srcu: Move combining-tree definitions for SRCU's benefit
This commit moves the C preprocessor code that defines the default shape of the rcu_node combining tree to a new include/linux/rcu_node_tree.h file as a first step towards enabling SRCU to create its own combining tree, which in turn enables SRCU to implement per-CPU callback handling, thus avoiding contention on the lock currently guarding the single list of callbacks. Note that users of SRCU still need to know the size of the srcu_struct structure, hence include/linux rather than kernel/rcu. This commit is code-movement only. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit is contained in:
parent
8660b7d8a5
commit
f2425b4efb
|
@ -0,0 +1,102 @@
|
|||
/*
|
||||
* RCU node combining tree definitions. These are used to compute
|
||||
* global attributes while avoiding common-case global contention. A key
|
||||
* property that these computations rely on is a tournament-style approach
|
||||
* where only one of the tasks contending a lower level in the tree need
|
||||
* advance to the next higher level. If properly configured, this allows
|
||||
* unlimited scalability while maintaining a constant level of contention
|
||||
* on the root node.
|
||||
*
|
||||
* 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, you can access it online at
|
||||
* http://www.gnu.org/licenses/gpl-2.0.html.
|
||||
*
|
||||
* Copyright IBM Corporation, 2017
|
||||
*
|
||||
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
||||
*/
|
||||
|
||||
#ifndef __LINUX_RCU_NODE_TREE_H
|
||||
#define __LINUX_RCU_NODE_TREE_H
|
||||
|
||||
/*
|
||||
* Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
|
||||
* CONFIG_RCU_FANOUT_LEAF.
|
||||
* In theory, it should be possible to add more levels straightforwardly.
|
||||
* In practice, this did work well going from three levels to four.
|
||||
* Of course, your mileage may vary.
|
||||
*/
|
||||
|
||||
#ifdef CONFIG_RCU_FANOUT
|
||||
#define RCU_FANOUT CONFIG_RCU_FANOUT
|
||||
#else /* #ifdef CONFIG_RCU_FANOUT */
|
||||
# ifdef CONFIG_64BIT
|
||||
# define RCU_FANOUT 64
|
||||
# else
|
||||
# define RCU_FANOUT 32
|
||||
# endif
|
||||
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
|
||||
|
||||
#ifdef CONFIG_RCU_FANOUT_LEAF
|
||||
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
|
||||
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
|
||||
#define RCU_FANOUT_LEAF 16
|
||||
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
|
||||
|
||||
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
|
||||
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
|
||||
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
|
||||
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
|
||||
|
||||
#if NR_CPUS <= RCU_FANOUT_1
|
||||
# define RCU_NUM_LVLS 1
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_NODES NUM_RCU_LVL_0
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_2
|
||||
# define RCU_NUM_LVLS 2
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_3
|
||||
# define RCU_NUM_LVLS 3
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
|
||||
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_4
|
||||
# define RCU_NUM_LVLS 4
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
|
||||
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
|
||||
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
|
||||
#else
|
||||
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
|
||||
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
|
||||
|
||||
extern int rcu_num_lvls;
|
||||
extern int rcu_num_nodes;
|
||||
|
||||
#endif /* __LINUX_RCU_NODE_TREE_H */
|
|
@ -31,76 +31,7 @@
|
|||
#include <linux/swait.h>
|
||||
#include <linux/stop_machine.h>
|
||||
#include <linux/rcu_segcblist.h>
|
||||
|
||||
/*
|
||||
* Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
|
||||
* CONFIG_RCU_FANOUT_LEAF.
|
||||
* In theory, it should be possible to add more levels straightforwardly.
|
||||
* In practice, this did work well going from three levels to four.
|
||||
* Of course, your mileage may vary.
|
||||
*/
|
||||
|
||||
#ifdef CONFIG_RCU_FANOUT
|
||||
#define RCU_FANOUT CONFIG_RCU_FANOUT
|
||||
#else /* #ifdef CONFIG_RCU_FANOUT */
|
||||
# ifdef CONFIG_64BIT
|
||||
# define RCU_FANOUT 64
|
||||
# else
|
||||
# define RCU_FANOUT 32
|
||||
# endif
|
||||
#endif /* #else #ifdef CONFIG_RCU_FANOUT */
|
||||
|
||||
#ifdef CONFIG_RCU_FANOUT_LEAF
|
||||
#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
|
||||
#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
|
||||
#define RCU_FANOUT_LEAF 16
|
||||
#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
|
||||
|
||||
#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
|
||||
#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
|
||||
#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
|
||||
#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
|
||||
|
||||
#if NR_CPUS <= RCU_FANOUT_1
|
||||
# define RCU_NUM_LVLS 1
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_NODES NUM_RCU_LVL_0
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_2
|
||||
# define RCU_NUM_LVLS 2
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_3
|
||||
# define RCU_NUM_LVLS 3
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
|
||||
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
|
||||
#elif NR_CPUS <= RCU_FANOUT_4
|
||||
# define RCU_NUM_LVLS 4
|
||||
# define NUM_RCU_LVL_0 1
|
||||
# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
|
||||
# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
|
||||
# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
|
||||
# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
|
||||
# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
|
||||
# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
|
||||
# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
|
||||
#else
|
||||
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
|
||||
#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
|
||||
|
||||
extern int rcu_num_lvls;
|
||||
extern int rcu_num_nodes;
|
||||
#include <linux/rcu_node_tree.h>
|
||||
|
||||
/*
|
||||
* Dynticks per-CPU state.
|
||||
|
|
Loading…
Reference in New Issue