The current srcu_struct structure is on the order of 200 bytes in size
(depending on architecture and .config), which is much better than the
old-style 26K bytes, but still all too inconvenient when one is trying
to achieve good cache locality on a fastpath involving SRCU readers.
However, only a few fields in srcu_struct are used by SRCU readers.
The remaining fields could be offloaded to a new srcu_update
structure, thus shrinking the srcu_struct structure down to a few
tens of bytes. This commit begins this noble quest, a quest that is
complicated by open-coded initialization of the srcu_struct within the
srcu_notifier_head structure. This complication is addressed by updating
the srcu_notifier_head structure's open coding, given that there does
not appear to be a straightforward way of abstracting that initialization.
This commit moves only the ->node pointer to srcu_update. Later commits
will move additional fields.
[ paulmck: Fold in qiang1.zhang@intel.com's memory-leak fix. ]
Link: https://lore.kernel.org/all/20230320055751.4120251-1-qiang1.zhang@intel.com/
Suggested-by: Christoph Hellwig <hch@lst.de>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: "Michał Mirosław" <mirq-linux@rere.qmqm.pl>
Cc: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Tested-by: Sachin Sant <sachinp@linux.ibm.com>
Tested-by: "Zhang, Qiang1" <qiang1.zhang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
struct srcu_notifier_head {
struct mutex mutex;
+#ifdef CONFIG_TREE_SRCU
+ struct srcu_usage srcuu;
+#endif
struct srcu_struct srcu;
struct notifier_block __rcu *head;
};
{ \
.mutex = __MUTEX_INITIALIZER(name.mutex), \
.head = NULL, \
- .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \
+ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \
}
#define ATOMIC_NOTIFIER_HEAD(name) \
void srcu_drive_gp(struct work_struct *wp);
-#define __SRCU_STRUCT_INIT(name, __ignored) \
+#define __SRCU_STRUCT_INIT(name, __ignored, ___ignored) \
{ \
.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \
.srcu_cb_tail = &name.srcu_cb_head, \
* Tree SRCU, which needs some per-CPU data.
*/
#define DEFINE_SRCU(name) \
- struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
+ struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name)
#define DEFINE_STATIC_SRCU(name) \
- static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
+ static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name)
void synchronize_srcu(struct srcu_struct *ssp);
int grphi; /* Biggest CPU for node. */
};
+/*
+ * Per-SRCU-domain structure, update-side data linked from srcu_struct.
+ */
+struct srcu_usage {
+ struct srcu_node *node; /* Combining tree. */
+};
+
/*
* Per-SRCU-domain structure, similar in function to rcu_state.
*/
struct srcu_struct {
- 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. */
unsigned long reschedule_count;
struct delayed_work work;
struct lockdep_map dep_map;
+ struct srcu_usage *srcu_sup; /* Update-side data. */
};
/* Values for size state variable (->srcu_size_state). */
#define SRCU_STATE_SCAN1 1
#define SRCU_STATE_SCAN2 2
-#define __SRCU_STRUCT_INIT_COMMON(name) \
+#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.srcu_gp_seq_needed = -1UL, \
.work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \
+ .srcu_sup = &usage_name, \
__SRCU_DEP_MAP_INIT(name)
-#define __SRCU_STRUCT_INIT_MODULE(name) \
+#define __SRCU_STRUCT_INIT_MODULE(name, usage_name) \
{ \
- __SRCU_STRUCT_INIT_COMMON(name) \
+ __SRCU_STRUCT_INIT_COMMON(name, usage_name) \
}
-#define __SRCU_STRUCT_INIT(name, pcpu_name) \
+#define __SRCU_STRUCT_INIT(name, usage_name, pcpu_name) \
{ \
.sda = &pcpu_name, \
- __SRCU_STRUCT_INIT_COMMON(name) \
+ __SRCU_STRUCT_INIT_COMMON(name, usage_name) \
}
-
/*
* Define and initialize a srcu struct at build time.
* Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
*/
#ifdef MODULE
# define __DEFINE_SRCU(name, is_static) \
- is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name); \
+ static struct srcu_usage name##_srcu_usage; \
+ is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \
extern struct srcu_struct * const __srcu_struct_##name; \
struct srcu_struct * const __srcu_struct_##name \
__section("___srcu_struct_ptrs") = &name
#else
# define __DEFINE_SRCU(name, is_static) \
static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \
+ static struct srcu_usage name##_srcu_usage; \
is_static struct srcu_struct name = \
- __SRCU_STRUCT_INIT(name, name##_srcu_data)
+ __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data)
#endif
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
* specified state structure (for SRCU) or the only rcu_state structure
* (for RCU).
*/
-#define srcu_for_each_node_breadth_first(sp, rnp) \
+#define _rcu_for_each_node_breadth_first(sp, rnp) \
for ((rnp) = &(sp)->node[0]; \
(rnp) < &(sp)->node[rcu_num_nodes]; (rnp)++)
#define rcu_for_each_node_breadth_first(rnp) \
- srcu_for_each_node_breadth_first(&rcu_state, rnp)
+ _rcu_for_each_node_breadth_first(&rcu_state, rnp)
+#define srcu_for_each_node_breadth_first(ssp, rnp) \
+ _rcu_for_each_node_breadth_first(ssp->srcu_sup, rnp)
/*
* Scan the leaves of the rcu_node hierarchy for the rcu_state structure.
/* Initialize geometry if it has not already been initialized. */
rcu_init_geometry();
- ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), gfp_flags);
- if (!ssp->node)
+ ssp->srcu_sup->node = kcalloc(rcu_num_nodes, sizeof(*ssp->srcu_sup->node), gfp_flags);
+ if (!ssp->srcu_sup->node)
return false;
/* Work out the overall tree geometry. */
- ssp->level[0] = &ssp->node[0];
+ ssp->level[0] = &ssp->srcu_sup->node[0];
for (i = 1; i < rcu_num_lvls; i++)
ssp->level[i] = ssp->level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
snp->srcu_gp_seq_needed_exp = SRCU_SNP_INIT_SEQ;
snp->grplo = -1;
snp->grphi = -1;
- if (snp == &ssp->node[0]) {
+ if (snp == &ssp->srcu_sup->node[0]) {
/* Root node, special case. */
snp->srcu_parent = NULL;
continue;
*/
static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
{
+ if (!is_static)
+ ssp->srcu_sup = kzalloc(sizeof(*ssp->srcu_sup), GFP_KERNEL);
+ if (!ssp->srcu_sup)
+ return -ENOMEM;
ssp->srcu_size_state = SRCU_SIZE_SMALL;
- ssp->node = NULL;
+ ssp->srcu_sup->node = NULL;
mutex_init(&ssp->srcu_cb_mutex);
mutex_init(&ssp->srcu_gp_mutex);
ssp->srcu_idx = 0;
ssp->sda_is_static = is_static;
if (!is_static)
ssp->sda = alloc_percpu(struct srcu_data);
- if (!ssp->sda)
+ if (!ssp->sda) {
+ if (!is_static)
+ kfree(ssp->srcu_sup);
return -ENOMEM;
+ }
init_srcu_struct_data(ssp);
ssp->srcu_gp_seq_needed_exp = 0;
ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
if (!ssp->sda_is_static) {
free_percpu(ssp->sda);
ssp->sda = NULL;
+ kfree(ssp->srcu_sup);
return -ENOMEM;
}
} else {
rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed);
return; /* Caller forgot to stop doing call_srcu()? */
}
+ kfree(ssp->srcu_sup->node);
+ ssp->srcu_sup->node = NULL;
+ ssp->srcu_size_state = SRCU_SIZE_SMALL;
if (!ssp->sda_is_static) {
free_percpu(ssp->sda);
ssp->sda = NULL;
+ kfree(ssp->srcu_sup);
+ ssp->srcu_sup = NULL;
}
- kfree(ssp->node);
- ssp->node = NULL;
- ssp->srcu_size_state = SRCU_SIZE_SMALL;
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
projects / linux-block.git / commitdiff