aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.locks202
-rw-r--r--kernel/Makefile8
-rw-r--r--kernel/acct.c3
-rw-r--r--kernel/audit.c18
-rw-r--r--kernel/audit_watch.c2
-rw-r--r--kernel/auditsc.c6
-rw-r--r--kernel/capability.c15
-rw-r--r--kernel/cgroup.c1130
-rw-r--r--kernel/cgroup_debug.c105
-rw-r--r--kernel/cgroup_freezer.c15
-rw-r--r--kernel/cpu.c23
-rw-r--r--kernel/cpuset.c111
-rw-r--r--kernel/cred.c19
-rw-r--r--kernel/exit.c185
-rw-r--r--kernel/fork.c69
-rw-r--r--kernel/futex.c220
-rw-r--r--kernel/gcov/Kconfig2
-rw-r--r--kernel/hrtimer.c225
-rw-r--r--kernel/hung_task.c6
-rw-r--r--kernel/hw_breakpoint.c453
-rw-r--r--kernel/irq/autoprobe.c20
-rw-r--r--kernel/irq/chip.c92
-rw-r--r--kernel/irq/handle.c23
-rw-r--r--kernel/irq/internals.h2
-rw-r--r--kernel/irq/manage.c52
-rw-r--r--kernel/irq/migration.c2
-rw-r--r--kernel/irq/numa_migrate.c8
-rw-r--r--kernel/irq/pm.c8
-rw-r--r--kernel/irq/proc.c44
-rw-r--r--kernel/irq/spurious.c32
-rw-r--r--kernel/itimer.c7
-rw-r--r--kernel/kallsyms.c1
-rw-r--r--kernel/kexec.c59
-rw-r--r--kernel/kgdb.c58
-rw-r--r--kernel/kmod.c21
-rw-r--r--kernel/kprobes.c76
-rw-r--r--kernel/ksysfs.c21
-rw-r--r--kernel/kthread.c23
-rw-r--r--kernel/lockdep.c69
-rw-r--r--kernel/module.c316
-rw-r--r--kernel/mutex-debug.c1
-rw-r--r--kernel/mutex-debug.h12
-rw-r--r--kernel/mutex.c4
-rw-r--r--kernel/notifier.c2
-rw-r--r--kernel/ns_cgroup.c16
-rw-r--r--kernel/panic.c3
-rw-r--r--kernel/params.c28
-rw-r--r--kernel/perf_event.c1114
-rw-r--r--kernel/pid.c12
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--kernel/pm_qos_params.c20
-rw-r--r--kernel/posix-cpu-timers.c5
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/console.c7
-rw-r--r--kernel/power/hibernate.c41
-rw-r--r--kernel/power/main.c1
-rw-r--r--kernel/power/process.c14
-rw-r--r--kernel/power/suspend_test.c5
-rw-r--r--kernel/power/swap.c147
-rw-r--r--kernel/power/swsusp.c130
-rw-r--r--kernel/printk.c7
-rw-r--r--kernel/ptrace.c11
-rw-r--r--kernel/rcupdate.c260
-rw-r--r--kernel/rcutiny.c282
-rw-r--r--kernel/rcutorture.c77
-rw-r--r--kernel/rcutree.c787
-rw-r--r--kernel/rcutree.h160
-rw-r--r--kernel/rcutree_plugin.h442
-rw-r--r--kernel/rcutree_trace.c26
-rw-r--r--kernel/relay.c4
-rw-r--r--kernel/res_counter.c3
-rw-r--r--kernel/resource.c26
-rw-r--r--kernel/rtmutex-debug.c4
-rw-r--r--kernel/rtmutex.c106
-rw-r--r--kernel/sched.c824
-rw-r--r--kernel/sched_clock.c4
-rw-r--r--kernel/sched_cpupri.c10
-rw-r--r--kernel/sched_cpupri.h2
-rw-r--r--kernel/sched_debug.c21
-rw-r--r--kernel/sched_fair.c268
-rw-r--r--kernel/sched_features.h5
-rw-r--r--kernel/sched_idletask.c6
-rw-r--r--kernel/sched_rt.c123
-rw-r--r--kernel/signal.c279
-rw-r--r--kernel/slow-work-debugfs.c227
-rw-r--r--kernel/slow-work.c531
-rw-r--r--kernel/slow-work.h72
-rw-r--r--kernel/smp.c98
-rw-r--r--kernel/softirq.c6
-rw-r--r--kernel/softlockup.c58
-rw-r--r--kernel/spinlock.c448
-rw-r--r--kernel/srcu.c74
-rw-r--r--kernel/sys.c80
-rw-r--r--kernel/sys_ni.c4
-rw-r--r--kernel/sysctl.c1029
-rw-r--r--kernel/sysctl_binary.c1507
-rw-r--r--kernel/sysctl_check.c1378
-rw-r--r--kernel/time.c31
-rw-r--r--kernel/time/Makefile2
-rw-r--r--kernel/time/clockevents.c27
-rw-r--r--kernel/time/clocksource.c109
-rw-r--r--kernel/time/tick-broadcast.c42
-rw-r--r--kernel/time/tick-common.c20
-rw-r--r--kernel/time/tick-internal.h1
-rw-r--r--kernel/time/tick-oneshot.c4
-rw-r--r--kernel/time/tick-sched.c150
-rw-r--r--kernel/time/timecompare.c8
-rw-r--r--kernel/time/timeconv.c127
-rw-r--r--kernel/time/timekeeping.c126
-rw-r--r--kernel/time/timer_list.c23
-rw-r--r--kernel/time/timer_stats.c20
-rw-r--r--kernel/trace/Kconfig38
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/blktrace.c39
-rw-r--r--kernel/trace/ftrace.c437
-rw-r--r--kernel/trace/kmemtrace.c2
-rw-r--r--kernel/trace/ring_buffer.c54
-rw-r--r--kernel/trace/ring_buffer_benchmark.c85
-rw-r--r--kernel/trace/trace.c153
-rw-r--r--kernel/trace/trace.h84
-rw-r--r--kernel/trace/trace_branch.c8
-rw-r--r--kernel/trace/trace_clock.c16
-rw-r--r--kernel/trace/trace_entries.h16
-rw-r--r--kernel/trace/trace_event_profile.c50
-rw-r--r--kernel/trace/trace_events.c198
-rw-r--r--kernel/trace/trace_events_filter.c426
-rw-r--r--kernel/trace/trace_export.c43
-rw-r--r--kernel/trace/trace_functions_graph.c169
-rw-r--r--kernel/trace/trace_hw_branches.c59
-rw-r--r--kernel/trace/trace_kprobe.c1542
-rw-r--r--kernel/trace/trace_ksym.c551
-rw-r--r--kernel/trace/trace_output.c98
-rw-r--r--kernel/trace/trace_sched_wakeup.c16
-rw-r--r--kernel/trace/trace_selftest.c59
-rw-r--r--kernel/trace/trace_stack.c20
-rw-r--r--kernel/trace/trace_syscalls.c231
-rw-r--r--kernel/uid16.c1
-rw-r--r--kernel/user-return-notifier.c44
-rw-r--r--kernel/user.c2
-rw-r--r--kernel/utsname_sysctl.c35
-rw-r--r--kernel/workqueue.c166
141 files changed, 13274 insertions, 6626 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
new file mode 100644
index 00000000000..88c92fb4461
--- /dev/null
+++ b/kernel/Kconfig.locks
@@ -0,0 +1,202 @@
+#
+# The ARCH_INLINE foo is necessary because select ignores "depends on"
+#
+config ARCH_INLINE_SPIN_TRYLOCK
+ bool
+
+config ARCH_INLINE_SPIN_TRYLOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_LOCK
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_SPIN_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+ bool
+
+
+config ARCH_INLINE_READ_TRYLOCK
+ bool
+
+config ARCH_INLINE_READ_LOCK
+ bool
+
+config ARCH_INLINE_READ_LOCK_BH
+ bool
+
+config ARCH_INLINE_READ_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_READ_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_READ_UNLOCK
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+ bool
+
+
+config ARCH_INLINE_WRITE_TRYLOCK
+ bool
+
+config ARCH_INLINE_WRITE_LOCK
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_BH
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQ
+ bool
+
+config ARCH_INLINE_WRITE_LOCK_IRQSAVE
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_BH
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQ
+ bool
+
+config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+ bool
+
+#
+# lock_* functions are inlined when:
+# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
+#
+# trylock_* functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+# unlock and unlock_irq functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+# or
+# - DEBUG_SPINLOCK=n and PREEMPT=n
+#
+# unlock_bh and unlock_irqrestore functions are inlined when:
+# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
+#
+
+config INLINE_SPIN_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK
+
+config INLINE_SPIN_TRYLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH
+
+config INLINE_SPIN_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
+
+config INLINE_SPIN_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_BH
+
+config INLINE_SPIN_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_IRQ
+
+config INLINE_SPIN_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_SPIN_LOCK_IRQSAVE
+
+config INLINE_SPIN_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK)
+
+config INLINE_SPIN_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH
+
+config INLINE_SPIN_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH)
+
+config INLINE_SPIN_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
+
+
+config INLINE_READ_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK
+
+config INLINE_READ_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
+
+config INLINE_READ_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_BH
+
+config INLINE_READ_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_IRQ
+
+config INLINE_READ_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_READ_LOCK_IRQSAVE
+
+config INLINE_READ_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK)
+
+config INLINE_READ_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH
+
+config INLINE_READ_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH)
+
+config INLINE_READ_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE
+
+
+config INLINE_WRITE_TRYLOCK
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK
+
+config INLINE_WRITE_LOCK
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
+
+config INLINE_WRITE_LOCK_BH
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_BH
+
+config INLINE_WRITE_LOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_IRQ
+
+config INLINE_WRITE_LOCK_IRQSAVE
+ def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \
+ ARCH_INLINE_WRITE_LOCK_IRQSAVE
+
+config INLINE_WRITE_UNLOCK
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK)
+
+config INLINE_WRITE_UNLOCK_BH
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH
+
+config INLINE_WRITE_UNLOCK_IRQ
+ def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH)
+
+config INLINE_WRITE_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+
+config MUTEX_SPIN_ON_OWNER
+ def_bool SMP && !DEBUG_MUTEXES && !HAVE_DEFAULT_NO_SPIN_MUTEXES
diff --git a/kernel/Makefile b/kernel/Makefile
index 187c89b4783..864ff75d65f 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -4,7 +4,7 @@
obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
cpu.o exit.o itimer.o time.o softirq.o resource.o \
- sysctl.o capability.o ptrace.o timer.o user.o \
+ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
signal.o sys.o kmod.o workqueue.o pid.o \
rcupdate.o extable.o params.o posix-timers.o \
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
CFLAGS_REMOVE_rtmutex-debug.o = -pg
CFLAGS_REMOVE_cgroup-debug.o = -pg
CFLAGS_REMOVE_sched_clock.o = -pg
+CFLAGS_REMOVE_perf_event.o = -pg
endif
obj-$(CONFIG_FREEZER) += freezer.o
@@ -58,7 +59,6 @@ obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_CGROUPS) += cgroup.o
-obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
obj-$(CONFIG_CPUSETS) += cpuset.o
obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
@@ -83,6 +83,7 @@ obj-$(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-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -95,7 +96,10 @@ obj-$(CONFIG_X86_DS) += trace/
obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/acct.c b/kernel/acct.c
index 9a4715a2f6b..a6605ca921b 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -536,7 +536,8 @@ static void do_acct_process(struct bsd_acct_struct *acct,
do_div(elapsed, AHZ);
ac.ac_btime = get_seconds() - elapsed;
/* we really need to bite the bullet and change layout */
- current_uid_gid(&ac.ac_uid, &ac.ac_gid);
+ ac.ac_uid = orig_cred->uid;
+ ac.ac_gid = orig_cred->gid;
#if ACCT_VERSION==2
ac.ac_ahz = AHZ;
#endif
diff --git a/kernel/audit.c b/kernel/audit.c
index defc2e6f1e3..5feed232be9 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -855,18 +855,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
break;
}
case AUDIT_SIGNAL_INFO:
- err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
- if (err)
- return err;
+ len = 0;
+ if (audit_sig_sid) {
+ err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
+ if (err)
+ return err;
+ }
sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
if (!sig_data) {
- security_release_secctx(ctx, len);
+ if (audit_sig_sid)
+ security_release_secctx(ctx, len);
return -ENOMEM;
}
sig_data->uid = audit_sig_uid;
sig_data->pid = audit_sig_pid;
- memcpy(sig_data->ctx, ctx, len);
- security_release_secctx(ctx, len);
+ if (audit_sig_sid) {
+ memcpy(sig_data->ctx, ctx, len);
+ security_release_secctx(ctx, len);
+ }
audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO,
0, 0, sig_data, sizeof(*sig_data) + len);
kfree(sig_data);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 0e96dbc60ea..cc7e87936cb 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -45,8 +45,8 @@
struct audit_watch {
atomic_t count; /* reference count */
- char *path; /* insertion path */
dev_t dev; /* associated superblock device */
+ char *path; /* insertion path */
unsigned long ino; /* associated inode number */
struct audit_parent *parent; /* associated parent */
struct list_head wlist; /* entry in parent->watches list */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 68d3c6a0ecd..267e484f019 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -168,12 +168,12 @@ struct audit_context {
int in_syscall; /* 1 if task is in a syscall */
enum audit_state state, current_state;
unsigned int serial; /* serial number for record */
- struct timespec ctime; /* time of syscall entry */
int major; /* syscall number */
+ struct timespec ctime; /* time of syscall entry */
unsigned long argv[4]; /* syscall arguments */
- int return_valid; /* return code is valid */
long return_code;/* syscall return code */
u64 prio;
+ int return_valid; /* return code is valid */
int name_count;
struct audit_names names[AUDIT_NAMES];
char * filterkey; /* key for rule that triggered record */
@@ -198,8 +198,8 @@ struct audit_context {
char target_comm[TASK_COMM_LEN];
struct audit_tree_refs *trees, *first_trees;
- int tree_count;
struct list_head killed_trees;
+ int tree_count;
int type;
union {
diff --git a/kernel/capability.c b/kernel/capability.c
index 4e17041963f..7f876e60521 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -29,7 +29,6 @@ EXPORT_SYMBOL(__cap_empty_set);
EXPORT_SYMBOL(__cap_full_set);
EXPORT_SYMBOL(__cap_init_eff_set);
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
int file_caps_enabled = 1;
static int __init file_caps_disable(char *str)
@@ -38,7 +37,6 @@ static int __init file_caps_disable(char *str)
return 1;
}
__setup("no_file_caps", file_caps_disable);
-#endif
/*
* More recent versions of libcap are available from:
@@ -169,8 +167,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
kernel_cap_t pE, pI, pP;
ret = cap_validate_magic(header, &tocopy);
- if (ret != 0)
- return ret;
+ if ((dataptr == NULL) || (ret != 0))
+ return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;
if (get_user(pid, &header->pid))
return -EFAULT;
@@ -238,7 +236,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
{
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
- unsigned i, tocopy;
+ unsigned i, tocopy, copybytes;
kernel_cap_t inheritable, permitted, effective;
struct cred *new;
int ret;
@@ -255,8 +253,11 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
if (pid != 0 && pid != task_pid_vnr(current))
return -EPERM;
- if (copy_from_user(&kdata, data,
- tocopy * sizeof(struct __user_cap_data_struct)))
+ copybytes = tocopy * sizeof(struct __user_cap_data_struct);
+ if (copybytes > sizeof(kdata))
+ return -EFAULT;
+
+ if (copy_from_user(&kdata, data, copybytes))
return -EFAULT;
for (i = 0; i < tocopy; i++) {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cd83d9933b6..0249f4be9b5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -23,6 +23,7 @@
*/
#include <linux/cgroup.h>
+#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
@@ -48,6 +49,8 @@
#include <linux/namei.h>
#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
+#include <linux/idr.h>
+#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <asm/atomic.h>
@@ -60,6 +63,8 @@ static struct cgroup_subsys *subsys[] = {
#include <linux/cgroup_subsys.h>
};
+#define MAX_CGROUP_ROOT_NAMELEN 64
+
/*
* A cgroupfs_root represents the root of a cgroup hierarchy,
* and may be associated with a superblock to form an active
@@ -74,6 +79,9 @@ struct cgroupfs_root {
*/
unsigned long subsys_bits;
+ /* Unique id for this hierarchy. */
+ int hierarchy_id;
+
/* The bitmask of subsystems currently attached to this hierarchy */
unsigned long actual_subsys_bits;
@@ -94,6 +102,9 @@ struct cgroupfs_root {
/* The path to use for release notifications. */
char release_agent_path[PATH_MAX];
+
+ /* The name for this hierarchy - may be empty */
+ char name[MAX_CGROUP_ROOT_NAMELEN];
};
/*
@@ -141,6 +152,10 @@ struct css_id {
static LIST_HEAD(roots);
static int root_count;
+static DEFINE_IDA(hierarchy_ida);
+static int next_hierarchy_id;
+static DEFINE_SPINLOCK(hierarchy_id_lock);
+
/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)
@@ -201,6 +216,7 @@ struct cg_cgroup_link {
* cgroup, anchored on cgroup->css_sets
*/
struct list_head cgrp_link_list;
+ struct cgroup *cgrp;
/*
* List running through cg_cgroup_links pointing at a
* single css_set object, anchored on css_set->cg_links
@@ -227,8 +243,11 @@ static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;
-/* hash table for cgroup groups. This improves the performance to
- * find an existing css_set */
+/*
+ * hash table for cgroup groups. This improves the performance to find
+ * an existing css_set. This hash doesn't (currently) take into
+ * account cgroups in empty hierarchies.
+ */
#define CSS_SET_HASH_BITS 7
#define CSS_SET_TABLE_SIZE (1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
@@ -248,48 +267,22 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
return &css_set_table[index];
}
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+ struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+ kfree(cg);
+}
+
/* We don't maintain the lists running through each css_set to its
* task until after the first call to cgroup_iter_start(). This
* reduces the fork()/exit() overhead for people who have cgroups
* compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;
-/* When we create or destroy a css_set, the operation simply
- * takes/releases a reference count on all the cgroups referenced
- * by subsystems in this css_set. This can end up multiple-counting
- * some cgroups, but that's OK - the ref-count is just a
- * busy/not-busy indicator; ensuring that we only count each cgroup
- * once would require taking a global lock to ensure that no
- * subsystems moved between hierarchies while we were doing so.
- *
- * Possible TODO: decide at boot time based on the number of
- * registered subsystems and the number of CPUs or NUMA nodes whether
- * it's better for performance to ref-count every subsystem, or to
- * take a global lock and only add one ref count to each hierarchy.
- */
-
-/*
- * unlink a css_set from the list and free it
- */
-static void unlink_css_set(struct css_set *cg)
+static void __put_css_set(struct css_set *cg, int taskexit)
{
struct cg_cgroup_link *link;
struct cg_cgroup_link *saved_link;
-
- hlist_del(&cg->hlist);
- css_set_count--;
-
- list_for_each_entry_safe(link, saved_link, &cg->cg_links,
- cg_link_list) {
- list_del(&link->cg_link_list);
- list_del(&link->cgrp_link_list);
- kfree(link);
- }
-}
-
-static void __put_css_set(struct css_set *cg, int taskexit)
-{
- int i;
/*
* Ensure that the refcount doesn't hit zero while any readers
* can see it. Similar to atomic_dec_and_lock(), but for an
@@ -302,21 +295,28 @@ static void __put_css_set(struct css_set *cg, int taskexit)
write_unlock(&css_set_lock);
return;
}
- unlink_css_set(cg);
- write_unlock(&css_set_lock);
- rcu_read_lock();
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
+ /* This css_set is dead. unlink it and release cgroup refcounts */
+ hlist_del(&cg->hlist);
+ css_set_count--;
+
+ list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+ cg_link_list) {
+ struct cgroup *cgrp = link->cgrp;
+ list_del(&link->cg_link_list);
+ list_del(&link->cgrp_link_list);
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
+
+ kfree(link);
}
- rcu_read_unlock();
- kfree(cg);
+
+ write_unlock(&css_set_lock);
+ call_rcu(&cg->rcu_head, free_css_set_rcu);
}
/*
@@ -338,6 +338,78 @@ static inline void put_css_set_taskexit(struct css_set *cg)
}
/*
+ * compare_css_sets - helper function for find_existing_css_set().
+ * @cg: candidate css_set being tested
+ * @old_cg: existing css_set for a task
+ * @new_cgrp: cgroup that's being entered by the task
+ * @template: desired set of css pointers in css_set (pre-calculated)
+ *
+ * Returns true if "cg" matches "old_cg" except for the hierarchy
+ * which "new_cgrp" belongs to, for which it should match "new_cgrp".
+ */
+static bool compare_css_sets(struct css_set *cg,
+ struct css_set *old_cg,
+ struct cgroup *new_cgrp,
+ struct cgroup_subsys_state *template[])
+{
+ struct list_head *l1, *l2;
+
+ if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+ /* Not all subsystems matched */
+ return false;
+ }
+
+ /*
+ * Compare cgroup pointers in order to distinguish between
+ * different cgroups in heirarchies with no subsystems. We
+ * could get by with just this check alone (and skip the
+ * memcmp above) but on most setups the memcmp check will
+ * avoid the need for this more expensive check on almost all
+ * candidates.
+ */
+
+ l1 = &cg->cg_links;
+ l2 = &old_cg->cg_links;
+ while (1) {
+ struct cg_cgroup_link *cgl1, *cgl2;
+ struct cgroup *cg1, *cg2;
+
+ l1 = l1->next;
+ l2 = l2->next;
+ /* See if we reached the end - both lists are equal length. */
+ if (l1 == &cg->cg_links) {
+ BUG_ON(l2 != &old_cg->cg_links);
+ break;
+ } else {
+ BUG_ON(l2 == &old_cg->cg_links);
+ }
+ /* Locate the cgroups associated with these links. */
+ cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
+ cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
+ cg1 = cgl1->cgrp;
+ cg2 = cgl2->cgrp;
+ /* Hierarchies should be linked in the same order. */
+ BUG_ON(cg1->root != cg2->root);
+
+ /*
+ * If this hierarchy is the hierarchy of the cgroup
+ * that's changing, then we need to check that this
+ * css_set points to the new cgroup; if it's any other
+ * hierarchy, then this css_set should point to the
+ * same cgroup as the old css_set.
+ */
+ if (cg1->root == new_cgrp->root) {
+ if (cg1 != new_cgrp)
+ return false;
+ } else {
+ if (cg1 != cg2)
+ return false;
+ }
+ }
+ return true;
+}
+
+/*
* find_existing_css_set() is a helper for
* find_css_set(), and checks to see whether an existing
* css_set is suitable.
@@ -378,10 +450,11 @@ static struct css_set *find_existing_css_set(
hhead = css_set_hash(template);
hlist_for_each_entry(cg, node, hhead, hlist) {
- if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
- /* All subsystems matched */
- return cg;
- }
+ if (!compare_css_sets(cg, oldcg, cgrp, template))
+ continue;
+
+ /* This css_set matches what we need */
+ return cg;
}
/* No existing cgroup group matched */
@@ -435,8 +508,14 @@ static void link_css_set(struct list_head *tmp_cg_links,
link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
cgrp_link_list);
link->cg = cg;
+ link->cgrp = cgrp;
+ atomic_inc(&cgrp->count);
list_move(&link->cgrp_link_list, &cgrp->css_sets);
- list_add(&link->cg_link_list, &cg->cg_links);
+ /*
+ * Always add links to the tail of the list so that the list
+ * is sorted by order of hierarchy creation
+ */
+ list_add_tail(&link->cg_link_list, &cg->cg_links);
}
/*
@@ -451,11 +530,11 @@ static struct css_set *find_css_set(
{
struct css_set *res;
struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
- int i;
struct list_head tmp_cg_links;
struct hlist_head *hhead;
+ struct cg_cgroup_link *link;
/* First see if we already have a cgroup group that matches
* the desired set */
@@ -489,20 +568,12 @@ static struct css_set *find_css_set(
write_lock(&css_set_lock);
/* Add reference counts and links from the new css_set. */
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup *cgrp = res->subsys[i]->cgroup;
- struct cgroup_subsys *ss = subsys[i];
- atomic_inc(&cgrp->count);
- /*
- * We want to add a link once per cgroup, so we
- * only do it for the first subsystem in each
- * hierarchy
- */
- if (ss->root->subsys_list.next == &ss->sibling)
- link_css_set(&tmp_cg_links, res, cgrp);
+ list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
+ struct cgroup *c = link->cgrp;
+ if (c->root == cgrp->root)
+ c = cgrp;
+ link_css_set(&tmp_cg_links, res, c);
}
- if (list_empty(&rootnode.subsys_list))
- link_css_set(&tmp_cg_links, res, dummytop);
BUG_ON(!list_empty(&tmp_cg_links));
@@ -518,6 +589,41 @@ static struct css_set *find_css_set(
}
/*
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+ struct cgroupfs_root *root)
+{
+ struct css_set *css;
+ struct cgroup *res = NULL;
+
+ BUG_ON(!mutex_is_locked(&cgroup_mutex));
+ read_lock(&css_set_lock);
+ /*
+ * No need to lock the task - since we hold cgroup_mutex the
+ * task can't change groups, so the only thing that can happen
+ * is that it exits and its css is set back to init_css_set.
+ */
+ css = task->cgroups;
+ if (css == &init_css_set) {
+ res = &root->top_cgroup;
+ } else {
+ struct cg_cgroup_link *link;
+ list_for_each_entry(link, &css->cg_links, cg_link_list) {
+ struct cgroup *c = link->cgrp;
+ if (c->root == root) {
+ res = c;
+ break;
+ }
+ }
+ }
+ read_unlock(&css_set_lock);
+ BUG_ON(!res);
+ return res;
+}
+
+/*
* There is one global cgroup mutex. We also require taking
* task_lock() when dereferencing a task's cgroup subsys pointers.
* See "The task_lock() exception", at the end of this comment.
@@ -597,7 +703,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
-static struct file_operations proc_cgroupstats_operations;
+static const struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
.name = "cgroup",
@@ -677,6 +783,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
*/
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));
+
call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
}
iput(inode);
@@ -841,6 +953,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ if (strlen(root->name))
+ seq_printf(seq, ",name=%s", root->name);
mutex_unlock(&cgroup_mutex);
return 0;
}
@@ -849,6 +963,12 @@ struct cgroup_sb_opts {
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
+ char *name;
+ /* User explicitly requested empty subsystem */
+ bool none;
+
+ struct cgroupfs_root *new_root;
+
};
/* Convert a hierarchy specifier into a bitmask of subsystems and
@@ -863,9 +983,7 @@ static int parse_cgroupfs_options(char *data,
mask = ~(1UL << cpuset_subsys_id);
#endif
- opts->subsys_bits = 0;
- opts->flags = 0;
- opts->release_agent = NULL;
+ memset(opts, 0, sizeof(*opts));
while ((token = strsep(&o, ",")) != NULL) {
if (!*token)
@@ -879,17 +997,42 @@ static int parse_cgroupfs_options(char *data,
if (!ss->disabled)
opts->subsys_bits |= 1ul << i;
}
+ } else if (!strcmp(token, "none")) {
+ /* Explicitly have no subsystems */
+ opts->none = true;
} else if (!strcmp(token, "noprefix")) {
set_bit(ROOT_NOPREFIX, &opts->flags);
} else if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
- opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+ opts->release_agent =
+ kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
- strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
- opts->release_agent[PATH_MAX - 1] = 0;
+ } else if (!strncmp(token, "name=", 5)) {
+ int i;
+ const char *name = token + 5;
+ /* Can't specify an empty name */
+ if (!strlen(name))
+ return -EINVAL;
+ /* Must match [\w.-]+ */
+ for (i = 0; i < strlen(name); i++) {
+ char c = name[i];
+ if (isalnum(c))
+ continue;
+ if ((c == '.') || (c == '-') || (c == '_'))
+ continue;
+ return -EINVAL;
+ }
+ /* Specifying two names is forbidden */
+ if (opts->name)
+ return -EINVAL;
+ opts->name = kstrndup(name,
+ MAX_CGROUP_ROOT_NAMELEN,
+ GFP_KERNEL);
+ if (!opts->name)
+ return -ENOMEM;
} else {
struct cgroup_subsys *ss;
int i;
@@ -906,6 +1049,8 @@ static int parse_cgroupfs_options(char *data,
}
}
+ /* Consistency checks */
+
/*
* Option noprefix was introduced just for backward compatibility
* with the old cpuset, so we allow noprefix only if mounting just
@@ -915,8 +1060,16 @@ static int parse_cgroupfs_options(char *data,
(opts->subsys_bits & mask))
return -EINVAL;
- /* We can't have an empty hierarchy */
- if (!opts->subsys_bits)
+
+ /* Can't specify "none" and some subsystems */
+ if (opts->subsys_bits && opts->none)
+ return -EINVAL;
+
+ /*
+ * We either have to specify by name or by subsystems. (So all
+ * empty hierarchies must have a name).
+ */
+ if (!opts->subsys_bits && !opts->name)
return -EINVAL;
return 0;
@@ -944,6 +1097,12 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
goto out_unlock;
}
+ /* Don't allow name to change at remount */
+ if (opts.name && strcmp(opts.name, root->name)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
ret = rebind_subsystems(root, opts.subsys_bits);
if (ret)
goto out_unlock;
@@ -955,6 +1114,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
strcpy(root->release_agent_path, opts.release_agent);
out_unlock:
kfree(opts.release_agent);
+ kfree(opts.name);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
unlock_kernel();
@@ -974,9 +1134,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
- INIT_LIST_HEAD(&cgrp->pids_list);
- init_rwsem(&cgrp->pids_mutex);
+ INIT_LIST_HEAD(&cgrp->pidlists);
+ mutex_init(&cgrp->pidlist_mutex);
}
+
static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
@@ -988,33 +1149,106 @@ static void init_cgroup_root(struct cgroupfs_root *root)
init_cgroup_housekeeping(cgrp);
}
+static bool init_root_id(struct cgroupfs_root *root)
+{
+ int ret = 0;
+
+ do {
+ if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
+ return false;
+ spin_lock(&hierarchy_id_lock);
+ /* Try to allocate the next unused ID */
+ ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
+ &root->hierarchy_id);
+ if (ret == -ENOSPC)
+ /* Try again starting from 0 */
+ ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
+ if (!ret) {
+ next_hierarchy_id = root->hierarchy_id + 1;
+ } else if (ret != -EAGAIN) {
+ /* Can only get here if the 31-bit IDR is full ... */
+ BUG_ON(ret);
+ }
+ spin_unlock(&hierarchy_id_lock);
+ } while (ret);
+ return true;
+}
+
static int cgroup_test_super(struct super_block *sb, void *data)
{
- struct cgroupfs_root *new = data;
+ struct cgroup_sb_opts *opts = data;
struct cgroupfs_root *root = sb->s_fs_info;
- /* First check subsystems */
- if (new->subsys_bits != root->subsys_bits)
- return 0;
+ /* If we asked for a name then it must match */
+ if (opts->name && strcmp(opts->name, root->name))
+ return 0;
- /* Next check flags */
- if (new->flags != root->flags)
+ /*
+ * If we asked for subsystems (or explicitly for no
+ * subsystems) then they must match
+ */
+ if ((opts->subsys_bits || opts->none)
+ && (opts->subsys_bits != root->subsys_bits))
return 0;
return 1;
}
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
+{
+ struct cgroupfs_root *root;
+
+ if (!opts->subsys_bits && !opts->none)
+ return NULL;
+
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root)
+ return ERR_PTR(-ENOMEM);
+
+ if (!init_root_id(root)) {
+ kfree(root);
+ return ERR_PTR(-ENOMEM);
+ }
+ init_cgroup_root(root);
+
+ root->subsys_bits = opts->subsys_bits;
+ root->flags = opts->flags;
+ if (opts->release_agent)
+ strcpy(root->release_agent_path, opts->release_agent);
+ if (opts->name)
+ strcpy(root->name, opts->name);
+ return root;
+}
+
+static void cgroup_drop_root(struct cgroupfs_root *root)
+{
+ if (!root)
+ return;
+
+ BUG_ON(!root->hierarchy_id);
+ spin_lock(&hierarchy_id_lock);
+ ida_remove(&hierarchy_ida, root->hierarchy_id);
+ spin_unlock(&hierarchy_id_lock);
+ kfree(root);
+}
+
static int cgroup_set_super(struct super_block *sb, void *data)
{
int ret;
- struct cgroupfs_root *root = data;
+ struct cgroup_sb_opts *opts = data;
+
+ /* If we don't have a new root, we can't set up a new sb */
+ if (!opts->new_root)
+ return -EINVAL;
+
+ BUG_ON(!opts->subsys_bits && !opts->none);
ret = set_anon_super(sb, NULL);
if (ret)
return ret;
- sb->s_fs_info = root;
- root->sb = sb;
+ sb->s_fs_info = opts->new_root;
+ opts->new_root->sb = sb;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1051,48 +1285,43 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
void *data, struct vfsmount *mnt)
{
struct cgroup_sb_opts opts;
+ struct cgroupfs_root *root;
int ret = 0;
struct super_block *sb;
- struct cgroupfs_root *root;
- struct list_head tmp_cg_links;
+ struct cgroupfs_root *new_root;
/* First find the desired set of subsystems */
ret = parse_cgroupfs_options(data, &opts);
- if (ret) {
- kfree(opts.release_agent);
- return ret;
- }
-
- root = kzalloc(sizeof(*root), GFP_KERNEL);
- if (!root) {
- kfree(opts.release_agent);
- return -ENOMEM;
- }
+ if (ret)
+ goto out_err;
- init_cgroup_root(root);
- root->subsys_bits = opts.subsys_bits;
- root->flags = opts.flags;
- if (opts.release_agent) {
- strcpy(root->release_agent_path, opts.release_agent);
- kfree(opts.release_agent);
+ /*
+ * Allocate a new cgroup root. We may not need it if we're
+ * reusing an existing hierarchy.
+ */
+ new_root = cgroup_root_from_opts(&opts);
+ if (IS_ERR(new_root)) {
+ ret = PTR_ERR(new_root);
+ goto out_err;
}
+ opts.new_root = new_root;
- sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
-
+ /* Locate an existing or new sb for this hierarchy */
+ sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
if (IS_ERR(sb)) {
- kfree(root);
- return PTR_ERR(sb);
+ ret = PTR_ERR(sb);
+ cgroup_drop_root(opts.new_root);
+ goto out_err;
}
- if (sb->s_fs_info != root) {
- /* Reusing an existing superblock */
- BUG_ON(sb->s_root == NULL);
- kfree(root);
- root = NULL;
- } else {
- /* New superblock */
+ root = sb->s_fs_info;
+ BUG_ON(!root);
+ if (root == opts.new_root) {
+ /* We used the new root structure, so this is a new hierarchy */
+ struct list_head tmp_cg_links;
struct cgroup *root_cgrp = &root->top_cgroup;
struct inode *inode;
+ struct cgroupfs_root *existing_root;
int i;
BUG_ON(sb->s_root != NULL);
@@ -1105,6 +1334,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
+ if (strlen(root->name)) {
+ /* Check for name clashes with existing mounts */
+ for_each_active_root(existing_root) {
+ if (!strcmp(existing_root->name, root->name)) {
+ ret = -EBUSY;
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
+ goto drop_new_super;
+ }
+ }
+ }
+
/*
* We're accessing css_set_count without locking
* css_set_lock here, but that's OK - it can only be
@@ -1123,7 +1364,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
if (ret == -EBUSY) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
- goto free_cg_links;
+ free_cg_links(&tmp_cg_links);
+ goto drop_new_super;
}
/* EBUSY should be the only error here */
@@ -1155,17 +1397,27 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
BUG_ON(root->number_of_cgroups != 1);
cgroup_populate_dir(root_cgrp);
- mutex_unlock(&inode->i_mutex);
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&inode->i_mutex);
+ } else {
+ /*
+ * We re-used an existing hierarchy - the new root (if
+ * any) is not needed
+ */
+ cgroup_drop_root(opts.new_root);
}
simple_set_mnt(mnt, sb);
+ kfree(opts.release_agent);
+ kfree(opts.name);
return 0;
- free_cg_links:
- free_cg_links(&tmp_cg_links);
drop_new_super:
deactivate_locked_super(sb);
+ out_err:
+ kfree(opts.release_agent);
+ kfree(opts.name);
+
return ret;
}
@@ -1211,7 +1463,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
mutex_unlock(&cgroup_mutex);
kill_litter_super(sb);
- kfree(root);
+ cgroup_drop_root(root);
}
static struct file_system_type cgroup_fs_type = {
@@ -1276,27 +1528,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
return 0;
}
-/*
- * Return the first subsystem attached to a cgroup's hierarchy, and
- * its subsystem id.
- */
-
-static void get_first_subsys(const struct cgroup *cgrp,
- struct cgroup_subsys_state **css, int *subsys_id)
-{
- const struct cgroupfs_root *root = cgrp->root;
- const struct cgroup_subsys *test_ss;
- BUG_ON(list_empty(&root->subsys_list));
- test_ss = list_entry(root->subsys_list.next,
- struct cgroup_subsys, sibling);
- if (css) {
- *css = cgrp->subsys[test_ss->subsys_id];
- BUG_ON(!*css);
- }
- if (subsys_id)
- *subsys_id = test_ss->subsys_id;
-}
-
/**
* cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
* @cgrp: the cgroup the task is attaching to
@@ -1313,18 +1544,15 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
struct css_set *cg;
struct css_set *newcg;
struct cgroupfs_root *root = cgrp->root;
- int subsys_id;
-
- get_first_subsys(cgrp, NULL, &subsys_id);
/* Nothing to do if the task is already in that cgroup */
- oldcgrp = task_cgroup(tsk, subsys_id);
+ oldcgrp = task_cgroup_from_root(tsk, root);
if (cgrp == oldcgrp)
return 0;
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, tsk);
+ retval = ss->can_attach(ss, cgrp, tsk, false);
if (retval)
return retval;
}
@@ -1362,7 +1590,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
for_each_subsys(root, ss) {
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, tsk);
+ ss->attach(ss, cgrp, oldcgrp, tsk, false);
}
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
synchronize_rcu();
@@ -1423,15 +1651,6 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
return ret;
}
-/* The various types of files and directories in a cgroup file system */
-enum cgroup_filetype {
- FILE_ROOT,
- FILE_DIR,
- FILE_TASKLIST,
- FILE_NOTIFY_ON_RELEASE,
- FILE_RELEASE_AGENT,
-};
-
/**
* cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
* @cgrp: the cgroup to be checked for liveness
@@ -1491,14 +1710,13 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
return -EFAULT;
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
if (cft->write_u64) {
- u64 val = simple_strtoull(buffer, &end, 0);
+ u64 val = simple_strtoull(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_u64(cgrp, cft, val);
} else {
- s64 val = simple_strtoll(buffer, &end, 0);
+ s64 val = simple_strtoll(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_s64(cgrp, cft, val);
@@ -1534,8 +1752,7 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
}
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
- retval = cft->write_string(cgrp, cft, buffer);
+ retval = cft->write_string(cgrp, cft, strstrip(buffer));
if (!retval)
retval = nbytes;
out:
@@ -1644,7 +1861,7 @@ static int cgroup_seqfile_release(struct inode *inode, struct file *file)
return single_release(inode, file);
}
-static struct file_operations cgroup_seqfile_operations = {
+static const struct file_operations cgroup_seqfile_operations = {
.read = seq_read,
.write = cgroup_file_write,
.llseek = seq_lseek,
@@ -1703,7 +1920,7 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}
-static struct file_operations cgroup_file_operations = {
+static const struct file_operations cgroup_file_operations = {
.read = cgroup_file_read,
.write = cgroup_file_write,
.llseek = generic_file_llseek,
@@ -1876,7 +2093,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
* the start of a css_set
*/
static void cgroup_advance_iter(struct cgroup *cgrp,
- struct cgroup_iter *it)
+ struct cgroup_iter *it)
{
struct list_head *l = it->cg_link;
struct cg_cgroup_link *link;
@@ -2129,7 +2346,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
}
/*
- * Stuff for reading the 'tasks' file.
+ * Stuff for reading the 'tasks'/'procs' files.
*
* Reading this file can return large amounts of data if a cgroup has
* *lots* of attached tasks. So it may need several calls to read(),
@@ -2139,27 +2356,196 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
*/
/*
- * Load into 'pidarray' up to 'npids' of the tasks using cgroup
- * 'cgrp'. Return actual number of pids loaded. No need to
- * task_lock(p) when reading out p->cgroup, since we're in an RCU
- * read section, so the css_set can't go away, and is
- * immutable after creation.
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+ if (PIDLIST_TOO_LARGE(count))
+ return vmalloc(count * sizeof(pid_t));
+ else
+ return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+ if (is_vmalloc_addr(p))
+ vfree(p);
+ else
+ kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+ void *newlist;
+ /* note: if new alloc fails, old p will still be valid either way */
+ if (is_vmalloc_addr(p)) {
+ newlist = vmalloc(newcount * sizeof(pid_t));
+ if (!newlist)
+ return NULL;
+ memcpy(newlist, p, newcount * sizeof(pid_t));
+ vfree(p);
+ } else {
+ newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+ }
+ return newlist;
+}
+
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * If the new stripped list is sufficiently smaller and there's enough memory
+ * to allocate a new buffer, will let go of the unneeded memory. Returns the
+ * number of unique elements.
+ */
+/* is the size difference enough that we should re-allocate the array? */
+#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
+static int pidlist_uniq(pid_t **p, int length)
+{
+ int src, dest = 1;
+ pid_t *list = *p;
+ pid_t *newlist;
+
+ /*
+ * we presume the 0th element is unique, so i starts at 1. trivial
+ * edge cases first; no work needs to be done for either
+ */
+ if (length == 0 || length == 1)
+ return length;
+ /* src and dest walk down the list; dest counts unique elements */
+ for (src = 1; src < length; src++) {
+ /* find next unique element */
+ while (list[src] == list[src-1]) {
+ src++;
+ if (src == length)
+ goto after;
+ }
+ /* dest always points to where the next unique element goes */
+ list[dest] = list[src];
+ dest++;
+ }
+after:
+ /*
+ * if the length difference is large enough, we want to allocate a
+ * smaller buffer to save memory. if this fails due to out of memory,
+ * we'll just stay with what we've got.
+ */
+ if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
+ newlist = pidlist_resize(list, dest);
+ if (newlist)
+ *p = newlist;
+ }
+ return dest;
+}
+
+static int cmppid(const void *a, const void *b)
+{
+ return *(pid_t *)a - *(pid_t *)b;
+}
+
+/*
+ * 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 int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+ enum cgroup_filetype type)
{
- int n = 0, pid;
+ struct cgroup_pidlist *l;
+ /* don't need task_nsproxy() if we're looking at ourself */
+ struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+ /*
+ * We can't drop the pidlist_mutex before taking the l->mutex 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) {
+ /* found a matching list - drop the extra refcount */
+ put_pid_ns(ns);
+ /* make sure l doesn't vanish out from under us */
+ down_write(&l->mutex);
+ mutex_unlock(&cgrp->pidlist_mutex);
+ l->use_count++;
+ return l;
+ }
+ }
+ /* entry not found; create a new one */
+ l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+ if (!l) {
+ mutex_unlock(&cgrp->pidlist_mutex);
+ put_pid_ns(ns);
+ return l;
+ }
+ init_rwsem(&l->mutex);
+ down_write(&l->mutex);
+ l->key.type = type;
+ l->key.ns = ns;
+ l->use_count = 0; /* don't increment here */
+ l->list = NULL;
+ l->owner = cgrp;
+ list_add(&l->links, &cgrp->pidlists);
+ mutex_unlock(&cgrp->pidlist_mutex);
+ return l;
+}
+
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
+ */
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+ struct cgroup_pidlist **lp)
+{
+ pid_t *array;
+ int length;
+ int pid, n = 0; /* used for populating the array */
struct cgroup_iter it;
struct task_struct *tsk;
+ struct cgroup_pidlist *l;
+
+ /*
+ * If cgroup gets more users after we read count, we won't have
+ * enough space - tough. This race is indistinguishable to the
+ * caller from the case that the additional cgroup users didn't
+ * show up until sometime later on.
+ */
+ length = cgroup_task_count(cgrp);
+ array = pidlist_allocate(length);
+ if (!array)
+ return -ENOMEM;
+ /* now, populate the array */
cgroup_iter_start(cgrp, &it);
while ((tsk = cgroup_iter_next(cgrp, &it))) {
- if (unlikely(n == npids))
+ if (unlikely(n == length))
break;
- pid = task_pid_vnr(tsk);
- if (pid > 0)
- pidarray[n++] = pid;
+ /* get tgid or pid for procs or tasks file respectively */
+ if (type == CGROUP_FILE_PROCS)
+ pid = task_tgid_vnr(tsk);
+ else
+ pid = task_pid_vnr(tsk);
+ if (pid > 0) /* make sure to only use valid results */
+ array[n++] = pid;
}
cgroup_iter_end(cgrp, &it);
- return n;
+ length = n;
+ /* now sort & (if procs) strip out duplicates */
+ sort(array, length, sizeof(pid_t), cmppid, NULL);
+ if (type == CGROUP_FILE_PROCS)
+ length = pidlist_uniq(&array, length);
+ l = cgroup_pidlist_find(cgrp, type);
+ if (!l) {
+ pidlist_free(array);
+ return -ENOMEM;
+ }
+ /* store array, freeing old if necessary - lock already held */
+ pidlist_free(l->list);
+ l->list = array;
+ l->length = length;
+ l->use_count++;
+ up_write(&l->mutex);
+ *lp = l;
+ return 0;
}
/**
@@ -2216,37 +2602,14 @@ err:
return ret;
}
-/*
- * Cache pids for all threads in the same pid namespace that are
- * opening the same "tasks" file.
- */
-struct cgroup_pids {
- /* The node in cgrp->pids_list */
- struct list_head list;
- /* The cgroup those pids belong to */
- struct cgroup *cgrp;
- /* The namepsace those pids belong to */
- struct pid_namespace *ns;
- /* Array of process ids in the cgroup */
- pid_t *tasks_pids;
- /* How many files are using the this tasks_pids array */
- int use_count;
- /* Length of the current tasks_pids array */
- int length;
-};
-
-static int cmppid(const void *a, const void *b)
-{
- return *(pid_t *)a - *(pid_t *)b;
-}
/*
- * seq_file methods for the "tasks" file. The seq_file position is the
+ * seq_file methods for the tasks/procs files. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
- * in the cgroup->tasks_pids array.
+ * in the cgroup->l->list array.
*/
-static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
/*
* Initially we receive a position value that corresponds to
@@ -2254,48 +2617,45 @@ static void *cgroup_tasks_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_pids *cp = s->private;
- struct cgroup *cgrp = cp->cgrp;
+ struct cgroup_pidlist *l = s->private;
int index = 0, pid = *pos;
int *iter;
- down_read(&cgrp->pids_mutex);
+ down_read(&l->mutex);
if (pid) {
- int end = cp->length;
+ int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
- if (cp->tasks_pids[mid] == pid) {
+ if (l->list[mid] == pid) {
index = mid;
break;
- } else if (cp->tasks_pids[mid] <= pid)
+ } else if (l->list[mid] <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
- if (index >= cp->length)
+ if (index >= l->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
- iter = cp->tasks_pids + index;
+ iter = l->list + index;
*pos = *iter;
return iter;
}
-static void cgroup_tasks_stop(struct seq_file *s, void *v)
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup_pids *cp = s->private;
- struct cgroup *cgrp = cp->cgrp;
- up_read(&cgrp->pids_mutex);
+ struct cgroup_pidlist *l = s->private;
+ up_read(&l->mutex);
}
-static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup_pids *cp = s->private;
- int *p = v;
- int *end = cp->tasks_pids + cp->length;
-
+ struct cgroup_pidlist *l = s->private;
+ pid_t *p = v;
+ pid_t *end = l->list + l->length;
/*
* Advance to the next pid in the array. If this goes off the
* end, we're done
@@ -2309,124 +2669,107 @@ static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
}
}
-static int cgroup_tasks_show(struct seq_file *s, void *v)
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
return seq_printf(s, "%d\n", *(int *)v);
}
-static const struct seq_operations cgroup_tasks_seq_operations = {
- .start = cgroup_tasks_start,
- .stop = cgroup_tasks_stop,
- .next = cgroup_tasks_next,
- .show = cgroup_tasks_show,
+/*
+ * seq_operations functions for iterating on pidlists through seq_file -
+ * independent of whether it's tasks or procs
+ */
+static const struct seq_operations cgroup_pidlist_seq_operations = {
+ .start = cgroup_pidlist_start,
+ .stop = cgroup_pidlist_stop,
+ .next = cgroup_pidlist_next,
+ .show = cgroup_pidlist_show,
};
-static void release_cgroup_pid_array(struct cgroup_pids *cp)
+static void cgroup_release_pid_array(struct cgroup_pidlist *l)
{
- struct cgroup *cgrp = cp->cgrp;
-
- down_write(&cgrp->pids_mutex);
- BUG_ON(!cp->use_count);
- if (!--cp->use_count) {
- list_del(&cp->list);
- put_pid_ns(cp->ns);
- kfree(cp->tasks_pids);
- kfree(cp);
+ /*
+ * 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->mutex);
+ 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->mutex);
+ kfree(l);
+ return;
}
- up_write(&cgrp->pids_mutex);
+ mutex_unlock(&l->owner->pidlist_mutex);
+ up_write(&l->mutex);
}
-static int cgroup_tasks_release(struct inode *inode, struct file *file)
+static int cgroup_pidlist_release(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- struct cgroup_pids *cp;
-
+ struct cgroup_pidlist *l;
if (!(file->f_mode & FMODE_READ))
return 0;
-
- seq = file->private_data;
- cp = seq->private;
-
- release_cgroup_pid_array(cp);
+ /*
+ * 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 struct file_operations cgroup_tasks_operations = {
+static const struct file_operations cgroup_pidlist_operations = {
.read = seq_read,
.llseek = seq_lseek,
.write = cgroup_file_write,
- .release = cgroup_tasks_release,
+ .release = cgroup_pidlist_release,
};
/*
- * Handle an open on 'tasks' file. Prepare an array containing the
- * process id's of tasks currently attached to the cgroup being opened.
+ * 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.
*/
-
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
+/* 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 pid_namespace *ns = current->nsproxy->pid_ns;
- struct cgroup_pids *cp;
- pid_t *pidarray;
- int npids;
+ struct cgroup_pidlist *l;
int retval;
/* Nothing to do for write-only files */
if (!(file->f_mode & FMODE_READ))
return 0;
- /*
- * If cgroup gets more users after we read count, we won't have
- * enough space - tough. This race is indistinguishable to the
- * caller from the case that the additional cgroup users didn't
- * show up until sometime later on.
- */
- npids = cgroup_task_count(cgrp);
- pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
- if (!pidarray)
- return -ENOMEM;
- npids = pid_array_load(pidarray, npids, cgrp);
- sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
- /*
- * Store the array in the cgroup, freeing the old
- * array if necessary
- */
- down_write(&cgrp->pids_mutex);
-
- list_for_each_entry(cp, &cgrp->pids_list, list) {
- if (ns == cp->ns)
- goto found;
- }
-
- cp = kzalloc(sizeof(*cp), GFP_KERNEL);
- if (!cp) {
- up_write(&cgrp->pids_mutex);
- kfree(pidarray);
- return -ENOMEM;
- }
- cp->cgrp = cgrp;
- cp->ns = ns;
- get_pid_ns(ns);
- list_add(&cp->list, &cgrp->pids_list);
-found:
- kfree(cp->tasks_pids);
- cp->tasks_pids = pidarray;
- cp->length = npids;
- cp->use_count++;
- up_write(&cgrp->pids_mutex);
-
- file->f_op = &cgroup_tasks_operations;
+ /* 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_tasks_seq_operations);
+ retval = seq_open(file, &cgroup_pidlist_seq_operations);
if (retval) {
- release_cgroup_pid_array(cp);
+ cgroup_release_pid_array(l);
return retval;
}
- ((struct seq_file *)file->private_data)->private = cp;
+ ((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 *cgrp,
struct cftype *cft)
@@ -2449,21 +2792,27 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
/*
* for the common functions, 'private' gives the type of file
*/
+/* for hysterical raisins, we can't put this on the older files */
+#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
static struct cftype files[] = {
{
.name = "tasks",
.open = cgroup_tasks_open,
.write_u64 = cgroup_tasks_write,
- .release = cgroup_tasks_release,
- .private = FILE_TASKLIST,
+ .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
-
+ {
+ .name = CGROUP_FILE_GENERIC_PREFIX "procs",
+ .open = cgroup_procs_open,
+ /* .write_u64 = cgroup_procs_write, TODO */
+ .release = cgroup_pidlist_release,
+ .mode = S_IRUGO,
+ },
{
.name = "notify_on_release",
.read_u64 = cgroup_read_notify_on_release,
.write_u64 = cgroup_write_notify_on_release,
- .private = FILE_NOTIFY_ON_RELEASE,
},
};
@@ -2472,7 +2821,6 @@ static struct cftype cft_release_agent = {
.read_seq_string = cgroup_release_agent_show,
.write_string = cgroup_release_agent_write,
.max_write_len = PATH_MAX,
- .private = FILE_RELEASE_AGENT,
};
static int cgroup_populate_dir(struct cgroup *cgrp)
@@ -2879,6 +3227,7 @@ int __init cgroup_init_early(void)
init_task.cgroups = &init_css_set;
init_css_set_link.cg = &init_css_set;
+ init_css_set_link.cgrp = dummytop;
list_add(&init_css_set_link.cgrp_link_list,
&rootnode.top_cgroup.css_sets);
list_add(&init_css_set_link.cg_link_list,
@@ -2933,7 +3282,7 @@ int __init cgroup_init(void)
/* Add init_css_set to the hash table */
hhead = css_set_hash(init_css_set.subsys);
hlist_add_head(&init_css_set.hlist, hhead);
-
+ BUG_ON(!init_root_id(&rootnode));
err = register_filesystem(&cgroup_fs_type);
if (err < 0)
goto out;
@@ -2986,15 +3335,16 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
for_each_active_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
- int subsys_id;
int count = 0;
- seq_printf(m, "%lu:", root->subsys_bits);
+ seq_printf(m, "%d:", root->hierarchy_id);
for_each_subsys(root, ss)
seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ if (strlen(root->name))
+ seq_printf(m, "%sname=%s", count ? "," : "",
+ root->name);
seq_putc(m, ':');
- get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
- cgrp = task_cgroup(tsk, subsys_id);
+ cgrp = task_cgroup_from_root(tsk, root);
retval = cgroup_path(cgrp, buf, PAGE_SIZE);
if (retval < 0)
goto out_unlock;
@@ -3017,7 +3367,7 @@ static int cgroup_open(struct inode *inode, struct file *file)
return single_open(file, proc_cgroup_show, pid);
}
-struct file_operations proc_cgroup_operations = {
+const struct file_operations proc_cgroup_operations = {
.open = cgroup_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -3033,8 +3383,8 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
mutex_lock(&cgroup_mutex);
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
- seq_printf(m, "%s\t%lu\t%d\t%d\n",
- ss->name, ss->root->subsys_bits,
+ seq_printf(m, "%s\t%d\t%d\t%d\n",
+ ss->name, ss->root->hierarchy_id,
ss->root->number_of_cgroups, !ss->disabled);
}
mutex_unlock(&cgroup_mutex);
@@ -3046,7 +3396,7 @@ static int cgroupstats_open(struct inode *inode, struct file *file)
return single_open(file, proc_cgroupstats_show, NULL);
}
-static struct file_operations proc_cgroupstats_operations = {
+static const struct file_operations proc_cgroupstats_operations = {
.open = cgroupstats_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -3320,13 +3670,11 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
{
int ret;
struct cgroup *target;
- int subsys_id;
if (cgrp == dummytop)
return 1;
- get_first_subsys(cgrp, NULL, &subsys_id);
- target = task_cgroup(task, subsys_id);
+ target = task_cgroup_from_root(task, cgrp->root);
while (cgrp != target && cgrp!= cgrp->top_cgroup)
cgrp = cgrp->parent;
ret = (cgrp == target);
@@ -3358,8 +3706,10 @@ static void check_for_release(struct cgroup *cgrp)
void __css_put(struct cgroup_subsys_state *css)
{
struct cgroup *cgrp = css->cgroup;
+ int val;
rcu_read_lock();
- if (atomic_dec_return(&css->refcnt) == 1) {
+ val = atomic_dec_return(&css->refcnt);
+ if (val == 1) {
if (notify_on_release(cgrp)) {
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
@@ -3367,6 +3717,7 @@ void __css_put(struct cgroup_subsys_state *css)
cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
+ WARN_ON_ONCE(val < 1);
}
/*
@@ -3693,3 +4044,154 @@ css_get_next(struct cgroup_subsys *ss, int id,
return ret;
}
+#ifdef CONFIG_CGROUP_DEBUG
+static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+
+ if (!css)
+ return ERR_PTR(-ENOMEM);
+
+ return css;
+}
+
+static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ kfree(cont->subsys[debug_subsys_id]);
+}
+
+static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
+{
+ return atomic_read(&cont->count);
+}
+
+static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
+{
+ return cgroup_task_count(cont);
+}
+
+static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
+{
+ return (u64)(unsigned long)current->cgroups;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup *cont,
+ struct cftype *cft)
+{
+ u64 count;
+
+ rcu_read_lock();
+ count = atomic_read(&current->cgroups->refcount);
+ rcu_read_unlock();
+ return count;
+}
+
+static int current_css_set_cg_links_read(struct cgroup *cont,
+ struct cftype *cft,
+ struct seq_file *seq)
+{
+ struct cg_cgroup_link *link;
+ struct css_set *cg;
+
+ read_lock(&css_set_lock);
+ rcu_read_lock();
+ cg = rcu_dereference(current->cgroups);
+ list_for_each_entry(link, &cg->cg_links, cg_link_list) {
+ struct cgroup *c = link->cgrp;
+ const char *name;
+
+ if (c->dentry)
+ name = c->dentry->d_name.name;
+ else
+ name = "?";
+ seq_printf(seq, "Root %d group %s\n",
+ c->root->hierarchy_id, name);
+ }
+ rcu_read_unlock();
+ read_unlock(&css_set_lock);
+ return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct cgroup *cont,
+ struct cftype *cft,
+ struct seq_file *seq)
+{
+ struct cg_cgroup_link *link;
+
+ read_lock(&css_set_lock);
+ list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
+ struct css_set *cg = link->cg;
+ struct task_struct *task;
+ int count = 0;
+ seq_printf(seq, "css_set %p\n", cg);
+ list_for_each_entry(task, &cg->tasks, cg_list) {
+ if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
+ seq_puts(seq, " ...\n");
+ break;
+ } else {
+ seq_printf(seq, " task %d\n",
+ task_pid_vnr(task));
+ }
+ }
+ }
+ read_unlock(&css_set_lock);
+ return 0;
+}
+
+static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
+{
+ return test_bit(CGRP_RELEASABLE, &cgrp->flags);
+}
+
+static struct cftype debug_files[] = {
+ {
+ .name = "cgroup_refcount",
+ .read_u64 = cgroup_refcount_read,
+ },
+ {
+ .name = "taskcount",
+ .read_u64 = debug_taskcount_read,
+ },
+
+ {
+ .name = "current_css_set",
+ .read_u64 = current_css_set_read,
+ },
+
+ {
+ .name = "current_css_set_refcount",
+ .read_u64 = current_css_set_refcount_read,
+ },
+
+ {
+ .name = "current_css_set_cg_links",
+ .read_seq_string = current_css_set_cg_links_read,
+ },
+
+ {
+ .name = "cgroup_css_links",
+ .read_seq_string = cgroup_css_links_read,
+ },
+
+ {
+ .name = "releasable",
+ .read_u64 = releasable_read,
+ },
+};
+
+static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_files(cont, ss, debug_files,
+ ARRAY_SIZE(debug_files));
+}
+
+struct cgroup_subsys debug_subsys = {
+ .name = "debug",
+ .create = debug_create,
+ .destroy = debug_destroy,
+ .populate = debug_populate,
+ .subsys_id = debug_subsys_id,
+};
+#endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
deleted file mode 100644
index 0c92d797baa..00000000000
--- a/kernel/cgroup_debug.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * kernel/cgroup_debug.c - Example cgroup subsystem that
- * exposes debug info
- *
- * Copyright (C) Google Inc, 2007
- *
- * Developed by Paul Menage (menage@google.com)
- *
- */
-
-#include <linux/cgroup.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/rcupdate.h>
-
-#include <asm/atomic.h>
-
-static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
- struct cgroup *cont)
-{
- struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
-
- if (!css)
- return ERR_PTR(-ENOMEM);
-
- return css;
-}
-
-static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
-{
- kfree(cont->subsys[debug_subsys_id]);
-}
-
-static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
-{
- return atomic_read(&cont->count);
-}
-
-static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
-{
- u64 count;
-
- count = cgroup_task_count(cont);
- return count;
-}
-
-static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
-{
- return (u64)(long)current->cgroups;
-}
-
-static u64 current_css_set_refcount_read(struct cgroup *cont,
- struct cftype *cft)
-{
- u64 count;
-
- rcu_read_lock();
- count = atomic_read(&current->cgroups->refcount);
- rcu_read_unlock();
- return count;
-}
-
-static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
-{
- return test_bit(CGRP_RELEASABLE, &cgrp->flags);
-}
-
-static struct cftype files[] = {
- {
- .name = "cgroup_refcount",
- .read_u64 = cgroup_refcount_read,
- },
- {
- .name = "taskcount",
- .read_u64 = taskcount_read,
- },
-
- {
- .name = "current_css_set",
- .read_u64 = current_css_set_read,
- },
-
- {
- .name = "current_css_set_refcount",
- .read_u64 = current_css_set_refcount_read,
- },
-
- {
- .name = "releasable",
- .read_u64 = releasable_read,
- },
-};
-
-static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
- return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-}
-
-struct cgroup_subsys debug_subsys = {
- .name = "debug",
- .create = debug_create,
- .destroy = debug_destroy,
- .populate = debug_populate,
- .subsys_id = debug_subsys_id,
-};
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index fb249e2bcad..59e9ef6aab4 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -159,7 +159,7 @@ static bool is_task_frozen_enough(struct task_struct *task)
*/
static int freezer_can_attach(struct cgroup_subsys *ss,
struct cgroup *new_cgroup,
- struct task_struct *task)
+ struct task_struct *task, bool threadgroup)
{
struct freezer *freezer;
@@ -177,6 +177,19 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
if (freezer->state == CGROUP_FROZEN)
return -EBUSY;
+ if (threadgroup) {
+ struct task_struct *c;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+ if (is_task_frozen_enough(c)) {
+ rcu_read_unlock();
+ return -EBUSY;
+ }
+ }
+ rcu_read_unlock();
+ }
+
return 0;
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ba0f1ecb21..291ac586f37 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -212,6 +212,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
hcpu, -1, &nr_calls);
if (err == NOTIFY_BAD) {
+ set_cpu_active(cpu, true);
+
nr_calls--;
__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu, nr_calls, NULL);
@@ -223,11 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
/* Ensure that we are not runnable on dying cpu */
cpumask_copy(old_allowed, &current->cpus_allowed);
- set_cpus_allowed_ptr(current,
- cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
+ set_cpus_allowed_ptr(current, cpu_active_mask);
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
+ set_cpu_active(cpu, true);
/* CPU didn't die: tell everyone. Can't complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu) == NOTIFY_BAD)
@@ -292,9 +294,6 @@ int __ref cpu_down(unsigned int cpu)
err = _cpu_down(cpu, 0);
- if (cpu_online(cpu))
- set_cpu_active(cpu, true);
-
out:
cpu_maps_update_done();
stop_machine_destroy();
@@ -387,15 +386,23 @@ int disable_nonboot_cpus(void)
* with the userspace trying to use the CPU hotplug at the same time
*/
cpumask_clear(frozen_cpus);
+
+ for_each_online_cpu(cpu) {
+ if (cpu == first_cpu)
+ continue;
+ set_cpu_active(cpu, false);
+ }
+
+ synchronize_sched();
+
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
if (cpu == first_cpu)
continue;
error = _cpu_down(cpu, 1);
- if (!error) {
+ if (!error)
cpumask_set_cpu(cpu, frozen_cpus);
- printk("CPU%d is down\n", cpu);
- } else {
+ else {
printk(KERN_ERR "Error taking CPU%d down: %d\n",
cpu, error);
break;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7e75a41bd50..ba401fab459 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
* element of the partition (one sched domain) to be passed to
* partition_sched_domains().
*/
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
struct sched_domain_attr **attributes)
{
LIST_HEAD(q); /* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
struct cpuset **csa; /* array of all cpuset ptrs */
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
- struct cpumask *doms; /* resulting partition; i.e. sched domains */
+ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms = 0; /* number of sched domains in result */
int nslot; /* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
- doms = kmalloc(cpumask_size(), GFP_KERNEL);
+ ndoms = 1;
+ doms = alloc_sched_domains(ndoms);
if (!doms)
goto done;
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
*dattr = SD_ATTR_INIT;
update_domain_attr_tree(dattr, &top_cpuset);
}
- cpumask_copy(doms, top_cpuset.cpus_allowed);
+ cpumask_copy(doms[0], top_cpuset.cpus_allowed);
- ndoms = 1;
goto done;
}
@@ -636,7 +635,7 @@ restart:
* Now we know how many domains to create.
* Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
*/
- doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+ doms = alloc_sched_domains(ndoms);
if (!doms)
goto done;
@@ -656,7 +655,7 @@ restart:
continue;
}
- dp = doms + nslot;
+ dp = doms[nslot];
if (nslot == ndoms) {
static int warnings = 10;
@@ -718,7 +717,7 @@ done:
static void do_rebuild_sched_domains(struct work_struct *unused)
{
struct sched_domain_attr *attr;
- struct cpumask *doms;
+ cpumask_var_t *doms;
int ndoms;
get_online_cpus();
@@ -738,7 +737,7 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
{
}
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
struct sched_domain_attr **attributes)
{
*domains = NULL;
@@ -873,7 +872,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (retval < 0)
return retval;
- if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
+ if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
return -EINVAL;
}
retval = validate_change(cs, trialcs);
@@ -1324,9 +1323,10 @@ static int fmeter_getrate(struct fmeter *fmp)
static cpumask_var_t cpus_attach;
/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss,
- struct cgroup *cont, struct task_struct *tsk)
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+ struct task_struct *tsk, bool threadgroup)
{
+ int ret;
struct cpuset *cs = cgroup_cs(cont);
if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
@@ -1343,18 +1343,51 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
if (tsk->flags & PF_THREAD_BOUND)
return -EINVAL;
- return security_task_setscheduler(tsk, 0, NULL);
+ ret = security_task_setscheduler(tsk, 0, NULL);
+ if (ret)
+ return ret;
+ if (threadgroup) {
+ struct task_struct *c;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ ret = security_task_setscheduler(c, 0, NULL);
+ if (ret) {
+ rcu_read_unlock();
+ return ret;
+ }
+ }
+ rcu_read_unlock();
+ }
+ return 0;
+}
+
+static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
+ struct cpuset *cs)
+{
+ int err;
+ /*
+ * can_attach beforehand should guarantee that this doesn't fail.
+ * TODO: have a better way to handle failure here
+ */
+ err = set_cpus_allowed_ptr(tsk, cpus_attach);
+ WARN_ON_ONCE(err);
+
+ task_lock(tsk);
+ cpuset_change_task_nodemask(tsk, to);
+ task_unlock(tsk);
+ cpuset_update_task_spread_flag(cs, tsk);
+
}
-static void cpuset_attach(struct cgroup_subsys *ss,
- struct cgroup *cont, struct cgroup *oldcont,
- struct task_struct *tsk)
+static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+ struct cgroup *oldcont, struct task_struct *tsk,
+ bool threadgroup)
{
nodemask_t from, to;
struct mm_struct *mm;
struct cpuset *cs = cgroup_cs(cont);
struct cpuset *oldcs = cgroup_cs(oldcont);
- int err;
if (cs == &top_cpuset) {
cpumask_copy(cpus_attach, cpu_possible_mask);
@@ -1363,15 +1396,19 @@ static void cpuset_attach(struct cgroup_subsys *ss,
guarantee_online_cpus(cs, cpus_attach);
guarantee_online_mems(cs, &to);
}
- err = set_cpus_allowed_ptr(tsk, cpus_attach);
- if (err)
- return;
- task_lock(tsk);
- cpuset_change_task_nodemask(tsk, &to);
- task_unlock(tsk);
- cpuset_update_task_spread_flag(cs, tsk);
+ /* do per-task migration stuff possibly for each in the threadgroup */
+ cpuset_attach_task(tsk, &to, cs);
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ cpuset_attach_task(c, &to, cs);
+ }
+ rcu_read_unlock();
+ }
+ /* change mm; only needs to be done once even if threadgroup */
from = oldcs->mems_allowed;
to = cs->mems_allowed;
mm = get_task_mm(tsk);
@@ -1973,7 +2010,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
}
/* Continue past cpusets with all cpus, mems online */
- if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
+ if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
continue;
@@ -1982,7 +2019,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
/* Remove offline cpus and mems from this cpuset. */
mutex_lock(&callback_mutex);
cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
- cpu_online_mask);
+ cpu_active_mask);
nodes_and(cp->mems_allowed, cp->mems_allowed,
node_states[N_HIGH_MEMORY]);
mutex_unlock(&callback_mutex);
@@ -2014,14 +2051,16 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
unsigned long phase, void *unused_cpu)
{
struct sched_domain_attr *attr;
- struct cpumask *doms;
+ cpumask_var_t *doms;
int ndoms;
switch (phase) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
break;
default:
@@ -2030,7 +2069,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
cgroup_lock();
mutex_lock(&callback_mutex);
- cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+ cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
mutex_unlock(&callback_mutex);
scan_for_empty_cpusets(&top_cpuset);
ndoms = generate_sched_domains(&doms, &attr);
@@ -2077,7 +2116,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
void __init cpuset_init_smp(void)
{
- cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+ cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
hotcpu_notifier(cpuset_track_online_cpus, 0);
@@ -2499,15 +2538,9 @@ const struct file_operations proc_cpuset_operations = {
};
#endif /* CONFIG_PROC_PID_CPUSET */
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
{
- seq_printf(m, "Cpus_allowed:\t");
- seq_cpumask(m, &task->cpus_allowed);
- seq_printf(m, "\n");
- seq_printf(m, "Cpus_allowed_list:\t");
- seq_cpumask_list(m, &task->cpus_allowed);
- seq_printf(m, "\n");
seq_printf(m, "Mems_allowed:\t");
seq_nodemask(m, &task->mems_allowed);
seq_printf(m, "\n");
diff --git a/kernel/cred.c b/kernel/cred.c
index d7f7a01082e..dd76cfe5f5b 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -782,6 +782,25 @@ EXPORT_SYMBOL(set_create_files_as);
#ifdef CONFIG_DEBUG_CREDENTIALS
+bool creds_are_invalid(const struct cred *cred)
+{
+ if (cred->magic != CRED_MAGIC)
+ return true;
+ if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers))
+ return true;
+#ifdef CONFIG_SECURITY_SELINUX
+ if (selinux_is_enabled()) {
+ if ((unsigned long) cred->security < PAGE_SIZE)
+ return true;
+ if ((*(u32 *)cred->security & 0xffffff00) ==
+ (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))
+ return true;
+ }
+#endif
+ return false;
+}
+EXPORT_SYMBOL(creds_are_invalid);
+
/*
* dump invalid credentials
*/
diff --git a/kernel/exit.c b/kernel/exit.c
index 60d6fdcc926..5962d7ccf24 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -49,6 +49,7 @@
#include <linux/init_task.h>
#include <linux/perf_event.h>
#include <trace/events/sched.h>
+#include <linux/hw_breakpoint.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -110,9 +111,9 @@ static void __exit_signal(struct task_struct *tsk)
* We won't ever get here for the group leader, since it
* will have been the last reference on the signal_struct.
*/
- sig->utime = cputime_add(sig->utime, task_utime(tsk));
- sig->stime = cputime_add(sig->stime, task_stime(tsk));
- sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+ sig->utime = cputime_add(sig->utime, tsk->utime);
+ sig->stime = cputime_add(sig->stime, tsk->stime);
+ sig->gtime = cputime_add(sig->gtime, tsk->gtime);
sig->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
sig->nvcsw += tsk->nvcsw;
@@ -359,10 +360,8 @@ void __set_special_pids(struct pid *pid)
{
struct task_struct *curr = current->group_leader;
- if (task_session(curr) != pid) {
+ if (task_session(curr) != pid)
change_pid(curr, PIDTYPE_SID, pid);
- proc_sid_connector(curr);
- }
if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
@@ -934,7 +933,7 @@ NORET_TYPE void do_exit(long code)
* an exiting task cleaning up the robust pi futexes.
*/
smp_mb();
- spin_unlock_wait(&tsk->pi_lock);
+ raw_spin_unlock_wait(&tsk->pi_lock);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
@@ -972,16 +971,18 @@ NORET_TYPE void do_exit(long code)
exit_thread();
cgroup_exit(tsk, 1);
- if (group_dead && tsk->signal->leader)
+ if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
- if (tsk->binfmt)
- module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
/*
+ * FIXME: do that only when needed, using sched_exit tracepoint
+ */
+ flush_ptrace_hw_breakpoint(tsk);
+ /*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
@@ -993,8 +994,6 @@ NORET_TYPE void do_exit(long code)
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
- if (unlikely(!list_empty(&tsk->pi_state_list)))
- exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
#endif
@@ -1010,7 +1009,7 @@ NORET_TYPE void do_exit(long code)
tsk->flags |= PF_EXITPIDONE;
if (tsk->io_context)
- exit_io_context();
+ exit_io_context(tsk);
if (tsk->splice_pipe)
__free_pipe_info(tsk->splice_pipe);
@@ -1097,28 +1096,28 @@ struct wait_opts {
int __user *wo_stat;
struct rusage __user *wo_rusage;
+ wait_queue_t child_wait;
int notask_error;
};
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
- struct pid *pid = NULL;
- if (type == PIDTYPE_PID)
- pid = task->pids[type].pid;
- else if (type < PIDTYPE_MAX)
- pid = task->group_leader->pids[type].pid;
- return pid;
+ if (type != PIDTYPE_PID)
+ task = task->group_leader;
+ return task->pids[type].pid;
}
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
- int err;
-
- if (wo->wo_type < PIDTYPE_MAX) {
- if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
- return 0;
- }
+ return wo->wo_type == PIDTYPE_MAX ||
+ task_pid_type(p, wo->wo_type) == wo->wo_pid;
+}
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+ if (!eligible_pid(wo, p))
+ return 0;
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
@@ -1128,10 +1127,6 @@ static int eligible_child(struct wait_opts *wo, struct task_struct *p)
&& !(wo->wo_flags & __WALL))
return 0;
- err = security_task_wait(p);
- if (err)
- return err;
-
return 1;
}
@@ -1144,18 +1139,20 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
put_task_struct(p);
infop = wo->wo_info;
- if (!retval)
- retval = put_user(SIGCHLD, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user((short)why, &infop->si_code);
- if (!retval)
- retval = put_user(pid, &infop->si_pid);
- if (!retval)
- retval = put_user(uid, &infop->si_uid);
- if (!retval)
- retval = put_user(status, &infop->si_status);
+ if (infop) {
+ if (!retval)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval)
+ retval = put_user((short)why, &infop->si_code);
+ if (!retval)
+ retval = put_user(pid, &infop->si_pid);
+ if (!retval)
+ retval = put_user(uid, &infop->si_uid);
+ if (!retval)
+ retval = put_user(status, &infop->si_status);
+ }
if (!retval)
retval = pid;
return retval;
@@ -1213,6 +1210,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
struct signal_struct *psig;
struct signal_struct *sig;
unsigned long maxrss;
+ cputime_t tgutime, tgstime;
/*
* The resource counters for the group leader are in its
@@ -1228,20 +1226,23 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
* need to protect the access to parent->signal fields,
* as other threads in the parent group can be right
* here reaping other children at the same time.
+ *
+ * We use thread_group_times() to get times for the thread
+ * group, which consolidates times for all threads in the
+ * group including the group leader.
*/
+ thread_group_times(p, &tgutime, &tgstime);
spin_lock_irq(&p->real_parent->sighand->siglock);
psig = p->real_parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
- cputime_add(p->utime,
- cputime_add(sig->utime,
- sig->cutime)));
+ cputime_add(tgutime,
+ sig->cutime));
psig->cstime =
cputime_add(psig->cstime,
- cputime_add(p->stime,
- cputime_add(sig->stime,
- sig->cstime)));
+ cputime_add(tgstime,
+ sig->cstime));
psig->cgtime =
cputime_add(psig->cgtime,
cputime_add(p->gtime,
@@ -1485,13 +1486,14 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
* then ->notask_error is 0 if @p is an eligible child,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
- int ptrace, struct task_struct *p)
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
+ struct task_struct *p)
{
int ret = eligible_child(wo, p);
if (!ret)
return ret;
+ ret = security_task_wait(p);
if (unlikely(ret < 0)) {
/*
* If we have not yet seen any eligible child,
@@ -1553,7 +1555,7 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
* Do not consider detached threads.
*/
if (!task_detached(p)) {
- int ret = wait_consider_task(wo, tsk, 0, p);
+ int ret = wait_consider_task(wo, 0, p);
if (ret)
return ret;
}
@@ -1567,7 +1569,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
struct task_struct *p;
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
- int ret = wait_consider_task(wo, tsk, 1, p);
+ int ret = wait_consider_task(wo, 1, p);
if (ret)
return ret;
}
@@ -1575,15 +1577,38 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
return 0;
}
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct wait_opts *wo = container_of(wait, struct wait_opts,
+ child_wait);
+ struct task_struct *p = key;
+
+ if (!eligible_pid(wo, p))
+ return 0;
+
+ if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+ return 0;
+
+ return default_wake_function(wait, mode, sync, key);
+}
+
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+ __wake_up_sync_key(&parent->signal->wait_chldexit,
+ TASK_INTERRUPTIBLE, 1, p);
+}
+
static long do_wait(struct wait_opts *wo)
{
- DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int retval;
trace_sched_process_wait(wo->wo_pid);
- add_wait_queue(&current->signal->wait_chldexit,&wait);
+ init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+ wo->child_wait.private = current;
+ add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
repeat:
/*
* If there is nothing that can match our critiera just get out.
@@ -1624,32 +1649,7 @@ notask:
}
end:
__set_current_state(TASK_RUNNING);
- remove_wait_queue(&current->signal->wait_chldexit,&wait);
- if (wo->wo_info) {
- struct siginfo __user *infop = wo->wo_info;
-
- if (retval > 0)
- retval = 0;
- else {
- /*
- * For a WNOHANG return, clear out all the fields
- * we would set so the user can easily tell the
- * difference.
- */
- if (!retval)
- retval = put_user(0, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user(0, &infop->si_code);
- if (!retval)
- retval = put_user(0, &infop->si_pid);
- if (!retval)
- retval = put_user(0, &infop->si_uid);
- if (!retval)
- retval = put_user(0, &infop->si_status);
- }
- }
+ remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
return retval;
}
@@ -1694,6 +1694,29 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
wo.wo_stat = NULL;
wo.wo_rusage = ru;
ret = do_wait(&wo);
+
+ if (ret > 0) {
+ ret = 0;
+ } else if (infop) {
+ /*
+ * For a WNOHANG return, clear out all the fields
+ * we would set so the user can easily tell the
+ * difference.
+ */
+ if (!ret)
+ ret = put_user(0, &infop->si_signo);
+ if (!ret)
+ ret = put_user(0, &infop->si_errno);
+ if (!ret)
+ ret = put_user(0, &infop->si_code);
+ if (!ret)
+ ret = put_user(0, &infop->si_pid);
+ if (!ret)
+ ret = put_user(0, &infop->si_uid);
+ if (!ret)
+ ret = put_user(0, &infop->si_status);
+ }
+
put_pid(pid);
/* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index 51ad0b0b726..202a0ba63d3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -64,6 +64,7 @@
#include <linux/magic.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
+#include <linux/user-return-notifier.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -91,7 +92,7 @@ int nr_processes(void)
int cpu;
int total = 0;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
total += per_cpu(process_counts, cpu);
return total;
@@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
goto out;
setup_thread_stack(tsk, orig);
+ clear_user_return_notifier(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
@@ -434,6 +436,14 @@ __setup("coredump_filter=", coredump_filter_setup);
#include <linux/init_task.h>
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+ spin_lock_init(&mm->ioctx_lock);
+ INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
+
static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
{
atomic_set(&mm->mm_users, 1);
@@ -447,10 +457,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
set_mm_counter(mm, file_rss, 0);
set_mm_counter(mm, anon_rss, 0);
spin_lock_init(&mm->page_table_lock);
- spin_lock_init(&mm->ioctx_lock);
- INIT_HLIST_HEAD(&mm->ioctx_list);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
+ mm_init_aio(mm);
mm_init_owner(mm, p);
if (likely(!mm_alloc_pgd(mm))) {
@@ -511,6 +520,8 @@ void mmput(struct mm_struct *mm)
spin_unlock(&mmlist_lock);
}
put_swap_token(mm);
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
mmdrop(mm);
}
}
@@ -561,12 +572,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
/* Get rid of any futexes when releasing the mm */
#ifdef CONFIG_FUTEX
- if (unlikely(tsk->robust_list))
+ if (unlikely(tsk->robust_list)) {
exit_robust_list(tsk);
+ tsk->robust_list = NULL;
+ }
#ifdef CONFIG_COMPAT
- if (unlikely(tsk->compat_robust_list))
+ if (unlikely(tsk->compat_robust_list)) {
compat_exit_robust_list(tsk);
+ tsk->compat_robust_list = NULL;
+ }
#endif
+ if (unlikely(!list_empty(&tsk->pi_state_list)))
+ exit_pi_state_list(tsk);
#endif
/* Get rid of any cached register state */
@@ -636,9 +653,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
+ if (mm->binfmt && !try_module_get(mm->binfmt->module))
+ goto free_pt;
+
return mm;
free_pt:
+ /* don't put binfmt in mmput, we haven't got module yet */
+ mm->binfmt = NULL;
mmput(mm);
fail_nomem:
@@ -864,6 +886,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
sig->gtime = cputime_zero;
sig->cgtime = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+ sig->prev_utime = sig->prev_stime = cputime_zero;
+#endif
sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
@@ -914,9 +939,9 @@ SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
static void rt_mutex_init_task(struct task_struct *p)
{
- spin_lock_init(&p->pi_lock);
+ raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&p->pi_waiters, &p->pi_lock);
+ plist_head_init_raw(&p->pi_waiters, &p->pi_lock);
p->pi_blocked_on = NULL;
#endif
}
@@ -979,6 +1004,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
+ /*
+ * Siblings of global init remain as zombies on exit since they are
+ * not reaped by their parent (swapper). To solve this and to avoid
+ * multi-rooted process trees, prevent global and container-inits
+ * from creating siblings.
+ */
+ if ((clone_flags & CLONE_PARENT) &&
+ current->signal->flags & SIGNAL_UNKILLABLE)
+ return ERR_PTR(-EINVAL);
+
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
@@ -1020,9 +1055,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
- if (p->binfmt && !try_module_get(p->binfmt->module))
- goto bad_fork_cleanup_put_domain;
-
p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
copy_flags(clone_flags, p);
@@ -1039,8 +1071,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
+#endif
p->default_timer_slack_ns = current->timer_slack_ns;
@@ -1093,6 +1127,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+ p->memcg_batch.do_batch = 0;
+ p->memcg_batch.memcg = NULL;
+#endif
p->bts = NULL;
@@ -1172,9 +1210,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->sas_ss_sp = p->sas_ss_size = 0;
/*
- * Syscall tracing should be turned off in the child regardless
- * of CLONE_PTRACE.
+ * Syscall tracing and stepping should be turned off in the
+ * child regardless of CLONE_PTRACE.
*/
+ user_disable_single_step(p);
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
@@ -1283,7 +1322,8 @@ bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_io:
- put_io_context(p->io_context);
+ if (p->io_context)
+ exit_io_context(p);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
@@ -1310,9 +1350,6 @@ bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
- if (p->binfmt)
- module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
diff --git a/kernel/futex.c b/kernel/futex.c
index 248dd119a86..8e3c3ffe1b9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -89,36 +89,36 @@ struct futex_pi_state {
union futex_key key;
};
-/*
- * We use this hashed waitqueue instead of a normal wait_queue_t, so
+/**
+ * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @task: the task waiting on the futex
+ * @lock_ptr: the hash bucket lock
+ * @key: the key the futex is hashed on
+ * @pi_state: optional priority inheritance state
+ * @rt_waiter: rt_waiter storage for use with requeue_pi
+ * @requeue_pi_key: the requeue_pi target futex key
+ * @bitset: bitset for the optional bitmasked wakeup
+ *
+ * We use this hashed waitqueue, instead of a normal wait_queue_t, so
* we can wake only the relevant ones (hashed queues may be shared).
*
* A futex_q has a woken state, just like tasks have TASK_RUNNING.
* It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
* The order of wakup is always to make the first condition true, then
- * wake up q->waiter, then make the second condition true.
+ * the second.
+ *
+ * PI futexes are typically woken before they are removed from the hash list via
+ * the rt_mutex code. See unqueue_me_pi().
*/
struct futex_q {
struct plist_node list;
- /* Waiter reference */
- struct task_struct *task;
- /* Which hash list lock to use: */
+ struct task_struct *task;
spinlock_t *lock_ptr;
-
- /* Key which the futex is hashed on: */
union futex_key key;
-
- /* Optional priority inheritance state: */
struct futex_pi_state *pi_state;
-
- /* rt_waiter storage for requeue_pi: */
struct rt_mutex_waiter *rt_waiter;
-
- /* The expected requeue pi target futex key: */
union futex_key *requeue_pi_key;
-
- /* Bitset for the optional bitmasked wakeup */
u32 bitset;
};
@@ -150,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
*/
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
- return (key1->both.word == key2->both.word
+ return (key1 && key2
+ && key1->both.word == key2->both.word
&& key1->both.ptr == key2->both.ptr
&& key1->both.offset == key2->both.offset);
}
@@ -198,11 +199,12 @@ static void drop_futex_key_refs(union futex_key *key)
}
/**
- * get_futex_key - Get parameters which are the keys for a futex.
- * @uaddr: virtual address of the futex
- * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
- * @key: address where result is stored.
- * @rw: mapping needs to be read/write (values: VERIFY_READ, VERIFY_WRITE)
+ * get_futex_key() - Get parameters which are the keys for a futex
+ * @uaddr: virtual address of the futex
+ * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @key: address where result is stored.
+ * @rw: mapping needs to be read/write (values: VERIFY_READ,
+ * VERIFY_WRITE)
*
* Returns a negative error code or 0
* The key words are stored in *key on success.
@@ -288,8 +290,8 @@ void put_futex_key(int fshared, union futex_key *key)
drop_futex_key_refs(key);
}
-/*
- * fault_in_user_writeable - fault in user address and verify RW access
+/**
+ * fault_in_user_writeable() - Fault in user address and verify RW access
* @uaddr: pointer to faulting user space address
*
* Slow path to fixup the fault we just took in the atomic write
@@ -302,15 +304,21 @@ void put_futex_key(int fshared, union futex_key *key)
*/
static int fault_in_user_writeable(u32 __user *uaddr)
{
- int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
- 1, 1, 0, NULL, NULL);
+ struct mm_struct *mm = current->mm;
+ int ret;
+
+ down_read(&mm->mmap_sem);
+ ret = get_user_pages(current, mm, (unsigned long)uaddr,
+ 1, 1, 0, NULL, NULL);
+ up_read(&mm->mmap_sem);
+
return ret < 0 ? ret : 0;
}
/**
* futex_top_waiter() - Return the highest priority waiter on a futex
- * @hb: the hash bucket the futex_q's reside in
- * @key: the futex key (to distinguish it from other futex futex_q's)
+ * @hb: the hash bucket the futex_q's reside in
+ * @key: the futex key (to distinguish it from other futex futex_q's)
*
* Must be called with the hb lock held.
*/
@@ -395,9 +403,9 @@ static void free_pi_state(struct futex_pi_state *pi_state)
* and has cleaned up the pi_state already
*/
if (pi_state->owner) {
- spin_lock_irq(&pi_state->owner->pi_lock);
+ raw_spin_lock_irq(&pi_state->owner->pi_lock);
list_del_init(&pi_state->list);
- spin_unlock_irq(&pi_state->owner->pi_lock);
+ raw_spin_unlock_irq(&pi_state->owner->pi_lock);
rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
}
@@ -462,18 +470,18 @@ void exit_pi_state_list(struct task_struct *curr)
* pi_state_list anymore, but we have to be careful
* versus waiters unqueueing themselves:
*/
- spin_lock_irq(&curr->pi_lock);
+ raw_spin_lock_irq(&curr->pi_lock);
while (!list_empty(head)) {
next = head->next;
pi_state = list_entry(next, struct futex_pi_state, list);
key = pi_state->key;
hb = hash_futex(&key);
- spin_unlock_irq(&curr->pi_lock);
+ raw_spin_unlock_irq(&curr->pi_lock);
spin_lock(&hb->lock);
- spin_lock_irq(&curr->pi_lock);
+ raw_spin_lock_irq(&curr->pi_lock);
/*
* We dropped the pi-lock, so re-check whether this
* task still owns the PI-state:
@@ -487,15 +495,15 @@ void exit_pi_state_list(struct task_struct *curr)
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
pi_state->owner = NULL;
- spin_unlock_irq(&curr->pi_lock);
+ raw_spin_unlock_irq(&curr->pi_lock);
rt_mutex_unlock(&pi_state->pi_mutex);
spin_unlock(&hb->lock);
- spin_lock_irq(&curr->pi_lock);
+ raw_spin_lock_irq(&curr->pi_lock);
}
- spin_unlock_irq(&curr->pi_lock);
+ raw_spin_unlock_irq(&curr->pi_lock);
}
static int
@@ -550,7 +558,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
* change of the task flags, we do this protected by
* p->pi_lock:
*/
- spin_lock_irq(&p->pi_lock);
+ raw_spin_lock_irq(&p->pi_lock);
if (unlikely(p->flags & PF_EXITING)) {
/*
* The task is on the way out. When PF_EXITPIDONE is
@@ -559,7 +567,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
*/
int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN;
- spin_unlock_irq(&p->pi_lock);
+ raw_spin_unlock_irq(&p->pi_lock);
put_task_struct(p);
return ret;
}
@@ -578,7 +586,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &p->pi_state_list);
pi_state->owner = p;
- spin_unlock_irq(&p->pi_lock);
+ raw_spin_unlock_irq(&p->pi_lock);
put_task_struct(p);
@@ -588,7 +596,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
}
/**
- * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
* @uaddr: the pi futex user address
* @hb: the pi futex hash bucket
* @key: the futex key associated with uaddr and hb
@@ -752,7 +760,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
if (!pi_state)
return -EINVAL;
- spin_lock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_lock(&pi_state->pi_mutex.wait_lock);
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
/*
@@ -781,23 +789,23 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
else if (curval != uval)
ret = -EINVAL;
if (ret) {
- spin_unlock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
return ret;
}
}
- spin_lock_irq(&pi_state->owner->pi_lock);
+ raw_spin_lock_irq(&pi_state->owner->pi_lock);
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
- spin_unlock_irq(&pi_state->owner->pi_lock);
+ raw_spin_unlock_irq(&pi_state->owner->pi_lock);
- spin_lock_irq(&new_owner->pi_lock);
+ raw_spin_lock_irq(&new_owner->pi_lock);
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &new_owner->pi_state_list);
pi_state->owner = new_owner;
- spin_unlock_irq(&new_owner->pi_lock);
+ raw_spin_unlock_irq(&new_owner->pi_lock);
- spin_unlock(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
rt_mutex_unlock(&pi_state->pi_mutex);
return 0;
@@ -915,8 +923,8 @@ retry:
hb1 = hash_futex(&key1);
hb2 = hash_futex(&key2);
- double_lock_hb(hb1, hb2);
retry_private:
+ double_lock_hb(hb1, hb2);
op_ret = futex_atomic_op_inuser(op, uaddr2);
if (unlikely(op_ret < 0)) {
@@ -1002,7 +1010,7 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
plist_add(&q->list, &hb2->chain);
q->lock_ptr = &hb2->lock;
#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.lock = &hb2->lock;
+ q->list.plist.spinlock = &hb2->lock;
#endif
}
get_futex_key_refs(key2);
@@ -1011,9 +1019,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
/**
* requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
- * q: the futex_q
- * key: the key of the requeue target futex
- * hb: the hash_bucket of the requeue target futex
+ * @q: the futex_q
+ * @key: the key of the requeue target futex
+ * @hb: the hash_bucket of the requeue target futex
*
* During futex_requeue, with requeue_pi=1, it is possible to acquire the
* target futex if it is uncontended or via a lock steal. Set the futex_q key
@@ -1027,7 +1035,6 @@ static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
struct futex_hash_bucket *hb)
{
- drop_futex_key_refs(&q->key);
get_futex_key_refs(key);
q->key = *key;
@@ -1039,7 +1046,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
q->lock_ptr = &hb->lock;
#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.lock = &hb->lock;
+ q->list.plist.spinlock = &hb->lock;
#endif
wake_up_state(q->task, TASK_NORMAL);
@@ -1225,6 +1232,7 @@ retry_private:
*/
if (ret == 1) {
WARN_ON(pi_state);
+ drop_count++;
task_count++;
ret = get_futex_value_locked(&curval2, uaddr2);
if (!ret)
@@ -1303,6 +1311,7 @@ retry_private:
if (ret == 1) {
/* We got the lock. */
requeue_pi_wake_futex(this, &key2, hb2);
+ drop_count++;
continue;
} else if (ret) {
/* -EDEADLK */
@@ -1350,6 +1359,25 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
return hb;
}
+static inline void
+queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+{
+ spin_unlock(&hb->lock);
+ drop_futex_key_refs(&q->key);
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q: The futex_q to enqueue
+ * @hb: The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me(). The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
{
int prio;
@@ -1366,26 +1394,24 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
plist_node_init(&q->list, prio);
#ifdef CONFIG_DEBUG_PI_LIST
- q->list.plist.lock = &hb->lock;
+ q->list.plist.spinlock = &hb->lock;
#endif
plist_add(&q->list, &hb->chain);
q->task = current;
spin_unlock(&hb->lock);
}
-static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
-{
- spin_unlock(&hb->lock);
- drop_futex_key_refs(&q->key);
-}
-
-/*
- * queue_me and unqueue_me must be called as a pair, each
- * exactly once. They are called with the hashed spinlock held.
+/**
+ * unqueue_me() - Remove the futex_q from its futex_hash_bucket
+ * @q: The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
+ * be paired with exactly one earlier call to queue_me().
+ *
+ * Returns:
+ * 1 - if the futex_q was still queued (and we removed unqueued it)
+ * 0 - if the futex_q was already removed by the waking thread
*/
-
-/* Return 1 if we were still queued (ie. 0 means we were woken) */
static int unqueue_me(struct futex_q *q)
{
spinlock_t *lock_ptr;
@@ -1503,18 +1529,18 @@ retry:
* itself.
*/
if (pi_state->owner != NULL) {
- spin_lock_irq(&pi_state->owner->pi_lock);
+ raw_spin_lock_irq(&pi_state->owner->pi_lock);
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
- spin_unlock_irq(&pi_state->owner->pi_lock);
+ raw_spin_unlock_irq(&pi_state->owner->pi_lock);
}
pi_state->owner = newowner;
- spin_lock_irq(&newowner->pi_lock);
+ raw_spin_lock_irq(&newowner->pi_lock);
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &newowner->pi_state_list);
- spin_unlock_irq(&newowner->pi_lock);
+ raw_spin_unlock_irq(&newowner->pi_lock);
return 0;
/*
@@ -1638,17 +1664,14 @@ out:
static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
struct hrtimer_sleeper *timeout)
{
- queue_me(q, hb);
-
/*
- * There might have been scheduling since the queue_me(), as we
- * cannot hold a spinlock across the get_user() in case it
- * faults, and we cannot just set TASK_INTERRUPTIBLE state when
- * queueing ourselves into the futex hash. This code thus has to
- * rely on the futex_wake() code removing us from hash when it
- * wakes us up.
+ * The task state is guaranteed to be set before another task can
+ * wake it. set_current_state() is implemented using set_mb() and
+ * queue_me() calls spin_unlock() upon completion, both serializing
+ * access to the hash list and forcing another memory barrier.
*/
set_current_state(TASK_INTERRUPTIBLE);
+ queue_me(q, hb);
/* Arm the timer */
if (timeout) {
@@ -1658,8 +1681,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
}
/*
- * !plist_node_empty() is safe here without any lock.
- * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+ * If we have been removed from the hash list, then another task
+ * has tried to wake us, and we can skip the call to schedule().
*/
if (likely(!plist_node_empty(&q->list))) {
/*
@@ -1776,6 +1799,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
current->timer_slack_ns);
}
+retry:
/* Prepare to wait on uaddr. */
ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
if (ret)
@@ -1793,9 +1817,14 @@ static int futex_wait(u32 __user *uaddr, int fshared,
goto out_put_key;
/*
- * We expect signal_pending(current), but another thread may
- * have handled it for us already.
+ * We expect signal_pending(current), but we might be the
+ * victim of a spurious wakeup as well.
*/
+ if (!signal_pending(current)) {
+ put_futex_key(fshared, &q.key);
+ goto retry;
+ }
+
ret = -ERESTARTSYS;
if (!abs_time)
goto out_put_key;
@@ -2102,11 +2131,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* Unqueue the futex_q and determine which it was.
*/
plist_del(&q->list, &q->list.plist);
- drop_futex_key_refs(&q->key);
+ /* Handle spurious wakeups gracefully */
+ ret = -EWOULDBLOCK;
if (timeout && !timeout->task)
ret = -ETIMEDOUT;
- else
+ else if (signal_pending(current))
ret = -ERESTARTNOINTR;
}
return ret;
@@ -2114,12 +2144,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
/**
* futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
- * @uaddr: the futex we initialyl wait on (non-pi)
+ * @uaddr: the futex we initially wait on (non-pi)
* @fshared: whether the futexes are shared (1) or not (0). They must be
* the same type, no requeueing from private to shared, etc.
* @val: the expected value of uaddr
* @abs_time: absolute timeout
- * @bitset: 32 bit wakeup bitset set by userspace, defaults to all.
+ * @bitset: 32 bit wakeup bitset set by userspace, defaults to all
* @clockrt: whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
* @uaddr2: the pi futex we will take prior to returning to user-space
*
@@ -2246,7 +2276,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
res = fixup_owner(uaddr2, fshared, &q, !ret);
/*
* If fixup_owner() returned an error, proprogate that. If it
- * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+ * acquired the lock, clear -ETIMEDOUT or -EINTR.
*/
if (res)
ret = (res < 0) ? res : 0;
@@ -2302,9 +2332,9 @@ out:
*/
/**
- * sys_set_robust_list - set the robust-futex list head of a task
- * @head: pointer to the list-head
- * @len: length of the list-head, as userspace expects
+ * sys_set_robust_list() - Set the robust-futex list head of a task
+ * @head: pointer to the list-head
+ * @len: length of the list-head, as userspace expects
*/
SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
size_t, len)
@@ -2323,10 +2353,10 @@ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
}
/**
- * sys_get_robust_list - get the robust-futex list head of a task
- * @pid: pid of the process [zero for current task]
- * @head_ptr: pointer to a list-head pointer, the kernel fills it in
- * @len_ptr: pointer to a length field, the kernel fills in the header size
+ * sys_get_robust_list() - Get the robust-futex list head of a task
+ * @pid: pid of the process [zero for current task]
+ * @head_ptr: pointer to a list-head pointer, the kernel fills it in
+ * @len_ptr: pointer to a length field, the kernel fills in the header size
*/
SYSCALL_DEFINE3(get_robust_list, int, pid,
struct robust_list_head __user * __user *, head_ptr,
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 654efd09f6a..70a298d6da7 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -34,7 +34,7 @@ config GCOV_KERNEL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
depends on GCOV_KERNEL
- depends on S390 || X86 || (PPC && EXPERIMENTAL)
+ depends on S390 || X86 || (PPC && EXPERIMENTAL) || MICROBLAZE
default n
---help---
This options activates profiling for the entire kernel.
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index e5d98ce50f8..0086628b6e9 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -127,11 +127,11 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
for (;;) {
base = timer->base;
if (likely(base != NULL)) {
- spin_lock_irqsave(&base->cpu_base->lock, *flags);
+ raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
return base;
/* The timer has migrated to another CPU: */
- spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
+ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
}
cpu_relax();
}
@@ -208,13 +208,13 @@ again:
/* See the comment in lock_timer_base() */
timer->base = NULL;
- spin_unlock(&base->cpu_base->lock);
- spin_lock(&new_base->cpu_base->lock);
+ raw_spin_unlock(&base->cpu_base->lock);
+ raw_spin_lock(&new_base->cpu_base->lock);
if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
cpu = this_cpu;
- spin_unlock(&new_base->cpu_base->lock);
- spin_lock(&base->cpu_base->lock);
+ raw_spin_unlock(&new_base->cpu_base->lock);
+ raw_spin_lock(&base->cpu_base->lock);
timer->base = base;
goto again;
}
@@ -230,7 +230,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
struct hrtimer_clock_base *base = timer->base;
- spin_lock_irqsave(&base->cpu_base->lock, *flags);
+ raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
return base;
}
@@ -509,13 +509,14 @@ static inline int hrtimer_hres_active(void)
* next event
* Called with interrupts disabled and base->lock held
*/
-static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
+static void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
{
int i;
struct hrtimer_clock_base *base = cpu_base->clock_base;
- ktime_t expires;
+ ktime_t expires, expires_next;
- cpu_base->expires_next.tv64 = KTIME_MAX;
+ expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
@@ -531,10 +532,15 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
*/
if (expires.tv64 < 0)
expires.tv64 = 0;
- if (expires.tv64 < cpu_base->expires_next.tv64)
- cpu_base->expires_next = expires;
+ if (expires.tv64 < expires_next.tv64)
+ expires_next = expires;
}
+ if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
+ return;
+
+ cpu_base->expires_next.tv64 = expires_next.tv64;
+
if (cpu_base->expires_next.tv64 != KTIME_MAX)
tick_program_event(cpu_base->expires_next, 1);
}
@@ -551,7 +557,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
static int hrtimer_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
- ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
int res;
@@ -576,7 +582,16 @@ static int hrtimer_reprogram(struct hrtimer *timer,
if (expires.tv64 < 0)
return -ETIME;
- if (expires.tv64 >= expires_next->tv64)
+ if (expires.tv64 >= cpu_base->expires_next.tv64)
+ return 0;
+
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * do not schedule a timer which is earlier than the expiry
+ * which we enforced in the hang detection. We want the system
+ * to make progress.
+ */
+ if (cpu_base->hang_detected)
return 0;
/*
@@ -584,7 +599,7 @@ static int hrtimer_reprogram(struct hrtimer *timer,
*/
res = tick_program_event(expires, 0);
if (!IS_ERR_VALUE(res))
- *expires_next = expires;
+ cpu_base->expires_next = expires;
return res;
}
@@ -613,12 +628,12 @@ static void retrigger_next_event(void *arg)
base = &__get_cpu_var(hrtimer_bases);
/* Adjust CLOCK_REALTIME offset */
- spin_lock(&base->lock);
+ raw_spin_lock(&base->lock);
base->clock_base[CLOCK_REALTIME].offset =
timespec_to_ktime(realtime_offset);
- hrtimer_force_reprogram(base);
- spin_unlock(&base->lock);
+ hrtimer_force_reprogram(base, 0);
+ raw_spin_unlock(&base->lock);
}
/*
@@ -679,9 +694,9 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
{
if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
if (wakeup) {
- spin_unlock(&base->cpu_base->lock);
+ raw_spin_unlock(&base->cpu_base->lock);
raise_softirq_irqoff(HRTIMER_SOFTIRQ);
- spin_lock(&base->cpu_base->lock);
+ raw_spin_lock(&base->cpu_base->lock);
} else
__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
@@ -720,8 +735,6 @@ static int hrtimer_switch_to_hres(void)
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
local_irq_restore(flags);
- printk(KERN_DEBUG "Switched to high resolution mode on CPU %d\n",
- smp_processor_id());
return 1;
}
@@ -730,7 +743,8 @@ static int hrtimer_switch_to_hres(void)
static inline int hrtimer_hres_active(void) { return 0; }
static inline int hrtimer_is_hres_enabled(void) { return 0; }
static inline int hrtimer_switch_to_hres(void) { return 0; }
-static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { }
+static inline void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
struct hrtimer_clock_base *base,
int wakeup)
@@ -742,17 +756,33 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
-#ifdef CONFIG_TIMER_STATS
-void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
+static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
+#ifdef CONFIG_TIMER_STATS
if (timer->start_site)
return;
-
- timer->start_site = addr;
+ timer->start_site = __builtin_return_address(0);
memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
timer->start_pid = current->pid;
+#endif
+}
+
+static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ timer->start_site = NULL;
+#endif
}
+
+static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ if (likely(!timer_stats_active))
+ return;
+ timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+ timer->function, timer->start_comm, 0);
#endif
+}
/*
* Counterpart to lock_hrtimer_base above:
@@ -760,7 +790,7 @@ void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer, void *addr)
static inline
void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
{
- spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
+ raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
}
/**
@@ -873,19 +903,29 @@ static void __remove_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base,
unsigned long newstate, int reprogram)
{
- if (timer->state & HRTIMER_STATE_ENQUEUED) {
- /*
- * Remove the timer from the rbtree and replace the
- * first entry pointer if necessary.
- */
- if (base->first == &timer->node) {
- base->first = rb_next(&timer->node);
- /* Reprogram the clock event device. if enabled */
- if (reprogram && hrtimer_hres_active())
- hrtimer_force_reprogram(base->cpu_base);
+ if (!(timer->state & HRTIMER_STATE_ENQUEUED))
+ goto out;
+
+ /*
+ * Remove the timer from the rbtree and replace the first
+ * entry pointer if necessary.
+ */
+ if (base->first == &timer->node) {
+ base->first = rb_next(&timer->node);
+#ifdef CONFIG_HIGH_RES_TIMERS
+ /* Reprogram the clock event device. if enabled */
+ if (reprogram && hrtimer_hres_active()) {
+ ktime_t expires;
+
+ expires = ktime_sub(hrtimer_get_expires(timer),
+ base->offset);
+ if (base->cpu_base->expires_next.tv64 == expires.tv64)
+ hrtimer_force_reprogram(base->cpu_base, 1);
}
- rb_erase(&timer->node, &base->active);
+#endif
}
+ rb_erase(&timer->node, &base->active);
+out:
timer->state = newstate;
}
@@ -1083,7 +1123,7 @@ ktime_t hrtimer_get_next_event(void)
unsigned long flags;
int i;
- spin_lock_irqsave(&cpu_base->lock, flags);
+ raw_spin_lock_irqsave(&cpu_base->lock, flags);
if (!hrtimer_hres_active()) {
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
@@ -1100,7 +1140,7 @@ ktime_t hrtimer_get_next_event(void)
}
}
- spin_unlock_irqrestore(&cpu_base->lock, flags);
+ raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
if (mindelta.tv64 < 0)
mindelta.tv64 = 0;
@@ -1182,11 +1222,11 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
* they get migrated to another cpu, therefore its safe to unlock
* the timer base.
*/
- spin_unlock(&cpu_base->lock);
+ raw_spin_unlock(&cpu_base->lock);
trace_hrtimer_expire_entry(timer, now);
restart = fn(timer);
trace_hrtimer_expire_exit(timer);
- spin_lock(&cpu_base->lock);
+ raw_spin_lock(&cpu_base->lock);
/*
* Note: We clear the CALLBACK bit after enqueue_hrtimer and
@@ -1202,29 +1242,6 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
#ifdef CONFIG_HIGH_RES_TIMERS
-static int force_clock_reprogram;
-
-/*
- * After 5 iteration's attempts, we consider that hrtimer_interrupt()
- * is hanging, which could happen with something that slows the interrupt
- * such as the tracing. Then we force the clock reprogramming for each future
- * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
- * threshold that we will overwrite.
- * The next tick event will be scheduled to 3 times we currently spend on
- * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
- * 1/4 of their time to process the hrtimer interrupts. This is enough to
- * let it running without serious starvation.
- */
-
-static inline void
-hrtimer_interrupt_hanging(struct clock_event_device *dev,
- ktime_t try_time)
-{
- force_clock_reprogram = 1;
- dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
- printk(KERN_WARNING "hrtimer: interrupt too slow, "
- "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
-}
/*
* High resolution timer interrupt
* Called with interrupts disabled
@@ -1233,24 +1250,18 @@ void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
- ktime_t expires_next, now;
- int nr_retries = 0;
- int i;
+ ktime_t expires_next, now, entry_time, delta;
+ int i, retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
- retry:
- /* 5 retries is enough to notice a hang */
- if (!(++nr_retries % 5))
- hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
-
- now = ktime_get();
-
+ entry_time = now = ktime_get();
+retry:
expires_next.tv64 = KTIME_MAX;
- spin_lock(&cpu_base->lock);
+ raw_spin_lock(&cpu_base->lock);
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
@@ -1306,13 +1317,51 @@ void hrtimer_interrupt(struct clock_event_device *dev)
* against it.
*/
cpu_base->expires_next = expires_next;
- spin_unlock(&cpu_base->lock);
+ raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
- if (expires_next.tv64 != KTIME_MAX) {
- if (tick_program_event(expires_next, force_clock_reprogram))
- goto retry;
+ if (expires_next.tv64 == KTIME_MAX ||
+ !tick_program_event(expires_next, 0)) {
+ cpu_base->hang_detected = 0;
+ return;
}
+
+ /*
+ * The next timer was already expired due to:
+ * - tracing
+ * - long lasting callbacks
+ * - being scheduled away when running in a VM
+ *
+ * We need to prevent that we loop forever in the hrtimer
+ * interrupt routine. We give it 3 attempts to avoid
+ * overreacting on some spurious event.
+ */
+ now = ktime_get();
+ cpu_base->nr_retries++;
+ if (++retries < 3)
+ goto retry;
+ /*
+ * Give the system a chance to do something else than looping
+ * here. We stored the entry time, so we know exactly how long
+ * we spent here. We schedule the next event this amount of
+ * time away.
+ */
+ cpu_base->nr_hangs++;
+ cpu_base->hang_detected = 1;
+ delta = ktime_sub(now, entry_time);
+ if (delta.tv64 > cpu_base->max_hang_time.tv64)
+ cpu_base->max_hang_time = delta;
+ /*
+ * Limit it to a sensible value as we enforce a longer
+ * delay. Give the CPU at least 100ms to catch up.
+ */
+ if (delta.tv64 > 100 * NSEC_PER_MSEC)
+ expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
+ else
+ expires_next = ktime_add(now, delta);
+ tick_program_event(expires_next, 1);
+ printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
+ ktime_to_ns(delta));
}
/*
@@ -1408,7 +1457,7 @@ void hrtimer_run_queues(void)
gettime = 0;
}
- spin_lock(&cpu_base->lock);
+ raw_spin_lock(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
@@ -1420,7 +1469,7 @@ void hrtimer_run_queues(void)
__run_hrtimer(timer, &base->softirq_time);
}
- spin_unlock(&cpu_base->lock);
+ raw_spin_unlock(&cpu_base->lock);
}
}
@@ -1576,7 +1625,7 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
- spin_lock_init(&cpu_base->lock);
+ raw_spin_lock_init(&cpu_base->lock);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
cpu_base->clock_base[i].cpu_base = cpu_base;
@@ -1634,16 +1683,16 @@ static void migrate_hrtimers(int scpu)
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
*/
- spin_lock(&new_base->lock);
- spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&new_base->lock);
+ raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
migrate_hrtimer_list(&old_base->clock_base[i],
&new_base->clock_base[i]);
}
- spin_unlock(&old_base->lock);
- spin_unlock(&new_base->lock);
+ raw_spin_unlock(&old_base->lock);
+ raw_spin_unlock(&new_base->lock);
/* Check, if we got expired work to do */
__hrtimer_peek_ahead_timers();
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 022a4927b78..0c642d51aac 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -144,7 +144,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
rcu_read_lock();
do_each_thread(g, t) {
- if (!--max_count)
+ if (!max_count--)
goto unlock;
if (!--batch_count) {
batch_count = HUNG_TASK_BATCHING;
@@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout)
* Process updating of timeout sysctl
*/
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int ret;
- ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
goto out;
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
new file mode 100644
index 00000000000..dbcbf6a33a0
--- /dev/null
+++ b/kernel/hw_breakpoint.c
@@ -0,0 +1,453 @@
+/*
+ * 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) 2007 Alan Stern
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Thanks to Ingo Molnar for his many suggestions.
+ *
+ * Authors: Alan Stern <stern@rowland.harvard.edu>
+ * K.Prasad <prasad@linux.vnet.ibm.com>
+ * Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ * This file contains the arch-independent routines.
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <linux/hw_breakpoint.h>
+
+/*
+ * Constraints data
+ */
+
+/* Number of pinned cpu breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
+
+/* Number of pinned task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
+
+/* Number of non-pinned cpu/task breakpoints in a cpu */
+static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
+
+/* Gather the number of total pinned and un-pinned bp in a cpuset */
+struct bp_busy_slots {
+ unsigned int pinned;
+ unsigned int flexible;
+};
+
+/* Serialize accesses to the above constraints */
+static DEFINE_MUTEX(nr_bp_mutex);
+
+/*
+ * Report the maximum number of pinned breakpoints a task
+ * have in this cpu
+ */
+static unsigned int max_task_bp_pinned(int cpu)
+{
+ int i;
+ unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+
+ for (i = HBP_NUM -1; i >= 0; i--) {
+ if (tsk_pinned[i] > 0)
+ return i + 1;
+ }
+
+ return 0;
+}
+
+static int task_bp_pinned(struct task_struct *tsk)
+{
+ struct perf_event_context *ctx = tsk->perf_event_ctxp;
+ struct list_head *list;
+ struct perf_event *bp;
+ unsigned long flags;
+ int count = 0;
+
+ if (WARN_ONCE(!ctx, "No perf context for this task"))
+ return 0;
+
+ list = &ctx->event_list;
+
+ raw_spin_lock_irqsave(&ctx->lock, flags);
+
+ /*
+ * The current breakpoint counter is not included in the list
+ * at the open() callback time
+ */
+ list_for_each_entry(bp, list, event_entry) {
+ if (bp->attr.type == PERF_TYPE_BREAKPOINT)
+ count++;
+ }
+
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return count;
+}
+
+/*
+ * Report the number of pinned/un-pinned breakpoints we have in
+ * a given cpu (cpu > -1) or in all of them (cpu = -1).
+ */
+static void
+fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
+{
+ int cpu = bp->cpu;
+ struct task_struct *tsk = bp->ctx->task;
+
+ if (cpu >= 0) {
+ slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
+ if (!tsk)
+ slots->pinned += max_task_bp_pinned(cpu);
+ else
+ slots->pinned += task_bp_pinned(tsk);
+ slots->flexible = per_cpu(nr_bp_flexible, cpu);
+
+ return;
+ }
+
+ for_each_online_cpu(cpu) {
+ unsigned int nr;
+
+ nr = per_cpu(nr_cpu_bp_pinned, cpu);
+ if (!tsk)
+ nr += max_task_bp_pinned(cpu);
+ else
+ nr += task_bp_pinned(tsk);
+
+ if (nr > slots->pinned)
+ slots->pinned = nr;
+
+ nr = per_cpu(nr_bp_flexible, cpu);
+
+ if (nr > slots->flexible)
+ slots->flexible = nr;
+ }
+}
+
+/*
+ * Add a pinned breakpoint for the given task in our constraint table
+ */
+static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
+{
+ unsigned int *tsk_pinned;
+ int count = 0;
+
+ count = task_bp_pinned(tsk);
+
+ tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
+ if (enable) {
+ tsk_pinned[count]++;
+ if (count > 0)
+ tsk_pinned[count-1]--;
+ } else {
+ tsk_pinned[count]--;
+ if (count > 0)
+ tsk_pinned[count-1]++;
+ }
+}
+
+/*
+ * Add/remove the given breakpoint in our constraint table
+ */
+static void toggle_bp_slot(struct perf_event *bp, bool enable)
+{
+ int cpu = bp->cpu;
+ struct task_struct *tsk = bp->ctx->task;
+
+ /* Pinned counter task profiling */
+ if (tsk) {
+ if (cpu >= 0) {
+ toggle_bp_task_slot(tsk, cpu, enable);
+ return;
+ }
+
+ for_each_online_cpu(cpu)
+ toggle_bp_task_slot(tsk, cpu, enable);
+ return;
+ }
+
+ /* Pinned counter cpu profiling */
+ if (enable)
+ per_cpu(nr_cpu_bp_pinned, bp->cpu)++;
+ else
+ per_cpu(nr_cpu_bp_pinned, bp->cpu)--;
+}
+
+/*
+ * Contraints to check before allowing this new breakpoint counter:
+ *
+ * == Non-pinned counter == (Considered as pinned for now)
+ *
+ * - If attached to a single cpu, check:
+ *
+ * (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ * + max(per_cpu(nr_task_bp_pinned, cpu)))) < HBP_NUM
+ *
+ * -> If there are already non-pinned counters in this cpu, it means
+ * there is already a free slot for them.
+ * Otherwise, we check that the maximum number of per task
+ * breakpoints (for this cpu) plus the number of per cpu breakpoint
+ * (for this cpu) doesn't cover every registers.
+ *
+ * - If attached to every cpus, check:
+ *
+ * (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ * + max(per_cpu(nr_task_bp_pinned, *)))) < HBP_NUM
+ *
+ * -> This is roughly the same, except we check the number of per cpu
+ * bp for every cpu and we keep the max one. Same for the per tasks
+ * breakpoints.
+ *
+ *
+ * == Pinned counter ==
+ *
+ * - If attached to a single cpu, check:
+ *
+ * ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
+ * + max(per_cpu(nr_task_bp_pinned, cpu))) < HBP_NUM
+ *
+ * -> Same checks as before. But now the nr_bp_flexible, if any, must keep
+ * one register at least (or they will never be fed).
+ *
+ * - If attached to every cpus, check:
+ *
+ * ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
+ * + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
+ */
+int reserve_bp_slot(struct perf_event *bp)
+{
+ struct bp_busy_slots slots = {0};
+ int ret = 0;
+
+ mutex_lock(&nr_bp_mutex);
+
+ fetch_bp_busy_slots(&slots, bp);
+
+ /* Flexible counters need to keep at least one slot */
+ if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
+ ret = -ENOSPC;
+ goto end;
+ }
+
+ toggle_bp_slot(bp, true);
+
+end:
+ mutex_unlock(&nr_bp_mutex);
+
+ return ret;
+}
+
+void release_bp_slot(struct perf_event *bp)
+{
+ mutex_lock(&nr_bp_mutex);
+
+ toggle_bp_slot(bp, false);
+
+ mutex_unlock(&nr_bp_mutex);
+}
+
+
+int register_perf_hw_breakpoint(struct perf_event *bp)
+{
+ int ret;
+
+ ret = reserve_bp_slot(bp);
+ if (ret)
+ return ret;
+
+ /*
+ * Ptrace breakpoints can be temporary perf events only
+ * meant to reserve a slot. In this case, it is created disabled and
+ * we don't want to check the params right now (as we put a null addr)
+ * But perf tools create events as disabled and we want to check
+ * the params for them.
+ * This is a quick hack that will be removed soon, once we remove
+ * the tmp breakpoints from ptrace
+ */
+ if (!bp->attr.disabled || !bp->overflow_handler)
+ ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+
+ return ret;
+}
+
+/**
+ * register_user_hw_breakpoint - register a hardware breakpoint for user space
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+ perf_overflow_handler_t triggered,
+ struct task_struct *tsk)
+{
+ return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+}
+EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+
+/**
+ * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
+ * @bp: the breakpoint structure to modify
+ * @attr: new breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ */
+int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
+{
+ u64 old_addr = bp->attr.bp_addr;
+ int old_type = bp->attr.bp_type;
+ int old_len = bp->attr.bp_len;
+ int err = 0;
+
+ perf_event_disable(bp);
+
+ bp->attr.bp_addr = attr->bp_addr;
+ bp->attr.bp_type = attr->bp_type;
+ bp->attr.bp_len = attr->bp_len;
+
+ if (attr->disabled)
+ goto end;
+
+ err = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+ if (!err)
+ perf_event_enable(bp);
+
+ if (err) {
+ bp->attr.bp_addr = old_addr;
+ bp->attr.bp_type = old_type;
+ bp->attr.bp_len = old_len;
+ if (!bp->attr.disabled)
+ perf_event_enable(bp);
+
+ return err;
+ }
+
+end:
+ bp->attr.disabled = attr->disabled;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
+
+/**
+ * unregister_hw_breakpoint - unregister a user-space hardware breakpoint
+ * @bp: the breakpoint structure to unregister
+ */
+void unregister_hw_breakpoint(struct perf_event *bp)
+{
+ if (!bp)
+ return;
+ perf_event_release_kernel(bp);
+}
+EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
+
+/**
+ * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
+ * @attr: breakpoint attributes
+ * @triggered: callback to trigger when we hit the breakpoint
+ *
+ * @return a set of per_cpu pointers to perf events
+ */
+struct perf_event **
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+ perf_overflow_handler_t triggered)
+{
+ struct perf_event **cpu_events, **pevent, *bp;
+ long err;
+ int cpu;
+
+ cpu_events = alloc_percpu(typeof(*cpu_events));
+ if (!cpu_events)
+ return ERR_PTR(-ENOMEM);
+
+ for_each_possible_cpu(cpu) {
+ pevent = per_cpu_ptr(cpu_events, cpu);
+ bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+
+ *pevent = bp;
+
+ if (IS_ERR(bp)) {
+ err = PTR_ERR(bp);
+ goto fail;
+ }
+ }
+
+ return cpu_events;
+
+fail:
+ for_each_possible_cpu(cpu) {
+ pevent = per_cpu_ptr(cpu_events, cpu);
+ if (IS_ERR(*pevent))
+ break;
+ unregister_hw_breakpoint(*pevent);
+ }
+ free_percpu(cpu_events);
+ /* return the error if any */
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
+
+/**
+ * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
+ * @cpu_events: the per cpu set of events to unregister
+ */
+void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+{
+ int cpu;
+ struct perf_event **pevent;
+
+ for_each_possible_cpu(cpu) {
+ pevent = per_cpu_ptr(cpu_events, cpu);
+ unregister_hw_breakpoint(*pevent);
+ }
+ free_percpu(cpu_events);
+}
+EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
+
+static struct notifier_block hw_breakpoint_exceptions_nb = {
+ .notifier_call = hw_breakpoint_exceptions_notify,
+ /* we need to be notified first */
+ .priority = 0x7fffffff
+};
+
+static int __init init_hw_breakpoint(void)
+{
+ return register_die_notifier(&hw_breakpoint_exceptions_nb);
+}
+core_initcall(init_hw_breakpoint);
+
+
+struct pmu perf_ops_bp = {
+ .enable = arch_install_hw_breakpoint,
+ .disable = arch_uninstall_hw_breakpoint,
+ .read = hw_breakpoint_pmu_read,
+ .unthrottle = hw_breakpoint_pmu_unthrottle
+};
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 1de9700f416..2295a31ef11 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -45,7 +45,7 @@ unsigned long probe_irq_on(void)
* flush such a longstanding irq before considering it as spurious.
*/
for_each_irq_desc_reverse(i, desc) {
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
/*
* An old-style architecture might still have
@@ -61,7 +61,7 @@ unsigned long probe_irq_on(void)
desc->chip->set_type(i, IRQ_TYPE_PROBE);
desc->chip->startup(i);
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
/* Wait for longstanding interrupts to trigger. */
@@ -73,13 +73,13 @@ unsigned long probe_irq_on(void)
* happened in the previous stage, it may have masked itself)
*/
for_each_irq_desc_reverse(i, desc) {
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
if (desc->chip->startup(i))
desc->status |= IRQ_PENDING;
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
/*
@@ -91,7 +91,7 @@ unsigned long probe_irq_on(void)
* Now filter out any obviously spurious interrupts
*/
for_each_irq_desc(i, desc) {
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
status = desc->status;
if (status & IRQ_AUTODETECT) {
@@ -103,7 +103,7 @@ unsigned long probe_irq_on(void)
if (i < 32)
mask |= 1 << i;
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
return mask;
@@ -129,7 +129,7 @@ unsigned int probe_irq_mask(unsigned long val)
int i;
for_each_irq_desc(i, desc) {
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
status = desc->status;
if (status & IRQ_AUTODETECT) {
@@ -139,7 +139,7 @@ unsigned int probe_irq_mask(unsigned long val)
desc->status = status & ~IRQ_AUTODETECT;
desc->chip->shutdown(i);
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
mutex_unlock(&probing_active);
@@ -171,7 +171,7 @@ int probe_irq_off(unsigned long val)
unsigned int status;
for_each_irq_desc(i, desc) {
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
status = desc->status;
if (status & IRQ_AUTODETECT) {
@@ -183,7 +183,7 @@ int probe_irq_off(unsigned long val)
desc->status = status & ~IRQ_AUTODETECT;
desc->chip->shutdown(i);
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
mutex_unlock(&probing_active);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c1660194d11..ecc3fa28f66 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -34,7 +34,7 @@ void dynamic_irq_init(unsigned int irq)
}
/* Ensure we don't have left over values from a previous use of this irq */
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->status = IRQ_DISABLED;
desc->chip = &no_irq_chip;
desc->handle_irq = handle_bad_irq;
@@ -51,7 +51,7 @@ void dynamic_irq_init(unsigned int irq)
cpumask_clear(desc->pending_mask);
#endif
#endif
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
/**
@@ -68,9 +68,9 @@ void dynamic_irq_cleanup(unsigned int irq)
return;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
if (desc->action) {
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
irq);
return;
@@ -82,7 +82,7 @@ void dynamic_irq_cleanup(unsigned int irq)
desc->chip = &no_irq_chip;
desc->name = NULL;
clear_kstat_irqs(desc);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
@@ -104,10 +104,10 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
if (!chip)
chip = &no_irq_chip;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
irq_chip_set_defaults(chip);
desc->chip = chip;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
@@ -133,9 +133,9 @@ int set_irq_type(unsigned int irq, unsigned int type)
if (type == IRQ_TYPE_NONE)
return 0;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
ret = __irq_set_trigger(desc, irq, type);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
EXPORT_SYMBOL(set_irq_type);
@@ -158,19 +158,19 @@ int set_irq_data(unsigned int irq, void *data)
return -EINVAL;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->handler_data = data;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
EXPORT_SYMBOL(set_irq_data);
/**
- * set_irq_data - set irq type data for an irq
+ * set_irq_msi - set MSI descriptor data for an irq
* @irq: Interrupt number
* @entry: Pointer to MSI descriptor data
*
- * Set the hardware irq controller data for an irq
+ * Set the MSI descriptor entry for an irq
*/
int set_irq_msi(unsigned int irq, struct msi_desc *entry)
{
@@ -183,11 +183,11 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
return -EINVAL;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->msi_desc = entry;
if (entry)
entry->irq = irq;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
@@ -214,9 +214,9 @@ int set_irq_chip_data(unsigned int irq, void *data)
return -EINVAL;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->chip_data = data;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
@@ -241,12 +241,12 @@ void set_irq_nested_thread(unsigned int irq, int nest)
if (!desc)
return;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
if (nest)
desc->status |= IRQ_NESTED_THREAD;
else
desc->status &= ~IRQ_NESTED_THREAD;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL_GPL(set_irq_nested_thread);
@@ -343,7 +343,7 @@ void handle_nested_irq(unsigned int irq)
might_sleep();
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
kstat_incr_irqs_this_cpu(irq, desc);
@@ -352,17 +352,17 @@ void handle_nested_irq(unsigned int irq)
goto out_unlock;
desc->status |= IRQ_INPROGRESS;
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
action_ret = action->thread_fn(action->irq, action->dev_id);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
desc->status &= ~IRQ_INPROGRESS;
out_unlock:
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
}
EXPORT_SYMBOL_GPL(handle_nested_irq);
@@ -384,7 +384,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
struct irqaction *action;
irqreturn_t action_ret;
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
if (unlikely(desc->status & IRQ_INPROGRESS))
goto out_unlock;
@@ -396,16 +396,16 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
goto out_unlock;
desc->status |= IRQ_INPROGRESS;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
desc->status &= ~IRQ_INPROGRESS;
out_unlock:
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
}
/**
@@ -424,7 +424,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
struct irqaction *action;
irqreturn_t action_ret;
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
mask_ack_irq(desc, irq);
if (unlikely(desc->status & IRQ_INPROGRESS))
@@ -441,13 +441,13 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
goto out_unlock;
desc->status |= IRQ_INPROGRESS;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
desc->status &= ~IRQ_INPROGRESS;
if (unlikely(desc->status & IRQ_ONESHOT))
@@ -455,7 +455,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
desc->chip->unmask(irq);
out_unlock:
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
}
EXPORT_SYMBOL_GPL(handle_level_irq);
@@ -475,7 +475,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
struct irqaction *action;
irqreturn_t action_ret;
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
if (unlikely(desc->status & IRQ_INPROGRESS))
goto out;
@@ -497,18 +497,18 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
desc->status |= IRQ_INPROGRESS;
desc->status &= ~IRQ_PENDING;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
desc->status &= ~IRQ_INPROGRESS;
out:
desc->chip->eoi(irq);
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
}
/**
@@ -530,7 +530,7 @@ out:
void
handle_edge_irq(unsigned int irq, struct irq_desc *desc)
{
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -576,21 +576,21 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
}
desc->status &= ~IRQ_PENDING;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
} while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING);
desc->status &= ~IRQ_INPROGRESS;
out_unlock:
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
}
/**
- * handle_percpu_IRQ - Per CPU local irq handler
+ * handle_percpu_irq - Per CPU local irq handler
* @irq: the interrupt number
* @desc: the interrupt description structure for this irq
*
@@ -643,7 +643,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
}
chip_bus_lock(irq, desc);
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
/* Uninstall? */
if (handle == handle_bad_irq) {
@@ -661,7 +661,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
desc->depth = 0;
desc->chip->startup(irq);
}
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
chip_bus_sync_unlock(irq, desc);
}
EXPORT_SYMBOL_GPL(__set_irq_handler);
@@ -692,9 +692,9 @@ void __init set_irq_noprobe(unsigned int irq)
return;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->status |= IRQ_NOPROBE;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
void __init set_irq_probe(unsigned int irq)
@@ -707,7 +707,7 @@ void __init set_irq_probe(unsigned int irq)
return;
}
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
desc->status &= ~IRQ_NOPROBE;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a81cf80554d..814940e7f48 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,6 +11,7 @@
*/
#include <linux/irq.h>
+#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/random.h>
@@ -79,7 +80,7 @@ static struct irq_desc irq_desc_init = {
.chip = &no_irq_chip,
.handle_irq = handle_bad_irq,
.depth = 1,
- .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
};
void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
@@ -107,7 +108,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
{
memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
- spin_lock_init(&desc->lock);
+ raw_spin_lock_init(&desc->lock);
desc->irq = irq;
#ifdef CONFIG_SMP
desc->node = node;
@@ -129,7 +130,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
/*
* Protect the sparse_irqs:
*/
-DEFINE_SPINLOCK(sparse_irq_lock);
+DEFINE_RAW_SPINLOCK(sparse_irq_lock);
struct irq_desc **irq_desc_ptrs __read_mostly;
@@ -140,7 +141,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
.chip = &no_irq_chip,
.handle_irq = handle_bad_irq,
.depth = 1,
- .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
}
};
@@ -211,7 +212,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
if (desc)
return desc;
- spin_lock_irqsave(&sparse_irq_lock, flags);
+ raw_spin_lock_irqsave(&sparse_irq_lock, flags);
/* We have to check it to avoid races with another CPU */
desc = irq_desc_ptrs[irq];
@@ -233,7 +234,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
irq_desc_ptrs[irq] = desc;
out_unlock:
- spin_unlock_irqrestore(&sparse_irq_lock, flags);
+ raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
return desc;
}
@@ -246,7 +247,7 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
.chip = &no_irq_chip,
.handle_irq = handle_bad_irq,
.depth = 1,
- .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
}
};
@@ -472,7 +473,7 @@ unsigned int __do_IRQ(unsigned int irq)
return 1;
}
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
if (desc->chip->ack)
desc->chip->ack(irq);
/*
@@ -516,13 +517,13 @@ unsigned int __do_IRQ(unsigned int irq)
for (;;) {
irqreturn_t action_ret;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
if (likely(!(desc->status & IRQ_PENDING)))
break;
desc->status &= ~IRQ_PENDING;
@@ -535,7 +536,7 @@ out:
* disabled while the handler was running.
*/
desc->chip->end(irq);
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
return 1;
}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 1b5d742c6a7..b2821f070a3 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -18,7 +18,7 @@ extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
extern struct lock_class_key irq_desc_lock_class;
extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
extern void clear_kstat_irqs(struct irq_desc *desc);
-extern spinlock_t sparse_irq_lock;
+extern raw_spinlock_t sparse_irq_lock;
#ifdef CONFIG_SPARSE_IRQ
/* irq_desc_ptrs allocated at boot time */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index bde4c667d24..eb6078ca60c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -46,9 +46,9 @@ void synchronize_irq(unsigned int irq)
cpu_relax();
/* Ok, that indicated we're done: double-check carefully. */
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
status = desc->status;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
/* Oops, that failed? */
} while (status & IRQ_INPROGRESS);
@@ -114,7 +114,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
if (!desc->chip->set_affinity)
return -EINVAL;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (desc->status & IRQ_MOVE_PCNTXT) {
@@ -134,7 +134,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
}
#endif
desc->status |= IRQ_AFFINITY_SET;
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
@@ -181,11 +181,11 @@ int irq_select_affinity_usr(unsigned int irq)
unsigned long flags;
int ret;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
ret = setup_affinity(irq, desc);
if (!ret)
irq_set_thread_affinity(desc);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
@@ -231,9 +231,9 @@ void disable_irq_nosync(unsigned int irq)
return;
chip_bus_lock(irq, desc);
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
__disable_irq(desc, irq, false);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
chip_bus_sync_unlock(irq, desc);
}
EXPORT_SYMBOL(disable_irq_nosync);
@@ -308,9 +308,9 @@ void enable_irq(unsigned int irq)
return;
chip_bus_lock(irq, desc);
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, false);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
chip_bus_sync_unlock(irq, desc);
}
EXPORT_SYMBOL(enable_irq);
@@ -347,7 +347,7 @@ int set_irq_wake(unsigned int irq, unsigned int on)
/* wakeup-capable irqs can be shared between drivers that
* don't need to have the same sleep mode behaviors.
*/
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
if (on) {
if (desc->wake_depth++ == 0) {
ret = set_irq_wake_real(irq, on);
@@ -368,7 +368,7 @@ int set_irq_wake(unsigned int irq, unsigned int on)
}
}
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
EXPORT_SYMBOL(set_irq_wake);
@@ -484,12 +484,12 @@ static int irq_wait_for_interrupt(struct irqaction *action)
static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
{
chip_bus_lock(irq, desc);
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
desc->status &= ~IRQ_MASKED;
desc->chip->unmask(irq);
}
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
chip_bus_sync_unlock(irq, desc);
}
@@ -514,9 +514,9 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
return;
}
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
cpumask_copy(mask, desc->affinity);
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
set_cpus_allowed_ptr(current, mask);
free_cpumask_var(mask);
@@ -545,7 +545,7 @@ static int irq_thread(void *data)
atomic_inc(&desc->threads_active);
- spin_lock_irq(&desc->lock);
+ raw_spin_lock_irq(&desc->lock);
if (unlikely(desc->status & IRQ_DISABLED)) {
/*
* CHECKME: We might need a dedicated
@@ -555,9 +555,9 @@ static int irq_thread(void *data)
* retriggers the interrupt itself --- tglx
*/
desc->status |= IRQ_PENDING;
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
} else {
- spin_unlock_irq(&desc->lock);
+ raw_spin_unlock_irq(&desc->lock);
action->thread_fn(action->irq, action->dev_id);
@@ -679,7 +679,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
/*
* The following block of code has to be executed atomically
*/
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
old_ptr = &desc->action;
old = *old_ptr;
if (old) {
@@ -775,7 +775,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
__enable_irq(desc, irq, false);
}
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
/*
* Strictly no need to wake it up, but hung_task complains
@@ -802,7 +802,7 @@ mismatch:
ret = -EBUSY;
out_thread:
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
if (new->thread) {
struct task_struct *t = new->thread;
@@ -844,7 +844,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
if (!desc)
return NULL;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
/*
* There can be multiple actions per IRQ descriptor, find the right
@@ -856,7 +856,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
if (!action) {
WARN(1, "Trying to free already-free IRQ %d\n", irq);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return NULL;
}
@@ -884,7 +884,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
desc->chip->disable(irq);
}
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
@@ -1067,7 +1067,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
kfree(action);
#ifdef CONFIG_DEBUG_SHIRQ
- if (irqflags & IRQF_SHARED) {
+ if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
* to happen immediately, so let's make sure....
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index fcb6c96f262..24196228083 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -27,7 +27,7 @@ void move_masked_irq(int irq)
if (!desc->chip->set_affinity)
return;
- assert_spin_locked(&desc->lock);
+ assert_raw_spin_locked(&desc->lock);
/*
* If there was a valid mask to work with, please
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 3fd30197da2..26bac9d8f86 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -42,7 +42,7 @@ static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
"for migration.\n", irq);
return false;
}
- spin_lock_init(&desc->lock);
+ raw_spin_lock_init(&desc->lock);
desc->node = node;
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
@@ -67,7 +67,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
irq = old_desc->irq;
- spin_lock_irqsave(&sparse_irq_lock, flags);
+ raw_spin_lock_irqsave(&sparse_irq_lock, flags);
/* We have to check it to avoid races with another CPU */
desc = irq_desc_ptrs[irq];
@@ -91,7 +91,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
}
irq_desc_ptrs[irq] = desc;
- spin_unlock_irqrestore(&sparse_irq_lock, flags);
+ raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
/* free the old one */
free_one_irq_desc(old_desc, desc);
@@ -100,7 +100,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
return desc;
out_unlock:
- spin_unlock_irqrestore(&sparse_irq_lock, flags);
+ raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
return desc;
}
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index a0bb09e7986..0d4005d85b0 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -28,9 +28,9 @@ void suspend_device_irqs(void)
for_each_irq_desc(irq, desc) {
unsigned long flags;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
__disable_irq(desc, irq, true);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
for_each_irq_desc(irq, desc)
@@ -56,9 +56,9 @@ void resume_device_irqs(void)
if (!(desc->status & IRQ_SUSPENDED))
continue;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, true);
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
}
}
EXPORT_SYMBOL_GPL(resume_device_irqs);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 692363dd591..6f50eccc79c 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -136,7 +136,7 @@ out:
static int default_affinity_open(struct inode *inode, struct file *file)
{
- return single_open(file, default_affinity_show, NULL);
+ return single_open(file, default_affinity_show, PDE(inode)->data);
}
static const struct file_operations default_affinity_proc_fops = {
@@ -148,18 +148,28 @@ static const struct file_operations default_affinity_proc_fops = {
};
#endif
-static int irq_spurious_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+static int irq_spurious_proc_show(struct seq_file *m, void *v)
{
- struct irq_desc *desc = irq_to_desc((long) data);
- return sprintf(page, "count %u\n"
- "unhandled %u\n"
- "last_unhandled %u ms\n",
- desc->irq_count,
- desc->irqs_unhandled,
- jiffies_to_msecs(desc->last_unhandled));
+ struct irq_desc *desc = irq_to_desc((long) m->private);
+
+ seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n",
+ desc->irq_count, desc->irqs_unhandled,
+ jiffies_to_msecs(desc->last_unhandled));
+ return 0;
+}
+
+static int irq_spurious_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, irq_spurious_proc_show, NULL);
}
+static const struct file_operations irq_spurious_proc_fops = {
+ .open = irq_spurious_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
#define MAX_NAMELEN 128
static int name_unique(unsigned int irq, struct irqaction *new_action)
@@ -169,7 +179,7 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
unsigned long flags;
int ret = 1;
- spin_lock_irqsave(&desc->lock, flags);
+ raw_spin_lock_irqsave(&desc->lock, flags);
for (action = desc->action ; action; action = action->next) {
if ((action != new_action) && action->name &&
!strcmp(new_action->name, action->name)) {
@@ -177,7 +187,7 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
break;
}
}
- spin_unlock_irqrestore(&desc->lock, flags);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
@@ -204,7 +214,6 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
void register_irq_proc(unsigned int irq, struct irq_desc *desc)
{
char name [MAX_NAMELEN];
- struct proc_dir_entry *entry;
if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
return;
@@ -214,6 +223,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
/* create /proc/irq/1234 */
desc->dir = proc_mkdir(name, root_irq_dir);
+ if (!desc->dir)
+ return;
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
@@ -221,11 +232,8 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
&irq_affinity_proc_fops, (void *)(long)irq);
#endif
- entry = create_proc_entry("spurious", 0444, desc->dir);
- if (entry) {
- entry->data = (void *)(long)irq;
- entry->read_proc = irq_spurious_read;
- }
+ proc_create_data("spurious", 0444, desc->dir,
+ &irq_spurious_proc_fops, (void *)(long)irq);
}
#undef MAX_NAMELEN
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 114e704760f..89fb90ae534 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -28,7 +28,7 @@ static int try_one_irq(int irq, struct irq_desc *desc)
struct irqaction *action;
int ok = 0, work = 0;
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
/* Already running on another processor */
if (desc->status & IRQ_INPROGRESS) {
/*
@@ -37,13 +37,13 @@ static int try_one_irq(int irq, struct irq_desc *desc)
*/
if (desc->action && (desc->action->flags & IRQF_SHARED))
desc->status |= IRQ_PENDING;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
return ok;
}
/* Honour the normal IRQ locking */
desc->status |= IRQ_INPROGRESS;
action = desc->action;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
while (action) {
/* Only shared IRQ handlers are safe to call */
@@ -56,7 +56,7 @@ static int try_one_irq(int irq, struct irq_desc *desc)
}
local_irq_disable();
/* Now clean up the flags */
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
action = desc->action;
/*
@@ -68,9 +68,9 @@ static int try_one_irq(int irq, struct irq_desc *desc)
* Perform real IRQ processing for the IRQ we deferred
*/
work = 1;
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
handle_IRQ_event(irq, action);
- spin_lock(&desc->lock);
+ raw_spin_lock(&desc->lock);
desc->status &= ~IRQ_PENDING;
}
desc->status &= ~IRQ_INPROGRESS;
@@ -80,7 +80,7 @@ static int try_one_irq(int irq, struct irq_desc *desc)
*/
if (work && desc->chip && desc->chip->end)
desc->chip->end(irq);
- spin_unlock(&desc->lock);
+ raw_spin_unlock(&desc->lock);
return ok;
}
@@ -104,7 +104,7 @@ static int misrouted_irq(int irq)
return ok;
}
-static void poll_all_shared_irqs(void)
+static void poll_spurious_irqs(unsigned long dummy)
{
struct irq_desc *desc;
int i;
@@ -121,25 +121,15 @@ static void poll_all_shared_irqs(void)
if (!(status & IRQ_SPURIOUS_DISABLED))
continue;
+ local_irq_disable();
try_one_irq(i, desc);
+ local_irq_enable();
}
-}
-
-static void poll_spurious_irqs(unsigned long dummy)
-{
- poll_all_shared_irqs();
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
}
-#ifdef CONFIG_DEBUG_SHIRQ
-void debug_poll_all_shared_irqs(void)
-{
- poll_all_shared_irqs();
-}
-#endif
-
/*
* If 99,900 of the previous 100,000 interrupts have not been handled
* then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -230,7 +220,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
/*
* If we are seeing only the odd spurious IRQ caused by
* bus asynchronicity then don't eventually trigger an error,
- * otherwise the couter becomes a doomsday timer for otherwise
+ * otherwise the counter becomes a doomsday timer for otherwise
* working systems
*/
if (time_after(jiffies, desc->last_unhandled + HZ/10))
diff --git a/kernel/itimer.c b/kernel/itimer.c
index b03451ede52..d802883153d 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -146,6 +146,7 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
{
cputime_t cval, nval, cinterval, ninterval;
s64 ns_ninterval, ns_nval;
+ u32 error, incr_error;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
nval = timeval_to_cputime(&value->it_value);
@@ -153,8 +154,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
ninterval = timeval_to_cputime(&value->it_interval);
ns_ninterval = timeval_to_ns(&value->it_interval);
- it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
- it->error = cputime_sub_ns(nval, ns_nval);
+ error = cputime_sub_ns(nval, ns_nval);
+ incr_error = cputime_sub_ns(ninterval, ns_ninterval);
spin_lock_irq(&tsk->sighand->siglock);
@@ -168,6 +169,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
}
it->expires = nval;
it->incr = ninterval;
+ it->error = error;
+ it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8b6b8b697c6..8e5288a8a35 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -181,6 +181,7 @@ unsigned long kallsyms_lookup_name(const char *name)
}
return module_kallsyms_lookup_name(name);
}
+EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
diff --git a/kernel/kexec.c b/kernel/kexec.c
index f336e2107f9..433e9fcc1fc 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -31,6 +31,7 @@
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/vmalloc.h>
+#include <linux/swap.h>
#include <asm/page.h>
#include <asm/uaccess.h>
@@ -1082,6 +1083,64 @@ void crash_kexec(struct pt_regs *regs)
}
}
+size_t crash_get_memory_size(void)
+{
+ size_t size;
+ mutex_lock(&kexec_mutex);
+ size = crashk_res.end - crashk_res.start + 1;
+ mutex_unlock(&kexec_mutex);
+ return size;
+}
+
+static void free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+ init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+ free_page((unsigned long)__va(addr));
+ totalram_pages++;
+ }
+}
+
+int crash_shrink_memory(unsigned long new_size)
+{
+ int ret = 0;
+ unsigned long start, end;
+
+ mutex_lock(&kexec_mutex);
+
+ if (kexec_crash_image) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+ start = crashk_res.start;
+ end = crashk_res.end;
+
+ if (new_size >= end - start + 1) {
+ ret = -EINVAL;
+ if (new_size == end - start + 1)
+ ret = 0;
+ goto unlock;
+ }
+
+ start = roundup(start, PAGE_SIZE);
+ end = roundup(start + new_size, PAGE_SIZE);
+
+ free_reserved_phys_range(end, crashk_res.end);
+
+ if (start == end) {
+ crashk_res.end = end;
+ release_resource(&crashk_res);
+ } else
+ crashk_res.end = end - 1;
+
+unlock:
+ mutex_unlock(&kexec_mutex);
+ return ret;
+}
+
static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
size_t data_len)
{
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 9147a3190c9..2eb517e2351 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -129,6 +129,7 @@ struct task_struct *kgdb_usethread;
struct task_struct *kgdb_contthread;
int kgdb_single_step;
+pid_t kgdb_sstep_pid;
/* Our I/O buffers. */
static char remcom_in_buffer[BUFMAX];
@@ -541,12 +542,17 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
*/
if (tid == 0 || tid == -1)
tid = -atomic_read(&kgdb_active) - 2;
- if (tid < 0) {
+ if (tid < -1 && tid > -NR_CPUS - 2) {
if (kgdb_info[-tid - 2].task)
return kgdb_info[-tid - 2].task;
else
return idle_task(-tid - 2);
}
+ if (tid <= 0) {
+ printk(KERN_ERR "KGDB: Internal thread select error\n");
+ dump_stack();
+ return NULL;
+ }
/*
* find_task_by_pid_ns() does not take the tasklist lock anymore
@@ -619,7 +625,8 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
static int kgdb_activate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -629,13 +636,16 @@ static int kgdb_activate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_set_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ ret = error;
+ printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
+ continue;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_ACTIVE;
}
- return 0;
+ return ret;
}
static int kgdb_set_sw_break(unsigned long addr)
@@ -682,7 +692,8 @@ static int kgdb_set_sw_break(unsigned long addr)
static int kgdb_deactivate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -691,13 +702,15 @@ static int kgdb_deactivate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_remove_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
+ ret = error;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_SET;
}
- return 0;
+ return ret;
}
static int kgdb_remove_sw_break(unsigned long addr)
@@ -870,7 +883,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
/*
* All threads that don't have debuggerinfo should be
- * in __schedule() sleeping, since all other CPUs
+ * in schedule() sleeping, since all other CPUs
* are in kgdb_wait, and thus have debuggerinfo.
*/
if (local_debuggerinfo) {
@@ -1204,8 +1217,10 @@ static int gdb_cmd_exception_pass(struct kgdb_state *ks)
return 1;
} else {
- error_packet(remcom_out_buffer, -EINVAL);
- return 0;
+ kgdb_msg_write("KGDB only knows signal 9 (pass)"
+ " and 15 (pass and disconnect)\n"
+ "Executing a continue without signal passing\n", 0);
+ remcom_in_buffer[0] = 'c';
}
/* Indicate fall through */
@@ -1395,6 +1410,7 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
struct kgdb_state kgdb_var;
struct kgdb_state *ks = &kgdb_var;
unsigned long flags;
+ int sstep_tries = 100;
int error = 0;
int i, cpu;
@@ -1425,13 +1441,14 @@ acquirelock:
cpu_relax();
/*
- * Do not start the debugger connection on this CPU if the last
- * instance of the exception handler wanted to come into the
- * debugger on a different CPU via a single step
+ * For single stepping, try to only enter on the processor
+ * that was single stepping. To gaurd against a deadlock, the
+ * kernel will only try for the value of sstep_tries before
+ * giving up and continuing on.
*/
if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
- atomic_read(&kgdb_cpu_doing_single_step) != cpu) {
-
+ (kgdb_info[cpu].task &&
+ kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
clocksource_touch_watchdog();
@@ -1524,6 +1541,13 @@ acquirelock:
}
kgdb_restore:
+ if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
+ int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
+ if (kgdb_info[sstep_cpu].task)
+ kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
+ else
+ kgdb_sstep_pid = 0;
+ }
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 689d20f3930..25b10319036 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -80,16 +80,16 @@ int __request_module(bool wait, const char *fmt, ...)
#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */
static int kmod_loop_msg;
- ret = security_kernel_module_request();
- if (ret)
- return ret;
-
va_start(args, fmt);
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
va_end(args);
if (ret >= MODULE_NAME_LEN)
return -ENAMETOOLONG;
+ ret = security_kernel_module_request(module_name);
+ if (ret)
+ return ret;
+
/* If modprobe needs a service that is in a module, we get a recursive
* loop. Limit the number of running kmod threads to max_threads/2 or
* MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method
@@ -143,7 +143,6 @@ struct subprocess_info {
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
- enum umh_wait wait = sub_info->wait;
int retval;
BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
@@ -185,14 +184,10 @@ static int ____call_usermodehelper(void *data)
*/
set_user_nice(current, 0);
- if (wait == UMH_WAIT_EXEC)
- complete(sub_info->complete);
-
retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
/* Exec failed? */
- if (wait != UMH_WAIT_EXEC)
- sub_info->retval = retval;
+ sub_info->retval = retval;
do_exit(0);
}
@@ -271,14 +266,16 @@ static void __call_usermodehelper(struct work_struct *work)
switch (wait) {
case UMH_NO_WAIT:
- case UMH_WAIT_EXEC:
break;
case UMH_WAIT_PROC:
if (pid > 0)
break;
sub_info->retval = pid;
- break;
+ /* FALLTHROUGH */
+
+ case UMH_WAIT_EXEC:
+ complete(sub_info->complete);
}
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index cfadc1291d0..e5342a344c4 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -90,6 +90,9 @@ static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
*/
static struct kprobe_blackpoint kprobe_blacklist[] = {
{"preempt_schedule",},
+ {"native_get_debugreg",},
+ {"irq_entries_start",},
+ {"common_interrupt",},
{NULL} /* Terminator */
};
@@ -673,6 +676,40 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
return (kprobe_opcode_t *)(((char *)addr) + p->offset);
}
+/* Check passed kprobe is valid and return kprobe in kprobe_table. */
+static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
+{
+ struct kprobe *old_p, *list_p;
+
+ old_p = get_kprobe(p->addr);
+ if (unlikely(!old_p))
+ return NULL;
+
+ if (p != old_p) {
+ list_for_each_entry_rcu(list_p, &old_p->list, list)
+ if (list_p == p)
+ /* kprobe p is a valid probe */
+ goto valid;
+ return NULL;
+ }
+valid:
+ return old_p;
+}
+
+/* Return error if the kprobe is being re-registered */
+static inline int check_kprobe_rereg(struct kprobe *p)
+{
+ int ret = 0;
+ struct kprobe *old_p;
+
+ mutex_lock(&kprobe_mutex);
+ old_p = __get_valid_kprobe(p);
+ if (old_p)
+ ret = -EINVAL;
+ mutex_unlock(&kprobe_mutex);
+ return ret;
+}
+
int __kprobes register_kprobe(struct kprobe *p)
{
int ret = 0;
@@ -685,6 +722,10 @@ int __kprobes register_kprobe(struct kprobe *p)
return -EINVAL;
p->addr = addr;
+ ret = check_kprobe_rereg(p);
+ if (ret)
+ return ret;
+
preempt_disable();
if (!kernel_text_address((unsigned long) p->addr) ||
in_kprobes_functions((unsigned long) p->addr)) {
@@ -754,26 +795,6 @@ out:
}
EXPORT_SYMBOL_GPL(register_kprobe);
-/* Check passed kprobe is valid and return kprobe in kprobe_table. */
-static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
-{
- struct kprobe *old_p, *list_p;
-
- old_p = get_kprobe(p->addr);
- if (unlikely(!old_p))
- return NULL;
-
- if (p != old_p) {
- list_for_each_entry_rcu(list_p, &old_p->list, list)
- if (list_p == p)
- /* kprobe p is a valid probe */
- goto valid;
- return NULL;
- }
-valid:
- return old_p;
-}
-
/*
* Unregister a kprobe without a scheduler synchronization.
*/
@@ -1014,9 +1035,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
/* Pre-allocate memory for max kretprobe instances */
if (rp->maxactive <= 0) {
#ifdef CONFIG_PREEMPT
- rp->maxactive = max(10, 2 * NR_CPUS);
+ rp->maxactive = max(10, 2 * num_possible_cpus());
#else
- rp->maxactive = NR_CPUS;
+ rp->maxactive = num_possible_cpus();
#endif
}
spin_lock_init(&rp->lock);
@@ -1141,6 +1162,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
arch_remove_kprobe(p);
}
+void __kprobes dump_kprobe(struct kprobe *kp)
+{
+ printk(KERN_WARNING "Dumping kprobe:\n");
+ printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
+ kp->symbol_name, kp->addr, kp->offset);
+}
+
/* Module notifier call back, checking kprobes on the module */
static int __kprobes kprobes_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -1333,7 +1361,7 @@ static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
return seq_open(filp, &kprobes_seq_ops);
}
-static struct file_operations debugfs_kprobes_operations = {
+static const struct file_operations debugfs_kprobes_operations = {
.open = kprobes_open,
.read = seq_read,
.llseek = seq_lseek,
@@ -1515,7 +1543,7 @@ static ssize_t write_enabled_file_bool(struct file *file,
return count;
}
-static struct file_operations fops_kp = {
+static const struct file_operations fops_kp = {
.read = read_enabled_file_bool,
.write = write_enabled_file_bool,
};
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 528dd78e7e7..3feaf5a7451 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -100,6 +100,26 @@ static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
}
KERNEL_ATTR_RO(kexec_crash_loaded);
+static ssize_t kexec_crash_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%zu\n", crash_get_memory_size());
+}
+static ssize_t kexec_crash_size_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned long cnt;
+ int ret;
+
+ if (strict_strtoul(buf, 0, &cnt))
+ return -EINVAL;
+
+ ret = crash_shrink_memory(cnt);
+ return ret < 0 ? ret : count;
+}
+KERNEL_ATTR_RW(kexec_crash_size);
+
static ssize_t vmcoreinfo_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -147,6 +167,7 @@ static struct attribute * kernel_attrs[] = {
#ifdef CONFIG_KEXEC
&kexec_loaded_attr.attr,
&kexec_crash_loaded_attr.attr,
+ &kexec_crash_size_attr.attr,
&vmcoreinfo_attr.attr,
#endif
NULL
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5fe709982ca..ab7ae57773e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
EXPORT_SYMBOL(kthread_create);
/**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
- /* Must have done schedule() in kthread() before we set_task_cpu */
- if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
- WARN_ON(1);
- return;
- }
- set_task_cpu(k, cpu);
- k->cpus_allowed = cpumask_of_cpu(cpu);
- k->rt.nr_cpus_allowed = 1;
- k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 3815ac1d58b..5feaddcdbe4 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -49,7 +49,7 @@
#include "lockdep_internals.h"
#define CREATE_TRACE_POINTS
-#include <trace/events/lockdep.h>
+#include <trace/events/lock.h>
#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
@@ -73,11 +73,11 @@ module_param(lock_stat, int, 0644);
* to use a raw spinlock - we really dont want the spinlock
* code to recurse back into the lockdep code...
*/
-static raw_spinlock_t lockdep_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static int graph_lock(void)
{
- __raw_spin_lock(&lockdep_lock);
+ arch_spin_lock(&lockdep_lock);
/*
* Make sure that if another CPU detected a bug while
* walking the graph we dont change it (while the other
@@ -85,7 +85,7 @@ static int graph_lock(void)
* dropped already)
*/
if (!debug_locks) {
- __raw_spin_unlock(&lockdep_lock);
+ arch_spin_unlock(&lockdep_lock);
return 0;
}
/* prevent any recursions within lockdep from causing deadlocks */
@@ -95,11 +95,11 @@ static int graph_lock(void)
static inline int graph_unlock(void)
{
- if (debug_locks && !__raw_spin_is_locked(&lockdep_lock))
+ if (debug_locks && !arch_spin_is_locked(&lockdep_lock))
return DEBUG_LOCKS_WARN_ON(1);
current->lockdep_recursion--;
- __raw_spin_unlock(&lockdep_lock);
+ arch_spin_unlock(&lockdep_lock);
return 0;
}
@@ -111,7 +111,7 @@ static inline int debug_locks_off_graph_unlock(void)
{
int ret = debug_locks_off();
- __raw_spin_unlock(&lockdep_lock);
+ arch_spin_unlock(&lockdep_lock);
return ret;
}
@@ -140,7 +140,13 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
}
#ifdef CONFIG_LOCK_STAT
-static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
+ cpu_lock_stats);
+
+static inline u64 lockstat_clock(void)
+{
+ return cpu_clock(smp_processor_id());
+}
static int lock_point(unsigned long points[], unsigned long ip)
{
@@ -158,12 +164,12 @@ static int lock_point(unsigned long points[], unsigned long ip)
return i;
}
-static void lock_time_inc(struct lock_time *lt, s64 time)
+static void lock_time_inc(struct lock_time *lt, u64 time)
{
if (time > lt->max)
lt->max = time;
- if (time < lt->min || !lt->min)
+ if (time < lt->min || !lt->nr)
lt->min = time;
lt->total += time;
@@ -172,8 +178,15 @@ static void lock_time_inc(struct lock_time *lt, s64 time)
static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
{
- dst->min += src->min;
- dst->max += src->max;
+ if (!src->nr)
+ return;
+
+ if (src->max > dst->max)
+ dst->max = src->max;
+
+ if (src->min < dst->min || !dst->nr)
+ dst->min = src->min;
+
dst->total += src->total;
dst->nr += src->nr;
}
@@ -186,7 +199,7 @@ struct lock_class_stats lock_stats(struct lock_class *class)
memset(&stats, 0, sizeof(struct lock_class_stats));
for_each_possible_cpu(cpu) {
struct lock_class_stats *pcs =
- &per_cpu(lock_stats, cpu)[class - lock_classes];
+ &per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
stats.contention_point[i] += pcs->contention_point[i];
@@ -213,7 +226,7 @@ void clear_lock_stats(struct lock_class *class)
for_each_possible_cpu(cpu) {
struct lock_class_stats *cpu_stats =
- &per_cpu(lock_stats, cpu)[class - lock_classes];
+ &per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
memset(cpu_stats, 0, sizeof(struct lock_class_stats));
}
@@ -223,23 +236,23 @@ void clear_lock_stats(struct lock_class *class)
static struct lock_class_stats *get_lock_stats(struct lock_class *class)
{
- return &get_cpu_var(lock_stats)[class - lock_classes];
+ return &get_cpu_var(cpu_lock_stats)[class - lock_classes];
}
static void put_lock_stats(struct lock_class_stats *stats)
{
- put_cpu_var(lock_stats);
+ put_cpu_var(cpu_lock_stats);
}
static void lock_release_holdtime(struct held_lock *hlock)
{
struct lock_class_stats *stats;
- s64 holdtime;
+ u64 holdtime;
if (!lock_stat)
return;
- holdtime = sched_clock() - hlock->holdtime_stamp;
+ holdtime = lockstat_clock() - hlock->holdtime_stamp;
stats = get_lock_stats(hlock_class(hlock));
if (hlock->read)
@@ -374,7 +387,8 @@ static int save_trace(struct stack_trace *trace)
* complete trace that maxes out the entries provided will be reported
* as incomplete, friggin useless </rant>
*/
- if (trace->entries[trace->nr_entries-1] == ULONG_MAX)
+ if (trace->nr_entries != 0 &&
+ trace->entries[trace->nr_entries-1] == ULONG_MAX)
trace->nr_entries--;
trace->max_entries = trace->nr_entries;
@@ -1156,9 +1170,9 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
this.class = class;
local_irq_save(flags);
- __raw_spin_lock(&lockdep_lock);
+ arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
- __raw_spin_unlock(&lockdep_lock);
+ arch_spin_unlock(&lockdep_lock);
local_irq_restore(flags);
return ret;
@@ -1183,9 +1197,9 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
this.class = class;
local_irq_save(flags);
- __raw_spin_lock(&lockdep_lock);
+ arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
- __raw_spin_unlock(&lockdep_lock);
+ arch_spin_unlock(&lockdep_lock);
local_irq_restore(flags);
return ret;
@@ -2792,7 +2806,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
hlock->references = references;
#ifdef CONFIG_LOCK_STAT
hlock->waittime_stamp = 0;
- hlock->holdtime_stamp = sched_clock();
+ hlock->holdtime_stamp = lockstat_clock();
#endif
if (check == 2 && !mark_irqflags(curr, hlock))
@@ -3322,7 +3336,7 @@ found_it:
if (hlock->instance != lock)
return;
- hlock->waittime_stamp = sched_clock();
+ hlock->waittime_stamp = lockstat_clock();
contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
contending_point = lock_point(hlock_class(hlock)->contending_point,
@@ -3345,8 +3359,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
struct held_lock *hlock, *prev_hlock;
struct lock_class_stats *stats;
unsigned int depth;
- u64 now;
- s64 waittime = 0;
+ u64 now, waittime = 0;
int i, cpu;
depth = curr->lockdep_depth;
@@ -3374,7 +3387,7 @@ found_it:
cpu = smp_processor_id();
if (hlock->waittime_stamp) {
- now = sched_clock();
+ now = lockstat_clock();
waittime = now - hlock->waittime_stamp;
hlock->holdtime_stamp = now;
}
diff --git a/kernel/module.c b/kernel/module.c
index e6bc4b28aa6..12afc5a3ddd 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,8 +370,6 @@ EXPORT_SYMBOL_GPL(find_module);
#ifdef CONFIG_SMP
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
static void *percpu_modalloc(unsigned long size, unsigned long align,
const char *name)
{
@@ -395,154 +393,6 @@ static void percpu_modfree(void *freeme)
free_percpu(freeme);
}
-#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-/* Number of blocks used and allocated. */
-static unsigned int pcpu_num_used, pcpu_num_allocated;
-/* Size of each block. -ve means used. */
-static int *pcpu_size;
-
-static int split_block(unsigned int i, unsigned short size)
-{
- /* Reallocation required? */
- if (pcpu_num_used + 1 > pcpu_num_allocated) {
- int *new;
-
- new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
- GFP_KERNEL);
- if (!new)
- return 0;
-
- pcpu_num_allocated *= 2;
- pcpu_size = new;
- }
-
- /* Insert a new subblock */
- memmove(&pcpu_size[i+1], &pcpu_size[i],
- sizeof(pcpu_size[0]) * (pcpu_num_used - i));
- pcpu_num_used++;
-
- pcpu_size[i+1] -= size;
- pcpu_size[i] = size;
- return 1;
-}
-
-static inline unsigned int block_size(int val)
-{
- if (val < 0)
- return -val;
- return val;
-}
-
-static void *percpu_modalloc(unsigned long size, unsigned long align,
- const char *name)
-{
- unsigned long extra;
- unsigned int i;
- void *ptr;
- int cpu;
-
- if (align > PAGE_SIZE) {
- printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
- name, align, PAGE_SIZE);
- align = PAGE_SIZE;
- }
-
- ptr = __per_cpu_start;
- for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- /* Extra for alignment requirement. */
- extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
- BUG_ON(i == 0 && extra != 0);
-
- if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
- continue;
-
- /* Transfer extra to previous block. */
- if (pcpu_size[i-1] < 0)
- pcpu_size[i-1] -= extra;
- else
- pcpu_size[i-1] += extra;
- pcpu_size[i] -= extra;
- ptr += extra;
-
- /* Split block if warranted */
- if (pcpu_size[i] - size > sizeof(unsigned long))
- if (!split_block(i, size))
- return NULL;
-
- /* add the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
- GFP_KERNEL);
-
- /* Mark allocated */
- pcpu_size[i] = -pcpu_size[i];
- return ptr;
- }
-
- printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
- size);
- return NULL;
-}
-
-static void percpu_modfree(void *freeme)
-{
- unsigned int i;
- void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
- int cpu;
-
- /* First entry is core kernel percpu data. */
- for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- if (ptr == freeme) {
- pcpu_size[i] = -pcpu_size[i];
- goto free;
- }
- }
- BUG();
-
- free:
- /* remove the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_free(freeme + per_cpu_offset(cpu));
-
- /* Merge with previous? */
- if (pcpu_size[i-1] >= 0) {
- pcpu_size[i-1] += pcpu_size[i];
- pcpu_num_used--;
- memmove(&pcpu_size[i], &pcpu_size[i+1],
- (pcpu_num_used - i) * sizeof(pcpu_size[0]));
- i--;
- }
- /* Merge with next? */
- if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
- pcpu_size[i] += pcpu_size[i+1];
- pcpu_num_used--;
- memmove(&pcpu_size[i+1], &pcpu_size[i+2],
- (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
- }
-}
-
-static int percpu_modinit(void)
-{
- pcpu_num_used = 2;
- pcpu_num_allocated = 2;
- pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
- GFP_KERNEL);
- /* Static in-kernel percpu data (used). */
- pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
- /* Free room. */
- pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
- if (pcpu_size[1] < 0) {
- printk(KERN_ERR "No per-cpu room for modules.\n");
- pcpu_num_used = 1;
- }
-
- return 0;
-}
-__initcall(percpu_modinit);
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
static unsigned int find_pcpusec(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
const char *secstrings)
@@ -1187,7 +1037,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
/* Count loaded sections and allocate structures */
for (i = 0; i < nsect; i++)
- if (sechdrs[i].sh_flags & SHF_ALLOC)
+ if (sechdrs[i].sh_flags & SHF_ALLOC
+ && sechdrs[i].sh_size)
nloaded++;
size[0] = ALIGN(sizeof(*sect_attrs)
+ nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1207,6 +1058,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
for (i = 0; i < nsect; i++) {
if (! (sechdrs[i].sh_flags & SHF_ALLOC))
continue;
+ if (!sechdrs[i].sh_size)
+ continue;
sattr->address = sechdrs[i].sh_addr;
sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
GFP_KERNEL);
@@ -1797,6 +1650,17 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
}
}
+static void free_modinfo(struct module *mod)
+{
+ struct module_attribute *attr;
+ int i;
+
+ for (i = 0; (attr = modinfo_attrs[i]); i++) {
+ if (attr->free)
+ attr->free(mod);
+ }
+}
+
#ifdef CONFIG_KALLSYMS
/* lookup symbol in given range of kernel_symbols */
@@ -1862,13 +1726,93 @@ static char elf_type(const Elf_Sym *sym,
return '?';
}
+static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
+ unsigned int shnum)
+{
+ const Elf_Shdr *sec;
+
+ if (src->st_shndx == SHN_UNDEF
+ || src->st_shndx >= shnum
+ || !src->st_name)
+ return false;
+
+ sec = sechdrs + src->st_shndx;
+ if (!(sec->sh_flags & SHF_ALLOC)
+#ifndef CONFIG_KALLSYMS_ALL
+ || !(sec->sh_flags & SHF_EXECINSTR)
+#endif
+ || (sec->sh_entsize & INIT_OFFSET_MASK))
+ return false;
+
+ return true;
+}
+
+static unsigned long layout_symtab(struct module *mod,
+ Elf_Shdr *sechdrs,
+ unsigned int symindex,
+ unsigned int strindex,
+ const Elf_Ehdr *hdr,
+ const char *secstrings,
+ unsigned long *pstroffs,
+ unsigned long *strmap)
+{
+ unsigned long symoffs;
+ Elf_Shdr *symsect = sechdrs + symindex;
+ Elf_Shdr *strsect = sechdrs + strindex;
+ const Elf_Sym *src;
+ const char *strtab;
+ unsigned int i, nsrc, ndst;
+
+ /* Put symbol section at end of init part of module. */
+ symsect->sh_flags |= SHF_ALLOC;
+ symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect,
+ symindex) | INIT_OFFSET_MASK;
+ DEBUGP("\t%s\n", secstrings + symsect->sh_name);
+
+ src = (void *)hdr + symsect->sh_offset;
+ nsrc = symsect->sh_size / sizeof(*src);
+ strtab = (void *)hdr + strsect->sh_offset;
+ for (ndst = i = 1; i < nsrc; ++i, ++src)
+ if (is_core_symbol(src, sechdrs, hdr->e_shnum)) {
+ unsigned int j = src->st_name;
+
+ while(!__test_and_set_bit(j, strmap) && strtab[j])
+ ++j;
+ ++ndst;
+ }
+
+ /* Append room for core symbols at end of core part. */
+ symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
+ mod->core_size = symoffs + ndst * sizeof(Elf_Sym);
+
+ /* Put string table section at end of init part of module. */
+ strsect->sh_flags |= SHF_ALLOC;
+ strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
+ strindex) | INIT_OFFSET_MASK;
+ DEBUGP("\t%s\n", secstrings + strsect->sh_name);
+
+ /* Append room for core symbols' strings at end of core part. */
+ *pstroffs = mod->core_size;
+ __set_bit(0, strmap);
+ mod->core_size += bitmap_weight(strmap, strsect->sh_size);
+
+ return symoffs;
+}
+
static void add_kallsyms(struct module *mod,
Elf_Shdr *sechdrs,
+ unsigned int shnum,
unsigned int symindex,
unsigned int strindex,
- const char *secstrings)
+ unsigned long symoffs,
+ unsigned long stroffs,
+ const char *secstrings,
+ unsigned long *strmap)
{
- unsigned int i;
+ unsigned int i, ndst;
+ const Elf_Sym *src;
+ Elf_Sym *dst;
+ char *s;
mod->symtab = (void *)sechdrs[symindex].sh_addr;
mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym);
@@ -1878,13 +1822,46 @@ static void add_kallsyms(struct module *mod,
for (i = 0; i < mod->num_symtab; i++)
mod->symtab[i].st_info
= elf_type(&mod->symtab[i], sechdrs, secstrings, mod);
+
+ mod->core_symtab = dst = mod->module_core + symoffs;
+ src = mod->symtab;
+ *dst = *src;
+ for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) {
+ if (!is_core_symbol(src, sechdrs, shnum))
+ continue;
+ dst[ndst] = *src;
+ dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name);
+ ++ndst;
+ }
+ mod->core_num_syms = ndst;
+
+ mod->core_strtab = s = mod->module_core + stroffs;
+ for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i)
+ if (test_bit(i, strmap))
+ *++s = mod->strtab[i];
}
#else
+static inline unsigned long layout_symtab(struct module *mod,
+ Elf_Shdr *sechdrs,
+ unsigned int symindex,
+ unsigned int strindex,
+ const Elf_Ehdr *hdr,
+ const char *secstrings,
+ unsigned long *pstroffs,
+ unsigned long *strmap)
+{
+ return 0;
+}
+
static inline void add_kallsyms(struct module *mod,
Elf_Shdr *sechdrs,
+ unsigned int shnum,
unsigned int symindex,
unsigned int strindex,
- const char *secstrings)
+ unsigned long symoffs,
+ unsigned long stroffs,
+ const char *secstrings,
+ const unsigned long *strmap)
{
}
#endif /* CONFIG_KALLSYMS */
@@ -1959,6 +1936,8 @@ static noinline struct module *load_module(void __user *umod,
struct module *mod;
long err = 0;
void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+ unsigned long symoffs, stroffs, *strmap;
+
mm_segment_t old_fs;
DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2040,11 +2019,6 @@ static noinline struct module *load_module(void __user *umod,
/* Don't keep modinfo and version sections. */
sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-#ifdef CONFIG_KALLSYMS
- /* Keep symbol and string tables for decoding later. */
- sechdrs[symindex].sh_flags |= SHF_ALLOC;
- sechdrs[strindex].sh_flags |= SHF_ALLOC;
-#endif
/* Check module struct version now, before we try to use module. */
if (!check_modstruct_version(sechdrs, versindex, mod)) {
@@ -2080,6 +2054,13 @@ static noinline struct module *load_module(void __user *umod,
goto free_hdr;
}
+ strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size)
+ * sizeof(long), GFP_KERNEL);
+ if (!strmap) {
+ err = -ENOMEM;
+ goto free_mod;
+ }
+
if (find_module(mod->name)) {
err = -EEXIST;
goto free_mod;
@@ -2109,6 +2090,8 @@ static noinline struct module *load_module(void __user *umod,
this is done generically; there doesn't appear to be any
special cases for the architectures. */
layout_sections(mod, hdr, sechdrs, secstrings);
+ symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr,
+ secstrings, &stroffs, strmap);
/* Do the allocs. */
ptr = module_alloc_update_bounds(mod->core_size);
@@ -2313,7 +2296,10 @@ static noinline struct module *load_module(void __user *umod,
percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
sechdrs[pcpuindex].sh_size);
- add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
+ add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
+ symoffs, stroffs, secstrings, strmap);
+ kfree(strmap);
+ strmap = NULL;
if (!mod->taints) {
struct _ddebug *debug;
@@ -2385,13 +2371,14 @@ static noinline struct module *load_module(void __user *umod,
synchronize_sched();
module_arch_cleanup(mod);
cleanup:
+ free_modinfo(mod);
kobject_del(&mod->mkobj.kobj);
kobject_put(&mod->mkobj.kobj);
free_unload:
module_unload_free(mod);
#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
- free_init:
percpu_modfree(mod->refptr);
+ free_init:
#endif
module_free(mod, mod->module_init);
free_core:
@@ -2402,6 +2389,7 @@ static noinline struct module *load_module(void __user *umod,
percpu_modfree(percpu);
free_mod:
kfree(args);
+ kfree(strmap);
free_hdr:
vfree(hdr);
return ERR_PTR(err);
@@ -2491,6 +2479,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
/* Drop initial reference. */
module_put(mod);
trim_init_extable(mod);
+#ifdef CONFIG_KALLSYMS
+ mod->num_symtab = mod->core_num_syms;
+ mod->symtab = mod->core_symtab;
+ mod->strtab = mod->core_strtab;
+#endif
module_free(mod, mod->module_init);
mod->module_init = NULL;
mod->init_size = 0;
@@ -2952,7 +2945,6 @@ void module_layout(struct module *mod,
struct modversion_info *ver,
struct kernel_param *kp,
struct kernel_symbol *ks,
- struct marker *marker,
struct tracepoint *tp)
{
}
diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c
index 50d022e5a56..ec815a960b5 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/mutex-debug.c
@@ -16,6 +16,7 @@
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/poison.h>
+#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h
index 6b2d735846a..57d527a16f9 100644
--- a/kernel/mutex-debug.h
+++ b/kernel/mutex-debug.h
@@ -43,13 +43,13 @@ static inline void mutex_clear_owner(struct mutex *lock)
\
DEBUG_LOCKS_WARN_ON(in_interrupt()); \
local_irq_save(flags); \
- __raw_spin_lock(&(lock)->raw_lock); \
+ arch_spin_lock(&(lock)->rlock.raw_lock);\
DEBUG_LOCKS_WARN_ON(l->magic != l); \
} while (0)
-#define spin_unlock_mutex(lock, flags) \
- do { \
- __raw_spin_unlock(&(lock)->raw_lock); \
- local_irq_restore(flags); \
- preempt_check_resched(); \
+#define spin_unlock_mutex(lock, flags) \
+ do { \
+ arch_spin_unlock(&(lock)->rlock.raw_lock); \
+ local_irq_restore(flags); \
+ preempt_check_resched(); \
} while (0)
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 947b3ad551f..632f04c57d8 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -148,8 +148,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
preempt_disable();
mutex_acquire(&lock->dep_map, subclass, 0, ip);
-#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && \
- !defined(CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES)
+
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Optimistic spinning.
*
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 61d5aa5eced..acd24e7643e 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -558,7 +558,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
static ATOMIC_NOTIFIER_HEAD(die_chain);
-int notrace notify_die(enum die_val val, const char *str,
+int notrace __kprobes notify_die(enum die_val val, const char *str,
struct pt_regs *regs, long err, int trap, int sig)
{
struct die_args args = {
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 5aa854f9e5a..2a5dfec8efe 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -42,8 +42,8 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
* (hence either you are in the same cgroup as task, or in an
* ancestor cgroup thereof)
*/
-static int ns_can_attach(struct cgroup_subsys *ss,
- struct cgroup *new_cgroup, struct task_struct *task)
+static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup,
+ struct task_struct *task, bool threadgroup)
{
if (current != task) {
if (!capable(CAP_SYS_ADMIN))
@@ -56,6 +56,18 @@ static int ns_can_attach(struct cgroup_subsys *ss,
if (!cgroup_is_descendant(new_cgroup, task))
return -EPERM;
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+ if (!cgroup_is_descendant(new_cgroup, c)) {
+ rcu_read_unlock();
+ return -EPERM;
+ }
+ }
+ rcu_read_unlock();
+ }
+
return 0;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index 8c43226a544..5827f7b9725 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -92,6 +92,8 @@ NORET_TYPE void panic(const char * fmt, ...)
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+ bust_spinlocks(0);
+
if (!panic_blink)
panic_blink = no_blink;
@@ -138,7 +140,6 @@ NORET_TYPE void panic(const char * fmt, ...)
mdelay(1);
i++;
}
- bust_spinlocks(0);
}
EXPORT_SYMBOL(panic);
diff --git a/kernel/params.c b/kernel/params.c
index 7f6912ced2b..cf1b6918312 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -23,6 +23,8 @@
#include <linux/device.h>
#include <linux/err.h>
#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
#if 0
#define DEBUGP printk
@@ -87,7 +89,7 @@ static char *next_arg(char *args, char **param, char **val)
}
for (i = 0; args[i]; i++) {
- if (args[i] == ' ' && !in_quote)
+ if (isspace(args[i]) && !in_quote)
break;
if (equals == 0) {
if (args[i] == '=')
@@ -121,9 +123,7 @@ static char *next_arg(char *args, char **param, char **val)
next = args + i;
/* Chew up trailing spaces. */
- while (*next == ' ')
- next++;
- return next;
+ return skip_spaces(next);
}
/* Args looks like "foo=bar,bar2 baz=fuz wiz". */
@@ -138,8 +138,7 @@ int parse_args(const char *name,
DEBUGP("Parsing ARGS: %s\n", args);
/* Chew leading spaces */
- while (*args == ' ')
- args++;
+ args = skip_spaces(args);
while (*args) {
int ret;
@@ -217,15 +216,11 @@ int param_set_charp(const char *val, struct kernel_param *kp)
return -ENOSPC;
}
- if (kp->flags & KPARAM_KMALLOCED)
- kfree(*(char **)kp->arg);
-
/* This is a hack. We can't need to strdup in early boot, and we
* don't need to; this mangled commandline is preserved. */
if (slab_is_available()) {
- kp->flags |= KPARAM_KMALLOCED;
*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
- if (!kp->arg)
+ if (!*(char **)kp->arg)
return -ENOMEM;
} else
*(const char **)kp->arg = val;
@@ -303,6 +298,7 @@ static int param_array(const char *name,
unsigned int min, unsigned int max,
void *elem, int elemsize,
int (*set)(const char *, struct kernel_param *kp),
+ u16 flags,
unsigned int *num)
{
int ret;
@@ -312,6 +308,7 @@ static int param_array(const char *name,
/* Get the name right for errors. */
kp.name = name;
kp.arg = elem;
+ kp.flags = flags;
/* No equals sign? */
if (!val) {
@@ -357,7 +354,8 @@ int param_array_set(const char *val, struct kernel_param *kp)
unsigned int temp_num;
return param_array(kp->name, val, 1, arr->max, arr->elem,
- arr->elemsize, arr->set, arr->num ?: &temp_num);
+ arr->elemsize, arr->set, kp->flags,
+ arr->num ?: &temp_num);
}
int param_array_get(char *buffer, struct kernel_param *kp)
@@ -604,11 +602,7 @@ void module_param_sysfs_remove(struct module *mod)
void destroy_params(const struct kernel_param *params, unsigned num)
{
- unsigned int i;
-
- for (i = 0; i < num; i++)
- if (params[i].flags & KPARAM_KMALLOCED)
- kfree(*(char **)params[i].arg);
+ /* FIXME: This should free kmalloced charp parameters. It doesn't. */
}
static void __init kernel_add_sysfs_param(const char *name,
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 76ac4db405e..9052d6c8c9f 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -20,6 +20,7 @@
#include <linux/percpu.h>
#include <linux/ptrace.h>
#include <linux/vmstat.h>
+#include <linux/vmalloc.h>
#include <linux/hardirq.h>
#include <linux/rculist.h>
#include <linux/uaccess.h>
@@ -27,13 +28,15 @@
#include <linux/anon_inodes.h>
#include <linux/kernel_stat.h>
#include <linux/perf_event.h>
+#include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
#include <asm/irq_regs.h>
/*
* Each CPU has a list of per CPU events:
*/
-DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
+static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
int perf_max_events __read_mostly = 1;
static int perf_reserved_percpu __read_mostly;
@@ -200,14 +203,14 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
* if so. If we locked the right context, then it
* can't get swapped on us any more.
*/
- spin_lock_irqsave(&ctx->lock, *flags);
+ raw_spin_lock_irqsave(&ctx->lock, *flags);
if (ctx != rcu_dereference(task->perf_event_ctxp)) {
- spin_unlock_irqrestore(&ctx->lock, *flags);
+ raw_spin_unlock_irqrestore(&ctx->lock, *flags);
goto retry;
}
if (!atomic_inc_not_zero(&ctx->refcount)) {
- spin_unlock_irqrestore(&ctx->lock, *flags);
+ raw_spin_unlock_irqrestore(&ctx->lock, *flags);
ctx = NULL;
}
}
@@ -228,7 +231,7 @@ static struct perf_event_context *perf_pin_task_context(struct task_struct *task
ctx = perf_lock_task_context(task, &flags);
if (ctx) {
++ctx->pin_count;
- spin_unlock_irqrestore(&ctx->lock, flags);
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
return ctx;
}
@@ -237,12 +240,55 @@ static void perf_unpin_context(struct perf_event_context *ctx)
{
unsigned long flags;
- spin_lock_irqsave(&ctx->lock, flags);
+ raw_spin_lock_irqsave(&ctx->lock, flags);
--ctx->pin_count;
- spin_unlock_irqrestore(&ctx->lock, flags);
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
put_ctx(ctx);
}
+static inline u64 perf_clock(void)
+{
+ return cpu_clock(smp_processor_id());
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void update_context_time(struct perf_event_context *ctx)
+{
+ u64 now = perf_clock();
+
+ ctx->time += now - ctx->timestamp;
+ ctx->timestamp = now;
+}
+
+/*
+ * Update the total_time_enabled and total_time_running fields for a event.
+ */
+static void update_event_times(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ u64 run_end;
+
+ if (event->state < PERF_EVENT_STATE_INACTIVE ||
+ event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
+ return;
+
+ if (ctx->is_active)
+ run_end = ctx->time;
+ else
+ run_end = event->tstamp_stopped;
+
+ event->total_time_enabled = run_end - event->tstamp_enabled;
+
+ if (event->state == PERF_EVENT_STATE_INACTIVE)
+ run_end = event->tstamp_stopped;
+ else
+ run_end = ctx->time;
+
+ event->total_time_running = run_end - event->tstamp_running;
+}
+
/*
* Add a event from the lists for its context.
* Must be called with ctx->mutex and ctx->lock held.
@@ -291,6 +337,18 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
if (event->group_leader != event)
event->group_leader->nr_siblings--;
+ update_event_times(event);
+
+ /*
+ * If event was in error state, then keep it
+ * that way, otherwise bogus counts will be
+ * returned on read(). The only way to get out
+ * of error state is by explicit re-enabling
+ * of the event
+ */
+ if (event->state > PERF_EVENT_STATE_OFF)
+ event->state = PERF_EVENT_STATE_OFF;
+
/*
* If this was a group event with sibling events then
* upgrade the siblings to singleton events by adding them
@@ -369,7 +427,7 @@ static void __perf_event_remove_from_context(void *info)
if (ctx->task && cpuctx->task_ctx != ctx)
return;
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
/*
* Protect the list operation against NMI by disabling the
* events on a global level.
@@ -391,7 +449,7 @@ static void __perf_event_remove_from_context(void *info)
}
perf_enable();
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
@@ -418,7 +476,7 @@ static void perf_event_remove_from_context(struct perf_event *event)
if (!task) {
/*
* Per cpu events are removed via an smp call and
- * the removal is always sucessful.
+ * the removal is always successful.
*/
smp_call_function_single(event->cpu,
__perf_event_remove_from_context,
@@ -430,12 +488,12 @@ retry:
task_oncpu_function_call(task, __perf_event_remove_from_context,
event);
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
/*
* If the context is active we need to retry the smp call.
*/
if (ctx->nr_active && !list_empty(&event->group_entry)) {
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
@@ -444,48 +502,9 @@ retry:
* can remove the event safely, if the call above did not
* succeed.
*/
- if (!list_empty(&event->group_entry)) {
+ if (!list_empty(&event->group_entry))
list_del_event(event, ctx);
- }
- spin_unlock_irq(&ctx->lock);
-}
-
-static inline u64 perf_clock(void)
-{
- return cpu_clock(smp_processor_id());
-}
-
-/*
- * Update the record of the current time in a context.
- */
-static void update_context_time(struct perf_event_context *ctx)
-{
- u64 now = perf_clock();
-
- ctx->time += now - ctx->timestamp;
- ctx->timestamp = now;
-}
-
-/*
- * Update the total_time_enabled and total_time_running fields for a event.
- */
-static void update_event_times(struct perf_event *event)
-{
- struct perf_event_context *ctx = event->ctx;
- u64 run_end;
-
- if (event->state < PERF_EVENT_STATE_INACTIVE ||
- event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
- return;
-
- event->total_time_enabled = ctx->time - event->tstamp_enabled;
-
- if (event->state == PERF_EVENT_STATE_INACTIVE)
- run_end = event->tstamp_stopped;
- else
- run_end = ctx->time;
-
- event->total_time_running = run_end - event->tstamp_running;
+ raw_spin_unlock_irq(&ctx->lock);
}
/*
@@ -516,7 +535,7 @@ static void __perf_event_disable(void *info)
if (ctx->task && cpuctx->task_ctx != ctx)
return;
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
/*
* If the event is on, turn it off.
@@ -532,7 +551,7 @@ static void __perf_event_disable(void *info)
event->state = PERF_EVENT_STATE_OFF;
}
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -548,7 +567,7 @@ static void __perf_event_disable(void *info)
* is the current context on this CPU and preemption is disabled,
* hence we can't get into perf_event_task_sched_out for this context.
*/
-static void perf_event_disable(struct perf_event *event)
+void perf_event_disable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
@@ -565,12 +584,12 @@ static void perf_event_disable(struct perf_event *event)
retry:
task_oncpu_function_call(task, __perf_event_disable, event);
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
/*
* If the event is still active, we need to retry the cross-call.
*/
if (event->state == PERF_EVENT_STATE_ACTIVE) {
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
@@ -583,7 +602,7 @@ static void perf_event_disable(struct perf_event *event)
event->state = PERF_EVENT_STATE_OFF;
}
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
}
static int
@@ -751,7 +770,7 @@ static void __perf_install_in_context(void *info)
cpuctx->task_ctx = ctx;
}
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
update_context_time(ctx);
@@ -801,7 +820,7 @@ static void __perf_install_in_context(void *info)
unlock:
perf_enable();
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -826,7 +845,7 @@ perf_install_in_context(struct perf_event_context *ctx,
if (!task) {
/*
* Per cpu events are installed via an smp call and
- * the install is always sucessful.
+ * the install is always successful.
*/
smp_call_function_single(cpu, __perf_install_in_context,
event, 1);
@@ -837,12 +856,12 @@ retry:
task_oncpu_function_call(task, __perf_install_in_context,
event);
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
/*
* we need to retry the smp call.
*/
if (ctx->is_active && list_empty(&event->group_entry)) {
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
goto retry;
}
@@ -853,7 +872,7 @@ retry:
*/
if (list_empty(&event->group_entry))
add_event_to_ctx(event, ctx);
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
}
/*
@@ -898,7 +917,7 @@ static void __perf_event_enable(void *info)
cpuctx->task_ctx = ctx;
}
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
update_context_time(ctx);
@@ -940,7 +959,7 @@ static void __perf_event_enable(void *info)
}
unlock:
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -952,7 +971,7 @@ static void __perf_event_enable(void *info)
* perf_event_for_each_child or perf_event_for_each as described
* for perf_event_disable.
*/
-static void perf_event_enable(struct perf_event *event)
+void perf_event_enable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
@@ -966,7 +985,7 @@ static void perf_event_enable(struct perf_event *event)
return;
}
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
if (event->state >= PERF_EVENT_STATE_INACTIVE)
goto out;
@@ -981,10 +1000,10 @@ static void perf_event_enable(struct perf_event *event)
event->state = PERF_EVENT_STATE_OFF;
retry:
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
task_oncpu_function_call(task, __perf_event_enable, event);
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
/*
* If the context is active and the event is still off,
@@ -1001,7 +1020,7 @@ static void perf_event_enable(struct perf_event *event)
__perf_event_mark_enabled(event, ctx);
out:
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
}
static int perf_event_refresh(struct perf_event *event, int refresh)
@@ -1023,7 +1042,7 @@ void __perf_event_sched_out(struct perf_event_context *ctx,
{
struct perf_event *event;
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
ctx->is_active = 0;
if (likely(!ctx->nr_events))
goto out;
@@ -1031,16 +1050,12 @@ void __perf_event_sched_out(struct perf_event_context *ctx,
perf_disable();
if (ctx->nr_active) {
- list_for_each_entry(event, &ctx->group_list, group_entry) {
- if (event != event->group_leader)
- event_sched_out(event, cpuctx, ctx);
- else
- group_sched_out(event, cpuctx, ctx);
- }
+ list_for_each_entry(event, &ctx->group_list, group_entry)
+ group_sched_out(event, cpuctx, ctx);
}
perf_enable();
out:
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -1062,8 +1077,6 @@ static int context_equiv(struct perf_event_context *ctx1,
&& !ctx1->pin_count && !ctx2->pin_count;
}
-static void __perf_event_read(void *event);
-
static void __perf_event_sync_stat(struct perf_event *event,
struct perf_event *next_event)
{
@@ -1081,8 +1094,8 @@ static void __perf_event_sync_stat(struct perf_event *event,
*/
switch (event->state) {
case PERF_EVENT_STATE_ACTIVE:
- __perf_event_read(event);
- break;
+ event->pmu->read(event);
+ /* fall-through */
case PERF_EVENT_STATE_INACTIVE:
update_event_times(event);
@@ -1121,6 +1134,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx,
if (!ctx->nr_stat)
return;
+ update_context_time(ctx);
+
event = list_first_entry(&ctx->event_list,
struct perf_event, event_entry);
@@ -1164,8 +1179,6 @@ void perf_event_task_sched_out(struct task_struct *task,
if (likely(!ctx || !cpuctx->task_ctx))
return;
- update_context_time(ctx);
-
rcu_read_lock();
parent = rcu_dereference(ctx->parent_ctx);
next_ctx = next->perf_event_ctxp;
@@ -1180,8 +1193,8 @@ void perf_event_task_sched_out(struct task_struct *task,
* order we take the locks because no other cpu could
* be trying to lock both of these tasks.
*/
- spin_lock(&ctx->lock);
- spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&ctx->lock);
+ raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
/*
* XXX do we need a memory barrier of sorts
@@ -1195,8 +1208,8 @@ void perf_event_task_sched_out(struct task_struct *task,
perf_event_sync_stat(ctx, next_ctx);
}
- spin_unlock(&next_ctx->lock);
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&next_ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
rcu_read_unlock();
@@ -1238,7 +1251,7 @@ __perf_event_sched_in(struct perf_event_context *ctx,
struct perf_event *event;
int can_add_hw = 1;
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
ctx->is_active = 1;
if (likely(!ctx->nr_events))
goto out;
@@ -1258,12 +1271,8 @@ __perf_event_sched_in(struct perf_event_context *ctx,
if (event->cpu != -1 && event->cpu != cpu)
continue;
- if (event != event->group_leader)
- event_sched_in(event, cpuctx, ctx, cpu);
- else {
- if (group_can_go_on(event, cpuctx, 1))
- group_sched_in(event, cpuctx, ctx, cpu);
- }
+ if (group_can_go_on(event, cpuctx, 1))
+ group_sched_in(event, cpuctx, ctx, cpu);
/*
* If this pinned group hasn't been scheduled,
@@ -1291,19 +1300,13 @@ __perf_event_sched_in(struct perf_event_context *ctx,
if (event->cpu != -1 && event->cpu != cpu)
continue;
- if (event != event->group_leader) {
- if (event_sched_in(event, cpuctx, ctx, cpu))
+ if (group_can_go_on(event, cpuctx, can_add_hw))
+ if (group_sched_in(event, cpuctx, ctx, cpu))
can_add_hw = 0;
- } else {
- if (group_can_go_on(event, cpuctx, can_add_hw)) {
- if (group_sched_in(event, cpuctx, ctx, cpu))
- can_add_hw = 0;
- }
- }
}
perf_enable();
out:
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -1367,8 +1370,8 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
struct hw_perf_event *hwc;
u64 interrupts, freq;
- spin_lock(&ctx->lock);
- list_for_each_entry(event, &ctx->group_list, group_entry) {
+ raw_spin_lock(&ctx->lock);
+ list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
@@ -1422,7 +1425,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
perf_enable();
}
}
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
/*
@@ -1435,7 +1438,7 @@ static void rotate_ctx(struct perf_event_context *ctx)
if (!ctx->nr_events)
return;
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
/*
* Rotate the first entry last (works just fine for group events too):
*/
@@ -1446,7 +1449,7 @@ static void rotate_ctx(struct perf_event_context *ctx)
}
perf_enable();
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
}
void perf_event_task_tick(struct task_struct *curr, int cpu)
@@ -1495,7 +1498,7 @@ static void perf_event_enable_on_exec(struct task_struct *task)
__perf_event_task_sched_out(ctx);
- spin_lock(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
list_for_each_entry(event, &ctx->group_list, group_entry) {
if (!event->attr.enable_on_exec)
@@ -1513,7 +1516,7 @@ static void perf_event_enable_on_exec(struct task_struct *task)
if (enabled)
unclone_ctx(ctx);
- spin_unlock(&ctx->lock);
+ raw_spin_unlock(&ctx->lock);
perf_event_task_sched_in(task, smp_processor_id());
out:
@@ -1528,7 +1531,6 @@ static void __perf_event_read(void *info)
struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
- unsigned long flags;
/*
* If this is a task context, we need to check whether it is
@@ -1540,12 +1542,12 @@ static void __perf_event_read(void *info)
if (ctx->task && cpuctx->task_ctx != ctx)
return;
- local_irq_save(flags);
- if (ctx->is_active)
- update_context_time(ctx);
- event->pmu->read(event);
+ raw_spin_lock(&ctx->lock);
+ update_context_time(ctx);
update_event_times(event);
- local_irq_restore(flags);
+ raw_spin_unlock(&ctx->lock);
+
+ event->pmu->read(event);
}
static u64 perf_event_read(struct perf_event *event)
@@ -1558,7 +1560,13 @@ static u64 perf_event_read(struct perf_event *event)
smp_call_function_single(event->oncpu,
__perf_event_read, event, 1);
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
+ struct perf_event_context *ctx = event->ctx;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&ctx->lock, flags);
+ update_context_time(ctx);
update_event_times(event);
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
return atomic64_read(&event->count);
@@ -1571,8 +1579,7 @@ static void
__perf_event_init_context(struct perf_event_context *ctx,
struct task_struct *task)
{
- memset(ctx, 0, sizeof(*ctx));
- spin_lock_init(&ctx->lock);
+ raw_spin_lock_init(&ctx->lock);
mutex_init(&ctx->mutex);
INIT_LIST_HEAD(&ctx->group_list);
INIT_LIST_HEAD(&ctx->event_list);
@@ -1642,11 +1649,11 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
ctx = perf_lock_task_context(task, &flags);
if (ctx) {
unclone_ctx(ctx);
- spin_unlock_irqrestore(&ctx->lock, flags);
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
if (!ctx) {
- ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+ ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
err = -ENOMEM;
if (!ctx)
goto errout;
@@ -1671,6 +1678,8 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
return ERR_PTR(err);
}
+static void perf_event_free_filter(struct perf_event *event);
+
static void free_event_rcu(struct rcu_head *head)
{
struct perf_event *event;
@@ -1678,6 +1687,7 @@ static void free_event_rcu(struct rcu_head *head)
event = container_of(head, struct perf_event, rcu_head);
if (event->ns)
put_pid_ns(event->ns);
+ perf_event_free_filter(event);
kfree(event);
}
@@ -1709,16 +1719,10 @@ static void free_event(struct perf_event *event)
call_rcu(&event->rcu_head, free_event_rcu);
}
-/*
- * Called when the last reference to the file is gone.
- */
-static int perf_release(struct inode *inode, struct file *file)
+int perf_event_release_kernel(struct perf_event *event)
{
- struct perf_event *event = file->private_data;
struct perf_event_context *ctx = event->ctx;
- file->private_data = NULL;
-
WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex);
perf_event_remove_from_context(event);
@@ -1733,6 +1737,19 @@ static int perf_release(struct inode *inode, struct file *file)
return 0;
}
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static int perf_release(struct inode *inode, struct file *file)
+{
+ struct perf_event *event = file->private_data;
+
+ file->private_data = NULL;
+
+ return perf_event_release_kernel(event);
+}
static int perf_event_read_size(struct perf_event *event)
{
@@ -1759,91 +1776,94 @@ static int perf_event_read_size(struct perf_event *event)
return size;
}
-static u64 perf_event_read_value(struct perf_event *event)
+u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
{
struct perf_event *child;
u64 total = 0;
+ *enabled = 0;
+ *running = 0;
+
+ mutex_lock(&event->child_mutex);
total += perf_event_read(event);
- list_for_each_entry(child, &event->child_list, child_list)
+ *enabled += event->total_time_enabled +
+ atomic64_read(&event->child_total_time_enabled);
+ *running += event->total_time_running +
+ atomic64_read(&event->child_total_time_running);
+
+ list_for_each_entry(child, &event->child_list, child_list) {
total += perf_event_read(child);
+ *enabled += child->total_time_enabled;
+ *running += child->total_time_running;
+ }
+ mutex_unlock(&event->child_mutex);
return total;
}
-
-static int perf_event_read_entry(struct perf_event *event,
- u64 read_format, char __user *buf)
-{
- int n = 0, count = 0;
- u64 values[2];
-
- values[n++] = perf_event_read_value(event);
- if (read_format & PERF_FORMAT_ID)
- values[n++] = primary_event_id(event);
-
- count = n * sizeof(u64);
-
- if (copy_to_user(buf, values, count))
- return -EFAULT;
-
- return count;
-}
+EXPORT_SYMBOL_GPL(perf_event_read_value);
static int perf_event_read_group(struct perf_event *event,
u64 read_format, char __user *buf)
{
struct perf_event *leader = event->group_leader, *sub;
- int n = 0, size = 0, err = -EFAULT;
- u64 values[3];
+ int n = 0, size = 0, ret = -EFAULT;
+ struct perf_event_context *ctx = leader->ctx;
+ u64 values[5];
+ u64 count, enabled, running;
+
+ mutex_lock(&ctx->mutex);
+ count = perf_event_read_value(leader, &enabled, &running);
values[n++] = 1 + leader->nr_siblings;
- if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
- values[n++] = leader->total_time_enabled +
- atomic64_read(&leader->child_total_time_enabled);
- }
- if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
- values[n++] = leader->total_time_running +
- atomic64_read(&leader->child_total_time_running);
- }
+ if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ values[n++] = enabled;
+ if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ values[n++] = running;
+ values[n++] = count;
+ if (read_format & PERF_FORMAT_ID)
+ values[n++] = primary_event_id(leader);
size = n * sizeof(u64);
if (copy_to_user(buf, values, size))
- return -EFAULT;
-
- err = perf_event_read_entry(leader, read_format, buf + size);
- if (err < 0)
- return err;
+ goto unlock;
- size += err;
+ ret = size;
list_for_each_entry(sub, &leader->sibling_list, group_entry) {
- err = perf_event_read_entry(sub, read_format,
- buf + size);
- if (err < 0)
- return err;
+ n = 0;
+
+ values[n++] = perf_event_read_value(sub, &enabled, &running);
+ if (read_format & PERF_FORMAT_ID)
+ values[n++] = primary_event_id(sub);
+
+ size = n * sizeof(u64);
+
+ if (copy_to_user(buf + ret, values, size)) {
+ ret = -EFAULT;
+ goto unlock;
+ }
- size += err;
+ ret += size;
}
+unlock:
+ mutex_unlock(&ctx->mutex);
- return size;
+ return ret;
}
static int perf_event_read_one(struct perf_event *event,
u64 read_format, char __user *buf)
{
+ u64 enabled, running;
u64 values[4];
int n = 0;
- values[n++] = perf_event_read_value(event);
- if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
- values[n++] = event->total_time_enabled +
- atomic64_read(&event->child_total_time_enabled);
- }
- if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
- values[n++] = event->total_time_running +
- atomic64_read(&event->child_total_time_running);
- }
+ values[n++] = perf_event_read_value(event, &enabled, &running);
+ if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ values[n++] = enabled;
+ if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ values[n++] = running;
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(event);
@@ -1874,12 +1894,10 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
return -ENOSPC;
WARN_ON_ONCE(event->ctx->parent_ctx);
- mutex_lock(&event->child_mutex);
if (read_format & PERF_FORMAT_GROUP)
ret = perf_event_read_group(event, read_format, buf);
else
ret = perf_event_read_one(event, read_format, buf);
- mutex_unlock(&event->child_mutex);
return ret;
}
@@ -1969,7 +1987,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
if (!value)
return -EINVAL;
- spin_lock_irq(&ctx->lock);
+ raw_spin_lock_irq(&ctx->lock);
if (event->attr.freq) {
if (value > sysctl_perf_event_sample_rate) {
ret = -EINVAL;
@@ -1982,12 +2000,13 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
event->hw.sample_period = value;
}
unlock:
- spin_unlock_irq(&ctx->lock);
+ raw_spin_unlock_irq(&ctx->lock);
return ret;
}
-int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_output(struct perf_event *event, int output_fd);
+static int perf_event_set_filter(struct perf_event *event, void __user *arg);
static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
@@ -2015,6 +2034,9 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case PERF_EVENT_IOC_SET_OUTPUT:
return perf_event_set_output(event, arg);
+ case PERF_EVENT_IOC_SET_FILTER:
+ return perf_event_set_filter(event, (void __user *)arg);
+
default:
return -ENOTTY;
}
@@ -2105,49 +2127,31 @@ unlock:
rcu_read_unlock();
}
-static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static unsigned long perf_data_size(struct perf_mmap_data *data)
{
- struct perf_event *event = vma->vm_file->private_data;
- struct perf_mmap_data *data;
- int ret = VM_FAULT_SIGBUS;
-
- if (vmf->flags & FAULT_FLAG_MKWRITE) {
- if (vmf->pgoff == 0)
- ret = 0;
- return ret;
- }
-
- rcu_read_lock();
- data = rcu_dereference(event->data);
- if (!data)
- goto unlock;
-
- if (vmf->pgoff == 0) {
- vmf->page = virt_to_page(data->user_page);
- } else {
- int nr = vmf->pgoff - 1;
+ return data->nr_pages << (PAGE_SHIFT + data->data_order);
+}
- if ((unsigned)nr > data->nr_pages)
- goto unlock;
+#ifndef CONFIG_PERF_USE_VMALLOC
- if (vmf->flags & FAULT_FLAG_WRITE)
- goto unlock;
+/*
+ * Back perf_mmap() with regular GFP_KERNEL-0 pages.
+ */
- vmf->page = virt_to_page(data->data_pages[nr]);
- }
+static struct page *
+perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+{
+ if (pgoff > data->nr_pages)
+ return NULL;
- get_page(vmf->page);
- vmf->page->mapping = vma->vm_file->f_mapping;
- vmf->page->index = vmf->pgoff;
+ if (pgoff == 0)
+ return virt_to_page(data->user_page);
- ret = 0;
-unlock:
- rcu_read_unlock();
-
- return ret;
+ return virt_to_page(data->data_pages[pgoff - 1]);
}
-static int perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+static struct perf_mmap_data *
+perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
{
struct perf_mmap_data *data;
unsigned long size;
@@ -2172,19 +2176,10 @@ static int perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
goto fail_data_pages;
}
+ data->data_order = 0;
data->nr_pages = nr_pages;
- atomic_set(&data->lock, -1);
- if (event->attr.watermark) {
- data->watermark = min_t(long, PAGE_SIZE * nr_pages,
- event->attr.wakeup_watermark);
- }
- if (!data->watermark)
- data->watermark = max(PAGE_SIZE, PAGE_SIZE * nr_pages / 4);
-
- rcu_assign_pointer(event->data, data);
-
- return 0;
+ return data;
fail_data_pages:
for (i--; i >= 0; i--)
@@ -2196,7 +2191,7 @@ fail_user_page:
kfree(data);
fail:
- return -ENOMEM;
+ return NULL;
}
static void perf_mmap_free_page(unsigned long addr)
@@ -2207,28 +2202,170 @@ static void perf_mmap_free_page(unsigned long addr)
__free_page(page);
}
-static void __perf_mmap_data_free(struct rcu_head *rcu_head)
+static void perf_mmap_data_free(struct perf_mmap_data *data)
{
- struct perf_mmap_data *data;
int i;
- data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
-
perf_mmap_free_page((unsigned long)data->user_page);
for (i = 0; i < data->nr_pages; i++)
perf_mmap_free_page((unsigned long)data->data_pages[i]);
+ kfree(data);
+}
+
+#else
+
+/*
+ * Back perf_mmap() with vmalloc memory.
+ *
+ * Required for architectures that have d-cache aliasing issues.
+ */
+
+static struct page *
+perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff)
+{
+ if (pgoff > (1UL << data->data_order))
+ return NULL;
+
+ return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE);
+}
+
+static void perf_mmap_unmark_page(void *addr)
+{
+ struct page *page = vmalloc_to_page(addr);
+
+ page->mapping = NULL;
+}
+
+static void perf_mmap_data_free_work(struct work_struct *work)
+{
+ struct perf_mmap_data *data;
+ void *base;
+ int i, nr;
+ data = container_of(work, struct perf_mmap_data, work);
+ nr = 1 << data->data_order;
+
+ base = data->user_page;
+ for (i = 0; i < nr + 1; i++)
+ perf_mmap_unmark_page(base + (i * PAGE_SIZE));
+
+ vfree(base);
+ kfree(data);
+}
+
+static void perf_mmap_data_free(struct perf_mmap_data *data)
+{
+ schedule_work(&data->work);
+}
+
+static struct perf_mmap_data *
+perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
+{
+ struct perf_mmap_data *data;
+ unsigned long size;
+ void *all_buf;
+
+ WARN_ON(atomic_read(&event->mmap_count));
+
+ size = sizeof(struct perf_mmap_data);
+ size += sizeof(void *);
+
+ data = kzalloc(size, GFP_KERNEL);
+ if (!data)
+ goto fail;
+
+ INIT_WORK(&data->work, perf_mmap_data_free_work);
+
+ all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
+ if (!all_buf)
+ goto fail_all_buf;
+
+ data->user_page = all_buf;
+ data->data_pages[0] = all_buf + PAGE_SIZE;
+ data->data_order = ilog2(nr_pages);
+ data->nr_pages = 1;
+
+ return data;
+
+fail_all_buf:
kfree(data);
+
+fail:
+ return NULL;
+}
+
+#endif
+
+static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct perf_event *event = vma->vm_file->private_data;
+ struct perf_mmap_data *data;
+ int ret = VM_FAULT_SIGBUS;
+
+ if (vmf->flags & FAULT_FLAG_MKWRITE) {
+ if (vmf->pgoff == 0)
+ ret = 0;
+ return ret;
+ }
+
+ rcu_read_lock();
+ data = rcu_dereference(event->data);
+ if (!data)
+ goto unlock;
+
+ if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE))
+ goto unlock;
+
+ vmf->page = perf_mmap_to_page(data, vmf->pgoff);
+ if (!vmf->page)
+ goto unlock;
+
+ get_page(vmf->page);
+ vmf->page->mapping = vma->vm_file->f_mapping;
+ vmf->page->index = vmf->pgoff;
+
+ ret = 0;
+unlock:
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static void
+perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data)
+{
+ long max_size = perf_data_size(data);
+
+ atomic_set(&data->lock, -1);
+
+ if (event->attr.watermark) {
+ data->watermark = min_t(long, max_size,
+ event->attr.wakeup_watermark);
+ }
+
+ if (!data->watermark)
+ data->watermark = max_size / 2;
+
+
+ rcu_assign_pointer(event->data, data);
+}
+
+static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head)
+{
+ struct perf_mmap_data *data;
+
+ data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
+ perf_mmap_data_free(data);
}
-static void perf_mmap_data_free(struct perf_event *event)
+static void perf_mmap_data_release(struct perf_event *event)
{
struct perf_mmap_data *data = event->data;
WARN_ON(atomic_read(&event->mmap_count));
rcu_assign_pointer(event->data, NULL);
- call_rcu(&data->rcu_head, __perf_mmap_data_free);
+ call_rcu(&data->rcu_head, perf_mmap_data_free_rcu);
}
static void perf_mmap_open(struct vm_area_struct *vma)
@@ -2244,16 +2381,17 @@ static void perf_mmap_close(struct vm_area_struct *vma)
WARN_ON_ONCE(event->ctx->parent_ctx);
if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
+ unsigned long size = perf_data_size(event->data);
struct user_struct *user = current_user();
- atomic_long_sub(event->data->nr_pages + 1, &user->locked_vm);
+ atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
vma->vm_mm->locked_vm -= event->data->nr_locked;
- perf_mmap_data_free(event);
+ perf_mmap_data_release(event);
mutex_unlock(&event->mmap_mutex);
}
}
-static struct vm_operations_struct perf_mmap_vmops = {
+static const struct vm_operations_struct perf_mmap_vmops = {
.open = perf_mmap_open,
.close = perf_mmap_close,
.fault = perf_mmap_fault,
@@ -2266,6 +2404,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
unsigned long user_locked, user_lock_limit;
struct user_struct *user = current_user();
unsigned long locked, lock_limit;
+ struct perf_mmap_data *data;
unsigned long vma_size;
unsigned long nr_pages;
long user_extra, extra;
@@ -2328,10 +2467,15 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
}
WARN_ON(event->data);
- ret = perf_mmap_data_alloc(event, nr_pages);
- if (ret)
+
+ data = perf_mmap_data_alloc(event, nr_pages);
+ ret = -ENOMEM;
+ if (!data)
goto unlock;
+ ret = 0;
+ perf_mmap_data_init(event, data);
+
atomic_set(&event->mmap_count, 1);
atomic_long_add(user_extra, &user->locked_vm);
vma->vm_mm->locked_vm += extra;
@@ -2519,7 +2663,7 @@ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail,
if (!data->writable)
return true;
- mask = (data->nr_pages << PAGE_SHIFT) - 1;
+ mask = perf_data_size(data) - 1;
offset = (offset - tail) & mask;
head = (head - tail) & mask;
@@ -2558,20 +2702,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
static void perf_output_lock(struct perf_output_handle *handle)
{
struct perf_mmap_data *data = handle->data;
- int cpu;
+ int cur, cpu = get_cpu();
handle->locked = 0;
- local_irq_save(handle->flags);
- cpu = smp_processor_id();
-
- if (in_nmi() && atomic_read(&data->lock) == cpu)
- return;
+ for (;;) {
+ cur = atomic_cmpxchg(&data->lock, -1, cpu);
+ if (cur == -1) {
+ handle->locked = 1;
+ break;
+ }
+ if (cur == cpu)
+ break;
- while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
cpu_relax();
-
- handle->locked = 1;
+ }
}
static void perf_output_unlock(struct perf_output_handle *handle)
@@ -2617,14 +2762,14 @@ again:
if (atomic_xchg(&data->wakeup, 0))
perf_output_wakeup(handle);
out:
- local_irq_restore(handle->flags);
+ put_cpu();
}
void perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
unsigned int pages_mask;
- unsigned int offset;
+ unsigned long offset;
unsigned int size;
void **pages;
@@ -2633,12 +2778,14 @@ void perf_output_copy(struct perf_output_handle *handle,
pages = handle->data->data_pages;
do {
- unsigned int page_offset;
+ unsigned long page_offset;
+ unsigned long page_size;
int nr;
nr = (offset >> PAGE_SHIFT) & pages_mask;
- page_offset = offset & (PAGE_SIZE - 1);
- size = min_t(unsigned int, PAGE_SIZE - page_offset, len);
+ page_size = 1UL << (handle->data->data_order + PAGE_SHIFT);
+ page_offset = offset & (page_size - 1);
+ size = min_t(unsigned int, page_size - page_offset, len);
memcpy(pages[nr] + page_offset, buf, size);
@@ -3126,15 +3273,10 @@ static void perf_event_task_ctx(struct perf_event_context *ctx,
{
struct perf_event *event;
- if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
- return;
-
- rcu_read_lock();
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (perf_event_task_match(event))
perf_event_task_output(event, task_event);
}
- rcu_read_unlock();
}
static void perf_event_task_event(struct perf_task_event *task_event)
@@ -3142,11 +3284,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
struct perf_cpu_context *cpuctx;
struct perf_event_context *ctx = task_event->task_ctx;
+ rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_task_ctx(&cpuctx->ctx, task_event);
put_cpu_var(perf_cpu_context);
- rcu_read_lock();
if (!ctx)
ctx = rcu_dereference(task_event->task->perf_event_ctxp);
if (ctx)
@@ -3238,15 +3380,10 @@ static void perf_event_comm_ctx(struct perf_event_context *ctx,
{
struct perf_event *event;
- if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
- return;
-
- rcu_read_lock();
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (perf_event_comm_match(event))
perf_event_comm_output(event, comm_event);
}
- rcu_read_unlock();
}
static void perf_event_comm_event(struct perf_comm_event *comm_event)
@@ -3257,7 +3394,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
char comm[TASK_COMM_LEN];
memset(comm, 0, sizeof(comm));
- strncpy(comm, comm_event->task->comm, sizeof(comm));
+ strlcpy(comm, comm_event->task->comm, sizeof(comm));
size = ALIGN(strlen(comm)+1, sizeof(u64));
comm_event->comm = comm;
@@ -3265,11 +3402,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
+ rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_comm_ctx(&cpuctx->ctx, comm_event);
put_cpu_var(perf_cpu_context);
- rcu_read_lock();
/*
* doesn't really matter which of the child contexts the
* events ends up in.
@@ -3362,15 +3499,10 @@ static void perf_event_mmap_ctx(struct perf_event_context *ctx,
{
struct perf_event *event;
- if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
- return;
-
- rcu_read_lock();
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (perf_event_mmap_match(event, mmap_event))
perf_event_mmap_output(event, mmap_event);
}
- rcu_read_unlock();
}
static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -3426,11 +3558,11 @@ got_name:
mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
+ rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
put_cpu_var(perf_cpu_context);
- rcu_read_lock();
/*
* doesn't really matter which of the child contexts the
* events ends up in.
@@ -3569,7 +3701,11 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
perf_event_disable(event);
}
- perf_event_output(event, nmi, data, regs);
+ if (event->overflow_handler)
+ event->overflow_handler(event, nmi, data, regs);
+ else
+ perf_event_output(event, nmi, data, regs);
+
return ret;
}
@@ -3614,16 +3750,16 @@ again:
return nr;
}
-static void perf_swevent_overflow(struct perf_event *event,
+static void perf_swevent_overflow(struct perf_event *event, u64 overflow,
int nmi, struct perf_sample_data *data,
struct pt_regs *regs)
{
struct hw_perf_event *hwc = &event->hw;
int throttle = 0;
- u64 overflow;
data->period = event->hw.last_period;
- overflow = perf_swevent_set_period(event);
+ if (!overflow)
+ overflow = perf_swevent_set_period(event);
if (hwc->interrupts == MAX_INTERRUPTS)
return;
@@ -3656,14 +3792,19 @@ static void perf_swevent_add(struct perf_event *event, u64 nr,
atomic64_add(nr, &event->count);
+ if (!regs)
+ return;
+
if (!hwc->sample_period)
return;
- if (!regs)
+ if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
+ return perf_swevent_overflow(event, 1, nmi, data, regs);
+
+ if (atomic64_add_negative(nr, &hwc->period_left))
return;
- if (!atomic64_add_negative(nr, &hwc->period_left))
- perf_swevent_overflow(event, nmi, data, regs);
+ perf_swevent_overflow(event, 0, nmi, data, regs);
}
static int perf_swevent_is_counting(struct perf_event *event)
@@ -3696,25 +3837,44 @@ static int perf_swevent_is_counting(struct perf_event *event)
return 1;
}
+static int perf_tp_event_match(struct perf_event *event,
+ struct perf_sample_data *data);
+
+static int perf_exclude_event(struct perf_event *event,
+ struct pt_regs *regs)
+{
+ if (regs) {
+ if (event->attr.exclude_user && user_mode(regs))
+ return 1;
+
+ if (event->attr.exclude_kernel && !user_mode(regs))
+ return 1;
+ }
+
+ return 0;
+}
+
static int perf_swevent_match(struct perf_event *event,
enum perf_type_id type,
- u32 event_id, struct pt_regs *regs)
+ u32 event_id,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
if (!perf_swevent_is_counting(event))
return 0;
if (event->attr.type != type)
return 0;
+
if (event->attr.config != event_id)
return 0;
- if (regs) {
- if (event->attr.exclude_user && user_mode(regs))
- return 0;
+ if (perf_exclude_event(event, regs))
+ return 0;
- if (event->attr.exclude_kernel && !user_mode(regs))
- return 0;
- }
+ if (event->attr.type == PERF_TYPE_TRACEPOINT &&
+ !perf_tp_event_match(event, data))
+ return 0;
return 1;
}
@@ -3727,49 +3887,59 @@ static void perf_swevent_ctx_event(struct perf_event_context *ctx,
{
struct perf_event *event;
- if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
- return;
-
- rcu_read_lock();
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
- if (perf_swevent_match(event, type, event_id, regs))
+ if (perf_swevent_match(event, type, event_id, data, regs))
perf_swevent_add(event, nr, nmi, data, regs);
}
- rcu_read_unlock();
}
-static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx)
+int perf_swevent_get_recursion_context(void)
{
+ struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
+ int rctx;
+
if (in_nmi())
- return &cpuctx->recursion[3];
+ rctx = 3;
+ else if (in_irq())
+ rctx = 2;
+ else if (in_softirq())
+ rctx = 1;
+ else
+ rctx = 0;
- if (in_irq())
- return &cpuctx->recursion[2];
+ if (cpuctx->recursion[rctx]) {
+ put_cpu_var(perf_cpu_context);
+ return -1;
+ }
- if (in_softirq())
- return &cpuctx->recursion[1];
+ cpuctx->recursion[rctx]++;
+ barrier();
- return &cpuctx->recursion[0];
+ return rctx;
+}
+EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
+
+void perf_swevent_put_recursion_context(int rctx)
+{
+ struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+ barrier();
+ cpuctx->recursion[rctx]--;
+ put_cpu_var(perf_cpu_context);
}
+EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context);
static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
u64 nr, int nmi,
struct perf_sample_data *data,
struct pt_regs *regs)
{
- struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
- int *recursion = perf_swevent_recursion_context(cpuctx);
+ struct perf_cpu_context *cpuctx;
struct perf_event_context *ctx;
- if (*recursion)
- goto out;
-
- (*recursion)++;
- barrier();
-
+ cpuctx = &__get_cpu_var(perf_cpu_context);
+ rcu_read_lock();
perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
nr, nmi, data, regs);
- rcu_read_lock();
/*
* doesn't really matter which of the child contexts the
* events ends up in.
@@ -3778,23 +3948,24 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
if (ctx)
perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
rcu_read_unlock();
-
- barrier();
- (*recursion)--;
-
-out:
- put_cpu_var(perf_cpu_context);
}
void __perf_sw_event(u32 event_id, u64 nr, int nmi,
struct pt_regs *regs, u64 addr)
{
- struct perf_sample_data data = {
- .addr = addr,
- };
+ struct perf_sample_data data;
+ int rctx;
- do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi,
- &data, regs);
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ return;
+
+ data.addr = addr;
+ data.raw = NULL;
+
+ do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
+
+ perf_swevent_put_recursion_context(rctx);
}
static void perf_swevent_read(struct perf_event *event)
@@ -3839,6 +4010,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
event->pmu->read(event);
data.addr = 0;
+ data.raw = NULL;
+ data.period = event->hw.last_period;
regs = get_irq_regs();
/*
* In case we exclude kernel IPs or are somehow not in interrupt
@@ -3849,8 +4022,9 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
regs = task_pt_regs(current);
if (regs) {
- if (perf_event_overflow(event, 0, &data, regs))
- ret = HRTIMER_NORESTART;
+ if (!(event->attr.exclude_idle && current->pid == 0))
+ if (perf_event_overflow(event, 0, &data, regs))
+ ret = HRTIMER_NORESTART;
}
period = max_t(u64, 10000, event->hw.sample_period);
@@ -3859,6 +4033,42 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
return ret;
}
+static void perf_swevent_start_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hwc->hrtimer.function = perf_swevent_hrtimer;
+ if (hwc->sample_period) {
+ u64 period;
+
+ if (hwc->remaining) {
+ if (hwc->remaining < 0)
+ period = 10000;
+ else
+ period = hwc->remaining;
+ hwc->remaining = 0;
+ } else {
+ period = max_t(u64, 10000, hwc->sample_period);
+ }
+ __hrtimer_start_range_ns(&hwc->hrtimer,
+ ns_to_ktime(period), 0,
+ HRTIMER_MODE_REL, 0);
+ }
+}
+
+static void perf_swevent_cancel_hrtimer(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->sample_period) {
+ ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
+ hwc->remaining = ktime_to_ns(remaining);
+
+ hrtimer_cancel(&hwc->hrtimer);
+ }
+}
+
/*
* Software event: cpu wall time clock
*/
@@ -3870,8 +4080,7 @@ static void cpu_clock_perf_event_update(struct perf_event *event)
u64 now;
now = cpu_clock(cpu);
- prev = atomic64_read(&event->hw.prev_count);
- atomic64_set(&event->hw.prev_count, now);
+ prev = atomic64_xchg(&event->hw.prev_count, now);
atomic64_add(now - prev, &event->count);
}
@@ -3881,22 +4090,14 @@ static int cpu_clock_perf_event_enable(struct perf_event *event)
int cpu = raw_smp_processor_id();
atomic64_set(&hwc->prev_count, cpu_clock(cpu));
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- u64 period = max_t(u64, 10000, hwc->sample_period);
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL, 0);
- }
+ perf_swevent_start_hrtimer(event);
return 0;
}
static void cpu_clock_perf_event_disable(struct perf_event *event)
{
- if (event->hw.sample_period)
- hrtimer_cancel(&event->hw.hrtimer);
+ perf_swevent_cancel_hrtimer(event);
cpu_clock_perf_event_update(event);
}
@@ -3933,22 +4134,15 @@ static int task_clock_perf_event_enable(struct perf_event *event)
now = event->ctx->time;
atomic64_set(&hwc->prev_count, now);
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- u64 period = max_t(u64, 10000, hwc->sample_period);
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL, 0);
- }
+
+ perf_swevent_start_hrtimer(event);
return 0;
}
static void task_clock_perf_event_disable(struct perf_event *event)
{
- if (event->hw.sample_period)
- hrtimer_cancel(&event->hw.hrtimer);
+ perf_swevent_cancel_hrtimer(event);
task_clock_perf_event_update(event, event->ctx->time);
}
@@ -3976,6 +4170,7 @@ static const struct pmu perf_ops_task_clock = {
};
#ifdef CONFIG_EVENT_PROFILE
+
void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
int entry_size)
{
@@ -3994,13 +4189,21 @@ void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
if (!regs)
regs = task_pt_regs(current);
+ /* Trace events already protected against recursion */
do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
&data, regs);
}
EXPORT_SYMBOL_GPL(perf_tp_event);
-extern int ftrace_profile_enable(int);
-extern void ftrace_profile_disable(int);
+static int perf_tp_event_match(struct perf_event *event,
+ struct perf_sample_data *data)
+{
+ void *record = data->raw->data;
+
+ if (likely(!event->filter) || filter_match_preds(event->filter, record))
+ return 1;
+ return 0;
+}
static void tp_perf_event_destroy(struct perf_event *event)
{
@@ -4025,11 +4228,93 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
return &perf_ops_generic;
}
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+ char *filter_str;
+ int ret;
+
+ if (event->attr.type != PERF_TYPE_TRACEPOINT)
+ return -EINVAL;
+
+ filter_str = strndup_user(arg, PAGE_SIZE);
+ if (IS_ERR(filter_str))
+ return PTR_ERR(filter_str);
+
+ ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
+
+ kfree(filter_str);
+ return ret;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+ ftrace_profile_free_filter(event);
+}
+
#else
+
+static int perf_tp_event_match(struct perf_event *event,
+ struct perf_sample_data *data)
+{
+ return 1;
+}
+
static const struct pmu *tp_perf_event_init(struct perf_event *event)
{
return NULL;
}
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+ return -ENOENT;
+}
+
+static void perf_event_free_filter(struct perf_event *event)
+{
+}
+
+#endif /* CONFIG_EVENT_PROFILE */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+ release_bp_slot(event);
+}
+
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+ int err;
+
+ err = register_perf_hw_breakpoint(bp);
+ if (err)
+ return ERR_PTR(err);
+
+ bp->destroy = bp_perf_event_destroy;
+
+ return &perf_ops_bp;
+}
+
+void perf_bp_event(struct perf_event *bp, void *data)
+{
+ struct perf_sample_data sample;
+ struct pt_regs *regs = data;
+
+ sample.raw = NULL;
+ sample.addr = bp->attr.bp_addr;
+
+ if (!perf_exclude_event(bp, regs))
+ perf_swevent_add(bp, 1, 1, &sample, regs);
+}
+#else
+static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+{
+ return NULL;
+}
+
+void perf_bp_event(struct perf_event *bp, void *regs)
+{
+}
#endif
atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -4076,6 +4361,8 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
case PERF_COUNT_SW_CONTEXT_SWITCHES:
case PERF_COUNT_SW_CPU_MIGRATIONS:
+ case PERF_COUNT_SW_ALIGNMENT_FAULTS:
+ case PERF_COUNT_SW_EMULATION_FAULTS:
if (!event->parent) {
atomic_inc(&perf_swevent_enabled[event_id]);
event->destroy = sw_perf_event_destroy;
@@ -4096,6 +4383,7 @@ perf_event_alloc(struct perf_event_attr *attr,
struct perf_event_context *ctx,
struct perf_event *group_leader,
struct perf_event *parent_event,
+ perf_overflow_handler_t overflow_handler,
gfp_t gfpflags)
{
const struct pmu *pmu;
@@ -4138,6 +4426,11 @@ perf_event_alloc(struct perf_event_attr *attr,
event->state = PERF_EVENT_STATE_INACTIVE;
+ if (!overflow_handler && parent_event)
+ overflow_handler = parent_event->overflow_handler;
+
+ event->overflow_handler = overflow_handler;
+
if (attr->disabled)
event->state = PERF_EVENT_STATE_OFF;
@@ -4172,6 +4465,11 @@ perf_event_alloc(struct perf_event_attr *attr,
pmu = tp_perf_event_init(event);
break;
+ case PERF_TYPE_BREAKPOINT:
+ pmu = bp_perf_event_init(event);
+ break;
+
+
default:
break;
}
@@ -4284,7 +4582,7 @@ err_size:
goto out;
}
-int perf_event_set_output(struct perf_event *event, int output_fd)
+static int perf_event_set_output(struct perf_event *event, int output_fd)
{
struct perf_event *output_event = NULL;
struct file *output_file = NULL;
@@ -4414,7 +4712,7 @@ SYSCALL_DEFINE5(perf_event_open,
}
event = perf_event_alloc(&attr, cpu, ctx, group_leader,
- NULL, GFP_KERNEL);
+ NULL, NULL, GFP_KERNEL);
err = PTR_ERR(event);
if (IS_ERR(event))
goto err_put_context;
@@ -4462,6 +4760,61 @@ err_put_context:
return err;
}
+/**
+ * perf_event_create_kernel_counter
+ *
+ * @attr: attributes of the counter to create
+ * @cpu: cpu in which the counter is bound
+ * @pid: task to profile
+ */
+struct perf_event *
+perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
+ pid_t pid,
+ perf_overflow_handler_t overflow_handler)
+{
+ struct perf_event *event;
+ struct perf_event_context *ctx;
+ int err;
+
+ /*
+ * Get the target context (task or percpu):
+ */
+
+ ctx = find_get_context(pid, cpu);
+ if (IS_ERR(ctx)) {
+ err = PTR_ERR(ctx);
+ goto err_exit;
+ }
+
+ event = perf_event_alloc(attr, cpu, ctx, NULL,
+ NULL, overflow_handler, GFP_KERNEL);
+ if (IS_ERR(event)) {
+ err = PTR_ERR(event);
+ goto err_put_context;
+ }
+
+ event->filp = NULL;
+ WARN_ON_ONCE(ctx->parent_ctx);
+ mutex_lock(&ctx->mutex);
+ perf_install_in_context(ctx, event, cpu);
+ ++ctx->generation;
+ mutex_unlock(&ctx->mutex);
+
+ event->owner = current;
+ get_task_struct(current);
+ mutex_lock(&current->perf_event_mutex);
+ list_add_tail(&event->owner_entry, &current->perf_event_list);
+ mutex_unlock(&current->perf_event_mutex);
+
+ return event;
+
+ err_put_context:
+ put_ctx(ctx);
+ err_exit:
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
+
/*
* inherit a event from parent task to child task:
*/
@@ -4487,7 +4840,7 @@ inherit_event(struct perf_event *parent_event,
child_event = perf_event_alloc(&parent_event->attr,
parent_event->cpu, child_ctx,
group_leader, parent_event,
- GFP_KERNEL);
+ NULL, GFP_KERNEL);
if (IS_ERR(child_event))
return child_event;
get_ctx(child_ctx);
@@ -4505,6 +4858,8 @@ inherit_event(struct perf_event *parent_event,
if (parent_event->attr.freq)
child_event->hw.sample_period = parent_event->hw.sample_period;
+ child_event->overflow_handler = parent_event->overflow_handler;
+
/*
* Link it up in the child's context:
*/
@@ -4594,7 +4949,6 @@ __perf_event_exit_task(struct perf_event *child_event,
{
struct perf_event *parent_event;
- update_event_times(child_event);
perf_event_remove_from_context(child_event);
parent_event = child_event->parent;
@@ -4638,7 +4992,7 @@ void perf_event_exit_task(struct task_struct *child)
* reading child->perf_event_ctxp, we wait until it has
* incremented the context's refcount before we do put_ctx below.
*/
- spin_lock(&child_ctx->lock);
+ raw_spin_lock(&child_ctx->lock);
child->perf_event_ctxp = NULL;
/*
* If this context is a clone; unclone it so it can't get
@@ -4646,7 +5000,8 @@ void perf_event_exit_task(struct task_struct *child)
* the events from it.
*/
unclone_ctx(child_ctx);
- spin_unlock_irqrestore(&child_ctx->lock, flags);
+ update_context_time(child_ctx);
+ raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
/*
* Report the task dead after unscheduling the events so that we
@@ -4729,7 +5084,7 @@ again:
*/
int perf_event_init_task(struct task_struct *child)
{
- struct perf_event_context *child_ctx, *parent_ctx;
+ struct perf_event_context *child_ctx = NULL, *parent_ctx;
struct perf_event_context *cloned_ctx;
struct perf_event *event;
struct task_struct *parent = current;
@@ -4745,20 +5100,6 @@ int perf_event_init_task(struct task_struct *child)
return 0;
/*
- * This is executed from the parent task context, so inherit
- * events that have been marked for cloning.
- * First allocate and initialize a context for the child.
- */
-
- child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
- if (!child_ctx)
- return -ENOMEM;
-
- __perf_event_init_context(child_ctx, child);
- child->perf_event_ctxp = child_ctx;
- get_task_struct(child);
-
- /*
* If the parent's context is a clone, pin it so it won't get
* swapped under us.
*/
@@ -4781,15 +5122,33 @@ int perf_event_init_task(struct task_struct *child)
* We dont have to disable NMIs - we are only looking at
* the list, not manipulating it:
*/
- list_for_each_entry_rcu(event, &parent_ctx->event_list, event_entry) {
- if (event != event->group_leader)
- continue;
+ list_for_each_entry(event, &parent_ctx->group_list, group_entry) {
if (!event->attr.inherit) {
inherited_all = 0;
continue;
}
+ if (!child->perf_event_ctxp) {
+ /*
+ * This is executed from the parent task context, so
+ * inherit events that have been marked for cloning.
+ * First allocate and initialize a context for the
+ * child.
+ */
+
+ child_ctx = kzalloc(sizeof(struct perf_event_context),
+ GFP_KERNEL);
+ if (!child_ctx) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ __perf_event_init_context(child_ctx, child);
+ child->perf_event_ctxp = child_ctx;
+ get_task_struct(child);
+ }
+
ret = inherit_group(event, parent, parent_ctx,
child, child_ctx);
if (ret) {
@@ -4818,6 +5177,7 @@ int perf_event_init_task(struct task_struct *child)
get_ctx(child_ctx->parent_ctx);
}
+exit:
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
@@ -4932,11 +5292,11 @@ perf_set_reserve_percpu(struct sysdev_class *class,
perf_reserved_percpu = val;
for_each_online_cpu(cpu) {
cpuctx = &per_cpu(perf_cpu_context, cpu);
- spin_lock_irq(&cpuctx->ctx.lock);
+ raw_spin_lock_irq(&cpuctx->ctx.lock);
mpt = min(perf_max_events - cpuctx->ctx.nr_events,
perf_max_events - perf_reserved_percpu);
cpuctx->max_pertask = mpt;
- spin_unlock_irq(&cpuctx->ctx.lock);
+ raw_spin_unlock_irq(&cpuctx->ctx.lock);
}
spin_unlock(&perf_resource_lock);
diff --git a/kernel/pid.c b/kernel/pid.c
index d3f722d20f9..2e17c9c92cb 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -141,11 +141,12 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
* installing it:
*/
spin_lock_irq(&pidmap_lock);
- if (map->page)
- kfree(page);
- else
+ if (!map->page) {
map->page = page;
+ page = NULL;
+ }
spin_unlock_irq(&pidmap_lock);
+ kfree(page);
if (unlikely(!map->page))
break;
}
@@ -268,12 +269,11 @@ struct pid *alloc_pid(struct pid_namespace *ns)
for (type = 0; type < PIDTYPE_MAX; ++type)
INIT_HLIST_HEAD(&pid->tasks[type]);
+ upid = pid->numbers + ns->level;
spin_lock_irq(&pidmap_lock);
- for (i = ns->level; i >= 0; i--) {
- upid = &pid->numbers[i];
+ for ( ; upid >= pid->numbers; --upid)
hlist_add_head_rcu(&upid->pid_chain,
&pid_hash[pid_hashfn(upid->nr, upid->ns)]);
- }
spin_unlock_irq(&pidmap_lock);
out:
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 821722ae58a..86b3796b043 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -118,7 +118,7 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old
{
if (!(flags & CLONE_NEWPID))
return get_pid_ns(old_ns);
- if (flags & CLONE_THREAD)
+ if (flags & (CLONE_THREAD|CLONE_PARENT))
return ERR_PTR(-EINVAL);
return create_pid_namespace(old_ns);
}
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index dfdec524d1b..3db49b9ca37 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -29,7 +29,6 @@
#include <linux/pm_qos_params.h>
#include <linux/sched.h>
-#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/time.h>
@@ -344,37 +343,33 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
}
EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
-#define PID_NAME_LEN sizeof("process_1234567890")
-static char name[PID_NAME_LEN];
+#define PID_NAME_LEN 32
static int pm_qos_power_open(struct inode *inode, struct file *filp)
{
int ret;
long pm_qos_class;
+ char name[PID_NAME_LEN];
- lock_kernel();
pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
if (pm_qos_class >= 0) {
filp->private_data = (void *)pm_qos_class;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
ret = pm_qos_add_requirement(pm_qos_class, name,
PM_QOS_DEFAULT_VALUE);
- if (ret >= 0) {
- unlock_kernel();
+ if (ret >= 0)
return 0;
- }
}
- unlock_kernel();
-
return -EPERM;
}
static int pm_qos_power_release(struct inode *inode, struct file *filp)
{
int pm_qos_class;
+ char name[PID_NAME_LEN];
pm_qos_class = (long)filp->private_data;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
pm_qos_remove_requirement(pm_qos_class, name);
return 0;
@@ -385,13 +380,14 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
{
s32 value;
int pm_qos_class;
+ char name[PID_NAME_LEN];
pm_qos_class = (long)filp->private_data;
if (count != sizeof(s32))
return -EINVAL;
if (copy_from_user(&value, buf, sizeof(s32)))
return -EFAULT;
- sprintf(name, "process_%d", current->pid);
+ snprintf(name, PID_NAME_LEN, "process_%d", current->pid);
pm_qos_update_requirement(pm_qos_class, name, value);
return sizeof(s32);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 5c9dc228747..438ff452351 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -384,7 +384,8 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
/*
* Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
- * This is called from sys_timer_create with the new timer already locked.
+ * This is called from sys_timer_create() and do_cpu_nanosleep() with the
+ * new timer already all-zeros initialized.
*/
int posix_cpu_timer_create(struct k_itimer *new_timer)
{
@@ -396,8 +397,6 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
return -EINVAL;
INIT_LIST_HEAD(&new_timer->it.cpu.entry);
- new_timer->it.cpu.incr.sched = 0;
- new_timer->it.cpu.expires.sched = 0;
read_lock(&tasklist_lock);
if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index c3b81c30e5d..43191815f87 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_PM_SLEEP) += console.o
obj-$(CONFIG_FREEZER) += process.o
obj-$(CONFIG_SUSPEND) += suspend.o
obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o
-obj-$(CONFIG_HIBERNATION) += swsusp.o hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o
obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 5187136fe1d..218e5af9015 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -6,7 +6,7 @@
#include <linux/vt_kern.h>
#include <linux/kbd_kern.h>
-#include <linux/console.h>
+#include <linux/vt.h>
#include <linux/module.h>
#include "power.h"
@@ -21,8 +21,7 @@ int pm_prepare_console(void)
if (orig_fgconsole < 0)
return 1;
- orig_kmsg = kmsg_redirect;
- kmsg_redirect = SUSPEND_CONSOLE;
+ orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
return 0;
}
@@ -30,7 +29,7 @@ void pm_restore_console(void)
{
if (orig_fgconsole >= 0) {
vt_move_to_console(orig_fgconsole, 0);
- kmsg_redirect = orig_kmsg;
+ vt_kmsg_redirect(orig_kmsg);
}
}
#endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 04b3a83d686..bbfe472d752 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -32,6 +32,7 @@ static int noresume = 0;
static char resume_file[256] = CONFIG_PM_STD_PARTITION;
dev_t swsusp_resume_device;
sector_t swsusp_resume_block;
+int in_suspend __nosavedata = 0;
enum {
HIBERNATION_INVALID,
@@ -202,6 +203,35 @@ static void platform_recover(int platform_mode)
}
/**
+ * swsusp_show_speed - print the time elapsed between two events.
+ * @start: Starting event.
+ * @stop: Final event.
+ * @nr_pages - number of pages processed between @start and @stop
+ * @msg - introductory message to print
+ */
+
+void swsusp_show_speed(struct timeval *start, struct timeval *stop,
+ unsigned nr_pages, char *msg)
+{
+ s64 elapsed_centisecs64;
+ int centisecs;
+ int k;
+ int kps;
+
+ elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start);
+ do_div(elapsed_centisecs64, NSEC_PER_SEC / 100);
+ centisecs = elapsed_centisecs64;
+ if (centisecs == 0)
+ centisecs = 1; /* avoid div-by-zero */
+ k = nr_pages * (PAGE_SIZE / 1024);
+ kps = (k * 100) / centisecs;
+ printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n",
+ msg, k,
+ centisecs / 100, centisecs % 100,
+ kps / 1000, (kps % 1000) / 10);
+}
+
+/**
* create_image - freeze devices that need to be frozen with interrupts
* off, create the hibernation image and thaw those devices. Control
* reappears in this routine after a restore.
@@ -693,21 +723,22 @@ static int software_resume(void)
/* The snapshot device should not be opened while we're running */
if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
error = -EBUSY;
+ swsusp_close(FMODE_READ);
goto Unlock;
}
pm_prepare_console();
error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
if (error)
- goto Finish;
+ goto close_finish;
error = usermodehelper_disable();
if (error)
- goto Finish;
+ goto close_finish;
error = create_basic_memory_bitmaps();
if (error)
- goto Finish;
+ goto close_finish;
pr_debug("PM: Preparing processes for restore.\n");
error = prepare_processes();
@@ -719,6 +750,7 @@ static int software_resume(void)
pr_debug("PM: Reading hibernation image.\n");
error = swsusp_read(&flags);
+ swsusp_close(FMODE_READ);
if (!error)
hibernation_restore(flags & SF_PLATFORM_MODE);
@@ -737,6 +769,9 @@ static int software_resume(void)
mutex_unlock(&pm_mutex);
pr_debug("PM: Resume from disk failed.\n");
return error;
+close_finish:
+ swsusp_close(FMODE_READ);
+ goto Finish;
}
late_initcall(software_resume);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 347d2cc88cd..0998c713905 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -220,6 +220,7 @@ static struct attribute_group attr_group = {
#ifdef CONFIG_PM_RUNTIME
struct workqueue_struct *pm_wq;
+EXPORT_SYMBOL_GPL(pm_wq);
static int __init pm_start_workqueue(void)
{
diff --git a/kernel/power/process.c b/kernel/power/process.c
index cc2e55373b6..5ade1bdcf36 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/freezer.h>
+#include <linux/delay.h>
/*
* Timeout for stopping processes
@@ -41,7 +42,7 @@ static int try_to_freeze_tasks(bool sig_only)
do_gettimeofday(&start);
end_time = jiffies + TIMEOUT;
- do {
+ while (true) {
todo = 0;
read_lock(&tasklist_lock);
do_each_thread(g, p) {
@@ -62,10 +63,15 @@ static int try_to_freeze_tasks(bool sig_only)
todo++;
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
- yield(); /* Yield is okay here */
- if (time_after(jiffies, end_time))
+ if (!todo || time_after(jiffies, end_time))
break;
- } while (todo);
+
+ /*
+ * We need to retry, but first give the freezing tasks some
+ * time to enter the regrigerator.
+ */
+ msleep(10);
+ }
do_gettimeofday(&end);
elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 17d8bb1acf9..25596e450ac 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -19,7 +19,7 @@
* The time it takes is system-specific though, so when we test this
* during system bootup we allow a LOT of time.
*/
-#define TEST_SUSPEND_SECONDS 5
+#define TEST_SUSPEND_SECONDS 10
static unsigned long suspend_test_start_time;
@@ -49,7 +49,8 @@ void suspend_test_finish(const char *label)
* has some performance issues. The stack dump of a WARN_ON
* is more likely to get the right attention than a printk...
*/
- WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
+ WARN(msec > (TEST_SUSPEND_SECONDS * 1000),
+ "Component: %s, time: %u\n", label, msec);
}
/*
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8ba052c86d4..09b2b0ae9e9 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -13,7 +13,6 @@
#include <linux/module.h>
#include <linux/file.h>
-#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/genhd.h>
@@ -39,6 +38,107 @@ struct swsusp_header {
static struct swsusp_header *swsusp_header;
+/**
+ * The following functions are used for tracing the allocated
+ * swap pages, so that they can be freed in case of an error.
+ */
+
+struct swsusp_extent {
+ struct rb_node node;
+ unsigned long start;
+ unsigned long end;
+};
+
+static struct rb_root swsusp_extents = RB_ROOT;
+
+static int swsusp_extents_insert(unsigned long swap_offset)
+{
+ struct rb_node **new = &(swsusp_extents.rb_node);
+ struct rb_node *parent = NULL;
+ struct swsusp_extent *ext;
+
+ /* Figure out where to put the new node */
+ while (*new) {
+ ext = container_of(*new, struct swsusp_extent, node);
+ parent = *new;
+ if (swap_offset < ext->start) {
+ /* Try to merge */
+ if (swap_offset == ext->start - 1) {
+ ext->start--;
+ return 0;
+ }
+ new = &((*new)->rb_left);
+ } else if (swap_offset > ext->end) {
+ /* Try to merge */
+ if (swap_offset == ext->end + 1) {
+ ext->end++;
+ return 0;
+ }
+ new = &((*new)->rb_right);
+ } else {
+ /* It already is in the tree */
+ return -EINVAL;
+ }
+ }
+ /* Add the new node and rebalance the tree. */
+ ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL);
+ if (!ext)
+ return -ENOMEM;
+
+ ext->start = swap_offset;
+ ext->end = swap_offset;
+ rb_link_node(&ext->node, parent, new);
+ rb_insert_color(&ext->node, &swsusp_extents);
+ return 0;
+}
+
+/**
+ * alloc_swapdev_block - allocate a swap page and register that it has
+ * been allocated, so that it can be freed in case of an error.
+ */
+
+sector_t alloc_swapdev_block(int swap)
+{
+ unsigned long offset;
+
+ offset = swp_offset(get_swap_page_of_type(swap));
+ if (offset) {
+ if (swsusp_extents_insert(offset))
+ swap_free(swp_entry(swap, offset));
+ else
+ return swapdev_block(swap, offset);
+ }
+ return 0;
+}
+
+/**
+ * free_all_swap_pages - free swap pages allocated for saving image data.
+ * It also frees the extents used to register which swap entres had been
+ * allocated.
+ */
+
+void free_all_swap_pages(int swap)
+{
+ struct rb_node *node;
+
+ while ((node = swsusp_extents.rb_node)) {
+ struct swsusp_extent *ext;
+ unsigned long offset;
+
+ ext = container_of(node, struct swsusp_extent, node);
+ rb_erase(node, &swsusp_extents);
+ for (offset = ext->start; offset <= ext->end; offset++)
+ swap_free(swp_entry(swap, offset));
+
+ kfree(ext);
+ }
+}
+
+int swsusp_swap_in_use(void)
+{
+ return (swsusp_extents.rb_node != NULL);
+}
+
/*
* General things
*/
@@ -315,7 +415,6 @@ static int save_image(struct swap_map_handle *handle,
{
unsigned int m;
int ret;
- int error = 0;
int nr_pages;
int err2;
struct bio *bio;
@@ -330,26 +429,27 @@ static int save_image(struct swap_map_handle *handle,
nr_pages = 0;
bio = NULL;
do_gettimeofday(&start);
- do {
+ while (1) {
ret = snapshot_read_next(snapshot, PAGE_SIZE);
- if (ret > 0) {
- error = swap_write_page(handle, data_of(*snapshot),
- &bio);
- if (error)
- break;
- if (!(nr_pages % m))
- printk("\b\b\b\b%3d%%", nr_pages / m);
- nr_pages++;
- }
- } while (ret > 0);
+ if (ret <= 0)
+ break;
+ ret = swap_write_page(handle, data_of(*snapshot), &bio);
+ if (ret)
+ break;
+ if (!(nr_pages % m))
+ printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
+ nr_pages++;
+ }
err2 = wait_on_bio_chain(&bio);
do_gettimeofday(&stop);
- if (!error)
- error = err2;
- if (!error)
- printk("\b\b\b\bdone\n");
+ if (!ret)
+ ret = err2;
+ if (!ret)
+ printk(KERN_CONT "\b\b\b\bdone\n");
+ else
+ printk(KERN_CONT "\n");
swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
- return error;
+ return ret;
}
/**
@@ -537,7 +637,8 @@ static int load_image(struct swap_map_handle *handle,
snapshot_write_finalize(snapshot);
if (!snapshot_image_loaded(snapshot))
error = -ENODATA;
- }
+ } else
+ printk("\n");
swsusp_show_speed(&start, &stop, nr_to_read, "Read");
return error;
}
@@ -573,8 +674,6 @@ int swsusp_read(unsigned int *flags_p)
error = load_image(&handle, &snapshot, header->pages - 1);
release_swap_reader(&handle);
- blkdev_put(resume_bdev, FMODE_READ);
-
if (!error)
pr_debug("PM: Image successfully loaded\n");
else
@@ -597,7 +696,7 @@ int swsusp_check(void)
error = bio_read_page(swsusp_resume_block,
swsusp_header, NULL);
if (error)
- return error;
+ goto put;
if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
@@ -605,8 +704,10 @@ int swsusp_check(void)
error = bio_write_page(swsusp_resume_block,
swsusp_header, NULL);
} else {
- return -EINVAL;
+ error = -EINVAL;
}
+
+put:
if (error)
blkdev_put(resume_bdev, FMODE_READ);
else
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 6a07f4dbf2f..5b3601bd189 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -56,133 +56,3 @@
#include "power.h"
int in_suspend __nosavedata = 0;
-
-/**
- * The following functions are used for tracing the allocated
- * swap pages, so that they can be freed in case of an error.
- */
-
-struct swsusp_extent {
- struct rb_node node;
- unsigned long start;
- unsigned long end;
-};
-
-static struct rb_root swsusp_extents = RB_ROOT;
-
-static int swsusp_extents_insert(unsigned long swap_offset)
-{
- struct rb_node **new = &(swsusp_extents.rb_node);
- struct rb_node *parent = NULL;
- struct swsusp_extent *ext;
-
- /* Figure out where to put the new node */
- while (*new) {
- ext = container_of(*new, struct swsusp_extent, node);
- parent = *new;
- if (swap_offset < ext->start) {
- /* Try to merge */
- if (swap_offset == ext->start - 1) {
- ext->start--;
- return 0;
- }
- new = &((*new)->rb_left);
- } else if (swap_offset > ext->end) {
- /* Try to merge */
- if (swap_offset == ext->end + 1) {
- ext->end++;
- return 0;
- }
- new = &((*new)->rb_right);
- } else {
- /* It already is in the tree */
- return -EINVAL;
- }
- }
- /* Add the new node and rebalance the tree. */
- ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL);
- if (!ext)
- return -ENOMEM;
-
- ext->start = swap_offset;
- ext->end = swap_offset;
- rb_link_node(&ext->node, parent, new);
- rb_insert_color(&ext->node, &swsusp_extents);
- return 0;
-}
-
-/**
- * alloc_swapdev_block - allocate a swap page and register that it has
- * been allocated, so that it can be freed in case of an error.
- */
-
-sector_t alloc_swapdev_block(int swap)
-{
- unsigned long offset;
-
- offset = swp_offset(get_swap_page_of_type(swap));
- if (offset) {
- if (swsusp_extents_insert(offset))
- swap_free(swp_entry(swap, offset));
- else
- return swapdev_block(swap, offset);
- }
- return 0;
-}
-
-/**
- * free_all_swap_pages - free swap pages allocated for saving image data.
- * It also frees the extents used to register which swap entres had been
- * allocated.
- */
-
-void free_all_swap_pages(int swap)
-{
- struct rb_node *node;
-
- while ((node = swsusp_extents.rb_node)) {
- struct swsusp_extent *ext;
- unsigned long offset;
-
- ext = container_of(node, struct swsusp_extent, node);
- rb_erase(node, &swsusp_extents);
- for (offset = ext->start; offset <= ext->end; offset++)
- swap_free(swp_entry(swap, offset));
-
- kfree(ext);
- }
-}
-
-int swsusp_swap_in_use(void)
-{
- return (swsusp_extents.rb_node != NULL);
-}
-
-/**
- * swsusp_show_speed - print the time elapsed between two events represented by
- * @start and @stop
- *
- * @nr_pages - number of pages processed between @start and @stop
- * @msg - introductory message to print
- */
-
-void swsusp_show_speed(struct timeval *start, struct timeval *stop,
- unsigned nr_pages, char *msg)
-{
- s64 elapsed_centisecs64;
- int centisecs;
- int k;
- int kps;
-
- elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start);
- do_div(elapsed_centisecs64, NSEC_PER_SEC / 100);
- centisecs = elapsed_centisecs64;
- if (centisecs == 0)
- centisecs = 1; /* avoid div-by-zero */
- k = nr_pages * (PAGE_SIZE / 1024);
- kps = (k * 100) / centisecs;
- printk(KERN_INFO "PM: %s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n",
- msg, k,
- centisecs / 100, centisecs % 100,
- kps / 1000, (kps % 1000) / 10);
-}
diff --git a/kernel/printk.c b/kernel/printk.c
index 2a564570f82..1ded8e7dd19 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -33,6 +33,7 @@
#include <linux/bootmem.h>
#include <linux/syscalls.h>
#include <linux/kexec.h>
+#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
#include <asm/uaccess.h>
@@ -1377,11 +1378,11 @@ late_initcall(disable_boot_consoles);
*/
DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
-int printk_ratelimit(void)
+int __printk_ratelimit(const char *func)
{
- return __ratelimit(&printk_ratelimit_state);
+ return ___ratelimit(&printk_ratelimit_state, func);
}
-EXPORT_SYMBOL(printk_ratelimit);
+EXPORT_SYMBOL(__printk_ratelimit);
/**
* printk_timed_ratelimit - caller-controlled printk ratelimiting
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 307c285af59..23bd09cd042 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -266,9 +266,10 @@ static int ignoring_children(struct sighand_struct *sigh)
* or self-reaping. Do notification now if it would have happened earlier.
* If it should reap itself, return true.
*
- * If it's our own child, there is no notification to do.
- * But if our normal children self-reap, then this child
- * was prevented by ptrace and we must reap it now.
+ * If it's our own child, there is no notification to do. But if our normal
+ * children self-reap, then this child was prevented by ptrace and we must
+ * reap it now, in that case we must also wake up sub-threads sleeping in
+ * do_wait().
*/
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
{
@@ -278,8 +279,10 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
if (!task_detached(p) && thread_group_empty(p)) {
if (!same_thread_group(p->real_parent, tracer))
do_notify_parent(p, p->exit_signal);
- else if (ignoring_children(tracer->sighand))
+ else if (ignoring_children(tracer->sighand)) {
+ __wake_up_parent(p, tracer);
p->exit_signal = -1;
+ }
}
if (task_detached(p)) {
/* Mark it as in the process of being reaped. */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 37ac4548308..9b7fd472387 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,23 +44,13 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
-#include <linux/kernel_stat.h>
-enum rcu_barrier {
- RCU_BARRIER_STD,
- RCU_BARRIER_BH,
- RCU_BARRIER_SCHED,
-};
-
-static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
-static atomic_t rcu_barrier_cpu_count;
-static DEFINE_MUTEX(rcu_barrier_mutex);
-static struct completion rcu_barrier_completion;
-int rcu_scheduler_active __read_mostly;
-
-static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
-static struct rcu_head rcu_migrate_head[3];
-static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_key;
+struct lockdep_map rcu_lock_map =
+ STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+EXPORT_SYMBOL_GPL(rcu_lock_map);
+#endif
/*
* Awaken the corresponding synchronize_rcu() instance now that a
@@ -73,241 +63,3 @@ void wakeme_after_rcu(struct rcu_head *head)
rcu = container_of(head, struct rcu_synchronize, head);
complete(&rcu->completion);
}
-
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-/**
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void synchronize_rcu(void)
-{
- struct rcu_synchronize rcu;
-
- if (!rcu_scheduler_active)
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-/**
- * synchronize_sched - wait until an rcu-sched grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-sched
- * grace period has elapsed, in other words after all currently executing
- * rcu-sched read-side critical sections have completed. These read-side
- * critical sections are delimited by rcu_read_lock_sched() and
- * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
- * local_irq_disable(), and so on may be used in place of
- * rcu_read_lock_sched().
- *
- * This means that all preempt_disable code sequences, including NMI and
- * hardware-interrupt handlers, in progress on entry will have completed
- * before this primitive returns. However, this does not guarantee that
- * softirq handlers will have completed, since in some kernels, these
- * handlers can run in process context, and can block.
- *
- * This primitive provides the guarantees made by the (now removed)
- * synchronize_kernel() API. In contrast, synchronize_rcu() only
- * guarantees that rcu_read_lock() sections will have completed.
- * In "classic RCU", these two guarantees happen to be one and
- * the same, but can differ in realtime RCU implementations.
- */
-void synchronize_sched(void)
-{
- struct rcu_synchronize rcu;
-
- if (rcu_blocking_is_gp())
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu_sched(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_sched);
-
-/**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu_bh grace
- * period has elapsed, in other words after all currently executing rcu_bh
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
- * and may be nested.
- */
-void synchronize_rcu_bh(void)
-{
- struct rcu_synchronize rcu;
-
- if (rcu_blocking_is_gp())
- return;
-
- init_completion(&rcu.completion);
- /* Will wake me after RCU finished. */
- call_rcu_bh(&rcu.head, wakeme_after_rcu);
- /* Wait for it. */
- wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
-static void rcu_barrier_callback(struct rcu_head *notused)
-{
- if (atomic_dec_and_test(&rcu_barrier_cpu_count))
- complete(&rcu_barrier_completion);
-}
-
-/*
- * Called with preemption disabled, and from cross-cpu IRQ context.
- */
-static void rcu_barrier_func(void *type)
-{
- int cpu = smp_processor_id();
- struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
-
- atomic_inc(&rcu_barrier_cpu_count);
- switch ((enum rcu_barrier)type) {
- case RCU_BARRIER_STD:
- call_rcu(head, rcu_barrier_callback);
- break;
- case RCU_BARRIER_BH:
- call_rcu_bh(head, rcu_barrier_callback);
- break;
- case RCU_BARRIER_SCHED:
- call_rcu_sched(head, rcu_barrier_callback);
- break;
- }
-}
-
-static inline void wait_migrated_callbacks(void)
-{
- wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
- smp_mb(); /* In case we didn't sleep. */
-}
-
-/*
- * Orchestrate the specified type of RCU barrier, waiting for all
- * RCU callbacks of the specified type to complete.
- */
-static void _rcu_barrier(enum rcu_barrier type)
-{
- BUG_ON(in_interrupt());
- /* Take cpucontrol mutex to protect against CPU hotplug */
- mutex_lock(&rcu_barrier_mutex);
- init_completion(&rcu_barrier_completion);
- /*
- * Initialize rcu_barrier_cpu_count to 1, then invoke
- * rcu_barrier_func() on each CPU, so that each CPU also has
- * incremented rcu_barrier_cpu_count. Only then is it safe to
- * decrement rcu_barrier_cpu_count -- otherwise the first CPU
- * might complete its grace period before all of the other CPUs
- * did their increment, causing this function to return too
- * early.
- */
- atomic_set(&rcu_barrier_cpu_count, 1);
- on_each_cpu(rcu_barrier_func, (void *)type, 1);
- if (atomic_dec_and_test(&rcu_barrier_cpu_count))
- complete(&rcu_barrier_completion);
- wait_for_completion(&rcu_barrier_completion);
- mutex_unlock(&rcu_barrier_mutex);
- wait_migrated_callbacks();
-}
-
-/**
- * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
- */
-void rcu_barrier(void)
-{
- _rcu_barrier(RCU_BARRIER_STD);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier);
-
-/**
- * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
- */
-void rcu_barrier_bh(void)
-{
- _rcu_barrier(RCU_BARRIER_BH);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_bh);
-
-/**
- * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
- */
-void rcu_barrier_sched(void)
-{
- _rcu_barrier(RCU_BARRIER_SCHED);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_sched);
-
-static void rcu_migrate_callback(struct rcu_head *notused)
-{
- if (atomic_dec_and_test(&rcu_migrate_type_count))
- wake_up(&rcu_migrate_wq);
-}
-
-extern int rcu_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu);
-
-static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- rcu_cpu_notify(self, action, hcpu);
- if (action == CPU_DYING) {
- /*
- * preempt_disable() in on_each_cpu() prevents stop_machine(),
- * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
- * returns, all online cpus have queued rcu_barrier_func(),
- * and the dead cpu(if it exist) queues rcu_migrate_callback()s.
- *
- * These callbacks ensure _rcu_barrier() waits for all
- * RCU callbacks of the specified type to complete.
- */
- atomic_set(&rcu_migrate_type_count, 3);
- call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
- call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
- call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
- } else if (action == CPU_DOWN_PREPARE) {
- /* Don't need to wait until next removal operation. */
- /* rcu_migrate_head is protected by cpu_add_remove_lock */
- wait_migrated_callbacks();
- }
-
- return NOTIFY_OK;
-}
-
-void __init rcu_init(void)
-{
- int i;
-
- __rcu_init();
- cpu_notifier(rcu_barrier_cpu_hotplug, 0);
-
- /*
- * We don't need protection against CPU-hotplug here because
- * this is called early in boot, before either interrupts
- * or the scheduler are operational.
- */
- for_each_online_cpu(i)
- rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
-}
-
-void rcu_scheduler_starting(void)
-{
- WARN_ON(num_online_cpus() != 1);
- WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = 1;
-}
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
new file mode 100644
index 00000000000..9f6d9ff2572
--- /dev/null
+++ b/kernel/rcutiny.c
@@ -0,0 +1,282 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
+ *
+ * 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 IBM Corporation, 2008
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * Documentation/RCU
+ */
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/cpu.h>
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+ struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
+ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
+ struct rcu_head **curtail; /* ->next pointer of last CB. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_ctrlblk = {
+ .donetail = &rcu_ctrlblk.rcucblist,
+ .curtail = &rcu_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+ .donetail = &rcu_bh_ctrlblk.rcucblist,
+ .curtail = &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_NO_HZ
+
+static long rcu_dynticks_nesting = 1;
+
+/*
+ * Enter dynticks-idle mode, which is an extended quiescent state
+ * if we have fully entered that mode (i.e., if the new value of
+ * dynticks_nesting is zero).
+ */
+void rcu_enter_nohz(void)
+{
+ if (--rcu_dynticks_nesting == 0)
+ rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
+
+/*
+ * Exit dynticks-idle mode, so that we are no longer in an extended
+ * quiescent state.
+ */
+void rcu_exit_nohz(void)
+{
+ rcu_dynticks_nesting++;
+}
+
+#endif /* #ifdef CONFIG_NO_HZ */
+
+/*
+ * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc().
+ * Also disable irqs to avoid confusion due to interrupt handlers
+ * invoking call_rcu().
+ */
+static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (rcp->rcucblist != NULL &&
+ rcp->donetail != rcp->curtail) {
+ rcp->donetail = rcp->curtail;
+ local_irq_restore(flags);
+ return 1;
+ }
+ local_irq_restore(flags);
+
+ return 0;
+}
+
+/*
+ * Record an rcu quiescent state. And an rcu_bh quiescent state while we
+ * are at it, given that any rcu quiescent state is also an rcu_bh
+ * quiescent state. Use "+" instead of "||" to defeat short circuiting.
+ */
+void rcu_sched_qs(int cpu)
+{
+ if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+ raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Record an rcu_bh quiescent state.
+ */
+void rcu_bh_qs(int cpu)
+{
+ if (rcu_qsctr_help(&rcu_bh_ctrlblk))
+ raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Check to see if the scheduling-clock interrupt came from an extended
+ * quiescent state, and, if so, tell RCU about it.
+ */
+void rcu_check_callbacks(int cpu, int user)
+{
+ if (user ||
+ (idle_cpu(cpu) &&
+ !in_softirq() &&
+ hardirq_count() <= (1 << HARDIRQ_SHIFT)))
+ rcu_sched_qs(cpu);
+ else if (!in_softirq())
+ rcu_bh_qs(cpu);
+}
+
+/*
+ * Helper function for rcu_process_callbacks() that operates on the
+ * specified rcu_ctrlkblk structure.
+ */
+static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+{
+ struct rcu_head *next, *list;
+ unsigned long flags;
+
+ /* If no RCU callbacks ready to invoke, just return. */
+ if (&rcp->rcucblist == rcp->donetail)
+ return;
+
+ /* Move the ready-to-invoke callbacks to a local list. */
+ local_irq_save(flags);
+ list = rcp->rcucblist;
+ rcp->rcucblist = *rcp->donetail;
+ *rcp->donetail = NULL;
+ if (rcp->curtail == rcp->donetail)
+ rcp->curtail = &rcp->rcucblist;
+ rcp->donetail = &rcp->rcucblist;
+ local_irq_restore(flags);
+
+ /* Invoke the callbacks on the local list. */
+ while (list) {
+ next = list->next;
+ prefetch(next);
+ list->func(list);
+ list = next;
+ }
+}
+
+/*
+ * Invoke any callbacks whose grace period has completed.
+ */
+static void rcu_process_callbacks(struct softirq_action *unused)
+{
+ __rcu_process_callbacks(&rcu_ctrlblk);
+ __rcu_process_callbacks(&rcu_bh_ctrlblk);
+}
+
+/*
+ * Wait for a grace period to elapse. But it is illegal to invoke
+ * synchronize_sched() from within an RCU read-side critical section.
+ * Therefore, any legal call to synchronize_sched() is a quiescent
+ * state, and so on a UP system, synchronize_sched() need do nothing.
+ * Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the
+ * benefits of doing might_sleep() to reduce latency.)
+ *
+ * Cool, huh? (Due to Josh Triplett.)
+ *
+ * But we want to make this a static inline later.
+ */
+void synchronize_sched(void)
+{
+ cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched);
+
+void synchronize_rcu_bh(void)
+{
+ synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
+/*
+ * Helper function for call_rcu() and call_rcu_bh().
+ */
+static void __call_rcu(struct rcu_head *head,
+ void (*func)(struct rcu_head *rcu),
+ struct rcu_ctrlblk *rcp)
+{
+ unsigned long flags;
+
+ head->func = func;
+ head->next = NULL;
+
+ local_irq_save(flags);
+ *rcp->curtail = head;
+ rcp->curtail = &head->next;
+ local_irq_restore(flags);
+}
+
+/*
+ * Post an RCU callback to be invoked after the end of an RCU grace
+ * period. But since we have but one CPU, that would be after any
+ * quiescent state.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Post an RCU bottom-half callback to be invoked after any subsequent
+ * quiescent state.
+ */
+void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+ __call_rcu(head, func, &rcu_bh_ctrlblk);
+}
+EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+void rcu_barrier(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+void rcu_barrier_bh(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_bh(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+void rcu_barrier_sched(void)
+{
+ struct rcu_synchronize rcu;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_sched(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
+void __init rcu_init(void)
+{
+ open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 233768f21f9..9bb52177af0 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -327,6 +327,11 @@ rcu_torture_cb(struct rcu_head *p)
cur_ops->deferred_free(rp);
}
+static int rcu_no_completed(void)
+{
+ return 0;
+}
+
static void rcu_torture_deferred_free(struct rcu_torture *p)
{
call_rcu(&p->rtort_rcu, rcu_torture_cb);
@@ -388,6 +393,21 @@ static struct rcu_torture_ops rcu_sync_ops = {
.name = "rcu_sync"
};
+static struct rcu_torture_ops rcu_expedited_ops = {
+ .init = rcu_sync_torture_init,
+ .cleanup = NULL,
+ .readlock = rcu_torture_read_lock,
+ .read_delay = rcu_read_delay, /* just reuse rcu's version. */
+ .readunlock = rcu_torture_read_unlock,
+ .completed = rcu_no_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = synchronize_rcu_expedited,
+ .cb_barrier = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .name = "rcu_expedited"
+};
+
/*
* Definitions for rcu_bh torture testing.
*/
@@ -547,6 +567,25 @@ static struct rcu_torture_ops srcu_ops = {
.name = "srcu"
};
+static void srcu_torture_synchronize_expedited(void)
+{
+ synchronize_srcu_expedited(&srcu_ctl);
+}
+
+static struct rcu_torture_ops srcu_expedited_ops = {
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = srcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .completed = srcu_torture_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = srcu_torture_synchronize_expedited,
+ .cb_barrier = NULL,
+ .stats = srcu_torture_stats,
+ .name = "srcu_expedited"
+};
+
/*
* Definitions for sched torture testing.
*/
@@ -562,11 +601,6 @@ static void sched_torture_read_unlock(int idx)
preempt_enable();
}
-static int sched_torture_completed(void)
-{
- return 0;
-}
-
static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
{
call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
@@ -583,7 +617,7 @@ static struct rcu_torture_ops sched_ops = {
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sched_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = rcu_barrier_sched,
@@ -592,13 +626,13 @@ static struct rcu_torture_ops sched_ops = {
.name = "sched"
};
-static struct rcu_torture_ops sched_ops_sync = {
+static struct rcu_torture_ops sched_sync_ops = {
.init = rcu_sync_torture_init,
.cleanup = NULL,
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = NULL,
@@ -606,15 +640,13 @@ static struct rcu_torture_ops sched_ops_sync = {
.name = "sched_sync"
};
-extern int rcu_expedited_torture_stats(char *page);
-
static struct rcu_torture_ops sched_expedited_ops = {
.init = rcu_sync_torture_init,
.cleanup = NULL,
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_sched_expedited,
.cb_barrier = NULL,
@@ -650,7 +682,7 @@ rcu_torture_writer(void *arg)
old_rp = rcu_torture_current;
rp->rtort_mbtest = 1;
rcu_assign_pointer(rcu_torture_current, rp);
- smp_wmb();
+ smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
if (old_rp) {
i = old_rp->rtort_pipe_count;
if (i > RCU_TORTURE_PIPE_LEN)
@@ -731,13 +763,13 @@ static void rcu_torture_timer(unsigned long unused)
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_count)[pipe_count];
+ __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
completed = cur_ops->completed() - completed;
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_batch)[completed];
+ __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
preempt_enable();
cur_ops->readunlock(idx);
}
@@ -786,13 +818,13 @@ rcu_torture_reader(void *arg)
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_count)[pipe_count];
+ __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
completed = cur_ops->completed() - completed;
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_batch)[completed];
+ __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
preempt_enable();
cur_ops->readunlock(idx);
schedule();
@@ -1099,9 +1131,10 @@ rcu_torture_init(void)
int cpu;
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] =
- { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
- &sched_expedited_ops,
- &srcu_ops, &sched_ops, &sched_ops_sync, };
+ { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
+ &rcu_bh_ops, &rcu_bh_sync_ops,
+ &srcu_ops, &srcu_expedited_ops,
+ &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
mutex_lock(&fullstop_mutex);
@@ -1112,8 +1145,12 @@ rcu_torture_init(void)
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
- printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
+ printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
torture_type);
+ printk(KERN_ALERT "rcu-torture types:");
+ for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+ printk(KERN_ALERT " %s", torture_ops[i]->name);
+ printk(KERN_ALERT "\n");
mutex_unlock(&fullstop_mutex);
return -EINVAL;
}
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 52b06f6e158..53ae9598f79 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,30 +46,30 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
+#include <linux/kernel_stat.h>
#include "rcutree.h"
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
-EXPORT_SYMBOL_GPL(rcu_lock_map);
-#endif
-
/* Data structures. */
+static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
+
#define RCU_STATE_INITIALIZER(name) { \
.level = { &name.node[0] }, \
.levelcnt = { \
NUM_RCU_LVL_0, /* root of hierarchy. */ \
NUM_RCU_LVL_1, \
NUM_RCU_LVL_2, \
- NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
+ NUM_RCU_LVL_3, \
+ NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \
}, \
- .signaled = RCU_SIGNAL_INIT, \
+ .signaled = RCU_GP_IDLE, \
.gpnum = -300, \
.completed = -300, \
.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
+ .orphan_cbs_list = NULL, \
+ .orphan_cbs_tail = &name.orphan_cbs_list, \
+ .orphan_qlen = 0, \
.fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
@@ -81,24 +81,18 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
-extern long rcu_batches_completed_sched(void);
-static struct rcu_node *rcu_get_root(struct rcu_state *rsp);
-static void cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp,
- struct rcu_node *rnp, unsigned long flags);
-static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags);
-#ifdef CONFIG_HOTPLUG_CPU
-static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static void __rcu_process_callbacks(struct rcu_state *rsp,
- struct rcu_data *rdp);
-static void __call_rcu(struct rcu_head *head,
- void (*func)(struct rcu_head *rcu),
- struct rcu_state *rsp);
-static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp);
-static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp,
- int preemptable);
+static int rcu_scheduler_active __read_mostly;
-#include "rcutree_plugin.h"
+
+/*
+ * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s
+ * permit this function to be invoked without holding the root rcu_node
+ * structure's ->lock, but of course results can be subject to change.
+ */
+static int rcu_gp_in_progress(struct rcu_state *rsp)
+{
+ return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+}
/*
* Note a quiescent state. Because we do not need to know
@@ -110,7 +104,7 @@ void rcu_sched_qs(int cpu)
struct rcu_data *rdp;
rdp = &per_cpu(rcu_sched_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
rcu_preempt_note_context_switch(cpu);
@@ -121,7 +115,7 @@ void rcu_bh_qs(int cpu)
struct rcu_data *rdp;
rdp = &per_cpu(rcu_bh_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
@@ -137,6 +131,10 @@ static int blimit = 10; /* Maximum callbacks per softirq. */
static int qhimark = 10000; /* If this many pending, ignore blimit. */
static int qlowmark = 100; /* Once only this many pending, use blimit. */
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
+
static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
static int rcu_pending(int cpu);
@@ -173,9 +171,7 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- /* ACCESS_ONCE() because we are accessing outside of lock. */
- return *rdp->nxttail[RCU_DONE_TAIL] &&
- ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum);
+ return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp);
}
/*
@@ -345,31 +341,12 @@ void rcu_irq_exit(void)
set_need_resched();
}
-/*
- * Record the specified "completed" value, which is later used to validate
- * dynticks counter manipulations. Specify "rsp->completed - 1" to
- * unconditionally invalidate any future dynticks manipulations (which is
- * useful at the beginning of a grace period).
- */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
- rsp->dynticks_completed = comp;
-}
-
#ifdef CONFIG_SMP
/*
- * Recall the previously recorded value of the completion for dynticks.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
- return rsp->dynticks_completed;
-}
-
-/*
* Snapshot the specified CPU's dynticks counter so that we can later
* credit them with an implicit quiescent state. Return 1 if this CPU
- * is already in a quiescent state courtesy of dynticks idle mode.
+ * is in dynticks idle mode, which is an extended quiescent state.
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
@@ -429,24 +406,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
#else /* #ifdef CONFIG_NO_HZ */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-}
-
#ifdef CONFIG_SMP
-/*
- * If there are no dynticks, then the only way that a CPU can passively
- * be in a quiescent state is to be offline. Unlike dynticks idle, which
- * is a point in time during the prior (already finished) grace period,
- * an offline CPU is always in a quiescent state, and thus can be
- * unconditionally applied. So just return the current value of completed.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
- return rsp->completed;
-}
-
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
return 0;
@@ -475,30 +436,34 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
long delta;
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
- struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
- struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
/* Only let one CPU complain about others per time interval. */
spin_lock_irqsave(&rnp->lock, flags);
delta = jiffies - rsp->jiffies_stall;
- if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) {
+ if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+
+ /*
+ * Now rat on any tasks that got kicked up to the root rcu_node
+ * due to CPU offlining.
+ */
+ rcu_print_task_stall(rnp);
spin_unlock_irqrestore(&rnp->lock, flags);
/* OK, time to rat on our buddy... */
printk(KERN_ERR "INFO: RCU detected CPU stalls:");
- for (; rnp_cur < rnp_end; rnp_cur++) {
+ rcu_for_each_leaf_node(rsp, rnp) {
rcu_print_task_stall(rnp);
- if (rnp_cur->qsmask == 0)
+ if (rnp->qsmask == 0)
continue;
- for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++)
- if (rnp_cur->qsmask & (1UL << cpu))
- printk(" %d", rnp_cur->grplo + cpu);
+ for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+ if (rnp->qsmask & (1UL << cpu))
+ printk(" %d", rnp->grplo + cpu);
}
printk(" (detected by %d, t=%ld jiffies)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start));
@@ -537,8 +502,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
- } else if (rsp->gpnum != rsp->completed &&
- delta >= RCU_STALL_RAT_DELAY) {
+ } else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) {
/* They had two time units to dump stack, so complain. */
print_other_cpu_stall(rsp);
@@ -560,13 +524,33 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
/*
* Update CPU-local rcu_data state to record the newly noticed grace period.
* This is used both when we started the grace period and when we notice
- * that someone else started the grace period.
+ * that someone else started the grace period. The caller must hold the
+ * ->lock of the leaf rcu_node structure corresponding to the current CPU,
+ * and must have irqs disabled.
*/
+static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ if (rdp->gpnum != rnp->gpnum) {
+ rdp->qs_pending = 1;
+ rdp->passed_quiesc = 0;
+ rdp->gpnum = rnp->gpnum;
+ }
+}
+
static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
{
- rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
- rdp->gpnum = rsp->gpnum;
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ local_irq_save(flags);
+ rnp = rdp->mynode;
+ if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
+ !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+ local_irq_restore(flags);
+ return;
+ }
+ __note_new_gpnum(rsp, rnp, rdp);
+ spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
@@ -590,6 +574,79 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
}
/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended. This may be called only from the CPU to whom the rdp
+ * belongs. In addition, the corresponding leaf rcu_node structure's
+ * ->lock must be held by the caller, with irqs disabled.
+ */
+static void
+__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ /* Did another grace period end? */
+ if (rdp->completed != rnp->completed) {
+
+ /* Advance callbacks. No harm if list empty. */
+ rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+ rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+ /* Remember that we saw this grace-period completion. */
+ rdp->completed = rnp->completed;
+ }
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended. This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+ unsigned long flags;
+ struct rcu_node *rnp;
+
+ local_irq_save(flags);
+ rnp = rdp->mynode;
+ if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+ !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+ local_irq_restore(flags);
+ return;
+ }
+ __rcu_process_gp_end(rsp, rnp, rdp);
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Do per-CPU grace-period initialization for running CPU. The caller
+ * must hold the lock of the leaf rcu_node structure corresponding to
+ * this CPU.
+ */
+static void
+rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+ /* Prior grace period ended, so advance callbacks for current CPU. */
+ __rcu_process_gp_end(rsp, rnp, rdp);
+
+ /*
+ * Because this CPU just now started the new grace period, we know
+ * that all of its callbacks will be covered by this upcoming grace
+ * period, even the ones that were registered arbitrarily recently.
+ * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
+ *
+ * Other CPUs cannot be sure exactly when the grace period started.
+ * Therefore, their recently registered callbacks must pass through
+ * an additional RCU_NEXT_READY stage, so that they will be handled
+ * by the next RCU grace period.
+ */
+ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+ /* Set state so that this CPU will detect the next quiescent state. */
+ __note_new_gpnum(rsp, rnp, rdp);
+}
+
+/*
* Start a new RCU grace period if warranted, re-initializing the hierarchy
* in preparation for detecting the next grace period. The caller must hold
* the root node's ->lock, which is released before return. Hard irqs must
@@ -603,7 +660,23 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
struct rcu_node *rnp = rcu_get_root(rsp);
if (!cpu_needs_another_gp(rsp, rdp)) {
- spin_unlock_irqrestore(&rnp->lock, flags);
+ if (rnp->completed == rsp->completed) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ return;
+ }
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+
+ /*
+ * Propagate new ->completed value to rcu_node structures
+ * so that other CPUs don't have to wait until the start
+ * of the next grace period to process their callbacks.
+ */
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->completed = rsp->completed;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+ local_irq_restore(flags);
return;
}
@@ -613,23 +686,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
record_gp_stall_check_time(rsp);
- dyntick_record_completed(rsp, rsp->completed - 1);
- note_new_gpnum(rsp, rdp);
-
- /*
- * Because we are first, we know that all our callbacks will
- * be covered by this upcoming grace period, even the ones
- * that were registered arbitrarily recently.
- */
- rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
- rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
/* Special-case the common single-level case. */
if (NUM_RCU_NODES == 1) {
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
+ rnp->completed = rsp->completed;
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+ rcu_start_gp_per_cpu(rsp, rnp, rdp);
spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
@@ -657,70 +722,51 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
* one corresponding to this CPU, due to the fact that we have
* irqs disabled.
*/
- for (rnp = &rsp->node[0]; rnp < &rsp->node[NUM_RCU_NODES]; rnp++) {
- spin_lock(&rnp->lock); /* irqs already disabled. */
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ spin_lock(&rnp->lock); /* irqs already disabled. */
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
rnp->gpnum = rsp->gpnum;
- spin_unlock(&rnp->lock); /* irqs already disabled. */
+ rnp->completed = rsp->completed;
+ if (rnp == rdp->mynode)
+ rcu_start_gp_per_cpu(rsp, rnp, rdp);
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
+ rnp = rcu_get_root(rsp);
+ spin_lock(&rnp->lock); /* irqs already disabled. */
rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended. This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- long completed_snap;
- unsigned long flags;
-
- local_irq_save(flags);
- completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */
-
- /* Did another grace period end? */
- if (rdp->completed != completed_snap) {
-
- /* Advance callbacks. No harm if list empty. */
- rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
- rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
- rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
- /* Remember that we saw this grace-period completion. */
- rdp->completed = completed_snap;
- }
- local_irq_restore(flags);
-}
-
-/*
- * Clean up after the prior grace period and let rcu_start_gp() start up
- * the next grace period if one is needed. Note that the caller must
- * hold rnp->lock, as required by rcu_start_gp(), which will release it.
+ * Report a full set of quiescent states to the specified rcu_state
+ * data structure. This involves cleaning up after the prior grace
+ * period and letting rcu_start_gp() start up the next grace period
+ * if one is needed. Note that the caller must hold rnp->lock, as
+ * required by rcu_start_gp(), which will release it.
*/
-static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
- __releases(rnp->lock)
+static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
+ __releases(rcu_get_root(rsp)->lock)
{
- WARN_ON_ONCE(rsp->completed == rsp->gpnum);
+ WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
rsp->completed = rsp->gpnum;
- rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
+ rsp->signaled = RCU_GP_IDLE;
rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */
}
/*
- * Similar to cpu_quiet(), for which it is a helper function. Allows
- * a group of CPUs to be quieted at one go, though all the CPUs in the
- * group must be represented by the same leaf rcu_node structure.
- * That structure's lock must be held upon entry, and it is released
- * before return.
+ * Similar to rcu_report_qs_rdp(), for which it is a helper function.
+ * Allows quiescent states for a group of CPUs to be reported at one go
+ * to the specified rcu_node structure, though all the CPUs in the group
+ * must be represented by the same rcu_node structure (which need not be
+ * a leaf rcu_node structure, though it often will be). That structure's
+ * lock must be held upon entry, and it is released before return.
*/
static void
-cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
- unsigned long flags)
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+ struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
struct rcu_node *rnp_c;
@@ -756,21 +802,23 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
/*
* Get here if we are the last CPU to pass through a quiescent
- * state for this grace period. Invoke cpu_quiet_msk_finish()
+ * state for this grace period. Invoke rcu_report_qs_rsp()
* to clean up and start the next grace period if one is needed.
*/
- cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */
+ rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
}
/*
- * Record a quiescent state for the specified CPU, which must either be
- * the current CPU. The lastcomp argument is used to make sure we are
- * still in the grace period of interest. We don't want to end the current
- * grace period based on quiescent states detected in an earlier grace
- * period!
+ * Record a quiescent state for the specified CPU to that CPU's rcu_data
+ * structure. This must be either called from the specified CPU, or
+ * called when the specified CPU is known to be offline (and when it is
+ * also known that no other CPU is concurrently trying to help the offline
+ * CPU). The lastcomp argument is used to make sure we are still in the
+ * grace period of interest. We don't want to end the current grace period
+ * based on quiescent states detected in an earlier grace period!
*/
static void
-cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
+rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
{
unsigned long flags;
unsigned long mask;
@@ -778,15 +826,15 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
rnp = rdp->mynode;
spin_lock_irqsave(&rnp->lock, flags);
- if (lastcomp != ACCESS_ONCE(rsp->completed)) {
+ if (lastcomp != rnp->completed) {
/*
* Someone beat us to it for this grace period, so leave.
* The race with GP start is resolved by the fact that we
* hold the leaf rcu_node lock, so that the per-CPU bits
* cannot yet be initialized -- so we would simply find our
- * CPU's bit already cleared in cpu_quiet_msk() if this race
- * occurred.
+ * CPU's bit already cleared in rcu_report_qs_rnp() if this
+ * race occurred.
*/
rdp->passed_quiesc = 0; /* try again later! */
spin_unlock_irqrestore(&rnp->lock, flags);
@@ -804,7 +852,7 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
*/
rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
- cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */
+ rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
}
}
@@ -835,24 +883,73 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
if (!rdp->passed_quiesc)
return;
- /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */
- cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
+ /*
+ * Tell RCU we are done (but rcu_report_qs_rdp() will be the
+ * judge of that).
+ */
+ rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
}
#ifdef CONFIG_HOTPLUG_CPU
/*
+ * Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
+ * specified flavor of RCU. The callbacks will be adopted by the next
+ * _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
+ * comes first. Because this is invoked from the CPU_DYING notifier,
+ * irqs are already disabled.
+ */
+static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+{
+ int i;
+ struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+
+ if (rdp->nxtlist == NULL)
+ return; /* irqs disabled, so comparison is stable. */
+ spin_lock(&rsp->onofflock); /* irqs already disabled. */
+ *rsp->orphan_cbs_tail = rdp->nxtlist;
+ rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
+ rdp->nxtlist = NULL;
+ for (i = 0; i < RCU_NEXT_SIZE; i++)
+ rdp->nxttail[i] = &rdp->nxtlist;
+ rsp->orphan_qlen += rdp->qlen;
+ rdp->qlen = 0;
+ spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
+}
+
+/*
+ * Adopt previously orphaned RCU callbacks.
+ */
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+ unsigned long flags;
+ struct rcu_data *rdp;
+
+ spin_lock_irqsave(&rsp->onofflock, flags);
+ rdp = rsp->rda[smp_processor_id()];
+ if (rsp->orphan_cbs_list == NULL) {
+ spin_unlock_irqrestore(&rsp->onofflock, flags);
+ return;
+ }
+ *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
+ rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
+ rdp->qlen += rsp->orphan_qlen;
+ rsp->orphan_cbs_list = NULL;
+ rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
+ rsp->orphan_qlen = 0;
+ spin_unlock_irqrestore(&rsp->onofflock, flags);
+}
+
+/*
* Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
* and move all callbacks from the outgoing CPU to the current one.
*/
static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
{
- int i;
unsigned long flags;
- long lastcomp;
unsigned long mask;
+ int need_report = 0;
struct rcu_data *rdp = rsp->rda[cpu];
- struct rcu_data *rdp_me;
struct rcu_node *rnp;
/* Exclude any attempts to start a new grace period. */
@@ -865,42 +962,34 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ if (rnp != rdp->mynode)
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
break;
}
- rcu_preempt_offline_tasks(rsp, rnp, rdp);
+ if (rnp == rdp->mynode)
+ need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
+ else
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
mask = rnp->grpmask;
- spin_unlock(&rnp->lock); /* irqs remain disabled. */
rnp = rnp->parent;
} while (rnp != NULL);
- lastcomp = rsp->completed;
-
- spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
/*
- * Move callbacks from the outgoing CPU to the running CPU.
- * Note that the outgoing CPU is now quiscent, so it is now
- * (uncharacteristically) safe to access its rcu_data structure.
- * Note also that we must carefully retain the order of the
- * outgoing CPU's callbacks in order for rcu_barrier() to work
- * correctly. Finally, note that we start all the callbacks
- * afresh, even those that have passed through a grace period
- * and are therefore ready to invoke. The theory is that hotplug
- * events are rare, and that if they are frequent enough to
- * indefinitely delay callbacks, you have far worse things to
- * be worrying about.
+ * We still hold the leaf rcu_node structure lock here, and
+ * irqs are still disabled. The reason for this subterfuge is
+ * because invoking rcu_report_unblock_qs_rnp() with ->onofflock
+ * held leads to deadlock.
*/
- rdp_me = rsp->rda[smp_processor_id()];
- if (rdp->nxtlist != NULL) {
- *rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
- rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
- rdp->nxtlist = NULL;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- rdp->nxttail[i] = &rdp->nxtlist;
- rdp_me->qlen += rdp->qlen;
- rdp->qlen = 0;
- }
- local_irq_restore(flags);
+ spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
+ rnp = rdp->mynode;
+ if (need_report & RCU_OFL_TASKS_NORM_GP)
+ rcu_report_unblock_qs_rnp(rnp, flags);
+ else
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ if (need_report & RCU_OFL_TASKS_EXP_GP)
+ rcu_report_exp_rnp(rsp, rnp);
+
+ rcu_adopt_orphan_cbs(rsp);
}
/*
@@ -918,6 +1007,14 @@ static void rcu_offline_cpu(int cpu)
#else /* #ifdef CONFIG_HOTPLUG_CPU */
+static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+{
+}
+
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+}
+
static void rcu_offline_cpu(int cpu)
{
}
@@ -928,7 +1025,7 @@ static void rcu_offline_cpu(int cpu)
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
-static void rcu_do_batch(struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
@@ -981,6 +1078,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
rdp->blimit = blimit;
+ /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
+ if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
+ rdp->qlen_last_fqs_check = rdp->qlen;
+
local_irq_restore(flags);
/* Re-raise the RCU softirq if there are callbacks remaining. */
@@ -1050,33 +1154,32 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
int cpu;
unsigned long flags;
unsigned long mask;
- struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
- struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+ struct rcu_node *rnp;
- for (; rnp_cur < rnp_end; rnp_cur++) {
+ rcu_for_each_leaf_node(rsp, rnp) {
mask = 0;
- spin_lock_irqsave(&rnp_cur->lock, flags);
- if (rsp->completed != lastcomp) {
- spin_unlock_irqrestore(&rnp_cur->lock, flags);
+ spin_lock_irqsave(&rnp->lock, flags);
+ if (rnp->completed != lastcomp) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
return 1;
}
- if (rnp_cur->qsmask == 0) {
- spin_unlock_irqrestore(&rnp_cur->lock, flags);
+ if (rnp->qsmask == 0) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
continue;
}
- cpu = rnp_cur->grplo;
+ cpu = rnp->grplo;
bit = 1;
- for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) {
- if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+ for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
+ if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
mask |= bit;
}
- if (mask != 0 && rsp->completed == lastcomp) {
+ if (mask != 0 && rnp->completed == lastcomp) {
- /* cpu_quiet_msk() releases rnp_cur->lock. */
- cpu_quiet_msk(mask, rsp, rnp_cur, flags);
+ /* rcu_report_qs_rnp() releases rnp->lock. */
+ rcu_report_qs_rnp(mask, rsp, rnp, flags);
continue;
}
- spin_unlock_irqrestore(&rnp_cur->lock, flags);
+ spin_unlock_irqrestore(&rnp->lock, flags);
}
return 0;
}
@@ -1091,8 +1194,9 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
long lastcomp;
struct rcu_node *rnp = rcu_get_root(rsp);
u8 signaled;
+ u8 forcenow;
- if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum))
+ if (!rcu_gp_in_progress(rsp))
return; /* No grace period in progress, nothing to force. */
if (!spin_trylock_irqsave(&rsp->fqslock, flags)) {
rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */
@@ -1103,19 +1207,20 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
goto unlock_ret; /* no emergency and done recently. */
rsp->n_force_qs++;
spin_lock(&rnp->lock);
- lastcomp = rsp->completed;
+ lastcomp = rsp->gpnum - 1;
signaled = rsp->signaled;
rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
- if (lastcomp == rsp->gpnum) {
+ if(!rcu_gp_in_progress(rsp)) {
rsp->n_force_qs_ngp++;
spin_unlock(&rnp->lock);
goto unlock_ret; /* no GP in progress, time updated. */
}
spin_unlock(&rnp->lock);
switch (signaled) {
+ case RCU_GP_IDLE:
case RCU_GP_INIT:
- break; /* grace period still initializing, ignore. */
+ break; /* grace period idle or initializing, ignore. */
case RCU_SAVE_DYNTICK:
@@ -1126,20 +1231,29 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
if (rcu_process_dyntick(rsp, lastcomp,
dyntick_save_progress_counter))
goto unlock_ret;
+ /* fall into next case. */
+
+ case RCU_SAVE_COMPLETED:
/* Update state, record completion counter. */
+ forcenow = 0;
spin_lock(&rnp->lock);
- if (lastcomp == rsp->completed) {
+ if (lastcomp + 1 == rsp->gpnum &&
+ lastcomp == rsp->completed &&
+ rsp->signaled == signaled) {
rsp->signaled = RCU_FORCE_QS;
- dyntick_record_completed(rsp, lastcomp);
+ rsp->completed_fqs = lastcomp;
+ forcenow = signaled == RCU_SAVE_COMPLETED;
}
spin_unlock(&rnp->lock);
- break;
+ if (!forcenow)
+ break;
+ /* fall into next case. */
case RCU_FORCE_QS:
/* Check dyntick-idle state, send IPI to laggarts. */
- if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp),
+ if (rcu_process_dyntick(rsp, rsp->completed_fqs,
rcu_implicit_dynticks_qs))
goto unlock_ret;
@@ -1195,7 +1309,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
}
/* If there are callbacks ready, invoke them. */
- rcu_do_batch(rdp);
+ rcu_do_batch(rsp, rdp);
}
/*
@@ -1251,7 +1365,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
/* Start a new grace period if one not already started. */
- if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) {
+ if (!rcu_gp_in_progress(rsp)) {
unsigned long nestflag;
struct rcu_node *rnp_root = rcu_get_root(rsp);
@@ -1259,10 +1373,20 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
}
- /* Force the grace period if too many callbacks or too long waiting. */
- if (unlikely(++rdp->qlen > qhimark)) {
+ /*
+ * Force the grace period if too many callbacks or too long waiting.
+ * Enforce hysteresis, and don't invoke force_quiescent_state()
+ * if some other CPU has recently done so. Also, don't bother
+ * invoking force_quiescent_state() if the newly enqueued callback
+ * is the only one waiting for a grace period to complete.
+ */
+ if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
rdp->blimit = LONG_MAX;
- force_quiescent_state(rsp, 0);
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1286,6 +1410,68 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
+/**
+ * synchronize_sched - wait until an rcu-sched grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-sched
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-sched read-side critical sections have completed. These read-side
+ * critical sections are delimited by rcu_read_lock_sched() and
+ * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(),
+ * local_irq_disable(), and so on may be used in place of
+ * rcu_read_lock_sched().
+ *
+ * This means that all preempt_disable code sequences, including NMI and
+ * hardware-interrupt handlers, in progress on entry will have completed
+ * before this primitive returns. However, this does not guarantee that
+ * softirq handlers will have completed, since in some kernels, these
+ * handlers can run in process context, and can block.
+ *
+ * This primitive provides the guarantees made by the (now removed)
+ * synchronize_kernel() API. In contrast, synchronize_rcu() only
+ * guarantees that rcu_read_lock() sections will have completed.
+ * In "classic RCU", these two guarantees happen to be one and
+ * the same, but can differ in realtime RCU implementations.
+ */
+void synchronize_sched(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (rcu_blocking_is_gp())
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_sched(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_sched);
+
+/**
+ * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu_bh grace
+ * period has elapsed, in other words after all currently executing rcu_bh
+ * read-side critical sections have completed. RCU read-side critical
+ * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
+ * and may be nested.
+ */
+void synchronize_rcu_bh(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (rcu_blocking_is_gp())
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu_bh(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, for the specified type of RCU, returning 1 if so.
@@ -1295,6 +1481,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
*/
static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
{
+ struct rcu_node *rnp = rdp->mynode;
+
rdp->n_rcu_pending++;
/* Check for CPU stalls, if enabled. */
@@ -1319,19 +1507,19 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
}
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+ if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
rdp->n_rp_gp_completed++;
return 1;
}
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+ if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */
rdp->n_rp_gp_started++;
return 1;
}
/* Has an RCU GP gone long enough to send resched IPIs &c? */
- if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
+ if (rcu_gp_in_progress(rsp) &&
((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
rdp->n_rp_need_fqs++;
return 1;
@@ -1369,6 +1557,97 @@ int rcu_needs_cpu(int cpu)
}
/*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process. Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system). After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.
+ */
+void rcu_scheduler_starting(void)
+{
+ WARN_ON(num_online_cpus() != 1);
+ WARN_ON(nr_context_switches() > 0);
+ rcu_scheduler_active = 1;
+}
+
+static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
+static atomic_t rcu_barrier_cpu_count;
+static DEFINE_MUTEX(rcu_barrier_mutex);
+static struct completion rcu_barrier_completion;
+
+static void rcu_barrier_callback(struct rcu_head *notused)
+{
+ if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+ complete(&rcu_barrier_completion);
+}
+
+/*
+ * Called with preemption disabled, and from cross-cpu IRQ context.
+ */
+static void rcu_barrier_func(void *type)
+{
+ int cpu = smp_processor_id();
+ struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
+ void (*call_rcu_func)(struct rcu_head *head,
+ void (*func)(struct rcu_head *head));
+
+ atomic_inc(&rcu_barrier_cpu_count);
+ call_rcu_func = type;
+ call_rcu_func(head, rcu_barrier_callback);
+}
+
+/*
+ * Orchestrate the specified type of RCU barrier, waiting for all
+ * RCU callbacks of the specified type to complete.
+ */
+static void _rcu_barrier(struct rcu_state *rsp,
+ void (*call_rcu_func)(struct rcu_head *head,
+ void (*func)(struct rcu_head *head)))
+{
+ BUG_ON(in_interrupt());
+ /* Take mutex to serialize concurrent rcu_barrier() requests. */
+ mutex_lock(&rcu_barrier_mutex);
+ init_completion(&rcu_barrier_completion);
+ /*
+ * Initialize rcu_barrier_cpu_count to 1, then invoke
+ * rcu_barrier_func() on each CPU, so that each CPU also has
+ * incremented rcu_barrier_cpu_count. Only then is it safe to
+ * decrement rcu_barrier_cpu_count -- otherwise the first CPU
+ * might complete its grace period before all of the other CPUs
+ * did their increment, causing this function to return too
+ * early.
+ */
+ atomic_set(&rcu_barrier_cpu_count, 1);
+ preempt_disable(); /* stop CPU_DYING from filling orphan_cbs_list */
+ rcu_adopt_orphan_cbs(rsp);
+ on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
+ preempt_enable(); /* CPU_DYING can again fill orphan_cbs_list */
+ if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+ complete(&rcu_barrier_completion);
+ wait_for_completion(&rcu_barrier_completion);
+ mutex_unlock(&rcu_barrier_mutex);
+}
+
+/**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+void rcu_barrier_bh(void)
+{
+ _rcu_barrier(&rcu_bh_state, call_rcu_bh);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+/**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+ */
+void rcu_barrier_sched(void)
+{
+ _rcu_barrier(&rcu_sched_state, call_rcu_sched);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
+/*
* Do boot-time initialization of a CPU's per-CPU RCU data.
*/
static void __init
@@ -1403,21 +1682,18 @@ static void __cpuinit
rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
{
unsigned long flags;
- long lastcomp;
unsigned long mask;
struct rcu_data *rdp = rsp->rda[cpu];
struct rcu_node *rnp = rcu_get_root(rsp);
/* Set up local state, ensuring consistent view of global state. */
spin_lock_irqsave(&rnp->lock, flags);
- lastcomp = rsp->completed;
- rdp->completed = lastcomp;
- rdp->gpnum = lastcomp;
rdp->passed_quiesc = 0; /* We could be racing with new GP, */
rdp->qs_pending = 1; /* so set up to respond to current GP. */
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptable = preemptable;
- rdp->passed_quiesc_completed = lastcomp - 1;
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -1437,6 +1713,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
spin_lock(&rnp->lock); /* irqs already disabled. */
rnp->qsmaskinit |= mask;
mask = rnp->grpmask;
+ if (rnp == rdp->mynode) {
+ rdp->gpnum = rnp->completed; /* if GP in progress... */
+ rdp->completed = rnp->completed;
+ rdp->passed_quiesc_completed = rnp->completed - 1;
+ }
spin_unlock(&rnp->lock); /* irqs already disabled. */
rnp = rnp->parent;
} while (rnp != NULL && !(rnp->qsmaskinit & mask));
@@ -1454,8 +1735,8 @@ static void __cpuinit rcu_online_cpu(int cpu)
/*
* Handle CPU online/offline notification events.
*/
-int __cpuinit rcu_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
@@ -1464,6 +1745,22 @@ int __cpuinit rcu_cpu_notify(struct notifier_block *self,
case CPU_UP_PREPARE_FROZEN:
rcu_online_cpu(cpu);
break;
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ /*
+ * preempt_disable() in _rcu_barrier() prevents stop_machine(),
+ * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
+ * returns, all online cpus have queued rcu_barrier_func().
+ * The dying CPU clears its cpu_online_mask bit and
+ * moves all of its RCU callbacks to ->orphan_cbs_list
+ * in the context of stop_machine(), so subsequent calls
+ * to _rcu_barrier() will adopt these callbacks and only
+ * then queue rcu_barrier_func() on all remaining CPUs.
+ */
+ rcu_send_cbs_to_orphanage(&rcu_bh_state);
+ rcu_send_cbs_to_orphanage(&rcu_sched_state);
+ rcu_preempt_send_cbs_to_orphanage();
+ break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
case CPU_UP_CANCELED:
@@ -1527,6 +1824,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
rnp = rsp->level[i];
for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
spin_lock_init(&rnp->lock);
+ lockdep_set_class(&rnp->lock, &rcu_node_class[i]);
rnp->gpnum = 0;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
@@ -1547,6 +1845,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
rnp->level = i;
INIT_LIST_HEAD(&rnp->blocked_tasks[0]);
INIT_LIST_HEAD(&rnp->blocked_tasks[1]);
+ INIT_LIST_HEAD(&rnp->blocked_tasks[2]);
+ INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
}
}
}
@@ -1558,6 +1858,10 @@ static void __init rcu_init_one(struct rcu_state *rsp)
*/
#define RCU_INIT_FLAVOR(rsp, rcu_data) \
do { \
+ int i; \
+ int j; \
+ struct rcu_node *rnp; \
+ \
rcu_init_one(rsp); \
rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
j = 0; \
@@ -1570,41 +1874,30 @@ do { \
} \
} while (0)
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-void __init __rcu_init_preempt(void)
-{
- int i; /* All used by RCU_INIT_FLAVOR(). */
- int j;
- struct rcu_node *rnp;
-
- RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
-}
-
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-void __init __rcu_init_preempt(void)
+void __init rcu_init(void)
{
-}
-
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-void __init __rcu_init(void)
-{
- int i; /* All used by RCU_INIT_FLAVOR(). */
- int j;
- struct rcu_node *rnp;
+ int i;
rcu_bootup_announce();
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#if NUM_RCU_LVL_4 != 0
+ printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
+#endif /* #if NUM_RCU_LVL_4 != 0 */
RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
__rcu_init_preempt();
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+
+ /*
+ * We don't need protection against CPU-hotplug here because
+ * this is called early in boot, before either interrupts
+ * or the scheduler are operational.
+ */
+ cpu_notifier(rcu_cpu_notify, 0);
+ for_each_online_cpu(i)
+ rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)i);
}
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
+#include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 8e8287a983c..d2a0046f63b 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -34,10 +34,11 @@
* In practice, this has not been tested, so there is probably some
* bug somewhere.
*/
-#define MAX_RCU_LVLS 3
+#define MAX_RCU_LVLS 4
#define RCU_FANOUT (CONFIG_RCU_FANOUT)
#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
+#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT
# define NUM_RCU_LVLS 1
@@ -45,23 +46,33 @@
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
+# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_SQ
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
+# define NUM_RCU_LVL_4 0
#elif NR_CPUS <= RCU_FANOUT_CUBE
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_2 (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
# define NUM_RCU_LVL_3 NR_CPUS
+# define NUM_RCU_LVL_4 0
+#elif NR_CPUS <= RCU_FANOUT_FOURTH
+# define NUM_RCU_LVLS 4
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+# define NUM_RCU_LVL_4 NR_CPUS
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT */
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
/*
@@ -79,24 +90,67 @@ struct rcu_dynticks {
* Definition for node within the RCU grace-period-detection hierarchy.
*/
struct rcu_node {
- spinlock_t lock;
+ spinlock_t lock; /* Root rcu_node's lock protects some */
+ /* rcu_state fields as well as following. */
long gpnum; /* Current grace period for this node. */
/* This will either be equal to or one */
/* behind the root rcu_node's gpnum. */
+ long completed; /* Last grace period completed for this node. */
+ /* This will either be equal to or one */
+ /* behind the root rcu_node's gpnum. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
+ /* In leaf rcu_node, each bit corresponds to */
+ /* an rcu_data structure, otherwise, each */
+ /* bit corresponds to a child rcu_node */
+ /* structure. */
+ unsigned long expmask; /* Groups that have ->blocked_tasks[] */
+ /* elements that need to drain to allow the */
+ /* current expedited grace period to */
+ /* complete (only for TREE_PREEMPT_RCU). */
unsigned long qsmaskinit;
- /* Per-GP initialization for qsmask. */
+ /* Per-GP initial value for qsmask & expmask. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
+ /* Only one bit will be set in this mask. */
int grplo; /* lowest-numbered CPU or group here. */
int grphi; /* highest-numbered CPU or group here. */
u8 grpnum; /* CPU/group number for next level up. */
u8 level; /* root is at level 0. */
struct rcu_node *parent;
- struct list_head blocked_tasks[2];
+ struct list_head blocked_tasks[4];
/* Tasks blocked in RCU read-side critsect. */
+ /* Grace period number (->gpnum) x blocked */
+ /* by tasks on the (x & 0x1) element of the */
+ /* blocked_tasks[] array. */
} ____cacheline_internodealigned_in_smp;
+/*
+ * Do a full breadth-first scan of the rcu_node structures for the
+ * specified rcu_state structure.
+ */
+#define rcu_for_each_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure. Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure. Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
+#define rcu_for_each_leaf_node(rsp, rnp) \
+ for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
+ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+
/* Index values for nxttail array in struct rcu_data. */
#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
@@ -126,23 +180,30 @@ struct rcu_data {
* Any of the partitions might be empty, in which case the
* pointer to that partition will be equal to the pointer for
* the following partition. When the list is empty, all of
- * the nxttail elements point to nxtlist, which is NULL.
+ * the nxttail elements point to the ->nxtlist pointer itself,
+ * which in that case is NULL.
*
- * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
- * Entries that might have arrived after current GP ended
- * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
- * Entries known to have arrived before current GP ended
- * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
- * Entries that batch # <= ->completed - 1: waiting for current GP
* [nxtlist, *nxttail[RCU_DONE_TAIL]):
* Entries that batch # <= ->completed
* The grace period for these entries has completed, and
* the other grace-period-completed entries may be moved
* here temporarily in rcu_process_callbacks().
+ * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
+ * Entries that batch # <= ->completed - 1: waiting for current GP
+ * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
+ * Entries known to have arrived before current GP ended
+ * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
+ * Entries that might have arrived after current GP ended
+ * Note that the value of *nxttail[RCU_NEXT_TAIL] will
+ * always be NULL, as this is the end of the list.
*/
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
long qlen; /* # of queued callbacks */
+ long qlen_last_fqs_check;
+ /* qlen at last check for QS forcing */
+ unsigned long n_force_qs_snap;
+ /* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
#ifdef CONFIG_NO_HZ
@@ -173,13 +234,15 @@ struct rcu_data {
};
/* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT 0 /* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */
-#define RCU_FORCE_QS 2 /* Need to force quiescent state. */
+#define RCU_GP_IDLE 0 /* No grace period in progress. */
+#define RCU_GP_INIT 1 /* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
+#define RCU_SAVE_COMPLETED 3 /* Need to save rsp->completed. */
+#define RCU_FORCE_QS 4 /* Need to force quiescent state. */
#ifdef CONFIG_NO_HZ
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT RCU_FORCE_QS
+#define RCU_SIGNAL_INIT RCU_SAVE_COMPLETED
#endif /* #else #ifdef CONFIG_NO_HZ */
#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
@@ -216,10 +279,23 @@ struct rcu_state {
/* Force QS state. */
long gpnum; /* Current gp number. */
long completed; /* # of last completed gp. */
+
+ /* End of fields guarded by root rcu_node's lock. */
+
spinlock_t onofflock; /* exclude on/offline and */
- /* starting new GP. */
+ /* starting new GP. Also */
+ /* protects the following */
+ /* orphan_cbs fields. */
+ struct rcu_head *orphan_cbs_list; /* list of rcu_head structs */
+ /* orphaned by all CPUs in */
+ /* a given leaf rcu_node */
+ /* going offline. */
+ struct rcu_head **orphan_cbs_tail; /* And tail pointer. */
+ long orphan_qlen; /* Number of orphaned cbs. */
spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
+ long completed_fqs; /* Value of completed @ snap. */
+ /* Protected by fqslock. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long n_force_qs; /* Number of calls to */
@@ -234,11 +310,15 @@ struct rcu_state {
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
- long dynticks_completed; /* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
};
+/* Return values for rcu_preempt_offline_tasks(). */
+
+#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */
+ /* GP were moved to root. */
+#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */
+ /* GP were moved to root. */
+
#ifdef RCU_TREE_NONCORE
/*
@@ -255,5 +335,37 @@ extern struct rcu_state rcu_preempt_state;
DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#endif /* #ifdef RCU_TREE_NONCORE */
+#else /* #ifdef RCU_TREE_NONCORE */
+
+/* Forward declarations for rcutree_plugin.h */
+static void rcu_bootup_announce(void);
+long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
+static int rcu_preempted_readers(struct rcu_node *rnp);
+#ifdef CONFIG_HOTPLUG_CPU
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
+ unsigned long flags);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+static void rcu_print_task_stall(struct rcu_node *rnp);
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+#ifdef CONFIG_HOTPLUG_CPU
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp);
+static void rcu_preempt_offline_cpu(int cpu);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+static void rcu_preempt_check_callbacks(int cpu);
+static void rcu_preempt_process_callbacks(void);
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+static int rcu_preempt_pending(int cpu);
+static int rcu_preempt_needs_cpu(int cpu);
+static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
+static void rcu_preempt_send_cbs_to_orphanage(void);
+static void __init __rcu_init_preempt(void);
+#endif /* #else #ifdef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 1cee04f627e..37fbccdf41d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -24,16 +24,19 @@
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/delay.h>
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+static int rcu_preempted_readers_exp(struct rcu_node *rnp);
+
/*
* Tell them what RCU they are running.
*/
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO
"Experimental preemptable hierarchical RCU implementation.\n");
@@ -67,7 +70,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
static void rcu_preempt_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
- rdp->passed_quiesc_completed = rdp->completed;
+ rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
@@ -150,11 +153,65 @@ void __rcu_read_lock(void)
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);
+/*
+ * Check for preempted RCU readers blocking the current grace period
+ * for the specified rcu_node structure. If the caller needs a reliable
+ * answer, it must hold the rcu_node's ->lock.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+ int phase = rnp->gpnum & 0x1;
+
+ return !list_empty(&rnp->blocked_tasks[phase]) ||
+ !list_empty(&rnp->blocked_tasks[phase + 2]);
+}
+
+/*
+ * Record a quiescent state for all tasks that were previously queued
+ * on the specified rcu_node structure and that were blocking the current
+ * RCU grace period. The caller must hold the specified rnp->lock with
+ * irqs disabled, and this lock is released upon return, but irqs remain
+ * disabled.
+ */
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+ __releases(rnp->lock)
+{
+ unsigned long mask;
+ struct rcu_node *rnp_p;
+
+ if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
+ spin_unlock_irqrestore(&rnp->lock, flags);
+ return; /* Still need more quiescent states! */
+ }
+
+ rnp_p = rnp->parent;
+ if (rnp_p == NULL) {
+ /*
+ * Either there is only one rcu_node in the tree,
+ * or tasks were kicked up to root rcu_node due to
+ * CPUs going offline.
+ */
+ rcu_report_qs_rsp(&rcu_preempt_state, flags);
+ return;
+ }
+
+ /* Report up the rest of the hierarchy. */
+ mask = rnp->grpmask;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
+}
+
+/*
+ * Handle special cases during rcu_read_unlock(), such as needing to
+ * notify RCU core processing or task having blocked during the RCU
+ * read-side critical section.
+ */
static void rcu_read_unlock_special(struct task_struct *t)
{
int empty;
+ int empty_exp;
unsigned long flags;
- unsigned long mask;
struct rcu_node *rnp;
int special;
@@ -196,37 +253,31 @@ static void rcu_read_unlock_special(struct task_struct *t)
break;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
- empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
+ empty = !rcu_preempted_readers(rnp);
+ empty_exp = !rcu_preempted_readers_exp(rnp);
+ smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
list_del_init(&t->rcu_node_entry);
t->rcu_blocked_node = NULL;
/*
* If this was the last task on the current list, and if
* we aren't waiting on any CPUs, report the quiescent state.
- * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk()
- * drop rnp->lock and restore irq.
+ * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
*/
- if (!empty && rnp->qsmask == 0 &&
- list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) {
- struct rcu_node *rnp_p;
-
- if (rnp->parent == NULL) {
- /* Only one rcu_node in the tree. */
- cpu_quiet_msk_finish(&rcu_preempt_state, flags);
- return;
- }
- /* Report up the rest of the hierarchy. */
- mask = rnp->grpmask;
+ if (empty)
spin_unlock_irqrestore(&rnp->lock, flags);
- rnp_p = rnp->parent;
- spin_lock_irqsave(&rnp_p->lock, flags);
- WARN_ON_ONCE(rnp->qsmask);
- cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags);
- return;
- }
- spin_unlock(&rnp->lock);
+ else
+ rcu_report_unblock_qs_rnp(rnp, flags);
+
+ /*
+ * If this was the last task on the expedited lists,
+ * then we need to report up the rcu_node hierarchy.
+ */
+ if (!empty_exp && !rcu_preempted_readers_exp(rnp))
+ rcu_report_exp_rnp(&rcu_preempt_state, rnp);
+ } else {
+ local_irq_restore(flags);
}
- local_irq_restore(flags);
}
/*
@@ -257,12 +308,12 @@ static void rcu_print_task_stall(struct rcu_node *rnp)
{
unsigned long flags;
struct list_head *lp;
- int phase = rnp->gpnum & 0x1;
+ int phase;
struct task_struct *t;
- if (!list_empty(&rnp->blocked_tasks[phase])) {
+ if (rcu_preempted_readers(rnp)) {
spin_lock_irqsave(&rnp->lock, flags);
- phase = rnp->gpnum & 0x1; /* re-read under lock. */
+ phase = rnp->gpnum & 0x1;
lp = &rnp->blocked_tasks[phase];
list_for_each_entry(t, lp, rcu_node_entry)
printk(" P%d", t->pid);
@@ -281,20 +332,10 @@ static void rcu_print_task_stall(struct rcu_node *rnp)
*/
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
{
- WARN_ON_ONCE(!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]));
+ WARN_ON_ONCE(rcu_preempted_readers(rnp));
WARN_ON_ONCE(rnp->qsmask);
}
-/*
- * Check for preempted RCU readers for the specified rcu_node structure.
- * If the caller needs a reliable answer, it must hold the rcu_node's
- * >lock.
- */
-static int rcu_preempted_readers(struct rcu_node *rnp)
-{
- return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
-}
-
#ifdef CONFIG_HOTPLUG_CPU
/*
@@ -303,26 +344,34 @@ static int rcu_preempted_readers(struct rcu_node *rnp)
* rcu_node. The reason for not just moving them to the immediate
* parent is to remove the need for rcu_read_unlock_special() to
* make more than two attempts to acquire the target rcu_node's lock.
+ * Returns true if there were tasks blocking the current RCU grace
+ * period.
+ *
+ * Returns 1 if there was previously a task blocking the current grace
+ * period on the specified rcu_node structure.
*
* The caller must hold rnp->lock with irqs disabled.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
int i;
struct list_head *lp;
struct list_head *lp_root;
+ int retval = 0;
struct rcu_node *rnp_root = rcu_get_root(rsp);
struct task_struct *tp;
if (rnp == rnp_root) {
WARN_ONCE(1, "Last CPU thought to be offlined?");
- return; /* Shouldn't happen: at least one CPU online. */
+ return 0; /* Shouldn't happen: at least one CPU online. */
}
WARN_ON_ONCE(rnp != rdp->mynode &&
(!list_empty(&rnp->blocked_tasks[0]) ||
- !list_empty(&rnp->blocked_tasks[1])));
+ !list_empty(&rnp->blocked_tasks[1]) ||
+ !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3])));
/*
* Move tasks up to root rcu_node. Rely on the fact that the
@@ -330,7 +379,11 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
* rcu_nodes in terms of gp_num value. This fact allows us to
* move the blocked_tasks[] array directly, element by element.
*/
- for (i = 0; i < 2; i++) {
+ if (rcu_preempted_readers(rnp))
+ retval |= RCU_OFL_TASKS_NORM_GP;
+ if (rcu_preempted_readers_exp(rnp))
+ retval |= RCU_OFL_TASKS_EXP_GP;
+ for (i = 0; i < 4; i++) {
lp = &rnp->blocked_tasks[i];
lp_root = &rnp_root->blocked_tasks[i];
while (!list_empty(lp)) {
@@ -342,6 +395,7 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
spin_unlock(&rnp_root->lock); /* irqs remain disabled */
}
}
+ return retval;
}
/*
@@ -392,6 +446,186 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu);
+/**
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed. RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
+ */
+void synchronize_rcu(void)
+{
+ struct rcu_synchronize rcu;
+
+ if (!rcu_scheduler_active)
+ return;
+
+ init_completion(&rcu.completion);
+ /* Will wake me after RCU finished. */
+ call_rcu(&rcu.head, wakeme_after_rcu);
+ /* Wait for it. */
+ wait_for_completion(&rcu.completion);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
+
+static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static long sync_rcu_preempt_exp_count;
+static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
+
+/*
+ * Return non-zero if there are any tasks in RCU read-side critical
+ * sections blocking the current preemptible-RCU expedited grace period.
+ * If there is no preemptible-RCU expedited grace period currently in
+ * progress, returns zero unconditionally.
+ */
+static int rcu_preempted_readers_exp(struct rcu_node *rnp)
+{
+ return !list_empty(&rnp->blocked_tasks[2]) ||
+ !list_empty(&rnp->blocked_tasks[3]);
+}
+
+/*
+ * return non-zero if there is no RCU expedited grace period in progress
+ * for the specified rcu_node structure, in other words, if all CPUs and
+ * tasks covered by the specified rcu_node structure have done their bit
+ * for the current expedited grace period. Works only for preemptible
+ * RCU -- other RCU implementation use other means.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+{
+ return !rcu_preempted_readers_exp(rnp) &&
+ ACCESS_ONCE(rnp->expmask) == 0;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period. This event is reported either to the rcu_node structure on
+ * which the task was queued or to one of that rcu_node structure's ancestors,
+ * recursively up the tree. (Calm down, calm down, we do the recursion
+ * iteratively!)
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ unsigned long flags;
+ unsigned long mask;
+
+ spin_lock_irqsave(&rnp->lock, flags);
+ for (;;) {
+ if (!sync_rcu_preempt_exp_done(rnp))
+ break;
+ if (rnp->parent == NULL) {
+ wake_up(&sync_rcu_preempt_exp_wq);
+ break;
+ }
+ mask = rnp->grpmask;
+ spin_unlock(&rnp->lock); /* irqs remain disabled */
+ rnp = rnp->parent;
+ spin_lock(&rnp->lock); /* irqs already disabled */
+ rnp->expmask &= ~mask;
+ }
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Snapshot the tasks blocking the newly started preemptible-RCU expedited
+ * grace period for the specified rcu_node structure. If there are no such
+ * tasks, report it up the rcu_node hierarchy.
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock.
+ */
+static void
+sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ int must_wait;
+
+ spin_lock(&rnp->lock); /* irqs already disabled */
+ list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
+ list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
+ must_wait = rcu_preempted_readers_exp(rnp);
+ spin_unlock(&rnp->lock); /* irqs remain disabled */
+ if (!must_wait)
+ rcu_report_exp_rnp(rsp, rnp);
+}
+
+/*
+ * Wait for an rcu-preempt grace period, but expedite it. The basic idea
+ * is to invoke synchronize_sched_expedited() to push all the tasks to
+ * the ->blocked_tasks[] lists, move all entries from the first set of
+ * ->blocked_tasks[] lists to the second set, and finally wait for this
+ * second set to drain.
+ */
+void synchronize_rcu_expedited(void)
+{
+ unsigned long flags;
+ struct rcu_node *rnp;
+ struct rcu_state *rsp = &rcu_preempt_state;
+ long snap;
+ int trycount = 0;
+
+ smp_mb(); /* Caller's modifications seen first by other CPUs. */
+ snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+ smp_mb(); /* Above access cannot bleed into critical section. */
+
+ /*
+ * Acquire lock, falling back to synchronize_rcu() if too many
+ * lock-acquisition failures. Of course, if someone does the
+ * expedited grace period for us, just leave.
+ */
+ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_rcu();
+ return;
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto mb_ret; /* Others did our work for us. */
+ }
+ if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
+ goto unlock_mb_ret; /* Others did our work for us. */
+
+ /* force all RCU readers onto blocked_tasks[]. */
+ synchronize_sched_expedited();
+
+ spin_lock_irqsave(&rsp->onofflock, flags);
+
+ /* Initialize ->expmask for all non-leaf rcu_node structures. */
+ rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
+ spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->expmask = rnp->qsmaskinit;
+ spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+
+ /* Snapshot current state of ->blocked_tasks[] lists. */
+ rcu_for_each_leaf_node(rsp, rnp)
+ sync_rcu_preempt_exp_init(rsp, rnp);
+ if (NUM_RCU_NODES > 1)
+ sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
+
+ spin_unlock_irqrestore(&rsp->onofflock, flags);
+
+ /* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+ rnp = rcu_get_root(rsp);
+ wait_event(sync_rcu_preempt_exp_wq,
+ sync_rcu_preempt_exp_done(rnp));
+
+ /* Clean up and exit. */
+ smp_mb(); /* ensure expedited GP seen before counter increment. */
+ ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
+unlock_mb_ret:
+ mutex_unlock(&sync_rcu_preempt_exp_mutex);
+mb_ret:
+ smp_mb(); /* ensure subsequent action seen after grace period. */
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
/*
* Check to see if there is any immediate preemptable-RCU-related work
* to be done.
@@ -410,6 +644,15 @@ static int rcu_preempt_needs_cpu(int cpu)
return !!per_cpu(rcu_preempt_data, cpu).nxtlist;
}
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+ _rcu_barrier(&rcu_preempt_state, call_rcu);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
/*
* Initialize preemptable RCU's per-CPU data.
*/
@@ -419,6 +662,22 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
}
/*
+ * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+ rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+}
+
+/*
+ * Initialize preemptable RCU's state structures.
+ */
+static void __init __rcu_init_preempt(void)
+{
+ RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+}
+
+/*
* Check for a task exiting while in a preemptable-RCU read-side
* critical section, clean up if so. No need to issue warnings,
* as debug_check_no_locks_held() already does this if lockdep
@@ -439,7 +698,7 @@ void exit_rcu(void)
/*
* Tell them what RCU they are running.
*/
-static inline void rcu_bootup_announce(void)
+static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO "Hierarchical RCU implementation.\n");
}
@@ -461,6 +720,25 @@ static void rcu_preempt_note_context_switch(int cpu)
{
}
+/*
+ * Because preemptable RCU does not exist, there are never any preempted
+ * RCU readers.
+ */
+static int rcu_preempted_readers(struct rcu_node *rnp)
+{
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/* Because preemptible RCU does not exist, no quieting of tasks. */
+static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+{
+ spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
/*
@@ -483,25 +761,19 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
WARN_ON_ONCE(rnp->qsmask);
}
-/*
- * Because preemptable RCU does not exist, there are never any preempted
- * RCU readers.
- */
-static int rcu_preempted_readers(struct rcu_node *rnp)
-{
- return 0;
-}
-
#ifdef CONFIG_HOTPLUG_CPU
/*
* Because preemptable RCU does not exist, it never needs to migrate
- * tasks that were blocked within RCU read-side critical sections.
+ * tasks that were blocked within RCU read-side critical sections, and
+ * such non-existent tasks cannot possibly have been blocking the current
+ * grace period.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
+ return 0;
}
/*
@@ -518,7 +790,7 @@ static void rcu_preempt_offline_cpu(int cpu)
* Because preemptable RCU does not exist, it never has any callbacks
* to check.
*/
-void rcu_preempt_check_callbacks(int cpu)
+static void rcu_preempt_check_callbacks(int cpu)
{
}
@@ -526,7 +798,7 @@ void rcu_preempt_check_callbacks(int cpu)
* Because preemptable RCU does not exist, it never has any callbacks
* to process.
*/
-void rcu_preempt_process_callbacks(void)
+static void rcu_preempt_process_callbacks(void)
{
}
@@ -540,6 +812,30 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
EXPORT_SYMBOL_GPL(call_rcu);
/*
+ * Wait for an rcu-preempt grace period, but make it happen quickly.
+ * But because preemptable RCU does not exist, map to rcu-sched.
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_sched_expedited();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Because preemptable RCU does not exist, there is never any need to
+ * report on tasks preempted in RCU read-side critical sections during
+ * expedited RCU grace periods.
+ */
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+{
+ return;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
static int rcu_preempt_pending(int cpu)
@@ -556,6 +852,16 @@ static int rcu_preempt_needs_cpu(int cpu)
}
/*
+ * Because preemptable RCU does not exist, rcu_barrier() is just
+ * another name for rcu_barrier_sched().
+ */
+void rcu_barrier(void)
+{
+ rcu_barrier_sched();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
* Because preemptable RCU does not exist, there is no per-CPU
* data to initialize.
*/
@@ -563,4 +869,18 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
{
}
+/*
+ * Because there is no preemptable RCU, there are no callbacks to move.
+ */
+static void rcu_preempt_send_cbs_to_orphanage(void)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, it need not be initialized.
+ */
+static void __init __rcu_init_preempt(void)
+{
+}
+
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index c89f5e9fd17..9d2c88423b3 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -93,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file)
return single_open(file, show_rcudata, NULL);
}
-static struct file_operations rcudata_fops = {
+static const struct file_operations rcudata_fops = {
.owner = THIS_MODULE,
.open = rcudata_open,
.read = seq_read,
@@ -145,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file)
return single_open(file, show_rcudata_csv, NULL);
}
-static struct file_operations rcudata_csv_fops = {
+static const struct file_operations rcudata_csv_fops = {
.owner = THIS_MODULE,
.open = rcudata_csv_open,
.read = seq_read,
@@ -155,24 +155,32 @@ static struct file_operations rcudata_csv_fops = {
static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
{
+ long gpnum;
int level = 0;
+ int phase;
struct rcu_node *rnp;
+ gpnum = rsp->gpnum;
seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
- "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
- rsp->completed, rsp->gpnum, rsp->signaled,
+ "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
+ rsp->completed, gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- rsp->n_force_qs_lh);
+ rsp->n_force_qs_lh, rsp->orphan_qlen);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
level = rnp->level;
}
- seq_printf(m, "%lx/%lx %d:%d ^%d ",
+ phase = gpnum & 0x1;
+ seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d ",
rnp->qsmask, rnp->qsmaskinit,
+ "T."[list_empty(&rnp->blocked_tasks[phase])],
+ "E."[list_empty(&rnp->blocked_tasks[phase + 2])],
+ "T."[list_empty(&rnp->blocked_tasks[!phase])],
+ "E."[list_empty(&rnp->blocked_tasks[!phase + 2])],
rnp->grplo, rnp->grphi, rnp->grpnum);
}
seq_puts(m, "\n");
@@ -196,7 +204,7 @@ static int rcuhier_open(struct inode *inode, struct file *file)
return single_open(file, show_rcuhier, NULL);
}
-static struct file_operations rcuhier_fops = {
+static const struct file_operations rcuhier_fops = {
.owner = THIS_MODULE,
.open = rcuhier_open,
.read = seq_read,
@@ -222,7 +230,7 @@ static int rcugp_open(struct inode *inode, struct file *file)
return single_open(file, show_rcugp, NULL);
}
-static struct file_operations rcugp_fops = {
+static const struct file_operations rcugp_fops = {
.owner = THIS_MODULE,
.open = rcugp_open,
.read = seq_read,
@@ -276,7 +284,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file)
return single_open(file, show_rcu_pending, NULL);
}
-static struct file_operations rcu_pending_fops = {
+static const struct file_operations rcu_pending_fops = {
.owner = THIS_MODULE,
.open = rcu_pending_open,
.read = seq_read,
diff --git a/kernel/relay.c b/kernel/relay.c
index bc188549788..c705a41b4ba 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -60,7 +60,7 @@ static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
/*
* vm_ops for relay file mappings.
*/
-static struct vm_operations_struct relay_file_mmap_ops = {
+static const struct vm_operations_struct relay_file_mmap_ops = {
.fault = relay_buf_fault,
.close = relay_file_mmap_close,
};
@@ -1198,7 +1198,7 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
relay_consume_bytes(rbuf, buf->private);
}
-static struct pipe_buf_operations relay_pipe_buf_ops = {
+static const struct pipe_buf_operations relay_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index e1338f07431..bcdabf37c40 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
counter->limit = RESOURCE_MAX;
+ counter->soft_limit = RESOURCE_MAX;
counter->parent = parent;
}
@@ -101,6 +102,8 @@ res_counter_member(struct res_counter *counter, int member)
return &counter->limit;
case RES_FAILCNT:
return &counter->failcnt;
+ case RES_SOFT_LIMIT:
+ return &counter->soft_limit;
};
BUG();
diff --git a/kernel/resource.c b/kernel/resource.c
index fb11a58b959..dc15686b7a7 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -308,35 +308,37 @@ static int find_resource(struct resource *root, struct resource *new,
void *alignf_data)
{
struct resource *this = root->child;
+ resource_size_t start, end;
- new->start = root->start;
+ start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
* of this->start - 1 to new->end below would cause an underflow.
*/
if (this && this->start == 0) {
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
- new->end = this->start - 1;
+ end = this->start - 1;
else
- new->end = root->end;
- if (new->start < min)
- new->start = min;
- if (new->end > max)
- new->end = max;
- new->start = ALIGN(new->start, align);
+ end = root->end;
+ if (start < min)
+ start = min;
+ if (end > max)
+ end = max;
+ start = ALIGN(start, align);
if (alignf)
alignf(alignf_data, new, size, align);
- if (new->start < new->end && new->end - new->start >= size - 1) {
- new->end = new->start + size - 1;
+ if (start < end && end - start >= size - 1) {
+ new->start = start;
+ new->end = start + size - 1;
return 0;
}
if (!this)
break;
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
return -EBUSY;
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index 5fcb4fe645e..ddabb54bb5c 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -37,8 +37,8 @@ do { \
if (rt_trace_on) { \
rt_trace_on = 0; \
console_verbose(); \
- if (spin_is_locked(&current->pi_lock)) \
- spin_unlock(&current->pi_lock); \
+ if (raw_spin_is_locked(&current->pi_lock)) \
+ raw_spin_unlock(&current->pi_lock); \
} \
} while (0)
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 29bd4baf9e7..a9604815786 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -138,9 +138,9 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
{
unsigned long flags;
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
/*
@@ -195,7 +195,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
/*
* Task can not go away as we did a get_task() before !
*/
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
/*
@@ -231,8 +231,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
goto out_unlock_pi;
lock = waiter->lock;
- if (!spin_trylock(&lock->wait_lock)) {
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ if (!raw_spin_trylock(&lock->wait_lock)) {
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
cpu_relax();
goto retry;
}
@@ -240,7 +240,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
/* Deadlock detection */
if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
ret = deadlock_detect ? -EDEADLK : 0;
goto out_unlock_pi;
}
@@ -253,13 +253,13 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
plist_add(&waiter->list_entry, &lock->wait_list);
/* Release the task */
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
put_task_struct(task);
/* Grab the next task */
task = rt_mutex_owner(lock);
get_task_struct(task);
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
@@ -277,10 +277,10 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
__rt_mutex_adjust_prio(task);
}
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
top_waiter = rt_mutex_top_waiter(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
@@ -288,7 +288,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
goto again;
out_unlock_pi:
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
out_put_task:
put_task_struct(task);
@@ -313,9 +313,9 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
if (pendowner == task)
return 1;
- spin_lock_irqsave(&pendowner->pi_lock, flags);
+ raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
if (task->prio >= pendowner->prio) {
- spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
return 0;
}
@@ -325,7 +325,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
* priority.
*/
if (likely(!rt_mutex_has_waiters(lock))) {
- spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
return 1;
}
@@ -333,7 +333,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
next = rt_mutex_top_waiter(lock);
plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
__rt_mutex_adjust_prio(pendowner);
- spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
/*
* We are going to steal the lock and a waiter was
@@ -350,10 +350,10 @@ static inline int try_to_steal_lock(struct rt_mutex *lock,
* might be task:
*/
if (likely(next->task != task)) {
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
plist_add(&next->pi_list_entry, &task->pi_waiters);
__rt_mutex_adjust_prio(task);
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
return 1;
}
@@ -420,7 +420,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
unsigned long flags;
int chain_walk = 0, res;
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
@@ -434,17 +434,17 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
task->pi_blocked_on = waiter;
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
- spin_lock_irqsave(&owner->pi_lock, flags);
+ 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_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
- spin_unlock_irqrestore(&owner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
chain_walk = 1;
@@ -459,12 +459,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
*/
get_task_struct(owner);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
task);
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
return res;
}
@@ -483,7 +483,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
struct task_struct *pendowner;
unsigned long flags;
- spin_lock_irqsave(&current->pi_lock, flags);
+ raw_spin_lock_irqsave(&current->pi_lock, flags);
waiter = rt_mutex_top_waiter(lock);
plist_del(&waiter->list_entry, &lock->wait_list);
@@ -500,7 +500,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
- spin_unlock_irqrestore(&current->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&current->pi_lock, flags);
/*
* Clear the pi_blocked_on variable and enqueue a possible
@@ -509,7 +509,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
* waiter with higher priority than pending-owner->normal_prio
* is blocked on the unboosted (pending) owner.
*/
- spin_lock_irqsave(&pendowner->pi_lock, flags);
+ raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
WARN_ON(!pendowner->pi_blocked_on);
WARN_ON(pendowner->pi_blocked_on != waiter);
@@ -523,7 +523,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
next = rt_mutex_top_waiter(lock);
plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
}
- spin_unlock_irqrestore(&pendowner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
wake_up_process(pendowner);
}
@@ -541,15 +541,15 @@ static void remove_waiter(struct rt_mutex *lock,
unsigned long flags;
int chain_walk = 0;
- spin_lock_irqsave(&current->pi_lock, flags);
+ raw_spin_lock_irqsave(&current->pi_lock, flags);
plist_del(&waiter->list_entry, &lock->wait_list);
waiter->task = NULL;
current->pi_blocked_on = NULL;
- spin_unlock_irqrestore(&current->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&current->pi_lock, flags);
if (first && owner != current) {
- spin_lock_irqsave(&owner->pi_lock, flags);
+ raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
@@ -564,7 +564,7 @@ static void remove_waiter(struct rt_mutex *lock,
if (owner->pi_blocked_on)
chain_walk = 1;
- spin_unlock_irqrestore(&owner->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
@@ -575,11 +575,11 @@ static void remove_waiter(struct rt_mutex *lock,
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(owner);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
}
/*
@@ -592,15 +592,15 @@ void rt_mutex_adjust_pi(struct task_struct *task)
struct rt_mutex_waiter *waiter;
unsigned long flags;
- spin_lock_irqsave(&task->pi_lock, flags);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
if (!waiter || waiter->list_entry.prio == task->prio) {
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
- spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(task);
@@ -672,14 +672,14 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
break;
}
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
if (waiter->task)
schedule_rt_mutex(lock);
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
set_current_state(state);
}
@@ -700,11 +700,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
debug_rt_mutex_init_waiter(&waiter);
waiter.task = NULL;
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
/* Try to acquire the lock again: */
if (try_to_take_rt_mutex(lock)) {
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
return 0;
}
@@ -731,7 +731,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
*/
fixup_rt_mutex_waiters(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
/* Remove pending timer: */
if (unlikely(timeout))
@@ -758,7 +758,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
{
int ret = 0;
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
if (likely(rt_mutex_owner(lock) != current)) {
@@ -770,7 +770,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
fixup_rt_mutex_waiters(lock);
}
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
return ret;
}
@@ -781,7 +781,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
static void __sched
rt_mutex_slowunlock(struct rt_mutex *lock)
{
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
debug_rt_mutex_unlock(lock);
@@ -789,13 +789,13 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
if (!rt_mutex_has_waiters(lock)) {
lock->owner = NULL;
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
return;
}
wakeup_next_waiter(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
/* Undo pi boosting if necessary: */
rt_mutex_adjust_prio(current);
@@ -970,8 +970,8 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy);
void __rt_mutex_init(struct rt_mutex *lock, const char *name)
{
lock->owner = NULL;
- spin_lock_init(&lock->wait_lock);
- plist_head_init(&lock->wait_list, &lock->wait_lock);
+ raw_spin_lock_init(&lock->wait_lock);
+ plist_head_init_raw(&lock->wait_list, &lock->wait_lock);
debug_rt_mutex_init(lock, name);
}
@@ -1032,7 +1032,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
{
int ret;
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
mark_rt_mutex_waiters(lock);
@@ -1040,7 +1040,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
/* We got the lock for task. */
debug_rt_mutex_lock(lock);
rt_mutex_set_owner(lock, task, 0);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
rt_mutex_deadlock_account_lock(lock, task);
return 1;
}
@@ -1056,7 +1056,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
*/
ret = 0;
}
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
@@ -1106,7 +1106,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
{
int ret;
- spin_lock(&lock->wait_lock);
+ raw_spin_lock(&lock->wait_lock);
set_current_state(TASK_INTERRUPTIBLE);
@@ -1124,7 +1124,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
*/
fixup_rt_mutex_waiters(lock);
- spin_unlock(&lock->wait_lock);
+ raw_spin_unlock(&lock->wait_lock);
/*
* Readjust priority, when we did not get the lock. We might have been
diff --git a/kernel/sched.c b/kernel/sched.c
index 2f76e06bea5..18cceeecce3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -141,7 +141,7 @@ struct rt_prio_array {
struct rt_bandwidth {
/* nests inside the rq lock: */
- spinlock_t rt_runtime_lock;
+ raw_spinlock_t rt_runtime_lock;
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
@@ -178,7 +178,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
rt_b->rt_period = ns_to_ktime(period);
rt_b->rt_runtime = runtime;
- spin_lock_init(&rt_b->rt_runtime_lock);
+ raw_spin_lock_init(&rt_b->rt_runtime_lock);
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -200,7 +200,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
if (hrtimer_active(&rt_b->rt_period_timer))
return;
- spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
for (;;) {
unsigned long delta;
ktime_t soft, hard;
@@ -217,7 +217,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
HRTIMER_MODE_ABS_PINNED, 0);
}
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
#ifdef CONFIG_RT_GROUP_SCHED
@@ -298,7 +298,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
}
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else /* !CONFIG_USER_SCHED */
@@ -469,7 +470,7 @@ struct rt_rq {
u64 rt_time;
u64 rt_runtime;
/* Nests inside the rq lock: */
- spinlock_t rt_runtime_lock;
+ raw_spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
unsigned long rt_nr_boosted;
@@ -524,7 +525,7 @@ static struct root_domain def_root_domain;
*/
struct rq {
/* runqueue lock: */
- spinlock_t lock;
+ raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
@@ -534,14 +535,12 @@ struct rq {
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
- unsigned long last_tick_seen;
unsigned char in_nohz_recently;
#endif
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
- u64 nr_migrations_in;
struct cfs_rq cfs;
struct rt_rq rt;
@@ -590,6 +589,8 @@ struct rq {
u64 rt_avg;
u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
@@ -676,6 +677,7 @@ inline void update_rq_clock(struct rq *rq)
/**
* runqueue_is_locked
+ * @cpu: the processor in question.
*
* Returns true if the current cpu runqueue is locked.
* This interface allows printk to be called with the runqueue lock
@@ -683,7 +685,7 @@ inline void update_rq_clock(struct rq *rq)
*/
int runqueue_is_locked(int cpu)
{
- return spin_is_locked(&cpu_rq(cpu)->lock);
+ return raw_spin_is_locked(&cpu_rq(cpu)->lock);
}
/*
@@ -770,7 +772,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
if (!sched_feat_names[i])
return -EINVAL;
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -780,7 +782,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp)
return single_open(filp, sched_feat_show, NULL);
}
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
.open = sched_feat_open,
.write = sched_feat_write,
.read = seq_read,
@@ -812,6 +814,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
* default: 0.25ms
*/
unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
/*
* Inject some fuzzyness into changing the per-cpu group shares
@@ -890,7 +893,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
@@ -914,9 +917,9 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
next->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
#else
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
#endif
}
@@ -946,10 +949,10 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
{
for (;;) {
struct rq *rq = task_rq(p);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p)))
return rq;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
}
@@ -966,10 +969,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
for (;;) {
local_irq_save(*flags);
rq = task_rq(p);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p)))
return rq;
- spin_unlock_irqrestore(&rq->lock, *flags);
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
}
}
@@ -978,19 +981,19 @@ void task_rq_unlock_wait(struct task_struct *p)
struct rq *rq = task_rq(p);
smp_mb(); /* spin-unlock-wait is not a full memory barrier */
- spin_unlock_wait(&rq->lock);
+ raw_spin_unlock_wait(&rq->lock);
}
static void __task_rq_unlock(struct rq *rq)
__releases(rq->lock)
{
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
__releases(rq->lock)
{
- spin_unlock_irqrestore(&rq->lock, *flags);
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
}
/*
@@ -1003,7 +1006,7 @@ static struct rq *this_rq_lock(void)
local_irq_disable();
rq = this_rq();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
return rq;
}
@@ -1050,10 +1053,10 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
return HRTIMER_NORESTART;
}
@@ -1066,10 +1069,10 @@ static void __hrtick_start(void *arg)
{
struct rq *rq = arg;
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
hrtimer_restart(&rq->hrtick_timer);
rq->hrtick_csd_pending = 0;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
/*
@@ -1176,7 +1179,7 @@ static void resched_task(struct task_struct *p)
{
int cpu;
- assert_spin_locked(&task_rq(p)->lock);
+ assert_raw_spin_locked(&task_rq(p)->lock);
if (test_tsk_need_resched(p))
return;
@@ -1198,10 +1201,10 @@ static void resched_cpu(int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- if (!spin_trylock_irqsave(&rq->lock, flags))
+ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
return;
resched_task(cpu_curr(cpu));
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#ifdef CONFIG_NO_HZ
@@ -1270,7 +1273,7 @@ static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
- assert_spin_locked(&task_rq(p)->lock);
+ assert_raw_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
}
@@ -1563,11 +1566,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
-struct update_shares_data {
- unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
@@ -1577,12 +1576,12 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares);
static void update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long sd_shares,
unsigned long sd_rq_weight,
- struct update_shares_data *usd)
+ unsigned long *usd_rq_weight)
{
unsigned long shares, rq_weight;
int boost = 0;
- rq_weight = usd->rq_weight[cpu];
+ rq_weight = usd_rq_weight[cpu];
if (!rq_weight) {
boost = 1;
rq_weight = NICE_0_LOAD;
@@ -1601,11 +1600,11 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
@@ -1616,8 +1615,8 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0, shares = 0;
- struct update_shares_data *usd;
+ unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
+ unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
unsigned long flags;
int i;
@@ -1626,12 +1625,13 @@ static int tg_shares_up(struct task_group *tg, void *data)
return 0;
local_irq_save(flags);
- usd = &__get_cpu_var(update_shares_data);
+ usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
for_each_cpu(i, sched_domain_span(sd)) {
weight = tg->cfs_rq[i]->load.weight;
- usd->rq_weight[i] = weight;
+ usd_rq_weight[i] = weight;
+ rq_weight += weight;
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
@@ -1640,10 +1640,13 @@ static int tg_shares_up(struct task_group *tg, void *data)
if (!weight)
weight = NICE_0_LOAD;
- rq_weight += weight;
+ sum_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
+ if (!rq_weight)
+ rq_weight = sum_weight;
+
if ((!shares && rq_weight) || shares > tg->shares)
shares = tg->shares;
@@ -1651,7 +1654,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
local_irq_restore(flags);
@@ -1703,9 +1706,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
if (root_task_group_empty())
return;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
update_shares(sd);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
}
static void update_h_load(long cpu)
@@ -1745,7 +1748,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
double_rq_lock(this_rq, busiest);
return 1;
@@ -1766,14 +1769,16 @@ static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
int ret = 0;
- if (unlikely(!spin_trylock(&busiest->lock))) {
+ if (unlikely(!raw_spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
- spin_unlock(&this_rq->lock);
- spin_lock(&busiest->lock);
- spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_unlock(&this_rq->lock);
+ raw_spin_lock(&busiest->lock);
+ raw_spin_lock_nested(&this_rq->lock,
+ SINGLE_DEPTH_NESTING);
ret = 1;
} else
- spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock_nested(&busiest->lock,
+ SINGLE_DEPTH_NESTING);
}
return ret;
}
@@ -1787,7 +1792,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
BUG_ON(1);
}
@@ -1797,7 +1802,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
- spin_unlock(&busiest->lock);
+ raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
#endif
@@ -1812,6 +1817,22 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
#endif
static void calc_load_account_active(struct rq *this_rq);
+static void update_sysctl(void);
+static int get_update_sysctl_factor(void);
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+ set_task_rq(p, cpu);
+#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+ * successfuly executed on another CPU. We must ensure that updates of
+ * per-task data have been completed by this moment.
+ */
+ smp_wmb();
+ task_thread_info(p)->cpu = cpu;
+#endif
+}
#include "sched_stats.h"
#include "sched_idletask.c"
@@ -1969,20 +1990,6 @@ inline int task_curr(const struct task_struct *p)
return cpu_curr(task_cpu(p)) == p;
}
-static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-{
- set_task_rq(p, cpu);
-#ifdef CONFIG_SMP
- /*
- * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
- * successfuly executed on another CPU. We must ensure that updates of
- * per-task data have been completed by this moment.
- */
- smp_wmb();
- task_thread_info(p)->cpu = cpu;
-#endif
-}
-
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
int oldprio, int running)
@@ -1995,6 +2002,39 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ /* Must have done schedule() in kthread() before we set_task_cpu */
+ if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+ WARN_ON(1);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+ set_task_cpu(p, cpu);
+ p->cpus_allowed = cpumask_of_cpu(cpu);
+ p->rt.nr_cpus_allowed = 1;
+ p->flags |= PF_THREAD_BOUND;
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
@@ -2007,7 +2047,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
/*
* Buddy candidates are cache hot:
*/
- if (sched_feat(CACHE_HOT_BUDDY) &&
+ if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
@@ -2029,30 +2069,13 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
int old_cpu = task_cpu(p);
- struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
struct cfs_rq *old_cfsrq = task_cfs_rq(p),
*new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
- u64 clock_offset;
-
- clock_offset = old_rq->clock - new_rq->clock;
trace_sched_migrate_task(p, new_cpu);
-#ifdef CONFIG_SCHEDSTATS
- if (p->se.wait_start)
- p->se.wait_start -= clock_offset;
- if (p->se.sleep_start)
- p->se.sleep_start -= clock_offset;
- if (p->se.block_start)
- p->se.block_start -= clock_offset;
-#endif
if (old_cpu != new_cpu) {
p->se.nr_migrations++;
- new_rq->nr_migrations_in++;
-#ifdef CONFIG_SCHEDSTATS
- if (task_hot(p, old_rq->clock, NULL))
- schedstat_inc(p, se.nr_forced2_migrations);
-#endif
perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
1, 1, NULL, 0);
}
@@ -2085,6 +2108,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
* it is sufficient to simply update the task's cpu field.
*/
if (!p->se.on_rq && !task_running(rq, p)) {
+ update_rq_clock(rq);
set_task_cpu(p, dest_cpu);
return 0;
}
@@ -2292,6 +2316,14 @@ void task_oncpu_function_call(struct task_struct *p,
preempt_enable();
}
+#ifdef CONFIG_SMP
+static inline
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+{
+ return p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+}
+#endif
+
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
@@ -2311,7 +2343,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
{
int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
- struct rq *rq;
+ struct rq *rq, *orig_rq;
if (!sched_feat(SYNC_WAKEUPS))
wake_flags &= ~WF_SYNC;
@@ -2319,7 +2351,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
this_cpu = get_cpu();
smp_wmb();
- rq = task_rq_lock(p, &flags);
+ rq = orig_rq = task_rq_lock(p, &flags);
update_rq_clock(rq);
if (!(p->state & state))
goto out;
@@ -2343,13 +2375,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
if (task_contributes_to_load(p))
rq->nr_uninterruptible--;
p->state = TASK_WAKING;
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
if (cpu != orig_cpu)
set_task_cpu(p, cpu);
- rq = task_rq_lock(p, &flags);
+ rq = __task_rq_lock(p);
+ update_rq_clock(rq);
+
WARN_ON(p->state != TASK_WAKING);
cpu = task_cpu(p);
@@ -2406,6 +2440,17 @@ out_running:
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
p->sched_class->task_wake_up(rq, p);
+
+ if (unlikely(rq->idle_stamp)) {
+ u64 delta = rq->clock - rq->idle_stamp;
+ u64 max = 2*sysctl_sched_migration_cost;
+
+ if (delta > max)
+ rq->avg_idle = max;
+ else
+ update_avg(&rq->avg_idle, delta);
+ rq->idle_stamp = 0;
+ }
#endif
out:
task_rq_unlock(rq, &flags);
@@ -2452,7 +2497,6 @@ static void __sched_fork(struct task_struct *p)
p->se.avg_overlap = 0;
p->se.start_runtime = 0;
p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
- p->se.avg_running = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
@@ -2474,7 +2518,6 @@ static void __sched_fork(struct task_struct *p)
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
- p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
@@ -2515,22 +2558,17 @@ void sched_fork(struct task_struct *p, int clone_flags)
__sched_fork(p);
/*
- * Make sure we do not leak PI boosting priority to the child.
- */
- p->prio = current->normal_prio;
-
- /*
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
p->policy = SCHED_NORMAL;
-
- if (p->normal_prio < DEFAULT_PRIO)
- p->prio = DEFAULT_PRIO;
+ p->normal_prio = p->static_prio;
+ }
if (PRIO_TO_NICE(p->static_prio) < 0) {
p->static_prio = NICE_TO_PRIO(0);
+ p->normal_prio = p->static_prio;
set_load_weight(p);
}
@@ -2541,11 +2579,19 @@ void sched_fork(struct task_struct *p, int clone_flags)
p->sched_reset_on_fork = 0;
}
+ /*
+ * Make sure we do not leak PI boosting priority to the child.
+ */
+ p->prio = current->normal_prio;
+
if (!rt_prio(p->prio))
p->sched_class = &fair_sched_class;
+ if (p->sched_class->task_fork)
+ p->sched_class->task_fork(p);
+
#ifdef CONFIG_SMP
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
+ cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
#endif
set_task_cpu(p, cpu);
@@ -2580,19 +2626,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
update_rq_clock(rq);
-
- p->prio = effective_prio(p);
-
- if (!p->sched_class->task_new || !current->se.on_rq) {
- activate_task(rq, p, 0);
- } else {
- /*
- * Let the scheduling class do new task startup
- * management (if any):
- */
- p->sched_class->task_new(rq, p);
- inc_nr_running(rq);
- }
+ activate_task(rq, p, 0);
trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
@@ -2749,10 +2783,10 @@ static inline void post_schedule(struct rq *rq)
if (rq->post_schedule) {
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->curr->sched_class->post_schedule)
rq->curr->sched_class->post_schedule(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
rq->post_schedule = 0;
}
@@ -2816,14 +2850,14 @@ context_switch(struct rq *rq, struct task_struct *prev,
*/
arch_start_context_switch(prev);
- if (unlikely(!mm)) {
+ if (likely(!mm)) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
- if (unlikely(!prev->mm)) {
+ if (likely(!prev->mm)) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
@@ -2986,15 +3020,6 @@ static void calc_load_account_active(struct rq *this_rq)
}
/*
- * Externally visible per-cpu scheduler statistics:
- * cpu_nr_migrations(cpu) - number of migrations into that cpu
- */
-u64 cpu_nr_migrations(int cpu)
-{
- return cpu_rq(cpu)->nr_migrations_in;
-}
-
-/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC).
*/
@@ -3043,15 +3068,15 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
{
BUG_ON(!irqs_disabled());
if (rq1 == rq2) {
- spin_lock(&rq1->lock);
+ raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
} else {
if (rq1 < rq2) {
- spin_lock(&rq1->lock);
- spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&rq1->lock);
+ raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
} else {
- spin_lock(&rq2->lock);
- spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&rq2->lock);
+ raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
}
}
update_rq_clock(rq1);
@@ -3068,9 +3093,9 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
- spin_unlock(&rq1->lock);
+ raw_spin_unlock(&rq1->lock);
if (rq1 != rq2)
- spin_unlock(&rq2->lock);
+ raw_spin_unlock(&rq2->lock);
else
__release(rq2->lock);
}
@@ -3116,7 +3141,7 @@ out:
void sched_exec(void)
{
int new_cpu, this_cpu = get_cpu();
- new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
+ new_cpu = select_task_rq(current, SD_BALANCE_EXEC, 0);
put_cpu();
if (new_cpu != this_cpu)
sched_migrate_task(current, new_cpu);
@@ -3132,10 +3157,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
deactivate_task(src_rq, p, 0);
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
- /*
- * Note that idle threads have a prio of MAX_PRIO, for this test
- * to be always true for them.
- */
check_preempt_curr(this_rq, p, 0);
}
@@ -3658,6 +3679,7 @@ static void update_group_power(struct sched_domain *sd, int cpu)
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
* @group: sched_group whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
@@ -4093,7 +4115,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
unsigned long flags;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
@@ -4166,14 +4188,15 @@ redo:
if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
- spin_lock_irqsave(&busiest->lock, flags);
+ raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
if (!cpumask_test_cpu(this_cpu,
&busiest->curr->cpus_allowed)) {
- spin_unlock_irqrestore(&busiest->lock, flags);
+ raw_spin_unlock_irqrestore(&busiest->lock,
+ flags);
all_pinned = 1;
goto out_one_pinned;
}
@@ -4183,7 +4206,7 @@ redo:
busiest->push_cpu = this_cpu;
active_balance = 1;
}
- spin_unlock_irqrestore(&busiest->lock, flags);
+ raw_spin_unlock_irqrestore(&busiest->lock, flags);
if (active_balance)
wake_up_process(busiest->migration_thread);
@@ -4256,7 +4279,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
int all_pinned = 0;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
@@ -4365,10 +4388,10 @@ redo:
/*
* Should not call ttwu while holding a rq->lock
*/
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
if (active_balance)
wake_up_process(busiest->migration_thread);
- spin_lock(&this_rq->lock);
+ raw_spin_lock(&this_rq->lock);
} else
sd->nr_balance_failed = 0;
@@ -4396,6 +4419,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ this_rq->idle_stamp = this_rq->clock;
+
+ if (this_rq->avg_idle < sysctl_sched_migration_cost)
+ return;
+
for_each_domain(this_cpu, sd) {
unsigned long interval;
@@ -4410,8 +4438,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
@@ -4646,7 +4676,7 @@ int select_nohz_load_balancer(int stop_tick)
cpumask_set_cpu(cpu, nohz.cpu_mask);
/* time for ilb owner also to sleep */
- if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+ if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu)
atomic_set(&nohz.load_balancer, -1);
return 0;
@@ -5013,8 +5043,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
p->gtime = cputime_add(p->gtime, cputime);
/* Add guest time to cpustat. */
- cpustat->user = cputime64_add(cpustat->user, tmp);
- cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ if (TASK_NICE(p) > 0) {
+ cpustat->nice = cputime64_add(cpustat->nice, tmp);
+ cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+ } else {
+ cpustat->user = cputime64_add(cpustat->user, tmp);
+ cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ }
}
/*
@@ -5129,60 +5164,86 @@ void account_idle_ticks(unsigned long ticks)
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-cputime_t task_utime(struct task_struct *p)
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->utime;
+ *ut = p->utime;
+ *st = p->stime;
}
-cputime_t task_stime(struct task_struct *p)
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->stime;
+ struct task_cputime cputime;
+
+ thread_group_cputime(p, &cputime);
+
+ *ut = cputime.utime;
+ *st = cputime.stime;
}
#else
-cputime_t task_utime(struct task_struct *p)
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
+#endif
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t utime = cputime_to_clock_t(p->utime),
- total = utime + cputime_to_clock_t(p->stime);
- u64 temp;
+ cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
/*
* Use CFS's precise accounting:
*/
- temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+ rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
if (total) {
- temp *= utime;
+ u64 temp;
+
+ temp = (u64)(rtime * utime);
do_div(temp, total);
- }
- utime = (clock_t)temp;
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
- p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
- return p->prev_utime;
+ /*
+ * Compare with previous values, to keep monotonicity:
+ */
+ p->prev_utime = max(p->prev_utime, utime);
+ p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));
+
+ *ut = p->prev_utime;
+ *st = p->prev_stime;
}
-cputime_t task_stime(struct task_struct *p)
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t stime;
+ struct signal_struct *sig = p->signal;
+ struct task_cputime cputime;
+ cputime_t rtime, utime, total;
- /*
- * Use CFS's precise accounting. (we subtract utime from
- * the total, to make sure the total observed by userspace
- * grows monotonically - apps rely on that):
- */
- stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
- cputime_to_clock_t(task_utime(p));
+ thread_group_cputime(p, &cputime);
- if (stime >= 0)
- p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+ total = cputime_add(cputime.utime, cputime.stime);
+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
- return p->prev_stime;
-}
-#endif
+ if (total) {
+ u64 temp;
-inline cputime_t task_gtime(struct task_struct *p)
-{
- return p->gtime;
+ temp = (u64)(rtime * cputime.utime);
+ do_div(temp, total);
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
+
+ sig->prev_utime = max(sig->prev_utime, utime);
+ sig->prev_stime = max(sig->prev_stime,
+ cputime_sub(rtime, sig->prev_utime));
+
+ *ut = sig->prev_utime;
+ *st = sig->prev_stime;
}
+#endif
/*
* This function gets called by the timer code, with HZ frequency.
@@ -5199,11 +5260,11 @@ void scheduler_tick(void)
sched_clock_tick();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
update_cpu_load(rq);
curr->sched_class->task_tick(rq, curr, 0);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
perf_event_task_tick(curr, cpu);
@@ -5317,13 +5378,14 @@ static inline void schedule_debug(struct task_struct *prev)
#endif
}
-static void put_prev_task(struct rq *rq, struct task_struct *p)
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;
+ if (prev->state == TASK_RUNNING) {
+ u64 runtime = prev->se.sum_exec_runtime;
- update_avg(&p->se.avg_running, runtime);
+ runtime -= prev->se.prev_sum_exec_runtime;
+ runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- if (p->state == TASK_RUNNING) {
/*
* In order to avoid avg_overlap growing stale when we are
* indeed overlapping and hence not getting put to sleep, grow
@@ -5333,12 +5395,9 @@ static void put_prev_task(struct rq *rq, struct task_struct *p)
* correlates to the amount of cache footprint a task can
* build up.
*/
- runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- update_avg(&p->se.avg_overlap, runtime);
- } else {
- update_avg(&p->se.avg_running, 0);
+ update_avg(&prev->se.avg_overlap, runtime);
}
- p->sched_class->put_prev_task(rq, p);
+ prev->sched_class->put_prev_task(rq, prev);
}
/*
@@ -5399,7 +5458,7 @@ need_resched_nonpreemptible:
if (sched_feat(HRTICK))
hrtick_clear(rq);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
clear_tsk_need_resched(prev);
@@ -5435,7 +5494,7 @@ need_resched_nonpreemptible:
cpu = smp_processor_id();
rq = cpu_rq(cpu);
} else
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
@@ -5448,7 +5507,7 @@ need_resched_nonpreemptible:
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
@@ -6142,22 +6201,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
BUG_ON(p->se.on_rq);
p->policy = policy;
- switch (p->policy) {
- case SCHED_NORMAL:
- case SCHED_BATCH:
- case SCHED_IDLE:
- p->sched_class = &fair_sched_class;
- break;
- case SCHED_FIFO:
- case SCHED_RR:
- p->sched_class = &rt_sched_class;
- break;
- }
-
p->rt_priority = prio;
p->normal_prio = normal_prio(p);
/* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
+ if (rt_prio(p->prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
set_load_weight(p);
}
@@ -6272,7 +6323,7 @@ recheck:
* make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
*/
- spin_lock_irqsave(&p->pi_lock, flags);
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
/*
* To be able to change p->policy safely, the apropriate
* runqueue lock must be held.
@@ -6282,7 +6333,7 @@ recheck:
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
__task_rq_unlock(rq);
- spin_unlock_irqrestore(&p->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
goto recheck;
}
update_rq_clock(rq);
@@ -6306,7 +6357,7 @@ recheck:
check_class_changed(rq, p, prev_class, oldprio, running);
}
__task_rq_unlock(rq);
- spin_unlock_irqrestore(&p->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
rt_mutex_adjust_pi(p);
@@ -6560,6 +6611,8 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
+ unsigned long flags;
+ struct rq *rq;
int retval;
get_online_cpus();
@@ -6574,7 +6627,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
if (retval)
goto out_unlock;
+ rq = task_rq_lock(p, &flags);
cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+ task_rq_unlock(rq, &flags);
out_unlock:
read_unlock(&tasklist_lock);
@@ -6632,7 +6687,7 @@ SYSCALL_DEFINE0(sched_yield)
*/
__release(rq->lock);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
- _raw_spin_unlock(&rq->lock);
+ do_raw_spin_unlock(&rq->lock);
preempt_enable_no_resched();
schedule();
@@ -6720,9 +6775,6 @@ EXPORT_SYMBOL(yield);
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
*/
void __sched io_schedule(void)
{
@@ -6815,6 +6867,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
{
struct task_struct *p;
unsigned int time_slice;
+ unsigned long flags;
+ struct rq *rq;
int retval;
struct timespec t;
@@ -6831,7 +6885,9 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
if (retval)
goto out_unlock;
- time_slice = p->sched_class->get_rr_interval(p);
+ rq = task_rq_lock(p, &flags);
+ time_slice = p->sched_class->get_rr_interval(rq, p);
+ task_rq_unlock(rq, &flags);
read_unlock(&tasklist_lock);
jiffies_to_timespec(time_slice, &t);
@@ -6905,7 +6961,7 @@ void show_state_filter(unsigned long state_filter)
/*
* Only show locks if all tasks are dumped:
*/
- if (state_filter == -1)
+ if (!state_filter)
debug_show_all_locks();
}
@@ -6927,12 +6983,11 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__sched_fork(idle);
idle->se.exec_start = sched_clock();
- idle->prio = idle->normal_prio = MAX_PRIO;
cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
__set_task_cpu(idle, cpu);
@@ -6940,7 +6995,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
idle->oncpu = 1;
#endif
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
#if defined(CONFIG_PREEMPT)
@@ -6973,22 +7028,43 @@ cpumask_var_t nohz_cpu_mask;
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static inline void sched_init_granularity(void)
+static int get_update_sysctl_factor(void)
{
- unsigned int factor = 1 + ilog2(num_online_cpus());
- const unsigned long limit = 200000000;
+ unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int factor;
- sysctl_sched_min_granularity *= factor;
- if (sysctl_sched_min_granularity > limit)
- sysctl_sched_min_granularity = limit;
+ switch (sysctl_sched_tunable_scaling) {
+ case SCHED_TUNABLESCALING_NONE:
+ factor = 1;
+ break;
+ case SCHED_TUNABLESCALING_LINEAR:
+ factor = cpus;
+ break;
+ case SCHED_TUNABLESCALING_LOG:
+ default:
+ factor = 1 + ilog2(cpus);
+ break;
+ }
- sysctl_sched_latency *= factor;
- if (sysctl_sched_latency > limit)
- sysctl_sched_latency = limit;
+ return factor;
+}
- sysctl_sched_wakeup_granularity *= factor;
+static void update_sysctl(void)
+{
+ unsigned int factor = get_update_sysctl_factor();
+
+#define SET_SYSCTL(name) \
+ (sysctl_##name = (factor) * normalized_sysctl_##name)
+ SET_SYSCTL(sched_min_granularity);
+ SET_SYSCTL(sched_latency);
+ SET_SYSCTL(sched_wakeup_granularity);
+ SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
- sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+ update_sysctl();
}
#ifdef CONFIG_SMP
@@ -7025,7 +7101,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
int ret = 0;
rq = task_rq_lock(p, &flags);
- if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+ if (!cpumask_intersects(new_mask, cpu_active_mask)) {
ret = -EINVAL;
goto out;
}
@@ -7047,7 +7123,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
if (cpumask_test_cpu(task_cpu(p), new_mask))
goto out;
- if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+ if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
struct task_struct *mt = rq->migration_thread;
@@ -7136,10 +7212,10 @@ static int migration_thread(void *data)
struct migration_req *req;
struct list_head *head;
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
if (cpu_is_offline(cpu)) {
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
break;
}
@@ -7151,7 +7227,7 @@ static int migration_thread(void *data)
head = &rq->migration_queue;
if (list_empty(head)) {
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
schedule();
set_current_state(TASK_INTERRUPTIBLE);
continue;
@@ -7160,14 +7236,14 @@ static int migration_thread(void *data)
list_del_init(head->next);
if (req->task != NULL) {
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
__migrate_task(req->task, cpu, req->dest_cpu);
} else if (likely(cpu == (badcpu = smp_processor_id()))) {
req->dest_cpu = RCU_MIGRATION_GOT_QS;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
} else {
req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
}
local_irq_enable();
@@ -7201,19 +7277,19 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
again:
/* Look for allowed, online CPU in same node. */
- for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+ for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
goto move;
/* Any allowed, online CPU? */
- dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
if (dest_cpu < nr_cpu_ids)
goto move;
/* No more Mr. Nice Guy. */
if (dest_cpu >= nr_cpu_ids) {
cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
- dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
+ dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
/*
* Don't tell them about moving exiting tasks or
@@ -7242,7 +7318,7 @@ move:
*/
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+ struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
unsigned long flags;
local_irq_save(flags);
@@ -7290,14 +7366,14 @@ void sched_idle_next(void)
* Strictly not necessary since rest of the CPUs are stopped by now
* and interrupts disabled on the current cpu.
*/
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
update_rq_clock(rq);
activate_task(rq, p, 0);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
@@ -7333,9 +7409,9 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
* that's OK. No task can be added to this CPU, so iteration is
* fine.
*/
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
move_task_off_dead_cpu(dead_cpu, p);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
put_task_struct(p);
}
@@ -7376,17 +7452,16 @@ static struct ctl_table sd_ctl_dir[] = {
.procname = "sched_domain",
.mode = 0555,
},
- {0, },
+ {}
};
static struct ctl_table sd_ctl_root[] = {
{
- .ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
.child = sd_ctl_dir,
},
- {0, },
+ {}
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
@@ -7496,7 +7571,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
static struct ctl_table_header *sd_sysctl_header;
static void register_sched_domain_sysctl(void)
{
- int i, cpu_num = num_online_cpus();
+ int i, cpu_num = num_possible_cpus();
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
@@ -7506,7 +7581,7 @@ static void register_sched_domain_sysctl(void)
if (entry == NULL)
return;
- for_each_online_cpu(i) {
+ for_each_possible_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
@@ -7602,13 +7677,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
/* Update our root-domain */
rq = cpu_rq(cpu);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_online(rq);
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
@@ -7633,14 +7708,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
put_task_struct(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
deactivate_task(rq, rq->idle, 0);
- rq->idle->static_prio = MAX_PRIO;
__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
rq->idle->sched_class = &idle_sched_class;
migrate_dead_tasks(cpu);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
@@ -7650,30 +7724,30 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
* they didn't take sched_hotcpu_mutex. Just wake up
* the requestors.
*/
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
while (!list_empty(&rq->migration_queue)) {
struct migration_req *req;
req = list_entry(rq->migration_queue.next,
struct migration_req, list);
list_del_init(&req->list);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
complete(&req->done);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
}
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
/* Update our root-domain */
rq = cpu_rq(cpu);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#endif
}
@@ -7710,6 +7784,16 @@ early_initcall(migration_init);
#ifdef CONFIG_SCHED_DEBUG
+static __read_mostly int sched_domain_debug_enabled;
+
+static int __init sched_domain_debug_setup(char *str)
+{
+ sched_domain_debug_enabled = 1;
+
+ return 0;
+}
+early_param("sched_debug", sched_domain_debug_setup);
+
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
{
@@ -7796,6 +7880,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
cpumask_var_t groupmask;
int level = 0;
+ if (!sched_domain_debug_enabled)
+ return;
+
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
return;
@@ -7875,6 +7962,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
static void free_rootdomain(struct root_domain *rd)
{
+ synchronize_sched();
+
cpupri_cleanup(&rd->cpupri);
free_cpumask_var(rd->rto_mask);
@@ -7888,7 +7977,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
struct root_domain *old_rd = NULL;
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
old_rd = rq->rd;
@@ -7914,7 +8003,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
free_rootdomain(old_rd);
@@ -8015,6 +8104,7 @@ static cpumask_var_t cpu_isolated_map;
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
+ alloc_bootmem_cpumask_var(&cpu_isolated_map);
cpulist_parse(str, cpu_isolated_map);
return 1;
}
@@ -8199,14 +8289,14 @@ enum s_alloc {
*/
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
static int
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg, struct cpumask *unused)
{
if (sg)
- *sg = &per_cpu(sched_group_cpus, cpu).sg;
+ *sg = &per_cpu(sched_groups, cpu).sg;
return cpu;
}
#endif /* CONFIG_SCHED_SMT */
@@ -8851,7 +8941,7 @@ static int build_sched_domains(const struct cpumask *cpu_map)
return __build_sched_domains(cpu_map, NULL);
}
-static struct cpumask *doms_cur; /* current sched domains */
+static cpumask_var_t *doms_cur; /* current sched domains */
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
/* attribues of custom domains in 'doms_cur' */
@@ -8873,6 +8963,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void)
return 0;
}
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+ int i;
+ cpumask_var_t *doms;
+
+ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+ if (!doms)
+ return NULL;
+ for (i = 0; i < ndoms; i++) {
+ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+ free_sched_domains(doms, i);
+ return NULL;
+ }
+ }
+ return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+ unsigned int i;
+ for (i = 0; i < ndoms; i++)
+ free_cpumask_var(doms[i]);
+ kfree(doms);
+}
+
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* For now this just excludes isolated cpus, but could be used to
@@ -8884,12 +8999,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map)
arch_update_cpu_topology();
ndoms_cur = 1;
- doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+ doms_cur = alloc_sched_domains(ndoms_cur);
if (!doms_cur)
- doms_cur = fallback_doms;
- cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+ doms_cur = &fallback_doms;
+ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
dattr_cur = NULL;
- err = build_sched_domains(doms_cur);
+ err = build_sched_domains(doms_cur[0]);
register_sched_domain_sysctl();
return err;
@@ -8939,19 +9054,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
* doms_new[] to the current sched domain partitioning, doms_cur[].
* It destroys each deleted domain and builds each new domain.
*
- * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
* The masks don't intersect (don't overlap.) We should setup one
* sched domain for each mask. CPUs not in any of the cpumasks will
* not be load balanced. If the same cpumask appears both in the
* current 'doms_cur' domains and in the new 'doms_new', we can leave
* it as it is.
*
- * The passed in 'doms_new' should be kmalloc'd. This routine takes
- * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL &&
- * ndoms_new == 1, and partition_sched_domains() will fallback to
- * the single partition 'fallback_doms', it also forces the domains
- * to be rebuilt.
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains. This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
*
* If doms_new == NULL it will be replaced with cpu_online_mask.
* ndoms_new == 0 is a special case for destroying existing domains,
@@ -8959,8 +9074,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
*
* Call with hotplug lock held
*/
-/* FIXME: Change to struct cpumask *doms_new[] */
-void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
int i, j, n;
@@ -8979,40 +9093,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(&doms_cur[i], &doms_new[j])
+ if (cpumask_equal(doms_cur[i], doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* no match - a current sched domain not in new doms_new[] */
- detach_destroy_domains(doms_cur + i);
+ detach_destroy_domains(doms_cur[i]);
match1:
;
}
if (doms_new == NULL) {
ndoms_cur = 0;
- doms_new = fallback_doms;
- cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+ doms_new = &fallback_doms;
+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
WARN_ON_ONCE(dattr_new);
}
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < ndoms_cur && !new_topology; j++) {
- if (cpumask_equal(&doms_new[i], &doms_cur[j])
+ if (cpumask_equal(doms_new[i], doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* no match - add a new doms_new */
- __build_sched_domains(doms_new + i,
+ __build_sched_domains(doms_new[i],
dattr_new ? dattr_new + i : NULL);
match2:
;
}
/* Remember the new sched domains */
- if (doms_cur != fallback_doms)
- kfree(doms_cur);
+ if (doms_cur != &fallback_doms)
+ free_sched_domains(doms_cur, ndoms_cur);
kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
dattr_cur = dattr_new;
@@ -9123,8 +9237,10 @@ static int update_sched_domains(struct notifier_block *nfb,
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
partition_sched_domains(1, NULL, NULL);
return NOTIFY_OK;
@@ -9171,7 +9287,7 @@ void __init sched_init_smp(void)
#endif
get_online_cpus();
mutex_lock(&sched_domains_mutex);
- arch_init_sched_domains(cpu_online_mask);
+ arch_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);
@@ -9244,13 +9360,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
- plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
+ plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
rt_rq->rt_throttled = 0;
rt_rq->rt_runtime = 0;
- spin_lock_init(&rt_rq->rt_runtime_lock);
+ raw_spin_lock_init(&rt_rq->rt_runtime_lock);
#ifdef CONFIG_RT_GROUP_SCHED
rt_rq->rt_nr_boosted = 0;
@@ -9334,10 +9450,6 @@ void __init sched_init(void)
#ifdef CONFIG_CPUMASK_OFFSTACK
alloc_size += num_possible_cpus() * cpumask_size();
#endif
- /*
- * As sched_init() is called before page_alloc is setup,
- * we use alloc_bootmem().
- */
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
@@ -9406,11 +9518,15 @@ void __init sched_init(void)
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_GROUP_SCHED */
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+ update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+ __alignof__(unsigned long));
+#endif
for_each_possible_cpu(i) {
struct rq *rq;
rq = cpu_rq(i);
- spin_lock_init(&rq->lock);
+ raw_spin_lock_init(&rq->lock);
rq->nr_running = 0;
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
@@ -9470,7 +9586,7 @@ void __init sched_init(void)
#elif defined CONFIG_USER_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
init_tg_rt_entry(&init_task_group,
- &per_cpu(init_rt_rq, i),
+ &per_cpu(init_rt_rq_var, i),
&per_cpu(init_sched_rt_entity, i), i, 1,
root_task_group.rt_se[i]);
#endif
@@ -9488,6 +9604,8 @@ void __init sched_init(void)
rq->cpu = i;
rq->online = 0;
rq->migration_thread = NULL;
+ rq->idle_stamp = 0;
+ rq->avg_idle = 2*sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->migration_queue);
rq_attach_root(rq, &def_root_domain);
#endif
@@ -9506,7 +9624,7 @@ void __init sched_init(void)
#endif
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+ plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock);
#endif
/*
@@ -9531,13 +9649,15 @@ void __init sched_init(void)
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ /* May be allocated at isolcpus cmdline parse time */
+ if (cpu_isolated_map == NULL)
+ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
perf_event_init();
@@ -9629,13 +9749,13 @@ void normalize_rt_tasks(void)
continue;
}
- spin_lock(&p->pi_lock);
+ raw_spin_lock(&p->pi_lock);
rq = __task_rq_lock(p);
normalize_task(rq, p);
__task_rq_unlock(rq);
- spin_unlock(&p->pi_lock);
+ raw_spin_unlock(&p->pi_lock);
} while_each_thread(g, p);
read_unlock_irqrestore(&tasklist_lock, flags);
@@ -9731,13 +9851,15 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
se = kzalloc_node(sizeof(struct sched_entity),
GFP_KERNEL, cpu_to_node(i));
if (!se)
- goto err;
+ goto err_free_rq;
init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
}
return 1;
+ err_free_rq:
+ kfree(cfs_rq);
err:
return 0;
}
@@ -9819,13 +9941,15 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
GFP_KERNEL, cpu_to_node(i));
if (!rt_se)
- goto err;
+ goto err_free_rq;
init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
}
return 1;
+ err_free_rq:
+ kfree(rt_rq);
err:
return 0;
}
@@ -9994,9 +10118,9 @@ static void set_se_shares(struct sched_entity *se, unsigned long shares)
struct rq *rq = cfs_rq->rq;
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__set_se_shares(se, shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static DEFINE_MUTEX(shares_mutex);
@@ -10181,18 +10305,18 @@ static int tg_set_bandwidth(struct task_group *tg,
if (err)
goto unlock;
- spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+ raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
tg->rt_bandwidth.rt_runtime = rt_runtime;
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = tg->rt_rq[i];
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = rt_runtime;
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
- spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+ raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
@@ -10297,22 +10421,22 @@ static int sched_rt_global_constraints(void)
if (sysctl_sched_rt_runtime == 0)
return -EBUSY;
- spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+ raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = global_rt_runtime();
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
- spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+ raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
return 0;
}
#endif /* CONFIG_RT_GROUP_SCHED */
int sched_rt_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
@@ -10323,7 +10447,7 @@ int sched_rt_handler(struct ctl_table *table, int write,
old_period = sysctl_sched_rt_period;
old_runtime = sysctl_sched_rt_runtime;
- ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
ret = sched_rt_global_constraints();
@@ -10377,8 +10501,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
}
static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct task_struct *tsk)
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
@@ -10388,15 +10511,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
if (tsk->sched_class != &fair_sched_class)
return -EINVAL;
#endif
+ return 0;
+}
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct task_struct *tsk, bool threadgroup)
+{
+ int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+ if (retval)
+ return retval;
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ retval = cpu_cgroup_can_attach_task(cgrp, c);
+ if (retval) {
+ rcu_read_unlock();
+ return retval;
+ }
+ }
+ rcu_read_unlock();
+ }
return 0;
}
static void
cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup *old_cont, struct task_struct *tsk)
+ struct cgroup *old_cont, struct task_struct *tsk,
+ bool threadgroup)
{
sched_move_task(tsk);
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ sched_move_task(c);
+ }
+ rcu_read_unlock();
+ }
}
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -10567,9 +10720,9 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
/*
* Take rq->lock to make 64-bit read safe on 32-bit platforms.
*/
- spin_lock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_lock_irq(&cpu_rq(cpu)->lock);
data = *cpuusage;
- spin_unlock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
data = *cpuusage;
#endif
@@ -10585,9 +10738,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
/*
* Take rq->lock to make 64-bit write safe on 32-bit platforms.
*/
- spin_lock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_lock_irq(&cpu_rq(cpu)->lock);
*cpuusage = val;
- spin_unlock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
*cpuusage = val;
#endif
@@ -10821,9 +10974,9 @@ void synchronize_sched_expedited(void)
init_completion(&req->done);
req->task = NULL;
req->dest_cpu = RCU_MIGRATION_NEED_QS;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
list_add(&req->list, &rq->migration_queue);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
wake_up_process(rq->migration_thread);
}
for_each_online_cpu(cpu) {
@@ -10831,13 +10984,14 @@ void synchronize_sched_expedited(void)
req = &per_cpu(rcu_migration_req, cpu);
rq = cpu_rq(cpu);
wait_for_completion(&req->done);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
need_full_sync = 1;
req->dest_cpu = RCU_MIGRATION_IDLE;
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ synchronize_sched_expedited_count++;
mutex_unlock(&rcu_sched_expedited_mutex);
put_online_cpus();
if (need_full_sync)
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index ac2e1dc708b..479ce5682d7 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -127,7 +127,7 @@ again:
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
- if (cmpxchg(&scd->clock, old_clock, clock) != old_clock)
+ if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
goto again;
return clock;
@@ -163,7 +163,7 @@ again:
val = remote_clock;
}
- if (cmpxchg(ptr, old_val, val) != old_val)
+ if (cmpxchg64(ptr, old_val, val) != old_val)
goto again;
return val;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 0f052fc674d..597b33099df 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -135,26 +135,26 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
- spin_lock_irqsave(&vec->lock, flags);
+ raw_spin_lock_irqsave(&vec->lock, flags);
cpumask_set_cpu(cpu, vec->mask);
vec->count++;
if (vec->count == 1)
set_bit(newpri, cp->pri_active);
- spin_unlock_irqrestore(&vec->lock, flags);
+ raw_spin_unlock_irqrestore(&vec->lock, flags);
}
if (likely(oldpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
- spin_lock_irqsave(&vec->lock, flags);
+ raw_spin_lock_irqsave(&vec->lock, flags);
vec->count--;
if (!vec->count)
clear_bit(oldpri, cp->pri_active);
cpumask_clear_cpu(cpu, vec->mask);
- spin_unlock_irqrestore(&vec->lock, flags);
+ raw_spin_unlock_irqrestore(&vec->lock, flags);
}
*currpri = newpri;
@@ -180,7 +180,7 @@ int cpupri_init(struct cpupri *cp, bool bootmem)
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
- spin_lock_init(&vec->lock);
+ raw_spin_lock_init(&vec->lock);
vec->count = 0;
if (!zalloc_cpumask_var(&vec->mask, gfp))
goto cleanup;
diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h
index 9a7e859b8fb..7cb5bb6b95b 100644
--- a/kernel/sched_cpupri.h
+++ b/kernel/sched_cpupri.h
@@ -12,7 +12,7 @@
/* values 2-101 are RT priorities 0-99 */
struct cpupri_vec {
- spinlock_t lock;
+ raw_spinlock_t lock;
int count;
cpumask_var_t mask;
};
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index efb84409bc4..67f95aada4b 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -184,7 +184,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
SPLIT_NS(cfs_rq->exec_clock));
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (cfs_rq->rb_leftmost)
MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
last = __pick_last_entity(cfs_rq);
@@ -192,7 +192,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
max_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
SPLIT_NS(MIN_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
@@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu)
#ifdef CONFIG_SCHEDSTATS
#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n);
P(yld_count);
P(sched_switch);
P(sched_count);
P(sched_goidle);
+#ifdef CONFIG_SMP
+ P64(avg_idle);
+#endif
P(ttwu_count);
P(ttwu_local);
@@ -305,6 +309,12 @@ static void print_cpu(struct seq_file *m, int cpu)
print_rq(m, rq, cpu);
}
+static const char *sched_tunable_scaling_names[] = {
+ "none",
+ "logaritmic",
+ "linear"
+};
+
static int sched_debug_show(struct seq_file *m, void *v)
{
u64 now = ktime_to_ns(ktime_get());
@@ -330,6 +340,10 @@ static int sched_debug_show(struct seq_file *m, void *v)
#undef PN
#undef P
+ SEQ_printf(m, " .%-40s: %d (%s)\n", "sysctl_sched_tunable_scaling",
+ sysctl_sched_tunable_scaling,
+ sched_tunable_scaling_names[sysctl_sched_tunable_scaling]);
+
for_each_online_cpu(cpu)
print_cpu(m, cpu);
@@ -395,7 +409,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
PN(se.sum_exec_runtime);
PN(se.avg_overlap);
PN(se.avg_wakeup);
- PN(se.avg_running);
nr_switches = p->nvcsw + p->nivcsw;
@@ -419,7 +432,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
P(se.nr_failed_migrations_running);
P(se.nr_failed_migrations_hot);
P(se.nr_forced_migrations);
- P(se.nr_forced2_migrations);
P(se.nr_wakeups);
P(se.nr_wakeups_sync);
P(se.nr_wakeups_migrate);
@@ -495,7 +507,6 @@ void proc_sched_set_task(struct task_struct *p)
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
- p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
p->se.nr_wakeups_migrate = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ecc637a0d59..5bedf6e3ebf 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -21,6 +21,7 @@
*/
#include <linux/latencytop.h>
+#include <linux/sched.h>
/*
* Targeted preemption latency for CPU-bound tasks:
@@ -35,12 +36,26 @@
* run vmstat and monitor the context-switches (cs) field)
*/
unsigned int sysctl_sched_latency = 5000000ULL;
+unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+
+/*
+ * The initial- and re-scaling of tunables is configurable
+ * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
+ *
+ * Options are:
+ * SCHED_TUNABLESCALING_NONE - unscaled, always *1
+ * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
+ * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
+ */
+enum sched_tunable_scaling sysctl_sched_tunable_scaling
+ = SCHED_TUNABLESCALING_LOG;
/*
* Minimal preemption granularity for CPU-bound tasks:
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_min_granularity = 1000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
/*
* is kept at sysctl_sched_latency / sysctl_sched_min_granularity
@@ -70,6 +85,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
@@ -383,11 +399,12 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
*/
#ifdef CONFIG_SCHED_DEBUG
-int sched_nr_latency_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+int sched_proc_update_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
@@ -395,6 +412,14 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
sysctl_sched_min_granularity);
+#define WRT_SYSCTL(name) \
+ (normalized_sysctl_##name = sysctl_##name / (factor))
+ WRT_SYSCTL(sched_min_granularity);
+ WRT_SYSCTL(sched_latency);
+ WRT_SYSCTL(sched_wakeup_granularity);
+ WRT_SYSCTL(sched_shares_ratelimit);
+#undef WRT_SYSCTL
+
return 0;
}
#endif
@@ -822,6 +847,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
* re-elected due to buddy favours.
*/
clear_buddies(cfs_rq, curr);
+ return;
+ }
+
+ /*
+ * Ensure that a task that missed wakeup preemption by a
+ * narrow margin doesn't have to wait for a full slice.
+ * This also mitigates buddy induced latencies under load.
+ */
+ if (!sched_feat(WAKEUP_PREEMPT))
+ return;
+
+ if (delta_exec < sysctl_sched_min_granularity)
+ return;
+
+ if (cfs_rq->nr_running > 1) {
+ struct sched_entity *se = __pick_next_entity(cfs_rq);
+ s64 delta = curr->vruntime - se->vruntime;
+
+ if (delta > ideal_runtime)
+ resched_task(rq_of(cfs_rq)->curr);
}
}
@@ -861,12 +906,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
- return cfs_rq->next;
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
- if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
- return cfs_rq->last;
+ /*
+ * Prefer last buddy, try to return the CPU to a preempted task.
+ */
+ if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+ se = cfs_rq->last;
+
+ clear_buddies(cfs_rq, se);
return se;
}
@@ -1319,6 +1370,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
}
/*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+ int cpu = smp_processor_id();
+ int prev_cpu = task_cpu(p);
+ int i;
+
+ /*
+ * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+ * test in select_task_rq_fair) and the prev_cpu is idle then that's
+ * always a better target than the current cpu.
+ */
+ if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+ return prev_cpu;
+
+ /*
+ * Otherwise, iterate the domain and find an elegible idle cpu.
+ */
+ for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+ if (!cpu_rq(i)->cfs.nr_running) {
+ target = i;
+ break;
+ }
+ }
+
+ return target;
+}
+
+/*
* sched_balance_self: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
* SD_BALANCE_EXEC.
@@ -1346,7 +1428,6 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
new_cpu = prev_cpu;
}
- rcu_read_lock();
for_each_domain(cpu, tmp) {
/*
* If power savings logic is enabled for a domain, see if we
@@ -1372,11 +1453,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
want_sd = 0;
}
- if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
- cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+ /*
+ * While iterating the domains looking for a spanning
+ * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+ * in cache sharing domains along the way.
+ */
+ if (want_affine) {
+ int target = -1;
- affine_sd = tmp;
- want_affine = 0;
+ /*
+ * If both cpu and prev_cpu are part of this domain,
+ * cpu is a valid SD_WAKE_AFFINE target.
+ */
+ if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+ target = cpu;
+
+ /*
+ * If there's an idle sibling in this domain, make that
+ * the wake_affine target instead of the current cpu.
+ */
+ if (tmp->flags & SD_PREFER_SIBLING)
+ target = select_idle_sibling(p, tmp, target);
+
+ if (target >= 0) {
+ if (tmp->flags & SD_WAKE_AFFINE) {
+ affine_sd = tmp;
+ want_affine = 0;
+ }
+ cpu = target;
+ }
}
if (!want_sd && !want_affine)
@@ -1403,10 +1508,8 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
update_shares(tmp);
}
- if (affine_sd && wake_affine(affine_sd, p, sync)) {
- new_cpu = cpu;
- goto out;
- }
+ if (affine_sd && wake_affine(affine_sd, p, sync))
+ return cpu;
while (sd) {
int load_idx = sd->forkexec_idx;
@@ -1447,8 +1550,6 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
/* while loop will break here if sd == NULL */
}
-out:
- rcu_read_unlock();
return new_cpu;
}
#endif /* CONFIG_SMP */
@@ -1568,13 +1669,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int sync = wake_flags & WF_SYNC;
+ int scale = cfs_rq->nr_running >= sched_nr_latency;
- update_curr(cfs_rq);
-
- if (unlikely(rt_prio(p->prio))) {
- resched_task(curr);
- return;
- }
+ if (unlikely(rt_prio(p->prio)))
+ goto preempt;
if (unlikely(p->sched_class != &fair_sched_class))
return;
@@ -1582,18 +1680,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (unlikely(se == pse))
return;
- /*
- * Only set the backward buddy when the current task is still on the
- * rq. This can happen when a wakeup gets interleaved with schedule on
- * the ->pre_schedule() or idle_balance() point, either of which can
- * drop the rq lock.
- *
- * Also, during early boot the idle thread is in the fair class, for
- * obvious reasons its a bad idea to schedule back to the idle thread.
- */
- if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
- set_last_buddy(se);
- if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+ if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
set_next_buddy(pse);
/*
@@ -1611,36 +1698,44 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
return;
/* Idle tasks are by definition preempted by everybody. */
- if (unlikely(curr->policy == SCHED_IDLE)) {
- resched_task(curr);
- return;
- }
+ if (unlikely(curr->policy == SCHED_IDLE))
+ goto preempt;
- if ((sched_feat(WAKEUP_SYNC) && sync) ||
- (sched_feat(WAKEUP_OVERLAP) &&
- (se->avg_overlap < sysctl_sched_migration_cost &&
- pse->avg_overlap < sysctl_sched_migration_cost))) {
- resched_task(curr);
- return;
- }
+ if (sched_feat(WAKEUP_SYNC) && sync)
+ goto preempt;
- if (sched_feat(WAKEUP_RUNNING)) {
- if (pse->avg_running < se->avg_running) {
- set_next_buddy(pse);
- resched_task(curr);
- return;
- }
- }
+ if (sched_feat(WAKEUP_OVERLAP) &&
+ se->avg_overlap < sysctl_sched_migration_cost &&
+ pse->avg_overlap < sysctl_sched_migration_cost)
+ goto preempt;
if (!sched_feat(WAKEUP_PREEMPT))
return;
+ update_curr(cfs_rq);
find_matching_se(&se, &pse);
-
BUG_ON(!pse);
-
if (wakeup_preempt_entity(se, pse) == 1)
- resched_task(curr);
+ goto preempt;
+
+ return;
+
+preempt:
+ resched_task(curr);
+ /*
+ * Only set the backward buddy when the current task is still
+ * on the rq. This can happen when a wakeup gets interleaved
+ * with schedule on the ->pre_schedule() or idle_balance()
+ * point, either of which can * drop the rq lock.
+ *
+ * Also, during early boot the idle thread is in the fair class,
+ * for obvious reasons its a bad idea to schedule back to it.
+ */
+ if (unlikely(!se->on_rq || curr == rq->idle))
+ return;
+
+ if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+ set_last_buddy(se);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1649,21 +1744,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
- if (unlikely(!cfs_rq->nr_running))
+ if (!cfs_rq->nr_running)
return NULL;
do {
se = pick_next_entity(cfs_rq);
- /*
- * If se was a buddy, clear it so that it will have to earn
- * the favour again.
- *
- * If se was not a buddy, clear the buddies because neither
- * was elegible to run, let them earn it again.
- *
- * IOW. unconditionally clear buddies.
- */
- __clear_buddies(cfs_rq, NULL);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
@@ -1830,6 +1915,17 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
return 0;
}
+
+static void rq_online_fair(struct rq *rq)
+{
+ update_sysctl();
+}
+
+static void rq_offline_fair(struct rq *rq)
+{
+ update_sysctl();
+}
+
#endif /* CONFIG_SMP */
/*
@@ -1847,28 +1943,30 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
}
/*
- * Share the fairness runtime between parent and child, thus the
- * total amount of pressure for CPU stays equal - new tasks
- * get a chance to run but frequent forkers are not allowed to
- * monopolize the CPU. Note: the parent runqueue is locked,
- * the child is not running yet.
+ * called on fork with the child task as argument from the parent's context
+ * - child not yet on the tasklist
+ * - preemption disabled
*/
-static void task_new_fair(struct rq *rq, struct task_struct *p)
+static void task_fork_fair(struct task_struct *p)
{
- struct cfs_rq *cfs_rq = task_cfs_rq(p);
+ struct cfs_rq *cfs_rq = task_cfs_rq(current);
struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
int this_cpu = smp_processor_id();
+ struct rq *rq = this_rq();
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
- sched_info_queued(p);
+ if (unlikely(task_cpu(p) != this_cpu))
+ __set_task_cpu(p, this_cpu);
update_curr(cfs_rq);
+
if (curr)
se->vruntime = curr->vruntime;
place_entity(cfs_rq, se, 1);
- /* 'curr' will be NULL if the child belongs to a different group */
- if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
- curr && entity_before(curr, se)) {
+ if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
@@ -1877,7 +1975,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
resched_task(rq->curr);
}
- enqueue_task_fair(rq, p, 0);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
@@ -1939,21 +2037,17 @@ static void moved_group_fair(struct task_struct *p)
}
#endif
-unsigned int get_rr_interval_fair(struct task_struct *task)
+unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
{
struct sched_entity *se = &task->se;
- unsigned long flags;
- struct rq *rq;
unsigned int rr_interval = 0;
/*
* Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
* idle runqueue:
*/
- rq = task_rq_lock(task, &flags);
if (rq->cfs.load.weight)
rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
- task_rq_unlock(rq, &flags);
return rr_interval;
}
@@ -1977,11 +2071,13 @@ static const struct sched_class fair_sched_class = {
.load_balance = load_balance_fair,
.move_one_task = move_one_task_fair,
+ .rq_online = rq_online_fair,
+ .rq_offline = rq_offline_fair,
#endif
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
- .task_new = task_new_fair,
+ .task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
.switched_to = switched_to_fair,
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 0d94083582c..d5059fd761d 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -54,11 +54,6 @@ SCHED_FEAT(WAKEUP_SYNC, 0)
SCHED_FEAT(WAKEUP_OVERLAP, 0)
/*
- * Wakeup preemption towards tasks that run short
- */
-SCHED_FEAT(WAKEUP_RUNNING, 0)
-
-/*
* Use the SYNC wakeup hint, pipes and the likes use this to indicate
* the remote end is likely to consume the data we just wrote, and
* therefore has cache benefit from being placed on the same cpu, see
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index b133a28fcde..5f93b570d38 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -34,10 +34,10 @@ static struct task_struct *pick_next_task_idle(struct rq *rq)
static void
dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
{
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
printk(KERN_ERR "bad: scheduling from the idle thread!\n");
dump_stack();
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
}
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
@@ -97,7 +97,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
check_preempt_curr(rq, p, 0);
}
-unsigned int get_rr_interval_idle(struct task_struct *task)
+unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
{
return 0;
}
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index a4d790cddb1..d2ea2828164 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -327,7 +327,7 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
weight = cpumask_weight(rd->span);
- spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
rt_period = ktime_to_ns(rt_b->rt_period);
for_each_cpu(i, rd->span) {
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
@@ -336,7 +336,7 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
if (iter == rt_rq)
continue;
- spin_lock(&iter->rt_runtime_lock);
+ raw_spin_lock(&iter->rt_runtime_lock);
/*
* Either all rqs have inf runtime and there's nothing to steal
* or __disable_runtime() below sets a specific rq to inf to
@@ -358,14 +358,14 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
rt_rq->rt_runtime += diff;
more = 1;
if (rt_rq->rt_runtime == rt_period) {
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
break;
}
}
next:
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
}
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
return more;
}
@@ -386,8 +386,8 @@ static void __disable_runtime(struct rq *rq)
s64 want;
int i;
- spin_lock(&rt_b->rt_runtime_lock);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
/*
* Either we're all inf and nobody needs to borrow, or we're
* already disabled and thus have nothing to do, or we have
@@ -396,7 +396,7 @@ static void __disable_runtime(struct rq *rq)
if (rt_rq->rt_runtime == RUNTIME_INF ||
rt_rq->rt_runtime == rt_b->rt_runtime)
goto balanced;
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
/*
* Calculate the difference between what we started out with
@@ -418,7 +418,7 @@ static void __disable_runtime(struct rq *rq)
if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
continue;
- spin_lock(&iter->rt_runtime_lock);
+ raw_spin_lock(&iter->rt_runtime_lock);
if (want > 0) {
diff = min_t(s64, iter->rt_runtime, want);
iter->rt_runtime -= diff;
@@ -427,13 +427,13 @@ static void __disable_runtime(struct rq *rq)
iter->rt_runtime -= want;
want -= want;
}
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
if (!want)
break;
}
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
/*
* We cannot be left wanting - that would mean some runtime
* leaked out of the system.
@@ -445,8 +445,8 @@ balanced:
* runtime - in which case borrowing doesn't make sense.
*/
rt_rq->rt_runtime = RUNTIME_INF;
- spin_unlock(&rt_rq->rt_runtime_lock);
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
}
@@ -454,9 +454,9 @@ static void disable_runtime(struct rq *rq)
{
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__disable_runtime(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static void __enable_runtime(struct rq *rq)
@@ -472,13 +472,13 @@ static void __enable_runtime(struct rq *rq)
for_each_leaf_rt_rq(rt_rq, rq) {
struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
- spin_lock(&rt_b->rt_runtime_lock);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = rt_b->rt_runtime;
rt_rq->rt_time = 0;
rt_rq->rt_throttled = 0;
- spin_unlock(&rt_rq->rt_runtime_lock);
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
}
@@ -486,9 +486,9 @@ static void enable_runtime(struct rq *rq)
{
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__enable_runtime(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static int balance_runtime(struct rt_rq *rt_rq)
@@ -496,9 +496,9 @@ static int balance_runtime(struct rt_rq *rt_rq)
int more = 0;
if (rt_rq->rt_time > rt_rq->rt_runtime) {
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
more = do_balance_runtime(rt_rq);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
}
return more;
@@ -524,11 +524,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
struct rq *rq = rq_of_rt_rq(rt_rq);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (rt_rq->rt_time) {
u64 runtime;
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
if (rt_rq->rt_throttled)
balance_runtime(rt_rq);
runtime = rt_rq->rt_runtime;
@@ -539,13 +539,13 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
}
if (rt_rq->rt_time || rt_rq->rt_nr_running)
idle = 0;
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
} else if (rt_rq->rt_nr_running)
idle = 0;
if (enqueue)
sched_rt_rq_enqueue(rt_rq);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
return idle;
@@ -624,11 +624,11 @@ static void update_curr_rt(struct rq *rq)
rt_rq = rt_rq_of_se(rt_se);
if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_time += delta_exec;
if (sched_rt_runtime_exceeded(rt_rq))
resched_task(curr);
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
}
}
@@ -1153,29 +1153,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
-static inline int pick_optimal_cpu(int this_cpu,
- const struct cpumask *mask)
-{
- int first;
-
- /* "this_cpu" is cheaper to preempt than a remote processor */
- if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
- return this_cpu;
-
- first = cpumask_first(mask);
- if (first < nr_cpu_ids)
- return first;
-
- return -1;
-}
-
static int find_lowest_rq(struct task_struct *task)
{
struct sched_domain *sd;
struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
- cpumask_var_t domain_mask;
if (task->rt.nr_cpus_allowed == 1)
return -1; /* No other targets possible */
@@ -1198,28 +1181,26 @@ static int find_lowest_rq(struct task_struct *task)
* Otherwise, we consult the sched_domains span maps to figure
* out which cpu is logically closest to our hot cache data.
*/
- if (this_cpu == cpu)
- this_cpu = -1; /* Skip this_cpu opt if the same */
-
- if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
- for_each_domain(cpu, sd) {
- if (sd->flags & SD_WAKE_AFFINE) {
- int best_cpu;
+ if (!cpumask_test_cpu(this_cpu, lowest_mask))
+ this_cpu = -1; /* Skip this_cpu opt if not among lowest */
- cpumask_and(domain_mask,
- sched_domain_span(sd),
- lowest_mask);
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+ int best_cpu;
- best_cpu = pick_optimal_cpu(this_cpu,
- domain_mask);
-
- if (best_cpu != -1) {
- free_cpumask_var(domain_mask);
- return best_cpu;
- }
- }
+ /*
+ * "this_cpu" is cheaper to preempt than a
+ * remote processor.
+ */
+ if (this_cpu != -1 &&
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+ return this_cpu;
+
+ best_cpu = cpumask_first_and(lowest_mask,
+ sched_domain_span(sd));
+ if (best_cpu < nr_cpu_ids)
+ return best_cpu;
}
- free_cpumask_var(domain_mask);
}
/*
@@ -1227,7 +1208,13 @@ static int find_lowest_rq(struct task_struct *task)
* just give the caller *something* to work with from the compatible
* locations.
*/
- return pick_optimal_cpu(this_cpu, lowest_mask);
+ if (this_cpu != -1)
+ return this_cpu;
+
+ cpu = cpumask_any(lowest_mask);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+ return -1;
}
/* Will lock the rq it finds */
@@ -1259,7 +1246,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
task_running(rq, task) ||
!task->se.on_rq)) {
- spin_unlock(&lowest_rq->lock);
+ raw_spin_unlock(&lowest_rq->lock);
lowest_rq = NULL;
break;
}
@@ -1734,7 +1721,7 @@ static void set_curr_task_rt(struct rq *rq)
dequeue_pushable_task(rq, p);
}
-unsigned int get_rr_interval_rt(struct task_struct *task)
+unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
/*
* Time slice is 0 for SCHED_FIFO tasks
diff --git a/kernel/signal.c b/kernel/signal.c
index 64c5deeaca5..1814e68e4de 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,12 +22,14 @@
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/signalfd.h>
+#include <linux/ratelimit.h>
#include <linux/tracehook.h>
#include <linux/capability.h>
#include <linux/freezer.h>
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
-#include <trace/events/sched.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/signal.h>
#include <asm/param.h>
#include <asm/uaccess.h>
@@ -41,6 +43,8 @@
static struct kmem_cache *sigqueue_cachep;
+int print_fatal_signals __read_mostly;
+
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
@@ -159,7 +163,7 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
{
unsigned long i, *s, *m, x;
int sig = 0;
-
+
s = pending->signal.sig;
m = mask->sig;
switch (_NSIG_WORDS) {
@@ -184,17 +188,31 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
sig = ffz(~x) + 1;
break;
}
-
+
return sig;
}
+static inline void print_dropped_signal(int sig)
+{
+ static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
+
+ if (!print_fatal_signals)
+ return;
+
+ if (!__ratelimit(&ratelimit_state))
+ return;
+
+ printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n",
+ current->comm, current->pid, sig);
+}
+
/*
* allocate a new signal queue record
* - this may be called without locks if and only if t == current, otherwise an
* appopriate lock must be held to stop the target task from exiting
*/
-static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
- int override_rlimit)
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
{
struct sigqueue *q = NULL;
struct user_struct *user;
@@ -207,10 +225,15 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
*/
user = get_uid(__task_cred(t)->user);
atomic_inc(&user->sigpending);
+
if (override_rlimit ||
atomic_read(&user->sigpending) <=
- t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur)
+ t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
q = kmem_cache_alloc(sigqueue_cachep, flags);
+ } else {
+ print_dropped_signal(sig);
+ }
+
if (unlikely(q == NULL)) {
atomic_dec(&user->sigpending);
free_uid(user);
@@ -400,7 +423,7 @@ still_pending:
*/
info->si_signo = sig;
info->si_errno = 0;
- info->si_code = 0;
+ info->si_code = SI_USER;
info->si_pid = 0;
info->si_uid = 0;
}
@@ -584,6 +607,17 @@ static int rm_from_queue(unsigned long mask, struct sigpending *s)
return 1;
}
+static inline int is_si_special(const struct siginfo *info)
+{
+ return info <= SEND_SIG_FORCED;
+}
+
+static inline bool si_fromuser(const struct siginfo *info)
+{
+ return info == SEND_SIG_NOINFO ||
+ (!is_si_special(info) && SI_FROMUSER(info));
+}
+
/*
* Bad permissions for sending the signal
* - the caller must hold at least the RCU read lock
@@ -598,7 +632,7 @@ static int check_kill_permission(int sig, struct siginfo *info,
if (!valid_signal(sig))
return -EINVAL;
- if (info != SEND_SIG_NOINFO && (is_si_special(info) || SI_FROMKERNEL(info)))
+ if (!si_fromuser(info))
return 0;
error = audit_signal_info(sig, t); /* Let audit system see the signal */
@@ -705,7 +739,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
if (why) {
/*
- * The first thread which returns from finish_stop()
+ * The first thread which returns from do_signal_stop()
* will take ->siglock, notice SIGNAL_CLD_MASK, and
* notify its parent. See get_signal_to_deliver().
*/
@@ -834,7 +868,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
struct sigqueue *q;
int override_rlimit;
- trace_sched_signal_send(sig, t);
+ trace_signal_generate(sig, info, t);
assert_spin_locked(&t->sighand->siglock);
@@ -869,7 +903,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
else
override_rlimit = 0;
- q = __sigqueue_alloc(t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
+ q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE,
override_rlimit);
if (q) {
list_add_tail(&q->list, &pending->list);
@@ -896,12 +930,21 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
break;
}
} else if (!is_si_special(info)) {
- if (sig >= SIGRTMIN && info->si_code != SI_USER)
- /*
- * Queue overflow, abort. We may abort if the signal was rt
- * and sent by user using something other than kill().
- */
+ if (sig >= SIGRTMIN && info->si_code != SI_USER) {
+ /*
+ * Queue overflow, abort. We may abort if the
+ * signal was rt and sent by user using something
+ * other than kill().
+ */
+ trace_signal_overflow_fail(sig, group, info);
return -EAGAIN;
+ } else {
+ /*
+ * This is a silent loss of information. We still
+ * send the signal, but the *info bits are lost.
+ */
+ trace_signal_lose_info(sig, group, info);
+ }
}
out_set:
@@ -917,16 +960,13 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
int from_ancestor_ns = 0;
#ifdef CONFIG_PID_NS
- if (!is_si_special(info) && SI_FROMUSER(info) &&
- task_pid_nr_ns(current, task_active_pid_ns(t)) <= 0)
- from_ancestor_ns = 1;
+ from_ancestor_ns = si_fromuser(info) &&
+ !task_pid_nr_ns(current, task_active_pid_ns(t));
#endif
return __send_signal(sig, info, t, group, from_ancestor_ns);
}
-int print_fatal_signals;
-
static void print_fatal_signal(struct pt_regs *regs, int signr)
{
printk("%s/%d: potentially unexpected fatal signal %d.\n",
@@ -971,6 +1011,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
return send_signal(sig, info, t, 0);
}
+int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+ bool group)
+{
+ unsigned long flags;
+ int ret = -ESRCH;
+
+ if (lock_task_sighand(p, &flags)) {
+ ret = send_signal(sig, info, p, group);
+ unlock_task_sighand(p, &flags);
+ }
+
+ return ret;
+}
+
/*
* Force a signal that the process can't ignore: if necessary
* we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1008,12 +1062,6 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
return ret;
}
-void
-force_sig_specific(int sig, struct task_struct *t)
-{
- force_sig_info(sig, SEND_SIG_FORCED, t);
-}
-
/*
* Nuke all other threads in the group.
*/
@@ -1036,12 +1084,6 @@ void zap_other_threads(struct task_struct *p)
}
}
-int __fatal_signal_pending(struct task_struct *tsk)
-{
- return sigismember(&tsk->pending.signal, SIGKILL);
-}
-EXPORT_SYMBOL(__fatal_signal_pending);
-
struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
{
struct sighand_struct *sighand;
@@ -1068,18 +1110,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
*/
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
- unsigned long flags;
- int ret;
-
- ret = check_kill_permission(sig, info, p);
+ int ret = check_kill_permission(sig, info, p);
- if (!ret && sig) {
- ret = -ESRCH;
- if (lock_task_sighand(p, &flags)) {
- ret = __group_send_sig_info(sig, info, p);
- unlock_task_sighand(p, &flags);
- }
- }
+ if (!ret && sig)
+ ret = do_send_sig_info(sig, info, p, true);
return ret;
}
@@ -1156,8 +1190,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
goto out_unlock;
}
pcred = __task_cred(p);
- if ((info == SEND_SIG_NOINFO ||
- (!is_si_special(info) && SI_FROMUSER(info))) &&
+ if (si_fromuser(info) &&
euid != pcred->suid && euid != pcred->uid &&
uid != pcred->suid && uid != pcred->uid) {
ret = -EPERM;
@@ -1224,15 +1257,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
* These are for backward compatibility with the rest of the kernel source.
*/
-/*
- * The caller must ensure the task can't exit.
- */
int
send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
- int ret;
- unsigned long flags;
-
/*
* Make sure legacy kernel users don't send in bad values
* (normal paths check this in check_kill_permission).
@@ -1240,10 +1267,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
if (!valid_signal(sig))
return -EINVAL;
- spin_lock_irqsave(&p->sighand->siglock, flags);
- ret = specific_send_sig_info(sig, info, p);
- spin_unlock_irqrestore(&p->sighand->siglock, flags);
- return ret;
+ return do_send_sig_info(sig, info, p, false);
}
#define __si_special(priv) \
@@ -1302,19 +1326,19 @@ EXPORT_SYMBOL(kill_pid);
* These functions support sending signals using preallocated sigqueue
* structures. This is needed "because realtime applications cannot
* afford to lose notifications of asynchronous events, like timer
- * expirations or I/O completions". In the case of Posix Timers
+ * expirations or I/O completions". In the case of Posix Timers
* we allocate the sigqueue structure from the timer_create. If this
* allocation fails we are able to report the failure to the application
* with an EAGAIN error.
*/
-
struct sigqueue *sigqueue_alloc(void)
{
- struct sigqueue *q;
+ struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
- if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0)))
+ if (q)
q->flags |= SIGQUEUE_PREALLOC;
- return(q);
+
+ return q;
}
void sigqueue_free(struct sigqueue *q)
@@ -1383,15 +1407,6 @@ ret:
}
/*
- * Wake up any threads in the parent blocked in wait* syscalls.
- */
-static inline void __wake_up_parent(struct task_struct *p,
- struct task_struct *parent)
-{
- wake_up_interruptible_sync(&parent->signal->wait_chldexit);
-}
-
-/*
* Let a parent know about the death of a child.
* For a stopped/continued status change, use do_notify_parent_cldstop instead.
*
@@ -1673,29 +1688,6 @@ void ptrace_notify(int exit_code)
spin_unlock_irq(&current->sighand->siglock);
}
-static void
-finish_stop(int stop_count)
-{
- /*
- * If there are no other threads in the group, or if there is
- * a group stop in progress and we are the last to stop,
- * report to the parent. When ptraced, every thread reports itself.
- */
- if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
- read_lock(&tasklist_lock);
- do_notify_parent_cldstop(current, CLD_STOPPED);
- read_unlock(&tasklist_lock);
- }
-
- do {
- schedule();
- } while (try_to_freeze());
- /*
- * Now we don't run again until continued.
- */
- current->exit_code = 0;
-}
-
/*
* This performs the stopping for SIGSTOP and other stop signals.
* We have to stop all threads in the thread group.
@@ -1705,15 +1697,9 @@ finish_stop(int stop_count)
static int do_signal_stop(int signr)
{
struct signal_struct *sig = current->signal;
- int stop_count;
+ int notify;
- if (sig->group_stop_count > 0) {
- /*
- * There is a group stop in progress. We don't need to
- * start another one.
- */
- stop_count = --sig->group_stop_count;
- } else {
+ if (!sig->group_stop_count) {
struct task_struct *t;
if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
@@ -1725,7 +1711,7 @@ static int do_signal_stop(int signr)
*/
sig->group_exit_code = signr;
- stop_count = 0;
+ sig->group_stop_count = 1;
for (t = next_thread(current); t != current; t = next_thread(t))
/*
* Setting state to TASK_STOPPED for a group
@@ -1734,19 +1720,44 @@ static int do_signal_stop(int signr)
*/
if (!(t->flags & PF_EXITING) &&
!task_is_stopped_or_traced(t)) {
- stop_count++;
+ sig->group_stop_count++;
signal_wake_up(t, 0);
}
- sig->group_stop_count = stop_count;
}
+ /*
+ * If there are no other threads in the group, or if there is
+ * a group stop in progress and we are the last to stop, report
+ * to the parent. When ptraced, every thread reports itself.
+ */
+ notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
+ notify = tracehook_notify_jctl(notify, CLD_STOPPED);
+ /*
+ * tracehook_notify_jctl() can drop and reacquire siglock, so
+ * we keep ->group_stop_count != 0 before the call. If SIGCONT
+ * or SIGKILL comes in between ->group_stop_count == 0.
+ */
+ if (sig->group_stop_count) {
+ if (!--sig->group_stop_count)
+ sig->flags = SIGNAL_STOP_STOPPED;
+ current->exit_code = sig->group_exit_code;
+ __set_current_state(TASK_STOPPED);
+ }
+ spin_unlock_irq(&current->sighand->siglock);
- if (stop_count == 0)
- sig->flags = SIGNAL_STOP_STOPPED;
- current->exit_code = sig->group_exit_code;
- __set_current_state(TASK_STOPPED);
+ if (notify) {
+ read_lock(&tasklist_lock);
+ do_notify_parent_cldstop(current, notify);
+ read_unlock(&tasklist_lock);
+ }
+
+ /* Now we don't run again until woken by SIGCONT or SIGKILL */
+ do {
+ schedule();
+ } while (try_to_freeze());
+
+ tracehook_finish_jctl();
+ current->exit_code = 0;
- spin_unlock_irq(&current->sighand->siglock);
- finish_stop(stop_count);
return 1;
}
@@ -1815,24 +1826,20 @@ relock:
int why = (signal->flags & SIGNAL_STOP_CONTINUED)
? CLD_CONTINUED : CLD_STOPPED;
signal->flags &= ~SIGNAL_CLD_MASK;
- spin_unlock_irq(&sighand->siglock);
- if (unlikely(!tracehook_notify_jctl(1, why)))
- goto relock;
+ why = tracehook_notify_jctl(why, CLD_CONTINUED);
+ spin_unlock_irq(&sighand->siglock);
- read_lock(&tasklist_lock);
- do_notify_parent_cldstop(current->group_leader, why);
- read_unlock(&tasklist_lock);
+ if (why) {
+ read_lock(&tasklist_lock);
+ do_notify_parent_cldstop(current->group_leader, why);
+ read_unlock(&tasklist_lock);
+ }
goto relock;
}
for (;;) {
struct k_sigaction *ka;
-
- if (unlikely(signal->group_stop_count > 0) &&
- do_signal_stop(0))
- goto relock;
-
/*
* Tracing can induce an artifical signal and choose sigaction.
* The return value in @signr determines the default action,
@@ -1844,6 +1851,10 @@ relock:
if (unlikely(signr != 0))
ka = return_ka;
else {
+ if (unlikely(signal->group_stop_count > 0) &&
+ do_signal_stop(0))
+ goto relock;
+
signr = dequeue_signal(current, &current->blocked,
info);
@@ -1860,6 +1871,9 @@ relock:
ka = &sighand->action[signr-1];
}
+ /* Trace actually delivered signals. */
+ trace_signal_deliver(signr, info, ka);
+
if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */
continue;
if (ka->sa.sa_handler != SIG_DFL) {
@@ -1987,14 +2001,14 @@ void exit_signals(struct task_struct *tsk)
if (unlikely(tsk->signal->group_stop_count) &&
!--tsk->signal->group_stop_count) {
tsk->signal->flags = SIGNAL_STOP_STOPPED;
- group_stop = 1;
+ group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
}
out:
spin_unlock_irq(&tsk->sighand->siglock);
- if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
+ if (unlikely(group_stop)) {
read_lock(&tasklist_lock);
- do_notify_parent_cldstop(tsk, CLD_STOPPED);
+ do_notify_parent_cldstop(tsk, group_stop);
read_unlock(&tasklist_lock);
}
}
@@ -2290,7 +2304,6 @@ static int
do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
{
struct task_struct *p;
- unsigned long flags;
int error = -ESRCH;
rcu_read_lock();
@@ -2300,14 +2313,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
/*
* The null signal is a permissions and process existence
* probe. No signal is actually delivered.
- *
- * If lock_task_sighand() fails we pretend the task dies
- * after receiving the signal. The window is tiny, and the
- * signal is private anyway.
*/
- if (!error && sig && lock_task_sighand(p, &flags)) {
- error = specific_send_sig_info(sig, info, p);
- unlock_task_sighand(p, &flags);
+ if (!error && sig) {
+ error = do_send_sig_info(sig, info, p, false);
+ /*
+ * If lock_task_sighand() failed we pretend the task
+ * dies after receiving the signal. The window is tiny,
+ * and the signal is private anyway.
+ */
+ if (unlikely(error == -ESRCH))
+ error = 0;
}
}
rcu_read_unlock();
diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c
new file mode 100644
index 00000000000..e45c4364529
--- /dev/null
+++ b/kernel/slow-work-debugfs.c
@@ -0,0 +1,227 @@
+/* Slow work debugging
+ *
+ * Copyright (C) 2009 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/module.h>
+#include <linux/slow-work.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include "slow-work.h"
+
+#define ITERATOR_SHIFT (BITS_PER_LONG - 4)
+#define ITERATOR_SELECTOR (0xfUL << ITERATOR_SHIFT)
+#define ITERATOR_COUNTER (~ITERATOR_SELECTOR)
+
+void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m)
+{
+ seq_puts(m, "Slow-work: New thread");
+}
+
+/*
+ * Render the time mark field on a work item into a 5-char time with units plus
+ * a space
+ */
+static void slow_work_print_mark(struct seq_file *m, struct slow_work *work)
+{
+ struct timespec now, diff;
+
+ now = CURRENT_TIME;
+ diff = timespec_sub(now, work->mark);
+
+ if (diff.tv_sec < 0)
+ seq_puts(m, " -ve ");
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000)
+ seq_printf(m, "%3luns ", diff.tv_nsec);
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000)
+ seq_printf(m, "%3luus ", diff.tv_nsec / 1000);
+ else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000)
+ seq_printf(m, "%3lums ", diff.tv_nsec / 1000000);
+ else if (diff.tv_sec <= 1)
+ seq_puts(m, " 1s ");
+ else if (diff.tv_sec < 60)
+ seq_printf(m, "%4lus ", diff.tv_sec);
+ else if (diff.tv_sec < 60 * 60)
+ seq_printf(m, "%4lum ", diff.tv_sec / 60);
+ else if (diff.tv_sec < 60 * 60 * 24)
+ seq_printf(m, "%4luh ", diff.tv_sec / 3600);
+ else
+ seq_puts(m, "exces ");
+}
+
+/*
+ * Describe a slow work item for debugfs
+ */
+static int slow_work_runqueue_show(struct seq_file *m, void *v)
+{
+ struct slow_work *work;
+ struct list_head *p = v;
+ unsigned long id;
+
+ switch ((unsigned long) v) {
+ case 1:
+ seq_puts(m, "THR PID ITEM ADDR FL MARK DESC\n");
+ return 0;
+ case 2:
+ seq_puts(m, "=== ===== ================ == ===== ==========\n");
+ return 0;
+
+ case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1:
+ id = (unsigned long) v - 3;
+
+ read_lock(&slow_work_execs_lock);
+ work = slow_work_execs[id];
+ if (work) {
+ smp_read_barrier_depends();
+
+ seq_printf(m, "%3lu %5d %16p %2lx ",
+ id, slow_work_pids[id], work, work->flags);
+ slow_work_print_mark(m, work);
+
+ if (work->ops->desc)
+ work->ops->desc(work, m);
+ seq_putc(m, '\n');
+ }
+ read_unlock(&slow_work_execs_lock);
+ return 0;
+
+ default:
+ work = list_entry(p, struct slow_work, link);
+ seq_printf(m, "%3s - %16p %2lx ",
+ work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq",
+ work, work->flags);
+ slow_work_print_mark(m, work);
+
+ if (work->ops->desc)
+ work->ops->desc(work, m);
+ seq_putc(m, '\n');
+ return 0;
+ }
+}
+
+/*
+ * map the iterator to a work item
+ */
+static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos)
+{
+ struct list_head *p;
+ unsigned long count, id;
+
+ switch (*_pos >> ITERATOR_SHIFT) {
+ case 0x0:
+ if (*_pos == 0)
+ *_pos = 1;
+ if (*_pos < 3)
+ return (void *)(unsigned long) *_pos;
+ if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT)
+ for (id = *_pos - 3;
+ id < SLOW_WORK_THREAD_LIMIT;
+ id++, (*_pos)++)
+ if (slow_work_execs[id])
+ return (void *)(unsigned long) *_pos;
+ *_pos = 0x1UL << ITERATOR_SHIFT;
+
+ case 0x1:
+ count = *_pos & ITERATOR_COUNTER;
+ list_for_each(p, &slow_work_queue) {
+ if (count == 0)
+ return p;
+ count--;
+ }
+ *_pos = 0x2UL << ITERATOR_SHIFT;
+
+ case 0x2:
+ count = *_pos & ITERATOR_COUNTER;
+ list_for_each(p, &vslow_work_queue) {
+ if (count == 0)
+ return p;
+ count--;
+ }
+ *_pos = 0x3UL << ITERATOR_SHIFT;
+
+ default:
+ return NULL;
+ }
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos)
+{
+ spin_lock_irq(&slow_work_queue_lock);
+ return slow_work_runqueue_index(m, _pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+ struct list_head *p = v;
+ unsigned long selector = *_pos >> ITERATOR_SHIFT;
+
+ (*_pos)++;
+ switch (selector) {
+ case 0x0:
+ return slow_work_runqueue_index(m, _pos);
+
+ case 0x1:
+ if (*_pos >> ITERATOR_SHIFT == 0x1) {
+ p = p->next;
+ if (p != &slow_work_queue)
+ return p;
+ }
+ *_pos = 0x2UL << ITERATOR_SHIFT;
+ p = &vslow_work_queue;
+
+ case 0x2:
+ if (*_pos >> ITERATOR_SHIFT == 0x2) {
+ p = p->next;
+ if (p != &vslow_work_queue)
+ return p;
+ }
+ *_pos = 0x3UL << ITERATOR_SHIFT;
+
+ default:
+ return NULL;
+ }
+}
+
+/*
+ * clean up after reading
+ */
+static void slow_work_runqueue_stop(struct seq_file *m, void *v)
+{
+ spin_unlock_irq(&slow_work_queue_lock);
+}
+
+static const struct seq_operations slow_work_runqueue_ops = {
+ .start = slow_work_runqueue_start,
+ .stop = slow_work_runqueue_stop,
+ .next = slow_work_runqueue_next,
+ .show = slow_work_runqueue_show,
+};
+
+/*
+ * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents
+ */
+static int slow_work_runqueue_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &slow_work_runqueue_ops);
+}
+
+const struct file_operations slow_work_runqueue_fops = {
+ .owner = THIS_MODULE,
+ .open = slow_work_runqueue_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 09d7519557d..7494bbf5a27 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -16,20 +16,17 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/wait.h>
-
-#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of
- * things to do */
-#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after
- * OOM */
+#include <linux/debugfs.h>
+#include "slow-work.h"
static void slow_work_cull_timeout(unsigned long);
static void slow_work_oom_timeout(unsigned long);
#ifdef CONFIG_SYSCTL
-static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+static int slow_work_min_threads_sysctl(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
-static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+static int slow_work_max_threads_sysctl(struct ctl_table *, int ,
void __user *, size_t *, loff_t *);
#endif
@@ -46,13 +43,12 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process
#ifdef CONFIG_SYSCTL
static const int slow_work_min_min_threads = 2;
-static int slow_work_max_max_threads = 255;
+static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT;
static const int slow_work_min_vslow = 1;
static const int slow_work_max_vslow = 99;
ctl_table slow_work_sysctls[] = {
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "min-threads",
.data = &slow_work_min_threads,
.maxlen = sizeof(unsigned),
@@ -62,7 +58,6 @@ ctl_table slow_work_sysctls[] = {
.extra2 = &slow_work_max_threads,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "max-threads",
.data = &slow_work_max_threads,
.maxlen = sizeof(unsigned),
@@ -72,16 +67,15 @@ ctl_table slow_work_sysctls[] = {
.extra2 = (void *) &slow_work_max_max_threads,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "vslow-percentage",
.data = &vslow_work_proportion,
.maxlen = sizeof(unsigned),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = (void *) &slow_work_min_vslow,
.extra2 = (void *) &slow_work_max_vslow,
},
- { .ctl_name = 0 }
+ {}
};
#endif
@@ -98,6 +92,56 @@ static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
static struct slow_work slow_work_new_thread; /* new thread starter */
/*
+ * slow work ID allocation (use slow_work_queue_lock)
+ */
+static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+
+/*
+ * Unregistration tracking to prevent put_ref() from disappearing during module
+ * unload
+ */
+#ifdef CONFIG_MODULES
+static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT];
+static struct module *slow_work_unreg_module;
+static struct slow_work *slow_work_unreg_work_item;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq);
+static DEFINE_MUTEX(slow_work_unreg_sync_lock);
+
+static void slow_work_set_thread_processing(int id, struct slow_work *work)
+{
+ if (work)
+ slow_work_thread_processing[id] = work->owner;
+}
+static void slow_work_done_thread_processing(int id, struct slow_work *work)
+{
+ struct module *module = slow_work_thread_processing[id];
+
+ slow_work_thread_processing[id] = NULL;
+ smp_mb();
+ if (slow_work_unreg_work_item == work ||
+ slow_work_unreg_module == module)
+ wake_up_all(&slow_work_unreg_wq);
+}
+static void slow_work_clear_thread_processing(int id)
+{
+ slow_work_thread_processing[id] = NULL;
+}
+#else
+static void slow_work_set_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_done_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_clear_thread_processing(int id) {}
+#endif
+
+/*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT];
+pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT];
+DEFINE_RWLOCK(slow_work_execs_lock);
+#endif
+
+/*
* The queues of work items and the lock governing access to them. These are
* shared between all the CPUs. It doesn't make sense to have per-CPU queues
* as the number of threads bears no relation to the number of CPUs.
@@ -105,9 +149,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */
* There are two queues of work items: one for slow work items, and one for
* very slow work items.
*/
-static LIST_HEAD(slow_work_queue);
-static LIST_HEAD(vslow_work_queue);
-static DEFINE_SPINLOCK(slow_work_queue_lock);
+LIST_HEAD(slow_work_queue);
+LIST_HEAD(vslow_work_queue);
+DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The following are two wait queues that get pinged when a work item is placed
+ * on an empty queue. These allow work items that are hogging a thread by
+ * sleeping in a way that could be deferred to yield their thread and enqueue
+ * themselves.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation);
+static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation);
/*
* The thread controls. A variable used to signal to the threads that they
@@ -126,6 +179,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited);
static int slow_work_user_count;
static DEFINE_MUTEX(slow_work_user_lock);
+static inline int slow_work_get_ref(struct slow_work *work)
+{
+ if (work->ops->get_ref)
+ return work->ops->get_ref(work);
+
+ return 0;
+}
+
+static inline void slow_work_put_ref(struct slow_work *work)
+{
+ if (work->ops->put_ref)
+ work->ops->put_ref(work);
+}
+
/*
* Calculate the maximum number of active threads in the pool that are
* permitted to process very slow work items.
@@ -149,7 +216,7 @@ static unsigned slow_work_calc_vsmax(void)
* Attempt to execute stuff queued on a slow thread. Return true if we managed
* it, false if there was nothing to do.
*/
-static bool slow_work_execute(void)
+static noinline bool slow_work_execute(int id)
{
struct slow_work *work = NULL;
unsigned vsmax;
@@ -186,6 +253,13 @@ static bool slow_work_execute(void)
} else {
very_slow = false; /* avoid the compiler warning */
}
+
+ slow_work_set_thread_processing(id, work);
+ if (work) {
+ slow_work_mark_time(work);
+ slow_work_begin_exec(id, work);
+ }
+
spin_unlock_irq(&slow_work_queue_lock);
if (!work)
@@ -194,12 +268,19 @@ static bool slow_work_execute(void)
if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
BUG();
- work->ops->execute(work);
+ /* don't execute if the work is in the process of being cancelled */
+ if (!test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ work->ops->execute(work);
if (very_slow)
atomic_dec(&vslow_work_executing_count);
clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
+ /* wake up anyone waiting for this work to be complete */
+ wake_up_bit(&work->flags, SLOW_WORK_EXECUTING);
+
+ slow_work_end_exec(id, work);
+
/* if someone tried to enqueue the item whilst we were executing it,
* then it'll be left unenqueued to avoid multiple threads trying to
* execute it simultaneously
@@ -219,7 +300,10 @@ static bool slow_work_execute(void)
spin_unlock_irq(&slow_work_queue_lock);
}
- work->ops->put_ref(work);
+ /* sort out the race between module unloading and put_ref() */
+ slow_work_put_ref(work);
+ slow_work_done_thread_processing(id, work);
+
return true;
auto_requeue:
@@ -227,15 +311,61 @@ auto_requeue:
* - we transfer our ref on the item back to the appropriate queue
* - don't wake another thread up as we're awake already
*/
+ slow_work_mark_time(work);
if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
list_add_tail(&work->link, &vslow_work_queue);
else
list_add_tail(&work->link, &slow_work_queue);
spin_unlock_irq(&slow_work_queue_lock);
+ slow_work_clear_thread_processing(id);
return true;
}
/**
+ * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work
+ * work: The work item under execution that wants to sleep
+ * _timeout: Scheduler sleep timeout
+ *
+ * Allow a requeueable work item to sleep on a slow-work processor thread until
+ * that thread is needed to do some other work or the sleep is interrupted by
+ * some other event.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * False is returned if there is nothing on the queue; true is returned if the
+ * work item should be requeued
+ */
+bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+ signed long *_timeout)
+{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
+
+ DEFINE_WAIT(wait);
+
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
+ if (!list_empty(queue))
+ return true;
+
+ add_wait_queue_exclusive(wfo_wq, &wait);
+ if (list_empty(queue))
+ *_timeout = schedule_timeout(*_timeout);
+ finish_wait(wfo_wq, &wait);
+
+ return !list_empty(queue);
+}
+EXPORT_SYMBOL(slow_work_sleep_till_thread_needed);
+
+/**
* slow_work_enqueue - Schedule a slow work item for processing
* @work: The work item to queue
*
@@ -260,16 +390,22 @@ auto_requeue:
* allowed to pick items to execute. This ensures that very slow items won't
* overly block ones that are just ordinarily slow.
*
- * Returns 0 if successful, -EAGAIN if not.
+ * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is
+ * attempted queued)
*/
int slow_work_enqueue(struct slow_work *work)
{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
unsigned long flags;
+ int ret;
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ return -ECANCELED;
BUG_ON(slow_work_user_count <= 0);
BUG_ON(!work);
BUG_ON(!work->ops);
- BUG_ON(!work->ops->get_ref);
/* when honouring an enqueue request, we only promise that we will run
* the work function in the future; we do not promise to run it once
@@ -280,8 +416,19 @@ int slow_work_enqueue(struct slow_work *work)
* maintaining our promise
*/
if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
spin_lock_irqsave(&slow_work_queue_lock, flags);
+ if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags)))
+ goto cancelled;
+
/* we promise that we will not attempt to execute the work
* function in more than one thread simultaneously
*
@@ -299,25 +446,221 @@ int slow_work_enqueue(struct slow_work *work)
if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
} else {
- if (work->ops->get_ref(work) < 0)
- goto cant_get_ref;
- if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
- list_add_tail(&work->link, &vslow_work_queue);
- else
- list_add_tail(&work->link, &slow_work_queue);
+ ret = slow_work_get_ref(work);
+ if (ret < 0)
+ goto failed;
+ slow_work_mark_time(work);
+ list_add_tail(&work->link, queue);
wake_up(&slow_work_thread_wq);
+
+ /* if someone who could be requeued is sleeping on a
+ * thread, then ask them to yield their thread */
+ if (work->link.prev == queue)
+ wake_up(wfo_wq);
}
spin_unlock_irqrestore(&slow_work_queue_lock, flags);
}
return 0;
-cant_get_ref:
+cancelled:
+ ret = -ECANCELED;
+failed:
spin_unlock_irqrestore(&slow_work_queue_lock, flags);
- return -EAGAIN;
+ return ret;
}
EXPORT_SYMBOL(slow_work_enqueue);
+static int slow_work_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
+/**
+ * slow_work_cancel - Cancel a slow work item
+ * @work: The work item to cancel
+ *
+ * This function will cancel a previously enqueued work item. If we cannot
+ * cancel the work item, it is guarenteed to have run when this function
+ * returns.
+ */
+void slow_work_cancel(struct slow_work *work)
+{
+ bool wait = true, put = false;
+
+ set_bit(SLOW_WORK_CANCELLING, &work->flags);
+ smp_mb();
+
+ /* if the work item is a delayed work item with an active timer, we
+ * need to wait for the timer to finish _before_ getting the spinlock,
+ * lest we deadlock against the timer routine
+ *
+ * the timer routine will leave DELAYED set if it notices the
+ * CANCELLING flag in time
+ */
+ if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+ struct delayed_slow_work *dwork =
+ container_of(work, struct delayed_slow_work, work);
+ del_timer_sync(&dwork->timer);
+ }
+
+ spin_lock_irq(&slow_work_queue_lock);
+
+ if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+ /* the timer routine aborted or never happened, so we are left
+ * holding the timer's reference on the item and should just
+ * drop the pending flag and wait for any ongoing execution to
+ * finish */
+ struct delayed_slow_work *dwork =
+ container_of(work, struct delayed_slow_work, work);
+
+ BUG_ON(timer_pending(&dwork->timer));
+ BUG_ON(!list_empty(&work->link));
+
+ clear_bit(SLOW_WORK_DELAYED, &work->flags);
+ put = true;
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+ } else if (test_bit(SLOW_WORK_PENDING, &work->flags) &&
+ !list_empty(&work->link)) {
+ /* the link in the pending queue holds a reference on the item
+ * that we will need to release */
+ list_del_init(&work->link);
+ wait = false;
+ put = true;
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+ } else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) {
+ /* the executor is holding our only reference on the item, so
+ * we merely need to wait for it to finish executing */
+ clear_bit(SLOW_WORK_PENDING, &work->flags);
+ }
+
+ spin_unlock_irq(&slow_work_queue_lock);
+
+ /* the EXECUTING flag is set by the executor whilst the spinlock is set
+ * and before the item is dequeued - so assuming the above doesn't
+ * actually dequeue it, simply waiting for the EXECUTING flag to be
+ * released here should be sufficient */
+ if (wait)
+ wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait,
+ TASK_UNINTERRUPTIBLE);
+
+ clear_bit(SLOW_WORK_CANCELLING, &work->flags);
+ if (put)
+ slow_work_put_ref(work);
+}
+EXPORT_SYMBOL(slow_work_cancel);
+
+/*
+ * Handle expiry of the delay timer, indicating that a delayed slow work item
+ * should now be queued if not cancelled
+ */
+static void delayed_slow_work_timer(unsigned long data)
+{
+ wait_queue_head_t *wfo_wq;
+ struct list_head *queue;
+ struct slow_work *work = (struct slow_work *) data;
+ unsigned long flags;
+ bool queued = false, put = false, first = false;
+
+ if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+ wfo_wq = &vslow_work_queue_waits_for_occupation;
+ queue = &vslow_work_queue;
+ } else {
+ wfo_wq = &slow_work_queue_waits_for_occupation;
+ queue = &slow_work_queue;
+ }
+
+ spin_lock_irqsave(&slow_work_queue_lock, flags);
+ if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) {
+ clear_bit(SLOW_WORK_DELAYED, &work->flags);
+
+ if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+ /* we discard the reference the timer was holding in
+ * favour of the one the executor holds */
+ set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+ put = true;
+ } else {
+ slow_work_mark_time(work);
+ list_add_tail(&work->link, queue);
+ queued = true;
+ if (work->link.prev == queue)
+ first = true;
+ }
+ }
+
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ if (put)
+ slow_work_put_ref(work);
+ if (first)
+ wake_up(wfo_wq);
+ if (queued)
+ wake_up(&slow_work_thread_wq);
+}
+
+/**
+ * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing
+ * @dwork: The delayed work item to queue
+ * @delay: When to start executing the work, in jiffies from now
+ *
+ * This is similar to slow_work_enqueue(), but it adds a delay before the work
+ * is actually queued for processing.
+ *
+ * The item can have delayed processing requested on it whilst it is being
+ * executed. The delay will begin immediately, and if it expires before the
+ * item finishes executing, the item will be placed back on the queue when it
+ * has done executing.
+ */
+int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+ unsigned long delay)
+{
+ struct slow_work *work = &dwork->work;
+ unsigned long flags;
+ int ret;
+
+ if (delay == 0)
+ return slow_work_enqueue(&dwork->work);
+
+ BUG_ON(slow_work_user_count <= 0);
+ BUG_ON(!work);
+ BUG_ON(!work->ops);
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ return -ECANCELED;
+
+ if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+ spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+ if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+ goto cancelled;
+
+ /* the timer holds a reference whilst it is pending */
+ ret = work->ops->get_ref(work);
+ if (ret < 0)
+ goto cant_get_ref;
+
+ if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags))
+ BUG();
+ dwork->timer.expires = jiffies + delay;
+ dwork->timer.data = (unsigned long) work;
+ dwork->timer.function = delayed_slow_work_timer;
+ add_timer(&dwork->timer);
+
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ }
+
+ return 0;
+
+cancelled:
+ ret = -ECANCELED;
+cant_get_ref:
+ spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL(delayed_slow_work_enqueue);
+
/*
* Schedule a cull of the thread pool at some time in the near future
*/
@@ -368,13 +711,23 @@ static inline bool slow_work_available(int vsmax)
*/
static int slow_work_thread(void *_data)
{
- int vsmax;
+ int vsmax, id;
DEFINE_WAIT(wait);
set_freezable();
set_user_nice(current, -5);
+ /* allocate ourselves an ID */
+ spin_lock_irq(&slow_work_queue_lock);
+ id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+ BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT);
+ __set_bit(id, slow_work_ids);
+ slow_work_set_thread_pid(id, current->pid);
+ spin_unlock_irq(&slow_work_queue_lock);
+
+ sprintf(current->comm, "kslowd%03u", id);
+
for (;;) {
vsmax = vslow_work_proportion;
vsmax *= atomic_read(&slow_work_thread_count);
@@ -395,7 +748,7 @@ static int slow_work_thread(void *_data)
vsmax *= atomic_read(&slow_work_thread_count);
vsmax /= 100;
- if (slow_work_available(vsmax) && slow_work_execute()) {
+ if (slow_work_available(vsmax) && slow_work_execute(id)) {
cond_resched();
if (list_empty(&slow_work_queue) &&
list_empty(&vslow_work_queue) &&
@@ -412,6 +765,11 @@ static int slow_work_thread(void *_data)
break;
}
+ spin_lock_irq(&slow_work_queue_lock);
+ slow_work_set_thread_pid(id, 0);
+ __clear_bit(id, slow_work_ids);
+ spin_unlock_irq(&slow_work_queue_lock);
+
if (atomic_dec_and_test(&slow_work_thread_count))
complete_and_exit(&slow_work_last_thread_exited, 0);
return 0;
@@ -427,21 +785,6 @@ static void slow_work_cull_timeout(unsigned long data)
}
/*
- * Get a reference on slow work thread starter
- */
-static int slow_work_new_thread_get_ref(struct slow_work *work)
-{
- return 0;
-}
-
-/*
- * Drop a reference on slow work thread starter
- */
-static void slow_work_new_thread_put_ref(struct slow_work *work)
-{
-}
-
-/*
* Start a new slow work thread
*/
static void slow_work_new_thread_execute(struct slow_work *work)
@@ -475,9 +818,11 @@ static void slow_work_new_thread_execute(struct slow_work *work)
}
static const struct slow_work_ops slow_work_new_thread_ops = {
- .get_ref = slow_work_new_thread_get_ref,
- .put_ref = slow_work_new_thread_put_ref,
+ .owner = THIS_MODULE,
.execute = slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_DEBUG
+ .desc = slow_work_new_thread_desc,
+#endif
};
/*
@@ -493,10 +838,10 @@ static void slow_work_oom_timeout(unsigned long data)
* Handle adjustment of the minimum number of threads
*/
static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
int n;
if (ret == 0) {
@@ -521,10 +866,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
* Handle adjustment of the maximum number of threads
*/
static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
int n;
if (ret == 0) {
@@ -546,12 +891,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
/**
* slow_work_register_user - Register a user of the facility
+ * @module: The module about to make use of the facility
*
* Register a user of the facility, starting up the initial threads if there
* aren't any other users at this point. This will return 0 if successful, or
* an error if not.
*/
-int slow_work_register_user(void)
+int slow_work_register_user(struct module *module)
{
struct task_struct *p;
int loop;
@@ -598,14 +944,81 @@ error:
}
EXPORT_SYMBOL(slow_work_register_user);
+/*
+ * wait for all outstanding items from the calling module to complete
+ * - note that more items may be queued whilst we're waiting
+ */
+static void slow_work_wait_for_items(struct module *module)
+{
+#ifdef CONFIG_MODULES
+ DECLARE_WAITQUEUE(myself, current);
+ struct slow_work *work;
+ int loop;
+
+ mutex_lock(&slow_work_unreg_sync_lock);
+ add_wait_queue(&slow_work_unreg_wq, &myself);
+
+ for (;;) {
+ spin_lock_irq(&slow_work_queue_lock);
+
+ /* first of all, we wait for the last queued item in each list
+ * to be processed */
+ list_for_each_entry_reverse(work, &vslow_work_queue, link) {
+ if (work->owner == module) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ slow_work_unreg_work_item = work;
+ goto do_wait;
+ }
+ }
+ list_for_each_entry_reverse(work, &slow_work_queue, link) {
+ if (work->owner == module) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ slow_work_unreg_work_item = work;
+ goto do_wait;
+ }
+ }
+
+ /* then we wait for the items being processed to finish */
+ slow_work_unreg_module = module;
+ smp_mb();
+ for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) {
+ if (slow_work_thread_processing[loop] == module)
+ goto do_wait;
+ }
+ spin_unlock_irq(&slow_work_queue_lock);
+ break; /* okay, we're done */
+
+ do_wait:
+ spin_unlock_irq(&slow_work_queue_lock);
+ schedule();
+ slow_work_unreg_work_item = NULL;
+ slow_work_unreg_module = NULL;
+ }
+
+ remove_wait_queue(&slow_work_unreg_wq, &myself);
+ mutex_unlock(&slow_work_unreg_sync_lock);
+#endif /* CONFIG_MODULES */
+}
+
/**
* slow_work_unregister_user - Unregister a user of the facility
+ * @module: The module whose items should be cleared
*
* Unregister a user of the facility, killing all the threads if this was the
* last one.
+ *
+ * This waits for all the work items belonging to the nominated module to go
+ * away before proceeding.
*/
-void slow_work_unregister_user(void)
+void slow_work_unregister_user(struct module *module)
{
+ /* first of all, wait for all outstanding items from the calling module
+ * to complete */
+ if (module)
+ slow_work_wait_for_items(module);
+
+ /* then we can actually go about shutting down the facility if need
+ * be */
mutex_lock(&slow_work_user_lock);
BUG_ON(slow_work_user_count <= 0);
@@ -639,6 +1052,16 @@ static int __init init_slow_work(void)
if (slow_work_max_max_threads < nr_cpus * 2)
slow_work_max_max_threads = nr_cpus * 2;
#endif
+#ifdef CONFIG_SLOW_WORK_DEBUG
+ {
+ struct dentry *dbdir;
+
+ dbdir = debugfs_create_dir("slow_work", NULL);
+ if (dbdir && !IS_ERR(dbdir))
+ debugfs_create_file("runqueue", S_IFREG | 0400, dbdir,
+ NULL, &slow_work_runqueue_fops);
+ }
+#endif
return 0;
}
diff --git a/kernel/slow-work.h b/kernel/slow-work.h
new file mode 100644
index 00000000000..321f3c59d73
--- /dev/null
+++ b/kernel/slow-work.h
@@ -0,0 +1,72 @@
+/* Slow work private definitions
+ *
+ * Copyright (C) 2009 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.
+ */
+
+#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of
+ * things to do */
+#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after
+ * OOM */
+
+#define SLOW_WORK_THREAD_LIMIT 255 /* abs maximum number of slow-work threads */
+
+/*
+ * slow-work.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern struct slow_work *slow_work_execs[];
+extern pid_t slow_work_pids[];
+extern rwlock_t slow_work_execs_lock;
+#endif
+
+extern struct list_head slow_work_queue;
+extern struct list_head vslow_work_queue;
+extern spinlock_t slow_work_queue_lock;
+
+/*
+ * slow-work-debugfs.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern const struct file_operations slow_work_runqueue_fops;
+
+extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
+#endif
+
+/*
+ * Helper functions
+ */
+static inline void slow_work_set_thread_pid(int id, pid_t pid)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ slow_work_pids[id] = pid;
+#endif
+}
+
+static inline void slow_work_mark_time(struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ work->mark = CURRENT_TIME;
+#endif
+}
+
+static inline void slow_work_begin_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ slow_work_execs[id] = work;
+#endif
+}
+
+static inline void slow_work_end_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+ write_lock(&slow_work_execs_lock);
+ slow_work_execs[id] = NULL;
+ write_unlock(&slow_work_execs_lock);
+#endif
+}
diff --git a/kernel/smp.c b/kernel/smp.c
index fd47a256a24..de735a6637d 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -16,11 +16,11 @@ static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
static struct {
struct list_head queue;
- spinlock_t lock;
+ raw_spinlock_t lock;
} call_function __cacheline_aligned_in_smp =
{
.queue = LIST_HEAD_INIT(call_function.queue),
- .lock = __SPIN_LOCK_UNLOCKED(call_function.lock),
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(call_function.lock),
};
enum {
@@ -35,7 +35,7 @@ struct call_function_data {
struct call_single_queue {
struct list_head list;
- spinlock_t lock;
+ raw_spinlock_t lock;
};
static DEFINE_PER_CPU(struct call_function_data, cfd_data);
@@ -80,7 +80,7 @@ static int __cpuinit init_call_single_data(void)
for_each_possible_cpu(i) {
struct call_single_queue *q = &per_cpu(call_single_queue, i);
- spin_lock_init(&q->lock);
+ raw_spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->list);
}
@@ -141,10 +141,10 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait)
unsigned long flags;
int ipi;
- spin_lock_irqsave(&dst->lock, flags);
+ raw_spin_lock_irqsave(&dst->lock, flags);
ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
- spin_unlock_irqrestore(&dst->lock, flags);
+ raw_spin_unlock_irqrestore(&dst->lock, flags);
/*
* The list addition should be visible before sending the IPI
@@ -171,7 +171,7 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait)
void generic_smp_call_function_interrupt(void)
{
struct call_function_data *data;
- int cpu = get_cpu();
+ int cpu = smp_processor_id();
/*
* Shouldn't receive this interrupt on a cpu that is not yet online.
@@ -201,9 +201,9 @@ void generic_smp_call_function_interrupt(void)
refs = atomic_dec_return(&data->refs);
WARN_ON(refs < 0);
if (!refs) {
- spin_lock(&call_function.lock);
+ raw_spin_lock(&call_function.lock);
list_del_rcu(&data->csd.list);
- spin_unlock(&call_function.lock);
+ raw_spin_unlock(&call_function.lock);
}
if (refs)
@@ -212,7 +212,6 @@ void generic_smp_call_function_interrupt(void)
csd_unlock(&data->csd);
}
- put_cpu();
}
/*
@@ -230,9 +229,9 @@ void generic_smp_call_function_single_interrupt(void)
*/
WARN_ON_ONCE(!cpu_online(smp_processor_id()));
- spin_lock(&q->lock);
+ raw_spin_lock(&q->lock);
list_replace_init(&q->list, &list);
- spin_unlock(&q->lock);
+ raw_spin_unlock(&q->lock);
while (!list_empty(&list)) {
struct call_single_data *data;
@@ -265,9 +264,7 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data);
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed on other CPUs.
*
- * Returns 0 on success, else a negative status code. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * Returns 0 on success, else a negative status code.
*/
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int wait)
@@ -321,6 +318,51 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
}
EXPORT_SYMBOL(smp_call_function_single);
+/*
+ * smp_call_function_any - Run a function on any of the given cpus
+ * @mask: The mask of cpus it can run on.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait until function has completed.
+ *
+ * Returns 0 on success, else a negative status code (if no cpus were online).
+ * Note that @wait will be implicitly turned on in case of allocation failures,
+ * since we fall back to on-stack allocation.
+ *
+ * Selection preference:
+ * 1) current cpu if in @mask
+ * 2) any cpu of current node if in @mask
+ * 3) any other online cpu in @mask
+ */
+int smp_call_function_any(const struct cpumask *mask,
+ void (*func)(void *info), void *info, int wait)
+{
+ unsigned int cpu;
+ const struct cpumask *nodemask;
+ int ret;
+
+ /* Try for same CPU (cheapest) */
+ cpu = get_cpu();
+ if (cpumask_test_cpu(cpu, mask))
+ goto call;
+
+ /* Try for same node. */
+ nodemask = cpumask_of_node(cpu);
+ for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
+ cpu = cpumask_next_and(cpu, nodemask, mask)) {
+ if (cpu_online(cpu))
+ goto call;
+ }
+
+ /* Any online will do: smp_call_function_single handles nr_cpu_ids. */
+ cpu = cpumask_any_and(mask, cpu_online_mask);
+call:
+ ret = smp_call_function_single(cpu, func, info, wait);
+ put_cpu();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(smp_call_function_any);
+
/**
* __smp_call_function_single(): Run a function on another CPU
* @cpu: The CPU to run on.
@@ -347,13 +389,6 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
generic_exec_single(cpu, data, wait);
}
-/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
-
-#ifndef arch_send_call_function_ipi_mask
-# define arch_send_call_function_ipi_mask(maskp) \
- arch_send_call_function_ipi(*(maskp))
-#endif
-
/**
* smp_call_function_many(): Run a function on a set of other CPUs.
* @mask: The set of cpus to run on (only runs on online subset).
@@ -362,9 +397,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
* @wait: If true, wait (atomically) until function has completed
* on other CPUs.
*
- * If @wait is true, then returns once @func has returned. Note that @wait
- * will be implicitly turned on in case of allocation failures, since
- * we fall back to on-stack allocation.
+ * If @wait is true, then returns once @func has returned.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. Preemption
@@ -415,14 +448,14 @@ void smp_call_function_many(const struct cpumask *mask,
cpumask_clear_cpu(this_cpu, data->cpumask);
atomic_set(&data->refs, cpumask_weight(data->cpumask));
- spin_lock_irqsave(&call_function.lock, flags);
+ raw_spin_lock_irqsave(&call_function.lock, flags);
/*
* Place entry at the _HEAD_ of the list, so that any cpu still
* observing the entry in generic_smp_call_function_interrupt()
* will not miss any other list entries:
*/
list_add_rcu(&data->csd.list, &call_function.queue);
- spin_unlock_irqrestore(&call_function.lock, flags);
+ raw_spin_unlock_irqrestore(&call_function.lock, flags);
/*
* Make the list addition visible before sending the ipi.
@@ -450,8 +483,7 @@ EXPORT_SYMBOL(smp_call_function_many);
* Returns 0.
*
* If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func. In case of allocation
- * failure, @wait will be implicitly turned on.
+ * it returns just before the target cpu calls @func.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
@@ -468,20 +500,20 @@ EXPORT_SYMBOL(smp_call_function);
void ipi_call_lock(void)
{
- spin_lock(&call_function.lock);
+ raw_spin_lock(&call_function.lock);
}
void ipi_call_unlock(void)
{
- spin_unlock(&call_function.lock);
+ raw_spin_unlock(&call_function.lock);
}
void ipi_call_lock_irq(void)
{
- spin_lock_irq(&call_function.lock);
+ raw_spin_lock_irq(&call_function.lock);
}
void ipi_call_unlock_irq(void)
{
- spin_unlock_irq(&call_function.lock);
+ raw_spin_unlock_irq(&call_function.lock);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index f8749e5216e..a09502e2ef7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -302,9 +302,9 @@ void irq_exit(void)
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
+ rcu_irq_exit();
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
- rcu_irq_exit();
if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
tick_nohz_stop_sched_tick(0);
#endif
@@ -697,7 +697,7 @@ void __init softirq_init(void)
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
-static int ksoftirqd(void * __bind_cpu)
+static int run_ksoftirqd(void * __bind_cpu)
{
set_current_state(TASK_INTERRUPTIBLE);
@@ -810,7 +810,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
+ p = kthread_create(run_ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
if (IS_ERR(p)) {
printk("ksoftirqd for %i failed\n", hotcpu);
return NOTIFY_BAD;
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 88796c33083..d22579087e2 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -22,9 +22,9 @@
static DEFINE_SPINLOCK(print_lock);
-static DEFINE_PER_CPU(unsigned long, touch_timestamp);
-static DEFINE_PER_CPU(unsigned long, print_timestamp);
-static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
+static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
+static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
+static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static int __read_mostly did_panic;
int __read_mostly softlockup_thresh = 60;
@@ -70,12 +70,12 @@ static void __touch_softlockup_watchdog(void)
{
int this_cpu = raw_smp_processor_id();
- __raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
+ __raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
}
void touch_softlockup_watchdog(void)
{
- __raw_get_cpu_var(touch_timestamp) = 0;
+ __raw_get_cpu_var(softlockup_touch_ts) = 0;
}
EXPORT_SYMBOL(touch_softlockup_watchdog);
@@ -85,16 +85,16 @@ void touch_all_softlockup_watchdogs(void)
/* Cause each CPU to re-update its timestamp rather than complain */
for_each_online_cpu(cpu)
- per_cpu(touch_timestamp, cpu) = 0;
+ per_cpu(softlockup_touch_ts, cpu) = 0;
}
EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
touch_all_softlockup_watchdogs();
- return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
/*
@@ -104,28 +104,28 @@ int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
void softlockup_tick(void)
{
int this_cpu = smp_processor_id();
- unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
- unsigned long print_timestamp;
+ unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
+ unsigned long print_ts;
struct pt_regs *regs = get_irq_regs();
unsigned long now;
/* Is detection switched off? */
- if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+ if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
/* Be sure we don't false trigger if switched back on */
- if (touch_timestamp)
- per_cpu(touch_timestamp, this_cpu) = 0;
+ if (touch_ts)
+ per_cpu(softlockup_touch_ts, this_cpu) = 0;
return;
}
- if (touch_timestamp == 0) {
+ if (touch_ts == 0) {
__touch_softlockup_watchdog();
return;
}
- print_timestamp = per_cpu(print_timestamp, this_cpu);
+ print_ts = per_cpu(softlockup_print_ts, this_cpu);
/* report at most once a second */
- if (print_timestamp == touch_timestamp || did_panic)
+ if (print_ts == touch_ts || did_panic)
return;
/* do not print during early bootup: */
@@ -140,18 +140,18 @@ void softlockup_tick(void)
* Wake up the high-prio watchdog task twice per
* threshold timespan.
*/
- if (now > touch_timestamp + softlockup_thresh/2)
- wake_up_process(per_cpu(watchdog_task, this_cpu));
+ if (now > touch_ts + softlockup_thresh/2)
+ wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
/* Warn about unreasonable delays: */
- if (now <= (touch_timestamp + softlockup_thresh))
+ if (now <= (touch_ts + softlockup_thresh))
return;
- per_cpu(print_timestamp, this_cpu) = touch_timestamp;
+ per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
spin_lock(&print_lock);
printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
- this_cpu, now - touch_timestamp,
+ this_cpu, now - touch_ts,
current->comm, task_pid_nr(current));
print_modules();
print_irqtrace_events(current);
@@ -209,32 +209,32 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- BUG_ON(per_cpu(watchdog_task, hotcpu));
+ BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
if (IS_ERR(p)) {
printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
return NOTIFY_BAD;
}
- per_cpu(touch_timestamp, hotcpu) = 0;
- per_cpu(watchdog_task, hotcpu) = p;
+ per_cpu(softlockup_touch_ts, hotcpu) = 0;
+ per_cpu(softlockup_watchdog, hotcpu) = p;
kthread_bind(p, hotcpu);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- wake_up_process(per_cpu(watchdog_task, hotcpu));
+ wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- if (!per_cpu(watchdog_task, hotcpu))
+ if (!per_cpu(softlockup_watchdog, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
- kthread_bind(per_cpu(watchdog_task, hotcpu),
+ kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
cpumask_any(cpu_online_mask));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- p = per_cpu(watchdog_task, hotcpu);
- per_cpu(watchdog_task, hotcpu) = NULL;
+ p = per_cpu(softlockup_watchdog, hotcpu);
+ per_cpu(softlockup_watchdog, hotcpu) = NULL;
kthread_stop(p);
break;
#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 5ddab730cb2..be6517fb9c1 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -21,193 +21,72 @@
#include <linux/debug_locks.h>
#include <linux/module.h>
-#ifndef _spin_trylock
-int __lockfunc _spin_trylock(spinlock_t *lock)
-{
- return __spin_trylock(lock);
-}
-EXPORT_SYMBOL(_spin_trylock);
-#endif
-
-#ifndef _read_trylock
-int __lockfunc _read_trylock(rwlock_t *lock)
-{
- return __read_trylock(lock);
-}
-EXPORT_SYMBOL(_read_trylock);
-#endif
-
-#ifndef _write_trylock
-int __lockfunc _write_trylock(rwlock_t *lock)
-{
- return __write_trylock(lock);
-}
-EXPORT_SYMBOL(_write_trylock);
-#endif
-
/*
* If lockdep is enabled then we use the non-preemption spin-ops
* even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
* not re-enabled during lock-acquire (which the preempt-spin-ops do):
*/
#if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC)
-
-#ifndef _read_lock
-void __lockfunc _read_lock(rwlock_t *lock)
-{
- __read_lock(lock);
-}
-EXPORT_SYMBOL(_read_lock);
-#endif
-
-#ifndef _spin_lock_irqsave
-unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
-{
- return __spin_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irqsave);
-#endif
-
-#ifndef _spin_lock_irq
-void __lockfunc _spin_lock_irq(spinlock_t *lock)
-{
- __spin_lock_irq(lock);
-}
-EXPORT_SYMBOL(_spin_lock_irq);
-#endif
-
-#ifndef _spin_lock_bh
-void __lockfunc _spin_lock_bh(spinlock_t *lock)
-{
- __spin_lock_bh(lock);
-}
-EXPORT_SYMBOL(_spin_lock_bh);
-#endif
-
-#ifndef _read_lock_irqsave
-unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
-{
- return __read_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_read_lock_irqsave);
-#endif
-
-#ifndef _read_lock_irq
-void __lockfunc _read_lock_irq(rwlock_t *lock)
-{
- __read_lock_irq(lock);
-}
-EXPORT_SYMBOL(_read_lock_irq);
-#endif
-
-#ifndef _read_lock_bh
-void __lockfunc _read_lock_bh(rwlock_t *lock)
-{
- __read_lock_bh(lock);
-}
-EXPORT_SYMBOL(_read_lock_bh);
-#endif
-
-#ifndef _write_lock_irqsave
-unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
-{
- return __write_lock_irqsave(lock);
-}
-EXPORT_SYMBOL(_write_lock_irqsave);
-#endif
-
-#ifndef _write_lock_irq
-void __lockfunc _write_lock_irq(rwlock_t *lock)
-{
- __write_lock_irq(lock);
-}
-EXPORT_SYMBOL(_write_lock_irq);
-#endif
-
-#ifndef _write_lock_bh
-void __lockfunc _write_lock_bh(rwlock_t *lock)
-{
- __write_lock_bh(lock);
-}
-EXPORT_SYMBOL(_write_lock_bh);
-#endif
-
-#ifndef _spin_lock
-void __lockfunc _spin_lock(spinlock_t *lock)
-{
- __spin_lock(lock);
-}
-EXPORT_SYMBOL(_spin_lock);
-#endif
-
-#ifndef _write_lock
-void __lockfunc _write_lock(rwlock_t *lock)
-{
- __write_lock(lock);
-}
-EXPORT_SYMBOL(_write_lock);
-#endif
-
-#else /* CONFIG_PREEMPT: */
-
/*
+ * The __lock_function inlines are taken from
+ * include/linux/spinlock_api_smp.h
+ */
+#else
+#define raw_read_can_lock(l) read_can_lock(l)
+#define raw_write_can_lock(l) write_can_lock(l)
+/*
+ * We build the __lock_function inlines here. They are too large for
+ * inlining all over the place, but here is only one user per function
+ * which embedds them into the calling _lock_function below.
+ *
* This could be a long-held lock. We both prepare to spin for a long
* time (making _this_ CPU preemptable if possible), and we also signal
* towards that other CPU that it should break the lock ASAP.
- *
- * (We do this in a function because inlining it would be excessive.)
*/
-
#define BUILD_LOCK_OPS(op, locktype) \
-void __lockfunc _##op##_lock(locktype##_t *lock) \
+void __lockfunc __raw_##op##_lock(locktype##_t *lock) \
{ \
for (;;) { \
preempt_disable(); \
- if (likely(_raw_##op##_trylock(lock))) \
+ if (likely(do_raw_##op##_trylock(lock))) \
break; \
preempt_enable(); \
\
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
- while (!op##_can_lock(lock) && (lock)->break_lock) \
- _raw_##op##_relax(&lock->raw_lock); \
+ while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+ arch_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
} \
\
-EXPORT_SYMBOL(_##op##_lock); \
- \
-unsigned long __lockfunc _##op##_lock_irqsave(locktype##_t *lock) \
+unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock) \
{ \
unsigned long flags; \
\
for (;;) { \
preempt_disable(); \
local_irq_save(flags); \
- if (likely(_raw_##op##_trylock(lock))) \
+ if (likely(do_raw_##op##_trylock(lock))) \
break; \
local_irq_restore(flags); \
preempt_enable(); \
\
if (!(lock)->break_lock) \
(lock)->break_lock = 1; \
- while (!op##_can_lock(lock) && (lock)->break_lock) \
- _raw_##op##_relax(&lock->raw_lock); \
+ while (!raw_##op##_can_lock(lock) && (lock)->break_lock)\
+ arch_##op##_relax(&lock->raw_lock); \
} \
(lock)->break_lock = 0; \
return flags; \
} \
\
-EXPORT_SYMBOL(_##op##_lock_irqsave); \
- \
-void __lockfunc _##op##_lock_irq(locktype##_t *lock) \
+void __lockfunc __raw_##op##_lock_irq(locktype##_t *lock) \
{ \
- _##op##_lock_irqsave(lock); \
+ _raw_##op##_lock_irqsave(lock); \
} \
\
-EXPORT_SYMBOL(_##op##_lock_irq); \
- \
-void __lockfunc _##op##_lock_bh(locktype##_t *lock) \
+void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \
{ \
unsigned long flags; \
\
@@ -216,164 +95,283 @@ void __lockfunc _##op##_lock_bh(locktype##_t *lock) \
/* irq-disabling. We use the generic preemption-aware */ \
/* function: */ \
/**/ \
- flags = _##op##_lock_irqsave(lock); \
+ flags = _raw_##op##_lock_irqsave(lock); \
local_bh_disable(); \
local_irq_restore(flags); \
} \
- \
-EXPORT_SYMBOL(_##op##_lock_bh)
/*
* Build preemption-friendly versions of the following
* lock-spinning functions:
*
- * _[spin|read|write]_lock()
- * _[spin|read|write]_lock_irq()
- * _[spin|read|write]_lock_irqsave()
- * _[spin|read|write]_lock_bh()
+ * __[spin|read|write]_lock()
+ * __[spin|read|write]_lock_irq()
+ * __[spin|read|write]_lock_irqsave()
+ * __[spin|read|write]_lock_bh()
*/
-BUILD_LOCK_OPS(spin, spinlock);
+BUILD_LOCK_OPS(spin, raw_spinlock);
BUILD_LOCK_OPS(read, rwlock);
BUILD_LOCK_OPS(write, rwlock);
-#endif /* CONFIG_PREEMPT */
+#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK
+int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock)
+{
+ return __raw_spin_trylock(lock);
+}
+EXPORT_SYMBOL(_raw_spin_trylock);
+#endif
-void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
+#ifndef CONFIG_INLINE_SPIN_TRYLOCK_BH
+int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock)
{
- preempt_disable();
- spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
- LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+ return __raw_spin_trylock_bh(lock);
}
-EXPORT_SYMBOL(_spin_lock_nested);
+EXPORT_SYMBOL(_raw_spin_trylock_bh);
+#endif
-unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
+#ifndef CONFIG_INLINE_SPIN_LOCK
+void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)
{
- unsigned long flags;
+ __raw_spin_lock(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock);
+#endif
- local_irq_save(flags);
- preempt_disable();
- spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
- LOCK_CONTENDED_FLAGS(lock, _raw_spin_trylock, _raw_spin_lock,
- _raw_spin_lock_flags, &flags);
- return flags;
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQSAVE
+unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock)
+{
+ return __raw_spin_lock_irqsave(lock);
}
-EXPORT_SYMBOL(_spin_lock_irqsave_nested);
+EXPORT_SYMBOL(_raw_spin_lock_irqsave);
+#endif
-void __lockfunc _spin_lock_nest_lock(spinlock_t *lock,
- struct lockdep_map *nest_lock)
+#ifndef CONFIG_INLINE_SPIN_LOCK_IRQ
+void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock)
{
- preempt_disable();
- spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
- LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+ __raw_spin_lock_irq(lock);
}
-EXPORT_SYMBOL(_spin_lock_nest_lock);
+EXPORT_SYMBOL(_raw_spin_lock_irq);
+#endif
+#ifndef CONFIG_INLINE_SPIN_LOCK_BH
+void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock)
+{
+ __raw_spin_lock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_bh);
#endif
-#ifndef _spin_unlock
-void __lockfunc _spin_unlock(spinlock_t *lock)
+#ifndef CONFIG_INLINE_SPIN_UNLOCK
+void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock)
{
- __spin_unlock(lock);
+ __raw_spin_unlock(lock);
}
-EXPORT_SYMBOL(_spin_unlock);
+EXPORT_SYMBOL(_raw_spin_unlock);
#endif
-#ifndef _write_unlock
-void __lockfunc _write_unlock(rwlock_t *lock)
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE
+void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags)
{
- __write_unlock(lock);
+ __raw_spin_unlock_irqrestore(lock, flags);
}
-EXPORT_SYMBOL(_write_unlock);
+EXPORT_SYMBOL(_raw_spin_unlock_irqrestore);
#endif
-#ifndef _read_unlock
-void __lockfunc _read_unlock(rwlock_t *lock)
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_IRQ
+void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock)
{
- __read_unlock(lock);
+ __raw_spin_unlock_irq(lock);
}
-EXPORT_SYMBOL(_read_unlock);
+EXPORT_SYMBOL(_raw_spin_unlock_irq);
#endif
-#ifndef _spin_unlock_irqrestore
-void __lockfunc _spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
+#ifndef CONFIG_INLINE_SPIN_UNLOCK_BH
+void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
{
- __spin_unlock_irqrestore(lock, flags);
+ __raw_spin_unlock_bh(lock);
}
-EXPORT_SYMBOL(_spin_unlock_irqrestore);
+EXPORT_SYMBOL(_raw_spin_unlock_bh);
#endif
-#ifndef _spin_unlock_irq
-void __lockfunc _spin_unlock_irq(spinlock_t *lock)
+#ifndef CONFIG_INLINE_READ_TRYLOCK
+int __lockfunc _raw_read_trylock(rwlock_t *lock)
{
- __spin_unlock_irq(lock);
+ return __raw_read_trylock(lock);
}
-EXPORT_SYMBOL(_spin_unlock_irq);
+EXPORT_SYMBOL(_raw_read_trylock);
#endif
-#ifndef _spin_unlock_bh
-void __lockfunc _spin_unlock_bh(spinlock_t *lock)
+#ifndef CONFIG_INLINE_READ_LOCK
+void __lockfunc _raw_read_lock(rwlock_t *lock)
{
- __spin_unlock_bh(lock);
+ __raw_read_lock(lock);
}
-EXPORT_SYMBOL(_spin_unlock_bh);
+EXPORT_SYMBOL(_raw_read_lock);
#endif
-#ifndef _read_unlock_irqrestore
-void __lockfunc _read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+#ifndef CONFIG_INLINE_READ_LOCK_IRQSAVE
+unsigned long __lockfunc _raw_read_lock_irqsave(rwlock_t *lock)
{
- __read_unlock_irqrestore(lock, flags);
+ return __raw_read_lock_irqsave(lock);
}
-EXPORT_SYMBOL(_read_unlock_irqrestore);
+EXPORT_SYMBOL(_raw_read_lock_irqsave);
#endif
-#ifndef _read_unlock_irq
-void __lockfunc _read_unlock_irq(rwlock_t *lock)
+#ifndef CONFIG_INLINE_READ_LOCK_IRQ
+void __lockfunc _raw_read_lock_irq(rwlock_t *lock)
{
- __read_unlock_irq(lock);
+ __raw_read_lock_irq(lock);
}
-EXPORT_SYMBOL(_read_unlock_irq);
+EXPORT_SYMBOL(_raw_read_lock_irq);
#endif
-#ifndef _read_unlock_bh
-void __lockfunc _read_unlock_bh(rwlock_t *lock)
+#ifndef CONFIG_INLINE_READ_LOCK_BH
+void __lockfunc _raw_read_lock_bh(rwlock_t *lock)
{
- __read_unlock_bh(lock);
+ __raw_read_lock_bh(lock);
}
-EXPORT_SYMBOL(_read_unlock_bh);
+EXPORT_SYMBOL(_raw_read_lock_bh);
#endif
-#ifndef _write_unlock_irqrestore
-void __lockfunc _write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+#ifndef CONFIG_INLINE_READ_UNLOCK
+void __lockfunc _raw_read_unlock(rwlock_t *lock)
{
- __write_unlock_irqrestore(lock, flags);
+ __raw_read_unlock(lock);
}
-EXPORT_SYMBOL(_write_unlock_irqrestore);
+EXPORT_SYMBOL(_raw_read_unlock);
#endif
-#ifndef _write_unlock_irq
-void __lockfunc _write_unlock_irq(rwlock_t *lock)
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQRESTORE
+void __lockfunc _raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
{
- __write_unlock_irq(lock);
+ __raw_read_unlock_irqrestore(lock, flags);
}
-EXPORT_SYMBOL(_write_unlock_irq);
+EXPORT_SYMBOL(_raw_read_unlock_irqrestore);
#endif
-#ifndef _write_unlock_bh
-void __lockfunc _write_unlock_bh(rwlock_t *lock)
+#ifndef CONFIG_INLINE_READ_UNLOCK_IRQ
+void __lockfunc _raw_read_unlock_irq(rwlock_t *lock)
{
- __write_unlock_bh(lock);
+ __raw_read_unlock_irq(lock);
}
-EXPORT_SYMBOL(_write_unlock_bh);
+EXPORT_SYMBOL(_raw_read_unlock_irq);
#endif
-#ifndef _spin_trylock_bh
-int __lockfunc _spin_trylock_bh(spinlock_t *lock)
+#ifndef CONFIG_INLINE_READ_UNLOCK_BH
+void __lockfunc _raw_read_unlock_bh(rwlock_t *lock)
{
- return __spin_trylock_bh(lock);
+ __raw_read_unlock_bh(lock);
}
-EXPORT_SYMBOL(_spin_trylock_bh);
+EXPORT_SYMBOL(_raw_read_unlock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_TRYLOCK
+int __lockfunc _raw_write_trylock(rwlock_t *lock)
+{
+ return __raw_write_trylock(lock);
+}
+EXPORT_SYMBOL(_raw_write_trylock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK
+void __lockfunc _raw_write_lock(rwlock_t *lock)
+{
+ __raw_write_lock(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE
+unsigned long __lockfunc _raw_write_lock_irqsave(rwlock_t *lock)
+{
+ return __raw_write_lock_irqsave(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_irqsave);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_IRQ
+void __lockfunc _raw_write_lock_irq(rwlock_t *lock)
+{
+ __raw_write_lock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_LOCK_BH
+void __lockfunc _raw_write_lock_bh(rwlock_t *lock)
+{
+ __raw_write_lock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_write_lock_bh);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK
+void __lockfunc _raw_write_unlock(rwlock_t *lock)
+{
+ __raw_write_unlock(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE
+void __lockfunc _raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
+{
+ __raw_write_unlock_irqrestore(lock, flags);
+}
+EXPORT_SYMBOL(_raw_write_unlock_irqrestore);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_IRQ
+void __lockfunc _raw_write_unlock_irq(rwlock_t *lock)
+{
+ __raw_write_unlock_irq(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock_irq);
+#endif
+
+#ifndef CONFIG_INLINE_WRITE_UNLOCK_BH
+void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
+{
+ __raw_write_unlock_bh(lock);
+}
+EXPORT_SYMBOL(_raw_write_unlock_bh);
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
+{
+ preempt_disable();
+ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+ LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_nested);
+
+unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
+ int subclass)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ preempt_disable();
+ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+ LOCK_CONTENDED_FLAGS(lock, do_raw_spin_trylock, do_raw_spin_lock,
+ do_raw_spin_lock_flags, &flags);
+ return flags;
+}
+EXPORT_SYMBOL(_raw_spin_lock_irqsave_nested);
+
+void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock,
+ struct lockdep_map *nest_lock)
+{
+ preempt_disable();
+ spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+ LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_nest_lock);
+
#endif
notrace int in_lock_functions(unsigned long addr)
diff --git a/kernel/srcu.c b/kernel/srcu.c
index b0aeeaf22ce..818d7d9aa03 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -49,6 +49,7 @@ int init_srcu_struct(struct srcu_struct *sp)
sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
return (sp->per_cpu_ref ? 0 : -ENOMEM);
}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
/*
* srcu_readers_active_idx -- returns approximate number of readers
@@ -97,6 +98,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
free_percpu(sp->per_cpu_ref);
sp->per_cpu_ref = NULL;
}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
/**
* srcu_read_lock - register a new reader for an SRCU-protected structure.
@@ -118,6 +120,7 @@ int srcu_read_lock(struct srcu_struct *sp)
preempt_enable();
return idx;
}
+EXPORT_SYMBOL_GPL(srcu_read_lock);
/**
* srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
@@ -136,22 +139,12 @@ void srcu_read_unlock(struct srcu_struct *sp, int idx)
per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
preempt_enable();
}
+EXPORT_SYMBOL_GPL(srcu_read_unlock);
-/**
- * synchronize_srcu - wait for prior SRCU read-side critical-section completion
- * @sp: srcu_struct with which to synchronize.
- *
- * Flip the completed counter, and wait for the old count to drain to zero.
- * As with classic RCU, the updater must use some separate means of
- * synchronizing concurrent updates. Can block; must be called from
- * process context.
- *
- * Note that it is illegal to call synchornize_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.
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
*/
-void synchronize_srcu(struct srcu_struct *sp)
+void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
{
int idx;
@@ -173,7 +166,7 @@ void synchronize_srcu(struct srcu_struct *sp)
return;
}
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() ensures that any CPU that
@@ -190,7 +183,7 @@ void synchronize_srcu(struct srcu_struct *sp)
idx = sp->completed & 0x1;
sp->completed++;
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* At this point, because of the preceding synchronize_sched(),
@@ -203,7 +196,7 @@ void synchronize_srcu(struct srcu_struct *sp)
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
- synchronize_sched(); /* Force memory barrier on all CPUs. */
+ sync_func(); /* Force memory barrier on all CPUs. */
/*
* The preceding synchronize_sched() forces all srcu_read_unlock()
@@ -237,6 +230,47 @@ void synchronize_srcu(struct srcu_struct *sp)
}
/**
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates. Can block; must be called from
+ * process context.
+ *
+ * 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.
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, synchronize_sched);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/**
+ * synchronize_srcu_expedited - like synchronize_srcu, but less patient
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Flip the completed counter, and wait for the old count to drain to zero.
+ * As with classic RCU, the updater must use some separate means of
+ * synchronizing concurrent updates. Can block; must be called from
+ * process context.
+ *
+ * Note that it is 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.
+ */
+void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, synchronize_sched_expedited);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
+
+/**
* srcu_batches_completed - return batches completed.
* @sp: srcu_struct on which to report batch completion.
*
@@ -248,10 +282,4 @@ long srcu_batches_completed(struct srcu_struct *sp)
{
return sp->completed;
}
-
-EXPORT_SYMBOL_GPL(init_srcu_struct);
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
-EXPORT_SYMBOL_GPL(srcu_read_lock);
-EXPORT_SYMBOL_GPL(srcu_read_unlock);
-EXPORT_SYMBOL_GPL(synchronize_srcu);
EXPORT_SYMBOL_GPL(srcu_batches_completed);
diff --git a/kernel/sys.c b/kernel/sys.c
index ebcb1561172..20ccfb5da6a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -8,7 +8,6 @@
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
@@ -190,10 +189,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
!(user = find_user(who)))
goto out_unlock; /* No processes for this user */
- do_each_thread(g, p)
+ do_each_thread(g, p) {
if (__task_cred(p)->uid == who)
error = set_one_prio(p, niceval, error);
- while_each_thread(g, p);
+ } while_each_thread(g, p);
if (who != cred->uid)
free_uid(user); /* For find_user() */
break;
@@ -253,13 +252,13 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
!(user = find_user(who)))
goto out_unlock; /* No processes for this user */
- do_each_thread(g, p)
+ do_each_thread(g, p) {
if (__task_cred(p)->uid == who) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
- while_each_thread(g, p);
+ } while_each_thread(g, p);
if (who != cred->uid)
free_uid(user); /* for find_user() */
break;
@@ -349,6 +348,9 @@ void kernel_power_off(void)
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
+
+static DEFINE_MUTEX(reboot_mutex);
+
/*
* Reboot system call: for obvious reasons only root may call it,
* and even root needs to set up some magic numbers in the registers
@@ -381,7 +383,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
- lock_kernel();
+ mutex_lock(&reboot_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
@@ -397,20 +399,18 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
case LINUX_REBOOT_CMD_HALT:
kernel_halt();
- unlock_kernel();
do_exit(0);
panic("cannot halt");
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_power_off();
- unlock_kernel();
do_exit(0);
break;
case LINUX_REBOOT_CMD_RESTART2:
if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
- unlock_kernel();
- return -EFAULT;
+ ret = -EFAULT;
+ break;
}
buffer[sizeof(buffer) - 1] = '\0';
@@ -433,7 +433,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
ret = -EINVAL;
break;
}
- unlock_kernel();
+ mutex_unlock(&reboot_mutex);
return ret;
}
@@ -911,16 +911,15 @@ change_okay:
void do_sys_times(struct tms *tms)
{
- struct task_cputime cputime;
- cputime_t cutime, cstime;
+ cputime_t tgutime, tgstime, cutime, cstime;
- thread_group_cputime(current, &cputime);
spin_lock_irq(&current->sighand->siglock);
+ thread_group_times(current, &tgutime, &tgstime);
cutime = current->signal->cutime;
cstime = current->signal->cstime;
spin_unlock_irq(&current->sighand->siglock);
- tms->tms_utime = cputime_to_clock_t(cputime.utime);
- tms->tms_stime = cputime_to_clock_t(cputime.stime);
+ tms->tms_utime = cputime_to_clock_t(tgutime);
+ tms->tms_stime = cputime_to_clock_t(tgstime);
tms->tms_cutime = cputime_to_clock_t(cutime);
tms->tms_cstime = cputime_to_clock_t(cstime);
}
@@ -1110,6 +1109,8 @@ SYSCALL_DEFINE0(setsid)
err = session;
out:
write_unlock_irq(&tasklist_lock);
+ if (err > 0)
+ proc_sid_connector(group_leader);
return err;
}
@@ -1336,16 +1337,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
struct task_struct *t;
unsigned long flags;
- cputime_t utime, stime;
- struct task_cputime cputime;
+ cputime_t tgutime, tgstime, utime, stime;
unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
if (who == RUSAGE_THREAD) {
- utime = task_utime(current);
- stime = task_stime(current);
+ task_times(current, &utime, &stime);
accumulate_thread_rusage(p, r);
maxrss = p->signal->maxrss;
goto out;
@@ -1371,9 +1370,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
break;
case RUSAGE_SELF:
- thread_group_cputime(p, &cputime);
- utime = cputime_add(utime, cputime.utime);
- stime = cputime_add(stime, cputime.stime);
+ thread_group_times(p, &tgutime, &tgstime);
+ utime = cputime_add(utime, tgutime);
+ stime = cputime_add(stime, tgstime);
r->ru_nvcsw += p->signal->nvcsw;
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
@@ -1542,6 +1541,41 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
current->timer_slack_ns = arg2;
error = 0;
break;
+ case PR_MCE_KILL:
+ if (arg4 | arg5)
+ return -EINVAL;
+ switch (arg2) {
+ case PR_MCE_KILL_CLEAR:
+ if (arg3 != 0)
+ return -EINVAL;
+ current->flags &= ~PF_MCE_PROCESS;
+ break;
+ case PR_MCE_KILL_SET:
+ current->flags |= PF_MCE_PROCESS;
+ if (arg3 == PR_MCE_KILL_EARLY)
+ current->flags |= PF_MCE_EARLY;
+ else if (arg3 == PR_MCE_KILL_LATE)
+ current->flags &= ~PF_MCE_EARLY;
+ else if (arg3 == PR_MCE_KILL_DEFAULT)
+ current->flags &=
+ ~(PF_MCE_EARLY|PF_MCE_PROCESS);
+ else
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+ error = 0;
+ break;
+ case PR_MCE_KILL_GET:
+ if (arg2 | arg3 | arg4 | arg5)
+ return -EINVAL;
+ if (current->flags & PF_MCE_PROCESS)
+ error = (current->flags & PF_MCE_EARLY) ?
+ PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
+ else
+ error = PR_MCE_KILL_DEFAULT;
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 515bc230ac2..695384f12a7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -48,7 +48,10 @@ cond_syscall(sys_shutdown);
cond_syscall(sys_sendmsg);
cond_syscall(compat_sys_sendmsg);
cond_syscall(sys_recvmsg);
+cond_syscall(sys_recvmmsg);
cond_syscall(compat_sys_recvmsg);
+cond_syscall(compat_sys_recvfrom);
+cond_syscall(compat_sys_recvmmsg);
cond_syscall(sys_socketcall);
cond_syscall(sys_futex);
cond_syscall(compat_sys_futex);
@@ -138,7 +141,6 @@ cond_syscall(sys_pciconfig_read);
cond_syscall(sys_pciconfig_write);
cond_syscall(sys_pciconfig_iobase);
cond_syscall(sys32_ipc);
-cond_syscall(sys32_sysctl);
cond_syscall(ppc_rtas);
cond_syscall(sys_spu_run);
cond_syscall(sys_spu_create);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0dfaa47d7cb..45e4bef0012 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -26,9 +26,7 @@
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/ctype.h>
-#include <linux/utsname.h>
#include <linux/kmemcheck.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
@@ -37,6 +35,7 @@
#include <linux/sysrq.h>
#include <linux/highuid.h>
#include <linux/writeback.h>
+#include <linux/ratelimit.h>
#include <linux/hugetlb.h>
#include <linux/initrd.h>
#include <linux/key.h>
@@ -61,7 +60,6 @@
#include <asm/io.h>
#endif
-static int deprecated_sysctl_warning(struct __sysctl_args *args);
#if defined(CONFIG_SYSCTL)
@@ -77,6 +75,7 @@ extern int max_threads;
extern int core_uses_pid;
extern int suid_dumpable;
extern char core_pattern[];
+extern unsigned int core_pipe_limit;
extern int pid_max;
extern int min_free_kbytes;
extern int pid_max_min, pid_max_max;
@@ -158,14 +157,16 @@ extern int no_unaligned_warning;
extern int unaligned_dump_stack;
#endif
+extern struct ratelimit_state printk_ratelimit_state;
+
#ifdef CONFIG_RT_MUTEXES
extern int max_lock_depth;
#endif
#ifdef CONFIG_PROC_SYSCTL
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
@@ -207,31 +208,26 @@ extern int lock_stat;
static struct ctl_table root_table[] = {
{
- .ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
.child = kern_table,
},
{
- .ctl_name = CTL_VM,
.procname = "vm",
.mode = 0555,
.child = vm_table,
},
{
- .ctl_name = CTL_FS,
.procname = "fs",
.mode = 0555,
.child = fs_table,
},
{
- .ctl_name = CTL_DEBUG,
.procname = "debug",
.mode = 0555,
.child = debug_table,
},
{
- .ctl_name = CTL_DEV,
.procname = "dev",
.mode = 0555,
.child = dev_table,
@@ -240,7 +236,7 @@ static struct ctl_table root_table[] = {
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
*/
- { .ctl_name = 0 }
+ { }
};
#ifdef CONFIG_SCHED_DEBUG
@@ -248,188 +244,178 @@ static int min_sched_granularity_ns = 100000; /* 100 usecs */
static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */
static int min_wakeup_granularity_ns; /* 0 usecs */
static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */
+static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
+static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
+static int min_sched_shares_ratelimit = 100000; /* 100 usec */
+static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
#endif
static struct ctl_table kern_table[] = {
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_child_runs_first",
.data = &sysctl_sched_child_runs_first,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_SCHED_DEBUG
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_min_granularity_ns",
.data = &sysctl_sched_min_granularity,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &sched_nr_latency_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = sched_proc_update_handler,
.extra1 = &min_sched_granularity_ns,
.extra2 = &max_sched_granularity_ns,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_latency_ns",
.data = &sysctl_sched_latency,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &sched_nr_latency_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = sched_proc_update_handler,
.extra1 = &min_sched_granularity_ns,
.extra2 = &max_sched_granularity_ns,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_wakeup_granularity_ns",
.data = &sysctl_sched_wakeup_granularity,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = sched_proc_update_handler,
.extra1 = &min_wakeup_granularity_ns,
.extra2 = &max_wakeup_granularity_ns,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_shares_ratelimit",
.data = &sysctl_sched_shares_ratelimit,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = sched_proc_update_handler,
+ .extra1 = &min_sched_shares_ratelimit,
+ .extra2 = &max_sched_shares_ratelimit,
},
{
- .ctl_name = CTL_UNNUMBERED,
- .procname = "sched_shares_thresh",
- .data = &sysctl_sched_shares_thresh,
- .maxlen = sizeof(unsigned int),
+ .procname = "sched_tunable_scaling",
+ .data = &sysctl_sched_tunable_scaling,
+ .maxlen = sizeof(enum sched_tunable_scaling),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
- .extra1 = &zero,
+ .proc_handler = sched_proc_update_handler,
+ .extra1 = &min_sched_tunable_scaling,
+ .extra2 = &max_sched_tunable_scaling,
},
{
- .ctl_name = CTL_UNNUMBERED,
- .procname = "sched_features",
- .data = &sysctl_sched_features,
+ .procname = "sched_shares_thresh",
+ .data = &sysctl_sched_shares_thresh,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_migration_cost",
.data = &sysctl_sched_migration_cost,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_nr_migrate",
.data = &sysctl_sched_nr_migrate,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_time_avg",
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "timer_migration",
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_rt_period_us",
.data = &sysctl_sched_rt_period,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &sched_rt_handler,
+ .proc_handler = sched_rt_handler,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_rt_runtime_us",
.data = &sysctl_sched_rt_runtime,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &sched_rt_handler,
+ .proc_handler = sched_rt_handler,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "sched_compat_yield",
.data = &sysctl_sched_compat_yield,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_PROVE_LOCKING
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "prove_locking",
.data = &prove_locking,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_LOCK_STAT
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "lock_stat",
.data = &lock_stat,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = KERN_PANIC,
.procname = "panic",
.data = &panic_timeout,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_CORE_USES_PID,
.procname = "core_uses_pid",
.data = &core_uses_pid,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_CORE_PATTERN,
.procname = "core_pattern",
.data = core_pattern,
.maxlen = CORENAME_MAX_SIZE,
.mode = 0644,
- .proc_handler = &proc_dostring,
- .strategy = &sysctl_string,
+ .proc_handler = proc_dostring,
+ },
+ {
+ .procname = "core_pipe_limit",
+ .data = &core_pipe_limit,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_PROC_SYSCTL
{
.procname = "tainted",
.maxlen = sizeof(long),
.mode = 0644,
- .proc_handler = &proc_taint,
+ .proc_handler = proc_taint,
},
#endif
#ifdef CONFIG_LATENCYTOP
@@ -438,181 +424,160 @@ static struct ctl_table kern_table[] = {
.data = &latencytop_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_BLK_DEV_INITRD
{
- .ctl_name = KERN_REALROOTDEV,
.procname = "real-root-dev",
.data = &real_root_dev,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "print-fatal-signals",
.data = &print_fatal_signals,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_SPARC
{
- .ctl_name = KERN_SPARC_REBOOT,
.procname = "reboot-cmd",
.data = reboot_command,
.maxlen = 256,
.mode = 0644,
- .proc_handler = &proc_dostring,
- .strategy = &sysctl_string,
+ .proc_handler = proc_dostring,
},
{
- .ctl_name = KERN_SPARC_STOP_A,
.procname = "stop-a",
.data = &stop_a_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_SPARC_SCONS_PWROFF,
.procname = "scons-poweroff",
.data = &scons_pwroff,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_SPARC64
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "tsb-ratio",
.data = &sysctl_tsb_ratio,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef __hppa__
{
- .ctl_name = KERN_HPPA_PWRSW,
.procname = "soft-power",
.data = &pwrsw_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_HPPA_UNALIGNED,
.procname = "unaligned-trap",
.data = &unaligned_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = KERN_CTLALTDEL,
.procname = "ctrl-alt-del",
.data = &C_A_D,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#ifdef CONFIG_FUNCTION_TRACER
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "ftrace_enabled",
.data = &ftrace_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &ftrace_enable_sysctl,
+ .proc_handler = ftrace_enable_sysctl,
},
#endif
#ifdef CONFIG_STACK_TRACER
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "stack_tracer_enabled",
.data = &stack_tracer_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &stack_trace_sysctl,
+ .proc_handler = stack_trace_sysctl,
},
#endif
#ifdef CONFIG_TRACING
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "ftrace_dump_on_oops",
.data = &ftrace_dump_on_oops,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_MODULES
{
- .ctl_name = KERN_MODPROBE,
.procname = "modprobe",
.data = &modprobe_path,
.maxlen = KMOD_PATH_LEN,
.mode = 0644,
- .proc_handler = &proc_dostring,
- .strategy = &sysctl_string,
+ .proc_handler = proc_dostring,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "modules_disabled",
.data = &modules_disabled,
.maxlen = sizeof(int),
.mode = 0644,
/* only handle a transition from default "0" to "1" */
- .proc_handler = &proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &one,
.extra2 = &one,
},
#endif
#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
{
- .ctl_name = KERN_HOTPLUG,
.procname = "hotplug",
.data = &uevent_helper,
.maxlen = UEVENT_HELPER_PATH_LEN,
.mode = 0644,
- .proc_handler = &proc_dostring,
- .strategy = &sysctl_string,
+ .proc_handler = proc_dostring,
},
#endif
#ifdef CONFIG_CHR_DEV_SG
{
- .ctl_name = KERN_SG_BIG_BUFF,
.procname = "sg-big-buff",
.data = &sg_big_buff,
.maxlen = sizeof (int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
{
- .ctl_name = KERN_ACCT,
.procname = "acct",
.data = &acct_parm,
.maxlen = 3*sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
{
- .ctl_name = KERN_SYSRQ,
.procname = "sysrq",
.data = &__sysrq_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_PROC_SYSCTL
@@ -621,215 +586,188 @@ static struct ctl_table kern_table[] = {
.data = NULL,
.maxlen = sizeof (int),
.mode = 0600,
- .proc_handler = &proc_do_cad_pid,
+ .proc_handler = proc_do_cad_pid,
},
#endif
{
- .ctl_name = KERN_MAX_THREADS,
.procname = "threads-max",
.data = &max_threads,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_RANDOM,
.procname = "random",
.mode = 0555,
.child = random_table,
},
{
- .ctl_name = KERN_OVERFLOWUID,
.procname = "overflowuid",
.data = &overflowuid,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
{
- .ctl_name = KERN_OVERFLOWGID,
.procname = "overflowgid",
.data = &overflowgid,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
{
- .ctl_name = KERN_IEEE_EMULATION_WARNINGS,
.procname = "ieee_emulation_warnings",
.data = &sysctl_ieee_emulation_warnings,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = KERN_S390_USER_DEBUG_LOGGING,
.procname = "userprocess_debug",
.data = &sysctl_userprocess_debug,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = KERN_PIDMAX,
.procname = "pid_max",
.data = &pid_max,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &pid_max_min,
.extra2 = &pid_max_max,
},
{
- .ctl_name = KERN_PANIC_ON_OOPS,
.procname = "panic_on_oops",
.data = &panic_on_oops,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#if defined CONFIG_PRINTK
{
- .ctl_name = KERN_PRINTK,
.procname = "printk",
.data = &console_loglevel,
.maxlen = 4*sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_PRINTK_RATELIMIT,
.procname = "printk_ratelimit",
.data = &printk_ratelimit_state.interval,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = KERN_PRINTK_RATELIMIT_BURST,
.procname = "printk_ratelimit_burst",
.data = &printk_ratelimit_state.burst,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "printk_delay",
.data = &printk_delay_msec,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &ten_thousand,
},
#endif
{
- .ctl_name = KERN_NGROUPS_MAX,
.procname = "ngroups_max",
.data = &ngroups_max,
.maxlen = sizeof (int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
- .ctl_name = KERN_UNKNOWN_NMI_PANIC,
.procname = "unknown_nmi_panic",
.data = &unknown_nmi_panic,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.procname = "nmi_watchdog",
.data = &nmi_watchdog_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_nmi_enabled,
+ .proc_handler = proc_nmi_enabled,
},
#endif
#if defined(CONFIG_X86)
{
- .ctl_name = KERN_PANIC_ON_NMI,
.procname = "panic_on_unrecovered_nmi",
.data = &panic_on_unrecovered_nmi,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "panic_on_io_nmi",
.data = &panic_on_io_nmi,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = KERN_BOOTLOADER_TYPE,
.procname = "bootloader_type",
.data = &bootloader_type,
.maxlen = sizeof (int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "bootloader_version",
.data = &bootloader_version,
.maxlen = sizeof (int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "kstack_depth_to_print",
.data = &kstack_depth_to_print,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "io_delay_type",
.data = &io_delay_type,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_MMU)
{
- .ctl_name = KERN_RANDOMIZE,
.procname = "randomize_va_space",
.data = &randomize_va_space,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_S390) && defined(CONFIG_SMP)
{
- .ctl_name = KERN_SPIN_RETRY,
.procname = "spin_retry",
.data = &spin_retry,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
@@ -838,123 +776,104 @@ static struct ctl_table kern_table[] = {
.data = &acpi_realmode_flags,
.maxlen = sizeof (unsigned long),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
},
#endif
#ifdef CONFIG_IA64
{
- .ctl_name = KERN_IA64_UNALIGNED,
.procname = "ignore-unaligned-usertrap",
.data = &no_unaligned_warning,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "unaligned-dump-stack",
.data = &unaligned_dump_stack,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_DETECT_SOFTLOCKUP
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "softlockup_panic",
.data = &softlockup_panic,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "softlockup_thresh",
.data = &softlockup_thresh,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dosoftlockup_thresh,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dosoftlockup_thresh,
.extra1 = &neg_one,
.extra2 = &sixty,
},
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_panic",
.data = &sysctl_hung_task_panic,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_check_count",
.data = &sysctl_hung_task_check_count,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_doulongvec_minmax,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_timeout_secs",
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &proc_dohung_task_timeout_secs,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dohung_task_timeout_secs,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_warnings",
.data = &sysctl_hung_task_warnings,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_doulongvec_minmax,
},
#endif
#ifdef CONFIG_COMPAT
{
- .ctl_name = KERN_COMPAT_LOG,
.procname = "compat-log",
.data = &compat_log,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_RT_MUTEXES
{
- .ctl_name = KERN_MAX_LOCK_DEPTH,
.procname = "max_lock_depth",
.data = &max_lock_depth,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "poweroff_cmd",
.data = &poweroff_cmd,
.maxlen = POWEROFF_CMD_PATH_LEN,
.mode = 0644,
- .proc_handler = &proc_dostring,
- .strategy = &sysctl_string,
+ .proc_handler = proc_dostring,
},
#ifdef CONFIG_KEYS
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "keys",
.mode = 0555,
.child = key_sysctls,
@@ -962,17 +881,15 @@ static struct ctl_table kern_table[] = {
#endif
#ifdef CONFIG_RCU_TORTURE_TEST
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "rcutorture_runnable",
.data = &rcutorture_runnable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_SLOW_WORK
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "slow-work",
.mode = 0555,
.child = slow_work_sysctls,
@@ -980,146 +897,127 @@ static struct ctl_table kern_table[] = {
#endif
#ifdef CONFIG_PERF_EVENTS
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "perf_event_paranoid",
.data = &sysctl_perf_event_paranoid,
.maxlen = sizeof(sysctl_perf_event_paranoid),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "perf_event_mlock_kb",
.data = &sysctl_perf_event_mlock,
.maxlen = sizeof(sysctl_perf_event_mlock),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "perf_event_max_sample_rate",
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_KMEMCHECK
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "kmemcheck",
.data = &kmemcheck_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_BLOCK
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "blk_iopoll",
.data = &blk_iopoll_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
*/
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table vm_table[] = {
{
- .ctl_name = VM_OVERCOMMIT_MEMORY,
.procname = "overcommit_memory",
.data = &sysctl_overcommit_memory,
.maxlen = sizeof(sysctl_overcommit_memory),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_PANIC_ON_OOM,
.procname = "panic_on_oom",
.data = &sysctl_panic_on_oom,
.maxlen = sizeof(sysctl_panic_on_oom),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "oom_kill_allocating_task",
.data = &sysctl_oom_kill_allocating_task,
.maxlen = sizeof(sysctl_oom_kill_allocating_task),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "oom_dump_tasks",
.data = &sysctl_oom_dump_tasks,
.maxlen = sizeof(sysctl_oom_dump_tasks),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_OVERCOMMIT_RATIO,
.procname = "overcommit_ratio",
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_PAGE_CLUSTER,
.procname = "page-cluster",
.data = &page_cluster,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_DIRTY_BACKGROUND,
.procname = "dirty_background_ratio",
.data = &dirty_background_ratio,
.maxlen = sizeof(dirty_background_ratio),
.mode = 0644,
- .proc_handler = &dirty_background_ratio_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = dirty_background_ratio_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "dirty_background_bytes",
.data = &dirty_background_bytes,
.maxlen = sizeof(dirty_background_bytes),
.mode = 0644,
- .proc_handler = &dirty_background_bytes_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = dirty_background_bytes_handler,
.extra1 = &one_ul,
},
{
- .ctl_name = VM_DIRTY_RATIO,
.procname = "dirty_ratio",
.data = &vm_dirty_ratio,
.maxlen = sizeof(vm_dirty_ratio),
.mode = 0644,
- .proc_handler = &dirty_ratio_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = dirty_ratio_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "dirty_bytes",
.data = &vm_dirty_bytes,
.maxlen = sizeof(vm_dirty_bytes),
.mode = 0644,
- .proc_handler = &dirty_bytes_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = dirty_bytes_handler,
.extra1 = &dirty_bytes_min,
},
{
@@ -1127,383 +1025,363 @@ static struct ctl_table vm_table[] = {
.data = &dirty_writeback_interval,
.maxlen = sizeof(dirty_writeback_interval),
.mode = 0644,
- .proc_handler = &dirty_writeback_centisecs_handler,
+ .proc_handler = dirty_writeback_centisecs_handler,
},
{
.procname = "dirty_expire_centisecs",
.data = &dirty_expire_interval,
.maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_NR_PDFLUSH_THREADS,
.procname = "nr_pdflush_threads",
.data = &nr_pdflush_threads,
.maxlen = sizeof nr_pdflush_threads,
.mode = 0444 /* read-only*/,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = VM_SWAPPINESS,
.procname = "swappiness",
.data = &vm_swappiness,
.maxlen = sizeof(vm_swappiness),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one_hundred,
},
#ifdef CONFIG_HUGETLB_PAGE
- {
+ {
.procname = "nr_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &hugetlb_sysctl_handler,
+ .proc_handler = hugetlb_sysctl_handler,
.extra1 = (void *)&hugetlb_zero,
.extra2 = (void *)&hugetlb_infinity,
- },
+ },
+#ifdef CONFIG_NUMA
+ {
+ .procname = "nr_hugepages_mempolicy",
+ .data = NULL,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = &hugetlb_mempolicy_sysctl_handler,
+ .extra1 = (void *)&hugetlb_zero,
+ .extra2 = (void *)&hugetlb_infinity,
+ },
+#endif
{
- .ctl_name = VM_HUGETLB_GROUP,
.procname = "hugetlb_shm_group",
.data = &sysctl_hugetlb_shm_group,
.maxlen = sizeof(gid_t),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "hugepages_treat_as_movable",
.data = &hugepages_treat_as_movable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &hugetlb_treat_movable_handler,
+ .proc_handler = hugetlb_treat_movable_handler,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "nr_overcommit_hugepages",
.data = NULL,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &hugetlb_overcommit_handler,
+ .proc_handler = hugetlb_overcommit_handler,
.extra1 = (void *)&hugetlb_zero,
.extra2 = (void *)&hugetlb_infinity,
},
#endif
{
- .ctl_name = VM_LOWMEM_RESERVE_RATIO,
.procname = "lowmem_reserve_ratio",
.data = &sysctl_lowmem_reserve_ratio,
.maxlen = sizeof(sysctl_lowmem_reserve_ratio),
.mode = 0644,
- .proc_handler = &lowmem_reserve_ratio_sysctl_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = lowmem_reserve_ratio_sysctl_handler,
},
{
- .ctl_name = VM_DROP_PAGECACHE,
.procname = "drop_caches",
.data = &sysctl_drop_caches,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = drop_caches_sysctl_handler,
- .strategy = &sysctl_intvec,
},
{
- .ctl_name = VM_MIN_FREE_KBYTES,
.procname = "min_free_kbytes",
.data = &min_free_kbytes,
.maxlen = sizeof(min_free_kbytes),
.mode = 0644,
- .proc_handler = &min_free_kbytes_sysctl_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = min_free_kbytes_sysctl_handler,
.extra1 = &zero,
},
{
- .ctl_name = VM_PERCPU_PAGELIST_FRACTION,
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
.mode = 0644,
- .proc_handler = &percpu_pagelist_fraction_sysctl_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = percpu_pagelist_fraction_sysctl_handler,
.extra1 = &min_percpu_pagelist_fract,
},
#ifdef CONFIG_MMU
{
- .ctl_name = VM_MAX_MAP_COUNT,
.procname = "max_map_count",
.data = &sysctl_max_map_count,
.maxlen = sizeof(sysctl_max_map_count),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = proc_dointvec,
+ .extra1 = &zero,
},
#else
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "nr_trim_pages",
.data = &sysctl_nr_trim_pages,
.maxlen = sizeof(sysctl_nr_trim_pages),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
#endif
{
- .ctl_name = VM_LAPTOP_MODE,
.procname = "laptop_mode",
.data = &laptop_mode,
.maxlen = sizeof(laptop_mode),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
{
- .ctl_name = VM_BLOCK_DUMP,
.procname = "block_dump",
.data = &block_dump,
.maxlen = sizeof(block_dump),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec,
.extra1 = &zero,
},
{
- .ctl_name = VM_VFS_CACHE_PRESSURE,
.procname = "vfs_cache_pressure",
.data = &sysctl_vfs_cache_pressure,
.maxlen = sizeof(sysctl_vfs_cache_pressure),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec,
.extra1 = &zero,
},
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
{
- .ctl_name = VM_LEGACY_VA_LAYOUT,
.procname = "legacy_va_layout",
.data = &sysctl_legacy_va_layout,
.maxlen = sizeof(sysctl_legacy_va_layout),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec,
.extra1 = &zero,
},
#endif
#ifdef CONFIG_NUMA
{
- .ctl_name = VM_ZONE_RECLAIM_MODE,
.procname = "zone_reclaim_mode",
.data = &zone_reclaim_mode,
.maxlen = sizeof(zone_reclaim_mode),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec,
.extra1 = &zero,
},
{
- .ctl_name = VM_MIN_UNMAPPED,
.procname = "min_unmapped_ratio",
.data = &sysctl_min_unmapped_ratio,
.maxlen = sizeof(sysctl_min_unmapped_ratio),
.mode = 0644,
- .proc_handler = &sysctl_min_unmapped_ratio_sysctl_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
{
- .ctl_name = VM_MIN_SLAB,
.procname = "min_slab_ratio",
.data = &sysctl_min_slab_ratio,
.maxlen = sizeof(sysctl_min_slab_ratio),
.mode = 0644,
- .proc_handler = &sysctl_min_slab_ratio_sysctl_handler,
- .strategy = &sysctl_intvec,
+ .proc_handler = sysctl_min_slab_ratio_sysctl_handler,
.extra1 = &zero,
.extra2 = &one_hundred,
},
#endif
#ifdef CONFIG_SMP
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "stat_interval",
.data = &sysctl_stat_interval,
.maxlen = sizeof(sysctl_stat_interval),
.mode = 0644,
- .proc_handler = &proc_dointvec_jiffies,
- .strategy = &sysctl_jiffies,
+ .proc_handler = proc_dointvec_jiffies,
},
#endif
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "mmap_min_addr",
.data = &dac_mmap_min_addr,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &mmap_min_addr_handler,
+ .proc_handler = mmap_min_addr_handler,
},
#ifdef CONFIG_NUMA
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "numa_zonelist_order",
.data = &numa_zonelist_order,
.maxlen = NUMA_ZONELIST_ORDER_LEN,
.mode = 0644,
- .proc_handler = &numa_zonelist_order_handler,
- .strategy = &sysctl_string,
+ .proc_handler = numa_zonelist_order_handler,
},
#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
(defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
{
- .ctl_name = VM_VDSO_ENABLED,
.procname = "vdso_enabled",
.data = &vdso_enabled,
.maxlen = sizeof(vdso_enabled),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec,
.extra1 = &zero,
},
#endif
#ifdef CONFIG_HIGHMEM
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "highmem_is_dirtyable",
.data = &vm_highmem_is_dirtyable,
.maxlen = sizeof(vm_highmem_is_dirtyable),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "scan_unevictable_pages",
.data = &scan_unevictable_pages,
.maxlen = sizeof(scan_unevictable_pages),
.mode = 0644,
- .proc_handler = &scan_unevictable_handler,
+ .proc_handler = scan_unevictable_handler,
},
+#ifdef CONFIG_MEMORY_FAILURE
+ {
+ .procname = "memory_failure_early_kill",
+ .data = &sysctl_memory_failure_early_kill,
+ .maxlen = sizeof(sysctl_memory_failure_early_kill),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "memory_failure_recovery",
+ .data = &sysctl_memory_failure_recovery,
+ .maxlen = sizeof(sysctl_memory_failure_recovery),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
+
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
*/
- { .ctl_name = 0 }
+ { }
};
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
static struct ctl_table binfmt_misc_table[] = {
- { .ctl_name = 0 }
+ { }
};
#endif
static struct ctl_table fs_table[] = {
{
- .ctl_name = FS_NRINODE,
.procname = "inode-nr",
.data = &inodes_stat,
.maxlen = 2*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = FS_STATINODE,
.procname = "inode-state",
.data = &inodes_stat,
.maxlen = 7*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
.procname = "file-nr",
.data = &files_stat,
.maxlen = 3*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_nr_files,
+ .proc_handler = proc_nr_files,
},
{
- .ctl_name = FS_MAXFILE,
.procname = "file-max",
.data = &files_stat.max_files,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "nr_open",
.data = &sysctl_nr_open,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &sysctl_nr_open_min,
.extra2 = &sysctl_nr_open_max,
},
{
- .ctl_name = FS_DENTRY,
.procname = "dentry-state",
.data = &dentry_stat,
.maxlen = 6*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
{
- .ctl_name = FS_OVERFLOWUID,
.procname = "overflowuid",
.data = &fs_overflowuid,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
{
- .ctl_name = FS_OVERFLOWGID,
.procname = "overflowgid",
.data = &fs_overflowgid,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
#ifdef CONFIG_FILE_LOCKING
{
- .ctl_name = FS_LEASES,
.procname = "leases-enable",
.data = &leases_enable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_DNOTIFY
{
- .ctl_name = FS_DIR_NOTIFY,
.procname = "dir-notify-enable",
.data = &dir_notify_enable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_MMU
#ifdef CONFIG_FILE_LOCKING
{
- .ctl_name = FS_LEASE_TIME,
.procname = "lease-break-time",
.data = &lease_break_time,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = proc_dointvec,
},
#endif
#ifdef CONFIG_AIO
@@ -1512,19 +1390,18 @@ static struct ctl_table fs_table[] = {
.data = &aio_nr,
.maxlen = sizeof(aio_nr),
.mode = 0444,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
},
{
.procname = "aio-max-nr",
.data = &aio_max_nr,
.maxlen = sizeof(aio_max_nr),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
},
#endif /* CONFIG_AIO */
#ifdef CONFIG_INOTIFY_USER
{
- .ctl_name = FS_INOTIFY,
.procname = "inotify",
.mode = 0555,
.child = inotify_table,
@@ -1539,19 +1416,16 @@ static struct ctl_table fs_table[] = {
#endif
#endif
{
- .ctl_name = KERN_SETUID_DUMPABLE,
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
- .strategy = &sysctl_intvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &two,
},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "binfmt_misc",
.mode = 0555,
.child = binfmt_misc_table,
@@ -1561,13 +1435,12 @@ static struct ctl_table fs_table[] = {
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
*/
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table debug_table[] = {
#if defined(CONFIG_X86) || defined(CONFIG_PPC)
{
- .ctl_name = CTL_UNNUMBERED,
.procname = "exception-trace",
.data = &show_unhandled_signals,
.maxlen = sizeof(int),
@@ -1575,11 +1448,11 @@ static struct ctl_table debug_table[] = {
.proc_handler = proc_dointvec
},
#endif
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table dev_table[] = {
- { .ctl_name = 0 }
+ { }
};
static DEFINE_SPINLOCK(sysctl_lock);
@@ -1733,122 +1606,6 @@ void register_sysctl_root(struct ctl_table_root *root)
spin_unlock(&sysctl_lock);
}
-#ifdef CONFIG_SYSCTL_SYSCALL
-/* Perform the actual read/write of a sysctl table entry. */
-static int do_sysctl_strategy(struct ctl_table_root *root,
- struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- int op = 0, rc;
-
- if (oldval)
- op |= MAY_READ;
- if (newval)
- op |= MAY_WRITE;
- if (sysctl_perm(root, table, op))
- return -EPERM;
-
- if (table->strategy) {
- rc = table->strategy(table, oldval, oldlenp, newval, newlen);
- if (rc < 0)
- return rc;
- if (rc > 0)
- return 0;
- }
-
- /* If there is no strategy routine, or if the strategy returns
- * zero, proceed with automatic r/w */
- if (table->data && table->maxlen) {
- rc = sysctl_data(table, oldval, oldlenp, newval, newlen);
- if (rc < 0)
- return rc;
- }
- return 0;
-}
-
-static int parse_table(int __user *name, int nlen,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen,
- struct ctl_table_root *root,
- struct ctl_table *table)
-{
- int n;
-repeat:
- if (!nlen)
- return -ENOTDIR;
- if (get_user(n, name))
- return -EFAULT;
- for ( ; table->ctl_name || table->procname; table++) {
- if (!table->ctl_name)
- continue;
- if (n == table->ctl_name) {
- int error;
- if (table->child) {
- if (sysctl_perm(root, table, MAY_EXEC))
- return -EPERM;
- name++;
- nlen--;
- table = table->child;
- goto repeat;
- }
- error = do_sysctl_strategy(root, table,
- oldval, oldlenp,
- newval, newlen);
- return error;
- }
- }
- return -ENOTDIR;
-}
-
-int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- struct ctl_table_header *head;
- int error = -ENOTDIR;
-
- if (nlen <= 0 || nlen >= CTL_MAXNAME)
- return -ENOTDIR;
- if (oldval) {
- int old_len;
- if (!oldlenp || get_user(old_len, oldlenp))
- return -EFAULT;
- }
-
- for (head = sysctl_head_next(NULL); head;
- head = sysctl_head_next(head)) {
- error = parse_table(name, nlen, oldval, oldlenp,
- newval, newlen,
- head->root, head->ctl_table);
- if (error != -ENOTDIR) {
- sysctl_head_finish(head);
- break;
- }
- }
- return error;
-}
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
- struct __sysctl_args tmp;
- int error;
-
- if (copy_from_user(&tmp, args, sizeof(tmp)))
- return -EFAULT;
-
- error = deprecated_sysctl_warning(&tmp);
- if (error)
- goto out;
-
- lock_kernel();
- error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp,
- tmp.newval, tmp.newlen);
- unlock_kernel();
-out:
- return error;
-}
-#endif /* CONFIG_SYSCTL_SYSCALL */
-
/*
* sysctl_perm does NOT grant the superuser all rights automatically, because
* some sysctl variables are readonly even to root.
@@ -1884,7 +1641,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
{
- for (; table->ctl_name || table->procname; table++) {
+ for (; table->procname; table++) {
table->parent = parent;
if (table->child)
sysctl_set_parent(table, table->child);
@@ -1916,11 +1673,11 @@ static struct ctl_table *is_branch_in(struct ctl_table *branch,
return NULL;
/* ... and nothing else */
- if (branch[1].procname || branch[1].ctl_name)
+ if (branch[1].procname)
return NULL;
/* table should contain subdirectory with the same name */
- for (p = table; p->procname || p->ctl_name; p++) {
+ for (p = table; p->procname; p++) {
if (!p->child)
continue;
if (p->procname && strcmp(p->procname, s) == 0)
@@ -1965,9 +1722,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
*
* The members of the &struct ctl_table structure are used as follows:
*
- * ctl_name - This is the numeric sysctl value used by sysctl(2). The number
- * must be unique within that level of sysctl
- *
* procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
* enter a sysctl file
*
@@ -1982,8 +1736,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
*
* proc_handler - the text handler routine (described below)
*
- * strategy - the strategy routine (described below)
- *
* de - for internal use by the sysctl routines
*
* extra1, extra2 - extra pointers usable by the proc handler routines
@@ -1996,19 +1748,6 @@ static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
* struct enable minimal validation of the values being written to be
* performed, and the mode field allows minimal authentication.
*
- * More sophisticated management can be enabled by the provision of a
- * strategy routine with the table entry. This will be called before
- * any automatic read or write of the data is performed.
- *
- * The strategy routine may return
- *
- * < 0 - Error occurred (error is passed to user process)
- *
- * 0 - OK - proceed with automatic read or write.
- *
- * > 0 - OK - read or write has been done by the strategy routine, so
- * return immediately.
- *
* There must be a proc_handler routine for any terminal nodes
* mirrored under /proc/sys (non-terminals are handled by a built-in
* directory handler). Several default handlers are available to
@@ -2035,13 +1774,13 @@ struct ctl_table_header *__register_sysctl_paths(
struct ctl_table_set *set;
/* Count the path components */
- for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
+ for (npath = 0; path[npath].procname; ++npath)
;
/*
* For each path component, allocate a 2-element ctl_table array.
* The first array element will be filled with the sysctl entry
- * for this, the second will be the sentinel (ctl_name == 0).
+ * for this, the second will be the sentinel (procname == 0).
*
* We allocate everything in one go so that we don't have to
* worry about freeing additional memory in unregister_sysctl_table.
@@ -2058,7 +1797,6 @@ struct ctl_table_header *__register_sysctl_paths(
for (n = 0; n < npath; ++n, ++path) {
/* Copy the procname */
new->procname = path->procname;
- new->ctl_name = path->ctl_name;
new->mode = 0555;
*prevp = new;
@@ -2218,7 +1956,7 @@ void sysctl_head_put(struct ctl_table_header *head)
#ifdef CONFIG_PROC_SYSCTL
static int _proc_do_string(void* data, int maxlen, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
size_t len;
@@ -2279,7 +2017,6 @@ static int _proc_do_string(void* data, int maxlen, int write,
* proc_dostring - read a string sysctl
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2293,10 +2030,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
*
* Returns 0 on success.
*/
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return _proc_do_string(table->data, table->maxlen, write, filp,
+ return _proc_do_string(table->data, table->maxlen, write,
buffer, lenp, ppos);
}
@@ -2321,7 +2058,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
}
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
- int write, struct file *filp, void __user *buffer,
+ int write, void __user *buffer,
size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
@@ -2428,13 +2165,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
#undef TMPBUFLEN
}
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+static int do_proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
- return __do_proc_dointvec(table->data, table, write, filp,
+ return __do_proc_dointvec(table->data, table, write,
buffer, lenp, ppos, conv, data);
}
@@ -2442,7 +2179,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
* proc_dointvec - read a vector of integers
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2452,10 +2188,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
*
* Returns 0 on success.
*/
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
NULL,NULL);
}
@@ -2463,7 +2199,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
* Taint values can only be increased
* This means we can safely use a temporary.
*/
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
@@ -2475,7 +2211,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp,
t = *table;
t.data = &tmptaint;
- err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
@@ -2527,7 +2263,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
* proc_dointvec_minmax - read a vector of integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2540,19 +2275,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
*
* Returns 0 on success.
*/
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct do_proc_dointvec_minmax_conv_param param = {
.min = (int *) table->extra1,
.max = (int *) table->extra2,
};
- return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_minmax_conv, &param);
}
static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
@@ -2657,21 +2391,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
}
static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
unsigned long convdiv)
{
return __do_proc_doulongvec_minmax(table->data, table, write,
- filp, buffer, lenp, ppos, convmul, convdiv);
+ buffer, lenp, ppos, convmul, convdiv);
}
/**
* proc_doulongvec_minmax - read a vector of long integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2684,17 +2416,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
*
* Returns 0 on success.
*/
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+ return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
}
/**
* proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2709,11 +2440,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp
* Returns 0 on success.
*/
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
- return do_proc_doulongvec_minmax(table, write, filp, buffer,
+ return do_proc_doulongvec_minmax(table, write, buffer,
lenp, ppos, HZ, 1000l);
}
@@ -2789,7 +2519,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
* proc_dointvec_jiffies - read a vector of integers as seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2801,10 +2530,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
*
* Returns 0 on success.
*/
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_jiffies_conv,NULL);
}
@@ -2812,7 +2541,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
* proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: pointer to the file position
@@ -2824,10 +2552,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
*
* Returns 0 on success.
*/
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_userhz_jiffies_conv,NULL);
}
@@ -2835,7 +2563,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
* proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
@@ -2848,14 +2575,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
*
* Returns 0 on success.
*/
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_ms_jiffies_conv, NULL);
}
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct pid *new_pid;
@@ -2864,7 +2591,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
tmp = pid_vnr(cad_pid);
- r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+ r = __do_proc_dointvec(&tmp, table, write, buffer,
lenp, ppos, NULL, NULL);
if (r || !write)
return r;
@@ -2879,50 +2606,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
#else /* CONFIG_PROC_FS */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -2932,286 +2658,6 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
#endif /* CONFIG_PROC_FS */
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-/*
- * General sysctl support routines
- */
-
-/* The generic sysctl data routine (used if no strategy routine supplied) */
-int sysctl_data(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- size_t len;
-
- /* Get out of I don't have a variable */
- if (!table->data || !table->maxlen)
- return -ENOTDIR;
-
- if (oldval && oldlenp) {
- if (get_user(len, oldlenp))
- return -EFAULT;
- if (len) {
- if (len > table->maxlen)
- len = table->maxlen;
- if (copy_to_user(oldval, table->data, len))
- return -EFAULT;
- if (put_user(len, oldlenp))
- return -EFAULT;
- }
- }
-
- if (newval && newlen) {
- if (newlen > table->maxlen)
- newlen = table->maxlen;
-
- if (copy_from_user(table->data, newval, newlen))
- return -EFAULT;
- }
- return 1;
-}
-
-/* The generic string strategy routine: */
-int sysctl_string(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- if (!table->data || !table->maxlen)
- return -ENOTDIR;
-
- if (oldval && oldlenp) {
- size_t bufsize;
- if (get_user(bufsize, oldlenp))
- return -EFAULT;
- if (bufsize) {
- size_t len = strlen(table->data), copied;
-
- /* This shouldn't trigger for a well-formed sysctl */
- if (len > table->maxlen)
- len = table->maxlen;
-
- /* Copy up to a max of bufsize-1 bytes of the string */
- copied = (len >= bufsize) ? bufsize - 1 : len;
-
- if (copy_to_user(oldval, table->data, copied) ||
- put_user(0, (char __user *)(oldval + copied)))
- return -EFAULT;
- if (put_user(len, oldlenp))
- return -EFAULT;
- }
- }
- if (newval && newlen) {
- size_t len = newlen;
- if (len > table->maxlen)
- len = table->maxlen;
- if(copy_from_user(table->data, newval, len))
- return -EFAULT;
- if (len == table->maxlen)
- len--;
- ((char *) table->data)[len] = 0;
- }
- return 1;
-}
-
-/*
- * This function makes sure that all of the integers in the vector
- * are between the minimum and maximum values given in the arrays
- * table->extra1 and table->extra2, respectively.
- */
-int sysctl_intvec(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
-
- if (newval && newlen) {
- int __user *vec = (int __user *) newval;
- int *min = (int *) table->extra1;
- int *max = (int *) table->extra2;
- size_t length;
- int i;
-
- if (newlen % sizeof(int) != 0)
- return -EINVAL;
-
- if (!table->extra1 && !table->extra2)
- return 0;
-
- if (newlen > table->maxlen)
- newlen = table->maxlen;
- length = newlen / sizeof(int);
-
- for (i = 0; i < length; i++) {
- int value;
- if (get_user(value, vec + i))
- return -EFAULT;
- if (min && value < min[i])
- return -EINVAL;
- if (max && value > max[i])
- return -EINVAL;
- }
- }
- return 0;
-}
-
-/* Strategy function to convert jiffies to seconds */
-int sysctl_jiffies(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- if (oldval && oldlenp) {
- size_t olen;
-
- if (get_user(olen, oldlenp))
- return -EFAULT;
- if (olen) {
- int val;
-
- if (olen < sizeof(int))
- return -EINVAL;
-
- val = *(int *)(table->data) / HZ;
- if (put_user(val, (int __user *)oldval))
- return -EFAULT;
- if (put_user(sizeof(int), oldlenp))
- return -EFAULT;
- }
- }
- if (newval && newlen) {
- int new;
- if (newlen != sizeof(int))
- return -EINVAL;
- if (get_user(new, (int __user *)newval))
- return -EFAULT;
- *(int *)(table->data) = new*HZ;
- }
- return 1;
-}
-
-/* Strategy function to convert jiffies to seconds */
-int sysctl_ms_jiffies(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- if (oldval && oldlenp) {
- size_t olen;
-
- if (get_user(olen, oldlenp))
- return -EFAULT;
- if (olen) {
- int val;
-
- if (olen < sizeof(int))
- return -EINVAL;
-
- val = jiffies_to_msecs(*(int *)(table->data));
- if (put_user(val, (int __user *)oldval))
- return -EFAULT;
- if (put_user(sizeof(int), oldlenp))
- return -EFAULT;
- }
- }
- if (newval && newlen) {
- int new;
- if (newlen != sizeof(int))
- return -EINVAL;
- if (get_user(new, (int __user *)newval))
- return -EFAULT;
- *(int *)(table->data) = msecs_to_jiffies(new);
- }
- return 1;
-}
-
-
-
-#else /* CONFIG_SYSCTL_SYSCALL */
-
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
- struct __sysctl_args tmp;
- int error;
-
- if (copy_from_user(&tmp, args, sizeof(tmp)))
- return -EFAULT;
-
- error = deprecated_sysctl_warning(&tmp);
-
- /* If no error reading the parameters then just -ENOSYS ... */
- if (!error)
- error = -ENOSYS;
-
- return error;
-}
-
-int sysctl_data(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- return -ENOSYS;
-}
-
-int sysctl_string(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- return -ENOSYS;
-}
-
-int sysctl_intvec(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- return -ENOSYS;
-}
-
-int sysctl_jiffies(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- return -ENOSYS;
-}
-
-int sysctl_ms_jiffies(struct ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- return -ENOSYS;
-}
-
-#endif /* CONFIG_SYSCTL_SYSCALL */
-
-static int deprecated_sysctl_warning(struct __sysctl_args *args)
-{
- static int msg_count;
- int name[CTL_MAXNAME];
- int i;
-
- /* Check args->nlen. */
- if (args->nlen < 0 || args->nlen > CTL_MAXNAME)
- return -ENOTDIR;
-
- /* Read in the sysctl name for better debug message logging */
- for (i = 0; i < args->nlen; i++)
- if (get_user(name[i], args->name + i))
- return -EFAULT;
-
- /* Ignore accesses to kernel.version */
- if ((args->nlen == 2) && (name[0] == CTL_KERN) && (name[1] == KERN_VERSION))
- return 0;
-
- if (msg_count < 5) {
- msg_count++;
- printk(KERN_INFO
- "warning: process `%s' used the deprecated sysctl "
- "system call with ", current->comm);
- for (i = 0; i < args->nlen; i++)
- printk("%d.", name[i]);
- printk("\n");
- }
- return 0;
-}
-
/*
* No sense putting this after each symbol definition, twice,
* exception granted :-)
@@ -3226,9 +2672,4 @@ EXPORT_SYMBOL(proc_doulongvec_minmax);
EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
EXPORT_SYMBOL(register_sysctl_table);
EXPORT_SYMBOL(register_sysctl_paths);
-EXPORT_SYMBOL(sysctl_intvec);
-EXPORT_SYMBOL(sysctl_jiffies);
-EXPORT_SYMBOL(sysctl_ms_jiffies);
-EXPORT_SYMBOL(sysctl_string);
-EXPORT_SYMBOL(sysctl_data);
EXPORT_SYMBOL(unregister_sysctl_table);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
new file mode 100644
index 00000000000..b75dbf40f57
--- /dev/null
+++ b/kernel/sysctl_binary.c
@@ -0,0 +1,1507 @@
+#include <linux/stat.h>
+#include <linux/sysctl.h>
+#include "../fs/xfs/linux-2.6/xfs_sysctl.h"
+#include <linux/sunrpc/debug.h>
+#include <linux/string.h>
+#include <net/ip_vs.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
+#include <linux/file.h>
+#include <linux/ctype.h>
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+
+struct bin_table;
+typedef ssize_t bin_convert_t(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen);
+
+static bin_convert_t bin_dir;
+static bin_convert_t bin_string;
+static bin_convert_t bin_intvec;
+static bin_convert_t bin_ulongvec;
+static bin_convert_t bin_uuid;
+static bin_convert_t bin_dn_node_address;
+
+#define CTL_DIR bin_dir
+#define CTL_STR bin_string
+#define CTL_INT bin_intvec
+#define CTL_ULONG bin_ulongvec
+#define CTL_UUID bin_uuid
+#define CTL_DNADR bin_dn_node_address
+
+#define BUFSZ 256
+
+struct bin_table {
+ bin_convert_t *convert;
+ int ctl_name;
+ const char *procname;
+ const struct bin_table *child;
+};
+
+static const struct bin_table bin_random_table[] = {
+ { CTL_INT, RANDOM_POOLSIZE, "poolsize" },
+ { CTL_INT, RANDOM_ENTROPY_COUNT, "entropy_avail" },
+ { CTL_INT, RANDOM_READ_THRESH, "read_wakeup_threshold" },
+ { CTL_INT, RANDOM_WRITE_THRESH, "write_wakeup_threshold" },
+ { CTL_UUID, RANDOM_BOOT_ID, "boot_id" },
+ { CTL_UUID, RANDOM_UUID, "uuid" },
+ {}
+};
+
+static const struct bin_table bin_pty_table[] = {
+ { CTL_INT, PTY_MAX, "max" },
+ { CTL_INT, PTY_NR, "nr" },
+ {}
+};
+
+static const struct bin_table bin_kern_table[] = {
+ { CTL_STR, KERN_OSTYPE, "ostype" },
+ { CTL_STR, KERN_OSRELEASE, "osrelease" },
+ /* KERN_OSREV not used */
+ { CTL_STR, KERN_VERSION, "version" },
+ /* KERN_SECUREMASK not used */
+ /* KERN_PROF not used */
+ { CTL_STR, KERN_NODENAME, "hostname" },
+ { CTL_STR, KERN_DOMAINNAME, "domainname" },
+
+ { CTL_INT, KERN_PANIC, "panic" },
+ { CTL_INT, KERN_REALROOTDEV, "real-root-dev" },
+
+ { CTL_STR, KERN_SPARC_REBOOT, "reboot-cmd" },
+ { CTL_INT, KERN_CTLALTDEL, "ctrl-alt-del" },
+ { CTL_INT, KERN_PRINTK, "printk" },
+
+ /* KERN_NAMETRANS not used */
+ /* KERN_PPC_HTABRECLAIM not used */
+ /* KERN_PPC_ZEROPAGED not used */
+ { CTL_INT, KERN_PPC_POWERSAVE_NAP, "powersave-nap" },
+
+ { CTL_STR, KERN_MODPROBE, "modprobe" },
+ { CTL_INT, KERN_SG_BIG_BUFF, "sg-big-buff" },
+ { CTL_INT, KERN_ACCT, "acct" },
+ /* KERN_PPC_L2CR "l2cr" no longer used */
+
+ /* KERN_RTSIGNR not used */
+ /* KERN_RTSIGMAX not used */
+
+ { CTL_ULONG, KERN_SHMMAX, "shmmax" },
+ { CTL_INT, KERN_MSGMAX, "msgmax" },
+ { CTL_INT, KERN_MSGMNB, "msgmnb" },
+ /* KERN_MSGPOOL not used*/
+ { CTL_INT, KERN_SYSRQ, "sysrq" },
+ { CTL_INT, KERN_MAX_THREADS, "threads-max" },
+ { CTL_DIR, KERN_RANDOM, "random", bin_random_table },
+ { CTL_ULONG, KERN_SHMALL, "shmall" },
+ { CTL_INT, KERN_MSGMNI, "msgmni" },
+ { CTL_INT, KERN_SEM, "sem" },
+ { CTL_INT, KERN_SPARC_STOP_A, "stop-a" },
+ { CTL_INT, KERN_SHMMNI, "shmmni" },
+
+ { CTL_INT, KERN_OVERFLOWUID, "overflowuid" },
+ { CTL_INT, KERN_OVERFLOWGID, "overflowgid" },
+
+ { CTL_STR, KERN_HOTPLUG, "hotplug", },
+ { CTL_INT, KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" },
+
+ { CTL_INT, KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" },
+ { CTL_INT, KERN_CORE_USES_PID, "core_uses_pid" },
+ /* KERN_TAINTED "tainted" no longer used */
+ { CTL_INT, KERN_CADPID, "cad_pid" },
+ { CTL_INT, KERN_PIDMAX, "pid_max" },
+ { CTL_STR, KERN_CORE_PATTERN, "core_pattern" },
+ { CTL_INT, KERN_PANIC_ON_OOPS, "panic_on_oops" },
+ { CTL_INT, KERN_HPPA_PWRSW, "soft-power" },
+ { CTL_INT, KERN_HPPA_UNALIGNED, "unaligned-trap" },
+
+ { CTL_INT, KERN_PRINTK_RATELIMIT, "printk_ratelimit" },
+ { CTL_INT, KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" },
+
+ { CTL_DIR, KERN_PTY, "pty", bin_pty_table },
+ { CTL_INT, KERN_NGROUPS_MAX, "ngroups_max" },
+ { CTL_INT, KERN_SPARC_SCONS_PWROFF, "scons-poweroff" },
+ /* KERN_HZ_TIMER "hz_timer" no longer used */
+ { CTL_INT, KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" },
+ { CTL_INT, KERN_BOOTLOADER_TYPE, "bootloader_type" },
+ { CTL_INT, KERN_RANDOMIZE, "randomize_va_space" },
+
+ { CTL_INT, KERN_SPIN_RETRY, "spin_retry" },
+ /* KERN_ACPI_VIDEO_FLAGS "acpi_video_flags" no longer used */
+ { CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" },
+ { CTL_INT, KERN_COMPAT_LOG, "compat-log" },
+ { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" },
+ { CTL_INT, KERN_NMI_WATCHDOG, "nmi_watchdog" },
+ { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" },
+ {}
+};
+
+static const struct bin_table bin_vm_table[] = {
+ { CTL_INT, VM_OVERCOMMIT_MEMORY, "overcommit_memory" },
+ { CTL_INT, VM_PAGE_CLUSTER, "page-cluster" },
+ { CTL_INT, VM_DIRTY_BACKGROUND, "dirty_background_ratio" },
+ { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" },
+ /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */
+ /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */
+ { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" },
+ { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" },
+ /* VM_PAGEBUF unused */
+ /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */
+ { CTL_INT, VM_SWAPPINESS, "swappiness" },
+ { CTL_INT, VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" },
+ { CTL_INT, VM_MIN_FREE_KBYTES, "min_free_kbytes" },
+ { CTL_INT, VM_MAX_MAP_COUNT, "max_map_count" },
+ { CTL_INT, VM_LAPTOP_MODE, "laptop_mode" },
+ { CTL_INT, VM_BLOCK_DUMP, "block_dump" },
+ { CTL_INT, VM_HUGETLB_GROUP, "hugetlb_shm_group" },
+ { CTL_INT, VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" },
+ { CTL_INT, VM_LEGACY_VA_LAYOUT, "legacy_va_layout" },
+ /* VM_SWAP_TOKEN_TIMEOUT unused */
+ { CTL_INT, VM_DROP_PAGECACHE, "drop_caches" },
+ { CTL_INT, VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" },
+ { CTL_INT, VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" },
+ { CTL_INT, VM_MIN_UNMAPPED, "min_unmapped_ratio" },
+ { CTL_INT, VM_PANIC_ON_OOM, "panic_on_oom" },
+ { CTL_INT, VM_VDSO_ENABLED, "vdso_enabled" },
+ { CTL_INT, VM_MIN_SLAB, "min_slab_ratio" },
+
+ {}
+};
+
+static const struct bin_table bin_net_core_table[] = {
+ { CTL_INT, NET_CORE_WMEM_MAX, "wmem_max" },
+ { CTL_INT, NET_CORE_RMEM_MAX, "rmem_max" },
+ { CTL_INT, NET_CORE_WMEM_DEFAULT, "wmem_default" },
+ { CTL_INT, NET_CORE_RMEM_DEFAULT, "rmem_default" },
+ /* NET_CORE_DESTROY_DELAY unused */
+ { CTL_INT, NET_CORE_MAX_BACKLOG, "netdev_max_backlog" },
+ /* NET_CORE_FASTROUTE unused */
+ { CTL_INT, NET_CORE_MSG_COST, "message_cost" },
+ { CTL_INT, NET_CORE_MSG_BURST, "message_burst" },
+ { CTL_INT, NET_CORE_OPTMEM_MAX, "optmem_max" },
+ /* NET_CORE_HOT_LIST_LENGTH unused */
+ /* NET_CORE_DIVERT_VERSION unused */
+ /* NET_CORE_NO_CONG_THRESH unused */
+ /* NET_CORE_NO_CONG unused */
+ /* NET_CORE_LO_CONG unused */
+ /* NET_CORE_MOD_CONG unused */
+ { CTL_INT, NET_CORE_DEV_WEIGHT, "dev_weight" },
+ { CTL_INT, NET_CORE_SOMAXCONN, "somaxconn" },
+ { CTL_INT, NET_CORE_BUDGET, "netdev_budget" },
+ { CTL_INT, NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" },
+ { CTL_INT, NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" },
+ { CTL_INT, NET_CORE_WARNINGS, "warnings" },
+ {},
+};
+
+static const struct bin_table bin_net_unix_table[] = {
+ /* NET_UNIX_DESTROY_DELAY unused */
+ /* NET_UNIX_DELETE_DELAY unused */
+ { CTL_INT, NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv4_route_table[] = {
+ { CTL_INT, NET_IPV4_ROUTE_FLUSH, "flush" },
+ /* NET_IPV4_ROUTE_MIN_DELAY "min_delay" no longer used */
+ /* NET_IPV4_ROUTE_MAX_DELAY "max_delay" no longer used */
+ { CTL_INT, NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" },
+ { CTL_INT, NET_IPV4_ROUTE_MAX_SIZE, "max_size" },
+ { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" },
+ { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" },
+ { CTL_INT, NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" },
+ { CTL_INT, NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" },
+ { CTL_INT, NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" },
+ { CTL_INT, NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" },
+ { CTL_INT, NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" },
+ { CTL_INT, NET_IPV4_ROUTE_ERROR_COST, "error_cost" },
+ { CTL_INT, NET_IPV4_ROUTE_ERROR_BURST, "error_burst" },
+ { CTL_INT, NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" },
+ { CTL_INT, NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" },
+ { CTL_INT, NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" },
+ { CTL_INT, NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" },
+ { CTL_INT, NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv4_conf_vars_table[] = {
+ { CTL_INT, NET_IPV4_CONF_FORWARDING, "forwarding" },
+ { CTL_INT, NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" },
+
+ { CTL_INT, NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" },
+ { CTL_INT, NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" },
+ { CTL_INT, NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" },
+ { CTL_INT, NET_IPV4_CONF_SHARED_MEDIA, "shared_media" },
+ { CTL_INT, NET_IPV4_CONF_RP_FILTER, "rp_filter" },
+ { CTL_INT, NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" },
+ { CTL_INT, NET_IPV4_CONF_PROXY_ARP, "proxy_arp" },
+ { CTL_INT, NET_IPV4_CONF_MEDIUM_ID, "medium_id" },
+ { CTL_INT, NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" },
+ { CTL_INT, NET_IPV4_CONF_LOG_MARTIANS, "log_martians" },
+ { CTL_INT, NET_IPV4_CONF_TAG, "tag" },
+ { CTL_INT, NET_IPV4_CONF_ARPFILTER, "arp_filter" },
+ { CTL_INT, NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" },
+ { CTL_INT, NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" },
+ { CTL_INT, NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" },
+ { CTL_INT, NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" },
+
+ { CTL_INT, NET_IPV4_CONF_NOXFRM, "disable_xfrm" },
+ { CTL_INT, NET_IPV4_CONF_NOPOLICY, "disable_policy" },
+ { CTL_INT, NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" },
+ { CTL_INT, NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv4_conf_table[] = {
+ { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv4_conf_vars_table },
+ { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv4_conf_vars_table },
+ { CTL_DIR, 0, NULL, bin_net_ipv4_conf_vars_table },
+ {}
+};
+
+static const struct bin_table bin_net_neigh_vars_table[] = {
+ { CTL_INT, NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" },
+ { CTL_INT, NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" },
+ { CTL_INT, NET_NEIGH_APP_SOLICIT, "app_solicit" },
+ /* NET_NEIGH_RETRANS_TIME "retrans_time" no longer used */
+ { CTL_INT, NET_NEIGH_REACHABLE_TIME, "base_reachable_time" },
+ { CTL_INT, NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" },
+ { CTL_INT, NET_NEIGH_GC_STALE_TIME, "gc_stale_time" },
+ { CTL_INT, NET_NEIGH_UNRES_QLEN, "unres_qlen" },
+ { CTL_INT, NET_NEIGH_PROXY_QLEN, "proxy_qlen" },
+ /* NET_NEIGH_ANYCAST_DELAY "anycast_delay" no longer used */
+ /* NET_NEIGH_PROXY_DELAY "proxy_delay" no longer used */
+ /* NET_NEIGH_LOCKTIME "locktime" no longer used */
+ { CTL_INT, NET_NEIGH_GC_INTERVAL, "gc_interval" },
+ { CTL_INT, NET_NEIGH_GC_THRESH1, "gc_thresh1" },
+ { CTL_INT, NET_NEIGH_GC_THRESH2, "gc_thresh2" },
+ { CTL_INT, NET_NEIGH_GC_THRESH3, "gc_thresh3" },
+ { CTL_INT, NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" },
+ { CTL_INT, NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" },
+ {}
+};
+
+static const struct bin_table bin_net_neigh_table[] = {
+ { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_neigh_vars_table },
+ { CTL_DIR, 0, NULL, bin_net_neigh_vars_table },
+ {}
+};
+
+static const struct bin_table bin_net_ipv4_netfilter_table[] = {
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" },
+
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "ip_conntrack_tcp_timeout_syn_sent" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "ip_conntrack_tcp_timeout_syn_recv" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "ip_conntrack_tcp_timeout_established" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "ip_conntrack_tcp_timeout_fin_wait" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "ip_conntrack_tcp_timeout_close_wait" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "ip_conntrack_tcp_timeout_last_ack" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "ip_conntrack_tcp_timeout_time_wait" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "ip_conntrack_tcp_timeout_close" no longer used */
+
+ /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT "ip_conntrack_udp_timeout" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM "ip_conntrack_udp_timeout_stream" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT "ip_conntrack_icmp_timeout" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT "ip_conntrack_generic_timeout" no longer used */
+
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" },
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" },
+ /* NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "ip_conntrack_tcp_timeout_max_retrans" no longer used */
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" },
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" },
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" },
+
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "ip_conntrack_sctp_timeout_closed" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "ip_conntrack_sctp_timeout_cookie_wait" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "ip_conntrack_sctp_timeout_cookie_echoed" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "ip_conntrack_sctp_timeout_established" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "ip_conntrack_sctp_timeout_shutdown_sent" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "ip_conntrack_sctp_timeout_shutdown_recd" no longer used */
+ /* NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "ip_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */
+
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" },
+ { CTL_INT, NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv4_table[] = {
+ {CTL_INT, NET_IPV4_FORWARD, "ip_forward" },
+
+ { CTL_DIR, NET_IPV4_CONF, "conf", bin_net_ipv4_conf_table },
+ { CTL_DIR, NET_IPV4_NEIGH, "neigh", bin_net_neigh_table },
+ { CTL_DIR, NET_IPV4_ROUTE, "route", bin_net_ipv4_route_table },
+ /* NET_IPV4_FIB_HASH unused */
+ { CTL_DIR, NET_IPV4_NETFILTER, "netfilter", bin_net_ipv4_netfilter_table },
+
+ { CTL_INT, NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" },
+ { CTL_INT, NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" },
+ { CTL_INT, NET_IPV4_TCP_SACK, "tcp_sack" },
+ { CTL_INT, NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" },
+ { CTL_INT, NET_IPV4_DEFAULT_TTL, "ip_default_ttl" },
+ /* NET_IPV4_AUTOCONFIG unused */
+ { CTL_INT, NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" },
+ { CTL_INT, NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" },
+ { CTL_INT, NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" },
+ { CTL_INT, NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" },
+ { CTL_INT, NET_TCP_MAX_ORPHANS, "tcp_max_orphans" },
+ { CTL_INT, NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" },
+ { CTL_INT, NET_IPV4_DYNADDR, "ip_dynaddr" },
+ { CTL_INT, NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" },
+ { CTL_INT, NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" },
+ { CTL_INT, NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" },
+ { CTL_INT, NET_IPV4_TCP_RETRIES1, "tcp_retries1" },
+ { CTL_INT, NET_IPV4_TCP_RETRIES2, "tcp_retries2" },
+ { CTL_INT, NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" },
+ { CTL_INT, NET_TCP_SYNCOOKIES, "tcp_syncookies" },
+ { CTL_INT, NET_TCP_TW_RECYCLE, "tcp_tw_recycle" },
+ { CTL_INT, NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" },
+ { CTL_INT, NET_TCP_STDURG, "tcp_stdurg" },
+ { CTL_INT, NET_TCP_RFC1337, "tcp_rfc1337" },
+ { CTL_INT, NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" },
+ { CTL_INT, NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" },
+ { CTL_INT, NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" },
+ { CTL_INT, NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" },
+ { CTL_INT, NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" },
+ { CTL_INT, NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" },
+ { CTL_INT, NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" },
+ { CTL_INT, NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" },
+ { CTL_INT, NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" },
+ { CTL_INT, NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" },
+ { CTL_INT, NET_TCP_FACK, "tcp_fack" },
+ { CTL_INT, NET_TCP_REORDERING, "tcp_reordering" },
+ { CTL_INT, NET_TCP_ECN, "tcp_ecn" },
+ { CTL_INT, NET_TCP_DSACK, "tcp_dsack" },
+ { CTL_INT, NET_TCP_MEM, "tcp_mem" },
+ { CTL_INT, NET_TCP_WMEM, "tcp_wmem" },
+ { CTL_INT, NET_TCP_RMEM, "tcp_rmem" },
+ { CTL_INT, NET_TCP_APP_WIN, "tcp_app_win" },
+ { CTL_INT, NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" },
+ { CTL_INT, NET_TCP_TW_REUSE, "tcp_tw_reuse" },
+ { CTL_INT, NET_TCP_FRTO, "tcp_frto" },
+ { CTL_INT, NET_TCP_FRTO_RESPONSE, "tcp_frto_response" },
+ { CTL_INT, NET_TCP_LOW_LATENCY, "tcp_low_latency" },
+ { CTL_INT, NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" },
+ { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" },
+ { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" },
+ { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" },
+ { CTL_INT, NET_TCP_ABC, "tcp_abc" },
+ { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" },
+ { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" },
+ { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" },
+ { CTL_INT, NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" },
+ { CTL_INT, NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" },
+ { CTL_INT, NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" },
+ { CTL_INT, NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" },
+ { CTL_INT, NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" },
+ { CTL_INT, NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" },
+ /* NET_TCP_AVAIL_CONG_CONTROL "tcp_available_congestion_control" no longer used */
+ { CTL_STR, NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" },
+ { CTL_INT, NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" },
+
+ { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" },
+ { CTL_INT, NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" },
+ { CTL_INT, NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" },
+ { CTL_INT, NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" },
+ { CTL_INT, NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" },
+ { CTL_INT, NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" },
+
+ { CTL_INT, NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" },
+ { CTL_INT, NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" },
+ { CTL_INT, NET_IPV4_IPFRAG_TIME, "ipfrag_time" },
+
+ { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" },
+ /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */
+
+ { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" },
+
+ /* NET_TCP_DEFAULT_WIN_SCALE unused */
+ /* NET_TCP_BIC_BETA unused */
+ /* NET_IPV4_TCP_MAX_KA_PROBES unused */
+ /* NET_IPV4_IP_MASQ_DEBUG unused */
+ /* NET_TCP_SYN_TAILDROP unused */
+ /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */
+ /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */
+ /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */
+ /* NET_IPV4_ICMP_PARAMPROB_RATE unused */
+ /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */
+ /* NET_IPV4_ALWAYS_DEFRAG unused */
+ {}
+};
+
+static const struct bin_table bin_net_ipx_table[] = {
+ { CTL_INT, NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" },
+ /* NET_IPX_FORWARDING unused */
+ {}
+};
+
+static const struct bin_table bin_net_atalk_table[] = {
+ { CTL_INT, NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" },
+ { CTL_INT, NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" },
+ { CTL_INT, NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" },
+ { CTL_INT, NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" },
+ {},
+};
+
+static const struct bin_table bin_net_netrom_table[] = {
+ { CTL_INT, NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" },
+ { CTL_INT, NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" },
+ { CTL_INT, NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" },
+ { CTL_INT, NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" },
+ { CTL_INT, NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" },
+ { CTL_INT, NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" },
+ { CTL_INT, NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" },
+ { CTL_INT, NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" },
+ { CTL_INT, NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" },
+ { CTL_INT, NET_NETROM_ROUTING_CONTROL, "routing_control" },
+ { CTL_INT, NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" },
+ { CTL_INT, NET_NETROM_RESET, "reset" },
+ {}
+};
+
+static const struct bin_table bin_net_ax25_param_table[] = {
+ { CTL_INT, NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" },
+ { CTL_INT, NET_AX25_DEFAULT_MODE, "ax25_default_mode" },
+ { CTL_INT, NET_AX25_BACKOFF_TYPE, "backoff_type" },
+ { CTL_INT, NET_AX25_CONNECT_MODE, "connect_mode" },
+ { CTL_INT, NET_AX25_STANDARD_WINDOW, "standard_window_size" },
+ { CTL_INT, NET_AX25_EXTENDED_WINDOW, "extended_window_size" },
+ { CTL_INT, NET_AX25_T1_TIMEOUT, "t1_timeout" },
+ { CTL_INT, NET_AX25_T2_TIMEOUT, "t2_timeout" },
+ { CTL_INT, NET_AX25_T3_TIMEOUT, "t3_timeout" },
+ { CTL_INT, NET_AX25_IDLE_TIMEOUT, "idle_timeout" },
+ { CTL_INT, NET_AX25_N2, "maximum_retry_count" },
+ { CTL_INT, NET_AX25_PACLEN, "maximum_packet_length" },
+ { CTL_INT, NET_AX25_PROTOCOL, "protocol" },
+ { CTL_INT, NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" },
+ {}
+};
+
+static const struct bin_table bin_net_ax25_table[] = {
+ { CTL_DIR, 0, NULL, bin_net_ax25_param_table },
+ {}
+};
+
+static const struct bin_table bin_net_rose_table[] = {
+ { CTL_INT, NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" },
+ { CTL_INT, NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" },
+ { CTL_INT, NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" },
+ { CTL_INT, NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" },
+ { CTL_INT, NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" },
+ { CTL_INT, NET_ROSE_ROUTING_CONTROL, "routing_control" },
+ { CTL_INT, NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" },
+ { CTL_INT, NET_ROSE_MAX_VCS, "maximum_virtual_circuits" },
+ { CTL_INT, NET_ROSE_WINDOW_SIZE, "window_size" },
+ { CTL_INT, NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv6_conf_var_table[] = {
+ { CTL_INT, NET_IPV6_FORWARDING, "forwarding" },
+ { CTL_INT, NET_IPV6_HOP_LIMIT, "hop_limit" },
+ { CTL_INT, NET_IPV6_MTU, "mtu" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA, "accept_ra" },
+ { CTL_INT, NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" },
+ { CTL_INT, NET_IPV6_AUTOCONF, "autoconf" },
+ { CTL_INT, NET_IPV6_DAD_TRANSMITS, "dad_transmits" },
+ { CTL_INT, NET_IPV6_RTR_SOLICITS, "router_solicitations" },
+ { CTL_INT, NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" },
+ { CTL_INT, NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" },
+ { CTL_INT, NET_IPV6_USE_TEMPADDR, "use_tempaddr" },
+ { CTL_INT, NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" },
+ { CTL_INT, NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" },
+ { CTL_INT, NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" },
+ { CTL_INT, NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" },
+ { CTL_INT, NET_IPV6_MAX_ADDRESSES, "max_addresses" },
+ { CTL_INT, NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" },
+ { CTL_INT, NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" },
+ { CTL_INT, NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" },
+ { CTL_INT, NET_IPV6_PROXY_NDP, "proxy_ndp" },
+ { CTL_INT, NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv6_conf_table[] = {
+ { CTL_DIR, NET_PROTO_CONF_ALL, "all", bin_net_ipv6_conf_var_table },
+ { CTL_DIR, NET_PROTO_CONF_DEFAULT, "default", bin_net_ipv6_conf_var_table },
+ { CTL_DIR, 0, NULL, bin_net_ipv6_conf_var_table },
+ {}
+};
+
+static const struct bin_table bin_net_ipv6_route_table[] = {
+ /* NET_IPV6_ROUTE_FLUSH "flush" no longer used */
+ { CTL_INT, NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" },
+ { CTL_INT, NET_IPV6_ROUTE_MAX_SIZE, "max_size" },
+ { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" },
+ { CTL_INT, NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" },
+ { CTL_INT, NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" },
+ { CTL_INT, NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" },
+ { CTL_INT, NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" },
+ { CTL_INT, NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" },
+ { CTL_INT, NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv6_icmp_table[] = {
+ { CTL_INT, NET_IPV6_ICMP_RATELIMIT, "ratelimit" },
+ {}
+};
+
+static const struct bin_table bin_net_ipv6_table[] = {
+ { CTL_DIR, NET_IPV6_CONF, "conf", bin_net_ipv6_conf_table },
+ { CTL_DIR, NET_IPV6_NEIGH, "neigh", bin_net_neigh_table },
+ { CTL_DIR, NET_IPV6_ROUTE, "route", bin_net_ipv6_route_table },
+ { CTL_DIR, NET_IPV6_ICMP, "icmp", bin_net_ipv6_icmp_table },
+ { CTL_INT, NET_IPV6_BINDV6ONLY, "bindv6only" },
+ { CTL_INT, NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" },
+ { CTL_INT, NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" },
+ { CTL_INT, NET_IPV6_IP6FRAG_TIME, "ip6frag_time" },
+ { CTL_INT, NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" },
+ { CTL_INT, NET_IPV6_MLD_MAX_MSF, "mld_max_msf" },
+ { CTL_INT, 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" },
+ {}
+};
+
+static const struct bin_table bin_net_x25_table[] = {
+ { CTL_INT, NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" },
+ { CTL_INT, NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" },
+ { CTL_INT, NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" },
+ { CTL_INT, NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" },
+ { CTL_INT, NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" },
+ { CTL_INT, NET_X25_FORWARD, "x25_forward" },
+ {}
+};
+
+static const struct bin_table bin_net_tr_table[] = {
+ { CTL_INT, NET_TR_RIF_TIMEOUT, "rif_timeout" },
+ {}
+};
+
+
+static const struct bin_table bin_net_decnet_conf_vars[] = {
+ { CTL_INT, NET_DECNET_CONF_DEV_FORWARDING, "forwarding" },
+ { CTL_INT, NET_DECNET_CONF_DEV_PRIORITY, "priority" },
+ { CTL_INT, NET_DECNET_CONF_DEV_T2, "t2" },
+ { CTL_INT, NET_DECNET_CONF_DEV_T3, "t3" },
+ {}
+};
+
+static const struct bin_table bin_net_decnet_conf[] = {
+ { CTL_DIR, NET_DECNET_CONF_ETHER, "ethernet", bin_net_decnet_conf_vars },
+ { CTL_DIR, NET_DECNET_CONF_GRE, "ipgre", bin_net_decnet_conf_vars },
+ { CTL_DIR, NET_DECNET_CONF_X25, "x25", bin_net_decnet_conf_vars },
+ { CTL_DIR, NET_DECNET_CONF_PPP, "ppp", bin_net_decnet_conf_vars },
+ { CTL_DIR, NET_DECNET_CONF_DDCMP, "ddcmp", bin_net_decnet_conf_vars },
+ { CTL_DIR, NET_DECNET_CONF_LOOPBACK, "loopback", bin_net_decnet_conf_vars },
+ { CTL_DIR, 0, NULL, bin_net_decnet_conf_vars },
+ {}
+};
+
+static const struct bin_table bin_net_decnet_table[] = {
+ { CTL_DIR, NET_DECNET_CONF, "conf", bin_net_decnet_conf },
+ { CTL_DNADR, NET_DECNET_NODE_ADDRESS, "node_address" },
+ { CTL_STR, NET_DECNET_NODE_NAME, "node_name" },
+ { CTL_STR, NET_DECNET_DEFAULT_DEVICE, "default_device" },
+ { CTL_INT, NET_DECNET_TIME_WAIT, "time_wait" },
+ { CTL_INT, NET_DECNET_DN_COUNT, "dn_count" },
+ { CTL_INT, NET_DECNET_DI_COUNT, "di_count" },
+ { CTL_INT, NET_DECNET_DR_COUNT, "dr_count" },
+ { CTL_INT, NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" },
+ { CTL_INT, NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" },
+ { CTL_INT, NET_DECNET_MEM, "decnet_mem" },
+ { CTL_INT, NET_DECNET_RMEM, "decnet_rmem" },
+ { CTL_INT, NET_DECNET_WMEM, "decnet_wmem" },
+ { CTL_INT, NET_DECNET_DEBUG_LEVEL, "debug" },
+ {}
+};
+
+static const struct bin_table bin_net_sctp_table[] = {
+ { CTL_INT, NET_SCTP_RTO_INITIAL, "rto_initial" },
+ { CTL_INT, NET_SCTP_RTO_MIN, "rto_min" },
+ { CTL_INT, NET_SCTP_RTO_MAX, "rto_max" },
+ { CTL_INT, NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" },
+ { CTL_INT, NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" },
+ { CTL_INT, NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" },
+ { CTL_INT, NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" },
+ { CTL_INT, NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" },
+ { CTL_INT, NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" },
+ { CTL_INT, NET_SCTP_HB_INTERVAL, "hb_interval" },
+ { CTL_INT, NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" },
+ { CTL_INT, NET_SCTP_MAX_BURST, "max_burst" },
+ { CTL_INT, NET_SCTP_ADDIP_ENABLE, "addip_enable" },
+ { CTL_INT, NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" },
+ { CTL_INT, NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" },
+ { CTL_INT, NET_SCTP_SACK_TIMEOUT, "sack_timeout" },
+ { CTL_INT, NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" },
+ {}
+};
+
+static const struct bin_table bin_net_llc_llc2_timeout_table[] = {
+ { CTL_INT, NET_LLC2_ACK_TIMEOUT, "ack" },
+ { CTL_INT, NET_LLC2_P_TIMEOUT, "p" },
+ { CTL_INT, NET_LLC2_REJ_TIMEOUT, "rej" },
+ { CTL_INT, NET_LLC2_BUSY_TIMEOUT, "busy" },
+ {}
+};
+
+static const struct bin_table bin_net_llc_station_table[] = {
+ { CTL_INT, NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" },
+ {}
+};
+
+static const struct bin_table bin_net_llc_llc2_table[] = {
+ { CTL_DIR, NET_LLC2, "timeout", bin_net_llc_llc2_timeout_table },
+ {}
+};
+
+static const struct bin_table bin_net_llc_table[] = {
+ { CTL_DIR, NET_LLC2, "llc2", bin_net_llc_llc2_table },
+ { CTL_DIR, NET_LLC_STATION, "station", bin_net_llc_station_table },
+ {}
+};
+
+static const struct bin_table bin_net_netfilter_table[] = {
+ { CTL_INT, NET_NF_CONNTRACK_MAX, "nf_conntrack_max" },
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT "nf_conntrack_tcp_timeout_syn_sent" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV "nf_conntrack_tcp_timeout_syn_recv" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED "nf_conntrack_tcp_timeout_established" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT "nf_conntrack_tcp_timeout_fin_wait" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT "nf_conntrack_tcp_timeout_close_wait" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK "nf_conntrack_tcp_timeout_last_ack" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT "nf_conntrack_tcp_timeout_time_wait" no longer used */
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE "nf_conntrack_tcp_timeout_close" no longer used */
+ /* NET_NF_CONNTRACK_UDP_TIMEOUT "nf_conntrack_udp_timeout" no longer used */
+ /* NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM "nf_conntrack_udp_timeout_stream" no longer used */
+ /* NET_NF_CONNTRACK_ICMP_TIMEOUT "nf_conntrack_icmp_timeout" no longer used */
+ /* NET_NF_CONNTRACK_GENERIC_TIMEOUT "nf_conntrack_generic_timeout" no longer used */
+ { CTL_INT, NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" },
+ { CTL_INT, NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" },
+ /* NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS "nf_conntrack_tcp_timeout_max_retrans" no longer used */
+ { CTL_INT, NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" },
+ { CTL_INT, NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" },
+ { CTL_INT, NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" },
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED "nf_conntrack_sctp_timeout_closed" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT "nf_conntrack_sctp_timeout_cookie_wait" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED "nf_conntrack_sctp_timeout_cookie_echoed" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED "nf_conntrack_sctp_timeout_established" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT "nf_conntrack_sctp_timeout_shutdown_sent" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD "nf_conntrack_sctp_timeout_shutdown_recd" no longer used */
+ /* NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT "nf_conntrack_sctp_timeout_shutdown_ack_sent" no longer used */
+ { CTL_INT, NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" },
+ /* NET_NF_CONNTRACK_ICMPV6_TIMEOUT "nf_conntrack_icmpv6_timeout" no longer used */
+ /* NET_NF_CONNTRACK_FRAG6_TIMEOUT "nf_conntrack_frag6_timeout" no longer used */
+ { CTL_INT, NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" },
+ { CTL_INT, NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" },
+ { CTL_INT, NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" },
+
+ {}
+};
+
+static const struct bin_table bin_net_irda_table[] = {
+ { CTL_INT, NET_IRDA_DISCOVERY, "discovery" },
+ { CTL_STR, NET_IRDA_DEVNAME, "devname" },
+ { CTL_INT, NET_IRDA_DEBUG, "debug" },
+ { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" },
+ { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" },
+ { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" },
+ { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" },
+ { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" },
+ { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" },
+ { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" },
+ { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" },
+ { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" },
+ { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" },
+ { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" },
+ {}
+};
+
+static const struct bin_table bin_net_table[] = {
+ { CTL_DIR, NET_CORE, "core", bin_net_core_table },
+ /* NET_ETHER not used */
+ /* NET_802 not used */
+ { CTL_DIR, NET_UNIX, "unix", bin_net_unix_table },
+ { CTL_DIR, NET_IPV4, "ipv4", bin_net_ipv4_table },
+ { CTL_DIR, NET_IPX, "ipx", bin_net_ipx_table },
+ { CTL_DIR, NET_ATALK, "appletalk", bin_net_atalk_table },
+ { CTL_DIR, NET_NETROM, "netrom", bin_net_netrom_table },
+ { CTL_DIR, NET_AX25, "ax25", bin_net_ax25_table },
+ /* NET_BRIDGE "bridge" no longer used */
+ { CTL_DIR, NET_ROSE, "rose", bin_net_rose_table },
+ { CTL_DIR, NET_IPV6, "ipv6", bin_net_ipv6_table },
+ { CTL_DIR, NET_X25, "x25", bin_net_x25_table },
+ { CTL_DIR, NET_TR, "token-ring", bin_net_tr_table },
+ { CTL_DIR, NET_DECNET, "decnet", bin_net_decnet_table },
+ /* NET_ECONET not used */
+ { CTL_DIR, NET_SCTP, "sctp", bin_net_sctp_table },
+ { CTL_DIR, NET_LLC, "llc", bin_net_llc_table },
+ { CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table },
+ /* NET_DCCP "dccp" no longer used */
+ { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table },
+ { CTL_INT, 2089, "nf_conntrack_max" },
+ {}
+};
+
+static const struct bin_table bin_fs_quota_table[] = {
+ { CTL_INT, FS_DQ_LOOKUPS, "lookups" },
+ { CTL_INT, FS_DQ_DROPS, "drops" },
+ { CTL_INT, FS_DQ_READS, "reads" },
+ { CTL_INT, FS_DQ_WRITES, "writes" },
+ { CTL_INT, FS_DQ_CACHE_HITS, "cache_hits" },
+ { CTL_INT, FS_DQ_ALLOCATED, "allocated_dquots" },
+ { CTL_INT, FS_DQ_FREE, "free_dquots" },
+ { CTL_INT, FS_DQ_SYNCS, "syncs" },
+ { CTL_INT, FS_DQ_WARNINGS, "warnings" },
+ {}
+};
+
+static const struct bin_table bin_fs_xfs_table[] = {
+ { CTL_INT, XFS_SGID_INHERIT, "irix_sgid_inherit" },
+ { CTL_INT, XFS_SYMLINK_MODE, "irix_symlink_mode" },
+ { CTL_INT, XFS_PANIC_MASK, "panic_mask" },
+
+ { CTL_INT, XFS_ERRLEVEL, "error_level" },
+ { CTL_INT, XFS_SYNCD_TIMER, "xfssyncd_centisecs" },
+ { CTL_INT, XFS_INHERIT_SYNC, "inherit_sync" },
+ { CTL_INT, XFS_INHERIT_NODUMP, "inherit_nodump" },
+ { CTL_INT, XFS_INHERIT_NOATIME, "inherit_noatime" },
+ { CTL_INT, XFS_BUF_TIMER, "xfsbufd_centisecs" },
+ { CTL_INT, XFS_BUF_AGE, "age_buffer_centisecs" },
+ { CTL_INT, XFS_INHERIT_NOSYM, "inherit_nosymlinks" },
+ { CTL_INT, XFS_ROTORSTEP, "rotorstep" },
+ { CTL_INT, XFS_INHERIT_NODFRG, "inherit_nodefrag" },
+ { CTL_INT, XFS_FILESTREAM_TIMER, "filestream_centisecs" },
+ { CTL_INT, XFS_STATS_CLEAR, "stats_clear" },
+ {}
+};
+
+static const struct bin_table bin_fs_ocfs2_nm_table[] = {
+ { CTL_STR, 1, "hb_ctl_path" },
+ {}
+};
+
+static const struct bin_table bin_fs_ocfs2_table[] = {
+ { CTL_DIR, 1, "nm", bin_fs_ocfs2_nm_table },
+ {}
+};
+
+static const struct bin_table bin_inotify_table[] = {
+ { CTL_INT, INOTIFY_MAX_USER_INSTANCES, "max_user_instances" },
+ { CTL_INT, INOTIFY_MAX_USER_WATCHES, "max_user_watches" },
+ { CTL_INT, INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" },
+ {}
+};
+
+static const struct bin_table bin_fs_table[] = {
+ { CTL_INT, FS_NRINODE, "inode-nr" },
+ { CTL_INT, FS_STATINODE, "inode-state" },
+ /* FS_MAXINODE unused */
+ /* FS_NRDQUOT unused */
+ /* FS_MAXDQUOT unused */
+ /* FS_NRFILE "file-nr" no longer used */
+ { CTL_INT, FS_MAXFILE, "file-max" },
+ { CTL_INT, FS_DENTRY, "dentry-state" },
+ /* FS_NRSUPER unused */
+ /* FS_MAXUPSER unused */
+ { CTL_INT, FS_OVERFLOWUID, "overflowuid" },
+ { CTL_INT, FS_OVERFLOWGID, "overflowgid" },
+ { CTL_INT, FS_LEASES, "leases-enable" },
+ { CTL_INT, FS_DIR_NOTIFY, "dir-notify-enable" },
+ { CTL_INT, FS_LEASE_TIME, "lease-break-time" },
+ { CTL_DIR, FS_DQSTATS, "quota", bin_fs_quota_table },
+ { CTL_DIR, FS_XFS, "xfs", bin_fs_xfs_table },
+ { CTL_ULONG, FS_AIO_NR, "aio-nr" },
+ { CTL_ULONG, FS_AIO_MAX_NR, "aio-max-nr" },
+ { CTL_DIR, FS_INOTIFY, "inotify", bin_inotify_table },
+ { CTL_DIR, FS_OCFS2, "ocfs2", bin_fs_ocfs2_table },
+ { CTL_INT, KERN_SETUID_DUMPABLE, "suid_dumpable" },
+ {}
+};
+
+static const struct bin_table bin_ipmi_table[] = {
+ { CTL_INT, DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" },
+ {}
+};
+
+static const struct bin_table bin_mac_hid_files[] = {
+ /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */
+ /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */
+ { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" },
+ { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" },
+ { CTL_INT, DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" },
+ /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */
+ {}
+};
+
+static const struct bin_table bin_raid_table[] = {
+ { CTL_INT, DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" },
+ { CTL_INT, DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" },
+ {}
+};
+
+static const struct bin_table bin_scsi_table[] = {
+ { CTL_INT, DEV_SCSI_LOGGING_LEVEL, "logging_level" },
+ {}
+};
+
+static const struct bin_table bin_dev_table[] = {
+ /* DEV_CDROM "cdrom" no longer used */
+ /* DEV_HWMON unused */
+ /* DEV_PARPORT "parport" no longer used */
+ { CTL_DIR, DEV_RAID, "raid", bin_raid_table },
+ { CTL_DIR, DEV_MAC_HID, "mac_hid", bin_mac_hid_files },
+ { CTL_DIR, DEV_SCSI, "scsi", bin_scsi_table },
+ { CTL_DIR, DEV_IPMI, "ipmi", bin_ipmi_table },
+ {}
+};
+
+static const struct bin_table bin_bus_isa_table[] = {
+ { CTL_INT, BUS_ISA_MEM_BASE, "membase" },
+ { CTL_INT, BUS_ISA_PORT_BASE, "portbase" },
+ { CTL_INT, BUS_ISA_PORT_SHIFT, "portshift" },
+ {}
+};
+
+static const struct bin_table bin_bus_table[] = {
+ { CTL_DIR, CTL_BUS_ISA, "isa", bin_bus_isa_table },
+ {}
+};
+
+
+static const struct bin_table bin_s390dbf_table[] = {
+ { CTL_INT, 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" },
+ { CTL_INT, 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" },
+ {}
+};
+
+static const struct bin_table bin_sunrpc_table[] = {
+ /* CTL_RPCDEBUG "rpc_debug" no longer used */
+ /* CTL_NFSDEBUG "nfs_debug" no longer used */
+ /* CTL_NFSDDEBUG "nfsd_debug" no longer used */
+ /* CTL_NLMDEBUG "nlm_debug" no longer used */
+
+ { CTL_INT, CTL_SLOTTABLE_UDP, "udp_slot_table_entries" },
+ { CTL_INT, CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" },
+ { CTL_INT, CTL_MIN_RESVPORT, "min_resvport" },
+ { CTL_INT, CTL_MAX_RESVPORT, "max_resvport" },
+ {}
+};
+
+static const struct bin_table bin_pm_table[] = {
+ /* frv specific */
+ /* 1 == CTL_PM_SUSPEND "suspend" no longer used" */
+ { CTL_INT, 2 /* CTL_PM_CMODE */, "cmode" },
+ { CTL_INT, 3 /* CTL_PM_P0 */, "p0" },
+ { CTL_INT, 4 /* CTL_PM_CM */, "cm" },
+ {}
+};
+
+static const struct bin_table bin_root_table[] = {
+ { CTL_DIR, CTL_KERN, "kernel", bin_kern_table },
+ { CTL_DIR, CTL_VM, "vm", bin_vm_table },
+ { CTL_DIR, CTL_NET, "net", bin_net_table },
+ /* CTL_PROC not used */
+ { CTL_DIR, CTL_FS, "fs", bin_fs_table },
+ /* CTL_DEBUG "debug" no longer used */
+ { CTL_DIR, CTL_DEV, "dev", bin_dev_table },
+ { CTL_DIR, CTL_BUS, "bus", bin_bus_table },
+ { CTL_DIR, CTL_ABI, "abi" },
+ /* CTL_CPU not used */
+ /* CTL_ARLAN "arlan" no longer used */
+ { CTL_DIR, CTL_S390DBF, "s390dbf", bin_s390dbf_table },
+ { CTL_DIR, CTL_SUNRPC, "sunrpc", bin_sunrpc_table },
+ { CTL_DIR, CTL_PM, "pm", bin_pm_table },
+ {}
+};
+
+static ssize_t bin_dir(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ return -ENOTDIR;
+}
+
+
+static ssize_t bin_string(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ ssize_t result, copied = 0;
+
+ if (oldval && oldlen) {
+ char __user *lastp;
+ loff_t pos = 0;
+ int ch;
+
+ result = vfs_read(file, oldval, oldlen, &pos);
+ if (result < 0)
+ goto out;
+
+ copied = result;
+ lastp = oldval + copied - 1;
+
+ result = -EFAULT;
+ if (get_user(ch, lastp))
+ goto out;
+
+ /* Trim off the trailing newline */
+ if (ch == '\n') {
+ result = -EFAULT;
+ if (put_user('\0', lastp))
+ goto out;
+ copied -= 1;
+ }
+ }
+
+ if (newval && newlen) {
+ loff_t pos = 0;
+
+ result = vfs_write(file, newval, newlen, &pos);
+ if (result < 0)
+ goto out;
+ }
+
+ result = copied;
+out:
+ return result;
+}
+
+static ssize_t bin_intvec(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ mm_segment_t old_fs = get_fs();
+ ssize_t copied = 0;
+ char *buffer;
+ ssize_t result;
+
+ result = -ENOMEM;
+ buffer = kmalloc(BUFSZ, GFP_KERNEL);
+ if (!buffer)
+ goto out;
+
+ if (oldval && oldlen) {
+ unsigned __user *vec = oldval;
+ size_t length = oldlen / sizeof(*vec);
+ loff_t pos = 0;
+ char *str, *end;
+ int i;
+
+ set_fs(KERNEL_DS);
+ result = vfs_read(file, buffer, BUFSZ - 1, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out_kfree;
+
+ str = buffer;
+ end = str + result;
+ *end++ = '\0';
+ for (i = 0; i < length; i++) {
+ unsigned long value;
+
+ value = simple_strtoul(str, &str, 10);
+ while (isspace(*str))
+ str++;
+
+ result = -EFAULT;
+ if (put_user(value, vec + i))
+ goto out_kfree;
+
+ copied += sizeof(*vec);
+ if (!isdigit(*str))
+ break;
+ }
+ }
+
+ if (newval && newlen) {
+ unsigned __user *vec = newval;
+ size_t length = newlen / sizeof(*vec);
+ loff_t pos = 0;
+ char *str, *end;
+ int i;
+
+ str = buffer;
+ end = str + BUFSZ;
+ for (i = 0; i < length; i++) {
+ unsigned long value;
+
+ result = -EFAULT;
+ if (get_user(value, vec + i))
+ goto out_kfree;
+
+ str += snprintf(str, end - str, "%lu\t", value);
+ }
+
+ set_fs(KERNEL_DS);
+ result = vfs_write(file, buffer, str - buffer, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out_kfree;
+ }
+ result = copied;
+out_kfree:
+ kfree(buffer);
+out:
+ return result;
+}
+
+static ssize_t bin_ulongvec(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ mm_segment_t old_fs = get_fs();
+ ssize_t copied = 0;
+ char *buffer;
+ ssize_t result;
+
+ result = -ENOMEM;
+ buffer = kmalloc(BUFSZ, GFP_KERNEL);
+ if (!buffer)
+ goto out;
+
+ if (oldval && oldlen) {
+ unsigned long __user *vec = oldval;
+ size_t length = oldlen / sizeof(*vec);
+ loff_t pos = 0;
+ char *str, *end;
+ int i;
+
+ set_fs(KERNEL_DS);
+ result = vfs_read(file, buffer, BUFSZ - 1, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out_kfree;
+
+ str = buffer;
+ end = str + result;
+ *end++ = '\0';
+ for (i = 0; i < length; i++) {
+ unsigned long value;
+
+ value = simple_strtoul(str, &str, 10);
+ while (isspace(*str))
+ str++;
+
+ result = -EFAULT;
+ if (put_user(value, vec + i))
+ goto out_kfree;
+
+ copied += sizeof(*vec);
+ if (!isdigit(*str))
+ break;
+ }
+ }
+
+ if (newval && newlen) {
+ unsigned long __user *vec = newval;
+ size_t length = newlen / sizeof(*vec);
+ loff_t pos = 0;
+ char *str, *end;
+ int i;
+
+ str = buffer;
+ end = str + BUFSZ;
+ for (i = 0; i < length; i++) {
+ unsigned long value;
+
+ result = -EFAULT;
+ if (get_user(value, vec + i))
+ goto out_kfree;
+
+ str += snprintf(str, end - str, "%lu\t", value);
+ }
+
+ set_fs(KERNEL_DS);
+ result = vfs_write(file, buffer, str - buffer, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out_kfree;
+ }
+ result = copied;
+out_kfree:
+ kfree(buffer);
+out:
+ return result;
+}
+
+static unsigned hex_value(int ch)
+{
+ return isdigit(ch) ? ch - '0' : ((ch | 0x20) - 'a') + 10;
+}
+
+static ssize_t bin_uuid(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ mm_segment_t old_fs = get_fs();
+ ssize_t result, copied = 0;
+
+ /* Only supports reads */
+ if (oldval && oldlen) {
+ loff_t pos = 0;
+ char buf[40], *str = buf;
+ unsigned char uuid[16];
+ int i;
+
+ set_fs(KERNEL_DS);
+ result = vfs_read(file, buf, sizeof(buf) - 1, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out;
+
+ buf[result] = '\0';
+
+ /* Convert the uuid to from a string to binary */
+ for (i = 0; i < 16; i++) {
+ result = -EIO;
+ if (!isxdigit(str[0]) || !isxdigit(str[1]))
+ goto out;
+
+ uuid[i] = (hex_value(str[0]) << 4) | hex_value(str[1]);
+ str += 2;
+ if (*str == '-')
+ str++;
+ }
+
+ if (oldlen > 16)
+ oldlen = 16;
+
+ result = -EFAULT;
+ if (copy_to_user(oldval, uuid, oldlen))
+ goto out;
+
+ copied = oldlen;
+ }
+ result = copied;
+out:
+ return result;
+}
+
+static ssize_t bin_dn_node_address(struct file *file,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ mm_segment_t old_fs = get_fs();
+ ssize_t result, copied = 0;
+
+ if (oldval && oldlen) {
+ loff_t pos = 0;
+ char buf[15], *nodep;
+ unsigned long area, node;
+ __le16 dnaddr;
+
+ set_fs(KERNEL_DS);
+ result = vfs_read(file, buf, sizeof(buf) - 1, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out;
+
+ buf[result] = '\0';
+
+ /* Convert the decnet addresss to binary */
+ result = -EIO;
+ nodep = strchr(buf, '.') + 1;
+ if (!nodep)
+ goto out;
+
+ area = simple_strtoul(buf, NULL, 10);
+ node = simple_strtoul(nodep, NULL, 10);
+
+ result = -EIO;
+ if ((area > 63)||(node > 1023))
+ goto out;
+
+ dnaddr = cpu_to_le16((area << 10) | node);
+
+ result = -EFAULT;
+ if (put_user(dnaddr, (__le16 __user *)oldval))
+ goto out;
+
+ copied = sizeof(dnaddr);
+ }
+
+ if (newval && newlen) {
+ loff_t pos = 0;
+ __le16 dnaddr;
+ char buf[15];
+ int len;
+
+ result = -EINVAL;
+ if (newlen != sizeof(dnaddr))
+ goto out;
+
+ result = -EFAULT;
+ if (get_user(dnaddr, (__le16 __user *)newval))
+ goto out;
+
+ len = snprintf(buf, sizeof(buf), "%hu.%hu",
+ le16_to_cpu(dnaddr) >> 10,
+ le16_to_cpu(dnaddr) & 0x3ff);
+
+ set_fs(KERNEL_DS);
+ result = vfs_write(file, buf, len, &pos);
+ set_fs(old_fs);
+ if (result < 0)
+ goto out;
+ }
+
+ result = copied;
+out:
+ return result;
+}
+
+static const struct bin_table *get_sysctl(const int *name, int nlen, char *path)
+{
+ const struct bin_table *table = &bin_root_table[0];
+ int ctl_name;
+
+ /* The binary sysctl tables have a small maximum depth so
+ * there is no danger of overflowing our path as it PATH_MAX
+ * bytes long.
+ */
+ memcpy(path, "sys/", 4);
+ path += 4;
+
+repeat:
+ if (!nlen)
+ return ERR_PTR(-ENOTDIR);
+ ctl_name = *name;
+ name++;
+ nlen--;
+ for ( ; table->convert; table++) {
+ int len = 0;
+
+ /*
+ * For a wild card entry map from ifindex to network
+ * device name.
+ */
+ if (!table->ctl_name) {
+#ifdef CONFIG_NET
+ struct net *net = current->nsproxy->net_ns;
+ struct net_device *dev;
+ dev = dev_get_by_index(net, ctl_name);
+ if (dev) {
+ len = strlen(dev->name);
+ memcpy(path, dev->name, len);
+ dev_put(dev);
+ }
+#endif
+ /* Use the well known sysctl number to proc name mapping */
+ } else if (ctl_name == table->ctl_name) {
+ len = strlen(table->procname);
+ memcpy(path, table->procname, len);
+ }
+ if (len) {
+ path += len;
+ if (table->child) {
+ *path++ = '/';
+ table = table->child;
+ goto repeat;
+ }
+ *path = '\0';
+ return table;
+ }
+ }
+ return ERR_PTR(-ENOTDIR);
+}
+
+static char *sysctl_getname(const int *name, int nlen, const struct bin_table **tablep)
+{
+ char *tmp, *result;
+
+ result = ERR_PTR(-ENOMEM);
+ tmp = __getname();
+ if (tmp) {
+ const struct bin_table *table = get_sysctl(name, nlen, tmp);
+ result = tmp;
+ *tablep = table;
+ if (IS_ERR(table)) {
+ __putname(tmp);
+ result = ERR_CAST(table);
+ }
+ }
+ return result;
+}
+
+static ssize_t binary_sysctl(const int *name, int nlen,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ const struct bin_table *table = NULL;
+ struct nameidata nd;
+ struct vfsmount *mnt;
+ struct file *file;
+ ssize_t result;
+ char *pathname;
+ int flags;
+ int acc_mode, fmode;
+
+ pathname = sysctl_getname(name, nlen, &table);
+ result = PTR_ERR(pathname);
+ if (IS_ERR(pathname))
+ goto out;
+
+ /* How should the sysctl be accessed? */
+ if (oldval && oldlen && newval && newlen) {
+ flags = O_RDWR;
+ acc_mode = MAY_READ | MAY_WRITE;
+ fmode = FMODE_READ | FMODE_WRITE;
+ } else if (newval && newlen) {
+ flags = O_WRONLY;
+ acc_mode = MAY_WRITE;
+ fmode = FMODE_WRITE;
+ } else if (oldval && oldlen) {
+ flags = O_RDONLY;
+ acc_mode = MAY_READ;
+ fmode = FMODE_READ;
+ } else {
+ result = 0;
+ goto out_putname;
+ }
+
+ mnt = current->nsproxy->pid_ns->proc_mnt;
+ result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd);
+ if (result)
+ goto out_putname;
+
+ result = may_open(&nd.path, acc_mode, fmode);
+ if (result)
+ goto out_putpath;
+
+ file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred());
+ result = PTR_ERR(file);
+ if (IS_ERR(file))
+ goto out_putname;
+
+ result = table->convert(file, oldval, oldlen, newval, newlen);
+
+ fput(file);
+out_putname:
+ putname(pathname);
+out:
+ return result;
+
+out_putpath:
+ path_put(&nd.path);
+ goto out_putname;
+}
+
+
+#else /* CONFIG_SYSCTL_SYSCALL */
+
+static ssize_t binary_sysctl(const int *name, int nlen,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ return -ENOSYS;
+}
+
+#endif /* CONFIG_SYSCTL_SYSCALL */
+
+
+static void deprecated_sysctl_warning(const int *name, int nlen)
+{
+ int i;
+
+ if (printk_ratelimit()) {
+ printk(KERN_INFO
+ "warning: process `%s' used the deprecated sysctl "
+ "system call with ", current->comm);
+ for (i = 0; i < nlen; i++)
+ printk("%d.", name[i]);
+ printk("\n");
+ }
+ return;
+}
+
+static ssize_t do_sysctl(int __user *args_name, int nlen,
+ void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
+{
+ int name[CTL_MAXNAME];
+ int i;
+
+ /* Check args->nlen. */
+ if (nlen < 0 || nlen > CTL_MAXNAME)
+ return -ENOTDIR;
+ /* Read in the sysctl name for simplicity */
+ for (i = 0; i < nlen; i++)
+ if (get_user(name[i], args_name + i))
+ return -EFAULT;
+
+ deprecated_sysctl_warning(name, nlen);
+
+ return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen);
+}
+
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
+{
+ struct __sysctl_args tmp;
+ size_t oldlen = 0;
+ ssize_t result;
+
+ if (copy_from_user(&tmp, args, sizeof(tmp)))
+ return -EFAULT;
+
+ if (tmp.oldval && !tmp.oldlenp)
+ return -EFAULT;
+
+ if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp))
+ return -EFAULT;
+
+ result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen,
+ tmp.newval, tmp.newlen);
+
+ if (result >= 0) {
+ oldlen = result;
+ result = 0;
+ }
+
+ if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp))
+ return -EFAULT;
+
+ return result;
+}
+
+
+#ifdef CONFIG_COMPAT
+#include <asm/compat.h>
+
+struct compat_sysctl_args {
+ compat_uptr_t name;
+ int nlen;
+ compat_uptr_t oldval;
+ compat_uptr_t oldlenp;
+ compat_uptr_t newval;
+ compat_size_t newlen;
+ compat_ulong_t __unused[4];
+};
+
+asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args)
+{
+ struct compat_sysctl_args tmp;
+ compat_size_t __user *compat_oldlenp;
+ size_t oldlen = 0;
+ ssize_t result;
+
+ if (copy_from_user(&tmp, args, sizeof(tmp)))
+ return -EFAULT;
+
+ if (tmp.oldval && !tmp.oldlenp)
+ return -EFAULT;
+
+ compat_oldlenp = compat_ptr(tmp.oldlenp);
+ if (compat_oldlenp && get_user(oldlen, compat_oldlenp))
+ return -EFAULT;
+
+ result = do_sysctl(compat_ptr(tmp.name), tmp.nlen,
+ compat_ptr(tmp.oldval), oldlen,
+ compat_ptr(tmp.newval), tmp.newlen);
+
+ if (result >= 0) {
+ oldlen = result;
+ result = 0;
+ }
+
+ if (compat_oldlenp && put_user(oldlen, compat_oldlenp))
+ return -EFAULT;
+
+ return result;
+}
+
+#endif /* CONFIG_COMPAT */
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index b38423ca711..04cdcf72c82 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -5,1239 +5,6 @@
#include <linux/string.h>
#include <net/ip_vs.h>
-struct trans_ctl_table {
- int ctl_name;
- const char *procname;
- const struct trans_ctl_table *child;
-};
-
-static const struct trans_ctl_table trans_random_table[] = {
- { RANDOM_POOLSIZE, "poolsize" },
- { RANDOM_ENTROPY_COUNT, "entropy_avail" },
- { RANDOM_READ_THRESH, "read_wakeup_threshold" },
- { RANDOM_WRITE_THRESH, "write_wakeup_threshold" },
- { RANDOM_BOOT_ID, "boot_id" },
- { RANDOM_UUID, "uuid" },
- {}
-};
-
-static const struct trans_ctl_table trans_pty_table[] = {
- { PTY_MAX, "max" },
- { PTY_NR, "nr" },
- {}
-};
-
-static const struct trans_ctl_table trans_kern_table[] = {
- { KERN_OSTYPE, "ostype" },
- { KERN_OSRELEASE, "osrelease" },
- /* KERN_OSREV not used */
- { KERN_VERSION, "version" },
- /* KERN_SECUREMASK not used */
- /* KERN_PROF not used */
- { KERN_NODENAME, "hostname" },
- { KERN_DOMAINNAME, "domainname" },
-
- { KERN_PANIC, "panic" },
- { KERN_REALROOTDEV, "real-root-dev" },
-
- { KERN_SPARC_REBOOT, "reboot-cmd" },
- { KERN_CTLALTDEL, "ctrl-alt-del" },
- { KERN_PRINTK, "printk" },
-
- /* KERN_NAMETRANS not used */
- /* KERN_PPC_HTABRECLAIM not used */
- /* KERN_PPC_ZEROPAGED not used */
- { KERN_PPC_POWERSAVE_NAP, "powersave-nap" },
-
- { KERN_MODPROBE, "modprobe" },
- { KERN_SG_BIG_BUFF, "sg-big-buff" },
- { KERN_ACCT, "acct" },
- { KERN_PPC_L2CR, "l2cr" },
-
- /* KERN_RTSIGNR not used */
- /* KERN_RTSIGMAX not used */
-
- { KERN_SHMMAX, "shmmax" },
- { KERN_MSGMAX, "msgmax" },
- { KERN_MSGMNB, "msgmnb" },
- /* KERN_MSGPOOL not used*/
- { KERN_SYSRQ, "sysrq" },
- { KERN_MAX_THREADS, "threads-max" },
- { KERN_RANDOM, "random", trans_random_table },
- { KERN_SHMALL, "shmall" },
- { KERN_MSGMNI, "msgmni" },
- { KERN_SEM, "sem" },
- { KERN_SPARC_STOP_A, "stop-a" },
- { KERN_SHMMNI, "shmmni" },
-
- { KERN_OVERFLOWUID, "overflowuid" },
- { KERN_OVERFLOWGID, "overflowgid" },
-
- { KERN_HOTPLUG, "hotplug", },
- { KERN_IEEE_EMULATION_WARNINGS, "ieee_emulation_warnings" },
-
- { KERN_S390_USER_DEBUG_LOGGING, "userprocess_debug" },
- { KERN_CORE_USES_PID, "core_uses_pid" },
- { KERN_TAINTED, "tainted" },
- { KERN_CADPID, "cad_pid" },
- { KERN_PIDMAX, "pid_max" },
- { KERN_CORE_PATTERN, "core_pattern" },
- { KERN_PANIC_ON_OOPS, "panic_on_oops" },
- { KERN_HPPA_PWRSW, "soft-power" },
- { KERN_HPPA_UNALIGNED, "unaligned-trap" },
-
- { KERN_PRINTK_RATELIMIT, "printk_ratelimit" },
- { KERN_PRINTK_RATELIMIT_BURST, "printk_ratelimit_burst" },
-
- { KERN_PTY, "pty", trans_pty_table },
- { KERN_NGROUPS_MAX, "ngroups_max" },
- { KERN_SPARC_SCONS_PWROFF, "scons-poweroff" },
- { KERN_HZ_TIMER, "hz_timer" },
- { KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" },
- { KERN_BOOTLOADER_TYPE, "bootloader_type" },
- { KERN_RANDOMIZE, "randomize_va_space" },
-
- { KERN_SPIN_RETRY, "spin_retry" },
- { KERN_ACPI_VIDEO_FLAGS, "acpi_video_flags" },
- { KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" },
- { KERN_COMPAT_LOG, "compat-log" },
- { KERN_MAX_LOCK_DEPTH, "max_lock_depth" },
- { KERN_NMI_WATCHDOG, "nmi_watchdog" },
- { KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" },
- {}
-};
-
-static const struct trans_ctl_table trans_vm_table[] = {
- { VM_OVERCOMMIT_MEMORY, "overcommit_memory" },
- { VM_PAGE_CLUSTER, "page-cluster" },
- { VM_DIRTY_BACKGROUND, "dirty_background_ratio" },
- { VM_DIRTY_RATIO, "dirty_ratio" },
- { VM_DIRTY_WB_CS, "dirty_writeback_centisecs" },
- { VM_DIRTY_EXPIRE_CS, "dirty_expire_centisecs" },
- { VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" },
- { VM_OVERCOMMIT_RATIO, "overcommit_ratio" },
- /* VM_PAGEBUF unused */
- { VM_HUGETLB_PAGES, "nr_hugepages" },
- { VM_SWAPPINESS, "swappiness" },
- { VM_LOWMEM_RESERVE_RATIO, "lowmem_reserve_ratio" },
- { VM_MIN_FREE_KBYTES, "min_free_kbytes" },
- { VM_MAX_MAP_COUNT, "max_map_count" },
- { VM_LAPTOP_MODE, "laptop_mode" },
- { VM_BLOCK_DUMP, "block_dump" },
- { VM_HUGETLB_GROUP, "hugetlb_shm_group" },
- { VM_VFS_CACHE_PRESSURE, "vfs_cache_pressure" },
- { VM_LEGACY_VA_LAYOUT, "legacy_va_layout" },
- /* VM_SWAP_TOKEN_TIMEOUT unused */
- { VM_DROP_PAGECACHE, "drop_caches" },
- { VM_PERCPU_PAGELIST_FRACTION, "percpu_pagelist_fraction" },
- { VM_ZONE_RECLAIM_MODE, "zone_reclaim_mode" },
- { VM_MIN_UNMAPPED, "min_unmapped_ratio" },
- { VM_PANIC_ON_OOM, "panic_on_oom" },
- { VM_VDSO_ENABLED, "vdso_enabled" },
- { VM_MIN_SLAB, "min_slab_ratio" },
-
- {}
-};
-
-static const struct trans_ctl_table trans_net_core_table[] = {
- { NET_CORE_WMEM_MAX, "wmem_max" },
- { NET_CORE_RMEM_MAX, "rmem_max" },
- { NET_CORE_WMEM_DEFAULT, "wmem_default" },
- { NET_CORE_RMEM_DEFAULT, "rmem_default" },
- /* NET_CORE_DESTROY_DELAY unused */
- { NET_CORE_MAX_BACKLOG, "netdev_max_backlog" },
- /* NET_CORE_FASTROUTE unused */
- { NET_CORE_MSG_COST, "message_cost" },
- { NET_CORE_MSG_BURST, "message_burst" },
- { NET_CORE_OPTMEM_MAX, "optmem_max" },
- /* NET_CORE_HOT_LIST_LENGTH unused */
- /* NET_CORE_DIVERT_VERSION unused */
- /* NET_CORE_NO_CONG_THRESH unused */
- /* NET_CORE_NO_CONG unused */
- /* NET_CORE_LO_CONG unused */
- /* NET_CORE_MOD_CONG unused */
- { NET_CORE_DEV_WEIGHT, "dev_weight" },
- { NET_CORE_SOMAXCONN, "somaxconn" },
- { NET_CORE_BUDGET, "netdev_budget" },
- { NET_CORE_AEVENT_ETIME, "xfrm_aevent_etime" },
- { NET_CORE_AEVENT_RSEQTH, "xfrm_aevent_rseqth" },
- { NET_CORE_WARNINGS, "warnings" },
- {},
-};
-
-static const struct trans_ctl_table trans_net_unix_table[] = {
- /* NET_UNIX_DESTROY_DELAY unused */
- /* NET_UNIX_DELETE_DELAY unused */
- { NET_UNIX_MAX_DGRAM_QLEN, "max_dgram_qlen" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_route_table[] = {
- { NET_IPV4_ROUTE_FLUSH, "flush" },
- { NET_IPV4_ROUTE_MIN_DELAY, "min_delay" },
- { NET_IPV4_ROUTE_MAX_DELAY, "max_delay" },
- { NET_IPV4_ROUTE_GC_THRESH, "gc_thresh" },
- { NET_IPV4_ROUTE_MAX_SIZE, "max_size" },
- { NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" },
- { NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" },
- { NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" },
- { NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" },
- { NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" },
- { NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" },
- { NET_IPV4_ROUTE_ERROR_COST, "error_cost" },
- { NET_IPV4_ROUTE_ERROR_BURST, "error_burst" },
- { NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity" },
- { NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" },
- { NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" },
- { NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" },
- { NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" },
- { NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = {
- { NET_IPV4_CONF_FORWARDING, "forwarding" },
- { NET_IPV4_CONF_MC_FORWARDING, "mc_forwarding" },
-
- { NET_IPV4_CONF_PROXY_ARP, "proxy_arp" },
- { NET_IPV4_CONF_ACCEPT_REDIRECTS, "accept_redirects" },
- { NET_IPV4_CONF_SECURE_REDIRECTS, "secure_redirects" },
- { NET_IPV4_CONF_SEND_REDIRECTS, "send_redirects" },
- { NET_IPV4_CONF_SHARED_MEDIA, "shared_media" },
- { NET_IPV4_CONF_RP_FILTER, "rp_filter" },
- { NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE, "accept_source_route" },
- { NET_IPV4_CONF_BOOTP_RELAY, "bootp_relay" },
- { NET_IPV4_CONF_LOG_MARTIANS, "log_martians" },
- { NET_IPV4_CONF_TAG, "tag" },
- { NET_IPV4_CONF_ARPFILTER, "arp_filter" },
- { NET_IPV4_CONF_MEDIUM_ID, "medium_id" },
- { NET_IPV4_CONF_NOXFRM, "disable_xfrm" },
- { NET_IPV4_CONF_NOPOLICY, "disable_policy" },
- { NET_IPV4_CONF_FORCE_IGMP_VERSION, "force_igmp_version" },
-
- { NET_IPV4_CONF_ARP_ANNOUNCE, "arp_announce" },
- { NET_IPV4_CONF_ARP_IGNORE, "arp_ignore" },
- { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" },
- { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" },
- { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_conf_table[] = {
- { NET_PROTO_CONF_ALL, "all", trans_net_ipv4_conf_vars_table },
- { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv4_conf_vars_table },
- { 0, NULL, trans_net_ipv4_conf_vars_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_neigh_vars_table[] = {
- { NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" },
- { NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" },
- { NET_NEIGH_APP_SOLICIT, "app_solicit" },
- { NET_NEIGH_RETRANS_TIME, "retrans_time" },
- { NET_NEIGH_REACHABLE_TIME, "base_reachable_time" },
- { NET_NEIGH_DELAY_PROBE_TIME, "delay_first_probe_time" },
- { NET_NEIGH_GC_STALE_TIME, "gc_stale_time" },
- { NET_NEIGH_UNRES_QLEN, "unres_qlen" },
- { NET_NEIGH_PROXY_QLEN, "proxy_qlen" },
- { NET_NEIGH_ANYCAST_DELAY, "anycast_delay" },
- { NET_NEIGH_PROXY_DELAY, "proxy_delay" },
- { NET_NEIGH_LOCKTIME, "locktime" },
- { NET_NEIGH_GC_INTERVAL, "gc_interval" },
- { NET_NEIGH_GC_THRESH1, "gc_thresh1" },
- { NET_NEIGH_GC_THRESH2, "gc_thresh2" },
- { NET_NEIGH_GC_THRESH3, "gc_thresh3" },
- { NET_NEIGH_RETRANS_TIME_MS, "retrans_time_ms" },
- { NET_NEIGH_REACHABLE_TIME_MS, "base_reachable_time_ms" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_neigh_table[] = {
- { NET_PROTO_CONF_DEFAULT, "default", trans_net_neigh_vars_table },
- { 0, NULL, trans_net_neigh_vars_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_netfilter_table[] = {
- { NET_IPV4_NF_CONNTRACK_MAX, "ip_conntrack_max" },
-
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "ip_conntrack_tcp_timeout_syn_sent" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "ip_conntrack_tcp_timeout_syn_recv" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "ip_conntrack_tcp_timeout_established" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "ip_conntrack_tcp_timeout_fin_wait" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "ip_conntrack_tcp_timeout_close_wait" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "ip_conntrack_tcp_timeout_last_ack" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "ip_conntrack_tcp_timeout_time_wait" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "ip_conntrack_tcp_timeout_close" },
-
- { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT, "ip_conntrack_udp_timeout" },
- { NET_IPV4_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "ip_conntrack_udp_timeout_stream" },
- { NET_IPV4_NF_CONNTRACK_ICMP_TIMEOUT, "ip_conntrack_icmp_timeout" },
- { NET_IPV4_NF_CONNTRACK_GENERIC_TIMEOUT, "ip_conntrack_generic_timeout" },
-
- { NET_IPV4_NF_CONNTRACK_BUCKETS, "ip_conntrack_buckets" },
- { NET_IPV4_NF_CONNTRACK_LOG_INVALID, "ip_conntrack_log_invalid" },
- { NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "ip_conntrack_tcp_timeout_max_retrans" },
- { NET_IPV4_NF_CONNTRACK_TCP_LOOSE, "ip_conntrack_tcp_loose" },
- { NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL, "ip_conntrack_tcp_be_liberal" },
- { NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS, "ip_conntrack_tcp_max_retrans" },
-
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "ip_conntrack_sctp_timeout_closed" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "ip_conntrack_sctp_timeout_cookie_wait" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "ip_conntrack_sctp_timeout_cookie_echoed" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "ip_conntrack_sctp_timeout_established" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "ip_conntrack_sctp_timeout_shutdown_sent" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "ip_conntrack_sctp_timeout_shutdown_recd" },
- { NET_IPV4_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "ip_conntrack_sctp_timeout_shutdown_ack_sent" },
-
- { NET_IPV4_NF_CONNTRACK_COUNT, "ip_conntrack_count" },
- { NET_IPV4_NF_CONNTRACK_CHECKSUM, "ip_conntrack_checksum" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv4_table[] = {
- { NET_IPV4_FORWARD, "ip_forward" },
- { NET_IPV4_DYNADDR, "ip_dynaddr" },
-
- { NET_IPV4_CONF, "conf", trans_net_ipv4_conf_table },
- { NET_IPV4_NEIGH, "neigh", trans_net_neigh_table },
- { NET_IPV4_ROUTE, "route", trans_net_ipv4_route_table },
- /* NET_IPV4_FIB_HASH unused */
- { NET_IPV4_NETFILTER, "netfilter", trans_net_ipv4_netfilter_table },
-
- { NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" },
- { NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" },
- { NET_IPV4_TCP_SACK, "tcp_sack" },
- { NET_IPV4_TCP_RETRANS_COLLAPSE, "tcp_retrans_collapse" },
- { NET_IPV4_DEFAULT_TTL, "ip_default_ttl" },
- /* NET_IPV4_AUTOCONFIG unused */
- { NET_IPV4_NO_PMTU_DISC, "ip_no_pmtu_disc" },
- { NET_IPV4_TCP_SYN_RETRIES, "tcp_syn_retries" },
- { NET_IPV4_IPFRAG_HIGH_THRESH, "ipfrag_high_thresh" },
- { NET_IPV4_IPFRAG_LOW_THRESH, "ipfrag_low_thresh" },
- { NET_IPV4_IPFRAG_TIME, "ipfrag_time" },
- /* NET_IPV4_TCP_MAX_KA_PROBES unused */
- { NET_IPV4_TCP_KEEPALIVE_TIME, "tcp_keepalive_time" },
- { NET_IPV4_TCP_KEEPALIVE_PROBES, "tcp_keepalive_probes" },
- { NET_IPV4_TCP_RETRIES1, "tcp_retries1" },
- { NET_IPV4_TCP_RETRIES2, "tcp_retries2" },
- { NET_IPV4_TCP_FIN_TIMEOUT, "tcp_fin_timeout" },
- /* NET_IPV4_IP_MASQ_DEBUG unused */
- { NET_TCP_SYNCOOKIES, "tcp_syncookies" },
- { NET_TCP_STDURG, "tcp_stdurg" },
- { NET_TCP_RFC1337, "tcp_rfc1337" },
- /* NET_TCP_SYN_TAILDROP unused */
- { NET_TCP_MAX_SYN_BACKLOG, "tcp_max_syn_backlog" },
- { NET_IPV4_LOCAL_PORT_RANGE, "ip_local_port_range" },
- { NET_IPV4_ICMP_ECHO_IGNORE_ALL, "icmp_echo_ignore_all" },
- { NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, "icmp_echo_ignore_broadcasts" },
- /* NET_IPV4_ICMP_SOURCEQUENCH_RATE unused */
- /* NET_IPV4_ICMP_DESTUNREACH_RATE unused */
- /* NET_IPV4_ICMP_TIMEEXCEED_RATE unused */
- /* NET_IPV4_ICMP_PARAMPROB_RATE unused */
- /* NET_IPV4_ICMP_ECHOREPLY_RATE unused */
- { NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, "icmp_ignore_bogus_error_responses" },
- { NET_IPV4_IGMP_MAX_MEMBERSHIPS, "igmp_max_memberships" },
- { NET_TCP_TW_RECYCLE, "tcp_tw_recycle" },
- /* NET_IPV4_ALWAYS_DEFRAG unused */
- { NET_IPV4_TCP_KEEPALIVE_INTVL, "tcp_keepalive_intvl" },
- { NET_IPV4_INET_PEER_THRESHOLD, "inet_peer_threshold" },
- { NET_IPV4_INET_PEER_MINTTL, "inet_peer_minttl" },
- { NET_IPV4_INET_PEER_MAXTTL, "inet_peer_maxttl" },
- { NET_IPV4_INET_PEER_GC_MINTIME, "inet_peer_gc_mintime" },
- { NET_IPV4_INET_PEER_GC_MAXTIME, "inet_peer_gc_maxtime" },
- { NET_TCP_ORPHAN_RETRIES, "tcp_orphan_retries" },
- { NET_TCP_ABORT_ON_OVERFLOW, "tcp_abort_on_overflow" },
- { NET_TCP_SYNACK_RETRIES, "tcp_synack_retries" },
- { NET_TCP_MAX_ORPHANS, "tcp_max_orphans" },
- { NET_TCP_MAX_TW_BUCKETS, "tcp_max_tw_buckets" },
- { NET_TCP_FACK, "tcp_fack" },
- { NET_TCP_REORDERING, "tcp_reordering" },
- { NET_TCP_ECN, "tcp_ecn" },
- { NET_TCP_DSACK, "tcp_dsack" },
- { NET_TCP_MEM, "tcp_mem" },
- { NET_TCP_WMEM, "tcp_wmem" },
- { NET_TCP_RMEM, "tcp_rmem" },
- { NET_TCP_APP_WIN, "tcp_app_win" },
- { NET_TCP_ADV_WIN_SCALE, "tcp_adv_win_scale" },
- { NET_IPV4_NONLOCAL_BIND, "ip_nonlocal_bind" },
- { NET_IPV4_ICMP_RATELIMIT, "icmp_ratelimit" },
- { NET_IPV4_ICMP_RATEMASK, "icmp_ratemask" },
- { NET_TCP_TW_REUSE, "tcp_tw_reuse" },
- { NET_TCP_FRTO, "tcp_frto" },
- { NET_TCP_LOW_LATENCY, "tcp_low_latency" },
- { NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" },
- { NET_IPV4_IGMP_MAX_MSF, "igmp_max_msf" },
- { NET_TCP_NO_METRICS_SAVE, "tcp_no_metrics_save" },
- /* NET_TCP_DEFAULT_WIN_SCALE unused */
- { NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" },
- { NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" },
- /* NET_TCP_BIC_BETA unused */
- { NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, "icmp_errors_use_inbound_ifaddr" },
- { NET_TCP_CONG_CONTROL, "tcp_congestion_control" },
- { NET_TCP_ABC, "tcp_abc" },
- { NET_IPV4_IPFRAG_MAX_DIST, "ipfrag_max_dist" },
- { NET_TCP_MTU_PROBING, "tcp_mtu_probing" },
- { NET_TCP_BASE_MSS, "tcp_base_mss" },
- { NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" },
- { NET_TCP_DMA_COPYBREAK, "tcp_dma_copybreak" },
- { NET_TCP_SLOW_START_AFTER_IDLE, "tcp_slow_start_after_idle" },
- { NET_CIPSOV4_CACHE_ENABLE, "cipso_cache_enable" },
- { NET_CIPSOV4_CACHE_BUCKET_SIZE, "cipso_cache_bucket_size" },
- { NET_CIPSOV4_RBM_OPTFMT, "cipso_rbm_optfmt" },
- { NET_CIPSOV4_RBM_STRICTVALID, "cipso_rbm_strictvalid" },
- { NET_TCP_AVAIL_CONG_CONTROL, "tcp_available_congestion_control" },
- { NET_TCP_ALLOWED_CONG_CONTROL, "tcp_allowed_congestion_control" },
- { NET_TCP_MAX_SSTHRESH, "tcp_max_ssthresh" },
- { NET_TCP_FRTO_RESPONSE, "tcp_frto_response" },
- { 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipx_table[] = {
- { NET_IPX_PPROP_BROADCASTING, "ipx_pprop_broadcasting" },
- /* NET_IPX_FORWARDING unused */
- {}
-};
-
-static const struct trans_ctl_table trans_net_atalk_table[] = {
- { NET_ATALK_AARP_EXPIRY_TIME, "aarp-expiry-time" },
- { NET_ATALK_AARP_TICK_TIME, "aarp-tick-time" },
- { NET_ATALK_AARP_RETRANSMIT_LIMIT, "aarp-retransmit-limit" },
- { NET_ATALK_AARP_RESOLVE_TIME, "aarp-resolve-time" },
- {},
-};
-
-static const struct trans_ctl_table trans_net_netrom_table[] = {
- { NET_NETROM_DEFAULT_PATH_QUALITY, "default_path_quality" },
- { NET_NETROM_OBSOLESCENCE_COUNT_INITIALISER, "obsolescence_count_initialiser" },
- { NET_NETROM_NETWORK_TTL_INITIALISER, "network_ttl_initialiser" },
- { NET_NETROM_TRANSPORT_TIMEOUT, "transport_timeout" },
- { NET_NETROM_TRANSPORT_MAXIMUM_TRIES, "transport_maximum_tries" },
- { NET_NETROM_TRANSPORT_ACKNOWLEDGE_DELAY, "transport_acknowledge_delay" },
- { NET_NETROM_TRANSPORT_BUSY_DELAY, "transport_busy_delay" },
- { NET_NETROM_TRANSPORT_REQUESTED_WINDOW_SIZE, "transport_requested_window_size" },
- { NET_NETROM_TRANSPORT_NO_ACTIVITY_TIMEOUT, "transport_no_activity_timeout" },
- { NET_NETROM_ROUTING_CONTROL, "routing_control" },
- { NET_NETROM_LINK_FAILS_COUNT, "link_fails_count" },
- { NET_NETROM_RESET, "reset" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ax25_param_table[] = {
- { NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" },
- { NET_AX25_DEFAULT_MODE, "ax25_default_mode" },
- { NET_AX25_BACKOFF_TYPE, "backoff_type" },
- { NET_AX25_CONNECT_MODE, "connect_mode" },
- { NET_AX25_STANDARD_WINDOW, "standard_window_size" },
- { NET_AX25_EXTENDED_WINDOW, "extended_window_size" },
- { NET_AX25_T1_TIMEOUT, "t1_timeout" },
- { NET_AX25_T2_TIMEOUT, "t2_timeout" },
- { NET_AX25_T3_TIMEOUT, "t3_timeout" },
- { NET_AX25_IDLE_TIMEOUT, "idle_timeout" },
- { NET_AX25_N2, "maximum_retry_count" },
- { NET_AX25_PACLEN, "maximum_packet_length" },
- { NET_AX25_PROTOCOL, "protocol" },
- { NET_AX25_DAMA_SLAVE_TIMEOUT, "dama_slave_timeout" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ax25_table[] = {
- { 0, NULL, trans_net_ax25_param_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_bridge_table[] = {
- { NET_BRIDGE_NF_CALL_ARPTABLES, "bridge-nf-call-arptables" },
- { NET_BRIDGE_NF_CALL_IPTABLES, "bridge-nf-call-iptables" },
- { NET_BRIDGE_NF_CALL_IP6TABLES, "bridge-nf-call-ip6tables" },
- { NET_BRIDGE_NF_FILTER_VLAN_TAGGED, "bridge-nf-filter-vlan-tagged" },
- { NET_BRIDGE_NF_FILTER_PPPOE_TAGGED, "bridge-nf-filter-pppoe-tagged" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_rose_table[] = {
- { NET_ROSE_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" },
- { NET_ROSE_CALL_REQUEST_TIMEOUT, "call_request_timeout" },
- { NET_ROSE_RESET_REQUEST_TIMEOUT, "reset_request_timeout" },
- { NET_ROSE_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" },
- { NET_ROSE_ACK_HOLD_BACK_TIMEOUT, "acknowledge_hold_back_timeout" },
- { NET_ROSE_ROUTING_CONTROL, "routing_control" },
- { NET_ROSE_LINK_FAIL_TIMEOUT, "link_fail_timeout" },
- { NET_ROSE_MAX_VCS, "maximum_virtual_circuits" },
- { NET_ROSE_WINDOW_SIZE, "window_size" },
- { NET_ROSE_NO_ACTIVITY_TIMEOUT, "no_activity_timeout" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_conf_var_table[] = {
- { NET_IPV6_FORWARDING, "forwarding" },
- { NET_IPV6_HOP_LIMIT, "hop_limit" },
- { NET_IPV6_MTU, "mtu" },
- { NET_IPV6_ACCEPT_RA, "accept_ra" },
- { NET_IPV6_ACCEPT_REDIRECTS, "accept_redirects" },
- { NET_IPV6_AUTOCONF, "autoconf" },
- { NET_IPV6_DAD_TRANSMITS, "dad_transmits" },
- { NET_IPV6_RTR_SOLICITS, "router_solicitations" },
- { NET_IPV6_RTR_SOLICIT_INTERVAL, "router_solicitation_interval" },
- { NET_IPV6_RTR_SOLICIT_DELAY, "router_solicitation_delay" },
- { NET_IPV6_USE_TEMPADDR, "use_tempaddr" },
- { NET_IPV6_TEMP_VALID_LFT, "temp_valid_lft" },
- { NET_IPV6_TEMP_PREFERED_LFT, "temp_prefered_lft" },
- { NET_IPV6_REGEN_MAX_RETRY, "regen_max_retry" },
- { NET_IPV6_MAX_DESYNC_FACTOR, "max_desync_factor" },
- { NET_IPV6_MAX_ADDRESSES, "max_addresses" },
- { NET_IPV6_FORCE_MLD_VERSION, "force_mld_version" },
- { NET_IPV6_ACCEPT_RA_DEFRTR, "accept_ra_defrtr" },
- { NET_IPV6_ACCEPT_RA_PINFO, "accept_ra_pinfo" },
- { NET_IPV6_ACCEPT_RA_RTR_PREF, "accept_ra_rtr_pref" },
- { NET_IPV6_RTR_PROBE_INTERVAL, "router_probe_interval" },
- { NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, "accept_ra_rt_info_max_plen" },
- { NET_IPV6_PROXY_NDP, "proxy_ndp" },
- { NET_IPV6_ACCEPT_SOURCE_ROUTE, "accept_source_route" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_conf_table[] = {
- { NET_PROTO_CONF_ALL, "all", trans_net_ipv6_conf_var_table },
- { NET_PROTO_CONF_DEFAULT, "default", trans_net_ipv6_conf_var_table },
- { 0, NULL, trans_net_ipv6_conf_var_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_route_table[] = {
- { NET_IPV6_ROUTE_FLUSH, "flush" },
- { NET_IPV6_ROUTE_GC_THRESH, "gc_thresh" },
- { NET_IPV6_ROUTE_MAX_SIZE, "max_size" },
- { NET_IPV6_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" },
- { NET_IPV6_ROUTE_GC_TIMEOUT, "gc_timeout" },
- { NET_IPV6_ROUTE_GC_INTERVAL, "gc_interval" },
- { NET_IPV6_ROUTE_GC_ELASTICITY, "gc_elasticity" },
- { NET_IPV6_ROUTE_MTU_EXPIRES, "mtu_expires" },
- { NET_IPV6_ROUTE_MIN_ADVMSS, "min_adv_mss" },
- { NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_icmp_table[] = {
- { NET_IPV6_ICMP_RATELIMIT, "ratelimit" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_ipv6_table[] = {
- { NET_IPV6_CONF, "conf", trans_net_ipv6_conf_table },
- { NET_IPV6_NEIGH, "neigh", trans_net_neigh_table },
- { NET_IPV6_ROUTE, "route", trans_net_ipv6_route_table },
- { NET_IPV6_ICMP, "icmp", trans_net_ipv6_icmp_table },
- { NET_IPV6_BINDV6ONLY, "bindv6only" },
- { NET_IPV6_IP6FRAG_HIGH_THRESH, "ip6frag_high_thresh" },
- { NET_IPV6_IP6FRAG_LOW_THRESH, "ip6frag_low_thresh" },
- { NET_IPV6_IP6FRAG_TIME, "ip6frag_time" },
- { NET_IPV6_IP6FRAG_SECRET_INTERVAL, "ip6frag_secret_interval" },
- { NET_IPV6_MLD_MAX_MSF, "mld_max_msf" },
- { 2088 /* IPQ_QMAX */, "ip6_queue_maxlen" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_x25_table[] = {
- { NET_X25_RESTART_REQUEST_TIMEOUT, "restart_request_timeout" },
- { NET_X25_CALL_REQUEST_TIMEOUT, "call_request_timeout" },
- { NET_X25_RESET_REQUEST_TIMEOUT, "reset_request_timeout" },
- { NET_X25_CLEAR_REQUEST_TIMEOUT, "clear_request_timeout" },
- { NET_X25_ACK_HOLD_BACK_TIMEOUT, "acknowledgement_hold_back_timeout" },
- { NET_X25_FORWARD, "x25_forward" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_tr_table[] = {
- { NET_TR_RIF_TIMEOUT, "rif_timeout" },
- {}
-};
-
-
-static const struct trans_ctl_table trans_net_decnet_conf_vars[] = {
- { NET_DECNET_CONF_DEV_FORWARDING, "forwarding" },
- { NET_DECNET_CONF_DEV_PRIORITY, "priority" },
- { NET_DECNET_CONF_DEV_T2, "t2" },
- { NET_DECNET_CONF_DEV_T3, "t3" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_decnet_conf[] = {
- { 0, NULL, trans_net_decnet_conf_vars },
- {}
-};
-
-static const struct trans_ctl_table trans_net_decnet_table[] = {
- { NET_DECNET_CONF, "conf", trans_net_decnet_conf },
- { NET_DECNET_NODE_ADDRESS, "node_address" },
- { NET_DECNET_NODE_NAME, "node_name" },
- { NET_DECNET_DEFAULT_DEVICE, "default_device" },
- { NET_DECNET_TIME_WAIT, "time_wait" },
- { NET_DECNET_DN_COUNT, "dn_count" },
- { NET_DECNET_DI_COUNT, "di_count" },
- { NET_DECNET_DR_COUNT, "dr_count" },
- { NET_DECNET_DST_GC_INTERVAL, "dst_gc_interval" },
- { NET_DECNET_NO_FC_MAX_CWND, "no_fc_max_cwnd" },
- { NET_DECNET_MEM, "decnet_mem" },
- { NET_DECNET_RMEM, "decnet_rmem" },
- { NET_DECNET_WMEM, "decnet_wmem" },
- { NET_DECNET_DEBUG_LEVEL, "debug" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_sctp_table[] = {
- { NET_SCTP_RTO_INITIAL, "rto_initial" },
- { NET_SCTP_RTO_MIN, "rto_min" },
- { NET_SCTP_RTO_MAX, "rto_max" },
- { NET_SCTP_RTO_ALPHA, "rto_alpha_exp_divisor" },
- { NET_SCTP_RTO_BETA, "rto_beta_exp_divisor" },
- { NET_SCTP_VALID_COOKIE_LIFE, "valid_cookie_life" },
- { NET_SCTP_ASSOCIATION_MAX_RETRANS, "association_max_retrans" },
- { NET_SCTP_PATH_MAX_RETRANS, "path_max_retrans" },
- { NET_SCTP_MAX_INIT_RETRANSMITS, "max_init_retransmits" },
- { NET_SCTP_HB_INTERVAL, "hb_interval" },
- { NET_SCTP_PRESERVE_ENABLE, "cookie_preserve_enable" },
- { NET_SCTP_MAX_BURST, "max_burst" },
- { NET_SCTP_ADDIP_ENABLE, "addip_enable" },
- { NET_SCTP_PRSCTP_ENABLE, "prsctp_enable" },
- { NET_SCTP_SNDBUF_POLICY, "sndbuf_policy" },
- { NET_SCTP_SACK_TIMEOUT, "sack_timeout" },
- { NET_SCTP_RCVBUF_POLICY, "rcvbuf_policy" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_llc_llc2_timeout_table[] = {
- { NET_LLC2_ACK_TIMEOUT, "ack" },
- { NET_LLC2_P_TIMEOUT, "p" },
- { NET_LLC2_REJ_TIMEOUT, "rej" },
- { NET_LLC2_BUSY_TIMEOUT, "busy" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_llc_station_table[] = {
- { NET_LLC_STATION_ACK_TIMEOUT, "ack_timeout" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_llc_llc2_table[] = {
- { NET_LLC2, "timeout", trans_net_llc_llc2_timeout_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_llc_table[] = {
- { NET_LLC2, "llc2", trans_net_llc_llc2_table },
- { NET_LLC_STATION, "station", trans_net_llc_station_table },
- {}
-};
-
-static const struct trans_ctl_table trans_net_netfilter_table[] = {
- { NET_NF_CONNTRACK_MAX, "nf_conntrack_max" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, "nf_conntrack_tcp_timeout_syn_sent" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV, "nf_conntrack_tcp_timeout_syn_recv" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED, "nf_conntrack_tcp_timeout_established" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT, "nf_conntrack_tcp_timeout_fin_wait" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT, "nf_conntrack_tcp_timeout_close_wait" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK, "nf_conntrack_tcp_timeout_last_ack" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT, "nf_conntrack_tcp_timeout_time_wait" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE, "nf_conntrack_tcp_timeout_close" },
- { NET_NF_CONNTRACK_UDP_TIMEOUT, "nf_conntrack_udp_timeout" },
- { NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM, "nf_conntrack_udp_timeout_stream" },
- { NET_NF_CONNTRACK_ICMP_TIMEOUT, "nf_conntrack_icmp_timeout" },
- { NET_NF_CONNTRACK_GENERIC_TIMEOUT, "nf_conntrack_generic_timeout" },
- { NET_NF_CONNTRACK_BUCKETS, "nf_conntrack_buckets" },
- { NET_NF_CONNTRACK_LOG_INVALID, "nf_conntrack_log_invalid" },
- { NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS, "nf_conntrack_tcp_timeout_max_retrans" },
- { NET_NF_CONNTRACK_TCP_LOOSE, "nf_conntrack_tcp_loose" },
- { NET_NF_CONNTRACK_TCP_BE_LIBERAL, "nf_conntrack_tcp_be_liberal" },
- { NET_NF_CONNTRACK_TCP_MAX_RETRANS, "nf_conntrack_tcp_max_retrans" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED, "nf_conntrack_sctp_timeout_closed" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT, "nf_conntrack_sctp_timeout_cookie_wait" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED, "nf_conntrack_sctp_timeout_cookie_echoed" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED, "nf_conntrack_sctp_timeout_established" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT, "nf_conntrack_sctp_timeout_shutdown_sent" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD, "nf_conntrack_sctp_timeout_shutdown_recd" },
- { NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT, "nf_conntrack_sctp_timeout_shutdown_ack_sent" },
- { NET_NF_CONNTRACK_COUNT, "nf_conntrack_count" },
- { NET_NF_CONNTRACK_ICMPV6_TIMEOUT, "nf_conntrack_icmpv6_timeout" },
- { NET_NF_CONNTRACK_FRAG6_TIMEOUT, "nf_conntrack_frag6_timeout" },
- { NET_NF_CONNTRACK_FRAG6_LOW_THRESH, "nf_conntrack_frag6_low_thresh" },
- { NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, "nf_conntrack_frag6_high_thresh" },
- { NET_NF_CONNTRACK_CHECKSUM, "nf_conntrack_checksum" },
-
- {}
-};
-
-static const struct trans_ctl_table trans_net_dccp_table[] = {
- { NET_DCCP_DEFAULT, "default" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_irda_table[] = {
- { NET_IRDA_DISCOVERY, "discovery" },
- { NET_IRDA_DEVNAME, "devname" },
- { NET_IRDA_DEBUG, "debug" },
- { NET_IRDA_FAST_POLL, "fast_poll_increase" },
- { NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" },
- { NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" },
- { NET_IRDA_SLOT_TIMEOUT, "slot_timeout" },
- { NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" },
- { NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" },
- { NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" },
- { NET_IRDA_MAX_TX_WINDOW, "max_tx_window" },
- { NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" },
- { NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" },
- { NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" },
- {}
-};
-
-static const struct trans_ctl_table trans_net_table[] = {
- { NET_CORE, "core", trans_net_core_table },
- /* NET_ETHER not used */
- /* NET_802 not used */
- { NET_UNIX, "unix", trans_net_unix_table },
- { NET_IPV4, "ipv4", trans_net_ipv4_table },
- { NET_IPX, "ipx", trans_net_ipx_table },
- { NET_ATALK, "appletalk", trans_net_atalk_table },
- { NET_NETROM, "netrom", trans_net_netrom_table },
- { NET_AX25, "ax25", trans_net_ax25_table },
- { NET_BRIDGE, "bridge", trans_net_bridge_table },
- { NET_ROSE, "rose", trans_net_rose_table },
- { NET_IPV6, "ipv6", trans_net_ipv6_table },
- { NET_X25, "x25", trans_net_x25_table },
- { NET_TR, "token-ring", trans_net_tr_table },
- { NET_DECNET, "decnet", trans_net_decnet_table },
- /* NET_ECONET not used */
- { NET_SCTP, "sctp", trans_net_sctp_table },
- { NET_LLC, "llc", trans_net_llc_table },
- { NET_NETFILTER, "netfilter", trans_net_netfilter_table },
- { NET_DCCP, "dccp", trans_net_dccp_table },
- { NET_IRDA, "irda", trans_net_irda_table },
- { 2089, "nf_conntrack_max" },
- {}
-};
-
-static const struct trans_ctl_table trans_fs_quota_table[] = {
- { FS_DQ_LOOKUPS, "lookups" },
- { FS_DQ_DROPS, "drops" },
- { FS_DQ_READS, "reads" },
- { FS_DQ_WRITES, "writes" },
- { FS_DQ_CACHE_HITS, "cache_hits" },
- { FS_DQ_ALLOCATED, "allocated_dquots" },
- { FS_DQ_FREE, "free_dquots" },
- { FS_DQ_SYNCS, "syncs" },
- { FS_DQ_WARNINGS, "warnings" },
- {}
-};
-
-static const struct trans_ctl_table trans_fs_xfs_table[] = {
- { XFS_SGID_INHERIT, "irix_sgid_inherit" },
- { XFS_SYMLINK_MODE, "irix_symlink_mode" },
- { XFS_PANIC_MASK, "panic_mask" },
-
- { XFS_ERRLEVEL, "error_level" },
- { XFS_SYNCD_TIMER, "xfssyncd_centisecs" },
- { XFS_INHERIT_SYNC, "inherit_sync" },
- { XFS_INHERIT_NODUMP, "inherit_nodump" },
- { XFS_INHERIT_NOATIME, "inherit_noatime" },
- { XFS_BUF_TIMER, "xfsbufd_centisecs" },
- { XFS_BUF_AGE, "age_buffer_centisecs" },
- { XFS_INHERIT_NOSYM, "inherit_nosymlinks" },
- { XFS_ROTORSTEP, "rotorstep" },
- { XFS_INHERIT_NODFRG, "inherit_nodefrag" },
- { XFS_FILESTREAM_TIMER, "filestream_centisecs" },
- { XFS_STATS_CLEAR, "stats_clear" },
- {}
-};
-
-static const struct trans_ctl_table trans_fs_ocfs2_nm_table[] = {
- { 1, "hb_ctl_path" },
- {}
-};
-
-static const struct trans_ctl_table trans_fs_ocfs2_table[] = {
- { 1, "nm", trans_fs_ocfs2_nm_table },
- {}
-};
-
-static const struct trans_ctl_table trans_inotify_table[] = {
- { INOTIFY_MAX_USER_INSTANCES, "max_user_instances" },
- { INOTIFY_MAX_USER_WATCHES, "max_user_watches" },
- { INOTIFY_MAX_QUEUED_EVENTS, "max_queued_events" },
- {}
-};
-
-static const struct trans_ctl_table trans_fs_table[] = {
- { FS_NRINODE, "inode-nr" },
- { FS_STATINODE, "inode-state" },
- /* FS_MAXINODE unused */
- /* FS_NRDQUOT unused */
- /* FS_MAXDQUOT unused */
- { FS_NRFILE, "file-nr" },
- { FS_MAXFILE, "file-max" },
- { FS_DENTRY, "dentry-state" },
- /* FS_NRSUPER unused */
- /* FS_MAXUPSER unused */
- { FS_OVERFLOWUID, "overflowuid" },
- { FS_OVERFLOWGID, "overflowgid" },
- { FS_LEASES, "leases-enable" },
- { FS_DIR_NOTIFY, "dir-notify-enable" },
- { FS_LEASE_TIME, "lease-break-time" },
- { FS_DQSTATS, "quota", trans_fs_quota_table },
- { FS_XFS, "xfs", trans_fs_xfs_table },
- { FS_AIO_NR, "aio-nr" },
- { FS_AIO_MAX_NR, "aio-max-nr" },
- { FS_INOTIFY, "inotify", trans_inotify_table },
- { FS_OCFS2, "ocfs2", trans_fs_ocfs2_table },
- { KERN_SETUID_DUMPABLE, "suid_dumpable" },
- {}
-};
-
-static const struct trans_ctl_table trans_debug_table[] = {
- {}
-};
-
-static const struct trans_ctl_table trans_cdrom_table[] = {
- { DEV_CDROM_INFO, "info" },
- { DEV_CDROM_AUTOCLOSE, "autoclose" },
- { DEV_CDROM_AUTOEJECT, "autoeject" },
- { DEV_CDROM_DEBUG, "debug" },
- { DEV_CDROM_LOCK, "lock" },
- { DEV_CDROM_CHECK_MEDIA, "check_media" },
- {}
-};
-
-static const struct trans_ctl_table trans_ipmi_table[] = {
- { DEV_IPMI_POWEROFF_POWERCYCLE, "poweroff_powercycle" },
- {}
-};
-
-static const struct trans_ctl_table trans_mac_hid_files[] = {
- /* DEV_MAC_HID_KEYBOARD_SENDS_LINUX_KEYCODES unused */
- /* DEV_MAC_HID_KEYBOARD_LOCK_KEYCODES unused */
- { DEV_MAC_HID_MOUSE_BUTTON_EMULATION, "mouse_button_emulation" },
- { DEV_MAC_HID_MOUSE_BUTTON2_KEYCODE, "mouse_button2_keycode" },
- { DEV_MAC_HID_MOUSE_BUTTON3_KEYCODE, "mouse_button3_keycode" },
- /* DEV_MAC_HID_ADB_MOUSE_SENDS_KEYCODES unused */
- {}
-};
-
-static const struct trans_ctl_table trans_raid_table[] = {
- { DEV_RAID_SPEED_LIMIT_MIN, "speed_limit_min" },
- { DEV_RAID_SPEED_LIMIT_MAX, "speed_limit_max" },
- {}
-};
-
-static const struct trans_ctl_table trans_scsi_table[] = {
- { DEV_SCSI_LOGGING_LEVEL, "logging_level" },
- {}
-};
-
-static const struct trans_ctl_table trans_parport_default_table[] = {
- { DEV_PARPORT_DEFAULT_TIMESLICE, "timeslice" },
- { DEV_PARPORT_DEFAULT_SPINTIME, "spintime" },
- {}
-};
-
-static const struct trans_ctl_table trans_parport_device_table[] = {
- { DEV_PARPORT_DEVICE_TIMESLICE, "timeslice" },
- {}
-};
-
-static const struct trans_ctl_table trans_parport_devices_table[] = {
- { DEV_PARPORT_DEVICES_ACTIVE, "active" },
- { 0, NULL, trans_parport_device_table },
- {}
-};
-
-static const struct trans_ctl_table trans_parport_parport_table[] = {
- { DEV_PARPORT_SPINTIME, "spintime" },
- { DEV_PARPORT_BASE_ADDR, "base-addr" },
- { DEV_PARPORT_IRQ, "irq" },
- { DEV_PARPORT_DMA, "dma" },
- { DEV_PARPORT_MODES, "modes" },
- { DEV_PARPORT_DEVICES, "devices", trans_parport_devices_table },
- { DEV_PARPORT_AUTOPROBE, "autoprobe" },
- { DEV_PARPORT_AUTOPROBE + 1, "autoprobe0" },
- { DEV_PARPORT_AUTOPROBE + 2, "autoprobe1" },
- { DEV_PARPORT_AUTOPROBE + 3, "autoprobe2" },
- { DEV_PARPORT_AUTOPROBE + 4, "autoprobe3" },
- {}
-};
-static const struct trans_ctl_table trans_parport_table[] = {
- { DEV_PARPORT_DEFAULT, "default", trans_parport_default_table },
- { 0, NULL, trans_parport_parport_table },
- {}
-};
-
-static const struct trans_ctl_table trans_dev_table[] = {
- { DEV_CDROM, "cdrom", trans_cdrom_table },
- /* DEV_HWMON unused */
- { DEV_PARPORT, "parport", trans_parport_table },
- { DEV_RAID, "raid", trans_raid_table },
- { DEV_MAC_HID, "mac_hid", trans_mac_hid_files },
- { DEV_SCSI, "scsi", trans_scsi_table },
- { DEV_IPMI, "ipmi", trans_ipmi_table },
- {}
-};
-
-static const struct trans_ctl_table trans_bus_isa_table[] = {
- { BUS_ISA_MEM_BASE, "membase" },
- { BUS_ISA_PORT_BASE, "portbase" },
- { BUS_ISA_PORT_SHIFT, "portshift" },
- {}
-};
-
-static const struct trans_ctl_table trans_bus_table[] = {
- { CTL_BUS_ISA, "isa", trans_bus_isa_table },
- {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table0[] = {
- { 1, "spreadingCode" },
- { 2, "channelNumber" },
- { 3, "scramblingDisable" },
- { 4, "txAttenuation" },
- { 5, "systemId" },
- { 6, "maxDatagramSize" },
- { 7, "maxFrameSize" },
- { 8, "maxRetries" },
- { 9, "receiveMode" },
- { 10, "priority" },
- { 11, "rootOrRepeater" },
- { 12, "SID" },
- { 13, "registrationMode" },
- { 14, "registrationFill" },
- { 15, "localTalkAddress" },
- { 16, "codeFormat" },
- { 17, "numChannels" },
- { 18, "channel1" },
- { 19, "channel2" },
- { 20, "channel3" },
- { 21, "channel4" },
- { 22, "txClear" },
- { 23, "txRetries" },
- { 24, "txRouting" },
- { 25, "txScrambled" },
- { 26, "rxParameter" },
- { 27, "txTimeoutMs" },
- { 28, "waitCardTimeout" },
- { 29, "channelSet" },
- { 30, "name" },
- { 31, "waitTime" },
- { 32, "lParameter" },
- { 33, "_15" },
- { 34, "headerSize" },
- { 36, "tx_delay_ms" },
- { 37, "retries" },
- { 38, "ReTransmitPacketMaxSize" },
- { 39, "waitReTransmitPacketMaxSize" },
- { 40, "fastReTransCount" },
- { 41, "driverRetransmissions" },
- { 42, "txAckTimeoutMs" },
- { 43, "registrationInterrupts" },
- { 44, "hardwareType" },
- { 45, "radioType" },
- { 46, "writeEEPROM" },
- { 47, "writeRadioType" },
- { 48, "entry_exit_debug" },
- { 49, "debug" },
- { 50, "in_speed" },
- { 51, "out_speed" },
- { 52, "in_speed10" },
- { 53, "out_speed10" },
- { 54, "in_speed_max" },
- { 55, "out_speed_max" },
- { 56, "measure_rate" },
- { 57, "pre_Command_Wait" },
- { 58, "rx_tweak1" },
- { 59, "rx_tweak2" },
- { 60, "tx_queue_len" },
-
- { 150, "arlan0-txRing" },
- { 151, "arlan0-rxRing" },
- { 152, "arlan0-18" },
- { 153, "arlan0-ring" },
- { 154, "arlan0-shm-cpy" },
- { 155, "config0" },
- { 156, "reset0" },
- {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table1[] = {
- { 1, "spreadingCode" },
- { 2, "channelNumber" },
- { 3, "scramblingDisable" },
- { 4, "txAttenuation" },
- { 5, "systemId" },
- { 6, "maxDatagramSize" },
- { 7, "maxFrameSize" },
- { 8, "maxRetries" },
- { 9, "receiveMode" },
- { 10, "priority" },
- { 11, "rootOrRepeater" },
- { 12, "SID" },
- { 13, "registrationMode" },
- { 14, "registrationFill" },
- { 15, "localTalkAddress" },
- { 16, "codeFormat" },
- { 17, "numChannels" },
- { 18, "channel1" },
- { 19, "channel2" },
- { 20, "channel3" },
- { 21, "channel4" },
- { 22, "txClear" },
- { 23, "txRetries" },
- { 24, "txRouting" },
- { 25, "txScrambled" },
- { 26, "rxParameter" },
- { 27, "txTimeoutMs" },
- { 28, "waitCardTimeout" },
- { 29, "channelSet" },
- { 30, "name" },
- { 31, "waitTime" },
- { 32, "lParameter" },
- { 33, "_15" },
- { 34, "headerSize" },
- { 36, "tx_delay_ms" },
- { 37, "retries" },
- { 38, "ReTransmitPacketMaxSize" },
- { 39, "waitReTransmitPacketMaxSize" },
- { 40, "fastReTransCount" },
- { 41, "driverRetransmissions" },
- { 42, "txAckTimeoutMs" },
- { 43, "registrationInterrupts" },
- { 44, "hardwareType" },
- { 45, "radioType" },
- { 46, "writeEEPROM" },
- { 47, "writeRadioType" },
- { 48, "entry_exit_debug" },
- { 49, "debug" },
- { 50, "in_speed" },
- { 51, "out_speed" },
- { 52, "in_speed10" },
- { 53, "out_speed10" },
- { 54, "in_speed_max" },
- { 55, "out_speed_max" },
- { 56, "measure_rate" },
- { 57, "pre_Command_Wait" },
- { 58, "rx_tweak1" },
- { 59, "rx_tweak2" },
- { 60, "tx_queue_len" },
-
- { 150, "arlan1-txRing" },
- { 151, "arlan1-rxRing" },
- { 152, "arlan1-18" },
- { 153, "arlan1-ring" },
- { 154, "arlan1-shm-cpy" },
- { 155, "config1" },
- { 156, "reset1" },
- {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table2[] = {
- { 1, "spreadingCode" },
- { 2, "channelNumber" },
- { 3, "scramblingDisable" },
- { 4, "txAttenuation" },
- { 5, "systemId" },
- { 6, "maxDatagramSize" },
- { 7, "maxFrameSize" },
- { 8, "maxRetries" },
- { 9, "receiveMode" },
- { 10, "priority" },
- { 11, "rootOrRepeater" },
- { 12, "SID" },
- { 13, "registrationMode" },
- { 14, "registrationFill" },
- { 15, "localTalkAddress" },
- { 16, "codeFormat" },
- { 17, "numChannels" },
- { 18, "channel1" },
- { 19, "channel2" },
- { 20, "channel3" },
- { 21, "channel4" },
- { 22, "txClear" },
- { 23, "txRetries" },
- { 24, "txRouting" },
- { 25, "txScrambled" },
- { 26, "rxParameter" },
- { 27, "txTimeoutMs" },
- { 28, "waitCardTimeout" },
- { 29, "channelSet" },
- { 30, "name" },
- { 31, "waitTime" },
- { 32, "lParameter" },
- { 33, "_15" },
- { 34, "headerSize" },
- { 36, "tx_delay_ms" },
- { 37, "retries" },
- { 38, "ReTransmitPacketMaxSize" },
- { 39, "waitReTransmitPacketMaxSize" },
- { 40, "fastReTransCount" },
- { 41, "driverRetransmissions" },
- { 42, "txAckTimeoutMs" },
- { 43, "registrationInterrupts" },
- { 44, "hardwareType" },
- { 45, "radioType" },
- { 46, "writeEEPROM" },
- { 47, "writeRadioType" },
- { 48, "entry_exit_debug" },
- { 49, "debug" },
- { 50, "in_speed" },
- { 51, "out_speed" },
- { 52, "in_speed10" },
- { 53, "out_speed10" },
- { 54, "in_speed_max" },
- { 55, "out_speed_max" },
- { 56, "measure_rate" },
- { 57, "pre_Command_Wait" },
- { 58, "rx_tweak1" },
- { 59, "rx_tweak2" },
- { 60, "tx_queue_len" },
-
- { 150, "arlan2-txRing" },
- { 151, "arlan2-rxRing" },
- { 152, "arlan2-18" },
- { 153, "arlan2-ring" },
- { 154, "arlan2-shm-cpy" },
- { 155, "config2" },
- { 156, "reset2" },
- {}
-};
-
-static const struct trans_ctl_table trans_arlan_conf_table3[] = {
- { 1, "spreadingCode" },
- { 2, "channelNumber" },
- { 3, "scramblingDisable" },
- { 4, "txAttenuation" },
- { 5, "systemId" },
- { 6, "maxDatagramSize" },
- { 7, "maxFrameSize" },
- { 8, "maxRetries" },
- { 9, "receiveMode" },
- { 10, "priority" },
- { 11, "rootOrRepeater" },
- { 12, "SID" },
- { 13, "registrationMode" },
- { 14, "registrationFill" },
- { 15, "localTalkAddress" },
- { 16, "codeFormat" },
- { 17, "numChannels" },
- { 18, "channel1" },
- { 19, "channel2" },
- { 20, "channel3" },
- { 21, "channel4" },
- { 22, "txClear" },
- { 23, "txRetries" },
- { 24, "txRouting" },
- { 25, "txScrambled" },
- { 26, "rxParameter" },
- { 27, "txTimeoutMs" },
- { 28, "waitCardTimeout" },
- { 29, "channelSet" },
- { 30, "name" },
- { 31, "waitTime" },
- { 32, "lParameter" },
- { 33, "_15" },
- { 34, "headerSize" },
- { 36, "tx_delay_ms" },
- { 37, "retries" },
- { 38, "ReTransmitPacketMaxSize" },
- { 39, "waitReTransmitPacketMaxSize" },
- { 40, "fastReTransCount" },
- { 41, "driverRetransmissions" },
- { 42, "txAckTimeoutMs" },
- { 43, "registrationInterrupts" },
- { 44, "hardwareType" },
- { 45, "radioType" },
- { 46, "writeEEPROM" },
- { 47, "writeRadioType" },
- { 48, "entry_exit_debug" },
- { 49, "debug" },
- { 50, "in_speed" },
- { 51, "out_speed" },
- { 52, "in_speed10" },
- { 53, "out_speed10" },
- { 54, "in_speed_max" },
- { 55, "out_speed_max" },
- { 56, "measure_rate" },
- { 57, "pre_Command_Wait" },
- { 58, "rx_tweak1" },
- { 59, "rx_tweak2" },
- { 60, "tx_queue_len" },
-
- { 150, "arlan3-txRing" },
- { 151, "arlan3-rxRing" },
- { 152, "arlan3-18" },
- { 153, "arlan3-ring" },
- { 154, "arlan3-shm-cpy" },
- { 155, "config3" },
- { 156, "reset3" },
- {}
-};
-
-static const struct trans_ctl_table trans_arlan_table[] = {
- { 1, "arlan0", trans_arlan_conf_table0 },
- { 2, "arlan1", trans_arlan_conf_table1 },
- { 3, "arlan2", trans_arlan_conf_table2 },
- { 4, "arlan3", trans_arlan_conf_table3 },
- {}
-};
-
-static const struct trans_ctl_table trans_s390dbf_table[] = {
- { 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" },
- { 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" },
- {}
-};
-
-static const struct trans_ctl_table trans_sunrpc_table[] = {
- { CTL_RPCDEBUG, "rpc_debug" },
- { CTL_NFSDEBUG, "nfs_debug" },
- { CTL_NFSDDEBUG, "nfsd_debug" },
- { CTL_NLMDEBUG, "nlm_debug" },
- { CTL_SLOTTABLE_UDP, "udp_slot_table_entries" },
- { CTL_SLOTTABLE_TCP, "tcp_slot_table_entries" },
- { CTL_MIN_RESVPORT, "min_resvport" },
- { CTL_MAX_RESVPORT, "max_resvport" },
- {}
-};
-
-static const struct trans_ctl_table trans_pm_table[] = {
- { 1 /* CTL_PM_SUSPEND */, "suspend" },
- { 2 /* CTL_PM_CMODE */, "cmode" },
- { 3 /* CTL_PM_P0 */, "p0" },
- { 4 /* CTL_PM_CM */, "cm" },
- {}
-};
-
-static const struct trans_ctl_table trans_frv_table[] = {
- { 1, "cache-mode" },
- { 2, "pin-cxnr" },
- {}
-};
-
-static const struct trans_ctl_table trans_root_table[] = {
- { CTL_KERN, "kernel", trans_kern_table },
- { CTL_VM, "vm", trans_vm_table },
- { CTL_NET, "net", trans_net_table },
- /* CTL_PROC not used */
- { CTL_FS, "fs", trans_fs_table },
- { CTL_DEBUG, "debug", trans_debug_table },
- { CTL_DEV, "dev", trans_dev_table },
- { CTL_BUS, "bus", trans_bus_table },
- { CTL_ABI, "abi" },
- /* CTL_CPU not used */
- { CTL_ARLAN, "arlan", trans_arlan_table },
- { CTL_S390DBF, "s390dbf", trans_s390dbf_table },
- { CTL_SUNRPC, "sunrpc", trans_sunrpc_table },
- { CTL_PM, "pm", trans_pm_table },
- { CTL_FRV, "frv", trans_frv_table },
- {}
-};
-
-
-
static int sysctl_depth(struct ctl_table *table)
{
@@ -1261,47 +28,6 @@ static struct ctl_table *sysctl_parent(struct ctl_table *table, int n)
return table;
}
-static const struct trans_ctl_table *sysctl_binary_lookup(struct ctl_table *table)
-{
- struct ctl_table *test;
- const struct trans_ctl_table *ref;
- int cur_depth;
-
- cur_depth = sysctl_depth(table);
-
- ref = trans_root_table;
-repeat:
- test = sysctl_parent(table, cur_depth);
- for (; ref->ctl_name || ref->procname || ref->child; ref++) {
- int match = 0;
-
- if (cur_depth && !ref->child)
- continue;
-
- if (test->procname && ref->procname &&
- (strcmp(test->procname, ref->procname) == 0))
- match++;
-
- if (test->ctl_name && ref->ctl_name &&
- (test->ctl_name == ref->ctl_name))
- match++;
-
- if (!ref->ctl_name && !ref->procname)
- match++;
-
- if (match) {
- if (cur_depth != 0) {
- cur_depth--;
- ref = ref->child;
- goto repeat;
- }
- goto out;
- }
- }
- ref = NULL;
-out:
- return ref;
-}
static void sysctl_print_path(struct ctl_table *table)
{
@@ -1315,26 +41,6 @@ static void sysctl_print_path(struct ctl_table *table)
}
}
printk(" ");
- if (table->ctl_name) {
- for (i = depth; i >= 0; i--) {
- tmp = sysctl_parent(table, i);
- printk(".%d", tmp->ctl_name);
- }
- }
-}
-
-static void sysctl_repair_table(struct ctl_table *table)
-{
- /* Don't complain about the classic default
- * sysctl strategy routine. Maybe later we
- * can get the tables fixed and complain about
- * this.
- */
- if (table->ctl_name && table->procname &&
- (table->proc_handler == proc_dointvec) &&
- (!table->strategy)) {
- table->strategy = sysctl_data;
- }
}
static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
@@ -1352,7 +58,7 @@ static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
ref = head->ctl_table;
repeat:
test = sysctl_parent(table, cur_depth);
- for (; ref->ctl_name || ref->procname; ref++) {
+ for (; ref->procname; ref++) {
int match = 0;
if (cur_depth && !ref->child)
continue;
@@ -1361,10 +67,6 @@ repeat:
(strcmp(test->procname, ref->procname) == 0))
match++;
- if (test->ctl_name && ref->ctl_name &&
- (test->ctl_name == ref->ctl_name))
- match++;
-
if (match) {
if (cur_depth != 0) {
cur_depth--;
@@ -1392,38 +94,6 @@ static void set_fail(const char **fail, struct ctl_table *table, const char *str
*fail = str;
}
-static int sysctl_check_dir(struct nsproxy *namespaces,
- struct ctl_table *table)
-{
- struct ctl_table *ref;
- int error;
-
- error = 0;
- ref = sysctl_check_lookup(namespaces, table);
- if (ref) {
- int match = 0;
- if ((!table->procname && !ref->procname) ||
- (table->procname && ref->procname &&
- (strcmp(table->procname, ref->procname) == 0)))
- match++;
-
- if ((!table->ctl_name && !ref->ctl_name) ||
- (table->ctl_name && ref->ctl_name &&
- (table->ctl_name == ref->ctl_name)))
- match++;
-
- if (match != 2) {
- printk(KERN_ERR "%s: failed: ", __func__);
- sysctl_print_path(table);
- printk(" ref: ");
- sysctl_print_path(ref);
- printk("\n");
- error = -EINVAL;
- }
- }
- return error;
-}
-
static void sysctl_check_leaf(struct nsproxy *namespaces,
struct ctl_table *table, const char **fail)
{
@@ -1434,37 +104,15 @@ static void sysctl_check_leaf(struct nsproxy *namespaces,
set_fail(fail, table, "Sysctl already exists");
}
-static void sysctl_check_bin_path(struct ctl_table *table, const char **fail)
-{
- const struct trans_ctl_table *ref;
-
- ref = sysctl_binary_lookup(table);
- if (table->ctl_name && !ref)
- set_fail(fail, table, "Unknown sysctl binary path");
- if (ref) {
- if (ref->procname &&
- (!table->procname ||
- (strcmp(table->procname, ref->procname) != 0)))
- set_fail(fail, table, "procname does not match binary path procname");
-
- if (ref->ctl_name && table->ctl_name &&
- (table->ctl_name != ref->ctl_name))
- set_fail(fail, table, "ctl_name does not match binary path ctl_name");
- }
-}
-
int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
{
int error = 0;
- for (; table->ctl_name || table->procname; table++) {
+ for (; table->procname; table++) {
const char *fail = NULL;
- sysctl_repair_table(table);
if (table->parent) {
if (table->procname && !table->parent->procname)
set_fail(&fail, table, "Parent without procname");
- if (table->ctl_name && !table->parent->ctl_name)
- set_fail(&fail, table, "Parent without ctl_name");
}
if (!table->procname)
set_fail(&fail, table, "No procname");
@@ -1477,21 +125,12 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
set_fail(&fail, table, "Writable sysctl directory");
if (table->proc_handler)
set_fail(&fail, table, "Directory with proc_handler");
- if (table->strategy)
- set_fail(&fail, table, "Directory with strategy");
if (table->extra1)
set_fail(&fail, table, "Directory with extra1");
if (table->extra2)
set_fail(&fail, table, "Directory with extra2");
- if (sysctl_check_dir(namespaces, table))
- set_fail(&fail, table, "Inconsistent directory names");
} else {
- if ((table->strategy == sysctl_data) ||
- (table->strategy == sysctl_string) ||
- (table->strategy == sysctl_intvec) ||
- (table->strategy == sysctl_jiffies) ||
- (table->strategy == sysctl_ms_jiffies) ||
- (table->proc_handler == proc_dostring) ||
+ if ((table->proc_handler == proc_dostring) ||
(table->proc_handler == proc_dointvec) ||
(table->proc_handler == proc_dointvec_minmax) ||
(table->proc_handler == proc_dointvec_jiffies) ||
@@ -1513,15 +152,7 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
set_fail(&fail, table, "No max");
}
}
-#ifdef CONFIG_SYSCTL_SYSCALL
- if (table->ctl_name && !table->strategy)
- set_fail(&fail, table, "Missing strategy");
-#endif
-#if 0
- if (!table->ctl_name && table->strategy)
- set_fail(&fail, table, "Strategy without ctl_name");
-#endif
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
if (table->procname && !table->proc_handler)
set_fail(&fail, table, "No proc_handler");
#endif
@@ -1531,7 +162,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
#endif
sysctl_check_leaf(namespaces, table, &fail);
}
- sysctl_check_bin_path(table, &fail);
if (table->mode > 0777)
set_fail(&fail, table, "bogus .mode");
if (fail) {
diff --git a/kernel/time.c b/kernel/time.c
index 2e2e469a7fe..c6324d96009 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -136,7 +136,6 @@ static inline void warp_clock(void)
write_seqlock_irq(&xtime_lock);
wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
xtime.tv_sec += sys_tz.tz_minuteswest * 60;
- update_xtime_cache(0);
write_sequnlock_irq(&xtime_lock);
clock_was_set();
}
@@ -662,6 +661,36 @@ u64 nsec_to_clock_t(u64 x)
#endif
}
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n: nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+#if (NSEC_PER_SEC % HZ) == 0
+ /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
+ return div_u64(n, NSEC_PER_SEC / HZ);
+#elif (HZ % 512) == 0
+ /* overflow after 292 years if HZ = 1024 */
+ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
+#else
+ /*
+ * Generic case - optimized for cases where HZ is a multiple of 3.
+ * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
+ */
+ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
+#endif
+}
+
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
{
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 0b0a6366c9d..ee266620b06 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,4 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 620b58abdc3..3d5fc0fd1cc 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -20,6 +20,8 @@
#include <linux/sysdev.h>
#include <linux/tick.h>
+#include "tick-internal.h"
+
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
static LIST_HEAD(clockevents_released);
@@ -28,7 +30,7 @@ static LIST_HEAD(clockevents_released);
static RAW_NOTIFIER_HEAD(clockevents_chain);
/* Protection for the above */
-static DEFINE_SPINLOCK(clockevents_lock);
+static DEFINE_RAW_SPINLOCK(clockevents_lock);
/**
* clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
@@ -37,10 +39,9 @@ static DEFINE_SPINLOCK(clockevents_lock);
*
* Math helper, returns latch value converted to nanoseconds (bound checked)
*/
-unsigned long clockevent_delta2ns(unsigned long latch,
- struct clock_event_device *evt)
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
{
- u64 clc = ((u64) latch << evt->shift);
+ u64 clc = (u64) latch << evt->shift;
if (unlikely(!evt->mult)) {
evt->mult = 1;
@@ -50,10 +51,10 @@ unsigned long clockevent_delta2ns(unsigned long latch,
do_div(clc, evt->mult);
if (clc < 1000)
clc = 1000;
- if (clc > LONG_MAX)
- clc = LONG_MAX;
+ if (clc > KTIME_MAX)
+ clc = KTIME_MAX;
- return (unsigned long) clc;
+ return clc;
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
@@ -140,9 +141,9 @@ int clockevents_register_notifier(struct notifier_block *nb)
unsigned long flags;
int ret;
- spin_lock_irqsave(&clockevents_lock, flags);
+ raw_spin_lock_irqsave(&clockevents_lock, flags);
ret = raw_notifier_chain_register(&clockevents_chain, nb);
- spin_unlock_irqrestore(&clockevents_lock, flags);
+ raw_spin_unlock_irqrestore(&clockevents_lock, flags);
return ret;
}
@@ -184,13 +185,13 @@ void clockevents_register_device(struct clock_event_device *dev)
BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
BUG_ON(!dev->cpumask);
- spin_lock_irqsave(&clockevents_lock, flags);
+ raw_spin_lock_irqsave(&clockevents_lock, flags);
list_add(&dev->list, &clockevent_devices);
clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
clockevents_notify_released();
- spin_unlock_irqrestore(&clockevents_lock, flags);
+ raw_spin_unlock_irqrestore(&clockevents_lock, flags);
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
@@ -240,7 +241,7 @@ void clockevents_notify(unsigned long reason, void *arg)
struct list_head *node, *tmp;
unsigned long flags;
- spin_lock_irqsave(&clockevents_lock, flags);
+ raw_spin_lock_irqsave(&clockevents_lock, flags);
clockevents_do_notify(reason, arg);
switch (reason) {
@@ -255,7 +256,7 @@ void clockevents_notify(unsigned long reason, void *arg)
default:
break;
}
- spin_unlock_irqrestore(&clockevents_lock, flags);
+ raw_spin_unlock_irqrestore(&clockevents_lock, flags);
}
EXPORT_SYMBOL_GPL(clockevents_notify);
#endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 09113347d32..e85c23404d3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -39,7 +39,7 @@ void timecounter_init(struct timecounter *tc,
tc->cycle_last = cc->read(cc);
tc->nsec = start_tstamp;
}
-EXPORT_SYMBOL(timecounter_init);
+EXPORT_SYMBOL_GPL(timecounter_init);
/**
* timecounter_read_delta - get nanoseconds since last call of this function
@@ -83,7 +83,7 @@ u64 timecounter_read(struct timecounter *tc)
return nsec;
}
-EXPORT_SYMBOL(timecounter_read);
+EXPORT_SYMBOL_GPL(timecounter_read);
u64 timecounter_cyc2time(struct timecounter *tc,
cycle_t cycle_tstamp)
@@ -105,7 +105,60 @@ u64 timecounter_cyc2time(struct timecounter *tc,
return nsec;
}
-EXPORT_SYMBOL(timecounter_cyc2time);
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
+
+/**
+ * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
+ * @mult: pointer to mult variable
+ * @shift: pointer to shift variable
+ * @from: frequency to convert from
+ * @to: frequency to convert to
+ * @minsec: guaranteed runtime conversion range in seconds
+ *
+ * The function evaluates the shift/mult pair for the scaled math
+ * operations of clocksources and clockevents.
+ *
+ * @to and @from are frequency values in HZ. For clock sources @to is
+ * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock
+ * event @to is the counter frequency and @from is NSEC_PER_SEC.
+ *
+ * The @minsec conversion range argument controls the time frame in
+ * seconds which must be covered by the runtime conversion with the
+ * calculated mult and shift factors. This guarantees that no 64bit
+ * overflow happens when the input value of the conversion is
+ * multiplied with the calculated mult factor. Larger ranges may
+ * reduce the conversion accuracy by chosing smaller mult and shift
+ * factors.
+ */
+void
+clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec)
+{
+ u64 tmp;
+ u32 sft, sftacc= 32;
+
+ /*
+ * Calculate the shift factor which is limiting the conversion
+ * range:
+ */
+ tmp = ((u64)minsec * from) >> 32;
+ while (tmp) {
+ tmp >>=1;
+ sftacc--;
+ }
+
+ /*
+ * Find the conversion shift/mult pair which has the best
+ * accuracy and fits the maxsec conversion range:
+ */
+ for (sft = 32; sft > 0; sft--) {
+ tmp = (u64) to << sft;
+ do_div(tmp, from);
+ if ((tmp >> sftacc) == 0)
+ break;
+ }
+ *mult = tmp;
+ *shift = sft;
+}
/*[Clocksource internal variables]---------
* curr_clocksource:
@@ -394,15 +447,11 @@ void clocksource_resume(void)
{
struct clocksource *cs;
- mutex_lock(&clocksource_mutex);
-
list_for_each_entry(cs, &clocksource_list, list)
if (cs->resume)
cs->resume();
clocksource_resume_watchdog();
-
- mutex_unlock(&clocksource_mutex);
}
/**
@@ -417,6 +466,47 @@ void clocksource_touch_watchdog(void)
clocksource_resume_watchdog();
}
+/**
+ * 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_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 which
+ * is equivalent to the below.
+ * max_cycles < (2^63)/cs->mult
+ * max_cycles < 2^(log2((2^63)/cs->mult))
+ * max_cycles < 2^(log2(2^63) - log2(cs->mult))
+ * max_cycles < 2^(63 - log2(cs->mult))
+ * max_cycles < 1 << (63 - log2(cs->mult))
+ * 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) + 1));
+
+ /*
+ * The actual maximum number of cycles we can defer the clocksource is
+ * determined by the minimum of max_cycles and cs->mask.
+ */
+ max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
+ max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+
+ /*
+ * To ensure that the clocksource does not wrap whilst we are idle,
+ * limit the time the clocksource can be deferred by 12.5%. Please
+ * note a margin of 12.5% is used because this can be computed with
+ * a shift, versus say 10% which would require division.
+ */
+ return max_nsecs - (max_nsecs >> 5);
+}
+
#ifdef CONFIG_GENERIC_TIME
/**
@@ -515,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs)
*/
int clocksource_register(struct clocksource *cs)
{
+ /* calculate max idle time permitted for this clocksource */
+ cs->max_idle_ns = clocksource_max_deferment(cs);
+
mutex_lock(&clocksource_mutex);
clocksource_enqueue(cs);
clocksource_select();
@@ -584,7 +677,7 @@ sysfs_show_current_clocksources(struct sys_device *dev,
* @count: length of buffer
*
* Takes input from sysfs interface for manually overriding the default
- * clocksource selction.
+ * clocksource selection.
*/
static ssize_t sysfs_override_clocksource(struct sys_device *dev,
struct sysdev_attribute *attr,
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index c2ec25087a3..b3bafd5fc66 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -31,7 +31,7 @@ static struct tick_device tick_broadcast_device;
/* FIXME: Use cpumask_var_t. */
static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
static DECLARE_BITMAP(tmpmask, NR_CPUS);
-static DEFINE_SPINLOCK(tick_broadcast_lock);
+static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
#ifdef CONFIG_TICK_ONESHOT
@@ -96,7 +96,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
unsigned long flags;
int ret = 0;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
* Devices might be registered with both periodic and oneshot
@@ -122,7 +122,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
tick_broadcast_clear_oneshot(cpu);
}
}
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
return ret;
}
@@ -161,13 +161,13 @@ static void tick_do_broadcast(struct cpumask *mask)
*/
static void tick_do_periodic_broadcast(void)
{
- spin_lock(&tick_broadcast_lock);
+ raw_spin_lock(&tick_broadcast_lock);
cpumask_and(to_cpumask(tmpmask),
cpu_online_mask, tick_get_broadcast_mask());
tick_do_broadcast(to_cpumask(tmpmask));
- spin_unlock(&tick_broadcast_lock);
+ raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -212,7 +212,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
unsigned long flags;
int cpu, bc_stopped;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
cpu = smp_processor_id();
td = &per_cpu(tick_cpu_device, cpu);
@@ -263,7 +263,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
tick_broadcast_setup_oneshot(bc);
}
out:
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
@@ -299,7 +299,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
unsigned long flags;
unsigned int cpu = *cpup;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
@@ -309,7 +309,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
clockevents_shutdown(bc);
}
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
void tick_suspend_broadcast(void)
@@ -317,13 +317,13 @@ void tick_suspend_broadcast(void)
struct clock_event_device *bc;
unsigned long flags;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
if (bc)
clockevents_shutdown(bc);
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
int tick_resume_broadcast(void)
@@ -332,7 +332,7 @@ int tick_resume_broadcast(void)
unsigned long flags;
int broadcast = 0;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
@@ -351,7 +351,7 @@ int tick_resume_broadcast(void)
break;
}
}
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
return broadcast;
}
@@ -405,7 +405,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
ktime_t now, next_event;
int cpu;
- spin_lock(&tick_broadcast_lock);
+ raw_spin_lock(&tick_broadcast_lock);
again:
dev->next_event.tv64 = KTIME_MAX;
next_event.tv64 = KTIME_MAX;
@@ -443,7 +443,7 @@ again:
if (tick_broadcast_set_event(next_event, 0))
goto again;
}
- spin_unlock(&tick_broadcast_lock);
+ raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -457,7 +457,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
unsigned long flags;
int cpu;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
* Periodic mode does not care about the enter/exit of power
@@ -492,7 +492,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
}
out:
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
@@ -563,13 +563,13 @@ void tick_broadcast_switch_to_oneshot(void)
struct clock_event_device *bc;
unsigned long flags;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
bc = tick_broadcast_device.evtdev;
if (bc)
tick_broadcast_setup_oneshot(bc);
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -581,7 +581,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
unsigned long flags;
unsigned int cpu = *cpup;
- spin_lock_irqsave(&tick_broadcast_lock, flags);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
* Clear the broadcast mask flag for the dead cpu, but do not
@@ -589,7 +589,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
*/
cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
- spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 83c4417b6a3..b6b898d2eee 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -34,7 +34,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
ktime_t tick_next_period;
ktime_t tick_period;
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
-DEFINE_SPINLOCK(tick_device_lock);
+static DEFINE_RAW_SPINLOCK(tick_device_lock);
/*
* Debugging: see timer_list.c
@@ -209,7 +209,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
int cpu, ret = NOTIFY_OK;
unsigned long flags;
- spin_lock_irqsave(&tick_device_lock, flags);
+ raw_spin_lock_irqsave(&tick_device_lock, flags);
cpu = smp_processor_id();
if (!cpumask_test_cpu(cpu, newdev->cpumask))
@@ -268,7 +268,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_oneshot_notify();
- spin_unlock_irqrestore(&tick_device_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_device_lock, flags);
return NOTIFY_STOP;
out_bc:
@@ -278,7 +278,7 @@ out_bc:
if (tick_check_broadcast_device(newdev))
ret = NOTIFY_STOP;
- spin_unlock_irqrestore(&tick_device_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_device_lock, flags);
return ret;
}
@@ -311,7 +311,7 @@ static void tick_shutdown(unsigned int *cpup)
struct clock_event_device *dev = td->evtdev;
unsigned long flags;
- spin_lock_irqsave(&tick_device_lock, flags);
+ raw_spin_lock_irqsave(&tick_device_lock, flags);
td->mode = TICKDEV_MODE_PERIODIC;
if (dev) {
/*
@@ -322,7 +322,7 @@ static void tick_shutdown(unsigned int *cpup)
clockevents_exchange_device(dev, NULL);
td->evtdev = NULL;
}
- spin_unlock_irqrestore(&tick_device_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
static void tick_suspend(void)
@@ -330,9 +330,9 @@ static void tick_suspend(void)
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
unsigned long flags;
- spin_lock_irqsave(&tick_device_lock, flags);
+ raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_shutdown(td->evtdev);
- spin_unlock_irqrestore(&tick_device_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
static void tick_resume(void)
@@ -341,7 +341,7 @@ static void tick_resume(void)
unsigned long flags;
int broadcast = tick_resume_broadcast();
- spin_lock_irqsave(&tick_device_lock, flags);
+ raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
if (!broadcast) {
@@ -350,7 +350,7 @@ static void tick_resume(void)
else
tick_resume_oneshot();
}
- spin_unlock_irqrestore(&tick_device_lock, flags);
+ raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
/*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index b1c05bf75ee..290eefbc1f6 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -6,7 +6,6 @@
#define TICK_DO_TIMER_BOOT -2
DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
-extern spinlock_t tick_device_lock;
extern ktime_t tick_next_period;
extern ktime_t tick_period;
extern int tick_do_timer_cpu __read_mostly;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index a96c0e2b89c..0a8a213016f 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -50,9 +50,9 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
dev->min_delta_ns += dev->min_delta_ns >> 1;
printk(KERN_WARNING
- "CE: %s increasing min_delta_ns to %lu nsec\n",
+ "CE: %s increasing min_delta_ns to %llu nsec\n",
dev->name ? dev->name : "?",
- dev->min_delta_ns << 1);
+ (unsigned long long) dev->min_delta_ns << 1);
i = 0;
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e0f59a21c06..f992762d7f5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,18 +134,13 @@ __setup("nohz=", setup_tick_nohz);
* value. We do this unconditionally on any cpu, as we don't know whether the
* cpu, which has the update task assigned is in a long sleep.
*/
-static void tick_nohz_update_jiffies(void)
+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;
- ktime_t now;
-
- if (!ts->tick_stopped)
- return;
cpumask_clear_cpu(cpu, nohz_cpu_mask);
- now = ktime_get();
ts->idle_waketime = now;
local_irq_save(flags);
@@ -155,20 +150,17 @@ static void tick_nohz_update_jiffies(void)
touch_softlockup_watchdog();
}
-static void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu, ktime_t now)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t delta;
- if (ts->idle_active) {
- ktime_t now, delta;
- now = ktime_get();
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- ts->idle_active = 0;
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_lastupdate = now;
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ ts->idle_active = 0;
- sched_clock_idle_wakeup_event(0);
- }
+ sched_clock_idle_wakeup_event(0);
}
static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -216,6 +208,7 @@ void tick_nohz_stop_sched_tick(int inidle)
struct tick_sched *ts;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+ u64 time_delta;
int cpu;
local_irq_save(flags);
@@ -231,6 +224,13 @@ void tick_nohz_stop_sched_tick(int inidle)
if (!inidle && !ts->inidle)
goto end;
+ /*
+ * 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;
+
now = tick_nohz_start_idle(ts);
/*
@@ -248,8 +248,6 @@ void tick_nohz_stop_sched_tick(int inidle)
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
- ts->inidle = 1;
-
if (need_resched())
goto end;
@@ -258,7 +256,7 @@ void tick_nohz_stop_sched_tick(int inidle)
if (ratelimit < 10) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- local_softirq_pending());
+ (unsigned int) local_softirq_pending());
ratelimit++;
}
goto end;
@@ -270,14 +268,18 @@ void tick_nohz_stop_sched_tick(int inidle)
seq = read_seqbegin(&xtime_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
+ time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
- /* Get the next timer wheel timer */
- next_jiffies = get_next_timer_interrupt(last_jiffies);
- delta_jiffies = next_jiffies - last_jiffies;
-
- if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
+ if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+ arch_needs_cpu(cpu)) {
+ next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
+ } else {
+ /* Get the next timer wheel timer */
+ next_jiffies = get_next_timer_interrupt(last_jiffies);
+ delta_jiffies = next_jiffies - last_jiffies;
+ }
/*
* Do not stop the tick, if we are only one off
* or if the cpu is required for rcu
@@ -289,22 +291,51 @@ void tick_nohz_stop_sched_tick(int inidle)
if ((long)delta_jiffies >= 1) {
/*
- * calculate the expiry time for the next timer wheel
- * timer
- */
- expires = ktime_add_ns(last_update, tick_period.tv64 *
- delta_jiffies);
-
- /*
* If this cpu is the one which updates jiffies, then
* give up the assignment and let it be taken by the
* cpu which runs the tick timer next, which might be
* this cpu as well. If we don't drop this here the
* jiffies might be stale and do_timer() never
- * invoked.
+ * invoked. Keep track of the fact that it was the one
+ * which had the do_timer() duty last. If this cpu is
+ * the one which had the do_timer() duty last, we
+ * limit the sleep time to the timekeeping
+ * max_deferement value which we retrieved
+ * above. Otherwise we can sleep as long as we want.
*/
- if (cpu == tick_do_timer_cpu)
+ if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ ts->do_timer_last = 1;
+ } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+ time_delta = KTIME_MAX;
+ ts->do_timer_last = 0;
+ } else if (!ts->do_timer_last) {
+ time_delta = KTIME_MAX;
+ }
+
+ /*
+ * calculate the expiry time for the next timer wheel
+ * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
+ * that there is no timer pending or at least extremely
+ * far into the future (12 days for HZ=1000). In this
+ * case we set the expiry to the end of time.
+ */
+ if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) {
+ /*
+ * Calculate the time delta for the next timer event.
+ * If the time delta exceeds the maximum time delta
+ * permitted by the current clocksource then adjust
+ * the time delta accordingly to ensure the
+ * clocksource does not wrap.
+ */
+ time_delta = min_t(u64, time_delta,
+ tick_period.tv64 * delta_jiffies);
+ }
+
+ if (time_delta < KTIME_MAX)
+ expires = ktime_add_ns(last_update, time_delta);
+ else
+ expires.tv64 = KTIME_MAX;
if (delta_jiffies > 1)
cpumask_set_cpu(cpu, nohz_cpu_mask);
@@ -337,22 +368,19 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->idle_sleeps++;
+ /* Mark expires */
+ ts->idle_expires = expires;
+
/*
- * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
- * there is no timer pending or at least extremly far
- * into the future (12 days for HZ=1000). In this case
- * we simply stop the tick timer:
+ * If the expiration time == KTIME_MAX, then
+ * in this case we simply stop the tick timer.
*/
- if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
- ts->idle_expires.tv64 = KTIME_MAX;
+ if (unlikely(expires.tv64 == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
goto out;
}
- /* Mark expiries */
- ts->idle_expires = expires;
-
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, expires,
HRTIMER_MODE_ABS_PINNED);
@@ -431,7 +459,11 @@ void tick_nohz_restart_sched_tick(void)
ktime_t now;
local_irq_disable();
- tick_nohz_stop_idle(cpu);
+ if (ts->idle_active || (ts->inidle && ts->tick_stopped))
+ now = ktime_get();
+
+ if (ts->idle_active)
+ tick_nohz_stop_idle(cpu, now);
if (!ts->inidle || !ts->tick_stopped) {
ts->inidle = 0;
@@ -445,7 +477,6 @@ void tick_nohz_restart_sched_tick(void)
/* Update jiffies first */
select_nohz_load_balancer(0);
- now = ktime_get();
tick_do_update_jiffies64(now);
cpumask_clear_cpu(cpu, nohz_cpu_mask);
@@ -579,22 +610,18 @@ 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)
+static void tick_nohz_kick_tick(int cpu, 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, now;
-
- if (!ts->tick_stopped)
- return;
+ ktime_t delta;
/*
* Do not touch the tick device, when the next expiry is either
* already reached or less/equal than the tick period.
*/
- now = ktime_get();
delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
if (delta.tv64 <= tick_period.tv64)
return;
@@ -603,9 +630,26 @@ static void tick_nohz_kick_tick(int cpu)
#endif
}
+static inline void tick_check_nohz(int cpu)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ ktime_t now;
+
+ if (!ts->idle_active && !ts->tick_stopped)
+ return;
+ now = ktime_get();
+ if (ts->idle_active)
+ tick_nohz_stop_idle(cpu, now);
+ if (ts->tick_stopped) {
+ tick_nohz_update_jiffies(now);
+ tick_nohz_kick_tick(cpu, now);
+ }
+}
+
#else
static inline void tick_nohz_switch_to_nohz(void) { }
+static inline void tick_check_nohz(int cpu) { }
#endif /* NO_HZ */
@@ -615,11 +659,7 @@ static inline void tick_nohz_switch_to_nohz(void) { }
void tick_check_idle(int cpu)
{
tick_check_oneshot_broadcast(cpu);
-#ifdef CONFIG_NO_HZ
- tick_nohz_stop_idle(cpu);
- tick_nohz_update_jiffies();
- tick_nohz_kick_tick(cpu);
-#endif
+ tick_check_nohz(cpu);
}
/*
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index 71e7f1a1915..12f5c55090b 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -40,7 +40,7 @@ ktime_t timecompare_transform(struct timecompare *sync,
return ns_to_ktime(nsec);
}
-EXPORT_SYMBOL(timecompare_transform);
+EXPORT_SYMBOL_GPL(timecompare_transform);
int timecompare_offset(struct timecompare *sync,
s64 *offset,
@@ -89,7 +89,7 @@ int timecompare_offset(struct timecompare *sync,
* source time
*/
sample.offset =
- ktime_to_ns(ktime_add(end, start)) / 2 -
+ (ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
ts;
/* simple insertion sort based on duration */
@@ -131,7 +131,7 @@ int timecompare_offset(struct timecompare *sync,
return used;
}
-EXPORT_SYMBOL(timecompare_offset);
+EXPORT_SYMBOL_GPL(timecompare_offset);
void __timecompare_update(struct timecompare *sync,
u64 source_tstamp)
@@ -188,4 +188,4 @@ void __timecompare_update(struct timecompare *sync,
}
}
}
-EXPORT_SYMBOL(__timecompare_update);
+EXPORT_SYMBOL_GPL(__timecompare_update);
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
new file mode 100644
index 00000000000..86628e755f3
--- /dev/null
+++ b/kernel/time/timeconv.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library 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
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB. If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * Converts the calendar time to broken-down time representation
+ * Based on code from glibc-2.6
+ *
+ * 2009-7-14:
+ * Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ */
+
+#include <linux/time.h>
+#include <linux/module.h>
+
+/*
+ * Nonzero if YEAR is a leap year (every 4 years,
+ * except every 100th isn't, and every 400th is).
+ */
+static int __isleap(long year)
+{
+ return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0);
+}
+
+/* do a mathdiv for long type */
+static long math_div(long a, long b)
+{
+ return a / b - (a % b < 0);
+}
+
+/* How many leap years between y1 and y2, y1 must less or equal to y2 */
+static long leaps_between(long y1, long y2)
+{
+ long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100)
+ + math_div(y1 - 1, 400);
+ long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100)
+ + math_div(y2 - 1, 400);
+ return leaps2 - leaps1;
+}
+
+/* How many days come before each month (0-12). */
+static const unsigned short __mon_yday[2][13] = {
+ /* Normal years. */
+ {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+ /* Leap years. */
+ {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+};
+
+#define SECS_PER_HOUR (60 * 60)
+#define SECS_PER_DAY (SECS_PER_HOUR * 24)
+
+/**
+ * time_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ * Coordinated Universal Time (UTC).
+ * @offset offset seconds adding to totalsecs.
+ * @result pointer to struct tm variable to receive broken-down time
+ */
+void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+{
+ long days, rem, y;
+ const unsigned short *ip;
+
+ days = totalsecs / SECS_PER_DAY;
+ rem = totalsecs % SECS_PER_DAY;
+ rem += offset;
+ while (rem < 0) {
+ rem += SECS_PER_DAY;
+ --days;
+ }
+ while (rem >= SECS_PER_DAY) {
+ rem -= SECS_PER_DAY;
+ ++days;
+ }
+
+ result->tm_hour = rem / SECS_PER_HOUR;
+ rem %= SECS_PER_HOUR;
+ result->tm_min = rem / 60;
+ result->tm_sec = rem % 60;
+
+ /* January 1, 1970 was a Thursday. */
+ result->tm_wday = (4 + days) % 7;
+ if (result->tm_wday < 0)
+ result->tm_wday += 7;
+
+ y = 1970;
+
+ while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
+ /* Guess a corrected year, assuming 365 days per year. */
+ long yg = y + math_div(days, 365);
+
+ /* Adjust DAYS and Y to match the guessed year. */
+ days -= (yg - y) * 365 + leaps_between(y, yg);
+ y = yg;
+ }
+
+ result->tm_year = y - 1900;
+
+ result->tm_yday = days;
+
+ ip = __mon_yday[__isleap(y)];
+ for (y = 11; days < ip[y]; y--)
+ continue;
+ days -= ip[y];
+
+ result->tm_mon = y;
+ result->tm_mday = days + 1;
+}
+EXPORT_SYMBOL(time_to_tm);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb0f46fa1ec..af4135f0582 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
+#include <linux/sched.h>
#include <linux/sysdev.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
@@ -164,19 +165,12 @@ struct timespec raw_time;
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
- xtime_cache = xtime;
- timespec_add_ns(&xtime_cache, nsec);
-}
-
/* must hold xtime_lock */
void timekeeping_leap_insert(int leapsecond)
{
xtime.tv_sec += leapsecond;
wall_to_monotonic.tv_sec -= leapsecond;
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
#ifdef CONFIG_GENERIC_TIME
@@ -331,12 +325,10 @@ int do_settimeofday(struct timespec *tv)
xtime = *tv;
- update_xtime_cache(0);
-
timekeeper.ntp_error = 0;
ntp_clear();
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -487,6 +479,17 @@ int timekeeping_valid_for_hres(void)
}
/**
+ * timekeeping_max_deferment - Returns max time the clocksource can be deferred
+ *
+ * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
+ * ensure that the clocksource does not change!
+ */
+u64 timekeeping_max_deferment(void)
+{
+ return timekeeper.clock->max_idle_ns;
+}
+
+/**
* read_persistent_clock - Return time from the persistent clock.
*
* Weak dummy function for arches that do not yet support it.
@@ -547,7 +550,6 @@ void __init timekeeping_init(void)
}
set_normalized_timespec(&wall_to_monotonic,
-boot.tv_sec, -boot.tv_nsec);
- update_xtime_cache(0);
total_sleep_time.tv_sec = 0;
total_sleep_time.tv_nsec = 0;
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -581,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
total_sleep_time = timespec_add_safe(total_sleep_time, ts);
}
- update_xtime_cache(0);
/* re-base the last cycle value */
timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
timekeeper.ntp_error = 0;
@@ -722,6 +723,49 @@ static void timekeeping_adjust(s64 offset)
}
/**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+ u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+ /* If the offset is smaller then a shifted interval, do nothing */
+ if (offset < timekeeper.cycle_interval<<shift)
+ return offset;
+
+ /* Accumulate one shifted interval */
+ offset -= timekeeper.cycle_interval << shift;
+ timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+ timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+ while (timekeeper.xtime_nsec >= nsecps) {
+ timekeeper.xtime_nsec -= nsecps;
+ xtime.tv_sec++;
+ second_overflow();
+ }
+
+ /* Accumulate into raw time */
+ raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+ while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+ raw_time.tv_nsec -= NSEC_PER_SEC;
+ raw_time.tv_sec++;
+ }
+
+ /* Accumulate error between NTP and clock interval */
+ timekeeper.ntp_error += tick_length << shift;
+ timekeeper.ntp_error -= timekeeper.xtime_interval <<
+ (timekeeper.ntp_error_shift + shift);
+
+ return offset;
+}
+
+/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
* Called from the timer interrupt, must hold a write on xtime_lock.
@@ -730,7 +774,7 @@ void update_wall_time(void)
{
struct clocksource *clock;
cycle_t offset;
- u64 nsecs;
+ int shift = 0, maxshift;
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
@@ -744,33 +788,22 @@ void update_wall_time(void)
#endif
timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
- /* normally this loop will run just once, however in the
- * case of lost or late ticks, it will accumulate correctly.
+ /*
+ * With NO_HZ we may have to accumulate many cycle_intervals
+ * (think "ticks") worth of time at once. To do this efficiently,
+ * we calculate the largest doubling multiple of cycle_intervals
+ * that is smaller then the offset. We then accumulate that
+ * chunk in one go, and then try to consume the next smaller
+ * doubled multiple.
*/
+ shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+ shift = max(0, shift);
+ /* Bound shift to one less then what overflows tick_length */
+ maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+ shift = min(shift, maxshift);
while (offset >= timekeeper.cycle_interval) {
- u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
- /* accumulate one interval */
- offset -= timekeeper.cycle_interval;
- clock->cycle_last += timekeeper.cycle_interval;
-
- timekeeper.xtime_nsec += timekeeper.xtime_interval;
- if (timekeeper.xtime_nsec >= nsecps) {
- timekeeper.xtime_nsec -= nsecps;
- xtime.tv_sec++;
- second_overflow();
- }
-
- raw_time.tv_nsec += timekeeper.raw_interval;
- if (raw_time.tv_nsec >= NSEC_PER_SEC) {
- raw_time.tv_nsec -= NSEC_PER_SEC;
- raw_time.tv_sec++;
- }
-
- /* accumulate error between NTP and clock interval */
- timekeeper.ntp_error += tick_length;
- timekeeper.ntp_error -= timekeeper.xtime_interval <<
- timekeeper.ntp_error_shift;
+ offset = logarithmic_accumulation(offset, shift);
+ shift--;
}
/* correct the clock when NTP error is too big */
@@ -806,11 +839,8 @@ void update_wall_time(void)
timekeeper.ntp_error += timekeeper.xtime_nsec <<
timekeeper.ntp_error_shift;
- nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
- update_xtime_cache(nsecs);
-
/* check to see if there is a new clocksource to use */
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
/**
@@ -845,13 +875,13 @@ void monotonic_to_bootbased(struct timespec *ts)
unsigned long get_seconds(void)
{
- return xtime_cache.tv_sec;
+ return xtime.tv_sec;
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
- return xtime_cache;
+ return xtime;
}
struct timespec current_kernel_time(void)
@@ -861,8 +891,7 @@ struct timespec current_kernel_time(void)
do {
seq = read_seqbegin(&xtime_lock);
-
- now = xtime_cache;
+ now = xtime;
} while (read_seqretry(&xtime_lock, seq));
return now;
@@ -876,8 +905,7 @@ struct timespec get_monotonic_coarse(void)
do {
seq = read_seqbegin(&xtime_lock);
-
- now = xtime_cache;
+ now = xtime;
mono = wall_to_monotonic;
} while (read_seqretry(&xtime_lock, seq));
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index fddd69d16e0..28265636b6c 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -84,7 +84,7 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
next_one:
i = 0;
- spin_lock_irqsave(&base->cpu_base->lock, flags);
+ raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
curr = base->first;
/*
@@ -100,13 +100,13 @@ next_one:
timer = rb_entry(curr, struct hrtimer, node);
tmp = *timer;
- spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+ raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
print_timer(m, timer, &tmp, i, now);
next++;
goto next_one;
}
- spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+ raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
}
static void
@@ -150,6 +150,9 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
P_ns(expires_next);
P(hres_active);
P(nr_events);
+ P(nr_retries);
+ P(nr_hangs);
+ P_ns(max_hang_time);
#endif
#undef P
#undef P_ns
@@ -204,10 +207,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
return;
}
SEQ_printf(m, "%s\n", dev->name);
- SEQ_printf(m, " max_delta_ns: %lu\n", dev->max_delta_ns);
- SEQ_printf(m, " min_delta_ns: %lu\n", dev->min_delta_ns);
- SEQ_printf(m, " mult: %lu\n", dev->mult);
- SEQ_printf(m, " shift: %d\n", dev->shift);
+ SEQ_printf(m, " max_delta_ns: %llu\n",
+ (unsigned long long) dev->max_delta_ns);
+ SEQ_printf(m, " min_delta_ns: %llu\n",
+ (unsigned long long) dev->min_delta_ns);
+ SEQ_printf(m, " mult: %u\n", dev->mult);
+ SEQ_printf(m, " shift: %u\n", dev->shift);
SEQ_printf(m, " mode: %d\n", dev->mode);
SEQ_printf(m, " next_event: %Ld nsecs\n",
(unsigned long long) ktime_to_ns(dev->next_event));
@@ -252,7 +257,7 @@ static int timer_list_show(struct seq_file *m, void *v)
u64 now = ktime_to_ns(ktime_get());
int cpu;
- SEQ_printf(m, "Timer List Version: v0.4\n");
+ SEQ_printf(m, "Timer List Version: v0.5\n");
SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
@@ -275,7 +280,7 @@ static int timer_list_open(struct inode *inode, struct file *filp)
return single_open(filp, timer_list_show, NULL);
}
-static struct file_operations timer_list_fops = {
+static const struct file_operations timer_list_fops = {
.open = timer_list_open,
.read = seq_read,
.llseek = seq_lseek,
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 4cde8b9c716..2f3b585b8d7 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -86,7 +86,7 @@ static DEFINE_SPINLOCK(table_lock);
/*
* Per-CPU lookup locks for fast hash lookup:
*/
-static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
/*
* Mutex to serialize state changes with show-stats activities:
@@ -238,14 +238,14 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
/*
* It doesnt matter which lock we take:
*/
- spinlock_t *lock;
+ raw_spinlock_t *lock;
struct entry *entry, input;
unsigned long flags;
if (likely(!timer_stats_active))
return;
- lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+ lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
input.timer = timer;
input.start_func = startf;
@@ -253,7 +253,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
input.pid = pid;
input.timer_flag = timer_flag;
- spin_lock_irqsave(lock, flags);
+ raw_spin_lock_irqsave(lock, flags);
if (!timer_stats_active)
goto out_unlock;
@@ -264,7 +264,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
atomic_inc(&overflow_count);
out_unlock:
- spin_unlock_irqrestore(lock, flags);
+ raw_spin_unlock_irqrestore(lock, flags);
}
static void print_name_offset(struct seq_file *m, unsigned long addr)
@@ -348,9 +348,11 @@ static void sync_access(void)
int cpu;
for_each_online_cpu(cpu) {
- spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+ raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
+
+ raw_spin_lock_irqsave(lock, flags);
/* nothing */
- spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+ raw_spin_unlock_irqrestore(lock, flags);
}
}
@@ -395,7 +397,7 @@ static int tstats_open(struct inode *inode, struct file *filp)
return single_open(filp, tstats_show, NULL);
}
-static struct file_operations tstats_fops = {
+static const struct file_operations tstats_fops = {
.open = tstats_open,
.read = seq_read,
.write = tstats_write,
@@ -408,7 +410,7 @@ void __init init_timer_stats(void)
int cpu;
for_each_possible_cpu(cpu)
- spin_lock_init(&per_cpu(lookup_lock, cpu));
+ raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
}
static int __init init_tstats_procfs(void)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b416512ad17..d006554888d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -339,6 +339,27 @@ config POWER_TRACER
power management decisions, specifically the C-state and P-state
behavior.
+config KSYM_TRACER
+ bool "Trace read and write access on kernel memory locations"
+ depends on HAVE_HW_BREAKPOINT
+ select TRACING
+ help
+ This tracer helps find read and write operations on any given kernel
+ symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+ bool "Profile all kernel memory accesses on 'watched' variables"
+ depends on KSYM_TRACER
+ help
+ This tracer profiles kernel accesses on variables watched through the
+ ksym tracer ftrace plugin. Depending upon the hardware, all read
+ and write operations on kernel variables can be monitored for
+ accesses.
+
+ The results will be displayed in:
+ /debugfs/tracing/profile_ksym
+
+ Say N if unsure.
config STACK_TRACER
bool "Trace max stack"
@@ -428,6 +449,23 @@ config BLK_DEV_IO_TRACE
If unsure, say N.
+config KPROBE_EVENT
+ depends on KPROBES
+ depends on X86
+ bool "Enable kprobes-based dynamic events"
+ select TRACING
+ default y
+ help
+ This allows the user to add tracing events (similar to tracepoints) on the fly
+ via the ftrace interface. See Documentation/trace/kprobetrace.txt
+ for more details.
+
+ Those events can be inserted wherever kprobes can probe, and record
+ various register and memory values.
+
+ This option is also required by perf-probe subcommand of perf tools. If
+ you want to use perf tools, this option is strongly recommended.
+
config DYNAMIC_FTRACE
bool "enable/disable ftrace tracepoints dynamically"
depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 26f03ac07c2..cd9ecd89ec7 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,8 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
obj-$(CONFIG_EVENT_TRACING) += power-traces.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 3eb159c277c..d9d6206e0b1 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -856,6 +856,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
}
/**
+ * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @q: queue the io is for
+ * @rq: the source request
+ * @dev: target device
+ * @from: source sector
+ *
+ * Description:
+ * Device mapper remaps request to other devices.
+ * Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_rq_remap(struct request_queue *q,
+ struct request *rq, dev_t dev,
+ sector_t from)
+{
+ struct blk_trace *bt = q->blk_trace;
+ struct blk_io_trace_remap r;
+
+ if (likely(!bt))
+ return;
+
+ r.device_from = cpu_to_be32(dev);
+ r.device_to = cpu_to_be32(disk_devt(rq->rq_disk));
+ r.sector_from = cpu_to_be64(from);
+
+ __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+ rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+ sizeof(r), &r);
+}
+
+/**
* blk_add_driver_data - Add binary message with driver-specific data
* @q: queue the io is for
* @rq: io request
@@ -922,10 +953,13 @@ static void blk_register_tracepoints(void)
WARN_ON(ret);
ret = register_trace_block_remap(blk_add_trace_remap);
WARN_ON(ret);
+ ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+ WARN_ON(ret);
}
static void blk_unregister_tracepoints(void)
{
+ unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
unregister_trace_block_remap(blk_add_trace_remap);
unregister_trace_block_split(blk_add_trace_split);
unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
@@ -1657,6 +1691,11 @@ int blk_trace_init_sysfs(struct device *dev)
return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
}
+void blk_trace_remove_sysfs(struct device *dev)
+{
+ sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
+}
+
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#ifdef CONFIG_EVENT_TRACING
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 23df7771c93..e51a1bcb7be 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -60,6 +60,13 @@ static int last_ftrace_enabled;
/* Quick disabling of function tracer. */
int function_trace_stop;
+/* List for set_ftrace_pid's pids. */
+LIST_HEAD(ftrace_pids);
+struct ftrace_pid {
+ struct list_head list;
+ struct pid *pid;
+};
+
/*
* ftrace_disabled is set when an anomaly is discovered.
* ftrace_disabled is much stronger than ftrace_enabled.
@@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+#endif
+
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_ops *op = ftrace_list;
@@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
else
func = ftrace_list_func;
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
@@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_list->next == &ftrace_list_end) {
ftrace_func_t func = ftrace_list->func;
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
@@ -225,9 +236,13 @@ static void ftrace_update_pid_func(void)
if (ftrace_trace_function == ftrace_stub)
return;
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
func = ftrace_trace_function;
+#else
+ func = __ftrace_trace_function;
+#endif
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
} else {
@@ -736,7 +751,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
out:
mutex_unlock(&ftrace_profile_lock);
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -817,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
}
#endif /* CONFIG_FUNCTION_PROFILER */
-/* set when tracing only a pid */
-struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -1074,14 +1087,9 @@ static void ftrace_replace_code(int enable)
failed = __ftrace_replace_code(rec, enable);
if (failed) {
rec->flags |= FTRACE_FL_FAILED;
- if ((system_state == SYSTEM_BOOTING) ||
- !core_kernel_text(rec->ip)) {
- ftrace_free_rec(rec);
- } else {
- ftrace_bug(failed, rec->ip);
- /* Stop processing */
- return;
- }
+ ftrace_bug(failed, rec->ip);
+ /* Stop processing */
+ return;
}
} while_for_each_ftrace_rec();
}
@@ -1262,12 +1270,34 @@ static int ftrace_update_code(struct module *mod)
ftrace_new_addrs = p->newlist;
p->flags = 0L;
- /* convert record (i.e, patch mcount-call with NOP) */
- if (ftrace_code_disable(mod, p)) {
- p->flags |= FTRACE_FL_CONVERTED;
- ftrace_update_cnt++;
- } else
+ /*
+ * Do the initial record convertion from mcount jump
+ * to the NOP instructions.
+ */
+ if (!ftrace_code_disable(mod, p)) {
ftrace_free_rec(p);
+ continue;
+ }
+
+ p->flags |= FTRACE_FL_CONVERTED;
+ ftrace_update_cnt++;
+
+ /*
+ * If the tracing is enabled, go ahead and enable the record.
+ *
+ * The reason not to enable the record immediatelly is the
+ * inherent check of ftrace_make_nop/ftrace_make_call for
+ * correct previous instructions. Making first the NOP
+ * conversion puts the module to the correct state, thus
+ * passing the ftrace_make_call check.
+ */
+ if (ftrace_start_up) {
+ int failed = __ftrace_replace_code(p, 1);
+ if (failed) {
+ ftrace_bug(failed, p->ip);
+ ftrace_free_rec(p);
+ }
+ }
}
stop = ftrace_now(raw_smp_processor_id());
@@ -1621,8 +1651,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
if (!ret) {
struct seq_file *m = file->private_data;
m->private = iter;
- } else
+ } else {
+ trace_parser_put(&iter->parser);
kfree(iter);
+ }
} else
file->private_data = iter;
mutex_unlock(&ftrace_regex_lock);
@@ -1655,60 +1687,6 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
return ret;
}
-enum {
- MATCH_FULL,
- MATCH_FRONT_ONLY,
- MATCH_MIDDLE_ONLY,
- MATCH_END_ONLY,
-};
-
-/*
- * (static function - no need for kernel doc)
- *
- * Pass in a buffer containing a glob and this function will
- * set search to point to the search part of the buffer and
- * return the type of search it is (see enum above).
- * This does modify buff.
- *
- * Returns enum type.
- * search returns the pointer to use for comparison.
- * not returns 1 if buff started with a '!'
- * 0 otherwise.
- */
-static int
-ftrace_setup_glob(char *buff, int len, char **search, int *not)
-{
- int type = MATCH_FULL;
- int i;
-
- if (buff[0] == '!') {
- *not = 1;
- buff++;
- len--;
- } else
- *not = 0;
-
- *search = buff;
-
- for (i = 0; i < len; i++) {
- if (buff[i] == '*') {
- if (!i) {
- *search = buff + 1;
- type = MATCH_END_ONLY;
- } else {
- if (type == MATCH_END_ONLY)
- type = MATCH_MIDDLE_ONLY;
- else
- type = MATCH_FRONT_ONLY;
- buff[i] = 0;
- break;
- }
- }
- }
-
- return type;
-}
-
static int ftrace_match(char *str, char *regex, int len, int type)
{
int matched = 0;
@@ -1757,7 +1735,7 @@ static void ftrace_match_records(char *buff, int len, int enable)
int not;
flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
- type = ftrace_setup_glob(buff, len, &search, &not);
+ type = filter_parse_regex(buff, len, &search, &not);
search_len = strlen(search);
@@ -1825,7 +1803,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
}
if (strlen(buff)) {
- type = ftrace_setup_glob(buff, strlen(buff), &search, &not);
+ type = filter_parse_regex(buff, strlen(buff), &search, &not);
search_len = strlen(search);
}
@@ -1990,7 +1968,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
int count = 0;
char *search;
- type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
len = strlen(search);
/* we do not support '!' for function probes */
@@ -2067,7 +2045,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
else if (glob) {
int not;
- type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
len = strlen(search);
/* we do not support '!' for function probes */
@@ -2202,7 +2180,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
struct trace_parser *parser;
ssize_t ret, read;
- if (!cnt || cnt < 0)
+ if (!cnt)
return 0;
mutex_lock(&ftrace_regex_lock);
@@ -2216,20 +2194,20 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
parser = &iter->parser;
read = trace_get_user(parser, ubuf, cnt, ppos);
- if (trace_parser_loaded(parser) &&
+ if (read >= 0 && trace_parser_loaded(parser) &&
!trace_parser_cont(parser)) {
ret = ftrace_process_regex(parser->buffer,
parser->idx, enable);
if (ret)
- goto out;
+ goto out_unlock;
trace_parser_clear(parser);
}
ret = read;
-
+out_unlock:
mutex_unlock(&ftrace_regex_lock);
-out:
+
return ret;
}
@@ -2311,6 +2289,32 @@ static int __init set_ftrace_filter(char *str)
}
__setup("ftrace_filter=", set_ftrace_filter);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int __init set_graph_function(char *str)
+{
+ strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_graph_filter=", set_graph_function);
+
+static void __init set_ftrace_early_graph(char *buf)
+{
+ int ret;
+ char *func;
+
+ while (buf) {
+ func = strsep(&buf, ",");
+ /* we allow only one expression at a time */
+ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+ func);
+ if (ret)
+ printk(KERN_DEBUG "ftrace: function %s not "
+ "traceable\n", func);
+ }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
static void __init set_ftrace_early_filter(char *buf, int enable)
{
char *func;
@@ -2327,6 +2331,10 @@ static void __init set_ftrace_early_filters(void)
set_ftrace_early_filter(ftrace_filter_buf, 1);
if (ftrace_notrace_buf[0])
set_ftrace_early_filter(ftrace_notrace_buf, 0);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ if (ftrace_graph_buf[0])
+ set_ftrace_early_graph(ftrace_graph_buf);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
}
static int
@@ -2512,7 +2520,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
return -ENODEV;
/* decode regex */
- type = ftrace_setup_glob(buffer, strlen(buffer), &search, &not);
+ type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
if (not)
return -EINVAL;
@@ -2552,8 +2560,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
- size_t read = 0;
- ssize_t ret;
+ ssize_t read, ret;
if (!cnt || cnt < 0)
return 0;
@@ -2562,29 +2569,31 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
ret = -EBUSY;
- goto out;
+ goto out_unlock;
}
if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
ret = -ENOMEM;
- goto out;
+ goto out_unlock;
}
read = trace_get_user(&parser, ubuf, cnt, ppos);
- if (trace_parser_loaded((&parser))) {
+ if (read >= 0 && trace_parser_loaded((&parser))) {
parser.buffer[parser.idx] = 0;
/* we allow only one expression at a time */
ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
parser.buffer);
if (ret)
- goto out;
+ goto out_free;
}
ret = read;
- out:
+
+out_free:
trace_parser_put(&parser);
+out_unlock:
mutex_unlock(&graph_lock);
return ret;
@@ -2622,7 +2631,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
return 0;
}
-static int ftrace_convert_nops(struct module *mod,
+static int ftrace_process_locs(struct module *mod,
unsigned long *start,
unsigned long *end)
{
@@ -2655,19 +2664,17 @@ static int ftrace_convert_nops(struct module *mod,
}
#ifdef CONFIG_MODULES
-void ftrace_release(void *start, void *end)
+void ftrace_release_mod(struct module *mod)
{
struct dyn_ftrace *rec;
struct ftrace_page *pg;
- unsigned long s = (unsigned long)start;
- unsigned long e = (unsigned long)end;
- if (ftrace_disabled || !start || start == end)
+ if (ftrace_disabled)
return;
mutex_lock(&ftrace_lock);
do_for_each_ftrace_rec(pg, rec) {
- if ((rec->ip >= s) && (rec->ip < e)) {
+ if (within_module_core(rec->ip, mod)) {
/*
* rec->ip is changed in ftrace_free_rec()
* It should not between s and e if record was freed.
@@ -2684,7 +2691,7 @@ static void ftrace_init_module(struct module *mod,
{
if (ftrace_disabled || start == end)
return;
- ftrace_convert_nops(mod, start, end);
+ ftrace_process_locs(mod, start, end);
}
static int ftrace_module_notify(struct notifier_block *self,
@@ -2699,9 +2706,7 @@ static int ftrace_module_notify(struct notifier_block *self,
mod->num_ftrace_callsites);
break;
case MODULE_STATE_GOING:
- ftrace_release(mod->ftrace_callsites,
- mod->ftrace_callsites +
- mod->num_ftrace_callsites);
+ ftrace_release_mod(mod);
break;
}
@@ -2747,7 +2752,7 @@ void __init ftrace_init(void)
last_ftrace_enabled = ftrace_enabled = 1;
- ret = ftrace_convert_nops(NULL,
+ ret = ftrace_process_locs(NULL,
__start_mcount_loc,
__stop_mcount_loc);
@@ -2780,23 +2785,6 @@ static inline void ftrace_startup_enable(int command) { }
# define ftrace_shutdown_sysctl() do { } while (0)
#endif /* CONFIG_DYNAMIC_FTRACE */
-static ssize_t
-ftrace_pid_read(struct file *file, char __user *ubuf,
- size_t cnt, loff_t *ppos)
-{
- char buf[64];
- int r;
-
- if (ftrace_pid_trace == ftrace_swapper_pid)
- r = sprintf(buf, "swapper tasks\n");
- else if (ftrace_pid_trace)
- r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
- else
- r = sprintf(buf, "no pid\n");
-
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
static void clear_ftrace_swapper(void)
{
struct task_struct *p;
@@ -2847,14 +2835,12 @@ static void set_ftrace_pid(struct pid *pid)
rcu_read_unlock();
}
-static void clear_ftrace_pid_task(struct pid **pid)
+static void clear_ftrace_pid_task(struct pid *pid)
{
- if (*pid == ftrace_swapper_pid)
+ if (pid == ftrace_swapper_pid)
clear_ftrace_swapper();
else
- clear_ftrace_pid(*pid);
-
- *pid = NULL;
+ clear_ftrace_pid(pid);
}
static void set_ftrace_pid_task(struct pid *pid)
@@ -2865,74 +2851,184 @@ static void set_ftrace_pid_task(struct pid *pid)
set_ftrace_pid(pid);
}
-static ssize_t
-ftrace_pid_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int ftrace_pid_add(int p)
{
struct pid *pid;
- char buf[64];
- long val;
- int ret;
+ struct ftrace_pid *fpid;
+ int ret = -EINVAL;
- if (cnt >= sizeof(buf))
- return -EINVAL;
+ mutex_lock(&ftrace_lock);
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
+ if (!p)
+ pid = ftrace_swapper_pid;
+ else
+ pid = find_get_pid(p);
- buf[cnt] = 0;
+ if (!pid)
+ goto out;
- ret = strict_strtol(buf, 10, &val);
- if (ret < 0)
- return ret;
+ ret = 0;
- mutex_lock(&ftrace_lock);
- if (val < 0) {
- /* disable pid tracing */
- if (!ftrace_pid_trace)
- goto out;
+ list_for_each_entry(fpid, &ftrace_pids, list)
+ if (fpid->pid == pid)
+ goto out_put;
- clear_ftrace_pid_task(&ftrace_pid_trace);
+ ret = -ENOMEM;
- } else {
- /* swapper task is special */
- if (!val) {
- pid = ftrace_swapper_pid;
- if (pid == ftrace_pid_trace)
- goto out;
- } else {
- pid = find_get_pid(val);
+ fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
+ if (!fpid)
+ goto out_put;
- if (pid == ftrace_pid_trace) {
- put_pid(pid);
- goto out;
- }
- }
+ list_add(&fpid->list, &ftrace_pids);
+ fpid->pid = pid;
- if (ftrace_pid_trace)
- clear_ftrace_pid_task(&ftrace_pid_trace);
+ set_ftrace_pid_task(pid);
- if (!pid)
- goto out;
+ ftrace_update_pid_func();
+ ftrace_startup_enable(0);
+
+ mutex_unlock(&ftrace_lock);
+ return 0;
+
+out_put:
+ if (pid != ftrace_swapper_pid)
+ put_pid(pid);
+
+out:
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+static void ftrace_pid_reset(void)
+{
+ struct ftrace_pid *fpid, *safe;
+
+ mutex_lock(&ftrace_lock);
+ list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
+ struct pid *pid = fpid->pid;
- ftrace_pid_trace = pid;
+ clear_ftrace_pid_task(pid);
- set_ftrace_pid_task(ftrace_pid_trace);
+ list_del(&fpid->list);
+ kfree(fpid);
}
- /* update the function call */
ftrace_update_pid_func();
ftrace_startup_enable(0);
- out:
mutex_unlock(&ftrace_lock);
+}
- return cnt;
+static void *fpid_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&ftrace_lock);
+
+ if (list_empty(&ftrace_pids) && (!*pos))
+ return (void *) 1;
+
+ return seq_list_start(&ftrace_pids, *pos);
+}
+
+static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ if (v == (void *)1)
+ return NULL;
+
+ return seq_list_next(v, &ftrace_pids, pos);
+}
+
+static void fpid_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&ftrace_lock);
+}
+
+static int fpid_show(struct seq_file *m, void *v)
+{
+ const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
+
+ if (v == (void *)1) {
+ seq_printf(m, "no pid\n");
+ return 0;
+ }
+
+ if (fpid->pid == ftrace_swapper_pid)
+ seq_printf(m, "swapper tasks\n");
+ else
+ seq_printf(m, "%u\n", pid_vnr(fpid->pid));
+
+ return 0;
+}
+
+static const struct seq_operations ftrace_pid_sops = {
+ .start = fpid_start,
+ .next = fpid_next,
+ .stop = fpid_stop,
+ .show = fpid_show,
+};
+
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_pid_reset();
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_open(file, &ftrace_pid_sops);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64], *tmp;
+ long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ /*
+ * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
+ * to clean the filter quietly.
+ */
+ tmp = strstrip(buf);
+ if (strlen(tmp) == 0)
+ return 1;
+
+ ret = strict_strtol(tmp, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = ftrace_pid_add(val);
+
+ return ret ? ret : cnt;
+}
+
+static int
+ftrace_pid_release(struct inode *inode, struct file *file)
+{
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ return 0;
}
static const struct file_operations ftrace_pid_fops = {
- .read = ftrace_pid_read,
- .write = ftrace_pid_write,
+ .open = ftrace_pid_open,
+ .write = ftrace_pid_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = ftrace_pid_release,
};
static __init int ftrace_init_debugfs(void)
@@ -3015,7 +3111,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
int
ftrace_enable_sysctl(struct ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
@@ -3025,7 +3121,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
mutex_lock(&ftrace_lock);
- ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
goto out;
@@ -3295,4 +3391,3 @@ void ftrace_graph_stop(void)
ftrace_stop();
}
#endif
-
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 81b1645c854..a91da69f153 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -501,7 +501,7 @@ static int __init init_kmem_tracer(void)
return 1;
}
- if (!register_tracer(&kmem_tracer)) {
+ if (register_tracer(&kmem_tracer) != 0) {
pr_warning("Warning: could not register the kmem tracer\n");
return 1;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d4ff0197054..f58c9ad1583 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -397,18 +397,21 @@ int ring_buffer_print_page_header(struct trace_seq *s)
int ret;
ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
- "offset:0;\tsize:%u;\n",
- (unsigned int)sizeof(field.time_stamp));
+ "offset:0;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)sizeof(field.time_stamp),
+ (unsigned int)is_signed_type(u64));
ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
- "offset:%u;\tsize:%u;\n",
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
(unsigned int)offsetof(typeof(field), commit),
- (unsigned int)sizeof(field.commit));
+ (unsigned int)sizeof(field.commit),
+ (unsigned int)is_signed_type(long));
ret = trace_seq_printf(s, "\tfield: char data;\t"
- "offset:%u;\tsize:%u;\n",
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
(unsigned int)offsetof(typeof(field), data),
- (unsigned int)BUF_PAGE_SIZE);
+ (unsigned int)BUF_PAGE_SIZE,
+ (unsigned int)is_signed_type(char));
return ret;
}
@@ -420,7 +423,7 @@ struct ring_buffer_per_cpu {
int cpu;
struct ring_buffer *buffer;
spinlock_t reader_lock; /* serialize readers */
- raw_spinlock_t lock;
+ arch_spinlock_t lock;
struct lock_class_key lock_key;
struct list_head *pages;
struct buffer_page *head_page; /* read from head */
@@ -483,7 +486,7 @@ struct ring_buffer_iter {
/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0
-static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+static inline u64 rb_time_stamp(struct ring_buffer *buffer)
{
/* shift to debug/test normalization and TIME_EXTENTS */
return buffer->clock() << DEBUG_SHIFT;
@@ -494,7 +497,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
u64 time;
preempt_disable_notrace();
- time = rb_time_stamp(buffer, cpu);
+ time = rb_time_stamp(buffer);
preempt_enable_no_resched_notrace();
return time;
@@ -599,7 +602,7 @@ static struct list_head *rb_list_head(struct list_head *list)
}
/*
- * rb_is_head_page - test if the give page is the head page
+ * rb_is_head_page - test if the given page is the head page
*
* Because the reader may move the head_page pointer, we can
* not trust what the head page is (it may be pointing to
@@ -995,7 +998,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
cpu_buffer->buffer = buffer;
spin_lock_init(&cpu_buffer->reader_lock);
lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
- cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+ cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
@@ -1193,6 +1196,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
atomic_inc(&cpu_buffer->record_disabled);
synchronize_sched();
+ spin_lock_irq(&cpu_buffer->reader_lock);
rb_head_page_deactivate(cpu_buffer);
for (i = 0; i < nr_pages; i++) {
@@ -1207,6 +1211,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
return;
rb_reset_cpu(cpu_buffer);
+ spin_unlock_irq(&cpu_buffer->reader_lock);
rb_check_pages(cpu_buffer);
@@ -1785,9 +1790,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
static struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long length, unsigned long tail,
- struct buffer_page *commit_page,
struct buffer_page *tail_page, u64 *ts)
{
+ struct buffer_page *commit_page = cpu_buffer->commit_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct buffer_page *next_page;
int ret;
@@ -1868,7 +1873,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
* Nested commits always have zero deltas, so
* just reread the time stamp
*/
- *ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+ *ts = rb_time_stamp(buffer);
next_page->page->time_stamp = *ts;
}
@@ -1890,13 +1895,10 @@ static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
unsigned type, unsigned long length, u64 *ts)
{
- struct buffer_page *tail_page, *commit_page;
+ struct buffer_page *tail_page;
struct ring_buffer_event *event;
unsigned long tail, write;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
tail_page = cpu_buffer->tail_page;
write = local_add_return(length, &tail_page->write);
@@ -1907,7 +1909,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* See if we shot pass the end of this buffer page */
if (write > BUF_PAGE_SIZE)
return rb_move_tail(cpu_buffer, length, tail,
- commit_page, tail_page, ts);
+ tail_page, ts);
/* We reserved something on the buffer */
@@ -2111,7 +2113,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
goto out_fail;
- ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+ ts = rb_time_stamp(cpu_buffer->buffer);
/*
* Only the first commit can update the timestamp.
@@ -2681,7 +2683,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
EXPORT_SYMBOL_GPL(ring_buffer_entries);
/**
- * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * ring_buffer_overruns - get the number of overruns in buffer
* @buffer: The ring buffer
*
* Returns the total number of overruns in the ring buffer
@@ -2832,7 +2834,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
int ret;
local_irq_save(flags);
- __raw_spin_lock(&cpu_buffer->lock);
+ arch_spin_lock(&cpu_buffer->lock);
again:
/*
@@ -2921,7 +2923,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
goto again;
out:
- __raw_spin_unlock(&cpu_buffer->lock);
+ arch_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);
return reader;
@@ -3284,9 +3286,9 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
synchronize_sched();
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
- __raw_spin_lock(&cpu_buffer->lock);
+ arch_spin_lock(&cpu_buffer->lock);
rb_iter_reset(iter);
- __raw_spin_unlock(&cpu_buffer->lock);
+ arch_spin_unlock(&cpu_buffer->lock);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return iter;
@@ -3406,11 +3408,11 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
goto out;
- __raw_spin_lock(&cpu_buffer->lock);
+ arch_spin_lock(&cpu_buffer->lock);
rb_reset_cpu(cpu_buffer);
- __raw_spin_unlock(&cpu_buffer->lock);
+ arch_spin_unlock(&cpu_buffer->lock);
out:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 573d3cc762c..b2477caf09c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -35,6 +35,28 @@ static int disable_reader;
module_param(disable_reader, uint, 0644);
MODULE_PARM_DESC(disable_reader, "only run producer");
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
static int read_events;
static int kill_test;
@@ -208,15 +230,18 @@ static void ring_buffer_producer(void)
do {
struct ring_buffer_event *event;
int *entry;
-
- event = ring_buffer_lock_reserve(buffer, 10);
- if (!event) {
- missed++;
- } else {
- hit++;
- entry = ring_buffer_event_data(event);
- *entry = smp_processor_id();
- ring_buffer_unlock_commit(buffer, event);
+ int i;
+
+ for (i = 0; i < write_iteration; i++) {
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
}
do_gettimeofday(&end_tv);
@@ -263,6 +288,27 @@ static void ring_buffer_producer(void)
if (kill_test)
trace_printk("ERROR!\n");
+
+ if (!disable_reader) {
+ if (consumer_fifo < 0)
+ trace_printk("Running Consumer at nice: %d\n",
+ consumer_nice);
+ else
+ trace_printk("Running Consumer at SCHED_FIFO %d\n",
+ consumer_fifo);
+ }
+ if (producer_fifo < 0)
+ trace_printk("Running Producer at nice: %d\n",
+ producer_nice);
+ else
+ trace_printk("Running Producer at SCHED_FIFO %d\n",
+ producer_fifo);
+
+ /* Let the user know that the test is running at low priority */
+ if (producer_fifo < 0 && consumer_fifo < 0 &&
+ producer_nice == 19 && consumer_nice == 19)
+ trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
trace_printk("Time: %lld (usecs)\n", time);
trace_printk("Overruns: %lld\n", overruns);
if (disable_reader)
@@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void)
if (IS_ERR(producer))
goto out_kill;
+ /*
+ * Run them as low-prio background tasks by default:
+ */
+ if (!disable_reader) {
+ if (consumer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(consumer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(consumer, consumer_nice);
+ }
+
+ if (producer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(producer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(producer, producer_nice);
+
return 0;
out_kill:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6c0f6a8a22e..31118ae16f0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -86,17 +86,17 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
*/
static int tracing_disabled = 1;
-DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
{
preempt_disable();
- local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
}
static inline void ftrace_enable_cpu(void)
{
- local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
preempt_enable();
}
@@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf);
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
{
strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
@@ -137,7 +137,7 @@ static int __init set_ftrace(char *str)
ring_buffer_expanded = 1;
return 1;
}
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
static int __init set_ftrace_dump_on_oops(char *str)
{
@@ -203,7 +203,7 @@ cycle_t ftrace_now(int cpu)
*/
static struct trace_array max_tr;
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
/* tracer_enabled is used to toggle activation of a tracer */
static int tracer_enabled = 1;
@@ -415,7 +415,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
/* read the non-space input */
while (cnt && !isspace(ch)) {
- if (parser->idx < parser->size)
+ if (parser->idx < parser->size - 1)
parser->buffer[parser->idx++] = ch;
else {
ret = -EINVAL;
@@ -493,15 +493,15 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
* protected by per_cpu spinlocks. But the action of the swap
* needs its own lock.
*
- * This is defined as a raw_spinlock_t in order to help
+ * This is defined as a arch_spinlock_t in order to help
* with performance when lockdep debugging is enabled.
*
* It is also used in other places outside the update_max_tr
* so it needs to be defined outside of the
* CONFIG_TRACER_MAX_TRACE.
*/
-static raw_spinlock_t ftrace_max_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t ftrace_max_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
#ifdef CONFIG_TRACER_MAX_TRACE
unsigned long __read_mostly tracing_max_latency;
@@ -555,13 +555,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
return;
WARN_ON_ONCE(!irqs_disabled());
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
tr->buffer = max_tr.buffer;
max_tr.buffer = buf;
__update_max_tr(tr, tsk, cpu);
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
}
/**
@@ -581,7 +581,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
return;
WARN_ON_ONCE(!irqs_disabled());
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
ftrace_disable_cpu();
@@ -603,7 +603,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
__update_max_tr(tr, tsk, cpu);
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
}
#endif /* CONFIG_TRACER_MAX_TRACE */
@@ -802,7 +802,7 @@ static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
static int cmdline_idx;
-static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
/* temporary disable recording */
static atomic_t trace_record_cmdline_disabled __read_mostly;
@@ -915,7 +915,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
* nor do we want to disable interrupts,
* so if we miss here, then better luck next time.
*/
- if (!__raw_spin_trylock(&trace_cmdline_lock))
+ if (!arch_spin_trylock(&trace_cmdline_lock))
return;
idx = map_pid_to_cmdline[tsk->pid];
@@ -940,7 +940,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
- __raw_spin_unlock(&trace_cmdline_lock);
+ arch_spin_unlock(&trace_cmdline_lock);
}
void trace_find_cmdline(int pid, char comm[])
@@ -958,14 +958,14 @@ void trace_find_cmdline(int pid, char comm[])
}
preempt_disable();
- __raw_spin_lock(&trace_cmdline_lock);
+ arch_spin_lock(&trace_cmdline_lock);
map = map_pid_to_cmdline[pid];
if (map != NO_CMDLINE_MAP)
strcpy(comm, saved_cmdlines[map]);
else
strcpy(comm, "<...>");
- __raw_spin_unlock(&trace_cmdline_lock);
+ arch_spin_unlock(&trace_cmdline_lock);
preempt_enable();
}
@@ -1085,7 +1085,7 @@ trace_function(struct trace_array *tr,
struct ftrace_entry *entry;
/* If we are reading the ring buffer, don't trace */
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -1251,8 +1251,8 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
*/
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
- static raw_spinlock_t trace_buf_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t trace_buf_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static u32 trace_buf[TRACE_BUF_SIZE];
struct ftrace_event_call *call = &event_bprint;
@@ -1283,7 +1283,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
/* Lockdep uses trace_printk for lock tracing */
local_irq_save(flags);
- __raw_spin_lock(&trace_buf_lock);
+ arch_spin_lock(&trace_buf_lock);
len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
if (len > TRACE_BUF_SIZE || len < 0)
@@ -1304,7 +1304,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
ring_buffer_unlock_commit(buffer, event);
out_unlock:
- __raw_spin_unlock(&trace_buf_lock);
+ arch_spin_unlock(&trace_buf_lock);
local_irq_restore(flags);
out:
@@ -1334,7 +1334,7 @@ int trace_array_printk(struct trace_array *tr,
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
- static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
static char trace_buf[TRACE_BUF_SIZE];
struct ftrace_event_call *call = &event_print;
@@ -1360,12 +1360,9 @@ int trace_array_vprintk(struct trace_array *tr,
pause_graph_tracing();
raw_local_irq_save(irq_flags);
- __raw_spin_lock(&trace_buf_lock);
+ arch_spin_lock(&trace_buf_lock);
len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
- len = min(len, TRACE_BUF_SIZE-1);
- trace_buf[len] = 0;
-
size = sizeof(*entry) + len + 1;
buffer = tr->buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
@@ -1373,15 +1370,15 @@ int trace_array_vprintk(struct trace_array *tr,
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- entry->ip = ip;
+ entry->ip = ip;
memcpy(&entry->buf, trace_buf, len);
- entry->buf[len] = 0;
+ entry->buf[len] = '\0';
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
out_unlock:
- __raw_spin_unlock(&trace_buf_lock);
+ arch_spin_unlock(&trace_buf_lock);
raw_local_irq_restore(irq_flags);
unpause_graph_tracing();
out:
@@ -1393,7 +1390,7 @@ int trace_array_vprintk(struct trace_array *tr,
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
- return trace_array_printk(&global_trace, ip, fmt, args);
+ return trace_array_vprintk(&global_trace, ip, fmt, args);
}
EXPORT_SYMBOL_GPL(trace_vprintk);
@@ -1515,6 +1512,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
int i = (int)*pos;
void *ent;
+ WARN_ON_ONCE(iter->leftover);
+
(*pos)++;
/* can't go backwards */
@@ -1613,8 +1612,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
;
} else {
- l = *pos - 1;
- p = s_next(m, p, &l);
+ /*
+ * If we overflowed the seq_file before, then we want
+ * to just reuse the trace_seq buffer again.
+ */
+ if (iter->leftover)
+ p = iter;
+ else {
+ l = *pos - 1;
+ p = s_next(m, p, &l);
+ }
}
trace_event_read_lock();
@@ -1922,6 +1929,7 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
static int s_show(struct seq_file *m, void *v)
{
struct trace_iterator *iter = v;
+ int ret;
if (iter->ent == NULL) {
if (iter->tr) {
@@ -1941,9 +1949,27 @@ static int s_show(struct seq_file *m, void *v)
if (!(trace_flags & TRACE_ITER_VERBOSE))
print_func_help_header(m);
}
+ } else if (iter->leftover) {
+ /*
+ * If we filled the seq_file buffer earlier, we
+ * want to just show it now.
+ */
+ ret = trace_print_seq(m, &iter->seq);
+
+ /* ret should this time be zero, but you never know */
+ iter->leftover = ret;
+
} else {
print_trace_line(iter);
- trace_print_seq(m, &iter->seq);
+ ret = trace_print_seq(m, &iter->seq);
+ /*
+ * If we overflow the seq_file buffer, then it will
+ * ask us for this data again at start up.
+ * Use that instead.
+ * ret is 0 if seq_file write succeeded.
+ * -1 otherwise.
+ */
+ iter->leftover = ret;
}
return 0;
@@ -1984,11 +2010,9 @@ __tracing_open(struct inode *inode, struct file *file)
if (current_trace)
*iter->trace = *current_trace;
- if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
goto fail;
- cpumask_clear(iter->started);
-
if (current_trace && current_trace->print_max)
iter->tr = &max_tr;
else
@@ -2255,7 +2279,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
mutex_lock(&tracing_cpumask_update_lock);
local_irq_disable();
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
for_each_tracing_cpu(cpu) {
/*
* Increase/decrease the disabled counter if we are
@@ -2270,7 +2294,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
atomic_dec(&global_trace.data[cpu]->disabled);
}
}
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
local_irq_enable();
cpumask_copy(tracing_cpumask, tracing_cpumask_new);
@@ -2442,7 +2466,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
return ret;
}
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -2584,7 +2608,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
}
mutex_unlock(&trace_types_lock);
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
@@ -2766,7 +2790,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
if (err)
return err;
- filp->f_pos += ret;
+ *ppos += ret;
return ret;
}
@@ -2899,6 +2923,10 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
else
cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
+
+ if (iter->trace->pipe_close)
+ iter->trace->pipe_close(iter);
+
mutex_unlock(&trace_types_lock);
free_cpumask_var(iter->started);
@@ -3105,7 +3133,7 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
__free_page(spd->pages[idx]);
}
-static struct pipe_buf_operations tracing_pipe_buf_ops = {
+static const struct pipe_buf_operations tracing_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
@@ -3301,7 +3329,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
}
}
- filp->f_pos += cnt;
+ *ppos += cnt;
/* If check pages failed, return ENOMEM */
if (tracing_disabled)
@@ -3336,7 +3364,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
{
char *buf;
- char *end;
if (tracing_disabled)
return -EINVAL;
@@ -3344,7 +3371,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
if (cnt > TRACE_BUF_SIZE)
cnt = TRACE_BUF_SIZE;
- buf = kmalloc(cnt + 1, GFP_KERNEL);
+ buf = kmalloc(cnt + 2, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
@@ -3352,14 +3379,13 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
kfree(buf);
return -EFAULT;
}
+ if (buf[cnt-1] != '\n') {
+ buf[cnt] = '\n';
+ buf[cnt+1] = '\0';
+ } else
+ buf[cnt] = '\0';
- /* Cut from the first nil or newline. */
- buf[cnt] = '\0';
- end = strchr(buf, '\n');
- if (end)
- *end = '\0';
-
- cnt = mark_printk("%s\n", buf);
+ cnt = mark_printk("%s", buf);
kfree(buf);
*fpos += cnt;
@@ -3591,7 +3617,7 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
}
/* Pipe buffer operations for a buffer. */
-static struct pipe_buf_operations buffer_pipe_buf_ops = {
+static const struct pipe_buf_operations buffer_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
@@ -3732,7 +3758,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
- return ENOMEM;
+ return -ENOMEM;
trace_seq_init(s);
@@ -4281,8 +4307,8 @@ trace_printk_seq(struct trace_seq *s)
static void __ftrace_dump(bool disable_tracing)
{
- static raw_spinlock_t ftrace_dump_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+ static arch_spinlock_t ftrace_dump_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
/* use static because iter can be a bit big for the stack */
static struct trace_iterator iter;
unsigned int old_userobj;
@@ -4292,7 +4318,7 @@ static void __ftrace_dump(bool disable_tracing)
/* only one dump */
local_irq_save(flags);
- __raw_spin_lock(&ftrace_dump_lock);
+ arch_spin_lock(&ftrace_dump_lock);
if (dump_ran)
goto out;
@@ -4367,7 +4393,7 @@ static void __ftrace_dump(bool disable_tracing)
}
out:
- __raw_spin_unlock(&ftrace_dump_lock);
+ arch_spin_unlock(&ftrace_dump_lock);
local_irq_restore(flags);
}
@@ -4389,7 +4415,7 @@ __init static int tracer_alloc_buffers(void)
if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
goto out_free_buffer_mask;
- if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
goto out_free_tracing_cpumask;
/* To save memory, keep the ring buffer size to its minimum */
@@ -4400,7 +4426,6 @@ __init static int tracer_alloc_buffers(void)
cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
cpumask_copy(tracing_cpumask, cpu_all_mask);
- cpumask_clear(tracing_reader_cpumask);
/* TODO: make the number of buffers hot pluggable with CPUS */
global_trace.buffer = ring_buffer_alloc(ring_buf_size,
@@ -4429,7 +4454,7 @@ __init static int tracer_alloc_buffers(void)
/* Allocate the first page for all buffers */
for_each_tracing_cpu(i) {
global_trace.data[i] = &per_cpu(global_trace_cpu, i);
- max_tr.data[i] = &per_cpu(max_data, i);
+ max_tr.data[i] = &per_cpu(max_tr_data, i);
}
trace_init_cmdlines();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 405cb850b75..a52bed2eedd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -11,6 +11,7 @@
#include <linux/ftrace.h>
#include <trace/boot.h>
#include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
#include <linux/trace_seq.h>
#include <linux/ftrace_event.h>
@@ -37,6 +38,7 @@ enum trace_type {
TRACE_KMEM_ALLOC,
TRACE_KMEM_FREE,
TRACE_BLK,
+ TRACE_KSYM,
__TRACE_LAST_TYPE,
};
@@ -98,9 +100,32 @@ struct syscall_trace_enter {
struct syscall_trace_exit {
struct trace_entry ent;
int nr;
- unsigned long ret;
+ long ret;
};
+struct kprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long func;
+ unsigned long ret_ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kretprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
@@ -209,6 +234,7 @@ extern void __ftrace_bad_type(void);
TRACE_KMEM_ALLOC); \
IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
TRACE_KMEM_FREE); \
+ IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
__ftrace_bad_type(); \
} while (0)
@@ -246,6 +272,7 @@ struct tracer_flags {
* @pipe_open: called when the trace_pipe file is opened
* @wait_pipe: override how the user waits for traces on trace_pipe
* @close: called when the trace file is released
+ * @pipe_close: called when the trace_pipe file is released
* @read: override the default read callback on trace_pipe
* @splice_read: override the default splice_read callback on trace_pipe
* @selftest: selftest to run on boot (see trace_selftest.c)
@@ -264,6 +291,7 @@ struct tracer {
void (*pipe_open)(struct trace_iterator *iter);
void (*wait_pipe)(struct trace_iterator *iter);
void (*close)(struct trace_iterator *iter);
+ void (*pipe_close)(struct trace_iterator *iter);
ssize_t (*read)(struct trace_iterator *iter,
struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos);
@@ -364,6 +392,8 @@ int register_tracer(struct tracer *type);
void unregister_tracer(struct tracer *type);
int is_tracing_stopped(void);
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -413,7 +443,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
extern int ring_buffer_expanded;
extern bool tracing_selftest_disabled;
-DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
#ifdef CONFIG_FTRACE_STARTUP_TEST
extern int trace_selftest_startup_function(struct tracer *trace,
@@ -438,6 +468,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
struct trace_array *tr);
extern int trace_selftest_startup_hw_branches(struct tracer *trace,
struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+ struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
@@ -483,10 +515,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 0;
}
#else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
- return 1;
-}
static inline int ftrace_graph_addr(unsigned long addr)
{
return 1;
@@ -500,12 +528,12 @@ print_graph_function(struct trace_iterator *iter)
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
#ifdef CONFIG_FUNCTION_TRACER
static inline int ftrace_trace_task(struct task_struct *task)
{
- if (!ftrace_pid_trace)
+ if (list_empty(&ftrace_pids))
return 1;
return test_tsk_trace_trace(task);
@@ -687,7 +715,6 @@ struct event_filter {
int n_preds;
struct filter_pred **preds;
char *filter_string;
- bool no_reset;
};
struct event_subsystem {
@@ -699,22 +726,40 @@ struct event_subsystem {
};
struct filter_pred;
+struct regex;
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
int val1, int val2);
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+ MATCH_FULL = 0,
+ MATCH_FRONT_ONLY,
+ MATCH_MIDDLE_ONLY,
+ MATCH_END_ONLY,
+};
+
+struct regex {
+ char pattern[MAX_FILTER_STR_VAL];
+ int len;
+ int field_len;
+ regex_match_func match;
+};
+
struct filter_pred {
- filter_pred_fn_t fn;
- u64 val;
- char str_val[MAX_FILTER_STR_VAL];
- int str_len;
- char *field_name;
- int offset;
- int not;
- int op;
- int pop_n;
+ filter_pred_fn_t fn;
+ u64 val;
+ struct regex regex;
+ char *field_name;
+ int offset;
+ int not;
+ int op;
+ int pop_n;
};
+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,
struct trace_seq *s);
extern int apply_event_filter(struct ftrace_event_call *call,
@@ -730,7 +775,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
{
- if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+ if (unlikely(call->filter_active) &&
+ !filter_match_preds(call->filter, rec)) {
ring_buffer_discard_commit(buffer, event);
return 1;
}
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 7a7a9fd249a..4a194f08f88 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -34,6 +34,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
struct trace_array *tr = branch_tracer;
struct ring_buffer_event *event;
struct trace_branch *entry;
+ struct ring_buffer *buffer;
unsigned long flags;
int cpu, pc;
const char *p;
@@ -54,7 +55,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
goto out;
pc = preempt_count();
- event = trace_buffer_lock_reserve(tr, TRACE_BRANCH,
+ buffer = tr->buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
sizeof(*entry), flags, pc);
if (!event)
goto out;
@@ -74,8 +76,8 @@ 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, tr->buffer, event))
- ring_buffer_unlock_commit(tr->buffer, event);
+ if (!filter_check_discard(call, entry, buffer, event))
+ ring_buffer_unlock_commit(buffer, event);
out:
atomic_dec(&tr->data[cpu]->disabled);
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 20c5f92e28a..84a3a7ba072 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -20,6 +20,8 @@
#include <linux/ktime.h>
#include <linux/trace_clock.h>
+#include "trace.h"
+
/*
* trace_clock_local(): the simplest and least coherent tracing clock.
*
@@ -28,17 +30,17 @@
*/
u64 notrace trace_clock_local(void)
{
- unsigned long flags;
u64 clock;
+ int resched;
/*
* sched_clock() is an architecture implemented, fast, scalable,
* lockless clock. It is not guaranteed to be coherent across
* CPUs, nor across CPU idle events.
*/
- raw_local_irq_save(flags);
+ resched = ftrace_preempt_disable();
clock = sched_clock();
- raw_local_irq_restore(flags);
+ ftrace_preempt_enable(resched);
return clock;
}
@@ -69,10 +71,10 @@ u64 notrace trace_clock(void)
/* keep prev_time and lock in the same cacheline. */
static struct {
u64 prev_time;
- raw_spinlock_t lock;
+ arch_spinlock_t lock;
} trace_clock_struct ____cacheline_aligned_in_smp =
{
- .lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED,
+ .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
};
u64 notrace trace_clock_global(void)
@@ -92,7 +94,7 @@ u64 notrace trace_clock_global(void)
if (unlikely(in_nmi()))
goto out;
- __raw_spin_lock(&trace_clock_struct.lock);
+ arch_spin_lock(&trace_clock_struct.lock);
/*
* TODO: if this happens often then maybe we should reset
@@ -104,7 +106,7 @@ u64 notrace trace_clock_global(void)
trace_clock_struct.prev_time = now;
- __raw_spin_unlock(&trace_clock_struct.lock);
+ arch_spin_unlock(&trace_clock_struct.lock);
out:
raw_local_irq_restore(flags);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ead3d724599..c16a08f399d 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
F_printk("type:%u call_site:%lx ptr:%p",
__entry->type_id, __entry->call_site, __entry->ptr)
);
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+ TRACE_KSYM,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( unsigned char, type )
+ __array( char , cmd, TASK_COMM_LEN )
+ __field( unsigned long, addr )
+ ),
+
+ F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s",
+ (void *)__entry->ip, (unsigned int)__entry->type,
+ (void *)__entry->addr, __entry->cmd)
+);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index dd44b876886..d9c60f80aa0 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -8,17 +8,14 @@
#include <linux/module.h>
#include "trace.h"
-/*
- * We can't use a size but a type in alloc_percpu()
- * So let's create a dummy type that matches the desired size
- */
-typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t;
-char *trace_profile_buf;
-EXPORT_SYMBOL_GPL(trace_profile_buf);
+char *perf_trace_buf;
+EXPORT_SYMBOL_GPL(perf_trace_buf);
+
+char *perf_trace_buf_nmi;
+EXPORT_SYMBOL_GPL(perf_trace_buf_nmi);
-char *trace_profile_buf_nmi;
-EXPORT_SYMBOL_GPL(trace_profile_buf_nmi);
+typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
/* Count the events in use (per event id, not per instance) */
static int total_profile_count;
@@ -31,29 +28,34 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
if (atomic_inc_return(&event->profile_count))
return 0;
- if (!total_profile_count++) {
- buf = (char *)alloc_percpu(profile_buf_t);
+ if (!total_profile_count) {
+ buf = (char *)alloc_percpu(perf_trace_t);
if (!buf)
goto fail_buf;
- rcu_assign_pointer(trace_profile_buf, buf);
+ rcu_assign_pointer(perf_trace_buf, buf);
- buf = (char *)alloc_percpu(profile_buf_t);
+ buf = (char *)alloc_percpu(perf_trace_t);
if (!buf)
goto fail_buf_nmi;
- rcu_assign_pointer(trace_profile_buf_nmi, buf);
+ rcu_assign_pointer(perf_trace_buf_nmi, buf);
}
- ret = event->profile_enable();
- if (!ret)
+ ret = event->profile_enable(event);
+ if (!ret) {
+ total_profile_count++;
return 0;
+ }
- kfree(trace_profile_buf_nmi);
fail_buf_nmi:
- kfree(trace_profile_buf);
+ if (!total_profile_count) {
+ free_percpu(perf_trace_buf_nmi);
+ free_percpu(perf_trace_buf);
+ perf_trace_buf_nmi = NULL;
+ perf_trace_buf = NULL;
+ }
fail_buf:
- total_profile_count--;
atomic_dec(&event->profile_count);
return ret;
@@ -84,14 +86,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
if (!atomic_add_negative(-1, &event->profile_count))
return;
- event->profile_disable();
+ event->profile_disable(event);
if (!--total_profile_count) {
- buf = trace_profile_buf;
- rcu_assign_pointer(trace_profile_buf, NULL);
+ buf = perf_trace_buf;
+ rcu_assign_pointer(perf_trace_buf, NULL);
- nmi_buf = trace_profile_buf_nmi;
- rcu_assign_pointer(trace_profile_buf_nmi, NULL);
+ nmi_buf = perf_trace_buf_nmi;
+ rcu_assign_pointer(perf_trace_buf_nmi, NULL);
/*
* Ensure every events in profiling have finished before
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6f03c8a1105..1d18315dc83 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -93,9 +93,7 @@ int trace_define_common_fields(struct ftrace_event_call *call)
}
EXPORT_SYMBOL_GPL(trace_define_common_fields);
-#ifdef CONFIG_MODULES
-
-static void trace_destroy_fields(struct ftrace_event_call *call)
+void trace_destroy_fields(struct ftrace_event_call *call)
{
struct ftrace_event_field *field, *next;
@@ -107,8 +105,6 @@ static void trace_destroy_fields(struct ftrace_event_call *call)
}
}
-#endif /* CONFIG_MODULES */
-
static void ftrace_event_enable_disable(struct ftrace_event_call *call,
int enable)
{
@@ -117,14 +113,14 @@ static void ftrace_event_enable_disable(struct ftrace_event_call *call,
if (call->enabled) {
call->enabled = 0;
tracing_stop_cmdline_record();
- call->unregfunc(call->data);
+ call->unregfunc(call);
}
break;
case 1:
if (!call->enabled) {
call->enabled = 1;
tracing_start_cmdline_record();
- call->regfunc(call->data);
+ call->regfunc(call);
}
break;
}
@@ -232,10 +228,9 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
- size_t read = 0;
- ssize_t ret;
+ ssize_t read, ret;
- if (!cnt || cnt < 0)
+ if (!cnt)
return 0;
ret = tracing_update_buffers();
@@ -247,7 +242,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
read = trace_get_user(&parser, ubuf, cnt, ppos);
- if (trace_parser_loaded((&parser))) {
+ if (read >= 0 && trace_parser_loaded((&parser))) {
int set = 1;
if (*parser.buffer == '!')
@@ -508,7 +503,7 @@ extern char *__bad_type_size(void);
#define FIELD(type, name) \
sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
#type, "common_" #name, offsetof(typeof(field), name), \
- sizeof(field.name)
+ sizeof(field.name), is_signed_type(type)
static int trace_write_header(struct trace_seq *s)
{
@@ -516,17 +511,17 @@ static int trace_write_header(struct trace_seq *s)
/* struct trace_entry */
return trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\n",
- FIELD(unsigned short, type),
- FIELD(unsigned char, flags),
- FIELD(unsigned char, preempt_count),
- FIELD(int, pid),
- FIELD(int, lock_depth));
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
+ "\n",
+ FIELD(unsigned short, type),
+ FIELD(unsigned char, flags),
+ FIELD(unsigned char, preempt_count),
+ FIELD(int, pid),
+ FIELD(int, lock_depth));
}
static ssize_t
@@ -879,9 +874,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
"'%s/filter' entry\n", name);
}
- entry = trace_create_file("enable", 0644, system->entry,
- (void *)system->name,
- &ftrace_system_enable_fops);
+ trace_create_file("enable", 0644, system->entry,
+ (void *)system->name,
+ &ftrace_system_enable_fops);
return system->entry;
}
@@ -893,7 +888,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
const struct file_operations *filter,
const struct file_operations *format)
{
- struct dentry *entry;
int ret;
/*
@@ -911,12 +905,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
}
if (call->regfunc)
- entry = trace_create_file("enable", 0644, call->dir, call,
- enable);
+ trace_create_file("enable", 0644, call->dir, call,
+ enable);
if (call->id && call->profile_enable)
- entry = trace_create_file("id", 0444, call->dir, call,
- id);
+ trace_create_file("id", 0444, call->dir, call,
+ id);
if (call->define_fields) {
ret = call->define_fields(call);
@@ -925,41 +919,60 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
" events/%s\n", call->name);
return ret;
}
- entry = trace_create_file("filter", 0644, call->dir, call,
- filter);
+ trace_create_file("filter", 0644, call->dir, call,
+ filter);
}
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
- entry = trace_create_file("format", 0444, call->dir, call,
- format);
+ trace_create_file("format", 0444, call->dir, call,
+ format);
return 0;
}
-#define for_each_event(event, start, end) \
- for (event = start; \
- (unsigned long)event < (unsigned long)end; \
- event++)
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+ struct dentry *d_events;
+ int ret;
-#ifdef CONFIG_MODULES
+ if (!call->name)
+ return -EINVAL;
-static LIST_HEAD(ftrace_module_file_list);
+ if (call->raw_init) {
+ ret = call->raw_init(call);
+ if (ret < 0) {
+ if (ret != -ENOSYS)
+ pr_warning("Could not initialize trace "
+ "events/%s\n", call->name);
+ return ret;
+ }
+ }
-/*
- * Modules must own their file_operations to keep up with
- * reference counting.
- */
-struct ftrace_module_file_ops {
- struct list_head list;
- struct module *mod;
- struct file_operations id;
- struct file_operations enable;
- struct file_operations format;
- struct file_operations filter;
-};
+ d_events = event_trace_events_dir();
+ if (!d_events)
+ return -ENOENT;
+
+ ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops, &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
+
+ return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+ int ret;
+ mutex_lock(&event_mutex);
+ ret = __trace_add_event_call(call);
+ mutex_unlock(&event_mutex);
+ return ret;
+}
static void remove_subsystem_dir(const char *name)
{
@@ -987,6 +1000,53 @@ static void remove_subsystem_dir(const char *name)
}
}
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+ ftrace_event_enable_disable(call, 0);
+ if (call->event)
+ __unregister_ftrace_event(call->event);
+ debugfs_remove_recursive(call->dir);
+ list_del(&call->list);
+ trace_destroy_fields(call);
+ destroy_preds(call);
+ remove_subsystem_dir(call->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+ mutex_lock(&event_mutex);
+ down_write(&trace_event_mutex);
+ __trace_remove_event_call(call);
+ up_write(&trace_event_mutex);
+ mutex_unlock(&event_mutex);
+}
+
+#define for_each_event(event, start, end) \
+ for (event = start; \
+ (unsigned long)event < (unsigned long)end; \
+ event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+ struct list_head list;
+ struct module *mod;
+ struct file_operations id;
+ struct file_operations enable;
+ struct file_operations format;
+ struct file_operations filter;
+};
+
static struct ftrace_module_file_ops *
trace_create_file_ops(struct module *mod)
{
@@ -1044,7 +1104,7 @@ static void trace_module_add_events(struct module *mod)
if (!call->name)
continue;
if (call->raw_init) {
- ret = call->raw_init();
+ ret = call->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1062,10 +1122,11 @@ static void trace_module_add_events(struct module *mod)
return;
}
call->mod = mod;
- list_add(&call->list, &ftrace_events);
- event_create_dir(call, d_events,
- &file_ops->id, &file_ops->enable,
- &file_ops->filter, &file_ops->format);
+ ret = event_create_dir(call, d_events,
+ &file_ops->id, &file_ops->enable,
+ &file_ops->filter, &file_ops->format);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
}
}
@@ -1079,14 +1140,7 @@ static void trace_module_remove_events(struct module *mod)
list_for_each_entry_safe(call, p, &ftrace_events, list) {
if (call->mod == mod) {
found = true;
- ftrace_event_enable_disable(call, 0);
- if (call->event)
- __unregister_ftrace_event(call->event);
- debugfs_remove_recursive(call->dir);
- list_del(&call->list);
- trace_destroy_fields(call);
- destroy_preds(call);
- remove_subsystem_dir(call->system);
+ __trace_remove_event_call(call);
}
}
@@ -1204,7 +1258,7 @@ static __init int event_trace_init(void)
if (!call->name)
continue;
if (call->raw_init) {
- ret = call->raw_init();
+ ret = call->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1212,10 +1266,12 @@ static __init int event_trace_init(void)
continue;
}
}
- list_add(&call->list, &ftrace_events);
- event_create_dir(call, d_events, &ftrace_event_id_fops,
- &ftrace_enable_fops, &ftrace_event_filter_fops,
- &ftrace_event_format_fops);
+ ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+ &ftrace_enable_fops,
+ &ftrace_event_filter_fops,
+ &ftrace_event_format_fops);
+ if (!ret)
+ list_add(&call->list, &ftrace_events);
}
while (true) {
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 23245785927..50504cb228d 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -18,11 +18,10 @@
* Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
*/
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
+#include <linux/perf_event.h>
#include "trace.h"
#include "trace_output.h"
@@ -31,6 +30,7 @@ enum filter_op_ids
{
OP_OR,
OP_AND,
+ OP_GLOB,
OP_NE,
OP_EQ,
OP_LT,
@@ -48,16 +48,17 @@ struct filter_op {
};
static struct filter_op filter_ops[] = {
- { OP_OR, "||", 1 },
- { OP_AND, "&&", 2 },
- { OP_NE, "!=", 4 },
- { OP_EQ, "==", 4 },
- { OP_LT, "<", 5 },
- { OP_LE, "<=", 5 },
- { OP_GT, ">", 5 },
- { OP_GE, ">=", 5 },
- { OP_NONE, "OP_NONE", 0 },
- { OP_OPEN_PAREN, "(", 0 },
+ { OP_OR, "||", 1 },
+ { OP_AND, "&&", 2 },
+ { OP_GLOB, "~", 4 },
+ { OP_NE, "!=", 4 },
+ { OP_EQ, "==", 4 },
+ { OP_LT, "<", 5 },
+ { OP_LE, "<=", 5 },
+ { OP_GT, ">", 5 },
+ { OP_GE, ">=", 5 },
+ { OP_NONE, "OP_NONE", 0 },
+ { OP_OPEN_PAREN, "(", 0 },
};
enum {
@@ -197,9 +198,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
char *addr = (char *)(event + pred->offset);
int cmp, match;
- cmp = strncmp(addr, pred->str_val, pred->str_len);
+ cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -211,9 +212,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
char **addr = (char **)(event + pred->offset);
int cmp, match;
- cmp = strncmp(*addr, pred->str_val, pred->str_len);
+ cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -237,9 +238,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
char *addr = (char *)(event + str_loc);
int cmp, match;
- cmp = strncmp(addr, pred->str_val, str_len);
+ cmp = pred->regex.match(addr, &pred->regex, str_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -250,10 +251,121 @@ static int filter_pred_none(struct filter_pred *pred, void *event,
return 0;
}
+/* Basic regex callbacks */
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+ if (strstr(str, r->pattern))
+ return 1;
+ return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+ char *ptr = strstr(str, r->pattern);
+
+ if (ptr && (ptr[r->len] == 0))
+ return 1;
+ return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff: the raw regex
+ * @len: length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not: tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ * search returns the pointer to use for comparison.
+ * not returns 1 if buff started with a '!'
+ * 0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+ int type = MATCH_FULL;
+ int i;
+
+ if (buff[0] == '!') {
+ *not = 1;
+ buff++;
+ len--;
+ } else
+ *not = 0;
+
+ *search = buff;
+
+ for (i = 0; i < len; i++) {
+ if (buff[i] == '*') {
+ if (!i) {
+ *search = buff + 1;
+ type = MATCH_END_ONLY;
+ } else {
+ if (type == MATCH_END_ONLY)
+ type = MATCH_MIDDLE_ONLY;
+ else
+ type = MATCH_FRONT_ONLY;
+ buff[i] = 0;
+ break;
+ }
+ }
+ }
+
+ return type;
+}
+
+static void filter_build_regex(struct filter_pred *pred)
+{
+ struct regex *r = &pred->regex;
+ char *search;
+ enum regex_type type = MATCH_FULL;
+ int not = 0;
+
+ if (pred->op == OP_GLOB) {
+ type = filter_parse_regex(r->pattern, r->len, &search, &not);
+ r->len = strlen(search);
+ memmove(r->pattern, search, r->len+1);
+ }
+
+ switch (type) {
+ case MATCH_FULL:
+ r->match = regex_match_full;
+ break;
+ case MATCH_FRONT_ONLY:
+ r->match = regex_match_front;
+ break;
+ case MATCH_MIDDLE_ONLY:
+ r->match = regex_match_middle;
+ break;
+ case MATCH_END_ONLY:
+ r->match = regex_match_end;
+ break;
+ }
+
+ pred->not ^= not;
+}
+
/* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+int filter_match_preds(struct event_filter *filter, void *rec)
{
- struct event_filter *filter = call->filter;
int match, top = 0, val1 = 0, val2 = 0;
int stack[MAX_FILTER_PRED];
struct filter_pred *pred;
@@ -396,7 +508,7 @@ static void filter_clear_pred(struct filter_pred *pred)
{
kfree(pred->field_name);
pred->field_name = NULL;
- pred->str_len = 0;
+ pred->regex.len = 0;
}
static int filter_set_pred(struct filter_pred *dest,
@@ -426,9 +538,8 @@ static void filter_disable_preds(struct ftrace_event_call *call)
filter->preds[i]->fn = filter_pred_none;
}
-void destroy_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
{
- struct event_filter *filter = call->filter;
int i;
if (!filter)
@@ -441,21 +552,24 @@ void destroy_preds(struct ftrace_event_call *call)
kfree(filter->preds);
kfree(filter->filter_string);
kfree(filter);
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+ __free_preds(call->filter);
call->filter = NULL;
+ call->filter_active = 0;
}
-static int init_preds(struct ftrace_event_call *call)
+static struct event_filter *__alloc_preds(void)
{
struct event_filter *filter;
struct filter_pred *pred;
int i;
- if (call->filter)
- return 0;
-
- filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
- if (!call->filter)
- return -ENOMEM;
+ filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+ if (!filter)
+ return ERR_PTR(-ENOMEM);
filter->n_preds = 0;
@@ -471,12 +585,24 @@ static int init_preds(struct ftrace_event_call *call)
filter->preds[i] = pred;
}
- return 0;
+ return filter;
oom:
- destroy_preds(call);
+ __free_preds(filter);
+ return ERR_PTR(-ENOMEM);
+}
+
+static int init_preds(struct ftrace_event_call *call)
+{
+ if (call->filter)
+ return 0;
+
+ call->filter_active = 0;
+ call->filter = __alloc_preds();
+ if (IS_ERR(call->filter))
+ return PTR_ERR(call->filter);
- return -ENOMEM;
+ return 0;
}
static int init_subsystem_preds(struct event_subsystem *system)
@@ -499,14 +625,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
return 0;
}
-enum {
- FILTER_DISABLE_ALL,
- FILTER_INIT_NO_RESET,
- FILTER_SKIP_NO_RESET,
-};
-
-static void filter_free_subsystem_preds(struct event_subsystem *system,
- int flag)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
{
struct ftrace_event_call *call;
@@ -517,14 +636,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
if (strcmp(call->system, system->name) != 0)
continue;
- if (flag == FILTER_INIT_NO_RESET) {
- call->filter->no_reset = false;
- continue;
- }
-
- if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
- continue;
-
filter_disable_preds(call);
remove_filter_string(call->filter);
}
@@ -532,10 +643,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
static int filter_add_pred_fn(struct filter_parse_state *ps,
struct ftrace_event_call *call,
+ struct event_filter *filter,
struct filter_pred *pred,
filter_pred_fn_t fn)
{
- struct event_filter *filter = call->filter;
int idx, err;
if (filter->n_preds == MAX_FILTER_PRED) {
@@ -550,7 +661,6 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
return err;
filter->n_preds++;
- call->filter_active = 1;
return 0;
}
@@ -575,7 +685,10 @@ static bool is_string_field(struct ftrace_event_field *field)
static int is_legal_op(struct ftrace_event_field *field, int op)
{
- if (is_string_field(field) && (op != OP_EQ && op != OP_NE))
+ if (is_string_field(field) &&
+ (op != OP_EQ && op != OP_NE && op != OP_GLOB))
+ return 0;
+ if (!is_string_field(field) && op == OP_GLOB)
return 0;
return 1;
@@ -626,6 +739,7 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
static int filter_add_pred(struct filter_parse_state *ps,
struct ftrace_event_call *call,
+ struct event_filter *filter,
struct filter_pred *pred,
bool dry_run)
{
@@ -660,21 +774,22 @@ static int filter_add_pred(struct filter_parse_state *ps,
}
if (is_string_field(field)) {
- pred->str_len = field->size;
+ filter_build_regex(pred);
- if (field->filter_type == FILTER_STATIC_STRING)
+ if (field->filter_type == FILTER_STATIC_STRING) {
fn = filter_pred_string;
- else if (field->filter_type == FILTER_DYN_STRING)
+ pred->regex.field_len = field->size;
+ } else if (field->filter_type == FILTER_DYN_STRING)
fn = filter_pred_strloc;
else {
fn = filter_pred_pchar;
- pred->str_len = strlen(pred->str_val);
+ pred->regex.field_len = strlen(pred->regex.pattern);
}
} else {
if (field->is_signed)
- ret = strict_strtoll(pred->str_val, 0, &val);
+ ret = strict_strtoll(pred->regex.pattern, 0, &val);
else
- ret = strict_strtoull(pred->str_val, 0, &val);
+ ret = strict_strtoull(pred->regex.pattern, 0, &val);
if (ret) {
parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
return -EINVAL;
@@ -694,45 +809,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
add_pred_fn:
if (!dry_run)
- return filter_add_pred_fn(ps, call, pred, fn);
- return 0;
-}
-
-static int filter_add_subsystem_pred(struct filter_parse_state *ps,
- struct event_subsystem *system,
- struct filter_pred *pred,
- char *filter_string,
- bool dry_run)
-{
- struct ftrace_event_call *call;
- int err = 0;
- bool fail = true;
-
- list_for_each_entry(call, &ftrace_events, list) {
-
- if (!call->define_fields)
- continue;
-
- if (strcmp(call->system, system->name))
- continue;
-
- if (call->filter->no_reset)
- continue;
-
- err = filter_add_pred(ps, call, pred, dry_run);
- if (err)
- call->filter->no_reset = true;
- else
- fail = false;
-
- if (!dry_run)
- replace_filter_string(call->filter, filter_string);
- }
-
- if (fail) {
- parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
- return err;
- }
+ return filter_add_pred_fn(ps, call, filter, pred, fn);
return 0;
}
@@ -933,8 +1010,9 @@ static void postfix_clear(struct filter_parse_state *ps)
while (!list_empty(&ps->postfix)) {
elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
- kfree(elt->operand);
list_del(&elt->list);
+ kfree(elt->operand);
+ kfree(elt);
}
}
@@ -1044,8 +1122,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
return NULL;
}
- strcpy(pred->str_val, operand2);
- pred->str_len = strlen(operand2);
+ strcpy(pred->regex.pattern, operand2);
+ pred->regex.len = strlen(pred->regex.pattern);
pred->op = op;
@@ -1089,8 +1167,8 @@ static int check_preds(struct filter_parse_state *ps)
return 0;
}
-static int replace_preds(struct event_subsystem *system,
- struct ftrace_event_call *call,
+static int replace_preds(struct ftrace_event_call *call,
+ struct event_filter *filter,
struct filter_parse_state *ps,
char *filter_string,
bool dry_run)
@@ -1137,11 +1215,7 @@ static int replace_preds(struct event_subsystem *system,
add_pred:
if (!pred)
return -ENOMEM;
- if (call)
- err = filter_add_pred(ps, call, pred, false);
- else
- err = filter_add_subsystem_pred(ps, system, pred,
- filter_string, dry_run);
+ err = filter_add_pred(ps, call, filter, pred, dry_run);
filter_free_pred(pred);
if (err)
return err;
@@ -1152,10 +1226,50 @@ add_pred:
return 0;
}
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+static int replace_system_preds(struct event_subsystem *system,
+ struct filter_parse_state *ps,
+ char *filter_string)
{
+ struct ftrace_event_call *call;
+ bool fail = true;
int err;
+ list_for_each_entry(call, &ftrace_events, list) {
+ struct event_filter *filter = call->filter;
+
+ if (!call->define_fields)
+ continue;
+
+ if (strcmp(call->system, system->name) != 0)
+ continue;
+
+ /* try to see if the filter can be applied */
+ err = replace_preds(call, filter, ps, filter_string, true);
+ if (err)
+ continue;
+
+ /* really apply the filter */
+ filter_disable_preds(call);
+ err = replace_preds(call, filter, ps, filter_string, false);
+ if (err)
+ filter_disable_preds(call);
+ else {
+ call->filter_active = 1;
+ replace_filter_string(filter, filter_string);
+ }
+ fail = false;
+ }
+
+ if (fail) {
+ parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+ int err;
struct filter_parse_state *ps;
mutex_lock(&event_mutex);
@@ -1167,8 +1281,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
if (!strcmp(strstrip(filter_string), "0")) {
filter_disable_preds(call);
remove_filter_string(call->filter);
- mutex_unlock(&event_mutex);
- return 0;
+ goto out_unlock;
}
err = -ENOMEM;
@@ -1186,10 +1299,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
goto out;
}
- err = replace_preds(NULL, call, ps, filter_string, false);
+ err = replace_preds(call, call->filter, ps, filter_string, false);
if (err)
append_filter_err(ps, call->filter);
-
+ else
+ call->filter_active = 1;
out:
filter_opstack_clear(ps);
postfix_clear(ps);
@@ -1204,7 +1318,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
char *filter_string)
{
int err;
-
struct filter_parse_state *ps;
mutex_lock(&event_mutex);
@@ -1214,10 +1327,9 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
goto out_unlock;
if (!strcmp(strstrip(filter_string), "0")) {
- filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
+ filter_free_subsystem_preds(system);
remove_filter_string(system->filter);
- mutex_unlock(&event_mutex);
- return 0;
+ goto out_unlock;
}
err = -ENOMEM;
@@ -1234,31 +1346,87 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
goto out;
}
- filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
-
- /* try to see the filter can be applied to which events */
- err = replace_preds(system, NULL, ps, filter_string, true);
- if (err) {
+ err = replace_system_preds(system, ps, filter_string);
+ if (err)
append_filter_err(ps, system->filter);
- goto out;
+
+out:
+ filter_opstack_clear(ps);
+ postfix_clear(ps);
+ kfree(ps);
+out_unlock:
+ mutex_unlock(&event_mutex);
+
+ return err;
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+void ftrace_profile_free_filter(struct perf_event *event)
+{
+ struct event_filter *filter = event->filter;
+
+ event->filter = NULL;
+ __free_preds(filter);
+}
+
+int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+ char *filter_str)
+{
+ int err;
+ struct event_filter *filter;
+ struct filter_parse_state *ps;
+ struct ftrace_event_call *call = NULL;
+
+ mutex_lock(&event_mutex);
+
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (call->id == event_id)
+ break;
}
- filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+ err = -EINVAL;
+ if (!call)
+ goto out_unlock;
- /* really apply the filter to the events */
- err = replace_preds(system, NULL, ps, filter_string, false);
- if (err) {
- append_filter_err(ps, system->filter);
- filter_free_subsystem_preds(system, 2);
+ err = -EEXIST;
+ if (event->filter)
+ goto out_unlock;
+
+ filter = __alloc_preds();
+ if (IS_ERR(filter)) {
+ err = PTR_ERR(filter);
+ goto out_unlock;
}
-out:
+ err = -ENOMEM;
+ ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ goto free_preds;
+
+ parse_init(ps, filter_ops, filter_str);
+ err = filter_parse(ps);
+ if (err)
+ goto free_ps;
+
+ err = replace_preds(call, filter, ps, filter_str, false);
+ if (!err)
+ event->filter = filter;
+
+free_ps:
filter_opstack_clear(ps);
postfix_clear(ps);
kfree(ps);
+
+free_preds:
+ if (err)
+ __free_preds(filter);
+
out_unlock:
mutex_unlock(&event_mutex);
return err;
}
+#endif /* CONFIG_EVENT_PROFILE */
+
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 9753fcc61bc..dff8c84ddf1 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -48,11 +48,11 @@
struct ____ftrace_##name { \
tstruct \
}; \
-static void __used ____ftrace_check_##name(void) \
+static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
- /* force cmpile-time check on F_printk() */ \
+ /* force compile-time check on F_printk() */ \
printk(print); \
}
@@ -66,44 +66,47 @@ static void __used ____ftrace_check_##name(void) \
#undef __field
#define __field(type, item) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\n", \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
offsetof(typeof(field), item), \
- sizeof(field.item)); \
+ sizeof(field.item), is_signed_type(type)); \
if (!ret) \
return 0;
#undef __field_desc
#define __field_desc(type, container, item) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\n", \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
offsetof(typeof(field), container.item), \
- sizeof(field.container.item)); \
+ sizeof(field.container.item), \
+ is_signed_type(type)); \
if (!ret) \
return 0;
#undef __array
#define __array(type, item, len) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\n", \
- offsetof(typeof(field), item), \
- sizeof(field.item)); \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed_type(type)); \
if (!ret) \
return 0;
#undef __array_desc
#define __array_desc(type, container, item, len) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\n", \
+ "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
offsetof(typeof(field), container.item), \
- sizeof(field.container.item)); \
+ sizeof(field.container.item), \
+ is_signed_type(type)); \
if (!ret) \
return 0;
#undef __dynamic_array
#define __dynamic_array(type, item) \
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:0;\n", \
- offsetof(typeof(field), item)); \
+ "offset:%zu;\tsize:0;\tsigned:%u;\n", \
+ offsetof(typeof(field), item), \
+ is_signed_type(type)); \
if (!ret) \
return 0;
@@ -131,7 +134,6 @@ ftrace_format_##name(struct ftrace_event_call *unused, \
#include "trace_entries.h"
-
#undef __field
#define __field(type, item) \
ret = trace_define_field(event_call, #type, #item, \
@@ -193,6 +195,11 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#include "trace_entries.h"
+static int ftrace_raw_init_event(struct ftrace_event_call *call)
+{
+ INIT_LIST_HEAD(&call->fields);
+ return 0;
+}
#undef __field
#define __field(type, item)
@@ -211,7 +218,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
-static int ftrace_raw_init_event_##call(void); \
\
struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
@@ -219,14 +225,9 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = type, \
.system = __stringify(TRACE_SYSTEM), \
- .raw_init = ftrace_raw_init_event_##call, \
+ .raw_init = ftrace_raw_init_event, \
.show_format = ftrace_format_##call, \
.define_fields = ftrace_define_fields_##call, \
}; \
-static int ftrace_raw_init_event_##call(void) \
-{ \
- INIT_LIST_HEAD(&event_##call.fields); \
- return 0; \
-} \
#include "trace_entries.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 45e6c01b2e4..b1342c5d37c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -14,9 +14,20 @@
#include "trace.h"
#include "trace_output.h"
-struct fgraph_data {
+struct fgraph_cpu_data {
pid_t last_pid;
int depth;
+ int ignore;
+};
+
+struct fgraph_data {
+ struct fgraph_cpu_data *cpu_data;
+
+ /* Place to preserve last processed entry. */
+ struct ftrace_graph_ent_entry ent;
+ struct ftrace_graph_ret_entry ret;
+ int failed;
+ int cpu;
};
#define TRACE_GRAPH_INDENT 2
@@ -176,7 +187,7 @@ static int __trace_graph_entry(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ent_entry *entry;
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return 0;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -240,7 +251,7 @@ static void __trace_graph_return(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ret_entry *entry;
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -384,7 +395,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
if (!data)
return TRACE_TYPE_HANDLED;
- last_pid = &(per_cpu_ptr(data, cpu)->last_pid);
+ last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
if (*last_pid == pid)
return TRACE_TYPE_HANDLED;
@@ -435,26 +446,49 @@ static struct ftrace_graph_ret_entry *
get_return_for_leaf(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *curr)
{
- struct ring_buffer_iter *ring_iter;
+ struct fgraph_data *data = iter->private;
+ struct ring_buffer_iter *ring_iter = NULL;
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *next;
- ring_iter = iter->buffer_iter[iter->cpu];
+ /*
+ * If the previous output failed to write to the seq buffer,
+ * then we just reuse the data from before.
+ */
+ if (data && data->failed) {
+ curr = &data->ent;
+ next = &data->ret;
+ } else {
- /* First peek to compare current entry and the next one */
- if (ring_iter)
- event = ring_buffer_iter_peek(ring_iter, NULL);
- else {
- /* We need to consume the current entry to see the next one */
- ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
- event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
- NULL);
- }
+ ring_iter = iter->buffer_iter[iter->cpu];
+
+ /* First peek to compare current entry and the next one */
+ if (ring_iter)
+ event = ring_buffer_iter_peek(ring_iter, NULL);
+ else {
+ /*
+ * We need to consume the current entry to see
+ * the next one.
+ */
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+ event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+ NULL);
+ }
- if (!event)
- return NULL;
+ if (!event)
+ return NULL;
+
+ next = ring_buffer_event_data(event);
- next = ring_buffer_event_data(event);
+ if (data) {
+ /*
+ * Save current and next entries for later reference
+ * if the output fails.
+ */
+ data->ent = *curr;
+ data->ret = *next;
+ }
+ }
if (next->ent.type != TRACE_GRAPH_RET)
return NULL;
@@ -640,7 +674,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
/*
* Comments display at + 1 to depth. Since
@@ -688,7 +722,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
*depth = call->depth;
}
@@ -782,19 +816,34 @@ static enum print_line_t
print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
struct trace_iterator *iter)
{
- int cpu = iter->cpu;
+ struct fgraph_data *data = iter->private;
struct ftrace_graph_ent *call = &field->graph_ent;
struct ftrace_graph_ret_entry *leaf_ret;
+ static enum print_line_t ret;
+ int cpu = iter->cpu;
if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
return TRACE_TYPE_PARTIAL_LINE;
leaf_ret = get_return_for_leaf(iter, field);
if (leaf_ret)
- return print_graph_entry_leaf(iter, field, leaf_ret, s);
+ ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
else
- return print_graph_entry_nested(iter, field, s, cpu);
+ ret = print_graph_entry_nested(iter, field, s, cpu);
+ if (data) {
+ /*
+ * If we failed to write our output, then we need to make
+ * note of it. Because we already consumed our entry.
+ */
+ if (s->full) {
+ data->failed = 1;
+ data->cpu = cpu;
+ } else
+ data->failed = 0;
+ }
+
+ return ret;
}
static enum print_line_t
@@ -810,7 +859,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
/*
* Comments display at + 1 to depth. This is the
@@ -873,7 +922,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
int i;
if (data)
- depth = per_cpu_ptr(data, iter->cpu)->depth;
+ depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
if (print_graph_prologue(iter, s, 0, 0))
return TRACE_TYPE_PARTIAL_LINE;
@@ -941,8 +990,33 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
enum print_line_t
print_graph_function(struct trace_iterator *iter)
{
+ struct ftrace_graph_ent_entry *field;
+ struct fgraph_data *data = iter->private;
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
+ int cpu = iter->cpu;
+ int ret;
+
+ if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
+ per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
+ return TRACE_TYPE_HANDLED;
+ }
+
+ /*
+ * If the last output failed, there's a possibility we need
+ * to print out the missing entry which would never go out.
+ */
+ if (data && data->failed) {
+ field = &data->ent;
+ iter->cpu = data->cpu;
+ ret = print_graph_entry(field, s, iter);
+ if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
+ per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
+ ret = TRACE_TYPE_NO_CONSUME;
+ }
+ iter->cpu = cpu;
+ return ret;
+ }
switch (entry->type) {
case TRACE_GRAPH_ENT: {
@@ -952,7 +1026,7 @@ print_graph_function(struct trace_iterator *iter)
* sizeof(struct ftrace_graph_ent_entry) is very small,
* it can be safely saved at the stack.
*/
- struct ftrace_graph_ent_entry *field, saved;
+ struct ftrace_graph_ent_entry saved;
trace_assign_type(field, entry);
saved = *field;
return print_graph_entry(&saved, s, iter);
@@ -1030,31 +1104,54 @@ static void print_graph_headers(struct seq_file *s)
static void graph_trace_open(struct trace_iterator *iter)
{
/* pid and depth on the last trace processed */
- struct fgraph_data *data = alloc_percpu(struct fgraph_data);
+ struct fgraph_data *data;
int cpu;
+ iter->private = NULL;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
- pr_warning("function graph tracer: not enough memory\n");
- else
- for_each_possible_cpu(cpu) {
- pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid);
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
- *pid = -1;
- *depth = 0;
- }
+ goto out_err;
+
+ data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+ if (!data->cpu_data)
+ goto out_err_free;
+
+ for_each_possible_cpu(cpu) {
+ pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+ int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+ *pid = -1;
+ *depth = 0;
+ *ignore = 0;
+ }
iter->private = data;
+
+ return;
+
+ out_err_free:
+ kfree(data);
+ out_err:
+ pr_warning("function graph tracer: not enough memory\n");
}
static void graph_trace_close(struct trace_iterator *iter)
{
- free_percpu(iter->private);
+ struct fgraph_data *data = iter->private;
+
+ if (data) {
+ free_percpu(data->cpu_data);
+ kfree(data);
+ }
}
static struct tracer graph_trace __read_mostly = {
.name = "function_graph",
.open = graph_trace_open,
+ .pipe_open = graph_trace_open,
.close = graph_trace_close,
+ .pipe_close = graph_trace_close,
.wait_pipe = poll_wait_pipe,
.init = graph_trace_init,
.reset = graph_trace_reset,
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 23b63859130..7b97000745f 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -20,10 +20,10 @@
#define BTS_BUFFER_SIZE (1 << 13)
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
+static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
-#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
static int trace_hw_branches_enabled __read_mostly;
static int trace_hw_branches_suspended __read_mostly;
@@ -32,12 +32,13 @@ static struct trace_array *hw_branch_trace __read_mostly;
static void bts_trace_init_cpu(int cpu)
{
- per_cpu(tracer, cpu) =
- ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
- NULL, (size_t)-1, BTS_KERNEL);
+ per_cpu(hwb_tracer, cpu) =
+ ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+ BTS_BUFFER_SIZE, NULL, (size_t)-1,
+ BTS_KERNEL);
- if (IS_ERR(per_cpu(tracer, cpu)))
- per_cpu(tracer, cpu) = NULL;
+ if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+ per_cpu(hwb_tracer, cpu) = NULL;
}
static int bts_trace_init(struct trace_array *tr)
@@ -51,7 +52,7 @@ static int bts_trace_init(struct trace_array *tr)
for_each_online_cpu(cpu) {
bts_trace_init_cpu(cpu);
- if (likely(per_cpu(tracer, cpu)))
+ if (likely(per_cpu(hwb_tracer, cpu)))
trace_hw_branches_enabled = 1;
}
trace_hw_branches_suspended = 0;
@@ -67,9 +68,9 @@ static void bts_trace_reset(struct trace_array *tr)
get_online_cpus();
for_each_online_cpu(cpu) {
- if (likely(per_cpu(tracer, cpu))) {
- ds_release_bts(per_cpu(tracer, cpu));
- per_cpu(tracer, cpu) = NULL;
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
}
}
trace_hw_branches_enabled = 0;
@@ -83,8 +84,8 @@ static void bts_trace_start(struct trace_array *tr)
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_resume_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
trace_hw_branches_suspended = 0;
put_online_cpus();
}
@@ -95,8 +96,8 @@ static void bts_trace_stop(struct trace_array *tr)
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
trace_hw_branches_suspended = 1;
put_online_cpus();
}
@@ -114,16 +115,16 @@ static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
bts_trace_init_cpu(cpu);
if (trace_hw_branches_suspended &&
- likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
}
break;
case CPU_DOWN_PREPARE:
/* The notification is sent with interrupts enabled. */
- if (likely(per_cpu(tracer, cpu))) {
- ds_release_bts(per_cpu(tracer, cpu));
- per_cpu(tracer, cpu) = NULL;
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
}
}
@@ -165,6 +166,7 @@ void trace_hw_branch(u64 from, u64 to)
struct ftrace_event_call *call = &event_hw_branch;
struct trace_array *tr = hw_branch_trace;
struct ring_buffer_event *event;
+ struct ring_buffer *buf;
struct hw_branch_entry *entry;
unsigned long irq1;
int cpu;
@@ -180,7 +182,8 @@ void trace_hw_branch(u64 from, u64 to)
if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
goto out;
- event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES,
+ buf = tr->buffer;
+ event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
sizeof(*entry), 0, 0);
if (!event)
goto out;
@@ -189,8 +192,8 @@ void trace_hw_branch(u64 from, u64 to)
entry->ent.type = TRACE_HW_BRANCHES;
entry->from = from;
entry->to = to;
- if (!filter_check_discard(call, entry, tr->buffer, event))
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, buf, event))
+ trace_buffer_unlock_commit(buf, event, 0, 0);
out:
atomic_dec(&tr->data[cpu]->disabled);
@@ -256,8 +259,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
/*
* We need to collect the trace on the respective cpu since ftrace
* implicitly adds the record for the current cpu.
@@ -266,8 +269,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
on_each_cpu(trace_bts_cpu, iter->tr, 1);
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_resume_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
put_online_cpus();
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 00000000000..b52d397e57e
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1542 @@
+/*
+ * Kprobes-based tracing events
+ *
+ * Created by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+ "common_type",
+ "common_flags",
+ "common_preempt_count",
+ "common_pid",
+ "common_tgid",
+ "common_lock_depth",
+ FIELD_STRING_IP,
+ FIELD_STRING_NARGS,
+ FIELD_STRING_RETIP,
+ FIELD_STRING_FUNC,
+};
+
+struct fetch_func {
+ unsigned long (*func)(struct pt_regs *, void *);
+ void *data;
+};
+
+static __kprobes unsigned long call_fetch(struct fetch_func *f,
+ struct pt_regs *regs)
+{
+ return f->func(regs, f->data);
+}
+
+/* fetch handlers */
+static __kprobes unsigned long fetch_register(struct pt_regs *regs,
+ void *offset)
+{
+ return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+}
+
+static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
+ void *num)
+{
+ return regs_get_kernel_stack_nth(regs,
+ (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
+{
+ unsigned long retval;
+
+ if (probe_kernel_address(addr, retval))
+ return 0;
+ return retval;
+}
+
+static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
+{
+ return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
+ void *dummy)
+{
+ return regs_return_value(regs);
+}
+
+static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
+ void *dummy)
+{
+ return kernel_stack_pointer(regs);
+}
+
+/* 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;
+}
+
+static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
+{
+ struct symbol_cache *sc = data;
+
+ if (sc->addr)
+ return fetch_memory(regs, (void *)sc->addr);
+ else
+ return 0;
+}
+
+/* Special indirect memory access interface */
+struct indirect_fetch_data {
+ struct fetch_func orig;
+ long offset;
+};
+
+static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
+{
+ struct indirect_fetch_data *ind = data;
+ unsigned long addr;
+
+ addr = call_fetch(&ind->orig, regs);
+ if (addr) {
+ addr += ind->offset;
+ return fetch_memory(regs, (void *)addr);
+ } else
+ return 0;
+}
+
+static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+{
+ if (data->orig.func == fetch_indirect)
+ free_indirect_fetch_data(data->orig.data);
+ else if (data->orig.func == fetch_symbol)
+ free_symbol_cache(data->orig.data);
+ kfree(data);
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+ struct fetch_func fetch;
+ const char *name;
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE 1
+#define TP_FLAG_PROFILE 2
+
+struct trace_probe {
+ 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_call call;
+ struct trace_event event;
+ unsigned int nr_args;
+ struct probe_arg args[];
+};
+
+#define SIZEOF_TRACE_PROBE(n) \
+ (offsetof(struct trace_probe, args) + \
+ (sizeof(struct probe_arg) * (n)))
+
+static __kprobes int probe_is_return(struct trace_probe *tp)
+{
+ return tp->rp.handler != NULL;
+}
+
+static __kprobes const char *probe_symbol(struct trace_probe *tp)
+{
+ return tp->symbol ? tp->symbol : "unknown";
+}
+
+static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
+{
+ int ret = -EINVAL;
+
+ if (ff->func == fetch_argument)
+ ret = snprintf(buf, n, "$arg%lu", (unsigned long)ff->data);
+ else if (ff->func == fetch_register) {
+ const char *name;
+ name = regs_query_register_name((unsigned int)((long)ff->data));
+ ret = snprintf(buf, n, "%%%s", name);
+ } else if (ff->func == fetch_stack)
+ ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
+ else if (ff->func == fetch_memory)
+ ret = snprintf(buf, n, "@0x%p", ff->data);
+ else if (ff->func == fetch_symbol) {
+ struct symbol_cache *sc = ff->data;
+ if (sc->offset)
+ ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
+ sc->offset);
+ else
+ ret = snprintf(buf, n, "@%s", sc->symbol);
+ } else if (ff->func == fetch_retvalue)
+ ret = snprintf(buf, n, "$retval");
+ else if (ff->func == fetch_stack_address)
+ ret = snprintf(buf, n, "$stack");
+ else if (ff->func == fetch_indirect) {
+ struct indirect_fetch_data *id = ff->data;
+ size_t l = 0;
+ ret = snprintf(buf, n, "%+ld(", id->offset);
+ if (ret >= n)
+ goto end;
+ l += ret;
+ ret = probe_arg_string(buf + l, n - l, &id->orig);
+ if (ret < 0)
+ goto end;
+ l += ret;
+ ret = snprintf(buf + l, n - l, ")");
+ ret += l;
+ }
+end:
+ if (ret >= n)
+ return -ENOSPC;
+ return ret;
+}
+
+static int register_probe_event(struct trace_probe *tp);
+static void unregister_probe_event(struct trace_probe *tp);
+
+static DEFINE_MUTEX(probe_lock);
+static LIST_HEAD(probe_list);
+
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+ struct pt_regs *regs);
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+ const char *event,
+ void *addr,
+ const char *symbol,
+ unsigned long offs,
+ int nargs, int is_return)
+{
+ struct trace_probe *tp;
+
+ tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
+ if (!tp)
+ return ERR_PTR(-ENOMEM);
+
+ if (symbol) {
+ tp->symbol = kstrdup(symbol, GFP_KERNEL);
+ if (!tp->symbol)
+ goto error;
+ tp->rp.kp.symbol_name = tp->symbol;
+ tp->rp.kp.offset = offs;
+ } else
+ tp->rp.kp.addr = addr;
+
+ if (is_return)
+ tp->rp.handler = kretprobe_dispatcher;
+ else
+ tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+ if (!event)
+ goto error;
+ tp->call.name = kstrdup(event, GFP_KERNEL);
+ if (!tp->call.name)
+ goto error;
+
+ if (!group)
+ goto error;
+ tp->call.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->call.system)
+ goto error;
+
+ INIT_LIST_HEAD(&tp->list);
+ return tp;
+error:
+ kfree(tp->call.name);
+ kfree(tp->symbol);
+ kfree(tp);
+ return ERR_PTR(-ENOMEM);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+ if (arg->fetch.func == fetch_symbol)
+ free_symbol_cache(arg->fetch.data);
+ else if (arg->fetch.func == fetch_indirect)
+ free_indirect_fetch_data(arg->fetch.data);
+ kfree(arg->name);
+}
+
+static void free_trace_probe(struct trace_probe *tp)
+{
+ int i;
+
+ for (i = 0; i < tp->nr_args; i++)
+ free_probe_arg(&tp->args[i]);
+
+ kfree(tp->call.system);
+ kfree(tp->call.name);
+ kfree(tp->symbol);
+ kfree(tp);
+}
+
+static struct trace_probe *find_probe_event(const char *event,
+ const char *group)
+{
+ struct trace_probe *tp;
+
+ list_for_each_entry(tp, &probe_list, list)
+ if (strcmp(tp->call.name, event) == 0 &&
+ strcmp(tp->call.system, group) == 0)
+ return tp;
+ return NULL;
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
+{
+ if (probe_is_return(tp))
+ unregister_kretprobe(&tp->rp);
+ else
+ unregister_kprobe(&tp->rp.kp);
+ list_del(&tp->list);
+ unregister_probe_event(tp);
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_probe(struct trace_probe *tp)
+{
+ struct trace_probe *old_tp;
+ int ret;
+
+ mutex_lock(&probe_lock);
+
+ /* register as an event */
+ old_tp = find_probe_event(tp->call.name, tp->call.system);
+ if (old_tp) {
+ /* delete old event */
+ unregister_trace_probe(old_tp);
+ free_trace_probe(old_tp);
+ }
+ ret = register_probe_event(tp);
+ if (ret) {
+ pr_warning("Faild to register probe event(%d)\n", ret);
+ goto end;
+ }
+
+ tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+ if (probe_is_return(tp))
+ ret = register_kretprobe(&tp->rp);
+ else
+ ret = register_kprobe(&tp->rp.kp);
+
+ if (ret) {
+ pr_warning("Could not insert probe(%d)\n", ret);
+ if (ret == -EILSEQ) {
+ pr_warning("Probing address(0x%p) is not an "
+ "instruction boundary.\n",
+ tp->rp.kp.addr);
+ ret = -EINVAL;
+ }
+ unregister_probe_event(tp);
+ } else
+ list_add_tail(&tp->list, &probe_list);
+end:
+ mutex_unlock(&probe_lock);
+ return ret;
+}
+
+/* Split symbol and offset. */
+static int split_symbol_offset(char *symbol, unsigned long *offset)
+{
+ char *tmp;
+ int ret;
+
+ if (!offset)
+ return -EINVAL;
+
+ tmp = strchr(symbol, '+');
+ if (tmp) {
+ /* skip sign because strict_strtol doesn't accept '+' */
+ ret = strict_strtoul(tmp + 1, 0, offset);
+ if (ret)
+ return ret;
+ *tmp = '\0';
+ } else
+ *offset = 0;
+ return 0;
+}
+
+#define PARAM_MAX_ARGS 16
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
+{
+ int ret = 0;
+ unsigned long param;
+
+ if (strcmp(arg, "retval") == 0) {
+ if (is_return) {
+ ff->func = fetch_retvalue;
+ ff->data = NULL;
+ } else
+ ret = -EINVAL;
+ } else if (strncmp(arg, "stack", 5) == 0) {
+ if (arg[5] == '\0') {
+ ff->func = fetch_stack_address;
+ ff->data = NULL;
+ } else if (isdigit(arg[5])) {
+ ret = strict_strtoul(arg + 5, 10, &param);
+ if (ret || param > PARAM_MAX_STACK)
+ ret = -EINVAL;
+ else {
+ ff->func = fetch_stack;
+ ff->data = (void *)param;
+ }
+ } else
+ ret = -EINVAL;
+ } else if (strncmp(arg, "arg", 3) == 0 && isdigit(arg[3])) {
+ ret = strict_strtoul(arg + 3, 10, &param);
+ if (ret || param > PARAM_MAX_ARGS)
+ ret = -EINVAL;
+ else {
+ ff->func = fetch_argument;
+ ff->data = (void *)param;
+ }
+ } else
+ ret = -EINVAL;
+ return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ int ret = 0;
+ unsigned long param;
+ long offset;
+ char *tmp;
+
+ switch (arg[0]) {
+ case '$':
+ ret = parse_probe_vars(arg + 1, ff, is_return);
+ break;
+ case '%': /* named register */
+ ret = regs_query_register_offset(arg + 1);
+ if (ret >= 0) {
+ ff->func = fetch_register;
+ ff->data = (void *)(unsigned long)ret;
+ ret = 0;
+ }
+ break;
+ case '@': /* memory or symbol */
+ if (isdigit(arg[1])) {
+ ret = strict_strtoul(arg + 1, 0, &param);
+ if (ret)
+ break;
+ ff->func = fetch_memory;
+ ff->data = (void *)param;
+ } else {
+ ret = split_symbol_offset(arg + 1, &offset);
+ if (ret)
+ break;
+ ff->data = alloc_symbol_cache(arg + 1, offset);
+ if (ff->data)
+ ff->func = fetch_symbol;
+ else
+ ret = -EINVAL;
+ }
+ break;
+ case '+': /* indirect memory */
+ case '-':
+ tmp = strchr(arg, '(');
+ if (!tmp) {
+ ret = -EINVAL;
+ break;
+ }
+ *tmp = '\0';
+ ret = strict_strtol(arg + 1, 0, &offset);
+ if (ret)
+ break;
+ if (arg[0] == '-')
+ offset = -offset;
+ arg = tmp + 1;
+ tmp = strrchr(arg, ')');
+ if (tmp) {
+ struct indirect_fetch_data *id;
+ *tmp = '\0';
+ id = kzalloc(sizeof(struct indirect_fetch_data),
+ GFP_KERNEL);
+ if (!id)
+ return -ENOMEM;
+ id->offset = offset;
+ ret = __parse_probe_arg(arg, &id->orig, is_return);
+ if (ret)
+ kfree(id);
+ else {
+ ff->func = fetch_indirect;
+ ff->data = (void *)id;
+ }
+ } else
+ ret = -EINVAL;
+ break;
+ default:
+ /* TODO: support custom handler */
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ if (strlen(arg) > MAX_ARGSTR_LEN) {
+ pr_info("Argument is too long.: %s\n", arg);
+ return -ENOSPC;
+ }
+ return __parse_probe_arg(arg, ff, is_return);
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+ struct probe_arg *args, int narg)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+ if (strcmp(reserved_field_names[i], name) == 0)
+ return 1;
+ for (i = 0; i < narg; i++)
+ if (strcmp(args[i].name, name) == 0)
+ return 1;
+ return 0;
+}
+
+static int create_trace_probe(int argc, char **argv)
+{
+ /*
+ * Argument syntax:
+ * - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+ * - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+ * Fetch args:
+ * $argN : fetch Nth of function argument. (N:0-)
+ * $retval : fetch return value
+ * $stack : fetch stack address
+ * $stackN : fetch Nth of stack (N:0-)
+ * @ADDR : fetch memory at ADDR (ADDR should be in kernel)
+ * @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+ * %REG : fetch register REG
+ * Indirect memory fetch:
+ * +|-offs(ARG) : fetch memory at ARG +|- offs address.
+ * Alias name of args:
+ * NAME=FETCHARG : set NAME as alias of FETCHARG.
+ */
+ struct trace_probe *tp;
+ int i, ret = 0;
+ int is_return = 0, is_delete = 0;
+ char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+ unsigned long offset = 0;
+ void *addr = NULL;
+ char buf[MAX_EVENT_NAME_LEN];
+
+ /* argc must be >= 1 */
+ if (argv[0][0] == 'p')
+ is_return = 0;
+ else if (argv[0][0] == 'r')
+ is_return = 1;
+ else if (argv[0][0] == '-')
+ is_delete = 1;
+ else {
+ pr_info("Probe definition must be started with 'p', 'r' or"
+ " '-'.\n");
+ return -EINVAL;
+ }
+
+ if (argv[0][1] == ':') {
+ event = &argv[0][2];
+ if (strchr(event, '/')) {
+ group = event;
+ event = strchr(group, '/') + 1;
+ event[-1] = '\0';
+ if (strlen(group) == 0) {
+ pr_info("Group name is not specifiled\n");
+ return -EINVAL;
+ }
+ }
+ if (strlen(event) == 0) {
+ pr_info("Event name is not specifiled\n");
+ return -EINVAL;
+ }
+ }
+ if (!group)
+ group = KPROBE_EVENT_SYSTEM;
+
+ if (is_delete) {
+ if (!event) {
+ pr_info("Delete command needs an event name.\n");
+ return -EINVAL;
+ }
+ tp = find_probe_event(event, group);
+ if (!tp) {
+ pr_info("Event %s/%s doesn't exist.\n", group, event);
+ return -ENOENT;
+ }
+ /* delete an event */
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ return 0;
+ }
+
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
+ return -EINVAL;
+ }
+ if (isdigit(argv[1][0])) {
+ if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
+ return -EINVAL;
+ }
+ /* an address specified */
+ ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+ if (ret) {
+ pr_info("Failed to parse address.\n");
+ return ret;
+ }
+ } else {
+ /* a symbol specified */
+ symbol = argv[1];
+ /* TODO: support .init module functions */
+ ret = split_symbol_offset(symbol, &offset);
+ if (ret) {
+ pr_info("Failed to parse symbol.\n");
+ return ret;
+ }
+ if (offset && is_return) {
+ pr_info("Return probe must be used without offset.\n");
+ return -EINVAL;
+ }
+ }
+ argc -= 2; argv += 2;
+
+ /* setup a probe */
+ if (!event) {
+ /* Make a new event name */
+ if (symbol)
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld",
+ is_return ? 'r' : 'p', symbol, offset);
+ else
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p",
+ is_return ? 'r' : 'p', addr);
+ event = buf;
+ }
+ tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+ is_return);
+ if (IS_ERR(tp)) {
+ pr_info("Failed to allocate trace_probe.(%d)\n",
+ (int)PTR_ERR(tp));
+ return PTR_ERR(tp);
+ }
+
+ /* parse arguments */
+ ret = 0;
+ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ /* Parse argument name */
+ arg = strchr(argv[i], '=');
+ if (arg)
+ *arg++ = '\0';
+ else
+ arg = argv[i];
+
+ if (conflict_field_name(argv[i], tp->args, i)) {
+ pr_info("Argument%d name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ if (!tp->args[i].name) {
+ pr_info("Failed to allocate argument%d name '%s'.\n",
+ i, argv[i]);
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ /* Parse fetch argument */
+ ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+ if (ret) {
+ pr_info("Parse error at argument%d. (%d)\n", i, ret);
+ kfree(tp->args[i].name);
+ goto error;
+ }
+
+ tp->nr_args++;
+ }
+
+ ret = register_trace_probe(tp);
+ if (ret)
+ goto error;
+ return 0;
+
+error:
+ free_trace_probe(tp);
+ return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+ struct trace_probe *tp;
+
+ mutex_lock(&probe_lock);
+ /* TODO: Use batch unregistration */
+ while (!list_empty(&probe_list)) {
+ tp = list_entry(probe_list.next, struct trace_probe, list);
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ }
+ mutex_unlock(&probe_lock);
+}
+
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&probe_lock);
+ return seq_list_start(&probe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return seq_list_next(v, &probe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+ mutex_unlock(&probe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_probe *tp = v;
+ int i, ret;
+ char buf[MAX_ARGSTR_LEN + 1];
+
+ seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+ seq_printf(m, ":%s/%s", tp->call.system, 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", probe_symbol(tp), tp->rp.kp.offset);
+ else
+ seq_printf(m, " %s", probe_symbol(tp));
+
+ for (i = 0; i < tp->nr_args; i++) {
+ ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
+ if (ret < 0) {
+ pr_warning("Argument%d decoding error(%d).\n", i, ret);
+ return ret;
+ }
+ seq_printf(m, " %s=%s", tp->args[i].name, buf);
+ }
+ seq_printf(m, "\n");
+ return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ cleanup_all_probes();
+
+ return seq_open(file, &probes_seq_op);
+}
+
+static int command_trace_probe(const char *buf)
+{
+ char **argv;
+ int argc = 0, ret = 0;
+
+ argv = argv_split(GFP_KERNEL, buf, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ if (argc)
+ ret = create_trace_probe(argc, argv);
+
+ argv_free(argv);
+ return ret;
+}
+
+#define WRITE_BUFSIZE 128
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ char *kbuf, *tmp;
+ int ret;
+ size_t done;
+ size_t size;
+
+ kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ ret = done = 0;
+ while (done < count) {
+ size = count - done;
+ if (size >= WRITE_BUFSIZE)
+ size = WRITE_BUFSIZE - 1;
+ if (copy_from_user(kbuf, buffer + done, size)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ kbuf[size] = '\0';
+ tmp = strchr(kbuf, '\n');
+ if (tmp) {
+ *tmp = '\0';
+ size = tmp - kbuf + 1;
+ } else if (done + size < count) {
+ pr_warning("Line length is too long: "
+ "Should be less than %d.", WRITE_BUFSIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+ done += size;
+ /* Remove comments */
+ tmp = strchr(kbuf, '#');
+ if (tmp)
+ *tmp = '\0';
+
+ ret = command_trace_probe(kbuf);
+ if (ret)
+ goto out;
+ }
+ ret = done;
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static const struct file_operations kprobe_events_ops = {
+ .owner = THIS_MODULE,
+ .open = probes_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .write = probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_probe *tp = v;
+
+ seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
+ tp->rp.kp.nmissed);
+
+ return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations kprobe_profile_ops = {
+ .owner = THIS_MODULE,
+ .open = profile_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+/* Kprobe handler */
+static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct kprobe_trace_entry *entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int size, i, pc;
+ unsigned long irq_flags;
+ struct ftrace_event_call *call = &tp->call;
+
+ tp->nhit++;
+
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
+ size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+ irq_flags, pc);
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->nargs = tp->nr_args;
+ entry->ip = (unsigned long)kp->addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ return 0;
+}
+
+/* Kretprobe handler */
+static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct kretprobe_trace_entry *entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ int size, i, pc;
+ unsigned long irq_flags;
+ struct ftrace_event_call *call = &tp->call;
+
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
+ size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+ irq_flags, pc);
+ if (!event)
+ return 0;
+
+ entry = ring_buffer_event_data(event);
+ entry->nargs = tp->nr_args;
+ entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->ret_ip = (unsigned long)ri->ret_addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+ return 0;
+}
+
+/* Event entry printers */
+enum print_line_t
+print_kprobe_event(struct trace_iterator *iter, int flags)
+{
+ struct kprobe_trace_entry *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
+ int i;
+
+ field = (struct kprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, ")"))
+ goto partial;
+
+ for (i = 0; i < field->nargs; i++)
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
+ goto partial;
+
+ if (!trace_seq_puts(s, "\n"))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+enum print_line_t
+print_kretprobe_event(struct trace_iterator *iter, int flags)
+{
+ struct kretprobe_trace_entry *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
+ int i;
+
+ field = (struct kretprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, " <- "))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, ")"))
+ goto partial;
+
+ for (i = 0; i < field->nargs; i++)
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
+ goto partial;
+
+ if (!trace_seq_puts(s, "\n"))
+ goto partial;
+
+ return TRACE_TYPE_HANDLED;
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags |= TP_FLAG_TRACE;
+ if (probe_is_return(tp))
+ return enable_kretprobe(&tp->rp);
+ else
+ return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_event_disable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags &= ~TP_FLAG_TRACE;
+ if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
+ }
+}
+
+static int probe_event_raw_init(struct ftrace_event_call *event_call)
+{
+ INIT_LIST_HEAD(&event_call->fields);
+
+ return 0;
+}
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed) \
+ do { \
+ ret = trace_define_field(event_call, #type, name, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed, \
+ FILTER_OTHER); \
+ if (ret) \
+ return ret; \
+ } while (0)
+
+static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+ int ret, i;
+ struct kprobe_trace_entry field;
+ struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+ ret = trace_define_common_fields(event_call);
+ if (ret)
+ return ret;
+
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+ int ret, i;
+ struct kretprobe_trace_entry field;
+ struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+ ret = trace_define_common_fields(event_call);
+ if (ret)
+ return ret;
+
+ DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ return 0;
+}
+
+static int __probe_event_show_format(struct trace_seq *s,
+ struct trace_probe *tp, const char *fmt,
+ const char *arg)
+{
+ int i;
+
+ /* Show format */
+ if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
+ return 0;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
+ return 0;
+
+ if (!trace_seq_printf(s, "\", %s", arg))
+ return 0;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
+ return 0;
+
+ return trace_seq_puts(s, "\n");
+}
+
+#undef SHOW_FIELD
+#define SHOW_FIELD(type, item, name) \
+ do { \
+ ret = trace_seq_printf(s, "\tfield: " #type " %s;\t" \
+ "offset:%u;\tsize:%u;\n", name, \
+ (unsigned int)offsetof(typeof(field), item),\
+ (unsigned int)sizeof(type)); \
+ if (!ret) \
+ return 0; \
+ } while (0)
+
+static int kprobe_event_show_format(struct ftrace_event_call *call,
+ struct trace_seq *s)
+{
+ struct kprobe_trace_entry field __attribute__((unused));
+ int ret, i;
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+ /* Show fields */
+ for (i = 0; i < tp->nr_args; i++)
+ SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+ trace_seq_puts(s, "\n");
+
+ return __probe_event_show_format(s, tp, "(%lx)",
+ "REC->" FIELD_STRING_IP);
+}
+
+static int kretprobe_event_show_format(struct ftrace_event_call *call,
+ struct trace_seq *s)
+{
+ struct kretprobe_trace_entry field __attribute__((unused));
+ int ret, i;
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
+ SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+
+ /* Show fields */
+ for (i = 0; i < tp->nr_args; i++)
+ SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
+ trace_seq_puts(s, "\n");
+
+ return __probe_event_show_format(s, tp, "(%lx <- %lx)",
+ "REC->" FIELD_STRING_FUNC
+ ", REC->" FIELD_STRING_RETIP);
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+
+/* Kprobe profile handler */
+static __kprobes int kprobe_profile_func(struct kprobe *kp,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kprobe_trace_entry *entry;
+ struct trace_entry *ent;
+ int size, __size, i, pc, __cpu;
+ unsigned long irq_flags;
+ char *trace_buf;
+ char *raw_data;
+ int rctx;
+
+ pc = preempt_count();
+ __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "profile buffer not large enough"))
+ return 0;
+
+ /*
+ * Protect the non nmi buffer
+ * This also protects the rcu read side
+ */
+ local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ __cpu = smp_processor_id();
+
+ if (in_nmi())
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ else
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+ /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ entry = (struct kprobe_trace_entry *)raw_data;
+ ent = &entry->ent;
+
+ tracing_generic_entry_update(ent, irq_flags, pc);
+ ent->type = call->id;
+ entry->nargs = tp->nr_args;
+ entry->ip = (unsigned long)kp->addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ perf_tp_event(call->id, entry->ip, 1, entry, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(irq_flags);
+
+ return 0;
+}
+
+/* Kretprobe profile handler */
+static __kprobes int kretprobe_profile_func(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kretprobe_trace_entry *entry;
+ struct trace_entry *ent;
+ int size, __size, i, pc, __cpu;
+ unsigned long irq_flags;
+ char *trace_buf;
+ char *raw_data;
+ int rctx;
+
+ pc = preempt_count();
+ __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ "profile buffer not large enough"))
+ return 0;
+
+ /*
+ * Protect the non nmi buffer
+ * This also protects the rcu read side
+ */
+ local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
+ __cpu = smp_processor_id();
+
+ if (in_nmi())
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ else
+ trace_buf = rcu_dereference(perf_trace_buf);
+
+ if (!trace_buf)
+ goto end;
+
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
+ /* Zero dead bytes from alignment to avoid buffer leak to userspace */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ entry = (struct kretprobe_trace_entry *)raw_data;
+ ent = &entry->ent;
+
+ tracing_generic_entry_update(ent, irq_flags, pc);
+ ent->type = call->id;
+ entry->nargs = tp->nr_args;
+ entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->ret_ip = (unsigned long)ri->ret_addr;
+ for (i = 0; i < tp->nr_args; i++)
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+ perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
+
+end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
+ local_irq_restore(irq_flags);
+
+ return 0;
+}
+
+static int probe_profile_enable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags |= TP_FLAG_PROFILE;
+
+ if (probe_is_return(tp))
+ return enable_kretprobe(&tp->rp);
+ else
+ return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_profile_disable(struct ftrace_event_call *call)
+{
+ struct trace_probe *tp = (struct trace_probe *)call->data;
+
+ tp->flags &= ~TP_FLAG_PROFILE;
+
+ if (!(tp->flags & TP_FLAG_TRACE)) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
+ }
+}
+#endif /* CONFIG_EVENT_PROFILE */
+
+
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kprobe_trace_func(kp, regs);
+#ifdef CONFIG_EVENT_PROFILE
+ if (tp->flags & TP_FLAG_PROFILE)
+ kprobe_profile_func(kp, regs);
+#endif /* CONFIG_EVENT_PROFILE */
+ return 0; /* We don't tweek kernel, so just return 0 */
+}
+
+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);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_EVENT_PROFILE
+ if (tp->flags & TP_FLAG_PROFILE)
+ kretprobe_profile_func(ri, regs);
+#endif /* CONFIG_EVENT_PROFILE */
+ return 0; /* We don't tweek kernel, so just return 0 */
+}
+
+static int register_probe_event(struct trace_probe *tp)
+{
+ struct ftrace_event_call *call = &tp->call;
+ int ret;
+
+ /* Initialize ftrace_event_call */
+ if (probe_is_return(tp)) {
+ tp->event.trace = print_kretprobe_event;
+ call->raw_init = probe_event_raw_init;
+ call->show_format = kretprobe_event_show_format;
+ call->define_fields = kretprobe_event_define_fields;
+ } else {
+ tp->event.trace = print_kprobe_event;
+ call->raw_init = probe_event_raw_init;
+ call->show_format = kprobe_event_show_format;
+ call->define_fields = kprobe_event_define_fields;
+ }
+ call->event = &tp->event;
+ call->id = register_ftrace_event(&tp->event);
+ if (!call->id)
+ return -ENODEV;
+ call->enabled = 0;
+ call->regfunc = probe_event_enable;
+ call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_EVENT_PROFILE
+ atomic_set(&call->profile_count, -1);
+ call->profile_enable = probe_profile_enable;
+ call->profile_disable = probe_profile_disable;
+#endif
+ call->data = tp;
+ ret = trace_add_event_call(call);
+ if (ret) {
+ pr_info("Failed to register kprobe event: %s\n", call->name);
+ unregister_ftrace_event(&tp->event);
+ }
+ return ret;
+}
+
+static void unregister_probe_event(struct trace_probe *tp)
+{
+ /* tp->event is unregistered in trace_remove_event_call() */
+ trace_remove_event_call(&tp->call);
+}
+
+/* Make a debugfs interface for controling probe points */
+static __init int init_kprobe_trace(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+ NULL, &kprobe_events_ops);
+
+ /* Event list interface */
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'kprobe_events' entry\n");
+
+ /* Profile interface */
+ entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+ NULL, &kprobe_profile_ops);
+
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'kprobe_profile' entry\n");
+ return 0;
+}
+fs_initcall(init_kprobe_trace);
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static int kprobe_trace_selftest_target(int a1, int a2, int a3,
+ int a4, int a5, int a6)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6;
+}
+
+static __init int kprobe_trace_self_tests_init(void)
+{
+ int ret;
+ int (*target)(int, int, int, int, int, int);
+
+ target = kprobe_trace_selftest_target;
+
+ pr_info("Testing kprobe tracing: ");
+
+ ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
+ "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error enabling function entry\n");
+
+ ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
+ "$retval");
+ if (WARN_ON_ONCE(ret))
+ pr_warning("error enabling function return\n");
+
+ ret = target(1, 2, 3, 4, 5, 6);
+
+ cleanup_all_probes();
+
+ pr_cont("OK\n");
+ return 0;
+}
+
+late_initcall(kprobe_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 00000000000..acb87d4a4ac
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,551 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * 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) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace_stat.h"
+#include "trace.h"
+
+#include <linux/hw_breakpoint.h>
+#include <asm/hw_breakpoint.h>
+
+/*
+ * For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+ struct perf_event **ksym_hbp;
+ struct perf_event_attr attr;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ unsigned long counter;
+#endif
+ struct hlist_node ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+ struct hlist_node *node;
+ struct trace_ksym *entry;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+ if ((entry->attr.bp_addr == hbp_hit_addr) &&
+ (entry->counter <= MAX_UL_INT)) {
+ entry->counter++;
+ break;
+ }
+ }
+ rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct perf_event *hbp, int nmi,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct ring_buffer_event *event;
+ struct ksym_trace_entry *entry;
+ struct ring_buffer *buffer;
+ int pc;
+
+ if (!ksym_tracing_enabled)
+ return;
+
+ buffer = ksym_trace_array->buffer;
+
+ pc = preempt_count();
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+ sizeof(*entry), 0, pc);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = instruction_pointer(regs);
+ entry->type = hw_breakpoint_type(hbp);
+ entry->addr = hw_breakpoint_addr(hbp);
+ strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ ksym_collect_stats(hw_breakpoint_addr(hbp));
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+ int access = 0;
+
+ if (str[0] == 'r')
+ access |= HW_BREAKPOINT_R;
+
+ if (str[1] == 'w')
+ access |= HW_BREAKPOINT_W;
+
+ if (str[2] == 'x')
+ access |= HW_BREAKPOINT_X;
+
+ switch (access) {
+ case HW_BREAKPOINT_R:
+ case HW_BREAKPOINT_W:
+ case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+ return access;
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ * i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ * <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+ unsigned long *addr)
+{
+ int ret;
+
+ *ksymname = strsep(&input_string, ":");
+ *addr = kallsyms_lookup_name(*ksymname);
+
+ /* Check for malformed request: (2), (1) and (5) */
+ if ((!input_string) ||
+ (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+ (*addr == 0))
+ return -EINVAL;;
+
+ ret = ksym_trace_get_access_type(input_string);
+
+ return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+ struct trace_ksym *entry;
+ int ret = -ENOMEM;
+
+ if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+ printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+ " new requests for tracing can be accepted now.\n",
+ KSYM_TRACER_MAX);
+ return -ENOSPC;
+ }
+
+ entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ hw_breakpoint_init(&entry->attr);
+
+ entry->attr.bp_type = op;
+ entry->attr.bp_addr = addr;
+ entry->attr.bp_len = HW_BREAKPOINT_LEN_4;
+
+ ret = -EAGAIN;
+ entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr,
+ ksym_hbp_handler);
+
+ if (IS_ERR(entry->ksym_hbp)) {
+ ret = PTR_ERR(entry->ksym_hbp);
+ printk(KERN_INFO "ksym_tracer request failed. Try again"
+ " later!!\n");
+ goto err;
+ }
+
+ hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+ ksym_filter_entry_count++;
+
+ return 0;
+
+err:
+ kfree(entry);
+
+ return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ struct trace_seq *s;
+ ssize_t cnt = 0;
+ int ret;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+ trace_seq_init(s);
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ ret = trace_seq_printf(s, "%pS:", (void *)entry->attr.bp_addr);
+ if (entry->attr.bp_type == HW_BREAKPOINT_R)
+ ret = trace_seq_puts(s, "r--\n");
+ else if (entry->attr.bp_type == HW_BREAKPOINT_W)
+ ret = trace_seq_puts(s, "-w-\n");
+ else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R))
+ ret = trace_seq_puts(s, "rw-\n");
+ WARN_ON_ONCE(!ret);
+ }
+
+ cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ mutex_unlock(&ksym_tracer_mutex);
+
+ kfree(s);
+
+ return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node, *node1;
+
+ mutex_lock(&ksym_tracer_mutex);
+ hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+ ksym_hlist) {
+ unregister_wide_hw_breakpoint(entry->ksym_hbp);
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry);
+ }
+ mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ char *input_string, *ksymname = NULL;
+ unsigned long ksym_addr = 0;
+ int ret, op, changed = 0;
+
+ input_string = kzalloc(count + 1, GFP_KERNEL);
+ if (!input_string)
+ return -ENOMEM;
+
+ if (copy_from_user(input_string, buffer, count)) {
+ kfree(input_string);
+ return -EFAULT;
+ }
+ input_string[count] = '\0';
+
+ strstrip(input_string);
+
+ /*
+ * Clear all breakpoints if:
+ * 1: echo > ksym_trace_filter
+ * 2: echo 0 > ksym_trace_filter
+ * 3: echo "*:---" > ksym_trace_filter
+ */
+ if (!input_string[0] || !strcmp(input_string, "0") ||
+ !strcmp(input_string, "*:---")) {
+ __ksym_trace_reset();
+ kfree(input_string);
+ return count;
+ }
+
+ ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+ if (ret < 0) {
+ kfree(input_string);
+ return ret;
+ }
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ ret = -EINVAL;
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ if (entry->attr.bp_addr == ksym_addr) {
+ /* Check for malformed request: (6) */
+ if (entry->attr.bp_type != op)
+ changed = 1;
+ else
+ goto out;
+ break;
+ }
+ }
+ if (changed) {
+ unregister_wide_hw_breakpoint(entry->ksym_hbp);
+ entry->attr.bp_type = op;
+ ret = 0;
+ if (op > 0) {
+ entry->ksym_hbp =
+ register_wide_hw_breakpoint(&entry->attr,
+ ksym_hbp_handler);
+ if (IS_ERR(entry->ksym_hbp))
+ ret = PTR_ERR(entry->ksym_hbp);
+ else
+ goto out;
+ }
+ /* Error or "symbol:---" case: drop it */
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry);
+ goto out;
+ } else {
+ /* Check for malformed request: (4) */
+ if (op == 0)
+ goto out;
+ ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+ }
+out:
+ mutex_unlock(&ksym_tracer_mutex);
+
+ kfree(input_string);
+
+ if (!ret)
+ ret = count;
+ return ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+ .open = tracing_open_generic,
+ .read = ksym_trace_filter_read,
+ .write = ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+ ksym_tracing_enabled = 0;
+ __ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+ int cpu, ret = 0;
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+ ksym_tracing_enabled = 1;
+ ksym_trace_array = tr;
+
+ return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "# TASK-PID CPU# Symbol "
+ "Type Function\n");
+ seq_puts(m,
+ "# | | | "
+ " | |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct ksym_trace_entry *field;
+ char str[KSYM_SYMBOL_LEN];
+ int ret;
+
+ if (entry->type != TRACE_KSYM)
+ return TRACE_TYPE_UNHANDLED;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd,
+ entry->pid, iter->cpu, (char *)field->addr);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ switch (field->type) {
+ case HW_BREAKPOINT_R:
+ ret = trace_seq_printf(s, " R ");
+ break;
+ case HW_BREAKPOINT_W:
+ ret = trace_seq_printf(s, " W ");
+ break;
+ case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+ ret = trace_seq_printf(s, " RW ");
+ break;
+ default:
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ sprint_symbol(str, field->ip);
+ ret = trace_seq_printf(s, "%s\n", str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+ .name = "ksym_tracer",
+ .init = ksym_trace_init,
+ .reset = ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_ksym,
+#endif
+ .print_header = ksym_trace_print_header,
+ .print_line = ksym_trace_output
+};
+
+__init static int init_ksym_trace(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+ ksym_filter_entry_count = 0;
+
+ entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer,
+ NULL, &ksym_tracing_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'ksym_trace_filter' file\n");
+
+ return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
+
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_tracer_stat_headers(struct seq_file *m)
+{
+ seq_puts(m, " Access Type ");
+ seq_puts(m, " Symbol Counter\n");
+ seq_puts(m, " ----------- ");
+ seq_puts(m, " ------ -------\n");
+ return 0;
+}
+
+static int ksym_tracer_stat_show(struct seq_file *m, void *v)
+{
+ struct hlist_node *stat = v;
+ struct trace_ksym *entry;
+ int access_type = 0;
+ char fn_name[KSYM_NAME_LEN];
+
+ entry = hlist_entry(stat, struct trace_ksym, ksym_hlist);
+
+ access_type = entry->attr.bp_type;
+
+ switch (access_type) {
+ case HW_BREAKPOINT_R:
+ seq_puts(m, " R ");
+ break;
+ case HW_BREAKPOINT_W:
+ seq_puts(m, " W ");
+ break;
+ case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+ seq_puts(m, " RW ");
+ break;
+ default:
+ seq_puts(m, " NA ");
+ }
+
+ if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0)
+ seq_printf(m, " %-36s", fn_name);
+ else
+ seq_printf(m, " %-36s", "<NA>");
+ seq_printf(m, " %15lu\n", entry->counter);
+
+ return 0;
+}
+
+static void *ksym_tracer_stat_start(struct tracer_stat *trace)
+{
+ return ksym_filter_head.first;
+}
+
+static void *
+ksym_tracer_stat_next(void *v, int idx)
+{
+ struct hlist_node *stat = v;
+
+ return stat->next;
+}
+
+static struct tracer_stat ksym_tracer_stats = {
+ .name = "ksym_tracer",
+ .stat_start = ksym_tracer_stat_start,
+ .stat_next = ksym_tracer_stat_next,
+ .stat_headers = ksym_tracer_stat_headers,
+ .stat_show = ksym_tracer_stat_show
+};
+
+__init static int ksym_tracer_stat_init(void)
+{
+ int ret;
+
+ ret = register_stat_tracer(&ksym_tracer_stats);
+ if (ret) {
+ printk(KERN_WARNING "Warning: could not register "
+ "ksym tracer stats\n");
+ return 1;
+ }
+
+ return 0;
+}
+fs_initcall(ksym_tracer_stat_init);
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index f572f44c6e1..8e46b3323cd 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -23,13 +23,21 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
-void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+ int ret;
+
+ ret = seq_write(m, s->buffer, len);
- seq_write(m, s->buffer, len);
+ /*
+ * Only reset this buffer if we successfully wrote to the
+ * seq_file buffer.
+ */
+ if (!ret)
+ trace_seq_init(s);
- trace_seq_init(s);
+ return ret;
}
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
@@ -69,6 +77,9 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
* @s: trace sequence descriptor
* @fmt: printf format string
*
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
* The tracer may use either sequence operations or its own
* copy to user routines. To simplify formating of a trace
* trace_seq_printf is used to store strings into a special
@@ -82,7 +93,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
va_list ap;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
va_start(ap, fmt);
@@ -90,12 +101,14 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
va_end(ap);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
- return len;
+ return 1;
}
EXPORT_SYMBOL_GPL(trace_seq_printf);
@@ -116,14 +129,16 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
int len = (PAGE_SIZE - 1) - s->len;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
ret = vsnprintf(s->buffer + s->len, len, fmt, args);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
@@ -136,14 +151,16 @@ int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
int len = (PAGE_SIZE - 1) - s->len;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
@@ -164,9 +181,14 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
{
int len = strlen(str);
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
return 0;
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
+ return 0;
+ }
+
memcpy(s->buffer + s->len, str, len);
s->len += len;
@@ -175,9 +197,14 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
int trace_seq_putc(struct trace_seq *s, unsigned char c)
{
- if (s->len >= (PAGE_SIZE - 1))
+ if (s->full)
return 0;
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
+ return 0;
+ }
+
s->buffer[s->len++] = c;
return 1;
@@ -185,8 +212,13 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
{
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
return 0;
+ }
memcpy(s->buffer + s->len, mem, len);
s->len += len;
@@ -200,6 +232,9 @@ int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
const unsigned char *data = mem;
int i, j;
+ if (s->full)
+ return 0;
+
#ifdef __BIG_ENDIAN
for (i = 0, j = 0; i < len; i++) {
#else
@@ -217,8 +252,13 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
{
void *ret;
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
return NULL;
+ }
ret = s->buffer + s->len;
s->len += len;
@@ -230,8 +270,14 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
{
unsigned char *p;
- if (s->len >= (PAGE_SIZE - 1))
+ if (s->full)
+ return 0;
+
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
return 0;
+ }
+
p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
if (!IS_ERR(p)) {
p = mangle_path(s->buffer + s->len, p, "\n");
@@ -244,6 +290,7 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
return 1;
}
+ s->full = 1;
return 0;
}
@@ -370,6 +417,9 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
unsigned long vmstart = 0;
int ret = 1;
+ if (s->full)
+ return 0;
+
if (mm) {
const struct vm_area_struct *vma;
@@ -486,16 +536,18 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
hardirq ? 'h' : softirq ? 's' : '.'))
return 0;
- if (entry->lock_depth < 0)
- ret = trace_seq_putc(s, '.');
+ if (entry->preempt_count)
+ ret = trace_seq_printf(s, "%x", entry->preempt_count);
else
- ret = trace_seq_printf(s, "%d", entry->lock_depth);
+ ret = trace_seq_putc(s, '.');
+
if (!ret)
return 0;
- if (entry->preempt_count)
- return trace_seq_printf(s, "%x", entry->preempt_count);
- return trace_seq_putc(s, '.');
+ if (entry->lock_depth < 0)
+ return trace_seq_putc(s, '.');
+
+ return trace_seq_printf(s, "%d", entry->lock_depth);
}
static int
@@ -883,7 +935,7 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
trace_assign_type(field, iter->ent);
if (!S)
- task_state_char(field->prev_state);
+ S = task_state_char(field->prev_state);
T = task_state_char(field->next_state);
if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
field->prev_pid,
@@ -918,7 +970,7 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
trace_assign_type(field, iter->ent);
if (!S)
- task_state_char(field->prev_state);
+ S = task_state_char(field->prev_state);
T = task_state_char(field->next_state);
SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 26185d72767..0271742abb8 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -28,8 +28,8 @@ static int wakeup_current_cpu;
static unsigned wakeup_prio = -1;
static int wakeup_rt;
-static raw_spinlock_t wakeup_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t wakeup_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static void __wakeup_reset(struct trace_array *tr);
@@ -143,7 +143,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
goto out;
local_irq_save(flags);
- __raw_spin_lock(&wakeup_lock);
+ arch_spin_lock(&wakeup_lock);
/* We could race with grabbing wakeup_lock */
if (unlikely(!tracer_enabled || next != wakeup_task))
@@ -169,7 +169,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
out_unlock:
__wakeup_reset(wakeup_trace);
- __raw_spin_unlock(&wakeup_lock);
+ arch_spin_unlock(&wakeup_lock);
local_irq_restore(flags);
out:
atomic_dec(&wakeup_trace->data[cpu]->disabled);
@@ -193,9 +193,9 @@ static void wakeup_reset(struct trace_array *tr)
tracing_reset_online_cpus(tr);
local_irq_save(flags);
- __raw_spin_lock(&wakeup_lock);
+ arch_spin_lock(&wakeup_lock);
__wakeup_reset(tr);
- __raw_spin_unlock(&wakeup_lock);
+ arch_spin_unlock(&wakeup_lock);
local_irq_restore(flags);
}
@@ -225,7 +225,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
goto out;
/* interrupts should be off from try_to_wake_up */
- __raw_spin_lock(&wakeup_lock);
+ arch_spin_lock(&wakeup_lock);
/* check for races. */
if (!tracer_enabled || p->prio >= wakeup_prio)
@@ -255,7 +255,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
out_locked:
- __raw_spin_unlock(&wakeup_lock);
+ arch_spin_unlock(&wakeup_lock);
out:
atomic_dec(&wakeup_trace->data[cpu]->disabled);
}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index d2cdbabb4ea..280fea470d6 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
case TRACE_GRAPH_ENT:
case TRACE_GRAPH_RET:
case TRACE_HW_BRANCHES:
+ case TRACE_KSYM:
return 1;
}
return 0;
@@ -66,7 +67,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
/* Don't allow flipping of max traces now */
local_irq_save(flags);
- __raw_spin_lock(&ftrace_max_lock);
+ arch_spin_lock(&ftrace_max_lock);
cnt = ring_buffer_entries(tr->buffer);
@@ -84,7 +85,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
break;
}
tracing_on();
- __raw_spin_unlock(&ftrace_max_lock);
+ arch_spin_unlock(&ftrace_max_lock);
local_irq_restore(flags);
if (count)
@@ -808,3 +809,57 @@ trace_selftest_startup_hw_branches(struct tracer *trace,
return ret;
}
#endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ ksym_selftest_dummy = 0;
+ /* Register the read-write tracing request */
+
+ ret = process_new_ksym_entry("ksym_selftest_dummy",
+ HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+ (unsigned long)(&ksym_selftest_dummy));
+
+ if (ret < 0) {
+ printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+ goto ret_path;
+ }
+ /* Perform a read and a write operation over the dummy variable to
+ * trigger the tracer
+ */
+ if (ksym_selftest_dummy == 0)
+ ksym_selftest_dummy++;
+
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ /* read & write operations - one each is performed on the dummy variable
+ * triggering two entries in the trace buffer
+ */
+ if (!ret && count != 2) {
+ printk(KERN_CONT "Ksym tracer startup test failed");
+ ret = -1;
+ }
+
+ret_path:
+ return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 0f6facb050a..678a5120ee3 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -27,8 +27,8 @@ static struct stack_trace max_stack_trace = {
};
static unsigned long max_stack_size;
-static raw_spinlock_t max_stack_lock =
- (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t max_stack_lock =
+ (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
static int stack_trace_disabled __read_mostly;
static DEFINE_PER_CPU(int, trace_active);
@@ -54,7 +54,7 @@ static inline void check_stack(void)
return;
local_irq_save(flags);
- __raw_spin_lock(&max_stack_lock);
+ arch_spin_lock(&max_stack_lock);
/* a race could have already updated it */
if (this_size <= max_stack_size)
@@ -103,7 +103,7 @@ static inline void check_stack(void)
}
out:
- __raw_spin_unlock(&max_stack_lock);
+ arch_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
}
@@ -171,9 +171,9 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
return ret;
local_irq_save(flags);
- __raw_spin_lock(&max_stack_lock);
+ arch_spin_lock(&max_stack_lock);
*ptr = val;
- __raw_spin_unlock(&max_stack_lock);
+ arch_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
return count;
@@ -207,7 +207,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
local_irq_disable();
- __raw_spin_lock(&max_stack_lock);
+ arch_spin_lock(&max_stack_lock);
if (*pos == 0)
return SEQ_START_TOKEN;
@@ -217,7 +217,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
static void t_stop(struct seq_file *m, void *p)
{
- __raw_spin_unlock(&max_stack_lock);
+ arch_spin_unlock(&max_stack_lock);
local_irq_enable();
}
@@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = {
int
stack_trace_sysctl(struct ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
mutex_lock(&stack_sysctl_mutex);
- ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret || !write ||
(last_stack_tracer_enabled == !!stack_tracer_enabled))
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 9fbce6c9d2e..57501d90096 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -14,6 +14,43 @@ static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+ struct syscall_metadata *start;
+ struct syscall_metadata *stop;
+ char str[KSYM_SYMBOL_LEN];
+
+
+ start = (struct syscall_metadata *)__start_syscalls_metadata;
+ stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+ kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+ for ( ; start < stop; start++) {
+ /*
+ * Only compare after the "sys" prefix. Archs that use
+ * syscall wrappers may have syscalls symbols aliases prefixed
+ * with "SyS" instead of "sys", leading to an unwanted
+ * mismatch.
+ */
+ if (start->name && !strcmp(start->name + 3, str + 3))
+ return start;
+ }
+ return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+ if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+ return NULL;
+
+ return syscalls_metadata[nr];
+}
+
enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags)
{
@@ -30,7 +67,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
if (!entry)
goto end;
- if (entry->enter_id != ent->type) {
+ if (entry->enter_event->id != ent->type) {
WARN_ON_ONCE(1);
goto end;
}
@@ -85,7 +122,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
- if (entry->exit_id != ent->type) {
+ if (entry->exit_event->id != ent->type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
@@ -103,24 +140,19 @@ extern char *__bad_type_size(void);
#define SYSCALL_FIELD(type, name) \
sizeof(type) != sizeof(trace.name) ? \
__bad_type_size() : \
- #type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+ #type, #name, offsetof(typeof(trace), name), \
+ sizeof(trace.name), is_signed_type(type)
int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
{
int i;
- int nr;
int ret;
- struct syscall_metadata *entry;
+ struct syscall_metadata *entry = call->data;
struct syscall_trace_enter trace;
int offset = offsetof(struct syscall_trace_enter, args);
- nr = syscall_name_to_nr(call->data);
- entry = syscall_nr_to_meta(nr);
-
- if (!entry)
- return 0;
-
- ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+ ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n",
SYSCALL_FIELD(int, nr));
if (!ret)
return 0;
@@ -130,8 +162,10 @@ int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
entry->args[i]);
if (!ret)
return 0;
- ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
- sizeof(unsigned long));
+ ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
+ "\tsigned:%u;\n", offset,
+ sizeof(unsigned long),
+ is_signed_type(unsigned long));
if (!ret)
return 0;
offset += sizeof(unsigned long);
@@ -163,10 +197,12 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
struct syscall_trace_exit trace;
ret = trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n"
+ "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
+ "\tsigned:%u;\n",
SYSCALL_FIELD(int, nr),
- SYSCALL_FIELD(unsigned long, ret));
+ SYSCALL_FIELD(long, ret));
if (!ret)
return 0;
@@ -176,22 +212,19 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
int syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
- struct syscall_metadata *meta;
+ struct syscall_metadata *meta = call->data;
int ret;
- int nr;
int i;
int offset = offsetof(typeof(trace), args);
- nr = syscall_name_to_nr(call->data);
- meta = syscall_nr_to_meta(nr);
-
- if (!meta)
- return 0;
-
ret = trace_define_common_fields(call);
if (ret)
return ret;
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ if (ret)
+ return ret;
+
for (i = 0; i < meta->nb_args; i++) {
ret = trace_define_field(call, meta->types[i],
meta->args[i], offset,
@@ -212,7 +245,11 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
if (ret)
return ret;
- ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0,
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ if (ret)
+ return ret;
+
+ ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
FILTER_OTHER);
return ret;
@@ -239,8 +276,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
- event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
- size, 0, 0);
+ event = trace_current_buffer_lock_reserve(&buffer,
+ sys_data->enter_event->id, size, 0, 0);
if (!event)
return;
@@ -271,8 +308,8 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
if (!sys_data)
return;
- event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
- sizeof(*entry), 0, 0);
+ event = trace_current_buffer_lock_reserve(&buffer,
+ sys_data->exit_event->id, sizeof(*entry), 0, 0);
if (!event)
return;
@@ -285,14 +322,12 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-int reg_event_syscall_enter(void *ptr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
{
int ret = 0;
int num;
- char *name;
- name = (char *)ptr;
- num = syscall_name_to_nr(name);
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
@@ -309,13 +344,11 @@ int reg_event_syscall_enter(void *ptr)
return ret;
}
-void unreg_event_syscall_enter(void *ptr)
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
{
int num;
- char *name;
- name = (char *)ptr;
- num = syscall_name_to_nr(name);
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return;
mutex_lock(&syscall_trace_lock);
@@ -326,14 +359,12 @@ void unreg_event_syscall_enter(void *ptr)
mutex_unlock(&syscall_trace_lock);
}
-int reg_event_syscall_exit(void *ptr)
+int reg_event_syscall_exit(struct ftrace_event_call *call)
{
int ret = 0;
int num;
- char *name;
- name = (char *)ptr;
- num = syscall_name_to_nr(name);
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
@@ -350,13 +381,11 @@ int reg_event_syscall_exit(void *ptr)
return ret;
}
-void unreg_event_syscall_exit(void *ptr)
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
{
int num;
- char *name;
- name = (char *)ptr;
- num = syscall_name_to_nr(name);
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return;
mutex_lock(&syscall_trace_lock);
@@ -367,13 +396,44 @@ void unreg_event_syscall_exit(void *ptr)
mutex_unlock(&syscall_trace_lock);
}
-struct trace_event event_syscall_enter = {
- .trace = print_syscall_enter,
-};
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+ int id;
+
+ id = register_ftrace_event(call->event);
+ if (!id)
+ return -ENODEV;
+ call->id = id;
+ INIT_LIST_HEAD(&call->fields);
+ return 0;
+}
+
+int __init init_ftrace_syscalls(void)
+{
+ struct syscall_metadata *meta;
+ unsigned long addr;
+ int i;
+
+ syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+ NR_syscalls, GFP_KERNEL);
+ if (!syscalls_metadata) {
+ WARN_ON(1);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < NR_syscalls; i++) {
+ addr = arch_syscall_addr(i);
+ meta = find_syscall_meta(addr);
+ if (!meta)
+ continue;
+
+ meta->syscall_nr = i;
+ syscalls_metadata[i] = meta;
+ }
-struct trace_event event_syscall_exit = {
- .trace = print_syscall_exit,
-};
+ return 0;
+}
+core_initcall(init_ftrace_syscalls);
#ifdef CONFIG_EVENT_PROFILE
@@ -387,8 +447,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
unsigned long flags;
+ char *trace_buf;
char *raw_data;
int syscall_nr;
+ int rctx;
int size;
int cpu;
@@ -412,41 +474,42 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
/* Protect the per cpu buffer, begin the rcu read side */
local_irq_save(flags);
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
cpu = smp_processor_id();
- if (in_nmi())
- raw_data = rcu_dereference(trace_profile_buf_nmi);
- else
- raw_data = rcu_dereference(trace_profile_buf);
+ trace_buf = rcu_dereference(perf_trace_buf);
- if (!raw_data)
+ if (!trace_buf)
goto end;
- raw_data = per_cpu_ptr(raw_data, cpu);
+ raw_data = per_cpu_ptr(trace_buf, cpu);
/* zero the dead bytes from align to not leak stack to user */
*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
rec = (struct syscall_trace_enter *) raw_data;
tracing_generic_entry_update(&rec->ent, 0, 0);
- rec->ent.type = sys_data->enter_id;
+ rec->ent.type = sys_data->enter_event->id;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
+ perf_tp_event(sys_data->enter_event->id, 0, 1, rec, size);
end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
local_irq_restore(flags);
}
-int reg_prof_syscall_enter(char *name)
+int prof_sysenter_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
- num = syscall_name_to_nr(name);
- if (num < 0 || num >= NR_syscalls)
- return -ENOSYS;
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
if (!sys_prof_refcount_enter)
@@ -462,13 +525,11 @@ int reg_prof_syscall_enter(char *name)
return ret;
}
-void unreg_prof_syscall_enter(char *name)
+void prof_sysenter_disable(struct ftrace_event_call *call)
{
int num;
- num = syscall_name_to_nr(name);
- if (num < 0 || num >= NR_syscalls)
- return;
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
sys_prof_refcount_enter--;
@@ -484,7 +545,9 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
struct syscall_trace_exit *rec;
unsigned long flags;
int syscall_nr;
+ char *trace_buf;
char *raw_data;
+ int rctx;
int size;
int cpu;
@@ -510,17 +573,19 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
/* Protect the per cpu buffer, begin the rcu read side */
local_irq_save(flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
cpu = smp_processor_id();
- if (in_nmi())
- raw_data = rcu_dereference(trace_profile_buf_nmi);
- else
- raw_data = rcu_dereference(trace_profile_buf);
+ trace_buf = rcu_dereference(perf_trace_buf);
- if (!raw_data)
+ if (!trace_buf)
goto end;
- raw_data = per_cpu_ptr(raw_data, cpu);
+ raw_data = per_cpu_ptr(trace_buf, cpu);
/* zero the dead bytes from align to not leak stack to user */
*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
@@ -528,24 +593,24 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
rec = (struct syscall_trace_exit *)raw_data;
tracing_generic_entry_update(&rec->ent, 0, 0);
- rec->ent.type = sys_data->exit_id;
+ rec->ent.type = sys_data->exit_event->id;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
+ perf_tp_event(sys_data->exit_event->id, 0, 1, rec, size);
end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
local_irq_restore(flags);
}
-int reg_prof_syscall_exit(char *name)
+int prof_sysexit_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
- num = syscall_name_to_nr(name);
- if (num < 0 || num >= NR_syscalls)
- return -ENOSYS;
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
if (!sys_prof_refcount_exit)
@@ -561,13 +626,11 @@ int reg_prof_syscall_exit(char *name)
return ret;
}
-void unreg_prof_syscall_exit(char *name)
+void prof_sysexit_disable(struct ftrace_event_call *call)
{
int num;
- num = syscall_name_to_nr(name);
- if (num < 0 || num >= NR_syscalls)
- return;
+ num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
sys_prof_refcount_exit--;
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 0314501688b..419209893d8 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -4,7 +4,6 @@
*/
#include <linux/mm.h>
-#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c
new file mode 100644
index 00000000000..eb27fd3430a
--- /dev/null
+++ b/kernel/user-return-notifier.c
@@ -0,0 +1,44 @@
+
+#include <linux/user-return-notifier.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
+
+/*
+ * Request a notification when the current cpu returns to userspace. Must be
+ * called in atomic context. The notifier will also be called in atomic
+ * context.
+ */
+void user_return_notifier_register(struct user_return_notifier *urn)
+{
+ set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+ hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list));
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_register);
+
+/*
+ * Removes a registered user return notifier. Must be called from atomic
+ * context, and from the same cpu registration occured in.
+ */
+void user_return_notifier_unregister(struct user_return_notifier *urn)
+{
+ hlist_del(&urn->link);
+ if (hlist_empty(&__get_cpu_var(return_notifier_list)))
+ clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
+
+/* Calls registered user return notifiers */
+void fire_user_return_notifiers(void)
+{
+ struct user_return_notifier *urn;
+ struct hlist_node *tmp1, *tmp2;
+ struct hlist_head *head;
+
+ head = &get_cpu_var(return_notifier_list);
+ hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link)
+ urn->on_user_return(urn);
+ put_cpu_var(return_notifier_list);
+}
diff --git a/kernel/user.c b/kernel/user.c
index 2c000e7132a..46d0165ca70 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -330,9 +330,9 @@ done:
*/
static void free_user(struct user_struct *up, unsigned long flags)
{
- spin_unlock_irqrestore(&uidhash_lock, flags);
INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
+ spin_unlock_irqrestore(&uidhash_lock, flags);
}
#else /* CONFIG_USER_SCHED && CONFIG_SYSFS */
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 92359cc747a..a2cd77e70d4 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which)
* Special case of dostring for the UTS structure. This has locks
* to observe. Should this be in kernel/sys.c ????
*/
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+static int proc_do_uts_string(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table uts_table;
int r;
memcpy(&uts_table, table, sizeof(uts_table));
uts_table.data = get_uts(table, write);
- r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos);
+ r = proc_dostring(&uts_table,write,buffer,lenp, ppos);
put_uts(table, write, uts_table.data);
return r;
}
@@ -57,78 +57,47 @@ static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
#define proc_do_uts_string NULL
#endif
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-/* The generic string strategy routine: */
-static int sysctl_uts_string(ctl_table *table,
- void __user *oldval, size_t __user *oldlenp,
- void __user *newval, size_t newlen)
-{
- struct ctl_table uts_table;
- int r, write;
- write = newval && newlen;
- memcpy(&uts_table, table, sizeof(uts_table));
- uts_table.data = get_uts(table, write);
- r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen);
- put_uts(table, write, uts_table.data);
- return r;
-}
-#else
-#define sysctl_uts_string NULL
-#endif
-
static struct ctl_table uts_kern_table[] = {
{
- .ctl_name = KERN_OSTYPE,
.procname = "ostype",
.data = init_uts_ns.name.sysname,
.maxlen = sizeof(init_uts_ns.name.sysname),
.mode = 0444,
.proc_handler = proc_do_uts_string,
- .strategy = sysctl_uts_string,
},
{
- .ctl_name = KERN_OSRELEASE,
.procname = "osrelease",
.data = init_uts_ns.name.release,
.maxlen = sizeof(init_uts_ns.name.release),
.mode = 0444,
.proc_handler = proc_do_uts_string,
- .strategy = sysctl_uts_string,
},
{
- .ctl_name = KERN_VERSION,
.procname = "version",
.data = init_uts_ns.name.version,
.maxlen = sizeof(init_uts_ns.name.version),
.mode = 0444,
.proc_handler = proc_do_uts_string,
- .strategy = sysctl_uts_string,
},
{
- .ctl_name = KERN_NODENAME,
.procname = "hostname",
.data = init_uts_ns.name.nodename,
.maxlen = sizeof(init_uts_ns.name.nodename),
.mode = 0644,
.proc_handler = proc_do_uts_string,
- .strategy = sysctl_uts_string,
},
{
- .ctl_name = KERN_DOMAINNAME,
.procname = "domainname",
.data = init_uts_ns.name.domainname,
.maxlen = sizeof(init_uts_ns.name.domainname),
.mode = 0644,
.proc_handler = proc_do_uts_string,
- .strategy = sysctl_uts_string,
},
{}
};
static struct ctl_table uts_root_table[] = {
{
- .ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
.child = uts_kern_table,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index addfe2df93b..dee48658805 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,116 @@ struct workqueue_struct {
#endif
};
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+
+static struct debug_obj_descr work_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int work_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_init(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int work_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. The work struct was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
+ debug_object_init(work, &work_debug_descr);
+ debug_object_activate(work, &work_debug_descr);
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int work_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_free(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr work_debug_descr = {
+ .name = "work_struct",
+ .fixup_init = work_fixup_init,
+ .fixup_activate = work_fixup_activate,
+ .fixup_free = work_fixup_free,
+};
+
+static inline void debug_work_activate(struct work_struct *work)
+{
+ debug_object_activate(work, &work_debug_descr);
+}
+
+static inline void debug_work_deactivate(struct work_struct *work)
+{
+ debug_object_deactivate(work, &work_debug_descr);
+}
+
+void __init_work(struct work_struct *work, int onstack)
+{
+ if (onstack)
+ debug_object_init_on_stack(work, &work_debug_descr);
+ else
+ debug_object_init(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(__init_work);
+
+void destroy_work_on_stack(struct work_struct *work)
+{
+ debug_object_free(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+
+#else
+static inline void debug_work_activate(struct work_struct *work) { }
+static inline void debug_work_deactivate(struct work_struct *work) { }
+#endif
+
/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
@@ -145,6 +255,7 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
{
unsigned long flags;
+ debug_work_activate(work);
spin_lock_irqsave(&cwq->lock, flags);
insert_work(cwq, work, &cwq->worklist);
spin_unlock_irqrestore(&cwq->lock, flags);
@@ -280,6 +391,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
struct lockdep_map lockdep_map = work->lockdep_map;
#endif
trace_workqueue_execution(cwq->thread, work);
+ debug_work_deactivate(work);
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
@@ -350,11 +462,18 @@ static void wq_barrier_func(struct work_struct *work)
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
struct wq_barrier *barr, struct list_head *head)
{
- INIT_WORK(&barr->work, wq_barrier_func);
+ /*
+ * debugobject calls are safe here even with cwq->lock locked
+ * as we know for sure that this will not trigger any of the
+ * checks and call back into the fixup functions where we
+ * might deadlock.
+ */
+ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
init_completion(&barr->done);
+ debug_work_activate(&barr->work);
insert_work(cwq, &barr->work, head);
}
@@ -372,8 +491,10 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
}
spin_unlock_irq(&cwq->lock);
- if (active)
+ if (active) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
return active;
}
@@ -451,6 +572,7 @@ out:
return 0;
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
return 1;
}
EXPORT_SYMBOL_GPL(flush_work);
@@ -485,6 +607,7 @@ static int try_to_grab_pending(struct work_struct *work)
*/
smp_rmb();
if (cwq == get_wq_data(work)) {
+ debug_work_deactivate(work);
list_del_init(&work->entry);
ret = 1;
}
@@ -507,8 +630,10 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
}
spin_unlock_irq(&cwq->lock);
- if (unlikely(running))
+ if (unlikely(running)) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
}
static void wait_on_work(struct work_struct *work)
@@ -640,6 +765,24 @@ int schedule_delayed_work(struct delayed_work *dwork,
EXPORT_SYMBOL(schedule_delayed_work);
/**
+ * flush_delayed_work - block until a dwork_struct's callback has terminated
+ * @dwork: the delayed work which is to be flushed
+ *
+ * Any timeout is cancelled, and any pending work is run immediately.
+ */
+void flush_delayed_work(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer)) {
+ struct cpu_workqueue_struct *cwq;
+ cwq = wq_per_cpu(keventd_wq, get_cpu());
+ __queue_work(cwq, &dwork->work);
+ put_cpu();
+ }
+ flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
@@ -667,6 +810,7 @@ EXPORT_SYMBOL(schedule_delayed_work_on);
int schedule_on_each_cpu(work_func_t func)
{
int cpu;
+ int orig = -1;
struct work_struct *works;
works = alloc_percpu(struct work_struct);
@@ -674,14 +818,28 @@ int schedule_on_each_cpu(work_func_t func)
return -ENOMEM;
get_online_cpus();
+
+ /*
+ * When running in keventd don't schedule a work item on
+ * itself. Can just call directly because the work queue is
+ * already bound. This also is faster.
+ */
+ if (current_is_keventd())
+ orig = raw_smp_processor_id();
+
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
- schedule_work_on(cpu, work);
+ if (cpu != orig)
+ schedule_work_on(cpu, work);
}
+ if (orig >= 0)
+ func(per_cpu_ptr(works, orig));
+
for_each_online_cpu(cpu)
flush_work(per_cpu_ptr(works, cpu));
+
put_online_cpus();
free_percpu(works);
return 0;