LKML Archive on lore.kernel.org
 help / color / Atom feed
From: paulmck@kernel.org
To: rcu@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, kernel-team@fb.com,
	mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
	akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
	josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
	rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
	fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
	"Uladzislau Rezki (Sony)" <urezki@gmail.com>,
	"Paul E . McKenney" <paulmck@kernel.org>
Subject: [PATCH tip/core/rcu 09/17] rcu/tree: cache specified number of objects
Date: Wed, 24 Jun 2020 13:12:18 -0700
Message-ID: <20200624201226.21197-9-paulmck@kernel.org> (raw)
In-Reply-To: <20200624201200.GA28901@paulmck-ThinkPad-P72>

From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>

In order to reduce the dynamic need for pages in kfree_rcu(),
pre-allocate a configurable number of pages per CPU and link
them in a list. When kfree_rcu() reclaims objects, the object's
container page is cached into a list instead of being released
to the low-level page allocator.

Such an approach provides O(1) access to free pages while also
reducing the number of requests to the page allocator. It also
makes the kfree_rcu() code to have free pages available during
a low memory condition.

A read-only sysfs parameter (rcu_min_cached_objs) reflects the
minimum number of allowed cached pages per CPU.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  8 +++
 kernel/rcu/tree.c                               | 66 +++++++++++++++++++++++--
 2 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index fb95fad..befaa63 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4038,6 +4038,14 @@
 			latencies, which will choose a value aligned
 			with the appropriate hardware boundaries.
 
+	rcutree.rcu_min_cached_objs= [KNL]
+			Minimum number of objects which are cached and
+			maintained per one CPU. Object size is equal
+			to PAGE_SIZE. The cache allows to reduce the
+			pressure to page allocator, also it makes the
+			whole algorithm to behave better in low memory
+			condition.
+
 	rcutree.jiffies_till_first_fqs= [KNL]
 			Set delay from grace-period initialization to
 			first attempt to force quiescent states.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4fba1e9..f767a37 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -175,6 +175,15 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/*
+ * 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 = 2;
+module_param(rcu_min_cached_objs, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -2979,7 +2988,6 @@ struct kfree_rcu_cpu_work {
  * 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
  * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period
- * @bcached: Keeps at most one object for later reuse when build chain blocks
  * @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
@@ -2995,13 +3003,22 @@ struct kfree_rcu_cpu_work {
 struct kfree_rcu_cpu {
 	struct rcu_head *head;
 	struct kfree_rcu_bulk_data *bhead;
-	struct kfree_rcu_bulk_data *bcached;
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
 	raw_spinlock_t lock;
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
 	int count;
+
+	/*
+	 * 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.
+	 */
+	struct llist_head bkvcache;
+	int nr_bkv_objs;
 };
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
@@ -3038,6 +3055,31 @@ krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
 	local_irq_restore(flags);
 }
 
+static inline struct kfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
+{
+	if (!krcp->nr_bkv_objs)
+		return NULL;
+
+	krcp->nr_bkv_objs--;
+	return (struct kfree_rcu_bulk_data *)
+		llist_del_first(&krcp->bkvcache);
+}
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+	struct kfree_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);
+	krcp->nr_bkv_objs++;
+	return true;
+
+}
+
 /*
  * This function is invoked in workqueue context after a grace period.
  * It frees all the objects queued on ->bhead_free or ->head_free.
@@ -3073,7 +3115,12 @@ static void kfree_rcu_work(struct work_struct *work)
 		kfree_bulk(bhead->nr_records, bhead->records);
 		rcu_lock_release(&rcu_callback_map);
 
-		if (cmpxchg(&krcp->bcached, NULL, bhead))
+		krcp = krc_this_cpu_lock(&flags);
+		if (put_cached_bnode(krcp, bhead))
+			bhead = NULL;
+		krc_this_cpu_unlock(krcp, flags);
+
+		if (bhead)
 			free_page((unsigned long) bhead);
 
 		cond_resched_tasks_rcu_qs();
@@ -3206,7 +3253,7 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp,
 	/* Check if a new block is required. */
 	if (!krcp->bhead ||
 			krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) {
-		bnode = xchg(&krcp->bcached, NULL);
+		bnode = get_cached_bnode(krcp);
 		if (!bnode) {
 			WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE);
 
@@ -4259,12 +4306,23 @@ static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+		struct kfree_rcu_bulk_data *bnode;
 
 		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 (i = 0; i < rcu_min_cached_objs; i++) {
+			bnode = (struct kfree_rcu_bulk_data *)
+				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+
+			if (bnode)
+				put_cached_bnode(krcp, bnode);
+			else
+				pr_err("Failed to preallocate for %d CPU!\n", cpu);
+		}
+
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
-- 
2.9.5


  parent reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-24 20:12 [PATCH tip/core/rcu 0/17] kfree_rcu updates for v5.9 Paul E. McKenney
2020-06-24 20:12 ` [PATCH tip/core/rcu 01/17] rcu: Fix a kernel-doc warnings for "count" paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 02/17] rcu/tree: Keep kfree_rcu() awake during lock contention paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 03/17] rcu/tree: Skip entry into the page allocator for PREEMPT_RT paulmck
2020-06-30 16:45   ` Sebastian Andrzej Siewior
2020-06-30 18:35     ` Paul E. McKenney
2020-07-02 14:12       ` Sebastian Andrzej Siewior
2020-07-02 16:48         ` Paul E. McKenney
2020-07-02 20:19           ` Sebastian Andrzej Siewior
2020-07-06 21:06             ` Paul E. McKenney
2020-07-07 17:34               ` Uladzislau Rezki
2020-07-07 18:45                 ` Joel Fernandes
2020-07-08 18:48                   ` Uladzislau Rezki
2020-07-02 19:45         ` Uladzislau Rezki
2020-07-06 19:42           ` Joel Fernandes
2020-07-06 19:55             ` Uladzislau Rezki
2020-07-06 20:29               ` Joel Fernandes
2020-07-07  9:27                 ` Sebastian Andrzej Siewior
2020-07-15 13:38     ` Uladzislau Rezki
2020-07-15 14:16       ` Sebastian Andrzej Siewior
2020-07-15 14:20         ` Uladzislau Rezki
2020-06-24 20:12 ` [PATCH tip/core/rcu 04/17] rcu/tree: Repeat the monitor if any free channel is busy paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 05/17] rcu/tree: Make debug_objects logic independent of rcu_head paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 06/17] rcu/tree: Simplify KFREE_BULK_MAX_ENTR macro paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 07/17] rcu/tree: Move kfree_rcu_cpu locking/unlocking to separate functions paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 08/17] rcu/tree: Use static initializer for krc.lock paulmck
2020-06-24 20:12 ` paulmck [this message]
2020-06-24 20:12 ` [PATCH tip/core/rcu 10/17] rcu/tree: Maintain separate array for vmalloc ptrs paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 11/17] rcu/tiny: support vmalloc in tiny-RCU paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 12/17] rcu: Rename *_kfree_callback/*_kfree_rcu_offset/kfree_call_* paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 13/17] mm/list_lru.c: Rename kvfree_rcu() to local variant paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 14/17] rcu: Introduce 2 arg kvfree_rcu() interface paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 15/17] rcu: Support reclaim for head-less object paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 16/17] rcu: Introduce single argument kvfree_rcu() interface paulmck
2020-06-24 20:12 ` [PATCH tip/core/rcu 17/17] lib/test_vmalloc.c: Add test cases for kvfree_rcu() paulmck

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200624201226.21197-9-paulmck@kernel.org \
    --to=paulmck@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=dipankar@in.ibm.com \
    --cc=edumazet@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jiangshanlai@gmail.com \
    --cc=joel@joelfernandes.org \
    --cc=josh@joshtriplett.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=urezki@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git