Commit Graph

2 Commits

Author SHA1 Message Date
Laurentiu Mihalcea
5080cf6339 bus: imx-aipstz: allow creating pdevs for child buses
devm_of_platform_populate() passes a NULL as the bus OF match table
to the underlying of_platform_populate(), meaning child bus devices
of the AIPSTZ bridge will not have its children devices created. Since
some SoCs (e.g. i.MX8MP) use this particular setup (e.g. SPBA bus, which
is a child of AIPSTZ5 and has multiple child nodes), the driver needs to
support it.

Therefore, replace devm_of_platform_populate() with of_platform_populate()
and pass a reference to the bus OF match table to it. For now, the only
possible child buses are simple buses.

Since the usage of devres is dropped, the complementary operation of
of_platform_populate() needs to be called during the driver's removal.

Signed-off-by: Laurentiu Mihalcea <laurentiu.mihalcea@nxp.com>
Fixes: 796cba2dd4 ("bus: add driver for IMX AIPSTZ bridge")
Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Closes: https://lore.kernel.org/lkml/5029548.31r3eYUQgx@steina-w/#t
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
2025-07-11 16:32:08 +08:00
Laurentiu Mihalcea
796cba2dd4 bus: add driver for IMX AIPSTZ bridge
The secure AHB to IP Slave (AIPSTZ) bus bridge provides access control
configurations meant to restrict access to certain peripherals.
Some of the configurations include:

	1) Marking masters as trusted for R/W. Based on this
	(and the configuration of the accessed peripheral), the bridge
	may choose to abort the R/W transactions issued by certain
	masters.

	2) Allowing/disallowing write accesses to peripherals.

Add driver for this IP. Since there's currently no framework for
access controllers (and since there's currently no need for having
flexibility w.r.t the configurations) all this driver does is it
applies a relaxed, "default" configuration, in which all masters
are trusted for R/W.

Note that some instances of this IP (e.g: AIPSTZ5 on i.MX8MP) may be tied
to a power domain and may lose their configuration when the domain is
powered off. This is why the configuration has to be restored when the
domain is powered on.

Co-developed-by: Daniel Baluta <daniel.baluta@nxp.com>
Signed-off-by: Daniel Baluta <daniel.baluta@nxp.com>
Signed-off-by: Laurentiu Mihalcea <laurentiu.mihalcea@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
2025-07-01 22:23:21 +08:00