Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   cyndis@kapsi.fi
To:     thierry.reding@gmail.com, jonathanh@nvidia.com, robh+dt@kernel.org,
        krzysztof.kozlowski+dt@linaro.org, digetx@gmail.com
Cc:     dri-devel@lists.freedesktop.org, devicetree@vger.kernel.org,
        linux-tegra@vger.kernel.org, linux-kernel@vger.kernel.org,
        Mikko Perttunen <mperttunen@nvidia.com>
Subject: [PATCH v1 08/13] gpu: host1x: Program interrupt destinations on Tegra234
Date:   Mon, 16 May 2022 13:02:08 +0300
Message-Id: <20220516100213.1536571-9-cyndis@kapsi.fi>
In-Reply-To: <20220516100213.1536571-1-cyndis@kapsi.fi>
References: <20220516100213.1536571-1-cyndis@kapsi.fi>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Mikko Perttunen <mperttunen@nvidia.com>

On Tegra234, each Host1x VM has 8 interrupt lines. Each syncpoint
can be configured with which interrupt line should be used for
threshold interrupt, allowing for load balancing.

For now, to keep backwards compatibility, just set all syncpoints
to the first interrupt.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
---
 drivers/gpu/host1x/hw/intr_hw.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index f56375ee6e71..9acccdb139e6 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -76,6 +76,17 @@ static void intr_hw_init(struct host1x *host, u32 cpm)
 	/* update host clocks per usec */
 	host1x_sync_writel(host, cpm, HOST1X_SYNC_USEC_CLK);
 #endif
+#if HOST1X_HW >= 8
+	u32 id;
+
+	/*
+	 * Program threshold interrupt destination among 8 lines per VM,
+	 * per syncpoint. For now, just direct all to the first interrupt
+	 * line.
+	 */
+	for (id = 0; id < host->info->nb_pts; id++)
+		host1x_sync_writel(host, 0, HOST1X_SYNC_SYNCPT_INTR_DEST(id));
+#endif
 }
 
 static int
-- 
2.36.1