linux-toradex.git/include/linux/device.h, branch v6.12-rc4

dma-mapping: clearly mark DMA ops as an architecture feature

2024-09-04T04:08:51+00:00

DMA ops are a helper for architectures and not for drivers to override
the DMA implementation.

Unfortunately driver authors keep ignoring this.  Make the fact more
clear by renaming the symbol to ARCH_HAS_DMA_OPS and having the two drivers
overriding their dma_ops depend on that.  These drivers should probably be
marked broken, but we can give them a bit of a grace period for that.

Signed-off-by: Christoph Hellwig 
Reviewed-by: Thomas Gleixner 
Acked-by: Sakari Ailus  # for IPU6
Acked-by: Robin Murphy

dma-mapping: direct calls for dma-iommu

2024-08-22T04:18:11+00:00

Directly call into dma-iommu just like we have been doing for dma-direct
for a while.  This avoids the indirect call overhead for IOMMU ops and
removes the need to have DMA ops entirely for many common configurations.

Signed-off-by: Leon Romanovsky 
Signed-off-by: Leon Romanovsky 
Acked-by: Greg Kroah-Hartman 
Acked-by: Robin Murphy 
Signed-off-by: Christoph Hellwig

driver core: make [device_]driver_attach take a const *

2024-06-20T10:51:42+00:00

Change device_driver_attach() and driver_attach() to take a const * to
struct device driver as neither of them modify the structure at all.

Also, for some odd reason, drivers/dma/idxd/compat.c had a duplicate
external reference to device_driver_attach(), so remove that to fix up
the build, it should never have had that there in the first place.

Cc: Rafael J. Wysocki 
Cc: Fenghua Yu 
Cc: Dave Jiang 
Cc: Vinod Koul 
Cc: Andy Shevchenko 
Cc: Petr Tesarik 
Cc: Alexander Lobakin 
Cc: dmaengine@vger.kernel.org
Link: https://lore.kernel.org/r/2024061401-rasping-manger-c385@gregkh
Signed-off-by: Greg Kroah-Hartman

Merge tag 'v6.10-rc4' into driver-core-next

2024-06-17T06:33:41+00:00

We need the driver core and sysfs fixes in here to build on top of.

Signed-off-by: Greg Kroah-Hartman

driver core: device.h: Group of_node handling declarations and definitions

2024-06-04T16:04:36+00:00

There are a few of_node related APIs defined in the driver core.
Group the respective declarations and definitions in the header.
There is no functional change.

Signed-off-by: Andy Shevchenko 
Link: https://lore.kernel.org/r/20240531145129.1506733-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman

driver core: remove devm_device_add_groups()

2024-06-04T13:53:36+00:00

There is no more in-kernel users of this function, and no driver should
ever be using it, so remove it from the kernel.

Acked-by: Dmitry Torokhov 
Acked-by: "Rafael J. Wysocki" 
Link: https://lore.kernel.org/r/20230704131715.44454-8-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman

Merge tag 'driver-core-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

2024-05-22T19:13:40+00:00

Pull driver core updates from Greg KH:
 "Here is the small set of driver core and kernfs changes for 6.10-rc1.

  Nothing major here at all, just a small set of changes for some driver
  core apis, and minor fixups. Included in here are:

   - sysfs_bin_attr_simple_read() helper added and used

   - device_show_string() helper added and used

  All usages of these were acked by the various maintainers. Also in
  here are:

   - kernfs minor cleanup

   - removed unused functions

   - typo fix in documentation

   - pay attention to sysfs_create_link() failures in module.c finally

  All of these have been in linux-next for a very long time with no
  reported problems"

* tag 'driver-core-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  device property: Fix a typo in the description of device_get_child_node_count()
  kernfs: mount: Remove unnecessary ‘NULL’ values from knparent
  scsi: Use device_show_string() helper for sysfs attributes
  platform/x86: Use device_show_string() helper for sysfs attributes
  perf: Use device_show_string() helper for sysfs attributes
  IB/qib: Use device_show_string() helper for sysfs attributes
  hwmon: Use device_show_string() helper for sysfs attributes
  driver core: Add device_show_string() helper for sysfs attributes
  treewide: Use sysfs_bin_attr_simple_read() helper
  sysfs: Add sysfs_bin_attr_simple_read() helper
  module: don't ignore sysfs_create_link() failures
  driver core: Remove unused platform_notify, platform_notify_remove

dma: fix DMA sync for drivers not calling dma_set_mask*()

2024-05-09T17:00:29+00:00

There are several reports that the DMA sync shortcut broke non-coherent
devices.
dev->dma_need_sync is false after the &device allocation and if a driver
didn't call dma_set_mask*(), it will still be false even if the device
is not DMA-coherent and thus needs synchronizing. Due to historical
reasons, there's still a lot of drivers not calling it.
Invert the boolean, so that the sync will be performed by default and
the shortcut will be enabled only when calling dma_set_mask*().

Reported-by: Steven Price 
Closes: https://lore.kernel.org/lkml/010686f5-3049-46a1-8230-7752a1b433ff@arm.com
Reported-by: Marek Szyprowski 
Closes: https://lore.kernel.org/lkml/46160534-5003-4809-a408-6b3a3f4921e9@samsung.com
Fixes: f406c8e4b770. ("dma: avoid redundant calls for sync operations")
Signed-off-by: Alexander Lobakin 
Signed-off-by: Christoph Hellwig 
Tested-by: Steven Price 
Tested-by: Marek Szyprowski

dma: avoid redundant calls for sync operations

2024-05-07T11:29:53+00:00

Quite often, devices do not need dma_sync operations on x86_64 at least.
Indeed, when dev_is_dma_coherent(dev) is true and
dev_use_swiotlb(dev) is false, iommu_dma_sync_single_for_cpu()
and friends do nothing.

However, indirectly calling them when CONFIG_RETPOLINE=y consumes about
10% of cycles on a cpu receiving packets from softirq at ~100Gbit rate.
Even if/when CONFIG_RETPOLINE is not set, there is a cost of about 3%.

Add dev->need_dma_sync boolean and turn it off during the device
initialization (dma_set_mask()) depending on the setup:
dev_is_dma_coherent() for the direct DMA, !(sync_single_for_device ||
sync_single_for_cpu) or the new dma_map_ops flag, %DMA_F_CAN_SKIP_SYNC,
advertised for non-NULL DMA ops.
Then later, if/when swiotlb is used for the first time, the flag
is reset back to on, from swiotlb_tbl_map_single().

On iavf, the UDP trafficgen with XDP_DROP in skb mode test shows
+3-5% increase for direct DMA.

Suggested-by: Christoph Hellwig  # direct DMA shortcut
Co-developed-by: Eric Dumazet 
Signed-off-by: Eric Dumazet 
Signed-off-by: Alexander Lobakin 
Signed-off-by: Christoph Hellwig

driver core: Add device_show_string() helper for sysfs attributes

2024-05-04T15:37:03+00:00

For drivers wishing to expose an unsigned long, int or bool at a static
memory location in sysfs, the driver core provides ready-made helpers
such as device_show_ulong() to be used as ->show() callback.

Some drivers need to expose a string and so far they all provide their
own ->show() implementation.  arch/powerpc/perf/hv-24x7.c went so far
as to create a device_show_string() helper but kept it private.

Make it public for reuse by other drivers.  The pattern seems to be
sufficiently frequent to merit a public helper.

Add a DEVICE_STRING_ATTR_RO() macro in line with the existing
DEVICE_ULONG_ATTR() and similar macros to ease declaration of string
attributes.

Signed-off-by: Lukas Wunner 
Acked-by: Michael Ellerman 
Link: https://lore.kernel.org/r/2e3eaaf2600bb55c0415c23ba301e809403a7aa2.1713608122.git.lukas@wunner.de
Signed-off-by: Greg Kroah-Hartman