Acked-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Then we can get rid of ->issue_flush_fn() and all the driver private
implementations of that.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

init_dma_ali15x3() guarantees that hwif->dma_base will never be set for
m5229_revision < 0x20 so remove redundant m5229_revision >= 0x20 check from
init_hwif_common_ali15x3().

While at it remove incorrect comment.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Set hwif->atapi_dma/{ultra,mwdma}_mask and drive->autodma after checking that
->dma_base exists.  If ->dma_base is not set (== PCI BAR4 cannot be reserved)
then DMA hooks shouldn't be initialized or bad things will happen.

OTOH hwif->set_{pio,dma}_mode hooks should be set even if hwif->dma_base == 0.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Set hwif->ide_dma_{check,on} and hwif->autodma to 1 after checking that
->dma_base exists.  If ->dma_base is not set (== PCI BAR4 cannot be reserved)
then DMA hooks shouldn't be initialized or bad things will happen.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks
shouldn't be initialized or bad things will happen.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks
shouldn't be initialized or bad things will happen.
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Devices which don't set word 93 validation bit should be now handled by
ide-iops.c::ivb_list[] and for debugging purposes cable detection can be
completely overriden with "idex=ata66" parameter.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Need to probe slave device first to make it release PDIAG-
(this is required for correct device side cable detection).

Based on libata commit f31f0cc2.

Thanks to Craig for testing this patch.

Cc: Craig Block <chblock3@yahoo.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Convert {ide_hwif_t,ide_pci_device_t}->host_flag to be u16.

* Add IDE_HFLAG_POST_SET_MODE host flag to indicate the need to program 
  the host for the transfer mode after programming the device.  Set it
  in au1xxx-ide, amd74xx, cs5530, cs5535, pdc202xx_new, sc1200, pmac
  and via82cxxx host drivers.

* Add IDE_HFLAG_NO_SET_MODE host flag to indicate the need to completely
  skip programming of host/device for the transfer mode ("smart" hosts).
  Set it in it821x host driver and check it in ide_tune_dma().

* Add ide_set_pio_mode()/ide_set_dma_mode() helpers and convert all
  direct ->set_pio_mode/->speedproc users to use these helpers.

* Move ide_config_drive_speed() calls from ->set_pio_mode/->speedproc
  methods to callers.

* Rename ->speedproc method to ->set_dma_mode, make it void and update
  all implementations accordingly.

* Update ide_set_xfer_rate() comments.

* Unexport ide_config_drive_speed().

v2:
* Fix issues noticed by Sergei:
  - export ide_set_dma_mode() instead of moving ->set_pio_mode abuse wrt
    to setting DMA modes from sc1200_set_pio_mode() to do_special()
  - check IDE_HFLAG_NO_SET_MODE in ide_tune_dma()
  - check for (hwif->set_pio_mode) == NULL in ide_set_pio_mode()
  - check for (hwif->set_dma_mode) == NULL in ide_set_dma_mode()
  - return -1 from ide_set_{pio,dma}_mode() if ->set_{pio,dma}_mode == NULL
  - don't set ->set_{pio,dma}_mode on it821x in "smart" mode
  - fix build problem in pmac.c
  - minor fixes in au1xxx-ide.c/cs5530.c/siimage.c
  - improve patch description

Changes in behavior caused by this patch:
- HDIO_SET_PIO_MODE ioctl would now return -ENOSYS for attempts to change
  PIO mode if it821x controller is in "smart" mode
- removal of two debugging printk-s (from cs5530.c and sc1200.c)
- transfer modes 0x00-0x07 passed from user space may be programmed twice on
  the device (not really an issue since 0x00 is not supported correctly by
  any host driver ATM, 0x01 is not supported at all and 0x02-0x07 are invalid)
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Check ide_config_drive_speed() return value.

* While at also call ide_config_drive_speed() if the transfer mode is
  XFER_PIO_SLOW (this case happens iff the transfer mode has already been
  set on the device by ide-proc.c::set_xfer_rate()) and remove redundant
  setting of ->{init,current}_speed.

* Bump driver version.
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Set transfer mode on the device before programming the host controller for
the new timings (matches what auide_tune_chipset() is doing wrt DMA modes).
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Add "good DMA drives" hack for icside to ide-dma.c::ide_find_dma_mode()
  (in the long-term it should be either removed or generalized for all hosts).

* Use ide_tune_dma() in icside.c::icside_dma_check().

  This results in the following changes in behavior:
  - pre-EIDE SWDMA modes are now also respected
  - drive->autodma is checked instead of hwif->autodma
    (doesn't really matter as icside sets both to "1")

* Make ide-dma.c::__ide_dma_good_drive() static and drop "__" prefix.

Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Add missing initialization of hwif->autodma and drive->autodma to
  pmac_ide_setup_dma().

* Use ide_tune_dma() in pmac_ide_dma_check().

While at it:

* Fix pmac_ide_dma_check() return value if DMA mode is not programmed
  (should be "-1" otherwise ide_set_dma() will try to enable DMA).

* Remove unnecessary drive->using_dma fiddling (->dma_off_quietly is always
  called before ide_set_dma() call and ide_set_dma() calls ->ide_dma_on if
  ->ide_dma_check returns "0").

v2:
* No reason to blacklist all ide_floppy devices and the old code was always
  enabling DMA anyway (without even programming controller/device if the
  device was ide_floppy).

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Use ide_config_drive_speed() instead of pmac_ide_do_setfeature() and remove
the latter, also  ide-iops.c::__ide_wait_stat() could be static again.

Since for IDE PMAC host driver IDE_CONTROL_REG is always true, device's
->quirk_list is always zero and ->ide_dma_host_{on,off} are nops than
the only changes in behavior are:

* if PIO mode is set then ->dma_off_queitly is called to disable DMA

* if setting transfer mode fails ide_dump_status() is called to dump status

v2:
* IDE PMAC controllers allow separate PIO and DMA timings and PPC userland
  depends on this fact, and calls "hdparm -p" without calling "hdparm -d".

  Therefore to compensate for DMA being disabled by ide_config_drive_speed()
  for PIO modes:

  - add IDE_HFLAG_SET_PIO_MODE_KEEP_DMA flag and set it in PMAC host driver

  - add handling of the new flag to ide-io.c::do_special()

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Upper layers are responsible for controlling nIEN so don't clear nIEN after
command execution in pmac_ide_do_setfeature().

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Use __ide_wait_stat() instead of wait_for_ready() in pmac_ide_do_setfeature().

While at it do following changes to match __ide_wait_stat() call in
ide_config_drive_speed():

* Wait WAIT_CMD time (20 sec) instead of 2 sec for device to clear BUSY_STAT.

* Check DRQ_STAT bit (shouldn't be set for good device status).

Also remove no longer needed wait_for_ready() from ide-iops.c.
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Don't check for good device status before executing the command in
pmac_ide_do_setfeature() (ide_config_drive_speed() doesn't do this).

It is a job of upper layers to guarantee that the device is ready to
accept new command before we get here.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Split off checking of the status register from ide_wait_stat() to
  __ide_wait_stat() helper.

* Use the new helper in ide_config_drive_speed().  The only change in the
  functionality is that the function now fails if after 20 sec (WAIT_CMD)
  device is still busy (BUSY_STAT bit is set) while previously instead of
  failing the function continued with checking for the correct device status
  (which would give the device additional 10 usec to clear BUSY_STAT bit).

* Remove stale comment for ide_config_drive_speed().

* Remove duplicate comment for ide_wait_stat() from <linux/ide.h>.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Fix pmac_ide_dma_check() to use pmac_ide_tune_chipset() and remove no longer
  necessary pmac_ide_{m,u}dma_enable().

* While at it remove some dead code from pmac_ide_dma_check() (leftovers from
  conversion to use ide_max_dma_mode()).

There should be no functionality changes caused by this patch.

v2:
* Fix compile by replacing "id" with "drive->id" in pmac_ide_dma_check()
  (Noticed by Ben).

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

pmac_ide_do_setfeature() contains matching nIEN setting/clearing so this
Device Control register messing in pmac_ide_dma_check() is totally unnecessary.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Move adjusting of cycle time for devices providing explicit DMA cycle time
  from pmac_ide_mdma_enable() to set_timings_mdma().

* Remove no longer needed drive_cycle_time argument.

* BUG() if unsupported speed argument value is passed (shouldn't happen).

* Matching access/recovery timings always exist so remove redundant check.

* Make set_timings_mdma() void.

* Update pmac_ide_tune_chipset()'s comment.
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Don't check check for pmif == NULL (it should never be NULL if we got here).

* Make a local copy of the timings and set the pmif->timings[] only after
  setting the transfer mode on the device (otherwise SELECT_DRIVE() call in
  pmac_ide_do_setfeature() will program new timings before the transfer mode
  is set on the device - this was pointed out by Sergei).  This change makes
  pmac_ide_tune_chipset() behavior match this of pmac_ide_{m,u}dma_enable().
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

kauai_lookup_timing() should always return non-zero return value:

* BUG() in kauai_lookup_timing() if the timing info cannot be found.

* Remove code checking for zero return value from all callers.
Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

This patch removes the unused EXPORT_SYMBOL_GPL(ide_acpi_set_state)
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

We need to set hwif->chipset or IDE PCI host drivers may try to claim
our ide_hwifs[] slot.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

This changes the uevent buffer functions to use a struct instead of a
long list of parameters. It does no longer require the caller to do the
proper buffer termination and size accounting, which is currently wrong
in some places. It fixes a known bug where parts of the uevent
environment are overwritten because of wrong index calculations.

Many thanks to Mathieu Desnoyers for finding bugs and improving the
error handling.
Signed-off-by: NKay Sievers <kay.sievers@vrfy.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Use ->set_pio_mode method to program PIO modes in ide_set_xfer_rate()
(the only place which used ->speedproc to program PIO modes) and remove
handling of PIO modes from all ->speedproc implementations.

v2:
* Fix pmac_ide_tune_chipset() comment.

There should be no functionality changes caused by this patch.
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Return failure in ->speedproc method for unsupported/invalid transfer
  modes passed from user-space (fixes theoretical OOPS in ali_tune_pio()
  and/or setting random PIO timings on host controller + disabling UDMA
  bit + setting unsupported/invalid transfer mode on the device).

* Don't disable UDMA bit when programming PIO modes.

* Add FIXME about DMA timings never being set.

* Bump driver version.
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Remember to select PIO data transfer (with IORDY monitored) in sil_tune_pio()
  (->set_pio_mode method) so the controller is always programmed correctly for
  PIO transfers (this is important if DMA is not going to be used).

* Don't set DMA/UDMA timings for PIO modes in siimage_tune_chipset().

* Bump driver version.
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

There is no need to do it in cs5520_tune_chipset() (->speedproc method)
since it is correctly handled by cs5520_dma_on() (->ide_dma_on method).
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

ide_config_drive_speed() called by sc1200_set_xfer_mode() already gives
a meaningful warning message in case of failure.
Acked-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* Add { 0, 0 } entry to {kauai,shasta}_pio_timings[] so kauai_lookup_timing()
  always returns a valid PIO timing (fixes PIO timing not being set for devices
  with minimum PIO cycle <= 120ns).

* Add setting transfer mode on the device to pmac_ide_set_pio_mode().

* Fix pmac_ide_set_pio() to always program chipset for given PIO timing instead
  of only when the device we want to program PIO timing for is the currently
  selected one.

* Now that pmac_ide_set_pio() is fixed there is no need to set transfer mode
  on the device and program chipset for PIO in pmac_ide_tune_chipset()
  (returning 0 == success is not entirely correct but is OK for now since
  the upper layers are only checking ->speedproc return value for DMA modes).

v2:
* s/speed/XFER_PIO_0 + pio/ in pmac_ide_set_pio_mode() so it actually compiles.

* Removal of kauai_lookup_timing() return value checking went to separate patch.

v3:
* Use XFER_PIO_0 not XFER_PIO. (Noticed by Ben)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

* All other implementations of ->speedproc return zero on success
  and non-zero on failure.  Currently it doesn't matter for icside host
  driver and isn't a bug per se since:

  - ide_set_xfer_rate() return value is ignored by all IDE core users

  - icside doesn't (yet!) use ide_tune_dma() in icside_dma_check()

  but sooner or later we will need to fix anyway - so lets do it now.

* icside_set_speed() happily accepts unsupported transfer modes which
  results in drive->drive_data being set to the maximum value (480)
  and drive->current_speed being set to the unsupported transfer mode.

  Fix it.

v2:
* The initial version of the patch was broken because it didn't take into
  the account (the different from usual) return values of icside_set_speed()
  (Noticed by Russell).

v3:
* Remove no longer needed initialization/checking of cycle_time
  (Noticed by Sergei).

* No need to set drive->drive_data if DMA is not going to be used
  (Noticed by Sergei).

* Remove incorrect setting of drive->current_speed
  (Noticed by Sergei).

* Move ide_config_drive_speed() at the end of icside_set_speed().

v4:
* If DMA mode is not found in icside_dma_check() then just return "-1" and
  don't call icside_set_speed() (v3 got it wrong and "1" was returned instead).

v5:
* Return "-1"/"0" in icside_set_speed() instead of icside_dma_check() return
  value (just like it was before this patch).

Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>