There are cases when the bootloader provides information to the kernel
in both ACPI and DTB, not interchangeably. One such use case is virtual
machines in Android. When running on x86, the Android Virtualization
Framework (AVF) boots VMs with ACPI like it is usually done on x86 (i.e.
the virtual LAPIC, IOAPIC, HPET, PCI MMCONFIG etc are described in ACPI)
but also passes various AVF-specific boot parameters in DTB. This allows
reusing the same implementations of various AVF components on both
arm64 and x86.
Commit 7b937cc243 ("of: Create of_root if no dtb provided by firmware")
removed the possibility to do that, since among other things
it introduced forcing emptying the bootloader-provided DTB if ACPI is
enabled (probably assuming that if ACPI is available, a DTB can only be
useful for applying overlays to it afterwards, for testing purposes).
So restore this possibility. Instead of completely preventing using ACPI
and DT together, rely on arch-specific setup code to prevent using both
to set up the same things (see various acpi_disabled checks under arch/).
Fixes: 7b937cc243 ("of: Create of_root if no dtb provided by firmware")
Signed-off-by: Dmytro Maluka <dmaluka@chromium.org>
Link: https://lore.kernel.org/r/20250105172741.3476758-3-dmaluka@chromium.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
There are some patches with long lines as a result of checkpatch
enforcing 100, not 80, but checkpatch is only a tool not a coding style.
The Linux Kernel Coding Style is still clear here on preferred limit.
Mentioned preferred style of wrapping long lines in DTS, based on Linux
Kernel Coding Style.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250118102247.18257-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
of_parse_phandle_with_args_map() defines array @dummy_mask and @dummy_pass
these two arrays only need @MAX_PHANDLE_ARGS elements separately, but they
actually have (@MAX_PHANDLE_ARGS + 1) elements, One extra element doesn't
hurt anything except for some stack usage.
Fix by using (@MAX_PHANDLE_ARGS - 1) as max element index in initializer.
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Link: https://lore.kernel.org/r/20250114-of_core_fix-v5-3-b8bafd00a86f@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
For child node of /reserved-memory, its property 'reg' may contain
multiple regions, but fdt_scan_reserved_mem_reg_nodes() only takes
into account the first region, and miss remaining regions.
But there are no simple approach to fix it, so give user warning
message when miss remaining regions.
Fixes: 8a6e02d0c0 ("of: reserved_mem: Restructure how the reserved memory regions are processed")
Cc: stable@vger.kernel.org
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20250114-of_core_fix-v5-2-b8bafd00a86f@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
The device full name is embedded trace extension. There is no good fit
in generic names list for the embedded trace extension. ETE is abbreviation
of embedded trace extension and the number is the CPU number that ete is
associated. Change the pattern of the node name as it won't affect any
device tree node as of now.
Signed-off-by: Mao Jinlong <quic_jinlmao@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20250107090031.3319-2-quic_jinlmao@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
The use of of_property_read_bool() for non-boolean properties is
deprecated. The primary use of it was to test property presence, but
that has been replaced in favor of of_property_present(). With those
uses now fixed, add a warning to discourage new ones.
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20250109-dt-type-warnings-v1-2-0150e32e716c@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
The fwnode/device property API currently implement
(fwnode|device)_property_read_bool() with (fwnode|device)_property_present().
That does not allow having different behavior depending on the backend.
Specifically, the usage of (fwnode|device)_property_read_bool() on
non-boolean properties is deprecated on DT. In order to add a warning
on this deprecated use, these 2 APIs need separate ops for the backend.
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20250109-dt-type-warnings-v1-1-0150e32e716c@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
early_init_dt_alloc_reserved_memory_arch() will free address @base when
suffers memblock_mark_nomap() error, but it still makes kmemleak ignore
the freed address @base via kmemleak_ignore_phys().
That is unnecessary, besides, also causes unnecessary warning messages:
kmemleak_ignore_phys()
-> make_black_object()
-> paint_ptr()
-> kmemleak_warn() // warning message here.
Fix by avoiding kmemleak_ignore_phys() when suffer the error.
Fixes: 658aafc813 ("memblock: exclude MEMBLOCK_NOMAP regions from kmemleak")
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Link: https://lore.kernel.org/r/20250109-of_core_fix-v4-10-db8a72415b8c@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
API of_parse_phandle_with_args_map() will use wrong input for nexus node
Nexus_2 as shown below:
Node_1 Nexus_1 Nexus_2
&Nexus_1,arg_1 -> arg_1,&Nexus_2,arg_2' -> &Nexus_2,arg_2 -> arg_2,...
map-pass-thru=<...>
Nexus_1's output arg_2 should be used as input of Nexus_2, but the API
wrongly uses arg_2' instead which != arg_2 due to Nexus_1's map-pass-thru.
Fix by always making @match_array point to @initial_match_array into
which to store nexus output.
Fixes: bd6f2fd5a1 ("of: Support parsing phandle argument lists through a nexus node")
Cc: stable@vger.kernel.org
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Link: https://lore.kernel.org/r/20250109-of_core_fix-v4-1-db8a72415b8c@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Convert socfpga-system.txt to altr,socfpga-sys-mgr.yaml and move to
soc directory.
Add platform names in description for clarity. ARM(32-bit) platforms
Cyclone5, Arria5 and Arria10 is using "altr,sys-mgr" compatible,
while ARM64 is using "altr,sys-mgr-s10" compatible.
Removed "cpu1-start-addr" for ARM64 as it is not required.
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Link: https://lore.kernel.org/r/20250107105129.2784203-1-niravkumar.l.rabara@intel.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Normal practice is examples only show what the binding document defines
and doesn't include consumers in a provider example (or vice-versa). The
"qca,ddr-wb-channel-interrupts" and "qca,ddr-wb-channels" properties are
also not yet documented by a schema, so avoid (not yet enabled) warnings
on them by dropping the interrupt-controller node from the example.
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20250103212448.2852884-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
of_find_node_opts_by_path() fails to find OF device node when its
@path parameter have pattern below:
"alias-name/node-name-1/.../node-name-N:options".
The reason is that alias name length calculated by the API is wrong, as
explained by example below:
"testcase-alias/phandle-tests/consumer-a:testaliasoption".
^ ^ ^
0 14 39
The right length of alias 'testcase-alias' is 14, but the result worked
out by the API is 39 which is obvious wrong.
Fix by using index of either '/' or ':' as the length who comes earlier.
Fixes: 75c28c09af ("of: add optional options parameter to of_find_node_by_path()")
Cc: stable@vger.kernel.org
Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Link: https://lore.kernel.org/r/20241216-of_core_fix-v2-1-e69b8f60da63@quicinc.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
The i.MX35 General Purpose Timer is compatible with i.MX31.
Document the fsl,imx35-gpt compatible.
This fixes the following dt-schema warning:
timer@53f90000: compatible: 'oneOf' conditional failed, one must be fixed:
['fsl,imx35-gpt', 'fsl,imx31-gpt'] is too long
'fsl,imx1-gpt' was expected
'fsl,imx21-gpt' was expected
'fsl,imx27-gpt' was expected
'fsl,imx31-gpt' was expected
'fsl,imx35-gpt' is not one of ['fsl,imx25-gpt', 'fsl,imx50-gpt', 'fsl,imx51-gpt', 'fsl,imx53-gpt', 'fsl,imx6q-gpt']
'fsl,imx6dl-gpt' was expected
'fsl,imx35-gpt' is not one of ['fsl,imx6sl-gpt', 'fsl,imx6sx-gpt', 'fsl,imx8mp-gpt', 'fsl,imxrt1050-gpt', 'fsl,imxrt1170-gpt']
'fsl,imx35-gpt' is not one of ['fsl,imx6ul-gpt', 'fsl,imx7d-gpt']
'fsl,imx6sx-gpt' was expected
Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20241202132147.587799-2-festevam@gmail.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
imx7s.dtsi correctly describes the GPT node as:
compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
Document the fallback compatible to be "fsl,imx6dl-gpt" in the bindings.
This fixes the following dt-schema warnings:
timer@302f0000: compatible: 'oneOf' conditional failed, one must be fixed:
['fsl,imx7d-gpt', 'fsl,imx6dl-gpt'] is too long
'fsl,imx1-gpt' was expected
'fsl,imx21-gpt' was expected
'fsl,imx27-gpt' was expected
'fsl,imx31-gpt' was expected
'fsl,imx7d-gpt' is not one of ['fsl,imx25-gpt', 'fsl,imx50-gpt', 'fsl,imx51-gpt', 'fsl,imx53-gpt', 'fsl,imx6q-gpt']
'fsl,imx6dl-gpt' was expected
'fsl,imx7d-gpt' is not one of ['fsl,imx6sl-gpt', 'fsl,imx6sx-gpt', 'fsl,imx8mp-gpt', 'fsl,imxrt1050-gpt', 'fsl,imxrt1170-gpt']
'fsl,imx6sx-gpt' was expected
Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20241202132147.587799-1-festevam@gmail.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
