linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: linuxppc-dev@lists.ozlabs.org
Cc: Jordan Niethe <jniethe5@gmail.com>,
	Laurent Dufour <ldufour@linux.ibm.com>,
	Nicholas Piggin <npiggin@gmail.com>
Subject: [PATCH v3 14/17] powerpc/qspinlock: reduce remote node steal spins
Date: Sat, 26 Nov 2022 19:59:29 +1000	[thread overview]
Message-ID: <20221126095932.1234527-15-npiggin@gmail.com> (raw)
In-Reply-To: <20221126095932.1234527-1-npiggin@gmail.com>

Allow for a reduction in the number of times a CPU from a different
node than the owner can attempt to steal the lock before queueing.
This could bias the transfer behaviour of the lock across the
machine and reduce NUMA crossings.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/lib/qspinlock.c | 43 +++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 70f924296b36..7f6b41627351 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -4,6 +4,7 @@
 #include <linux/export.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
+#include <linux/topology.h>
 #include <asm/qspinlock.h>
 #include <asm/paravirt.h>
 
@@ -24,6 +25,7 @@ struct qnodes {
 
 /* Tuning parameters */
 static int steal_spins __read_mostly = (1<<5);
+static int remote_steal_spins __read_mostly = (1<<2);
 #if _Q_SPIN_TRY_LOCK_STEAL == 1
 static const bool maybe_stealers = true;
 #else
@@ -44,6 +46,11 @@ static __always_inline int get_steal_spins(bool paravirt)
 	return steal_spins;
 }
 
+static __always_inline int get_remote_steal_spins(bool paravirt)
+{
+	return remote_steal_spins;
+}
+
 static __always_inline int get_head_spins(bool paravirt)
 {
 	return head_spins;
@@ -335,10 +342,24 @@ static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *
 	spin_cpu_relax();
 }
 
+static __always_inline bool steal_break(u32 val, int iters, bool paravirt)
+{
+	if (iters >= get_steal_spins(paravirt))
+		return true;
+
+	if (IS_ENABLED(CONFIG_NUMA) &&
+			(iters >= get_remote_steal_spins(paravirt))) {
+		int cpu = get_owner_cpu(val);
+		if (numa_node_id() != cpu_to_node(cpu))
+			return true;
+	}
+	return false;
+}
 
 static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool paravirt)
 {
 	int iters = 0;
+	u32 val;
 
 	if (!steal_spins)
 		return false;
@@ -347,8 +368,7 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 	spin_begin();
 
 	do {
-		u32 val = READ_ONCE(lock->val);
-
+		val = READ_ONCE(lock->val);
 		if (val & _Q_MUST_Q_VAL)
 			break;
 
@@ -362,7 +382,7 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 		}
 
 		iters++;
-	} while (iters < get_steal_spins(paravirt));
+	} while (!steal_break(val, iters, paravirt));
 
 	spin_end();
 
@@ -560,6 +580,22 @@ static int steal_spins_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_steal_spins, steal_spins_get, steal_spins_set, "%llu\n");
 
+static int remote_steal_spins_set(void *data, u64 val)
+{
+	remote_steal_spins = val;
+
+	return 0;
+}
+
+static int remote_steal_spins_get(void *data, u64 *val)
+{
+	*val = remote_steal_spins;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_remote_steal_spins, remote_steal_spins_get, remote_steal_spins_set, "%llu\n");
+
 static int head_spins_set(void *data, u64 val)
 {
 	head_spins = val;
@@ -659,6 +695,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_pv_prod_head, pv_prod_head_get, pv_prod_head_set, "
 static __init int spinlock_debugfs_init(void)
 {
 	debugfs_create_file("qspl_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_steal_spins);
+	debugfs_create_file("qspl_remote_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_remote_steal_spins);
 	debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
 	if (is_shared_processor()) {
 		debugfs_create_file("qspl_pv_yield_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_owner);
-- 
2.37.2


  parent reply	other threads:[~2022-11-26 10:13 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-26  9:59 [PATCH v3 00/17] powerpc: alternate queued spinlock implementation Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 01/17] powerpc/qspinlock: add mcs queueing for contended waiters Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 02/17] powerpc/qspinlock: use a half-word store to unlock to avoid larx/stcx Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 03/17] powerpc/qspinlock: convert atomic operations to assembly Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 04/17] powerpc/qspinlock: allow new waiters to steal the lock before queueing Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 05/17] powerpc/qspinlock: theft prevention to control latency Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 06/17] powerpc/qspinlock: store owner CPU in lock word Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 07/17] powerpc/qspinlock: paravirt yield to lock owner Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 08/17] powerpc/qspinlock: implement option to yield to previous node Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 09/17] powerpc/qspinlock: allow stealing when head of queue yields Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 10/17] powerpc/qspinlock: allow propagation of yield CPU down the queue Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 11/17] powerpc/qspinlock: add ability to prod new queue head CPU Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 12/17] powerpc/qspinlock: allow lock stealing in trylock and lock fastpath Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 13/17] powerpc/qspinlock: use spin_begin/end API Nicholas Piggin
2022-11-26  9:59 ` Nicholas Piggin [this message]
2022-11-26  9:59 ` [PATCH v3 15/17] powerpc/qspinlock: allow indefinite spinning on a preempted owner Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 16/17] powerpc/qspinlock: provide accounting and options for sleepy locks Nicholas Piggin
2022-11-26  9:59 ` [PATCH v3 17/17] powerpc/qspinlock: add compile-time tuning adjustments Nicholas Piggin
2022-11-28  3:11 ` [PATCH v3 real 01/17] powerpc/qspinlock: powerpc qspinlock implementation Nicholas Piggin
2022-12-08 12:39 ` (subset) [PATCH v3 00/17] powerpc: alternate queued spinlock implementation Michael Ellerman
2023-04-13 10:58 ` Shrikanth Hegde

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=20221126095932.1234527-15-npiggin@gmail.com \
    --to=npiggin@gmail.com \
    --cc=jniethe5@gmail.com \
    --cc=ldufour@linux.ibm.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).