2009-08-23 04:56:45 +08:00
|
|
|
/*
|
|
|
|
|
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
|
|
|
|
|
* Internal non-public definitions.
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
|
* (at your option) any later version.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
|
*
|
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
|
|
|
*
|
|
|
|
|
* Copyright IBM Corporation, 2008
|
|
|
|
|
*
|
|
|
|
|
* Author: Ingo Molnar <mingo@elte.hu>
|
|
|
|
|
* Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/cache.h>
|
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
|
#include <linux/threads.h>
|
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
|
#include <linux/seqlock.h>
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
|
|
|
|
|
* In theory, it should be possible to add more levels straightforwardly.
|
|
|
|
|
* In practice, this has not been tested, so there is probably some
|
|
|
|
|
* bug somewhere.
|
|
|
|
|
*/
|
2009-12-03 04:10:14 +08:00
|
|
|
#define MAX_RCU_LVLS 4
|
2009-08-23 04:56:45 +08:00
|
|
|
#define RCU_FANOUT (CONFIG_RCU_FANOUT)
|
|
|
|
|
#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
|
|
|
|
|
#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
|
2009-12-03 04:10:14 +08:00
|
|
|
#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
|
2009-08-23 04:56:45 +08:00
|
|
|
|
|
|
|
|
#if NR_CPUS <= RCU_FANOUT
|
|
|
|
|
# define NUM_RCU_LVLS 1
|
|
|
|
|
# define NUM_RCU_LVL_0 1
|
|
|
|
|
# define NUM_RCU_LVL_1 (NR_CPUS)
|
|
|
|
|
# define NUM_RCU_LVL_2 0
|
|
|
|
|
# define NUM_RCU_LVL_3 0
|
2009-12-03 04:10:14 +08:00
|
|
|
# define NUM_RCU_LVL_4 0
|
2009-08-23 04:56:45 +08:00
|
|
|
#elif NR_CPUS <= RCU_FANOUT_SQ
|
|
|
|
|
# define NUM_RCU_LVLS 2
|
|
|
|
|
# define NUM_RCU_LVL_0 1
|
2009-09-24 00:50:41 +08:00
|
|
|
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
|
2009-08-23 04:56:45 +08:00
|
|
|
# define NUM_RCU_LVL_2 (NR_CPUS)
|
|
|
|
|
# define NUM_RCU_LVL_3 0
|
2009-12-03 04:10:14 +08:00
|
|
|
# define NUM_RCU_LVL_4 0
|
2009-08-23 04:56:45 +08:00
|
|
|
#elif NR_CPUS <= RCU_FANOUT_CUBE
|
|
|
|
|
# define NUM_RCU_LVLS 3
|
|
|
|
|
# define NUM_RCU_LVL_0 1
|
2009-09-24 00:50:41 +08:00
|
|
|
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
|
|
|
|
|
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
|
2009-08-23 04:56:45 +08:00
|
|
|
# define NUM_RCU_LVL_3 NR_CPUS
|
2009-12-03 04:10:14 +08:00
|
|
|
# define NUM_RCU_LVL_4 0
|
|
|
|
|
#elif NR_CPUS <= RCU_FANOUT_FOURTH
|
|
|
|
|
# define NUM_RCU_LVLS 4
|
|
|
|
|
# define NUM_RCU_LVL_0 1
|
|
|
|
|
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
|
|
|
|
|
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
|
|
|
|
|
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
|
|
|
|
|
# define NUM_RCU_LVL_4 NR_CPUS
|
2009-08-23 04:56:45 +08:00
|
|
|
#else
|
|
|
|
|
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
|
|
|
|
|
#endif /* #if (NR_CPUS) <= RCU_FANOUT */
|
|
|
|
|
|
2009-12-03 04:10:14 +08:00
|
|
|
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
|
2009-08-23 04:56:45 +08:00
|
|
|
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Dynticks per-CPU state.
|
|
|
|
|
*/
|
|
|
|
|
struct rcu_dynticks {
|
|
|
|
|
int dynticks_nesting; /* Track nesting level, sort of. */
|
|
|
|
|
int dynticks; /* Even value for dynticks-idle, else odd. */
|
|
|
|
|
int dynticks_nmi; /* Even value for either dynticks-idle or */
|
|
|
|
|
/* not in nmi handler, else odd. So this */
|
|
|
|
|
/* remains even for nmi from irq handler. */
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Definition for node within the RCU grace-period-detection hierarchy.
|
|
|
|
|
*/
|
|
|
|
|
struct rcu_node {
|
2010-02-23 09:05:02 +08:00
|
|
|
raw_spinlock_t lock; /* Root rcu_node's lock protects some */
|
2009-09-24 00:50:42 +08:00
|
|
|
/* rcu_state fields as well as following. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long gpnum; /* Current grace period for this node. */
|
2009-08-28 06:00:12 +08:00
|
|
|
/* This will either be equal to or one */
|
|
|
|
|
/* behind the root rcu_node's gpnum. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long completed; /* Last GP completed for this node. */
|
2009-11-03 05:52:28 +08:00
|
|
|
/* This will either be equal to or one */
|
|
|
|
|
/* behind the root rcu_node's gpnum. */
|
2009-08-23 04:56:45 +08:00
|
|
|
unsigned long qsmask; /* CPUs or groups that need to switch in */
|
|
|
|
|
/* order for current grace period to proceed.*/
|
2009-09-24 00:50:42 +08:00
|
|
|
/* In leaf rcu_node, each bit corresponds to */
|
|
|
|
|
/* an rcu_data structure, otherwise, each */
|
|
|
|
|
/* bit corresponds to a child rcu_node */
|
|
|
|
|
/* structure. */
|
2009-12-03 04:10:15 +08:00
|
|
|
unsigned long expmask; /* Groups that have ->blocked_tasks[] */
|
|
|
|
|
/* elements that need to drain to allow the */
|
|
|
|
|
/* current expedited grace period to */
|
|
|
|
|
/* complete (only for TREE_PREEMPT_RCU). */
|
2009-08-23 04:56:45 +08:00
|
|
|
unsigned long qsmaskinit;
|
2009-12-03 04:10:15 +08:00
|
|
|
/* Per-GP initial value for qsmask & expmask. */
|
2009-08-23 04:56:45 +08:00
|
|
|
unsigned long grpmask; /* Mask to apply to parent qsmask. */
|
2009-09-24 00:50:42 +08:00
|
|
|
/* Only one bit will be set in this mask. */
|
2009-08-23 04:56:45 +08:00
|
|
|
int grplo; /* lowest-numbered CPU or group here. */
|
|
|
|
|
int grphi; /* highest-numbered CPU or group here. */
|
|
|
|
|
u8 grpnum; /* CPU/group number for next level up. */
|
|
|
|
|
u8 level; /* root is at level 0. */
|
|
|
|
|
struct rcu_node *parent;
|
2009-12-03 04:10:15 +08:00
|
|
|
struct list_head blocked_tasks[4];
|
rcu: Merge preemptable-RCU functionality into hierarchical RCU
Create a kernel/rcutree_plugin.h file that contains definitions
for preemptable RCU (or, under the #else branch of the #ifdef,
empty definitions for the classic non-preemptable semantics).
These definitions fit into plugins defined in kernel/rcutree.c
for this purpose.
This variant of preemptable RCU uses a new algorithm whose
read-side expense is roughly that of classic hierarchical RCU
under CONFIG_PREEMPT. This new algorithm's update-side expense
is similar to that of classic hierarchical RCU, and, in absence
of read-side preemption or blocking, is exactly that of classic
hierarchical RCU. Perhaps more important, this new algorithm
has a much simpler implementation, saving well over 1,000 lines
of code compared to mainline's implementation of preemptable
RCU, which will hopefully be retired in favor of this new
algorithm.
The simplifications are obtained by maintaining per-task
nesting state for running tasks, and using a simple
lock-protected algorithm to handle accounting when tasks block
within RCU read-side critical sections, making use of lessons
learned while creating numerous user-level RCU implementations
over the past 18 months.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josht@linux.vnet.ibm.com
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
LKML-Reference: <12509746134003-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-23 04:56:52 +08:00
|
|
|
/* Tasks blocked in RCU read-side critsect. */
|
2009-09-24 00:50:42 +08:00
|
|
|
/* Grace period number (->gpnum) x blocked */
|
|
|
|
|
/* by tasks on the (x & 0x1) element of the */
|
|
|
|
|
/* blocked_tasks[] array. */
|
2009-08-23 04:56:45 +08:00
|
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
|
|
2009-09-28 22:46:33 +08:00
|
|
|
/*
|
|
|
|
|
* Do a full breadth-first scan of the rcu_node structures for the
|
|
|
|
|
* specified rcu_state structure.
|
|
|
|
|
*/
|
|
|
|
|
#define rcu_for_each_node_breadth_first(rsp, rnp) \
|
|
|
|
|
for ((rnp) = &(rsp)->node[0]; \
|
|
|
|
|
(rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
|
|
|
|
|
|
2009-12-03 04:10:15 +08:00
|
|
|
/*
|
|
|
|
|
* Do a breadth-first scan of the non-leaf rcu_node structures for the
|
|
|
|
|
* specified rcu_state structure. Note that if there is a singleton
|
|
|
|
|
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
|
|
|
|
|
*/
|
|
|
|
|
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
|
|
|
|
|
for ((rnp) = &(rsp)->node[0]; \
|
|
|
|
|
(rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
|
|
|
|
|
* structure. Note that if there is a singleton rcu_node tree with but
|
|
|
|
|
* one rcu_node structure, this loop -will- visit the rcu_node structure.
|
|
|
|
|
* It is still a leaf node, even if it is also the root node.
|
|
|
|
|
*/
|
2009-09-28 22:46:33 +08:00
|
|
|
#define rcu_for_each_leaf_node(rsp, rnp) \
|
|
|
|
|
for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
|
|
|
|
|
(rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
|
|
|
|
|
|
2009-08-23 04:56:45 +08:00
|
|
|
/* Index values for nxttail array in struct rcu_data. */
|
|
|
|
|
#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
|
|
|
|
|
#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
|
|
|
|
|
#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
|
|
|
|
|
#define RCU_NEXT_TAIL 3
|
|
|
|
|
#define RCU_NEXT_SIZE 4
|
|
|
|
|
|
|
|
|
|
/* Per-CPU data for read-copy update. */
|
|
|
|
|
struct rcu_data {
|
|
|
|
|
/* 1) quiescent-state and grace-period handling : */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long completed; /* Track rsp->completed gp number */
|
2009-08-23 04:56:45 +08:00
|
|
|
/* in order to detect GP end. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long gpnum; /* Highest gp number that this CPU */
|
2009-08-23 04:56:45 +08:00
|
|
|
/* is aware of having started. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long passed_quiesc_completed;
|
2009-08-23 04:56:45 +08:00
|
|
|
/* Value of completed at time of qs. */
|
|
|
|
|
bool passed_quiesc; /* User-mode/idle loop etc. */
|
|
|
|
|
bool qs_pending; /* Core waits for quiesc state. */
|
|
|
|
|
bool beenonline; /* CPU online at least once. */
|
rcu: Merge preemptable-RCU functionality into hierarchical RCU
Create a kernel/rcutree_plugin.h file that contains definitions
for preemptable RCU (or, under the #else branch of the #ifdef,
empty definitions for the classic non-preemptable semantics).
These definitions fit into plugins defined in kernel/rcutree.c
for this purpose.
This variant of preemptable RCU uses a new algorithm whose
read-side expense is roughly that of classic hierarchical RCU
under CONFIG_PREEMPT. This new algorithm's update-side expense
is similar to that of classic hierarchical RCU, and, in absence
of read-side preemption or blocking, is exactly that of classic
hierarchical RCU. Perhaps more important, this new algorithm
has a much simpler implementation, saving well over 1,000 lines
of code compared to mainline's implementation of preemptable
RCU, which will hopefully be retired in favor of this new
algorithm.
The simplifications are obtained by maintaining per-task
nesting state for running tasks, and using a simple
lock-protected algorithm to handle accounting when tasks block
within RCU read-side critical sections, making use of lessons
learned while creating numerous user-level RCU implementations
over the past 18 months.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josht@linux.vnet.ibm.com
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
LKML-Reference: <12509746134003-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-23 04:56:52 +08:00
|
|
|
bool preemptable; /* Preemptable RCU? */
|
2009-08-23 04:56:45 +08:00
|
|
|
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
|
|
|
|
|
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
|
|
|
|
|
|
|
|
|
|
/* 2) batch handling */
|
|
|
|
|
/*
|
|
|
|
|
* If nxtlist is not NULL, it is partitioned as follows.
|
|
|
|
|
* Any of the partitions might be empty, in which case the
|
|
|
|
|
* pointer to that partition will be equal to the pointer for
|
|
|
|
|
* the following partition. When the list is empty, all of
|
2009-09-24 00:50:42 +08:00
|
|
|
* the nxttail elements point to the ->nxtlist pointer itself,
|
|
|
|
|
* which in that case is NULL.
|
2009-08-23 04:56:45 +08:00
|
|
|
*
|
|
|
|
|
* [nxtlist, *nxttail[RCU_DONE_TAIL]):
|
|
|
|
|
* Entries that batch # <= ->completed
|
|
|
|
|
* The grace period for these entries has completed, and
|
|
|
|
|
* the other grace-period-completed entries may be moved
|
|
|
|
|
* here temporarily in rcu_process_callbacks().
|
2009-09-24 00:50:42 +08:00
|
|
|
* [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
|
|
|
|
|
* Entries that batch # <= ->completed - 1: waiting for current GP
|
|
|
|
|
* [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
|
|
|
|
|
* Entries known to have arrived before current GP ended
|
|
|
|
|
* [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
|
|
|
|
|
* Entries that might have arrived after current GP ended
|
|
|
|
|
* Note that the value of *nxttail[RCU_NEXT_TAIL] will
|
|
|
|
|
* always be NULL, as this is the end of the list.
|
2009-08-23 04:56:45 +08:00
|
|
|
*/
|
|
|
|
|
struct rcu_head *nxtlist;
|
|
|
|
|
struct rcu_head **nxttail[RCU_NEXT_SIZE];
|
2009-09-19 01:28:19 +08:00
|
|
|
long qlen; /* # of queued callbacks */
|
2009-10-15 01:15:55 +08:00
|
|
|
long qlen_last_fqs_check;
|
|
|
|
|
/* qlen at last check for QS forcing */
|
|
|
|
|
unsigned long n_force_qs_snap;
|
|
|
|
|
/* did other CPU force QS recently? */
|
2009-08-23 04:56:45 +08:00
|
|
|
long blimit; /* Upper limit on a processed batch */
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_NO_HZ
|
|
|
|
|
/* 3) dynticks interface. */
|
|
|
|
|
struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
|
|
|
|
|
int dynticks_snap; /* Per-GP tracking for dynticks. */
|
|
|
|
|
int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */
|
|
|
|
|
#endif /* #ifdef CONFIG_NO_HZ */
|
|
|
|
|
|
|
|
|
|
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
|
|
|
|
|
#ifdef CONFIG_NO_HZ
|
|
|
|
|
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
|
|
|
|
|
#endif /* #ifdef CONFIG_NO_HZ */
|
|
|
|
|
unsigned long offline_fqs; /* Kicked due to being offline. */
|
|
|
|
|
unsigned long resched_ipi; /* Sent a resched IPI. */
|
|
|
|
|
|
|
|
|
|
/* 5) __rcu_pending() statistics. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */
|
|
|
|
|
unsigned long n_rp_qs_pending;
|
|
|
|
|
unsigned long n_rp_cb_ready;
|
|
|
|
|
unsigned long n_rp_cpu_needs_gp;
|
|
|
|
|
unsigned long n_rp_gp_completed;
|
|
|
|
|
unsigned long n_rp_gp_started;
|
|
|
|
|
unsigned long n_rp_need_fqs;
|
|
|
|
|
unsigned long n_rp_need_nothing;
|
2009-08-23 04:56:45 +08:00
|
|
|
|
|
|
|
|
int cpu;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* Values for signaled field in struct rcu_state. */
|
rcu: Fix long-grace-period race between forcing and initialization
Very long RCU read-side critical sections (50 milliseconds or
so) can cause a race between force_quiescent_state() and
rcu_start_gp() as follows on kernel builds with multi-level
rcu_node hierarchies:
1. CPU 0 calls force_quiescent_state(), sees that there is a
grace period in progress, and acquires ->fsqlock.
2. CPU 1 detects the end of the grace period, and so
cpu_quiet_msk_finish() sets rsp->completed to rsp->gpnum.
This operation is carried out under the root rnp->lock,
but CPU 0 has not yet acquired that lock. Note that
rsp->signaled is still RCU_SAVE_DYNTICK from the last
grace period.
3. CPU 1 calls rcu_start_gp(), but no one wants a new grace
period, so it drops the root rnp->lock and returns.
4. CPU 0 acquires the root rnp->lock and picks up rsp->completed
and rsp->signaled, then drops rnp->lock. It then enters the
RCU_SAVE_DYNTICK leg of the switch statement.
5. CPU 2 invokes call_rcu(), and now needs a new grace period.
It calls rcu_start_gp(), which acquires the root rnp->lock, sets
rsp->signaled to RCU_GP_INIT (too bad that CPU 0 is already in
the RCU_SAVE_DYNTICK leg of the switch statement!) and starts
initializing the rcu_node hierarchy. If there are multiple
levels to the hierarchy, it will drop the root rnp->lock and
initialize the lower levels of the hierarchy.
6. CPU 0 notes that rsp->completed has not changed, which permits
both CPU 2 and CPU 0 to try updating it concurrently. If CPU 0's
update prevails, later calls to force_quiescent_state() can
count old quiescent states against the new grace period, which
can in turn result in premature ending of grace periods.
Not good.
This patch adds an RCU_GP_IDLE state for rsp->signaled that is
set initially at boot time and any time a grace period ends.
This prevents CPU 0 from getting into the workings of
force_quiescent_state() in step 4. Additional locking and
checks prevent the concurrent update of rsp->signaled in step 6.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1256742889199-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-28 23:14:49 +08:00
|
|
|
#define RCU_GP_IDLE 0 /* No grace period in progress. */
|
|
|
|
|
#define RCU_GP_INIT 1 /* Grace period being initialized. */
|
|
|
|
|
#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */
|
2010-01-05 07:09:07 +08:00
|
|
|
#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
|
2009-08-23 04:56:45 +08:00
|
|
|
#ifdef CONFIG_NO_HZ
|
|
|
|
|
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
|
|
|
|
|
#else /* #ifdef CONFIG_NO_HZ */
|
2010-01-05 07:09:07 +08:00
|
|
|
#define RCU_SIGNAL_INIT RCU_FORCE_QS
|
2009-08-23 04:56:45 +08:00
|
|
|
#endif /* #else #ifdef CONFIG_NO_HZ */
|
|
|
|
|
|
|
|
|
|
#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
|
|
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
2010-03-06 07:03:26 +08:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_PROVE_RCU
|
|
|
|
|
#define RCU_STALL_DELAY_DELTA (5 * HZ)
|
|
|
|
|
#else
|
|
|
|
|
#define RCU_STALL_DELAY_DELTA 0
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ + RCU_STALL_DELAY_DELTA)
|
|
|
|
|
/* for rsp->jiffies_stall */
|
|
|
|
|
#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
|
|
|
|
|
/* for rsp->jiffies_stall */
|
|
|
|
|
#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */
|
|
|
|
|
/* to take at least one */
|
|
|
|
|
/* scheduling clock irq */
|
|
|
|
|
/* before ratting on them. */
|
2009-08-23 04:56:45 +08:00
|
|
|
|
|
|
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
|
|
|
|
|
2010-02-23 09:05:01 +08:00
|
|
|
#define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b))
|
|
|
|
|
#define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b))
|
|
|
|
|
|
2009-08-23 04:56:45 +08:00
|
|
|
/*
|
|
|
|
|
* RCU global state, including node hierarchy. This hierarchy is
|
|
|
|
|
* represented in "heap" form in a dense array. The root (first level)
|
|
|
|
|
* of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
|
|
|
|
|
* level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
|
|
|
|
|
* and the third level in ->node[m+1] and following (->node[m+1] referenced
|
|
|
|
|
* by ->level[2]). The number of levels is determined by the number of
|
|
|
|
|
* CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
|
|
|
|
|
* consisting of a single rcu_node.
|
|
|
|
|
*/
|
|
|
|
|
struct rcu_state {
|
|
|
|
|
struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
|
|
|
|
|
struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */
|
|
|
|
|
u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */
|
|
|
|
|
u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */
|
|
|
|
|
struct rcu_data *rda[NR_CPUS]; /* array of rdp pointers. */
|
|
|
|
|
|
|
|
|
|
/* The following fields are guarded by the root rcu_node's lock. */
|
|
|
|
|
|
|
|
|
|
u8 signaled ____cacheline_internodealigned_in_smp;
|
|
|
|
|
/* Force QS state. */
|
2010-01-05 07:09:02 +08:00
|
|
|
u8 fqs_active; /* force_quiescent_state() */
|
|
|
|
|
/* is running. */
|
2010-01-05 07:09:09 +08:00
|
|
|
u8 fqs_need_gp; /* A CPU was prevented from */
|
|
|
|
|
/* starting a new grace */
|
|
|
|
|
/* period because */
|
|
|
|
|
/* force_quiescent_state() */
|
|
|
|
|
/* was running. */
|
2010-02-23 09:05:01 +08:00
|
|
|
unsigned long gpnum; /* Current gp number. */
|
|
|
|
|
unsigned long completed; /* # of last completed gp. */
|
2009-09-24 00:50:42 +08:00
|
|
|
|
2009-12-03 04:10:15 +08:00
|
|
|
/* End of fields guarded by root rcu_node's lock. */
|
2009-09-24 00:50:42 +08:00
|
|
|
|
2010-02-23 09:05:02 +08:00
|
|
|
raw_spinlock_t onofflock; /* exclude on/offline and */
|
2009-10-07 12:48:17 +08:00
|
|
|
/* starting new GP. Also */
|
|
|
|
|
/* protects the following */
|
|
|
|
|
/* orphan_cbs fields. */
|
|
|
|
|
struct rcu_head *orphan_cbs_list; /* list of rcu_head structs */
|
|
|
|
|
/* orphaned by all CPUs in */
|
|
|
|
|
/* a given leaf rcu_node */
|
|
|
|
|
/* going offline. */
|
|
|
|
|
struct rcu_head **orphan_cbs_tail; /* And tail pointer. */
|
|
|
|
|
long orphan_qlen; /* Number of orphaned cbs. */
|
2010-02-23 09:05:02 +08:00
|
|
|
raw_spinlock_t fqslock; /* Only one task forcing */
|
2009-08-23 04:56:45 +08:00
|
|
|
/* quiescent states. */
|
|
|
|
|
unsigned long jiffies_force_qs; /* Time at which to invoke */
|
|
|
|
|
/* force_quiescent_state(). */
|
|
|
|
|
unsigned long n_force_qs; /* Number of calls to */
|
|
|
|
|
/* force_quiescent_state(). */
|
|
|
|
|
unsigned long n_force_qs_lh; /* ~Number of calls leaving */
|
|
|
|
|
/* due to lock unavailable. */
|
|
|
|
|
unsigned long n_force_qs_ngp; /* Number of calls leaving */
|
|
|
|
|
/* due to no GP active. */
|
|
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
|
|
|
|
unsigned long gp_start; /* Time at which GP started, */
|
|
|
|
|
/* but in jiffies. */
|
|
|
|
|
unsigned long jiffies_stall; /* Time at which to check */
|
|
|
|
|
/* for CPU stalls. */
|
|
|
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
|
|
|
|
};
|
|
|
|
|
|
2009-12-03 04:10:15 +08:00
|
|
|
/* Return values for rcu_preempt_offline_tasks(). */
|
|
|
|
|
|
|
|
|
|
#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */
|
|
|
|
|
/* GP were moved to root. */
|
|
|
|
|
#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */
|
|
|
|
|
/* GP were moved to root. */
|
|
|
|
|
|
2009-03-25 23:42:24 +08:00
|
|
|
/*
|
|
|
|
|
* RCU implementation internal declarations:
|
|
|
|
|
*/
|
2009-08-23 04:56:46 +08:00
|
|
|
extern struct rcu_state rcu_sched_state;
|
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
|
2009-03-25 23:42:24 +08:00
|
|
|
|
|
|
|
|
extern struct rcu_state rcu_bh_state;
|
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
|
|
|
|
|
|
rcu: Merge preemptable-RCU functionality into hierarchical RCU
Create a kernel/rcutree_plugin.h file that contains definitions
for preemptable RCU (or, under the #else branch of the #ifdef,
empty definitions for the classic non-preemptable semantics).
These definitions fit into plugins defined in kernel/rcutree.c
for this purpose.
This variant of preemptable RCU uses a new algorithm whose
read-side expense is roughly that of classic hierarchical RCU
under CONFIG_PREEMPT. This new algorithm's update-side expense
is similar to that of classic hierarchical RCU, and, in absence
of read-side preemption or blocking, is exactly that of classic
hierarchical RCU. Perhaps more important, this new algorithm
has a much simpler implementation, saving well over 1,000 lines
of code compared to mainline's implementation of preemptable
RCU, which will hopefully be retired in favor of this new
algorithm.
The simplifications are obtained by maintaining per-task
nesting state for running tasks, and using a simple
lock-protected algorithm to handle accounting when tasks block
within RCU read-side critical sections, making use of lessons
learned while creating numerous user-level RCU implementations
over the past 18 months.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josht@linux.vnet.ibm.com
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
LKML-Reference: <12509746134003-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-23 04:56:52 +08:00
|
|
|
#ifdef CONFIG_TREE_PREEMPT_RCU
|
|
|
|
|
extern struct rcu_state rcu_preempt_state;
|
|
|
|
|
DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
|
|
|
|
|
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
|
|
|
|
|
|
2010-01-15 08:10:58 +08:00
|
|
|
#ifndef RCU_TREE_NONCORE
|
2009-08-23 04:56:45 +08:00
|
|
|
|
2009-09-24 00:50:43 +08:00
|
|
|
/* Forward declarations for rcutree_plugin.h */
|
2009-11-11 05:37:19 +08:00
|
|
|
static void rcu_bootup_announce(void);
|
2009-09-24 00:50:43 +08:00
|
|
|
long rcu_batches_completed(void);
|
|
|
|
|
static void rcu_preempt_note_context_switch(int cpu);
|
|
|
|
|
static int rcu_preempted_readers(struct rcu_node *rnp);
|
rcu: Fix grace-period-stall bug on large systems with CPU hotplug
When the last CPU of a given leaf rcu_node structure goes
offline, all of the tasks queued on that leaf rcu_node structure
(due to having blocked in their current RCU read-side critical
sections) are requeued onto the root rcu_node structure. This
requeuing is carried out by rcu_preempt_offline_tasks().
However, it is possible that these queued tasks are the only
thing preventing the leaf rcu_node structure from reporting a
quiescent state up the rcu_node hierarchy. Unfortunately, the
old code would fail to do this reporting, resulting in a
grace-period stall given the following sequence of events:
1. Kernel built for more than 32 CPUs on 32-bit systems or for more
than 64 CPUs on 64-bit systems, so that there is more than one
rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set
to a number smaller than CONFIG_NR_CPUS.)
2. The kernel is built with CONFIG_TREE_PREEMPT_RCU.
3. A task running on a CPU associated with a given leaf rcu_node
structure blocks while in an RCU read-side critical section
-and- that CPU has not yet passed through a quiescent state
for the current RCU grace period. This will cause the task
to be queued on the leaf rcu_node's blocked_tasks[] array, in
particular, on the element of this array corresponding to the
current grace period.
4. Each of the remaining CPUs corresponding to this same leaf rcu_node
structure pass through a quiescent state. However, the task is
still in its RCU read-side critical section, so these quiescent
states cannot be reported further up the rcu_node hierarchy.
Nevertheless, all bits in the leaf rcu_node structure's ->qsmask
field are now zero.
5. Each of the remaining CPUs go offline. (The events in step
#4 and #5 can happen in any order as long as each CPU passes
through a quiescent state before going offline.)
6. When the last CPU goes offline, __rcu_offline_cpu() will invoke
rcu_preempt_offline_tasks(), which will move the task to the
root rcu_node structure, but without reporting a quiescent state
up the rcu_node hierarchy (and this failure to report a quiescent
state is the bug).
But because this leaf rcu_node structure's ->qsmask field is
already zero and its ->block_tasks[] entries are all empty,
force_quiescent_state() will skip this rcu_node structure.
Therefore, grace periods are now hung.
This patch abstracts some code out of rcu_read_unlock_special(),
calling the result task_quiet() by analogy with cpu_quiet(), and
invokes task_quiet() from both rcu_read_lock_special() and
__rcu_offline_cpu(). Invoking task_quiet() from
__rcu_offline_cpu() reports the quiescent state up the rcu_node
hierarchy, fixing the bug. This ends up requiring a separate
lock_class_key per level of the rcu_node hierarchy, which this
patch also provides.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12589088301770-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-23 00:53:48 +08:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
2009-12-03 04:10:13 +08:00
|
|
|
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
|
|
|
|
|
unsigned long flags);
|
rcu: Fix grace-period-stall bug on large systems with CPU hotplug
When the last CPU of a given leaf rcu_node structure goes
offline, all of the tasks queued on that leaf rcu_node structure
(due to having blocked in their current RCU read-side critical
sections) are requeued onto the root rcu_node structure. This
requeuing is carried out by rcu_preempt_offline_tasks().
However, it is possible that these queued tasks are the only
thing preventing the leaf rcu_node structure from reporting a
quiescent state up the rcu_node hierarchy. Unfortunately, the
old code would fail to do this reporting, resulting in a
grace-period stall given the following sequence of events:
1. Kernel built for more than 32 CPUs on 32-bit systems or for more
than 64 CPUs on 64-bit systems, so that there is more than one
rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set
to a number smaller than CONFIG_NR_CPUS.)
2. The kernel is built with CONFIG_TREE_PREEMPT_RCU.
3. A task running on a CPU associated with a given leaf rcu_node
structure blocks while in an RCU read-side critical section
-and- that CPU has not yet passed through a quiescent state
for the current RCU grace period. This will cause the task
to be queued on the leaf rcu_node's blocked_tasks[] array, in
particular, on the element of this array corresponding to the
current grace period.
4. Each of the remaining CPUs corresponding to this same leaf rcu_node
structure pass through a quiescent state. However, the task is
still in its RCU read-side critical section, so these quiescent
states cannot be reported further up the rcu_node hierarchy.
Nevertheless, all bits in the leaf rcu_node structure's ->qsmask
field are now zero.
5. Each of the remaining CPUs go offline. (The events in step
#4 and #5 can happen in any order as long as each CPU passes
through a quiescent state before going offline.)
6. When the last CPU goes offline, __rcu_offline_cpu() will invoke
rcu_preempt_offline_tasks(), which will move the task to the
root rcu_node structure, but without reporting a quiescent state
up the rcu_node hierarchy (and this failure to report a quiescent
state is the bug).
But because this leaf rcu_node structure's ->qsmask field is
already zero and its ->block_tasks[] entries are all empty,
force_quiescent_state() will skip this rcu_node structure.
Therefore, grace periods are now hung.
This patch abstracts some code out of rcu_read_unlock_special(),
calling the result task_quiet() by analogy with cpu_quiet(), and
invokes task_quiet() from both rcu_read_lock_special() and
__rcu_offline_cpu(). Invoking task_quiet() from
__rcu_offline_cpu() reports the quiescent state up the rcu_node
hierarchy, fixing the bug. This ends up requiring a separate
lock_class_key per level of the rcu_node hierarchy, which this
patch also provides.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12589088301770-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-23 00:53:48 +08:00
|
|
|
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
|
2009-09-24 00:50:43 +08:00
|
|
|
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
|
2010-02-23 09:05:05 +08:00
|
|
|
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
|
2009-09-24 00:50:43 +08:00
|
|
|
static void rcu_print_task_stall(struct rcu_node *rnp);
|
|
|
|
|
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
|
|
|
|
|
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
|
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
rcu: Fix TREE_PREEMPT_RCU CPU_HOTPLUG bad-luck hang
If the following sequence of events occurs, then
TREE_PREEMPT_RCU will hang waiting for a grace period to
complete, eventually OOMing the system:
o A TREE_PREEMPT_RCU build of the kernel is booted on a system
with more than 64 physical CPUs present (32 on a 32-bit system).
Alternatively, a TREE_PREEMPT_RCU build of the kernel is booted
with RCU_FANOUT set to a sufficiently small value that the
physical CPUs populate two or more leaf rcu_node structures.
o A task is preempted in an RCU read-side critical section
while running on a CPU corresponding to a given leaf rcu_node
structure.
o All CPUs corresponding to this same leaf rcu_node structure
record quiescent states for the current grace period.
o All of these same CPUs go offline (hence the need for enough
physical CPUs to populate more than one leaf rcu_node structure).
This causes the preempted task to be moved to the root rcu_node
structure.
At this point, there is nothing left to cause the quiescent
state to be propagated up the rcu_node tree, so the current
grace period never completes.
The simplest fix, especially after considering the deadlock
possibilities, is to detect this situation when the last CPU is
offlined, and to set that CPU's ->qsmask bit in its leaf
rcu_node structure. This will cause the next invocation of
force_quiescent_state() to end the grace period.
Without this fix, this hang can be triggered in an hour or so on
some machines with rcutorture and random CPU onlining/offlining.
With this fix, these same machines pass a full 10 hours of this
sort of abuse.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <20091015162614.GA19131@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-16 00:26:14 +08:00
|
|
|
static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
|
|
|
|
|
struct rcu_node *rnp,
|
|
|
|
|
struct rcu_data *rdp);
|
2009-09-24 00:50:43 +08:00
|
|
|
static void rcu_preempt_offline_cpu(int cpu);
|
|
|
|
|
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
|
|
|
|
|
static void rcu_preempt_check_callbacks(int cpu);
|
|
|
|
|
static void rcu_preempt_process_callbacks(void);
|
|
|
|
|
void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
|
2009-12-03 04:10:15 +08:00
|
|
|
#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
|
|
|
|
|
static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
|
|
|
|
|
#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
|
2009-09-24 00:50:43 +08:00
|
|
|
static int rcu_preempt_pending(int cpu);
|
|
|
|
|
static int rcu_preempt_needs_cpu(int cpu);
|
|
|
|
|
static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
|
2009-10-07 12:48:17 +08:00
|
|
|
static void rcu_preempt_send_cbs_to_orphanage(void);
|
2009-09-24 00:50:43 +08:00
|
|
|
static void __init __rcu_init_preempt(void);
|
2010-02-27 08:38:56 +08:00
|
|
|
static void rcu_needs_cpu_flush(void);
|
2009-09-24 00:50:43 +08:00
|
|
|
|
2010-01-15 08:10:58 +08:00
|
|
|
#endif /* #ifndef RCU_TREE_NONCORE */
|
