Ben Hutchings [Thu, 6 Nov 2014 03:35:09 +0000 (03:35 +0000)]
mmc: block: Increase max_devices
Currently the driver imposes a limit of 256 total minor numbers,
apparently based on the historic Unix/Linux limit. This is quite
restrictive, particularly if we raise the maximum number of
partitions per card to 256 to match sd.
In order to make the full minor number space available we would
have to replace the static dev_use and name_use arrays with struct
ida. But we can at least allow use of 256 cards rather than just
256 minors, with only a small change.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
between mmc_go_idle() and mmc_sdio_init_card().
mmc_sdio_resume() needs to as well, else my libertas sdio wifi
device doesn't resume properly from suspend.
NeilBrown [Wed, 12 Nov 2014 03:55:19 +0000 (14:55 +1100)]
mmc: core: use card->ocr when negotiating voltage setting in mmc_sdio_power_restore
As we are restoring power to a known card, it makes sense to use
the 'ocr' value known for the card rather than the generic one
for the host interface.
This matches the use of card->ocr passed to mmc_power_up in
mmc_sdio_runtime_resume (just before mmc_sdio_power_restore is
called), and the value passed to mmc_sdio_init_card() a little
later in mmc_sdio_power_restore().
Ondrej Zary [Tue, 11 Nov 2014 16:54:55 +0000 (17:54 +0100)]
mmc: add Toshiba PCI SD controller driver
This patch resurrects an old never-finished driver for Toshiba PCI SD
controllers found in some older Toshiba laptops (such as Portege R100):
02:0d.0 System peripheral [0880]: Toshiba America Info Systems SD TypA Controller [1179:0805] (rev 05)
The code is fixed, cleaned up and successfully tested with SD, SDHC, SDXC and
MMC cards on Portege R100. (MMC cards don't even work in Windows!)
SDIO probably does not work (don't have any SDIO card).
The hardware is slow (around 2 MB/s - same in Windows) because it does not
support bus mastering (busmaster enable bit cannot be set in PCI control reg).
Also the card clock is limited to 16MHz (33MHz PCI clock divided by 2).
Signed-off-by: Ondrej Zary <linux@rainbow-software.org> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Abhilash Kesavan [Thu, 28 Aug 2014 13:18:53 +0000 (18:48 +0530)]
mmc: dw_mmc: exynos: Add support for exynos7
The Exynos7 has a DWMMC controller (v2.70a) which is different from
prior versions. This patch adds new compatible strings for exynos7.
This patch also fixes the CLKSEL register offset on exynos7.
Johan Rudholm [Thu, 6 Nov 2014 13:46:54 +0000 (14:46 +0100)]
mmc: core: consistent handling of initial values
mmc_do_hw_reset(), mmc_power_up() and mmc_power_off() all set similar
initial values for bus_mode, bus_width, chip_select and timing. Let's
make this handling simpler and more consistent by sticking them
together in a common function. This will introduce small changes in
behavior in the following places:
mmc_power_off():
For SPI hosts, explicitly set bus_mode = MMC_BUSMODE_PUSHPULL and
chip_select = MMC_CS_HIGH, before we left them as they were.
For non-SPI hosts, set bus_mode = MMC_BUSMODE_PUSHPULL instead of
MMC_BUSMODE_OPENDRAIN as before.
These two changes should not be a problem since the device will be
powered off anyway.
mmc_do_hw_reset():
Always set bus_mode = MMC_BUSMODE_PUSHPULL, as required by SD/SDIO
cards. MMC cards require MMC_BUSMODE_OPENDRAIN, but this is taken
care of by mmc_init_card() and mmc_attach_mmc().
Signed-off-by: Johan Rudholm <johanru@axis.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andreas Fenkart [Sat, 8 Nov 2014 14:33:16 +0000 (15:33 +0100)]
mmc: omap_hsmmc: Remove unnecessary callbacks from platform data
These callbacks are set during driver probe and not from the platform
init, -- evtl. they had been for oamp 1/2 -- for omap3 they are local
functions of the driver. These indirection could be dropped
altogether in favor of regular function calls TODO
Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andreas Fenkart [Sat, 8 Nov 2014 14:33:15 +0000 (15:33 +0100)]
mmc: omap_hsmmc: pass mmc_priv struct to gpio init / free
this is needed when installing callbacks in the host struct and not
in the platform data, e.g. cover detect irq should be stored in
omap_hsmmc_host and not platform data
Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
omap_hsmmc supports only one slot per controller, see OMAP_MMC_MAX_SLOTS.
This unnecessary indirection leads to confusion in the omap_hsmmc driver.
For example the card_detect callback is not installed by platform code
but from the driver probe function. So it should be a field of
omap_hsmmc_host. But since it is declared under the platform slot while
the drivers struct omap_hsmmc_host has no slot abstraction, this looks
like a bug, especially when not familiar that this driver only supports
1 slot anyway.
Either we should add a slot abstraction to omap_hsmmc_host or remove
it from the platform data struct. Removed since slot multiplexing is
an un-implemented feature
Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andreas Fenkart [Sat, 8 Nov 2014 14:33:10 +0000 (15:33 +0100)]
mmc: omap_hsmmc: remove unused fields in platform_data
platform data is built from omap2_hsmmc_info, remove all fields that
are never set in omap_hsmmc_info, hence never copied to platform data.
Note that the omap_hsmmc driver is not affected by this patch those
fields were completely unused.
Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andreas Fenkart [Sat, 8 Nov 2014 14:33:09 +0000 (15:33 +0100)]
ARM: OMAP1/2+: MMC: separate platform data for mmc and mmc hs driver
- omap mmc driver supports multiplexing, omap_mmc_hs doesn't
this leads to one of the major confusions in the omap_hsmmc driver
- platform data should be read-only for the driver
most callbacks are not set by the omap3 platform init code while still
required. So they are set from the driver probe function, which is against
the paradigm that platform-data should not be modified by the driver
typical examples are card_detect, read_only callbacks
un-bundling by searching for driver name \"omap_hsmmc in the
arch/arm folder. omap_hsmmc_platform_data is not initialized directly,
but from omap2_hsmmc_info, which is defined in a separate header file
not touched by this patch
hwmod includes platform headers to declare features of the platform. All
the declared features are prefixed OMAP_HSMMC. There is no need to
include platform header from hwmod other except for feature defines
Acked-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andreas Fenkart [Sat, 8 Nov 2014 14:33:08 +0000 (15:33 +0100)]
ARM: OMAP2: MMC: include mmc-omap platform header directly
Only a few files really need that platform header. When later splitting
omap_mmc_platform_data into omap_mmc and omap_mmc_hs, those files
declaring an hs mmc platform data will have to change the platform
include, which is a good sanity check.
Also removing omap242x_init_mmc, which is not used anywhere, checked
with grep.
Signed-off-by: Andreas Fenkart <afenkart@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Wenyou Yang [Fri, 7 Nov 2014 00:48:13 +0000 (08:48 +0800)]
mmc: atmel-mci: adopt pinctrl support
Amend the atmel mci pin controller to optionally take a pin control
handle and set the state of the pins to:
- "default" on boot, resume and before performing an transfer.
- "sleep" on suspend().
This should make it possible to optimize energy usage for the pins
both for the suspend/resume cycle.
Signed-off-by: Wenyou Yang <wenyou.yang@atmel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Thu, 6 Nov 2014 13:19:06 +0000 (15:19 +0200)]
mmc: sdhci: Add HS400 support to SDHCI driver
MMC core already has support for HS400. Add HS400
support to SDHCI driver. The SDHC Standard specification
does not define HS400 so consequently HS400 support is
non-standard. However HS400 is not selected without
the host controller setting the corresponding capability
flags so host controllers not yet supporting HS400
will not be affected. To support that, a quirk
SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 is introduced to
enable the use of capabilities register reserved bit-63
to indicate HS400 support.
Because HS400 is non-standard for SDHCI, it is possible
that different vendors will do things in different ways.
However HS200 support faced the same issue but currently
there is only one solution. As such, no attempt has
been made to provide for alternate HS400 solutions except
for SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
mmc: dw_mmc: Add IDMAC 64-bit address mode support
Synopsys DW_MMC IP core supports Internal DMA Controller with 64-bit address mode from IP version 2.70a onwards.
Updated the driver to support IDMAC 64-bit addressing mode.
Signed-off-by: Prabu Thangamuthu <prabu.t@synopsys.com> Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com> Acked-by: Jaehoon Chung <jh80.chung@samsung.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Vincent Wan [Wed, 5 Nov 2014 06:09:00 +0000 (14:09 +0800)]
mmc: sdhci: Add a quirk for AMD SDHC transfer mode register need to be cleared for cmd without data
SDHC controller in AMD chipsets require SDHC transfer mode
register to be cleared for commands without data. The issue was
uncovered during testing eMMC cards on KB/ML based platforms
Signed-off-by: Vincent Wan <vincent.wan@amd.com> Signed-off-by: Wan Zongshun <mcuos.com@gmail.com> Signed-off-by: Arindam Nath <arindam.nath@amd.com> Tested-by: Vikram B <vikram.b@amd.com> Tested-by: Raghavendra Swamy <raghavendra.swamy@amd.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Wenyou Yang [Thu, 30 Oct 2014 04:00:41 +0000 (12:00 +0800)]
mmc: atmel-mci: add runtime pm support
Add runtime pm support to atmel mci controller.
Use runtime pm APIs to enable/disable atmel mci's clock.
Use runtime autosuspend APIs to enable auto suspend delay.
Adrian Hunter [Tue, 4 Nov 2014 10:42:49 +0000 (12:42 +0200)]
mmc: mmc_test: Extend "Badly aligned" tests for 8-byte alignment
The "Badly aligned" tests, test reading/writing with alignments
of 1,2 and 3. SDHCI now has 64-bit ADMA which has 8-byte
alignment, so extend the tests to test up to 7.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:47 +0000 (12:42 +0200)]
mmc: sdhci-acpi: Add 64-bit DMA support
Set the DMA mask during the first call to ->enable_dma() to
make use of the SDHCI_USE_64_BIT_DMA flag.
This patch is dependent on
commit 8a2f38ddfeb526c30b3ec209468172a30a38d996 ("ACPI / platform: provide default DMA mask")
which provides the dev->dma_mask pointer without
which dma_set_mask_and_coherent() will always fail.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:46 +0000 (12:42 +0200)]
mmc: sdhci: Add 64-bit ADMA support
Add 64-bit ADMA support including:
- add 64-bit ADMA descriptor
- add SDHCI_USE_64_BIT_DMA flag
- set upper 32-bits of DMA addresses
- ability to select 64-bit ADMA
- ability to use 64-bit ADMA sizes and alignment
- display "ADMA 64-bit" when host is added
It is assumed that a 64-bit capable device has set a 64-bit DMA mask
and *must* do 64-bit DMA. A driver has the opportunity to change
that during the first call to ->enable_dma(). Similarly
SDHCI_QUIRK2_BROKEN_64_BIT_DMA must be left to the drivers to
implement.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:42 +0000 (12:42 +0200)]
mmc: sdhci: Parameterize ADMA sizes and alignment
In preparation for 64-bit ADMA, parameterize ADMA sizes
and alignment. 64-bit ADMA has a larger descriptor
because it contains a 64-bit address instead of a 32-bit
address. Also data must be 8-byte aligned instead
of 4-byte aligned. Consequently, sdhci_host members
are added for descriptor, table, and buffer sizes
and alignment.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:41 +0000 (12:42 +0200)]
mmc: sdhci: Use 'void *' for not 'u8 *' for ADMA data
It is kernel-style to use 'void *' for anonymous data.
This is being applied to the ADMA bounce buffer which
contains unaligned bytes, and to the ADMA descriptor
table which will contain 32-bit ADMA descriptors
or 64-bit ADMA descriptors when support is added.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:39 +0000 (12:42 +0200)]
mmc: sdhci: Rename adma_desc to adma_table
In preparation for 64-bit ADMA, rename adma_desc to
adma_table. That is because members will be added
for descriptor size and table size, so using adma_desc
(which is the table) is confusing.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:38 +0000 (12:42 +0200)]
mmc: sdhci: Rename two ADMA-related functions for consistency
Rename sdhci_set_adma_desc to sdhci_adma_write_desc and
sdhci_show_adma_error to sdhci_adma_show_error so that
all ADMA functions start with sdhci_adma_.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:37 +0000 (12:42 +0200)]
mmc: sdhci: Fix ADMA table size warning
The intent of the warning is to warn if the ADMA table
overflows. However there can be one more 'end' entry
so the condition should be adjusted accordingly.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Adrian Hunter [Tue, 4 Nov 2014 10:42:36 +0000 (12:42 +0200)]
mmc: sdhci: Fix ADMA page boundary warnings
Bytes are being copied from/to a single page. The intent
of the warning is to warn if the page boundary is crossed.
There are two problems. First, PAGE_MASK is mistaken for
(PAGE_SIZE - 1). Secondly, instead of using the number
of bytes to copy, the warning is using the maximum that
that value could be. Fix both.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
The ADMA2 descriptor table size was being calculated incorrectly
Fix it.
Note that it has been wrong for a long time and likely has not
caused any problems because of a combination of 1) not needing
alignment descriptors for block operations 2) more memory being
allocated than was requested 3) the use of
SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC which does not use an extra
descriptor for the end marker.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
mmc: sdhci-pxav3: Try to get named I/O clock first
With support for more than one clock, we'll need to distinguish between
the clock by name. Change clock probing to first try to get "io" clock
before falling back to unnamed clock.
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
As we are using references to the I/O clock throughout the driver,
move it to the private data. Also, in preparation for core clock,
rename it to clk_io.
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
sdhci_add_host and sdhci_platfm_init already report failure,
so don't emit error messages when a failure occurs. This prevents
occurences of "deferred" messages when required power supplies
are not ready for operation yet.
Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Ulf Hansson [Fri, 17 Oct 2014 09:58:24 +0000 (11:58 +0200)]
mmc: core: Don't handle buffers on stack while fetching CXD registers
Due to previous patches, all callers of mmc_send_cxd_data() now
allocates their buffers from the heap. This enables us to simplify
mmc_send_cxd_data() by removing the support of handling buffers, which
are allocated from the stack.
Ulf Hansson [Mon, 20 Oct 2014 11:37:24 +0000 (13:37 +0200)]
mmc: core: Fetch and decode EXT_CSD from mmc_read_ext_csd()
As a step in cleaning up code around reading/decoding EXT_CSD, convert
the current mmc_read_ext_csd(), to handle both fetching the EXT_CSD
and decoding its data.
Ulf Hansson [Mon, 20 Oct 2014 09:33:53 +0000 (11:33 +0200)]
mmc: core: Add helper function for EXT_CSD support
The helper function mmc_can_ext_csd() will return a positive value if
the card supports the EXT_CSD register. Start using it at relavant
places in the mmc core.
Ulf Hansson [Mon, 20 Oct 2014 09:49:21 +0000 (11:49 +0200)]
mmc: core: Remove redundant check of max_dtr while selecting timings
If the MMC spec version is < CSD_SPEC_VER_4, there aren't support for
the EXT_CSD register. Since max_dtr is fetched from there, it will
default to zero, which thus isn't needed to verify.
Ulf Hansson [Fri, 17 Oct 2014 09:16:57 +0000 (11:16 +0200)]
mmc: core: Remove duplicated definition of mmc_send_ext_csd()
mmc_send_ext_csd() is an exported function used by both the mmc core
and the mmc block layer. Let's remove the local duplicated definition
in the mmc core.
Doug Anderson [Tue, 14 Oct 2014 16:33:09 +0000 (09:33 -0700)]
mmc: dw_mmc: Remove old card detect infrastructure
The dw_mmc driver had a bunch of code that ran whenever a card was
ejected and inserted. However, this code was old and crufty and
should be removed. Some evidence that it's really not needed:
1. Is is supposed to be legal to use 'cd-gpio' on dw_mmc instead of
using the built-in card detect mechanism. The 'cd-gpio' code
doesn't run any of the crufty old code but yet still works.
2. While looking at this, I realized that my old change (369ac86 mmc:
dw_mmc: don't queue up a card detect at slot startup) actually
castrated the old code a little bit already and nobody noticed.
Specifically "last_detect_state" was left as 0 at bootup. That
means that on the first card removal none of the crufty code ran.
3. I can run "while true; do dd if=/dev/mmcblk1 of=/dev/null; done"
while ejecting and inserting an SD Card and the world doesn't
explode.
If some of the crufty old code is actually needed, we should justify
it and also put it in some place where it will be run even with
"cd-gpio".
Note that in my case I'm using the "cd-gpio" mechanism but for various
reasons the hardware triggers a dw_mmc "card detect" at bootup. That
was actually causing a real bug. The card detect workqueue was
running while the system was trying to enumerate the card. The
"present != slot->last_detect_state" triggered and we were doing all
kinds of crazy stuff and messing up enumeration. The new mechanism of
just asking the core to check the card is much safer and then the
bogus interrupt doesn't hurt.
Mike Looijmans [Thu, 23 Oct 2014 11:31:00 +0000 (13:31 +0200)]
mmc: sdhci-of-arasan: Use signed formatting in error messages
"ret" is a signed int, so use "%d" in format strings instead of "%u".
This prevents cryptic codes in error messages like this:
sdhci-arasan e0101000.sdhci: platform register failed (4294966779)
Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl> Reviewed-by: Michal Simek <michal.simek@xilinx.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Gwendal Grignou [Thu, 16 Oct 2014 18:27:16 +0000 (11:27 -0700)]
mmc: core: Report firmware version for eMMC 5.0 devices.
For eMMC 5.0 compliant device, firmware version is stored in ext_csd.
Report firmware as a 64bit hexa decimal. Vendor can use hexa or ascii
string to report firmware version.
Also add FFU related EXT_CSD register and note if the device is FFU capable.
Doug Anderson [Tue, 14 Oct 2014 16:39:12 +0000 (09:39 -0700)]
mmc: dw_mmc: rockchip: Don't recalc the clock when it goes off
The "set_ios" function is called with a clock of 0 when the clock is
turning off. There's no reason to go through all the extra Rockchip
logic (whose goal is to make sure DIV is 0 or 1) in that case. The
Rockchip logic happened to work because the CCF will pick the lowest
possible rate when you ask it for a clock of 0, but it's silly to go
through all the remuxing and adjusting for no reason.
Doug Anderson [Sat, 11 Oct 2014 04:16:16 +0000 (21:16 -0700)]
mmc: dw_mmc: Change signal voltage error to dev_dbg()
In (28f92b5 mmc: core: Try other signal levels during power up) we can
see that there are times when it's valid to try several signal
voltages. Don't print an ugly error in the logs when that happens.
Signed-off-by: Doug Anderson <dianders@chromium.org> Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com> Acked-by: Jaehoon Chung <jh80.chung@samsung.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Sonny Rao [Thu, 16 Oct 2014 16:58:05 +0000 (09:58 -0700)]
mmc: dw_mmc: Reset DMA before enabling IDMAC
We've already got a reset of DMA after it's done. Add one before we
start DMA too. This fixes a data corruption on Rockchip SoCs which
will get bad data when doing a DMA transfer after doing a PIO transfer.
We tested this on an Exynos 5800 with HS200 and didn't notice any
difference in sequential read throughput.
Signed-off-by: Sonny Rao <sonnyrao@chromium.org> Signed-off-by: Doug Anderson <dianders@chromium.org> Tested-by: Doug Anderson <dianders@chromium.org> Acked-by: Jaehoon Chung <jh80.chung@samsung.com> Tested-by: Jaehoon Chung <jh80.chung@samsung.com> Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Ulf Hansson [Mon, 6 Oct 2014 11:51:40 +0000 (13:51 +0200)]
mmc: core: Convert mmc_driver to device_driver
The struct mmc_driver adds an extra layer on top of the struct
device_driver. That would be fine, if there were a good reason, but
that's not the case.
Let's simplify code by converting to the common struct device_driver
instead and thus also removing superfluous overhead.
mmc: sdhci-pxav3: Remove checks for mandatory host clock
NULL-checking a struct clk it not only wrong but also not required as
for PXAv3 driver the corresponding clock is mandatory. Remove the
checks from sdhci_pxav3_runtime_{suspend,resume}.
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
mmc: sdhci-pxav3: Respect MMC_DDR52 timing on uhs signaling
commit bb8175a8aa42d731a840cd474e348ac3367eb5a0
("mmc: sdhci: clarify DDR timing mode between SD-UHS and eMMC")
added MMC_DDR52 as eMMC's DDR mode to be distinguished from SD-UHS.
While the differentation may be useful, pxav3 SDHCI controller lacks
a corresponding check in its custom .set_uhs_signaling callback for
MMC_DDR52. This patch adds a new switch case for MMC_TIMING_MMC_DDR52
to MMC_TIMING_UHS_DDR50 case.
Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
If the post request is cancelling the channel and descriptor and which are
equal to host->dma_current and host->dma_desc_current respectively, then it
makes sense to reset these pointers to NULL, so that the driver does not
reference it.
Also the host_cookie can be reset to 0 in cases of error, so that the
core could reissue the same mmc_request.
This patch was tested with 'mmc: core: fix prepared requests while doing
bkops' to fix the below issue.
mmc: core: fix prepared requests while doing bkops
While starting the bkops the previously prepared request should be canceled
and restarted after the bkops. As the prepared resource might already
setup the dma channels and ready to be started. Now with the arrival of bkops
request this prepared request can be serviced ONLY after the bkops. So
holding on to the prepared request in the host driver is confusing at
this point in time, so it makes sense to cleanup such dangling requests and
reissue this request once bkops is done.
Canceling the prepared request would give opportunity to the host drivers
to perform cleanup on the prepared request.
Without this patch host drivers like mmci gets confused when a blocking
request like send_ext_csd(CMD8) is issued while there is already a prepared
request. With the help of this patch, the driver can better manage such
blocking requests and cleanup the prepared requests which are not started yet.
Without this patch I hit below crash on Qualcomm APQ8064 based IFC6410 board
with mmci host driver.
Andrew Gabbasov [Wed, 1 Oct 2014 12:14:11 +0000 (07:14 -0500)]
mmc: core: Fix error paths and messages in mmc_init_card
In mmc_init_card function some of the branches in error handling paths
go to "err" label, which skips removing of newly allocated card structure,
that will actually not be used. Fix that by using proper "free_card" label.
Also, some messages in these branches are reported as warnings,
although the operation processing is not continued. Change these
messages to error level.
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andrew Gabbasov [Wed, 1 Oct 2014 12:14:10 +0000 (07:14 -0500)]
mmc: core: Add debug message for SET_BLOCK_COUNT result
The debug messages with commands execution results, that are printed
after processing the request, do not include results of sbc (set block count)
part of request. Add the debug message for that part too.
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Some request fields are initialized just before request processing
for sanity purposes. This is done for command, data, and stop parts
of the request, but not for sbc (set block count) part. Add such
initialization for that part too.
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andrew Gabbasov [Wed, 1 Oct 2014 12:14:08 +0000 (07:14 -0500)]
mmc: sdhci: fix error conditions for controller reset
Add the case of SET_BLOCK_COUNT command error to the error conditions
check for making a controller reset at request handling finish.
Otherwise, if the SET_BLOCK_COUNT command failed, e.g. with a timeout,
the controller state was not reset, and the next command failed too.
In the case of data error the controller reset is already done in
finish_data() function before sending stop command (if present),
so the finish tasklet should make a reset after data error only
if no stop command existed in the request.
Also, fix the indentation of this condition check to make it more logical.
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Andrew Gabbasov [Wed, 1 Oct 2014 12:14:07 +0000 (07:14 -0500)]
mmc: sdhci: Balance vmmc regulator_disable()
As a follow-up of commit
"mmc: sdhci: Balance vmmc regulator_enable(), and always enable vqmmc"
vmmc regulator disable is also not needed in sdhci_remove_host.
The regulator is completely controlled by mmc_power_up and mmc_power_off
functions and is already disabled by the time of removing the host.
Extra regulator_disable call in sdhci_remove_host is unbalanced and
causes a warning reported by regulator core, so should be removed.
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Dirk Behme [Wed, 1 Oct 2014 09:25:32 +0000 (04:25 -0500)]
mmc: sdhci-esdhc-imx: don't exit in case of no pinctrl states
The commit ad93220de7da ("mmc: sdhci-esdhc-imx: change pinctrl state
according to uhs mode") exits the probe in case there are no valid
pinctrl states found.
As there are configurations doing the pin mux properly in the boot
loader, don't exit. Just warn, but go on in case if there are no
pinctrl states in the device tree.
mmc: mxcmmc: fix race condition when dma finish a data transfer
During a read of data block using dma, driver might have two ways to finish to read
and free the resources:
1) checking STATUS_DATA_TRANS_DONE mask, in the mxcmci_irq() routine
(pending to mmc irq)
2) mxmmc driver, registers also a mxcmci_dma_callback() and when transfer is finished,
dma driver calls this callback. (pending to dma irq)
Both ways are concurrent with each other.
Race condition happens when following events occur:
/* (1) mxcmci driver start data transfer */
158.418970: mpc_dma_execute: mpc_dma_execute(): will_access_peripheral start cid=31
158.418976: mpc_dma_issue_pending <-mxcmci_request
158.418983: mxcmci_start_cmd <-mxcmci_request
/* (2) mxcmci driver receive mmc irq */
158.419656: mxcmci_irq <-handle_irq_event_percpu
158.419692: mxcmci_read_response <-mxcmci_irq
/* (3) mxcmci driver checks that transfer is complete and call mxcmci_finish_data() */
158.419726: mxcmci_data_done <-mxcmci_irq
158.419729: mxcmci_finish_data <-mxcmci_data_done
158.419733: dma_direct_unmap_sg <-mxcmci_finish_data
158.419736: mxcmci_swap_buffers.isra.24 <-mxcmci_finish_data
158.419762: mxcmci_read_response <-mxcmci_data_done
/* (4) mxcmci driver (no dma): send stop command */
158.419765: mxcmci_start_cmd <-mxcmci_data_done
/* (5) mxcmci driver (no dma): receive the stop command irq response */
158.419782: mxcmci_irq <-handle_irq_event_percpu
158.419812: mxcmci_read_response <-mxcmci_irq
158.419843: mxcmci_finish_request <-mxcmci_irq
/* (6) dma driver: receive dma irq (finish data transfer) related by request on step 1 */
158.419853: mpc_dma_irq <-handle_irq_event_percpu
158.420001: mpc_dma_irq_process <-mpc_dma_irq
158.420004: mpc_dma_irq_process <-mpc_dma_irq
/* (7) dma driver: start dma tasklet to finish the dma irq handling */
158.420008: mpc_dma_irq_process: mpc_dma_irq_process(): completed ch:31
/* (8) mxcmci driver: start next data transfer using dma */
158.420174: mxcmci_request <-mmc_start_req
158.420182: dma_direct_map_sg <-mxcmci_request
158.420192: mpc_dma_prep_slave_sg <-mxcmci_request
/* (9) dma driver: schedule irq tasklet and execute mxcmci dma driver callback */
158.420250: mpc_dma_tasklet <-tasklet_action
158.420254: mpc_dma_process_completed <-tasklet_action
158.420267: mxcmci_dma_callback <-mpc_dma_process_completed
/* ERROR!!! (10) mxcmci driver callback works on dma data related to the step 1
that is already finished */
158.420271: mxcmci_data_done <-mpc_dma_process_completed
158.420273: mxcmci_finish_data <-mxcmci_data_done
/* ERROR!!! (11) mxcmci driver: clear data that should be used by step 8 and
send an other mmc stop command (already sended on step 4) */
158.420276: dma_direct_unmap_sg <-mxcmci_finish_data
158.420279: mxcmci_swap_buffers.isra.24 <-mxcmci_finish_data
158.420330: mxcmci_read_response <-mxcmci_data_done
158.420333: mxcmci_start_cmd <-mxcmci_data_done
158.420338: dma_run_dependencies <-mpc_dma_process_completed
...
...
...
168.474223: mxcmci_watchdog <-call_timer_fn
168.474236: mxcmci_watchdog: mxcmci_watchdog
168.474397: mpc_dma_device_control <-mxcmci_watchdog
In accordance with the other drivers that using the dma engine,
fix it, leaving *only* to dma driver the complete control to
ending the read operation.
Removing STATUS_READ_OP_DONE event activation, has as effect
to force mxcmci driver to handle the finish data transfer only
by mxcmci dma callback.
projects / karo-tx-linux.git / log