The comment in spinand_write_to_cache_op() says that
spinand_ondie_ecc_prepare_io_req() should 0xff fill the OOB
area but it doesn't.
This causes the OOB area to get filled with zeros
and anytime the first page in a block the bad block marker
is cleared and it becomes a bad block on the next boot.
This was observed on Longsys FORSEE branded parts and
might be specific to these parts.
Signed-off-by: Daniel Palmer <daniel@0x0f.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20210617110842.2358461-1-daniel@0x0f.com
Pull MTD updates from Richard Weinberger:
"MTD core changes:
- Convert list_for_each to entry variant
- Use MTD_DEVICE_ATTR_RO/RW() helper macros
- Remove unnecessary OOM messages
- Potential NULL dereference in mtd_otp_size()
- Fix freeing of otp_info buffer
- Create partname and partid debug files for child MTDs
- tests:
- Remove redundant assignment to err
- Fix error return code in mtd_oobtest_init()
- Add OTP NVMEM provider support
- Allow specifying of_node
- Convert sysfs sprintf/snprintf family to sysfs_emit
Bindings changes:
- Convert ti,am654-hbmc.txt to YAML schema
- spi-nor: add otp property
- Add OTP bindings
- add YAML schema for the generic MTD bindings
- Add brcm,trx-magic
MTD device drivers changes:
- Add support for microchip 48l640 EERAM
- Remove superfluous "break"
- sm_ftl:
- Fix alignment of block comment
- nftl:
- Return -ENOMEM when kmalloc failed
- nftlcore:
- Remove set but rewrite variables
- phram:
- Fix error return code in phram_setup()
- plat-ram:
- Remove redundant dev_err call in platram_probe()
MTD parsers changes:
- Qcom:
- Fix leaking of partition name
- Redboot:
- Fix style issues
- Seek fis-index-block in the right node
- trx:
- Allow to use TRX parser on Mediatek SoCs
- Allow to specify brcm, trx-magic in DT
Raw NAND core:
- Allow SDR timings to be nacked
- Bring support for NV-DDR timings which involved a number of small
preparation changes to bring new helpers, properly introduce NV-DDR
structures, fill them, differenciate them and pick the best timing
set.
- Add the necessary infrastructure to parse the new gpio-cs property
which aims at enlarging the number of available CS when a hardware
controller is too constrained.
- Update dead URL
- Silence static checker warning in nand_setup_interface()
- BBT:
- Fix corner case in bad block table handling
- onfi:
- Use more recent ONFI specification wording
- Use the BIT() macro when possible
Raw NAND controller drivers:
- Atmel:
- Ensure the data interface is supported.
- Arasan:
- Finer grain NV-DDR configuration
- Rename the data interface register
- Use the right DMA mask
- Leverage additional GPIO CS
- Ensure proper configuration for the asserted target
- Add support for the NV-DDR interface
- Fix a macro parameter
- brcmnand:
- Convert bindings to json-schema
- OMAP:
- Various fixes and style improvements
- Add larger page NAND chips support
- PL35X:
- New driver
- QCOM:
- Avoid writing to obsolete register
- Delete an unneeded bool conversion
- Allow override of partition parser
- Marvell:
- Minor documentation correction
- Add missing clk_disable_unprepare() on error in
marvell_nfc_resume()
- R852:
- Use DEVICE_ATTR_RO() helper macro
- MTK:
- Remove redundant dev_err call in mtk_ecc_probe()
- HISI504:
- Remove redundant dev_err call in probe
SPI-NAND core:
- Light reorganisation for the introduction of a core resume handler
- Fix double counting of ECC stats
SPI-NAND manufacturer drivers:
- Macronix:
- Add support for serial NAND flash
SPI NOR core changes:
- Ability to dump SFDP tables via sysfs
- Support for erasing OTP regions on Winbond and similar flashes
- Few API doc updates and fixes
- Locking support for MX25L12805D
SPI NOR controller drivers changes:
- Use SPI_MODE_X_MASK in nxp-spifi
- Intel Alder Lake-M SPI serial flash support"
* tag 'mtd/for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux: (125 commits)
mtd: spi-nor: remove redundant continue statement
mtd: rawnand: omap: Add larger page NAND chips support
mtd: rawnand: omap: Various style fixes
mtd: rawnand: omap: Check return values
mtd: rawnand: omap: Rename a macro
mtd: rawnand: omap: Aggregate the HW configuration of the ELM
mtd: rawnand: pl353: Add support for the ARM PL353 SMC NAND controller
dt-bindings: mtd: pl353-nand: Describe this hardware controller
MAINTAINERS: Add PL353 NAND controller entry
mtd: rawnand: qcom: avoid writing to obsolete register
mtd: rawnand: marvell: Minor documentation correction
mtd: rawnand: r852: use DEVICE_ATTR_RO() helper macro
mtd: spinand: add SPI-NAND MTD resume handler
mtd: spinand: Add spinand_init_flash() helper
mtd: spinand: add spinand_read_cfg() helper
mtd: rawnand: marvell: add missing clk_disable_unprepare() on error in marvell_nfc_resume()
mtd: rawnand: arasan: Finer grain NV-DDR configuration
mtd: rawnand: arasan: Rename the data interface register
mtd: rawnand: onfi: Fix endianness when reading NV-DDR values
mtd: rawnand: arasan: Use the right DMA mask
...
After power up, all SPI NAND's blocks are locked. Only read operations
are allowed, write and erase operations are forbidden.
The SPI NAND framework unlocks all the blocks during its initialization.
During a standby low power, the memory is powered down, losing its
configuration.
During the resume, the QSPI driver state is restored but the SPI NAND
framework does not reconfigured the memory.
This patch adds SPI-NAND MTD PM handlers for resume ops.
SPI NAND resume op re-initializes SPI NAND flash to its probed state.
Signed-off-by: Christophe Kerello <christophe.kerello@foss.st.com>
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20210602094913.26472-4-patrice.chotard@foss.st.com
In the raw NAND world, ECC engines increment ecc_stats and the final
caller is responsible for returning -EBADMSG if the verification
failed.
In the SPI-NAND world it was a bit different until now because there was
only one possible ECC engine: the on-die one. Indeed, the
spinand_mtd_read() call was incrementing the ecc_stats counters
depending on the outcome of spinand_check_ecc_status() directly.
So now let's split the logic like this:
- spinand_check_ecc_status() is specific to the SPI-NAND on-die engine
and is kept very simple: it just returns the ECC status (bonus point:
the content of this helper can be overloaded).
- spinand_ondie_ecc_finish_io_req() is the caller of
spinand_check_ecc_status() and will increment the counters and
eventually return -EBADMSG.
- spinand_mtd_read() is not tied to the on-die ECC implementation and
should be able to handle results coming from other ECC engines: it has
the responsibility of returning the maximum number of bitflips which
happened during the entire operation as this is the only helper that
is aware that several pages may be read in a row.
Fixes: 945845b54c ("mtd: spinand: Instantiate a SPI-NAND on-die ECC engine")
Reported-by: YouChing Lin <ycllin@mxic.com.tw>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: YouChing Lin <ycllin@mxic.com.tw>
Link: https://lore.kernel.org/linux-mtd/20210527084345.208215-1-miquel.raynal@bootlin.com
The relevant changes to the already existing GD5F1GQ4UExxG support has
been determined by consulting the GigaDevice product change notice
AN-0392-10, version 1.0 from November 30, 2020.
As the overlaps are huge, variable names have been generalized
accordingly.
Apart from the lowered ECC strength (4 instead of 8 bits per 512 bytes),
the new device ID, and the extra quad IO dummy byte, no changes had to
be taken into account.
New hardware features are not supported, namely:
- Power on reset
- Unique ID
- Double transfer rate (DTR)
- Parameter page
- Random data quad IO
The inverted semantic of the "driver strength" register bits, defaulting
to 100% instead of 50% for the Q5 devices, got ignored as the driver has
never touched them anyway.
The no longer supported "read from cache during block erase"
functionality is not reflected as the current SPI NAND core does not
support it anyway.
Implementation has been tested on MediaTek MT7688 based GARDENA smart
Gateways using both, GigaDevice GD5F1GQ5UEYIG and GD5F1GQ4UBYIG.
Signed-off-by: Reto Schneider <reto.schneider@husqvarnagroup.com>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Stefan Roese <sr@denx.de>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20210211113619.3502-1-code@reto-schneider.ch
The initial change breaking the logic is
commit 3d1f08b032 ("mtd: spinand: Use the external ECC engine logic")
It inadvertently dropped proper OOB support while doing something
else.
Shortly later, half of it got re-integrated by
commit 868cbe2a6d ("mtd: spinand: Fix OOB read")
(pointing by the way to a more early change which had nothing to do
with the issue). Problem is, this commit failed to revert the faulty
change entirely and missed the logic handling MTD_OPS_AUTO_OOB
requests.
Let's fix this mess by re-inserting the missing part now.
Fixes: 868cbe2a6d ("mtd: spinand: Fix OOB read")
Reported-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20210107083813.24283-1-miquel.raynal@bootlin.com
SPI NOR core changes:
- Initial support for stateful Octal DTR mode using volatile settings
- Preliminary support for JEDEC 251 (xSPI) and JEDEC 216D standards
- Support for Cypress Semper flash
- Support to specify ECC block size of SPI NOR flashes
- Fixes to avoid clearing of non-volatile Block Protection bits at probe
Generic NAND core:
* ECC management:
- Add an I/O request tweaking mechanism
- Entire rework of the software BCH ECC driver, creation of a real
ECC engine, getting rid of raw NAND structures, migration to more
generic prototypes, misc fixes and style cleanup. Moved now to the
Generic NAND layer.
- Entire rework of the software Hamming ECC driver, creation of a
real ECC engine, getting rid of raw NAND structures, misc renames,
comment updates, cleanup, and style fixes. Moved now to the
generic NAND layer.
- Necessary plumbing at the NAND level to retrieve generic NAND ECC
engines (softwares and on-die).
- Update of the bindings.
Raw NAND core:
* Geting rid of the chip->ecc.priv entry.
* Fix miscellaneous typos in kernel-doc
Raw NAND controller drivers:
* AU1550: Ensure the presence of the right includes
* Davinci: Do not use extra dereferencing
* GPMI:
- Fix the driver only sense CS0 R/B issue
- Fix the random DMA timeout issue
- Use a single line for of_device_id
- Use of_device_get_match_data()
- Fix reference count leak in gpmi ops
- Cleanup makefile
- Fix binding matching of clocks on different SoCs
* Ingenic: remove redundant get_device() in ingenic_ecc_get()
* Intel LGM: New NAND controller driver
* Marvell: Drop useless line
* Meson:
- Fix a resource leak in init
- Fix meson_nfc_dma_buffer_release() arguments
* mxc:
- Use device_get_match_data()
- Use a single line for of_device_id
- Remove platform data support
* Qcom:
- Add support for SDX55
- Support for IPQ6018 QPIC NAND controller
- Fix DMA sync on FLASH_STATUS register read
* Rockchip: New NAND controller driver for RK3308, RK2928 and others
* Sunxi: Add MDMA support
SPI-NAND core:
* Creation of a SPI-NAND on-die ECC engine
* Move ECC related definitions earlier in the driver
* Fix typo in comment
* Fill a default ECC provider/algorithm
* Remove outdated comment
* Fix OOB read
* Allow the case where there is no ECC engine
* Use the external ECC engine logic
SPI-NAND chip drivers:
* Micron:
- Add support for MT29F2G01AAAED
- Use more specific names
* Macronix:
- Add support for MX35LFxG24AD
- Add support for MX35LFxGE4AD
Others:
* onenand: Use mtd->oops_panic_write as condition
* plat-ram: correctly free memory on error path in platram_probe()
The Macronix MX35LF1G24AD(/2G24AD/4G24AD) are 3V, 1G/2G/4Gbit serial
SLC NAND flash device (without on-die ECC).
Validated by read, erase, read back, write, read back on Xilinx Zynq
PicoZed FPGA board which included Macronix SPI Host(drivers/spi/spi-mxic.c)
& S/W BCH ecc(drivers/mtd/nand/ecc-sw-bch.c) with bug fixing patch
(mtd: nand: ecc-bch: Fix the size of calc_buf/code_buf of the BCH).
Signed-off-by: YouChing Lin <ycllin@mxic.com.tw>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/1607570529-22341-3-git-send-email-ycllin@mxic.com.tw
Even if this is not supposed to happen, there is no reason to fail the
probe if it was explicitly requested to use no ECC engine at all (for
instance, during development). This condition is met by just
commenting out the error on the OOB free bytes count after the
assignation of an ECC engine if none was provided (any other situation
would error out much earlier anyway).
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20201001102014.20100-5-miquel.raynal@bootlin.com
Now that all the logic is available in the NAND core, let's use it
from the SPI-NAND core. Right now there is no functional change as the
default ECC engine for SPI-NANDs is set to 'on-die', but user can now
use software correction if they want to by just setting the right
properties in the DT.
Also note that the OOB layout handling is removed from the SPI-NAND
core as each ECC engine is supposed to handle it by it's own; users
should not be aware of that.
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20201001102014.20100-4-miquel.raynal@bootlin.com
This is done by default in the raw NAND core (nand_base.c) but was
missing in the SPI-NAND core. Without these two lines the ecc_strength
and ecc_step_size values are not exported to the user through sysfs.
Fixes: 7529df4652 ("mtd: nand: Add core infrastructure to support SPI NANDs")
Cc: stable@vger.kernel.org
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
The suffix was changed from "G" to "J" to classify between 1st generation
and 2nd generation serial NAND devices (which now belong to the Kioxia
brand).
As reference that's
1st generation device of 1Gbit product is "TC58CVG0S3HRAIG"
2nd generation device of 1Gbit product is "TC58CVG0S3HRAIJ".
The 8Gbit type "TH58CxG3S0HRAIJ" is new to Kioxia's serial NAND lineup and
the prefix was changed from "TC58" to "TH58".
Thus the functions were renamed from tc58cxgxsx_*() to tx58cxgxsxraix_*().
Signed-off-by: Yoshio Furuyama <ytc-mb-yfuruyama7@kioxia.com>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/0dedd9869569a17625822dba87878254d253ba0e.1584949601.git.ytc-mb-yfuruyama7@kioxia.com
Add SPINAND_HAS_CR_FEAT_BIT flag to identify the SPI NAND device with
the Continuous Read mode.
Some of the Micron SPI NAND devices have the "Continuous Read" feature
enabled by default, which does not fit the subsystem needs.
In this mode, the READ CACHE command doesn't require the starting column
address. The device always output the data starting from the first
column of the cache register, and once the end of the cache register
reached, the data output continues through the next page. With the
continuous read mode, it is possible to read out the entire block using
a single READ command, and once the end of the block reached, the output
pins become High-Z state. However, during this mode the read command
doesn't output the OOB area.
Hence, we disable the feature at probe time.
Signed-off-by: Shivamurthy Shastri <sshivamurthy@micron.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200311175735.2007-5-sshivamurthy@micron.com
Currently when marking a block, we use spinand_erase_op() to erase
the block before writing the marker to the OOB area. Doing so without
waiting for the operation to finish can lead to the marking failing
silently and no bad block marker being written to the flash.
In fact we don't need to do an erase at all before writing the BBM.
The ECC is disabled for raw accesses to the OOB data and we don't
need to work around any issues with chips reporting ECC errors as it
is known to be the case for raw NAND.
Fixes: 7529df4652 ("mtd: nand: Add core infrastructure to support SPI NANDs")
Cc: stable@vger.kernel.org
Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200218100432.32433-4-frieder.schrempf@kontron.de
For reading and writing the bad block markers, spinand->oobbuf is
currently used as a buffer for the marker bytes. During the
underlying read and write operations to actually get/set the content
of the OOB area, the content of spinand->oobbuf is reused and changed
by accessing it through spinand->oobbuf and/or spinand->databuf.
This is a flaw in the original design of the SPI NAND core and at the
latest from 13c15e07ee ("mtd: spinand: Handle the case where
PROGRAM LOAD does not reset the cache") on, it results in not having
the bad block marker written at all, as the spinand->oobbuf is
cleared to 0xff after setting the marker bytes to zero.
To fix it, we now just store the two bytes for the marker on the
stack and let the read/write operations copy it from/to the page
buffer later.
Fixes: 7529df4652 ("mtd: nand: Add core infrastructure to support SPI NANDs")
Cc: stable@vger.kernel.org
Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200218100432.32433-2-frieder.schrempf@kontron.de
Currently there are 3 different variants of read_id implementation:
1. opcode only. Found in GD5FxGQ4xF.
2. opcode + 1 addr byte. Found in GD5GxGQ4xA/E
3. opcode + 1 dummy byte. Found in other currently supported chips.
Original implementation was for variant 1 and let detect function
of chips with variant 2 and 3 to ignore the first byte. This isn't
robust:
1. For chips of variant 2, if SPI master doesn't keep MOSI low
during read, chip will get a random id offset, and the entire id
buffer will shift by that offset, causing detect failure.
2. For chips of variant 1, if it happens to get a devid that equals
to manufacture id of variant 2 or 3 chips, it'll get incorrectly
detected.
This patch reworks detect procedure to address problems above. New
logic do detection for all variants separatedly, in 1-2-3 order.
Since all current detect methods do exactly the same id matching
procedure, unify them into core.c and remove detect method from
manufacture_ops.
Tested on GD5F1GQ4UAYIG and W25N01GVZEIG.
Signed-off-by: Chuanhong Guo <gch981213@gmail.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200208074439.146296-1-gch981213@gmail.com
