Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Frederic Weisbecker <frederic@kernel.org>
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     LKML <linux-kernel@vger.kernel.org>,
        Frederic Weisbecker <frederic@kernel.org>,
        Anna-Maria Gleixner <anna-maria@linutronix.de>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>
Subject: [RFC PATCH 04/10] timer: Optimize _next_timer_interrupt() level iteration
Date:   Wed,  1 Jul 2020 03:10:24 +0200
Message-Id: <20200701011030.14324-5-frederic@kernel.org>
In-Reply-To: <20200701011030.14324-1-frederic@kernel.org>
References: <20200701011030.14324-1-frederic@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

If a level has a timer that expires before we reach the next level,
there is no need to iterate further.

The next level is reached when the 3 lower bits of the current level are
cleared. If the next event happens before/during that, the next levels
won't give us an earlier expiration.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Anna-Maria Gleixner <anna-maria@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
---
 kernel/time/timer.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index b4838d63a016..4aa74aafdd33 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1515,6 +1515,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 	clk = base->clk;
 	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
 		int pos = next_pending_bucket(base, offset, clk & LVL_MASK);
+		unsigned long lvl_clk = clk & LVL_CLK_MASK;
 
 		if (pos >= 0) {
 			unsigned long tmp = clk + (unsigned long) pos;
@@ -1522,6 +1523,13 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 			tmp <<= LVL_SHIFT(lvl);
 			if (time_before(tmp, next))
 				next = tmp;
+
+			/*
+			 * If the next expiration happens before we reach
+			 * the next level, no need to check further.
+			 */
+			if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK))
+				break;
 		}
 		/*
 		 * Clock for the next level. If the current level clock lower
@@ -1559,7 +1567,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 		 * So the simple check whether the lower bits of the current
 		 * level are 0 or not is sufficient for all cases.
 		 */
-		adj = clk & LVL_CLK_MASK ? 1 : 0;
+		adj = lvl_clk ? 1 : 0;
 		clk >>= LVL_CLK_SHIFT;
 		clk += adj;
 	}
-- 
2.26.2