| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20100503004351.GA25163@linux.vnet.ibm.com>
Date: Sun, 2 May 2010 17:43:51 -0700
From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To: mingo@...e.hu
Cc: linux-kernel@...r.kernel.org, akpm@...ux-foundation.org,
a.p.zijlstra@...llo.nl, tglx@...utronix.de
Subject: [GIT PULL] RCU fixes for 2.6.34 and changes for 2.6.35
Hello, Ingo,
Here are RCU fixes for 2.6.34 and changes for 2.6.35.
The following will pull only the 2.6.34 fixes, which are RCU-lockdep fixes:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git urgent-to-mingo
The following will pull the 2.6.34 fixes plus the first installment of
2.6.35 changes:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git urgent-to-mingo
The changes include some fixes and cleanups from Lai Jiangshan,
application of debugobjects to detect RCU callback misbehavior and
abuse from Mathieu Desnoyers, and some TINY_RCU slimdowns and
RCU CPU stall-warning improvements from myself. Arnd and I are still
working on the sparse-based RCU-pointer debug checks, and I hope to
have it ready soon.
The 2.6.35 changes depend on the 2.6.34 fixes. If you would rather I use
some other organization, please let me know. For example, I could merge
the 2.6.34 fixes on top of tip/core/rcu, then apply the 2.6.35 changes,
if that would work better.
Thanx, Paul
------------------>
David Howells (2)
KEYS: Fix an RCU warning
KEYS: Fix an RCU warning in the reading of user keys
Lai Jiangshan (4)
rcu: ignore offline CPUs in last non-dyntick-idle CPU check
rcu: make dead code really dead
rcu: move some code from macro to function
rcu: v2: optionally leave lockdep enabled after RCU lockdep splat
Li Zefan (4)
cgroup: Check task_lock in task_subsys_state()
cgroup: Fix an RCU warning in alloc_css_id()
cgroup: Fix an RCU warning in cgroup_path()
sched: Fix an RCU warning in print_task()
Mathieu Desnoyers (6)
Debugobjects transition check
rcu: fix debugobjects rcu head init on stack in rcutree_plugin.h
rcu head introduce rcu head init on stack
rcu head remove init
remove all rcu head initializations, except on_stack initializations
tree/tiny rcu: Add debug RCU head objects (v5)
Paul E. McKenney (19)
memcg: css_id() must be called under rcu_read_lock()
rcu: disable CPU stall warnings upon panic
rcu: enable CPU_STALL_VERBOSE by default
rcu: Fix bogus CONFIG_PROVE_LOCKING in comments to reflect reality.
rcu: fix now-bogus rcu_scheduler_active comments.
rcu: improve RCU CPU stall-warning messages
rcu: improve the RCU CPU-stall warning documentation
rcu: make SRCU usable in modules
rcu: permit discontiguous cpu_possible_mask CPU numbering
rcu: print boot-time console messages if RCU configs out of ordinary
rcu: RCU_FAST_NO_HZ must check RCU dyntick state
rcu: refactor RCU's context-switch handling
rcu: rename rcutiny rcu_ctrlblk to rcu_sched_ctrlblk
rcu: shrink rcutiny by making synchronize_rcu_bh() be inline
rcu: slim down rcutiny by removing rcu_scheduler_active and friends
rcu: substitute set_need_resched for sending resched IPIs
rcu: v2: reduce the number of spurious RCU_SOFTIRQ invocations
vfs: fix RCU-lockdep false positive due to /proc access
blk-cgroup: Fix RCU correctness warning in cfq_init_queue()
Documentation/RCU/stallwarn.txt | 94 +++++++++++---
Documentation/RCU/trace.txt | 35 ++---
arch/powerpc/mm/pgtable.c | 1
block/cfq-iosched.c | 3
block/genhd.c | 1
drivers/staging/batman-adv/hard-interface.c | 1
fs/file.c | 3
fs/fs-writeback.c | 31 ++++
fs/partitions/check.c | 1
include/linux/cgroup.h | 1
include/linux/debugobjects.h | 11 +
include/linux/fdtable.h | 3
include/linux/init_task.h | 1
include/linux/rcupdate.h | 105 ++++++++++++----
include/linux/rcutiny.h | 29 ++++
include/linux/rcutree.h | 6
include/linux/srcu.h | 6
kernel/cgroup.c | 16 +-
kernel/cgroup_freezer.c | 5
kernel/lockdep.c | 2
kernel/rcupdate.c | 179 +++++++++++++++++++++++++---
kernel/rcutiny.c | 37 +++--
kernel/rcutiny_plugin.h | 39 ++++++
kernel/rcutorture.c | 2
kernel/rcutree.c | 133 +++++++++++++++-----
kernel/rcutree.h | 2
kernel/rcutree_plugin.h | 69 +++++++++-
kernel/rcutree_trace.c | 4
kernel/sched.c | 12 +
kernel/sched_debug.c | 2
kernel/softirq.c | 2
lib/Kconfig.debug | 20 ++-
lib/debugobjects.c | 59 ++++++++-
mm/backing-dev.c | 1
mm/memcontrol.c | 21 ++-
mm/slob.c | 1
security/keys/request_key.c | 13 +-
security/keys/user_defined.c | 3
security/selinux/avc.c | 1
security/selinux/netnode.c | 2
40 files changed, 773 insertions(+), 184 deletions(-)
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 1423d25..44c6dcc 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -3,35 +3,79 @@ Using RCU's CPU Stall Detector
The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
RCU's CPU stall detector, which detects conditions that unduly delay
RCU grace periods. The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a pair of C preprocessor macros:
+"unduly delayed" is controlled by a set of C preprocessor macros:
RCU_SECONDS_TILL_STALL_CHECK
This macro defines the period of time that RCU will wait from
the beginning of a grace period until it issues an RCU CPU
- stall warning. It is normally ten seconds.
+ stall warning. This time period is normally ten seconds.
RCU_SECONDS_TILL_STALL_RECHECK
This macro defines the period of time that RCU will wait after
- issuing a stall warning until it issues another stall warning.
- It is normally set to thirty seconds.
+ issuing a stall warning until it issues another stall warning
+ for the same stall. This time period is normally set to thirty
+ seconds.
RCU_STALL_RAT_DELAY
- The CPU stall detector tries to make the offending CPU rat on itself,
- as this often gives better-quality stack traces. However, if
- the offending CPU does not detect its own stall in the number
- of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
- complain. This is normally set to two jiffies.
+ The CPU stall detector tries to make the offending CPU print its
+ own warnings, as this often gives better-quality stack traces.
+ However, if the offending CPU does not detect its own stall in
+ the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+ some other CPU will complain. This delay is normally set to
+ two jiffies.
-The following problems can result in an RCU CPU stall warning:
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched. This message will normally be
+followed by a stack dump of the offending CPU. On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh. This message
+will normally be followed by stack dumps for each CPU. Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+
+This is rare, but does happen from time to time in real life.
+
+So your kernel printed an RCU CPU stall warning. The next question is
+"What caused it?" The following problems can result in RCU CPU stall
+warnings:
o A CPU looping in an RCU read-side critical section.
-o A CPU looping with interrupts disabled.
+o A CPU looping with interrupts disabled. This condition can
+ result in RCU-sched and RCU-bh stalls.
-o A CPU looping with preemption disabled.
+o A CPU looping with preemption disabled. This condition can
+ result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+ stalls.
+
+o A CPU looping with bottom halves disabled. This condition can
+ result in RCU-sched and RCU-bh stalls.
o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
without invoking schedule().
@@ -39,20 +83,24 @@ o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
o A bug in the RCU implementation.
o A hardware failure. This is quite unlikely, but has occurred
- at least once in a former life. A CPU failed in a running system,
+ at least once in real life. A CPU failed in a running system,
becoming unresponsive, but not causing an immediate crash.
This resulted in a series of RCU CPU stall warnings, eventually
leading the realization that the CPU had failed.
-The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
-SRCU does not do so directly, but its calls to synchronize_sched() will
-result in RCU-sched detecting any CPU stalls that might be occurring.
-
-To diagnose the cause of the stall, inspect the stack traces. The offending
-function will usually be near the top of the stack. If you have a series
-of stall warnings from a single extended stall, comparing the stack traces
-can often help determine where the stall is occurring, which will usually
-be in the function nearest the top of the stack that stays the same from
-trace to trace.
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning. SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls. Please note that RCU only detects
+CPU stalls when there is a grace period in progress. No grace period,
+no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd8..efd8cc9 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@ o Each element of the form "1/1 0:127 ^0" represents one struct
The output of "cat rcu/rcu_pending" looks as follows:
rcu_sched:
- 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
+ 0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+ 1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+ 2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+ 3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+ 4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+ 5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+ 6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+ 7 np=249893 qsp=49390 rpq=42 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
+ 0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+ 1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+ 2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+ 3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+ 4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+ 5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+ 6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+ 7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
As always, this is once again split into "rcu_sched" and "rcu_bh"
portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@ o "np" is the number of times that __rcu_pending() has been invoked
o "qsp" is the number of times that the RCU was waiting for a
quiescent state from this CPU.
+o "rpq" is the number of times that the CPU had passed through
+ a quiescent state, but not yet reported it to RCU.
+
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.
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index ebc2f38..2c7e801 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -92,7 +92,6 @@ static void pte_free_rcu_callback(struct rcu_head *head)
static void pte_free_submit(struct pte_freelist_batch *batch)
{
- INIT_RCU_HEAD(&batch->rcu);
call_rcu(&batch->rcu, pte_free_rcu_callback);
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 838834b..702d006 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3694,8 +3694,10 @@ static void *cfq_init_queue(struct request_queue *q)
* to make sure that cfq_put_cfqg() does not try to kfree root group
*/
atomic_set(&cfqg->ref, 1);
+ rcu_read_lock();
blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
0);
+ rcu_read_unlock();
#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
@@ -3741,7 +3743,6 @@ static void *cfq_init_queue(struct request_queue *q)
* second, in order to have larger depth for async operations.
*/
cfqd->last_delayed_sync = jiffies - HZ;
- INIT_RCU_HEAD(&cfqd->rcu);
return cfqd;
}
diff --git a/block/genhd.c b/block/genhd.c
index d13ba76..27e85a2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -987,7 +987,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
if (!new_ptbl)
return -ENOMEM;
- INIT_RCU_HEAD(&new_ptbl->rcu_head);
new_ptbl->len = target;
for (i = 0; i < len; i++)
diff --git a/drivers/staging/batman-adv/hard-interface.c b/drivers/staging/batman-adv/hard-interface.c
index befd488..96ea0e5 100644
--- a/drivers/staging/batman-adv/hard-interface.c
+++ b/drivers/staging/batman-adv/hard-interface.c
@@ -301,7 +301,6 @@ int hardif_add_interface(char *dev, int if_num)
batman_if->if_num = if_num;
batman_if->dev = dev;
batman_if->if_active = IF_INACTIVE;
- INIT_RCU_HEAD(&batman_if->rcu);
printk(KERN_INFO "batman-adv:Adding interface: %s\n", dev);
avail_ifs++;
diff --git a/fs/file.c b/fs/file.c
index 34bb7f7..cccaead 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -178,7 +178,6 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
fdt->open_fds = (fd_set *)data;
data += nr / BITS_PER_BYTE;
fdt->close_on_exec = (fd_set *)data;
- INIT_RCU_HEAD(&fdt->rcu);
fdt->next = NULL;
return fdt;
@@ -312,7 +311,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
new_fdt->fd = &newf->fd_array[0];
- INIT_RCU_HEAD(&new_fdt->rcu);
new_fdt->next = NULL;
spin_lock(&oldf->file_lock);
@@ -430,7 +428,6 @@ struct files_struct init_files = {
.fd = &init_files.fd_array[0],
.close_on_exec = (fd_set *)&init_files.close_on_exec_init,
.open_fds = (fd_set *)&init_files.open_fds_init,
- .rcu = RCU_HEAD_INIT,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
};
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 4b37f7c..ea38c65 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -75,12 +75,33 @@ static inline bool bdi_work_on_stack(struct bdi_work *work)
return test_bit(WS_ONSTACK_B, &work->state);
}
-static inline void bdi_work_init(struct bdi_work *work,
- struct wb_writeback_args *args)
+static inline void __bdi_work_init(struct bdi_work *work,
+ struct wb_writeback_args *args,
+ int on_stack)
{
- INIT_RCU_HEAD(&work->rcu_head);
work->args = *args;
work->state = WS_USED;
+ if (on_stack) {
+ work->state |= WS_ONSTACK;
+ init_rcu_head_on_stack(&work->rcu_head);
+ }
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+ struct wb_writeback_args *args)
+{
+ __bdi_work_init(work, args, false);
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+ struct wb_writeback_args *args)
+{
+ __bdi_work_init(work, args, true);
+}
+
+static inline void bdi_destroy_work_on_stack(struct bdi_work *work)
+{
+ destroy_rcu_head_on_stack(&work->rcu_head);
}
/**
@@ -233,11 +254,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
};
struct bdi_work work;
- bdi_work_init(&work, &args);
- work.state |= WS_ONSTACK;
+ bdi_work_init_on_stack(&work, &args);
bdi_queue_work(bdi, &work);
bdi_wait_on_work_clear(&work);
+ bdi_destroy_work_on_stack(&work);
}
/**
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index e238ab2..7444e6f 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -456,7 +456,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
}
/* everything is up and running, commence */
- INIT_RCU_HEAD(&p->rcu_head);
rcu_assign_pointer(ptbl->part[partno], p);
/* suppress uevent if the disk supresses it */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b8ad1ea..8f78073 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -530,6 +530,7 @@ static inline struct cgroup_subsys_state *task_subsys_state(
{
return rcu_dereference_check(task->cgroups->subsys[subsys_id],
rcu_read_lock_held() ||
+ lockdep_is_held(&task->alloc_lock) ||
cgroup_lock_is_held());
}
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 8c243aa..597692f 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -20,12 +20,14 @@ struct debug_obj_descr;
* struct debug_obj - representaion of an tracked object
* @node: hlist node to link the object into the tracker list
* @state: tracked object state
+ * @astate: current active state
* @object: pointer to the real object
* @descr: pointer to an object type specific debug description structure
*/
struct debug_obj {
struct hlist_node node;
enum debug_obj_state state;
+ unsigned int astate;
void *object;
struct debug_obj_descr *descr;
};
@@ -60,6 +62,15 @@ extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr);
extern void debug_object_free (void *addr, struct debug_obj_descr *descr);
+/*
+ * Active state:
+ * - Set at 0 upon initialization.
+ * - Must return to 0 before deactivation.
+ */
+extern void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+ unsigned int expect, unsigned int next);
+
extern void debug_objects_early_init(void);
extern void debug_objects_mem_init(void);
#else
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 013dc52..d147461 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -61,7 +61,8 @@ struct files_struct {
(rcu_dereference_check((fdtfd), \
rcu_read_lock_held() || \
lockdep_is_held(&(files)->file_lock) || \
- atomic_read(&(files)->count) == 1))
+ atomic_read(&(files)->count) == 1 || \
+ rcu_my_thread_group_empty()))
#define files_fdtable(files) \
(rcu_dereference_check_fdtable((files), (files)->fdt))
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b1ed1cd..7996fc2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -49,7 +49,6 @@ extern struct group_info init_groups;
{ .first = &init_task.pids[PIDTYPE_PGID].node }, \
{ .first = &init_task.pids[PIDTYPE_SID].node }, \
}, \
- .rcu = RCU_HEAD_INIT, \
.level = 0, \
.numbers = { { \
.nr = 0, \
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 07db2fe..2f9e56c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
#include <linux/seqlock.h>
#include <linux/lockdep.h>
#include <linux/completion.h>
+#include <linux/debugobjects.h>
#ifdef CONFIG_RCU_TORTURE_TEST
extern int rcutorture_runnable; /* for sysctl */
@@ -56,8 +57,6 @@ struct rcu_head {
};
/* Exported common interfaces */
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
extern void rcu_barrier(void);
extern void rcu_barrier_bh(void);
extern void rcu_barrier_sched(void);
@@ -66,8 +65,6 @@ extern int sched_expedited_torture_stats(char *page);
/* Internal to kernel */
extern void rcu_init(void);
-extern int rcu_scheduler_active;
-extern void rcu_scheduler_starting(void);
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
#include <linux/rcutree.h>
@@ -77,11 +74,24 @@ extern void rcu_scheduler_starting(void);
#error "Unknown RCU implementation specified to kernel configuration"
#endif
-#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
-#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
-#define INIT_RCU_HEAD(ptr) do { \
- (ptr)->next = NULL; (ptr)->func = NULL; \
-} while (0)
+/*
+ * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
+ * initialization and destruction of rcu_head on the stack. rcu_head structures
+ * allocated dynamically in the heap or defined statically don't need any
+ * initialization.
+ */
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+extern void init_rcu_head_on_stack(struct rcu_head *head);
+extern void destroy_rcu_head_on_stack(struct rcu_head *head);
+#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void init_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -106,12 +116,13 @@ extern int debug_lockdep_rcu_enabled(void);
/**
* rcu_read_lock_held - might we be in RCU read-side critical section?
*
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an RCU read-side critical section unless it can
* prove otherwise.
*
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
*/
static inline int rcu_read_lock_held(void)
{
@@ -129,13 +140,15 @@ extern int rcu_read_lock_bh_held(void);
/**
* rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
*
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
- * RCU-sched read-side critical section. In absence of CONFIG_PROVE_LOCKING,
- * this assumes we are in an RCU-sched read-side critical section unless it
- * can prove otherwise. Note that disabling of preemption (including
- * disabling irqs) counts as an RCU-sched read-side critical section.
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section. In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise. Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.
*
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
*/
#ifdef CONFIG_PREEMPT
static inline int rcu_read_lock_sched_held(void)
@@ -177,7 +190,7 @@ static inline int rcu_read_lock_bh_held(void)
#ifdef CONFIG_PREEMPT
static inline int rcu_read_lock_sched_held(void)
{
- return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled();
+ return preempt_count() != 0 || irqs_disabled();
}
#else /* #ifdef CONFIG_PREEMPT */
static inline int rcu_read_lock_sched_held(void)
@@ -190,6 +203,17 @@ static inline int rcu_read_lock_sched_held(void)
#ifdef CONFIG_PROVE_RCU
+extern int rcu_my_thread_group_empty(void);
+
+#define __do_rcu_dereference_check(c) \
+ do { \
+ static bool __warned; \
+ if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \
+ __warned = true; \
+ lockdep_rcu_dereference(__FILE__, __LINE__); \
+ } \
+ } while (0)
+
/**
* rcu_dereference_check - rcu_dereference with debug checking
* @p: The pointer to read, prior to dereferencing
@@ -219,8 +243,7 @@ static inline int rcu_read_lock_sched_held(void)
*/
#define rcu_dereference_check(p, c) \
({ \
- if (debug_lockdep_rcu_enabled() && !(c)) \
- lockdep_rcu_dereference(__FILE__, __LINE__); \
+ __do_rcu_dereference_check(c); \
rcu_dereference_raw(p); \
})
@@ -237,8 +260,7 @@ static inline int rcu_read_lock_sched_held(void)
*/
#define rcu_dereference_protected(p, c) \
({ \
- if (debug_lockdep_rcu_enabled() && !(c)) \
- lockdep_rcu_dereference(__FILE__, __LINE__); \
+ __do_rcu_dereference_check(c); \
(p); \
})
@@ -501,4 +523,41 @@ extern void call_rcu(struct rcu_head *head,
extern void call_rcu_bh(struct rcu_head *head,
void (*func)(struct rcu_head *head));
+/*
+ * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
+ * by call_rcu() and rcu callback execution, and are therefore not part of the
+ * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
+ */
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+# define STATE_RCU_HEAD_READY 0
+# define STATE_RCU_HEAD_QUEUED 1
+
+extern struct debug_obj_descr rcuhead_debug_descr;
+
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+ debug_object_activate(head, &rcuhead_debug_descr);
+ debug_object_active_state(head, &rcuhead_debug_descr,
+ STATE_RCU_HEAD_READY,
+ STATE_RCU_HEAD_QUEUED);
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+ debug_object_active_state(head, &rcuhead_debug_descr,
+ STATE_RCU_HEAD_QUEUED,
+ STATE_RCU_HEAD_READY);
+ debug_object_deactivate(head, &rcuhead_debug_descr);
+}
+#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+}
+#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
#endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index a519587..14e5a76 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -29,6 +29,10 @@
void rcu_sched_qs(int cpu);
void rcu_bh_qs(int cpu);
+static inline void rcu_note_context_switch(int cpu)
+{
+ rcu_sched_qs(cpu);
+}
#define __rcu_read_lock() preempt_disable()
#define __rcu_read_unlock() preempt_enable()
@@ -74,7 +78,17 @@ static inline void rcu_sched_force_quiescent_state(void)
{
}
-#define synchronize_rcu synchronize_sched
+extern void synchronize_sched(void);
+
+static inline void synchronize_rcu(void)
+{
+ synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh(void)
+{
+ synchronize_sched();
+}
static inline void synchronize_rcu_expedited(void)
{
@@ -114,4 +128,17 @@ static inline int rcu_preempt_depth(void)
return 0;
}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern int rcu_scheduler_active __read_mostly;
+extern void rcu_scheduler_starting(void);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline void rcu_scheduler_starting(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
#endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 42cc3a0..4828205 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,6 +34,7 @@ struct notifier_block;
extern void rcu_sched_qs(int cpu);
extern void rcu_bh_qs(int cpu);
+extern void rcu_note_context_switch(int cpu);
extern int rcu_needs_cpu(int cpu);
extern int rcu_expedited_torture_stats(char *page);
@@ -86,6 +87,8 @@ static inline void __rcu_read_unlock_bh(void)
extern void call_rcu_sched(struct rcu_head *head,
void (*func)(struct rcu_head *rcu));
+extern void synchronize_rcu_bh(void);
+extern void synchronize_sched(void);
extern void synchronize_rcu_expedited(void);
static inline void synchronize_rcu_bh_expedited(void)
@@ -120,4 +123,7 @@ static inline int rcu_blocking_is_gp(void)
return num_online_cpus() == 1;
}
+extern void rcu_scheduler_starting(void);
+extern int rcu_scheduler_active __read_mostly;
+
#endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5ecb2..4d5d2f5 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -27,6 +27,8 @@
#ifndef _LINUX_SRCU_H
#define _LINUX_SRCU_H
+#include <linux/mutex.h>
+
struct srcu_struct_array {
int c[2];
};
@@ -84,8 +86,8 @@ long srcu_batches_completed(struct srcu_struct *sp);
/**
* srcu_read_lock_held - might we be in SRCU read-side critical section?
*
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an SRCU read-side critical section. In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
+ * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
* this assumes we are in an SRCU read-side critical section unless it can
* prove otherwise.
*/
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2769e1..3a53c77 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1646,7 +1646,9 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
- struct dentry *dentry = rcu_dereference(cgrp->dentry);
+ struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!dentry || cgrp == dummytop) {
/*
@@ -1662,13 +1664,17 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
*--start = '\0';
for (;;) {
int len = dentry->d_name.len;
+
if ((start -= len) < buf)
return -ENAMETOOLONG;
- memcpy(start, cgrp->dentry->d_name.name, len);
+ memcpy(start, dentry->d_name.name, len);
cgrp = cgrp->parent;
if (!cgrp)
break;
- dentry = rcu_dereference(cgrp->dentry);
+
+ dentry = rcu_dereference_check(cgrp->dentry,
+ rcu_read_lock_held() ||
+ cgroup_lock_is_held());
if (!cgrp->parent)
continue;
if (--start < buf)
@@ -4555,13 +4561,13 @@ static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
{
int subsys_id, i, depth = 0;
struct cgroup_subsys_state *parent_css, *child_css;
- struct css_id *child_id, *parent_id = NULL;
+ struct css_id *child_id, *parent_id;
subsys_id = ss->subsys_id;
parent_css = parent->subsys[subsys_id];
child_css = child->subsys[subsys_id];
- depth = css_depth(parent_css) + 1;
parent_id = parent_css->id;
+ depth = parent_id->depth;
child_id = get_new_cssid(ss, depth);
if (IS_ERR(child_id))
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index da5e139..e5c0244 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -205,9 +205,12 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
* No lock is needed, since the task isn't on tasklist yet,
* so it can't be moved to another cgroup, which means the
* freezer won't be removed and will be valid during this
- * function call.
+ * function call. Nevertheless, apply RCU read-side critical
+ * section to suppress RCU lockdep false positives.
*/
+ rcu_read_lock();
freezer = task_freezer(task);
+ rcu_read_unlock();
/*
* The root cgroup is non-freezable, so we can skip the
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 2594e1c..73747b7 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3801,8 +3801,10 @@ void lockdep_rcu_dereference(const char *file, const int line)
{
struct task_struct *curr = current;
+#ifndef CONFIG_PROVE_RCU_REPEATEDLY
if (!debug_locks_off())
return;
+#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
printk("\n===================================================\n");
printk( "[ INFO: suspicious rcu_dereference_check() usage. ]\n");
printk( "---------------------------------------------------\n");
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 03a7ea1..be12514 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
-#include <linux/kernel_stat.h>
#include <linux/hardirq.h>
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -64,9 +63,6 @@ struct lockdep_map rcu_sched_lock_map =
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
#endif
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
int debug_lockdep_rcu_enabled(void)
@@ -97,21 +93,6 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
/*
- * This function is invoked towards the end of the scheduler's initialization
- * process. Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system). After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.
- */
-void rcu_scheduler_starting(void)
-{
- WARN_ON(num_online_cpus() != 1);
- WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = 1;
-}
-
-/*
* Awaken the corresponding synchronize_rcu() instance now that a
* grace period has elapsed.
*/
@@ -122,3 +103,163 @@ void wakeme_after_rcu(struct rcu_head *head)
rcu = container_of(head, struct rcu_synchronize, head);
complete(&rcu->completion);
}
+
+#ifdef CONFIG_PROVE_RCU
+/*
+ * wrapper function to avoid #include problems.
+ */
+int rcu_my_thread_group_empty(void)
+{
+ return thread_group_empty(current);
+}
+EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+static inline void debug_init_rcu_head(struct rcu_head *head)
+{
+ debug_object_init(head, &rcuhead_debug_descr);
+}
+
+static inline void debug_rcu_head_free(struct rcu_head *head)
+{
+ debug_object_free(head, &rcuhead_debug_descr);
+}
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct rcu_head *head = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ /*
+ * Ensure that queued callbacks are all executed.
+ * If we detect that we are nested in a RCU read-side critical
+ * section, we should simply fail, otherwise we would deadlock.
+ */
+#ifndef CONFIG_PREEMPT
+ WARN_ON(1);
+ return 0;
+#else
+ if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+ irqs_disabled()) {
+ WARN_ON(1);
+ return 0;
+ }
+ rcu_barrier();
+ rcu_barrier_sched();
+ rcu_barrier_bh();
+ debug_object_init(head, &rcuhead_debug_descr);
+ return 1;
+#endif
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ * Activation is performed internally by call_rcu().
+ */
+static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct rcu_head *head = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. We just make sure that it is
+ * tracked in the object tracker.
+ */
+ debug_object_init(head, &rcuhead_debug_descr);
+ debug_object_activate(head, &rcuhead_debug_descr);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ /*
+ * Ensure that queued callbacks are all executed.
+ * If we detect that we are nested in a RCU read-side critical
+ * section, we should simply fail, otherwise we would deadlock.
+ */
+#ifndef CONFIG_PREEMPT
+ WARN_ON(1);
+ return 0;
+#else
+ if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+ irqs_disabled()) {
+ WARN_ON(1);
+ return 0;
+ }
+ rcu_barrier();
+ rcu_barrier_sched();
+ rcu_barrier_bh();
+ debug_object_activate(head, &rcuhead_debug_descr);
+ return 1;
+#endif
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct rcu_head *head = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ /*
+ * Ensure that queued callbacks are all executed.
+ * If we detect that we are nested in a RCU read-side critical
+ * section, we should simply fail, otherwise we would deadlock.
+ */
+#ifndef CONFIG_PREEMPT
+ WARN_ON(1);
+ return 0;
+#else
+ if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
+ irqs_disabled()) {
+ WARN_ON(1);
+ return 0;
+ }
+ rcu_barrier();
+ rcu_barrier_sched();
+ rcu_barrier_bh();
+ debug_object_free(head, &rcuhead_debug_descr);
+ return 1;
+#endif
+ default:
+ return 0;
+ }
+}
+
+void init_rcu_head_on_stack(struct rcu_head *head)
+{
+ debug_object_init_on_stack(head, &rcuhead_debug_descr);
+}
+EXPORT_SYMBOL_GPL(init_rcu_head_on_stack);
+
+void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+ debug_object_free(head, &rcuhead_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
+
+struct debug_obj_descr rcuhead_debug_descr = {
+ .name = "rcu_head",
+ .fixup_init = rcuhead_fixup_init,
+ .fixup_activate = rcuhead_fixup_activate,
+ .fixup_free = rcuhead_fixup_free,
+};
+EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
+#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9f6d9ff..196ec02 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -44,9 +44,9 @@ struct rcu_ctrlblk {
};
/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_ctrlblk = {
- .donetail = &rcu_ctrlblk.rcucblist,
- .curtail = &rcu_ctrlblk.rcucblist,
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+ .donetail = &rcu_sched_ctrlblk.rcucblist,
+ .curtail = &rcu_sched_ctrlblk.rcucblist,
};
static struct rcu_ctrlblk rcu_bh_ctrlblk = {
@@ -54,6 +54,11 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
.curtail = &rcu_bh_ctrlblk.rcucblist,
};
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
#ifdef CONFIG_NO_HZ
static long rcu_dynticks_nesting = 1;
@@ -108,7 +113,8 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
*/
void rcu_sched_qs(int cpu)
{
- if (rcu_qsctr_help(&rcu_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk))
+ if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
+ rcu_qsctr_help(&rcu_bh_ctrlblk))
raise_softirq(RCU_SOFTIRQ);
}
@@ -163,6 +169,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
while (list) {
next = list->next;
prefetch(next);
+ debug_rcu_head_unqueue(list);
list->func(list);
list = next;
}
@@ -173,7 +180,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
*/
static void rcu_process_callbacks(struct softirq_action *unused)
{
- __rcu_process_callbacks(&rcu_ctrlblk);
+ __rcu_process_callbacks(&rcu_sched_ctrlblk);
__rcu_process_callbacks(&rcu_bh_ctrlblk);
}
@@ -187,7 +194,8 @@ static void rcu_process_callbacks(struct softirq_action *unused)
*
* Cool, huh? (Due to Josh Triplett.)
*
- * But we want to make this a static inline later.
+ * But we want to make this a static inline later. The cond_resched()
+ * currently makes this problematic.
*/
void synchronize_sched(void)
{
@@ -195,12 +203,6 @@ void synchronize_sched(void)
}
EXPORT_SYMBOL_GPL(synchronize_sched);
-void synchronize_rcu_bh(void)
-{
- synchronize_sched();
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
/*
* Helper function for call_rcu() and call_rcu_bh().
*/
@@ -210,6 +212,7 @@ static void __call_rcu(struct rcu_head *head,
{
unsigned long flags;
+ debug_rcu_head_queue(head);
head->func = func;
head->next = NULL;
@@ -226,7 +229,7 @@ static void __call_rcu(struct rcu_head *head,
*/
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
- __call_rcu(head, func, &rcu_ctrlblk);
+ __call_rcu(head, func, &rcu_sched_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu);
@@ -244,11 +247,13 @@ void rcu_barrier(void)
{
struct rcu_synchronize rcu;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
@@ -256,11 +261,13 @@ void rcu_barrier_bh(void)
{
struct rcu_synchronize rcu;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_bh(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(rcu_barrier_bh);
@@ -268,11 +275,13 @@ void rcu_barrier_sched(void)
{
struct rcu_synchronize rcu;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_sched(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
@@ -280,3 +289,5 @@ void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
}
+
+#include "rcutiny_plugin.h"
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
new file mode 100644
index 0000000..d223a92
--- /dev/null
+++ b/kernel/rcutiny_plugin.h
@@ -0,0 +1,39 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Internal non-public definitions that provide either classic
+ * or preemptable semantics.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2009
+ *
+ * Author: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
+ */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+#include <linux/kernel_stat.h>
+
+/*
+ * During boot, we forgive RCU lockdep issues. After this function is
+ * invoked, we start taking RCU lockdep issues seriously.
+ */
+void rcu_scheduler_starting(void)
+{
+ WARN_ON(nr_context_switches() > 0);
+ rcu_scheduler_active = 1;
+}
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55b..077defb 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -464,9 +464,11 @@ static void rcu_bh_torture_synchronize(void)
{
struct rcu_bh_torture_synchronize rcu;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb);
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
static struct rcu_torture_ops rcu_bh_ops = {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 3ec8160..d5bc439 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,6 +46,7 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
+#include <linux/kernel_stat.h>
#include "rcutree.h"
@@ -53,8 +54,8 @@
static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
-#define RCU_STATE_INITIALIZER(name) { \
- .level = { &name.node[0] }, \
+#define RCU_STATE_INITIALIZER(structname) { \
+ .level = { &structname.node[0] }, \
.levelcnt = { \
NUM_RCU_LVL_0, /* root of hierarchy. */ \
NUM_RCU_LVL_1, \
@@ -65,13 +66,14 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
.signaled = RCU_GP_IDLE, \
.gpnum = -300, \
.completed = -300, \
- .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&name.onofflock), \
+ .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
.orphan_cbs_list = NULL, \
- .orphan_cbs_tail = &name.orphan_cbs_list, \
+ .orphan_cbs_tail = &structname.orphan_cbs_list, \
.orphan_qlen = 0, \
- .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&name.fqslock), \
+ .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
+ .name = #structname, \
}
struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state);
@@ -80,6 +82,9 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+
/*
* 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
@@ -97,25 +102,32 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
*/
void rcu_sched_qs(int cpu)
{
- struct rcu_data *rdp;
+ struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
- rdp = &per_cpu(rcu_sched_data, cpu);
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
- rcu_preempt_note_context_switch(cpu);
}
void rcu_bh_qs(int cpu)
{
- struct rcu_data *rdp;
+ struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
- rdp = &per_cpu(rcu_bh_data, cpu);
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
}
+/*
+ * Note a context switch. This is a quiescent state for RCU-sched,
+ * and requires special handling for preemptible RCU.
+ */
+void rcu_note_context_switch(int cpu)
+{
+ rcu_sched_qs(cpu);
+ rcu_preempt_note_context_switch(cpu);
+}
+
#ifdef CONFIG_NO_HZ
DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = 1,
@@ -438,6 +450,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+int rcu_cpu_stall_panicking __read_mostly;
+
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
rsp->gp_start = jiffies;
@@ -470,7 +484,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
/* OK, time to rat on our buddy... */
- printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+ printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
+ rsp->name);
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
rcu_print_task_stall(rnp);
@@ -481,7 +496,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
if (rnp->qsmask & (1UL << cpu))
printk(" %d", rnp->grplo + cpu);
}
- printk(" (detected by %d, t=%ld jiffies)\n",
+ printk("} (detected by %d, t=%ld jiffies)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start));
trigger_all_cpu_backtrace();
@@ -497,8 +512,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
unsigned long flags;
struct rcu_node *rnp = rcu_get_root(rsp);
- printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
- smp_processor_id(), jiffies - rsp->gp_start);
+ printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
+ rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
trigger_all_cpu_backtrace();
raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -515,6 +530,8 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
long delta;
struct rcu_node *rnp;
+ if (rcu_cpu_stall_panicking)
+ return;
delta = jiffies - rsp->jiffies_stall;
rnp = rdp->mynode;
if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
@@ -529,6 +546,21 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
}
}
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+ rcu_cpu_stall_panicking = 1;
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+ .notifier_call = rcu_panic,
+};
+
+static void __init check_cpu_stall_init(void)
+{
+ atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+}
+
#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -539,6 +571,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
}
+static void __init check_cpu_stall_init(void)
+{
+}
+
#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
/*
@@ -1076,6 +1112,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
while (list) {
next = list->next;
prefetch(next);
+ debug_rcu_head_unqueue(list);
list->func(list);
list = next;
if (++count >= rdp->blimit)
@@ -1125,8 +1162,6 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
*/
void rcu_check_callbacks(int cpu, int user)
{
- if (!rcu_pending(cpu))
- return; /* if nothing for RCU to do. */
if (user ||
(idle_cpu(cpu) && rcu_scheduler_active &&
!in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
@@ -1158,7 +1193,8 @@ void rcu_check_callbacks(int cpu, int user)
rcu_bh_qs(cpu);
}
rcu_preempt_check_callbacks(cpu);
- raise_softirq(RCU_SOFTIRQ);
+ if (rcu_pending(cpu))
+ raise_softirq(RCU_SOFTIRQ);
}
#ifdef CONFIG_SMP
@@ -1236,11 +1272,11 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
break; /* grace period idle or initializing, ignore. */
case RCU_SAVE_DYNTICK:
-
- raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
break; /* So gcc recognizes the dead code. */
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+
/* Record dyntick-idle state. */
force_qs_rnp(rsp, dyntick_save_progress_counter);
raw_spin_lock(&rnp->lock); /* irqs already disabled */
@@ -1353,6 +1389,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
unsigned long flags;
struct rcu_data *rdp;
+ debug_rcu_head_queue(head);
head->func = func;
head->next = NULL;
@@ -1449,11 +1486,13 @@ void synchronize_sched(void)
if (rcu_blocking_is_gp())
return;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_sched(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(synchronize_sched);
@@ -1473,11 +1512,13 @@ void synchronize_rcu_bh(void)
if (rcu_blocking_is_gp())
return;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_bh(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
@@ -1498,8 +1539,20 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
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->passed_quiesc) {
+
+ /*
+ * If force_quiescent_state() coming soon and this CPU
+ * needs a quiescent state, and this is either RCU-sched
+ * or RCU-bh, force a local reschedule.
+ */
rdp->n_rp_qs_pending++;
+ if (!rdp->preemptable &&
+ ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
+ jiffies))
+ set_need_resched();
+ } else if (rdp->qs_pending && rdp->passed_quiesc) {
+ rdp->n_rp_report_qs++;
return 1;
}
@@ -1767,6 +1820,21 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
}
/*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process. Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system). After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections. This function also enables RCU lockdep checking.
+ */
+void rcu_scheduler_starting(void)
+{
+ WARN_ON(num_online_cpus() != 1);
+ WARN_ON(nr_context_switches() > 0);
+ rcu_scheduler_active = 1;
+}
+
+/*
* Compute the per-level fanout, either using the exact fanout specified
* or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
*/
@@ -1849,6 +1917,14 @@ static void __init rcu_init_one(struct rcu_state *rsp)
INIT_LIST_HEAD(&rnp->blocked_tasks[3]);
}
}
+
+ rnp = rsp->level[NUM_RCU_LVLS - 1];
+ for_each_possible_cpu(i) {
+ while (i > rnp->grphi)
+ rnp++;
+ rsp->rda[i]->mynode = rnp;
+ rcu_boot_init_percpu_data(i, rsp);
+ }
}
/*
@@ -1859,19 +1935,11 @@ static void __init rcu_init_one(struct rcu_state *rsp)
#define RCU_INIT_FLAVOR(rsp, rcu_data) \
do { \
int i; \
- int j; \
- struct rcu_node *rnp; \
\
- rcu_init_one(rsp); \
- rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
- j = 0; \
for_each_possible_cpu(i) { \
- if (i > rnp[j].grphi) \
- j++; \
- per_cpu(rcu_data, i).mynode = &rnp[j]; \
(rsp)->rda[i] = &per_cpu(rcu_data, i); \
- rcu_boot_init_percpu_data(i, rsp); \
} \
+ rcu_init_one(rsp); \
} while (0)
void __init rcu_init(void)
@@ -1879,12 +1947,6 @@ void __init rcu_init(void)
int cpu;
rcu_bootup_announce();
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
- printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#if NUM_RCU_LVL_4 != 0
- printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n");
-#endif /* #if NUM_RCU_LVL_4 != 0 */
RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
__rcu_init_preempt();
@@ -1898,6 +1960,7 @@ void __init rcu_init(void)
cpu_notifier(rcu_cpu_notify, 0);
for_each_online_cpu(cpu)
rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+ check_cpu_stall_init();
}
#include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4a525a3..14c040b 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -223,6 +223,7 @@ struct rcu_data {
/* 5) __rcu_pending() statistics. */
unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */
unsigned long n_rp_qs_pending;
+ unsigned long n_rp_report_qs;
unsigned long n_rp_cb_ready;
unsigned long n_rp_cpu_needs_gp;
unsigned long n_rp_gp_completed;
@@ -326,6 +327,7 @@ struct rcu_state {
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+ char *name; /* Name of structure. */
};
/* Return values for rcu_preempt_offline_tasks(). */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 79b53bd..92e5c9b 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -26,6 +26,45 @@
#include <linux/delay.h>
+/*
+ * Check the RCU kernel configuration parameters and print informative
+ * messages about anything out of the ordinary. If you like #ifdef, you
+ * will love this function.
+ */
+static void __init rcu_bootup_announce_oddness(void)
+{
+#ifdef CONFIG_RCU_TRACE
+ printk(KERN_INFO "\tRCU debugfs-based tracing is enabled.\n");
+#endif
+#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)
+ printk(KERN_INFO "\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
+ CONFIG_RCU_FANOUT);
+#endif
+#ifdef CONFIG_RCU_FANOUT_EXACT
+ printk(KERN_INFO "\tHierarchical RCU autobalancing is disabled.\n");
+#endif
+#ifdef CONFIG_RCU_FAST_NO_HZ
+ printk(KERN_INFO
+ "\tRCU dyntick-idle grace-period acceleration is enabled.\n");
+#endif
+#ifdef CONFIG_PROVE_RCU
+ printk(KERN_INFO "\tRCU lockdep checking is enabled.\n");
+#endif
+#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
+ printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
+ printk(KERN_INFO
+ "\tRCU-based detection of stalled CPUs is disabled.\n");
+#endif
+#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+ printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
+#endif
+#if NUM_RCU_LVL_4 != 0
+ printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n");
+#endif
+}
+
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
@@ -38,8 +77,8 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
*/
static void __init rcu_bootup_announce(void)
{
- printk(KERN_INFO
- "Experimental preemptable hierarchical RCU implementation.\n");
+ printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+ rcu_bootup_announce_oddness();
}
/*
@@ -75,13 +114,19 @@ EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
* that this just means that the task currently running on the CPU is
* not in a quiescent state. There might be any number of tasks blocked
* while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
*/
static void rcu_preempt_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
+
rdp->passed_quiesc_completed = rdp->gpnum - 1;
barrier();
rdp->passed_quiesc = 1;
+ current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
}
/*
@@ -144,9 +189,8 @@ static void rcu_preempt_note_context_switch(int cpu)
* grace period, then the fact that the task has been enqueued
* means that we continue to block the current grace period.
*/
- rcu_preempt_qs(cpu);
local_irq_save(flags);
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ rcu_preempt_qs(cpu);
local_irq_restore(flags);
}
@@ -236,7 +280,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
*/
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
rcu_preempt_qs(smp_processor_id());
}
@@ -473,7 +516,6 @@ static void rcu_preempt_check_callbacks(int cpu)
struct task_struct *t = current;
if (t->rcu_read_lock_nesting == 0) {
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
rcu_preempt_qs(cpu);
return;
}
@@ -515,11 +557,13 @@ void synchronize_rcu(void)
if (!rcu_scheduler_active)
return;
+ init_rcu_head_on_stack(&rcu.head);
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu(&rcu.head, wakeme_after_rcu);
/* Wait for it. */
wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
@@ -754,6 +798,7 @@ void exit_rcu(void)
static void __init rcu_bootup_announce(void)
{
printk(KERN_INFO "Hierarchical RCU implementation.\n");
+ rcu_bootup_announce_oddness();
}
/*
@@ -1008,6 +1053,8 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
int rcu_needs_cpu(int cpu)
{
int c = 0;
+ int snap;
+ int snap_nmi;
int thatcpu;
/* Check for being in the holdoff period. */
@@ -1015,12 +1062,18 @@ int rcu_needs_cpu(int cpu)
return rcu_needs_cpu_quick_check(cpu);
/* Don't bother unless we are the last non-dyntick-idle CPU. */
- for_each_cpu_not(thatcpu, nohz_cpu_mask)
- if (thatcpu != cpu) {
+ for_each_online_cpu(thatcpu) {
+ if (thatcpu == cpu)
+ continue;
+ snap = per_cpu(rcu_dynticks, thatcpu)->dynticks;
+ snap_nmi = per_cpu(rcu_dynticks, thatcpu)->dynticks_nmi;
+ smp_mb(); /* Order sampling of snap with end of grace period. */
+ if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
per_cpu(rcu_dyntick_drain, cpu) = 0;
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
return rcu_needs_cpu_quick_check(cpu);
}
+ }
/* Check and update the rcu_dyntick_drain sequencing. */
if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d45db2e..36c95b4 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -241,11 +241,13 @@ static const struct file_operations rcugp_fops = {
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",
+ "qsp=%ld rpq=%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_report_qs,
rdp->n_rp_cb_ready,
rdp->n_rp_cpu_needs_gp,
rdp->n_rp_gp_completed,
diff --git a/kernel/sched.c b/kernel/sched.c
index de0bd26..d8a213c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -323,6 +323,15 @@ static inline struct task_group *task_group(struct task_struct *p)
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
+ /*
+ * Strictly speaking this rcu_read_lock() is not needed since the
+ * task_group is tied to the cgroup, which in turn can never go away
+ * as long as there are tasks attached to it.
+ *
+ * However since task_group() uses task_subsys_state() which is an
+ * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
+ */
+ rcu_read_lock();
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
p->se.parent = task_group(p)->se[cpu];
@@ -332,6 +341,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
p->rt.rt_rq = task_group(p)->rt_rq[cpu];
p->rt.parent = task_group(p)->rt_se[cpu];
#endif
+ rcu_read_unlock();
}
#else
@@ -3696,7 +3706,7 @@ need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
- rcu_sched_qs(cpu);
+ rcu_note_context_switch(cpu);
prev = rq->curr;
switch_count = &prev->nivcsw;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9b49db1..19be00b 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -114,7 +114,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
char path[64];
+ rcu_read_lock();
cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
+ rcu_read_unlock();
SEQ_printf(m, " %s", path);
}
#endif
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7c1a67e..0db913a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -716,7 +716,7 @@ static int run_ksoftirqd(void * __bind_cpu)
preempt_enable_no_resched();
cond_resched();
preempt_disable();
- rcu_sched_qs((long)__bind_cpu);
+ rcu_note_context_switch((long)__bind_cpu);
}
preempt_enable();
set_current_state(TASK_INTERRUPTIBLE);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 935248b..8689646 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -307,6 +307,12 @@ config DEBUG_OBJECTS_WORK
work queue routines to track the life time of work objects and
validate the work operations.
+config DEBUG_OBJECTS_RCU_HEAD
+ bool "Debug RCU callbacks objects"
+ depends on DEBUG_OBJECTS
+ help
+ Enable this to turn on debugging of RCU list heads (call_rcu() usage).
+
config DEBUG_OBJECTS_ENABLE_DEFAULT
int "debug_objects bootup default value (0-1)"
range 0 1
@@ -512,6 +518,18 @@ config PROVE_RCU
Say N if you are unsure.
+config PROVE_RCU_REPEATEDLY
+ bool "RCU debugging: don't disable PROVE_RCU on first splat"
+ depends on PROVE_RCU
+ default n
+ help
+ By itself, PROVE_RCU will disable checking upon issuing the
+ first warning (or "splat"). This feature prevents such
+ disabling, allowing multiple RCU-lockdep warnings to be printed
+ on a single reboot.
+
+ Say N if you are unsure.
+
config LOCKDEP
bool
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -793,7 +811,7 @@ config RCU_CPU_STALL_DETECTOR
config RCU_CPU_STALL_VERBOSE
bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
- default n
+ default y
help
This option causes RCU to printk detailed per-task information
for any tasks that are stalling the current RCU grace period.
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index b862b30..076464f 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -141,6 +141,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
obj->object = addr;
obj->descr = descr;
obj->state = ODEBUG_STATE_NONE;
+ obj->astate = 0;
hlist_del(&obj->node);
hlist_add_head(&obj->node, &b->list);
@@ -252,8 +253,10 @@ static void debug_print_object(struct debug_obj *obj, char *msg)
if (limit < 5 && obj->descr != descr_test) {
limit++;
- WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
- obj_states[obj->state], obj->descr->name);
+ WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) "
+ "object type: %s\n",
+ msg, obj_states[obj->state], obj->astate,
+ obj->descr->name);
}
debug_objects_warnings++;
}
@@ -447,7 +450,10 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
case ODEBUG_STATE_INIT:
case ODEBUG_STATE_INACTIVE:
case ODEBUG_STATE_ACTIVE:
- obj->state = ODEBUG_STATE_INACTIVE;
+ if (!obj->astate)
+ obj->state = ODEBUG_STATE_INACTIVE;
+ else
+ debug_print_object(obj, "deactivate");
break;
case ODEBUG_STATE_DESTROYED:
@@ -553,6 +559,53 @@ out_unlock:
raw_spin_unlock_irqrestore(&db->lock, flags);
}
+/**
+ * debug_object_active_state - debug checks object usage state machine
+ * @addr: address of the object
+ * @descr: pointer to an object specific debug description structure
+ * @expect: expected state
+ * @next: state to move to if expected state is found
+ */
+void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+ unsigned int expect, unsigned int next)
+{
+ struct debug_bucket *db;
+ struct debug_obj *obj;
+ unsigned long flags;
+
+ if (!debug_objects_enabled)
+ return;
+
+ db = get_bucket((unsigned long) addr);
+
+ raw_spin_lock_irqsave(&db->lock, flags);
+
+ obj = lookup_object(addr, db);
+ if (obj) {
+ switch (obj->state) {
+ case ODEBUG_STATE_ACTIVE:
+ if (obj->astate == expect)
+ obj->astate = next;
+ else
+ debug_print_object(obj, "active_state");
+ break;
+
+ default:
+ debug_print_object(obj, "active_state");
+ break;
+ }
+ } else {
+ struct debug_obj o = { .object = addr,
+ .state = ODEBUG_STATE_NOTAVAILABLE,
+ .descr = descr };
+
+ debug_print_object(&o, "active_state");
+ }
+
+ raw_spin_unlock_irqrestore(&db->lock, flags);
+}
+
#ifdef CONFIG_DEBUG_OBJECTS_FREE
static void __debug_check_no_obj_freed(const void *address, unsigned long size)
{
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f13e067..1bba4ae 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -656,7 +656,6 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
spin_lock_init(&bdi->wb_lock);
- INIT_RCU_HEAD(&bdi->rcu_head);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->wb_list);
INIT_LIST_HEAD(&bdi->work_list);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ede99..e06490d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -811,10 +811,12 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
* enabled in "curr" and "curr" is a child of "mem" in *cgroup*
* hierarchy(even if use_hierarchy is disabled in "mem").
*/
+ rcu_read_lock();
if (mem->use_hierarchy)
ret = css_is_ancestor(&curr->css, &mem->css);
else
ret = (curr == mem);
+ rcu_read_unlock();
css_put(&curr->css);
return ret;
}
@@ -2312,7 +2314,9 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
/* record memcg information */
if (do_swap_account && swapout && memcg) {
+ rcu_read_lock();
swap_cgroup_record(ent, css_id(&memcg->css));
+ rcu_read_unlock();
mem_cgroup_get(memcg);
}
if (swapout && memcg)
@@ -2369,8 +2373,10 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
{
unsigned short old_id, new_id;
+ rcu_read_lock();
old_id = css_id(&from->css);
new_id = css_id(&to->css);
+ rcu_read_unlock();
if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
mem_cgroup_swap_statistics(from, false);
@@ -4038,11 +4044,16 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
put_page(page);
}
/* throught */
- if (ent.val && do_swap_account && !ret &&
- css_id(&mc.from->css) == lookup_swap_cgroup(ent)) {
- ret = MC_TARGET_SWAP;
- if (target)
- target->ent = ent;
+ if (ent.val && do_swap_account && !ret) {
+ unsigned short id;
+ rcu_read_lock();
+ id = css_id(&mc.from->css);
+ rcu_read_unlock();
+ if (id == lookup_swap_cgroup(ent)) {
+ ret = MC_TARGET_SWAP;
+ if (target)
+ target->ent = ent;
+ }
}
return ret;
}
diff --git a/mm/slob.c b/mm/slob.c
index 837ebd6..6de238d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -647,7 +647,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
- INIT_RCU_HEAD(&slob_rcu->head);
slob_rcu->size = c->size;
call_rcu(&slob_rcu->head, kmem_rcu_free);
} else {
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 03fe63e..ea97c31 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -68,7 +68,8 @@ static int call_sbin_request_key(struct key_construction *cons,
{
const struct cred *cred = current_cred();
key_serial_t prkey, sskey;
- struct key *key = cons->key, *authkey = cons->authkey, *keyring;
+ struct key *key = cons->key, *authkey = cons->authkey, *keyring,
+ *session;
char *argv[9], *envp[3], uid_str[12], gid_str[12];
char key_str[12], keyring_str[3][12];
char desc[20];
@@ -112,10 +113,12 @@ static int call_sbin_request_key(struct key_construction *cons,
if (cred->tgcred->process_keyring)
prkey = cred->tgcred->process_keyring->serial;
- if (cred->tgcred->session_keyring)
- sskey = rcu_dereference(cred->tgcred->session_keyring)->serial;
- else
- sskey = cred->user->session_keyring->serial;
+ rcu_read_lock();
+ session = rcu_dereference(cred->tgcred->session_keyring);
+ if (!session)
+ session = cred->user->session_keyring;
+ sskey = session->serial;
+ rcu_read_unlock();
sprintf(keyring_str[2], "%d", sskey);
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 7c687d5..e9aa079 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -199,7 +199,8 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen)
struct user_key_payload *upayload;
long ret;
- upayload = rcu_dereference(key->payload.data);
+ upayload = rcu_dereference_protected(
+ key->payload.data, rwsem_is_locked(&((struct key *)key)->sem));
ret = upayload->datalen;
/* we can return the data as is */
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 989fef8..bf4e3bc 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -288,7 +288,6 @@ static struct avc_node *avc_alloc_node(void)
if (!node)
goto out;
- INIT_RCU_HEAD(&node->rhead);
INIT_HLIST_NODE(&node->list);
avc_cache_stats_incr(allocations);
diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index dc92792..65ebfe9 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -183,8 +183,6 @@ static void sel_netnode_insert(struct sel_netnode *node)
BUG();
}
- INIT_RCU_HEAD(&node->rcu);
-
/* we need to impose a limit on the growth of the hash table so check
* this bucket to make sure it is within the specified bounds */
list_add_rcu(&node->list, &sel_netnode_hash[idx].list);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists