Commit Graph

39 Commits

Author SHA1 Message Date
Prahlad V d06a3507fe spi: spi-ti-qspi: reinit of completion variable
completion variable should be reinitialized before reusing.

Signed-off-by: Prahlad V <prahlad.eee@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2016-11-15 18:37:01 +00:00
Vignesh R 5720ec0a6d spi: spi-ti-qspi: Add DMA support for QSPI mmap read
Use mem-to-mem DMA to read from flash when reading in mmap mode. This
gives improved read performance and reduces CPU load.

With this patch the raw-read throughput is ~16MB/s on DRA74 EVM. And CPU
load is <20%. UBIFS read throughput ~13 MB/s.

Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2016-08-17 12:24:28 +01:00
Mark Brown 1cb2e84873 Merge remote-tracking branches 'spi/topic/spidev', 'spi/topic/sunxi', 'spi/topic/ti-qspi', 'spi/topic/topcliff-pch' and 'spi/topic/txx9' into spi-next 2016-07-24 22:08:27 +01:00
Colin Ian King 77cca63acc spi: ti-qspi: spelling mistake: "trasnfers" -> "transfers"
trivial fix to spelling mistake in dev_dbg message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2016-06-26 12:29:04 +01:00
Jean-Jacques Hiblot 3ac066e222 spi: spi-ti-qspi: Suspend the queue before removing the device
Before disabling the pm_runtime, we must ensure that there is no transfer
in progress nor will a new one be started. Otherwise the message pump will
fail and in the end, the process requesting the transfer will be stuck.
This behavior has been observed when transferring data from a SPI flash
with dd while removing the module on a DRA7x-evm.

Signed-off-by: Jean-Jacques Hiblot <jjhiblot@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2016-05-31 18:51:58 +01:00
Ben Hutchings 1ff7760ff6 spi: spi-ti-qspi: Handle truncated frames properly
We clamp frame_len_words to a maximum of 4096, but do not actually
limit the number of words written or read through the DATA registers
or the length added to spi_message::actual_length.  This results in
silent data corruption for commands longer than this maximum.

Recalculate the length of each transfer, taking frame_len_words into
account.  Use this length in qspi_{read,write}_msg(), and to increment
spi_message::actual_length.

Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
2016-04-13 08:12:41 +01:00
Ben Hutchings ea1b60fb08 spi: spi-ti-qspi: Fix FLEN and WLEN settings if bits_per_word is overridden
Each transfer can specify 8, 16 or 32 bits per word independently of
the default for the device being addressed.  However, currently we
calculate the number of words in the frame assuming that the word size
is the device default.

If multiple transfers in the same message have differing
bits_per_word, we bitwise-or the different values in the WLEN register
field.

Fix both of these.  Also rename 'frame_length' to 'frame_len_words' to
make clear that it's not a byte count like spi_message::frame_length.

Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
2016-04-13 08:11:17 +01:00
Vignesh R 4dea6c9b0b spi: spi-ti-qspi: add mmap mode read support
ti-qspi controller provides mmap port to read data from SPI flashes.
mmap port is enabled in QSPI_SPI_SWITCH_REG. ctrl module register may
also need to be accessed for some SoCs. The QSPI_SPI_SETUP_REGx needs to
be populated with flash specific information like read opcode, read
mode(quad, dual, normal), address width and dummy bytes. Once,
controller is in mmap mode, the whole flash memory is available as a
memory region at SoC specific address. This region can be accessed using
normal memcpy() (or mem-to-mem dma copy). The ti-qspi controller hardware
will internally communicate with SPI flash over SPI bus and get the
requested data.

Implement spi_flash_read() callback to support mmap read over SPI
flash devices. With this, the read throughput increases from ~100kB/s to
~2.5 MB/s.

Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2016-02-09 19:34:43 +00:00
Mark Brown c70efb8515 Merge remote-tracking branches 'spi/topic/s3c64xx', 'spi/topic/ti-qspi' and 'spi/topic/txx9' into spi-next 2015-11-04 11:02:16 +00:00
Felipe Balbi e6b5140b70 spi: ti-qspi: improve ->remove() callback
there's no need to call pm_runtime_get_sync()
followed by pm_runtime_put(). We should, instead,
just call pm_runtime_put_sync() and pm_runtime_disable().

Signed-off-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-10-30 10:24:57 +09:00
Vignesh R 57c2ecd9bf spi: spi-ti-qspi: switch to polling mode for better r/w performance
Currently word completion interrupt is fired for transfer of every
word(8bit to 128bit in size). This adds a lot of overhead, and decreases
r/w throughput. It hardly takes 3us(@48MHz) for 128bit r/w to complete,
hence its better to poll on word complete bit to be set in
QSPI_SPI_STATUS_REG instead of using interrupts.
This increases the throughput by 30% in both read and write case.

So, switch to polling mode instead of interrupts to determine completion
of word transfer.

Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-10-16 19:08:06 +01:00
Vignesh R bc27a53928 spi: ti-qspi: Fix data corruption seen on r/w stress test
Writing invalid command to QSPI_SPI_CMD_REG will terminate current
transfer and de-assert the chip select. This has to be done before
calling spi_finalize_current_message(). Because
spi_finalize_current_message() will mark the end of current message
transfer and schedule the next transfer. If the chipselect is not
de-asserted before calling spi_finalize_current_message() then the next
transfer will overlap with the previous transfer leading to data
corruption.
__spi_pump_message() can be called either from kthread worker context or
directly from the calling process's context. It is possible that these
two calls can race against each other. But race is serialized by
checking whether master->cur_msg == NULL (pointer to msg being handled
by transfer_one() at present). The master->cur_msg is set to NULL when
spi_finalize_current_message() is called on that message, which means
calling spi_finalize_current_message() allows __spi_sync() to pump next
message in calling process context.
Now if spi-ti-qspi calls spi_finalize_current_message() before we
terminate transfer at hardware side, if __spi_pump_message() is called
from process context then the successive transactions can overlap.

Fix this by moving writing invalid command to QSPI_SPI_CMD_REG to
before calling spi_finalize_current_message() call.

Cc: stable@vger.kernel.org # v3.12+
Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-10-12 17:58:48 +01:00
Vignesh R f682c4ffd2 spi: ti-qspi: use 128 bit transfer mode where possible
TI QSPI has four 32 bit data regsiters which can be used to transfer 16
bytes of data at once. The register group QSPI_SPI_DATA_REG_3,
QSPI_SPI_DATA_REG_2, QSPI_SPI_DATA_REG_1 and QSPI_SPI_DATA_REG is
treated as a single 128-bit word for shifting data in and out. The bit
at QSPI_SPI_DATA_REG_3[31] position is the first bit to be shifted out
in case of 128 bit transfer mode. Therefore the first byte to be written
to flash should be at QSPI_SPI_DATA_REG_3[31-25] position.
Instead of writing 1 byte at a time when interacting with spi-nor flash,
make use of all the four registers so that 16 bytes can be transferred
in one go. This reduces number of register writes and Word Complete
interrupts for a given transfer message size, thereby increasing the
write performance.

Without this patch the raw flash write speed is ~100KB/s, with this
patch the write speed increases to ~400 kB/s on DRA74 EVM.

Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-08-20 10:56:42 -07:00
Mugunthan V N 0061104764 drivers: spi: ti-qspi: wait for busy bit clear before data write/read
Data corruption is seen while reading/writing large data from/to qspi
device because the data register is over written or read before data
is ready which is denoted by busy bit in status register. SO adding
a busy bit check before writing/reading data to/from qspi device.

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-02-21 18:29:09 +09:00
Nicholas Mc Guire 060556a9bd spi: ti-qspi: cleanup wait_for_completion return handling
return type of wait_for_completion_timeout is unsigned long not int, this
patch uses the return value of wait_for_completion_timeout in the condition
directly rather than assigning it to an incorrect type variable.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
2015-02-05 18:04:03 +00:00
Wolfram Sang 14ac00e033 spi: drop owner assignment from platform_drivers
A platform_driver does not need to set an owner, it will be populated by the
driver core.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
2014-10-20 16:21:36 +02:00
Mark Brown b1ad487c42 Merge remote-tracking branches 'spi/topic/sunxi', 'spi/topic/tegra114', 'spi/topic/ti-qspi', 'spi/topic/ti-ssp', 'spi/topic/topcliff-pch', 'spi/topic/txx9', 'spi/topic/xcomm' and 'spi/topic/xfer' into spi-next 2014-03-30 00:51:41 +00:00
Mark Brown 9dee279b40 Merge remote-tracking branches 'spi/topic/bus-num', 'spi/topic/cleanup', 'spi/topic/clps711x', 'spi/topic/coldfire', 'spi/topic/completion' and 'spi/topic/davinci' into spi-next 2014-03-30 00:51:03 +00:00
Sourav Poddar 9304f51e5f spi/ti-qspi: Fix return from mmap path
mmap resource requirement is only for memory mapped operations.
If the user does not populate mmap resource, dont call return,
instead we go on for normal spi mode operations.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-03-10 11:10:19 +00:00
Axel Lin 78e39523b8 spi: Remove explictly set bus_num and num_chipselect to default setting
The purpose of commit 1e8a52e18c
"spi: By default setup spi_masters with 1 chipselect and dynamics bus number"
is to avoid setting default value for bus_num and num_chipselect in spi master
drivers. So let's remove the duplicate code.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-By: David Daney <david.daney@cavium.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-02-16 09:51:02 +08:00
Axel Lin aa188f90ff spi: Use SPI_BPW_MASK macro at appropriate places
Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-02-07 12:21:28 +00:00
Mark Brown 8aeab58e56 Merge remote-tracking branches 'spi/topic/pxa2xx', 'spi/topic/qspi', 'spi/topic/s3c24xx', 'spi/topic/s3c64xx', 'spi/topic/sh', 'spi/topic/tegra114', 'spi/topic/tegra20-sflash', 'spi/topic/tegra20-slink', 'spi/topic/txx9' and 'spi/topic/xcomm' into spi-linus 2014-01-23 13:07:14 +00:00
Axel Lin 5a33d30ff1 spi: ti-qspi: Fixup driver name
The driver name in current code looks like a compatible string which is not
the naming convention for platform drivers.
Fix it and also add modalias since this driver can be built as a module.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-01-13 10:16:16 +00:00
Axel Lin 3ab5462054 spi: ti-qspi: Simplify qspi_write_msg and qspi_read_msg implementation
Make the unit of wlen to be byte, and simplify the code to avoid duplicate
code for different wlen cases.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-01-13 10:15:13 +00:00
Axel Lin e3d8bee385 spi: ti-qspi: Fix getting correct address for qspi
Now platform_get_drvdata() returns the address of qspi rather than master.
Also drop unneeded spi_unregister_master() call in ti_qspi_remove() because
we use devm_spi_register_master() in probe.

commit cbcabb7a30 "spi/qspi: Fix qspi remove path" assumes
platform_get_drvdata() returns address of master. However,
commit 160a061301 "spi/qspi: set correct platform drvdata in ti_qspi_probe()"
pass qspi to platform_set_drvdata().

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Reviewed-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2014-01-07 11:38:00 +00:00
Sourav Poddar f17414c4fc spi/qspi: Fix runtime resume path
Due to the following commit
commit 160a061301
Author: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Date:   Mon Nov 11 14:13:41 2013 +0800

    spi/qspi: set correct platform drvdata in ti_qspi_probe()

    The ti_qspi_remove() use the platform drvdata as a type of
    struct ti_qspi, we should pass correct platform drvdata to
    platform_set_drvdata() in ti_qspi_probe().

    Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
    Signed-off-by: Mark Brown <broonie@linaro.org>

platform_set_drvdata was changed in  the probe, so we need to
correspondingly change deferencing of qspi in runtime resume
path. Else, this will lead to a NULL dereference pointer.

Based on v3.13-rc3

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-12-31 12:55:59 +00:00
Sourav Poddar 6b3938aed0 spi/qspi: parse register by name.
Modify the qspi driver to parse reg information by name.
If "reg names" is not found, then revert back to normal
get resource.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-12-19 13:33:43 +00:00
Sourav Poddar cbcabb7a30 spi/qspi: Fix qspi remove path.
There is a bug in qspi removal path, as a result of which
qspi cannot be removed when used as a module. The patch
solves the bug and qspi can be removed cleanly.

The bugs fixed are:
-pm_runtime used around register access.
- pm_runtime_disable need to be done before removal.
- spi_unregister_master need to be called to unregister
   the spi device.
Tested on DRA7 board.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-11-24 14:15:11 +00:00
Sourav Poddar 05b96675db spi/qspi: cleanup pm_runtime error check.
clean up pm_runtime error check in accordance with rest of the check in
the driver.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-11-24 14:15:10 +00:00
Wei Yongjun 160a061301 spi/qspi: set correct platform drvdata in ti_qspi_probe()
The ti_qspi_remove() use the platform drvdata as a type of
struct ti_qspi, we should pass correct platform drvdata to
platform_set_drvdata() in ti_qspi_probe().

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-11-24 14:15:10 +00:00
Mark Brown dabefd56c6 Merge remote-tracking branch 'spi/topic/devm' into spi-qspi
Conflicts:
	drivers/spi/spi-ti-qspi.c
2013-10-07 12:02:26 +01:00
Sebastian Andrzej Siewior 3b3a80019f spi: ti-qspi: one only one interrupt handler
The here used irq and threaded irq handler is a complete non-sense. After
the status register is read and the source disabled it schedules a thread
(the irq thread) to read the status from the variable, invoke complete()
and then renable the interrupt. Again: schedule a thread which invokes
_only_ complete().
This patch removes this non-sense and we remain with one handler which
invokes complete() if needed.
The device remove path should now disable the interupts.
This has been compile time tested.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-10-07 11:29:22 +01:00
Sourav Poddar 633795b992 spi/qspi: Add dual/quad read mode bit.
Add dual/quad read mode bit flag for the master controller.
These check will be used in the spi framework to determine
whether the master controller can do dual/quad read respectively.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-09-26 12:12:04 +01:00
Jingoo Han 7388c03bac spi: ti-qspi: use devm_spi_register_master()
Use devm_spi_register_master() to make cleanup paths simpler,
and remove unnecessary remove().

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-09-26 11:43:09 +01:00
Wei Yongjun b6460366fb spi/qspi: fix missing unlock on error in ti_qspi_start_transfer_one()
Add the missing unlock before return from function ti_qspi_start_transfer_one()
in the error handling case.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-09-01 13:47:55 +01:00
Sourav Poddar 09222fc33f spi/qspi: Add compatible string for am4372.
Add a compatible string for am4372.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-27 15:44:10 +01:00
Sourav Poddar e1432d30cb spi/qspi: Fix device table entry
Fix module device table entry. Without this, there will
be a build failure while trying to build qspi as a module.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-27 14:30:20 +01:00
Sourav Poddar 70e2e9761a spi/qspi: Add dual/quad spi read support
Support for multiple lines in SPI framework has been picked[1].
[1]: http://comments.gmane.org/gmane.linux.kernel.spi.devel/14420

Hence, adapting ti qspi driver to support multiple data lines for read.

Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-23 12:00:32 +01:00
Sourav Poddar 505a14954e spi/qspi: Add qspi flash controller
The patch add basic support for the quad spi controller.

QSPI is a kind of spi module that allows single,
dual and quad read access to external spi devices. The module
has a memory mapped interface which provide direct interface
for accessing data form external spi devices.

The patch will configure controller clocks, device control
register and for defining low level transfer apis which
will be used by the spi framework to transfer data to
the slave spi device(flash in this case).

Test details:
-------------
Tested this on dra7 board.
Test1: Ran mtd_stesstest for 40000 iterations.
   - All iterations went through without failure.
Test2: Use mtd utilities:
  - flash_erase to erase the flash device
  - mtd_debug read to read data back.
  - mtd_debug write to write to the data flash.
 diff between the write and read data shows zero.

Acked-by: Felipe Balbi<balbi@ti.com>
Reviewed-by: Felipe Balbi<balbi@ti.com>
Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
2013-08-22 13:08:06 +01:00