Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/linux-2.6-tip

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (78 commits)
  Revert "rcu: Decrease memory-barrier usage based on semi-formal proof"
  net,rcu: convert call_rcu(prl_entry_destroy_rcu) to kfree
  batman,rcu: convert call_rcu(softif_neigh_free_rcu) to kfree_rcu
  batman,rcu: convert call_rcu(neigh_node_free_rcu) to kfree()
  batman,rcu: convert call_rcu(gw_node_free_rcu) to kfree_rcu
  net,rcu: convert call_rcu(kfree_tid_tx) to kfree_rcu()
  net,rcu: convert call_rcu(xt_osf_finger_free_rcu) to kfree_rcu()
  net/mac80211,rcu: convert call_rcu(work_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(wq_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(phonet_device_rcu_free) to kfree_rcu()
  perf,rcu: convert call_rcu(swevent_hlist_release_rcu) to kfree_rcu()
  perf,rcu: convert call_rcu(free_ctx) to kfree_rcu()
  net,rcu: convert call_rcu(__nf_ct_ext_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(net_generic_release) to kfree_rcu()
  net,rcu: convert call_rcu(netlbl_unlhsh_free_addr6) to kfree_rcu()
  net,rcu: convert call_rcu(netlbl_unlhsh_free_addr4) to kfree_rcu()
  security,rcu: convert call_rcu(sel_netif_free) to kfree_rcu()
  net,rcu: convert call_rcu(xps_dev_maps_release) to kfree_rcu()
  net,rcu: convert call_rcu(xps_map_release) to kfree_rcu()
  net,rcu: convert call_rcu(rps_map_release) to kfree_rcu()
  ...

Documentation/RCU/00-INDEX

@@ -21,7 +21,7 @@ rcu.txt
 RTFP.txt
 	- List of RCU papers (bibliography) going back to 1980.
 stallwarn.txt
-	- RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
+	- RCU CPU stall warnings (module parameter rcu_cpu_stall_suppress)
 torture.txt
 	- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt

Documentation/RCU/stallwarn.txt

@@ -1,22 +1,25 @@
 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 set of C preprocessor macros:
+The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
+detector, which detects conditions that unduly delay RCU grace periods.
+This module parameter enables CPU stall detection by default, but
+may be overridden via boot-time parameter or at runtime via sysfs.
+The stall detector's idea of what constitutes "unduly delayed" is
+controlled by a set of kernel configuration variables and cpp macros:
 
-RCU_SECONDS_TILL_STALL_CHECK
+CONFIG_RCU_CPU_STALL_TIMEOUT
 
-	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.	This time period is normally ten seconds.
+	This kernel configuration parameter defines the period of time
+	that RCU will wait from the beginning of a grace period until it
+	issues an RCU CPU 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
-	for the same stall.  This time period is normally set to thirty
-	seconds.
+	for the same stall.  This time period is normally set to three
+	times the check interval plus thirty seconds.
 
 RCU_STALL_RAT_DELAY
 

Documentation/filesystems/proc.txt

@@ -836,7 +836,6 @@ Provides counts of softirq handlers serviced since boot time, for each cpu.
  TASKLET:          0          0          0        290
    SCHED:      27035      26983      26971      26746
  HRTIMER:          0          0          0          0
-     RCU:       1678       1769       2178       2250
 
 
 1.3 IDE devices in /proc/ide

drivers/net/ixgbe/ixgbe_main.c

@@ -5100,11 +5100,6 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter)
 	return err;
 }
 
-static void ring_free_rcu(struct rcu_head *head)
-{
-	kfree(container_of(head, struct ixgbe_ring, rcu));
-}
-
 /**
  * ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings
  * @adapter: board private structure to clear interrupt scheme on
@@ -5126,7 +5121,7 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
 		/* ixgbe_get_stats64() might access this ring, we must wait
 		 * a grace period before freeing it.
 		 */
-		call_rcu(&ring->rcu, ring_free_rcu);
+		kfree_rcu(ring, rcu);
 		adapter->rx_ring[i] = NULL;
 	}
 

drivers/net/macvlan.c

@@ -603,21 +603,13 @@ static int macvlan_port_create(struct net_device *dev)
 	return err;
 }
 
-static void macvlan_port_rcu_free(struct rcu_head *head)
-{
-	struct macvlan_port *port;
-
-	port = container_of(head, struct macvlan_port, rcu);
-	kfree(port);
-}
-
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get(dev);
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
-	call_rcu(&port->rcu, macvlan_port_rcu_free);
+	kfree_rcu(port, rcu);
 }
 
 static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])

include/linux/interrupt.h

@@ -414,7 +414,6 @@ enum
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
-	RCU_SOFTIRQ,	/* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS
 };

include/linux/rcupdate.h

@@ -47,6 +47,18 @@
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
+extern void rcutorture_record_test_transition(void);
+extern void rcutorture_record_progress(unsigned long vernum);
+#else
+static inline void rcutorture_record_test_transition(void)
+{
+}
+static inline void rcutorture_record_progress(unsigned long vernum)
+{
+}
+#endif
+
 #define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
 #define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
@@ -68,7 +80,6 @@ extern void call_rcu_sched(struct rcu_head *head,
 extern void synchronize_sched(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
-extern int sched_expedited_torture_stats(char *page);
 
 static inline void __rcu_read_lock_bh(void)
 {
@@ -774,6 +785,7 @@ extern struct debug_obj_descr rcuhead_debug_descr;
 
 static inline void debug_rcu_head_queue(struct rcu_head *head)
 {
+	WARN_ON_ONCE((unsigned long)head & 0x3);
 	debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
@@ -797,4 +809,60 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
+{
+	return offset < 4096;
+}
+
+static __always_inline
+void __kfree_rcu(struct rcu_head *head, unsigned long offset)
+{
+	typedef void (*rcu_callback)(struct rcu_head *);
+
+	BUILD_BUG_ON(!__builtin_constant_p(offset));
+
+	/* See the kfree_rcu() header comment. */
+	BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+
+	call_rcu(head, (rcu_callback)offset);
+}
+
+extern void kfree(const void *);
+
+static inline void __rcu_reclaim(struct rcu_head *head)
+{
+	unsigned long offset = (unsigned long)head->func;
+
+	if (__is_kfree_rcu_offset(offset))
+		kfree((void *)head - offset);
+	else
+		head->func(head);
+}
+
+/**
+ * kfree_rcu() - kfree an object after a grace period.
+ * @ptr:	pointer to kfree
+ * @rcu_head:	the name of the struct rcu_head within the type of @ptr.
+ *
+ * Many rcu callbacks functions just call kfree() on the base structure.
+ * These functions are trivial, but their size adds up, and furthermore
+ * when they are used in a kernel module, that module must invoke the
+ * high-latency rcu_barrier() function at module-unload time.
+ *
+ * The kfree_rcu() function handles this issue.  Rather than encoding a
+ * function address in the embedded rcu_head structure, kfree_rcu() instead
+ * encodes the offset of the rcu_head structure within the base structure.
+ * Because the functions are not allowed in the low-order 4096 bytes of
+ * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
+ * If the offset is larger than 4095 bytes, a compile-time error will
+ * be generated in __kfree_rcu().  If this error is triggered, you can
+ * either fall back to use of call_rcu() or rearrange the structure to
+ * position the rcu_head structure into the first 4096 bytes.
+ *
+ * Note that the allowable offset might decrease in the future, for example,
+ * to allow something like kmem_cache_free_rcu().
+ */
+#define kfree_rcu(ptr, rcu_head)					\
+	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
+
 #endif /* __LINUX_RCUPDATE_H */

include/linux/rcutiny.h

@@ -99,6 +99,14 @@ static inline void rcu_note_context_switch(int cpu)
 	rcu_preempt_note_context_switch();
 }
 
+/*
+ * Take advantage of the fact that there is only one CPU, which
+ * allows us to ignore virtualization-based context switches.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+}
+
 /*
  * Return the number of grace periods.
  */

include/linux/rcutree.h

@@ -35,6 +35,16 @@ extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
 extern void rcu_cpu_stall_reset(void);
 
+/*
+ * Note a virtualization-based context switch.  This is simply a
+ * wrapper around rcu_note_context_switch(), which allows TINY_RCU
+ * to save a few bytes.
+ */
+static inline void rcu_virt_note_context_switch(int cpu)
+{
+	rcu_note_context_switch(cpu);
+}
+
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 extern void exit_rcu(void);
@@ -58,9 +68,12 @@ static inline void synchronize_rcu_bh_expedited(void)
 
 extern void rcu_barrier(void);
 
+extern unsigned long rcutorture_testseq;
+extern unsigned long rcutorture_vernum;
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
 extern long rcu_batches_completed_sched(void);
+
 extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);

include/net/sctp/sctp.h

@@ -115,7 +115,6 @@
  * sctp/protocol.c
  */
 extern struct sock *sctp_get_ctl_sock(void);
-extern void sctp_local_addr_free(struct rcu_head *head);
 extern int sctp_copy_local_addr_list(struct sctp_bind_addr *,
 				     sctp_scope_t, gfp_t gfp,
 				     int flags);

include/trace/events/irq.h

@@ -20,8 +20,7 @@ struct softirq_action;
 			 softirq_name(BLOCK_IOPOLL),	\
 			 softirq_name(TASKLET),		\
 			 softirq_name(SCHED),		\
-			 softirq_name(HRTIMER),		\
-			 softirq_name(RCU))
+			 softirq_name(HRTIMER))
 
 /**
  * irq_handler_entry - called immediately before the irq action handler

init/Kconfig

@@ -485,7 +485,7 @@ config TREE_RCU_TRACE
 
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
-	depends on RT_MUTEXES && TINY_PREEMPT_RCU
+	depends on RT_MUTEXES && PREEMPT_RCU
 	default n
 	help
 	  This option boosts the priority of preempted RCU readers that

kernel/cgroup.c

@@ -326,12 +326,6 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
 	return &css_set_table[index];
 }
 
-static void free_css_set_rcu(struct rcu_head *obj)
-{
-	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
-	kfree(cg);
-}
-
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
@@ -375,7 +369,7 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 	}
 
 	write_unlock(&css_set_lock);
-	call_rcu(&cg->rcu_head, free_css_set_rcu);
+	kfree_rcu(cg, rcu_head);
 }
 
 /*
@@ -812,13 +806,6 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 	return ret;
 }
 
-static void free_cgroup_rcu(struct rcu_head *obj)
-{
-	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
-
-	kfree(cgrp);
-}
-
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -856,7 +843,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		 */
 		BUG_ON(!list_empty(&cgrp->pidlists));
 
-		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
+		kfree_rcu(cgrp, rcu_head);
 	}
 	iput(inode);
 }
@@ -4623,14 +4610,6 @@ bool css_is_ancestor(struct cgroup_subsys_state *child,
 	return ret;
 }
 
-static void __free_css_id_cb(struct rcu_head *head)
-{
-	struct css_id *id;
-
-	id = container_of(head, struct css_id, rcu_head);
-	kfree(id);
-}
-
 void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 {
 	struct css_id *id = css->id;
@@ -4645,7 +4624,7 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, id->id);
 	spin_unlock(&ss->id_lock);
-	call_rcu(&id->rcu_head, __free_css_id_cb);
+	kfree_rcu(id, rcu_head);
 }
 EXPORT_SYMBOL_GPL(free_css_id);
 

kernel/events/core.c

@@ -586,22 +586,14 @@ static void get_ctx(struct perf_event_context *ctx)
 	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
-static void free_ctx(struct rcu_head *head)
-{
-	struct perf_event_context *ctx;
-
-	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx);
-}
-
 static void put_ctx(struct perf_event_context *ctx)
 {
 	if (atomic_dec_and_test(&ctx->refcount)) {
 		if (ctx->parent_ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task)
 			put_task_struct(ctx->task);
-		call_rcu(&ctx->rcu_head, free_ctx);
+		kfree_rcu(ctx, rcu_head);
 	}
 }
 
@@ -5331,14 +5323,6 @@ swevent_hlist_deref(struct swevent_htable *swhash)
 					 lockdep_is_held(&swhash->hlist_mutex));
 }
 
-static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
-{
-	struct swevent_hlist *hlist;
-
-	hlist = container_of(rcu_head, struct swevent_hlist, rcu_head);
-	kfree(hlist);
-}
-
 static void swevent_hlist_release(struct swevent_htable *swhash)
 {
 	struct swevent_hlist *hlist = swevent_hlist_deref(swhash);
@@ -5347,7 +5331,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash)
 		return;
 
 	rcu_assign_pointer(swhash->swevent_hlist, NULL);
-	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
+	kfree_rcu(hlist, rcu_head);
 }
 
 static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)