summaryrefslogtreecommitdiff
path: root/kernel/rcu/tree.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/rcu/tree.c')
-rw-r--r--kernel/rcu/tree.c1048
1 files changed, 76 insertions, 972 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ff98233d4aa5..659f83e71048 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -149,7 +149,6 @@ static int rcu_scheduler_fully_active __read_mostly;
static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
unsigned long gps, unsigned long flags);
-static struct task_struct *rcu_boost_task(struct rcu_node *rnp);
static void invoke_rcu_core(void);
static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
@@ -186,26 +185,6 @@ static int rcu_unlock_delay;
module_param(rcu_unlock_delay, int, 0444);
#endif
-/*
- * This rcu parameter is runtime-read-only. It reflects
- * a minimum allowed number of objects which can be cached
- * per-CPU. Object size is equal to one page. This value
- * can be changed at boot time.
- */
-static int rcu_min_cached_objs = 5;
-module_param(rcu_min_cached_objs, int, 0444);
-
-// A page shrinker can ask for pages to be freed to make them
-// available for other parts of the system. This usually happens
-// under low memory conditions, and in that case we should also
-// defer page-cache filling for a short time period.
-//
-// The default value is 5 seconds, which is long enough to reduce
-// interference with the shrinker while it asks other systems to
-// drain their caches.
-static int rcu_delay_page_cache_fill_msec = 5000;
-module_param(rcu_delay_page_cache_fill_msec, int, 0444);
-
/* Retrieve RCU kthreads priority for rcutorture */
int rcu_get_gp_kthreads_prio(void)
{
@@ -559,6 +538,26 @@ void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq)
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
+/* Gather grace-period sequence numbers for rcutorture diagnostics. */
+unsigned long long rcutorture_gather_gp_seqs(void)
+{
+ return ((READ_ONCE(rcu_state.gp_seq) & 0xffffULL) << 40) |
+ ((READ_ONCE(rcu_state.expedited_sequence) & 0xffffffULL) << 16) |
+ (READ_ONCE(rcu_state.gp_seq_polled) & 0xffffULL);
+}
+EXPORT_SYMBOL_GPL(rcutorture_gather_gp_seqs);
+
+/* Format grace-period sequence numbers for rcutorture diagnostics. */
+void rcutorture_format_gp_seqs(unsigned long long seqs, char *cp, size_t len)
+{
+ unsigned int egp = (seqs >> 16) & 0xffffffULL;
+ unsigned int ggp = (seqs >> 40) & 0xffffULL;
+ unsigned int pgp = seqs & 0xffffULL;
+
+ snprintf(cp, len, "g%04x:e%06x:p%04x", ggp, egp, pgp);
+}
+EXPORT_SYMBOL_GPL(rcutorture_format_gp_seqs);
+
#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK))
/*
* An empty function that will trigger a reschedule on
@@ -1275,7 +1274,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
/* Handle the ends of any preceding grace periods first. */
if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
- unlikely(READ_ONCE(rdp->gpwrap))) {
+ unlikely(rdp->gpwrap)) {
if (!offloaded)
ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
rdp->core_needs_qs = false;
@@ -1289,7 +1288,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
/* Now handle the beginnings of any new-to-this-CPU grace periods. */
if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
- unlikely(READ_ONCE(rdp->gpwrap))) {
+ unlikely(rdp->gpwrap)) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
@@ -1304,7 +1303,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
- if (IS_ENABLED(CONFIG_PROVE_RCU) && READ_ONCE(rdp->gpwrap))
+ if (IS_ENABLED(CONFIG_PROVE_RCU) && rdp->gpwrap)
WRITE_ONCE(rdp->last_sched_clock, jiffies);
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
@@ -1633,12 +1632,10 @@ static void rcu_sr_normal_complete(struct llist_node *node)
{
struct rcu_synchronize *rs = container_of(
(struct rcu_head *) node, struct rcu_synchronize, head);
- unsigned long oldstate = (unsigned long) rs->head.func;
WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) &&
- !poll_state_synchronize_rcu(oldstate),
- "A full grace period is not passed yet: %lu",
- rcu_seq_diff(get_state_synchronize_rcu(), oldstate));
+ !poll_state_synchronize_rcu_full(&rs->oldstate),
+ "A full grace period is not passed yet!\n");
/* Finally. */
complete(&rs->completion);
@@ -1822,10 +1819,14 @@ static noinline_for_stack bool rcu_gp_init(void)
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time();
+ /*
+ * A new wait segment must be started before gp_seq advanced, so
+ * that previous gp waiters won't observe the new gp_seq.
+ */
+ start_new_poll = rcu_sr_normal_gp_init();
/* Record GP times before starting GP, hence rcu_seq_start(). */
rcu_seq_start(&rcu_state.gp_seq);
ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
- start_new_poll = rcu_sr_normal_gp_init();
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
rcu_poll_gp_seq_start(&rcu_state.gp_seq_polled_snap);
raw_spin_unlock_irq_rcu_node(rnp);
@@ -2952,13 +2953,8 @@ static int __init rcu_spawn_core_kthreads(void)
static void rcutree_enqueue(struct rcu_data *rdp, struct rcu_head *head, rcu_callback_t func)
{
rcu_segcblist_enqueue(&rdp->cblist, head);
- if (__is_kvfree_rcu_offset((unsigned long)func))
- trace_rcu_kvfree_callback(rcu_state.name, head,
- (unsigned long)func,
- rcu_segcblist_n_cbs(&rdp->cblist));
- else
- trace_rcu_callback(rcu_state.name, head,
- rcu_segcblist_n_cbs(&rdp->cblist));
+ trace_rcu_callback(rcu_state.name, head,
+ rcu_segcblist_n_cbs(&rdp->cblist));
trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
}
@@ -3083,9 +3079,12 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
}
head->func = func;
head->next = NULL;
- kasan_record_aux_stack_noalloc(head);
+ kasan_record_aux_stack(head);
+
local_irq_save(flags);
rdp = this_cpu_ptr(&rcu_data);
+ RCU_LOCKDEP_WARN(!rcu_rdp_cpu_online(rdp), "Callback enqueued on offline CPU!");
+
lazy = lazy_in && !rcu_async_should_hurry();
/* Add the callback to our list. */
@@ -3125,7 +3124,7 @@ module_param(enable_rcu_lazy, bool, 0444);
* critical sections have completed.
*
* Use this API instead of call_rcu() if you don't want the callback to be
- * invoked after very long periods of time, which can happen on systems without
+ * delayed for very long periods of time, which can happen on systems without
* memory pressure and on systems which are lightly loaded or mostly idle.
* This function will cause callbacks to be invoked sooner than later at the
* expense of extra power. Other than that, this function is identical to, and
@@ -3156,6 +3155,12 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
* might well execute concurrently with RCU read-side critical sections
* that started after call_rcu() was invoked.
*
+ * It is perfectly legal to repost an RCU callback, potentially with
+ * a different callback function, from within its callback function.
+ * The specified function will be invoked after another full grace period
+ * has elapsed. This use case is similar in form to the common practice
+ * of reposting a timer from within its own handler.
+ *
* RCU read-side critical sections are delimited by rcu_read_lock()
* and rcu_read_unlock(), and may be nested. In addition, but only in
* v5.0 and later, regions of code across which interrupts, preemption,
@@ -3184,6 +3189,13 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
*
* Implementation of these memory-ordering guarantees is described here:
* Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
+ *
+ * Specific to call_rcu() (as opposed to the other call_rcu*() functions),
+ * in kernels built with CONFIG_RCU_LAZY=y, call_rcu() might delay for many
+ * seconds before starting the grace period needed by the corresponding
+ * callback. This delay can significantly improve energy-efficiency
+ * on low-utilization battery-powered devices. To avoid this delay,
+ * in latency-sensitive kernel code, use call_rcu_hurry().
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
@@ -3191,812 +3203,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
}
EXPORT_SYMBOL_GPL(call_rcu);
-/* Maximum number of jiffies to wait before draining a batch. */
-#define KFREE_DRAIN_JIFFIES (5 * HZ)
-#define KFREE_N_BATCHES 2
-#define FREE_N_CHANNELS 2
-
-/**
- * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
- * @list: List node. All blocks are linked between each other
- * @gp_snap: Snapshot of RCU state for objects placed to this bulk
- * @nr_records: Number of active pointers in the array
- * @records: Array of the kvfree_rcu() pointers
- */
-struct kvfree_rcu_bulk_data {
- struct list_head list;
- struct rcu_gp_oldstate gp_snap;
- unsigned long nr_records;
- void *records[] __counted_by(nr_records);
-};
-
-/*
- * This macro defines how many entries the "records" array
- * will contain. It is based on the fact that the size of
- * kvfree_rcu_bulk_data structure becomes exactly one page.
- */
-#define KVFREE_BULK_MAX_ENTR \
- ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
-
-/**
- * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
- * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
- * @head_free: List of kfree_rcu() objects waiting for a grace period
- * @head_free_gp_snap: Grace-period snapshot to check for attempted premature frees.
- * @bulk_head_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
- * @krcp: Pointer to @kfree_rcu_cpu structure
- */
-
-struct kfree_rcu_cpu_work {
- struct rcu_work rcu_work;
- struct rcu_head *head_free;
- struct rcu_gp_oldstate head_free_gp_snap;
- struct list_head bulk_head_free[FREE_N_CHANNELS];
- struct kfree_rcu_cpu *krcp;
-};
-
-/**
- * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
- * @head: List of kfree_rcu() objects not yet waiting for a grace period
- * @head_gp_snap: Snapshot of RCU state for objects placed to "@head"
- * @bulk_head: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
- * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
- * @lock: Synchronize access to this structure
- * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
- * @initialized: The @rcu_work fields have been initialized
- * @head_count: Number of objects in rcu_head singular list
- * @bulk_count: Number of objects in bulk-list
- * @bkvcache:
- * A simple cache list that contains objects for reuse purpose.
- * In order to save some per-cpu space the list is singular.
- * Even though it is lockless an access has to be protected by the
- * per-cpu lock.
- * @page_cache_work: A work to refill the cache when it is empty
- * @backoff_page_cache_fill: Delay cache refills
- * @work_in_progress: Indicates that page_cache_work is running
- * @hrtimer: A hrtimer for scheduling a page_cache_work
- * @nr_bkv_objs: number of allocated objects at @bkvcache.
- *
- * This is a per-CPU structure. The reason that it is not included in
- * the rcu_data structure is to permit this code to be extracted from
- * the RCU files. Such extraction could allow further optimization of
- * the interactions with the slab allocators.
- */
-struct kfree_rcu_cpu {
- // Objects queued on a linked list
- // through their rcu_head structures.
- struct rcu_head *head;
- unsigned long head_gp_snap;
- atomic_t head_count;
-
- // Objects queued on a bulk-list.
- struct list_head bulk_head[FREE_N_CHANNELS];
- atomic_t bulk_count[FREE_N_CHANNELS];
-
- struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
- raw_spinlock_t lock;
- struct delayed_work monitor_work;
- bool initialized;
-
- struct delayed_work page_cache_work;
- atomic_t backoff_page_cache_fill;
- atomic_t work_in_progress;
- struct hrtimer hrtimer;
-
- struct llist_head bkvcache;
- int nr_bkv_objs;
-};
-
-static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
- .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
-};
-
-static __always_inline void
-debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
-{
-#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
- int i;
-
- for (i = 0; i < bhead->nr_records; i++)
- debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
-#endif
-}
-
-static inline struct kfree_rcu_cpu *
-krc_this_cpu_lock(unsigned long *flags)
-{
- struct kfree_rcu_cpu *krcp;
-
- local_irq_save(*flags); // For safely calling this_cpu_ptr().
- krcp = this_cpu_ptr(&krc);
- raw_spin_lock(&krcp->lock);
-
- return krcp;
-}
-
-static inline void
-krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
-{
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-}
-
-static inline struct kvfree_rcu_bulk_data *
-get_cached_bnode(struct kfree_rcu_cpu *krcp)
-{
- if (!krcp->nr_bkv_objs)
- return NULL;
-
- WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1);
- return (struct kvfree_rcu_bulk_data *)
- llist_del_first(&krcp->bkvcache);
-}
-
-static inline bool
-put_cached_bnode(struct kfree_rcu_cpu *krcp,
- struct kvfree_rcu_bulk_data *bnode)
-{
- // Check the limit.
- if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
- return false;
-
- llist_add((struct llist_node *) bnode, &krcp->bkvcache);
- WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1);
- return true;
-}
-
-static int
-drain_page_cache(struct kfree_rcu_cpu *krcp)
-{
- unsigned long flags;
- struct llist_node *page_list, *pos, *n;
- int freed = 0;
-
- if (!rcu_min_cached_objs)
- return 0;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- page_list = llist_del_all(&krcp->bkvcache);
- WRITE_ONCE(krcp->nr_bkv_objs, 0);
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-
- llist_for_each_safe(pos, n, page_list) {
- free_page((unsigned long)pos);
- freed++;
- }
-
- return freed;
-}
-
-static void
-kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp,
- struct kvfree_rcu_bulk_data *bnode, int idx)
-{
- unsigned long flags;
- int i;
-
- if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) {
- debug_rcu_bhead_unqueue(bnode);
- rcu_lock_acquire(&rcu_callback_map);
- if (idx == 0) { // kmalloc() / kfree().
- trace_rcu_invoke_kfree_bulk_callback(
- rcu_state.name, bnode->nr_records,
- bnode->records);
-
- kfree_bulk(bnode->nr_records, bnode->records);
- } else { // vmalloc() / vfree().
- for (i = 0; i < bnode->nr_records; i++) {
- trace_rcu_invoke_kvfree_callback(
- rcu_state.name, bnode->records[i], 0);
-
- vfree(bnode->records[i]);
- }
- }
- rcu_lock_release(&rcu_callback_map);
- }
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- if (put_cached_bnode(krcp, bnode))
- bnode = NULL;
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-
- if (bnode)
- free_page((unsigned long) bnode);
-
- cond_resched_tasks_rcu_qs();
-}
-
-static void
-kvfree_rcu_list(struct rcu_head *head)
-{
- struct rcu_head *next;
-
- for (; head; head = next) {
- void *ptr = (void *) head->func;
- unsigned long offset = (void *) head - ptr;
-
- next = head->next;
- debug_rcu_head_unqueue((struct rcu_head *)ptr);
- rcu_lock_acquire(&rcu_callback_map);
- trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
-
- if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
- kvfree(ptr);
-
- rcu_lock_release(&rcu_callback_map);
- cond_resched_tasks_rcu_qs();
- }
-}
-
-/*
- * This function is invoked in workqueue context after a grace period.
- * It frees all the objects queued on ->bulk_head_free or ->head_free.
- */
-static void kfree_rcu_work(struct work_struct *work)
-{
- unsigned long flags;
- struct kvfree_rcu_bulk_data *bnode, *n;
- struct list_head bulk_head[FREE_N_CHANNELS];
- struct rcu_head *head;
- struct kfree_rcu_cpu *krcp;
- struct kfree_rcu_cpu_work *krwp;
- struct rcu_gp_oldstate head_gp_snap;
- int i;
-
- krwp = container_of(to_rcu_work(work),
- struct kfree_rcu_cpu_work, rcu_work);
- krcp = krwp->krcp;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- // Channels 1 and 2.
- for (i = 0; i < FREE_N_CHANNELS; i++)
- list_replace_init(&krwp->bulk_head_free[i], &bulk_head[i]);
-
- // Channel 3.
- head = krwp->head_free;
- krwp->head_free = NULL;
- head_gp_snap = krwp->head_free_gp_snap;
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-
- // Handle the first two channels.
- for (i = 0; i < FREE_N_CHANNELS; i++) {
- // Start from the tail page, so a GP is likely passed for it.
- list_for_each_entry_safe(bnode, n, &bulk_head[i], list)
- kvfree_rcu_bulk(krcp, bnode, i);
- }
-
- /*
- * This is used when the "bulk" path can not be used for the
- * double-argument of kvfree_rcu(). This happens when the
- * page-cache is empty, which means that objects are instead
- * queued on a linked list through their rcu_head structures.
- * This list is named "Channel 3".
- */
- if (head && !WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&head_gp_snap)))
- kvfree_rcu_list(head);
-}
-
-static bool
-need_offload_krc(struct kfree_rcu_cpu *krcp)
-{
- int i;
-
- for (i = 0; i < FREE_N_CHANNELS; i++)
- if (!list_empty(&krcp->bulk_head[i]))
- return true;
-
- return !!READ_ONCE(krcp->head);
-}
-
-static bool
-need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp)
-{
- int i;
-
- for (i = 0; i < FREE_N_CHANNELS; i++)
- if (!list_empty(&krwp->bulk_head_free[i]))
- return true;
-
- return !!krwp->head_free;
-}
-
-static int krc_count(struct kfree_rcu_cpu *krcp)
-{
- int sum = atomic_read(&krcp->head_count);
- int i;
-
- for (i = 0; i < FREE_N_CHANNELS; i++)
- sum += atomic_read(&krcp->bulk_count[i]);
-
- return sum;
-}
-
-static void
-__schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
-{
- long delay, delay_left;
-
- delay = krc_count(krcp) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES;
- if (delayed_work_pending(&krcp->monitor_work)) {
- delay_left = krcp->monitor_work.timer.expires - jiffies;
- if (delay < delay_left)
- mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
- return;
- }
- queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
-}
-
-static void
-schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- __schedule_delayed_monitor_work(krcp);
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-}
-
-static void
-kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp)
-{
- struct list_head bulk_ready[FREE_N_CHANNELS];
- struct kvfree_rcu_bulk_data *bnode, *n;
- struct rcu_head *head_ready = NULL;
- unsigned long flags;
- int i;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- for (i = 0; i < FREE_N_CHANNELS; i++) {
- INIT_LIST_HEAD(&bulk_ready[i]);
-
- list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) {
- if (!poll_state_synchronize_rcu_full(&bnode->gp_snap))
- break;
-
- atomic_sub(bnode->nr_records, &krcp->bulk_count[i]);
- list_move(&bnode->list, &bulk_ready[i]);
- }
- }
-
- if (krcp->head && poll_state_synchronize_rcu(krcp->head_gp_snap)) {
- head_ready = krcp->head;
- atomic_set(&krcp->head_count, 0);
- WRITE_ONCE(krcp->head, NULL);
- }
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-
- for (i = 0; i < FREE_N_CHANNELS; i++) {
- list_for_each_entry_safe(bnode, n, &bulk_ready[i], list)
- kvfree_rcu_bulk(krcp, bnode, i);
- }
-
- if (head_ready)
- kvfree_rcu_list(head_ready);
-}
-
-/*
- * Return: %true if a work is queued, %false otherwise.
- */
-static bool
-kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp)
-{
- unsigned long flags;
- bool queued = false;
- int i, j;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
-
- // Attempt to start a new batch.
- for (i = 0; i < KFREE_N_BATCHES; i++) {
- struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
-
- // Try to detach bulk_head or head and attach it, only when
- // all channels are free. Any channel is not free means at krwp
- // there is on-going rcu work to handle krwp's free business.
- if (need_wait_for_krwp_work(krwp))
- continue;
-
- // kvfree_rcu_drain_ready() might handle this krcp, if so give up.
- if (need_offload_krc(krcp)) {
- // Channel 1 corresponds to the SLAB-pointer bulk path.
- // Channel 2 corresponds to vmalloc-pointer bulk path.
- for (j = 0; j < FREE_N_CHANNELS; j++) {
- if (list_empty(&krwp->bulk_head_free[j])) {
- atomic_set(&krcp->bulk_count[j], 0);
- list_replace_init(&krcp->bulk_head[j],
- &krwp->bulk_head_free[j]);
- }
- }
-
- // Channel 3 corresponds to both SLAB and vmalloc
- // objects queued on the linked list.
- if (!krwp->head_free) {
- krwp->head_free = krcp->head;
- get_state_synchronize_rcu_full(&krwp->head_free_gp_snap);
- atomic_set(&krcp->head_count, 0);
- WRITE_ONCE(krcp->head, NULL);
- }
-
- // One work is per one batch, so there are three
- // "free channels", the batch can handle. Break
- // the loop since it is done with this CPU thus
- // queuing an RCU work is _always_ success here.
- queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work);
- WARN_ON_ONCE(!queued);
- break;
- }
- }
-
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
- return queued;
-}
-
-/*
- * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
- */
-static void kfree_rcu_monitor(struct work_struct *work)
-{
- struct kfree_rcu_cpu *krcp = container_of(work,
- struct kfree_rcu_cpu, monitor_work.work);
-
- // Drain ready for reclaim.
- kvfree_rcu_drain_ready(krcp);
-
- // Queue a batch for a rest.
- kvfree_rcu_queue_batch(krcp);
-
- // If there is nothing to detach, it means that our job is
- // successfully done here. In case of having at least one
- // of the channels that is still busy we should rearm the
- // work to repeat an attempt. Because previous batches are
- // still in progress.
- if (need_offload_krc(krcp))
- schedule_delayed_monitor_work(krcp);
-}
-
-static enum hrtimer_restart
-schedule_page_work_fn(struct hrtimer *t)
-{
- struct kfree_rcu_cpu *krcp =
- container_of(t, struct kfree_rcu_cpu, hrtimer);
-
- queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0);
- return HRTIMER_NORESTART;
-}
-
-static void fill_page_cache_func(struct work_struct *work)
-{
- struct kvfree_rcu_bulk_data *bnode;
- struct kfree_rcu_cpu *krcp =
- container_of(work, struct kfree_rcu_cpu,
- page_cache_work.work);
- unsigned long flags;
- int nr_pages;
- bool pushed;
- int i;
-
- nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
- 1 : rcu_min_cached_objs;
-
- for (i = READ_ONCE(krcp->nr_bkv_objs); i < nr_pages; i++) {
- bnode = (struct kvfree_rcu_bulk_data *)
- __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
-
- if (!bnode)
- break;
-
- raw_spin_lock_irqsave(&krcp->lock, flags);
- pushed = put_cached_bnode(krcp, bnode);
- raw_spin_unlock_irqrestore(&krcp->lock, flags);
-
- if (!pushed) {
- free_page((unsigned long) bnode);
- break;
- }
- }
-
- atomic_set(&krcp->work_in_progress, 0);
- atomic_set(&krcp->backoff_page_cache_fill, 0);
-}
-
-static void
-run_page_cache_worker(struct kfree_rcu_cpu *krcp)
-{
- // If cache disabled, bail out.
- if (!rcu_min_cached_objs)
- return;
-
- if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
- !atomic_xchg(&krcp->work_in_progress, 1)) {
- if (atomic_read(&krcp->backoff_page_cache_fill)) {
- queue_delayed_work(system_unbound_wq,
- &krcp->page_cache_work,
- msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
- } else {
- hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- krcp->hrtimer.function = schedule_page_work_fn;
- hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
- }
- }
-}
-
-// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
-// state specified by flags. If can_alloc is true, the caller must
-// be schedulable and not be holding any locks or mutexes that might be
-// acquired by the memory allocator or anything that it might invoke.
-// Returns true if ptr was successfully recorded, else the caller must
-// use a fallback.
-static inline bool
-add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
- unsigned long *flags, void *ptr, bool can_alloc)
-{
- struct kvfree_rcu_bulk_data *bnode;
- int idx;
-
- *krcp = krc_this_cpu_lock(flags);
- if (unlikely(!(*krcp)->initialized))
- return false;
-
- idx = !!is_vmalloc_addr(ptr);
- bnode = list_first_entry_or_null(&(*krcp)->bulk_head[idx],
- struct kvfree_rcu_bulk_data, list);
-
- /* Check if a new block is required. */
- if (!bnode || bnode->nr_records == KVFREE_BULK_MAX_ENTR) {
- bnode = get_cached_bnode(*krcp);
- if (!bnode && can_alloc) {
- krc_this_cpu_unlock(*krcp, *flags);
-
- // __GFP_NORETRY - allows a light-weight direct reclaim
- // what is OK from minimizing of fallback hitting point of
- // view. Apart of that it forbids any OOM invoking what is
- // also beneficial since we are about to release memory soon.
- //
- // __GFP_NOMEMALLOC - prevents from consuming of all the
- // memory reserves. Please note we have a fallback path.
- //
- // __GFP_NOWARN - it is supposed that an allocation can
- // be failed under low memory or high memory pressure
- // scenarios.
- bnode = (struct kvfree_rcu_bulk_data *)
- __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
- raw_spin_lock_irqsave(&(*krcp)->lock, *flags);
- }
-
- if (!bnode)
- return false;
-
- // Initialize the new block and attach it.
- bnode->nr_records = 0;
- list_add(&bnode->list, &(*krcp)->bulk_head[idx]);
- }
-
- // Finally insert and update the GP for this page.
- bnode->nr_records++;
- bnode->records[bnode->nr_records - 1] = ptr;
- get_state_synchronize_rcu_full(&bnode->gp_snap);
- atomic_inc(&(*krcp)->bulk_count[idx]);
-
- return true;
-}
-
-/*
- * Queue a request for lazy invocation of the appropriate free routine
- * after a grace period. Please note that three paths are maintained,
- * two for the common case using arrays of pointers and a third one that
- * is used only when the main paths cannot be used, for example, due to
- * memory pressure.
- *
- * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
- * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
- * be free'd in workqueue context. This allows us to: batch requests together to
- * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
- */
-void kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
- unsigned long flags;
- struct kfree_rcu_cpu *krcp;
- bool success;
-
- /*
- * Please note there is a limitation for the head-less
- * variant, that is why there is a clear rule for such
- * objects: it can be used from might_sleep() context
- * only. For other places please embed an rcu_head to
- * your data.
- */
- if (!head)
- might_sleep();
-
- // Queue the object but don't yet schedule the batch.
- if (debug_rcu_head_queue(ptr)) {
- // Probable double kfree_rcu(), just leak.
- WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
- __func__, head);
-
- // Mark as success and leave.
- return;
- }
-
- kasan_record_aux_stack_noalloc(ptr);
- success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
- if (!success) {
- run_page_cache_worker(krcp);
-
- if (head == NULL)
- // Inline if kvfree_rcu(one_arg) call.
- goto unlock_return;
-
- head->func = ptr;
- head->next = krcp->head;
- WRITE_ONCE(krcp->head, head);
- atomic_inc(&krcp->head_count);
-
- // Take a snapshot for this krcp.
- krcp->head_gp_snap = get_state_synchronize_rcu();
- success = true;
- }
-
- /*
- * The kvfree_rcu() caller considers the pointer freed at this point
- * and likely removes any references to it. Since the actual slab
- * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore
- * this object (no scanning or false positives reporting).
- */
- kmemleak_ignore(ptr);
-
- // Set timer to drain after KFREE_DRAIN_JIFFIES.
- if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
- __schedule_delayed_monitor_work(krcp);
-
-unlock_return:
- krc_this_cpu_unlock(krcp, flags);
-
- /*
- * Inline kvfree() after synchronize_rcu(). We can do
- * it from might_sleep() context only, so the current
- * CPU can pass the QS state.
- */
- if (!success) {
- debug_rcu_head_unqueue((struct rcu_head *) ptr);
- synchronize_rcu();
- kvfree(ptr);
- }
-}
-EXPORT_SYMBOL_GPL(kvfree_call_rcu);
-
-/**
- * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete.
- *
- * Note that a single argument of kvfree_rcu() call has a slow path that
- * triggers synchronize_rcu() following by freeing a pointer. It is done
- * before the return from the function. Therefore for any single-argument
- * call that will result in a kfree() to a cache that is to be destroyed
- * during module exit, it is developer's responsibility to ensure that all
- * such calls have returned before the call to kmem_cache_destroy().
- */
-void kvfree_rcu_barrier(void)
-{
- struct kfree_rcu_cpu_work *krwp;
- struct kfree_rcu_cpu *krcp;
- bool queued;
- int i, cpu;
-
- /*
- * Firstly we detach objects and queue them over an RCU-batch
- * for all CPUs. Finally queued works are flushed for each CPU.
- *
- * Please note. If there are outstanding batches for a particular
- * CPU, those have to be finished first following by queuing a new.
- */
- for_each_possible_cpu(cpu) {
- krcp = per_cpu_ptr(&krc, cpu);
-
- /*
- * Check if this CPU has any objects which have been queued for a
- * new GP completion. If not(means nothing to detach), we are done
- * with it. If any batch is pending/running for this "krcp", below
- * per-cpu flush_rcu_work() waits its completion(see last step).
- */
- if (!need_offload_krc(krcp))
- continue;
-
- while (1) {
- /*
- * If we are not able to queue a new RCU work it means:
- * - batches for this CPU are still in flight which should
- * be flushed first and then repeat;
- * - no objects to detach, because of concurrency.
- */
- queued = kvfree_rcu_queue_batch(krcp);
-
- /*
- * Bail out, if there is no need to offload this "krcp"
- * anymore. As noted earlier it can run concurrently.
- */
- if (queued || !need_offload_krc(krcp))
- break;
-
- /* There are ongoing batches. */
- for (i = 0; i < KFREE_N_BATCHES; i++) {
- krwp = &(krcp->krw_arr[i]);
- flush_rcu_work(&krwp->rcu_work);
- }
- }
- }
-
- /*
- * Now we guarantee that all objects are flushed.
- */
- for_each_possible_cpu(cpu) {
- krcp = per_cpu_ptr(&krc, cpu);
-
- /*
- * A monitor work can drain ready to reclaim objects
- * directly. Wait its completion if running or pending.
- */
- cancel_delayed_work_sync(&krcp->monitor_work);
-
- for (i = 0; i < KFREE_N_BATCHES; i++) {
- krwp = &(krcp->krw_arr[i]);
- flush_rcu_work(&krwp->rcu_work);
- }
- }
-}
-EXPORT_SYMBOL_GPL(kvfree_rcu_barrier);
-
-static unsigned long
-kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
-{
- int cpu;
- unsigned long count = 0;
-
- /* Snapshot count of all CPUs */
- for_each_possible_cpu(cpu) {
- struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-
- count += krc_count(krcp);
- count += READ_ONCE(krcp->nr_bkv_objs);
- atomic_set(&krcp->backoff_page_cache_fill, 1);
- }
-
- return count == 0 ? SHRINK_EMPTY : count;
-}
-
-static unsigned long
-kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
-{
- int cpu, freed = 0;
-
- for_each_possible_cpu(cpu) {
- int count;
- struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-
- count = krc_count(krcp);
- count += drain_page_cache(krcp);
- kfree_rcu_monitor(&krcp->monitor_work.work);
-
- sc->nr_to_scan -= count;
- freed += count;
-
- if (sc->nr_to_scan <= 0)
- break;
- }
-
- return freed == 0 ? SHRINK_STOP : freed;
-}
-
-void __init kfree_rcu_scheduler_running(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-
- if (need_offload_krc(krcp))
- schedule_delayed_monitor_work(krcp);
- }
-}
-
/*
* During early boot, any blocking grace-period wait automatically
* implies a grace period.
@@ -4038,7 +3244,7 @@ static void synchronize_rcu_normal(void)
* snapshot before adding a request.
*/
if (IS_ENABLED(CONFIG_PROVE_RCU))
- rs.head.func = (void *) get_state_synchronize_rcu();
+ get_state_synchronize_rcu_full(&rs.oldstate);
rcu_sr_normal_add_req(&rs);
@@ -4181,14 +3387,17 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
*/
void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
{
- struct rcu_node *rnp = rcu_get_root();
-
/*
* Any prior manipulation of RCU-protected data must happen
* before the loads from ->gp_seq and ->expedited_sequence.
*/
smp_mb(); /* ^^^ */
- rgosp->rgos_norm = rcu_seq_snap(&rnp->gp_seq);
+
+ // Yes, rcu_state.gp_seq, not rnp_root->gp_seq, the latter's use
+ // in poll_state_synchronize_rcu_full() notwithstanding. Use of
+ // the latter here would result in too-short grace periods due to
+ // interactions with newly onlined CPUs.
+ rgosp->rgos_norm = rcu_seq_snap(&rcu_state.gp_seq);
rgosp->rgos_exp = rcu_seq_snap(&rcu_state.expedited_sequence);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu_full);
@@ -4895,6 +4104,22 @@ rcu_boot_init_percpu_data(int cpu)
rcu_boot_init_nocb_percpu_data(rdp);
}
+static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp)
+{
+ cpumask_var_t affinity;
+ int cpu;
+
+ if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
+ return;
+
+ for_each_leaf_node_possible_cpu(rnp, cpu)
+ cpumask_set_cpu(cpu, affinity);
+
+ kthread_affine_preferred(t, affinity);
+
+ free_cpumask_var(affinity);
+}
+
struct kthread_worker *rcu_exp_gp_kworker;
static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
@@ -4917,16 +4142,9 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-}
-
-static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp)
-{
- struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker);
- if (!kworker)
- return NULL;
-
- return kworker->task;
+ rcu_thread_affine_rnp(kworker->task, rnp);
+ wake_up_process(kworker->task);
}
static void __init rcu_start_exp_gp_kworker(void)
@@ -4934,7 +4152,7 @@ static void __init rcu_start_exp_gp_kworker(void)
const char *name = "rcu_exp_gp_kthread_worker";
struct sched_param param = { .sched_priority = kthread_prio };
- rcu_exp_gp_kworker = kthread_create_worker(0, name);
+ rcu_exp_gp_kworker = kthread_run_worker(0, name);
if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
pr_err("Failed to create %s!\n", name);
rcu_exp_gp_kworker = NULL;
@@ -5012,67 +4230,6 @@ int rcutree_prepare_cpu(unsigned int cpu)
}
/*
- * Update kthreads affinity during CPU-hotplug changes.
- *
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question. The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU. If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- *
- * Any future concurrent calls are serialized via ->kthread_mutex.
- */
-static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu)
-{
- cpumask_var_t cm;
- unsigned long mask;
- struct rcu_data *rdp;
- struct rcu_node *rnp;
- struct task_struct *task_boost, *task_exp;
-
- rdp = per_cpu_ptr(&rcu_data, cpu);
- rnp = rdp->mynode;
-
- task_boost = rcu_boost_task(rnp);
- task_exp = rcu_exp_par_gp_task(rnp);
-
- /*
- * If CPU is the boot one, those tasks are created later from early
- * initcall since kthreadd must be created first.
- */
- if (!task_boost && !task_exp)
- return;
-
- if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
- return;
-
- mutex_lock(&rnp->kthread_mutex);
- mask = rcu_rnp_online_cpus(rnp);
- for_each_leaf_node_possible_cpu(rnp, cpu)
- if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
- cpu != outgoingcpu)
- cpumask_set_cpu(cpu, cm);
- cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
- if (cpumask_empty(cm)) {
- cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
- if (outgoingcpu >= 0)
- cpumask_clear_cpu(outgoingcpu, cm);
- }
-
- if (task_exp)
- set_cpus_allowed_ptr(task_exp, cm);
-
- if (task_boost)
- set_cpus_allowed_ptr(task_boost, cm);
-
- mutex_unlock(&rnp->kthread_mutex);
-
- free_cpumask_var(cm);
-}
-
-/*
* Has the specified (known valid) CPU ever been fully online?
*/
bool rcu_cpu_beenfullyonline(int cpu)
@@ -5100,7 +4257,6 @@ int rcutree_online_cpu(unsigned int cpu)
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
- rcutree_affinity_setting(cpu, -1);
// Stop-machine done, so allow nohz_full to disable tick.
tick_dep_clear(TICK_DEP_BIT_RCU);
@@ -5317,8 +4473,6 @@ int rcutree_offline_cpu(unsigned int cpu)
rnp->ffmask &= ~rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- rcutree_affinity_setting(cpu, cpu);
-
// nohz_full CPUs need the tick for stop-machine to work quickly
tick_dep_set(TICK_DEP_BIT_RCU);
return 0;
@@ -5648,62 +4802,12 @@ static void __init rcu_dump_rcu_node_tree(void)
struct workqueue_struct *rcu_gp_wq;
-static void __init kfree_rcu_batch_init(void)
-{
- int cpu;
- int i, j;
- struct shrinker *kfree_rcu_shrinker;
-
- /* Clamp it to [0:100] seconds interval. */
- if (rcu_delay_page_cache_fill_msec < 0 ||
- rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {
-
- rcu_delay_page_cache_fill_msec =
- clamp(rcu_delay_page_cache_fill_msec, 0,
- (int) (100 * MSEC_PER_SEC));
-
- pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n",
- rcu_delay_page_cache_fill_msec);
- }
-
- for_each_possible_cpu(cpu) {
- struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-
- for (i = 0; i < KFREE_N_BATCHES; i++) {
- INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
- krcp->krw_arr[i].krcp = krcp;
-
- for (j = 0; j < FREE_N_CHANNELS; j++)
- INIT_LIST_HEAD(&krcp->krw_arr[i].bulk_head_free[j]);
- }
-
- for (i = 0; i < FREE_N_CHANNELS; i++)
- INIT_LIST_HEAD(&krcp->bulk_head[i]);
-
- INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
- INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
- krcp->initialized = true;
- }
-
- kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree");
- if (!kfree_rcu_shrinker) {
- pr_err("Failed to allocate kfree_rcu() shrinker!\n");
- return;
- }
-
- kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count;
- kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan;
-
- shrinker_register(kfree_rcu_shrinker);
-}
-
void __init rcu_init(void)
{
int cpu = smp_processor_id();
rcu_early_boot_tests();
- kfree_rcu_batch_init();
rcu_bootup_announce();
sanitize_kthread_prio();
rcu_init_geometry();