From 95ebe80d99de3cb849c522a1f768e5e8befa0b7c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 20 Jan 2022 13:16:18 -0800 Subject: srcu: Fix s/is/if/ typo in srcu_node comment This commit fixed a typo in the srcu_node structure's ->srcu_have_cbs comment. While in the area, redo a couple of comments to take advantage of 100-character line lengths. Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..4025840ba9a3 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ -- cgit v1.2.3 From 994f706872e6ce080506bd795ecf783d5b617de6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 24 Jan 2022 09:46:57 -0800 Subject: srcu: Make Tree SRCU able to operate without snp_node array This commit makes Tree SRCU able to operate without an snp_node array, that is, when the srcu_data structures' ->mynode pointers are NULL. This can result in high contention on the srcu_struct structure's ->lock, but only when there are lots of call_srcu(), synchronize_srcu(), and synchronize_srcu_expedited() calls. Note that when there is no snp_node array, all SRCU callbacks use CPU 0's callback queue. This is optimal in the common case of low update-side load because it removes the need to search each CPU for the single callback that made the grace period happen. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 4025840ba9a3..8d1da136a93a 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -63,8 +63,9 @@ struct srcu_struct { struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -83,6 +84,17 @@ struct srcu_struct { struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 -- cgit v1.2.3 From 2ec303113d978931ef368886c4c6bc854493e8bf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jan 2022 16:13:52 -0800 Subject: srcu: Dynamically allocate srcu_node array This commit shrinks the srcu_struct structure by converting its ->node field from a fixed-size compile-time array to a pointer to a dynamically allocated array. In kernels built with large values of NR_CPUS that boot on systems with smaller numbers of CPUs, this can save significant memory. [ paulmck: Apply kernel test robot feedback. ] Reported-by: A cast of thousands Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8d1da136a93a..8501b6b45941 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -60,7 +60,7 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ -- cgit v1.2.3 From db8f1471c61336477e2bf74dcb00e67d650e6dea Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 26 Jan 2022 10:03:54 -0500 Subject: srcu: Use export for srcu_struct defined by DEFINE_STATIC_SRCU() If an srcu_struct structure defined by tree SRCU's DEFINE_STATIC_SRCU() is used by a module, sparse will give the following diagnostic: sparse: symbol '__srcu_struct_nodes_srcu' was not declared. Should it be static? The problem is that a within-module DEFINE_STATIC_SRCU() must define a non-static srcu_struct because it is exported by referencing it in a special '__section("___srcu_struct_ptrs")'. This reference is needed so that module load and unloading can invoke init_srcu_struct() and cleanup_srcu_struct(), respectively. Unfortunately, sparse is unaware of '__section("___srcu_struct_ptrs")', resulting in the above false-positive diagnostic. To avoid this false positive, this commit therefore creates a prototype of the srcu_struct with an "extern" keyword. Signed-off-by: Alexander Aring Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8501b6b45941..44e998643f48 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -131,6 +131,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -- cgit v1.2.3 From 46470cf85d2b61abd37c6f66c4dacc1bc510d10f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 13:20:49 -0800 Subject: srcu: Prevent cleanup_srcu_struct() from freeing non-dynamic ->sda When an srcu_struct structure is created (but not in a kernel module) by DEFINE_SRCU() and friends, the per-CPU srcu_data structure is statically allocated. In all other cases, that structure is obtained from alloc_percpu(), in which case cleanup_srcu_struct() must invoke free_percpu() on the resulting ->sda pointer in the srcu_struct pointer. Which it does. Except that it also invokes free_percpu() on the ->sda pointer referencing the statically allocated per-CPU srcu_data structures. Which free_percpu() is surprisingly OK with. This commit nevertheless stops cleanup_srcu_struct() from freeing statically allocated per-CPU srcu_data structures. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44e998643f48..44bd204498a1 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -73,6 +73,7 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; -- cgit v1.2.3 From 9f2e91d94c91558e3764fe4e01c5e6281a90f239 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 20:32:05 -0800 Subject: srcu: Add contention-triggered addition of srcu_node tree This commit instruments the acquisitions of the srcu_struct structure's ->lock, enabling the initiation of a transition from SRCU_SIZE_SMALL to SRCU_SIZE_BIG when sufficient contention is experienced. The instrumentation counts the number of trylock failures within the confines of a single jiffy. If that number exceeds the value specified by the srcutree.small_contention_lim kernel boot parameter (which defaults to 100), and if the value specified by the srcutree.convert_to_big kernel boot parameter has the 0x10 bit set (defaults to 0), then a transition will be automatically initiated. By default, there will never be any transitions, so that none of the srcu_struct structures ever gains an srcu_node array. The useful values for srcutree.convert_to_big are: 0x00: Never convert. 0x01: Always convert at init_srcu_struct() time. 0x02: Convert when rcutorture prints its first round of statistics. 0x03: Decide conversion approach at boot given system size. 0x10: Convert if contention is encountered. 0x12: Convert if contention is encountered or when rcutorture prints its first round of statistics, whichever comes first. The value 0x11 acts the same as 0x01 because the conversion happens before there is any chance of contention. [ paulmck: Apply "static" feedback from kernel test robot. ] Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44bd204498a1..1b9ff4ed37e4 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -72,6 +72,8 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ -- cgit v1.2.3 From 282d8998e9979c2186af7f7d22366f2fc3149838 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 Mar 2022 15:45:33 -0800 Subject: srcu: Prevent expedited GPs and blocking readers from consuming CPU If an SRCU reader blocks while a synchronize_srcu_expedited() waits for that same reader, then that grace period will spawn an endless series of workqueue handlers, consuming a full CPU. This quickly gets pointless because consuming more CPU isn't going to make that reader get done faster, especially if it is blocked waiting for an external event. This commit therefore spawns at most one pair of back-to-back workqueue handlers per expedited grace period phase, instead inserting increasing delays as that grace period phase grows older, but capped at 10 jiffies. In any case, if there have been at least 100 back-to-back workqueue handlers within a single jiffy, regardless of grace period or grace-period phase, then a one-jiffy delay is inserted. [ paulmck: Apply feedback from kernel test robot. ] Cc: Neeraj Upadhyay Reported-by: Song Liu Tested-by: kernel test robot Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/srcutree.h') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 1b9ff4ed37e4..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -71,9 +71,11 @@ struct srcu_struct { unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ @@ -83,6 +85,8 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; -- cgit v1.2.3