aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/auditsc.c8
-rw-r--r--kernel/compat.c63
-rw-r--r--kernel/cpu.c13
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/fork.c75
-rw-r--r--kernel/hung_task.c4
-rw-r--r--kernel/irq/chip.c1
-rw-r--r--kernel/irq/debug.h38
-rw-r--r--kernel/irq/irqdesc.c1
-rw-r--r--kernel/power/swap.c28
-rw-r--r--kernel/rcupdate.c28
-rw-r--r--kernel/rcutiny_plugin.h16
-rw-r--r--kernel/rcutorture.c257
-rw-r--r--kernel/rcutree.c333
-rw-r--r--kernel/rcutree.h23
-rw-r--r--kernel/rcutree_plugin.h154
-rw-r--r--kernel/rcutree_trace.c4
-rw-r--r--kernel/sched/Makefile2
-rw-r--r--kernel/sched/core.c27
-rw-r--r--kernel/sched/fair.c18
-rw-r--r--kernel/sched/features.h1
-rw-r--r--kernel/seccomp.c458
-rw-r--r--kernel/signal.c9
-rw-r--r--kernel/smp.c27
-rw-r--r--kernel/smpboot.c62
-rw-r--r--kernel/smpboot.h18
-rw-r--r--kernel/srcu.c548
-rw-r--r--kernel/sys.c12
-rw-r--r--kernel/time/tick-broadcast.c13
-rw-r--r--kernel/timer.c8
-rw-r--r--kernel/trace/trace.c8
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_events.c5
-rw-r--r--kernel/trace/trace_export.c1
-rw-r--r--kernel/trace/trace_output.c5
36 files changed, 1857 insertions, 418 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index cb41b9547c9..6c07f30fa9b 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += smpboot.o
ifneq ($(CONFIG_SMP),y)
obj-y += up.o
endif
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index af1de0f34ea..4b96415527b 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -67,6 +67,7 @@
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/fs_struct.h>
+#include <linux/compat.h>
#include "audit.h"
@@ -2710,13 +2711,16 @@ void audit_core_dumps(long signr)
audit_log_end(ab);
}
-void __audit_seccomp(unsigned long syscall)
+void __audit_seccomp(unsigned long syscall, long signr, int code)
{
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
- audit_log_abend(ab, "seccomp", SIGKILL);
+ audit_log_abend(ab, "seccomp", signr);
audit_log_format(ab, " syscall=%ld", syscall);
+ audit_log_format(ab, " compat=%d", is_compat_task());
+ audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));
+ audit_log_format(ab, " code=0x%x", code);
audit_log_end(ab);
}
diff --git a/kernel/compat.c b/kernel/compat.c
index 74ff8498809..d2c67aa49ae 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -372,25 +372,54 @@ asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
#ifdef __ARCH_WANT_SYS_SIGPROCMASK
-asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set,
- compat_old_sigset_t __user *oset)
+/*
+ * sys_sigprocmask SIG_SETMASK sets the first (compat) word of the
+ * blocked set of signals to the supplied signal set
+ */
+static inline void compat_sig_setmask(sigset_t *blocked, compat_sigset_word set)
{
- old_sigset_t s;
- long ret;
- mm_segment_t old_fs;
+ memcpy(blocked->sig, &set, sizeof(set));
+}
- if (set && get_user(s, set))
- return -EFAULT;
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- ret = sys_sigprocmask(how,
- set ? (old_sigset_t __user *) &s : NULL,
- oset ? (old_sigset_t __user *) &s : NULL);
- set_fs(old_fs);
- if (ret == 0)
- if (oset)
- ret = put_user(s, oset);
- return ret;
+asmlinkage long compat_sys_sigprocmask(int how,
+ compat_old_sigset_t __user *nset,
+ compat_old_sigset_t __user *oset)
+{
+ old_sigset_t old_set, new_set;
+ sigset_t new_blocked;
+
+ old_set = current->blocked.sig[0];
+
+ if (nset) {
+ if (get_user(new_set, nset))
+ return -EFAULT;
+ new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP));
+
+ new_blocked = current->blocked;
+
+ switch (how) {
+ case SIG_BLOCK:
+ sigaddsetmask(&new_blocked, new_set);
+ break;
+ case SIG_UNBLOCK:
+ sigdelsetmask(&new_blocked, new_set);
+ break;
+ case SIG_SETMASK:
+ compat_sig_setmask(&new_blocked, new_set);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ set_current_blocked(&new_blocked);
+ }
+
+ if (oset) {
+ if (put_user(old_set, oset))
+ return -EFAULT;
+ }
+
+ return 0;
}
#endif
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2060c6e5702..0e6353cf147 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -17,6 +17,8 @@
#include <linux/gfp.h>
#include <linux/suspend.h>
+#include "smpboot.h"
+
#ifdef CONFIG_SMP
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
@@ -295,11 +297,19 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
int ret, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+ struct task_struct *idle;
if (cpu_online(cpu) || !cpu_present(cpu))
return -EINVAL;
cpu_hotplug_begin();
+
+ idle = idle_thread_get(cpu);
+ if (IS_ERR(idle)) {
+ ret = PTR_ERR(idle);
+ goto out;
+ }
+
ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
if (ret) {
nr_calls--;
@@ -309,7 +319,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
}
/* Arch-specific enabling code. */
- ret = __cpu_up(cpu);
+ ret = __cpu_up(cpu, idle);
if (ret != 0)
goto out_notify;
BUG_ON(!cpu_online(cpu));
@@ -320,6 +330,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
out_notify:
if (ret != 0)
__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+out:
cpu_hotplug_done();
return ret;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4cd8f..fd126f82b57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3183,7 +3183,7 @@ static void perf_event_for_each(struct perf_event *event,
perf_event_for_each_child(event, func);
func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
- perf_event_for_each_child(event, func);
+ perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index b9372a0bff1..ad54c833116 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -34,6 +34,7 @@
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
+#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
@@ -47,6 +48,7 @@
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
+#include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
@@ -111,32 +113,67 @@ int nr_processes(void)
return total;
}
-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct_node(node) \
- kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node)
-# define free_task_struct(tsk) \
- kmem_cache_free(task_struct_cachep, (tsk))
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;
+
+static inline struct task_struct *alloc_task_struct_node(int node)
+{
+ return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
+}
+
+void __weak arch_release_task_struct(struct task_struct *tsk) { }
+
+static inline void free_task_struct(struct task_struct *tsk)
+{
+ arch_release_task_struct(tsk);
+ kmem_cache_free(task_struct_cachep, tsk);
+}
#endif
-#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+void __weak arch_release_thread_info(struct thread_info *ti) { }
+
+/*
+ * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
+ * kmemcache based allocator.
+ */
+# if THREAD_SIZE >= PAGE_SIZE
static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
int node)
{
-#ifdef CONFIG_DEBUG_STACK_USAGE
- gfp_t mask = GFP_KERNEL | __GFP_ZERO;
-#else
- gfp_t mask = GFP_KERNEL;
-#endif
- struct page *page = alloc_pages_node(node, mask, THREAD_SIZE_ORDER);
+ struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+ THREAD_SIZE_ORDER);
return page ? page_address(page) : NULL;
}
static inline void free_thread_info(struct thread_info *ti)
{
+ arch_release_thread_info(ti);
free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
}
+# else
+static struct kmem_cache *thread_info_cache;
+
+static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+ int node)
+{
+ return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+}
+
+static void free_thread_info(struct thread_info *ti)
+{
+ arch_release_thread_info(ti);
+ kmem_cache_free(thread_info_cache, ti);
+}
+
+void thread_info_cache_init(void)
+{
+ thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ THREAD_SIZE, 0, NULL);
+ BUG_ON(thread_info_cache == NULL);
+}
+# endif
#endif
/* SLAB cache for signal_struct structures (tsk->signal) */
@@ -170,6 +207,7 @@ void free_task(struct task_struct *tsk)
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
+ put_seccomp_filter(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -203,17 +241,11 @@ void __put_task_struct(struct task_struct *tsk)
}
EXPORT_SYMBOL_GPL(__put_task_struct);
-/*
- * macro override instead of weak attribute alias, to workaround
- * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
- */
-#ifndef arch_task_cache_init
-#define arch_task_cache_init()
-#endif
+void __init __weak arch_task_cache_init(void) { }
void __init fork_init(unsigned long mempages)
{
-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES
#endif
@@ -1162,6 +1194,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
ftrace_graph_init_task(p);
+ get_seccomp_filter(p);
rt_mutex_init_task(p);
@@ -1464,6 +1497,8 @@ bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
+ if (unlikely(clone_flags & CLONE_NEWPID))
+ pid_ns_release_proc(p->nsproxy->pid_ns);
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm)
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index c21449f85a2..6df614912b9 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -108,8 +108,10 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
touch_nmi_watchdog();
- if (sysctl_hung_task_panic)
+ if (sysctl_hung_task_panic) {
+ trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
+ }
}
/*
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 741f83643da..fc275e4f629 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -520,6 +520,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
out_unlock:
raw_spin_unlock(&desc->lock);
}
+EXPORT_SYMBOL(handle_edge_irq);
#ifdef CONFIG_IRQ_EDGE_EOI_HANDLER
/**
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 97a8bfadc88..e75e29e4434 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -4,10 +4,10 @@
#include <linux/kallsyms.h>
-#define P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
-#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
+#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f)
/* FIXME */
-#define PD(f) do { } while (0)
+#define ___PD(f) do { } while (0)
static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
{
@@ -23,23 +23,23 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
print_symbol("%s\n", (unsigned long)desc->action->handler);
}
- P(IRQ_LEVEL);
- P(IRQ_PER_CPU);
- P(IRQ_NOPROBE);
- P(IRQ_NOREQUEST);
- P(IRQ_NOTHREAD);
- P(IRQ_NOAUTOEN);
+ ___P(IRQ_LEVEL);
+ ___P(IRQ_PER_CPU);
+ ___P(IRQ_NOPROBE);
+ ___P(IRQ_NOREQUEST);
+ ___P(IRQ_NOTHREAD);
+ ___P(IRQ_NOAUTOEN);
- PS(IRQS_AUTODETECT);
- PS(IRQS_REPLAY);
- PS(IRQS_WAITING);
- PS(IRQS_PENDING);
+ ___PS(IRQS_AUTODETECT);
+ ___PS(IRQS_REPLAY);
+ ___PS(IRQS_WAITING);
+ ___PS(IRQS_PENDING);
- PD(IRQS_INPROGRESS);
- PD(IRQS_DISABLED);
- PD(IRQS_MASKED);
+ ___PD(IRQS_INPROGRESS);
+ ___PD(IRQS_DISABLED);
+ ___PD(IRQS_MASKED);
}
-#undef P
-#undef PS
-#undef PD
+#undef ___P
+#undef ___PS
+#undef ___PD
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index d86e254b95e..192a302d6cf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -112,6 +112,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
{
return radix_tree_lookup(&irq_desc_tree, irq);
}
+EXPORT_SYMBOL(irq_to_desc);
static void delete_irq_desc(unsigned int irq)
{
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8742fd013a9..eef311a58a6 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -51,6 +51,23 @@
#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
+/*
+ * Number of free pages that are not high.
+ */
+static inline unsigned long low_free_pages(void)
+{
+ return nr_free_pages() - nr_free_highpages();
+}
+
+/*
+ * Number of pages required to be kept free while writing the image. Always
+ * half of all available low pages before the writing starts.
+ */
+static inline unsigned long reqd_free_pages(void)
+{
+ return low_free_pages() / 2;
+}
+
struct swap_map_page {
sector_t entries[MAP_PAGE_ENTRIES];
sector_t next_swap;
@@ -72,7 +89,7 @@ struct swap_map_handle {
sector_t cur_swap;
sector_t first_sector;
unsigned int k;
- unsigned long nr_free_pages, written;
+ unsigned long reqd_free_pages;
u32 crc32;
};
@@ -316,8 +333,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
goto err_rel;
}
handle->k = 0;
- handle->nr_free_pages = nr_free_pages() >> 1;
- handle->written = 0;
+ handle->reqd_free_pages = reqd_free_pages();
handle->first_sector = handle->cur_swap;
return 0;
err_rel:
@@ -352,11 +368,11 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
handle->cur_swap = offset;
handle->k = 0;
}
- if (bio_chain && ++handle->written > handle->nr_free_pages) {
+ if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
error = hib_wait_on_bio_chain(bio_chain);
if (error)
goto out;
- handle->written = 0;
+ handle->reqd_free_pages = reqd_free_pages();
}
out:
return error;
@@ -618,7 +634,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
* Adjust number of free pages after all allocations have been done.
* We don't want to run out of pages when writing.
*/
- handle->nr_free_pages = nr_free_pages() >> 1;
+ handle->reqd_free_pages = reqd_free_pages();
/*
* Start the CRC32 thread.
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a86f1741cc2..95cba41ce1e 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -51,6 +51,34 @@
#include "rcu.h"
+#ifdef CONFIG_PREEMPT_RCU
+
+/*
+ * Check for a task exiting while in a preemptible-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
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+ struct task_struct *t = current;
+
+ if (likely(list_empty(&current->rcu_node_entry)))
+ return;
+ t->rcu_read_lock_nesting = 1;
+ barrier();
+ t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+ __rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+void exit_rcu(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
struct lockdep_map rcu_lock_map =
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 22ecea0dfb6..fc31a2d6510 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -851,22 +851,6 @@ int rcu_preempt_needs_cpu(void)
return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
}
-/*
- * Check for a task exiting while in a preemptible -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
- * is enabled.
- */
-void exit_rcu(void)
-{
- struct task_struct *t = current;
-
- if (t->rcu_read_lock_nesting == 0)
- return;
- t->rcu_read_lock_nesting = 1;
- __rcu_read_unlock();
-}
-
#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
#ifdef CONFIG_RCU_TRACE
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index a89b381a8c6..e66b34ab755 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -64,6 +64,7 @@ static int irqreader = 1; /* RCU readers from irq (timers). */
static int fqs_duration; /* Duration of bursts (us), 0 to disable. */
static int fqs_holdoff; /* Hold time within burst (us). */
static int fqs_stutter = 3; /* Wait time between bursts (s). */
+static int n_barrier_cbs; /* Number of callbacks to test RCU barriers. */
static int onoff_interval; /* Wait time between CPU hotplugs, 0=disable. */
static int onoff_holdoff; /* Seconds after boot before CPU hotplugs. */
static int shutdown_secs; /* Shutdown time (s). <=0 for no shutdown. */
@@ -96,6 +97,8 @@ module_param(fqs_holdoff, int, 0444);
MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
module_param(fqs_stutter, int, 0444);
MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(n_barrier_cbs, int, 0444);
+MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
module_param(onoff_interval, int, 0444);
MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
module_param(onoff_holdoff, int, 0444);
@@ -139,6 +142,8 @@ static struct task_struct *shutdown_task;
static struct task_struct *onoff_task;
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static struct task_struct *stall_task;
+static struct task_struct **barrier_cbs_tasks;
+static struct task_struct *barrier_task;
#define RCU_TORTURE_PIPE_LEN 10
@@ -164,6 +169,7 @@ static atomic_t n_rcu_torture_alloc_fail;
static atomic_t n_rcu_torture_free;
static atomic_t n_rcu_torture_mberror;
static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_barrier_error;
static long n_rcu_torture_boost_ktrerror;
static long n_rcu_torture_boost_rterror;
static long n_rcu_torture_boost_failure;
@@ -173,6 +179,8 @@ static long n_offline_attempts;
static long n_offline_successes;
static long n_online_attempts;
static long n_online_successes;
+static long n_barrier_attempts;
+static long n_barrier_successes;
static struct list_head rcu_torture_removed;
static cpumask_var_t shuffle_tmp_mask;
@@ -197,6 +205,10 @@ static unsigned long shutdown_time; /* jiffies to system shutdown. */
static unsigned long boost_starttime; /* jiffies of next boost test start. */
DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
/* and boost task create/destroy. */
+static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */
+static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */
+static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
+static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
@@ -327,6 +339,7 @@ struct rcu_torture_ops {
int (*completed)(void);
void (*deferred_free)(struct rcu_torture *p);
void (*sync)(void);
+ void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
void (*cb_barrier)(void);
void (*fqs)(void);
int (*stats)(char *page);
@@ -417,6 +430,7 @@ static struct rcu_torture_ops rcu_ops = {
.completed = rcu_torture_completed,
.deferred_free = rcu_torture_deferred_free,
.sync = synchronize_rcu,
+ .call = call_rcu,
.cb_barrier = rcu_barrier,
.fqs = rcu_force_quiescent_state,
.stats = NULL,
@@ -460,6 +474,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
.completed = rcu_torture_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_rcu,
+ .call = NULL,
.cb_barrier = NULL,
.fqs = rcu_force_quiescent_state,
.stats = NULL,
@@ -477,6 +492,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
.completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_rcu_expedited,
+ .call = NULL,
.cb_barrier = NULL,
.fqs = rcu_force_quiescent_state,
.stats = NULL,
@@ -519,6 +535,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
.completed = rcu_bh_torture_completed,
.deferred_free = rcu_bh_torture_deferred_free,
.sync = synchronize_rcu_bh,
+ .call = call_rcu_bh,
.cb_barrier = rcu_barrier_bh,
.fqs = rcu_bh_force_quiescent_state,
.stats = NULL,
@@ -535,6 +552,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
.completed = rcu_bh_torture_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_rcu_bh,
+ .call = NULL,
.cb_barrier = NULL,
.fqs = rcu_bh_force_quiescent_state,
.stats = NULL,
@@ -551,6 +569,7 @@ static struct rcu_torture_ops rcu_bh_expedited_ops = {
.completed = rcu_bh_torture_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_rcu_bh_expedited,
+ .call = NULL,
.cb_barrier = NULL,
.fqs = rcu_bh_force_quiescent_state,
.stats = NULL,
@@ -606,6 +625,11 @@ static int srcu_torture_completed(void)
return srcu_batches_completed(&srcu_ctl);
}
+static void srcu_torture_deferred_free(struct rcu_torture *rp)
+{
+ call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+}
+
static void srcu_torture_synchronize(void)
{
synchronize_srcu(&srcu_ctl);
@@ -620,7 +644,7 @@ static int srcu_torture_stats(char *page)
cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
- cnt += sprintf(&page[cnt], " %d(%d,%d)", cpu,
+ cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
}
@@ -635,13 +659,29 @@ static struct rcu_torture_ops srcu_ops = {
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock,
.completed = srcu_torture_completed,
- .deferred_free = rcu_sync_torture_deferred_free,
+ .deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
+ .call = NULL,
.cb_barrier = NULL,
.stats = srcu_torture_stats,
.name = "srcu"
};
+static struct rcu_torture_ops srcu_sync_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,
+ .call = NULL,
+ .cb_barrier = NULL,
+ .stats = srcu_torture_stats,
+ .name = "srcu_sync"
+};
+
static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl)
{
return srcu_read_lock_raw(&srcu_ctl);
@@ -659,13 +699,29 @@ static struct rcu_torture_ops srcu_raw_ops = {
.read_delay = srcu_read_delay,
.readunlock = srcu_torture_read_unlock_raw,
.completed = srcu_torture_completed,
- .deferred_free = rcu_sync_torture_deferred_free,
+ .deferred_free = srcu_torture_deferred_free,
.sync = srcu_torture_synchronize,
+ .call = NULL,
.cb_barrier = NULL,
.stats = srcu_torture_stats,
.name = "srcu_raw"
};
+static struct rcu_torture_ops srcu_raw_sync_ops = {
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock_raw,
+ .read_delay = srcu_read_delay,
+ .readunlock = srcu_torture_read_unlock_raw,
+ .completed = srcu_torture_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = srcu_torture_synchronize,
+ .call = NULL,
+ .cb_barrier = NULL,
+ .stats = srcu_torture_stats,
+ .name = "srcu_raw_sync"
+};
+
static void srcu_torture_synchronize_expedited(void)
{
synchronize_srcu_expedited(&srcu_ctl);
@@ -680,6 +736,7 @@ static struct rcu_torture_ops srcu_expedited_ops = {
.completed = srcu_torture_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = srcu_torture_synchronize_expedited,
+ .call = NULL,
.cb_barrier = NULL,
.stats = srcu_torture_stats,
.name = "srcu_expedited"
@@ -1129,7 +1186,8 @@ rcu_torture_printk(char *page)
"rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
"rtmbe: %d rtbke: %ld rtbre: %ld "
"rtbf: %ld rtb: %ld nt: %ld "
- "onoff: %ld/%ld:%ld/%ld",
+ "onoff: %ld/%ld:%ld/%ld "
+ "barrier: %ld/%ld:%ld",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
@@ -1145,14 +1203,17 @@ rcu_torture_printk(char *page)
n_online_successes,
n_online_attempts,
n_offline_successes,
- n_offline_attempts);
+ n_offline_attempts,
+ n_barrier_successes,
+ n_barrier_attempts,
+ n_rcu_torture_barrier_error);
+ cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
+ n_rcu_torture_barrier_error != 0 ||
n_rcu_torture_boost_ktrerror != 0 ||
n_rcu_torture_boost_rterror != 0 ||
- n_rcu_torture_boost_failure != 0)
- cnt += sprintf(&page[cnt], " !!!");
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- if (i > 1) {
+ n_rcu_torture_boost_failure != 0 ||
+ i > 1) {
cnt += sprintf(&page[cnt], "!!! ");
atomic_inc(&n_rcu_torture_error);
WARN_ON_ONCE(1);
@@ -1337,6 +1398,7 @@ static void rcutorture_booster_cleanup(int cpu)
/* This must be outside of the mutex, otherwise deadlock! */
kthread_stop(t);
+ boost_tasks[cpu] = NULL;
}
static int rcutorture_booster_init(int cpu)
@@ -1484,13 +1546,15 @@ static void rcu_torture_onoff_cleanup(void)
return;
VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
kthread_stop(onoff_task);
+ onoff_task = NULL;
}
#else /* #ifdef CONFIG_HOTPLUG_CPU */
-static void
+static int
rcu_torture_onoff_init(void)
{
+ return 0;
}
static void rcu_torture_onoff_cleanup(void)
@@ -1554,6 +1618,152 @@ static void rcu_torture_stall_cleanup(void)
return;
VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task.");
kthread_stop(stall_task);
+ stall_task = NULL;
+}
+
+/* Callback function for RCU barrier testing. */
+void rcu_torture_barrier_cbf(struct rcu_head *rcu)
+{
+ atomic_inc(&barrier_cbs_invoked);
+}
+
+/* kthread function to register callbacks used to test RCU barriers. */
+static int rcu_torture_barrier_cbs(void *arg)
+{
+ long myid = (long)arg;
+ struct rcu_head rcu;
+
+ init_rcu_head_on_stack(&rcu);
+ VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started");
+ set_user_nice(current, 19);
+ do {
+ wait_event(barrier_cbs_wq[myid],
+ atomic_read(&barrier_cbs_count) == n_barrier_cbs ||
+ kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP);
+ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+ break;
+ cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+ if (atomic_dec_and_test(&barrier_cbs_count))
+ wake_up(&barrier_wq);
+ } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+ VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping");
+ rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
+ while (!kthread_should_stop())
+ schedule_timeout_interruptible(1);
+ cur_ops->cb_barrier();
+ destroy_rcu_head_on_stack(&rcu);
+ return 0;
+}
+
+/* kthread function to drive and coordinate RCU barrier testing. */
+static int rcu_torture_barrier(void *arg)
+{
+ int i;
+
+ VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting");
+ do {
+ atomic_set(&barrier_cbs_invoked, 0);
+ atomic_set(&barrier_cbs_count, n_barrier_cbs);
+ /* wake_up() path contains the required barriers. */
+ for (i = 0; i < n_barrier_cbs; i++)
+ wake_up(&barrier_cbs_wq[i]);
+ wait_event(barrier_wq,
+ atomic_read(&barrier_cbs_count) == 0 ||
+ kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP);
+ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+ break;
+ n_barrier_attempts++;
+ cur_ops->cb_barrier();
+ if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
+ n_rcu_torture_barrier_error++;
+ WARN_ON_ONCE(1);
+ }
+ n_barrier_successes++;
+ schedule_timeout_interruptible(HZ / 10);
+ } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+ VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
+ rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
+ while (!kthread_should_stop())
+ schedule_timeout_interruptible(1);
+ return 0;
+}
+
+/* Initialize RCU barrier testing. */
+static int rcu_torture_barrier_init(void)
+{
+ int i;
+ int ret;
+
+ if (n_barrier_cbs == 0)
+ return 0;
+ if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
+ printk(KERN_ALERT "%s" TORTURE_FLAG
+ " Call or barrier ops missing for %s,\n",
+ torture_type, cur_ops->name);
+ printk(KERN_ALERT "%s" TORTURE_FLAG
+ " RCU barrier testing omitted from run.\n",
+ torture_type);
+ return 0;
+ }
+ atomic_set(&barrier_cbs_count, 0);
+ atomic_set(&barrier_cbs_invoked, 0);
+ barrier_cbs_tasks =
+ kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]),
+ GFP_KERNEL);
+ barrier_cbs_wq =
+ kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
+ GFP_KERNEL);
+ if (barrier_cbs_tasks == NULL || barrier_cbs_wq == 0)
+ return -ENOMEM;
+ for (i = 0; i < n_barrier_cbs; i++) {
+ init_waitqueue_head(&barrier_cbs_wq[i]);
+ barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs,
+ (void *)(long)i,
+ "rcu_torture_barrier_cbs");
+ if (IS_ERR(barrier_cbs_tasks[i])) {
+ ret = PTR_ERR(barrier_cbs_tasks[i]);
+ VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs");
+ barrier_cbs_tasks[i] = NULL;
+ return ret;
+ }
+ }
+ barrier_task = kthread_run(rcu_torture_barrier, NULL,
+ "rcu_torture_barrier");
+ if (IS_ERR(barrier_task)) {
+ ret = PTR_ERR(barrier_task);
+ VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier");
+ barrier_task = NULL;
+ }
+ return 0;
+}
+
+/* Clean up after RCU barrier testing. */
+static void rcu_torture_barrier_cleanup(void)
+{
+ int i;
+
+ if (barrier_task != NULL) {
+ VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task");
+ kthread_stop(barrier_task);
+ barrier_task = NULL;
+ }
+ if (barrier_cbs_tasks != NULL) {
+ for (i = 0; i < n_barrier_cbs; i++) {
+ if (barrier_cbs_tasks[i] != NULL) {
+ VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task");
+ kthread_stop(barrier_cbs_tasks[i]);
+ barrier_cbs_tasks[i] = NULL;
+ }
+ }
+ kfree(barrier_cbs_tasks);
+ barrier_cbs_tasks = NULL;
+ }
+ if (barrier_cbs_wq != NULL) {
+ kfree(barrier_cbs_wq);
+ barrier_cbs_wq = NULL;
+ }
}
static int rcutorture_cpu_notify(struct notifier_block *self,
@@ -1598,6 +1808,7 @@ rcu_torture_cleanup(void)
fullstop = FULLSTOP_RMMOD;
mutex_unlock(&fullstop_mutex);
unregister_reboot_notifier(&rcutorture_shutdown_nb);
+ rcu_torture_barrier_cleanup();
rcu_torture_stall_cleanup();
if (stutter_task) {
VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
@@ -1665,6 +1876,7 @@ rcu_torture_cleanup(void)
VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
kthread_stop(shutdown_task);
}
+ shutdown_task = NULL;
rcu_torture_onoff_cleanup();
/* Wait for all RCU callbacks to fire. */
@@ -1676,7 +1888,7 @@ rcu_torture_cleanup(void)
if (cur_ops->cleanup)
cur_ops->cleanup();
- if (atomic_read(&n_rcu_torture_error))
+ if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
else if (n_online_successes != n_online_attempts ||
n_offline_successes != n_offline_attempts)
@@ -1692,10 +1904,12 @@ rcu_torture_init(void)
int i;
int cpu;
int firsterr = 0;
+ int retval;
static struct rcu_torture_ops *torture_ops[] =
{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
&rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
- &srcu_ops, &srcu_raw_ops, &srcu_expedited_ops,
+ &srcu_ops, &srcu_sync_ops, &srcu_raw_ops,
+ &srcu_raw_sync_ops, &srcu_expedited_ops,
&sched_ops, &sched_sync_ops, &sched_expedited_ops, };
mutex_lock(&fullstop_mutex);
@@ -1749,6 +1963,7 @@ rcu_torture_init(void)
atomic_set(&n_rcu_torture_free, 0);
atomic_set(&n_rcu_torture_mberror, 0);
atomic_set(&n_rcu_torture_error, 0);
+ n_rcu_torture_barrier_error = 0;
n_rcu_torture_boost_ktrerror = 0;
n_rcu_torture_boost_rterror = 0;
n_rcu_torture_boost_failure = 0;
@@ -1872,7 +2087,6 @@ rcu_torture_init(void)
test_boost_duration = 2;
if ((test_boost == 1 && cur_ops->can_boost) ||
test_boost == 2) {
- int retval;
boost_starttime = jiffies + test_boost_interval * HZ;
register_cpu_notifier(&rcutorture_cpu_nb);
@@ -1897,9 +2111,22 @@ rcu_torture_init(void)
goto unwind;
}
}
- rcu_torture_onoff_init();
+ i = rcu_torture_onoff_init();
+ if (i != 0) {
+ firsterr = i;
+ goto unwind;
+ }
register_reboot_notifier(&rcutorture_shutdown_nb);
- rcu_torture_stall_init();
+ i = rcu_torture_stall_init();
+ if (i != 0) {
+ firsterr = i;
+ goto unwind;
+ }
+ retval = rcu_torture_barrier_init();
+ if (retval != 0) {
+ firsterr = retval;
+ goto unwind;
+ }
rcutorture_record_test_transition();
mutex_unlock(&fullstop_mutex);
return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1050d6d3922..0da7b88d92d 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -75,6 +75,8 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
.gpnum = -300, \
.completed = -300, \
.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \
+ .orphan_nxttail = &structname##_state.orphan_nxtlist, \
+ .orphan_donetail = &structname##_state.orphan_donelist, \
.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
@@ -145,6 +147,13 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
unsigned long rcutorture_testseq;
unsigned long rcutorture_vernum;
+/* State information for rcu_barrier() and friends. */
+
+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;
+
/*
* 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
@@ -192,7 +201,6 @@ void rcu_note_context_switch(int cpu)
{
trace_rcu_utilization("Start context switch");
rcu_sched_qs(cpu);
- rcu_preempt_note_context_switch(cpu);
trace_rcu_utilization("End context switch");
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -1311,95 +1319,133 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Move a dying CPU's RCU callbacks to online CPU's callback list.
- * Also record a quiescent state for this CPU for the current grace period.
- * Synchronization and interrupt disabling are not required because
- * this function executes in stop_machine() context. Therefore, cleanup
- * operations that might block must be done later from the CPU_DEAD
- * notifier.
- *
- * Note that the outgoing CPU's bit has already been cleared in the
- * cpu_online_mask. This allows us to randomly pick a callback
- * destination from the bits set in that mask.
+ * Send the specified CPU's RCU callbacks to the orphanage. The
+ * specified CPU must be offline, and the caller must hold the
+ * ->onofflock.
*/
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
+static void
+rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
+ struct rcu_node *rnp, struct rcu_data *rdp)
{
int i;
- unsigned long mask;
- int receive_cpu = cpumask_any(cpu_online_mask);
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu);
- RCU_TRACE(struct rcu_node *rnp = rdp->mynode); /* For dying CPU. */
- /* First, adjust the counts. */
+ /*
+ * Orphan the callbacks. First adjust the counts. This is safe
+ * because ->onofflock excludes _rcu_barrier()'s adoption of
+ * the callbacks, thus no memory barrier is required.
+ */
if (rdp->nxtlist != NULL) {
- receive_rdp->qlen_lazy += rdp->qlen_lazy;
- receive_rdp->qlen += rdp->qlen;
+ rsp->qlen_lazy += rdp->qlen_lazy;
+ rsp->qlen += rdp->qlen;
+ rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen_lazy = 0;
rdp->qlen = 0;
}
/*
- * Next, move ready-to-invoke callbacks to be invoked on some
- * other CPU. These will not be required to pass through another
- * grace period: They are done, regardless of CPU.
+ * Next, move those callbacks still needing a grace period to
+ * the orphanage, where some other CPU will pick them up.
+ * Some of the callbacks might have gone partway through a grace
+ * period, but that is too bad. They get to start over because we
+ * cannot assume that grace periods are synchronized across CPUs.
+ * We don't bother updating the ->nxttail[] array yet, instead
+ * we just reset the whole thing later on.
*/
- if (rdp->nxtlist != NULL &&
- rdp->nxttail[RCU_DONE_TAIL] != &rdp->nxtlist) {
- struct rcu_head *oldhead;
- struct rcu_head **oldtail;
- struct rcu_head **newtail;
-
- oldhead = rdp->nxtlist;
- oldtail = receive_rdp->nxttail[RCU_DONE_TAIL];
- rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = *oldtail;
- *receive_rdp->nxttail[RCU_DONE_TAIL] = oldhead;
- newtail = rdp->nxttail[RCU_DONE_TAIL];
- for (i = RCU_DONE_TAIL; i < RCU_NEXT_SIZE; i++) {
- if (receive_rdp->nxttail[i] == oldtail)
- receive_rdp->nxttail[i] = newtail;
- if (rdp->nxttail[i] == newtail)
- rdp->nxttail[i] = &rdp->nxtlist;
- }
+ if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
+ *rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
+ rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
+ *rdp->nxttail[RCU_DONE_TAIL] = NULL;
}
/*
- * Finally, put the rest of the callbacks at the end of the list.
- * The ones that made it partway through get to start over: We
- * cannot assume that grace periods are synchronized across CPUs.
- * (We could splice RCU_WAIT_TAIL into RCU_NEXT_READY_TAIL, but
- * this does not seem compelling. Not yet, anyway.)
+ * Then move the ready-to-invoke callbacks to the orphanage,
+ * where some other CPU will pick them up. These will not be
+ * required to pass though another grace period: They are done.
*/
if (rdp->nxtlist != NULL) {
- *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
- receive_rdp->nxttail[RCU_NEXT_TAIL] =
- rdp->nxttail[RCU_NEXT_TAIL];
- receive_rdp->n_cbs_adopted += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
-
- rdp->nxtlist = NULL;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- rdp->nxttail[i] = &rdp->nxtlist;
+ *rsp->orphan_donetail = rdp->nxtlist;
+ rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
}
+ /* Finally, initialize the rcu_data structure's list to empty. */
+ rdp->nxtlist = NULL;
+ for (i = 0; i < RCU_NEXT_SIZE; i++)
+ rdp->nxttail[i] = &rdp->nxtlist;
+}
+
+/*
+ * Adopt the RCU callbacks from the specified rcu_state structure's
+ * orphanage. The caller must hold the ->onofflock.
+ */
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+ int i;
+ struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
+
/*
- * Record a quiescent state for the dying CPU. This is safe
- * only because we have already cleared out the callbacks.
- * (Otherwise, the RCU core might try to schedule the invocation
- * of callbacks on this now-offline CPU, which would be bad.)
+ * If there is an rcu_barrier() operation in progress, then
+ * only the task doing that operation is permitted to adopt
+ * callbacks. To do otherwise breaks rcu_barrier() and friends
+ * by causing them to fail to wait for the callbacks in the
+ * orphanage.
*/
- mask = rdp->grpmask; /* rnp->grplo is constant. */
+ if (rsp->rcu_barrier_in_progress &&
+ rsp->rcu_barrier_in_progress != current)
+ return;
+
+ /* Do the accounting first. */
+ rdp->qlen_lazy += rsp->qlen_lazy;
+ rdp->qlen += rsp->qlen;
+ rdp->n_cbs_adopted += rsp->qlen;
+ rsp->qlen_lazy = 0;
+ rsp->qlen = 0;
+
+ /*
+ * We do not need a memory barrier here because the only way we
+ * can get here if there is an rcu_barrier() in flight is if
+ * we are the task doing the rcu_barrier().
+ */
+
+ /* First adopt the ready-to-invoke callbacks. */
+ if (rsp->orphan_donelist != NULL) {
+ *rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
+ *rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
+ for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
+ if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
+ rdp->nxttail[i] = rsp->orphan_donetail;
+ rsp->orphan_donelist = NULL;
+ rsp->orphan_donetail = &rsp->orphan_donelist;
+ }
+
+ /* And then adopt the callbacks that still need a grace period. */
+ if (rsp->orphan_nxtlist != NULL) {
+ *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
+ rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
+ rsp->orphan_nxtlist = NULL;
+ rsp->orphan_nxttail = &rsp->orphan_nxtlist;
+ }
+}
+
+/*
+ * Trace the fact that this CPU is going offline.
+ */
+static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
+{
+ RCU_TRACE(unsigned long mask);
+ RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
+ RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
+
+ RCU_TRACE(mask = rdp->grpmask);
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
"cpuofl");
- rcu_report_qs_rdp(smp_processor_id(), rsp, rdp, rsp->gpnum);
- /* Note that rcu_report_qs_rdp() might call trace_rcu_grace_period(). */
}
/*
* The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context. Do the remainder of the cleanup.
+ * this fact from process context. Do the remainder of the cleanup,
+ * including orphaning the outgoing CPU's RCU callbacks, and also
+ * adopting them, if there is no _rcu_barrier() instance running.
* There can only be one CPU hotplug operation at a time, so no other
* CPU can be attempting to update rcu_cpu_kthread_task.
*/
@@ -1409,17 +1455,21 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
unsigned long mask;
int need_report = 0;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rnp. */
+ struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
/* Adjust any no-longer-needed kthreads. */
rcu_stop_cpu_kthread(cpu);
rcu_node_kthread_setaffinity(rnp, -1);
- /* Remove the dying CPU from the bitmasks in the rcu_node hierarchy. */
+ /* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
/* Exclude any attempts to start a new grace period. */
raw_spin_lock_irqsave(&rsp->onofflock, flags);
+ /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
+ rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
+ rcu_adopt_orphan_cbs(rsp);
+
/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
mask = rdp->grpmask; /* rnp->grplo is constant. */
do {
@@ -1456,6 +1506,10 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
#else /* #ifdef CONFIG_HOTPLUG_CPU */
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+{
+}
+
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
}
@@ -1524,9 +1578,6 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
rcu_is_callbacks_kthread());
/* Update count, and requeue any remaining callbacks. */
- rdp->qlen_lazy -= count_lazy;
- rdp->qlen -= count;
- rdp->n_cbs_invoked += count;
if (list != NULL) {
*tail = rdp->nxtlist;
rdp->nxtlist = list;
@@ -1536,6 +1587,10 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
else
break;
}
+ smp_mb(); /* List handling before counting for rcu_barrier(). */
+ rdp->qlen_lazy -= count_lazy;
+ rdp->qlen -= count;
+ rdp->n_cbs_invoked += count;
/* Reinstate batch limit if we have worked down the excess. */
if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
@@ -1820,15 +1875,17 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
* a quiescent state betweentimes.
*/
local_irq_save(flags);
- WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
- *rdp->nxttail[RCU_NEXT_TAIL] = head;
- rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
rdp->qlen++;
if (lazy)
rdp->qlen_lazy++;
+ else
+ rcu_idle_count_callbacks_posted();
+ smp_mb(); /* Count before adding callback for rcu_barrier(). */
+ *rdp->nxttail[RCU_NEXT_TAIL] = head;
+ rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
@@ -1894,6 +1951,38 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
+/*
+ * Because a context switch is a grace period for RCU-sched and RCU-bh,
+ * any blocking grace-period wait automatically implies a grace period
+ * if there is only one CPU online at any point time during execution
+ * of either synchronize_sched() or synchronize_rcu_bh(). It is OK to
+ * occasionally incorrectly indicate that there are multiple CPUs online
+ * when there was in fact only one the whole time, as this just adds
+ * some overhead: RCU still operates correctly.
+ *
+ * Of course, sampling num_online_cpus() with preemption enabled can
+ * give erroneous results if there are concurrent CPU-hotplug operations.
+ * For example, given a demonic sequence of preemptions in num_online_cpus()
+ * and CPU-hotplug operations, there could be two or more CPUs online at
+ * all times, but num_online_cpus() might well return one (or even zero).
+ *
+ * However, all such demonic sequences require at least one CPU-offline
+ * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer
+ * is only a problem if there is an RCU read-side critical section executing
+ * throughout. But RCU-sched and RCU-bh read-side critical sections
+ * disable either preemption or bh, which prevents a CPU from going offline.
+ * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return
+ * that there is only one CPU when in fact there was more than one throughout
+ * is when there were no RCU readers in the system. If there are no
+ * RCU readers, the grace period by definition can be of zero length,
+ * regardless of the number of online CPUs.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+ might_sleep(); /* Check for RCU read-side critical section. */
+ return num_online_cpus() <= 1;
+}
+
/**
* synchronize_sched - wait until an rcu-sched grace period has elapsed.
*
@@ -2167,11 +2256,10 @@ static int rcu_cpu_has_callbacks(int cpu)
rcu_preempt_cpu_has_callbacks(cpu);
}
-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;
-
+/*
+ * RCU callback function for _rcu_barrier(). If we are last, wake
+ * up the task executing _rcu_barrier().
+ */
static void rcu_barrier_callback(struct rcu_head *notused)
{
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
@@ -2201,27 +2289,94 @@ 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());
+ int cpu;
+ unsigned long flags;
+ struct rcu_data *rdp;
+ struct rcu_head rh;
+
+ init_rcu_head_on_stack(&rh);
+
/* Take mutex to serialize concurrent rcu_barrier() requests. */
mutex_lock(&rcu_barrier_mutex);
- init_completion(&rcu_barrier_completion);
+
+ smp_mb(); /* Prevent any prior operations from leaking in. */
+
/*
- * 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. Note that on_each_cpu() disables irqs, which prevents
- * any CPUs from coming online or going offline until each online
- * CPU has queued its RCU-barrier callback.
+ * Initialize the count to one rather than to zero in order to
+ * avoid a too-soon return to zero in case of a short grace period
+ * (or preemption of this task). Also flag this task as doing
+ * an rcu_barrier(). This will prevent anyone else from adopting
+ * orphaned callbacks, which could cause otherwise failure if a
+ * CPU went offline and quickly came back online. To see this,
+ * consider the following sequence of events:
+ *
+ * 1. We cause CPU 0 to post an rcu_barrier_callback() callback.
+ * 2. CPU 1 goes offline, orphaning its callbacks.
+ * 3. CPU 0 adopts CPU 1's orphaned callbacks.
+ * 4. CPU 1 comes back online.
+ * 5. We cause CPU 1 to post an rcu_barrier_callback() callback.
+ * 6. Both rcu_barrier_callback() callbacks are invoked, awakening
+ * us -- but before CPU 1's orphaned callbacks are invoked!!!
*/
+ init_completion(&rcu_barrier_completion);
atomic_set(&rcu_barrier_cpu_count, 1);
- on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
+ raw_spin_lock_irqsave(&rsp->onofflock, flags);
+ rsp->rcu_barrier_in_progress = current;
+ raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+
+ /*
+ * Force every CPU with callbacks to register a new callback
+ * that will tell us when all the preceding callbacks have
+ * been invoked. If an offline CPU has callbacks, wait for
+ * it to either come back online or to finish orphaning those
+ * callbacks.
+ */
+ for_each_possible_cpu(cpu) {
+ preempt_disable();
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ if (cpu_is_offline(cpu)) {
+ preempt_enable();
+ while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen))
+ schedule_timeout_interruptible(1);
+ } else if (ACCESS_ONCE(rdp->qlen)) {
+ smp_call_function_single(cpu, rcu_barrier_func,
+ (void *)call_rcu_func, 1);
+ preempt_enable();
+ } else {
+ preempt_enable();
+ }
+ }
+
+ /*
+ * Now that all online CPUs have rcu_barrier_callback() callbacks
+ * posted, we can adopt all of the orphaned callbacks and place
+ * an rcu_barrier_callback() callback after them. When that is done,
+ * we are guaranteed to have an rcu_barrier_callback() callback
+ * following every callback that could possibly have been
+ * registered before _rcu_barrier() was called.
+ */
+ raw_spin_lock_irqsave(&rsp->onofflock, flags);
+ rcu_adopt_orphan_cbs(rsp);
+ rsp->rcu_barrier_in_progress = NULL;
+ raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+ atomic_inc(&rcu_barrier_cpu_count);
+ smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */
+ call_rcu_func(&rh, rcu_barrier_callback);
+
+ /*
+ * Now that we have an rcu_barrier_callback() callback on each
+ * CPU, and thus each counted, remove the initial count.
+ */
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
+
+ /* Wait for all rcu_barrier_callback() callbacks to be invoked. */
wait_for_completion(&rcu_barrier_completion);
+
+ /* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rcu_barrier_mutex);
+
+ destroy_rcu_head_on_stack(&rh);
}
/**
@@ -2418,7 +2573,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
for (i = NUM_RCU_LVLS - 1; i > 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
- rsp->levelspread[0] = RCU_FANOUT_LEAF;
+ rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index cdd1be0a407..7f5d138dedf 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -29,18 +29,14 @@
#include <linux/seqlock.h>
/*
- * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
+ * CONFIG_RCU_FANOUT_LEAF.
* In theory, it should be possible to add more levels straightforwardly.
* In practice, this did work well going from three levels to four.
* Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
-#if CONFIG_RCU_FANOUT > 16
-#define RCU_FANOUT_LEAF 16
-#else /* #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_LEAF (CONFIG_RCU_FANOUT)
-#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF)
#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
@@ -371,6 +367,17 @@ struct rcu_state {
raw_spinlock_t onofflock; /* exclude on/offline and */
/* starting new GP. */
+ struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */
+ /* need a grace period. */
+ struct rcu_head **orphan_nxttail; /* Tail of above. */
+ struct rcu_head *orphan_donelist; /* Orphaned callbacks that */
+ /* are ready to invoke. */
+ struct rcu_head **orphan_donetail; /* Tail of above. */
+ long qlen_lazy; /* Number of lazy callbacks. */
+ long qlen; /* Total number of callbacks. */
+ struct task_struct *rcu_barrier_in_progress;
+ /* Task doing rcu_barrier(), */
+ /* or NULL if no barrier. */
raw_spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
@@ -423,7 +430,6 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
/* 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_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
@@ -471,6 +477,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu);
static void rcu_prepare_for_idle_init(int cpu);
static void rcu_cleanup_after_idle(int cpu);
static void rcu_prepare_for_idle(int cpu);
+static void rcu_idle_count_callbacks_posted(void);
static void print_cpu_stall_info_begin(void);
static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
static void print_cpu_stall_info_end(void);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c023464816b..2411000d986 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
*
* Caller must disable preemption.
*/
-static void rcu_preempt_note_context_switch(int cpu)
+void rcu_preempt_note_context_switch(void)
{
struct task_struct *t = current;
unsigned long flags;
@@ -164,7 +164,7 @@ static void rcu_preempt_note_context_switch(int cpu)
(t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
/* Possibly blocking in an RCU read-side critical section. */
- rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
+ rdp = __this_cpu_ptr(rcu_preempt_state.rda);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ static void rcu_preempt_note_context_switch(int cpu)
* means that we continue to block the current grace period.
*/
local_irq_save(flags);
- rcu_preempt_qs(cpu);
+ rcu_preempt_qs(smp_processor_id());
local_irq_restore(flags);
}
@@ -969,22 +969,6 @@ static void __init __rcu_init_preempt(void)
rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
}
-/*
- * Check for a task exiting while in a preemptible-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
- * is enabled.
- */
-void exit_rcu(void)
-{
- struct task_struct *t = current;
-
- if (t->rcu_read_lock_nesting == 0)
- return;
- t->rcu_read_lock_nesting = 1;
- __rcu_read_unlock();
-}
-
#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
static struct rcu_state *rcu_state = &rcu_sched_state;
@@ -1018,14 +1002,6 @@ void rcu_force_quiescent_state(void)
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
- * Because preemptible RCU does not exist, we never have to check for
- * CPUs being in quiescent states.
- */
-static void rcu_preempt_note_context_switch(int cpu)
-{
-}
-
-/*
* Because preemptible RCU does not exist, there are never any preempted
* RCU readers.
*/
@@ -1938,6 +1914,14 @@ static void rcu_prepare_for_idle(int cpu)
{
}
+/*
+ * Don't bother keeping a running count of the number of RCU callbacks
+ * posted because CONFIG_RCU_FAST_NO_HZ=n.
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+}
+
#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
/*
@@ -1978,11 +1962,20 @@ static void rcu_prepare_for_idle(int cpu)
#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */
#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
+/* Loop counter for rcu_prepare_for_idle(). */
static DEFINE_PER_CPU(int, rcu_dyntick_drain);
+/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer);
-static ktime_t rcu_idle_gp_wait; /* If some non-lazy callbacks. */
-static ktime_t rcu_idle_lazy_gp_wait; /* If only lazy callbacks. */
+/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
+static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
+/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
+static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
+/* Enable special processing on first attempt to enter dyntick-idle mode. */
+static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
+/* Running count of non-lazy callbacks posted, never decremented. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
+/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
/*
* Allow the CPU to enter dyntick-idle mode if either: (1) There are no
@@ -1995,6 +1988,8 @@ static ktime_t rcu_idle_lazy_gp_wait; /* If only lazy callbacks. */
*/
int rcu_needs_cpu(int cpu)
{
+ /* Flag a new idle sojourn to the idle-entry state machine. */
+ per_cpu(rcu_idle_first_pass, cpu) = 1;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(cpu))
return 0;
@@ -2045,16 +2040,34 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
}
/*
+ * Handler for smp_call_function_single(). The only point of this
+ * handler is to wake the CPU up, so the handler does only tracing.
+ */
+void rcu_idle_demigrate(void *unused)
+{
+ trace_rcu_prep_idle("Demigrate");
+}
+
+/*
* Timer handler used to force CPU to start pushing its remaining RCU
* callbacks in the case where it entered dyntick-idle mode with callbacks
* pending. The hander doesn't really need to do anything because the
* real work is done upon re-entry to idle, or by the next scheduling-clock
* interrupt should idle not be re-entered.
+ *
+ * One special case: the timer gets migrated without awakening the CPU
+ * on which the timer was scheduled on. In this case, we must wake up
+ * that CPU. We do so with smp_call_function_single().
*/
-static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
+static void rcu_idle_gp_timer_func(unsigned long cpu_in)
{
+ int cpu = (int)cpu_in;
+
trace_rcu_prep_idle("Timer");
- return HRTIMER_NORESTART;
+ if (cpu != smp_processor_id())
+ smp_call_function_single(cpu, rcu_idle_demigrate, NULL, 0);
+ else
+ WARN_ON_ONCE(1); /* Getting here can hang the system... */
}
/*
@@ -2062,19 +2075,11 @@ static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
*/
static void rcu_prepare_for_idle_init(int cpu)
{
- static int firsttime = 1;
- struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
-
- hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hrtp->function = rcu_idle_gp_timer_func;
- if (firsttime) {
- unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY);
-
- rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000);
- upj = jiffies_to_usecs(RCU_IDLE_LAZY_GP_DELAY);
- rcu_idle_lazy_gp_wait = ns_to_ktime(upj * (u64)1000);
- firsttime = 0;
- }
+ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+ setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
+ rcu_idle_gp_timer_func, cpu);
+ per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
+ per_cpu(rcu_idle_first_pass, cpu) = 1;
}
/*
@@ -2084,7 +2089,8 @@ static void rcu_prepare_for_idle_init(int cpu)
*/
static void rcu_cleanup_after_idle(int cpu)
{
- hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu));
+ del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+ trace_rcu_prep_idle("Cleanup after idle");
}
/*
@@ -2108,6 +2114,29 @@ static void rcu_cleanup_after_idle(int cpu)
*/
static void rcu_prepare_for_idle(int cpu)
{
+ struct timer_list *tp;
+
+ /*
+ * If this is an idle re-entry, for example, due to use of
+ * RCU_NONIDLE() or the new idle-loop tracing API within the idle
+ * loop, then don't take any state-machine actions, unless the
+ * momentary exit from idle queued additional non-lazy callbacks.
+ * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+ * pending.
+ */
+ if (!per_cpu(rcu_idle_first_pass, cpu) &&
+ (per_cpu(rcu_nonlazy_posted, cpu) ==
+ per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+ if (rcu_cpu_has_callbacks(cpu)) {
+ tp = &per_cpu(rcu_idle_gp_timer, cpu);
+ mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+ }
+ return;
+ }
+ per_cpu(rcu_idle_first_pass, cpu) = 0;
+ per_cpu(rcu_nonlazy_posted_snap, cpu) =
+ per_cpu(rcu_nonlazy_posted, cpu) - 1;
+
/*
* If there are no callbacks on this CPU, enter dyntick-idle mode.
* Also reset state to avoid prejudicing later attempts.
@@ -2140,11 +2169,15 @@ static void rcu_prepare_for_idle(int cpu)
per_cpu(rcu_dyntick_drain, cpu) = 0;
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
if (rcu_cpu_has_nonlazy_callbacks(cpu))
- hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
- rcu_idle_gp_wait, HRTIMER_MODE_REL);
+ per_cpu(rcu_idle_gp_timer_expires, cpu) =
+ jiffies + RCU_IDLE_GP_DELAY;
else
- hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
- rcu_idle_lazy_gp_wait, HRTIMER_MODE_REL);
+ per_cpu(rcu_idle_gp_timer_expires, cpu) =
+ jiffies + RCU_IDLE_LAZY_GP_DELAY;
+ tp = &per_cpu(rcu_idle_gp_timer, cpu);
+ mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+ per_cpu(rcu_nonlazy_posted_snap, cpu) =
+ per_cpu(rcu_nonlazy_posted, cpu);
return; /* Nothing more to do immediately. */
} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
/* We have hit the limit, so time to give up. */
@@ -2184,6 +2217,19 @@ static void rcu_prepare_for_idle(int cpu)
trace_rcu_prep_idle("Callbacks drained");
}
+/*
+ * Keep a running count of the number of non-lazy callbacks posted
+ * on this CPU. This running counter (which is never decremented) allows
+ * rcu_prepare_for_idle() to detect when something out of the idle loop
+ * posts a callback, even if an equal number of callbacks are invoked.
+ * Of course, callbacks should only be posted from within a trace event
+ * designed to be called from idle or from within RCU_NONIDLE().
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+ __this_cpu_add(rcu_nonlazy_posted, 1);
+}
+
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
#ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -2192,14 +2238,12 @@ static void rcu_prepare_for_idle(int cpu)
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
- struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
+ struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
- sprintf(cp, "drain=%d %c timer=%lld",
+ sprintf(cp, "drain=%d %c timer=%lu",
per_cpu(rcu_dyntick_drain, cpu),
per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
- hrtimer_active(hrtp)
- ? ktime_to_us(hrtimer_get_remaining(hrtp))
- : -1);
+ timer_pending(tltp) ? tltp->expires - jiffies : -1);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index ed459edeff4..d4bc16ddd1d 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -271,13 +271,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
gpnum = rsp->gpnum;
seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
- "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+ "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->completed, gpnum, rsp->fqs_state,
(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->qlen_lazy, rsp->qlen);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 9a7dd35102a..173ea52f3af 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,5 +16,3 @@ obj-$(CONFIG_SMP) += cpupri.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
-
-
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4603b9d8f30..ea8a4769fea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -83,6 +83,7 @@
#include "sched.h"
#include "../workqueue_sched.h"
+#include "../smpboot.h"
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
@@ -2083,6 +2084,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
#endif
/* Here we just switch the register state and the stack. */
+ rcu_switch_from(prev);
switch_to(prev, next, prev);
barrier();
@@ -6382,6 +6384,8 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
if (!sg)
return -ENOMEM;
+ sg->next = sg;
+
*per_cpu_ptr(sdd->sg, j) = sg;
sgp = kzalloc_node(sizeof(struct sched_group_power),
@@ -6405,16 +6409,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
struct sd_data *sdd = &tl->data;
for_each_cpu(j, cpu_map) {
- struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
- if (sd && (sd->flags & SD_OVERLAP))
- free_sched_groups(sd->groups, 0);
- kfree(*per_cpu_ptr(sdd->sd, j));
- kfree(*per_cpu_ptr(sdd->sg, j));
- kfree(*per_cpu_ptr(sdd->sgp, j));
+ struct sched_domain *sd;
+
+ if (sdd->sd) {
+ sd = *per_cpu_ptr(sdd->sd, j);
+ if (sd && (sd->flags & SD_OVERLAP))
+ free_sched_groups(sd->groups, 0);
+ kfree(*per_cpu_ptr(sdd->sd, j));
+ }
+
+ if (sdd->sg)
+ kfree(*per_cpu_ptr(sdd->sg, j));
+ if (sdd->sgp)
+ kfree(*per_cpu_ptr(sdd->sgp, j));
}
free_percpu(sdd->sd);
+ sdd->sd = NULL;
free_percpu(sdd->sg);
+ sdd->sg = NULL;
free_percpu(sdd->sgp);
+ sdd->sgp = NULL;
}
}
@@ -7049,6 +7063,7 @@ void __init sched_init(void)
/* May be allocated at isolcpus cmdline parse time */
if (cpu_isolated_map == NULL)
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ idle_thread_set_boot_cpu();
#endif
init_sched_fair_class();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d97ebdc58f..e9553640c1c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
if (entity_is_task(se))
- list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+ list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
#endif
cfs_rq->nr_running++;
}
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
static unsigned long task_h_load(struct task_struct *p);
+static const unsigned int sched_nr_migrate_break = 32;
+
/*
* move_tasks tries to move up to load_move weighted load from busiest to
* this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
/* take a breather every nr_migrate tasks */
if (env->loop > env->loop_break) {
- env->loop_break += sysctl_sched_nr_migrate;
+ env->loop_break += sched_nr_migrate_break;
env->flags |= LBF_NEED_BREAK;
break;
}
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
load = task_h_load(p);
- if (load < 16 && !env->sd->nr_balance_failed)
+ if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
goto next;
if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
.idle = idle,
- .loop_break = sysctl_sched_nr_migrate,
+ .loop_break = sched_nr_migrate_break,
};
cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ redo:
* correctly treated as an imbalance.
*/
env.flags |= LBF_ALL_PINNED;
- env.load_move = imbalance;
- env.src_cpu = busiest->cpu;
- env.src_rq = busiest;
- env.loop_max = busiest->nr_running;
+ env.load_move = imbalance;
+ env.src_cpu = busiest->cpu;
+ env.src_rq = busiest;
+ env.loop_max = min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
local_irq_save(flags);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e61fd73913d..de00a486c5c 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
SCHED_FEAT(FORCE_SD_OVERLAP, false)
SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e8d76c5895e..ee376beedaf 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -3,16 +3,357 @@
*
* Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com>
*
- * This defines a simple but solid secure-computing mode.
+ * Copyright (C) 2012 Google, Inc.
+ * Will Drewry <wad@chromium.org>
+ *
+ * This defines a simple but solid secure-computing facility.
+ *
+ * Mode 1 uses a fixed list of allowed system calls.
+ * Mode 2 allows user-defined system call filters in the form
+ * of Berkeley Packet Filters/Linux Socket Filters.
*/
+#include <linux/atomic.h>
#include <linux/audit.h>
-#include <linux/seccomp.h>
-#include <linux/sched.h>
#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/seccomp.h>
/* #define SECCOMP_DEBUG 1 */
-#define NR_SECCOMP_MODES 1
+
+#ifdef CONFIG_SECCOMP_FILTER
+#include <asm/syscall.h>
+#include <linux/filter.h>
+#include <linux/ptrace.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/tracehook.h>
+#include <linux/uaccess.h>
+
+/**
+ * struct seccomp_filter - container for seccomp BPF programs
+ *
+ * @usage: reference count to manage the object lifetime.
+ * get/put helpers should be used when accessing an instance
+ * outside of a lifetime-guarded section. In general, this
+ * is only needed for handling filters shared across tasks.
+ * @prev: points to a previously installed, or inherited, filter
+ * @len: the number of instructions in the program
+ * @insns: the BPF program instructions to evaluate
+ *
+ * seccomp_filter objects are organized in a tree linked via the @prev
+ * pointer. For any task, it appears to be a singly-linked list starting
+ * with current->seccomp.filter, the most recently attached or inherited filter.
+ * However, multiple filters may share a @prev node, by way of fork(), which
+ * results in a unidirectional tree existing in memory. This is similar to
+ * how namespaces work.
+ *
+ * seccomp_filter objects should never be modified after being attached
+ * to a task_struct (other than @usage).
+ */
+struct seccomp_filter {
+ atomic_t usage;
+ struct seccomp_filter *prev;
+ unsigned short len; /* Instruction count */
+ struct sock_filter insns[];
+};
+
+/* Limit any path through the tree to 256KB worth of instructions. */
+#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
+
+/**
+ * get_u32 - returns a u32 offset into data
+ * @data: a unsigned 64 bit value
+ * @index: 0 or 1 to return the first or second 32-bits
+ *
+ * This inline exists to hide the length of unsigned long. If a 32-bit
+ * unsigned long is passed in, it will be extended and the top 32-bits will be
+ * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
+ * properly returned.
+ *
+ * Endianness is explicitly ignored and left for BPF program authors to manage
+ * as per the specific architecture.
+ */
+static inline u32 get_u32(u64 data, int index)
+{
+ return ((u32 *)&data)[index];
+}
+
+/* Helper for bpf_load below. */
+#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
+/**
+ * bpf_load: checks and returns a pointer to the requested offset
+ * @off: offset into struct seccomp_data to load from
+ *
+ * Returns the requested 32-bits of data.
+ * seccomp_check_filter() should assure that @off is 32-bit aligned
+ * and not out of bounds. Failure to do so is a BUG.
+ */
+u32 seccomp_bpf_load(int off)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ if (off == BPF_DATA(nr))
+ return syscall_get_nr(current, regs);
+ if (off == BPF_DATA(arch))
+ return syscall_get_arch(current, regs);
+ if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
+ unsigned long value;
+ int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
+ int index = !!(off % sizeof(u64));
+ syscall_get_arguments(current, regs, arg, 1, &value);
+ return get_u32(value, index);
+ }
+ if (off == BPF_DATA(instruction_pointer))
+ return get_u32(KSTK_EIP(current), 0);
+ if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
+ return get_u32(KSTK_EIP(current), 1);
+ /* seccomp_check_filter should make this impossible. */
+ BUG();
+}
+
+/**
+ * seccomp_check_filter - verify seccomp filter code
+ * @filter: filter to verify
+ * @flen: length of filter
+ *
+ * Takes a previously checked filter (by sk_chk_filter) and
+ * redirects all filter code that loads struct sk_buff data
+ * and related data through seccomp_bpf_load. It also
+ * enforces length and alignment checking of those loads.
+ *
+ * Returns 0 if the rule set is legal or -EINVAL if not.
+ */
+static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
+{
+ int pc;
+ for (pc = 0; pc < flen; pc++) {
+ struct sock_filter *ftest = &filter[pc];
+ u16 code = ftest->code;
+ u32 k = ftest->k;
+
+ switch (code) {
+ case BPF_S_LD_W_ABS:
+ ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+ /* 32-bit aligned and not out of bounds. */
+ if (k >= sizeof(struct seccomp_data) || k & 3)
+ return -EINVAL;
+ continue;
+ case BPF_S_LD_W_LEN:
+ ftest->code = BPF_S_LD_IMM;
+ ftest->k = sizeof(struct seccomp_data);
+ continue;
+ case BPF_S_LDX_W_LEN:
+ ftest->code = BPF_S_LDX_IMM;
+ ftest->k = sizeof(struct seccomp_data);
+ continue;
+ /* Explicitly include allowed calls. */
+ case BPF_S_RET_K:
+ case BPF_S_RET_A:
+ case BPF_S_ALU_ADD_K:
+ case BPF_S_ALU_ADD_X:
+ case BPF_S_ALU_SUB_K:
+ case BPF_S_ALU_SUB_X:
+ case BPF_S_ALU_MUL_K:
+ case BPF_S_ALU_MUL_X:
+ case BPF_S_ALU_DIV_X:
+ case BPF_S_ALU_AND_K:
+ case BPF_S_ALU_AND_X:
+ case BPF_S_ALU_OR_K:
+ case BPF_S_ALU_OR_X:
+ case BPF_S_ALU_LSH_K:
+ case BPF_S_ALU_LSH_X:
+ case BPF_S_ALU_RSH_K:
+ case BPF_S_ALU_RSH_X:
+ case BPF_S_ALU_NEG:
+ case BPF_S_LD_IMM:
+ case BPF_S_LDX_IMM:
+ case BPF_S_MISC_TAX:
+ case BPF_S_MISC_TXA:
+ case BPF_S_ALU_DIV_K:
+ case BPF_S_LD_MEM:
+ case BPF_S_LDX_MEM:
+ case BPF_S_ST:
+ case BPF_S_STX:
+ case BPF_S_JMP_JA:
+ case BPF_S_JMP_JEQ_K:
+ case BPF_S_JMP_JEQ_X:
+ case BPF_S_JMP_JGE_K:
+ case BPF_S_JMP_JGE_X:
+ case BPF_S_JMP_JGT_K:
+ case BPF_S_JMP_JGT_X:
+ case BPF_S_JMP_JSET_K:
+ case BPF_S_JMP_JSET_X:
+ continue;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+/**
+ * seccomp_run_filters - evaluates all seccomp filters against @syscall
+ * @syscall: number of the current system call
+ *
+ * Returns valid seccomp BPF response codes.
+ */
+static u32 seccomp_run_filters(int syscall)
+{
+ struct seccomp_filter *f;
+ u32 ret = SECCOMP_RET_ALLOW;
+
+ /* Ensure unexpected behavior doesn't result in failing open. */
+ if (WARN_ON(current->seccomp.filter == NULL))
+ return SECCOMP_RET_KILL;
+
+ /*
+ * All filters in the list are evaluated and the lowest BPF return
+ * value always takes priority (ignoring the DATA).
+ */
+ for (f = current->seccomp.filter; f; f = f->prev) {
+ u32 cur_ret = sk_run_filter(NULL, f->insns);
+ if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+ ret = cur_ret;
+ }
+ return ret;
+}
+
+/**
+ * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * @fprog: BPF program to install
+ *
+ * Returns 0 on success or an errno on failure.
+ */
+static long seccomp_attach_filter(struct sock_fprog *fprog)
+{
+ struct seccomp_filter *filter;
+ unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
+ unsigned long total_insns = fprog->len;
+ long ret;
+
+ if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
+ return -EINVAL;
+
+ for (filter = current->seccomp.filter; filter; filter = filter->prev)
+ total_insns += filter->len + 4; /* include a 4 instr penalty */
+ if (total_insns > MAX_INSNS_PER_PATH)
+ return -ENOMEM;
+
+ /*
+ * Installing a seccomp filter requires that the task have
+ * CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
+ * This avoids scenarios where unprivileged tasks can affect the
+ * behavior of privileged children.
+ */
+ if (!current->no_new_privs &&
+ security_capable_noaudit(current_cred(), current_user_ns(),
+ CAP_SYS_ADMIN) != 0)
+ return -EACCES;
+
+ /* Allocate a new seccomp_filter */
+ filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
+ GFP_KERNEL|__GFP_NOWARN);
+ if (!filter)
+ return -ENOMEM;
+ atomic_set(&filter->usage, 1);
+ filter->len = fprog->len;
+
+ /* Copy the instructions from fprog. */
+ ret = -EFAULT;
+ if (copy_from_user(filter->insns, fprog->filter, fp_size))
+ goto fail;
+
+ /* Check and rewrite the fprog via the skb checker */
+ ret = sk_chk_filter(filter->insns, filter->len);
+ if (ret)
+ goto fail;
+
+ /* Check and rewrite the fprog for seccomp use */
+ ret = seccomp_check_filter(filter->insns, filter->len);
+ if (ret)
+ goto fail;
+
+ /*
+ * If there is an existing filter, make it the prev and don't drop its
+ * task reference.
+ */
+ filter->prev = current->seccomp.filter;
+ current->seccomp.filter = filter;
+ return 0;
+fail:
+ kfree(filter);
+ return ret;
+}
+
+/**
+ * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * @user_filter: pointer to the user data containing a sock_fprog.
+ *
+ * Returns 0 on success and non-zero otherwise.
+ */
+long seccomp_attach_user_filter(char __user *user_filter)
+{
+ struct sock_fprog fprog;
+ long ret = -EFAULT;
+
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ struct compat_sock_fprog fprog32;
+ if (copy_from_user(&fprog32, user_filter, sizeof(fprog32)))
+ goto out;
+ fprog.len = fprog32.len;
+ fprog.filter = compat_ptr(fprog32.filter);
+ } else /* falls through to the if below. */
+#endif
+ if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
+ goto out;
+ ret = seccomp_attach_filter(&fprog);
+out:
+ return ret;
+}
+
+/* get_seccomp_filter - increments the reference count of the filter on @tsk */
+void get_seccomp_filter(struct task_struct *tsk)
+{
+ struct seccomp_filter *orig = tsk->seccomp.filter;
+ if (!orig)
+ return;
+ /* Reference count is bounded by the number of total processes. */
+ atomic_inc(&orig->usage);
+}
+
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+ struct seccomp_filter *orig = tsk->seccomp.filter;
+ /* Clean up single-reference branches iteratively. */
+ while (orig && atomic_dec_and_test(&orig->usage)) {
+ struct seccomp_filter *freeme = orig;
+ orig = orig->prev;
+ kfree(freeme);
+ }
+}
+
+/**
+ * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+static void seccomp_send_sigsys(int syscall, int reason)
+{
+ struct siginfo info;
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGSYS;
+ info.si_code = SYS_SECCOMP;
+ info.si_call_addr = (void __user *)KSTK_EIP(current);
+ info.si_errno = reason;
+ info.si_arch = syscall_get_arch(current, task_pt_regs(current));
+ info.si_syscall = syscall;
+ force_sig_info(SIGSYS, &info, current);
+}
+#endif /* CONFIG_SECCOMP_FILTER */
/*
* Secure computing mode 1 allows only read/write/exit/sigreturn.
@@ -31,13 +372,15 @@ static int mode1_syscalls_32[] = {
};
#endif
-void __secure_computing(int this_syscall)
+int __secure_computing(int this_syscall)
{
int mode = current->seccomp.mode;
- int * syscall;
+ int exit_sig = 0;
+ int *syscall;
+ u32 ret;
switch (mode) {
- case 1:
+ case SECCOMP_MODE_STRICT:
syscall = mode1_syscalls;
#ifdef CONFIG_COMPAT
if (is_compat_task())
@@ -45,9 +388,54 @@ void __secure_computing(int this_syscall)
#endif
do {
if (*syscall == this_syscall)
- return;
+ return 0;
} while (*++syscall);
+ exit_sig = SIGKILL;
+ ret = SECCOMP_RET_KILL;
+ break;
+#ifdef CONFIG_SECCOMP_FILTER
+ case SECCOMP_MODE_FILTER: {
+ int data;
+ ret = seccomp_run_filters(this_syscall);
+ data = ret & SECCOMP_RET_DATA;
+ ret &= SECCOMP_RET_ACTION;
+ switch (ret) {
+ case SECCOMP_RET_ERRNO:
+ /* Set the low-order 16-bits as a errno. */
+ syscall_set_return_value(current, task_pt_regs(current),
+ -data, 0);
+ goto skip;
+ case SECCOMP_RET_TRAP:
+ /* Show the handler the original registers. */
+ syscall_rollback(current, task_pt_regs(current));
+ /* Let the filter pass back 16 bits of data. */
+ seccomp_send_sigsys(this_syscall, data);
+ goto skip;
+ case SECCOMP_RET_TRACE:
+ /* Skip these calls if there is no tracer. */
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+ goto skip;
+ /* Allow the BPF to provide the event message */
+ ptrace_event(PTRACE_EVENT_SECCOMP, data);
+ /*
+ * The delivery of a fatal signal during event
+ * notification may silently skip tracer notification.
+ * Terminating the task now avoids executing a system
+ * call that may not be intended.
+ */
+ if (fatal_signal_pending(current))
+ break;
+ return 0;
+ case SECCOMP_RET_ALLOW:
+ return 0;
+ case SECCOMP_RET_KILL:
+ default:
+ break;
+ }
+ exit_sig = SIGSYS;
break;
+ }
+#endif
default:
BUG();
}
@@ -55,8 +443,13 @@ void __secure_computing(int this_syscall)
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
- audit_seccomp(this_syscall);
- do_exit(SIGKILL);
+ audit_seccomp(this_syscall, exit_sig, ret);
+ do_exit(exit_sig);
+#ifdef CONFIG_SECCOMP_FILTER
+skip:
+ audit_seccomp(this_syscall, exit_sig, ret);
+#endif
+ return -1;
}
long prctl_get_seccomp(void)
@@ -64,25 +457,48 @@ long prctl_get_seccomp(void)
return current->seccomp.mode;
}
-long prctl_set_seccomp(unsigned long seccomp_mode)
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * This function may be called repeatedly with a @seccomp_mode of
+ * SECCOMP_MODE_FILTER to install additional filters. Every filter
+ * successfully installed will be evaluated (in reverse order) for each system
+ * call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
- long ret;
+ long ret = -EINVAL;
- /* can set it only once to be even more secure */
- ret = -EPERM;
- if (unlikely(current->seccomp.mode))
+ if (current->seccomp.mode &&
+ current->seccomp.mode != seccomp_mode)
goto out;
- ret = -EINVAL;
- if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
- current->seccomp.mode = seccomp_mode;
- set_thread_flag(TIF_SECCOMP);
+ switch (seccomp_mode) {
+ case SECCOMP_MODE_STRICT:
+ ret = 0;
#ifdef TIF_NOTSC
disable_TSC();
#endif
- ret = 0;
+ break;
+#ifdef CONFIG_SECCOMP_FILTER
+ case SECCOMP_MODE_FILTER:
+ ret = seccomp_attach_user_filter(filter);
+ if (ret)
+ goto out;
+ break;
+#endif
+ default:
+ goto out;
}
- out:
+ current->seccomp.mode = seccomp_mode;
+ set_thread_flag(TIF_SECCOMP);
+out:
return ret;
}
diff --git a/kernel/signal.c b/kernel/signal.c
index 17afcaf582d..1a006b5d9d9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -160,7 +160,7 @@ void recalc_sigpending(void)
#define SYNCHRONOUS_MASK \
(sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
- sigmask(SIGTRAP) | sigmask(SIGFPE))
+ sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS))
int next_signal(struct sigpending *pending, sigset_t *mask)
{
@@ -2706,6 +2706,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
err |= __put_user(from->si_uid, &to->si_uid);
err |= __put_user(from->si_ptr, &to->si_ptr);
break;
+#ifdef __ARCH_SIGSYS
+ case __SI_SYS:
+ err |= __put_user(from->si_call_addr, &to->si_call_addr);
+ err |= __put_user(from->si_syscall, &to->si_syscall);
+ err |= __put_user(from->si_arch, &to->si_arch);
+ break;
+#endif
default: /* this is just in case for now ... */
err |= __put_user(from->si_pid, &to->si_pid);
err |= __put_user(from->si_uid, &to->si_uid);
diff --git a/kernel/smp.c b/kernel/smp.c
index 2f8b10ecf75..d0ae5b24875 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -13,6 +13,8 @@
#include <linux/smp.h>
#include <linux/cpu.h>
+#include "smpboot.h"
+
#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
static struct {
struct list_head queue;
@@ -669,6 +671,8 @@ void __init smp_init(void)
{
unsigned int cpu;
+ idle_threads_init();
+
/* FIXME: This should be done in userspace --RR */
for_each_present_cpu(cpu) {
if (num_online_cpus() >= setup_max_cpus)
@@ -791,3 +795,26 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
}
}
EXPORT_SYMBOL(on_each_cpu_cond);
+
+static void do_nothing(void *unused)
+{
+}
+
+/**
+ * kick_all_cpus_sync - Force all cpus out of idle
+ *
+ * Used to synchronize the update of pm_idle function pointer. It's
+ * called after the pointer is updated and returns after the dummy
+ * callback function has been executed on all cpus. The execution of
+ * the function can only happen on the remote cpus after they have
+ * left the idle function which had been called via pm_idle function
+ * pointer. So it's guaranteed that nothing uses the previous pointer
+ * anymore.
+ */
+void kick_all_cpus_sync(void)
+{
+ /* Make sure the change is visible before we kick the cpus */
+ smp_mb();
+ smp_call_function(do_nothing, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
new file mode 100644
index 00000000000..e1a797e028a
--- /dev/null
+++ b/kernel/smpboot.c
@@ -0,0 +1,62 @@
+/*
+ * Common SMP CPU bringup/teardown functions
+ */
+#include <linux/err.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+
+#include "smpboot.h"
+
+#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
+/*
+ * For the hotplug case we keep the task structs around and reuse
+ * them.
+ */
+static DEFINE_PER_CPU(struct task_struct *, idle_threads);
+
+struct task_struct * __cpuinit idle_thread_get(unsigned int cpu)
+{
+ struct task_struct *tsk = per_cpu(idle_threads, cpu);
+
+ if (!tsk)
+ return ERR_PTR(-ENOMEM);
+ init_idle(tsk, cpu);
+ return tsk;
+}
+
+void __init idle_thread_set_boot_cpu(void)
+{
+ per_cpu(idle_threads, smp_processor_id()) = current;
+}
+
+static inline void idle_init(unsigned int cpu)
+{
+ struct task_struct *tsk = per_cpu(idle_threads, cpu);
+
+ if (!tsk) {
+ tsk = fork_idle(cpu);
+ if (IS_ERR(tsk))
+ pr_err("SMP: fork_idle() failed for CPU %u\n", cpu);
+ else
+ per_cpu(idle_threads, cpu) = tsk;
+ }
+}
+
+/**
+ * idle_thread_init - Initialize the idle thread for a cpu
+ * @cpu: The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
+void __init idle_threads_init(void)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (cpu != smp_processor_id())
+ idle_init(cpu);
+ }
+}
+#endif
diff --git a/kernel/smpboot.h b/kernel/smpboot.h
new file mode 100644
index 00000000000..80c0acfb847
--- /dev/null
+++ b/kernel/smpboot.h
@@ -0,0 +1,18 @@
+#ifndef SMPBOOT_H
+#define SMPBOOT_H
+
+struct task_struct;
+
+int smpboot_prepare(unsigned int cpu);
+
+#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
+struct task_struct *idle_thread_get(unsigned int cpu);
+void idle_thread_set_boot_cpu(void);
+void idle_threads_init(void);
+#else
+static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; }
+static inline void idle_thread_set_boot_cpu(void) { }
+static inline void idle_threads_init(void) { }
+#endif
+
+#endif
diff --git a/kernel/srcu.c b/kernel/srcu.c
index ba35f3a4a1f..2095be3318d 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -34,10 +34,77 @@
#include <linux/delay.h>
#include <linux/srcu.h>
+/*
+ * Initialize an rcu_batch structure to empty.
+ */
+static inline void rcu_batch_init(struct rcu_batch *b)
+{
+ b->head = NULL;
+ b->tail = &b->head;
+}
+
+/*
+ * Enqueue a callback onto the tail of the specified rcu_batch structure.
+ */
+static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head)
+{
+ *b->tail = head;
+ b->tail = &head->next;
+}
+
+/*
+ * Is the specified rcu_batch structure empty?
+ */
+static inline bool rcu_batch_empty(struct rcu_batch *b)
+{
+ return b->tail == &b->head;
+}
+
+/*
+ * Remove the callback at the head of the specified rcu_batch structure
+ * and return a pointer to it, or return NULL if the structure is empty.
+ */
+static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b)
+{
+ struct rcu_head *head;
+
+ if (rcu_batch_empty(b))
+ return NULL;
+
+ head = b->head;
+ b->head = head->next;
+ if (b->tail == &head->next)
+ rcu_batch_init(b);
+
+ return head;
+}
+
+/*
+ * Move all callbacks from the rcu_batch structure specified by "from" to
+ * the structure specified by "to".
+ */
+static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from)
+{
+ if (!rcu_batch_empty(from)) {
+ *to->tail = from->head;
+ to->tail = from->tail;
+ rcu_batch_init(from);
+ }
+}
+
+/* single-thread state-machine */
+static void process_srcu(struct work_struct *work);
+
static int init_srcu_struct_fields(struct srcu_struct *sp)
{
sp->completed = 0;
- mutex_init(&sp->mutex);
+ spin_lock_init(&sp->queue_lock);
+ sp->running = false;
+ rcu_batch_init(&sp->batch_queue);
+ rcu_batch_init(&sp->batch_check0);
+ rcu_batch_init(&sp->batch_check1);
+ rcu_batch_init(&sp->batch_done);
+ INIT_DELAYED_WORK(&sp->work, process_srcu);
sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
return sp->per_cpu_ref ? 0 : -ENOMEM;
}
@@ -73,21 +140,116 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
- * srcu_readers_active_idx -- returns approximate number of readers
- * active on the specified rank of per-CPU counters.
+ * Returns approximate total of the readers' ->seq[] values for the
+ * rank of per-CPU counters specified by idx.
*/
+static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
+{
+ int cpu;
+ unsigned long sum = 0;
+ unsigned long t;
-static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+ for_each_possible_cpu(cpu) {
+ t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+ sum += t;
+ }
+ return sum;
+}
+
+/*
+ * Returns approximate number of readers active on the specified rank
+ * of the per-CPU ->c[] counters.
+ */
+static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
{
int cpu;
- int sum;
+ unsigned long sum = 0;
+ unsigned long t;
- sum = 0;
- for_each_possible_cpu(cpu)
- sum += per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx];
+ for_each_possible_cpu(cpu) {
+ t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+ sum += t;
+ }
return sum;
}
+/*
+ * Return true if the number of pre-existing readers is determined to
+ * be stably zero. An example unstable zero can occur if the call
+ * to srcu_readers_active_idx() misses an __srcu_read_lock() increment,
+ * but due to task migration, sees the corresponding __srcu_read_unlock()
+ * decrement. This can happen because srcu_readers_active_idx() takes
+ * time to sum the array, and might in fact be interrupted or preempted
+ * partway through the summation.
+ */
+static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+{
+ unsigned long seq;
+
+ seq = srcu_readers_seq_idx(sp, idx);
+
+ /*
+ * The following smp_mb() A pairs with the smp_mb() B located in
+ * __srcu_read_lock(). This pairing ensures that if an
+ * __srcu_read_lock() increments its counter after the summation
+ * in srcu_readers_active_idx(), then the corresponding SRCU read-side
+ * critical section will see any changes made prior to the start
+ * of the current SRCU grace period.
+ *
+ * Also, if the above call to srcu_readers_seq_idx() saw the
+ * increment of ->seq[], then the call to srcu_readers_active_idx()
+ * must see the increment of ->c[].
+ */
+ smp_mb(); /* A */
+
+ /*
+ * Note that srcu_readers_active_idx() can incorrectly return
+ * zero even though there is a pre-existing reader throughout.
+ * To see this, suppose that task A is in a very long SRCU
+ * read-side critical section that started on CPU 0, and that
+ * no other reader exists, so that the sum of the counters
+ * is equal to one. Then suppose that task B starts executing
+ * srcu_readers_active_idx(), summing up to CPU 1, and then that
+ * task C starts reading on CPU 0, so that its increment is not
+ * summed, but finishes reading on CPU 2, so that its decrement
+ * -is- summed. Then when task B completes its sum, it will
+ * incorrectly get zero, despite the fact that task A has been
+ * in its SRCU read-side critical section the whole time.
+ *
+ * We therefore do a validation step should srcu_readers_active_idx()
+ * return zero.
+ */
+ if (srcu_readers_active_idx(sp, idx) != 0)
+ return false;
+
+ /*
+ * The remainder of this function is the validation step.
+ * The following smp_mb() D pairs with the smp_mb() C in
+ * __srcu_read_unlock(). If the __srcu_read_unlock() was seen
+ * by srcu_readers_active_idx() above, then any destructive
+ * operation performed after the grace period will happen after
+ * the corresponding SRCU read-side critical section.
+ *
+ * Note that there can be at most NR_CPUS worth of readers using
+ * the old index, which is not enough to overflow even a 32-bit
+ * integer. (Yes, this does mean that systems having more than
+ * a billion or so CPUs need to be 64-bit systems.) Therefore,
+ * the sum of the ->seq[] counters cannot possibly overflow.
+ * Therefore, the only way that the return values of the two
+ * calls to srcu_readers_seq_idx() can be equal is if there were
+ * no increments of the corresponding rank of ->seq[] counts
+ * in the interim. But the missed-increment scenario laid out
+ * above includes an increment of the ->seq[] counter by
+ * the corresponding __srcu_read_lock(). Therefore, if this
+ * scenario occurs, the return values from the two calls to
+ * srcu_readers_seq_idx() will differ, and thus the validation
+ * step below suffices.
+ */
+ smp_mb(); /* D */
+
+ return srcu_readers_seq_idx(sp, idx) == seq;
+}
+
/**
* srcu_readers_active - returns approximate number of readers.
* @sp: which srcu_struct to count active readers (holding srcu_read_lock).
@@ -98,7 +260,14 @@ static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
*/
static int srcu_readers_active(struct srcu_struct *sp)
{
- return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1);
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+ sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+ }
+ return sum;
}
/**
@@ -131,10 +300,11 @@ int __srcu_read_lock(struct srcu_struct *sp)
int idx;
preempt_disable();
- idx = sp->completed & 0x1;
- barrier(); /* ensure compiler looks -once- at sp->completed. */
- per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]++;
- srcu_barrier(); /* ensure compiler won't misorder critical section. */
+ idx = rcu_dereference_index_check(sp->completed,
+ rcu_read_lock_sched_held()) & 0x1;
+ ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
+ smp_mb(); /* B */ /* Avoid leaking the critical section. */
+ ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
preempt_enable();
return idx;
}
@@ -149,8 +319,8 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
void __srcu_read_unlock(struct srcu_struct *sp, int idx)
{
preempt_disable();
- srcu_barrier(); /* ensure compiler won't misorder critical section. */
- per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
+ smp_mb(); /* C */ /* Avoid leaking the critical section. */
+ ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1;
preempt_enable();
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -163,106 +333,119 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
* we repeatedly block for 1-millisecond time periods. This approach
* has done well in testing, so there is no need for a config parameter.
*/
-#define SYNCHRONIZE_SRCU_READER_DELAY 10
+#define SRCU_RETRY_CHECK_DELAY 5
+#define SYNCHRONIZE_SRCU_TRYCOUNT 2
+#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT 12
/*
- * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ * @@@ Wait until all pre-existing readers complete. Such readers
+ * will have used the index specified by "idx".
+ * the caller should ensures the ->completed is not changed while checking
+ * and idx = (->completed & 1) ^ 1
*/
-static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
+static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
{
- int idx;
-
- rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
- !lock_is_held(&rcu_bh_lock_map) &&
- !lock_is_held(&rcu_lock_map) &&
- !lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
-
- idx = sp->completed;
- mutex_lock(&sp->mutex);
+ for (;;) {
+ if (srcu_readers_active_idx_check(sp, idx))
+ return true;
+ if (--trycount <= 0)
+ return false;
+ udelay(SRCU_RETRY_CHECK_DELAY);
+ }
+}
- /*
- * Check to see if someone else did the work for us while we were
- * waiting to acquire the lock. We need -two- advances of
- * the counter, not just one. If there was but one, we might have
- * shown up -after- our helper's first synchronize_sched(), thus
- * having failed to prevent CPU-reordering races with concurrent
- * srcu_read_unlock()s on other CPUs (see comment below). So we
- * either (1) wait for two or (2) supply the second ourselves.
- */
+/*
+ * Increment the ->completed counter so that future SRCU readers will
+ * use the other rank of the ->c[] and ->seq[] arrays. This allows
+ * us to wait for pre-existing readers in a starvation-free manner.
+ */
+static void srcu_flip(struct srcu_struct *sp)
+{
+ sp->completed++;
+}
- if ((sp->completed - idx) >= 2) {
- mutex_unlock(&sp->mutex);
- return;
+/*
+ * Enqueue an SRCU callback on the specified srcu_struct structure,
+ * initiating grace-period processing if it is not already running.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+ void (*func)(struct rcu_head *head))
+{
+ unsigned long flags;
+
+ head->next = NULL;
+ head->func = func;
+ spin_lock_irqsave(&sp->queue_lock, flags);
+ rcu_batch_queue(&sp->batch_queue, head);
+ if (!sp->running) {
+ sp->running = true;
+ queue_delayed_work(system_nrt_wq, &sp->work, 0);
}
+ spin_unlock_irqrestore(&sp->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
- sync_func(); /* Force memory barrier on all CPUs. */
+struct rcu_synchronize {
+ struct rcu_head head;
+ struct completion completion;
+};
- /*
- * The preceding synchronize_sched() ensures that any CPU that
- * sees the new value of sp->completed will also see any preceding
- * changes to data structures made by this CPU. This prevents
- * some other CPU from reordering the accesses in its SRCU
- * read-side critical section to precede the corresponding
- * srcu_read_lock() -- ensuring that such references will in
- * fact be protected.
- *
- * So it is now safe to do the flip.
- */
+/*
+ * Awaken the corresponding synchronize_srcu() instance now that a
+ * grace period has elapsed.
+ */
+static void wakeme_after_rcu(struct rcu_head *head)
+{
+ struct rcu_synchronize *rcu;
- idx = sp->completed & 0x1;
- sp->completed++;
+ rcu = container_of(head, struct rcu_synchronize, head);
+ complete(&rcu->completion);
+}
- sync_func(); /* Force memory barrier on all CPUs. */
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount);
+static void srcu_reschedule(struct srcu_struct *sp);
- /*
- * At this point, because of the preceding synchronize_sched(),
- * all srcu_read_lock() calls using the old counters have completed.
- * Their corresponding critical sections might well be still
- * executing, but the srcu_read_lock() primitives themselves
- * will have finished executing. We initially give readers
- * an arbitrarily chosen 10 microseconds to get out of their
- * SRCU read-side critical sections, then loop waiting 1/HZ
- * seconds per iteration. The 10-microsecond value has done
- * very well in testing.
- */
-
- if (srcu_readers_active_idx(sp, idx))
- udelay(SYNCHRONIZE_SRCU_READER_DELAY);
- while (srcu_readers_active_idx(sp, idx))
- schedule_timeout_interruptible(1);
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ */
+static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
+{
+ struct rcu_synchronize rcu;
+ struct rcu_head *head = &rcu.head;
+ bool done = false;
- sync_func(); /* Force memory barrier on all CPUs. */
+ rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
+ !lock_is_held(&rcu_bh_lock_map) &&
+ !lock_is_held(&rcu_lock_map) &&
+ !lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
- /*
- * The preceding synchronize_sched() forces all srcu_read_unlock()
- * primitives that were executing concurrently with the preceding
- * for_each_possible_cpu() loop to have completed by this point.
- * More importantly, it also forces the corresponding SRCU read-side
- * critical sections to have also completed, and the corresponding
- * references to SRCU-protected data items to be dropped.
- *
- * Note:
- *
- * Despite what you might think at first glance, the
- * preceding synchronize_sched() -must- be within the
- * critical section ended by the following mutex_unlock().
- * Otherwise, a task taking the early exit can race
- * with a srcu_read_unlock(), which might have executed
- * just before the preceding srcu_readers_active() check,
- * and whose CPU might have reordered the srcu_read_unlock()
- * with the preceding critical section. In this case, there
- * is nothing preventing the synchronize_sched() task that is
- * taking the early exit from freeing a data structure that
- * is still being referenced (out of order) by the task
- * doing the srcu_read_unlock().
- *
- * Alternatively, the comparison with "2" on the early exit
- * could be changed to "3", but this increases synchronize_srcu()
- * latency for bulk loads. So the current code is preferred.
- */
+ init_completion(&rcu.completion);
+
+ head->next = NULL;
+ head->func = wakeme_after_rcu;
+ spin_lock_irq(&sp->queue_lock);
+ if (!sp->running) {
+ /* steal the processing owner */
+ sp->running = true;
+ rcu_batch_queue(&sp->batch_check0, head);
+ spin_unlock_irq(&sp->queue_lock);
+
+ srcu_advance_batches(sp, trycount);
+ if (!rcu_batch_empty(&sp->batch_done)) {
+ BUG_ON(sp->batch_done.head != head);
+ rcu_batch_dequeue(&sp->batch_done);
+ done = true;
+ }
+ /* give the processing owner to work_struct */
+ srcu_reschedule(sp);
+ } else {
+ rcu_batch_queue(&sp->batch_queue, head);
+ spin_unlock_irq(&sp->queue_lock);
+ }
- mutex_unlock(&sp->mutex);
+ if (!done)
+ wait_for_completion(&rcu.completion);
}
/**
@@ -281,7 +464,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
*/
void synchronize_srcu(struct srcu_struct *sp)
{
- __synchronize_srcu(sp, synchronize_sched);
+ __synchronize_srcu(sp, SYNCHRONIZE_SRCU_TRYCOUNT);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
@@ -289,18 +472,11 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
* synchronize_srcu_expedited - Brute-force SRCU grace period
* @sp: srcu_struct with which to synchronize.
*
- * Wait for an SRCU grace period to elapse, but use a "big hammer"
- * approach to force the grace period to end quickly. This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code. In fact,
- * if you are using synchronize_srcu_expedited() in a loop, please
- * restructure your code to batch your updates, and then use a single
- * synchronize_srcu() instead.
+ * Wait for an SRCU grace period to elapse, but be more aggressive about
+ * spinning rather than blocking when waiting.
*
* Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier. Failing to observe
- * these restriction will result in deadlock. It is also illegal to call
+ * that is acquired by a CPU-hotplug notifier. It is also illegal to call
* synchronize_srcu_expedited() from the corresponding SRCU read-side
* critical section; doing so will result in deadlock. However, it is
* perfectly legal to call synchronize_srcu_expedited() on one srcu_struct
@@ -309,20 +485,166 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
*/
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
- __synchronize_srcu(sp, synchronize_sched_expedited);
+ __synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT);
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
+ * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ */
+void srcu_barrier(struct srcu_struct *sp)
+{
+ synchronize_srcu(sp);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
+/**
* srcu_batches_completed - return batches completed.
* @sp: srcu_struct on which to report batch completion.
*
* Report the number of batches, correlated with, but not necessarily
* precisely the same as, the number of grace periods that have elapsed.
*/
-
long srcu_batches_completed(struct srcu_struct *sp)
{
return sp->completed;
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
+
+#define SRCU_CALLBACK_BATCH 10
+#define SRCU_INTERVAL 1
+
+/*
+ * Move any new SRCU callbacks to the first stage of the SRCU grace
+ * period pipeline.
+ */
+static void srcu_collect_new(struct srcu_struct *sp)
+{
+ if (!rcu_batch_empty(&sp->batch_queue)) {
+ spin_lock_irq(&sp->queue_lock);
+ rcu_batch_move(&sp->batch_check0, &sp->batch_queue);
+ spin_unlock_irq(&sp->queue_lock);
+ }
+}
+
+/*
+ * Core SRCU state machine. Advance callbacks from ->batch_check0 to
+ * ->batch_check1 and then to ->batch_done as readers drain.
+ */
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
+{
+ int idx = 1 ^ (sp->completed & 1);
+
+ /*
+ * Because readers might be delayed for an extended period after
+ * fetching ->completed for their index, at any point in time there
+ * might well be readers using both idx=0 and idx=1. We therefore
+ * need to wait for readers to clear from both index values before
+ * invoking a callback.
+ */
+
+ if (rcu_batch_empty(&sp->batch_check0) &&
+ rcu_batch_empty(&sp->batch_check1))
+ return; /* no callbacks need to be advanced */
+
+ if (!try_check_zero(sp, idx, trycount))
+ return; /* failed to advance, will try after SRCU_INTERVAL */
+
+ /*
+ * The callbacks in ->batch_check1 have already done with their
+ * first zero check and flip back when they were enqueued on
+ * ->batch_check0 in a previous invocation of srcu_advance_batches().
+ * (Presumably try_check_zero() returned false during that
+ * invocation, leaving the callbacks stranded on ->batch_check1.)
+ * They are therefore ready to invoke, so move them to ->batch_done.
+ */
+ rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+
+ if (rcu_batch_empty(&sp->batch_check0))
+ return; /* no callbacks need to be advanced */
+ srcu_flip(sp);
+
+ /*
+ * The callbacks in ->batch_check0 just finished their
+ * first check zero and flip, so move them to ->batch_check1
+ * for future checking on the other idx.
+ */
+ rcu_batch_move(&sp->batch_check1, &sp->batch_check0);
+
+ /*
+ * SRCU read-side critical sections are normally short, so check
+ * at least twice in quick succession after a flip.
+ */
+ trycount = trycount < 2 ? 2 : trycount;
+ if (!try_check_zero(sp, idx^1, trycount))
+ return; /* failed to advance, will try after SRCU_INTERVAL */
+
+ /*
+ * The callbacks in ->batch_check1 have now waited for all
+ * pre-existing readers using both idx values. They are therefore
+ * ready to invoke, so move them to ->batch_done.
+ */
+ rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+}
+
+/*
+ * Invoke a limited number of SRCU callbacks that have passed through
+ * their grace period. If there are more to do, SRCU will reschedule
+ * the workqueue.
+ */
+static void srcu_invoke_callbacks(struct srcu_struct *sp)
+{
+ int i;
+ struct rcu_head *head;
+
+ for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
+ head = rcu_batch_dequeue(&sp->batch_done);
+ if (!head)
+ break;
+ local_bh_disable();
+ head->func(head);
+ local_bh_enable();
+ }
+}
+
+/*
+ * Finished one round of SRCU grace period. Start another if there are
+ * more SRCU callbacks queued, otherwise put SRCU into not-running state.
+ */
+static void srcu_reschedule(struct srcu_struct *sp)
+{
+ bool pending = true;
+
+ if (rcu_batch_empty(&sp->batch_done) &&
+ rcu_batch_empty(&sp->batch_check1) &&
+ rcu_batch_empty(&sp->batch_check0) &&
+ rcu_batch_empty(&sp->batch_queue)) {
+ spin_lock_irq(&sp->queue_lock);
+ if (rcu_batch_empty(&sp->batch_done) &&
+ rcu_batch_empty(&sp->batch_check1) &&
+ rcu_batch_empty(&sp->batch_check0) &&
+ rcu_batch_empty(&sp->batch_queue)) {
+ sp->running = false;
+ pending = false;
+ }
+ spin_unlock_irq(&sp->queue_lock);
+ }
+
+ if (pending)
+ queue_delayed_work(system_nrt_wq, &sp->work, SRCU_INTERVAL);
+}
+
+/*
+ * This is the work-queue function that handles SRCU grace periods.
+ */
+static void process_srcu(struct work_struct *work)
+{
+ struct srcu_struct *sp;
+
+ sp = container_of(work, struct srcu_struct, work.work);
+
+ srcu_collect_new(sp);
+ srcu_advance_batches(sp, 1);
+ srcu_invoke_callbacks(sp);
+ srcu_reschedule(sp);
+}
diff --git a/kernel/sys.c b/kernel/sys.c
index e7006eb6c1e..ba0ae8eea6f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1908,7 +1908,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = prctl_get_seccomp();
break;
case PR_SET_SECCOMP:
- error = prctl_set_seccomp(arg2);
+ error = prctl_set_seccomp(arg2, (char __user *)arg3);
break;
case PR_GET_TSC:
error = GET_TSC_CTL(arg2);
@@ -1979,6 +1979,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = put_user(me->signal->is_child_subreaper,
(int __user *) arg2);
break;
+ case PR_SET_NO_NEW_PRIVS:
+ if (arg2 != 1 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ current->no_new_privs = 1;
+ break;
+ case PR_GET_NO_NEW_PRIVS:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ return current->no_new_privs ? 1 : 0;
default:
error = -EINVAL;
break;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index bf57abdc7bd..f113755695e 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -346,7 +346,8 @@ int tick_resume_broadcast(void)
tick_get_broadcast_mask());
break;
case TICKDEV_MODE_ONESHOT:
- broadcast = tick_resume_broadcast_oneshot(bc);
+ if (!cpumask_empty(tick_get_broadcast_mask()))
+ broadcast = tick_resume_broadcast_oneshot(bc);
break;
}
}
@@ -373,6 +374,9 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
{
struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
return clockevents_program_event(bc, expires, force);
}
@@ -531,7 +535,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
bc->event_handler = tick_handle_oneshot_broadcast;
- clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
/* Take the do_timer update */
tick_do_timer_cpu = cpu;
@@ -549,6 +552,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
to_cpumask(tmpmask));
if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
tick_broadcast_init_next_event(to_cpumask(tmpmask),
tick_next_period);
tick_broadcast_set_event(tick_next_period, 1);
@@ -577,15 +581,10 @@ void tick_broadcast_switch_to_oneshot(void)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
-
- if (cpumask_empty(tick_get_broadcast_mask()))
- goto end;
-
bc = tick_broadcast_device.evtdev;
if (bc)
tick_broadcast_setup_oneshot(bc);
-end:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
diff --git a/kernel/timer.c b/kernel/timer.c
index a297ffcf888..837c552fe83 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -861,7 +861,13 @@ EXPORT_SYMBOL(mod_timer);
*
* mod_timer_pinned() is a way to update the expire field of an
* active timer (if the timer is inactive it will be activated)
- * and not allow the timer to be migrated to a different CPU.
+ * and to ensure that the timer is scheduled on the current CPU.
+ *
+ * Note that this does not prevent the timer from being migrated
+ * when the current CPU goes offline. If this is a problem for
+ * you, use CPU-hotplug notifiers to handle it correctly, for
+ * example, cancelling the timer when the corresponding CPU goes
+ * offline.
*
* mod_timer_pinned(timer, expires) is equivalent to:
*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1e12f..2a22255c101 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4629,7 +4629,8 @@ static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ring_buffer *buffer = filp->private_data;
+ struct trace_array *tr = filp->private_data;
+ struct ring_buffer *buffer = tr->buffer;
char buf[64];
int r;
@@ -4647,7 +4648,8 @@ static ssize_t
rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ring_buffer *buffer = filp->private_data;
+ struct trace_array *tr = filp->private_data;
+ struct ring_buffer *buffer = tr->buffer;
unsigned long val;
int ret;
@@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void)
&trace_clock_fops);
trace_create_file("tracing_on", 0644, d_tracer,
- global_trace.buffer, &rb_simple_fops);
+ &global_trace, &rb_simple_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f091a2..f95d65da6db 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
filter)
#include "trace_entries.h"
-#ifdef CONFIG_FUNCTION_TRACER
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
int perf_ftrace_event_register(struct ftrace_event_call *call,
enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 079a93ae8a9..29111da1d10 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -294,6 +294,9 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
if (!call->name || !call->class || !call->class->reg)
continue;
+ if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
+ continue;
+
if (match &&
strcmp(match, call->name) != 0 &&
strcmp(match, call->class->system) != 0)
@@ -1164,7 +1167,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
return -1;
}
- if (call->class->reg)
+ if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
trace_create_file("enable", 0644, call->dir, call,
enable);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 3dd15e8bc85..e039906b037 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -180,6 +180,7 @@ struct ftrace_event_call __used event_##call = { \
.event.type = etype, \
.class = &event_class_ftrace_##call, \
.print_fmt = print, \
+ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \
}; \
struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 859fae6b182..df611a0e76c 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
{
u64 next_ts;
int ret;
+ /* trace_find_next_entry will reset ent_size */
+ int ent_size = iter->ent_size;
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent,
*next_entry = trace_find_next_entry(iter, NULL,
@@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
unsigned long rel_usecs;
+ /* Restore the original ent_size */
+ iter->ent_size = ent_size;
+
if (!next_entry)
next_ts = iter->ts;
rel_usecs = ns2usecs(next_ts - iter->ts);