All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jaewon Kim <jaewon02.kim@samsung.com>
To: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>,
	Andi Shyti <andi@etezian.org>, Mark Brown <broonie@kernel.org>,
	Alim Akhtar <alim.akhtar@samsung.com>
Cc: linux-spi@vger.kernel.org, linux-samsung-soc@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Chanho Park <chanho61.park@samsung.com>,
	Jaewon Kim <jaewon02.kim@samsung.com>
Subject: [PATCH v3 2/3] spi: s3c64xx: add sleep during transfer
Date: Tue,  2 May 2023 15:28:12 +0900	[thread overview]
Message-ID: <20230502062813.112434-3-jaewon02.kim@samsung.com> (raw)
In-Reply-To: <20230502062813.112434-1-jaewon02.kim@samsung.com>

In polling mode, the status register is continuously read to check data
transfer completion. It can cause excessive CPU usage.
To reduce this, we can calculate the transfer time and put the sleep during
transfer.

When test on ExynosAuto9 SADK board, throughput remained the same, but
100% CPU utilization decreased to 40%.

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
---
 drivers/spi/spi-s3c64xx.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 66ac94022a1b..2a8304678df9 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -561,11 +561,18 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
 	u32 cpy_len;
 	u8 *buf;
 	int ms;
+	unsigned long time_us;
 
-	/* millisecs to xfer 'len' bytes @ 'cur_speed' */
-	ms = xfer->len * 8 * 1000 / sdd->cur_speed;
+	/* microsecs to xfer 'len' bytes @ 'cur_speed' */
+	time_us = (xfer->len * 8 * 1000 * 1000) / sdd->cur_speed;
+	ms = (time_us / 1000);
 	ms += 10; /* some tolerance */
 
+	/* sleep during signal transfer time */
+	status = readl(regs + S3C64XX_SPI_STATUS);
+	if (RX_FIFO_LVL(status, sdd) < xfer->len)
+		usleep_range(time_us / 2, time_us);
+
 	val = msecs_to_loops(ms);
 	do {
 		status = readl(regs + S3C64XX_SPI_STATUS);
-- 
2.17.1


WARNING: multiple messages have this Message-ID (diff)
From: Jaewon Kim <jaewon02.kim@samsung.com>
To: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>,
	Andi Shyti <andi@etezian.org>, Mark Brown <broonie@kernel.org>,
	Alim Akhtar <alim.akhtar@samsung.com>
Cc: linux-spi@vger.kernel.org, linux-samsung-soc@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Chanho Park <chanho61.park@samsung.com>,
	Jaewon Kim <jaewon02.kim@samsung.com>
Subject: [PATCH v3 2/3] spi: s3c64xx: add sleep during transfer
Date: Tue,  2 May 2023 15:28:12 +0900	[thread overview]
Message-ID: <20230502062813.112434-3-jaewon02.kim@samsung.com> (raw)
In-Reply-To: <20230502062813.112434-1-jaewon02.kim@samsung.com>

In polling mode, the status register is continuously read to check data
transfer completion. It can cause excessive CPU usage.
To reduce this, we can calculate the transfer time and put the sleep during
transfer.

When test on ExynosAuto9 SADK board, throughput remained the same, but
100% CPU utilization decreased to 40%.

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
---
 drivers/spi/spi-s3c64xx.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 66ac94022a1b..2a8304678df9 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -561,11 +561,18 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
 	u32 cpy_len;
 	u8 *buf;
 	int ms;
+	unsigned long time_us;
 
-	/* millisecs to xfer 'len' bytes @ 'cur_speed' */
-	ms = xfer->len * 8 * 1000 / sdd->cur_speed;
+	/* microsecs to xfer 'len' bytes @ 'cur_speed' */
+	time_us = (xfer->len * 8 * 1000 * 1000) / sdd->cur_speed;
+	ms = (time_us / 1000);
 	ms += 10; /* some tolerance */
 
+	/* sleep during signal transfer time */
+	status = readl(regs + S3C64XX_SPI_STATUS);
+	if (RX_FIFO_LVL(status, sdd) < xfer->len)
+		usleep_range(time_us / 2, time_us);
+
 	val = msecs_to_loops(ms);
 	do {
 		status = readl(regs + S3C64XX_SPI_STATUS);
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2023-05-02  6:50 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20230502065025epcas2p16f5a02e6990d6f2b2257f001979ebcf9@epcas2p1.samsung.com>
2023-05-02  6:28 ` [PATCH v3 0/3] Improve polling mode of s3c64xx driver Jaewon Kim
2023-05-02  6:28   ` Jaewon Kim
     [not found]   ` <CGME20230502065025epcas2p4143c8ff3d44b7676ea8667c14618f2cd@epcas2p4.samsung.com>
2023-05-02  6:28     ` [PATCH v3 1/3] spi: s3c64xx: change polling mode to optional Jaewon Kim
2023-05-02  6:28       ` Jaewon Kim
2023-05-05  9:09       ` Krzysztof Kozlowski
2023-05-05  9:09         ` Krzysztof Kozlowski
     [not found]   ` <CGME20230502065025epcas2p11549db7400e6707c61bbb1cff1b22252@epcas2p1.samsung.com>
2023-05-02  6:28     ` Jaewon Kim [this message]
2023-05-02  6:28       ` [PATCH v3 2/3] spi: s3c64xx: add sleep during transfer Jaewon Kim
2023-05-05  9:09       ` Krzysztof Kozlowski
2023-05-05  9:09         ` Krzysztof Kozlowski
     [not found]   ` <CGME20230502065025epcas2p34507ffad60b32e091ff0efeced9bc12f@epcas2p3.samsung.com>
2023-05-02  6:28     ` [PATCH v3 3/3] spi: s3c64xx: support interrupt based pio mode Jaewon Kim
2023-05-02  6:28       ` Jaewon Kim
2023-05-05  9:47       ` Krzysztof Kozlowski
2023-05-05  9:47         ` Krzysztof Kozlowski
2023-05-08  1:42         ` Jaewon Kim
2023-05-08  1:42           ` Jaewon Kim
2023-05-09 13:03       ` Marek Szyprowski
2023-05-10  4:05         ` Jaewon Kim
2023-05-10  6:54           ` Marek Szyprowski
2023-05-08 13:27   ` [PATCH v3 0/3] Improve polling mode of s3c64xx driver Mark Brown

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=20230502062813.112434-3-jaewon02.kim@samsung.com \
    --to=jaewon02.kim@samsung.com \
    --cc=alim.akhtar@samsung.com \
    --cc=andi@etezian.org \
    --cc=broonie@kernel.org \
    --cc=chanho61.park@samsung.com \
    --cc=krzysztof.kozlowski@linaro.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-samsung-soc@vger.kernel.org \
    --cc=linux-spi@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.