Merge branch 'rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: rcu_sched_grace_period(): kill the bogus flush_signals()
rculist: use list_entry_rcu in places where it's appropriate
rculist.h: introduce list_entry_rcu() and list_first_entry_rcu()
rcu: Update RCU tracing documentation for __rcu_pending
rcu: Add __rcu_pending tracing to hierarchical RCU
RCU: make treercu be default
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 0688482..02cced1 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -192,23 +192,24 @@
The output of "cat rcu/rcudata" looks as follows:
rcu:
- 0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
- 1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
- 2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
- 3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
- 4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
- 5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
- 6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
- 7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
+rcu:
+ 0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
+ 1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
+ 2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
+ 3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
+ 4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
+ 5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
+ 6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
+ 7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
rcu_bh:
- 0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
- 1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
- 2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
- 3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
- 4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
- 5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
- 6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
- 7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
+ 0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
+ 1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
+ 2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+ 3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
+ 4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+ 5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+ 6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+ 7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
The first section lists the rcu_data structures for rcu, the second for
rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system.
@@ -253,12 +254,6 @@
o "qp" indicates that RCU still expects a quiescent state from
this CPU.
-o "rpfq" is the number of rcu_pending() calls on this CPU required
- to induce this CPU to invoke force_quiescent_state().
-
-o "rp" is low-order four hex digits of the count of how many times
- rcu_pending() has been invoked on this CPU.
-
o "dt" is the current value of the dyntick counter that is incremented
when entering or leaving dynticks idle state, either by the
scheduler or by irq. The number after the "/" is the interrupt
@@ -305,6 +300,9 @@
of RCU callbacks is ready to invoke, then the remainder will
be deferred.
+There is also an rcu/rcudata.csv file with the same information in
+comma-separated-variable spreadsheet format.
+
The output of "cat rcu/rcugp" looks as follows:
@@ -411,3 +409,63 @@
For example, the first entry at the lowest level shows
"^0", indicating that it corresponds to bit zero in
the first entry at the middle level.
+
+
+The output of "cat rcu/rcu_pending" looks as follows:
+
+rcu:
+ 0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+ 1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+ 2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+ 3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+ 4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+ 5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+ 6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+ 7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+rcu_bh:
+ 0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+ 1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+ 2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+ 3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+ 4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+ 5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+ 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+ 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+
+As always, this is once again split into "rcu" and "rcu_bh" portions.
+The fields are as follows:
+
+o "np" is the number of times that __rcu_pending() has been invoked
+ for the corresponding flavor of RCU.
+
+o "qsp" is the number of times that the RCU was waiting for a
+ quiescent state from this CPU.
+
+o "cbr" is the number of times that this CPU had RCU callbacks
+ that had passed through a grace period, and were thus ready
+ to be invoked.
+
+o "cng" is the number of times that this CPU needed another
+ grace period while RCU was idle.
+
+o "gpc" is the number of times that an old grace period had
+ completed, but this CPU was not yet aware of it.
+
+o "gps" is the number of times that a new grace period had started,
+ but this CPU was not yet aware of it.
+
+o "nf" is the number of times that this CPU suspected that the
+ current grace period had run for too long, and thus needed to
+ be forced.
+
+ Please note that "forcing" consists of sending resched IPIs
+ to holdout CPUs. If that CPU really still is in an old RCU
+ read-side critical section, then we really do have to wait for it.
+ The assumption behing "forcing" is that the CPU is not still in
+ an old RCU read-side critical section, but has not yet responded
+ for some other reason.
+
+o "nn" is the number of times that this CPU needed nothing. Alert
+ readers will note that the rcu "nn" number for a given CPU very
+ closely matches the rcu_bh "np" number for that same CPU. This
+ is due to short-circuit evaluation in rcu_pending().
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e649bd3..5710f43 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -198,6 +198,32 @@
at->prev = last;
}
+/**
+ * list_entry_rcu - get the struct for this entry
+ * @ptr: the &struct list_head pointer.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_entry_rcu(ptr, type, member) \
+ container_of(rcu_dereference(ptr), type, member)
+
+/**
+ * list_first_entry_rcu - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_first_entry_rcu(ptr, type, member) \
+ list_entry_rcu((ptr)->next, type, member)
+
#define __list_for_each_rcu(pos, head) \
for (pos = rcu_dereference((head)->next); \
pos != (head); \
@@ -214,9 +240,9 @@
* as long as the traversal is guarded by rcu_read_lock().
*/
#define list_for_each_entry_rcu(pos, head, member) \
- for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+ for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
prefetch(pos->member.next), &pos->member != (head); \
- pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+ pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
/**
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 58b2aa5..5a51538 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -161,8 +161,15 @@
unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long resched_ipi; /* Sent a resched IPI. */
- /* 5) For future __rcu_pending statistics. */
+ /* 5) __rcu_pending() statistics. */
long n_rcu_pending; /* rcu_pending() calls since boot. */
+ long n_rp_qs_pending;
+ long n_rp_cb_ready;
+ long n_rp_cpu_needs_gp;
+ long n_rp_gp_completed;
+ long n_rp_gp_started;
+ long n_rp_need_fqs;
+ long n_rp_need_nothing;
int cpu;
};
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dbb1043..d4646ae 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -77,6 +77,7 @@
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
+#include <linux/rculist.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
@@ -2030,7 +2031,8 @@
}
#endif
-#define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+ list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
@@ -2069,8 +2071,8 @@
static inline struct task_struct *next_thread(const struct task_struct *p)
{
- return list_entry(rcu_dereference(p->thread_group.next),
- struct task_struct, thread_group);
+ return list_entry_rcu(p->thread_group.next,
+ struct task_struct, thread_group);
}
static inline int thread_group_empty(struct task_struct *p)
diff --git a/init/Kconfig b/init/Kconfig
index 7be4d38..d4e9671 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -308,7 +308,7 @@
choice
prompt "RCU Implementation"
- default CLASSIC_RCU
+ default TREE_RCU
config CLASSIC_RCU
bool "Classic RCU"
diff --git a/ipc/sem.c b/ipc/sem.c
index 16a2189..87c2b64 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1290,8 +1290,8 @@
int i;
rcu_read_lock();
- un = list_entry(rcu_dereference(ulp->list_proc.next),
- struct sem_undo, list_proc);
+ un = list_entry_rcu(ulp->list_proc.next,
+ struct sem_undo, list_proc);
if (&un->list_proc == &ulp->list_proc)
semid = -1;
else
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index ce97a4d..beb0e65 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1356,17 +1356,11 @@
rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
- ret = 0;
+ ret = 0; /* unused */
__wait_event_interruptible(rcu_ctrlblk.sched_wq,
rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
ret);
- /*
- * Signals would prevent us from sleeping, and we cannot
- * do much with them in any case. So flush them.
- */
- if (ret)
- flush_signals(current);
couldsleepnext = 0;
} while (!kthread_should_stop());
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d2a372f..0dccfbb 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1259,31 +1259,44 @@
check_cpu_stall(rsp, rdp);
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->qs_pending)
+ if (rdp->qs_pending) {
+ rdp->n_rp_qs_pending++;
return 1;
+ }
/* Does this CPU have callbacks ready to invoke? */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+ rdp->n_rp_cb_ready++;
return 1;
+ }
/* Has RCU gone idle with this CPU needing another grace period? */
- if (cpu_needs_another_gp(rsp, rdp))
+ if (cpu_needs_another_gp(rsp, rdp)) {
+ rdp->n_rp_cpu_needs_gp++;
return 1;
+ }
/* Has another RCU grace period completed? */
- if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+ if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+ rdp->n_rp_gp_completed++;
return 1;
+ }
/* Has a new RCU grace period started? */
- if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+ if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+ rdp->n_rp_gp_started++;
return 1;
+ }
/* Has an RCU GP gone long enough to send resched IPIs &c? */
if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
- ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0))
+ ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
+ rdp->n_rp_need_fqs++;
return 1;
+ }
/* nothing to do */
+ rdp->n_rp_need_nothing++;
return 0;
}
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 4b1875b..fe1dcdb 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -213,7 +213,63 @@
.release = single_release,
};
-static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
+{
+ seq_printf(m, "%3d%cnp=%ld "
+ "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+ rdp->cpu,
+ cpu_is_offline(rdp->cpu) ? '!' : ' ',
+ rdp->n_rcu_pending,
+ rdp->n_rp_qs_pending,
+ rdp->n_rp_cb_ready,
+ rdp->n_rp_cpu_needs_gp,
+ rdp->n_rp_gp_completed,
+ rdp->n_rp_gp_started,
+ rdp->n_rp_need_fqs,
+ rdp->n_rp_need_nothing);
+}
+
+static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
+{
+ int cpu;
+ struct rcu_data *rdp;
+
+ for_each_possible_cpu(cpu) {
+ rdp = rsp->rda[cpu];
+ if (rdp->beenonline)
+ print_one_rcu_pending(m, rdp);
+ }
+}
+
+static int show_rcu_pending(struct seq_file *m, void *unused)
+{
+ seq_puts(m, "rcu:\n");
+ print_rcu_pendings(m, &rcu_state);
+ seq_puts(m, "rcu_bh:\n");
+ print_rcu_pendings(m, &rcu_bh_state);
+ return 0;
+}
+
+static int rcu_pending_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, show_rcu_pending, NULL);
+}
+
+static struct file_operations rcu_pending_fops = {
+ .owner = THIS_MODULE,
+ .open = rcu_pending_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *rcudir;
+static struct dentry *datadir;
+static struct dentry *datadir_csv;
+static struct dentry *gpdir;
+static struct dentry *hierdir;
+static struct dentry *rcu_pendingdir;
+
static int __init rcuclassic_trace_init(void)
{
rcudir = debugfs_create_dir("rcu", NULL);
@@ -238,6 +294,11 @@
NULL, &rcuhier_fops);
if (!hierdir)
goto free_out;
+
+ rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+ NULL, &rcu_pending_fops);
+ if (!rcu_pendingdir)
+ goto free_out;
return 0;
free_out:
if (datadir)
@@ -257,6 +318,7 @@
debugfs_remove(datadir_csv);
debugfs_remove(gpdir);
debugfs_remove(hierdir);
+ debugfs_remove(rcu_pendingdir);
debugfs_remove(rcudir);
}
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index ffbe259..510186f 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -84,8 +84,8 @@
* against concurrent list-extension
*/
rcu_read_lock();
- qe = list_entry(rcu_dereference(qe->later.next),
- struct ima_queue_entry, later);
+ qe = list_entry_rcu(qe->later.next,
+ struct ima_queue_entry, later);
rcu_read_unlock();
(*pos)++;
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index e03a7e1..11d2cb1 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -734,8 +734,8 @@
return;
}
- m = list_entry(rcu_dereference(smk_netlbladdr_list.next),
- struct smk_netlbladdr, list);
+ m = list_entry_rcu(smk_netlbladdr_list.next,
+ struct smk_netlbladdr, list);
/* the comparison '>' is a bit hacky, but works */
if (new->smk_mask.s_addr > m->smk_mask.s_addr) {
@@ -748,8 +748,8 @@
list_add_rcu(&new->list, &m->list);
return;
}
- m_next = list_entry(rcu_dereference(m->list.next),
- struct smk_netlbladdr, list);
+ m_next = list_entry_rcu(m->list.next,
+ struct smk_netlbladdr, list);
if (new->smk_mask.s_addr > m_next->smk_mask.s_addr) {
list_add_rcu(&new->list, &m->list);
return;