma(struct task_struct *p, int nid)
+{
+ struct rq *rq;
+ unsigned long flags;
+ bool on_rq, running;
+
+ rq = task_rq_lock(p, &flags);
+ on_rq = p->on_rq;
+ running = task_current(rq, p);
+
+ if (on_rq)
+ dequeue_task(rq, p, 0);
+ if (running)
+ p->sched_class->put_prev_task(rq, p);
+
+ p->numa_preferred_nid = nid;
+
+ if (running)
+ p->sched_class->set_curr_task(rq);
+ if (on_rq)
+ enqueue_task(rq, p, 0);
+ task_rq_unlock(rq, p, &flags);
+}
+#endif
+
/*
* migration_cpu_stop - this will be executed by a highprio stopper thread
* and performs thread migration by bumping thread off CPU then
@@ -4738,13 +5029,31 @@ static int sched_cpu_active(struct notifier_block *nfb,
static int sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ unsigned long flags;
+ long cpu = (long)hcpu;
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
- set_cpu_active((long)hcpu, false);
+ set_cpu_active(cpu, false);
+
+ /* explicitly allow suspend */
+ if (!(action & CPU_TASKS_FROZEN)) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+ bool overflow;
+ int cpus;
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
+ }
return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
}
+
+ return NOTIFY_DONE;
}
static int __init migration_init(void)
@@ -4963,6 +5272,8 @@ static void free_rootdomain(struct rcu_head *rcu)
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
cpupri_cleanup(&rd->cpupri);
+ cpudl_cleanup(&rd->cpudl);
+ free_cpumask_var(rd->dlo_mask);
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
@@ -4985,7 +5296,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
cpumask_clear_cpu(rq->cpu, old_rd->span);
/*
- * If we dont want to free the old_rt yet then
+ * If we dont want to free the old_rd yet then
* set old_rd to NULL to skip the freeing later
* in this function:
*/
@@ -5014,8 +5325,14 @@ static int init_rootdomain(struct root_domain *rd)
goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
+ if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ goto free_dlo_mask;
+
+ init_dl_bw(&rd->dl_bw);
+ if (cpudl_init(&rd->cpudl) != 0)
+ goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
@@ -5023,6 +5340,8 @@ static int init_rootdomain(struct root_domain *rd)
free_rto_mask:
free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+ free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
@@ -5119,10 +5438,14 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_busy);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
+ struct sched_domain *busy_sd = NULL;
int id = cpu;
int size = 1;
@@ -5130,11 +5453,19 @@ static void update_top_cache_domain(int cpu)
if (sd) {
id = cpumask_first(sched_domain_span(sd));
size = cpumask_weight(sched_domain_span(sd));
+ busy_sd = sd->parent; /* sd_busy */
}
+ rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
per_cpu(sd_llc_size, cpu) = size;
per_cpu(sd_llc_id, cpu) = id;
+
+ sd = lowest_flag_domain(cpu, SD_NUMA);
+ rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+ sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+ rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}
/*
@@ -5325,6 +5656,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
* die on a /0 trap.
*/
sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+ sg->sgp->power_orig = sg->sgp->power;
/*
* Make sure the first group of this domain contains the
@@ -5654,6 +5986,7 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
| 0*SD_SHARE_PKG_RESOURCES
| 1*SD_SERIALIZE
| 0*SD_PREFER_SIBLING
+ | 1*SD_NUMA
| sd_local_flags(level)
,
.last_balance = jiffies,
@@ -6335,14 +6668,17 @@ void __init sched_init_smp(void)
sched_init_numa();
- get_online_cpus();
+ /*
+ * There's no userspace yet to cause hotplug operations; hence all the
+ * cpu masks are stable and all blatant races in the below code cannot
+ * happen.
+ */
mutex_lock(&sched_domains_mutex);
init_sched_domains(cpu_active_mask);
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
if (cpumask_empty(non_isolated_cpus))
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
mutex_unlock(&sched_domains_mutex);
- put_online_cpus();
hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
@@ -6357,6 +6693,7 @@ void __init sched_init_smp(void)
free_cpumask_var(non_isolated_cpus);
init_sched_rt_class();
+ init_sched_dl_class();
}
#else
void __init sched_init_smp(void)
@@ -6426,13 +6763,15 @@ void __init sched_init(void)
#endif /* CONFIG_CPUMASK_OFFSTACK */
}
+ init_rt_bandwidth(&def_rt_bandwidth,
+ global_rt_period(), global_rt_runtime());
+ init_dl_bandwidth(&def_dl_bandwidth,
+ global_rt_period(), global_rt_runtime());
+
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
- init_rt_bandwidth(&def_rt_bandwidth,
- global_rt_period(), global_rt_runtime());
-
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
@@ -6456,6 +6795,7 @@ void __init sched_init(void)
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
init_rt_rq(&rq->rt, rq);
+ init_dl_rq(&rq->dl, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -6505,6 +6845,7 @@ void __init sched_init(void)
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
+ rq->max_idle_balance_cost = sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -6526,10 +6867,6 @@ void __init sched_init(void)
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif
-#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&init_task.pi_waiters);
-#endif
-
/*
* The boot idle thread does lazy MMU switching as well:
*/
@@ -6603,13 +6940,16 @@ EXPORT_SYMBOL(__might_sleep);
static void normalize_task(struct rq *rq, struct task_struct *p)
{
const struct sched_class *prev_class = p->sched_class;
+ struct sched_attr attr = {
+ .sched_policy = SCHED_NORMAL,
+ };
int old_prio = p->prio;
int on_rq;
on_rq = p->on_rq;
if (on_rq)
dequeue_task(rq, p, 0);
- __setscheduler(rq, p, SCHED_NORMAL, 0);
+ __setscheduler(rq, p, &attr);
if (on_rq) {
enqueue_task(rq, p, 0);
resched_task(rq->curr);
@@ -6639,7 +6979,7 @@ void normalize_rt_tasks(void)
p->se.statistics.block_start = 0;
#endif
- if (!rt_task(p)) {
+ if (!dl_task(p) && !rt_task(p)) {
/*
* Renice negative nice level userspace
* tasks back to 0:
@@ -6834,16 +7174,6 @@ void sched_move_task(struct task_struct *tsk)
}
#endif /* CONFIG_CGROUP_SCHED */
-#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
-static unsigned long to_ratio(u64 period, u64 runtime)
-{
- if (runtime == RUNTIME_INF)
- return 1ULL << 20;
-
- return div64_u64(runtime << 20, period);
-}
-#endif
-
#ifdef CONFIG_RT_GROUP_SCHED
/*
* Ensure that the real time constraints are schedulable.
@@ -7017,24 +7347,13 @@ static long sched_group_rt_period(struct task_group *tg)
do_div(rt_period_us, NSEC_PER_USEC);
return rt_period_us;
}
+#endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_RT_GROUP_SCHED
static int sched_rt_global_constraints(void)
{
- u64 runtime, period;
int ret = 0;
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- runtime = global_rt_runtime();
- period = global_rt_period();
-
- /*
- * Sanity check on the sysctl variables.
- */
- if (runtime > period && runtime != RUNTIME_INF)
- return -EINVAL;
-
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
ret = __rt_schedulable(NULL, 0, 0);
@@ -7057,17 +7376,7 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
static int sched_rt_global_constraints(void)
{
unsigned long flags;
- int i;
-
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- /*
- * There's always some RT tasks in the root group
- * -- migration, kstopmachine etc..
- */
- if (sysctl_sched_rt_runtime == 0)
- return -EBUSY;
+ int i, ret = 0;
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
@@ -7079,36 +7388,88 @@ static int sched_rt_global_constraints(void)
}
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
- return 0;
+ return ret;
}
#endif /* CONFIG_RT_GROUP_SCHED */
-int sched_rr_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+static int sched_dl_global_constraints(void)
{
- int ret;
- static DEFINE_MUTEX(mutex);
+ u64 runtime = global_rt_runtime();
+ u64 period = global_rt_period();
+ u64 new_bw = to_ratio(period, runtime);
+ int cpu, ret = 0;
- mutex_lock(&mutex);
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
- /* make sure that internally we keep jiffies */
- /* also, writing zero resets timeslice to default */
- if (!ret && write) {
- sched_rr_timeslice = sched_rr_timeslice <= 0 ?
- RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ /*
+ * Here we want to check the bandwidth not being set to some
+ * value smaller than the currently allocated bandwidth in
+ * any of the root_domains.
+ *
+ * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+ * cycling on root_domains... Discussion on different/better
+ * solutions is welcome!
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock(&dl_b->lock);
+ if (new_bw < dl_b->total_bw)
+ ret = -EBUSY;
+ raw_spin_unlock(&dl_b->lock);
+
+ if (ret)
+ break;
}
- mutex_unlock(&mutex);
+
return ret;
}
+static void sched_dl_do_global(void)
+{
+ u64 new_bw = -1;
+ int cpu;
+
+ def_dl_bandwidth.dl_period = global_rt_period();
+ def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+ if (global_rt_runtime() != RUNTIME_INF)
+ new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+ /*
+ * FIXME: As above...
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock(&dl_b->lock);
+ dl_b->bw = new_bw;
+ raw_spin_unlock(&dl_b->lock);
+ }
+}
+
+static int sched_rt_global_validate(void)
+{
+ if (sysctl_sched_rt_period <= 0)
+ return -EINVAL;
+
+ if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+ return -EINVAL;
+
+ return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+ def_rt_bandwidth.rt_runtime = global_rt_runtime();
+ def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret;
int old_period, old_runtime;
static DEFINE_MUTEX(mutex);
+ int ret;
mutex_lock(&mutex);
old_period = sysctl_sched_rt_period;
@@ -7117,21 +7478,50 @@ int sched_rt_handler(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
+ ret = sched_rt_global_validate();
+ if (ret)
+ goto undo;
+
ret = sched_rt_global_constraints();
- if (ret) {
- sysctl_sched_rt_period = old_period;
- sysctl_sched_rt_runtime = old_runtime;
- } else {
- def_rt_bandwidth.rt_runtime = global_rt_runtime();
- def_rt_bandwidth.rt_period =
- ns_to_ktime(global_rt_period());
- }
+ if (ret)
+ goto undo;
+
+ ret = sched_dl_global_constraints();
+ if (ret)
+ goto undo;
+
+ sched_rt_do_global();
+ sched_dl_do_global();
+ }
+ if (0) {
+undo:
+ sysctl_sched_rt_period = old_period;
+ sysctl_sched_rt_runtime = old_runtime;
}
mutex_unlock(&mutex);
return ret;
}
+int sched_rr_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ static DEFINE_MUTEX(mutex);
+
+ mutex_lock(&mutex);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ /* make sure that internally we keep jiffies */
+ /* also, writing zero resets timeslice to default */
+ if (!ret && write) {
+ sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+ RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ }
+ mutex_unlock(&mutex);
+ return ret;
+}
+
#ifdef CONFIG_CGROUP_SCHED
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -7277,7 +7667,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
runtime_enabled = quota != RUNTIME_INF;
runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
- account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled);
+ /*
+ * If we need to toggle cfs_bandwidth_used, off->on must occur
+ * before making related changes, and on->off must occur afterwards
+ */
+ if (runtime_enabled && !runtime_was_enabled)
+ cfs_bandwidth_usage_inc();
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
@@ -7303,6 +7698,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
unthrottle_cfs_rq(cfs_rq);
raw_spin_unlock_irq(&rq->lock);
}
+ if (runtime_was_enabled && !runtime_enabled)
+ cfs_bandwidth_usage_dec();
out_unlock:
mutex_unlock(&cfs_constraints_mutex);
@@ -7457,15 +7854,14 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
return ret;
}
-static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft,
- struct cgroup_map_cb *cb)
+static int cpu_stats_show(struct seq_file *sf, void *v)
{
- struct task_group *tg = css_tg(css);
+ struct task_group *tg = css_tg(seq_css(sf));
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
- cb->fill(cb, "nr_periods", cfs_b->nr_periods);
- cb->fill(cb, "nr_throttled", cfs_b->nr_throttled);
- cb->fill(cb, "throttled_time", cfs_b->throttled_time);
+ seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
+ seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
+ seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
return 0;
}
@@ -7519,7 +7915,7 @@ static struct cftype cpu_files[] = {
},
{
.name = "stat",
- .read_map = cpu_stats_show,
+ .seq_show = cpu_stats_show,
},
#endif
#ifdef CONFIG_RT_GROUP_SCHED
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index f64722ff0299..622e0818f905 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -163,10 +163,9 @@ out:
return err;
}
-static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *m)
+static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
{
- struct cpuacct *ca = css_ca(css);
+ struct cpuacct *ca = css_ca(seq_css(m));
u64 percpu;
int i;
@@ -183,10 +182,9 @@ static const char * const cpuacct_stat_desc[] = {
[CPUACCT_STAT_SYSTEM] = "system",
};
-static int cpuacct_stats_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct cgroup_map_cb *cb)
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
{
- struct cpuacct *ca = css_ca(css);
+ struct cpuacct *ca = css_ca(seq_css(sf));
int cpu;
s64 val = 0;
@@ -196,7 +194,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
val += kcpustat->cpustat[CPUTIME_NICE];
}
val = cputime64_to_clock_t(val);
- cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+ seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
val = 0;
for_each_online_cpu(cpu) {
@@ -207,7 +205,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
}
val = cputime64_to_clock_t(val);
- cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+ seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
return 0;
}
@@ -220,11 +218,11 @@ static struct cftype files[] = {
},
{
.name = "usage_percpu",
- .read_seq_string = cpuacct_percpu_seq_read,
+ .seq_show = cpuacct_percpu_seq_show,
},
{
.name = "stat",
- .read_map = cpuacct_stats_show,
+ .seq_show = cpuacct_stats_show,
},
{ } /* terminate */
};
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
new file mode 100644
index 000000000000..045fc74e3f09
--- /dev/null
+++ b/kernel/sched/cpudeadline.c
@@ -0,0 +1,216 @@
+/*
+ * kernel/sched/cpudl.c
+ *
+ * Global CPU deadline management
+ *
+ * Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ * 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; version 2
+ * of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+ return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+ return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+ return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+static void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+ int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+ swap(cp->elements[a], cp->elements[b]);
+ swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+}
+
+static void cpudl_heapify(struct cpudl *cp, int idx)
+{
+ int l, r, largest;
+
+ /* adapted from lib/prio_heap.c */
+ while(1) {
+ l = left_child(idx);
+ r = right_child(idx);
+ largest = idx;
+
+ if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+ cp->elements[l].dl))
+ largest = l;
+ if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+ cp->elements[r].dl))
+ largest = r;
+ if (largest == idx)
+ break;
+
+ /* Push idx down the heap one level and bump one up */
+ cpudl_exchange(cp, largest, idx);
+ idx = largest;
+ }
+}
+
+static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+ WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+
+ if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+ cp->elements[idx].dl = new_dl;
+ cpudl_heapify(cp, idx);
+ } else {
+ cp->elements[idx].dl = new_dl;
+ while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+ cp->elements[idx].dl)) {
+ cpudl_exchange(cp, idx, parent(idx));
+ idx = parent(idx);
+ }
+ }
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+ return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask)
+{
+ int best_cpu = -1;
+ const struct sched_dl_entity *dl_se = &p->dl;
+
+ if (later_mask && cpumask_and(later_mask, cp->free_cpus,
+ &p->cpus_allowed) && cpumask_and(later_mask,
+ later_mask, cpu_active_mask)) {
+ best_cpu = cpumask_any(later_mask);
+ goto out;
+ } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+ dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+ best_cpu = cpudl_maximum(cp);
+ if (later_mask)
+ cpumask_set_cpu(best_cpu, later_mask);
+ }
+
+out:
+ WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+
+ return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+ int old_idx, new_cpu;
+ unsigned long flags;
+
+ WARN_ON(cpu > num_present_cpus());
+
+ raw_spin_lock_irqsave(&cp->lock, flags);
+ old_idx = cp->cpu_to_idx[cpu];
+ if (!is_valid) {
+ /* remove item */
+ if (old_idx == IDX_INVALID) {
+ /*
+ * Nothing to remove if old_idx was invalid.
+ * This could happen if a rq_offline_dl is
+ * called for a CPU without -dl tasks running.
+ */
+ goto out;
+ }
+ new_cpu = cp->elements[cp->size - 1].cpu;
+ cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+ cp->elements[old_idx].cpu = new_cpu;
+ cp->size--;
+ cp->cpu_to_idx[new_cpu] = old_idx;
+ cp->cpu_to_idx[cpu] = IDX_INVALID;
+ while (old_idx > 0 && dl_time_before(
+ cp->elements[parent(old_idx)].dl,
+ cp->elements[old_idx].dl)) {
+ cpudl_exchange(cp, old_idx, parent(old_idx));
+ old_idx = parent(old_idx);
+ }
+ cpumask_set_cpu(cpu, cp->free_cpus);
+ cpudl_heapify(cp, old_idx);
+
+ goto out;
+ }
+
+ if (old_idx == IDX_INVALID) {
+ cp->size++;
+ cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].cpu = cpu;
+ cp->cpu_to_idx[cpu] = cp->size - 1;
+ cpudl_change_key(cp, cp->size - 1, dl);
+ cpumask_clear_cpu(cpu, cp->free_cpus);
+ } else {
+ cpudl_change_key(cp, old_idx, dl);
+ }
+
+out:
+ raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+ int i;
+
+ memset(cp, 0, sizeof(*cp));
+ raw_spin_lock_init(&cp->lock);
+ cp->size = 0;
+ for (i = 0; i < NR_CPUS; i++)
+ cp->cpu_to_idx[i] = IDX_INVALID;
+ if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+ return -ENOMEM;
+ cpumask_setall(cp->free_cpus);
+
+ return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+ /*
+ * nothing to do for the moment
+ */
+}
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
new file mode 100644
index 000000000000..a202789a412c
--- /dev/null
+++ b/kernel/sched/cpudeadline.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID -1
+
+struct array_item {
+ u64 dl;
+ int cpu;
+};
+
+struct cpudl {
+ raw_spinlock_t lock;
+ int size;
+ int cpu_to_idx[NR_CPUS];
+ struct array_item elements[NR_CPUS];
+ cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
new file mode 100644
index 000000000000..0de248202879
--- /dev/null
+++ b/kernel/sched/deadline.c
@@ -0,0 +1,1640 @@
+/*
+ * Deadline Scheduling Class (SCHED_DEADLINE)
+ *
+ * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
+ *
+ * Tasks that periodically executes their instances for less than their
+ * runtime won't miss any of their deadlines.
+ * Tasks that are not periodic or sporadic or that tries to execute more
+ * than their reserved bandwidth will be slowed down (and may potentially
+ * miss some of their deadlines), and won't affect any other task.
+ *
+ * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ * Juri Lelli <juri.lelli@gmail.com>,
+ * Michael Trimarchi <michael@amarulasolutions.com>,
+ * Fabio Checconi <fchecconi@gmail.com>
+ */
+#include "sched.h"
+
+#include <linux/slab.h>
+
+struct dl_bandwidth def_dl_bandwidth;
+
+static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
+{
+ return container_of(dl_se, struct task_struct, dl);
+}
+
+static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
+{
+ return container_of(dl_rq, struct rq, dl);
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->dl;
+}
+
+static inline int on_dl_rq(struct sched_dl_entity *dl_se)
+{
+ return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ return dl_rq->rb_leftmost == &dl_se->rb_node;
+}
+
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
+{
+ raw_spin_lock_init(&dl_b->dl_runtime_lock);
+ dl_b->dl_period = period;
+ dl_b->dl_runtime = runtime;
+}
+
+extern unsigned long to_ratio(u64 period, u64 runtime);
+
+void init_dl_bw(struct dl_bw *dl_b)
+{
+ raw_spin_lock_init(&dl_b->lock);
+ raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
+ if (global_rt_runtime() == RUNTIME_INF)
+ dl_b->bw = -1;
+ else
+ dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
+ raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
+ dl_b->total_bw = 0;
+}
+
+void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+{
+ dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+ /* zero means no -deadline tasks */
+ dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+ dl_rq->dl_nr_migratory = 0;
+ dl_rq->overloaded = 0;
+ dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#else
+ init_dl_bw(&dl_rq->dl_bw);
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+ return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+ /*
+ * Must be visible before the overload count is
+ * set (as in sched_rt.c).
+ *
+ * Matched by the barrier in pull_dl_task().
+ */
+ smp_wmb();
+ atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ atomic_dec(&rq->rd->dlo_count);
+ cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+ if (!dl_rq->overloaded) {
+ dl_set_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 1;
+ }
+ } else if (dl_rq->overloaded) {
+ dl_clear_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 0;
+ }
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+ dl_rq->dl_nr_total++;
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory++;
+
+ update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+ dl_rq->dl_nr_total--;
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory--;
+
+ update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+ struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct task_struct *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct task_struct,
+ pushable_dl_tasks);
+ if (dl_entity_preempt(&p->dl, &entry->dl))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+ rb_link_node(&p->pushable_dl_tasks, parent, link);
+ rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+}
+
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+
+ if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+ return;
+
+ if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&p->pushable_dl_tasks);
+ dl_rq->pushable_dl_tasks_leftmost = next_node;
+ }
+
+ rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+ return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags);
+
+/*
+ * We are being explicitly informed that a new instance is starting,
+ * and this means that:
+ * - the absolute deadline of the entity has to be placed at
+ * current time + relative deadline;
+ * - the runtime of the entity has to be set to the maximum value.
+ *
+ * The capability of specifying such event is useful whenever a -deadline
+ * entity wants to (try to!) synchronize its behaviour with the scheduler's
+ * one, and to (try to!) reconcile itself with its own scheduling
+ * parameters.
+ */
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+
+ /*
+ * We use the regular wall clock time to set deadlines in the
+ * future; in fact, we must consider execution overheads (time
+ * spent on hardirq context, etc.).
+ */
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ dl_se->dl_new = 0;
+}
+
+/*
+ * Pure Earliest Deadline First (EDF) scheduling does not deal with the
+ * possibility of a entity lasting more than what it declared, and thus
+ * exhausting its runtime.
+ *
+ * Here we are interested in making runtime overrun possible, but we do
+ * not want a entity which is misbehaving to affect the scheduling of all
+ * other entities.
+ * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
+ * is used, in order to confine each entity within its own bandwidth.
+ *
+ * This function deals exactly with that, and ensures that when the runtime
+ * of a entity is replenished, its deadline is also postponed. That ensures
+ * the overrunning entity can't interfere with other entity in the system and
+ * can't make them miss their deadlines. Reasons why this kind of overruns
+ * could happen are, typically, a entity voluntarily trying to overcome its
+ * runtime, or it just underestimated it during sched_setscheduler_ex().
+ */
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ BUG_ON(pi_se->dl_runtime <= 0);
+
+ /*
+ * This could be the case for a !-dl task that is boosted.
+ * Just go with full inherited parameters.
+ */
+ if (dl_se->dl_deadline == 0) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+
+ /*
+ * We keep moving the deadline away until we get some
+ * available runtime for the entity. This ensures correct
+ * handling of situations where the runtime overrun is
+ * arbitrary large.
+ */
+ while (dl_se->runtime <= 0) {
+ dl_se->deadline += pi_se->dl_period;
+ dl_se->runtime += pi_se->dl_runtime;
+ }
+
+ /*
+ * At this point, the deadline really should be "in
+ * the future" with respect to rq->clock. If it's
+ * not, we are, for some reason, lagging too much!
+ * Anyway, after having warn userspace abut that,
+ * we still try to keep the things running by
+ * resetting the deadline and the budget of the
+ * entity.
+ */
+ if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
+ static bool lag_once = false;
+
+ if (!lag_once) {
+ lag_once = true;
+ printk_sched("sched: DL replenish lagged to much\n");
+ }
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * Here we check if --at time t-- an entity (which is probably being
+ * [re]activated or, in general, enqueued) can use its remaining runtime
+ * and its current deadline _without_ exceeding the bandwidth it is
+ * assigned (function returns true if it can't). We are in fact applying
+ * one of the CBS rules: when a task wakes up, if the residual runtime
+ * over residual deadline fits within the allocated bandwidth, then we
+ * can keep the current (absolute) deadline and residual budget without
+ * disrupting the schedulability of the system. Otherwise, we should
+ * refill the runtime and set the deadline a period in the future,
+ * because keeping the current (absolute) deadline of the task would
+ * result in breaking guarantees promised to other tasks.
+ *
+ * This function returns true if:
+ *
+ * runtime / (deadline - t) > dl_runtime / dl_period ,
+ *
+ * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
+ */
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, u64 t)
+{
+ u64 left, right;
+
+ /*
+ * left and right are the two sides of the equation above,
+ * after a bit of shuffling to use multiplications instead
+ * of divisions.
+ *
+ * Note that none of the time values involved in the two
+ * multiplications are absolute: dl_deadline and dl_runtime
+ * are the relative deadline and the maximum runtime of each
+ * instance, runtime is the runtime left for the last instance
+ * and (deadline - t), since t is rq->clock, is the time left
+ * to the (absolute) deadline. Even if overflowing the u64 type
+ * is very unlikely to occur in both cases, here we scale down
+ * as we want to avoid that risk at all. Scaling down by 10
+ * means that we reduce granularity to 1us. We are fine with it,
+ * since this is only a true/false check and, anyway, thinking
+ * of anything below microseconds resolution is actually fiction
+ * (but still we want to give the user that illusion >;).
+ */
+ left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ right = ((dl_se->deadline - t) >> DL_SCALE) *
+ (pi_se->dl_runtime >> DL_SCALE);
+
+ return dl_time_before(right, left);
+}
+
+/*
+ * When a -deadline entity is queued back on the runqueue, its runtime and
+ * deadline might need updating.
+ *
+ * The policy here is that we update the deadline of the entity only if:
+ * - the current deadline is in the past,
+ * - using the remaining runtime with the current deadline would make
+ * the entity exceed its bandwidth.
+ */
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * The arrival of a new instance needs special treatment, i.e.,
+ * the actual scheduling parameters have to be "renewed".
+ */
+ if (dl_se->dl_new) {
+ setup_new_dl_entity(dl_se, pi_se);
+ return;
+ }
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
+ dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * If the entity depleted all its runtime, and if we want it to sleep
+ * while waiting for some new execution time to become available, we
+ * set the bandwidth enforcement timer to the replenishment instant
+ * and try to activate it.
+ *
+ * Notice that it is important for the caller to know if the timer
+ * actually started or not (i.e., the replenishment instant is in
+ * the future or in the past).
+ */
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+ ktime_t now, act;
+ ktime_t soft, hard;
+ unsigned long range;
+ s64 delta;
+
+ if (boosted)
+ return 0;
+ /*
+ * We want the timer to fire at the deadline, but considering
+ * that it is actually coming from rq->clock and not from
+ * hrtimer's time base reading.
+ */
+ act = ns_to_ktime(dl_se->deadline);
+ now = hrtimer_cb_get_time(&dl_se->dl_timer);
+ delta = ktime_to_ns(now) - rq_clock(rq);
+ act = ktime_add_ns(act, delta);
+
+ /*
+ * If the expiry time already passed, e.g., because the value
+ * chosen as the deadline is too small, don't even try to
+ * start the timer in the past!
+ */
+ if (ktime_us_delta(act, now) < 0)
+ return 0;
+
+ hrtimer_set_expires(&dl_se->dl_timer, act);
+
+ soft = hrtimer_get_softexpires(&dl_se->dl_timer);
+ hard = hrtimer_get_expires(&dl_se->dl_timer);
+ range = ktime_to_ns(ktime_sub(hard, soft));
+ __hrtimer_start_range_ns(&dl_se->dl_timer, soft,
+ range, HRTIMER_MODE_ABS, 0);
+
+ return hrtimer_active(&dl_se->dl_timer);
+}
+
+/*
+ * This is the bandwidth enforcement timer callback. If here, we know
+ * a task is not on its dl_rq, since the fact that the timer was running
+ * means the task is throttled and needs a runtime replenishment.
+ *
+ * However, what we actually do depends on the fact the task is active,
+ * (it is on its rq) or has been removed from there by a call to
+ * dequeue_task_dl(). In the former case we must issue the runtime
+ * replenishment and add the task back to the dl_rq; in the latter, we just
+ * do nothing but clearing dl_throttled, so that runtime and deadline
+ * updating (and the queueing back to dl_rq) will be done by the
+ * next call to enqueue_task_dl().
+ */
+static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
+{
+ struct sched_dl_entity *dl_se = container_of(timer,
+ struct sched_dl_entity,
+ dl_timer);
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * We need to take care of a possible races here. In fact, the
+ * task might have changed its scheduling policy to something
+ * different from SCHED_DEADLINE or changed its reservation
+ * parameters (through sched_setscheduler()).
+ */
+ if (!dl_task(p) || dl_se->dl_new)
+ goto unlock;
+
+ sched_clock_tick();
+ update_rq_clock(rq);
+ dl_se->dl_throttled = 0;
+ if (p->on_rq) {
+ enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+ if (task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ else
+ resched_task(rq->curr);
+#ifdef CONFIG_SMP
+ /*
+ * Queueing this task back might have overloaded rq,
+ * check if we need to kick someone away.
+ */
+ if (has_pushable_dl_tasks(rq))
+ push_dl_task(rq);
+#endif
+ }
+unlock:
+ raw_spin_unlock(&rq->lock);
+
+ return HRTIMER_NORESTART;
+}
+
+void init_dl_task_timer(struct sched_dl_entity *dl_se)
+{
+ struct hrtimer *timer = &dl_se->dl_timer;
+
+ if (hrtimer_active(timer)) {
+ hrtimer_try_to_cancel(timer);
+ return;
+ }
+
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ timer->function = dl_task_timer;
+}
+
+static
+int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
+ int rorun = dl_se->runtime <= 0;
+
+ if (!rorun && !dmiss)
+ return 0;
+
+ /*
+ * If we are beyond our current deadline and we are still
+ * executing, then we have already used some of the runtime of
+ * the next instance. Thus, if we do not account that, we are
+ * stealing bandwidth from the system at each deadline miss!
+ */
+ if (dmiss) {
+ dl_se->runtime = rorun ? dl_se->runtime : 0;
+ dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
+ }
+
+ return 1;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct sched_dl_entity *dl_se = &curr->dl;
+ u64 delta_exec;
+
+ if (!dl_task(curr) || !on_dl_rq(dl_se))
+ return;
+
+ /*
+ * Consumed budget is computed considering the time as
+ * observed by schedulable tasks (excluding time spent
+ * in hardirq context, etc.). Deadlines are instead
+ * computed using hard walltime. This seems to be the more
+ * natural solution, but the full ramifications of this
+ * approach need further study.
+ */
+ delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+ if (unlikely((s64)delta_exec < 0))
+ delta_exec = 0;
+
+ schedstat_set(curr->se.statistics.exec_max,
+ max(curr->se.statistics.exec_max, delta_exec));
+
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+
+ curr->se.exec_start = rq_clock_task(rq);
+ cpuacct_charge(curr, delta_exec);
+
+ sched_rt_avg_update(rq, delta_exec);
+
+ dl_se->runtime -= delta_exec;
+ if (dl_runtime_exceeded(rq, dl_se)) {
+ __dequeue_task_dl(rq, curr, 0);
+ if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
+ dl_se->dl_throttled = 1;
+ else
+ enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+
+ if (!is_leftmost(curr, &rq->dl))
+ resched_task(curr);
+ }
+
+ /*
+ * Because -- for now -- we share the rt bandwidth, we need to
+ * account our runtime there too, otherwise actual rt tasks
+ * would be able to exceed the shared quota.
+ *
+ * Account to the root rt group for now.
+ *
+ * The solution we're working towards is having the RT groups scheduled
+ * using deadline servers -- however there's a few nasties to figure
+ * out before that can happen.
+ */
+ if (rt_bandwidth_enabled()) {
+ struct rt_rq *rt_rq = &rq->rt;
+
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
+ rt_rq->rt_time += delta_exec;
+ /*
+ * We'll let actual RT tasks worry about the overflow here, we
+ * have our own CBS to keep us inline -- see above.
+ */
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ }
+}
+
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+ struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+ if (next && dl_prio(next->prio))
+ return next->dl.deadline;
+ else
+ return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ if (dl_rq->earliest_dl.curr == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+ /*
+ * If the dl_rq had no -deadline tasks, or if the new task
+ * has shorter deadline than the current one on dl_rq, we
+ * know that the previous earliest becomes our next earliest,
+ * as the new task becomes the earliest itself.
+ */
+ dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+ dl_rq->earliest_dl.curr = deadline;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
+ } else if (dl_rq->earliest_dl.next == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+ /*
+ * On the other hand, if the new -deadline task has a
+ * a later deadline than the earliest one on dl_rq, but
+ * it is earlier than the next (if any), we must
+ * recompute the next-earliest.
+ */
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ }
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * Since we may have removed our earliest (and/or next earliest)
+ * task we must recompute them.
+ */
+ if (!dl_rq->dl_nr_running) {
+ dl_rq->earliest_dl.curr = 0;
+ dl_rq->earliest_dl.next = 0;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+ } else {
+ struct rb_node *leftmost = dl_rq->rb_leftmost;
+ struct sched_dl_entity *entry;
+
+ entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+ dl_rq->earliest_dl.curr = entry->deadline;
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
+ }
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+ u64 deadline = dl_se->deadline;
+
+ WARN_ON(!dl_prio(prio));
+ dl_rq->dl_nr_running++;
+
+ inc_dl_deadline(dl_rq, deadline);
+ inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+
+ WARN_ON(!dl_prio(prio));
+ WARN_ON(!dl_rq->dl_nr_running);
+ dl_rq->dl_nr_running--;
+
+ dec_dl_deadline(dl_rq, dl_se->deadline);
+ dec_dl_migration(dl_se, dl_rq);
+}
+
+static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rb_node **link = &dl_rq->rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct sched_dl_entity *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct sched_dl_entity, rb_node);
+ if (dl_time_before(dl_se->deadline, entry->deadline))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->rb_leftmost = &dl_se->rb_node;
+
+ rb_link_node(&dl_se->rb_node, parent, link);
+ rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+
+ inc_dl_tasks(dl_se, dl_rq);
+}
+
+static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+ if (RB_EMPTY_NODE(&dl_se->rb_node))
+ return;
+
+ if (dl_rq->rb_leftmost == &dl_se->rb_node) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&dl_se->rb_node);
+ dl_rq->rb_leftmost = next_node;
+ }
+
+ rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+ RB_CLEAR_NODE(&dl_se->rb_node);
+
+ dec_dl_tasks(dl_se, dl_rq);
+}
+
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, int flags)
+{
+ BUG_ON(on_dl_rq(dl_se));
+
+ /*
+ * If this is a wakeup or a new instance, the scheduling
+ * parameters of the task might need updating. Otherwise,
+ * we want a replenishment of its runtime.
+ */
+ if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
+ replenish_dl_entity(dl_se, pi_se);
+ else
+ update_dl_entity(dl_se, pi_se);
+
+ __enqueue_dl_entity(dl_se);
+}
+
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ __dequeue_dl_entity(dl_se);
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
+ struct sched_dl_entity *pi_se = &p->dl;
+
+ /*
+ * Use the scheduling parameters of the top pi-waiter
+ * task if we have one and its (relative) deadline is
+ * smaller than our one... OTW we keep our runtime and
+ * deadline.
+ */
+ if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+ pi_se = &pi_task->dl;
+
+ /*
+ * If p is throttled, we do nothing. In fact, if it exhausted
+ * its budget it needs a replenishment and, since it now is on
+ * its rq, the bandwidth timer callback (which clearly has not
+ * run yet) will take care of this.
+ */
+ if (p->dl.dl_throttled)
+ return;
+
+ enqueue_dl_entity(&p->dl, pi_se, flags);
+
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+
+ inc_nr_running(rq);
+}
+
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ dequeue_dl_entity(&p->dl);
+ dequeue_pushable_dl_task(rq, p);
+}
+
+static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ update_curr_dl(rq);
+ __dequeue_task_dl(rq, p, flags);
+
+ dec_nr_running(rq);
+}
+
+/*
+ * Yield task semantic for -deadline tasks is:
+ *
+ * get off from the CPU until our next instance, with
+ * a new runtime. This is of little use now, since we
+ * don't have a bandwidth reclaiming mechanism. Anyway,
+ * bandwidth reclaiming is planned for the future, and
+ * yield_task_dl will indicate that some spare budget
+ * is available for other task instances to use it.
+ */
+static void yield_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ /*
+ * We make the task go to sleep until its current deadline by
+ * forcing its runtime to zero. This way, update_curr_dl() stops
+ * it and the bandwidth timer will wake it up and will give it
+ * new scheduling parameters (thanks to dl_new=1).
+ */
+ if (p->dl.runtime > 0) {
+ rq->curr->dl.dl_new = 1;
+ p->dl.runtime = 0;
+ }
+ update_curr_dl(rq);
+}
+
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+ struct task_struct *curr;
+ struct rq *rq;
+
+ if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+ goto out;
+
+ rq = cpu_rq(cpu);
+
+ rcu_read_lock();
+ curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+ /*
+ * If we are dealing with a -deadline task, we must
+ * decide where to wake it up.
+ * If it has a later deadline and the current task
+ * on this rq can't move (provided the waking task
+ * can!) we prefer to send it somewhere else. On the
+ * other hand, if it has a shorter deadline, we
+ * try to make it stay here, it might be important.
+ */
+ if (unlikely(dl_task(curr)) &&
+ (curr->nr_cpus_allowed < 2 ||
+ !dl_entity_preempt(&p->dl, &curr->dl)) &&
+ (p->nr_cpus_allowed > 1)) {
+ int target = find_later_rq(p);
+
+ if (target != -1)
+ cpu = target;
+ }
+ rcu_read_unlock();
+
+out:
+ return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+ /*
+ * Current can't be migrated, useless to reschedule,
+ * let's hope p can move out.
+ */
+ if (rq->curr->nr_cpus_allowed == 1 ||
+ cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
+ return;
+
+ /*
+ * p is migratable, so let's not schedule it and
+ * see if it is pushed or pulled somewhere else.
+ */
+ if (p->nr_cpus_allowed != 1 &&
+ cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
+ return;
+
+ resched_task(rq->curr);
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Only called when both the current and waking task are -deadline
+ * tasks.
+ */
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags)
+{
+ if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
+ resched_task(rq->curr);
+ return;
+ }
+
+#ifdef CONFIG_SMP
+ /*
+ * In the unlikely case current and p have the same deadline
+ * let us try to decide what's the best thing to do...
+ */
+ if ((p->dl.deadline == rq->curr->dl.deadline) &&
+ !test_tsk_need_resched(rq->curr))
+ check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+ s64 delta = p->dl.dl_runtime - p->dl.runtime;
+
+ if (delta > 10000)
+ hrtick_start(rq, p->dl.runtime);
+}
+#endif
+
+static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
+ struct dl_rq *dl_rq)
+{
+ struct rb_node *left = dl_rq->rb_leftmost;
+
+ if (!left)
+ return NULL;
+
+ return rb_entry(left, struct sched_dl_entity, rb_node);
+}
+
+struct task_struct *pick_next_task_dl(struct rq *rq)
+{
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p;
+ struct dl_rq *dl_rq;
+
+ dl_rq = &rq->dl;
+
+ if (unlikely(!dl_rq->dl_nr_running))
+ return NULL;
+
+ dl_se = pick_next_dl_entity(rq, dl_rq);
+ BUG_ON(!dl_se);
+
+ p = dl_task_of(dl_se);
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* Running task will never be pushed. */
+ dequeue_pushable_dl_task(rq, p);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, p);
+#endif
+
+#ifdef CONFIG_SMP
+ rq->post_schedule = has_pushable_dl_tasks(rq);
+#endif /* CONFIG_SMP */
+
+ return p;
+}
+
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+{
+ update_curr_dl(rq);
+
+ if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+}
+
+static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
+{
+ update_curr_dl(rq);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+ start_hrtick_dl(rq, p);
+#endif
+}
+
+static void task_fork_dl(struct task_struct *p)
+{
+ /*
+ * SCHED_DEADLINE tasks cannot fork and this is achieved through
+ * sched_fork()
+ */
+}
+
+static void task_dead_dl(struct task_struct *p)
+{
+ struct hrtimer *timer = &p->dl.dl_timer;
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+ /*
+ * Since we are TASK_DEAD we won't slip out of the domain!
+ */
+ raw_spin_lock_irq(&dl_b->lock);
+ dl_b->total_bw -= p->dl.dl_bw;
+ raw_spin_unlock_irq(&dl_b->lock);
+
+ hrtimer_cancel(timer);
+}
+
+static void set_curr_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* You can't push away the running task */
+ dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+ if (!task_running(rq, p) &&
+ (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+ (p->nr_cpus_allowed > 1))
+ return 1;
+
+ return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+ struct rb_node *next_node = rq->dl.rb_leftmost;
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p = NULL;
+
+next_node:
+ next_node = rb_next(next_node);
+ if (next_node) {
+ dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+ p = dl_task_of(dl_se);
+
+ if (pick_dl_task(rq, p, cpu))
+ return p;
+
+ goto next_node;
+ }
+
+ return NULL;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+ struct sched_domain *sd;
+ struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+ int this_cpu = smp_processor_id();
+ int best_cpu, cpu = task_cpu(task);
+
+ /* Make sure the mask is initialized first */
+ if (unlikely(!later_mask))
+ return -1;
+
+ if (task->nr_cpus_allowed == 1)
+ return -1;
+
+ best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
+ task, later_mask);
+ if (best_cpu == -1)
+ return -1;
+
+ /*
+ * If we are here, some target has been found,
+ * the most suitable of which is cached in best_cpu.
+ * This is, among the runqueues where the current tasks
+ * have later deadlines than the task's one, the rq
+ * with the latest possible one.
+ *
+ * Now we check how well this matches with task's
+ * affinity and system topology.
+ *
+ * The last cpu where the task run is our first
+ * guess, since it is most likely cache-hot there.
+ */
+ if (cpumask_test_cpu(cpu, later_mask))
+ return cpu;
+ /*
+ * Check if this_cpu is to be skipped (i.e., it is
+ * not in the mask) or not.
+ */
+ if (!cpumask_test_cpu(this_cpu, later_mask))
+ this_cpu = -1;
+
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+
+ /*
+ * If possible, preempting this_cpu is
+ * cheaper than migrating.
+ */
+ if (this_cpu != -1 &&
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return this_cpu;
+ }
+
+ /*
+ * Last chance: if best_cpu is valid and is
+ * in the mask, that becomes our choice.
+ */
+ if (best_cpu < nr_cpu_ids &&
+ cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return best_cpu;
+ }
+ }
+ }
+ rcu_read_unlock();
+
+ /*
+ * At this point, all our guesses failed, we just return
+ * 'something', and let the caller sort the things out.
+ */
+ if (this_cpu != -1)
+ return this_cpu;
+
+ cpu = cpumask_any(later_mask);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+
+ return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+ struct rq *later_rq = NULL;
+ int tries;
+ int cpu;
+
+ for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+ cpu = find_later_rq(task);
+
+ if ((cpu == -1) || (cpu == rq->cpu))
+ break;
+
+ later_rq = cpu_rq(cpu);
+
+ /* Retry if something changed. */
+ if (double_lock_balance(rq, later_rq)) {
+ if (unlikely(task_rq(task) != rq ||
+ !cpumask_test_cpu(later_rq->cpu,
+ &task->cpus_allowed) ||
+ task_running(rq, task) || !task->on_rq)) {
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ break;
+ }
+ }
+
+ /*
+ * If the rq we found has no -deadline task, or
+ * its earliest one has a later deadline than our
+ * task, the rq is a good one.
+ */
+ if (!later_rq->dl.dl_nr_running ||
+ dl_time_before(task->dl.deadline,
+ later_rq->dl.earliest_dl.curr))
+ break;
+
+ /* Otherwise we try again. */
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ }
+
+ return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+ struct task_struct *p;
+
+ if (!has_pushable_dl_tasks(rq))
+ return NULL;
+
+ p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+ struct task_struct, pushable_dl_tasks);
+
+ BUG_ON(rq->cpu != task_cpu(p));
+ BUG_ON(task_current(rq, p));
+ BUG_ON(p->nr_cpus_allowed <= 1);
+
+ BUG_ON(!p->on_rq);
+ BUG_ON(!dl_task(p));
+
+ return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+ struct task_struct *next_task;
+ struct rq *later_rq;
+
+ if (!rq->dl.overloaded)
+ return 0;
+
+ next_task = pick_next_pushable_dl_task(rq);
+ if (!next_task)
+ return 0;
+
+retry:
+ if (unlikely(next_task == rq->curr)) {
+ WARN_ON(1);
+ return 0;
+ }
+
+ /*
+ * If next_task preempts rq->curr, and rq->curr
+ * can move away, it makes sense to just reschedule
+ * without going further in pushing next_task.
+ */
+ if (dl_task(rq->curr) &&
+ dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+ rq->curr->nr_cpus_allowed > 1) {
+ resched_task(rq->curr);
+ return 0;
+ }
+
+ /* We might release rq lock */
+ get_task_struct(next_task);
+
+ /* Will lock the rq it'll find */
+ later_rq = find_lock_later_rq(next_task, rq);
+ if (!later_rq) {
+ struct task_struct *task;
+
+ /*
+ * We must check all this again, since
+ * find_lock_later_rq releases rq->lock and it is
+ * then possible that next_task has migrated.
+ */
+ task = pick_next_pushable_dl_task(rq);
+ if (task_cpu(next_task) == rq->cpu && task == next_task) {
+ /*
+ * The task is still there. We don't try
+ * again, some other cpu will pull it when ready.
+ */
+ dequeue_pushable_dl_task(rq, next_task);
+ goto out;
+ }
+
+ if (!task)
+ /* No more tasks */
+ goto out;
+
+ put_task_struct(next_task);
+ next_task = task;
+ goto retry;
+ }
+
+ deactivate_task(rq, next_task, 0);
+ set_task_cpu(next_task, later_rq->cpu);
+ activate_task(later_rq, next_task, 0);
+
+ resched_task(later_rq->curr);
+
+ double_unlock_balance(rq, later_rq);
+
+out:
+ put_task_struct(next_task);
+
+ return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+ /* Terminates as it moves a -deadline task */
+ while (push_dl_task(rq))
+ ;
+}
+
+static int pull_dl_task(struct rq *this_rq)
+{
+ int this_cpu = this_rq->cpu, ret = 0, cpu;
+ struct task_struct *p;
+ struct rq *src_rq;
+ u64 dmin = LONG_MAX;
+
+ if (likely(!dl_overloaded(this_rq)))
+ return 0;
+
+ /*
+ * Match the barrier from dl_set_overloaded; this guarantees that if we
+ * see overloaded we must also see the dlo_mask bit.
+ */
+ smp_rmb();
+
+ for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+ if (this_cpu == cpu)
+ continue;
+
+ src_rq = cpu_rq(cpu);
+
+ /*
+ * It looks racy, abd it is! However, as in sched_rt.c,
+ * we are fine with this.
+ */
+ if (this_rq->dl.dl_nr_running &&
+ dl_time_before(this_rq->dl.earliest_dl.curr,
+ src_rq->dl.earliest_dl.next))
+ continue;
+
+ /* Might drop this_rq->lock */
+ double_lock_balance(this_rq, src_rq);
+
+ /*
+ * If there are no more pullable tasks on the
+ * rq, we're done with it.
+ */
+ if (src_rq->dl.dl_nr_running <= 1)
+ goto skip;
+
+ p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+ /*
+ * We found a task to be pulled if:
+ * - it preempts our current (if there's one),
+ * - it will preempt the last one we pulled (if any).
+ */
+ if (p && dl_time_before(p->dl.deadline, dmin) &&
+ (!this_rq->dl.dl_nr_running ||
+ dl_time_before(p->dl.deadline,
+ this_rq->dl.earliest_dl.curr))) {
+ WARN_ON(p == src_rq->curr);
+ WARN_ON(!p->on_rq);
+
+ /*
+ * Then we pull iff p has actually an earlier
+ * deadline than the current task of its runqueue.
+ */
+ if (dl_time_before(p->dl.deadline,
+ src_rq->curr->dl.deadline))
+ goto skip;
+
+ ret = 1;
+
+ deactivate_task(src_rq, p, 0);
+ set_task_cpu(p, this_cpu);
+ activate_task(this_rq, p, 0);
+ dmin = p->dl.deadline;
+
+ /* Is there any other task even earlier? */
+ }
+skip:
+ double_unlock_balance(this_rq, src_rq);
+ }
+
+ return ret;
+}
+
+static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
+{
+ /* Try to pull other tasks here */
+ if (dl_task(prev))
+ pull_dl_task(rq);
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+ push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+ if (!task_running(rq, p) &&
+ !test_tsk_need_resched(rq->curr) &&
+ has_pushable_dl_tasks(rq) &&
+ p->nr_cpus_allowed > 1 &&
+ dl_task(rq->curr) &&
+ (rq->curr->nr_cpus_allowed < 2 ||
+ dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+ push_dl_tasks(rq);
+ }
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+ const struct cpumask *new_mask)
+{
+ struct rq *rq;
+ int weight;
+
+ BUG_ON(!dl_task(p));
+
+ /*
+ * Update only if the task is actually running (i.e.,
+ * it is on the rq AND it is not throttled).
+ */
+ if (!on_dl_rq(&p->dl))
+ return;
+
+ weight = cpumask_weight(new_mask);
+
+ /*
+ * Only update if the process changes its state from whether it
+ * can migrate or not.
+ */
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
+ return;
+
+ rq = task_rq(p);
+
+ /*
+ * The process used to be able to migrate OR it can now migrate
+ */
+ if (weight <= 1) {
+ if (!task_current(rq, p))
+ dequeue_pushable_dl_task(rq, p);
+ BUG_ON(!rq->dl.dl_nr_migratory);
+ rq->dl.dl_nr_migratory--;
+ } else {
+ if (!task_current(rq, p))
+ enqueue_pushable_dl_task(rq, p);
+ rq->dl.dl_nr_migratory++;
+ }
+
+ update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_set_overload(rq);
+
+ if (rq->dl.dl_nr_running > 0)
+ cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_clear_overload(rq);
+
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+}
+
+void init_sched_dl_class(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+ GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
+static void switched_from_dl(struct rq *rq, struct task_struct *p)
+{
+ if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
+ hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+ /*
+ * Since this might be the only -deadline task on the rq,
+ * this is the right place to try to pull some other one
+ * from an overloaded cpu, if any.
+ */
+ if (!rq->dl.dl_nr_running)
+ pull_dl_task(rq);
+#endif
+}
+
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
+static void switched_to_dl(struct rq *rq, struct task_struct *p)
+{
+ int check_resched = 1;
+
+ /*
+ * If p is throttled, don't consider the possibility
+ * of preempting rq->curr, the check will be done right
+ * after its runtime will get replenished.
+ */
+ if (unlikely(p->dl.dl_throttled))
+ return;
+
+ if (p->on_rq || rq->curr != p) {
+#ifdef CONFIG_SMP
+ if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+ /* Only reschedule if pushing failed */
+ check_resched = 0;
+#endif /* CONFIG_SMP */
+ if (check_resched && task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ }
+}
+
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
+static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+ int oldprio)
+{
+ if (p->on_rq || rq->curr == p) {
+#ifdef CONFIG_SMP
+ /*
+ * This might be too much, but unfortunately
+ * we don't have the old deadline value, and
+ * we can't argue if the task is increasing
+ * or lowering its prio, so...
+ */
+ if (!rq->dl.overloaded)
+ pull_dl_task(rq);
+
+ /*
+ * If we now have a earlier deadline task than p,
+ * then reschedule, provided p is still on this
+ * runqueue.
+ */
+ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+ rq->curr == p)
+ resched_task(p);
+#else
+ /*
+ * Again, we don't know if p has a earlier
+ * or later deadline, so let's blindly set a
+ * (maybe not needed) rescheduling point.
+ */
+ resched_task(p);
+#endif /* CONFIG_SMP */
+ } else
+ switched_to_dl(rq, p);
+}
+
+const struct sched_class dl_sched_class = {
+ .next = &rt_sched_class,
+ .enqueue_task = enqueue_task_dl,
+ .dequeue_task = dequeue_task_dl,
+ .yield_task = yield_task_dl,
+
+ .check_preempt_curr = check_preempt_curr_dl,
+
+ .pick_next_task = pick_next_task_dl,
+ .put_prev_task = put_prev_task_dl,
+
+#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_dl,
+ .set_cpus_allowed = set_cpus_allowed_dl,
+ .rq_online = rq_online_dl,
+ .rq_offline = rq_offline_dl,
+ .pre_schedule = pre_schedule_dl,
+ .post_schedule = post_schedule_dl,
+ .task_woken = task_woken_dl,
+#endif
+
+ .set_curr_task = set_curr_task_dl,
+ .task_tick = task_tick_dl,
+ .task_fork = task_fork_dl,
+ .task_dead = task_dead_dl,
+
+ .prio_changed = prio_changed_dl,
+ .switched_from = switched_from_dl,
+ .switched_to = switched_to_dl,
+};
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 196559994f7c..dd52e7ffb10e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -15,6 +15,7 @@
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
#include <linux/utsname.h>
+#include <linux/mempolicy.h>
#include "sched.h"
@@ -137,6 +138,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
#endif
+#ifdef CONFIG_NUMA_BALANCING
+ SEQ_printf(m, " %d", task_node(p));
+#endif
#ifdef CONFIG_CGROUP_SCHED
SEQ_printf(m, " %s", task_group_path(task_group(p)));
#endif
@@ -159,7 +163,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
read_lock_irqsave(&tasklist_lock, flags);
do_each_thread(g, p) {
- if (!p->on_rq || task_cpu(p) != rq_cpu)
+ if (task_cpu(p) != rq_cpu)
continue;
print_task(m, rq, p);
@@ -225,6 +229,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
atomic_read(&cfs_rq->tg->runnable_avg));
#endif
#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+ SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+ cfs_rq->tg->cfs_bandwidth.timer_active);
+ SEQ_printf(m, " .%-30s: %d\n", "throttled",
+ cfs_rq->throttled);
+ SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
+ cfs_rq->throttle_count);
+#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
print_cfs_group_stats(m, cpu, cfs_rq->tg);
@@ -345,7 +357,7 @@ static void sched_debug_header(struct seq_file *m)
cpu_clk = local_clock();
local_irq_restore(flags);
- SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
+ SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
@@ -359,7 +371,7 @@ static void sched_debug_header(struct seq_file *m)
PN(cpu_clk);
P(jiffies);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- P(sched_clock_stable);
+ P(sched_clock_stable());
#endif
#undef PN
#undef P
@@ -488,6 +500,56 @@ static int __init init_sched_debug_procfs(void)
__initcall(init_sched_debug_procfs);
+#define __P(F) \
+ SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+ SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+ SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+ SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+
+static void sched_show_numa(struct task_struct *p, struct seq_file *m)
+{
+#ifdef CONFIG_NUMA_BALANCING
+ struct mempolicy *pol;
+ int node, i;
+
+ if (p->mm)
+ P(mm->numa_scan_seq);
+
+ task_lock(p);
+ pol = p->mempolicy;
+ if (pol && !(pol->flags & MPOL_F_MORON))
+ pol = NULL;
+ mpol_get(pol);
+ task_unlock(p);
+
+ SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
+
+ for_each_online_node(node) {
+ for (i = 0; i < 2; i++) {
+ unsigned long nr_faults = -1;
+ int cpu_current, home_node;
+
+ if (p->numa_faults)
+ nr_faults = p->numa_faults[2*node + i];
+
+ cpu_current = !i ? (task_node(p) == node) :
+ (pol && node_isset(node, pol->v.nodes));
+
+ home_node = (p->numa_preferred_nid == node);
+
+ SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+ i, node, cpu_current, home_node, nr_faults);
+ }
+ }
+
+ mpol_put(pol);
+#endif
+}
+
void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
unsigned long nr_switches;
@@ -591,6 +653,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
SEQ_printf(m, "%-45s:%21Ld\n",
"clock-delta", (long long)(t1-t0));
}
+
+ sched_show_numa(p, m);
}
void proc_sched_set_task(struct task_struct *p)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c70201fbc61..867b0a4b0893 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,59 +178,61 @@ void sched_init_granularity(void)
update_sysctl();
}
-#if BITS_PER_LONG == 32
-# define WMULT_CONST (~0UL)
-#else
-# define WMULT_CONST (1UL << 32)
-#endif
-
+#define WMULT_CONST (~0U)
#define WMULT_SHIFT 32
-/*
- * Shift right and round:
- */
-#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+static void __update_inv_weight(struct load_weight *lw)
+{
+ unsigned long w;
+
+ if (likely(lw->inv_weight))
+ return;
+
+ w = scale_load_down(lw->weight);
+
+ if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
+ lw->inv_weight = 1;
+ else if (unlikely(!w))
+ lw->inv_weight = WMULT_CONST;
+ else
+ lw->inv_weight = WMULT_CONST / w;
+}
/*
- * delta *= weight / lw
+ * delta_exec * weight / lw.weight
+ * OR
+ * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
+ *
+ * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
+ * we're guaranteed shift stays positive because inv_weight is guaranteed to
+ * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
+ *
+ * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
+ * weight/lw.weight <= 1, and therefore our shift will also be positive.
*/
-static unsigned long
-calc_delta_mine(unsigned long delta_exec, unsigned long weight,
- struct load_weight *lw)
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
{
- u64 tmp;
-
- /*
- * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
- * entities since MIN_SHARES = 2. Treat weight as 1 if less than
- * 2^SCHED_LOAD_RESOLUTION.
- */
- if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
- tmp = (u64)delta_exec * scale_load_down(weight);
- else
- tmp = (u64)delta_exec;
+ u64 fact = scale_load_down(weight);
+ int shift = WMULT_SHIFT;
- if (!lw->inv_weight) {
- unsigned long w = scale_load_down(lw->weight);
+ __update_inv_weight(lw);
- if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
- lw->inv_weight = 1;
- else if (unlikely(!w))
- lw->inv_weight = WMULT_CONST;
- else
- lw->inv_weight = WMULT_CONST / w;
+ if (unlikely(fact >> 32)) {
+ while (fact >> 32) {
+ fact >>= 1;
+ shift--;
+ }
}
- /*
- * Check whether we'd overflow the 64-bit multiplication:
- */
- if (unlikely(tmp > WMULT_CONST))
- tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
- WMULT_SHIFT/2);
- else
- tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+ /* hint to use a 32x32->64 mul */
+ fact = (u64)(u32)fact * lw->inv_weight;
+
+ while (fact >> 32) {
+ fact >>= 1;
+ shift--;
+ }
- return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+ return mul_u64_u32_shr(delta_exec, fact, shift);
}
@@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
#endif /* CONFIG_FAIR_GROUP_SCHED */
static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
/**************************************************************
* Scheduling class tree data structure manipulation methods:
@@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
/*
* delta /= w
*/
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
{
if (unlikely(se->load.weight != NICE_0_LOAD))
- delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+ delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
return delta;
}
@@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_add(&lw, se->load.weight);
load = &lw;
}
- slice = calc_delta_mine(slice, se->load.weight, load);
+ slice = __calc_delta(slice, se->load.weight, load);
}
return slice;
}
@@ -681,6 +682,8 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
#ifdef CONFIG_SMP
+static unsigned long task_h_load(struct task_struct *p);
+
static inline void __update_task_entity_contrib(struct sched_entity *se);
/* Give new task start runnable values to heavy its load in infant time */
@@ -701,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p)
#endif
/*
- * Update the current task's runtime statistics. Skip current tasks that
- * are not in our scheduling class.
+ * Update the current task's runtime statistics.
*/
-static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
- unsigned long delta_exec)
-{
- unsigned long delta_exec_weighted;
-
- schedstat_set(curr->statistics.exec_max,
- max((u64)delta_exec, curr->statistics.exec_max));
-
- curr->sum_exec_runtime += delta_exec;
- schedstat_add(cfs_rq, exec_clock, delta_exec);
- delta_exec_weighted = calc_delta_fair(delta_exec, curr);
-
- curr->vruntime += delta_exec_weighted;
- update_min_vruntime(cfs_rq);
-}
-
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_clock_task(rq_of(cfs_rq));
- unsigned long delta_exec;
+ u64 delta_exec;
if (unlikely(!curr))
return;
- /*
- * Get the amount of time the current task was running
- * since the last time we changed load (this cannot
- * overflow on 32 bits):
- */
- delta_exec = (unsigned long)(now - curr->exec_start);
- if (!delta_exec)
+ delta_exec = now - curr->exec_start;
+ if (unlikely((s64)delta_exec <= 0))
return;
- __update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
+ schedstat_set(curr->statistics.exec_max,
+ max(delta_exec, curr->statistics.exec_max));
+
+ curr->sum_exec_runtime += delta_exec;
+ schedstat_add(cfs_rq, exec_clock, delta_exec);
+
+ curr->vruntime += calc_delta_fair(delta_exec, curr);
+ update_min_vruntime(cfs_rq);
+
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
@@ -818,11 +806,12 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
#ifdef CONFIG_NUMA_BALANCING
/*
- * numa task sample period in ms
+ * Approximate time to scan a full NUMA task in ms. The task scan period is
+ * calculated based on the tasks virtual memory size and
+ * numa_balancing_scan_size.
*/
-unsigned int sysctl_numa_balancing_scan_period_min = 100;
-unsigned int sysctl_numa_balancing_scan_period_max = 100*50;
-unsigned int sysctl_numa_balancing_scan_period_reset = 100*600;
+unsigned int sysctl_numa_balancing_scan_period_min = 1000;
+unsigned int sysctl_numa_balancing_scan_period_max = 60000;
/* Portion of address space to scan in MB */
unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -830,41 +819,830 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
-static void task_numa_placement(struct task_struct *p)
+/*
+ * After skipping a page migration on a shared page, skip N more numa page
+ * migrations unconditionally. This reduces the number of NUMA migrations
+ * in shared memory workloads, and has the effect of pulling tasks towards
+ * where their memory lives, over pulling the memory towards the task.
+ */
+unsigned int sysctl_numa_balancing_migrate_deferred = 16;
+
+static unsigned int task_nr_scan_windows(struct task_struct *p)
+{
+ unsigned long rss = 0;
+ unsigned long nr_scan_pages;
+
+ /*
+ * Calculations based on RSS as non-present and empty pages are skipped
+ * by the PTE scanner and NUMA hinting faults should be trapped based
+ * on resident pages
+ */
+ nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
+ rss = get_mm_rss(p->mm);
+ if (!rss)
+ rss = nr_scan_pages;
+
+ rss = round_up(rss, nr_scan_pages);
+ return rss / nr_scan_pages;
+}
+
+/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
+#define MAX_SCAN_WINDOW 2560
+
+static unsigned int task_scan_min(struct task_struct *p)
+{
+ unsigned int scan, floor;
+ unsigned int windows = 1;
+
+ if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
+ windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+ floor = 1000 / windows;
+
+ scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
+ return max_t(unsigned int, floor, scan);
+}
+
+static unsigned int task_scan_max(struct task_struct *p)
+{
+ unsigned int smin = task_scan_min(p);
+ unsigned int smax;
+
+ /* Watch for min being lower than max due to floor calculations */
+ smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
+ return max(smin, smax);
+}
+
+static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
+{
+ rq->nr_numa_running += (p->numa_preferred_nid != -1);
+ rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
+}
+
+static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
+{
+ rq->nr_numa_running -= (p->numa_preferred_nid != -1);
+ rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
+}
+
+struct numa_group {
+ atomic_t refcount;
+
+ spinlock_t lock; /* nr_tasks, tasks */
+ int nr_tasks;
+ pid_t gid;
+ struct list_head task_list;
+
+ struct rcu_head rcu;
+ unsigned long total_faults;
+ unsigned long faults[0];
+};
+
+pid_t task_numa_group_id(struct task_struct *p)
+{
+ return p->numa_group ? p->numa_group->gid : 0;
+}
+
+static inline int task_faults_idx(int nid, int priv)
+{
+ return 2 * nid + priv;
+}
+
+static inline unsigned long task_faults(struct task_struct *p, int nid)
+{
+ if (!p->numa_faults)
+ return 0;
+
+ return p->numa_faults[task_faults_idx(nid, 0)] +
+ p->numa_faults[task_faults_idx(nid, 1)];
+}
+
+static inline unsigned long group_faults(struct task_struct *p, int nid)
+{
+ if (!p->numa_group)
+ return 0;
+
+ return p->numa_group->faults[task_faults_idx(nid, 0)] +
+ p->numa_group->faults[task_faults_idx(nid, 1)];
+}
+
+/*
+ * These return the fraction of accesses done by a particular task, or
+ * task group, on a particular numa node. The group weight is given a
+ * larger multiplier, in order to group tasks together that are almost
+ * evenly spread out between numa nodes.
+ */
+static inline unsigned long task_weight(struct task_struct *p, int nid)
+{
+ unsigned long total_faults;
+
+ if (!p->numa_faults)
+ return 0;
+
+ total_faults = p->total_numa_faults;
+
+ if (!total_faults)
+ return 0;
+
+ return 1000 * task_faults(p, nid) / total_faults;
+}
+
+static inline unsigned long group_weight(struct task_struct *p, int nid)
+{
+ if (!p->numa_group || !p->numa_group->total_faults)
+ return 0;
+
+ return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
+}
+
+static unsigned long weighted_cpuload(const int cpu);
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long power_of(int cpu);
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
+
+/* Cached statistics for all CPUs within a node */
+struct numa_stats {
+ unsigned long nr_running;
+ unsigned long load;
+
+ /* Total compute capacity of CPUs on a node */
+ unsigned long power;
+
+ /* Approximate capacity in terms of runnable tasks on a node */
+ unsigned long capacity;
+ int has_capacity;
+};
+
+/*
+ * XXX borrowed from update_sg_lb_stats
+ */
+static void update_numa_stats(struct numa_stats *ns, int nid)
+{
+ int cpu, cpus = 0;
+
+ memset(ns, 0, sizeof(*ns));
+ for_each_cpu(cpu, cpumask_of_node(nid)) {
+ struct rq *rq = cpu_rq(cpu);
+
+ ns->nr_running += rq->nr_running;
+ ns->load += weighted_cpuload(cpu);
+ ns->power += power_of(cpu);
+
+ cpus++;
+ }
+
+ /*
+ * If we raced with hotplug and there are no CPUs left in our mask
+ * the @ns structure is NULL'ed and task_numa_compare() will
+ * not find this node attractive.
+ *
+ * We'll either bail at !has_capacity, or we'll detect a huge imbalance
+ * and bail there.
+ */
+ if (!cpus)
+ return;
+
+ ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power;
+ ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE);
+ ns->has_capacity = (ns->nr_running < ns->capacity);
+}
+
+struct task_numa_env {
+ struct task_struct *p;
+
+ int src_cpu, src_nid;
+ int dst_cpu, dst_nid;
+
+ struct numa_stats src_stats, dst_stats;
+
+ int imbalance_pct;
+
+ struct task_struct *best_task;
+ long best_imp;
+ int best_cpu;
+};
+
+static void task_numa_assign(struct task_numa_env *env,
+ struct task_struct *p, long imp)
+{
+ if (env->best_task)
+ put_task_struct(env->best_task);
+ if (p)
+ get_task_struct(p);
+
+ env->best_task = p;
+ env->best_imp = imp;
+ env->best_cpu = env->dst_cpu;
+}
+
+/*
+ * This checks if the overall compute and NUMA accesses of the system would
+ * be improved if the source tasks was migrated to the target dst_cpu taking
+ * into account that it might be best if task running on the dst_cpu should
+ * be exchanged with the source task
+ */
+static void task_numa_compare(struct task_numa_env *env,
+ long taskimp, long groupimp)
+{
+ struct rq *src_rq = cpu_rq(env->src_cpu);
+ struct rq *dst_rq = cpu_rq(env->dst_cpu);
+ struct task_struct *cur;
+ long dst_load, src_load;
+ long load;
+ long imp = (groupimp > 0) ? groupimp : taskimp;
+
+ rcu_read_lock();
+ cur = ACCESS_ONCE(dst_rq->curr);
+ if (cur->pid == 0) /* idle */
+ cur = NULL;
+
+ /*
+ * "imp" is the fault differential for the source task between the
+ * source and destination node. Calculate the total differential for
+ * the source task and potential destination task. The more negative
+ * the value is, the more rmeote accesses that would be expected to
+ * be incurred if the tasks were swapped.
+ */
+ if (cur) {
+ /* Skip this swap candidate if cannot move to the source cpu */
+ if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
+ goto unlock;
+
+ /*
+ * If dst and source tasks are in the same NUMA group, or not
+ * in any group then look only at task weights.
+ */
+ if (cur->numa_group == env->p->numa_group) {
+ imp = taskimp + task_weight(cur, env->src_nid) -
+ task_weight(cur, env->dst_nid);
+ /*
+ * Add some hysteresis to prevent swapping the
+ * tasks within a group over tiny differences.
+ */
+ if (cur->numa_group)
+ imp -= imp/16;
+ } else {
+ /*
+ * Compare the group weights. If a task is all by
+ * itself (not part of a group), use the task weight
+ * instead.
+ */
+ if (env->p->numa_group)
+ imp = groupimp;
+ else
+ imp = taskimp;
+
+ if (cur->numa_group)
+ imp += group_weight(cur, env->src_nid) -
+ group_weight(cur, env->dst_nid);
+ else
+ imp += task_weight(cur, env->src_nid) -
+ task_weight(cur, env->dst_nid);
+ }
+ }
+
+ if (imp < env->best_imp)
+ goto unlock;
+
+ if (!cur) {
+ /* Is there capacity at our destination? */
+ if (env->src_stats.has_capacity &&
+ !env->dst_stats.has_capacity)
+ goto unlock;
+
+ goto balance;
+ }
+
+ /* Balance doesn't matter much if we're running a task per cpu */
+ if (src_rq->nr_running == 1 && dst_rq->nr_running == 1)
+ goto assign;
+
+ /*
+ * In the overloaded case, try and keep the load balanced.
+ */
+balance:
+ dst_load = env->dst_stats.load;
+ src_load = env->src_stats.load;
+
+ /* XXX missing power terms */
+ load = task_h_load(env->p);
+ dst_load += load;
+ src_load -= load;
+
+ if (cur) {
+ load = task_h_load(cur);
+ dst_load -= load;
+ src_load += load;
+ }
+
+ /* make src_load the smaller */
+ if (dst_load < src_load)
+ swap(dst_load, src_load);
+
+ if (src_load * env->imbalance_pct < dst_load * 100)
+ goto unlock;
+
+assign:
+ task_numa_assign(env, cur, imp);
+unlock:
+ rcu_read_unlock();
+}
+
+static void task_numa_find_cpu(struct task_numa_env *env,
+ long taskimp, long groupimp)
+{
+ int cpu;
+
+ for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
+ /* Skip this CPU if the source task cannot migrate */
+ if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p)))
+ continue;
+
+ env->dst_cpu = cpu;
+ task_numa_compare(env, taskimp, groupimp);
+ }
+}
+
+static int task_numa_migrate(struct task_struct *p)
+{
+ struct task_numa_env env = {
+ .p = p,
+
+ .src_cpu = task_cpu(p),
+ .src_nid = task_node(p),
+
+ .imbalance_pct = 112,
+
+ .best_task = NULL,
+ .best_imp = 0,
+ .best_cpu = -1
+ };
+ struct sched_domain *sd;
+ unsigned long taskweight, groupweight;
+ int nid, ret;
+ long taskimp, groupimp;
+
+ /*
+ * Pick the lowest SD_NUMA domain, as that would have the smallest
+ * imbalance and would be the first to start moving tasks about.
+ *
+ * And we want to avoid any moving of tasks about, as that would create
+ * random movement of tasks -- counter the numa conditions we're trying
+ * to satisfy here.
+ */
+ rcu_read_lock();
+ sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
+ if (sd)
+ env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
+ rcu_read_unlock();
+
+ /*
+ * Cpusets can break the scheduler domain tree into smaller
+ * balance domains, some of which do not cross NUMA boundaries.
+ * Tasks that are "trapped" in such domains cannot be migrated
+ * elsewhere, so there is no point in (re)trying.
+ */
+ if (unlikely(!sd)) {
+ p->numa_preferred_nid = task_node(p);
+ return -EINVAL;
+ }
+
+ taskweight = task_weight(p, env.src_nid);
+ groupweight = group_weight(p, env.src_nid);
+ update_numa_stats(&env.src_stats, env.src_nid);
+ env.dst_nid = p->numa_preferred_nid;
+ taskimp = task_weight(p, env.dst_nid) - taskweight;
+ groupimp = group_weight(p, env.dst_nid) - groupweight;
+ update_numa_stats(&env.dst_stats, env.dst_nid);
+
+ /* If the preferred nid has capacity, try to use it. */
+ if (env.dst_stats.has_capacity)
+ task_numa_find_cpu(&env, taskimp, groupimp);
+
+ /* No space available on the preferred nid. Look elsewhere. */
+ if (env.best_cpu == -1) {
+ for_each_online_node(nid) {
+ if (nid == env.src_nid || nid == p->numa_preferred_nid)
+ continue;
+
+ /* Only consider nodes where both task and groups benefit */
+ taskimp = task_weight(p, nid) - taskweight;
+ groupimp = group_weight(p, nid) - groupweight;
+ if (taskimp < 0 && groupimp < 0)
+ continue;
+
+ env.dst_nid = nid;
+ update_numa_stats(&env.dst_stats, env.dst_nid);
+ task_numa_find_cpu(&env, taskimp, groupimp);
+ }
+ }
+
+ /* No better CPU than the current one was found. */
+ if (env.best_cpu == -1)
+ return -EAGAIN;
+
+ sched_setnuma(p, env.dst_nid);
+
+ /*
+ * Reset the scan period if the task is being rescheduled on an
+ * alternative node to recheck if the tasks is now properly placed.
+ */
+ p->numa_scan_period = task_scan_min(p);
+
+ if (env.best_task == NULL) {
+ ret = migrate_task_to(p, env.best_cpu);
+ if (ret != 0)
+ trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
+ return ret;
+ }
+
+ ret = migrate_swap(p, env.best_task);
+ if (ret != 0)
+ trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
+ put_task_struct(env.best_task);
+ return ret;
+}
+
+/* Attempt to migrate a task to a CPU on the preferred node. */
+static void numa_migrate_preferred(struct task_struct *p)
+{
+ /* This task has no NUMA fault statistics yet */
+ if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+ return;
+
+ /* Periodically retry migrating the task to the preferred node */
+ p->numa_migrate_retry = jiffies + HZ;
+
+ /* Success if task is already running on preferred CPU */
+ if (task_node(p) == p->numa_preferred_nid)
+ return;
+
+ /* Otherwise, try migrate to a CPU on the preferred node */
+ task_numa_migrate(p);
+}
+
+/*
+ * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
+ * increments. The more local the fault statistics are, the higher the scan
+ * period will be for the next scan window. If local/remote ratio is below
+ * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the
+ * scan period will decrease
+ */
+#define NUMA_PERIOD_SLOTS 10
+#define NUMA_PERIOD_THRESHOLD 3
+
+/*
+ * Increase the scan period (slow down scanning) if the majority of
+ * our memory is already on our local node, or if the majority of
+ * the page accesses are shared with other processes.
+ * Otherwise, decrease the scan period.
+ */
+static void update_task_scan_period(struct task_struct *p,
+ unsigned long shared, unsigned long private)
{
- int seq;
+ unsigned int period_slot;
+ int ratio;
+ int diff;
+
+ unsigned long remote = p->numa_faults_locality[0];
+ unsigned long local = p->numa_faults_locality[1];
+
+ /*
+ * If there were no record hinting faults then either the task is
+ * completely idle or all activity is areas that are not of interest
+ * to automatic numa balancing. Scan slower
+ */
+ if (local + shared == 0) {
+ p->numa_scan_period = min(p->numa_scan_period_max,
+ p->numa_scan_period << 1);
+
+ p->mm->numa_next_scan = jiffies +
+ msecs_to_jiffies(p->numa_scan_period);
- if (!p->mm) /* for example, ksmd faulting in a user's mm */
return;
+ }
+
+ /*
+ * Prepare to scale scan period relative to the current period.
+ * == NUMA_PERIOD_THRESHOLD scan period stays the same
+ * < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
+ * >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
+ */
+ period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
+ ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
+ if (ratio >= NUMA_PERIOD_THRESHOLD) {
+ int slot = ratio - NUMA_PERIOD_THRESHOLD;
+ if (!slot)
+ slot = 1;
+ diff = slot * period_slot;
+ } else {
+ diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
+
+ /*
+ * Scale scan rate increases based on sharing. There is an
+ * inverse relationship between the degree of sharing and
+ * the adjustment made to the scanning period. Broadly
+ * speaking the intent is that there is little point
+ * scanning faster if shared accesses dominate as it may
+ * simply bounce migrations uselessly
+ */
+ ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+ diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
+ }
+
+ p->numa_scan_period = clamp(p->numa_scan_period + diff,
+ task_scan_min(p), task_scan_max(p));
+ memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+}
+
+static void task_numa_placement(struct task_struct *p)
+{
+ int seq, nid, max_nid = -1, max_group_nid = -1;
+ unsigned long max_faults = 0, max_group_faults = 0;
+ unsigned long fault_types[2] = { 0, 0 };
+ spinlock_t *group_lock = NULL;
+
seq = ACCESS_ONCE(p->mm->numa_scan_seq);
if (p->numa_scan_seq == seq)
return;
p->numa_scan_seq = seq;
+ p->numa_scan_period_max = task_scan_max(p);
+
+ /* If the task is part of a group prevent parallel updates to group stats */
+ if (p->numa_group) {
+ group_lock = &p->numa_group->lock;
+ spin_lock(group_lock);
+ }
+
+ /* Find the node with the highest number of faults */
+ for_each_online_node(nid) {
+ unsigned long faults = 0, group_faults = 0;
+ int priv, i;
+
+ for (priv = 0; priv < 2; priv++) {
+ long diff;
+
+ i = task_faults_idx(nid, priv);
+ diff = -p->numa_faults[i];
+
+ /* Decay existing window, copy faults since last scan */
+ p->numa_faults[i] >>= 1;
+ p->numa_faults[i] += p->numa_faults_buffer[i];
+ fault_types[priv] += p->numa_faults_buffer[i];
+ p->numa_faults_buffer[i] = 0;
+
+ faults += p->numa_faults[i];
+ diff += p->numa_faults[i];
+ p->total_numa_faults += diff;
+ if (p->numa_group) {
+ /* safe because we can only change our own group */
+ p->numa_group->faults[i] += diff;
+ p->numa_group->total_faults += diff;
+ group_faults += p->numa_group->faults[i];
+ }
+ }
+
+ if (faults > max_faults) {
+ max_faults = faults;
+ max_nid = nid;
+ }
+
+ if (group_faults > max_group_faults) {
+ max_group_faults = group_faults;
+ max_group_nid = nid;
+ }
+ }
+
+ update_task_scan_period(p, fault_types[0], fault_types[1]);
+
+ if (p->numa_group) {
+ /*
+ * If the preferred task and group nids are different,
+ * iterate over the nodes again to find the best place.
+ */
+ if (max_nid != max_group_nid) {
+ unsigned long weight, max_weight = 0;
+
+ for_each_online_node(nid) {
+ weight = task_weight(p, nid) + group_weight(p, nid);
+ if (weight > max_weight) {
+ max_weight = weight;
+ max_nid = nid;
+ }
+ }
+ }
+
+ spin_unlock(group_lock);
+ }
+
+ /* Preferred node as the node with the most faults */
+ if (max_faults && max_nid != p->numa_preferred_nid) {
+ /* Update the preferred nid and migrate task if possible */
+ sched_setnuma(p, max_nid);
+ numa_migrate_preferred(p);
+ }
+}
+
+static inline int get_numa_group(struct numa_group *grp)
+{
+ return atomic_inc_not_zero(&grp->refcount);
+}
+
+static inline void put_numa_group(struct numa_group *grp)
+{
+ if (atomic_dec_and_test(&grp->refcount))
+ kfree_rcu(grp, rcu);
+}
+
+static void task_numa_group(struct task_struct *p, int cpupid, int flags,
+ int *priv)
+{
+ struct numa_group *grp, *my_grp;
+ struct task_struct *tsk;
+ bool join = false;
+ int cpu = cpupid_to_cpu(cpupid);
+ int i;
+
+ if (unlikely(!p->numa_group)) {
+ unsigned int size = sizeof(struct numa_group) +
+ 2*nr_node_ids*sizeof(unsigned long);
+
+ grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+ if (!grp)
+ return;
+
+ atomic_set(&grp->refcount, 1);
+ spin_lock_init(&grp->lock);
+ INIT_LIST_HEAD(&grp->task_list);
+ grp->gid = p->pid;
- /* FIXME: Scheduling placement policy hints go here */
+ for (i = 0; i < 2*nr_node_ids; i++)
+ grp->faults[i] = p->numa_faults[i];
+
+ grp->total_faults = p->total_numa_faults;
+
+ list_add(&p->numa_entry, &grp->task_list);
+ grp->nr_tasks++;
+ rcu_assign_pointer(p->numa_group, grp);
+ }
+
+ rcu_read_lock();
+ tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+
+ if (!cpupid_match_pid(tsk, cpupid))
+ goto no_join;
+
+ grp = rcu_dereference(tsk->numa_group);
+ if (!grp)
+ goto no_join;
+
+ my_grp = p->numa_group;
+ if (grp == my_grp)
+ goto no_join;
+
+ /*
+ * Only join the other group if its bigger; if we're the bigger group,
+ * the other task will join us.
+ */
+ if (my_grp->nr_tasks > grp->nr_tasks)
+ goto no_join;
+
+ /*
+ * Tie-break on the grp address.
+ */
+ if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
+ goto no_join;
+
+ /* Always join threads in the same process. */
+ if (tsk->mm == current->mm)
+ join = true;
+
+ /* Simple filter to avoid false positives due to PID collisions */
+ if (flags & TNF_SHARED)
+ join = true;
+
+ /* Update priv based on whether false sharing was detected */
+ *priv = !join;
+
+ if (join && !get_numa_group(grp))
+ goto no_join;
+
+ rcu_read_unlock();
+
+ if (!join)
+ return;
+
+ double_lock(&my_grp->lock, &grp->lock);
+
+ for (i = 0; i < 2*nr_node_ids; i++) {
+ my_grp->faults[i] -= p->numa_faults[i];
+ grp->faults[i] += p->numa_faults[i];
+ }
+ my_grp->total_faults -= p->total_numa_faults;
+ grp->total_faults += p->total_numa_faults;
+
+ list_move(&p->numa_entry, &grp->task_list);
+ my_grp->nr_tasks--;
+ grp->nr_tasks++;
+
+ spin_unlock(&my_grp->lock);
+ spin_unlock(&grp->lock);
+
+ rcu_assign_pointer(p->numa_group, grp);
+
+ put_numa_group(my_grp);
+ return;
+
+no_join:
+ rcu_read_unlock();
+ return;
+}
+
+void task_numa_free(struct task_struct *p)
+{
+ struct numa_group *grp = p->numa_group;
+ int i;
+ void *numa_faults = p->numa_faults;
+
+ if (grp) {
+ spin_lock(&grp->lock);
+ for (i = 0; i < 2*nr_node_ids; i++)
+ grp->faults[i] -= p->numa_faults[i];
+ grp->total_faults -= p->total_numa_faults;
+
+ list_del(&p->numa_entry);
+ grp->nr_tasks--;
+ spin_unlock(&grp->lock);
+ rcu_assign_pointer(p->numa_group, NULL);
+ put_numa_group(grp);
+ }
+
+ p->numa_faults = NULL;
+ p->numa_faults_buffer = NULL;
+ kfree(numa_faults);
}
/*
* Got a PROT_NONE fault for a page on @node.
*/
-void task_numa_fault(int node, int pages, bool migrated)
+void task_numa_fault(int last_cpupid, int node, int pages, int flags)
{
struct task_struct *p = current;
+ bool migrated = flags & TNF_MIGRATED;
+ int priv;
if (!numabalancing_enabled)
return;
- /* FIXME: Allocate task-specific structure for placement policy here */
+ /* for example, ksmd faulting in a user's mm */
+ if (!p->mm)
+ return;
+
+ /* Do not worry about placement if exiting */
+ if (p->state == TASK_DEAD)
+ return;
+
+ /* Allocate buffer to track faults on a per-node basis */
+ if (unlikely(!p->numa_faults)) {
+ int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+
+ /* numa_faults and numa_faults_buffer share the allocation */
+ p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
+ if (!p->numa_faults)
+ return;
+
+ BUG_ON(p->numa_faults_buffer);
+ p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+ p->total_numa_faults = 0;
+ memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+ }
/*
- * If pages are properly placed (did not migrate) then scan slower.
- * This is reset periodically in case of phase changes
+ * First accesses are treated as private, otherwise consider accesses
+ * to be private if the accessing pid has not changed
*/
- if (!migrated)
- p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
- p->numa_scan_period + jiffies_to_msecs(10));
+ if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
+ priv = 1;
+ } else {
+ priv = cpupid_match_pid(p, last_cpupid);
+ if (!priv && !(flags & TNF_NO_GROUP))
+ task_numa_group(p, last_cpupid, flags, &priv);
+ }
task_numa_placement(p);
+
+ /*
+ * Retry task to preferred node migration periodically, in case it
+ * case it previously failed, or the scheduler moved us.
+ */
+ if (time_after(jiffies, p->numa_migrate_retry))
+ numa_migrate_preferred(p);
+
+ if (migrated)
+ p->numa_pages_migrated += pages;
+
+ p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+ p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
}
static void reset_ptenuma_scan(struct task_struct *p)
@@ -884,6 +1662,7 @@ void task_numa_work(struct callback_head *work)
struct mm_struct *mm = p->mm;
struct vm_area_struct *vma;
unsigned long start, end;
+ unsigned long nr_pte_updates = 0;
long pages;
WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -900,35 +1679,9 @@ void task_numa_work(struct callback_head *work)
if (p->flags & PF_EXITING)
return;
- /*
- * We do not care about task placement until a task runs on a node
- * other than the first one used by the address space. This is
- * largely because migrations are driven by what CPU the task
- * is running on. If it's never scheduled on another node, it'll
- * not migrate so why bother trapping the fault.
- */
- if (mm->first_nid == NUMA_PTE_SCAN_INIT)
- mm->first_nid = numa_node_id();
- if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
- /* Are we running on a new node yet? */
- if (numa_node_id() == mm->first_nid &&
- !sched_feat_numa(NUMA_FORCE))
- return;
-
- mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
- }
-
- /*
- * Reset the scan period if enough time has gone by. Objective is that
- * scanning will be reduced if pages are properly placed. As tasks
- * can enter different phases this needs to be re-examined. Lacking
- * proper tracking of reference behaviour, this blunt hammer is used.
- */
- migrate = mm->numa_next_reset;
- if (time_after(now, migrate)) {
- p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
- next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
- xchg(&mm->numa_next_reset, next_scan);
+ if (!mm->numa_next_scan) {
+ mm->numa_next_scan = now +
+ msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
}
/*
@@ -938,20 +1691,20 @@ void task_numa_work(struct callback_head *work)
if (time_before(now, migrate))
return;
- if (p->numa_scan_period == 0)
- p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+ if (p->numa_scan_period == 0) {
+ p->numa_scan_period_max = task_scan_max(p);
+ p->numa_scan_period = task_scan_min(p);
+ }
next_scan = now + msecs_to_jiffies(p->numa_scan_period);
if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
return;
/*
- * Do not set pte_numa if the current running node is rate-limited.
- * This loses statistics on the fault but if we are unwilling to
- * migrate to this node, it is less likely we can do useful work
+ * Delay this task enough that another task of this mm will likely win
+ * the next time around.
*/
- if (migrate_ratelimited(numa_node_id()))
- return;
+ p->node_stamp += 2 * TICK_NSEC;
start = mm->numa_scan_offset;
pages = sysctl_numa_balancing_scan_size;
@@ -967,18 +1720,39 @@ void task_numa_work(struct callback_head *work)
vma = mm->mmap;
}
for (; vma; vma = vma->vm_next) {
- if (!vma_migratable(vma))
+ if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
continue;
- /* Skip small VMAs. They are not likely to be of relevance */
- if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
+ /*
+ * Shared library pages mapped by multiple processes are not
+ * migrated as it is expected they are cache replicated. Avoid
+ * hinting faults in read-only file-backed mappings or the vdso
+ * as migrating the pages will be of marginal benefit.
+ */
+ if (!vma->vm_mm ||
+ (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
+ continue;
+
+ /*
+ * Skip inaccessible VMAs to avoid any confusion between
+ * PROT_NONE and NUMA hinting ptes
+ */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
continue;
do {
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
end = min(end, vma->vm_end);
- pages -= change_prot_numa(vma, start, end);
+ nr_pte_updates += change_prot_numa(vma, start, end);
+
+ /*
+ * Scan sysctl_numa_balancing_scan_size but ensure that
+ * at least one PTE is updated so that unused virtual
+ * address space is quickly skipped.
+ */
+ if (nr_pte_updates)
+ pages -= (end - start) >> PAGE_SHIFT;
start = end;
if (pages <= 0)
@@ -988,10 +1762,10 @@ void task_numa_work(struct callback_head *work)
out:
/*
- * It is possible to reach the end of the VMA list but the last few VMAs are
- * not guaranteed to the vma_migratable. If they are not, we would find the
- * !migratable VMA on the next scan but not reset the scanner to the start
- * so check it now.
+ * It is possible to reach the end of the VMA list but the last few
+ * VMAs are not guaranteed to the vma_migratable. If they are not, we
+ * would find the !migratable VMA on the next scan but not reset the
+ * scanner to the start so check it now.
*/
if (vma)
mm->numa_scan_offset = start;
@@ -1025,8 +1799,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
if (now - curr->node_stamp > period) {
if (!curr->node_stamp)
- curr->numa_scan_period = sysctl_numa_balancing_scan_period_min;
- curr->node_stamp = now;
+ curr->numa_scan_period = task_scan_min(curr);
+ curr->node_stamp += period;
if (!time_before(jiffies, curr->mm->numa_next_scan)) {
init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
@@ -1038,6 +1812,14 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
}
+
+static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
+{
+}
#endif /* CONFIG_NUMA_BALANCING */
static void
@@ -1047,8 +1829,12 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
if (!parent_entity(se))
update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
- if (entity_is_task(se))
- list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+ if (entity_is_task(se)) {
+ struct rq *rq = rq_of(cfs_rq);
+
+ account_numa_enqueue(rq, task_of(se));
+ list_add(&se->group_node, &rq->cfs_tasks);
+ }
#endif
cfs_rq->nr_running++;
}
@@ -1059,8 +1845,10 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
update_load_sub(&rq_of(cfs_rq)->load, se->load.weight);
- if (entity_is_task(se))
+ if (entity_is_task(se)) {
+ account_numa_dequeue(rq_of(cfs_rq), task_of(se));
list_del_init(&se->group_node);
+ }
cfs_rq->nr_running--;
}
@@ -1378,7 +2166,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
long contrib;
/* The fraction of a cpu used by this cfs_rq */
- contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT,
+ contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
sa->runnable_avg_period + 1);
contrib -= cfs_rq->tg_runnable_contrib;
@@ -2070,13 +2858,14 @@ static inline bool cfs_bandwidth_used(void)
return static_key_false(&__cfs_bandwidth_used);
}
-void account_cfs_bandwidth_used(int enabled, int was_enabled)
+void cfs_bandwidth_usage_inc(void)
+{
+ static_key_slow_inc(&__cfs_bandwidth_used);
+}
+
+void cfs_bandwidth_usage_dec(void)
{
- /* only need to count groups transitioning between enabled/!enabled */
- if (enabled && !was_enabled)
- static_key_slow_inc(&__cfs_bandwidth_used);
- else if (!enabled && was_enabled)
- static_key_slow_dec(&__cfs_bandwidth_used);
+ static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
@@ -2084,7 +2873,8 @@ static bool cfs_bandwidth_used(void)
return true;
}
-void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
+void cfs_bandwidth_usage_inc(void) {}
+void cfs_bandwidth_usage_dec(void) {}
#endif /* HAVE_JUMP_LABEL */
/*
@@ -2213,8 +3003,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
}
}
-static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
- unsigned long delta_exec)
+static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
@@ -2232,7 +3021,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
}
static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
return;
@@ -2335,6 +3124,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (!cfs_b->timer_active)
+ __start_cfs_bandwidth(cfs_b);
raw_spin_unlock(&cfs_b->lock);
}
@@ -2448,6 +3239,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
if (idle)
goto out_unlock;
+ /*
+ * if we have relooped after returning idle once, we need to update our
+ * status as actually running, so that other cpus doing
+ * __start_cfs_bandwidth will stop trying to cancel us.
+ */
+ cfs_b->timer_active = 1;
+
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
@@ -2508,7 +3306,13 @@ static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
/* how long we wait to gather additional slack before distributing */
static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
-/* are we near the end of the current quota period? */
+/*
+ * Are we near the end of the current quota period?
+ *
+ * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
+ * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * migrate_hrtimers, base is never cleared, so we are fine.
+ */
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
{
struct hrtimer *refresh_timer = &cfs_b->period_timer;
@@ -2584,10 +3388,12 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
u64 expires;
/* confirm we're still not at a refresh boundary */
- if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
+ raw_spin_lock(&cfs_b->lock);
+ if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
+ raw_spin_unlock(&cfs_b->lock);
return;
+ }
- raw_spin_lock(&cfs_b->lock);
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
runtime = cfs_b->runtime;
cfs_b->runtime = 0;
@@ -2708,11 +3514,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
* (timer_active==0 becomes visible before the hrtimer call-back
* terminates). In either case we ensure that it's re-programmed
*/
- while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+ while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+ hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+ /* bounce the lock to allow do_sched_cfs_period_timer to run */
raw_spin_unlock(&cfs_b->lock);
- /* ensure cfs_b->lock is available while we wait */
- hrtimer_cancel(&cfs_b->period_timer);
-
+ cpu_relax();
raw_spin_lock(&cfs_b->lock);
/* if someone else restarted the timer then we're done */
if (cfs_b->timer_active)
@@ -2755,8 +3561,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
return rq_clock_task(rq_of(cfs_rq));
}
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
- unsigned long delta_exec) {}
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -3166,8 +3971,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
}
#else
-static inline unsigned long effective_load(struct task_group *tg, int cpu,
- unsigned long wl, unsigned long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
return wl;
}
@@ -3292,12 +4096,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
- int this_cpu, int load_idx)
+ int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
+ int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
+ if (sd_flag & SD_BALANCE_WAKE)
+ load_idx = sd->wake_idx;
+
do {
unsigned long load, avg_load;
int local_group;
@@ -3420,11 +4228,10 @@ done:
* preempt must be disabled.
*/
static int
-select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
- int prev_cpu = task_cpu(p);
int new_cpu = cpu;
int want_affine = 0;
int sync = wake_flags & WF_SYNC;
@@ -3466,7 +4273,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
}
while (sd) {
- int load_idx = sd->forkexec_idx;
struct sched_group *group;
int weight;
@@ -3475,10 +4281,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
continue;
}
- if (sd_flag & SD_BALANCE_WAKE)
- load_idx = sd->wake_idx;
-
- group = find_idlest_group(sd, p, cpu, load_idx);
+ group = find_idlest_group(sd, p, cpu, sd_flag);
if (!group) {
sd = sd->child;
continue;
@@ -3904,9 +4707,12 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+enum fbq_type { regular, remote, all };
+
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
-#define LBF_SOME_PINNED 0x04
+#define LBF_DST_PINNED 0x04
+#define LBF_SOME_PINNED 0x08
struct lb_env {
struct sched_domain *sd;
@@ -3929,6 +4735,8 @@ struct lb_env {
unsigned int loop;
unsigned int loop_break;
unsigned int loop_max;
+
+ enum fbq_type fbq_type;
};
/*
@@ -3975,6 +4783,78 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
return delta < (s64)sysctl_sched_migration_cost;
}
+#ifdef CONFIG_NUMA_BALANCING
+/* Returns true if the destination node has incurred more faults */
+static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
+{
+ int src_nid, dst_nid;
+
+ if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+ !(env->sd->flags & SD_NUMA)) {
+ return false;
+ }
+
+ src_nid = cpu_to_node(env->src_cpu);
+ dst_nid = cpu_to_node(env->dst_cpu);
+
+ if (src_nid == dst_nid)
+ return false;
+
+ /* Always encourage migration to the preferred node. */
+ if (dst_nid == p->numa_preferred_nid)
+ return true;
+
+ /* If both task and group weight improve, this move is a winner. */
+ if (task_weight(p, dst_nid) > task_weight(p, src_nid) &&
+ group_weight(p, dst_nid) > group_weight(p, src_nid))
+ return true;
+
+ return false;
+}
+
+
+static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
+{
+ int src_nid, dst_nid;
+
+ if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
+ return false;
+
+ if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ return false;
+
+ src_nid = cpu_to_node(env->src_cpu);
+ dst_nid = cpu_to_node(env->dst_cpu);
+
+ if (src_nid == dst_nid)
+ return false;
+
+ /* Migrating away from the preferred node is always bad. */
+ if (src_nid == p->numa_preferred_nid)
+ return true;
+
+ /* If either task or group weight get worse, don't do it. */
+ if (task_weight(p, dst_nid) < task_weight(p, src_nid) ||
+ group_weight(p, dst_nid) < group_weight(p, src_nid))
+ return true;
+
+ return false;
+}
+
+#else
+static inline bool migrate_improves_locality(struct task_struct *p,
+ struct lb_env *env)
+{
+ return false;
+}
+
+static inline bool migrate_degrades_locality(struct task_struct *p,
+ struct lb_env *env)
+{
+ return false;
+}
+#endif
+
/*
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
@@ -3997,6 +4877,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+ env->flags |= LBF_SOME_PINNED;
+
/*
* Remember if this task can be migrated to any other cpu in
* our sched_group. We may want to revisit it if we couldn't
@@ -4005,13 +4887,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* Also avoid computing new_dst_cpu if we have already computed
* one in current iteration.
*/
- if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
+ if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
return 0;
/* Prevent to re-select dst_cpu via env's cpus */
for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
- env->flags |= LBF_SOME_PINNED;
+ env->flags |= LBF_DST_PINNED;
env->new_dst_cpu = cpu;
break;
}
@@ -4030,11 +4912,24 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/*
* Aggressive migration if:
- * 1) task is cache cold, or
- * 2) too many balance attempts have failed.
+ * 1) destination numa is preferred
+ * 2) task is cache cold, or
+ * 3) too many balance attempts have failed.
*/
-
tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+ if (!tsk_cache_hot)
+ tsk_cache_hot = migrate_degrades_locality(p, env);
+
+ if (migrate_improves_locality(p, env)) {
+#ifdef CONFIG_SCHEDSTATS
+ if (tsk_cache_hot) {
+ schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+ schedstat_inc(p, se.statistics.nr_forced_migrations);
+ }
+#endif
+ return 1;
+ }
+
if (!tsk_cache_hot ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
@@ -4077,8 +4972,6 @@ static int move_one_task(struct lb_env *env)
return 0;
}
-static unsigned long task_h_load(struct task_struct *p);
-
static const unsigned int sched_nr_migrate_break = 32;
/*
@@ -4291,6 +5184,10 @@ struct sg_lb_stats {
unsigned int group_weight;
int group_imb; /* Is there an imbalance in the group ? */
int group_has_capacity; /* Is there extra capacity in the group? */
+#ifdef CONFIG_NUMA_BALANCING
+ unsigned int nr_numa_running;
+ unsigned int nr_preferred_running;
+#endif
};
/*
@@ -4330,7 +5227,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
/**
* get_sd_load_idx - Obtain the load index for a given sched domain.
* @sd: The sched_domain whose load_idx is to be obtained.
- * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ * @idle: The idle status of the CPU for whose sd load_idx is obtained.
*
* Return: The load index.
*/
@@ -4447,7 +5344,7 @@ void update_group_power(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long power;
+ unsigned long power, power_orig;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
@@ -4459,7 +5356,7 @@ void update_group_power(struct sched_domain *sd, int cpu)
return;
}
- power = 0;
+ power_orig = power = 0;
if (child->flags & SD_OVERLAP) {
/*
@@ -4467,8 +5364,33 @@ void update_group_power(struct sched_domain *sd, int cpu)
* span the current group.
*/
- for_each_cpu(cpu, sched_group_cpus(sdg))
- power += power_of(cpu);
+ for_each_cpu(cpu, sched_group_cpus(sdg)) {
+ struct sched_group_power *sgp;
+ struct rq *rq = cpu_rq(cpu);
+
+ /*
+ * build_sched_domains() -> init_sched_groups_power()
+ * gets here before we've attached the domains to the
+ * runqueues.
+ *
+ * Use power_of(), which is set irrespective of domains
+ * in update_cpu_power().
+ *
+ * This avoids power/power_orig from being 0 and
+ * causing divide-by-zero issues on boot.
+ *
+ * Runtime updates will correct power_orig.
+ */
+ if (unlikely(!rq->sd)) {
+ power_orig += power_of(cpu);
+ power += power_of(cpu);
+ continue;
+ }
+
+ sgp = rq->sd->groups->sgp;
+ power_orig += sgp->power_orig;
+ power += sgp->power;
+ }
} else {
/*
* !SD_OVERLAP domains can assume that child groups
@@ -4477,12 +5399,14 @@ void update_group_power(struct sched_domain *sd, int cpu)
group = child->groups;
do {
+ power_orig += group->sgp->power_orig;
power += group->sgp->power;
group = group->next;
} while (group != child->groups);
}
- sdg->sgp->power_orig = sdg->sgp->power = power;
+ sdg->sgp->power_orig = power_orig;
+ sdg->sgp->power = power;
}
/*
@@ -4526,13 +5450,12 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
* cpu 3 and leave one of the cpus in the second group unused.
*
* The current solution to this issue is detecting the skew in the first group
- * by noticing it has a cpu that is overloaded while the remaining cpus are
- * idle -- or rather, there's a distinct imbalance in the cpus; see
- * sg_imbalanced().
+ * by noticing the lower domain failed to reach balance and had difficulty
+ * moving tasks due to affinity constraints.
*
* When this is so detected; this group becomes a candidate for busiest; see
- * update_sd_pick_busiest(). And calculcate_imbalance() and
- * find_busiest_group() avoid some of the usual balance conditional to allow it
+ * update_sd_pick_busiest(). And calculate_imbalance() and
+ * find_busiest_group() avoid some of the usual balance conditions to allow it
* to create an effective group imbalance.
*
* This is a somewhat tricky proposition since the next run might not find the
@@ -4540,49 +5463,36 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
* subtle and fragile situation.
*/
-struct sg_imb_stats {
- unsigned long max_nr_running, min_nr_running;
- unsigned long max_cpu_load, min_cpu_load;
-};
-
-static inline void init_sg_imb_stats(struct sg_imb_stats *sgi)
+static inline int sg_imbalanced(struct sched_group *group)
{
- sgi->max_cpu_load = sgi->max_nr_running = 0UL;
- sgi->min_cpu_load = sgi->min_nr_running = ~0UL;
+ return group->sgp->imbalance;
}
-static inline void
-update_sg_imb_stats(struct sg_imb_stats *sgi,
- unsigned long load, unsigned long nr_running)
+/*
+ * Compute the group capacity.
+ *
+ * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by
+ * first dividing out the smt factor and computing the actual number of cores
+ * and limit power unit capacity with that.
+ */
+static inline int sg_capacity(struct lb_env *env, struct sched_group *group)
{
- if (load > sgi->max_cpu_load)
- sgi->max_cpu_load = load;
- if (sgi->min_cpu_load > load)
- sgi->min_cpu_load = load;
+ unsigned int capacity, smt, cpus;
+ unsigned int power, power_orig;
- if (nr_running > sgi->max_nr_running)
- sgi->max_nr_running = nr_running;
- if (sgi->min_nr_running > nr_running)
- sgi->min_nr_running = nr_running;
-}
+ power = group->sgp->power;
+ power_orig = group->sgp->power_orig;
+ cpus = group->group_weight;
-static inline int
-sg_imbalanced(struct sg_lb_stats *sgs, struct sg_imb_stats *sgi)
-{
- /*
- * Consider the group unbalanced when the imbalance is larger
- * than the average weight of a task.
- *
- * APZ: with cgroup the avg task weight can vary wildly and
- * might not be a suitable number - should we keep a
- * normalized nr_running number somewhere that negates
- * the hierarchy?
- */
- if ((sgi->max_cpu_load - sgi->min_cpu_load) >= sgs->load_per_task &&
- (sgi->max_nr_running - sgi->min_nr_running) > 1)
- return 1;
+ /* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */
+ smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig);
+ capacity = cpus / smt; /* cores */
- return 0;
+ capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE));
+ if (!capacity)
+ capacity = fix_small_capacity(env->sd, group);
+
+ return capacity;
}
/**
@@ -4597,37 +5507,31 @@ static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs)
{
- struct sg_imb_stats sgi;
- unsigned long nr_running;
unsigned long load;
int i;
- init_sg_imb_stats(&sgi);
+ memset(sgs, 0, sizeof(*sgs));
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
- nr_running = rq->nr_running;
-
/* Bias balancing toward cpus of our domain */
- if (local_group) {
+ if (local_group)
load = target_load(i, load_idx);
- } else {
+ else
load = source_load(i, load_idx);
- update_sg_imb_stats(&sgi, load, nr_running);
- }
sgs->group_load += load;
- sgs->sum_nr_running += nr_running;
+ sgs->sum_nr_running += rq->nr_running;
+#ifdef CONFIG_NUMA_BALANCING
+ sgs->nr_numa_running += rq->nr_numa_running;
+ sgs->nr_preferred_running += rq->nr_preferred_running;
+#endif
sgs->sum_weighted_load += weighted_cpuload(i);
if (idle_cpu(i))
sgs->idle_cpus++;
}
- if (local_group && (env->idle != CPU_NEWLY_IDLE ||
- time_after_eq(jiffies, group->sgp->next_update)))
- update_group_power(env->sd, env->dst_cpu);
-
/* Adjust by relative CPU power of the group */
sgs->group_power = group->sgp->power;
sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power;
@@ -4635,16 +5539,11 @@ static inline void update_sg_lb_stats(struct lb_env *env,
if (sgs->sum_nr_running)
sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- sgs->group_imb = sg_imbalanced(sgs, &sgi);
-
- sgs->group_capacity =
- DIV_ROUND_CLOSEST(sgs->group_power, SCHED_POWER_SCALE);
-
- if (!sgs->group_capacity)
- sgs->group_capacity = fix_small_capacity(env->sd, group);
-
sgs->group_weight = group->group_weight;
+ sgs->group_imb = sg_imbalanced(group);
+ sgs->group_capacity = sg_capacity(env, group);
+
if (sgs->group_capacity > sgs->sum_nr_running)
sgs->group_has_capacity = 1;
}
@@ -4693,14 +5592,42 @@ static bool update_sd_pick_busiest(struct lb_env *env,
return false;
}
+#ifdef CONFIG_NUMA_BALANCING
+static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
+{
+ if (sgs->sum_nr_running > sgs->nr_numa_running)
+ return regular;
+ if (sgs->sum_nr_running > sgs->nr_preferred_running)
+ return remote;
+ return all;
+}
+
+static inline enum fbq_type fbq_classify_rq(struct rq *rq)
+{
+ if (rq->nr_running > rq->nr_numa_running)
+ return regular;
+ if (rq->nr_running > rq->nr_preferred_running)
+ return remote;
+ return all;
+}
+#else
+static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
+{
+ return all;
+}
+
+static inline enum fbq_type fbq_classify_rq(struct rq *rq)
+{
+ return regular;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
- * @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
-static inline void update_sd_lb_stats(struct lb_env *env,
- struct sd_lb_stats *sds)
+static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
@@ -4720,11 +5647,17 @@ static inline void update_sd_lb_stats(struct lb_env *env,
if (local_group) {
sds->local = sg;
sgs = &sds->local_stat;
+
+ if (env->idle != CPU_NEWLY_IDLE ||
+ time_after_eq(jiffies, sg->sgp->next_update))
+ update_group_power(env->sd, env->dst_cpu);
}
- memset(sgs, 0, sizeof(*sgs));
update_sg_lb_stats(env, sg, load_idx, local_group, sgs);
+ if (local_group)
+ goto next_group;
+
/*
* In case the child domain prefers tasks go to siblings
* first, lower the sg capacity to one so that we'll try
@@ -4735,21 +5668,25 @@ static inline void update_sd_lb_stats(struct lb_env *env,
* heaviest group when it is already under-utilized (possible
* with a large weight task outweighs the tasks on the system).
*/
- if (prefer_sibling && !local_group &&
- sds->local && sds->local_stat.group_has_capacity)
+ if (prefer_sibling && sds->local &&
+ sds->local_stat.group_has_capacity)
sgs->group_capacity = min(sgs->group_capacity, 1U);
- /* Now, start updating sd_lb_stats */
- sds->total_load += sgs->group_load;
- sds->total_pwr += sgs->group_power;
-
- if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
+ if (update_sd_pick_busiest(env, sds, sg, sgs)) {
sds->busiest = sg;
sds->busiest_stat = *sgs;
}
+next_group:
+ /* Now, start updating sd_lb_stats */
+ sds->total_load += sgs->group_load;
+ sds->total_pwr += sgs->group_power;
+
sg = sg->next;
} while (sg != env->sd->groups);
+
+ if (env->sd->flags & SD_NUMA)
+ env->fbq_type = fbq_classify_group(&sds->busiest_stat);
}
/**
@@ -5053,15 +5990,39 @@ static struct rq *find_busiest_queue(struct lb_env *env,
int i;
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
- unsigned long power = power_of(i);
- unsigned long capacity = DIV_ROUND_CLOSEST(power,
- SCHED_POWER_SCALE);
- unsigned long wl;
+ unsigned long power, capacity, wl;
+ enum fbq_type rt;
+
+ rq = cpu_rq(i);
+ rt = fbq_classify_rq(rq);
+
+ /*
+ * We classify groups/runqueues into three groups:
+ * - regular: there are !numa tasks
+ * - remote: there are numa tasks that run on the 'wrong' node
+ * - all: there is no distinction
+ *
+ * In order to avoid migrating ideally placed numa tasks,
+ * ignore those when there's better options.
+ *
+ * If we ignore the actual busiest queue to migrate another
+ * task, the next balance pass can still reduce the busiest
+ * queue by moving tasks around inside the node.
+ *
+ * If we cannot move enough load due to this classification
+ * the next pass will adjust the group classification and
+ * allow migration of more tasks.
+ *
+ * Both cases only affect the total convergence complexity.
+ */
+ if (rt > env->fbq_type)
+ continue;
+ power = power_of(i);
+ capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
if (!capacity)
capacity = fix_small_capacity(env->sd, group);
- rq = cpu_rq(i);
wl = weighted_cpuload(i);
/*
@@ -5164,6 +6125,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
int *continue_balancing)
{
int ld_moved, cur_ld_moved, active_balance = 0;
+ struct sched_domain *sd_parent = sd->parent;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
@@ -5177,6 +6139,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.idle = idle,
.loop_break = sched_nr_migrate_break,
.cpus = cpus,
+ .fbq_type = all,
};
/*
@@ -5268,17 +6231,17 @@ more_balance:
* moreover subsequent load balance cycles should correct the
* excess load moved.
*/
- if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
+ if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
+
+ /* Prevent to re-select dst_cpu via env's cpus */
+ cpumask_clear_cpu(env.dst_cpu, env.cpus);
env.dst_rq = cpu_rq(env.new_dst_cpu);
env.dst_cpu = env.new_dst_cpu;
- env.flags &= ~LBF_SOME_PINNED;
+ env.flags &= ~LBF_DST_PINNED;
env.loop = 0;
env.loop_break = sched_nr_migrate_break;
- /* Prevent to re-select dst_cpu via env's cpus */
- cpumask_clear_cpu(env.dst_cpu, env.cpus);
-
/*
* Go back to "more_balance" rather than "redo" since we
* need to continue with same src_cpu.
@@ -5286,6 +6249,18 @@ more_balance:
goto more_balance;
}
+ /*
+ * We failed to reach balance because of affinity.
+ */
+ if (sd_parent) {
+ int *group_imbalance = &sd_parent->groups->sgp->imbalance;
+
+ if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
+ *group_imbalance = 1;
+ } else if (*group_imbalance)
+ *group_imbalance = 0;
+ }
+
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
cpumask_clear_cpu(cpu_of(busiest), cpus);
@@ -5393,6 +6368,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
struct sched_domain *sd;
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ u64 curr_cost = 0;
this_rq->idle_stamp = rq_clock(this_rq);
@@ -5409,15 +6385,27 @@ void idle_balance(int this_cpu, struct rq *this_rq)
for_each_domain(this_cpu, sd) {
unsigned long interval;
int continue_balancing = 1;
+ u64 t0, domain_cost;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
+ if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
+ break;
+
if (sd->flags & SD_BALANCE_NEWIDLE) {
+ t0 = sched_clock_cpu(this_cpu);
+
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance(this_cpu, this_rq,
sd, CPU_NEWLY_IDLE,
&continue_balancing);
+
+ domain_cost = sched_clock_cpu(this_cpu) - t0;
+ if (domain_cost > sd->max_newidle_lb_cost)
+ sd->max_newidle_lb_cost = domain_cost;
+
+ curr_cost += domain_cost;
}
interval = msecs_to_jiffies(sd->balance_interval);
@@ -5439,6 +6427,9 @@ void idle_balance(int this_cpu, struct rq *this_rq)
*/
this_rq->next_balance = next_balance;
}
+
+ if (curr_cost > this_rq->max_idle_balance_cost)
+ this_rq->max_idle_balance_cost = curr_cost;
}
/*
@@ -5522,7 +6513,7 @@ static struct {
unsigned long next_balance; /* in jiffy units */
} nohz ____cacheline_aligned;
-static inline int find_new_ilb(int call_cpu)
+static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
@@ -5537,13 +6528,13 @@ static inline int find_new_ilb(int call_cpu)
* nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
* CPU (if there is one).
*/
-static void nohz_balancer_kick(int cpu)
+static void nohz_balancer_kick(void)
{
int ilb_cpu;
nohz.next_balance++;
- ilb_cpu = find_new_ilb(cpu);
+ ilb_cpu = find_new_ilb();
if (ilb_cpu >= nr_cpu_ids)
return;
@@ -5572,16 +6563,16 @@ static inline void nohz_balance_exit_idle(int cpu)
static inline void set_cpu_sd_state_busy(void)
{
struct sched_domain *sd;
+ int cpu = smp_processor_id();
rcu_read_lock();
- sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));
if (!sd || !sd->nohz_idle)
goto unlock;
sd->nohz_idle = 0;
- for (; sd; sd = sd->parent)
- atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+ atomic_inc(&sd->groups->sgp->nr_busy_cpus);
unlock:
rcu_read_unlock();
}
@@ -5589,16 +6580,16 @@ unlock:
void set_cpu_sd_state_idle(void)
{
struct sched_domain *sd;
+ int cpu = smp_processor_id();
rcu_read_lock();
- sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));
if (!sd || sd->nohz_idle)
goto unlock;
sd->nohz_idle = 1;
- for (; sd; sd = sd->parent)
- atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+ atomic_dec(&sd->groups->sgp->nr_busy_cpus);
unlock:
rcu_read_unlock();
}
@@ -5653,24 +6644,48 @@ void update_max_interval(void)
*
* Balancing parameters are set up in init_sched_domains.
*/
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
{
int continue_balancing = 1;
- struct rq *rq = cpu_rq(cpu);
+ int cpu = rq->cpu;
unsigned long interval;
struct sched_domain *sd;
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
- int need_serialize;
+ int need_serialize, need_decay = 0;
+ u64 max_cost = 0;
update_blocked_averages(cpu);
rcu_read_lock();
for_each_domain(cpu, sd) {
+ /*
+ * Decay the newidle max times here because this is a regular
+ * visit to all the domains. Decay ~1% per second.
+ */
+ if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
+ sd->max_newidle_lb_cost =
+ (sd->max_newidle_lb_cost * 253) / 256;
+ sd->next_decay_max_lb_cost = jiffies + HZ;
+ need_decay = 1;
+ }
+ max_cost += sd->max_newidle_lb_cost;
+
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
+ /*
+ * Stop the load balance at this level. There is another
+ * CPU in our sched group which is doing load balancing more
+ * actively.
+ */
+ if (!continue_balancing) {
+ if (need_decay)
+ continue;
+ break;
+ }
+
interval = sd->balance_interval;
if (idle != CPU_IDLE)
interval *= sd->busy_factor;
@@ -5689,7 +6704,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
if (time_after_eq(jiffies, sd->last_balance + interval)) {
if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
/*
- * The LBF_SOME_PINNED logic could have changed
+ * The LBF_DST_PINNED logic could have changed
* env->dst_cpu, so we can't know our idle
* state even if we migrated tasks. Update it.
*/
@@ -5704,14 +6719,14 @@ out:
next_balance = sd->last_balance + interval;
update_next_balance = 1;
}
-
+ }
+ if (need_decay) {
/*
- * Stop the load balance at this level. There is another
- * CPU in our sched group which is doing load balancing more
- * actively.
+ * Ensure the rq-wide value also decays but keep it at a
+ * reasonable floor to avoid funnies with rq->avg_idle.
*/
- if (!continue_balancing)
- break;
+ rq->max_idle_balance_cost =
+ max((u64)sysctl_sched_migration_cost, max_cost);
}
rcu_read_unlock();
@@ -5729,9 +6744,9 @@ out:
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
* rebalancing for all the cpus for whom scheduler ticks are stopped.
*/
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
{
- struct rq *this_rq = cpu_rq(this_cpu);
+ int this_cpu = this_rq->cpu;
struct rq *rq;
int balance_cpu;
@@ -5758,7 +6773,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
update_idle_cpu_load(rq);
raw_spin_unlock_irq(&rq->lock);
- rebalance_domains(balance_cpu, CPU_IDLE);
+ rebalance_domains(rq, CPU_IDLE);
if (time_after(this_rq->next_balance, rq->next_balance))
this_rq->next_balance = rq->next_balance;
@@ -5777,12 +6792,14 @@ end:
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
* domain span are idle.
*/
-static inline int nohz_kick_needed(struct rq *rq, int cpu)
+static inline int nohz_kick_needed(struct rq *rq)
{
unsigned long now = jiffies;
struct sched_domain *sd;
+ struct sched_group_power *sgp;
+ int nr_busy, cpu = rq->cpu;
- if (unlikely(idle_cpu(cpu)))
+ if (unlikely(rq->idle_balance))
return 0;
/*
@@ -5806,22 +6823,22 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
goto need_kick;
rcu_read_lock();
- for_each_domain(cpu, sd) {
- struct sched_group *sg = sd->groups;
- struct sched_group_power *sgp = sg->sgp;
- int nr_busy = atomic_read(&sgp->nr_busy_cpus);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));
- if (sd->flags & SD_SHARE_PKG_RESOURCES && nr_busy > 1)
- goto need_kick_unlock;
+ if (sd) {
+ sgp = sd->groups->sgp;
+ nr_busy = atomic_read(&sgp->nr_busy_cpus);
- if (sd->flags & SD_ASYM_PACKING && nr_busy != sg->group_weight
- && (cpumask_first_and(nohz.idle_cpus_mask,
- sched_domain_span(sd)) < cpu))
+ if (nr_busy > 1)
goto need_kick_unlock;
-
- if (!(sd->flags & (SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING)))
- break;
}
+
+ sd = rcu_dereference(per_cpu(sd_asym, cpu));
+
+ if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
+ sched_domain_span(sd)) < cpu))
+ goto need_kick_unlock;
+
rcu_read_unlock();
return 0;
@@ -5831,7 +6848,7 @@ need_kick:
return 1;
}
#else
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
#endif
/*
@@ -5840,38 +6857,39 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
*/
static void run_rebalance_domains(struct softirq_action *h)
{
- int this_cpu = smp_processor_id();
- struct rq *this_rq = cpu_rq(this_cpu);
+ struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
- rebalance_domains(this_cpu, idle);
+ rebalance_domains(this_rq, idle);
/*
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
* stopped.
*/
- nohz_idle_balance(this_cpu, idle);
+ nohz_idle_balance(this_rq, idle);
}
-static inline int on_null_domain(int cpu)
+static inline int on_null_domain(struct rq *rq)
{
- return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+ return !rcu_dereference_sched(rq->sd);
}
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*/
-void trigger_load_balance(struct rq *rq, int cpu)
+void trigger_load_balance(struct rq *rq)
{
/* Don't need to rebalance while attached to NULL domain */
- if (time_after_eq(jiffies, rq->next_balance) &&
- likely(!on_null_domain(cpu)))
+ if (unlikely(on_null_domain(rq)))
+ return;
+
+ if (time_after_eq(jiffies, rq->next_balance))
raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ_COMMON
- if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
- nohz_balancer_kick(cpu);
+ if (nohz_kick_needed(rq))
+ nohz_balancer_kick();
#endif
}
@@ -6214,7 +7232,8 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
se->cfs_rq = parent->my_q;
se->my_q = cfs_rq;
- update_load_set(&se->load, 0);
+ /* guarantee group entities always have weight */
+ update_load_set(&se->load, NICE_0_LOAD);
se->parent = parent;
}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 99399f8e4799..5716929a2e3a 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,10 +63,23 @@ SCHED_FEAT(LB_MIN, false)
/*
* Apply the automatic NUMA scheduling policy. Enabled automatically
* at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=. Allow PTE scanning to be forced on UMA machines
- * for debugging the core machinery.
+ * numa_balancing=
*/
#ifdef CONFIG_NUMA_BALANCING
SCHED_FEAT(NUMA, false)
-SCHED_FEAT(NUMA_FORCE, false)
+
+/*
+ * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a
+ * higher number of hinting faults are recorded during active load
+ * balancing.
+ */
+SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
+
+/*
+ * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a
+ * lower number of hinting faults have been recorded. As this has
+ * the potential to prevent a task ever migrating to a new node
+ * due to CPU overload it is disabled by default.
+ */
+SCHED_FEAT(NUMA_RESIST_LOWER, false)
#endif
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index d8da01008d39..516c3d9ceea1 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -9,7 +9,7 @@
#ifdef CONFIG_SMP
static int
-select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 01970c8e64df..a2740b775b45 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -246,8 +246,10 @@ static inline void rt_set_overload(struct rq *rq)
* if we should look at the mask. It would be a shame
* if we looked at the mask, but the mask was not
* updated yet.
+ *
+ * Matched by the barrier in pull_rt_task().
*/
- wmb();
+ smp_wmb();
atomic_inc(&rq->rd->rto_count);
}
@@ -899,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && prio < prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
}
@@ -908,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && rt_rq->highest_prio.curr != prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}
@@ -1169,13 +1185,10 @@ static void yield_task_rt(struct rq *rq)
static int find_lowest_rq(struct task_struct *task);
static int
-select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
{
struct task_struct *curr;
struct rq *rq;
- int cpu;
-
- cpu = task_cpu(p);
if (p->nr_cpus_allowed == 1)
goto out;
@@ -1213,8 +1226,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
*/
if (curr && unlikely(rt_task(curr)) &&
(curr->nr_cpus_allowed < 2 ||
- curr->prio <= p->prio) &&
- (p->nr_cpus_allowed > 1)) {
+ curr->prio <= p->prio)) {
int target = find_lowest_rq(p);
if (target != -1)
@@ -1630,6 +1642,12 @@ static int pull_rt_task(struct rq *this_rq)
if (likely(!rt_overloaded(this_rq)))
return 0;
+ /*
+ * Match the barrier from rt_set_overloaded; this guarantees that if we
+ * see overloaded we must also see the rto_mask bit.
+ */
+ smp_rmb();
+
for_each_cpu(cpu, this_rq->rd->rto_mask) {
if (this_cpu == cpu)
continue;
@@ -1720,7 +1738,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
p->nr_cpus_allowed > 1 &&
- rt_task(rq->curr) &&
+ (dl_task(rq->curr) || rt_task(rq->curr)) &&
(rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
@@ -1931,8 +1949,8 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
p->rt.time_slice = sched_rr_timeslice;
/*
- * Requeue to the end of queue if we (and all of our ancestors) are the
- * only element on the queue
+ * Requeue to the end of queue if we (and all of our ancestors) are not
+ * the only element on the queue
*/
for_each_sched_rt_entity(rt_se) {
if (rt_se->run_list.prev != rt_se->run_list.next) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b3c5653e1dca..c2119fd20f8b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,12 +2,15 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
#include <linux/tick.h>
+#include <linux/slab.h>
#include "cpupri.h"
+#include "cpudeadline.h"
#include "cpuacct.h"
struct rq;
@@ -72,6 +75,13 @@ extern void update_cpu_load_active(struct rq *this_rq);
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9 -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
* These are the 'tuning knobs' of the scheduler:
*/
@@ -80,11 +90,19 @@ extern void update_cpu_load_active(struct rq *this_rq);
*/
#define RUNTIME_INF ((u64)~0ULL)
+static inline int fair_policy(int policy)
+{
+ return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
static inline int rt_policy(int policy)
{
- if (policy == SCHED_FIFO || policy == SCHED_RR)
- return 1;
- return 0;
+ return policy == SCHED_FIFO || policy == SCHED_RR;
+}
+
+static inline int dl_policy(int policy)
+{
+ return policy == SCHED_DEADLINE;
}
static inline int task_has_rt_policy(struct task_struct *p)
@@ -92,6 +110,25 @@ static inline int task_has_rt_policy(struct task_struct *p)
return rt_policy(p->policy);
}
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+ return dl_policy(p->policy);
+}
+
+static inline bool dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+ return dl_time_before(a->deadline, b->deadline);
+}
+
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
@@ -107,6 +144,47 @@ struct rt_bandwidth {
u64 rt_runtime;
struct hrtimer rt_period_timer;
};
+/*
+ * To keep the bandwidth of -deadline tasks and groups under control
+ * we need some place where:
+ * - store the maximum -deadline bandwidth of the system (the group);
+ * - cache the fraction of that bandwidth that is currently allocated.
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * meaning that:
+ * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
+ * - dl_total_bw array contains, in the i-eth element, the currently
+ * allocated bandwidth on the i-eth CPU.
+ * Moreover, groups consume bandwidth on each CPU, while tasks only
+ * consume bandwidth on the CPU they're running on.
+ * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
+ * that will be shown the next time the proc or cgroup controls will
+ * be red. It on its turn can be changed by writing on its own
+ * control.
+ */
+struct dl_bandwidth {
+ raw_spinlock_t dl_runtime_lock;
+ u64 dl_runtime;
+ u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+ return sysctl_sched_rt_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+ raw_spinlock_t lock;
+ u64 bw, total_bw;
+};
extern struct mutex sched_domains_mutex;
@@ -363,6 +441,42 @@ struct rt_rq {
#endif
};
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+ /* runqueue is an rbtree, ordered by deadline */
+ struct rb_root rb_root;
+ struct rb_node *rb_leftmost;
+
+ unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+ /*
+ * Deadline values of the currently executing and the
+ * earliest ready task on this rq. Caching these facilitates
+ * the decision wether or not a ready but not running task
+ * should migrate somewhere else.
+ */
+ struct {
+ u64 curr;
+ u64 next;
+ } earliest_dl;
+
+ unsigned long dl_nr_migratory;
+ unsigned long dl_nr_total;
+ int overloaded;
+
+ /*
+ * Tasks on this rq that can be pushed away. They are kept in
+ * an rb-tree, ordered by tasks' deadlines, with caching
+ * of the leftmost (earliest deadline) element.
+ */
+ struct rb_root pushable_dl_tasks_root;
+ struct rb_node *pushable_dl_tasks_leftmost;
+#else
+ struct dl_bw dl_bw;
+#endif
+};
+
#ifdef CONFIG_SMP
/*
@@ -381,6 +495,15 @@ struct root_domain {
cpumask_var_t online;
/*
+ * The bit corresponding to a CPU gets set here if such CPU has more
+ * than one runnable -deadline task (as it is below for RT tasks).
+ */
+ cpumask_var_t dlo_mask;
+ atomic_t dlo_count;
+ struct dl_bw dl_bw;
+ struct cpudl cpudl;
+
+ /*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
@@ -408,6 +531,10 @@ struct rq {
* remote CPUs use both these fields when doing load calculation.
*/
unsigned int nr_running;
+#ifdef CONFIG_NUMA_BALANCING
+ unsigned int nr_numa_running;
+ unsigned int nr_preferred_running;
+#endif
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
unsigned long last_load_update_tick;
@@ -427,6 +554,7 @@ struct rq {
struct cfs_rq cfs;
struct rt_rq rt;
+ struct dl_rq dl;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
@@ -476,6 +604,9 @@ struct rq {
u64 age_stamp;
u64 idle_stamp;
u64 avg_idle;
+
+ /* This is used to determine avg_idle's max value */
+ u64 max_idle_balance_cost;
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -552,6 +683,12 @@ static inline u64 rq_clock_task(struct rq *rq)
return rq->clock_task;
}
+#ifdef CONFIG_NUMA_BALANCING
+extern void sched_setnuma(struct task_struct *p, int node);
+extern int migrate_task_to(struct task_struct *p, int cpu);
+extern int migrate_swap(struct task_struct *, struct task_struct *);
+#endif /* CONFIG_NUMA_BALANCING */
+
#ifdef CONFIG_SMP
#define rcu_dereference_check_sched_domain(p) \
@@ -593,9 +730,24 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
return hsd;
}
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+ struct sched_domain *sd;
+
+ for_each_domain(cpu, sd) {
+ if (sd->flags & flag)
+ break;
+ }
+
+ return sd;
+}
+
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(struct sched_domain *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain *, sd_busy);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym);
struct sched_group_power {
atomic_t ref;
@@ -605,6 +757,7 @@ struct sched_group_power {
*/
unsigned int power, power_orig;
unsigned long next_update;
+ int imbalance; /* XXX unrelated to power but shared group state */
/*
* Number of busy cpus in this group.
*/
@@ -719,6 +872,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
*/
smp_wmb();
task_thread_info(p)->cpu = cpu;
+ p->wake_cpu = cpu;
#endif
}
@@ -796,8 +950,6 @@ static inline u64 global_rt_runtime(void)
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
-
-
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
@@ -957,6 +1109,7 @@ static const u32 prio_to_wmult[40] = {
#else
#define ENQUEUE_WAKING 0
#endif
+#define ENQUEUE_REPLENISH 8
#define DEQUEUE_SLEEP 1
@@ -974,7 +1127,7 @@ struct sched_class {
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
- int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+ int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
@@ -992,6 +1145,7 @@ struct sched_class {
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
+ void (*task_dead) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
@@ -1011,6 +1165,7 @@ struct sched_class {
for (class = sched_class_highest; class; class = class->next)
extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
@@ -1020,7 +1175,7 @@ extern const struct sched_class idle_sched_class;
extern void update_group_power(struct sched_domain *sd, int cpu);
-extern void trigger_load_balance(struct rq *rq, int cpu);
+extern void trigger_load_balance(struct rq *rq);
extern void idle_balance(int this_cpu, struct rq *this_rq);
extern void idle_enter_fair(struct rq *this_rq);
@@ -1037,8 +1192,11 @@ static inline void idle_balance(int cpu, struct rq *rq)
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
extern void resched_task(struct task_struct *p);
extern void resched_cpu(int cpu);
@@ -1046,6 +1204,12 @@ extern void resched_cpu(int cpu);
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
+extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+
+unsigned long to_ratio(u64 period, u64 runtime);
+
extern void update_idle_cpu_load(struct rq *this_rq);
extern void init_task_runnable_average(struct task_struct *p);
@@ -1220,6 +1384,24 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
+static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+ if (l1 > l2)
+ swap(l1, l2);
+
+ spin_lock(l1);
+ spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
+static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+ if (l1 > l2)
+ swap(l1, l2);
+
+ raw_spin_lock(l1);
+ raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
/*
* double_rq_lock - safely lock two runqueues
*
@@ -1304,8 +1486,10 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
-extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
+extern void cfs_bandwidth_usage_inc(void);
+extern void cfs_bandwidth_usage_dec(void);
#ifdef CONFIG_NO_HZ_COMMON
enum rq_nohz_flag_bits {
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index c7edee71bce8..4ab704339656 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -59,9 +59,9 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
* from dequeue_task() to account for possible rq->clock skew across cpus. The
* delta taken on each cpu would annul the skew.
*/
-static inline void sched_info_dequeued(struct task_struct *t)
+static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t)
{
- unsigned long long now = rq_clock(task_rq(t)), delta = 0;
+ unsigned long long now = rq_clock(rq), delta = 0;
if (unlikely(sched_info_on()))
if (t->sched_info.last_queued)
@@ -69,7 +69,7 @@ static inline void sched_info_dequeued(struct task_struct *t)
sched_info_reset_dequeued(t);
t->sched_info.run_delay += delta;
- rq_sched_info_dequeued(task_rq(t), delta);
+ rq_sched_info_dequeued(rq, delta);
}
/*
@@ -77,9 +77,9 @@ static inline void sched_info_dequeued(struct task_struct *t)
* long it was waiting to run. We also note when it began so that we
* can keep stats on how long its timeslice is.
*/
-static void sched_info_arrive(struct task_struct *t)
+static void sched_info_arrive(struct rq *rq, struct task_struct *t)
{
- unsigned long long now = rq_clock(task_rq(t)), delta = 0;
+ unsigned long long now = rq_clock(rq), delta = 0;
if (t->sched_info.last_queued)
delta = now - t->sched_info.last_queued;
@@ -88,7 +88,7 @@ static void sched_info_arrive(struct task_struct *t)
t->sched_info.last_arrival = now;
t->sched_info.pcount++;
- rq_sched_info_arrive(task_rq(t), delta);
+ rq_sched_info_arrive(rq, delta);
}
/*
@@ -96,11 +96,11 @@ static void sched_info_arrive(struct task_struct *t)
* the timestamp if it is already not set. It's assumed that
* sched_info_dequeued() will clear that stamp when appropriate.
*/
-static inline void sched_info_queued(struct task_struct *t)
+static inline void sched_info_queued(struct rq *rq, struct task_struct *t)
{
if (unlikely(sched_info_on()))
if (!t->sched_info.last_queued)
- t->sched_info.last_queued = rq_clock(task_rq(t));
+ t->sched_info.last_queued = rq_clock(rq);
}
/*
@@ -111,15 +111,15 @@ static inline void sched_info_queued(struct task_struct *t)
* sched_info_queued() to mark that it has now again started waiting on
* the runqueue.
*/
-static inline void sched_info_depart(struct task_struct *t)
+static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
{
- unsigned long long delta = rq_clock(task_rq(t)) -
+ unsigned long long delta = rq_clock(rq) -
t->sched_info.last_arrival;
- rq_sched_info_depart(task_rq(t), delta);
+ rq_sched_info_depart(rq, delta);
if (t->state == TASK_RUNNING)
- sched_info_queued(t);
+ sched_info_queued(rq, t);
}
/*
@@ -128,32 +128,34 @@ static inline void sched_info_depart(struct task_struct *t)
* the idle task.) We are only called when prev != next.
*/
static inline void
-__sched_info_switch(struct task_struct *prev, struct task_struct *next)
+__sched_info_switch(struct rq *rq,
+ struct task_struct *prev, struct task_struct *next)
{
- struct rq *rq = task_rq(prev);
-
/*
* prev now departs the cpu. It's not interesting to record
* stats about how efficient we were at scheduling the idle
* process, however.
*/
if (prev != rq->idle)
- sched_info_depart(prev);
+ sched_info_depart(rq, prev);
if (next != rq->idle)
- sched_info_arrive(next);
+ sched_info_arrive(rq, next);
}
static inline void
-sched_info_switch(struct task_struct *prev, struct task_struct *next)
+sched_info_switch(struct rq *rq,
+ struct task_struct *prev, struct task_struct *next)
{
if (unlikely(sched_info_on()))
- __sched_info_switch(prev, next);
+ __sched_info_switch(rq, prev, next);
}
#else
-#define sched_info_queued(t) do { } while (0)
+#define sched_info_queued(rq, t) do { } while (0)
#define sched_info_reset_dequeued(t) do { } while (0)
-#define sched_info_dequeued(t) do { } while (0)
-#define sched_info_switch(t, next) do { } while (0)
+#define sched_info_dequeued(rq, t) do { } while (0)
+#define sched_info_depart(rq, t) do { } while (0)
+#define sched_info_arrive(rq, next) do { } while (0)
+#define sched_info_switch(rq, t, next) do { } while (0)
#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
/*
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index e08fbeeb54b9..fdb6bb0b3356 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -11,7 +11,7 @@
#ifdef CONFIG_SMP
static int
-select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* stop tasks as never migrate */
}
@@ -103,7 +103,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
* Simple, special scheduling class for the per-CPU stop tasks:
*/
const struct sched_class stop_sched_class = {
- .next = &rt_sched_class,
+ .next = &dl_sched_class,
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
diff --git a/kernel/wait.c b/kernel/sched/wait.c
index d550920e040c..7d50f794e248 100644
--- a/kernel/wait.c
+++ b/kernel/sched/wait.c
@@ -53,6 +53,109 @@ EXPORT_SYMBOL(remove_wait_queue);
/*
+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int wake_flags, void *key)
+{
+ wait_queue_t *curr, *next;
+
+ list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
+ unsigned flags = curr->flags;
+
+ if (curr->func(curr, mode, wake_flags, key) &&
+ (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+ break;
+ }
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, void *key)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->lock, flags);
+ __wake_up_common(q, mode, nr_exclusive, 0, key);
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+{
+ __wake_up_common(q, mode, nr, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked);
+
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+ __wake_up_common(q, mode, 1, 0, key);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
+
+/**
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, void *key)
+{
+ unsigned long flags;
+ int wake_flags = 1; /* XXX WF_SYNC */
+
+ if (unlikely(!q))
+ return;
+
+ if (unlikely(nr_exclusive != 1))
+ wake_flags = 0;
+
+ spin_lock_irqsave(&q->lock, flags);
+ __wake_up_common(q, mode, nr_exclusive, wake_flags, key);
+ spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+ __wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
+
+/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
* wake-function that tests for the wait-queue being active
@@ -92,6 +195,30 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
+long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+ unsigned long flags;
+
+ if (signal_pending_state(state, current))
+ return -ERESTARTSYS;
+
+ wait->private = current;
+ wait->func = autoremove_wake_function;
+
+ spin_lock_irqsave(&q->lock, flags);
+ if (list_empty(&wait->task_list)) {
+ if (wait->flags & WQ_FLAG_EXCLUSIVE)
+ __add_wait_queue_tail(q, wait);
+ else
+ __add_wait_queue(q, wait);
+ }
+ set_current_state(state);
+ spin_unlock_irqrestore(&q->lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL(prepare_to_wait_event);
+
/**
* finish_wait - clean up after waiting in a queue
* @q: waitqueue waited on
diff --git a/kernel/signal.c b/kernel/signal.c
index ded28b91fa53..940b30ee9a30 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2723,7 +2723,7 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
#ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER
-int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
{
int err;
diff --git a/kernel/smp.c b/kernel/smp.c
index 0564571dcdf7..bd9f94028838 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -15,9 +15,9 @@
#include "smpboot.h"
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
enum {
CSD_FLAG_LOCK = 0x01,
+ CSD_FLAG_WAIT = 0x02,
};
struct call_function_data {
@@ -124,7 +124,7 @@ static void csd_lock(struct call_single_data *csd)
static void csd_unlock(struct call_single_data *csd)
{
- WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
+ WARN_ON((csd->flags & CSD_FLAG_WAIT) && !(csd->flags & CSD_FLAG_LOCK));
/*
* ensure we're all done before releasing data:
@@ -139,13 +139,15 @@ static void csd_unlock(struct call_single_data *csd)
* for execution on the given CPU. data must already have
* ->func, ->info, and ->flags set.
*/
-static
-void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
+static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
{
struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
unsigned long flags;
int ipi;
+ if (wait)
+ csd->flags |= CSD_FLAG_WAIT;
+
raw_spin_lock_irqsave(&dst->lock, flags);
ipi = list_empty(&dst->list);
list_add_tail(&csd->list, &dst->list);
@@ -340,6 +342,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *csd,
}
put_cpu();
}
+EXPORT_SYMBOL_GPL(__smp_call_function_single);
/**
* smp_call_function_many(): Run a function on a set of other CPUs.
@@ -459,7 +462,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait)
return 0;
}
EXPORT_SYMBOL(smp_call_function);
-#endif /* USE_GENERIC_SMP_HELPERS */
/* Setup configured maximum number of CPUs to activate */
unsigned int setup_max_cpus = NR_CPUS;
@@ -524,6 +526,11 @@ void __init setup_nr_cpu_ids(void)
nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
}
+void __weak smp_announce(void)
+{
+ printk(KERN_INFO "Brought up %d CPUs\n", num_online_cpus());
+}
+
/* Called by boot processor to activate the rest. */
void __init smp_init(void)
{
@@ -540,7 +547,7 @@ void __init smp_init(void)
}
/* Any cleanup work */
- printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
+ smp_announce();
smp_cpus_done(setup_max_cpus);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d7d498d8cc4f..8a1e6e104892 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -6,8 +6,6 @@
* Distribute under GPLv2.
*
* Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
- *
- * Remote softirq infrastructure is by Jens Axboe.
*/
#include <linux/export.h>
@@ -29,7 +27,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/irq.h>
-#include <asm/irq.h>
/*
- No shared variables, all the data are CPU local.
- If a softirq needs serialization, let it serialize itself
@@ -92,7 +89,7 @@ static void wakeup_softirqd(void)
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip, unsigned int cnt)
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -100,46 +97,33 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
raw_local_irq_save(flags);
/*
- * The preempt tracer hooks into add_preempt_count and will break
+ * The preempt tracer hooks into preempt_count_add and will break
* lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
* is set and before current->softirq_enabled is cleared.
* We must manually increment preempt_count here and manually
* call the trace_preempt_off later.
*/
- preempt_count() += cnt;
+ __preempt_count_add(cnt);
/*
* Were softirqs turned off above:
*/
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
-#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
-{
- add_preempt_count(cnt);
- barrier();
-}
+EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */
-void local_bh_disable(void)
-{
- __local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
-}
-
-EXPORT_SYMBOL(local_bh_disable);
-
static void __local_bh_enable(unsigned int cnt)
{
- WARN_ON_ONCE(in_irq());
WARN_ON_ONCE(!irqs_disabled());
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
- sub_preempt_count(cnt);
+ preempt_count_sub(cnt);
}
/*
@@ -149,12 +133,13 @@ static void __local_bh_enable(unsigned int cnt)
*/
void _local_bh_enable(void)
{
+ WARN_ON_ONCE(in_irq());
__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}
EXPORT_SYMBOL(_local_bh_enable);
-static inline void _local_bh_enable_ip(unsigned long ip)
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -169,29 +154,23 @@ static inline void _local_bh_enable_ip(unsigned long ip)
* Keep preemption disabled until we are done with
* softirq processing:
*/
- sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
+ preempt_count_sub(cnt - 1);
- if (unlikely(!in_interrupt() && local_softirq_pending()))
+ if (unlikely(!in_interrupt() && local_softirq_pending())) {
+ /*
+ * Run softirq if any pending. And do it in its own stack
+ * as we may be calling this deep in a task call stack already.
+ */
do_softirq();
+ }
- dec_preempt_count();
+ preempt_count_dec();
#ifdef CONFIG_TRACE_IRQFLAGS
local_irq_enable();
#endif
preempt_check_resched();
}
-
-void local_bh_enable(void)
-{
- _local_bh_enable_ip(_RET_IP_);
-}
-EXPORT_SYMBOL(local_bh_enable);
-
-void local_bh_enable_ip(unsigned long ip)
-{
- _local_bh_enable_ip(ip);
-}
-EXPORT_SYMBOL(local_bh_enable_ip);
+EXPORT_SYMBOL(__local_bh_enable_ip);
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
@@ -209,14 +188,48 @@ EXPORT_SYMBOL(local_bh_enable_ip);
#define MAX_SOFTIRQ_TIME msecs_to_jiffies(2)
#define MAX_SOFTIRQ_RESTART 10
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+ bool in_hardirq = false;
+
+ if (trace_hardirq_context(current)) {
+ in_hardirq = true;
+ trace_hardirq_exit();
+ }
+
+ lockdep_softirq_enter();
+
+ return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+ lockdep_softirq_exit();
+
+ if (in_hardirq)
+ trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
asmlinkage void __do_softirq(void)
{
- struct softirq_action *h;
- __u32 pending;
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
- int cpu;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
+ struct softirq_action *h;
+ bool in_hardirq;
+ __u32 pending;
+ int cpu;
/*
* Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -228,8 +241,8 @@ asmlinkage void __do_softirq(void)
pending = local_softirq_pending();
account_irq_enter_time(current);
- __local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
- lockdep_softirq_enter();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ in_hardirq = lockdep_softirq_start();
cpu = smp_processor_id();
restart:
@@ -256,7 +269,7 @@ restart:
" exited with %08x?\n", vec_nr,
softirq_to_name[vec_nr], h->action,
prev_count, preempt_count());
- preempt_count() = prev_count;
+ preempt_count_set(prev_count);
}
rcu_bh_qs(cpu);
@@ -276,15 +289,13 @@ restart:
wakeup_softirqd();
}
- lockdep_softirq_exit();
-
+ lockdep_softirq_end(in_hardirq);
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
+ WARN_ON_ONCE(in_interrupt());
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
-#ifndef __ARCH_HAS_DO_SOFTIRQ
-
asmlinkage void do_softirq(void)
{
__u32 pending;
@@ -298,20 +309,16 @@ asmlinkage void do_softirq(void)
pending = local_softirq_pending();
if (pending)
- __do_softirq();
+ do_softirq_own_stack();
local_irq_restore(flags);
}
-#endif
-
/*
* Enter an interrupt context.
*/
void irq_enter(void)
{
- int cpu = smp_processor_id();
-
rcu_irq_enter();
if (is_idle_task(current) && !in_interrupt()) {
/*
@@ -319,7 +326,7 @@ void irq_enter(void)
* here, as softirq will be serviced on return from interrupt.
*/
local_bh_disable();
- tick_check_idle(cpu);
+ tick_check_idle();
_local_bh_enable();
}
@@ -329,15 +336,21 @@ void irq_enter(void)
static inline void invoke_softirq(void)
{
if (!force_irqthreads) {
+#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
/*
* We can safely execute softirq on the current stack if
* it is the irq stack, because it should be near empty
- * at this stage. But we have no way to know if the arch
- * calls irq_exit() on the irq stack. So call softirq
- * in its own stack to prevent from any overrun on top
- * of a potentially deep task stack.
+ * at this stage.
*/
- do_softirq();
+ __do_softirq();
+#else
+ /*
+ * Otherwise, irq_exit() is called on the task stack that can
+ * be potentially deep already. So call softirq in its own stack
+ * to prevent from any overrun.
+ */
+ do_softirq_own_stack();
+#endif
} else {
wakeup_softirqd();
}
@@ -368,13 +381,13 @@ void irq_exit(void)
#endif
account_irq_exit_time(current);
- trace_hardirq_exit();
- sub_preempt_count(HARDIRQ_OFFSET);
+ preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
tick_irq_exit();
rcu_irq_exit();
+ trace_hardirq_exit(); /* must be last! */
}
/*
@@ -618,146 +631,17 @@ void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
}
EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-/*
- * Remote softirq bits
- */
-
-DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
-EXPORT_PER_CPU_SYMBOL(softirq_work_list);
-
-static void __local_trigger(struct call_single_data *cp, int softirq)
-{
- struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
-
- list_add_tail(&cp->list, head);
-
- /* Trigger the softirq only if the list was previously empty. */
- if (head->next == &cp->list)
- raise_softirq_irqoff(softirq);
-}
-
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
-static void remote_softirq_receive(void *data)
-{
- struct call_single_data *cp = data;
- unsigned long flags;
- int softirq;
-
- softirq = *(int *)cp->info;
- local_irq_save(flags);
- __local_trigger(cp, softirq);
- local_irq_restore(flags);
-}
-
-static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
- if (cpu_online(cpu)) {
- cp->func = remote_softirq_receive;
- cp->info = &softirq;
- cp->flags = 0;
-
- __smp_call_function_single(cpu, cp, 0);
- return 0;
- }
- return 1;
-}
-#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
-static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
- return 1;
-}
-#endif
-
-/**
- * __send_remote_softirq - try to schedule softirq work on a remote cpu
- * @cp: private SMP call function data area
- * @cpu: the remote cpu
- * @this_cpu: the currently executing cpu
- * @softirq: the softirq for the work
- *
- * Attempt to schedule softirq work on a remote cpu. If this cannot be
- * done, the work is instead queued up on the local cpu.
- *
- * Interrupts must be disabled.
- */
-void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
-{
- if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
- __local_trigger(cp, softirq);
-}
-EXPORT_SYMBOL(__send_remote_softirq);
-
-/**
- * send_remote_softirq - try to schedule softirq work on a remote cpu
- * @cp: private SMP call function data area
- * @cpu: the remote cpu
- * @softirq: the softirq for the work
- *
- * Like __send_remote_softirq except that disabling interrupts and
- * computing the current cpu is done for the caller.
- */
-void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
- unsigned long flags;
- int this_cpu;
-
- local_irq_save(flags);
- this_cpu = smp_processor_id();
- __send_remote_softirq(cp, cpu, this_cpu, softirq);
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL(send_remote_softirq);
-
-static int remote_softirq_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- /*
- * If a CPU goes away, splice its entries to the current CPU
- * and trigger a run of the softirq
- */
- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- int cpu = (unsigned long) hcpu;
- int i;
-
- local_irq_disable();
- for (i = 0; i < NR_SOFTIRQS; i++) {
- struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
- struct list_head *local_head;
-
- if (list_empty(head))
- continue;
-
- local_head = &__get_cpu_var(softirq_work_list[i]);
- list_splice_init(head, local_head);
- raise_softirq_irqoff(i);
- }
- local_irq_enable();
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block remote_softirq_cpu_notifier = {
- .notifier_call = remote_softirq_cpu_notify,
-};
-
void __init softirq_init(void)
{
int cpu;
for_each_possible_cpu(cpu) {
- int i;
-
per_cpu(tasklet_vec, cpu).tail =
&per_cpu(tasklet_vec, cpu).head;
per_cpu(tasklet_hi_vec, cpu).tail =
&per_cpu(tasklet_hi_vec, cpu).head;
- for (i = 0; i < NR_SOFTIRQS; i++)
- INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
}
- register_hotcpu_notifier(&remote_softirq_cpu_notifier);
-
open_softirq(TASKLET_SOFTIRQ, tasklet_action);
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
@@ -771,6 +655,10 @@ static void run_ksoftirqd(unsigned int cpu)
{
local_irq_disable();
if (local_softirq_pending()) {
+ /*
+ * We can safely run softirq on inline stack, as we are not deep
+ * in the task stack here.
+ */
__do_softirq();
rcu_note_context_switch(cpu);
local_irq_enable();
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c09f2955ae30..84571e09c907 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -20,6 +20,7 @@
#include <linux/kallsyms.h>
#include <linux/smpboot.h>
#include <linux/atomic.h>
+#include <linux/lglock.h>
/*
* Structure to determine completion condition and record errors. May
@@ -43,6 +44,14 @@ static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task);
static bool stop_machine_initialized = false;
+/*
+ * Avoids a race between stop_two_cpus and global stop_cpus, where
+ * the stoppers could get queued up in reverse order, leading to
+ * system deadlock. Using an lglock means stop_two_cpus remains
+ * relatively cheap.
+ */
+DEFINE_STATIC_LGLOCK(stop_cpus_lock);
+
static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
{
memset(done, 0, sizeof(*done));
@@ -115,6 +124,184 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
return done.executed ? done.ret : -ENOENT;
}
+/* This controls the threads on each CPU. */
+enum multi_stop_state {
+ /* Dummy starting state for thread. */
+ MULTI_STOP_NONE,
+ /* Awaiting everyone to be scheduled. */
+ MULTI_STOP_PREPARE,
+ /* Disable interrupts. */
+ MULTI_STOP_DISABLE_IRQ,
+ /* Run the function */
+ MULTI_STOP_RUN,
+ /* Exit */
+ MULTI_STOP_EXIT,
+};
+
+struct multi_stop_data {
+ int (*fn)(void *);
+ void *data;
+ /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+ unsigned int num_threads;
+ const struct cpumask *active_cpus;
+
+ enum multi_stop_state state;
+ atomic_t thread_ack;
+};
+
+static void set_state(struct multi_stop_data *msdata,
+ enum multi_stop_state newstate)
+{
+ /* Reset ack counter. */
+ atomic_set(&msdata->thread_ack, msdata->num_threads);
+ smp_wmb();
+ msdata->state = newstate;
+}
+
+/* Last one to ack a state moves to the next state. */
+static void ack_state(struct multi_stop_data *msdata)
+{
+ if (atomic_dec_and_test(&msdata->thread_ack))
+ set_state(msdata, msdata->state + 1);
+}
+
+/* This is the cpu_stop function which stops the CPU. */
+static int multi_cpu_stop(void *data)
+{
+ struct multi_stop_data *msdata = data;
+ enum multi_stop_state curstate = MULTI_STOP_NONE;
+ int cpu = smp_processor_id(), err = 0;
+ unsigned long flags;
+ bool is_active;
+
+ /*
+ * When called from stop_machine_from_inactive_cpu(), irq might
+ * already be disabled. Save the state and restore it on exit.
+ */
+ local_save_flags(flags);
+
+ if (!msdata->active_cpus)
+ is_active = cpu == cpumask_first(cpu_online_mask);
+ else
+ is_active = cpumask_test_cpu(cpu, msdata->active_cpus);
+
+ /* Simple state machine */
+ do {
+ /* Chill out and ensure we re-read multi_stop_state. */
+ cpu_relax();
+ if (msdata->state != curstate) {
+ curstate = msdata->state;
+ switch (curstate) {
+ case MULTI_STOP_DISABLE_IRQ:
+ local_irq_disable();
+ hard_irq_disable();
+ break;
+ case MULTI_STOP_RUN:
+ if (is_active)
+ err = msdata->fn(msdata->data);
+ break;
+ default:
+ break;
+ }
+ ack_state(msdata);
+ }
+ } while (curstate != MULTI_STOP_EXIT);
+
+ local_irq_restore(flags);
+ return err;
+}
+
+struct irq_cpu_stop_queue_work_info {
+ int cpu1;
+ int cpu2;
+ struct cpu_stop_work *work1;
+ struct cpu_stop_work *work2;
+};
+
+/*
+ * This function is always run with irqs and preemption disabled.
+ * This guarantees that both work1 and work2 get queued, before
+ * our local migrate thread gets the chance to preempt us.
+ */
+static void irq_cpu_stop_queue_work(void *arg)
+{
+ struct irq_cpu_stop_queue_work_info *info = arg;
+ cpu_stop_queue_work(info->cpu1, info->work1);
+ cpu_stop_queue_work(info->cpu2, info->work2);
+}
+
+/**
+ * stop_two_cpus - stops two cpus
+ * @cpu1: the cpu to stop
+ * @cpu2: the other cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Stops both the current and specified CPU and runs @fn on one of them.
+ *
+ * returns when both are completed.
+ */
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg)
+{
+ struct cpu_stop_done done;
+ struct cpu_stop_work work1, work2;
+ struct irq_cpu_stop_queue_work_info call_args;
+ struct multi_stop_data msdata;
+
+ preempt_disable();
+ msdata = (struct multi_stop_data){
+ .fn = fn,
+ .data = arg,
+ .num_threads = 2,
+ .active_cpus = cpumask_of(cpu1),
+ };
+
+ work1 = work2 = (struct cpu_stop_work){
+ .fn = multi_cpu_stop,
+ .arg = &msdata,
+ .done = &done
+ };
+
+ call_args = (struct irq_cpu_stop_queue_work_info){
+ .cpu1 = cpu1,
+ .cpu2 = cpu2,
+ .work1 = &work1,
+ .work2 = &work2,
+ };
+
+ cpu_stop_init_done(&done, 2);
+ set_state(&msdata, MULTI_STOP_PREPARE);
+
+ /*
+ * If we observe both CPUs active we know _cpu_down() cannot yet have
+ * queued its stop_machine works and therefore ours will get executed
+ * first. Or its not either one of our CPUs that's getting unplugged,
+ * in which case we don't care.
+ *
+ * This relies on the stopper workqueues to be FIFO.
+ */
+ if (!cpu_active(cpu1) || !cpu_active(cpu2)) {
+ preempt_enable();
+ return -ENOENT;
+ }
+
+ lg_local_lock(&stop_cpus_lock);
+ /*
+ * Queuing needs to be done by the lowest numbered CPU, to ensure
+ * that works are always queued in the same order on every CPU.
+ * This prevents deadlocks.
+ */
+ smp_call_function_single(min(cpu1, cpu2),
+ &irq_cpu_stop_queue_work,
+ &call_args, 0);
+ lg_local_unlock(&stop_cpus_lock);
+ preempt_enable();
+
+ wait_for_completion(&done.completion);
+
+ return done.executed ? done.ret : -ENOENT;
+}
+
/**
* stop_one_cpu_nowait - stop a cpu but don't wait for completion
* @cpu: cpu to stop
@@ -159,10 +346,10 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask,
* preempted by a stopper which might wait for other stoppers
* to enter @fn which can lead to deadlock.
*/
- preempt_disable();
+ lg_global_lock(&stop_cpus_lock);
for_each_cpu(cpu, cpumask)
cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu));
- preempt_enable();
+ lg_global_unlock(&stop_cpus_lock);
}
static int __stop_cpus(const struct cpumask *cpumask,
@@ -359,98 +546,14 @@ early_initcall(cpu_stop_init);
#ifdef CONFIG_STOP_MACHINE
-/* This controls the threads on each CPU. */
-enum stopmachine_state {
- /* Dummy starting state for thread. */
- STOPMACHINE_NONE,
- /* Awaiting everyone to be scheduled. */
- STOPMACHINE_PREPARE,
- /* Disable interrupts. */
- STOPMACHINE_DISABLE_IRQ,
- /* Run the function */
- STOPMACHINE_RUN,
- /* Exit */
- STOPMACHINE_EXIT,
-};
-
-struct stop_machine_data {
- int (*fn)(void *);
- void *data;
- /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
- unsigned int num_threads;
- const struct cpumask *active_cpus;
-
- enum stopmachine_state state;
- atomic_t thread_ack;
-};
-
-static void set_state(struct stop_machine_data *smdata,
- enum stopmachine_state newstate)
-{
- /* Reset ack counter. */
- atomic_set(&smdata->thread_ack, smdata->num_threads);
- smp_wmb();
- smdata->state = newstate;
-}
-
-/* Last one to ack a state moves to the next state. */
-static void ack_state(struct stop_machine_data *smdata)
-{
- if (atomic_dec_and_test(&smdata->thread_ack))
- set_state(smdata, smdata->state + 1);
-}
-
-/* This is the cpu_stop function which stops the CPU. */
-static int stop_machine_cpu_stop(void *data)
-{
- struct stop_machine_data *smdata = data;
- enum stopmachine_state curstate = STOPMACHINE_NONE;
- int cpu = smp_processor_id(), err = 0;
- unsigned long flags;
- bool is_active;
-
- /*
- * When called from stop_machine_from_inactive_cpu(), irq might
- * already be disabled. Save the state and restore it on exit.
- */
- local_save_flags(flags);
-
- if (!smdata->active_cpus)
- is_active = cpu == cpumask_first(cpu_online_mask);
- else
- is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
-
- /* Simple state machine */
- do {
- /* Chill out and ensure we re-read stopmachine_state. */
- cpu_relax();
- if (smdata->state != curstate) {
- curstate = smdata->state;
- switch (curstate) {
- case STOPMACHINE_DISABLE_IRQ:
- local_irq_disable();
- hard_irq_disable();
- break;
- case STOPMACHINE_RUN:
- if (is_active)
- err = smdata->fn(smdata->data);
- break;
- default:
- break;
- }
- ack_state(smdata);
- }
- } while (curstate != STOPMACHINE_EXIT);
-
- local_irq_restore(flags);
- return err;
-}
-
int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
{
- struct stop_machine_data smdata = { .fn = fn, .data = data,
- .num_threads = num_online_cpus(),
- .active_cpus = cpus };
+ struct multi_stop_data msdata = {
+ .fn = fn,
+ .data = data,
+ .num_threads = num_online_cpus(),
+ .active_cpus = cpus,
+ };
if (!stop_machine_initialized) {
/*
@@ -461,7 +564,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
unsigned long flags;
int ret;
- WARN_ON_ONCE(smdata.num_threads != 1);
+ WARN_ON_ONCE(msdata.num_threads != 1);
local_irq_save(flags);
hard_irq_disable();
@@ -472,8 +575,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
}
/* Set the initial state and stop all online cpus. */
- set_state(&smdata, STOPMACHINE_PREPARE);
- return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
+ set_state(&msdata, MULTI_STOP_PREPARE);
+ return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata);
}
int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
@@ -513,25 +616,25 @@ EXPORT_SYMBOL_GPL(stop_machine);
int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
const struct cpumask *cpus)
{
- struct stop_machine_data smdata = { .fn = fn, .data = data,
+ struct multi_stop_data msdata = { .fn = fn, .data = data,
.active_cpus = cpus };
struct cpu_stop_done done;
int ret;
/* Local CPU must be inactive and CPU hotplug in progress. */
BUG_ON(cpu_active(raw_smp_processor_id()));
- smdata.num_threads = num_active_cpus() + 1; /* +1 for local */
+ msdata.num_threads = num_active_cpus() + 1; /* +1 for local */
/* No proper task established and can't sleep - busy wait for lock. */
while (!mutex_trylock(&stop_cpus_mutex))
cpu_relax();
/* Schedule work on other CPUs and execute directly for local CPU */
- set_state(&smdata, STOPMACHINE_PREPARE);
+ set_state(&msdata, MULTI_STOP_PREPARE);
cpu_stop_init_done(&done, num_active_cpus());
- queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
+ queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
&done);
- ret = stop_machine_cpu_stop(&smdata);
+ ret = multi_cpu_stop(&msdata);
/* Busy wait for completion. */
while (!completion_done(&done.completion))
diff --git a/kernel/sys.c b/kernel/sys.c
index c18ecca575b4..c72311324ea7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -16,7 +16,6 @@
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
-#include <linux/kexec.h>
#include <linux/workqueue.h>
#include <linux/capability.h>
#include <linux/device.h>
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2f06f3c6a3f..332cefcdb04b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -95,8 +95,6 @@
#if defined(CONFIG_SYSCTL)
/* External variables not in a header file. */
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
extern int max_threads;
extern int suid_dumpable;
#ifdef CONFIG_COREDUMP
@@ -190,7 +188,7 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses it's own private copy */
-static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
+static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
static int sysrq_sysctl_handler(ctl_table *table, int write,
void __user *buffer, size_t *lenp,
@@ -371,13 +369,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "numa_balancing_scan_period_reset",
- .data = &sysctl_numa_balancing_scan_period_reset,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "numa_balancing_scan_period_max_ms",
.data = &sysctl_numa_balancing_scan_period_max,
.maxlen = sizeof(unsigned int),
@@ -391,6 +382,13 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "numa_balancing_migrate_deferred",
+ .data = &sysctl_numa_balancing_migrate_deferred,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
{
@@ -962,9 +960,10 @@ static struct ctl_table kern_table[] = {
{
.procname = "hung_task_check_count",
.data = &sysctl_hung_task_check_count,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "hung_task_timeout_secs",
@@ -1049,6 +1048,7 @@ static struct ctl_table kern_table[] = {
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = perf_proc_update_handler,
+ .extra1 = &one,
},
{
.procname = "perf_cpu_time_max_percent",
@@ -1119,7 +1119,14 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = overcommit_ratio_handler,
+ },
+ {
+ .procname = "overcommit_kbytes",
+ .data = &sysctl_overcommit_kbytes,
+ .maxlen = sizeof(sysctl_overcommit_kbytes),
+ .mode = 0644,
+ .proc_handler = overcommit_kbytes_handler,
},
{
.procname = "page-cluster",
@@ -2214,8 +2221,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
*i = val;
} else {
val = convdiv * (*i) / convmul;
- if (!first)
+ if (!first) {
err = proc_put_char(&buffer, &left, '\t');
+ if (err)
+ break;
+ }
err = proc_put_long(&buffer, &left, val, false);
if (err)
break;
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index b609213ca9a2..653cbbd9e7ad 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1024,7 +1024,7 @@ static ssize_t bin_intvec(struct file *file,
if (get_user(value, vec + i))
goto out_kfree;
- str += snprintf(str, end - str, "%lu\t", value);
+ str += scnprintf(str, end - str, "%lu\t", value);
}
result = kernel_write(file, buffer, str - buffer, 0);
@@ -1095,7 +1095,7 @@ static ssize_t bin_ulongvec(struct file *file,
if (get_user(value, vec + i))
goto out_kfree;
- str += snprintf(str, end - str, "%lu\t", value);
+ str += scnprintf(str, end - str, "%lu\t", value);
}
result = kernel_write(file, buffer, str - buffer, 0);
@@ -1205,7 +1205,7 @@ static ssize_t bin_dn_node_address(struct file *file,
if (get_user(dnaddr, (__le16 __user *)newval))
goto out;
- len = snprintf(buf, sizeof(buf), "%hu.%hu",
+ len = scnprintf(buf, sizeof(buf), "%hu.%hu",
le16_to_cpu(dnaddr) >> 10,
le16_to_cpu(dnaddr) & 0x3ff);
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
new file mode 100644
index 000000000000..3e9868d47535
--- /dev/null
+++ b/kernel/system_certificates.S
@@ -0,0 +1,20 @@
+#include <linux/export.h>
+#include <linux/init.h>
+
+ __INITRODATA
+
+ .align 8
+ .globl VMLINUX_SYMBOL(system_certificate_list)
+VMLINUX_SYMBOL(system_certificate_list):
+__cert_list_start:
+ .incbin "kernel/x509_certificate_list"
+__cert_list_end:
+
+ .align 8
+ .globl VMLINUX_SYMBOL(system_certificate_list_size)
+VMLINUX_SYMBOL(system_certificate_list_size):
+#ifdef CONFIG_64BIT
+ .quad __cert_list_end - __cert_list_start
+#else
+ .long __cert_list_end - __cert_list_start
+#endif
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
new file mode 100644
index 000000000000..52ebc70263f4
--- /dev/null
+++ b/kernel/system_keyring.c
@@ -0,0 +1,105 @@
+/* System trusted keyring for trusted public keys
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "module-internal.h"
+
+struct key *system_trusted_keyring;
+EXPORT_SYMBOL_GPL(system_trusted_keyring);
+
+extern __initconst const u8 system_certificate_list[];
+extern __initconst const unsigned long system_certificate_list_size;
+
+/*
+ * Load the compiled-in keys
+ */
+static __init int system_trusted_keyring_init(void)
+{
+ pr_notice("Initialise system trusted keyring\n");
+
+ system_trusted_keyring =
+ keyring_alloc(".system_keyring",
+ KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH),
+ KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ if (IS_ERR(system_trusted_keyring))
+ panic("Can't allocate system trusted keyring\n");
+
+ set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags);
+ return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(system_trusted_keyring_init);
+
+/*
+ * Load the compiled-in list of X.509 certificates.
+ */
+static __init int load_system_certificate_list(void)
+{
+ key_ref_t key;
+ const u8 *p, *end;
+ size_t plen;
+
+ pr_notice("Loading compiled-in X.509 certificates\n");
+
+ p = system_certificate_list;
+ end = p + system_certificate_list_size;
+ while (p < end) {
+ /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+ * than 256 bytes in size.
+ */
+ if (end - p < 4)
+ goto dodgy_cert;
+ if (p[0] != 0x30 &&
+ p[1] != 0x82)
+ goto dodgy_cert;
+ plen = (p[2] << 8) | p[3];
+ plen += 4;
+ if (plen > end - p)
+ goto dodgy_cert;
+
+ key = key_create_or_update(make_key_ref(system_trusted_keyring, 1),
+ "asymmetric",
+ NULL,
+ p,
+ plen,
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA |
+ KEY_ALLOC_TRUSTED);
+ if (IS_ERR(key)) {
+ pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+ PTR_ERR(key));
+ } else {
+ pr_notice("Loaded X.509 cert '%s'\n",
+ key_ref_to_ptr(key)->description);
+ key_ref_put(key);
+ }
+ p += plen;
+ }
+
+ return 0;
+
+dodgy_cert:
+ pr_err("Problem parsing in-kernel X.509 certificate list\n");
+ return 0;
+}
+late_initcall(load_system_certificate_list);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 145bb4d3bd4d..13d2f7cd65db 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -290,6 +290,7 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
struct listener_list *listeners;
struct listener *s, *tmp, *s2;
unsigned int cpu;
+ int ret = 0;
if (!cpumask_subset(mask, cpu_possible_mask))
return -EINVAL;
@@ -304,9 +305,10 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
for_each_cpu(cpu, mask) {
s = kmalloc_node(sizeof(struct listener),
GFP_KERNEL, cpu_to_node(cpu));
- if (!s)
+ if (!s) {
+ ret = -ENOMEM;
goto cleanup;
-
+ }
s->pid = pid;
s->valid = 1;
@@ -339,7 +341,7 @@ cleanup:
}
up_write(&listeners->sem);
}
- return 0;
+ return ret;
}
static int parse(struct nlattr *na, struct cpumask *mask)
@@ -404,11 +406,15 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
if (!na)
goto err;
- if (nla_put(skb, type, sizeof(pid), &pid) < 0)
+ if (nla_put(skb, type, sizeof(pid), &pid) < 0) {
+ nla_nest_cancel(skb, na);
goto err;
+ }
ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
- if (!ret)
+ if (!ret) {
+ nla_nest_cancel(skb, na);
goto err;
+ }
nla_nest_end(skb, na);
return nla_data(ret);
@@ -667,17 +673,18 @@ err:
nlmsg_free(rep_skb);
}
-static struct genl_ops taskstats_ops = {
- .cmd = TASKSTATS_CMD_GET,
- .doit = taskstats_user_cmd,
- .policy = taskstats_cmd_get_policy,
- .flags = GENL_ADMIN_PERM,
-};
-
-static struct genl_ops cgroupstats_ops = {
- .cmd = CGROUPSTATS_CMD_GET,
- .doit = cgroupstats_user_cmd,
- .policy = cgroupstats_cmd_get_policy,
+static const struct genl_ops taskstats_ops[] = {
+ {
+ .cmd = TASKSTATS_CMD_GET,
+ .doit = taskstats_user_cmd,
+ .policy = taskstats_cmd_get_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = CGROUPSTATS_CMD_GET,
+ .doit = cgroupstats_user_cmd,
+ .policy = cgroupstats_cmd_get_policy,
+ },
};
/* Needed early in initialization */
@@ -696,26 +703,13 @@ static int __init taskstats_init(void)
{
int rc;
- rc = genl_register_family(&family);
+ rc = genl_register_family_with_ops(&family, taskstats_ops);
if (rc)
return rc;
- rc = genl_register_ops(&family, &taskstats_ops);
- if (rc < 0)
- goto err;
-
- rc = genl_register_ops(&family, &cgroupstats_ops);
- if (rc < 0)
- goto err_cgroup_ops;
-
family_registered = 1;
pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION);
return 0;
-err_cgroup_ops:
- genl_unregister_ops(&family, &taskstats_ops);
-err:
- genl_unregister_family(&family);
- return rc;
}
/*
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 2b62fe86f9ec..3ce6e8c5f3fc 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -100,7 +100,7 @@ config NO_HZ_FULL
# RCU_USER_QS dependency
depends on HAVE_CONTEXT_TRACKING
# VIRT_CPU_ACCOUNTING_GEN dependency
- depends on 64BIT
+ depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
select NO_HZ_COMMON
select RCU_USER_QS
select RCU_NOCB_CPU
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index eec50fcef9e4..88c9c65a430d 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -490,7 +490,7 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EINVAL;
return hrtimer_get_res(baseid, tp);
}
@@ -507,7 +507,7 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EINVAL;
*tp = ktime_to_timespec(base->gettime());
return 0;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 662c5798a685..086ad6043bcb 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -619,7 +619,7 @@ static ssize_t sysfs_unbind_tick_dev(struct device *dev,
const char *buf, size_t count)
{
char name[CS_NAME_LEN];
- size_t ret = sysfs_get_uname(buf, name, count);
+ ssize_t ret = sysfs_get_uname(buf, name, count);
struct clock_event_device *ce;
if (ret < 0)
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 50a8736757f3..ba3e502c955a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -479,6 +479,7 @@ static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
static inline int __clocksource_watchdog_kthread(void) { return 0; }
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
+void clocksource_mark_unstable(struct clocksource *cs) { }
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
@@ -537,40 +538,55 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
}
/**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
- * @cs: Pointer to clocksource
- *
+ * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
+ * @mult: cycle to nanosecond multiplier
+ * @shift: cycle to nanosecond divisor (power of two)
+ * @maxadj: maximum adjustment value to mult (~11%)
+ * @mask: bitmask for two's complement subtraction of non 64 bit counters
*/
-static u64 clocksource_max_deferment(struct clocksource *cs)
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
{
u64 max_nsecs, max_cycles;
/*
* Calculate the maximum number of cycles that we can pass to the
* cyc2ns function without overflowing a 64-bit signed result. The
- * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+ * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
* which is equivalent to the below.
- * max_cycles < (2^63)/(cs->mult + cs->maxadj)
- * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
- * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
- * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
- * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
+ * max_cycles < (2^63)/(mult + maxadj)
+ * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
+ * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
+ * max_cycles < 2^(63 - log2(mult + maxadj))
+ * max_cycles < 1 << (63 - log2(mult + maxadj))
* Please note that we add 1 to the result of the log2 to account for
* any rounding errors, ensure the above inequality is satisfied and
* no overflow will occur.
*/
- max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
+ max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
/*
* The actual maximum number of cycles we can defer the clocksource is
- * determined by the minimum of max_cycles and cs->mask.
+ * determined by the minimum of max_cycles and mask.
* Note: Here we subtract the maxadj to make sure we don't sleep for
* too long if there's a large negative adjustment.
*/
- max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
- max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
- cs->shift);
+ max_cycles = min(max_cycles, mask);
+ max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
+
+ return max_nsecs;
+}
+
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs: Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+ u64 max_nsecs;
+ max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
+ cs->mask);
/*
* To ensure that the clocksource does not wrap whilst we are idle,
* limit the time the clocksource can be deferred by 12.5%. Please
@@ -893,7 +909,7 @@ sysfs_show_current_clocksources(struct device *dev,
return count;
}
-size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
+ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
{
size_t ret = cnt;
@@ -924,7 +940,7 @@ static ssize_t sysfs_override_clocksource(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
- size_t ret;
+ ssize_t ret;
mutex_lock(&clocksource_mutex);
@@ -952,7 +968,7 @@ static ssize_t sysfs_unbind_clocksource(struct device *dev,
{
struct clocksource *cs;
char name[CS_NAME_LEN];
- size_t ret;
+ ssize_t ret;
ret = sysfs_get_uname(buf, name, count);
if (ret < 0)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index bb2215174f05..af8d1d4f3d55 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -475,6 +475,7 @@ static void sync_cmos_clock(struct work_struct *work)
* called as close as possible to 500 ms before the new second starts.
* This code is run on a timer. If the clock is set, that timer
* may not expire at the correct time. Thus, we adjust...
+ * We want the clock to be within a couple of ticks from the target.
*/
if (!ntp_synced()) {
/*
@@ -485,7 +486,7 @@ static void sync_cmos_clock(struct work_struct *work)
}
getnstimeofday(&now);
- if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+ if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
struct timespec adjust = now;
fail = -ENODEV;
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0b479a6a22bb..0abb36464281 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -8,25 +8,28 @@
#include <linux/clocksource.h>
#include <linux/init.h>
#include <linux/jiffies.h>
+#include <linux/ktime.h>
#include <linux/kernel.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/syscore_ops.h>
-#include <linux/timer.h>
+#include <linux/hrtimer.h>
#include <linux/sched_clock.h>
+#include <linux/seqlock.h>
+#include <linux/bitops.h>
struct clock_data {
+ ktime_t wrap_kt;
u64 epoch_ns;
- u32 epoch_cyc;
- u32 epoch_cyc_copy;
+ u64 epoch_cyc;
+ seqcount_t seq;
unsigned long rate;
u32 mult;
u32 shift;
bool suspended;
};
-static void sched_clock_poll(unsigned long wrap_ticks);
-static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
+static struct hrtimer sched_clock_timer;
static int irqtime = -1;
core_param(irqtime, irqtime, int, 0400);
@@ -35,42 +38,46 @@ static struct clock_data cd = {
.mult = NSEC_PER_SEC / HZ,
};
-static u32 __read_mostly sched_clock_mask = 0xffffffff;
+static u64 __read_mostly sched_clock_mask;
-static u32 notrace jiffy_sched_clock_read(void)
+static u64 notrace jiffy_sched_clock_read(void)
{
- return (u32)(jiffies - INITIAL_JIFFIES);
+ /*
+ * We don't need to use get_jiffies_64 on 32-bit arches here
+ * because we register with BITS_PER_LONG
+ */
+ return (u64)(jiffies - INITIAL_JIFFIES);
}
-static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+static u32 __read_mostly (*read_sched_clock_32)(void);
+
+static u64 notrace read_sched_clock_32_wrapper(void)
+{
+ return read_sched_clock_32();
+}
+
+static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
{
return (cyc * mult) >> shift;
}
-static unsigned long long notrace sched_clock_32(void)
+unsigned long long notrace sched_clock(void)
{
u64 epoch_ns;
- u32 epoch_cyc;
- u32 cyc;
+ u64 epoch_cyc;
+ u64 cyc;
+ unsigned long seq;
if (cd.suspended)
return cd.epoch_ns;
- /*
- * Load the epoch_cyc and epoch_ns atomically. We do this by
- * ensuring that we always write epoch_cyc, epoch_ns and
- * epoch_cyc_copy in strict order, and read them in strict order.
- * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
- * the middle of an update, and we should repeat the load.
- */
do {
+ seq = raw_read_seqcount_begin(&cd.seq);
epoch_cyc = cd.epoch_cyc;
- smp_rmb();
epoch_ns = cd.epoch_ns;
- smp_rmb();
- } while (epoch_cyc != cd.epoch_cyc_copy);
+ } while (read_seqcount_retry(&cd.seq, seq));
cyc = read_sched_clock();
cyc = (cyc - epoch_cyc) & sched_clock_mask;
@@ -83,49 +90,46 @@ static unsigned long long notrace sched_clock_32(void)
static void notrace update_sched_clock(void)
{
unsigned long flags;
- u32 cyc;
+ u64 cyc;
u64 ns;
cyc = read_sched_clock();
ns = cd.epoch_ns +
cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
cd.mult, cd.shift);
- /*
- * Write epoch_cyc and epoch_ns in a way that the update is
- * detectable in cyc_to_fixed_sched_clock().
- */
+
raw_local_irq_save(flags);
- cd.epoch_cyc_copy = cyc;
- smp_wmb();
+ raw_write_seqcount_begin(&cd.seq);
cd.epoch_ns = ns;
- smp_wmb();
cd.epoch_cyc = cyc;
+ raw_write_seqcount_end(&cd.seq);
raw_local_irq_restore(flags);
}
-static void sched_clock_poll(unsigned long wrap_ticks)
+static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
{
- mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
update_sched_clock();
+ hrtimer_forward_now(hrt, cd.wrap_kt);
+ return HRTIMER_RESTART;
}
-void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
+void __init sched_clock_register(u64 (*read)(void), int bits,
+ unsigned long rate)
{
- unsigned long r, w;
+ unsigned long r;
u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
- BUG_ON(bits > 32);
WARN_ON(!irqs_disabled());
read_sched_clock = read;
- sched_clock_mask = (1ULL << bits) - 1;
+ sched_clock_mask = CLOCKSOURCE_MASK(bits);
cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
- clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
+ clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
r = rate;
if (r >= 4000000) {
@@ -138,20 +142,14 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
r_unit = ' ';
/* calculate how many ns until we wrap */
- wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
- do_div(wrap, NSEC_PER_MSEC);
- w = wrap;
+ wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
+ cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
/* calculate the ns resolution of this counter */
res = cyc_to_ns(1ULL, cd.mult, cd.shift);
- pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
- bits, r, r_unit, res, w);
+ pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
+ bits, r, r_unit, res, wrap);
- /*
- * Start the timer to keep sched_clock() properly updated and
- * sets the initial epoch.
- */
- sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
update_sched_clock();
/*
@@ -166,11 +164,10 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
pr_debug("Registered %pF as sched_clock source\n", read);
}
-unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
-
-unsigned long long notrace sched_clock(void)
+void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
{
- return sched_clock_func();
+ read_sched_clock_32 = read;
+ sched_clock_register(read_sched_clock_32_wrapper, bits, rate);
}
void __init sched_clock_postinit(void)
@@ -180,14 +177,22 @@ void __init sched_clock_postinit(void)
* make it the final one one.
*/
if (read_sched_clock == jiffy_sched_clock_read)
- setup_sched_clock(jiffy_sched_clock_read, 32, HZ);
+ sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
- sched_clock_poll(sched_clock_timer.data);
+ update_sched_clock();
+
+ /*
+ * Start the timer to keep sched_clock() properly updated and
+ * sets the initial epoch.
+ */
+ hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ sched_clock_timer.function = sched_clock_poll;
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
}
static int sched_clock_suspend(void)
{
- sched_clock_poll(sched_clock_timer.data);
+ sched_clock_poll(&sched_clock_timer);
cd.suspended = true;
return 0;
}
@@ -195,7 +200,6 @@ static int sched_clock_suspend(void)
static void sched_clock_resume(void)
{
cd.epoch_cyc = read_sched_clock();
- cd.epoch_cyc_copy = cd.epoch_cyc;
cd.suspended = false;
}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 218bcb565fed..43780ab5e279 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -70,6 +70,7 @@ static bool tick_check_broadcast_device(struct clock_event_device *curdev,
struct clock_event_device *newdev)
{
if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+ (newdev->features & CLOCK_EVT_FEAT_PERCPU) ||
(newdev->features & CLOCK_EVT_FEAT_C3STOP))
return false;
@@ -537,10 +538,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
* Called from irq_enter() when idle was interrupted to reenable the
* per cpu device.
*/
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
{
- if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
- struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+ if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+ struct tick_device *td = &__get_cpu_var(tick_cpu_device);
/*
* We might be in the middle of switching over from
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0e..20b2fe37d105 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,6 +33,21 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
*/
ktime_t tick_next_period;
ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ * timekeeping lock all at once. Only the CPU which is assigned to do the
+ * update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ * TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ * at it will take over and keep the time keeping alive. The handover
+ * procedure also covers cpu hotplug.
+ */
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
/*
@@ -70,6 +85,7 @@ static void tick_periodic(int cpu)
do_timer(1);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
update_process_times(user_mode(get_irq_regs()));
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index bc906cad709b..8329669b51ec 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -31,7 +31,7 @@ extern void tick_install_replacement(struct clock_event_device *dev);
extern void clockevents_shutdown(struct clock_event_device *dev);
-extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
+extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
/*
* NO_HZ / high resolution timer shared code
@@ -51,7 +51,7 @@ extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
@@ -62,7 +62,7 @@ static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
@@ -155,3 +155,4 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
#endif
extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3612fc77f834..08cb0c3b8ccb 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -86,6 +86,7 @@ static void tick_do_update_jiffies64(ktime_t now)
tick_next_period = ktime_add(last_jiffies_update, tick_period);
}
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
/*
@@ -177,7 +178,7 @@ static bool can_stop_full_tick(void)
* TODO: kick full dynticks CPUs when
* sched_clock_stable is set.
*/
- if (!sched_clock_stable) {
+ if (!sched_clock_stable()) {
trace_tick_stop(0, "unstable sched clock\n");
/*
* Don't allow the user to think they can get
@@ -361,8 +362,8 @@ void __init tick_nohz_init(void)
/*
* NO HZ enabled ?
*/
-int tick_nohz_enabled __read_mostly = 1;
-
+static int tick_nohz_enabled __read_mostly = 1;
+int tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
@@ -391,11 +392,9 @@ __setup("nohz=", setup_tick_nohz);
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- ts->idle_waketime = now;
+ __this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
@@ -426,17 +425,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
}
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
- update_ts_time_stats(cpu, ts, now, NULL);
+ update_ts_time_stats(smp_processor_id(), ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
}
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
ktime_t now = ktime_get();
@@ -465,7 +462,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, idle;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
now = ktime_get();
@@ -506,7 +503,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, iowait;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
now = ktime_get();
@@ -711,8 +708,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
return false;
}
- if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+ if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+ ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
return false;
+ }
if (need_resched())
return false;
@@ -752,7 +751,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
ktime_t now, expires;
int cpu = smp_processor_id();
- now = tick_nohz_start_idle(cpu, ts);
+ now = tick_nohz_start_idle(ts);
if (can_stop_idle_tick(cpu, ts)) {
int was_stopped = ts->tick_stopped;
@@ -799,11 +798,6 @@ void tick_nohz_idle_enter(void)
local_irq_disable();
ts = &__get_cpu_var(tick_cpu_sched);
- /*
- * set ts->inidle unconditionally. even if the system did not
- * switch to nohz mode the cpu frequency governers rely on the
- * update of the idle time accounting in tick_nohz_start_idle().
- */
ts->inidle = 1;
__tick_nohz_idle_enter(ts);
@@ -914,8 +908,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
*/
void tick_nohz_idle_exit(void)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
local_irq_disable();
@@ -928,7 +921,7 @@ void tick_nohz_idle_exit(void)
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_restart_sched_tick(ts, now);
@@ -973,7 +966,7 @@ static void tick_nohz_switch_to_nohz(void)
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t next;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return;
local_irq_disable();
@@ -981,7 +974,7 @@ static void tick_nohz_switch_to_nohz(void)
local_irq_enable();
return;
}
-
+ tick_nohz_active = 1;
ts->nohz_mode = NOHZ_MODE_LOWRES;
/*
@@ -1012,12 +1005,10 @@ static void tick_nohz_switch_to_nohz(void)
* timer and do not touch the other magic bits which need to be done
* when idle is left.
*/
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
{
#if 0
/* Switch back to 2.6.27 behaviour */
-
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t delta;
/*
@@ -1032,36 +1023,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
#endif
}
-static inline void tick_check_nohz(int cpu)
+static inline void tick_check_nohz_this_cpu(void)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
if (!ts->idle_active && !ts->tick_stopped)
return;
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_update_jiffies(now);
- tick_nohz_kick_tick(cpu, now);
+ tick_nohz_kick_tick(ts, now);
}
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_check_nohz_this_cpu(void) { }
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
-void tick_check_idle(int cpu)
+void tick_check_idle(void)
{
- tick_check_oneshot_broadcast(cpu);
- tick_check_nohz(cpu);
+ tick_check_oneshot_broadcast_this_cpu();
+ tick_check_nohz_this_cpu();
}
/*
@@ -1139,8 +1130,10 @@ void tick_setup_sched_timer(void)
}
#ifdef CONFIG_NO_HZ_COMMON
- if (tick_nohz_enabled)
+ if (tick_nohz_enabled) {
ts->nohz_mode = NOHZ_MODE_HIGHRES;
+ tick_nohz_active = 1;
+ }
#endif
}
#endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 947ba25a95a0..0aa4ce81bc16 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -77,7 +77,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
tk->wall_to_monotonic = wtm;
set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
tk->offs_real = timespec_to_ktime(tmp);
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -90,8 +90,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
}
/**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
*
+ * @tk: The target timekeeper to setup.
* @clock: Pointer to clocksource.
*
* Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
@@ -595,7 +596,7 @@ s32 timekeeping_get_tai_offset(void)
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
tk->tai_offset = tai_offset;
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}
/**
@@ -610,6 +611,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
__timekeeping_set_tai_offset(tk, tai_offset);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clock_was_set();
@@ -1023,6 +1025,8 @@ static int timekeeping_suspend(void)
timekeeping_suspend_time =
timespec_add(timekeeping_suspend_time, delta_delta);
}
+
+ timekeeping_update(tk, TK_MIRROR);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1130,16 +1134,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
* we can adjust by 1.
*/
error >>= 2;
- /*
- * XXX - In update_wall_time, we round up to the next
- * nanosecond, and store the amount rounded up into
- * the error. This causes the likely below to be unlikely.
- *
- * The proper fix is to avoid rounding up by using
- * the high precision tk->xtime_nsec instead of
- * xtime.tv_nsec everywhere. Fixing this will take some
- * time.
- */
if (likely(error <= interval))
adj = 1;
else
@@ -1255,7 +1249,7 @@ out_adjust:
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
- unsigned int action = 0;
+ unsigned int clock_set = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
@@ -1277,11 +1271,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
- clock_was_set_delayed();
- action = TK_CLOCK_WAS_SET;
+ clock_set = TK_CLOCK_WAS_SET;
}
}
- return action;
+ return clock_set;
}
/**
@@ -1294,7 +1287,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
* Returns the unconsumed cycles.
*/
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
- u32 shift)
+ u32 shift,
+ unsigned int *clock_set)
{
cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
@@ -1308,7 +1302,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
tk->cycle_last += interval;
tk->xtime_nsec += tk->xtime_interval << shift;
- accumulate_nsecs_to_secs(tk);
+ *clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1347,7 +1341,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
tk->xtime_nsec -= remainder;
tk->xtime_nsec += 1ULL << tk->shift;
tk->ntp_error += remainder << tk->ntp_error_shift;
-
+ tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
}
#else
#define old_vsyscall_fixup(tk)
@@ -1359,14 +1353,14 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
* update_wall_time - Uses the current clocksource to increment the wall time
*
*/
-static void update_wall_time(void)
+void update_wall_time(void)
{
struct clocksource *clock;
struct timekeeper *real_tk = &timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
- unsigned int action;
+ unsigned int clock_set = 0;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1401,7 +1395,8 @@ static void update_wall_time(void)
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
- offset = logarithmic_accumulation(tk, offset, shift);
+ offset = logarithmic_accumulation(tk, offset, shift,
+ &clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
@@ -1419,7 +1414,7 @@ static void update_wall_time(void)
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
- action = accumulate_nsecs_to_secs(tk);
+ clock_set |= accumulate_nsecs_to_secs(tk);
write_seqcount_begin(&timekeeper_seq);
/* Update clock->cycle_last with the new value */
@@ -1435,10 +1430,12 @@ static void update_wall_time(void)
* updating.
*/
memcpy(real_tk, tk, sizeof(*tk));
- timekeeping_update(real_tk, action);
+ timekeeping_update(real_tk, clock_set);
write_seqcount_end(&timekeeper_seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (clock_set)
+ clock_was_set();
}
/**
@@ -1583,7 +1580,6 @@ struct timespec get_monotonic_coarse(void)
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
- update_wall_time();
calc_global_load(ticks);
}
@@ -1613,9 +1609,10 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
* ktime_get_update_offsets - hrtimer helper
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
+ * @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets
- * Called from hrtimer_interupt() or retrigger_next_event()
+ * Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot,
ktime_t *offs_tai)
@@ -1697,12 +1694,14 @@ int do_adjtimex(struct timex *txc)
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
- update_pvclock_gtod(tk, true);
- clock_was_set_delayed();
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (tai != orig_tai)
+ clock_was_set();
+
ntp_notify_cmos_timer();
return ret;
@@ -1738,4 +1737,5 @@ void xtime_update(unsigned long ticks)
write_seqlock(&jiffies_lock);
do_timer(ticks);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 0b537f27b559..1fb08f21302e 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -298,15 +298,15 @@ static int tstats_show(struct seq_file *m, void *v)
period = ktime_to_timespec(time);
ms = period.tv_nsec / 1000000;
- seq_puts(m, "Timer Stats Version: v0.2\n");
+ seq_puts(m, "Timer Stats Version: v0.3\n");
seq_printf(m, "Sample period: %ld.%03ld s\n", period.tv_sec, ms);
if (atomic_read(&overflow_count))
- seq_printf(m, "Overflow: %d entries\n",
- atomic_read(&overflow_count));
+ seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count));
+ seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive");
for (i = 0; i < nr_entries; i++) {
entry = entries + i;
- if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
+ if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) {
seq_printf(m, "%4luD, %5d %-16s ",
entry->count, entry->pid, entry->comm);
} else {
diff --git a/kernel/timer.c b/kernel/timer.c
index 4296d13db3d1..accfd241b9e5 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1092,7 +1092,7 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
unsigned long data)
{
- int preempt_count = preempt_count();
+ int count = preempt_count();
#ifdef CONFIG_LOCKDEP
/*
@@ -1119,16 +1119,16 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
lock_map_release(&lockdep_map);
- if (preempt_count != preempt_count()) {
+ if (count != preempt_count()) {
WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
- fn, preempt_count, preempt_count());
+ fn, count, preempt_count());
/*
* Restore the preempt count. That gives us a decent
* chance to survive and extract information. If the
* callback kept a lock held, bad luck, but not worse
* than the BUG() we had.
*/
- preempt_count() = preempt_count;
+ preempt_count_set(count);
}
}
@@ -1518,9 +1518,8 @@ static int init_timers_cpu(int cpu)
/*
* The APs use this path later in boot
*/
- base = kmalloc_node(sizeof(*base),
- GFP_KERNEL | __GFP_ZERO,
- cpu_to_node(cpu));
+ base = kzalloc_node(sizeof(*base), GFP_KERNEL,
+ cpu_to_node(cpu));
if (!base)
return -ENOMEM;
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d7e2068e4b71..1378e84fbe39 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM_RUNTIME),y)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b8b8560bfb95..f785aef65799 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -26,6 +26,7 @@
#include <linux/export.h>
#include <linux/time.h>
#include <linux/uaccess.h>
+#include <linux/list.h>
#include <trace/events/block.h>
@@ -38,6 +39,9 @@ static unsigned int blktrace_seq __read_mostly = 1;
static struct trace_array *blk_tr;
static bool blk_tracer_enabled __read_mostly;
+static LIST_HEAD(running_trace_list);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
+
/* Select an alternative, minimalistic output than the original one */
#define TRACE_BLK_OPT_CLASSIC 0x1
@@ -107,10 +111,18 @@ record_it:
* Send out a notify for this process, if we haven't done so since a trace
* started
*/
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+static void trace_note_tsk(struct task_struct *tsk)
{
+ unsigned long flags;
+ struct blk_trace *bt;
+
tsk->btrace_seq = blktrace_seq;
- trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+ spin_lock_irqsave(&running_trace_lock, flags);
+ list_for_each_entry(bt, &running_trace_list, running_list) {
+ trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
+ sizeof(tsk->comm));
+ }
+ spin_unlock_irqrestore(&running_trace_lock, flags);
}
static void trace_note_time(struct blk_trace *bt)
@@ -229,16 +241,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
goto record_it;
}
+ if (unlikely(tsk->btrace_seq != blktrace_seq))
+ trace_note_tsk(tsk);
+
/*
* A word about the locking here - we disable interrupts to reserve
* some space in the relay per-cpu buffer, to prevent an irq
* from coming in and stepping on our toes.
*/
local_irq_save(flags);
-
- if (unlikely(tsk->btrace_seq != blktrace_seq))
- trace_note_tsk(bt, tsk);
-
t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
if (t) {
sequence = per_cpu_ptr(bt->sequence, cpu);
@@ -477,6 +488,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
bt->dir = dir;
bt->dev = dev;
atomic_set(&bt->dropped, 0);
+ INIT_LIST_HEAD(&bt->running_list);
ret = -EIO;
bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
@@ -567,13 +579,12 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
.end_lba = cbuts.end_lba,
.pid = cbuts.pid,
};
- memcpy(&buts.name, &cbuts.name, 32);
ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
if (ret)
return ret;
- if (copy_to_user(arg, &buts.name, 32)) {
+ if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
blk_trace_remove(q);
return -EFAULT;
}
@@ -601,6 +612,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
blktrace_seq++;
smp_mb();
bt->trace_state = Blktrace_running;
+ spin_lock_irq(&running_trace_lock);
+ list_add(&bt->running_list, &running_trace_list);
+ spin_unlock_irq(&running_trace_lock);
trace_note_time(bt);
ret = 0;
@@ -608,6 +622,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
} else {
if (bt->trace_state == Blktrace_running) {
bt->trace_state = Blktrace_stopped;
+ spin_lock_irq(&running_trace_lock);
+ list_del_init(&bt->running_list);
+ spin_unlock_irq(&running_trace_lock);
relay_flush(bt->rchan);
ret = 0;
}
@@ -1472,6 +1489,9 @@ static int blk_trace_remove_queue(struct request_queue *q)
if (atomic_dec_and_test(&blk_probes_ref))
blk_unregister_tracepoints();
+ spin_lock_irq(&running_trace_lock);
+ list_del(&bt->running_list);
+ spin_unlock_irq(&running_trace_lock);
blk_trace_free(bt);
return 0;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 03cf44ac54d3..cd7f76d1eb86 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@ int function_trace_stop __read_mostly;
/* Current function tracing op */
struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
@@ -278,6 +280,29 @@ static void update_global_ops(void)
global_ops.func = func;
}
+static void ftrace_sync(struct work_struct *work)
+{
+ /*
+ * This function is just a stub to implement a hard force
+ * of synchronize_sched(). This requires synchronizing
+ * tasks even in userspace and idle.
+ *
+ * Yes, function tracing is rude.
+ */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+ /* Probably not needed, but do it anyway */
+ smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
static void update_ftrace_function(void)
{
ftrace_func_t func;
@@ -296,16 +321,61 @@ static void update_ftrace_function(void)
!FTRACE_FORCE_LIST_FUNC)) {
/* Set the ftrace_ops that the arch callback uses */
if (ftrace_ops_list == &global_ops)
- function_trace_op = ftrace_global_list;
+ set_function_trace_op = ftrace_global_list;
else
- function_trace_op = ftrace_ops_list;
+ set_function_trace_op = ftrace_ops_list;
func = ftrace_ops_list->func;
} else {
/* Just use the default ftrace_ops */
- function_trace_op = &ftrace_list_end;
+ set_function_trace_op = &ftrace_list_end;
func = ftrace_ops_list_func;
}
+ /* If there's no change, then do nothing more here */
+ if (ftrace_trace_function == func)
+ return;
+
+ update_function_graph_func();
+
+ /*
+ * If we are using the list function, it doesn't care
+ * about the function_trace_ops.
+ */
+ if (func == ftrace_ops_list_func) {
+ ftrace_trace_function = func;
+ /*
+ * Don't even bother setting function_trace_ops,
+ * it would be racy to do so anyway.
+ */
+ return;
+ }
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ /*
+ * For static tracing, we need to be a bit more careful.
+ * The function change takes affect immediately. Thus,
+ * we need to coorditate the setting of the function_trace_ops
+ * with the setting of the ftrace_trace_function.
+ *
+ * Set the function to the list ops, which will call the
+ * function we want, albeit indirectly, but it handles the
+ * ftrace_ops and doesn't depend on function_trace_op.
+ */
+ ftrace_trace_function = ftrace_ops_list_func;
+ /*
+ * Make sure all CPUs see this. Yes this is slow, but static
+ * tracing is slow and nasty to have enabled.
+ */
+ schedule_on_each_cpu(ftrace_sync);
+ /* Now all cpus are using the list ops. */
+ function_trace_op = set_function_trace_op;
+ /* Make sure the function_trace_op is visible on all CPUs */
+ smp_wmb();
+ /* Nasty way to force a rmb on all cpus */
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
+ /* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
ftrace_trace_function = func;
}
@@ -367,9 +437,6 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
static int __register_ftrace_function(struct ftrace_ops *ops)
{
- if (unlikely(ftrace_disabled))
- return -ENODEV;
-
if (FTRACE_WARN_ON(ops == &global_ops))
return -EINVAL;
@@ -413,24 +480,10 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
return 0;
}
-static void ftrace_sync(struct work_struct *work)
-{
- /*
- * This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
- * tasks even in userspace and idle.
- *
- * Yes, function tracing is rude.
- */
-}
-
static int __unregister_ftrace_function(struct ftrace_ops *ops)
{
int ret;
- if (ftrace_disabled)
- return -ENODEV;
-
if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
return -EBUSY;
@@ -445,20 +498,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
ret = remove_ftrace_list_ops(&ftrace_control_list,
&control_ops, ops);
- if (!ret) {
- /*
- * The ftrace_ops is now removed from the list,
- * so there'll be no new users. We must ensure
- * all current users are done before we free
- * the control data.
- * Note synchronize_sched() is not enough, as we
- * use preempt_disable() to do RCU, but the function
- * tracer can be called where RCU is not active
- * (before user_exit()).
- */
- schedule_on_each_cpu(ftrace_sync);
- control_ops_free(ops);
- }
} else
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
@@ -468,17 +507,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_enabled)
update_ftrace_function();
- /*
- * Dynamic ops may be freed, we must make sure that all
- * callers are done before leaving this function.
- *
- * Again, normal synchronize_sched() is not good enough.
- * We need to do a hard force of sched synchronization.
- */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- schedule_on_each_cpu(ftrace_sync);
-
-
return 0;
}
@@ -781,7 +809,7 @@ static int ftrace_profile_init(void)
int cpu;
int ret = 0;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
ret = ftrace_profile_init_cpu(cpu);
if (ret)
break;
@@ -1088,19 +1116,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
-loff_t
-ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
-{
- loff_t ret;
-
- if (file->f_mode & FMODE_READ)
- ret = seq_lseek(file, offset, whence);
- else
- file->f_pos = ret = 1;
-
- return ret;
-}
-
#ifdef CONFIG_DYNAMIC_FTRACE
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -1998,8 +2013,14 @@ void ftrace_modify_all_code(int command)
else if (command & FTRACE_DISABLE_CALLS)
ftrace_replace_code(0);
- if (update && ftrace_trace_function != ftrace_ops_list_func)
+ if (update && ftrace_trace_function != ftrace_ops_list_func) {
+ function_trace_op = set_function_trace_op;
+ smp_wmb();
+ /* If irqs are disabled, we are in stop machine */
+ if (!irqs_disabled())
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
ftrace_update_ftrace_func(ftrace_trace_function);
+ }
if (command & FTRACE_START_FUNC_RET)
ftrace_enable_ftrace_graph_caller();
@@ -2088,10 +2109,15 @@ static void ftrace_startup_enable(int command)
static int ftrace_startup(struct ftrace_ops *ops, int command)
{
bool hash_enable = true;
+ int ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
+ ret = __register_ftrace_function(ops);
+ if (ret)
+ return ret;
+
ftrace_start_up++;
command |= FTRACE_UPDATE_CALLS;
@@ -2113,12 +2139,17 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
return 0;
}
-static void ftrace_shutdown(struct ftrace_ops *ops, int command)
+static int ftrace_shutdown(struct ftrace_ops *ops, int command)
{
bool hash_disable = true;
+ int ret;
if (unlikely(ftrace_disabled))
- return;
+ return -ENODEV;
+
+ ret = __unregister_ftrace_function(ops);
+ if (ret)
+ return ret;
ftrace_start_up--;
/*
@@ -2152,10 +2183,42 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command)
command |= FTRACE_UPDATE_TRACE_FUNC;
}
- if (!command || !ftrace_enabled)
- return;
+ if (!command || !ftrace_enabled) {
+ /*
+ * If these are control ops, they still need their
+ * per_cpu field freed. Since, function tracing is
+ * not currently active, we can just free them
+ * without synchronizing all CPUs.
+ */
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
+ return 0;
+ }
ftrace_run_update_code(command);
+
+ /*
+ * Dynamic ops may be freed, we must make sure that all
+ * callers are done before leaving this function.
+ * The same goes for freeing the per_cpu data of the control
+ * ops.
+ *
+ * Again, normal synchronize_sched() is not good enough.
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
+ if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+ schedule_on_each_cpu(ftrace_sync);
+
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
+ }
+
+ return 0;
}
static void ftrace_startup_sysctl(void)
@@ -2734,7 +2797,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
* routine, you can use ftrace_filter_write() for the write
* routine if @flag has FTRACE_ITER_FILTER set, or
* ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_filter_lseek() should be used as the lseek routine, and
+ * tracing_lseek() should be used as the lseek routine, and
* release must call ftrace_regex_release().
*/
int
@@ -3060,16 +3123,13 @@ static void __enable_ftrace_function_probe(void)
if (i == FTRACE_FUNC_HASHSIZE)
return;
- ret = __register_ftrace_function(&trace_probe_ops);
- if (!ret)
- ret = ftrace_startup(&trace_probe_ops, 0);
+ ret = ftrace_startup(&trace_probe_ops, 0);
ftrace_probe_registered = 1;
}
static void __disable_ftrace_function_probe(void)
{
- int ret;
int i;
if (!ftrace_probe_registered)
@@ -3082,9 +3142,7 @@ static void __disable_ftrace_function_probe(void)
}
/* no more funcs left */
- ret = __unregister_ftrace_function(&trace_probe_ops);
- if (!ret)
- ftrace_shutdown(&trace_probe_ops, 0);
+ ftrace_shutdown(&trace_probe_ops, 0);
ftrace_probe_registered = 0;
}
@@ -3307,7 +3365,11 @@ void unregister_ftrace_function_probe_all(char *glob)
static LIST_HEAD(ftrace_commands);
static DEFINE_MUTEX(ftrace_cmd_mutex);
-int register_ftrace_command(struct ftrace_func_command *cmd)
+/*
+ * Currently we only register ftrace commands from __init, so mark this
+ * __init too.
+ */
+__init int register_ftrace_command(struct ftrace_func_command *cmd)
{
struct ftrace_func_command *p;
int ret = 0;
@@ -3326,7 +3388,11 @@ int register_ftrace_command(struct ftrace_func_command *cmd)
return ret;
}
-int unregister_ftrace_command(struct ftrace_func_command *cmd)
+/*
+ * Currently we only unregister ftrace commands from __init, so mark
+ * this __init too.
+ */
+__init int unregister_ftrace_command(struct ftrace_func_command *cmd)
{
struct ftrace_func_command *p, *n;
int ret = -ENODEV;
@@ -3641,7 +3707,7 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
static int __init set_graph_function(char *str)
{
@@ -3659,7 +3725,7 @@ static void __init set_ftrace_early_graph(char *buf)
func = strsep(&buf, ",");
/* we allow only one expression at a time */
ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
- func);
+ FTRACE_GRAPH_MAX_FUNCS, func);
if (ret)
printk(KERN_DEBUG "ftrace: function %s not "
"traceable\n", func);
@@ -3759,7 +3825,7 @@ static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -3767,7 +3833,7 @@ static const struct file_operations ftrace_notrace_fops = {
.open = ftrace_notrace_open,
.read = seq_read,
.write = ftrace_notrace_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -3776,15 +3842,25 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
int ftrace_graph_count;
-int ftrace_graph_filter_enabled;
+int ftrace_graph_notrace_count;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+
+struct ftrace_graph_data {
+ unsigned long *table;
+ size_t size;
+ int *count;
+ const struct seq_operations *seq_ops;
+};
static void *
__g_next(struct seq_file *m, loff_t *pos)
{
- if (*pos >= ftrace_graph_count)
+ struct ftrace_graph_data *fgd = m->private;
+
+ if (*pos >= *fgd->count)
return NULL;
- return &ftrace_graph_funcs[*pos];
+ return &fgd->table[*pos];
}
static void *
@@ -3796,10 +3872,12 @@ g_next(struct seq_file *m, void *v, loff_t *pos)
static void *g_start(struct seq_file *m, loff_t *pos)
{
+ struct ftrace_graph_data *fgd = m->private;
+
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
- if (!ftrace_graph_filter_enabled && !*pos)
+ if (!*fgd->count && !*pos)
return (void *)1;
return __g_next(m, pos);
@@ -3835,38 +3913,88 @@ static const struct seq_operations ftrace_graph_seq_ops = {
};
static int
-ftrace_graph_open(struct inode *inode, struct file *file)
+__ftrace_graph_open(struct inode *inode, struct file *file,
+ struct ftrace_graph_data *fgd)
{
int ret = 0;
- if (unlikely(ftrace_disabled))
- return -ENODEV;
-
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
- ftrace_graph_filter_enabled = 0;
- ftrace_graph_count = 0;
- memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
+ *fgd->count = 0;
+ memset(fgd->table, 0, fgd->size * sizeof(*fgd->table));
}
mutex_unlock(&graph_lock);
- if (file->f_mode & FMODE_READ)
- ret = seq_open(file, &ftrace_graph_seq_ops);
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, fgd->seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = fgd;
+ }
+ } else
+ file->private_data = fgd;
return ret;
}
static int
+ftrace_graph_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_graph_data *fgd;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ fgd = kmalloc(sizeof(*fgd), GFP_KERNEL);
+ if (fgd == NULL)
+ return -ENOMEM;
+
+ fgd->table = ftrace_graph_funcs;
+ fgd->size = FTRACE_GRAPH_MAX_FUNCS;
+ fgd->count = &ftrace_graph_count;
+ fgd->seq_ops = &ftrace_graph_seq_ops;
+
+ return __ftrace_graph_open(inode, file, fgd);
+}
+
+static int
+ftrace_graph_notrace_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_graph_data *fgd;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ fgd = kmalloc(sizeof(*fgd), GFP_KERNEL);
+ if (fgd == NULL)
+ return -ENOMEM;
+
+ fgd->table = ftrace_graph_notrace_funcs;
+ fgd->size = FTRACE_GRAPH_MAX_FUNCS;
+ fgd->count = &ftrace_graph_notrace_count;
+ fgd->seq_ops = &ftrace_graph_seq_ops;
+
+ return __ftrace_graph_open(inode, file, fgd);
+}
+
+static int
ftrace_graph_release(struct inode *inode, struct file *file)
{
- if (file->f_mode & FMODE_READ)
+ if (file->f_mode & FMODE_READ) {
+ struct seq_file *m = file->private_data;
+
+ kfree(m->private);
seq_release(inode, file);
+ } else {
+ kfree(file->private_data);
+ }
+
return 0;
}
static int
-ftrace_set_func(unsigned long *array, int *idx, char *buffer)
+ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
{
struct dyn_ftrace *rec;
struct ftrace_page *pg;
@@ -3879,7 +4007,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
/* decode regex */
type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
- if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+ if (!not && *idx >= size)
return -EBUSY;
search_len = strlen(search);
@@ -3907,7 +4035,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
fail = 0;
if (!exists) {
array[(*idx)++] = rec->ip;
- if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+ if (*idx >= size)
goto out;
}
} else {
@@ -3925,8 +4053,6 @@ out:
if (fail)
return -EINVAL;
- ftrace_graph_filter_enabled = !!(*idx);
-
return 0;
}
@@ -3935,36 +4061,33 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
- ssize_t read, ret;
+ ssize_t read, ret = 0;
+ struct ftrace_graph_data *fgd = file->private_data;
if (!cnt)
return 0;
- mutex_lock(&graph_lock);
-
- if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
- ret = -ENOMEM;
- goto out_unlock;
- }
+ if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX))
+ return -ENOMEM;
read = trace_get_user(&parser, ubuf, cnt, ppos);
if (read >= 0 && trace_parser_loaded((&parser))) {
parser.buffer[parser.idx] = 0;
+ mutex_lock(&graph_lock);
+
/* we allow only one expression at a time */
- ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
- parser.buffer);
- if (ret)
- goto out_free;
+ ret = ftrace_set_func(fgd->table, fgd->count, fgd->size,
+ parser.buffer);
+
+ mutex_unlock(&graph_lock);
}
- ret = read;
+ if (!ret)
+ ret = read;
-out_free:
trace_parser_put(&parser);
-out_unlock:
- mutex_unlock(&graph_lock);
return ret;
}
@@ -3973,7 +4096,15 @@ static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
+ .release = ftrace_graph_release,
+};
+
+static const struct file_operations ftrace_graph_notrace_fops = {
+ .open = ftrace_graph_notrace_open,
+ .read = seq_read,
+ .write = ftrace_graph_write,
+ .llseek = tracing_lseek,
.release = ftrace_graph_release,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -3997,6 +4128,9 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
trace_create_file("set_graph_function", 0444, d_tracer,
NULL,
&ftrace_graph_fops);
+ trace_create_file("set_graph_notrace", 0444, d_tracer,
+ NULL,
+ &ftrace_graph_notrace_fops);
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
return 0;
@@ -4290,12 +4424,15 @@ core_initcall(ftrace_nodyn_init);
static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
static inline void ftrace_startup_enable(int command) { }
/* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command) \
- ({ \
- (ops)->flags |= FTRACE_OPS_FL_ENABLED; \
- 0; \
+# define ftrace_startup(ops, command) \
+ ({ \
+ int ___ret = __register_ftrace_function(ops); \
+ if (!___ret) \
+ (ops)->flags |= FTRACE_OPS_FL_ENABLED; \
+ ___ret; \
})
-# define ftrace_shutdown(ops, command) do { } while (0)
+# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+
# define ftrace_startup_sysctl() do { } while (0)
# define ftrace_shutdown_sysctl() do { } while (0)
@@ -4320,12 +4457,21 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
*/
preempt_disable_notrace();
trace_recursion_set(TRACE_CONTROL_BIT);
+
+ /*
+ * Control funcs (perf) uses RCU. Only trace if
+ * RCU is currently active.
+ */
+ if (!rcu_is_watching())
+ goto out;
+
do_for_each_ftrace_op(op, ftrace_control_list) {
if (!(op->flags & FTRACE_OPS_FL_STUB) &&
!ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip, regs))
op->func(ip, parent_ip, op, regs);
} while_for_each_ftrace_op(op);
+ out:
trace_recursion_clear(TRACE_CONTROL_BIT);
preempt_enable_notrace();
}
@@ -4631,7 +4777,7 @@ static const struct file_operations ftrace_pid_fops = {
.open = ftrace_pid_open,
.write = ftrace_pid_write,
.read = seq_read,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_pid_release,
};
@@ -4695,9 +4841,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
mutex_lock(&ftrace_lock);
- ret = __register_ftrace_function(ops);
- if (!ret)
- ret = ftrace_startup(ops, 0);
+ ret = ftrace_startup(ops, 0);
mutex_unlock(&ftrace_lock);
@@ -4716,9 +4860,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
int ret;
mutex_lock(&ftrace_lock);
- ret = __unregister_ftrace_function(ops);
- if (!ret)
- ftrace_shutdown(ops, 0);
+ ret = ftrace_shutdown(ops, 0);
mutex_unlock(&ftrace_lock);
return ret;
@@ -4778,6 +4920,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
trace_func_graph_ret_t ftrace_graph_return =
(trace_func_graph_ret_t)ftrace_stub;
trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -4912,6 +5055,37 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
return NOTIFY_DONE;
}
+/* Just a place holder for function graph */
+static struct ftrace_ops fgraph_ops __read_mostly = {
+ .func = ftrace_stub,
+ .flags = FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
+ FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+ if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+ return 0;
+ return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+ if (ftrace_ops_list == &ftrace_list_end ||
+ (ftrace_ops_list == &global_ops &&
+ global_ops.next == &ftrace_list_end))
+ ftrace_graph_entry = __ftrace_graph_entry;
+ else
+ ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc)
{
@@ -4936,9 +5110,18 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
}
ftrace_graph_return = retfunc;
- ftrace_graph_entry = entryfunc;
- ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+ /*
+ * Update the indirect function to the entryfunc, and the
+ * function that gets called to the entry_test first. Then
+ * call the update fgraph entry function to determine if
+ * the entryfunc should be called directly or not.
+ */
+ __ftrace_graph_entry = entryfunc;
+ ftrace_graph_entry = ftrace_graph_entry_test;
+ update_function_graph_func();
+
+ ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
out:
mutex_unlock(&ftrace_lock);
@@ -4955,7 +5138,8 @@ void unregister_ftrace_graph(void)
ftrace_graph_active--;
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
- ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+ __ftrace_graph_entry = ftrace_graph_entry_stub;
+ ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cc2f66f68dc5..294b8a271a04 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2558,7 +2558,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
if (unlikely(test_time_stamp(delta))) {
int local_clock_stable = 1;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- local_clock_stable = sched_clock_stable;
+ local_clock_stable = sched_clock_stable();
#endif
WARN_ONCE(delta > (1ULL << 59),
KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7974ba20557d..20c755e018ca 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -235,13 +235,33 @@ void trace_array_put(struct trace_array *this_tr)
mutex_unlock(&trace_types_lock);
}
-int filter_current_check_discard(struct ring_buffer *buffer,
- struct ftrace_event_call *call, void *rec,
- struct ring_buffer_event *event)
+int filter_check_discard(struct ftrace_event_file *file, void *rec,
+ struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
{
- return filter_check_discard(call, rec, buffer, event);
+ if (unlikely(file->flags & FTRACE_EVENT_FL_FILTERED) &&
+ !filter_match_preds(file->filter, rec)) {
+ ring_buffer_discard_commit(buffer, event);
+ return 1;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(filter_check_discard);
+
+int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
+ struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
+ !filter_match_preds(call->filter, rec)) {
+ ring_buffer_discard_commit(buffer, event);
+ return 1;
+ }
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(filter_current_check_discard);
+EXPORT_SYMBOL_GPL(call_filter_check_discard);
cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
{
@@ -575,6 +595,28 @@ void free_snapshot(struct trace_array *tr)
}
/**
+ * tracing_alloc_snapshot - allocate snapshot buffer.
+ *
+ * This only allocates the snapshot buffer if it isn't already
+ * allocated - it doesn't also take a snapshot.
+ *
+ * This is meant to be used in cases where the snapshot buffer needs
+ * to be set up for events that can't sleep but need to be able to
+ * trigger a snapshot.
+ */
+int tracing_alloc_snapshot(void)
+{
+ struct trace_array *tr = &global_trace;
+ int ret;
+
+ ret = alloc_snapshot(tr);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
+
+/**
* trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
*
* This is similar to trace_snapshot(), but it will allocate the
@@ -587,11 +629,10 @@ void free_snapshot(struct trace_array *tr)
*/
void tracing_snapshot_alloc(void)
{
- struct trace_array *tr = &global_trace;
int ret;
- ret = alloc_snapshot(tr);
- if (WARN_ON(ret < 0))
+ ret = tracing_alloc_snapshot();
+ if (ret < 0)
return;
tracing_snapshot();
@@ -603,6 +644,12 @@ void tracing_snapshot(void)
WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot);
+int tracing_alloc_snapshot(void)
+{
+ WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used");
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
void tracing_snapshot_alloc(void)
{
/* Give warning */
@@ -843,9 +890,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
if (isspace(ch)) {
parser->buffer[parser->idx] = 0;
parser->cont = false;
- } else {
+ } else if (parser->idx < parser->size - 1) {
parser->cont = true;
parser->buffer[parser->idx++] = ch;
+ } else {
+ ret = -EINVAL;
+ goto out;
}
*ppos += read;
@@ -1261,21 +1311,6 @@ int is_tracing_stopped(void)
}
/**
- * ftrace_off_permanent - disable all ftrace code permanently
- *
- * This should only be called when a serious anomally has
- * been detected. This will turn off the function tracing,
- * ring buffers, and other tracing utilites. It takes no
- * locks and can be called from any context.
- */
-void ftrace_off_permanent(void)
-{
- tracing_disabled = 1;
- ftrace_stop();
- tracing_off_permanent();
-}
-
-/**
* tracing_start - quick start of the tracer
*
* If tracing is enabled but was stopped by tracing_stop,
@@ -1509,7 +1544,8 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
#endif
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
- (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
+ (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
+ (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
}
EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
@@ -1630,7 +1666,7 @@ trace_function(struct trace_array *tr,
entry->ip = ip;
entry->parent_ip = parent_ip;
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
}
@@ -1714,7 +1750,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
entry->size = trace.nr_entries;
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
out:
@@ -1816,7 +1852,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
trace.entries = entry->caller;
save_stack_trace_user(&trace);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
out_drop_count:
@@ -2008,7 +2044,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
entry->fmt = fmt;
memcpy(entry->buf, tbuffer, sizeof(u32) * len);
- if (!filter_check_discard(call, entry, buffer, event)) {
+ if (!call_filter_check_discard(call, entry, buffer, event)) {
__buffer_unlock_commit(buffer, event);
ftrace_trace_stack(buffer, flags, 6, pc);
}
@@ -2063,7 +2099,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
memcpy(&entry->buf, tbuffer, len);
entry->buf[len] = '\0';
- if (!filter_check_discard(call, entry, buffer, event)) {
+ if (!call_filter_check_discard(call, entry, buffer, event)) {
__buffer_unlock_commit(buffer, event);
ftrace_trace_stack(buffer, flags, 6, pc);
}
@@ -2760,7 +2796,7 @@ static void show_snapshot_main_help(struct seq_file *m)
seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n");
seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n");
seq_printf(m, "# Takes a snapshot of the main buffer.\n");
- seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n");
+ seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n");
seq_printf(m, "# (Doesn't have to be '2' works with any number that\n");
seq_printf(m, "# is not a '0' or '1')\n");
}
@@ -2964,6 +3000,11 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
return 0;
}
+bool tracing_is_disabled(void)
+{
+ return (tracing_disabled) ? true: false;
+}
+
/*
* Open and update trace_array ref count.
* Must have the current trace_array passed to it.
@@ -3142,19 +3183,23 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
return count;
}
-static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence)
{
+ int ret;
+
if (file->f_mode & FMODE_READ)
- return seq_lseek(file, offset, origin);
+ ret = seq_lseek(file, offset, whence);
else
- return 0;
+ file->f_pos = ret = 0;
+
+ return ret;
}
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_release,
};
@@ -4198,12 +4243,6 @@ out:
return sret;
}
-static void tracing_pipe_buf_release(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- __free_page(buf->page);
-}
-
static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
unsigned int idx)
{
@@ -4215,7 +4254,7 @@ static const struct pipe_buf_operations tracing_pipe_buf_ops = {
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
.confirm = generic_pipe_buf_confirm,
- .release = tracing_pipe_buf_release,
+ .release = generic_pipe_buf_release,
.steal = generic_pipe_buf_steal,
.get = generic_pipe_buf_get,
};
@@ -4899,7 +4938,7 @@ static const struct file_operations snapshot_fops = {
.open = tracing_snapshot_open,
.read = seq_read,
.write = tracing_snapshot_write,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_snapshot_release,
};
@@ -5454,12 +5493,12 @@ static struct ftrace_func_command ftrace_snapshot_cmd = {
.func = ftrace_trace_snapshot_callback,
};
-static int register_snapshot_cmd(void)
+static __init int register_snapshot_cmd(void)
{
return register_ftrace_command(&ftrace_snapshot_cmd);
}
#else
-static inline int register_snapshot_cmd(void) { return 0; }
+static inline __init int register_snapshot_cmd(void) { return 0; }
#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */
struct dentry *tracing_init_dentry_tr(struct trace_array *tr)
@@ -5869,6 +5908,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+ buf->tr = tr;
+
buf->buffer = ring_buffer_alloc(size, rb_flags);
if (!buf->buffer)
return -ENOMEM;
@@ -6253,6 +6294,17 @@ void trace_init_global_iter(struct trace_iterator *iter)
iter->trace = iter->tr->current_trace;
iter->cpu_file = RING_BUFFER_ALL_CPUS;
iter->trace_buffer = &global_trace.trace_buffer;
+
+ if (iter->trace && iter->trace->open)
+ iter->trace->open(iter);
+
+ /* Annotate start of buffers if we had overruns */
+ if (ring_buffer_overruns(iter->trace_buffer->buffer))
+ iter->iter_flags |= TRACE_FILE_ANNOTATE;
+
+ /* Output in nanoseconds only if we are using a clock in nanoseconds. */
+ if (trace_clocks[iter->tr->clock_id].in_ns)
+ iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
}
void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 10c86fb7a2b4..02b592f2d4b7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,3 +1,4 @@
+
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H
@@ -124,6 +125,7 @@ enum trace_flag_type {
TRACE_FLAG_NEED_RESCHED = 0x04,
TRACE_FLAG_HARDIRQ = 0x08,
TRACE_FLAG_SOFTIRQ = 0x10,
+ TRACE_FLAG_PREEMPT_RESCHED = 0x20,
};
#define TRACE_BUF_SIZE 1024
@@ -192,8 +194,8 @@ struct trace_array {
#ifdef CONFIG_FTRACE_SYSCALLS
int sys_refcount_enter;
int sys_refcount_exit;
- DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
- DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+ struct ftrace_event_file __rcu *enter_syscall_files[NR_syscalls];
+ struct ftrace_event_file __rcu *exit_syscall_files[NR_syscalls];
#endif
int stop_count;
int clock_id;
@@ -514,6 +516,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf);
void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
+bool tracing_is_disabled(void);
struct dentry *trace_create_file(const char *name,
umode_t mode,
struct dentry *parent,
@@ -585,6 +588,8 @@ void tracing_start_sched_switch_record(void);
int register_tracer(struct tracer *type);
int is_tracing_stopped(void);
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence);
+
extern cpumask_var_t __read_mostly tracing_buffer_mask;
#define for_each_tracing_cpu(cpu) \
@@ -711,6 +716,8 @@ extern unsigned long trace_flags;
#define TRACE_GRAPH_PRINT_PROC 0x8
#define TRACE_GRAPH_PRINT_DURATION 0x10
#define TRACE_GRAPH_PRINT_ABS_TIME 0x20
+#define TRACE_GRAPH_PRINT_FILL_SHIFT 28
+#define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
extern enum print_line_t
print_graph_function_flags(struct trace_iterator *iter, u32 flags);
@@ -730,15 +737,16 @@ extern void __trace_graph_return(struct trace_array *tr,
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS 32
-extern int ftrace_graph_filter_enabled;
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
+extern int ftrace_graph_notrace_count;
+extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS];
static inline int ftrace_graph_addr(unsigned long addr)
{
int i;
- if (!ftrace_graph_filter_enabled)
+ if (!ftrace_graph_count)
return 1;
for (i = 0; i < ftrace_graph_count; i++) {
@@ -758,11 +766,31 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 0;
}
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+ int i;
+
+ if (!ftrace_graph_notrace_count)
+ return 0;
+
+ for (i = 0; i < ftrace_graph_notrace_count; i++) {
+ if (addr == ftrace_graph_notrace_funcs[i])
+ return 1;
+ }
+
+ return 0;
+}
#else
static inline int ftrace_graph_addr(unsigned long addr)
{
return 1;
}
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+ return 0;
+}
#endif /* CONFIG_DYNAMIC_FTRACE */
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
@@ -986,40 +1014,216 @@ struct filter_pred {
extern enum regex_type
filter_parse_regex(char *buff, int len, char **search, int *not);
-extern void print_event_filter(struct ftrace_event_call *call,
+extern void print_event_filter(struct ftrace_event_file *file,
struct trace_seq *s);
-extern int apply_event_filter(struct ftrace_event_call *call,
+extern int apply_event_filter(struct ftrace_event_file *file,
char *filter_string);
extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
char *filter_string);
extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
+extern int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp);
+extern void free_event_filter(struct event_filter *filter);
struct ftrace_event_field *
trace_find_event_field(struct ftrace_event_call *call, char *name);
-static inline int
-filter_check_discard(struct ftrace_event_call *call, void *rec,
- struct ring_buffer *buffer,
- struct ring_buffer_event *event)
-{
- if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
- !filter_match_preds(call->filter, rec)) {
- ring_buffer_discard_commit(buffer, event);
- return 1;
- }
-
- return 0;
-}
-
extern void trace_event_enable_cmd_record(bool enable);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
+extern struct ftrace_event_file *find_event_file(struct trace_array *tr,
+ const char *system,
+ const char *event);
+
+static inline void *event_file_data(struct file *filp)
+{
+ return ACCESS_ONCE(file_inode(filp)->i_private);
+}
+
extern struct mutex event_mutex;
extern struct list_head ftrace_events;
+extern const struct file_operations event_trigger_fops;
+
+extern int register_trigger_cmds(void);
+extern void clear_event_triggers(struct trace_array *tr);
+
+struct event_trigger_data {
+ unsigned long count;
+ int ref;
+ struct event_trigger_ops *ops;
+ struct event_command *cmd_ops;
+ struct event_filter __rcu *filter;
+ char *filter_str;
+ void *private_data;
+ struct list_head list;
+};
+
+/**
+ * struct event_trigger_ops - callbacks for trace event triggers
+ *
+ * The methods in this structure provide per-event trigger hooks for
+ * various trigger operations.
+ *
+ * All the methods below, except for @init() and @free(), must be
+ * implemented.
+ *
+ * @func: The trigger 'probe' function called when the triggering
+ * event occurs. The data passed into this callback is the data
+ * that was supplied to the event_command @reg() function that
+ * registered the trigger (see struct event_command).
+ *
+ * @init: An optional initialization function called for the trigger
+ * when the trigger is registered (via the event_command reg()
+ * function). This can be used to perform per-trigger
+ * initialization such as incrementing a per-trigger reference
+ * count, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_init() (see
+ * trace_event_triggers.c).
+ *
+ * @free: An optional de-initialization function called for the
+ * trigger when the trigger is unregistered (via the
+ * event_command @reg() function). This can be used to perform
+ * per-trigger de-initialization such as decrementing a
+ * per-trigger reference count and freeing corresponding trigger
+ * data, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_free() (see
+ * trace_event_triggers.c).
+ *
+ * @print: The callback function invoked to have the trigger print
+ * itself. This is usually implemented by a wrapper function
+ * that calls the generic utility function @event_trigger_print()
+ * (see trace_event_triggers.c).
+ */
+struct event_trigger_ops {
+ void (*func)(struct event_trigger_data *data);
+ int (*init)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ void (*free)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ int (*print)(struct seq_file *m,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+};
+
+/**
+ * struct event_command - callbacks and data members for event commands
+ *
+ * Event commands are invoked by users by writing the command name
+ * into the 'trigger' file associated with a trace event. The
+ * parameters associated with a specific invocation of an event
+ * command are used to create an event trigger instance, which is
+ * added to the list of trigger instances associated with that trace
+ * event. When the event is hit, the set of triggers associated with
+ * that event is invoked.
+ *
+ * The data members in this structure provide per-event command data
+ * for various event commands.
+ *
+ * All the data members below, except for @post_trigger, must be set
+ * for each event command.
+ *
+ * @name: The unique name that identifies the event command. This is
+ * the name used when setting triggers via trigger files.
+ *
+ * @trigger_type: A unique id that identifies the event command
+ * 'type'. This value has two purposes, the first to ensure that
+ * only one trigger of the same type can be set at a given time
+ * for a particular event e.g. it doesn't make sense to have both
+ * a traceon and traceoff trigger attached to a single event at
+ * the same time, so traceon and traceoff have the same type
+ * though they have different names. The @trigger_type value is
+ * also used as a bit value for deferring the actual trigger
+ * action until after the current event is finished. Some
+ * commands need to do this if they themselves log to the trace
+ * buffer (see the @post_trigger() member below). @trigger_type
+ * values are defined by adding new values to the trigger_type
+ * enum in include/linux/ftrace_event.h.
+ *
+ * @post_trigger: A flag that says whether or not this command needs
+ * to have its action delayed until after the current event has
+ * been closed. Some triggers need to avoid being invoked while
+ * an event is currently in the process of being logged, since
+ * the trigger may itself log data into the trace buffer. Thus
+ * we make sure the current event is committed before invoking
+ * those triggers. To do that, the trigger invocation is split
+ * in two - the first part checks the filter using the current
+ * trace record; if a command has the @post_trigger flag set, it
+ * sets a bit for itself in the return value, otherwise it
+ * directly invokes the trigger. Once all commands have been
+ * either invoked or set their return flag, the current record is
+ * either committed or discarded. At that point, if any commands
+ * have deferred their triggers, those commands are finally
+ * invoked following the close of the current event. In other
+ * words, if the event_trigger_ops @func() probe implementation
+ * itself logs to the trace buffer, this flag should be set,
+ * otherwise it can be left unspecified.
+ *
+ * All the methods below, except for @set_filter(), must be
+ * implemented.
+ *
+ * @func: The callback function responsible for parsing and
+ * registering the trigger written to the 'trigger' file by the
+ * user. It allocates the trigger instance and registers it with
+ * the appropriate trace event. It makes use of the other
+ * event_command callback functions to orchestrate this, and is
+ * usually implemented by the generic utility function
+ * @event_trigger_callback() (see trace_event_triggers.c).
+ *
+ * @reg: Adds the trigger to the list of triggers associated with the
+ * event, and enables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @init() function).
+ * This is also where commands can use the @trigger_type value to
+ * make the decision as to whether or not multiple instances of
+ * the trigger should be allowed. This is usually implemented by
+ * the generic utility function @register_trigger() (see
+ * trace_event_triggers.c).
+ *
+ * @unreg: Removes the trigger from the list of triggers associated
+ * with the event, and disables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @free() function).
+ * This is usually implemented by the generic utility function
+ * @unregister_trigger() (see trace_event_triggers.c).
+ *
+ * @set_filter: An optional function called to parse and set a filter
+ * for the trigger. If no @set_filter() method is set for the
+ * event command, filters set by the user for the command will be
+ * ignored. This is usually implemented by the generic utility
+ * function @set_trigger_filter() (see trace_event_triggers.c).
+ *
+ * @get_trigger_ops: The callback function invoked to retrieve the
+ * event_trigger_ops implementation associated with the command.
+ */
+struct event_command {
+ struct list_head list;
+ char *name;
+ enum event_trigger_type trigger_type;
+ bool post_trigger;
+ int (*func)(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *params);
+ int (*reg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ void (*unreg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ int (*set_filter)(char *filter_str,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
+};
+
+extern int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable);
+extern int tracing_alloc_snapshot(void);
+
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index d594da0dc03c..697fb9bac8f0 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -78,7 +78,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
entry->line = f->line;
entry->correct = val == expect;
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
out:
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 80c36bcf66e8..e854f420e033 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,9 +24,15 @@ static int total_ref_count;
static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
+ if (tp_event->perf_perm) {
+ int ret = tp_event->perf_perm(tp_event, p_event);
+ if (ret)
+ return ret;
+ }
+
/* The ftrace function trace is allowed only for root. */
if (ftrace_event_is_function(tp_event) &&
- perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+ perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
return -EPERM;
/* No tracing, just counting, so no obvious leak */
@@ -173,7 +179,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
int perf_trace_init(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event;
- int event_id = p_event->attr.config;
+ u64 event_id = p_event->attr.config;
int ret = -EINVAL;
mutex_lock(&event_mutex);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 368a4d50cc30..e71ffd4eccb5 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -342,6 +342,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
return ret;
}
+int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable)
+{
+ return __ftrace_event_enable_disable(file, enable, soft_disable);
+}
+
static int ftrace_event_enable_disable(struct ftrace_event_file *file,
int enable)
{
@@ -421,11 +427,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir)
}
}
-static void *event_file_data(struct file *filp)
-{
- return ACCESS_ONCE(file_inode(filp)->i_private);
-}
-
static void remove_event_file_dir(struct ftrace_event_file *file)
{
struct dentry *dir = file->dir;
@@ -989,7 +990,7 @@ static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
struct trace_seq *s;
int r = -ENODEV;
@@ -1004,12 +1005,12 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
mutex_lock(&event_mutex);
- call = event_file_data(filp);
- if (call)
- print_event_filter(call, s);
+ file = event_file_data(filp);
+ if (file)
+ print_event_filter(file, s);
mutex_unlock(&event_mutex);
- if (call)
+ if (file)
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
@@ -1021,7 +1022,7 @@ static ssize_t
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_file *file;
char *buf;
int err = -ENODEV;
@@ -1039,9 +1040,9 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
buf[cnt] = '\0';
mutex_lock(&event_mutex);
- call = event_file_data(filp);
- if (call)
- err = apply_event_filter(call, buf);
+ file = event_file_data(filp);
+ if (file)
+ err = apply_event_filter(file, buf);
mutex_unlock(&event_mutex);
free_page((unsigned long) buf);
@@ -1062,6 +1063,9 @@ static int subsystem_open(struct inode *inode, struct file *filp)
struct trace_array *tr;
int ret;
+ if (tracing_is_disabled())
+ return -ENODEV;
+
/* Make sure the system still exists */
mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
@@ -1108,6 +1112,9 @@ static int system_tr_open(struct inode *inode, struct file *filp)
struct trace_array *tr = inode->i_private;
int ret;
+ if (tracing_is_disabled())
+ return -ENODEV;
+
if (trace_array_get(tr) < 0)
return -ENODEV;
@@ -1124,11 +1131,12 @@ static int system_tr_open(struct inode *inode, struct file *filp)
if (ret < 0) {
trace_array_put(tr);
kfree(dir);
+ return ret;
}
filp->private_data = dir;
- return ret;
+ return 0;
}
static int subsystem_release(struct inode *inode, struct file *file)
@@ -1539,9 +1547,12 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
return -1;
}
}
- trace_create_file("filter", 0644, file->dir, call,
+ trace_create_file("filter", 0644, file->dir, file,
&ftrace_event_filter_fops);
+ trace_create_file("trigger", 0644, file->dir, file,
+ &event_trigger_fops);
+
trace_create_file("format", 0444, file->dir, call,
&ftrace_event_format_fops);
@@ -1577,6 +1588,7 @@ static void event_remove(struct ftrace_event_call *call)
if (file->event_call != call)
continue;
ftrace_event_enable_disable(file, 0);
+ destroy_preds(file);
/*
* The do_for_each_event_file() is
* a double loop. After finding the call for this
@@ -1637,6 +1649,8 @@ trace_create_new_event(struct ftrace_event_call *call,
file->event_call = call;
file->tr = tr;
atomic_set(&file->sm_ref, 0);
+ atomic_set(&file->tm_ref, 0);
+ INIT_LIST_HEAD(&file->triggers);
list_add(&file->list, &tr->events);
return file;
@@ -1700,7 +1714,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call)
{
event_remove(call);
trace_destroy_fields(call);
- destroy_preds(call);
+ destroy_call_preds(call);
}
static int probe_remove_event_call(struct ftrace_event_call *call)
@@ -1841,20 +1855,7 @@ __trace_add_event_dirs(struct trace_array *tr)
}
}
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-/* Avoid typos */
-#define ENABLE_EVENT_STR "enable_event"
-#define DISABLE_EVENT_STR "disable_event"
-
-struct event_probe_data {
- struct ftrace_event_file *file;
- unsigned long count;
- int ref;
- bool enable;
-};
-
-static struct ftrace_event_file *
+struct ftrace_event_file *
find_event_file(struct trace_array *tr, const char *system, const char *event)
{
struct ftrace_event_file *file;
@@ -1877,6 +1878,19 @@ find_event_file(struct trace_array *tr, const char *system, const char *event)
return NULL;
}
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct event_probe_data {
+ struct ftrace_event_file *file;
+ unsigned long count;
+ int ref;
+ bool enable;
+};
+
static void
event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
{
@@ -2303,9 +2317,15 @@ int event_trace_del_tracer(struct trace_array *tr)
{
mutex_lock(&event_mutex);
+ /* Disable any event triggers and associated soft-disabled events */
+ clear_event_triggers(tr);
+
/* Disable any running events */
__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
+ /* Access to events are within rcu_read_lock_sched() */
+ synchronize_sched();
+
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
debugfs_remove_recursive(tr->event_dir);
@@ -2366,6 +2386,8 @@ static __init int event_trace_enable(void)
register_event_cmds();
+ register_trigger_cmds();
+
return 0;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 97daa8cf958d..8a8631926a07 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -637,10 +637,18 @@ static void append_filter_err(struct filter_parse_state *ps,
free_page((unsigned long) buf);
}
+static inline struct event_filter *event_filter(struct ftrace_event_file *file)
+{
+ if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ return file->event_call->filter;
+ else
+ return file->filter;
+}
+
/* caller must hold event_mutex */
-void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
+void print_event_filter(struct ftrace_event_file *file, struct trace_seq *s)
{
- struct event_filter *filter = call->filter;
+ struct event_filter *filter = event_filter(file);
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
@@ -766,11 +774,21 @@ static void __free_preds(struct event_filter *filter)
filter->n_preds = 0;
}
-static void filter_disable(struct ftrace_event_call *call)
+static void call_filter_disable(struct ftrace_event_call *call)
{
call->flags &= ~TRACE_EVENT_FL_FILTERED;
}
+static void filter_disable(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ call_filter_disable(call);
+ else
+ file->flags &= ~FTRACE_EVENT_FL_FILTERED;
+}
+
static void __free_filter(struct event_filter *filter)
{
if (!filter)
@@ -781,16 +799,35 @@ static void __free_filter(struct event_filter *filter)
kfree(filter);
}
+void free_event_filter(struct event_filter *filter)
+{
+ __free_filter(filter);
+}
+
+void destroy_call_preds(struct ftrace_event_call *call)
+{
+ __free_filter(call->filter);
+ call->filter = NULL;
+}
+
+static void destroy_file_preds(struct ftrace_event_file *file)
+{
+ __free_filter(file->filter);
+ file->filter = NULL;
+}
+
/*
- * Called when destroying the ftrace_event_call.
- * The call is being freed, so we do not need to worry about
- * the call being currently used. This is for module code removing
+ * Called when destroying the ftrace_event_file.
+ * The file is being freed, so we do not need to worry about
+ * the file being currently used. This is for module code removing
* the tracepoints from within it.
*/
-void destroy_preds(struct ftrace_event_call *call)
+void destroy_preds(struct ftrace_event_file *file)
{
- __free_filter(call->filter);
- call->filter = NULL;
+ if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ destroy_call_preds(file->event_call);
+ else
+ destroy_file_preds(file);
}
static struct event_filter *__alloc_filter(void)
@@ -825,28 +862,56 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)
return 0;
}
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static inline void __remove_filter(struct ftrace_event_file *file)
{
+ struct ftrace_event_call *call = file->event_call;
+
+ filter_disable(file);
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ remove_filter_string(call->filter);
+ else
+ remove_filter_string(file->filter);
+}
+
+static void filter_free_subsystem_preds(struct event_subsystem *system,
+ struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
struct ftrace_event_call *call;
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
+ call = file->event_call;
if (strcmp(call->class->system, system->name) != 0)
continue;
- filter_disable(call);
- remove_filter_string(call->filter);
+ __remove_filter(file);
}
}
-static void filter_free_subsystem_filters(struct event_subsystem *system)
+static inline void __free_subsystem_filter(struct ftrace_event_file *file)
{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) {
+ __free_filter(call->filter);
+ call->filter = NULL;
+ } else {
+ __free_filter(file->filter);
+ file->filter = NULL;
+ }
+}
+
+static void filter_free_subsystem_filters(struct event_subsystem *system,
+ struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
struct ftrace_event_call *call;
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
+ call = file->event_call;
if (strcmp(call->class->system, system->name) != 0)
continue;
- __free_filter(call->filter);
- call->filter = NULL;
+ __free_subsystem_filter(file);
}
}
@@ -1617,15 +1682,85 @@ fail:
return err;
}
+static inline void event_set_filtered_flag(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ call->flags |= TRACE_EVENT_FL_FILTERED;
+ else
+ file->flags |= FTRACE_EVENT_FL_FILTERED;
+}
+
+static inline void event_set_filter(struct ftrace_event_file *file,
+ struct event_filter *filter)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ rcu_assign_pointer(call->filter, filter);
+ else
+ rcu_assign_pointer(file->filter, filter);
+}
+
+static inline void event_clear_filter(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ RCU_INIT_POINTER(call->filter, NULL);
+ else
+ RCU_INIT_POINTER(file->filter, NULL);
+}
+
+static inline void
+event_set_no_set_filter_flag(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+ else
+ file->flags |= FTRACE_EVENT_FL_NO_SET_FILTER;
+}
+
+static inline void
+event_clear_no_set_filter_flag(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+ call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
+ else
+ file->flags &= ~FTRACE_EVENT_FL_NO_SET_FILTER;
+}
+
+static inline bool
+event_no_set_filter_flag(struct ftrace_event_file *file)
+{
+ struct ftrace_event_call *call = file->event_call;
+
+ if (file->flags & FTRACE_EVENT_FL_NO_SET_FILTER)
+ return true;
+
+ if ((call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) &&
+ (call->flags & TRACE_EVENT_FL_NO_SET_FILTER))
+ return true;
+
+ return false;
+}
+
struct filter_list {
struct list_head list;
struct event_filter *filter;
};
static int replace_system_preds(struct event_subsystem *system,
+ struct trace_array *tr,
struct filter_parse_state *ps,
char *filter_string)
{
+ struct ftrace_event_file *file;
struct ftrace_event_call *call;
struct filter_list *filter_item;
struct filter_list *tmp;
@@ -1633,8 +1768,8 @@ static int replace_system_preds(struct event_subsystem *system,
bool fail = true;
int err;
- list_for_each_entry(call, &ftrace_events, list) {
-
+ list_for_each_entry(file, &tr->events, list) {
+ call = file->event_call;
if (strcmp(call->class->system, system->name) != 0)
continue;
@@ -1644,18 +1779,20 @@ static int replace_system_preds(struct event_subsystem *system,
*/
err = replace_preds(call, NULL, ps, filter_string, true);
if (err)
- call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+ event_set_no_set_filter_flag(file);
else
- call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
+ event_clear_no_set_filter_flag(file);
}
- list_for_each_entry(call, &ftrace_events, list) {
+ list_for_each_entry(file, &tr->events, list) {
struct event_filter *filter;
+ call = file->event_call;
+
if (strcmp(call->class->system, system->name) != 0)
continue;
- if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+ if (event_no_set_filter_flag(file))
continue;
filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
@@ -1676,17 +1813,17 @@ static int replace_system_preds(struct event_subsystem *system,
err = replace_preds(call, filter, ps, filter_string, false);
if (err) {
- filter_disable(call);
+ filter_disable(file);
parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
append_filter_err(ps, filter);
} else
- call->flags |= TRACE_EVENT_FL_FILTERED;
+ event_set_filtered_flag(file);
/*
* Regardless of if this returned an error, we still
* replace the filter for the call.
*/
- filter = call->filter;
- rcu_assign_pointer(call->filter, filter_item->filter);
+ filter = event_filter(file);
+ event_set_filter(file, filter_item->filter);
filter_item->filter = filter;
fail = false;
@@ -1806,6 +1943,13 @@ static int create_filter(struct ftrace_event_call *call,
return err;
}
+int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp)
+{
+ return create_filter(call, filter_str, set_str, filterp);
+}
+
/**
* create_system_filter - create a filter for an event_subsystem
* @system: event_subsystem to create a filter for
@@ -1816,6 +1960,7 @@ static int create_filter(struct ftrace_event_call *call,
* and always remembers @filter_str.
*/
static int create_system_filter(struct event_subsystem *system,
+ struct trace_array *tr,
char *filter_str, struct event_filter **filterp)
{
struct event_filter *filter = NULL;
@@ -1824,7 +1969,7 @@ static int create_system_filter(struct event_subsystem *system,
err = create_filter_start(filter_str, true, &ps, &filter);
if (!err) {
- err = replace_system_preds(system, ps, filter_str);
+ err = replace_system_preds(system, tr, ps, filter_str);
if (!err) {
/* System filters just show a default message */
kfree(filter->filter_string);
@@ -1840,20 +1985,25 @@ static int create_system_filter(struct event_subsystem *system,
}
/* caller must hold event_mutex */
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+int apply_event_filter(struct ftrace_event_file *file, char *filter_string)
{
+ struct ftrace_event_call *call = file->event_call;
struct event_filter *filter;
int err;
if (!strcmp(strstrip(filter_string), "0")) {
- filter_disable(call);
- filter = call->filter;
+ filter_disable(file);
+ filter = event_filter(file);
+
if (!filter)
return 0;
- RCU_INIT_POINTER(call->filter, NULL);
+
+ event_clear_filter(file);
+
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
+
return 0;
}
@@ -1866,14 +2016,15 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
* string
*/
if (filter) {
- struct event_filter *tmp = call->filter;
+ struct event_filter *tmp;
+ tmp = event_filter(file);
if (!err)
- call->flags |= TRACE_EVENT_FL_FILTERED;
+ event_set_filtered_flag(file);
else
- filter_disable(call);
+ filter_disable(file);
- rcu_assign_pointer(call->filter, filter);
+ event_set_filter(file, filter);
if (tmp) {
/* Make sure the call is done with the filter */
@@ -1889,6 +2040,7 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
char *filter_string)
{
struct event_subsystem *system = dir->subsystem;
+ struct trace_array *tr = dir->tr;
struct event_filter *filter;
int err = 0;
@@ -1901,18 +2053,18 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
}
if (!strcmp(strstrip(filter_string), "0")) {
- filter_free_subsystem_preds(system);
+ filter_free_subsystem_preds(system, tr);
remove_filter_string(system->filter);
filter = system->filter;
system->filter = NULL;
/* Ensure all filters are no longer used */
synchronize_sched();
- filter_free_subsystem_filters(system);
+ filter_free_subsystem_filters(system, tr);
__free_filter(filter);
goto out_unlock;
}
- err = create_system_filter(system, filter_string, &filter);
+ err = create_system_filter(system, tr, filter_string, &filter);
if (filter) {
/*
* No event actually uses the system filter
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
new file mode 100644
index 000000000000..8efbb69b04f0
--- /dev/null
+++ b/kernel/trace/trace_events_trigger.c
@@ -0,0 +1,1437 @@
+/*
+ * trace_events_trigger - trace event triggers
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "trace.h"
+
+static LIST_HEAD(trigger_commands);
+static DEFINE_MUTEX(trigger_cmd_mutex);
+
+static void
+trigger_data_free(struct event_trigger_data *data)
+{
+ if (data->cmd_ops->set_filter)
+ data->cmd_ops->set_filter(NULL, data, NULL);
+
+ synchronize_sched(); /* make sure current triggers exit before free */
+ kfree(data);
+}
+
+/**
+ * event_triggers_call - Call triggers associated with a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @rec: The trace entry for the event, NULL for unconditional invocation
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command. If rec is
+ * non-NULL, it means that the trigger requires further processing and
+ * shouldn't be unconditionally invoked. If rec is non-NULL and the
+ * trigger has a filter associated with it, rec will checked against
+ * the filter and if the record matches the trigger will be invoked.
+ * If the trigger is a 'post_trigger', meaning it shouldn't be invoked
+ * in any case until the current event is written, the trigger
+ * function isn't invoked but the bit associated with the deferred
+ * trigger is set in the return value.
+ *
+ * Returns an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ *
+ * Return: an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ */
+enum event_trigger_type
+event_triggers_call(struct ftrace_event_file *file, void *rec)
+{
+ struct event_trigger_data *data;
+ enum event_trigger_type tt = ETT_NONE;
+ struct event_filter *filter;
+
+ if (list_empty(&file->triggers))
+ return tt;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (!rec) {
+ data->ops->func(data);
+ continue;
+ }
+ filter = rcu_dereference(data->filter);
+ if (filter && !filter_match_preds(filter, rec))
+ continue;
+ if (data->cmd_ops->post_trigger) {
+ tt |= data->cmd_ops->trigger_type;
+ continue;
+ }
+ data->ops->func(data);
+ }
+ return tt;
+}
+EXPORT_SYMBOL_GPL(event_triggers_call);
+
+/**
+ * event_triggers_post_call - Call 'post_triggers' for a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command, if the
+ * corresponding bit is set in the tt enum passed into this function.
+ * See @event_triggers_call for details on how those bits are set.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ */
+void
+event_triggers_post_call(struct ftrace_event_file *file,
+ enum event_trigger_type tt)
+{
+ struct event_trigger_data *data;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type & tt)
+ data->ops->func(data);
+ }
+}
+EXPORT_SYMBOL_GPL(event_triggers_post_call);
+
+#define SHOW_AVAILABLE_TRIGGERS (void *)(1UL)
+
+static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
+{
+ struct ftrace_event_file *event_file = event_file_data(m->private);
+
+ if (t == SHOW_AVAILABLE_TRIGGERS)
+ return NULL;
+
+ return seq_list_next(t, &event_file->triggers, pos);
+}
+
+static void *trigger_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_event_file *event_file;
+
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(m->private);
+ if (unlikely(!event_file))
+ return ERR_PTR(-ENODEV);
+
+ if (list_empty(&event_file->triggers))
+ return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL;
+
+ return seq_list_start(&event_file->triggers, *pos);
+}
+
+static void trigger_stop(struct seq_file *m, void *t)
+{
+ mutex_unlock(&event_mutex);
+}
+
+static int trigger_show(struct seq_file *m, void *v)
+{
+ struct event_trigger_data *data;
+ struct event_command *p;
+
+ if (v == SHOW_AVAILABLE_TRIGGERS) {
+ seq_puts(m, "# Available triggers:\n");
+ seq_putc(m, '#');
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry_reverse(p, &trigger_commands, list)
+ seq_printf(m, " %s", p->name);
+ seq_putc(m, '\n');
+ mutex_unlock(&trigger_cmd_mutex);
+ return 0;
+ }
+
+ data = list_entry(v, struct event_trigger_data, list);
+ data->ops->print(m, data->ops, data);
+
+ return 0;
+}
+
+static const struct seq_operations event_triggers_seq_ops = {
+ .start = trigger_start,
+ .next = trigger_next,
+ .stop = trigger_stop,
+ .show = trigger_show,
+};
+
+static int event_trigger_regex_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ mutex_lock(&event_mutex);
+
+ if (unlikely(!event_file_data(file))) {
+ mutex_unlock(&event_mutex);
+ return -ENODEV;
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, &event_triggers_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = file;
+ }
+ }
+
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static int trigger_process_regex(struct ftrace_event_file *file, char *buff)
+{
+ char *command, *next = buff;
+ struct event_command *p;
+ int ret = -EINVAL;
+
+ command = strsep(&next, ": \t");
+ command = (command[0] != '!') ? command : command + 1;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(p->name, command) == 0) {
+ ret = p->func(p, file, buff, command, next);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+static ssize_t event_trigger_regex_write(struct file *file,
+ const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct ftrace_event_file *event_file;
+ ssize_t ret;
+ char *buf;
+
+ if (!cnt)
+ return 0;
+
+ if (cnt >= PAGE_SIZE)
+ return -EINVAL;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long)buf);
+ return -EFAULT;
+ }
+ buf[cnt] = '\0';
+ strim(buf);
+
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(file);
+ if (unlikely(!event_file)) {
+ mutex_unlock(&event_mutex);
+ free_page((unsigned long)buf);
+ return -ENODEV;
+ }
+ ret = trigger_process_regex(event_file, buf);
+ mutex_unlock(&event_mutex);
+
+ free_page((unsigned long)buf);
+ if (ret < 0)
+ goto out;
+
+ *ppos += cnt;
+ ret = cnt;
+ out:
+ return ret;
+}
+
+static int event_trigger_regex_release(struct inode *inode, struct file *file)
+{
+ mutex_lock(&event_mutex);
+
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+
+static ssize_t
+event_trigger_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return event_trigger_regex_write(filp, ubuf, cnt, ppos);
+}
+
+static int
+event_trigger_open(struct inode *inode, struct file *filp)
+{
+ return event_trigger_regex_open(inode, filp);
+}
+
+static int
+event_trigger_release(struct inode *inode, struct file *file)
+{
+ return event_trigger_regex_release(inode, file);
+}
+
+const struct file_operations event_trigger_fops = {
+ .open = event_trigger_open,
+ .read = seq_read,
+ .write = event_trigger_write,
+ .llseek = tracing_lseek,
+ .release = event_trigger_release,
+};
+
+/*
+ * Currently we only register event commands from __init, so mark this
+ * __init too.
+ */
+static __init int register_event_command(struct event_command *cmd)
+{
+ struct event_command *p;
+ int ret = 0;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ }
+ list_add(&cmd->list, &trigger_commands);
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/*
+ * Currently we only unregister event commands from __init, so mark
+ * this __init too.
+ */
+static __init int unregister_event_command(struct event_command *cmd)
+{
+ struct event_command *p, *n;
+ int ret = -ENODEV;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry_safe(p, n, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = 0;
+ list_del_init(&p->list);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/**
+ * event_trigger_print - Generic event_trigger_ops @print implementation
+ * @name: The name of the event trigger
+ * @m: The seq_file being printed to
+ * @data: Trigger-specific data
+ * @filter_str: filter_str to print, if present
+ *
+ * Common implementation for event triggers to print themselves.
+ *
+ * Usually wrapped by a function that simply sets the @name of the
+ * trigger command and then invokes this.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_print(const char *name, struct seq_file *m,
+ void *data, char *filter_str)
+{
+ long count = (long)data;
+
+ seq_printf(m, "%s", name);
+
+ if (count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", count);
+
+ if (filter_str)
+ seq_printf(m, " if %s\n", filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+/**
+ * event_trigger_init - Generic event_trigger_ops @init implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger initialization.
+ *
+ * Usually used directly as the @init method in event trigger
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ data->ref++;
+ return 0;
+}
+
+/**
+ * event_trigger_free - Generic event_trigger_ops @free implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger de-initialization.
+ *
+ * Usually used directly as the @free method in event trigger
+ * implementations.
+ */
+static void
+event_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref)
+ trigger_data_free(data);
+}
+
+static int trace_event_trigger_enable_disable(struct ftrace_event_file *file,
+ int trigger_enable)
+{
+ int ret = 0;
+
+ if (trigger_enable) {
+ if (atomic_inc_return(&file->tm_ref) > 1)
+ return ret;
+ set_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 1, 1);
+ } else {
+ if (atomic_dec_return(&file->tm_ref) > 0)
+ return ret;
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 0, 1);
+ }
+
+ return ret;
+}
+
+/**
+ * clear_event_triggers - Clear all triggers associated with a trace array
+ * @tr: The trace array to clear
+ *
+ * For each trigger, the triggering event has its tm_ref decremented
+ * via trace_event_trigger_enable_disable(), and any associated event
+ * (in the case of enable/disable_event triggers) will have its sm_ref
+ * decremented via free()->trace_event_enable_disable(). That
+ * combination effectively reverses the soft-mode/trigger state added
+ * by trigger registration.
+ *
+ * Must be called with event_mutex held.
+ */
+void
+clear_event_triggers(struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
+
+ list_for_each_entry(file, &tr->events, list) {
+ struct event_trigger_data *data;
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ trace_event_trigger_enable_disable(file, 0);
+ if (data->ops->free)
+ data->ops->free(data->ops, data);
+ }
+ }
+}
+
+/**
+ * update_cond_flag - Set or reset the TRIGGER_COND bit
+ * @file: The ftrace_event_file associated with the event
+ *
+ * If an event has triggers and any of those triggers has a filter or
+ * a post_trigger, trigger invocation needs to be deferred until after
+ * the current event has logged its data, and the event should have
+ * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
+ * cleared.
+ */
+static void update_cond_flag(struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool set_cond = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->filter || data->cmd_ops->post_trigger) {
+ set_cond = true;
+ break;
+ }
+ }
+
+ if (set_cond)
+ set_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+ else
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+}
+
+/**
+ * register_trigger - Generic event_command @reg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data to associate with the trigger
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger registration.
+ *
+ * Usually used directly as the @reg method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int register_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+ update_cond_flag(file);
+out:
+ return ret;
+}
+
+/**
+ * unregister_trigger - Generic event_command @unreg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @test: Trigger-specific data used to find the trigger to remove
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger unregistration.
+ *
+ * Usually used directly as the @unreg method in event command
+ * implementations.
+ */
+static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ update_cond_flag(file);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+/**
+ * event_trigger_callback - Generic event_command @func implementation
+ * @cmd_ops: The command ops, used for trigger registration
+ * @file: The ftrace_event_file associated with the event
+ * @glob: The raw string used to register the trigger
+ * @cmd: The cmd portion of the string used to register the trigger
+ * @param: The params portion of the string used to register the trigger
+ *
+ * Common implementation for event command parsing and trigger
+ * instantiation.
+ *
+ * Usually used directly as the @func method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_callback(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ char *trigger = NULL;
+ char *number;
+ int ret;
+
+ /* separate the trigger from the filter (t:n [if filter]) */
+ if (param && isdigit(param[0]))
+ trigger = strsep(&param, " \t");
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_free;
+ } else if (ret < 0)
+ goto out_free;
+ ret = 0;
+ out:
+ return ret;
+
+ out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
+ kfree(trigger_data);
+ goto out;
+}
+
+/**
+ * set_trigger_filter - Generic event_command @set_filter implementation
+ * @filter_str: The filter string for the trigger, NULL to remove filter
+ * @trigger_data: Trigger-specific data
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event command filter parsing and filter
+ * instantiation.
+ *
+ * Usually used directly as the @set_filter method in event command
+ * implementations.
+ *
+ * Also used to remove a filter (if filter_str = NULL).
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int set_trigger_filter(char *filter_str,
+ struct event_trigger_data *trigger_data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data = trigger_data;
+ struct event_filter *filter = NULL, *tmp;
+ int ret = -EINVAL;
+ char *s;
+
+ if (!filter_str) /* clear the current filter */
+ goto assign;
+
+ s = strsep(&filter_str, " \t");
+
+ if (!strlen(s) || strcmp(s, "if") != 0)
+ goto out;
+
+ if (!filter_str)
+ goto out;
+
+ /* The filter is for the 'trigger' event, not the triggered event */
+ ret = create_event_filter(file->event_call, filter_str, false, &filter);
+ if (ret)
+ goto out;
+ assign:
+ tmp = rcu_access_pointer(data->filter);
+
+ rcu_assign_pointer(data->filter, filter);
+
+ if (tmp) {
+ /* Make sure the call is done with the filter */
+ synchronize_sched();
+ free_event_filter(tmp);
+ }
+
+ kfree(data->filter_str);
+ data->filter_str = NULL;
+
+ if (filter_str) {
+ data->filter_str = kstrdup(filter_str, GFP_KERNEL);
+ if (!data->filter_str) {
+ free_event_filter(rcu_access_pointer(data->filter));
+ data->filter = NULL;
+ ret = -ENOMEM;
+ }
+ }
+ out:
+ return ret;
+}
+
+static void
+traceon_trigger(struct event_trigger_data *data)
+{
+ if (tracing_is_on())
+ return;
+
+ tracing_on();
+}
+
+static void
+traceon_count_trigger(struct event_trigger_data *data)
+{
+ if (tracing_is_on())
+ return;
+
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ tracing_on();
+}
+
+static void
+traceoff_trigger(struct event_trigger_data *data)
+{
+ if (!tracing_is_on())
+ return;
+
+ tracing_off();
+}
+
+static void
+traceoff_count_trigger(struct event_trigger_data *data)
+{
+ if (!tracing_is_on())
+ return;
+
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ tracing_off();
+}
+
+static int
+traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceon", m, (void *)data->count,
+ data->filter_str);
+}
+
+static int
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceoff", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops traceon_trigger_ops = {
+ .func = traceon_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceon_count_trigger_ops = {
+ .func = traceon_count_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_trigger_ops = {
+ .func = traceoff_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_count_trigger_ops = {
+ .func = traceoff_count_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+onoff_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = param ? &traceon_count_trigger_ops :
+ &traceon_trigger_ops;
+ else
+ ops = param ? &traceoff_count_trigger_ops :
+ &traceoff_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_traceon_cmd = {
+ .name = "traceon",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static struct event_command trigger_traceoff_cmd = {
+ .name = "traceoff",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+static void
+snapshot_trigger(struct event_trigger_data *data)
+{
+ tracing_snapshot();
+}
+
+static void
+snapshot_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ snapshot_trigger(data);
+}
+
+static int
+register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ int ret = register_trigger(glob, ops, data, file);
+
+ if (ret > 0 && tracing_alloc_snapshot() != 0) {
+ unregister_trigger(glob, ops, data, file);
+ ret = 0;
+ }
+
+ return ret;
+}
+
+static int
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("snapshot", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops snapshot_trigger_ops = {
+ .func = snapshot_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops snapshot_count_trigger_ops = {
+ .func = snapshot_count_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+snapshot_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &snapshot_count_trigger_ops : &snapshot_trigger_ops;
+}
+
+static struct event_command trigger_snapshot_cmd = {
+ .name = "snapshot",
+ .trigger_type = ETT_SNAPSHOT,
+ .func = event_trigger_callback,
+ .reg = register_snapshot_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = snapshot_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init int register_trigger_snapshot_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_snapshot_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_snapshot_cmd(void) { return 0; }
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+#ifdef CONFIG_STACKTRACE
+/*
+ * Skip 3:
+ * stacktrace_trigger()
+ * event_triggers_post_call()
+ * ftrace_raw_event_xxx()
+ */
+#define STACK_SKIP 3
+
+static void
+stacktrace_trigger(struct event_trigger_data *data)
+{
+ trace_dump_stack(STACK_SKIP);
+}
+
+static void
+stacktrace_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ stacktrace_trigger(data);
+}
+
+static int
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("stacktrace", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops stacktrace_trigger_ops = {
+ .func = stacktrace_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops stacktrace_count_trigger_ops = {
+ .func = stacktrace_count_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+stacktrace_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &stacktrace_count_trigger_ops : &stacktrace_trigger_ops;
+}
+
+static struct event_command trigger_stacktrace_cmd = {
+ .name = "stacktrace",
+ .trigger_type = ETT_STACKTRACE,
+ .post_trigger = true,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = stacktrace_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init int register_trigger_stacktrace_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_stacktrace_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_stacktrace_cmd(void) { return 0; }
+#endif /* CONFIG_STACKTRACE */
+
+static __init void unregister_trigger_traceon_traceoff_cmds(void)
+{
+ unregister_event_command(&trigger_traceon_cmd);
+ unregister_event_command(&trigger_traceoff_cmd);
+}
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct enable_trigger_data {
+ struct ftrace_event_file *file;
+ bool enable;
+};
+
+static void
+event_enable_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (enable_data->enable)
+ clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+ else
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+}
+
+static void
+event_enable_count_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (!data->count)
+ return;
+
+ /* Skip if the event is in a state we want to switch to */
+ if (enable_data->enable == !(enable_data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ event_enable_trigger(data);
+}
+
+static int
+event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ seq_printf(m, "%s:%s:%s",
+ enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+ enable_data->file->event_call->class->system,
+ enable_data->file->event_call->name);
+
+ if (data->count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", data->count);
+
+ if (data->filter_str)
+ seq_printf(m, " if %s\n", data->filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+static void
+event_enable_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref) {
+ /* Remove the SOFT_MODE flag */
+ trace_event_enable_disable(enable_data->file, 0, 1);
+ module_put(enable_data->file->event_call->mod);
+ trigger_data_free(data);
+ kfree(enable_data);
+ }
+}
+
+static struct event_trigger_ops event_enable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_enable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static int
+event_enable_trigger_func(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct ftrace_event_file *event_enable_file;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ struct trace_array *tr = file->tr;
+ const char *system;
+ const char *event;
+ char *trigger;
+ char *number;
+ bool enable;
+ int ret;
+
+ if (!param)
+ return -EINVAL;
+
+ /* separate the trigger from the filter (s:e:n [if filter]) */
+ trigger = strsep(&param, " \t");
+ if (!trigger)
+ return -EINVAL;
+
+ system = strsep(&trigger, ":");
+ if (!trigger)
+ return -EINVAL;
+
+ event = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ event_enable_file = find_event_file(tr, system, event);
+ if (!event_enable_file)
+ goto out;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
+ if (!enable_data) {
+ kfree(trigger_data);
+ goto out;
+ }
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+ RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+ enable_data->enable = enable;
+ enable_data->file = event_enable_file;
+ trigger_data->private_data = enable_data;
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ kfree(enable_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ /* Don't let event modules unload while probe registered */
+ ret = try_module_get(event_enable_file->event_call->mod);
+ if (!ret) {
+ ret = -EBUSY;
+ goto out_free;
+ }
+
+ ret = trace_event_enable_disable(event_enable_file, 1, 1);
+ if (ret < 0)
+ goto out_put;
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_disable;
+ } else if (ret < 0)
+ goto out_disable;
+ /* Just return zero, not the number of enabled functions */
+ ret = 0;
+ out:
+ return ret;
+
+ out_disable:
+ trace_event_enable_disable(event_enable_file, 0, 1);
+ out_put:
+ module_put(event_enable_file->event_call->mod);
+ out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
+ kfree(trigger_data);
+ kfree(enable_data);
+ goto out;
+}
+
+static int event_enable_register_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+ struct enable_trigger_data *test_enable_data;
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ test_enable_data = test->private_data;
+ if (test_enable_data &&
+ (test_enable_data->file == enable_data->file)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+ update_cond_flag(file);
+out:
+ return ret;
+}
+
+static void event_enable_unregister_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *test_enable_data = test->private_data;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ enable_data = data->private_data;
+ if (enable_data &&
+ (enable_data->file == test_enable_data->file)) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ update_cond_flag(file);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+static struct event_trigger_ops *
+event_enable_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+ bool enable;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ if (enable)
+ ops = param ? &event_enable_count_trigger_ops :
+ &event_enable_trigger_ops;
+ else
+ ops = param ? &event_disable_count_trigger_ops :
+ &event_disable_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_enable_cmd = {
+ .name = ENABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static struct event_command trigger_disable_cmd = {
+ .name = DISABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init void unregister_trigger_enable_disable_cmds(void)
+{
+ unregister_event_command(&trigger_enable_cmd);
+ unregister_event_command(&trigger_disable_cmd);
+}
+
+static __init int register_trigger_enable_disable_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_enable_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_disable_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_enable_disable_cmds();
+
+ return ret;
+}
+
+static __init int register_trigger_traceon_traceoff_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_traceon_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_traceoff_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_traceon_traceoff_cmds();
+
+ return ret;
+}
+
+__init int register_trigger_cmds(void)
+{
+ register_trigger_traceon_traceoff_cmds();
+ register_trigger_snapshot_cmd();
+ register_trigger_stacktrace_cmd();
+ register_trigger_enable_disable_cmds();
+
+ return 0;
+}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d21a74670088..7c3e3e72e2b6 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -180,7 +180,7 @@ struct ftrace_event_call __used event_##call = { \
.event.type = etype, \
.class = &event_class_ftrace_##call, \
.print_fmt = print, \
- .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \
+ .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \
}; \
struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b5c09242683d..0b99120d395c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -82,9 +82,9 @@ static struct trace_array *graph_array;
* to fill in space into DURATION column.
*/
enum {
- DURATION_FILL_FULL = -1,
- DURATION_FILL_START = -2,
- DURATION_FILL_END = -3,
+ FLAGS_FILL_FULL = 1 << TRACE_GRAPH_PRINT_FILL_SHIFT,
+ FLAGS_FILL_START = 2 << TRACE_GRAPH_PRINT_FILL_SHIFT,
+ FLAGS_FILL_END = 3 << TRACE_GRAPH_PRINT_FILL_SHIFT,
};
static enum print_line_t
@@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
return -EBUSY;
}
+ /*
+ * The curr_ret_stack is an index to ftrace return stack of
+ * current task. Its value should be in [0, FTRACE_RETFUNC_
+ * DEPTH) when the function graph tracer is used. To support
+ * filtering out specific functions, it makes the index
+ * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
+ * so when it sees a negative index the ftrace will ignore
+ * the record. And the index gets recovered when returning
+ * from the filtered function by adding the FTRACE_NOTRACE_
+ * DEPTH and then it'll continue to record functions normally.
+ *
+ * The curr_ret_stack is initialized to -1 and get increased
+ * in this function. So it can be less than -1 only if it was
+ * filtered out via ftrace_graph_notrace_addr() which can be
+ * set from set_graph_notrace file in debugfs by user.
+ */
+ if (current->curr_ret_stack < -1)
+ return -EBUSY;
+
calltime = trace_clock_local();
index = ++current->curr_ret_stack;
+ if (ftrace_graph_notrace_addr(func))
+ current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
barrier();
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
current->ret_stack[index].subtime = 0;
current->ret_stack[index].fp = frame_pointer;
- *depth = index;
+ *depth = current->curr_ret_stack;
return 0;
}
@@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
index = current->curr_ret_stack;
- if (unlikely(index < 0)) {
+ /*
+ * A negative index here means that it's just returned from a
+ * notrace'd function. Recover index to get an original
+ * return address. See ftrace_push_return_trace().
+ *
+ * TODO: Need to check whether the stack gets corrupted.
+ */
+ if (index < 0)
+ index += FTRACE_NOTRACE_DEPTH;
+
+ if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
ftrace_graph_stop();
WARN_ON(1);
/* Might as well panic, otherwise we have no where to go */
@@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
trace.rettime = trace_clock_local();
barrier();
current->curr_ret_stack--;
+ /*
+ * The curr_ret_stack can be less than -1 only if it was
+ * filtered out and it's about to return from the function.
+ * Recover the index and continue to trace normal functions.
+ */
+ if (current->curr_ret_stack < -1) {
+ current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
+ return ret;
+ }
/*
* The trace should run after decrementing the ret counter
@@ -230,7 +270,7 @@ int __trace_graph_entry(struct trace_array *tr,
return 0;
entry = ring_buffer_event_data(event);
entry->graph_ent = *trace;
- if (!filter_current_check_discard(buffer, call, entry, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
return 1;
@@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
/* trace it when it is-nested-in or is a function enabled. */
if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
- ftrace_graph_ignore_irqs()) ||
+ ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
(max_depth && trace->depth >= max_depth))
return 0;
+ /*
+ * Do not trace a function if it's filtered by set_graph_notrace.
+ * Make the index of ret stack negative to indicate that it should
+ * ignore further functions. But it needs its own ret stack entry
+ * to recover the original index in order to continue tracing after
+ * returning from the function.
+ */
+ if (ftrace_graph_notrace_addr(trace->func))
+ return 1;
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -335,7 +385,7 @@ void __trace_graph_return(struct trace_array *tr,
return;
entry = ring_buffer_event_data(event);
entry->ret = *trace;
- if (!filter_current_check_discard(buffer, call, entry, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
__buffer_unlock_commit(buffer, event);
}
@@ -652,7 +702,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
}
/* No overhead */
- ret = print_graph_duration(DURATION_FILL_START, s, flags);
+ ret = print_graph_duration(0, s, flags | FLAGS_FILL_START);
if (ret != TRACE_TYPE_HANDLED)
return ret;
@@ -664,7 +714,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
- ret = print_graph_duration(DURATION_FILL_END, s, flags);
+ ret = print_graph_duration(0, s, flags | FLAGS_FILL_END);
if (ret != TRACE_TYPE_HANDLED)
return ret;
@@ -729,14 +779,14 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s,
return TRACE_TYPE_HANDLED;
/* No real adata, just filling the column with spaces */
- switch (duration) {
- case DURATION_FILL_FULL:
+ switch (flags & TRACE_GRAPH_PRINT_FILL_MASK) {
+ case FLAGS_FILL_FULL:
ret = trace_seq_puts(s, " | ");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
- case DURATION_FILL_START:
+ case FLAGS_FILL_START:
ret = trace_seq_puts(s, " ");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
- case DURATION_FILL_END:
+ case FLAGS_FILL_END:
ret = trace_seq_puts(s, " |");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
}
@@ -852,7 +902,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
}
/* No time */
- ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+ ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
if (ret != TRACE_TYPE_HANDLED)
return ret;
@@ -1172,7 +1222,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
return TRACE_TYPE_PARTIAL_LINE;
/* No time */
- ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+ ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
if (ret != TRACE_TYPE_HANDLED)
return ret;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 243f6834d026..bdbae450c13e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -27,18 +27,12 @@
/**
* Kprobe event core functions
*/
-struct trace_probe {
+struct trace_kprobe {
struct list_head list;
struct kretprobe rp; /* Use rp.kp for kprobe use */
unsigned long nhit;
- unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
- struct ftrace_event_class class;
- struct ftrace_event_call call;
- struct list_head files;
- ssize_t size; /* trace entry size */
- unsigned int nr_args;
- struct probe_arg args[];
+ struct trace_probe tp;
};
struct event_file_link {
@@ -46,56 +40,46 @@ struct event_file_link {
struct list_head list;
};
-#define SIZEOF_TRACE_PROBE(n) \
- (offsetof(struct trace_probe, args) + \
+#define SIZEOF_TRACE_KPROBE(n) \
+ (offsetof(struct trace_kprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
-static __kprobes bool trace_probe_is_return(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_return(struct trace_kprobe *tk)
{
- return tp->rp.handler != NULL;
+ return tk->rp.handler != NULL;
}
-static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
+static __kprobes const char *trace_kprobe_symbol(struct trace_kprobe *tk)
{
- return tp->symbol ? tp->symbol : "unknown";
+ return tk->symbol ? tk->symbol : "unknown";
}
-static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+static __kprobes unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
{
- return tp->rp.kp.offset;
+ return tk->rp.kp.offset;
}
-static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_has_gone(struct trace_kprobe *tk)
{
- return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+ return !!(kprobe_gone(&tk->rp.kp));
}
-static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
-{
- return !!(tp->flags & TP_FLAG_REGISTERED);
-}
-
-static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
-{
- return !!(kprobe_gone(&tp->rp.kp));
-}
-
-static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
- struct module *mod)
+static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk,
+ struct module *mod)
{
int len = strlen(mod->name);
- const char *name = trace_probe_symbol(tp);
+ const char *name = trace_kprobe_symbol(tk);
return strncmp(mod->name, name, len) == 0 && name[len] == ':';
}
-static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
{
- return !!strchr(trace_probe_symbol(tp), ':');
+ return !!strchr(trace_kprobe_symbol(tk), ':');
}
-static int register_probe_event(struct trace_probe *tp);
-static int unregister_probe_event(struct trace_probe *tp);
+static int register_kprobe_event(struct trace_kprobe *tk);
+static int unregister_kprobe_event(struct trace_kprobe *tk);
static DEFINE_MUTEX(probe_lock);
static LIST_HEAD(probe_list);
@@ -104,45 +88,224 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
struct pt_regs *regs);
+/* Memory fetching by symbol */
+struct symbol_cache {
+ char *symbol;
+ long offset;
+ unsigned long addr;
+};
+
+unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+ sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+
+ if (sc->addr)
+ sc->addr += sc->offset;
+
+ return sc->addr;
+}
+
+void free_symbol_cache(struct symbol_cache *sc)
+{
+ kfree(sc->symbol);
+ kfree(sc);
+}
+
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+ struct symbol_cache *sc;
+
+ if (!sym || strlen(sym) == 0)
+ return NULL;
+
+ sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+ if (!sc)
+ return NULL;
+
+ sc->symbol = kstrdup(sym, GFP_KERNEL);
+ if (!sc->symbol) {
+ kfree(sc);
+ return NULL;
+ }
+ sc->offset = offset;
+ update_symbol_cache(sc);
+
+ return sc;
+}
+
+/*
+ * Kprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
+ (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ if (probe_kernel_address(addr, retval)) \
+ *(type *)dest = 0; \
+ else \
+ *(type *)dest = retval; \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ long ret;
+ int maxlen = get_rloc_len(*(u32 *)dest);
+ u8 *dst = get_rloc_data(dest);
+ u8 *src = addr;
+ mm_segment_t old_fs = get_fs();
+
+ if (!maxlen)
+ return;
+
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do
+ ret = __copy_from_user_inatomic(dst++, src++, 1);
+ while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+
+ dst[-1] = '\0';
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) { /* Failed to fetch string */
+ ((u8 *)get_rloc_data(dest))[0] = '\0';
+ *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+ } else {
+ *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+ get_rloc_offs(*(u32 *)dest));
+ }
+}
+
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ mm_segment_t old_fs;
+ int ret, len = 0;
+ u8 c;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do {
+ ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) /* Failed to check the length */
+ *(u32 *)dest = 0;
+ else
+ *(u32 *)dest = len;
+}
+
+#define DEFINE_FETCH_symbol(type) \
+__kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, \
+ void *data, void *dest) \
+{ \
+ struct symbol_cache *sc = data; \
+ if (sc->addr) \
+ fetch_memory_##type(regs, (void *)sc->addr, dest); \
+ else \
+ *(type *)dest = 0; \
+}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
+
+/* kprobes don't support file_offset fetch methods */
+#define fetch_file_offset_u8 NULL
+#define fetch_file_offset_u16 NULL
+#define fetch_file_offset_u32 NULL
+#define fetch_file_offset_u64 NULL
+#define fetch_file_offset_string NULL
+#define fetch_file_offset_string_size NULL
+
+/* Fetch type information table */
+const struct fetch_type kprobes_fetch_type_table[] = {
+ /* Special types */
+ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+ sizeof(u32), 1, "__data_loc char[]"),
+ [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+ string_size, sizeof(u32), 0, "u32"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+ ASSIGN_FETCH_TYPE_END
+};
+
/*
* Allocate new trace_probe and initialize it (including kprobes).
*/
-static struct trace_probe *alloc_trace_probe(const char *group,
+static struct trace_kprobe *alloc_trace_kprobe(const char *group,
const char *event,
void *addr,
const char *symbol,
unsigned long offs,
int nargs, bool is_return)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret = -ENOMEM;
- tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
- if (!tp)
+ tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL);
+ if (!tk)
return ERR_PTR(ret);
if (symbol) {
- tp->symbol = kstrdup(symbol, GFP_KERNEL);
- if (!tp->symbol)
+ tk->symbol = kstrdup(symbol, GFP_KERNEL);
+ if (!tk->symbol)
goto error;
- tp->rp.kp.symbol_name = tp->symbol;
- tp->rp.kp.offset = offs;
+ tk->rp.kp.symbol_name = tk->symbol;
+ tk->rp.kp.offset = offs;
} else
- tp->rp.kp.addr = addr;
+ tk->rp.kp.addr = addr;
if (is_return)
- tp->rp.handler = kretprobe_dispatcher;
+ tk->rp.handler = kretprobe_dispatcher;
else
- tp->rp.kp.pre_handler = kprobe_dispatcher;
+ tk->rp.kp.pre_handler = kprobe_dispatcher;
if (!event || !is_good_name(event)) {
ret = -EINVAL;
goto error;
}
- tp->call.class = &tp->class;
- tp->call.name = kstrdup(event, GFP_KERNEL);
- if (!tp->call.name)
+ tk->tp.call.class = &tk->tp.class;
+ tk->tp.call.name = kstrdup(event, GFP_KERNEL);
+ if (!tk->tp.call.name)
goto error;
if (!group || !is_good_name(group)) {
@@ -150,42 +313,42 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
- tp->class.system = kstrdup(group, GFP_KERNEL);
- if (!tp->class.system)
+ tk->tp.class.system = kstrdup(group, GFP_KERNEL);
+ if (!tk->tp.class.system)
goto error;
- INIT_LIST_HEAD(&tp->list);
- INIT_LIST_HEAD(&tp->files);
- return tp;
+ INIT_LIST_HEAD(&tk->list);
+ INIT_LIST_HEAD(&tk->tp.files);
+ return tk;
error:
- kfree(tp->call.name);
- kfree(tp->symbol);
- kfree(tp);
+ kfree(tk->tp.call.name);
+ kfree(tk->symbol);
+ kfree(tk);
return ERR_PTR(ret);
}
-static void free_trace_probe(struct trace_probe *tp)
+static void free_trace_kprobe(struct trace_kprobe *tk)
{
int i;
- for (i = 0; i < tp->nr_args; i++)
- traceprobe_free_probe_arg(&tp->args[i]);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ traceprobe_free_probe_arg(&tk->tp.args[i]);
- kfree(tp->call.class->system);
- kfree(tp->call.name);
- kfree(tp->symbol);
- kfree(tp);
+ kfree(tk->tp.call.class->system);
+ kfree(tk->tp.call.name);
+ kfree(tk->symbol);
+ kfree(tk);
}
-static struct trace_probe *find_trace_probe(const char *event,
- const char *group)
+static struct trace_kprobe *find_trace_kprobe(const char *event,
+ const char *group)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
- list_for_each_entry(tp, &probe_list, list)
- if (strcmp(tp->call.name, event) == 0 &&
- strcmp(tp->call.class->system, group) == 0)
- return tp;
+ list_for_each_entry(tk, &probe_list, list)
+ if (strcmp(tk->tp.call.name, event) == 0 &&
+ strcmp(tk->tp.call.class->system, group) == 0)
+ return tk;
return NULL;
}
@@ -194,7 +357,7 @@ static struct trace_probe *find_trace_probe(const char *event,
* if the file is NULL, enable "perf" handler, or enable "trace" handler.
*/
static int
-enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
{
int ret = 0;
@@ -208,17 +371,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
}
link->file = file;
- list_add_tail_rcu(&link->list, &tp->files);
+ list_add_tail_rcu(&link->list, &tk->tp.files);
- tp->flags |= TP_FLAG_TRACE;
+ tk->tp.flags |= TP_FLAG_TRACE;
} else
- tp->flags |= TP_FLAG_PROFILE;
+ tk->tp.flags |= TP_FLAG_PROFILE;
- if (trace_probe_is_registered(tp) && !trace_probe_has_gone(tp)) {
- if (trace_probe_is_return(tp))
- ret = enable_kretprobe(&tp->rp);
+ if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
+ if (trace_kprobe_is_return(tk))
+ ret = enable_kretprobe(&tk->rp);
else
- ret = enable_kprobe(&tp->rp.kp);
+ ret = enable_kprobe(&tk->rp.kp);
}
out:
return ret;
@@ -241,14 +404,14 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
* if the file is NULL, disable "perf" handler, or disable "trace" handler.
*/
static int
-disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+disable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
{
struct event_file_link *link = NULL;
int wait = 0;
int ret = 0;
if (file) {
- link = find_event_file_link(tp, file);
+ link = find_event_file_link(&tk->tp, file);
if (!link) {
ret = -EINVAL;
goto out;
@@ -256,18 +419,18 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
list_del_rcu(&link->list);
wait = 1;
- if (!list_empty(&tp->files))
+ if (!list_empty(&tk->tp.files))
goto out;
- tp->flags &= ~TP_FLAG_TRACE;
+ tk->tp.flags &= ~TP_FLAG_TRACE;
} else
- tp->flags &= ~TP_FLAG_PROFILE;
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
- if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
- if (trace_probe_is_return(tp))
- disable_kretprobe(&tp->rp);
+ if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) {
+ if (trace_kprobe_is_return(tk))
+ disable_kretprobe(&tk->rp);
else
- disable_kprobe(&tp->rp.kp);
+ disable_kprobe(&tk->rp.kp);
wait = 1;
}
out:
@@ -288,40 +451,40 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
}
/* Internal register function - just handle k*probes and flags */
-static int __register_trace_probe(struct trace_probe *tp)
+static int __register_trace_kprobe(struct trace_kprobe *tk)
{
int i, ret;
- if (trace_probe_is_registered(tp))
+ if (trace_probe_is_registered(&tk->tp))
return -EINVAL;
- for (i = 0; i < tp->nr_args; i++)
- traceprobe_update_arg(&tp->args[i]);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ traceprobe_update_arg(&tk->tp.args[i]);
/* Set/clear disabled flag according to tp->flag */
- if (trace_probe_is_enabled(tp))
- tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+ if (trace_probe_is_enabled(&tk->tp))
+ tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
else
- tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+ tk->rp.kp.flags |= KPROBE_FLAG_DISABLED;
- if (trace_probe_is_return(tp))
- ret = register_kretprobe(&tp->rp);
+ if (trace_kprobe_is_return(tk))
+ ret = register_kretprobe(&tk->rp);
else
- ret = register_kprobe(&tp->rp.kp);
+ ret = register_kprobe(&tk->rp.kp);
if (ret == 0)
- tp->flags |= TP_FLAG_REGISTERED;
+ tk->tp.flags |= TP_FLAG_REGISTERED;
else {
pr_warning("Could not insert probe at %s+%lu: %d\n",
- trace_probe_symbol(tp), trace_probe_offset(tp), ret);
- if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+ trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
+ if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
pr_warning("This probe might be able to register after"
"target module is loaded. Continue.\n");
ret = 0;
} else if (ret == -EILSEQ) {
pr_warning("Probing address(0x%p) is not an "
"instruction boundary.\n",
- tp->rp.kp.addr);
+ tk->rp.kp.addr);
ret = -EINVAL;
}
}
@@ -330,67 +493,67 @@ static int __register_trace_probe(struct trace_probe *tp)
}
/* Internal unregister function - just handle k*probes and flags */
-static void __unregister_trace_probe(struct trace_probe *tp)
+static void __unregister_trace_kprobe(struct trace_kprobe *tk)
{
- if (trace_probe_is_registered(tp)) {
- if (trace_probe_is_return(tp))
- unregister_kretprobe(&tp->rp);
+ if (trace_probe_is_registered(&tk->tp)) {
+ if (trace_kprobe_is_return(tk))
+ unregister_kretprobe(&tk->rp);
else
- unregister_kprobe(&tp->rp.kp);
- tp->flags &= ~TP_FLAG_REGISTERED;
+ unregister_kprobe(&tk->rp.kp);
+ tk->tp.flags &= ~TP_FLAG_REGISTERED;
/* Cleanup kprobe for reuse */
- if (tp->rp.kp.symbol_name)
- tp->rp.kp.addr = NULL;
+ if (tk->rp.kp.symbol_name)
+ tk->rp.kp.addr = NULL;
}
}
/* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static int unregister_trace_probe(struct trace_probe *tp)
+static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
/* Enabled event can not be unregistered */
- if (trace_probe_is_enabled(tp))
+ if (trace_probe_is_enabled(&tk->tp))
return -EBUSY;
/* Will fail if probe is being used by ftrace or perf */
- if (unregister_probe_event(tp))
+ if (unregister_kprobe_event(tk))
return -EBUSY;
- __unregister_trace_probe(tp);
- list_del(&tp->list);
+ __unregister_trace_kprobe(tk);
+ list_del(&tk->list);
return 0;
}
/* Register a trace_probe and probe_event */
-static int register_trace_probe(struct trace_probe *tp)
+static int register_trace_kprobe(struct trace_kprobe *tk)
{
- struct trace_probe *old_tp;
+ struct trace_kprobe *old_tk;
int ret;
mutex_lock(&probe_lock);
/* Delete old (same name) event if exist */
- old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
- if (old_tp) {
- ret = unregister_trace_probe(old_tp);
+ old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system);
+ if (old_tk) {
+ ret = unregister_trace_kprobe(old_tk);
if (ret < 0)
goto end;
- free_trace_probe(old_tp);
+ free_trace_kprobe(old_tk);
}
/* Register new event */
- ret = register_probe_event(tp);
+ ret = register_kprobe_event(tk);
if (ret) {
pr_warning("Failed to register probe event(%d)\n", ret);
goto end;
}
/* Register k*probe */
- ret = __register_trace_probe(tp);
+ ret = __register_trace_kprobe(tk);
if (ret < 0)
- unregister_probe_event(tp);
+ unregister_kprobe_event(tk);
else
- list_add_tail(&tp->list, &probe_list);
+ list_add_tail(&tk->list, &probe_list);
end:
mutex_unlock(&probe_lock);
@@ -398,11 +561,11 @@ end:
}
/* Module notifier call back, checking event on the module */
-static int trace_probe_module_callback(struct notifier_block *nb,
+static int trace_kprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
{
struct module *mod = data;
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret;
if (val != MODULE_STATE_COMING)
@@ -410,15 +573,15 @@ static int trace_probe_module_callback(struct notifier_block *nb,
/* Update probes on coming module */
mutex_lock(&probe_lock);
- list_for_each_entry(tp, &probe_list, list) {
- if (trace_probe_within_module(tp, mod)) {
+ list_for_each_entry(tk, &probe_list, list) {
+ if (trace_kprobe_within_module(tk, mod)) {
/* Don't need to check busy - this should have gone. */
- __unregister_trace_probe(tp);
- ret = __register_trace_probe(tp);
+ __unregister_trace_kprobe(tk);
+ ret = __register_trace_kprobe(tk);
if (ret)
pr_warning("Failed to re-register probe %s on"
"%s: %d\n",
- tp->call.name, mod->name, ret);
+ tk->tp.call.name, mod->name, ret);
}
}
mutex_unlock(&probe_lock);
@@ -426,12 +589,12 @@ static int trace_probe_module_callback(struct notifier_block *nb,
return NOTIFY_DONE;
}
-static struct notifier_block trace_probe_module_nb = {
- .notifier_call = trace_probe_module_callback,
+static struct notifier_block trace_kprobe_module_nb = {
+ .notifier_call = trace_kprobe_module_callback,
.priority = 1 /* Invoked after kprobe module callback */
};
-static int create_trace_probe(int argc, char **argv)
+static int create_trace_kprobe(int argc, char **argv)
{
/*
* Argument syntax:
@@ -451,7 +614,7 @@ static int create_trace_probe(int argc, char **argv)
* Type of args:
* FETCHARG:TYPE : use TYPE instead of unsigned long.
*/
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int i, ret = 0;
bool is_return = false, is_delete = false;
char *symbol = NULL, *event = NULL, *group = NULL;
@@ -498,16 +661,16 @@ static int create_trace_probe(int argc, char **argv)
return -EINVAL;
}
mutex_lock(&probe_lock);
- tp = find_trace_probe(event, group);
- if (!tp) {
+ tk = find_trace_kprobe(event, group);
+ if (!tk) {
mutex_unlock(&probe_lock);
pr_info("Event %s/%s doesn't exist.\n", group, event);
return -ENOENT;
}
/* delete an event */
- ret = unregister_trace_probe(tp);
+ ret = unregister_trace_kprobe(tk);
if (ret == 0)
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
mutex_unlock(&probe_lock);
return ret;
}
@@ -554,47 +717,49 @@ static int create_trace_probe(int argc, char **argv)
is_return ? 'r' : 'p', addr);
event = buf;
}
- tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc,
is_return);
- if (IS_ERR(tp)) {
+ if (IS_ERR(tk)) {
pr_info("Failed to allocate trace_probe.(%d)\n",
- (int)PTR_ERR(tp));
- return PTR_ERR(tp);
+ (int)PTR_ERR(tk));
+ return PTR_ERR(tk);
}
/* parse arguments */
ret = 0;
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
/* Increment count for freeing args in error case */
- tp->nr_args++;
+ tk->tp.nr_args++;
/* Parse argument name */
arg = strchr(argv[i], '=');
if (arg) {
*arg++ = '\0';
- tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ parg->name = kstrdup(argv[i], GFP_KERNEL);
} else {
arg = argv[i];
/* If argument name is omitted, set "argN" */
snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
- tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+ parg->name = kstrdup(buf, GFP_KERNEL);
}
- if (!tp->args[i].name) {
+ if (!parg->name) {
pr_info("Failed to allocate argument[%d] name.\n", i);
ret = -ENOMEM;
goto error;
}
- if (!is_good_name(tp->args[i].name)) {
+ if (!is_good_name(parg->name)) {
pr_info("Invalid argument[%d] name: %s\n",
- i, tp->args[i].name);
+ i, parg->name);
ret = -EINVAL;
goto error;
}
- if (traceprobe_conflict_field_name(tp->args[i].name,
- tp->args, i)) {
+ if (traceprobe_conflict_field_name(parg->name,
+ tk->tp.args, i)) {
pr_info("Argument[%d] name '%s' conflicts with "
"another field.\n", i, argv[i]);
ret = -EINVAL;
@@ -602,7 +767,7 @@ static int create_trace_probe(int argc, char **argv)
}
/* Parse fetch argument */
- ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i],
+ ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
is_return, true);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
@@ -610,35 +775,35 @@ static int create_trace_probe(int argc, char **argv)
}
}
- ret = register_trace_probe(tp);
+ ret = register_trace_kprobe(tk);
if (ret)
goto error;
return 0;
error:
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
return ret;
}
-static int release_all_trace_probes(void)
+static int release_all_trace_kprobes(void)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret = 0;
mutex_lock(&probe_lock);
/* Ensure no probe is in use. */
- list_for_each_entry(tp, &probe_list, list)
- if (trace_probe_is_enabled(tp)) {
+ list_for_each_entry(tk, &probe_list, list)
+ if (trace_probe_is_enabled(&tk->tp)) {
ret = -EBUSY;
goto end;
}
/* TODO: Use batch unregistration */
while (!list_empty(&probe_list)) {
- tp = list_entry(probe_list.next, struct trace_probe, list);
- ret = unregister_trace_probe(tp);
+ tk = list_entry(probe_list.next, struct trace_kprobe, list);
+ ret = unregister_trace_kprobe(tk);
if (ret)
goto end;
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
}
end:
@@ -666,22 +831,22 @@ static void probes_seq_stop(struct seq_file *m, void *v)
static int probes_seq_show(struct seq_file *m, void *v)
{
- struct trace_probe *tp = v;
+ struct trace_kprobe *tk = v;
int i;
- seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
+ seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p');
+ seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name);
- if (!tp->symbol)
- seq_printf(m, " 0x%p", tp->rp.kp.addr);
- else if (tp->rp.kp.offset)
- seq_printf(m, " %s+%u", trace_probe_symbol(tp),
- tp->rp.kp.offset);
+ if (!tk->symbol)
+ seq_printf(m, " 0x%p", tk->rp.kp.addr);
+ else if (tk->rp.kp.offset)
+ seq_printf(m, " %s+%u", trace_kprobe_symbol(tk),
+ tk->rp.kp.offset);
else
- seq_printf(m, " %s", trace_probe_symbol(tp));
+ seq_printf(m, " %s", trace_kprobe_symbol(tk));
- for (i = 0; i < tp->nr_args; i++)
- seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm);
seq_printf(m, "\n");
return 0;
@@ -699,7 +864,7 @@ static int probes_open(struct inode *inode, struct file *file)
int ret;
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
- ret = release_all_trace_probes();
+ ret = release_all_trace_kprobes();
if (ret < 0)
return ret;
}
@@ -711,7 +876,7 @@ static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
return traceprobe_probes_write(file, buffer, count, ppos,
- create_trace_probe);
+ create_trace_kprobe);
}
static const struct file_operations kprobe_events_ops = {
@@ -726,10 +891,10 @@ static const struct file_operations kprobe_events_ops = {
/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
- struct trace_probe *tp = v;
+ struct trace_kprobe *tk = v;
- seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
- tp->rp.kp.nmissed);
+ seq_printf(m, " %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit,
+ tk->rp.kp.nmissed);
return 0;
}
@@ -754,57 +919,9 @@ static const struct file_operations kprobe_profile_ops = {
.release = seq_release,
};
-/* Sum up total data length for dynamic arraies (strings) */
-static __kprobes int __get_data_size(struct trace_probe *tp,
- struct pt_regs *regs)
-{
- int i, ret = 0;
- u32 len;
-
- for (i = 0; i < tp->nr_args; i++)
- if (unlikely(tp->args[i].fetch_size.fn)) {
- call_fetch(&tp->args[i].fetch_size, regs, &len);
- ret += len;
- }
-
- return ret;
-}
-
-/* Store the value of each argument */
-static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp,
- struct pt_regs *regs,
- u8 *data, int maxlen)
-{
- int i;
- u32 end = tp->size;
- u32 *dl; /* Data (relative) location */
-
- for (i = 0; i < tp->nr_args; i++) {
- if (unlikely(tp->args[i].fetch_size.fn)) {
- /*
- * First, we set the relative location and
- * maximum data length to *dl
- */
- dl = (u32 *)(data + tp->args[i].offset);
- *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
- /* Then try to fetch string or dynamic array data */
- call_fetch(&tp->args[i].fetch, regs, dl);
- /* Reduce maximum length */
- end += get_rloc_len(*dl);
- maxlen -= get_rloc_len(*dl);
- /* Trick here, convert data_rloc to data_loc */
- *dl = convert_rloc_to_loc(*dl,
- ent_size + tp->args[i].offset);
- } else
- /* Just fetching data normally */
- call_fetch(&tp->args[i].fetch, regs,
- data + tp->args[i].offset);
- }
-}
-
/* Kprobe handler */
static __kprobes void
-__kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
+__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
struct ftrace_event_file *ftrace_file)
{
struct kprobe_trace_entry_head *entry;
@@ -812,18 +929,18 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
struct ring_buffer *buffer;
int size, dsize, pc;
unsigned long irq_flags;
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
WARN_ON(call != ftrace_file->event_call);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
local_save_flags(irq_flags);
pc = preempt_count();
- dsize = __get_data_size(tp, regs);
- size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ size = sizeof(*entry) + tk->tp.size + dsize;
event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
call->event.type,
@@ -832,26 +949,25 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
return;
entry = ring_buffer_event_data(event);
- entry->ip = (unsigned long)tp->rp.kp.addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ entry->ip = (unsigned long)tk->rp.kp.addr;
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- if (!filter_current_check_discard(buffer, call, entry, event))
- trace_buffer_unlock_commit_regs(buffer, event,
- irq_flags, pc, regs);
+ event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+ entry, irq_flags, pc, regs);
}
static __kprobes void
-kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct event_file_link *link;
- list_for_each_entry_rcu(link, &tp->files, list)
- __kprobe_trace_func(tp, regs, link->file);
+ list_for_each_entry_rcu(link, &tk->tp.files, list)
+ __kprobe_trace_func(tk, regs, link->file);
}
/* Kretprobe handler */
static __kprobes void
-__kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+__kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs,
struct ftrace_event_file *ftrace_file)
{
@@ -860,18 +976,18 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
struct ring_buffer *buffer;
int size, pc, dsize;
unsigned long irq_flags;
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
WARN_ON(call != ftrace_file->event_call);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
local_save_flags(irq_flags);
pc = preempt_count();
- dsize = __get_data_size(tp, regs);
- size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ size = sizeof(*entry) + tk->tp.size + dsize;
event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
call->event.type,
@@ -880,23 +996,22 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
return;
entry = ring_buffer_event_data(event);
- entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- if (!filter_current_check_discard(buffer, call, entry, event))
- trace_buffer_unlock_commit_regs(buffer, event,
- irq_flags, pc, regs);
+ event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+ entry, irq_flags, pc, regs);
}
static __kprobes void
-kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct event_file_link *link;
- list_for_each_entry_rcu(link, &tp->files, list)
- __kretprobe_trace_func(tp, ri, regs, link->file);
+ list_for_each_entry_rcu(link, &tk->tp.files, list)
+ __kretprobe_trace_func(tk, ri, regs, link->file);
}
/* Event entry printers */
@@ -983,16 +1098,18 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
struct kprobe_trace_entry_head field;
- struct trace_probe *tp = (struct trace_probe *)event_call->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++) {
- ret = trace_define_field(event_call, tp->args[i].type->fmttype,
- tp->args[i].name,
- sizeof(field) + tp->args[i].offset,
- tp->args[i].type->size,
- tp->args[i].type->is_signed,
+ for (i = 0; i < tk->tp.nr_args; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name,
+ sizeof(field) + parg->offset,
+ parg->type->size,
+ parg->type->is_signed,
FILTER_OTHER);
if (ret)
return ret;
@@ -1004,17 +1121,19 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
struct kretprobe_trace_entry_head field;
- struct trace_probe *tp = (struct trace_probe *)event_call->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++) {
- ret = trace_define_field(event_call, tp->args[i].type->fmttype,
- tp->args[i].name,
- sizeof(field) + tp->args[i].offset,
- tp->args[i].type->size,
- tp->args[i].type->is_signed,
+ for (i = 0; i < tk->tp.nr_args; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name,
+ sizeof(field) + parg->offset,
+ parg->type->size,
+ parg->type->is_signed,
FILTER_OTHER);
if (ret)
return ret;
@@ -1022,74 +1141,13 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
return 0;
}
-static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
-{
- int i;
- int pos = 0;
-
- const char *fmt, *arg;
-
- if (!trace_probe_is_return(tp)) {
- fmt = "(%lx)";
- arg = "REC->" FIELD_STRING_IP;
- } else {
- fmt = "(%lx <- %lx)";
- arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
- }
-
- /* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
- for (i = 0; i < tp->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tp->args[i].name, tp->args[i].type->fmt);
- }
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
- for (i = 0; i < tp->nr_args; i++) {
- if (strcmp(tp->args[i].type->name, "string") == 0)
- pos += snprintf(buf + pos, LEN_OR_ZERO,
- ", __get_str(%s)",
- tp->args[i].name);
- else
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tp->args[i].name);
- }
-
-#undef LEN_OR_ZERO
-
- /* return the length of print_fmt */
- return pos;
-}
-
-static int set_print_fmt(struct trace_probe *tp)
-{
- int len;
- char *print_fmt;
-
- /* First: called with 0 length to calculate the needed length */
- len = __set_print_fmt(tp, NULL, 0);
- print_fmt = kmalloc(len + 1, GFP_KERNEL);
- if (!print_fmt)
- return -ENOMEM;
-
- /* Second: actually write the @print_fmt */
- __set_print_fmt(tp, print_fmt, len + 1);
- tp->call.print_fmt = print_fmt;
-
- return 0;
-}
-
#ifdef CONFIG_PERF_EVENTS
/* Kprobe profile handler */
static __kprobes void
-kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
struct kprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
@@ -1099,8 +1157,8 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
if (hlist_empty(head))
return;
- dsize = __get_data_size(tp, regs);
- __size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ __size = sizeof(*entry) + tk->tp.size + dsize;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
@@ -1108,18 +1166,18 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
if (!entry)
return;
- entry->ip = (unsigned long)tp->rp.kp.addr;
+ entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
}
/* Kretprobe profile handler */
static __kprobes void
-kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
struct kretprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
@@ -1129,8 +1187,8 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
if (hlist_empty(head))
return;
- dsize = __get_data_size(tp, regs);
- __size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ __size = sizeof(*entry) + tk->tp.size + dsize;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
@@ -1138,9 +1196,9 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
if (!entry)
return;
- entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
}
#endif /* CONFIG_PERF_EVENTS */
@@ -1155,20 +1213,20 @@ static __kprobes
int kprobe_register(struct ftrace_event_call *event,
enum trace_reg type, void *data)
{
- struct trace_probe *tp = (struct trace_probe *)event->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
struct ftrace_event_file *file = data;
switch (type) {
case TRACE_REG_REGISTER:
- return enable_trace_probe(tp, file);
+ return enable_trace_kprobe(tk, file);
case TRACE_REG_UNREGISTER:
- return disable_trace_probe(tp, file);
+ return disable_trace_kprobe(tk, file);
#ifdef CONFIG_PERF_EVENTS
case TRACE_REG_PERF_REGISTER:
- return enable_trace_probe(tp, NULL);
+ return enable_trace_kprobe(tk, NULL);
case TRACE_REG_PERF_UNREGISTER:
- return disable_trace_probe(tp, NULL);
+ return disable_trace_kprobe(tk, NULL);
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
@@ -1182,15 +1240,15 @@ int kprobe_register(struct ftrace_event_call *event,
static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
- struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
- tp->nhit++;
+ tk->nhit++;
- if (tp->flags & TP_FLAG_TRACE)
- kprobe_trace_func(tp, regs);
+ if (tk->tp.flags & TP_FLAG_TRACE)
+ kprobe_trace_func(tk, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tp->flags & TP_FLAG_PROFILE)
- kprobe_perf_func(tp, regs);
+ if (tk->tp.flags & TP_FLAG_PROFILE)
+ kprobe_perf_func(tk, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1198,15 +1256,15 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
static __kprobes
int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
- struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
- tp->nhit++;
+ tk->nhit++;
- if (tp->flags & TP_FLAG_TRACE)
- kretprobe_trace_func(tp, ri, regs);
+ if (tk->tp.flags & TP_FLAG_TRACE)
+ kretprobe_trace_func(tk, ri, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tp->flags & TP_FLAG_PROFILE)
- kretprobe_perf_func(tp, ri, regs);
+ if (tk->tp.flags & TP_FLAG_PROFILE)
+ kretprobe_perf_func(tk, ri, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1219,21 +1277,21 @@ static struct trace_event_functions kprobe_funcs = {
.trace = print_kprobe_event
};
-static int register_probe_event(struct trace_probe *tp)
+static int register_kprobe_event(struct trace_kprobe *tk)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
int ret;
/* Initialize ftrace_event_call */
INIT_LIST_HEAD(&call->class->fields);
- if (trace_probe_is_return(tp)) {
+ if (trace_kprobe_is_return(tk)) {
call->event.funcs = &kretprobe_funcs;
call->class->define_fields = kretprobe_event_define_fields;
} else {
call->event.funcs = &kprobe_funcs;
call->class->define_fields = kprobe_event_define_fields;
}
- if (set_print_fmt(tp) < 0)
+ if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
return -ENOMEM;
ret = register_ftrace_event(&call->event);
if (!ret) {
@@ -1242,7 +1300,7 @@ static int register_probe_event(struct trace_probe *tp)
}
call->flags = 0;
call->class->reg = kprobe_register;
- call->data = tp;
+ call->data = tk;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
@@ -1252,14 +1310,14 @@ static int register_probe_event(struct trace_probe *tp)
return ret;
}
-static int unregister_probe_event(struct trace_probe *tp)
+static int unregister_kprobe_event(struct trace_kprobe *tk)
{
int ret;
/* tp->event is unregistered in trace_remove_event_call() */
- ret = trace_remove_event_call(&tp->call);
+ ret = trace_remove_event_call(&tk->tp.call);
if (!ret)
- kfree(tp->call.print_fmt);
+ kfree(tk->tp.call.print_fmt);
return ret;
}
@@ -1269,7 +1327,7 @@ static __init int init_kprobe_trace(void)
struct dentry *d_tracer;
struct dentry *entry;
- if (register_module_notifier(&trace_probe_module_nb))
+ if (register_module_notifier(&trace_kprobe_module_nb))
return -EINVAL;
d_tracer = tracing_init_dentry();
@@ -1309,26 +1367,26 @@ static __used int kprobe_trace_selftest_target(int a1, int a2, int a3,
}
static struct ftrace_event_file *
-find_trace_probe_file(struct trace_probe *tp, struct trace_array *tr)
+find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
struct ftrace_event_file *file;
list_for_each_entry(file, &tr->events, list)
- if (file->event_call == &tp->call)
+ if (file->event_call == &tk->tp.call)
return file;
return NULL;
}
/*
- * Nobody but us can call enable_trace_probe/disable_trace_probe at this
+ * Nobody but us can call enable_trace_kprobe/disable_trace_kprobe at this
* stage, we can do this lockless.
*/
static __init int kprobe_trace_self_tests_init(void)
{
int ret, warn = 0;
int (*target)(int, int, int, int, int, int);
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
struct ftrace_event_file *file;
target = kprobe_trace_selftest_target;
@@ -1337,44 +1395,44 @@ static __init int kprobe_trace_self_tests_init(void)
ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
"$stack $stack0 +0($stack)",
- create_trace_probe);
+ create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function entry.\n");
warn++;
} else {
/* Enable trace point */
- tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting new probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_probe(tp, file);
+ enable_trace_kprobe(tk, file);
}
}
ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
- "$retval", create_trace_probe);
+ "$retval", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function return.\n");
warn++;
} else {
/* Enable trace point */
- tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting 2nd new probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_probe(tp, file);
+ enable_trace_kprobe(tk, file);
}
}
@@ -1384,46 +1442,46 @@ static __init int kprobe_trace_self_tests_init(void)
ret = target(1, 2, 3, 4, 5, 6);
/* Disable trace points before removing it */
- tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting test probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_probe(tp, file);
+ disable_trace_kprobe(tk, file);
}
- tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting 2nd test probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_probe(tp, file);
+ disable_trace_kprobe(tk, file);
}
- ret = traceprobe_command("-:testprobe", create_trace_probe);
+ ret = traceprobe_command("-:testprobe", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
}
- ret = traceprobe_command("-:testprobe2", create_trace_probe);
+ ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
}
end:
- release_all_trace_probes();
+ release_all_trace_kprobes();
if (warn)
pr_cont("NG: Some tests are failed. Please check them.\n");
else
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index b3dcfb2f0fef..0abd9b863474 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -323,7 +323,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
entry = ring_buffer_event_data(event);
entry->rw = *rw;
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, 0, pc);
}
@@ -353,7 +353,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
entry = ring_buffer_event_data(event);
entry->map = *map;
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, 0, pc);
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 34e7cbac0c9c..ed32284fbe32 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -618,8 +618,23 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
'.';
- need_resched =
- (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+
+ switch (entry->flags & (TRACE_FLAG_NEED_RESCHED |
+ TRACE_FLAG_PREEMPT_RESCHED)) {
+ case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
+ need_resched = 'N';
+ break;
+ case TRACE_FLAG_NEED_RESCHED:
+ need_resched = 'n';
+ break;
+ case TRACE_FLAG_PREEMPT_RESCHED:
+ need_resched = 'p';
+ break;
+ default:
+ need_resched = '.';
+ break;
+ }
+
hardsoft_irq =
(hardirq && softirq) ? 'H' :
hardirq ? 'h' :
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 412e959709b4..8364a421b4df 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -35,46 +35,27 @@ const char *reserved_field_names[] = {
FIELD_STRING_FUNC,
};
-/* Printing function type */
-#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
-#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
-
/* Printing in basic type function template */
-#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \
-static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt) \
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
const char *name, \
- void *data, void *ent)\
+ void *data, void *ent) \
{ \
- return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+ return trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \
} \
-static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-
-DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
-
-static inline void *get_rloc_data(u32 *dl)
-{
- return (u8 *)dl + get_rloc_offs(*dl);
-}
+const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-/* For data_loc conversion */
-static inline void *get_loc_data(u32 *dl, void *ent)
-{
- return (u8 *)ent + get_rloc_offs(*dl);
-}
-
-/* For defining macros, define string/string_size types */
-typedef u32 string;
-typedef u32 string_size;
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "0x%Lx")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld")
/* Print type function for string type */
-static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+__kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
const char *name,
void *data, void *ent)
{
@@ -87,18 +68,7 @@ static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
(const char *)get_loc_data(data, ent));
}
-static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
-
-#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
-/*
- * Define macro for basic types - we don't need to define s* types, because
- * we have to care only about bitwidth at recording time.
- */
-#define DEFINE_BASIC_FETCH_FUNCS(method) \
-DEFINE_FETCH_##method(u8) \
-DEFINE_FETCH_##method(u16) \
-DEFINE_FETCH_##method(u32) \
-DEFINE_FETCH_##method(u64)
+const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
#define CHECK_FETCH_FUNCS(method, fn) \
(((FETCH_FUNC_NAME(method, u8) == fn) || \
@@ -111,7 +81,7 @@ DEFINE_FETCH_##method(u64)
/* Data fetch function templates */
#define DEFINE_FETCH_reg(type) \
-static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
+__kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
void *offset, void *dest) \
{ \
*(type *)dest = (type)regs_get_register(regs, \
@@ -122,20 +92,8 @@ DEFINE_BASIC_FETCH_FUNCS(reg)
#define fetch_reg_string NULL
#define fetch_reg_string_size NULL
-#define DEFINE_FETCH_stack(type) \
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
- (unsigned int)((unsigned long)offset)); \
-}
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string NULL
-#define fetch_stack_string_size NULL
-
#define DEFINE_FETCH_retval(type) \
-static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \
void *dummy, void *dest) \
{ \
*(type *)dest = (type)regs_return_value(regs); \
@@ -145,150 +103,16 @@ DEFINE_BASIC_FETCH_FUNCS(retval)
#define fetch_retval_string NULL
#define fetch_retval_string_size NULL
-#define DEFINE_FETCH_memory(type) \
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
- void *addr, void *dest) \
-{ \
- type retval; \
- if (probe_kernel_address(addr, retval)) \
- *(type *)dest = 0; \
- else \
- *(type *)dest = retval; \
-}
-DEFINE_BASIC_FETCH_FUNCS(memory)
-/*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
- * length and relative data location.
- */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- long ret;
- int maxlen = get_rloc_len(*(u32 *)dest);
- u8 *dst = get_rloc_data(dest);
- u8 *src = addr;
- mm_segment_t old_fs = get_fs();
-
- if (!maxlen)
- return;
-
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- set_fs(KERNEL_DS);
- pagefault_disable();
-
- do
- ret = __copy_from_user_inatomic(dst++, src++, 1);
- while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
-
- dst[-1] = '\0';
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) { /* Failed to fetch string */
- ((u8 *)get_rloc_data(dest))[0] = '\0';
- *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
- } else {
- *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
- get_rloc_offs(*(u32 *)dest));
- }
-}
-
-/* Return the length of string -- including null terminal byte */
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- mm_segment_t old_fs;
- int ret, len = 0;
- u8 c;
-
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- pagefault_disable();
-
- do {
- ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
-
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) /* Failed to check the length */
- *(u32 *)dest = 0;
- else
- *(u32 *)dest = len;
-}
-
-/* Memory fetching by symbol */
-struct symbol_cache {
- char *symbol;
- long offset;
- unsigned long addr;
-};
-
-static unsigned long update_symbol_cache(struct symbol_cache *sc)
-{
- sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
-
- if (sc->addr)
- sc->addr += sc->offset;
-
- return sc->addr;
-}
-
-static void free_symbol_cache(struct symbol_cache *sc)
-{
- kfree(sc->symbol);
- kfree(sc);
-}
-
-static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
-{
- struct symbol_cache *sc;
-
- if (!sym || strlen(sym) == 0)
- return NULL;
-
- sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
- if (!sc)
- return NULL;
-
- sc->symbol = kstrdup(sym, GFP_KERNEL);
- if (!sc->symbol) {
- kfree(sc);
- return NULL;
- }
- sc->offset = offset;
- update_symbol_cache(sc);
-
- return sc;
-}
-
-#define DEFINE_FETCH_symbol(type) \
-static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
- void *data, void *dest) \
-{ \
- struct symbol_cache *sc = data; \
- if (sc->addr) \
- fetch_memory_##type(regs, (void *)sc->addr, dest); \
- else \
- *(type *)dest = 0; \
-}
-DEFINE_BASIC_FETCH_FUNCS(symbol)
-DEFINE_FETCH_symbol(string)
-DEFINE_FETCH_symbol(string_size)
-
/* Dereference memory access function */
struct deref_fetch_param {
struct fetch_param orig;
long offset;
+ fetch_func_t fetch;
+ fetch_func_t fetch_size;
};
#define DEFINE_FETCH_deref(type) \
-static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \
void *data, void *dest) \
{ \
struct deref_fetch_param *dprm = data; \
@@ -296,13 +120,26 @@ static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
call_fetch(&dprm->orig, regs, &addr); \
if (addr) { \
addr += dprm->offset; \
- fetch_memory_##type(regs, (void *)addr, dest); \
+ dprm->fetch(regs, (void *)addr, dest); \
} else \
*(type *)dest = 0; \
}
DEFINE_BASIC_FETCH_FUNCS(deref)
DEFINE_FETCH_deref(string)
-DEFINE_FETCH_deref(string_size)
+
+__kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
+ void *data, void *dest)
+{
+ struct deref_fetch_param *dprm = data;
+ unsigned long addr;
+
+ call_fetch(&dprm->orig, regs, &addr);
+ if (addr && dprm->fetch_size) {
+ addr += dprm->offset;
+ dprm->fetch_size(regs, (void *)addr, dest);
+ } else
+ *(string_size *)dest = 0;
+}
static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
{
@@ -329,7 +166,7 @@ struct bitfield_fetch_param {
};
#define DEFINE_FETCH_bitfield(type) \
-static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \
void *data, void *dest) \
{ \
struct bitfield_fetch_param *bprm = data; \
@@ -374,58 +211,8 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
kfree(data);
}
-/* Default (unsigned long) fetch type */
-#define __DEFAULT_FETCH_TYPE(t) u##t
-#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
-#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
-#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
-
-#define ASSIGN_FETCH_FUNC(method, type) \
- [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
-
-#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
- {.name = _name, \
- .size = _size, \
- .is_signed = sign, \
- .print = PRINT_TYPE_FUNC_NAME(ptype), \
- .fmt = PRINT_TYPE_FMT_NAME(ptype), \
- .fmttype = _fmttype, \
- .fetch = { \
-ASSIGN_FETCH_FUNC(reg, ftype), \
-ASSIGN_FETCH_FUNC(stack, ftype), \
-ASSIGN_FETCH_FUNC(retval, ftype), \
-ASSIGN_FETCH_FUNC(memory, ftype), \
-ASSIGN_FETCH_FUNC(symbol, ftype), \
-ASSIGN_FETCH_FUNC(deref, ftype), \
-ASSIGN_FETCH_FUNC(bitfield, ftype), \
- } \
- }
-
-#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
- __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
-
-#define FETCH_TYPE_STRING 0
-#define FETCH_TYPE_STRSIZE 1
-
-/* Fetch type information table */
-static const struct fetch_type fetch_type_table[] = {
- /* Special types */
- [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
- sizeof(u32), 1, "__data_loc char[]"),
- [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
- string_size, sizeof(u32), 0, "u32"),
- /* Basic types */
- ASSIGN_FETCH_TYPE(u8, u8, 0),
- ASSIGN_FETCH_TYPE(u16, u16, 0),
- ASSIGN_FETCH_TYPE(u32, u32, 0),
- ASSIGN_FETCH_TYPE(u64, u64, 0),
- ASSIGN_FETCH_TYPE(s8, u8, 1),
- ASSIGN_FETCH_TYPE(s16, u16, 1),
- ASSIGN_FETCH_TYPE(s32, u32, 1),
- ASSIGN_FETCH_TYPE(s64, u64, 1),
-};
-
-static const struct fetch_type *find_fetch_type(const char *type)
+static const struct fetch_type *find_fetch_type(const char *type,
+ const struct fetch_type *ftbl)
{
int i;
@@ -446,44 +233,52 @@ static const struct fetch_type *find_fetch_type(const char *type)
switch (bs) {
case 8:
- return find_fetch_type("u8");
+ return find_fetch_type("u8", ftbl);
case 16:
- return find_fetch_type("u16");
+ return find_fetch_type("u16", ftbl);
case 32:
- return find_fetch_type("u32");
+ return find_fetch_type("u32", ftbl);
case 64:
- return find_fetch_type("u64");
+ return find_fetch_type("u64", ftbl);
default:
goto fail;
}
}
- for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
- if (strcmp(type, fetch_type_table[i].name) == 0)
- return &fetch_type_table[i];
+ for (i = 0; ftbl[i].name; i++) {
+ if (strcmp(type, ftbl[i].name) == 0)
+ return &ftbl[i];
+ }
fail:
return NULL;
}
/* Special function : only accept unsigned long */
-static __kprobes void fetch_stack_address(struct pt_regs *regs,
- void *dummy, void *dest)
+static __kprobes void fetch_kernel_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
{
*(unsigned long *)dest = kernel_stack_pointer(regs);
}
+static __kprobes void fetch_user_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
+{
+ *(unsigned long *)dest = user_stack_pointer(regs);
+}
+
static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
- fetch_func_t orig_fn)
+ fetch_func_t orig_fn,
+ const struct fetch_type *ftbl)
{
int i;
- if (type != &fetch_type_table[FETCH_TYPE_STRING])
+ if (type != &ftbl[FETCH_TYPE_STRING])
return NULL; /* Only string type needs size function */
for (i = 0; i < FETCH_MTD_END; i++)
if (type->fetch[i] == orig_fn)
- return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+ return ftbl[FETCH_TYPE_STRSIZE].fetch[i];
WARN_ON(1); /* This should not happen */
@@ -516,7 +311,8 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_param *f, bool is_return)
+ struct fetch_param *f, bool is_return,
+ bool is_kprobe)
{
int ret = 0;
unsigned long param;
@@ -528,13 +324,16 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
ret = -EINVAL;
} else if (strncmp(arg, "stack", 5) == 0) {
if (arg[5] == '\0') {
- if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
- f->fn = fetch_stack_address;
+ if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR))
+ return -EINVAL;
+
+ if (is_kprobe)
+ f->fn = fetch_kernel_stack_address;
else
- ret = -EINVAL;
+ f->fn = fetch_user_stack_address;
} else if (isdigit(arg[5])) {
ret = kstrtoul(arg + 5, 10, &param);
- if (ret || param > PARAM_MAX_STACK)
+ if (ret || (is_kprobe && param > PARAM_MAX_STACK))
ret = -EINVAL;
else {
f->fn = t->fetch[FETCH_MTD_stack];
@@ -552,20 +351,18 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
static int parse_probe_arg(char *arg, const struct fetch_type *t,
struct fetch_param *f, bool is_return, bool is_kprobe)
{
+ const struct fetch_type *ftbl;
unsigned long param;
long offset;
char *tmp;
- int ret;
-
- ret = 0;
+ int ret = 0;
- /* Until uprobe_events supports only reg arguments */
- if (!is_kprobe && arg[0] != '%')
- return -EINVAL;
+ ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+ BUG_ON(ftbl == NULL);
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, t, f, is_return);
+ ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
break;
case '%': /* named register */
@@ -577,7 +374,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
}
break;
- case '@': /* memory or symbol */
+ case '@': /* memory, file-offset or symbol */
if (isdigit(arg[1])) {
ret = kstrtoul(arg + 1, 0, &param);
if (ret)
@@ -585,7 +382,22 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
f->fn = t->fetch[FETCH_MTD_memory];
f->data = (void *)param;
+ } else if (arg[1] == '+') {
+ /* kprobes don't support file offsets */
+ if (is_kprobe)
+ return -EINVAL;
+
+ ret = kstrtol(arg + 2, 0, &offset);
+ if (ret)
+ break;
+
+ f->fn = t->fetch[FETCH_MTD_file_offset];
+ f->data = (void *)offset;
} else {
+ /* uprobes don't support symbols */
+ if (!is_kprobe)
+ return -EINVAL;
+
ret = traceprobe_split_symbol_offset(arg + 1, &offset);
if (ret)
break;
@@ -616,7 +428,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
struct deref_fetch_param *dprm;
const struct fetch_type *t2;
- t2 = find_fetch_type(NULL);
+ t2 = find_fetch_type(NULL, ftbl);
*tmp = '\0';
dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
@@ -624,6 +436,9 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
return -ENOMEM;
dprm->offset = offset;
+ dprm->fetch = t->fetch[FETCH_MTD_memory];
+ dprm->fetch_size = get_fetch_size_function(t,
+ dprm->fetch, ftbl);
ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
is_kprobe);
if (ret)
@@ -685,9 +500,13 @@ static int __parse_bitfield_probe_arg(const char *bf,
int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
struct probe_arg *parg, bool is_return, bool is_kprobe)
{
+ const struct fetch_type *ftbl;
const char *t;
int ret;
+ ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+ BUG_ON(ftbl == NULL);
+
if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
return -ENOSPC;
@@ -702,7 +521,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
arg[t - parg->comm] = '\0';
t++;
}
- parg->type = find_fetch_type(t);
+ parg->type = find_fetch_type(t, ftbl);
if (!parg->type) {
pr_info("Unsupported type: %s\n", t);
return -EINVAL;
@@ -716,7 +535,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
if (ret >= 0) {
parg->fetch_size.fn = get_fetch_size_function(parg->type,
- parg->fetch.fn);
+ parg->fetch.fn,
+ ftbl);
parg->fetch_size.data = parg->fetch.data;
}
@@ -837,3 +657,65 @@ out:
return ret;
}
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
+ bool is_return)
+{
+ int i;
+ int pos = 0;
+
+ const char *fmt, *arg;
+
+ if (!is_return) {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ } else {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ }
+
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+ tp->args[i].name, tp->args[i].type->fmt);
+ }
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+ for (i = 0; i < tp->nr_args; i++) {
+ if (strcmp(tp->args[i].type->name, "string") == 0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", __get_str(%s)",
+ tp->args[i].name);
+ else
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tp->args[i].name);
+ }
+
+#undef LEN_OR_ZERO
+
+ /* return the length of print_fmt */
+ return pos;
+}
+
+int set_print_fmt(struct trace_probe *tp, bool is_return)
+{
+ int len;
+ char *print_fmt;
+
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tp, NULL, 0, is_return);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
+
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tp, print_fmt, len + 1, is_return);
+ tp->call.print_fmt = print_fmt;
+
+ return 0;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5c7e09d10d74..b73574a5f429 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -81,6 +81,17 @@
*/
#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs))
+static inline void *get_rloc_data(u32 *dl)
+{
+ return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+ return (u8 *)ent + get_rloc_offs(*dl);
+}
+
/* Data fetch function type */
typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
/* Printing function type */
@@ -95,6 +106,7 @@ enum {
FETCH_MTD_symbol,
FETCH_MTD_deref,
FETCH_MTD_bitfield,
+ FETCH_MTD_file_offset,
FETCH_MTD_END,
};
@@ -115,6 +127,148 @@ struct fetch_param {
void *data;
};
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
+#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
+
+/* Printing in basic type function template */
+#define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+ const char *name, \
+ void *data, void *ent); \
+extern const char PRINT_TYPE_FMT_NAME(type)[]
+
+DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(string);
+
+#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
+
+/* Declare macro for basic types */
+#define DECLARE_FETCH_FUNC(method, type) \
+extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, \
+ void *data, void *dest)
+
+#define DECLARE_BASIC_FETCH_FUNCS(method) \
+DECLARE_FETCH_FUNC(method, u8); \
+DECLARE_FETCH_FUNC(method, u16); \
+DECLARE_FETCH_FUNC(method, u32); \
+DECLARE_FETCH_FUNC(method, u64)
+
+DECLARE_BASIC_FETCH_FUNCS(reg);
+#define fetch_reg_string NULL
+#define fetch_reg_string_size NULL
+
+DECLARE_BASIC_FETCH_FUNCS(retval);
+#define fetch_retval_string NULL
+#define fetch_retval_string_size NULL
+
+DECLARE_BASIC_FETCH_FUNCS(symbol);
+DECLARE_FETCH_FUNC(symbol, string);
+DECLARE_FETCH_FUNC(symbol, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(deref);
+DECLARE_FETCH_FUNC(deref, string);
+DECLARE_FETCH_FUNC(deref, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(bitfield);
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8) \
+DEFINE_FETCH_##method(u16) \
+DEFINE_FETCH_##method(u32) \
+DEFINE_FETCH_##method(u64)
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(method, type) \
+ [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
+ {.name = _name, \
+ .size = _size, \
+ .is_signed = sign, \
+ .print = PRINT_TYPE_FUNC_NAME(ptype), \
+ .fmt = PRINT_TYPE_FMT_NAME(ptype), \
+ .fmttype = _fmttype, \
+ .fetch = { \
+ASSIGN_FETCH_FUNC(reg, ftype), \
+ASSIGN_FETCH_FUNC(stack, ftype), \
+ASSIGN_FETCH_FUNC(retval, ftype), \
+ASSIGN_FETCH_FUNC(memory, ftype), \
+ASSIGN_FETCH_FUNC(symbol, ftype), \
+ASSIGN_FETCH_FUNC(deref, ftype), \
+ASSIGN_FETCH_FUNC(bitfield, ftype), \
+ASSIGN_FETCH_FUNC(file_offset, ftype), \
+ } \
+ }
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
+ __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define ASSIGN_FETCH_TYPE_END {}
+
+#define FETCH_TYPE_STRING 0
+#define FETCH_TYPE_STRSIZE 1
+
+/*
+ * Fetch type information table.
+ * It's declared as a weak symbol due to conditional compilation.
+ */
+extern __weak const struct fetch_type kprobes_fetch_type_table[];
+extern __weak const struct fetch_type uprobes_fetch_type_table[];
+
+#ifdef CONFIG_KPROBE_EVENT
+struct symbol_cache;
+unsigned long update_symbol_cache(struct symbol_cache *sc);
+void free_symbol_cache(struct symbol_cache *sc);
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+#else
+/* uprobes do not support symbol fetch methods */
+#define fetch_symbol_u8 NULL
+#define fetch_symbol_u16 NULL
+#define fetch_symbol_u32 NULL
+#define fetch_symbol_u64 NULL
+#define fetch_symbol_string NULL
+#define fetch_symbol_string_size NULL
+
+struct symbol_cache {
+};
+static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc)
+{
+ return 0;
+}
+
+static inline void __used free_symbol_cache(struct symbol_cache *sc)
+{
+}
+
+static inline struct symbol_cache * __used
+alloc_symbol_cache(const char *sym, long offset)
+{
+ return NULL;
+}
+#endif /* CONFIG_KPROBE_EVENT */
+
struct probe_arg {
struct fetch_param fetch;
struct fetch_param fetch_size;
@@ -124,6 +278,26 @@ struct probe_arg {
const struct fetch_type *type; /* Type of this argument */
};
+struct trace_probe {
+ unsigned int flags; /* For TP_FLAG_* */
+ struct ftrace_event_class class;
+ struct ftrace_event_call call;
+ struct list_head files;
+ ssize_t size; /* trace entry size */
+ unsigned int nr_args;
+ struct probe_arg args[];
+};
+
+static inline bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+ return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static inline bool trace_probe_is_registered(struct trace_probe *tp)
+{
+ return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
static inline __kprobes void call_fetch(struct fetch_param *fprm,
struct pt_regs *regs, void *dest)
{
@@ -158,3 +332,53 @@ extern ssize_t traceprobe_probes_write(struct file *file,
int (*createfn)(int, char**));
extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
+
+/* Sum up total data length for dynamic arraies (strings) */
+static inline __kprobes int
+__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
+{
+ int i, ret = 0;
+ u32 len;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (unlikely(tp->args[i].fetch_size.fn)) {
+ call_fetch(&tp->args[i].fetch_size, regs, &len);
+ ret += len;
+ }
+
+ return ret;
+}
+
+/* Store the value of each argument */
+static inline __kprobes void
+store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
+ u8 *data, int maxlen)
+{
+ int i;
+ u32 end = tp->size;
+ u32 *dl; /* Data (relative) location */
+
+ for (i = 0; i < tp->nr_args; i++) {
+ if (unlikely(tp->args[i].fetch_size.fn)) {
+ /*
+ * First, we set the relative location and
+ * maximum data length to *dl
+ */
+ dl = (u32 *)(data + tp->args[i].offset);
+ *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+ /* Then try to fetch string or dynamic array data */
+ call_fetch(&tp->args[i].fetch, regs, dl);
+ /* Reduce maximum length */
+ end += get_rloc_len(*dl);
+ maxlen -= get_rloc_len(*dl);
+ /* Trick here, convert data_rloc to data_loc */
+ *dl = convert_rloc_to_loc(*dl,
+ ent_size + tp->args[i].offset);
+ } else
+ /* Just fetching data normally */
+ call_fetch(&tp->args[i].fetch, regs,
+ data + tp->args[i].offset);
+ }
+}
+
+extern int set_print_fmt(struct trace_probe *tp, bool is_return);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 4e98e3b257a3..3f34dc9b40f3 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -45,7 +45,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, flags, pc);
}
@@ -101,7 +101,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, flags, pc);
}
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e15d815..6e32635e5e57 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -16,6 +16,7 @@
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <trace/events/sched.h>
#include "trace.h"
@@ -27,6 +28,8 @@ static int wakeup_cpu;
static int wakeup_current_cpu;
static unsigned wakeup_prio = -1;
static int wakeup_rt;
+static int wakeup_dl;
+static int tracing_dl = 0;
static arch_spinlock_t wakeup_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -437,6 +440,7 @@ static void __wakeup_reset(struct trace_array *tr)
{
wakeup_cpu = -1;
wakeup_prio = -1;
+ tracing_dl = 0;
if (wakeup_task)
put_task_struct(wakeup_task);
@@ -472,9 +476,17 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
tracing_record_cmdline(p);
tracing_record_cmdline(current);
- if ((wakeup_rt && !rt_task(p)) ||
- p->prio >= wakeup_prio ||
- p->prio >= current->prio)
+ /*
+ * Semantic is like this:
+ * - wakeup tracer handles all tasks in the system, independently
+ * from their scheduling class;
+ * - wakeup_rt tracer handles tasks belonging to sched_dl and
+ * sched_rt class;
+ * - wakeup_dl handles tasks belonging to sched_dl class only.
+ */
+ if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+ (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+ (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
return;
pc = preempt_count();
@@ -486,7 +498,8 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
arch_spin_lock(&wakeup_lock);
/* check for races. */
- if (!tracer_enabled || p->prio >= wakeup_prio)
+ if (!tracer_enabled || tracing_dl ||
+ (!dl_task(p) && p->prio >= wakeup_prio))
goto out_locked;
/* reset the trace */
@@ -496,6 +509,15 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
wakeup_current_cpu = wakeup_cpu;
wakeup_prio = p->prio;
+ /*
+ * Once you start tracing a -deadline task, don't bother tracing
+ * another task until the first one wakes up.
+ */
+ if (dl_task(p))
+ tracing_dl = 1;
+ else
+ tracing_dl = 0;
+
wakeup_task = p;
get_task_struct(wakeup_task);
@@ -597,16 +619,25 @@ static int __wakeup_tracer_init(struct trace_array *tr)
static int wakeup_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 0;
return __wakeup_tracer_init(tr);
}
static int wakeup_rt_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 1;
return __wakeup_tracer_init(tr);
}
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+ wakeup_dl = 1;
+ wakeup_rt = 0;
+ return __wakeup_tracer_init(tr);
+}
+
static void wakeup_tracer_reset(struct trace_array *tr)
{
int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
@@ -674,6 +705,28 @@ static struct tracer wakeup_rt_tracer __read_mostly =
.use_max_tr = true,
};
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+ .name = "wakeup_dl",
+ .init = wakeup_dl_tracer_init,
+ .reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
+ .wait_pipe = poll_wait_pipe,
+ .print_max = true,
+ .print_header = wakeup_print_header,
+ .print_line = wakeup_print_line,
+ .flags = &tracer_flags,
+ .set_flag = wakeup_set_flag,
+ .flag_changed = wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_wakeup,
+#endif
+ .open = wakeup_trace_open,
+ .close = wakeup_trace_close,
+ .use_max_tr = true,
+};
+
__init static int init_wakeup_tracer(void)
{
int ret;
@@ -686,6 +739,10 @@ __init static int init_wakeup_tracer(void)
if (ret)
return ret;
+ ret = register_tracer(&wakeup_dl_tracer);
+ if (ret)
+ return ret;
+
return 0;
}
core_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index a7329b7902f8..e98fca60974f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1022,11 +1022,16 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
#ifdef CONFIG_SCHED_TRACER
static int trace_wakeup_test_thread(void *data)
{
- /* Make this a RT thread, doesn't need to be too high */
- static const struct sched_param param = { .sched_priority = 5 };
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
+ };
struct completion *x = data;
- sched_setscheduler(current, SCHED_FIFO, &param);
+ sched_setattr(current, &attr);
/* Make it know we have a new prio */
complete(x);
@@ -1040,8 +1045,8 @@ static int trace_wakeup_test_thread(void *data)
/* we are awake, now wait to disappear */
while (!kthread_should_stop()) {
/*
- * This is an RT task, do short sleeps to let
- * others run.
+ * This will likely be the system top priority
+ * task, do short sleeps to let others run.
*/
msleep(100);
}
@@ -1054,21 +1059,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
{
unsigned long save_max = tracing_max_latency;
struct task_struct *p;
- struct completion isrt;
+ struct completion is_ready;
unsigned long count;
int ret;
- init_completion(&isrt);
+ init_completion(&is_ready);
- /* create a high prio thread */
- p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+ /* create a -deadline thread */
+ p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
if (IS_ERR(p)) {
printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
return -1;
}
- /* make sure the thread is running at an RT prio */
- wait_for_completion(&isrt);
+ /* make sure the thread is running at -deadline policy */
+ wait_for_completion(&is_ready);
/* start the tracing */
ret = tracer_init(trace, tr);
@@ -1082,19 +1087,19 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
while (p->on_rq) {
/*
- * Sleep to make sure the RT thread is asleep too.
+ * Sleep to make sure the -deadline thread is asleep too.
* On virtual machines we can't rely on timings,
* but we want to make sure this test still works.
*/
msleep(100);
}
- init_completion(&isrt);
+ init_completion(&is_ready);
wake_up_process(p);
/* Wait for the task to wake up */
- wait_for_completion(&isrt);
+ wait_for_completion(&is_ready);
/* stop the tracing. */
tracing_stop();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b20428c5efe2..e6be585cf06a 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -382,7 +382,7 @@ static const struct file_operations stack_trace_filter_fops = {
.open = stack_trace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 847f88a6194b..7af67360b330 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -43,46 +43,15 @@ static DEFINE_MUTEX(all_stat_sessions_mutex);
/* The root directory for all stat files */
static struct dentry *stat_dir;
-/*
- * Iterate through the rbtree using a post order traversal path
- * to release the next node.
- * It won't necessary release one at each iteration
- * but it will at least advance closer to the next one
- * to be released.
- */
-static struct rb_node *release_next(struct tracer_stat *ts,
- struct rb_node *node)
+static void __reset_stat_session(struct stat_session *session)
{
- struct stat_node *snode;
- struct rb_node *parent = rb_parent(node);
-
- if (node->rb_left)
- return node->rb_left;
- else if (node->rb_right)
- return node->rb_right;
- else {
- if (!parent)
- ;
- else if (parent->rb_left == node)
- parent->rb_left = NULL;
- else
- parent->rb_right = NULL;
+ struct stat_node *snode, *n;
- snode = container_of(node, struct stat_node, node);
- if (ts->stat_release)
- ts->stat_release(snode->stat);
+ rbtree_postorder_for_each_entry_safe(snode, n, &session->stat_root, node) {
+ if (session->ts->stat_release)
+ session->ts->stat_release(snode->stat);
kfree(snode);
-
- return parent;
}
-}
-
-static void __reset_stat_session(struct stat_session *session)
-{
- struct rb_node *node = session->stat_root.rb_node;
-
- while (node)
- node = release_next(session->ts, node);
session->stat_root = RB_ROOT;
}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 559329d9bd2f..759d5e004517 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -302,6 +302,7 @@ static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
{
struct trace_array *tr = data;
+ struct ftrace_event_file *ftrace_file;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -314,7 +315,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
+
+ /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
+ ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
+ if (!ftrace_file)
+ return;
+
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -336,15 +343,14 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
- if (!filter_current_check_discard(buffer, sys_data->enter_event,
- entry, event))
- trace_current_buffer_unlock_commit(buffer, event,
- irq_flags, pc);
+ event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+ irq_flags, pc);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
{
struct trace_array *tr = data;
+ struct ftrace_event_file *ftrace_file;
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
@@ -356,7 +362,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0)
return;
- if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
+
+ /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
+ ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
+ if (!ftrace_file)
+ return;
+
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -377,10 +389,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
entry->nr = syscall_nr;
entry->ret = syscall_get_return_value(current, regs);
- if (!filter_current_check_discard(buffer, sys_data->exit_event,
- entry, event))
- trace_current_buffer_unlock_commit(buffer, event,
- irq_flags, pc);
+ event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+ irq_flags, pc);
}
static int reg_event_syscall_enter(struct ftrace_event_file *file,
@@ -397,7 +407,7 @@ static int reg_event_syscall_enter(struct ftrace_event_file *file,
if (!tr->sys_refcount_enter)
ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
if (!ret) {
- set_bit(num, tr->enabled_enter_syscalls);
+ rcu_assign_pointer(tr->enter_syscall_files[num], file);
tr->sys_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
@@ -415,7 +425,7 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
return;
mutex_lock(&syscall_trace_lock);
tr->sys_refcount_enter--;
- clear_bit(num, tr->enabled_enter_syscalls);
+ rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
if (!tr->sys_refcount_enter)
unregister_trace_sys_enter(ftrace_syscall_enter, tr);
mutex_unlock(&syscall_trace_lock);
@@ -435,7 +445,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,
if (!tr->sys_refcount_exit)
ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
if (!ret) {
- set_bit(num, tr->enabled_exit_syscalls);
+ rcu_assign_pointer(tr->exit_syscall_files[num], file);
tr->sys_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
@@ -453,7 +463,7 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
return;
mutex_lock(&syscall_trace_lock);
tr->sys_refcount_exit--;
- clear_bit(num, tr->enabled_exit_syscalls);
+ rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
if (!tr->sys_refcount_exit)
unregister_trace_sys_exit(ftrace_syscall_exit, tr);
mutex_unlock(&syscall_trace_lock);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 272261b5f94f..79e52d93860b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -51,22 +51,17 @@ struct trace_uprobe_filter {
*/
struct trace_uprobe {
struct list_head list;
- struct ftrace_event_class class;
- struct ftrace_event_call call;
struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
struct inode *inode;
char *filename;
unsigned long offset;
unsigned long nhit;
- unsigned int flags; /* For TP_FLAG_* */
- ssize_t size; /* trace entry size */
- unsigned int nr_args;
- struct probe_arg args[];
+ struct trace_probe tp;
};
-#define SIZEOF_TRACE_UPROBE(n) \
- (offsetof(struct trace_uprobe, args) + \
+#define SIZEOF_TRACE_UPROBE(n) \
+ (offsetof(struct trace_uprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
static int register_uprobe_event(struct trace_uprobe *tu);
@@ -75,10 +70,151 @@ static int unregister_uprobe_event(struct trace_uprobe *tu);
static DEFINE_MUTEX(uprobe_lock);
static LIST_HEAD(uprobe_list);
+struct uprobe_dispatch_data {
+ struct trace_uprobe *tu;
+ unsigned long bp_addr;
+};
+
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs);
+#ifdef CONFIG_STACK_GROWSUP
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+ return addr - (n * sizeof(long));
+}
+#else
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+ return addr + (n * sizeof(long));
+}
+#endif
+
+static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long ret;
+ unsigned long addr = user_stack_pointer(regs);
+
+ addr = adjust_stack_addr(addr, n);
+
+ if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret)))
+ return 0;
+
+ return ret;
+}
+
+/*
+ * Uprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)get_user_stack_nth(regs, \
+ ((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ void __user *vaddr = (void __force __user *) addr; \
+ \
+ if (copy_from_user(&retval, vaddr, sizeof(type))) \
+ *(type *)dest = 0; \
+ else \
+ *(type *) dest = retval; \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ long ret;
+ u32 rloc = *(u32 *)dest;
+ int maxlen = get_rloc_len(rloc);
+ u8 *dst = get_rloc_data(dest);
+ void __user *src = (void __force __user *) addr;
+
+ if (!maxlen)
+ return;
+
+ ret = strncpy_from_user(dst, src, maxlen);
+
+ if (ret < 0) { /* Failed to fetch string */
+ ((u8 *)get_rloc_data(dest))[0] = '\0';
+ *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc));
+ } else {
+ *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc));
+ }
+}
+
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ int len;
+ void __user *vaddr = (void __force __user *) addr;
+
+ len = strnlen_user(vaddr, MAX_STRING_SIZE);
+
+ if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */
+ *(u32 *)dest = 0;
+ else
+ *(u32 *)dest = len;
+}
+
+static unsigned long translate_user_vaddr(void *file_offset)
+{
+ unsigned long base_addr;
+ struct uprobe_dispatch_data *udd;
+
+ udd = (void *) current->utask->vaddr;
+
+ base_addr = udd->bp_addr - udd->tu->offset;
+ return base_addr + (unsigned long)file_offset;
+}
+
+#define DEFINE_FETCH_file_offset(type) \
+static __kprobes void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ void *vaddr = (void *)translate_user_vaddr(offset); \
+ \
+ FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \
+}
+DEFINE_BASIC_FETCH_FUNCS(file_offset)
+DEFINE_FETCH_file_offset(string)
+DEFINE_FETCH_file_offset(string_size)
+
+/* Fetch type information table */
+const struct fetch_type uprobes_fetch_type_table[] = {
+ /* Special types */
+ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+ sizeof(u32), 1, "__data_loc char[]"),
+ [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+ string_size, sizeof(u32), 0, "u32"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+ ASSIGN_FETCH_TYPE_END
+};
+
static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
rwlock_init(&filter->rwlock);
@@ -114,13 +250,13 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (!tu)
return ERR_PTR(-ENOMEM);
- tu->call.class = &tu->class;
- tu->call.name = kstrdup(event, GFP_KERNEL);
- if (!tu->call.name)
+ tu->tp.call.class = &tu->tp.class;
+ tu->tp.call.name = kstrdup(event, GFP_KERNEL);
+ if (!tu->tp.call.name)
goto error;
- tu->class.system = kstrdup(group, GFP_KERNEL);
- if (!tu->class.system)
+ tu->tp.class.system = kstrdup(group, GFP_KERNEL);
+ if (!tu->tp.class.system)
goto error;
INIT_LIST_HEAD(&tu->list);
@@ -128,10 +264,11 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (is_ret)
tu->consumer.ret_handler = uretprobe_dispatcher;
init_trace_uprobe_filter(&tu->filter);
+ tu->tp.call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
return tu;
error:
- kfree(tu->call.name);
+ kfree(tu->tp.call.name);
kfree(tu);
return ERR_PTR(-ENOMEM);
@@ -141,12 +278,12 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
{
int i;
- for (i = 0; i < tu->nr_args; i++)
- traceprobe_free_probe_arg(&tu->args[i]);
+ for (i = 0; i < tu->tp.nr_args; i++)
+ traceprobe_free_probe_arg(&tu->tp.args[i]);
iput(tu->inode);
- kfree(tu->call.class->system);
- kfree(tu->call.name);
+ kfree(tu->tp.call.class->system);
+ kfree(tu->tp.call.name);
kfree(tu->filename);
kfree(tu);
}
@@ -156,8 +293,8 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou
struct trace_uprobe *tu;
list_for_each_entry(tu, &uprobe_list, list)
- if (strcmp(tu->call.name, event) == 0 &&
- strcmp(tu->call.class->system, group) == 0)
+ if (strcmp(tu->tp.call.name, event) == 0 &&
+ strcmp(tu->tp.call.class->system, group) == 0)
return tu;
return NULL;
@@ -180,16 +317,16 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
/* Register a trace_uprobe and probe_event */
static int register_trace_uprobe(struct trace_uprobe *tu)
{
- struct trace_uprobe *old_tp;
+ struct trace_uprobe *old_tu;
int ret;
mutex_lock(&uprobe_lock);
/* register as an event */
- old_tp = find_probe_event(tu->call.name, tu->call.class->system);
- if (old_tp) {
+ old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system);
+ if (old_tu) {
/* delete old event */
- ret = unregister_trace_uprobe(old_tp);
+ ret = unregister_trace_uprobe(old_tu);
if (ret)
goto end;
}
@@ -210,7 +347,7 @@ end:
/*
* Argument syntax:
- * - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS]
+ * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
*
* - Remove uprobe: -:[GRP/]EVENT
*/
@@ -359,34 +496,36 @@ static int create_trace_uprobe(int argc, char **argv)
/* parse arguments */
ret = 0;
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
/* Increment count for freeing args in error case */
- tu->nr_args++;
+ tu->tp.nr_args++;
/* Parse argument name */
arg = strchr(argv[i], '=');
if (arg) {
*arg++ = '\0';
- tu->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ parg->name = kstrdup(argv[i], GFP_KERNEL);
} else {
arg = argv[i];
/* If argument name is omitted, set "argN" */
snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
- tu->args[i].name = kstrdup(buf, GFP_KERNEL);
+ parg->name = kstrdup(buf, GFP_KERNEL);
}
- if (!tu->args[i].name) {
+ if (!parg->name) {
pr_info("Failed to allocate argument[%d] name.\n", i);
ret = -ENOMEM;
goto error;
}
- if (!is_good_name(tu->args[i].name)) {
- pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name);
+ if (!is_good_name(parg->name)) {
+ pr_info("Invalid argument[%d] name: %s\n", i, parg->name);
ret = -EINVAL;
goto error;
}
- if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) {
+ if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) {
pr_info("Argument[%d] name '%s' conflicts with "
"another field.\n", i, argv[i]);
ret = -EINVAL;
@@ -394,7 +533,8 @@ static int create_trace_uprobe(int argc, char **argv)
}
/* Parse fetch argument */
- ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false);
+ ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg,
+ is_return, false);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -458,11 +598,11 @@ static int probes_seq_show(struct seq_file *m, void *v)
char c = is_ret_probe(tu) ? 'r' : 'p';
int i;
- seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name);
+ seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name);
seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
- for (i = 0; i < tu->nr_args; i++)
- seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm);
+ for (i = 0; i < tu->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
seq_printf(m, "\n");
return 0;
@@ -508,7 +648,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
{
struct trace_uprobe *tu = v;
- seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit);
+ seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit);
return 0;
}
@@ -532,21 +672,117 @@ static const struct file_operations uprobe_profile_ops = {
.release = seq_release,
};
+struct uprobe_cpu_buffer {
+ struct mutex mutex;
+ void *buf;
+};
+static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
+static int uprobe_buffer_refcnt;
+
+static int uprobe_buffer_init(void)
+{
+ int cpu, err_cpu;
+
+ uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer);
+ if (uprobe_cpu_buffer == NULL)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct page *p = alloc_pages_node(cpu_to_node(cpu),
+ GFP_KERNEL, 0);
+ if (p == NULL) {
+ err_cpu = cpu;
+ goto err;
+ }
+ per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p);
+ mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex);
+ }
+
+ return 0;
+
+err:
+ for_each_possible_cpu(cpu) {
+ if (cpu == err_cpu)
+ break;
+ free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf);
+ }
+
+ free_percpu(uprobe_cpu_buffer);
+ return -ENOMEM;
+}
+
+static int uprobe_buffer_enable(void)
+{
+ int ret = 0;
+
+ BUG_ON(!mutex_is_locked(&event_mutex));
+
+ if (uprobe_buffer_refcnt++ == 0) {
+ ret = uprobe_buffer_init();
+ if (ret < 0)
+ uprobe_buffer_refcnt--;
+ }
+
+ return ret;
+}
+
+static void uprobe_buffer_disable(void)
+{
+ BUG_ON(!mutex_is_locked(&event_mutex));
+
+ if (--uprobe_buffer_refcnt == 0) {
+ free_percpu(uprobe_cpu_buffer);
+ uprobe_cpu_buffer = NULL;
+ }
+}
+
+static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
+{
+ struct uprobe_cpu_buffer *ucb;
+ int cpu;
+
+ cpu = raw_smp_processor_id();
+ ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu);
+
+ /*
+ * Use per-cpu buffers for fastest access, but we might migrate
+ * so the mutex makes sure we have sole access to it.
+ */
+ mutex_lock(&ucb->mutex);
+
+ return ucb;
+}
+
+static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
+{
+ mutex_unlock(&ucb->mutex);
+}
+
static void uprobe_trace_print(struct trace_uprobe *tu,
unsigned long func, struct pt_regs *regs)
{
struct uprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
+ struct uprobe_cpu_buffer *ucb;
void *data;
- int size, i;
- struct ftrace_event_call *call = &tu->call;
+ int size, dsize, esize;
+ struct ftrace_event_call *call = &tu->tp.call;
+
+ dsize = __get_data_size(&tu->tp, regs);
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
- size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+ if (WARN_ON_ONCE(!uprobe_cpu_buffer || tu->tp.size + dsize > PAGE_SIZE))
+ return;
+
+ ucb = uprobe_buffer_get();
+ store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
+ size = esize + tu->tp.size + dsize;
event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
- size + tu->size, 0, 0);
+ size, 0, 0);
if (!event)
- return;
+ goto out;
entry = ring_buffer_event_data(event);
if (is_ret_probe(tu)) {
@@ -558,11 +794,13 @@ static void uprobe_trace_print(struct trace_uprobe *tu,
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++)
- call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+ memcpy(data, ucb->buf, tu->tp.size + dsize);
- if (!filter_current_check_discard(buffer, call, entry, event))
+ if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, 0, 0);
+
+out:
+ uprobe_buffer_put(ucb);
}
/* uprobe handler */
@@ -590,23 +828,24 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
int i;
entry = (struct uprobe_trace_entry_head *)iter->ent;
- tu = container_of(event, struct trace_uprobe, call.event);
+ tu = container_of(event, struct trace_uprobe, tp.call.event);
if (is_ret_probe(tu)) {
- if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name,
+ if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name,
entry->vaddr[1], entry->vaddr[0]))
goto partial;
data = DATAOF_TRACE_ENTRY(entry, true);
} else {
- if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name,
+ if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name,
entry->vaddr[0]))
goto partial;
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++) {
- if (!tu->args[i].type->print(s, tu->args[i].name,
- data + tu->args[i].offset, entry))
+ for (i = 0; i < tu->tp.nr_args; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
+ if (!parg->type->print(s, parg->name, data + parg->offset, entry))
goto partial;
}
@@ -617,11 +856,6 @@ partial:
return TRACE_TYPE_PARTIAL_LINE;
}
-static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
-{
- return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
-}
-
typedef bool (*filter_func_t)(struct uprobe_consumer *self,
enum uprobe_filter_ctx ctx,
struct mm_struct *mm);
@@ -631,29 +865,35 @@ probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
{
int ret = 0;
- if (is_trace_uprobe_enabled(tu))
+ if (trace_probe_is_enabled(&tu->tp))
return -EINTR;
+ ret = uprobe_buffer_enable();
+ if (ret < 0)
+ return ret;
+
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
- tu->flags |= flag;
+ tu->tp.flags |= flag;
tu->consumer.filter = filter;
ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
if (ret)
- tu->flags &= ~flag;
+ tu->tp.flags &= ~flag;
return ret;
}
static void probe_event_disable(struct trace_uprobe *tu, int flag)
{
- if (!is_trace_uprobe_enabled(tu))
+ if (!trace_probe_is_enabled(&tu->tp))
return;
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
- tu->flags &= ~flag;
+ tu->tp.flags &= ~flag;
+
+ uprobe_buffer_disable();
}
static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
@@ -671,12 +911,12 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
size = SIZEOF_TRACE_ENTRY(false);
}
/* Set argument names as fields */
- for (i = 0; i < tu->nr_args; i++) {
- ret = trace_define_field(event_call, tu->args[i].type->fmttype,
- tu->args[i].name,
- size + tu->args[i].offset,
- tu->args[i].type->size,
- tu->args[i].type->is_signed,
+ for (i = 0; i < tu->tp.nr_args; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name, size + parg->offset,
+ parg->type->size, parg->type->is_signed,
FILTER_OTHER);
if (ret)
@@ -685,59 +925,6 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
return 0;
}
-#define LEN_OR_ZERO (len ? len - pos : 0)
-static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
-{
- const char *fmt, *arg;
- int i;
- int pos = 0;
-
- if (is_ret_probe(tu)) {
- fmt = "(%lx <- %lx)";
- arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
- } else {
- fmt = "(%lx)";
- arg = "REC->" FIELD_STRING_IP;
- }
-
- /* When len=0, we just calculate the needed length */
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
- for (i = 0; i < tu->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tu->args[i].name, tu->args[i].type->fmt);
- }
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
- for (i = 0; i < tu->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tu->args[i].name);
- }
-
- return pos; /* return the length of print_fmt */
-}
-#undef LEN_OR_ZERO
-
-static int set_print_fmt(struct trace_uprobe *tu)
-{
- char *print_fmt;
- int len;
-
- /* First: called with 0 length to calculate the needed length */
- len = __set_print_fmt(tu, NULL, 0);
- print_fmt = kmalloc(len + 1, GFP_KERNEL);
- if (!print_fmt)
- return -ENOMEM;
-
- /* Second: actually write the @print_fmt */
- __set_print_fmt(tu, print_fmt, len + 1);
- tu->call.print_fmt = print_fmt;
-
- return 0;
-}
-
#ifdef CONFIG_PERF_EVENTS
static bool
__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
@@ -830,14 +1017,27 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
static void uprobe_perf_print(struct trace_uprobe *tu,
unsigned long func, struct pt_regs *regs)
{
- struct ftrace_event_call *call = &tu->call;
+ struct ftrace_event_call *call = &tu->tp.call;
struct uprobe_trace_entry_head *entry;
struct hlist_head *head;
+ struct uprobe_cpu_buffer *ucb;
void *data;
- int size, rctx, i;
+ int size, dsize, esize;
+ int rctx;
- size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
- size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+ dsize = __get_data_size(&tu->tp, regs);
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+ if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+ return;
+
+ size = esize + tu->tp.size + dsize;
+ size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
+ return;
+
+ ucb = uprobe_buffer_get();
+ store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
preempt_disable();
head = this_cpu_ptr(call->perf_events);
@@ -857,12 +1057,18 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++)
- call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+ memcpy(data, ucb->buf, tu->tp.size + dsize);
+
+ if (size - esize > tu->tp.size + dsize) {
+ int len = tu->tp.size + dsize;
+
+ memset(data + len, 0, size - esize - len);
+ }
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
out:
preempt_enable();
+ uprobe_buffer_put(ucb);
}
/* uprobe profile handler */
@@ -920,16 +1126,22 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
{
struct trace_uprobe *tu;
+ struct uprobe_dispatch_data udd;
int ret = 0;
tu = container_of(con, struct trace_uprobe, consumer);
tu->nhit++;
- if (tu->flags & TP_FLAG_TRACE)
+ udd.tu = tu;
+ udd.bp_addr = instruction_pointer(regs);
+
+ current->utask->vaddr = (unsigned long) &udd;
+
+ if (tu->tp.flags & TP_FLAG_TRACE)
ret |= uprobe_trace_func(tu, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tu->flags & TP_FLAG_PROFILE)
+ if (tu->tp.flags & TP_FLAG_PROFILE)
ret |= uprobe_perf_func(tu, regs);
#endif
return ret;
@@ -939,14 +1151,20 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs)
{
struct trace_uprobe *tu;
+ struct uprobe_dispatch_data udd;
tu = container_of(con, struct trace_uprobe, consumer);
- if (tu->flags & TP_FLAG_TRACE)
+ udd.tu = tu;
+ udd.bp_addr = func;
+
+ current->utask->vaddr = (unsigned long) &udd;
+
+ if (tu->tp.flags & TP_FLAG_TRACE)
uretprobe_trace_func(tu, func, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tu->flags & TP_FLAG_PROFILE)
+ if (tu->tp.flags & TP_FLAG_PROFILE)
uretprobe_perf_func(tu, func, regs);
#endif
return 0;
@@ -958,7 +1176,7 @@ static struct trace_event_functions uprobe_funcs = {
static int register_uprobe_event(struct trace_uprobe *tu)
{
- struct ftrace_event_call *call = &tu->call;
+ struct ftrace_event_call *call = &tu->tp.call;
int ret;
/* Initialize ftrace_event_call */
@@ -966,7 +1184,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
call->event.funcs = &uprobe_funcs;
call->class->define_fields = uprobe_event_define_fields;
- if (set_print_fmt(tu) < 0)
+ if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
return -ENOMEM;
ret = register_ftrace_event(&call->event);
@@ -993,11 +1211,11 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
int ret;
/* tu->event is unregistered in trace_remove_event_call() */
- ret = trace_remove_event_call(&tu->call);
+ ret = trace_remove_event_call(&tu->tp.call);
if (ret)
return ret;
- kfree(tu->call.print_fmt);
- tu->call.print_fmt = NULL;
+ kfree(tu->tp.call.print_fmt);
+ tu->tp.call.print_fmt = NULL;
return 0;
}
diff --git a/kernel/up.c b/kernel/up.c
index 630d72bf7e41..509403e3fbc6 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,6 +22,17 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
}
EXPORT_SYMBOL(smp_call_function_single);
+void __smp_call_function_single(int cpu, struct call_single_data *csd,
+ int wait)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ csd->func(csd->info);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__smp_call_function_single);
+
int on_each_cpu(smp_call_func_t func, void *info, int wait)
{
unsigned long flags;
diff --git a/kernel/user.c b/kernel/user.c
index 5bbb91988e69..c006131beb77 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,10 @@ struct user_namespace init_user_ns = {
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
.proc_inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ .persistent_keyring_register_sem =
+ __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
+#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 13fb1134ba58..240fb62cf394 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -101,6 +101,9 @@ int create_user_ns(struct cred *new)
set_cred_user_ns(new, ns);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ init_rwsem(&ns->persistent_keyring_register_sem);
+#endif
return 0;
}
@@ -130,6 +133,9 @@ void free_user_ns(struct user_namespace *ns)
do {
parent = ns->parent;
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ key_put(ns->persistent_keyring_register);
+#endif
proc_free_inum(ns->proc_inum);
kmem_cache_free(user_ns_cachep, ns);
ns = parent;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 987293d03ebc..82ef9f3b7473 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -305,6 +305,9 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
/* I: attributes used when instantiating standard unbound pools on demand */
static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -518,14 +521,21 @@ static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif
-/* allocate ID and assign it to @pool */
+/**
+ * worker_pool_assign_id - allocate ID and assing it to @pool
+ * @pool: the pool pointer of interest
+ *
+ * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned
+ * successfully, -errno on failure.
+ */
static int worker_pool_assign_id(struct worker_pool *pool)
{
int ret;
lockdep_assert_held(&wq_pool_mutex);
- ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+ ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE,
+ GFP_KERNEL);
if (ret >= 0) {
pool->id = ret;
return 0;
@@ -1320,7 +1330,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
debug_work_activate(work);
- /* if dying, only works from the same workqueue are allowed */
+ /* if draining, only works from the same workqueue are allowed */
if (unlikely(wq->flags & __WQ_DRAINING) &&
WARN_ON_ONCE(!is_chained_work(wq)))
return;
@@ -1736,16 +1746,17 @@ static struct worker *create_worker(struct worker_pool *pool)
if (IS_ERR(worker->task))
goto fail;
+ set_user_nice(worker->task, pool->attrs->nice);
+
+ /* prevent userland from meddling with cpumask of workqueue workers */
+ worker->task->flags |= PF_NO_SETAFFINITY;
+
/*
* set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
* online CPUs. It'll be re-applied when any of the CPUs come up.
*/
- set_user_nice(worker->task, pool->attrs->nice);
set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
- /* prevent userland from meddling with cpumask of workqueue workers */
- worker->task->flags |= PF_NO_SETAFFINITY;
-
/*
* The caller is responsible for ensuring %POOL_DISASSOCIATED
* remains stable across this function. See the comments above the
@@ -2840,19 +2851,6 @@ already_gone:
return false;
}
-static bool __flush_work(struct work_struct *work)
-{
- struct wq_barrier barr;
-
- if (start_flush_work(work, &barr)) {
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- return true;
- } else {
- return false;
- }
-}
-
/**
* flush_work - wait for a work to finish executing the last queueing instance
* @work: the work to flush
@@ -2866,10 +2864,18 @@ static bool __flush_work(struct work_struct *work)
*/
bool flush_work(struct work_struct *work)
{
+ struct wq_barrier barr;
+
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
- return __flush_work(work);
+ if (start_flush_work(work, &barr)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else {
+ return false;
+ }
}
EXPORT_SYMBOL_GPL(flush_work);
@@ -4106,7 +4112,7 @@ out_unlock:
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
bool highpri = wq->flags & WQ_HIGHPRI;
- int cpu;
+ int cpu, ret;
if (!(wq->flags & WQ_UNBOUND)) {
wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4126,6 +4132,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
mutex_unlock(&wq->mutex);
}
return 0;
+ } else if (wq->flags & __WQ_ORDERED) {
+ ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+ /* there should only be single pwq for ordering guarantee */
+ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+ wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+ "ordering guarantee broken for workqueue %s\n", wq->name);
+ return ret;
} else {
return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
}
@@ -4776,6 +4789,7 @@ static int workqueue_cpu_down_callback(struct notifier_block *nfb,
/* wait for per-cpu unbinding to finish */
flush_work(&unbind_work);
+ destroy_work_on_stack(&unbind_work);
break;
}
return NOTIFY_OK;
@@ -4814,14 +4828,8 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
schedule_work_on(cpu, &wfc.work);
-
- /*
- * The work item is on-stack and can't lead to deadlock through
- * flushing. Use __flush_work() to avoid spurious lockdep warnings
- * when work_on_cpu()s are nested.
- */
- __flush_work(&wfc.work);
-
+ flush_work(&wfc.work);
+ destroy_work_on_stack(&wfc.work);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
@@ -5009,10 +5017,6 @@ static int __init init_workqueues(void)
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int i, cpu;
- /* make sure we have enough bits for OFFQ pool ID */
- BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) <
- WORK_CPU_END * NR_STD_WORKER_POOLS);
-
WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
@@ -5051,13 +5055,23 @@ static int __init init_workqueues(void)
}
}
- /* create default unbound wq attrs */
+ /* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
+
+ /*
+ * An ordered wq should have only one pwq as ordering is
+ * guaranteed by max_active which is enforced by pwqs.
+ * Turn off NUMA so that dfl_pwq is used for all nodes.
+ */
+ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+ attrs->nice = std_nice[i];
+ attrs->no_numa = true;
+ ordered_wq_attrs[i] = attrs;
}
system_wq = alloc_workqueue("events", 0, 0);