From 319362c90f7af92d03714759bea5d2ba7c88e388 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 19 May 2015 14:16:52 -0700 Subject: [PATCH 01/32] rcu: Provide more diagnostics for stalled GP kthread Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 10 ++++++++-- kernel/rcu/tree.h | 6 +++++- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 65137bc28b2b..1c58cbd03922 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1178,9 +1178,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n", + pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n", rsp->name, j - gpa, - rsp->gpnum, rsp->completed, rsp->gp_flags); + rsp->gpnum, rsp->completed, + rsp->gp_flags, rsp->gp_state, + rsp->gp_kthread ? rsp->gp_kthread->state : 0); } /* @@ -2041,6 +2043,7 @@ static int __noreturn rcu_gp_kthread(void *arg) wait_event_interruptible(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); + rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) break; @@ -2073,6 +2076,7 @@ static int __noreturn rcu_gp_kthread(void *arg) (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)), j); + rsp->gp_state = RCU_GP_DONE_FQS; /* Locking provides needed memory barriers. */ /* If grace period done, leave loop. */ if (!READ_ONCE(rnp->qsmask) && @@ -2110,7 +2114,9 @@ static int __noreturn rcu_gp_kthread(void *arg) } /* Handle grace-period end. */ + rsp->gp_state = RCU_GP_CLEANUP; rcu_gp_cleanup(rsp); + rsp->gp_state = RCU_GP_CLEANED; } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4adb7ca0bf47..f1f4784f9107 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -527,7 +527,11 @@ struct rcu_state { /* Values for rcu_state structure's gp_flags field. */ #define RCU_GP_WAIT_INIT 0 /* Initial state. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ -#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ +#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DONE_FQS 4 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ +#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ extern struct list_head rcu_struct_flavors; From 75cf15a4c0dd57f5d230bd30c2d41bd8e06ae5a9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:23 +0200 Subject: [PATCH 02/32] rcu: Panic if RCU tree can not accommodate all CPUs Currently a condition when RCU tree is unable to accommodate the configured number of CPUs is not permitted and causes a fall back to compile-time values. However, the code has no means to exceed the RCU tree capacity neither at compile-time nor in run-time. Therefore, if the condition is met in run- time then it indicates a serios problem elsewhere and should be handled with a panic. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1c58cbd03922..fe8d92987dfa 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4106,6 +4106,19 @@ static void __init rcu_init_geometry(void) pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n", rcu_fanout_leaf, nr_cpu_ids); + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Complain and fall back to the compile- + * time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8) { + WARN_ON(1); + return; + } + /* * Compute number of nodes that can be handled an rcu_node tree * with the given number of levels. Setting rcu_capacity[0] makes @@ -4117,19 +4130,11 @@ static void __init rcu_init_geometry(void) rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT; /* - * The boot-time rcu_fanout_leaf parameter is only permitted - * to increase the leaf-level fanout, not decrease it. Of course, - * the leaf-level fanout cannot exceed the number of bits in - * the rcu_node masks. Finally, the tree must be able to accommodate - * the configured number of CPUs. Complain and fall back to the - * compile-time values if these limits are exceeded. + * The tree must be able to accommodate the configured number of CPUs. + * If this limit is exceeded than we have a serious problem elsewhere. */ - if (rcu_fanout_leaf < RCU_FANOUT_LEAF || - rcu_fanout_leaf > sizeof(unsigned long) * 8 || - n > rcu_capacity[MAX_RCU_LVLS]) { - WARN_ON(1); - return; - } + if (n > rcu_capacity[MAX_RCU_LVLS]) + panic("rcu_init_geometry: rcu_capacity[] is too small"); /* Calculate the number of rcu_nodes at each level of the tree. */ for (i = 1; i <= MAX_RCU_LVLS; i++) From 372b0ec24f6b516174934d68fd86d2056f1a5bba Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:24 +0200 Subject: [PATCH 03/32] rcu: Remove superfluous local variable in rcu_init_geometry() Local variable 'n' mimics 'nr_cpu_ids' while the both are used within one function. There is no reason for 'n' to exist whatsoever. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index fe8d92987dfa..ad49dbed44fb 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4083,7 +4083,6 @@ static void __init rcu_init_geometry(void) ulong d; int i; int j; - int n = nr_cpu_ids; int rcu_capacity[MAX_RCU_LVLS + 1]; /* @@ -4133,15 +4132,16 @@ static void __init rcu_init_geometry(void) * The tree must be able to accommodate the configured number of CPUs. * If this limit is exceeded than we have a serious problem elsewhere. */ - if (n > rcu_capacity[MAX_RCU_LVLS]) + if (nr_cpu_ids > rcu_capacity[MAX_RCU_LVLS]) panic("rcu_init_geometry: rcu_capacity[] is too small"); /* Calculate the number of rcu_nodes at each level of the tree. */ for (i = 1; i <= MAX_RCU_LVLS; i++) - if (n <= rcu_capacity[i]) { - for (j = 0; j <= i; j++) - num_rcu_lvl[j] = - DIV_ROUND_UP(n, rcu_capacity[i - j]); + if (nr_cpu_ids <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) { + int cap = rcu_capacity[i - j]; + num_rcu_lvl[j] = DIV_ROUND_UP(nr_cpu_ids, cap); + } rcu_num_lvls = i; for (j = i + 1; j <= MAX_RCU_LVLS; j++) num_rcu_lvl[j] = 0; @@ -4152,7 +4152,7 @@ static void __init rcu_init_geometry(void) rcu_num_nodes = 0; for (i = 0; i <= MAX_RCU_LVLS; i++) rcu_num_nodes += num_rcu_lvl[i]; - rcu_num_nodes -= n; + rcu_num_nodes -= nr_cpu_ids; } /* From 679f9858b1769d740d933f5f1ad9dbe3292f26d2 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:25 +0200 Subject: [PATCH 04/32] rcu: Cleanup rcu_init_geometry() code and arithmetics This update simplifies rcu_init_geometry() code flow and makes calculation of the total number of rcu_node structures more easy to read. The update relies on the fact num_rcu_lvl[] is never accessed beyond rcu_num_lvls index by the rest of the code. Therefore, there is no need initialize the whole num_rcu_lvl[]. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ad49dbed44fb..37ca8a867a1c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4082,7 +4082,6 @@ static void __init rcu_init_geometry(void) { ulong d; int i; - int j; int rcu_capacity[MAX_RCU_LVLS + 1]; /* @@ -4135,24 +4134,21 @@ static void __init rcu_init_geometry(void) if (nr_cpu_ids > rcu_capacity[MAX_RCU_LVLS]) panic("rcu_init_geometry: rcu_capacity[] is too small"); + /* Calculate the number of levels in the tree. */ + for (i = 1; nr_cpu_ids > rcu_capacity[i]; i++) { + } + rcu_num_lvls = i; + /* Calculate the number of rcu_nodes at each level of the tree. */ - for (i = 1; i <= MAX_RCU_LVLS; i++) - if (nr_cpu_ids <= rcu_capacity[i]) { - for (j = 0; j <= i; j++) { - int cap = rcu_capacity[i - j]; - num_rcu_lvl[j] = DIV_ROUND_UP(nr_cpu_ids, cap); - } - rcu_num_lvls = i; - for (j = i + 1; j <= MAX_RCU_LVLS; j++) - num_rcu_lvl[j] = 0; - break; - } + for (i = 0; i < rcu_num_lvls; i++) { + int cap = rcu_capacity[rcu_num_lvls - i]; + num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap); + } /* Calculate the total number of rcu_node structures. */ rcu_num_nodes = 0; - for (i = 0; i <= MAX_RCU_LVLS; i++) + for (i = 0; i < rcu_num_lvls; i++) rcu_num_nodes += num_rcu_lvl[i]; - rcu_num_nodes -= nr_cpu_ids; } /* From 9618138b09260e3df5af5a0d7bdc8fca010f6a3f Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:26 +0200 Subject: [PATCH 05/32] rcu: Simplify rcu_init_geometry() capacity arithmetics Current code suggests that introducing the extra level to rcu_capacity[] array makes some of the arithmetic easier. Well, in fact it appears rather confusing and unnecessary. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 37ca8a867a1c..2103beedb49f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4082,7 +4082,7 @@ static void __init rcu_init_geometry(void) { ulong d; int i; - int rcu_capacity[MAX_RCU_LVLS + 1]; + int rcu_capacity[MAX_RCU_LVLS]; /* * Initialize any unspecified boot parameters. @@ -4119,29 +4119,27 @@ static void __init rcu_init_geometry(void) /* * Compute number of nodes that can be handled an rcu_node tree - * with the given number of levels. Setting rcu_capacity[0] makes - * some of the arithmetic easier. + * with the given number of levels. */ - rcu_capacity[0] = 1; - rcu_capacity[1] = rcu_fanout_leaf; - for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[0] = rcu_fanout_leaf; + for (i = 1; i < MAX_RCU_LVLS; i++) rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT; /* * The tree must be able to accommodate the configured number of CPUs. * If this limit is exceeded than we have a serious problem elsewhere. */ - if (nr_cpu_ids > rcu_capacity[MAX_RCU_LVLS]) + if (nr_cpu_ids > rcu_capacity[MAX_RCU_LVLS - 1]) panic("rcu_init_geometry: rcu_capacity[] is too small"); /* Calculate the number of levels in the tree. */ - for (i = 1; nr_cpu_ids > rcu_capacity[i]; i++) { + for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) { } - rcu_num_lvls = i; + rcu_num_lvls = i + 1; /* Calculate the number of rcu_nodes at each level of the tree. */ for (i = 0; i < rcu_num_lvls; i++) { - int cap = rcu_capacity[rcu_num_lvls - i]; + int cap = rcu_capacity[(rcu_num_lvls - 1) - i]; num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap); } From a6d77081e266605c9f4d8c11e0ee00468b9dc614 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:27 +0200 Subject: [PATCH 06/32] rcu: Limit rcu_state::levelcnt[] to RCU_NUM_LVLS items Variable rcu_num_lvls is limited by RCU_NUM_LVLS macro. In turn, rcu_state::levelcnt[] array is never accessed beyond rcu_num_lvls. Thus, rcu_state::levelcnt[] is safe to limit to RCU_NUM_LVLS items. Since rcu_num_lvls could be changed during boot (as result of rcutree.rcu_fanout_leaf kernel parameter update) one might assume a new value could overflow the value of RCU_NUM_LVLS. However, that is not the case, since leaf-level fanout is only permitted to increase, resulting in rcu_num_lvls possibly to decrease. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index f1f4784f9107..a6faae53ea8f 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -443,7 +443,7 @@ do { \ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ - u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ + u32 levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ From 05b84aec465c34da242a224d2438d192ca0feec7 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:28 +0200 Subject: [PATCH 07/32] rcu: Limit rcu_capacity[] size to RCU_NUM_LVLS items Number of items in rcu_capacity[] array is defined by macro MAX_RCU_LVLS. However, that array is never accessed beyond RCU_NUM_LVLS index. Therefore, we can limit the array to RCU_NUM_LVLS items and eliminate MAX_RCU_LVLS. As result, in most cases the memory is conserved. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 12 ++++++------ kernel/rcu/tree.h | 2 -- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2103beedb49f..2ec7b796f660 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3998,19 +3998,19 @@ static void __init rcu_init_one(struct rcu_state *rsp, "rcu_node_0", "rcu_node_1", "rcu_node_2", - "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + "rcu_node_3" }; static const char * const fqs[] = { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", - "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ + "rcu_node_fqs_3" }; static u8 fl_mask = 0x1; int cpustride = 1; int i; int j; struct rcu_node *rnp; - BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */ + BUILD_BUG_ON(RCU_NUM_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */ /* Silence gcc 4.8 false positive about array index out of range. */ if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS) @@ -4082,7 +4082,7 @@ static void __init rcu_init_geometry(void) { ulong d; int i; - int rcu_capacity[MAX_RCU_LVLS]; + int rcu_capacity[RCU_NUM_LVLS]; /* * Initialize any unspecified boot parameters. @@ -4122,14 +4122,14 @@ static void __init rcu_init_geometry(void) * with the given number of levels. */ rcu_capacity[0] = rcu_fanout_leaf; - for (i = 1; i < MAX_RCU_LVLS; i++) + for (i = 1; i < RCU_NUM_LVLS; i++) rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT; /* * The tree must be able to accommodate the configured number of CPUs. * If this limit is exceeded than we have a serious problem elsewhere. */ - if (nr_cpu_ids > rcu_capacity[MAX_RCU_LVLS - 1]) + if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) panic("rcu_init_geometry: rcu_capacity[] is too small"); /* Calculate the number of levels in the tree. */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index a6faae53ea8f..d625e9ff0faf 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -36,8 +36,6 @@ * Of course, your mileage may vary. */ -#define MAX_RCU_LVLS 4 - #ifdef CONFIG_RCU_FANOUT #define RCU_FANOUT CONFIG_RCU_FANOUT #else /* #ifdef CONFIG_RCU_FANOUT */ From 199977bff9efceec649d74510fa9754e107ce0c5 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:29 +0200 Subject: [PATCH 08/32] rcu: Remove unnecessary fields from rcu_state structure Members rcu_state::levelcnt[] and rcu_state::levelspread[] are only used at init. There is no reason to keep them afterwards. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 27 +++++++++++++++------------ kernel/rcu/tree.h | 2 -- 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2ec7b796f660..7226e25ba97f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3967,22 +3967,22 @@ void rcu_scheduler_starting(void) * Compute the per-level fanout, either using the exact fanout specified * or balancing the tree, depending on the rcu_fanout_exact boot parameter. */ -static void __init rcu_init_levelspread(struct rcu_state *rsp) +static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt) { int i; if (rcu_fanout_exact) { - rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; + levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; for (i = rcu_num_lvls - 2; i >= 0; i--) - rsp->levelspread[i] = RCU_FANOUT; + levelspread[i] = RCU_FANOUT; } else { int ccur; int cprv; cprv = nr_cpu_ids; for (i = rcu_num_lvls - 1; i >= 0; i--) { - ccur = rsp->levelcnt[i]; - rsp->levelspread[i] = (cprv + ccur - 1) / ccur; + ccur = levelcnt[i]; + levelspread[i] = (cprv + ccur - 1) / ccur; cprv = ccur; } } @@ -4005,6 +4005,9 @@ static void __init rcu_init_one(struct rcu_state *rsp, "rcu_node_fqs_2", "rcu_node_fqs_3" }; static u8 fl_mask = 0x1; + + int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ + int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ int cpustride = 1; int i; int j; @@ -4019,19 +4022,19 @@ static void __init rcu_init_one(struct rcu_state *rsp, /* Initialize the level-tracking arrays. */ for (i = 0; i < rcu_num_lvls; i++) - rsp->levelcnt[i] = num_rcu_lvl[i]; + levelcnt[i] = num_rcu_lvl[i]; for (i = 1; i < rcu_num_lvls; i++) - rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; - rcu_init_levelspread(rsp); + rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1]; + rcu_init_levelspread(levelspread, levelcnt); rsp->flavor_mask = fl_mask; fl_mask <<= 1; /* Initialize the elements themselves, starting from the leaves. */ for (i = rcu_num_lvls - 1; i >= 0; i--) { - cpustride *= rsp->levelspread[i]; + cpustride *= levelspread[i]; rnp = rsp->level[i]; - for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { + for (j = 0; j < levelcnt[i]; j++, rnp++) { raw_spin_lock_init(&rnp->lock); lockdep_set_class_and_name(&rnp->lock, &rcu_node_class[i], buf[i]); @@ -4051,10 +4054,10 @@ static void __init rcu_init_one(struct rcu_state *rsp, rnp->grpmask = 0; rnp->parent = NULL; } else { - rnp->grpnum = j % rsp->levelspread[i - 1]; + rnp->grpnum = j % levelspread[i - 1]; rnp->grpmask = 1UL << rnp->grpnum; rnp->parent = rsp->level[i - 1] + - j / rsp->levelspread[i - 1]; + j / levelspread[i - 1]; } rnp->level = i; INIT_LIST_HEAD(&rnp->blkd_tasks); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index d625e9ff0faf..3413f3c5c8b2 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -441,8 +441,6 @@ do { \ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ - u32 levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ - u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ From cb007102398edd06ffc4488bf841c2e10f14d2e7 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:30 +0200 Subject: [PATCH 09/32] rcu: Limit count of static data to the number of RCU levels Although a number of RCU levels may be less than the current maximum of four, some static data associated with each level are allocated for all four levels. As result, the extra data never get accessed and just wast memory. This update limits count of allocated items to the number of used RCU levels. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 21 ++++----------------- kernel/rcu/tree.h | 12 ++++++++++++ 2 files changed, 16 insertions(+), 17 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7226e25ba97f..e53bbc53bcd5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -124,13 +124,8 @@ module_param(rcu_fanout_exact, bool, 0444); static int rcu_fanout_leaf = RCU_FANOUT_LEAF; module_param(rcu_fanout_leaf, int, 0444); int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; -static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ - NUM_RCU_LVL_0, - NUM_RCU_LVL_1, - NUM_RCU_LVL_2, - NUM_RCU_LVL_3, - NUM_RCU_LVL_4, -}; +/* Number of rcu_nodes at specified level. */ +static int num_rcu_lvl[] = NUM_RCU_LVL_INIT; int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ /* @@ -3994,16 +3989,8 @@ static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt) static void __init rcu_init_one(struct rcu_state *rsp, struct rcu_data __percpu *rda) { - static const char * const buf[] = { - "rcu_node_0", - "rcu_node_1", - "rcu_node_2", - "rcu_node_3" }; - static const char * const fqs[] = { - "rcu_node_fqs_0", - "rcu_node_fqs_1", - "rcu_node_fqs_2", - "rcu_node_fqs_3" }; + static const char * const buf[] = RCU_NODE_NAME_INIT; + static const char * const fqs[] = RCU_FQS_NAME_INIT; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 3413f3c5c8b2..d44856b6170a 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -68,6 +68,9 @@ # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 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 @@ -75,6 +78,9 @@ # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 +# 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 @@ -82,6 +88,9 @@ # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_3 (NR_CPUS) # define NUM_RCU_LVL_4 0 +# 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 @@ -89,6 +98,9 @@ # 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_LVL_4 (NR_CPUS) +# 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 */ From 426216970e0458c1f507860f4837cbde66a72263 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:31 +0200 Subject: [PATCH 10/32] rcu: Simplify arithmetic to calculate number of RCU nodes This update makes arithmetic to calculate number of RCU nodes more straight and easy to read. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 17 ++++------------- kernel/rcu/tree_plugin.h | 4 ++-- 2 files changed, 6 insertions(+), 15 deletions(-) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index d44856b6170a..581f8d3c5b28 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -64,10 +64,7 @@ #if NR_CPUS <= RCU_FANOUT_1 # define RCU_NUM_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 -# define NUM_RCU_LVL_4 0 +# 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" } @@ -75,9 +72,7 @@ # 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_LVL_2 (NR_CPUS) -# define NUM_RCU_LVL_3 0 -# define NUM_RCU_LVL_4 0 +# 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" } @@ -86,8 +81,7 @@ # 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_LVL_3 (NR_CPUS) -# define NUM_RCU_LVL_4 0 +# 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" } @@ -97,7 +91,7 @@ # 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_LVL_4 (NR_CPUS) +# 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" } @@ -105,9 +99,6 @@ # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ -#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) -#define NUM_RCU_NODES (RCU_SUM - NR_CPUS) - extern int rcu_num_lvls; extern int rcu_num_nodes; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 013485fb2b06..5dac0a10a985 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -84,8 +84,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU torture testing starts during boot.\n"); if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) pr_info("\tAdditional per-CPU info printed with stalls.\n"); - if (NUM_RCU_LVL_4 != 0) - pr_info("\tFour-level hierarchy is enabled.\n"); + if (RCU_NUM_LVLS >= 4) + pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); From 032dfc87225c96ec1771e5967436c4b23d1dc5d6 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 9 Jul 2015 15:34:23 +0200 Subject: [PATCH 11/32] rcu: Shut up bogus gcc array bounds warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Because gcc does not realize a loop would not be entered ever (i.e. in case of rcu_num_lvls == 1): for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1]; some compiler (pre- 5.x?) versions give a bogus warning: kernel/rcu/tree.c: In function ‘rcu_init_one.isra.55’: kernel/rcu/tree.c:4108:13: warning: array subscript is above array bounds [-Warray-bounds] rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; ^ Fix that warning by adding an extra item to rcu_state::level[] array. Once the bogus warning is fixed in gcc and kernel drops support of older versions, the dummy item may be removed from the array. Cc: "Paul E. McKenney" Suggested-by: "Paul E. McKenney" Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 581f8d3c5b28..faee5242d6ff 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -443,7 +443,9 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ + struct rcu_node *level[RCU_NUM_LVLS + 1]; + /* Hierarchy levels (+1 to */ + /* shut bogus gcc warning) */ u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ From 13bd64947f53ba8d7199922be94b6626b8e222d7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 4 Jun 2015 10:06:01 -0700 Subject: [PATCH 12/32] rcu: Reset rcu_fanout_leaf if out of bounds Currently if the rcu_fanout_leaf boot parameter is out of bounds (that is, less than RCU_FANOUT_LEAF or greater than the number of bits in an unsigned long), a warning is issued and execution continues with the out-of-bounds value. This can result in all manner of failures, so this patch resets rcu_fanout_leaf to RCU_FANOUT_LEAF when an out-of-bounds condition is detected. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e53bbc53bcd5..a2147d7b51c0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4103,6 +4103,7 @@ static void __init rcu_init_geometry(void) */ if (rcu_fanout_leaf < RCU_FANOUT_LEAF || rcu_fanout_leaf > sizeof(unsigned long) * 8) { + rcu_fanout_leaf = RCU_FANOUT_LEAF; WARN_ON(1); return; } From 9b683874504a57cfa97558d403c75e286e20c9ce Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 11 Jun 2015 14:50:22 -0700 Subject: [PATCH 13/32] rcu: Stop disabling CPU hotplug in synchronize_rcu_expedited() The fact that tasks could be migrated from leaf to root rcu_node structures meant that synchronize_rcu_expedited() had to disable CPU hotplug. However, tasks now stay put, so this commit removes the CPU-hotplug disabling from synchronize_rcu_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 5dac0a10a985..7234f03e0aa2 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -727,20 +727,6 @@ void synchronize_rcu_expedited(void) snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1; smp_mb(); /* Above access cannot bleed into critical section. */ - /* - * Block CPU-hotplug operations. This means that any CPU-hotplug - * operation that finds an rcu_node structure with tasks in the - * process of being boosted will know that all tasks blocking - * this expedited grace period will already be in the process of - * being boosted. This simplifies the process of moving tasks - * from leaf to root rcu_node structures. - */ - if (!try_get_online_cpus()) { - /* CPU-hotplug operation in flight, fall back to normal GP. */ - wait_rcu_gp(call_rcu); - return; - } - /* * Acquire lock, falling back to synchronize_rcu() if too many * lock-acquisition failures. Of course, if someone does the @@ -748,22 +734,17 @@ void synchronize_rcu_expedited(void) */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { if (ULONG_CMP_LT(snap, - READ_ONCE(sync_rcu_preempt_exp_count))) { - put_online_cpus(); + READ_ONCE(sync_rcu_preempt_exp_count))) goto mb_ret; /* Others did our work for us. */ - } if (trycount++ < 10) { udelay(trycount * num_online_cpus()); } else { - put_online_cpus(); wait_rcu_gp(call_rcu); return; } } - if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) { - put_online_cpus(); + if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) goto unlock_mb_ret; /* Others did our work for us. */ - } /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); @@ -779,8 +760,6 @@ void synchronize_rcu_expedited(void) rcu_for_each_leaf_node(rsp, rnp) sync_rcu_preempt_exp_init2(rsp, rnp); - put_online_cpus(); - /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); wait_event(sync_rcu_preempt_exp_wq, From 75c27f119b6475d95374bdad872c6938b5c26196 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 11 Jun 2015 15:22:43 -0700 Subject: [PATCH 14/32] rcu: Remove CONFIG_RCU_CPU_STALL_INFO The CONFIG_RCU_CPU_STALL_INFO has been default-y for a couple of releases with no complaints, so it is time to eliminate this Kconfig option entirely, so that the long-form RCU CPU stall warnings cannot be disabled. This commit does just that. Signed-off-by: Paul E. McKenney --- Documentation/RCU/stallwarn.txt | 12 +---- kernel/rcu/tree.h | 4 -- kernel/rcu/tree_plugin.h | 45 ------------------- lib/Kconfig.debug | 14 ------ .../selftests/rcutorture/configs/rcu/TREE01 | 1 - .../selftests/rcutorture/configs/rcu/TREE02 | 1 - .../selftests/rcutorture/configs/rcu/TREE02-T | 1 - .../selftests/rcutorture/configs/rcu/TREE03 | 1 - .../selftests/rcutorture/configs/rcu/TREE04 | 1 - .../selftests/rcutorture/configs/rcu/TREE05 | 1 - .../selftests/rcutorture/configs/rcu/TREE06 | 1 - .../selftests/rcutorture/configs/rcu/TREE07 | 1 - .../selftests/rcutorture/configs/rcu/TREE08 | 1 - .../selftests/rcutorture/configs/rcu/TREE08-T | 1 - .../selftests/rcutorture/configs/rcu/TREE09 | 1 - .../rcutorture/doc/TREE_RCU-kconfig.txt | 1 - 16 files changed, 2 insertions(+), 85 deletions(-) diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index b57c0c1cdac6..046f32637b95 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -26,12 +26,6 @@ CONFIG_RCU_CPU_STALL_TIMEOUT Stall-warning messages may be enabled and disabled completely via /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. -CONFIG_RCU_CPU_STALL_INFO - - This kernel configuration parameter causes the stall warning to - print out additional per-CPU diagnostic information, including - information on scheduling-clock ticks and RCU's idle-CPU tracking. - RCU_STALL_DELAY_DELTA Although the lockdep facility is extremely useful, it does add @@ -101,15 +95,13 @@ interact. Please note that it is not possible to entirely eliminate this sort of false positive without resorting to things like stop_machine(), which is overkill for this sort of problem. -If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set, -more information is printed with the stall-warning message, for example: +Recent kernels will print a long form of the stall-warning message: INFO: rcu_preempt detected stall on CPU 0: (63959 ticks this GP) idle=241/3fffffffffffffff/0 softirq=82/543 (t=65000 jiffies) -In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is -printed: +In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed: INFO: rcu_preempt detected stall on CPU 0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index faee5242d6ff..7c0b09d754a1 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -288,12 +288,10 @@ struct rcu_data { bool gpwrap; /* Possible gpnum/completed wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ -#ifdef CONFIG_RCU_CPU_STALL_INFO unsigned long ticks_this_gp; /* The number of scheduling-clock */ /* ticks this CPU has handled */ /* during and after the last grace */ /* period it is aware of. */ -#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ /* 2) batch handling */ /* @@ -388,9 +386,7 @@ struct rcu_data { #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* 8) RCU CPU stall data. */ -#ifdef CONFIG_RCU_CPU_STALL_INFO unsigned int softirq_snap; /* Snapshot of softirq activity. */ -#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ int cpu; struct rcu_state *rsp; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7234f03e0aa2..ef41c1b04ba6 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -82,8 +82,6 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU lockdep checking is enabled.\n"); if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) pr_info("\tRCU torture testing starts during boot.\n"); - if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) - pr_info("\tAdditional per-CPU info printed with stalls.\n"); if (RCU_NUM_LVLS >= 4) pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) @@ -418,8 +416,6 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) rcu_print_detail_task_stall_rnp(rnp); } -#ifdef CONFIG_RCU_CPU_STALL_INFO - static void rcu_print_task_stall_begin(struct rcu_node *rnp) { pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", @@ -431,18 +427,6 @@ static void rcu_print_task_stall_end(void) pr_cont("\n"); } -#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ - -static void rcu_print_task_stall_begin(struct rcu_node *rnp) -{ -} - -static void rcu_print_task_stall_end(void) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ - /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -1685,8 +1669,6 @@ early_initcall(rcu_register_oom_notifier); #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ -#ifdef CONFIG_RCU_CPU_STALL_INFO - #ifdef CONFIG_RCU_FAST_NO_HZ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) @@ -1775,33 +1757,6 @@ static void increment_cpu_stall_ticks(void) raw_cpu_inc(rsp->rda->ticks_this_gp); } -#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ - -static void print_cpu_stall_info_begin(void) -{ - pr_cont(" {"); -} - -static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) -{ - pr_cont(" %d", cpu); -} - -static void print_cpu_stall_info_end(void) -{ - pr_cont("} "); -} - -static void zero_cpu_stall_ticks(struct rcu_data *rdp) -{ -} - -static void increment_cpu_stall_ticks(void) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ - #ifdef CONFIG_RCU_NOCB_CPU /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e2894b23efb6..8a34205d6922 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1353,20 +1353,6 @@ config RCU_CPU_STALL_TIMEOUT RCU grace period persists, additional CPU stall warnings are printed at more widely spaced intervals. -config RCU_CPU_STALL_INFO - bool "Print additional diagnostics on RCU CPU stall" - depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL - default y - help - For each stalled CPU that is aware of the current RCU grace - period, print out additional per-CPU diagnostic information - regarding scheduling-clock ticks, idle state, and, - for RCU_FAST_NO_HZ kernels, idle-entry state. - - Say N if you are unsure. - - Say Y if you want to enable such diagnostics. - config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 8e9137f66831..f572b873c620 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -13,7 +13,6 @@ CONFIG_MAXSMP=y CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index aeea6a204d14..ef6a22c44dea 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -17,7 +17,6 @@ CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T index 2ac9e68ea3d1..917d2517b5b5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 72aa7d87ea99..7a17c503b382 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -13,7 +13,6 @@ CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=y CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 3f5112751cda..39a2c6d7d7ec 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT=4 CONFIG_RCU_FANOUT_LEAF=4 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index c04dfea6fd21..1257d3227b1e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -17,6 +17,5 @@ CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index f51d2c73a68e..d3e456b74cbe 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -18,6 +18,5 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index f422af4ff5a3..3956b4131f72 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index a24d2ca30646..bb9b0c1a23c2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -19,7 +19,6 @@ CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T index b2b8cea69dc9..2ad13f0d29cc 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T @@ -17,6 +17,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index aa4ed08d999d..6710e749d9de 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -13,7 +13,6 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_CPU_STALL_INFO=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n #CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index b24c0004fc49..657f3a035488 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -16,7 +16,6 @@ CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. -CONFIG_RCU_CPU_STALL_INFO -- Now default, avoid at least twice. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. CONFIG_RCU_FANOUT_LEAF -- Do one non-default. CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL. From c190c3b16c0f56ff338df12df53c03859155951b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Jun 2015 19:03:45 -0700 Subject: [PATCH 15/32] rcu: Switch synchronize_sched_expedited() to stop_one_cpu() The synchronize_sched_expedited() currently invokes try_stop_cpus(), which schedules the stopper kthreads on each online non-idle CPU, and waits until all those kthreads are running before letting any of them stop. This is disastrous for real-time workloads, which get hit with a preemption that is as long as the longest scheduling latency on any CPU, including any non-realtime housekeeping CPUs. This commit therefore switches to using stop_one_cpu() on each CPU in turn. This avoids inflicting the worst-case scheduling latency on the worst-case CPU onto all other CPUs, and also simplifies the code a little bit. Follow-up commits will simplify the counter-snapshotting algorithm and convert a number of the counters that are now protected by the new ->expedited_mutex to non-atomic. Signed-off-by: Peter Zijlstra [ paulmck: Kept stop_one_cpu(), dropped disabling of "guardrails". ] Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 41 ++++++++++++++--------------------------- kernel/rcu/tree.h | 1 + 2 files changed, 15 insertions(+), 27 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a2147d7b51c0..ae39a49daa58 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -103,6 +103,7 @@ struct rcu_state sname##_state = { \ .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ + .expedited_mutex = __MUTEX_INITIALIZER(sname##_state.expedited_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ } @@ -3305,8 +3306,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data) */ void synchronize_sched_expedited(void) { - cpumask_var_t cm; - bool cma = false; int cpu; long firstsnap, s, snap; int trycount = 0; @@ -3342,28 +3341,11 @@ void synchronize_sched_expedited(void) } WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); - /* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */ - cma = zalloc_cpumask_var(&cm, GFP_KERNEL); - if (cma) { - cpumask_copy(cm, cpu_online_mask); - cpumask_clear_cpu(raw_smp_processor_id(), cm); - for_each_cpu(cpu, cm) { - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - - if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1)) - cpumask_clear_cpu(cpu, cm); - } - if (cpumask_weight(cm) == 0) - goto all_cpus_idle; - } - /* * Each pass through the following loop attempts to force a * context switch on each CPU. */ - while (try_stop_cpus(cma ? cm : cpu_online_mask, - synchronize_sched_expedited_cpu_stop, - NULL) == -EAGAIN) { + while (!mutex_trylock(&rsp->expedited_mutex)) { put_online_cpus(); atomic_long_inc(&rsp->expedited_tryfail); @@ -3373,7 +3355,6 @@ void synchronize_sched_expedited(void) /* ensure test happens before caller kfree */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(&rsp->expedited_workdone1); - free_cpumask_var(cm); return; } @@ -3383,7 +3364,6 @@ void synchronize_sched_expedited(void) } else { wait_rcu_gp(call_rcu_sched); atomic_long_inc(&rsp->expedited_normal); - free_cpumask_var(cm); return; } @@ -3393,7 +3373,6 @@ void synchronize_sched_expedited(void) /* ensure test happens before caller kfree */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(&rsp->expedited_workdone2); - free_cpumask_var(cm); return; } @@ -3408,16 +3387,23 @@ void synchronize_sched_expedited(void) /* CPU hotplug operation in flight, use normal GP. */ wait_rcu_gp(call_rcu_sched); atomic_long_inc(&rsp->expedited_normal); - free_cpumask_var(cm); return; } snap = atomic_long_read(&rsp->expedited_start); smp_mb(); /* ensure read is before try_stop_cpus(). */ } - atomic_long_inc(&rsp->expedited_stoppedcpus); -all_cpus_idle: - free_cpumask_var(cm); + /* Stop each CPU that is online, non-idle, and not us. */ + for_each_online_cpu(cpu) { + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + /* Skip our CPU and any idle CPUs. */ + if (raw_smp_processor_id() == cpu || + !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) + continue; + stop_one_cpu(cpu, synchronize_sched_expedited_cpu_stop, NULL); + } + atomic_long_inc(&rsp->expedited_stoppedcpus); /* * Everyone up to our most recent fetch is covered by our grace @@ -3436,6 +3422,7 @@ all_cpus_idle: } } while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s); atomic_long_inc(&rsp->expedited_done_exit); + mutex_unlock(&rsp->expedited_mutex); put_online_cpus(); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7c0b09d754a1..7c25fe473ad9 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -480,6 +480,7 @@ struct rcu_state { /* _rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ + struct mutex expedited_mutex; /* Serializes expediting. */ atomic_long_t expedited_start; /* Starting ticket. */ atomic_long_t expedited_done; /* Done ticket. */ atomic_long_t expedited_wrap; /* # near-wrap incidents. */ From d6ada2cf2f81dab8a231d0ef8fb5dec4f5ac8379 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 24 Jun 2015 10:46:30 -0700 Subject: [PATCH 16/32] rcu: Rework synchronize_sched_expedited() counter handling Now that synchronize_sched_expedited() have a mutex, it can use simpler work-already-done detection scheme. This commit simplifies this scheme by using something similar to the sequence-locking counter scheme. A counter is incremented before and after each grace period, so that the counter is odd in the midst of the grace period and even otherwise. So if the counter has advanced to the second even number that is greater than or equal to the snapshot, the required grace period has already happened. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 98 +++++++++++++---------------------------- kernel/rcu/tree.h | 9 +--- kernel/rcu/tree_trace.c | 12 ++--- 3 files changed, 36 insertions(+), 83 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ae39a49daa58..3c182fdec805 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3283,56 +3283,24 @@ static int synchronize_sched_expedited_cpu_stop(void *data) * restructure your code to batch your updates, and then use a single * synchronize_sched() instead. * - * This implementation can be thought of as an application of ticket - * locking to RCU, with sync_sched_expedited_started and - * sync_sched_expedited_done taking on the roles of the halves - * of the ticket-lock word. Each task atomically increments - * sync_sched_expedited_started upon entry, snapshotting the old value, - * then attempts to stop all the CPUs. If this succeeds, then each - * CPU will have executed a context switch, resulting in an RCU-sched - * grace period. We are then done, so we use atomic_cmpxchg() to - * update sync_sched_expedited_done to match our snapshot -- but - * only if someone else has not already advanced past our snapshot. - * - * On the other hand, if try_stop_cpus() fails, we check the value - * of sync_sched_expedited_done. If it has advanced past our - * initial snapshot, then someone else must have forced a grace period - * some time after we took our snapshot. In this case, our work is - * done for us, and we can simply return. Otherwise, we try again, - * but keep our initial snapshot for purposes of checking for someone - * doing our work for us. - * - * If we fail too many times in a row, we fall back to synchronize_sched(). + * This implementation can be thought of as an application of sequence + * locking to expedited grace periods, but using the sequence counter to + * determine when someone else has already done the work instead of for + * retrying readers. We do a mutex_trylock() polling loop, but if we fail + * too many times in a row, we fall back to synchronize_sched(). */ void synchronize_sched_expedited(void) { int cpu; - long firstsnap, s, snap; + long s; int trycount = 0; struct rcu_state *rsp = &rcu_sched_state; - /* - * If we are in danger of counter wrap, just do synchronize_sched(). - * By allowing sync_sched_expedited_started to advance no more than - * ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring - * that more than 3.5 billion CPUs would be required to force a - * counter wrap on a 32-bit system. Quite a few more CPUs would of - * course be required on a 64-bit system. - */ - if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start), - (ulong)atomic_long_read(&rsp->expedited_done) + - ULONG_MAX / 8)) { - wait_rcu_gp(call_rcu_sched); - atomic_long_inc(&rsp->expedited_wrap); - return; - } + /* Take a snapshot of the sequence number. */ + smp_mb(); /* Caller's modifications seen first by other CPUs. */ + s = (READ_ONCE(rsp->expedited_sequence) + 3) & ~0x1; + smp_mb(); /* Above access must not bleed into critical section. */ - /* - * Take a ticket. Note that atomic_inc_return() implies a - * full memory barrier. - */ - snap = atomic_long_inc_return(&rsp->expedited_start); - firstsnap = snap; if (!try_get_online_cpus()) { /* CPU hotplug operation in flight, fall back to normal GP. */ wait_rcu_gp(call_rcu_sched); @@ -3342,16 +3310,15 @@ void synchronize_sched_expedited(void) WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); /* - * Each pass through the following loop attempts to force a - * context switch on each CPU. + * Each pass through the following loop attempts to acquire + * ->expedited_mutex, checking for others doing our work each time. */ while (!mutex_trylock(&rsp->expedited_mutex)) { put_online_cpus(); atomic_long_inc(&rsp->expedited_tryfail); /* Check to see if someone else did our work for us. */ - s = atomic_long_read(&rsp->expedited_done); - if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) { + if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { /* ensure test happens before caller kfree */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(&rsp->expedited_workdone1); @@ -3368,8 +3335,7 @@ void synchronize_sched_expedited(void) } /* Recheck to see if someone else did our work for us. */ - s = atomic_long_read(&rsp->expedited_done); - if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) { + if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { /* ensure test happens before caller kfree */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(&rsp->expedited_workdone2); @@ -3389,10 +3355,20 @@ void synchronize_sched_expedited(void) atomic_long_inc(&rsp->expedited_normal); return; } - snap = atomic_long_read(&rsp->expedited_start); - smp_mb(); /* ensure read is before try_stop_cpus(). */ } + /* Recheck yet again to see if someone else did our work for us. */ + if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { + rsp->expedited_workdone3++; + mutex_unlock(&rsp->expedited_mutex); + smp_mb(); /* ensure test happens before caller kfree */ + return; + } + + WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); + smp_mb(); /* Ensure expedited GP seen after counter increment. */ + WARN_ON_ONCE(!(rsp->expedited_sequence & 0x1)); + /* Stop each CPU that is online, non-idle, and not us. */ for_each_online_cpu(cpu) { struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); @@ -3403,26 +3379,12 @@ void synchronize_sched_expedited(void) continue; stop_one_cpu(cpu, synchronize_sched_expedited_cpu_stop, NULL); } - atomic_long_inc(&rsp->expedited_stoppedcpus); - /* - * Everyone up to our most recent fetch is covered by our grace - * period. Update the counter, but only if our work is still - * relevant -- which it won't be if someone who started later - * than we did already did their update. - */ - do { - atomic_long_inc(&rsp->expedited_done_tries); - s = atomic_long_read(&rsp->expedited_done); - if (ULONG_CMP_GE((ulong)s, (ulong)snap)) { - /* ensure test happens before caller kfree */ - smp_mb__before_atomic(); /* ^^^ */ - atomic_long_inc(&rsp->expedited_done_lost); - break; - } - } while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s); - atomic_long_inc(&rsp->expedited_done_exit); + smp_mb(); /* Ensure expedited GP seen before counter increment. */ + WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); + WARN_ON_ONCE(rsp->expedited_sequence & 0x1); mutex_unlock(&rsp->expedited_mutex); + smp_mb(); /* ensure subsequent action seen after grace period. */ put_online_cpus(); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7c25fe473ad9..6a2b741436de 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -481,17 +481,12 @@ struct rcu_state { /* End of fields guarded by barrier_mutex. */ struct mutex expedited_mutex; /* Serializes expediting. */ - atomic_long_t expedited_start; /* Starting ticket. */ - atomic_long_t expedited_done; /* Done ticket. */ - atomic_long_t expedited_wrap; /* # near-wrap incidents. */ + unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_tryfail; /* # acquisition failures. */ atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ + unsigned long expedited_workdone3; /* # done by others #3. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ - atomic_long_t expedited_stoppedcpus; /* # successful stop_cpus. */ - atomic_long_t expedited_done_tries; /* # tries to update _done. */ - atomic_long_t expedited_done_lost; /* # times beaten to _done. */ - atomic_long_t expedited_done_exit; /* # times exited _done loop. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 3ea7ffc7d5c4..a1ab3a5f6290 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,18 +185,14 @@ static int show_rcuexp(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "s=%lu d=%lu w=%lu tf=%lu wd1=%lu wd2=%lu n=%lu sc=%lu dt=%lu dl=%lu dx=%lu\n", - atomic_long_read(&rsp->expedited_start), - atomic_long_read(&rsp->expedited_done), - atomic_long_read(&rsp->expedited_wrap), + seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu sc=%lu\n", + rsp->expedited_sequence, atomic_long_read(&rsp->expedited_tryfail), atomic_long_read(&rsp->expedited_workdone1), atomic_long_read(&rsp->expedited_workdone2), + rsp->expedited_workdone3, atomic_long_read(&rsp->expedited_normal), - atomic_long_read(&rsp->expedited_stoppedcpus), - atomic_long_read(&rsp->expedited_done_tries), - atomic_long_read(&rsp->expedited_done_lost), - atomic_long_read(&rsp->expedited_done_exit)); + rsp->expedited_sequence / 2); return 0; } From 385b73c06f6a733547d0a7714d0c4cb4c8788b88 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 24 Jun 2015 14:20:08 -0700 Subject: [PATCH 17/32] rcu: Get rid of synchronize_sched_expedited()'s polling loop This commit gets rid of synchronize_sched_expedited()'s mutex_trylock() polling loop in favor of a funnel-locking scheme based on the rcu_node tree. The work-done check is done at each level of the tree, allowing high-contention situations to be resolved quickly with reasonable levels of mutex contention. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 95 +++++++++++++++++------------------------ kernel/rcu/tree.h | 8 +++- kernel/rcu/tree_trace.c | 3 +- 3 files changed, 47 insertions(+), 59 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3c182fdec805..b310b40a49a2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -70,6 +70,7 @@ MODULE_ALIAS("rcutree"); static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; +static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; /* * In order to export the rcu_state name to the tracing tools, it @@ -103,7 +104,6 @@ struct rcu_state sname##_state = { \ .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .expedited_mutex = __MUTEX_INITIALIZER(sname##_state.expedited_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ } @@ -3272,6 +3272,22 @@ static int synchronize_sched_expedited_cpu_stop(void *data) return 0; } +/* Common code for synchronize_sched_expedited() work-done checking. */ +static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, + atomic_long_t *stat, unsigned long s) +{ + if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { + if (rnp) + mutex_unlock(&rnp->exp_funnel_mutex); + /* Ensure test happens before caller kfree(). */ + smp_mb__before_atomic(); /* ^^^ */ + atomic_long_inc(stat); + put_online_cpus(); + return true; + } + return false; +} + /** * synchronize_sched_expedited - Brute-force RCU-sched grace period * @@ -3286,15 +3302,15 @@ static int synchronize_sched_expedited_cpu_stop(void *data) * This implementation can be thought of as an application of sequence * locking to expedited grace periods, but using the sequence counter to * determine when someone else has already done the work instead of for - * retrying readers. We do a mutex_trylock() polling loop, but if we fail - * too many times in a row, we fall back to synchronize_sched(). + * retrying readers. */ void synchronize_sched_expedited(void) { int cpu; long s; - int trycount = 0; struct rcu_state *rsp = &rcu_sched_state; + struct rcu_node *rnp0; + struct rcu_node *rnp1 = NULL; /* Take a snapshot of the sequence number. */ smp_mb(); /* Caller's modifications seen first by other CPUs. */ @@ -3310,60 +3326,25 @@ void synchronize_sched_expedited(void) WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); /* - * Each pass through the following loop attempts to acquire - * ->expedited_mutex, checking for others doing our work each time. + * Each pass through the following loop works its way + * up the rcu_node tree, returning if others have done the + * work or otherwise falls through holding the root rnp's + * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure + * can be inexact, as it is just promoting locality and is not + * strictly needed for correctness. */ - while (!mutex_trylock(&rsp->expedited_mutex)) { - put_online_cpus(); - atomic_long_inc(&rsp->expedited_tryfail); - - /* Check to see if someone else did our work for us. */ - if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { - /* ensure test happens before caller kfree */ - smp_mb__before_atomic(); /* ^^^ */ - atomic_long_inc(&rsp->expedited_workdone1); + rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + for (; rnp0 != NULL; rnp0 = rnp0->parent) { + if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone1, s)) return; - } - - /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) { - udelay(trycount * num_online_cpus()); - } else { - wait_rcu_gp(call_rcu_sched); - atomic_long_inc(&rsp->expedited_normal); - return; - } - - /* Recheck to see if someone else did our work for us. */ - if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { - /* ensure test happens before caller kfree */ - smp_mb__before_atomic(); /* ^^^ */ - atomic_long_inc(&rsp->expedited_workdone2); - return; - } - - /* - * Refetching sync_sched_expedited_started allows later - * callers to piggyback on our grace period. We retry - * after they started, so our grace period works for them, - * and they started after our first try, so their grace - * period works for us. - */ - if (!try_get_online_cpus()) { - /* CPU hotplug operation in flight, use normal GP. */ - wait_rcu_gp(call_rcu_sched); - atomic_long_inc(&rsp->expedited_normal); - return; - } + mutex_lock(&rnp0->exp_funnel_mutex); + if (rnp1) + mutex_unlock(&rnp1->exp_funnel_mutex); + rnp1 = rnp0; } - - /* Recheck yet again to see if someone else did our work for us. */ - if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { - rsp->expedited_workdone3++; - mutex_unlock(&rsp->expedited_mutex); - smp_mb(); /* ensure test happens before caller kfree */ + rnp0 = rnp1; /* rcu_get_root(rsp), AKA root rcu_node structure. */ + if (sync_sched_exp_wd(rsp, rnp0, &rsp->expedited_workdone2, s)) return; - } WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); smp_mb(); /* Ensure expedited GP seen after counter increment. */ @@ -3383,7 +3364,7 @@ void synchronize_sched_expedited(void) smp_mb(); /* Ensure expedited GP seen before counter increment. */ WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); WARN_ON_ONCE(rsp->expedited_sequence & 0x1); - mutex_unlock(&rsp->expedited_mutex); + mutex_unlock(&rnp0->exp_funnel_mutex); smp_mb(); /* ensure subsequent action seen after grace period. */ put_online_cpus(); @@ -3940,6 +3921,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; + static const char * const exp[] = RCU_EXP_NAME_INIT; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -3998,6 +3980,9 @@ static void __init rcu_init_one(struct rcu_state *rsp, rnp->level = i; INIT_LIST_HEAD(&rnp->blkd_tasks); rcu_init_one_nocb(rnp); + mutex_init(&rnp->exp_funnel_mutex); + lockdep_set_class_and_name(&rnp->exp_funnel_mutex, + &rcu_exp_class[i], exp[i]); } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6a2b741436de..2ef036b356f7 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -68,6 +68,7 @@ # 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" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 @@ -76,6 +77,7 @@ # 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" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 @@ -85,6 +87,7 @@ # 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" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 @@ -95,6 +98,7 @@ # 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" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ @@ -237,6 +241,8 @@ struct rcu_node { int need_future_gp[2]; /* Counts of upcoming no-CB GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; + + struct mutex exp_funnel_mutex ____cacheline_internodealigned_in_smp; } ____cacheline_internodealigned_in_smp; /* @@ -480,12 +486,10 @@ struct rcu_state { /* _rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ - struct mutex expedited_mutex; /* Serializes expediting. */ unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_tryfail; /* # acquisition failures. */ atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ - unsigned long expedited_workdone3; /* # done by others #3. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index a1ab3a5f6290..d2aab8dcd58e 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,12 +185,11 @@ static int show_rcuexp(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu sc=%lu\n", + seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu n=%lu sc=%lu\n", rsp->expedited_sequence, atomic_long_read(&rsp->expedited_tryfail), atomic_long_read(&rsp->expedited_workdone1), atomic_long_read(&rsp->expedited_workdone2), - rsp->expedited_workdone3, atomic_long_read(&rsp->expedited_normal), rsp->expedited_sequence / 2); return 0; From 3a6d7c64d78a78d279851524d39999637a549363 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Jun 2015 11:27:10 -0700 Subject: [PATCH 18/32] rcu: Make expedited GP CPU stoppage asynchronous Sequentially stopping the CPUs slows down expedited grace periods by at least a factor of two, based on rcutorture's grace-period-per-second rate. This is a conservative measure because rcutorture uses unusually long RCU read-side critical sections and because rcutorture periodically quiesces the system in order to test RCU's ability to ramp down to and up from the idle state. This commit therefore replaces the stop_one_cpu() with stop_one_cpu_nowait(), using an atomic-counter scheme to determine when all CPUs have passed through the stopped state. Signed-off-by: Peter Zijlstra Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 31 +++++++++++++++++-------------- kernel/rcu/tree.h | 6 ++++++ kernel/rcu/tree_trace.c | 3 ++- 3 files changed, 25 insertions(+), 15 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b310b40a49a2..c5c8509054ef 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3257,18 +3257,11 @@ EXPORT_SYMBOL_GPL(cond_synchronize_rcu); static int synchronize_sched_expedited_cpu_stop(void *data) { - /* - * There must be a full memory barrier on each affected CPU - * between the time that try_stop_cpus() is called and the - * time that it returns. - * - * In the current initial implementation of cpu_stop, the - * above condition is already met when the control reaches - * this point and the following smp_mb() is not strictly - * necessary. Do smp_mb() anyway for documentation and - * robustness against future implementation changes. - */ - smp_mb(); /* See above comment block. */ + struct rcu_state *rsp = data; + + /* We are here: If we are last, do the wakeup. */ + if (atomic_dec_and_test(&rsp->expedited_need_qs)) + wake_up(&rsp->expedited_wq); return 0; } @@ -3308,9 +3301,9 @@ void synchronize_sched_expedited(void) { int cpu; long s; - struct rcu_state *rsp = &rcu_sched_state; struct rcu_node *rnp0; struct rcu_node *rnp1 = NULL; + struct rcu_state *rsp = &rcu_sched_state; /* Take a snapshot of the sequence number. */ smp_mb(); /* Caller's modifications seen first by other CPUs. */ @@ -3351,16 +3344,26 @@ void synchronize_sched_expedited(void) WARN_ON_ONCE(!(rsp->expedited_sequence & 0x1)); /* Stop each CPU that is online, non-idle, and not us. */ + init_waitqueue_head(&rsp->expedited_wq); + atomic_set(&rsp->expedited_need_qs, 1); /* Extra count avoids race. */ for_each_online_cpu(cpu) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); /* Skip our CPU and any idle CPUs. */ if (raw_smp_processor_id() == cpu || !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) continue; - stop_one_cpu(cpu, synchronize_sched_expedited_cpu_stop, NULL); + atomic_inc(&rsp->expedited_need_qs); + stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, + rsp, &rdp->exp_stop_work); } + /* Remove extra count and, if necessary, wait for CPUs to stop. */ + if (!atomic_dec_and_test(&rsp->expedited_need_qs)) + wait_event(rsp->expedited_wq, + !atomic_read(&rsp->expedited_need_qs)); + smp_mb(); /* Ensure expedited GP seen before counter increment. */ WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); WARN_ON_ONCE(rsp->expedited_sequence & 0x1); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 2ef036b356f7..4edc277d08eb 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,6 +27,7 @@ #include #include #include +#include /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -298,6 +299,9 @@ struct rcu_data { /* ticks this CPU has handled */ /* during and after the last grace */ /* period it is aware of. */ + struct cpu_stop_work exp_stop_work; + /* Expedited grace-period control */ + /* for CPU stopping. */ /* 2) batch handling */ /* @@ -491,6 +495,8 @@ struct rcu_state { atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ + atomic_t expedited_need_qs; /* # CPUs left to check in. */ + wait_queue_head_t expedited_wq; /* Wait for check-ins. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index d2aab8dcd58e..36c04b46d3b8 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,12 +185,13 @@ static int show_rcuexp(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu n=%lu sc=%lu\n", + seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu n=%lu enq=%d sc=%lu\n", rsp->expedited_sequence, atomic_long_read(&rsp->expedited_tryfail), atomic_long_read(&rsp->expedited_workdone1), atomic_long_read(&rsp->expedited_workdone2), atomic_long_read(&rsp->expedited_normal), + atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); return 0; } From 28f00767e3db933cacc3030f4d9736acd037be2c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 15:00:58 -0700 Subject: [PATCH 19/32] rcu: Abstract sequence counting from synchronize_sched_expedited() This commit creates rcu_exp_gp_seq_start() and rcu_exp_gp_seq_end() to bracket an expedited grace period, rcu_exp_gp_seq_snap() to snapshot the sequence counter, and rcu_exp_gp_seq_done() to check to see if a full expedited grace period has elapsed since the snapshot. These will be applied to synchronize_rcu_expedited(). These are defined in terms of underlying rcu_seq_start(), rcu_seq_end(), rcu_seq_snap(), rcu_seq_done(), which will be applied to _rcu_barrier(). One reason that this commit doesn't use the seqcount primitives themselves is that the smp_wmb() in those primitive is insufficient due to the fact that expedited grace periods do reads as well as writes. In addition, the read-side seqcount primitives detect a potentially partial change, where the expedited primitives instead need a guaranteed full change. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 68 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 58 insertions(+), 10 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c5c8509054ef..67fe75725486 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3255,6 +3255,60 @@ void cond_synchronize_rcu(unsigned long oldstate) } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); +/* Adjust sequence number for start of update-side operation. */ +static void rcu_seq_start(unsigned long *sp) +{ + WRITE_ONCE(*sp, *sp + 1); + smp_mb(); /* Ensure update-side operation after counter increment. */ + WARN_ON_ONCE(!(*sp & 0x1)); +} + +/* Adjust sequence number for end of update-side operation. */ +static void rcu_seq_end(unsigned long *sp) +{ + smp_mb(); /* Ensure update-side operation before counter increment. */ + WRITE_ONCE(*sp, *sp + 1); + WARN_ON_ONCE(*sp & 0x1); +} + +/* Take a snapshot of the update side's sequence number. */ +static unsigned long rcu_seq_snap(unsigned long *sp) +{ + unsigned long s; + + smp_mb(); /* Caller's modifications seen first by other CPUs. */ + s = (READ_ONCE(*sp) + 3) & ~0x1; + smp_mb(); /* Above access must not bleed into critical section. */ + return s; +} + +/* + * Given a snapshot from rcu_seq_snap(), determine whether or not a + * full update-side operation has occurred. + */ +static bool rcu_seq_done(unsigned long *sp, unsigned long s) +{ + return ULONG_CMP_GE(READ_ONCE(*sp), s); +} + +/* Wrapper functions for expedited grace periods. */ +static void rcu_exp_gp_seq_start(struct rcu_state *rsp) +{ + rcu_seq_start(&rsp->expedited_sequence); +} +static void rcu_exp_gp_seq_end(struct rcu_state *rsp) +{ + rcu_seq_end(&rsp->expedited_sequence); +} +static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) +{ + return rcu_seq_snap(&rsp->expedited_sequence); +} +static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) +{ + return rcu_seq_done(&rsp->expedited_sequence, s); +} + static int synchronize_sched_expedited_cpu_stop(void *data) { struct rcu_state *rsp = data; @@ -3269,7 +3323,7 @@ static int synchronize_sched_expedited_cpu_stop(void *data) static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, atomic_long_t *stat, unsigned long s) { - if (ULONG_CMP_GE(READ_ONCE(rsp->expedited_sequence), s)) { + if (rcu_exp_gp_seq_done(rsp, s)) { if (rnp) mutex_unlock(&rnp->exp_funnel_mutex); /* Ensure test happens before caller kfree(). */ @@ -3306,9 +3360,7 @@ void synchronize_sched_expedited(void) struct rcu_state *rsp = &rcu_sched_state; /* Take a snapshot of the sequence number. */ - smp_mb(); /* Caller's modifications seen first by other CPUs. */ - s = (READ_ONCE(rsp->expedited_sequence) + 3) & ~0x1; - smp_mb(); /* Above access must not bleed into critical section. */ + s = rcu_exp_gp_seq_snap(rsp); if (!try_get_online_cpus()) { /* CPU hotplug operation in flight, fall back to normal GP. */ @@ -3339,9 +3391,7 @@ void synchronize_sched_expedited(void) if (sync_sched_exp_wd(rsp, rnp0, &rsp->expedited_workdone2, s)) return; - WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); - smp_mb(); /* Ensure expedited GP seen after counter increment. */ - WARN_ON_ONCE(!(rsp->expedited_sequence & 0x1)); + rcu_exp_gp_seq_start(rsp); /* Stop each CPU that is online, non-idle, and not us. */ init_waitqueue_head(&rsp->expedited_wq); @@ -3364,9 +3414,7 @@ void synchronize_sched_expedited(void) wait_event(rsp->expedited_wq, !atomic_read(&rsp->expedited_need_qs)); - smp_mb(); /* Ensure expedited GP seen before counter increment. */ - WRITE_ONCE(rsp->expedited_sequence, rsp->expedited_sequence + 1); - WARN_ON_ONCE(rsp->expedited_sequence & 0x1); + rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp0->exp_funnel_mutex); smp_mb(); /* ensure subsequent action seen after grace period. */ From 543c6158f6dff20a741dfa492771f18ceaa1a109 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 15:52:50 -0700 Subject: [PATCH 20/32] rcu: Make synchronize_rcu_expedited() use sequence-counter scheme Although synchronize_rcu_expedited() uses a sequence-counter scheme, it is based on a single increment per grace period, which means that tasks piggybacking off of concurrent grace periods may be forced to wait longer than necessary. This commit therefore applies the new sequence-count functions developed for synchronize_sched_expedited() to speed things up a bit and to consolidate the sequence-counter implementation. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index ef41c1b04ba6..759883f51de7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -536,7 +536,6 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* @@ -704,12 +703,10 @@ void synchronize_rcu_expedited(void) { struct rcu_node *rnp; struct rcu_state *rsp = rcu_state_p; - unsigned long snap; + unsigned long s; int trycount = 0; - smp_mb(); /* Caller's modifications seen first by other CPUs. */ - snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1; - smp_mb(); /* Above access cannot bleed into critical section. */ + s = rcu_exp_gp_seq_snap(rsp); /* * Acquire lock, falling back to synchronize_rcu() if too many @@ -717,8 +714,7 @@ void synchronize_rcu_expedited(void) * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (ULONG_CMP_LT(snap, - READ_ONCE(sync_rcu_preempt_exp_count))) + if (rcu_exp_gp_seq_done(rsp, s)) goto mb_ret; /* Others did our work for us. */ if (trycount++ < 10) { udelay(trycount * num_online_cpus()); @@ -727,8 +723,9 @@ void synchronize_rcu_expedited(void) return; } } - if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) + if (rcu_exp_gp_seq_done(rsp, s)) goto unlock_mb_ret; /* Others did our work for us. */ + rcu_exp_gp_seq_start(rsp); /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); @@ -750,8 +747,7 @@ void synchronize_rcu_expedited(void) sync_rcu_preempt_exp_done(rnp)); /* Clean up and exit. */ - smp_mb(); /* ensure expedited GP seen before counter increment. */ - WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1); + rcu_exp_gp_seq_end(rsp); unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); mb_ret: From b09e5f8601d7e5b8d45348c9c09e1fb4109e8dc6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 16:30:54 -0700 Subject: [PATCH 21/32] rcu: Abstract funnel locking from synchronize_sched_expedited() This commit abstracts funnel locking from synchronize_sched_expedited() so that it may be used by synchronize_rcu_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 80 ++++++++++++++++++++++++++++------------------- 1 file changed, 47 insertions(+), 33 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 67fe75725486..f79a1c646846 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3309,16 +3309,6 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) return rcu_seq_done(&rsp->expedited_sequence, s); } -static int synchronize_sched_expedited_cpu_stop(void *data) -{ - struct rcu_state *rsp = data; - - /* We are here: If we are last, do the wakeup. */ - if (atomic_dec_and_test(&rsp->expedited_need_qs)) - wake_up(&rsp->expedited_wq); - return 0; -} - /* Common code for synchronize_sched_expedited() work-done checking. */ static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, atomic_long_t *stat, unsigned long s) @@ -3335,6 +3325,48 @@ static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, return false; } +/* + * Funnel-lock acquisition for expedited grace periods. Returns a + * pointer to the root rcu_node structure, or NULL if some other + * task did the expedited grace period for us. + */ +static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) +{ + struct rcu_node *rnp0; + struct rcu_node *rnp1 = NULL; + + /* + * Each pass through the following loop works its way + * up the rcu_node tree, returning if others have done the + * work or otherwise falls through holding the root rnp's + * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure + * can be inexact, as it is just promoting locality and is not + * strictly needed for correctness. + */ + rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + for (; rnp0 != NULL; rnp0 = rnp0->parent) { + if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone1, s)) + return NULL; + mutex_lock(&rnp0->exp_funnel_mutex); + if (rnp1) + mutex_unlock(&rnp1->exp_funnel_mutex); + rnp1 = rnp0; + } + if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone2, s)) + return NULL; + return rnp1; +} + +static int synchronize_sched_expedited_cpu_stop(void *data) +{ + struct rcu_state *rsp = data; + + /* We are here: If we are last, do the wakeup. */ + if (atomic_dec_and_test(&rsp->expedited_need_qs)) + wake_up(&rsp->expedited_wq); + return 0; +} + /** * synchronize_sched_expedited - Brute-force RCU-sched grace period * @@ -3355,8 +3387,7 @@ void synchronize_sched_expedited(void) { int cpu; long s; - struct rcu_node *rnp0; - struct rcu_node *rnp1 = NULL; + struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; /* Take a snapshot of the sequence number. */ @@ -3370,26 +3401,9 @@ void synchronize_sched_expedited(void) } WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); - /* - * Each pass through the following loop works its way - * up the rcu_node tree, returning if others have done the - * work or otherwise falls through holding the root rnp's - * ->exp_funnel_mutex. The mapping from CPU to rcu_node structure - * can be inexact, as it is just promoting locality and is not - * strictly needed for correctness. - */ - rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; - for (; rnp0 != NULL; rnp0 = rnp0->parent) { - if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone1, s)) - return; - mutex_lock(&rnp0->exp_funnel_mutex); - if (rnp1) - mutex_unlock(&rnp1->exp_funnel_mutex); - rnp1 = rnp0; - } - rnp0 = rnp1; /* rcu_get_root(rsp), AKA root rcu_node structure. */ - if (sync_sched_exp_wd(rsp, rnp0, &rsp->expedited_workdone2, s)) - return; + rnp = exp_funnel_lock(rsp, s); + if (rnp == NULL) + return; /* Someone else did our work for us. */ rcu_exp_gp_seq_start(rsp); @@ -3415,7 +3429,7 @@ void synchronize_sched_expedited(void) !atomic_read(&rsp->expedited_need_qs)); rcu_exp_gp_seq_end(rsp); - mutex_unlock(&rnp0->exp_funnel_mutex); + mutex_unlock(&rnp->exp_funnel_mutex); smp_mb(); /* ensure subsequent action seen after grace period. */ put_online_cpus(); From 7fd0ddc5bf1ab5259c80a53a01984e13befd658b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 16:35:03 -0700 Subject: [PATCH 22/32] rcu: Fix synchronize_sched_expedited() type error for "s" The type of "s" has been "long" rather than the correct "unsigned long" for quite some time. This commit fixes this type error. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f79a1c646846..094ed8ff82b4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3386,7 +3386,7 @@ static int synchronize_sched_expedited_cpu_stop(void *data) void synchronize_sched_expedited(void) { int cpu; - long s; + unsigned long s; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; From 29fd930940193a9a035a75a3847457160d65559a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 19:03:16 -0700 Subject: [PATCH 23/32] rcu: Use funnel locking for synchronize_rcu_expedited()'s polling loop This commit gets rid of synchronize_rcu_expedited()'s mutex_trylock() polling loop in favor of the funnel-locking scheme that was abstracted from synchronize_sched_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 15 ++++++++------- kernel/rcu/tree_plugin.h | 36 ++++++++++-------------------------- 2 files changed, 18 insertions(+), 33 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 094ed8ff82b4..338ea61929bd 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3309,9 +3309,9 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) return rcu_seq_done(&rsp->expedited_sequence, s); } -/* Common code for synchronize_sched_expedited() work-done checking. */ -static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, - atomic_long_t *stat, unsigned long s) +/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ +static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, + atomic_long_t *stat, unsigned long s) { if (rcu_exp_gp_seq_done(rsp, s)) { if (rnp) @@ -3319,7 +3319,6 @@ static bool sync_sched_exp_wd(struct rcu_state *rsp, struct rcu_node *rnp, /* Ensure test happens before caller kfree(). */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(stat); - put_online_cpus(); return true; } return false; @@ -3345,14 +3344,14 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) */ rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; for (; rnp0 != NULL; rnp0 = rnp0->parent) { - if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone1, s)) + if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone1, s)) return NULL; mutex_lock(&rnp0->exp_funnel_mutex); if (rnp1) mutex_unlock(&rnp1->exp_funnel_mutex); rnp1 = rnp0; } - if (sync_sched_exp_wd(rsp, rnp1, &rsp->expedited_workdone2, s)) + if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone2, s)) return NULL; return rnp1; } @@ -3402,8 +3401,10 @@ void synchronize_sched_expedited(void) WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); rnp = exp_funnel_lock(rsp, s); - if (rnp == NULL) + if (rnp == NULL) { + put_online_cpus(); return; /* Someone else did our work for us. */ + } rcu_exp_gp_seq_start(rsp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 759883f51de7..f0d71449ec0c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -536,7 +536,6 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* * Return non-zero if there are any tasks in RCU read-side critical @@ -556,7 +555,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp) * for the current expedited grace period. Works only for preemptible * RCU -- other RCU implementation use other means. * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) { @@ -572,7 +571,7 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake) @@ -611,7 +610,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 * that work is needed here. * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static void sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) @@ -654,7 +653,7 @@ sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits, * enabling rcu_read_unlock_special() to do the bit-clearing. * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static void sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) @@ -702,29 +701,16 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) void synchronize_rcu_expedited(void) { struct rcu_node *rnp; + struct rcu_node *rnp_unlock; struct rcu_state *rsp = rcu_state_p; unsigned long s; - int trycount = 0; s = rcu_exp_gp_seq_snap(rsp); - /* - * Acquire lock, falling back to synchronize_rcu() if too many - * lock-acquisition failures. Of course, if someone does the - * expedited grace period for us, just leave. - */ - while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (rcu_exp_gp_seq_done(rsp, s)) - goto mb_ret; /* Others did our work for us. */ - if (trycount++ < 10) { - udelay(trycount * num_online_cpus()); - } else { - wait_rcu_gp(call_rcu); - return; - } - } - if (rcu_exp_gp_seq_done(rsp, s)) - goto unlock_mb_ret; /* Others did our work for us. */ + rnp_unlock = exp_funnel_lock(rsp, s); + if (rnp_unlock == NULL) + return; /* Someone else did our work for us. */ + rcu_exp_gp_seq_start(rsp); /* force all RCU readers onto ->blkd_tasks lists. */ @@ -748,9 +734,7 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); -unlock_mb_ret: - mutex_unlock(&sync_rcu_preempt_exp_mutex); -mb_ret: + mutex_unlock(&rnp_unlock->exp_funnel_mutex); smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); From 4f525a528b9e75571c6bedc6202beff1ced24c32 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 26 Jun 2015 11:20:00 -0700 Subject: [PATCH 24/32] rcu: Apply rcu_seq operations to _rcu_barrier() The rcu_seq operations were open-coded in _rcu_barrier(), so this commit replaces the open-coding with the shiny new rcu_seq operations. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 1 - kernel/rcu/tree.c | 72 ++++++++++---------------------------- kernel/rcu/tree.h | 2 +- kernel/rcu/tree_trace.c | 4 +-- 4 files changed, 22 insertions(+), 57 deletions(-) diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index c78e88ce5ea3..ef72c4aada56 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -661,7 +661,6 @@ TRACE_EVENT(rcu_torture_read, * Tracepoint for _rcu_barrier() execution. The string "s" describes * the _rcu_barrier phase: * "Begin": _rcu_barrier() started. - * "Check": _rcu_barrier() checking for piggybacking. * "EarlyExit": _rcu_barrier() piggybacked, thus early exit. * "Inc1": _rcu_barrier() piggyback check counter incremented. * "OfflineNoCB": _rcu_barrier() found callback on never-online CPU diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 338ea61929bd..44245ae4c1c2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3568,10 +3568,10 @@ static void rcu_barrier_callback(struct rcu_head *rhp) struct rcu_state *rsp = rdp->rsp; if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { - _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence); complete(&rsp->barrier_completion); } else { - _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence); } } @@ -3583,7 +3583,7 @@ static void rcu_barrier_func(void *type) struct rcu_state *rsp = type; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence); atomic_inc(&rsp->barrier_cpu_count); rsp->call(&rdp->barrier_head, rcu_barrier_callback); } @@ -3596,55 +3596,24 @@ static void _rcu_barrier(struct rcu_state *rsp) { int cpu; struct rcu_data *rdp; - unsigned long snap = READ_ONCE(rsp->n_barrier_done); - unsigned long snap_done; + unsigned long s = rcu_seq_snap(&rsp->barrier_sequence); - _rcu_barrier_trace(rsp, "Begin", -1, snap); + _rcu_barrier_trace(rsp, "Begin", -1, s); /* Take mutex to serialize concurrent rcu_barrier() requests. */ mutex_lock(&rsp->barrier_mutex); - /* - * Ensure that all prior references, including to ->n_barrier_done, - * are ordered before the _rcu_barrier() machinery. - */ - smp_mb(); /* See above block comment. */ - - /* - * Recheck ->n_barrier_done to see if others did our work for us. - * This means checking ->n_barrier_done for an even-to-odd-to-even - * transition. The "if" expression below therefore rounds the old - * value up to the next even number and adds two before comparing. - */ - snap_done = rsp->n_barrier_done; - _rcu_barrier_trace(rsp, "Check", -1, snap_done); - - /* - * If the value in snap is odd, we needed to wait for the current - * rcu_barrier() to complete, then wait for the next one, in other - * words, we need the value of snap_done to be three larger than - * the value of snap. On the other hand, if the value in snap is - * even, we only had to wait for the next rcu_barrier() to complete, - * in other words, we need the value of snap_done to be only two - * greater than the value of snap. The "(snap + 3) & ~0x1" computes - * this for us (thank you, Linus!). - */ - if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) { - _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); + /* Did someone else do our work for us? */ + if (rcu_seq_done(&rsp->barrier_sequence, s)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ mutex_unlock(&rsp->barrier_mutex); return; } - /* - * Increment ->n_barrier_done to avoid duplicate work. Use - * WRITE_ONCE() to prevent the compiler from speculating - * the increment to precede the early-exit check. - */ - WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1); - WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); - _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); - smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ + /* Mark the start of the barrier operation. */ + rcu_seq_start(&rsp->barrier_sequence); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence); /* * Initialize the count to one rather than to zero in order to @@ -3668,10 +3637,10 @@ static void _rcu_barrier(struct rcu_state *rsp) if (rcu_is_nocb_cpu(cpu)) { if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { _rcu_barrier_trace(rsp, "OfflineNoCB", cpu, - rsp->n_barrier_done); + rsp->barrier_sequence); } else { _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, - rsp->n_barrier_done); + rsp->barrier_sequence); smp_mb__before_atomic(); atomic_inc(&rsp->barrier_cpu_count); __call_rcu(&rdp->barrier_head, @@ -3679,11 +3648,11 @@ static void _rcu_barrier(struct rcu_state *rsp) } } else if (READ_ONCE(rdp->qlen)) { _rcu_barrier_trace(rsp, "OnlineQ", cpu, - rsp->n_barrier_done); + rsp->barrier_sequence); smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); } else { _rcu_barrier_trace(rsp, "OnlineNQ", cpu, - rsp->n_barrier_done); + rsp->barrier_sequence); } } put_online_cpus(); @@ -3695,16 +3664,13 @@ static void _rcu_barrier(struct rcu_state *rsp) if (atomic_dec_and_test(&rsp->barrier_cpu_count)) complete(&rsp->barrier_completion); - /* Increment ->n_barrier_done to prevent duplicate work. */ - smp_mb(); /* Keep increment after above mechanism. */ - WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1); - WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); - _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); - smp_mb(); /* Keep increment before caller's subsequent code. */ - /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ wait_for_completion(&rsp->barrier_completion); + /* Mark the end of the barrier operation. */ + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence); + rcu_seq_end(&rsp->barrier_sequence); + /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rsp->barrier_mutex); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4edc277d08eb..5c1042d9c310 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -486,7 +486,7 @@ struct rcu_state { struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ - unsigned long n_barrier_done; /* ++ at start and end of */ + unsigned long barrier_sequence; /* ++ at start and end of */ /* _rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 36c04b46d3b8..d9982a2ce305 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -81,9 +81,9 @@ static void r_stop(struct seq_file *m, void *v) static int show_rcubarrier(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "bcc: %d nbd: %lu\n", + seq_printf(m, "bcc: %d bseq: %lu\n", atomic_read(&rsp->barrier_cpu_count), - rsp->n_barrier_done); + rsp->barrier_sequence); return 0; } From 704dd435ac7eaefa89fcd82fd2876b8330e00ff3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Jun 2015 09:36:29 -0700 Subject: [PATCH 25/32] rcu: Consolidate last open-coded expedited memory barrier One of the requirements on RCU grace periods is that if there is a causal chain of operations that starts after one grace period and ends before another grace period, then the two grace periods must be serialized. There has been (and might still be) code that relies on this, for example, certain types of reference-counting code that does a call_rcu() within an RCU callback function. This requirement is why there is an smp_mb() at the end of both synchronize_sched_expedited() and synchronize_rcu_expedited(). However, this is the only smp_mb() in these functions, so it would be nicer to consolidate it into rcu_exp_gp_seq_end(). This commit does just that. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- kernel/rcu/tree_plugin.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 44245ae4c1c2..a905d3ba8673 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3299,6 +3299,7 @@ static void rcu_exp_gp_seq_start(struct rcu_state *rsp) static void rcu_exp_gp_seq_end(struct rcu_state *rsp) { rcu_seq_end(&rsp->expedited_sequence); + smp_mb(); /* Ensure that consecutive grace periods serialize. */ } static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) { @@ -3431,7 +3432,6 @@ void synchronize_sched_expedited(void) rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp->exp_funnel_mutex); - smp_mb(); /* ensure subsequent action seen after grace period. */ put_online_cpus(); } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index f0d71449ec0c..27b714601c6e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -735,7 +735,6 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp_unlock->exp_funnel_mutex); - smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); From 2cd6ffafec066118365f6d7eb7a42ea16c1f032c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 29 Jun 2015 17:06:39 -0700 Subject: [PATCH 26/32] rcu: Extend expedited funnel locking to rcu_data structure The strictly rcu_node based funnel-locking scheme works well in many cases, but systems with CONFIG_RCU_FANOUT_LEAF=64 won't necessarily get all that much concurrency. This commit therefore extends the funnel locking into the per-CPU rcu_data structure, providing concurrency equal to the number of CPUs. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 19 ++++++++++++++++--- kernel/rcu/tree.h | 4 +++- kernel/rcu/tree_trace.c | 3 ++- 3 files changed, 21 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a905d3ba8673..e45097fc39fa 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3312,11 +3312,14 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp, atomic_long_t *stat, unsigned long s) { if (rcu_exp_gp_seq_done(rsp, s)) { if (rnp) mutex_unlock(&rnp->exp_funnel_mutex); + else if (rdp) + mutex_unlock(&rdp->exp_funnel_mutex); /* Ensure test happens before caller kfree(). */ smp_mb__before_atomic(); /* ^^^ */ atomic_long_inc(stat); @@ -3332,6 +3335,7 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, */ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) { + struct rcu_data *rdp; struct rcu_node *rnp0; struct rcu_node *rnp1 = NULL; @@ -3343,16 +3347,24 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) * can be inexact, as it is just promoting locality and is not * strictly needed for correctness. */ - rnp0 = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); + if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s)) + return NULL; + mutex_lock(&rdp->exp_funnel_mutex); + rnp0 = rdp->mynode; for (; rnp0 != NULL; rnp0 = rnp0->parent) { - if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone1, s)) + if (sync_exp_work_done(rsp, rnp1, rdp, + &rsp->expedited_workdone2, s)) return NULL; mutex_lock(&rnp0->exp_funnel_mutex); if (rnp1) mutex_unlock(&rnp1->exp_funnel_mutex); + else + mutex_unlock(&rdp->exp_funnel_mutex); rnp1 = rnp0; } - if (sync_exp_work_done(rsp, rnp1, &rsp->expedited_workdone2, s)) + if (sync_exp_work_done(rsp, rnp1, rdp, + &rsp->expedited_workdone3, s)) return NULL; return rnp1; } @@ -3733,6 +3745,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); rdp->cpu = cpu; rdp->rsp = rsp; + mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 5c1042d9c310..efee84ce1e08 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -364,11 +364,12 @@ struct rcu_data { unsigned long n_rp_nocb_defer_wakeup; unsigned long n_rp_need_nothing; - /* 6) _rcu_barrier() and OOM callbacks. */ + /* 6) _rcu_barrier(), OOM callbacks, and expediting. */ struct rcu_head barrier_head; #ifdef CONFIG_RCU_FAST_NO_HZ struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + struct mutex exp_funnel_mutex; /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -494,6 +495,7 @@ struct rcu_state { atomic_long_t expedited_tryfail; /* # acquisition failures. */ atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ + atomic_long_t expedited_workdone3; /* # done by others #3. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ wait_queue_head_t expedited_wq; /* Wait for check-ins. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index d9982a2ce305..ec62369f1b02 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,11 +185,12 @@ static int show_rcuexp(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu n=%lu enq=%d sc=%lu\n", + seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", rsp->expedited_sequence, atomic_long_read(&rsp->expedited_tryfail), atomic_long_read(&rsp->expedited_workdone1), atomic_long_read(&rsp->expedited_workdone2), + atomic_long_read(&rsp->expedited_workdone3), atomic_long_read(&rsp->expedited_normal), atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); From cf3620a6c7798be3395163d3bb863ab378a6aa80 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Jun 2015 11:14:32 -0700 Subject: [PATCH 27/32] rcu: Add stall warnings to synchronize_sched_expedited() Although synchronize_sched_expedited() historically has no RCU CPU stall warnings, the availability of the rcupdate.rcu_expedited boot parameter invalidates the old assumption that synchronize_sched()'s stall warnings would suffice. This commit therefore adds RCU CPU stall warnings to synchronize_sched_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 58 +++++++++++++++++++++++++++++++++++++++++++---- kernel/rcu/tree.h | 1 + 2 files changed, 55 insertions(+), 4 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e45097fc39fa..4b6594c7db58 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3369,16 +3369,65 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) return rnp1; } +/* Invoked on each online non-idle CPU for expedited quiescent state. */ static int synchronize_sched_expedited_cpu_stop(void *data) { - struct rcu_state *rsp = data; + struct rcu_data *rdp = data; + struct rcu_state *rsp = rdp->rsp; /* We are here: If we are last, do the wakeup. */ + rdp->exp_done = true; if (atomic_dec_and_test(&rsp->expedited_need_qs)) wake_up(&rsp->expedited_wq); return 0; } +static void synchronize_sched_expedited_wait(struct rcu_state *rsp) +{ + int cpu; + unsigned long jiffies_stall; + unsigned long jiffies_start; + struct rcu_data *rdp; + int ret; + + jiffies_stall = rcu_jiffies_till_stall_check(); + jiffies_start = jiffies; + + for (;;) { + ret = wait_event_interruptible_timeout( + rsp->expedited_wq, + !atomic_read(&rsp->expedited_need_qs), + jiffies_stall); + if (ret > 0) + return; + if (ret < 0) { + /* Hit a signal, disable CPU stall warnings. */ + wait_event(rsp->expedited_wq, + !atomic_read(&rsp->expedited_need_qs)); + return; + } + pr_err("INFO: %s detected expedited stalls on CPUs: {", + rsp->name); + for_each_online_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + + if (rdp->exp_done) + continue; + pr_cont(" %d", cpu); + } + pr_cont(" } %lu jiffies s: %lu\n", + jiffies - jiffies_start, rsp->expedited_sequence); + for_each_online_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + + if (rdp->exp_done) + continue; + dump_cpu_task(cpu); + } + jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; + } +} + /** * synchronize_sched_expedited - Brute-force RCU-sched grace period * @@ -3428,19 +3477,20 @@ void synchronize_sched_expedited(void) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + rdp->exp_done = false; + /* Skip our CPU and any idle CPUs. */ if (raw_smp_processor_id() == cpu || !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) continue; atomic_inc(&rsp->expedited_need_qs); stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, - rsp, &rdp->exp_stop_work); + rdp, &rdp->exp_stop_work); } /* Remove extra count and, if necessary, wait for CPUs to stop. */ if (!atomic_dec_and_test(&rsp->expedited_need_qs)) - wait_event(rsp->expedited_wq, - !atomic_read(&rsp->expedited_need_qs)); + synchronize_sched_expedited_wait(rsp); rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp->exp_funnel_mutex); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index efee84ce1e08..b3ae8d3cffbc 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -370,6 +370,7 @@ struct rcu_data { struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ struct mutex exp_funnel_mutex; + bool exp_done; /* Expedited QS for this CPU? */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU From 99a930b0d2b018f31474d69137f311ce3581a4c2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Jun 2015 14:54:09 -0700 Subject: [PATCH 28/32] documentation: Describe new expedited stall warnings Signed-off-by: Paul E. McKenney --- Documentation/RCU/stallwarn.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 046f32637b95..efb9454875ab 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -163,6 +163,23 @@ message will be about three times the interval between the beginning of the stall and the first message. +Stall Warnings for Expedited Grace Periods + +If an expedited grace period detects a stall, it will place a message +like the following in dmesg: + + INFO: rcu_sched detected expedited stalls on CPUs: { 1 2 6 } 26009 jiffies s: 1043 + +This indicates that CPUs 1, 2, and 6 have failed to respond to a +reschedule IPI, that the expedited grace period has been going on for +26,009 jiffies, and that the expedited grace-period sequence counter is +1043. The fact that this last value is odd indicates that an expedited +grace period is in flight. + +It is entirely possible to see stall warnings from normal and from +expedited grace periods at about the same time from the same run. + + What Causes RCU CPU Stall Warnings? So your kernel printed an RCU CPU stall warning. The next question is From b9a425cfcb3c473b4ca2f3dfaeaf13848f4a7976 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Jul 2015 13:50:28 -0700 Subject: [PATCH 29/32] rcu: Pull out wait_event*() condition into helper function The condition for the wait_event_interruptible_timeout() that waits to do the next force-quiescent-state scan is a bit ornate: ((gf = READ_ONCE(rsp->gp_flags)) & RCU_GP_FLAG_FQS) || (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)) This commit therefore pulls this condition out into a helper function and comments its component conditions. Reported-by: Peter Zijlstra Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4b6594c7db58..b2803730ac13 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1903,6 +1903,26 @@ static int rcu_gp_init(struct rcu_state *rsp) return 1; } +/* + * Helper function for wait_event_interruptible_timeout() wakeup + * at force-quiescent-state time. + */ +static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + + /* Someone like call_rcu() requested a force-quiescent-state scan. */ + *gfp = READ_ONCE(rsp->gp_flags); + if (*gfp & RCU_GP_FLAG_FQS) + return true; + + /* The current grace period has completed. */ + if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)) + return true; + + return false; +} + /* * Do one round of quiescent-state forcing. */ @@ -2067,11 +2087,7 @@ static int __noreturn rcu_gp_kthread(void *arg) TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; ret = wait_event_interruptible_timeout(rsp->gp_wq, - ((gf = READ_ONCE(rsp->gp_flags)) & - RCU_GP_FLAG_FQS) || - (!READ_ONCE(rnp->qsmask) && - !rcu_preempt_blocked_readers_cgp(rnp)), - j); + rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DONE_FQS; /* Locking provides needed memory barriers. */ /* If grace period done, leave loop. */ From 32bb1c79996069ef9e4e53b428050749f9841c3f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 2 Jul 2015 12:27:31 -0700 Subject: [PATCH 30/32] rcu: Rename RCU_GP_DONE_FQS to RCU_GP_DOING_FQS The grace-period kthread sleeps waiting to do a force-quiescent-state scan, and when awakened sets rsp->gp_state to RCU_GP_DONE_FQS. However, this is confusing because the kthread has not done the force-quiescent-state, but is instead just starting to do it. This commit therefore renames RCU_GP_DONE_FQS to RCU_GP_DOING_FQS in order to make things a bit easier on reviewers. Reported-by: Peter Zijlstra Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- kernel/rcu/tree.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b2803730ac13..f66f6e7730bc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2088,7 +2088,7 @@ static int __noreturn rcu_gp_kthread(void *arg) rsp->gp_state = RCU_GP_WAIT_FQS; ret = wait_event_interruptible_timeout(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); - rsp->gp_state = RCU_GP_DONE_FQS; + rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ /* If grace period done, leave loop. */ if (!READ_ONCE(rnp->qsmask) && diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index b3ae8d3cffbc..543ba726396c 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -535,7 +535,7 @@ struct rcu_state { #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ #define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ #define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ -#define RCU_GP_DONE_FQS 4 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */ #define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ From cdacbe1f91264687af956e810278030f2ab5a3d0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 11 Jul 2015 16:24:45 -0700 Subject: [PATCH 31/32] rcu: Add fastpath bypassing funnel locking In the common case, there will be only one expedited grace period in the system at a given time, in which case it is not helpful to use funnel locking. This commit therefore adds a fastpath that bypasses funnel locking when the root ->exp_funnel_mutex is not held. Signed-off-by: Paul E. McKenney --- Documentation/RCU/trace.txt | 36 ++++++++++-------------------------- kernel/rcu/tree.c | 16 ++++++++++++++++ kernel/rcu/tree.h | 2 +- kernel/rcu/tree_trace.c | 4 ++-- 4 files changed, 29 insertions(+), 29 deletions(-) diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 08651da15448..97f17e9decda 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -237,42 +237,26 @@ o "ktl" is the low-order 16 bits (in hexadecimal) of the count of The output of "cat rcu/rcu_preempt/rcuexp" looks as follows: -s=21872 d=21872 w=0 tf=0 wd1=0 wd2=0 n=0 sc=21872 dt=21872 dl=0 dx=21872 +s=21872 wd0=0 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872 These fields are as follows: -o "s" is the starting sequence number. +o "s" is the sequence number, with an odd number indicating that + an expedited grace period is in progress. -o "d" is the ending sequence number. When the starting and ending - numbers differ, there is an expedited grace period in progress. - -o "w" is the number of times that the sequence numbers have been - in danger of wrapping. - -o "tf" is the number of times that contention has resulted in a - failure to begin an expedited grace period. - -o "wd1" and "wd2" are the number of times that an attempt to - start an expedited grace period found that someone else had - completed an expedited grace period that satisfies the +o "wd0", "wd1", "wd2", and "wd3" are the number of times that an + attempt to start an expedited grace period found that someone + else had completed an expedited grace period that satisfies the attempted request. "Our work is done." -o "n" is number of times that contention was so great that - the request was demoted from an expedited grace period to - a normal grace period. +o "n" is number of times that a concurrent CPU-hotplug operation + forced a fallback to a normal grace period. + +o "enq" is the number of quiescent states still outstanding. o "sc" is the number of times that the attempt to start a new expedited grace period succeeded. -o "dt" is the number of times that we attempted to update - the "d" counter. - -o "dl" is the number of times that we failed to update the "d" - counter. - -o "dx" is the number of times that we succeeded in updating - the "d" counter. - The output of "cat rcu/rcu_preempt/rcugp" looks as follows: diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f66f6e7730bc..3af0dee2d045 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3355,6 +3355,22 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) struct rcu_node *rnp0; struct rcu_node *rnp1 = NULL; + /* + * First try directly acquiring the root lock in order to reduce + * latency in the common case where expedited grace periods are + * rare. We check mutex_is_locked() to avoid pathological levels of + * memory contention on ->exp_funnel_mutex in the heavy-load case. + */ + rnp0 = rcu_get_root(rsp); + if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) { + if (mutex_trylock(&rnp0->exp_funnel_mutex)) { + if (sync_exp_work_done(rsp, rnp0, NULL, + &rsp->expedited_workdone0, s)) + return NULL; + return rnp0; + } + } + /* * Each pass through the following loop works its way * up the rcu_node tree, returning if others have done the diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 543ba726396c..80d974df0ea0 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -493,7 +493,7 @@ struct rcu_state { /* End of fields guarded by barrier_mutex. */ unsigned long expedited_sequence; /* Take a ticket. */ - atomic_long_t expedited_tryfail; /* # acquisition failures. */ + atomic_long_t expedited_workdone0; /* # done by others #0. */ atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ atomic_long_t expedited_workdone3; /* # done by others #3. */ diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index ec62369f1b02..6fc4c5ff3bb5 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -185,9 +185,9 @@ static int show_rcuexp(struct seq_file *m, void *v) { struct rcu_state *rsp = (struct rcu_state *)m->private; - seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", + seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", rsp->expedited_sequence, - atomic_long_read(&rsp->expedited_tryfail), + atomic_long_read(&rsp->expedited_workdone0), atomic_long_read(&rsp->expedited_workdone1), atomic_long_read(&rsp->expedited_workdone2), atomic_long_read(&rsp->expedited_workdone3), From af859beaaba4d57883b08f4acbcb3974bc1f975e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 19 Jul 2015 15:13:40 -0700 Subject: [PATCH 32/32] rcu: Silence lockdep false positive for expedited grace periods In a CONFIG_PREEMPT=y kernel, synchronize_rcu_expedited() acquires the ->exp_funnel_mutex in rcu_preempt_state, then invokes synchronize_sched_expedited, which acquires the ->exp_funnel_mutex in rcu_sched_state. There can be no deadlock because rcu_preempt_state ->exp_funnel_mutex acquisition always precedes that of rcu_sched_state. But lockdep does not know that, so it gives false-positive splats. This commit therefore associates a separate lock_class_key structure with the rcu_sched_state structure's ->exp_funnel_mutex, allowing lockdep to see the lock ordering, avoiding the false positives. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 12 ++++++++++-- kernel/rcu/tree.h | 8 ++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3af0dee2d045..439112e9d1b3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -71,6 +71,7 @@ MODULE_ALIAS("rcutree"); static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; +static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS]; /* * In order to export the rcu_state name to the tracing tools, it @@ -4049,6 +4050,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; static const char * const exp[] = RCU_EXP_NAME_INIT; + static const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4108,8 +4110,14 @@ static void __init rcu_init_one(struct rcu_state *rsp, INIT_LIST_HEAD(&rnp->blkd_tasks); rcu_init_one_nocb(rnp); mutex_init(&rnp->exp_funnel_mutex); - lockdep_set_class_and_name(&rnp->exp_funnel_mutex, - &rcu_exp_class[i], exp[i]); + if (rsp == &rcu_sched_state) + lockdep_set_class_and_name( + &rnp->exp_funnel_mutex, + &rcu_exp_sched_class[i], exp_sched[i]); + else + lockdep_set_class_and_name( + &rnp->exp_funnel_mutex, + &rcu_exp_class[i], exp[i]); } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 80d974df0ea0..0412030ca882 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -70,6 +70,8 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 @@ -79,6 +81,8 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 @@ -89,6 +93,8 @@ # 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" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 @@ -100,6 +106,8 @@ # 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" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */