Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   David Lechner <david@lechnology.com>
To:     linux-spi@vger.kernel.org, linux-iio@vger.kernel.org
Cc:     David Lechner <david@lechnology.com>,
        Jonathan Cameron <jic23@kernel.org>,
        Hartmut Knaack <knaack.h@gmx.de>,
        Lars-Peter Clausen <lars@metafoo.de>,
        Peter Meerwald-Stadler <pmeerw@pmeerw.net>,
        Mark Brown <broonie@kernel.org>,
        Geert Uytterhoeven <geert@linux-m68k.org>,
        linux-kernel@vger.kernel.org
Subject: [PATCH 3/3] iio: adc: ti-ads7950: use SPI_CS_WORD to reduce CPU usage
Date:   Tue, 18 Sep 2018 12:08:50 -0500
Message-Id: <20180918170850.2749-4-david@lechnology.com>
In-Reply-To: <20180918170850.2749-1-david@lechnology.com>
References: <20180918170850.2749-1-david@lechnology.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This changes how the SPI message for the triggered buffer is setup in
the TI ADS7950 A/DC driver. By using the SPI_CS_WORD flag, we can read
multiple samples in a single SPI transfer. If the SPI controller
supports DMA transfers, we can see a significant reduction in CPU usage.

For example, on an ARM9 system running at 456MHz reading just 4 channels
at 100Hz: before this change, top shows the CPU usage of the IRQ thread
of this driver to be ~7.7%. After this change, the CPU usage drops to
~3.8%.

The use of big-endian for the raw data was cargo culted from another
driver when this driver was originally written. It used an SPI word size
of 8 bits and big-endian byte ordering to effectively emulate 16 bit
words.

Now, in order to inject a CS toggle between each word, we need to use
the correct word size, otherwise we would get a CS toggle half way
through each word 16-bit. The SPI subsystem uses CPU byte ordering for
multi-byte words. So, the data we get back from the SPI is going to be
CPU endian now no matter what. Converting that to big endian will just
add overhead on little endian systems so we opt to change the raw data
format from big endian to CPU endian.

There is a small risk that this could break some lazy userspace programs
that use the raw data without checking the data format. We can address
this if/when it actually comes up.

Signed-off-by: David Lechner <david@lechnology.com>
---
 drivers/iio/adc/ti-ads7950.c | 53 +++++++++++++++++++++---------------
 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c
index a5bd5944bc66..0ad63592cc3c 100644
--- a/drivers/iio/adc/ti-ads7950.c
+++ b/drivers/iio/adc/ti-ads7950.c
@@ -51,7 +51,7 @@
 
 struct ti_ads7950_state {
 	struct spi_device	*spi;
-	struct spi_transfer	ring_xfer[TI_ADS7950_MAX_CHAN + 2];
+	struct spi_transfer	ring_xfer;
 	struct spi_transfer	scan_single_xfer[3];
 	struct spi_message	ring_msg;
 	struct spi_message	scan_single_msg;
@@ -65,11 +65,11 @@ struct ti_ads7950_state {
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache lines.
 	 */
-	__be16	rx_buf[TI_ADS7950_MAX_CHAN + TI_ADS7950_TIMESTAMP_SIZE]
+	u16 rx_buf[TI_ADS7950_MAX_CHAN + 2 + TI_ADS7950_TIMESTAMP_SIZE]
 							____cacheline_aligned;
-	__be16	tx_buf[TI_ADS7950_MAX_CHAN];
-	__be16			single_tx;
-	__be16			single_rx;
+	u16 tx_buf[TI_ADS7950_MAX_CHAN + 2];
+	u16 single_tx;
+	u16 single_rx;
 
 };
 
@@ -108,7 +108,7 @@ enum ti_ads7950_id {
 		.realbits = bits,				\
 		.storagebits = 16,				\
 		.shift = 12 - (bits),				\
-		.endianness = IIO_BE,				\
+		.endianness = IIO_CPU,				\
 	},							\
 }
 
@@ -249,23 +249,14 @@ static int ti_ads7950_update_scan_mode(struct iio_dev *indio_dev,
 	len = 0;
 	for_each_set_bit(i, active_scan_mask, indio_dev->num_channels) {
 		cmd = TI_ADS7950_CR_WRITE | TI_ADS7950_CR_CHAN(i) | st->settings;
-		st->tx_buf[len++] = cpu_to_be16(cmd);
+		st->tx_buf[len++] = cmd;
 	}
 
 	/* Data for the 1st channel is not returned until the 3rd transfer */
-	len += 2;
-	for (i = 0; i < len; i++) {
-		if ((i + 2) < len)
-			st->ring_xfer[i].tx_buf = &st->tx_buf[i];
-		if (i >= 2)
-			st->ring_xfer[i].rx_buf = &st->rx_buf[i - 2];
-		st->ring_xfer[i].len = 2;
-		st->ring_xfer[i].cs_change = 1;
-	}
-	/* make sure last transfer's cs_change is not set */
-	st->ring_xfer[len - 1].cs_change = 0;
+	st->tx_buf[len++] = 0;
+	st->tx_buf[len++] = 0;
 
-	spi_message_init_with_transfers(&st->ring_msg, st->ring_xfer, len);
+	st->ring_xfer.len = len * 2;
 
 	return 0;
 }
@@ -281,7 +272,7 @@ static irqreturn_t ti_ads7950_trigger_handler(int irq, void *p)
 	if (ret < 0)
 		goto out;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, st->rx_buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &st->rx_buf[2],
 					   iio_get_time_ns(indio_dev));
 
 out:
@@ -298,13 +289,13 @@ static int ti_ads7950_scan_direct(struct iio_dev *indio_dev, unsigned int ch)
 	mutex_lock(&indio_dev->mlock);
 
 	cmd = TI_ADS7950_CR_WRITE | TI_ADS7950_CR_CHAN(ch) | st->settings;
-	st->single_tx = cpu_to_be16(cmd);
+	st->single_tx = cmd;
 
 	ret = spi_sync(st->spi, &st->scan_single_msg);
 	if (ret)
 		goto out;
 
-	ret = be16_to_cpu(st->single_rx);
+	ret = st->single_rx;
 
 out:
 	mutex_unlock(&indio_dev->mlock);
@@ -378,6 +369,14 @@ static int ti_ads7950_probe(struct spi_device *spi)
 	const struct ti_ads7950_chip_info *info;
 	int ret;
 
+	spi->bits_per_word = 16;
+	spi->mode |= SPI_CS_WORD;
+	ret = spi_setup(spi);
+	if (ret < 0) {
+		dev_err(&spi->dev, "Error in spi setup\n");
+		return ret;
+	}
+
 	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st));
 	if (!indio_dev)
 		return -ENOMEM;
@@ -398,6 +397,16 @@ static int ti_ads7950_probe(struct spi_device *spi)
 	indio_dev->num_channels = info->num_channels;
 	indio_dev->info = &ti_ads7950_info;
 
+	/* build spi ring message */
+	spi_message_init(&st->ring_msg);
+
+	st->ring_xfer.tx_buf = &st->tx_buf[0];
+	st->ring_xfer.rx_buf = &st->rx_buf[0];
+	/* len will be set later */
+	st->ring_xfer.cs_change = true;
+
+	spi_message_add_tail(&st->ring_xfer, &st->ring_msg);
+
 	/*
 	 * Setup default message. The sample is read at the end of the first
 	 * transfer, then it takes one full cycle to convert the sample and one
-- 
2.17.1