diff options
| author | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2009-12-02 15:10:14 -0500 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2009-12-03 05:34:53 -0500 |
| commit | cf244dc01bf68e1ad338b82447f8686d24ea4435 (patch) | |
| tree | dc2aebb60ef1eddf92d7e23b72ec2f6c08797684 /kernel | |
| parent | d3f6bad3911736e44ba11f3f3f6ac4e8c837fdfc (diff) | |
rcu: Enable fourth level of TREE_RCU hierarchy
Enable a fourth level of rcu_node hierarchy for TREE_RCU and
TREE_PREEMPT_RCU. This is for stress-testing and experiemental
purposes only, although in theory this would enable 16,777,216
CPUs on 64-bit systems, though only 1,048,576 CPUs on 32-bit
systems. Normal experimental use of this fourth level will
normally set CONFIG_RCU_FANOUT=2, requiring a 16-CPU system,
though the more adventurous (and more fortunate) experimenters
may wish to chose CONFIG_RCU_FANOUT=3 for 81-CPU systems or even
CONFIG_RCU_FANOUT=4 for 256-CPU systems.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
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: <12597846161257-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/rcutree.c | 6 | ||||
| -rw-r--r-- | kernel/rcutree.h | 15 |
2 files changed, 18 insertions, 3 deletions
diff --git a/kernel/rcutree.c b/kernel/rcutree.c index a9f51031d3e8..d47e03e5792a 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c | |||
| @@ -60,7 +60,8 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; | |||
| 60 | NUM_RCU_LVL_0, /* root of hierarchy. */ \ | 60 | NUM_RCU_LVL_0, /* root of hierarchy. */ \ |
| 61 | NUM_RCU_LVL_1, \ | 61 | NUM_RCU_LVL_1, \ |
| 62 | NUM_RCU_LVL_2, \ | 62 | NUM_RCU_LVL_2, \ |
| 63 | NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \ | 63 | NUM_RCU_LVL_3, \ |
| 64 | NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ | ||
| 64 | }, \ | 65 | }, \ |
| 65 | .signaled = RCU_GP_IDLE, \ | 66 | .signaled = RCU_GP_IDLE, \ |
| 66 | .gpnum = -300, \ | 67 | .gpnum = -300, \ |
| @@ -1877,6 +1878,9 @@ void __init rcu_init(void) | |||
| 1877 | #ifdef CONFIG_RCU_CPU_STALL_DETECTOR | 1878 | #ifdef CONFIG_RCU_CPU_STALL_DETECTOR |
| 1878 | printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); | 1879 | printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); |
| 1879 | #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ | 1880 | #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ |
| 1881 | #if NUM_RCU_LVL_4 != 0 | ||
| 1882 | printk(KERN_INFO "Experimental four-level hierarchy is enabled.\n"); | ||
| 1883 | #endif /* #if NUM_RCU_LVL_4 != 0 */ | ||
| 1880 | RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data); | 1884 | RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data); |
| 1881 | RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data); | 1885 | RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data); |
| 1882 | __rcu_init_preempt(); | 1886 | __rcu_init_preempt(); |
diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 8bb03cb07447..df2e0b694744 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h | |||
| @@ -34,10 +34,11 @@ | |||
| 34 | * In practice, this has not been tested, so there is probably some | 34 | * In practice, this has not been tested, so there is probably some |
| 35 | * bug somewhere. | 35 | * bug somewhere. |
| 36 | */ | 36 | */ |
| 37 | #define MAX_RCU_LVLS 3 | 37 | #define MAX_RCU_LVLS 4 |
| 38 | #define RCU_FANOUT (CONFIG_RCU_FANOUT) | 38 | #define RCU_FANOUT (CONFIG_RCU_FANOUT) |
| 39 | #define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT) | 39 | #define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT) |
| 40 | #define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT) | 40 | #define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT) |
| 41 | #define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT) | ||
| 41 | 42 | ||
| 42 | #if NR_CPUS <= RCU_FANOUT | 43 | #if NR_CPUS <= RCU_FANOUT |
| 43 | # define NUM_RCU_LVLS 1 | 44 | # define NUM_RCU_LVLS 1 |
| @@ -45,23 +46,33 @@ | |||
| 45 | # define NUM_RCU_LVL_1 (NR_CPUS) | 46 | # define NUM_RCU_LVL_1 (NR_CPUS) |
| 46 | # define NUM_RCU_LVL_2 0 | 47 | # define NUM_RCU_LVL_2 0 |
| 47 | # define NUM_RCU_LVL_3 0 | 48 | # define NUM_RCU_LVL_3 0 |
| 49 | # define NUM_RCU_LVL_4 0 | ||
| 48 | #elif NR_CPUS <= RCU_FANOUT_SQ | 50 | #elif NR_CPUS <= RCU_FANOUT_SQ |
| 49 | # define NUM_RCU_LVLS 2 | 51 | # define NUM_RCU_LVLS 2 |
| 50 | # define NUM_RCU_LVL_0 1 | 52 | # define NUM_RCU_LVL_0 1 |
| 51 | # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) | 53 | # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) |
| 52 | # define NUM_RCU_LVL_2 (NR_CPUS) | 54 | # define NUM_RCU_LVL_2 (NR_CPUS) |
| 53 | # define NUM_RCU_LVL_3 0 | 55 | # define NUM_RCU_LVL_3 0 |
| 56 | # define NUM_RCU_LVL_4 0 | ||
| 54 | #elif NR_CPUS <= RCU_FANOUT_CUBE | 57 | #elif NR_CPUS <= RCU_FANOUT_CUBE |
| 55 | # define NUM_RCU_LVLS 3 | 58 | # define NUM_RCU_LVLS 3 |
| 56 | # define NUM_RCU_LVL_0 1 | 59 | # define NUM_RCU_LVL_0 1 |
| 57 | # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) | 60 | # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) |
| 58 | # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) | 61 | # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) |
| 59 | # define NUM_RCU_LVL_3 NR_CPUS | 62 | # define NUM_RCU_LVL_3 NR_CPUS |
| 63 | # define NUM_RCU_LVL_4 0 | ||
| 64 | #elif NR_CPUS <= RCU_FANOUT_FOURTH | ||
| 65 | # define NUM_RCU_LVLS 4 | ||
| 66 | # define NUM_RCU_LVL_0 1 | ||
| 67 | # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE) | ||
| 68 | # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) | ||
| 69 | # define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) | ||
| 70 | # define NUM_RCU_LVL_4 NR_CPUS | ||
| 60 | #else | 71 | #else |
| 61 | # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" | 72 | # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" |
| 62 | #endif /* #if (NR_CPUS) <= RCU_FANOUT */ | 73 | #endif /* #if (NR_CPUS) <= RCU_FANOUT */ |
| 63 | 74 | ||
| 64 | #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) | 75 | #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) |
| 65 | #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) | 76 | #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) |
| 66 | 77 | ||
| 67 | /* | 78 | /* |
