| Message ID | 20230329-dt-cpu-header-cleanups-v1-0-581e2605fe47@kernel.org |
|---|---|
| Headers | show |
| Series | DT header disentangling, part 1 | expand |
On 29-03-23, 10:52, Rob Herring wrote: > Now that of_cpu_device_node_get() is defined in of.h, of_device.h is just > implicitly including other includes, and is no longer needed. Adjust the > include files with what was implicitly included by of_device.h (cpu.h and > of.h) and drop including of_device.h. > > Signed-off-by: Rob Herring <robh@kernel.org> > --- > Please ack and I will take the series via the DT tree. > --- > drivers/cpufreq/cpufreq-dt-platdev.c | 1 - > drivers/cpufreq/kirkwood-cpufreq.c | 2 +- > drivers/cpufreq/maple-cpufreq.c | 2 +- > drivers/cpufreq/pmac32-cpufreq.c | 2 +- > drivers/cpufreq/pmac64-cpufreq.c | 2 +- > drivers/cpufreq/qcom-cpufreq-hw.c | 4 ++-- > drivers/cpufreq/spear-cpufreq.c | 2 +- > drivers/cpufreq/tegra124-cpufreq.c | 1 - > drivers/cpufreq/tegra20-cpufreq.c | 2 +- > include/linux/cpufreq.h | 1 - > 10 files changed, 8 insertions(+), 11 deletions(-) Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
On 29-03-23, 10:52, Rob Herring wrote: > Now that of_cpu_device_node_get() is defined in of.h, of_device.h is just > implicitly including other includes, and is no longer needed. Adjust the > include files with what was implicitly included by of_device.h (cpu.h and > of.h) and drop including of_device.h. > > Signed-off-by: Rob Herring <robh@kernel.org> > --- > Please ack and I will take the series via the DT tree. > --- > drivers/opp/of.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/opp/of.c b/drivers/opp/of.c > index e55c6095adf0..63b126c6215e 100644 > --- a/drivers/opp/of.c > +++ b/drivers/opp/of.c > @@ -13,7 +13,7 @@ > #include <linux/cpu.h> > #include <linux/errno.h> > #include <linux/device.h> > -#include <linux/of_device.h> > +#include <linux/of.h> > #include <linux/pm_domain.h> > #include <linux/slab.h> > #include <linux/export.h> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
On 29/03/2023 17:52, Rob Herring wrote: > Removing include of cpu.h from of_device.h (included by of_platform.h) > causes an error in ingenic-timer: > > drivers/clocksource/ingenic-timer.c: In function ‘ingenic_tcu_init’: > drivers/clocksource/ingenic-timer.c:338:15: error: implicit declaration of function ‘cpuhp_setup_state’ > > The of_platform.h header is not necessary either, so it and of_address.h > can be dropped. > > Signed-off-by: Rob Herring <robh@kernel.org> > --- > Please ack and I will take the series via the DT tree. > --- Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
On 29/03/2023 17:52, Rob Herring wrote: > Now that of_cpu_device_node_get() is defined in of.h, of_device.h is just > implicitly including other includes, and is no longer needed. Adjust the > include files with what was implicitly included by of_device.h (cpu.h and > of.h) and drop including of_device.h. > > Signed-off-by: Rob Herring <robh@kernel.org> > --- > Please ack and I will take the series via the DT tree. Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
This is the first of a series of clean-ups to disentangle the DT includes. There's a decade plus old comment in of_device.h: #include <linux/of_platform.h> /* temporary until merge */ Who's this Grant person that wrote this? ;) It gets better. of_device.h also pulls in of.h, and of_platform.h includes of_device.h. So naturally, drivers include all combinations of those 3 headers and sometimes they actually need them. I started on fixing this years ago, but just dropping the circular includes and fixing all the fallout was massive and didn't sit well. Pulling in of_device.h in all the drivers that happen to call only of_device_get_match_data/of_match_device didn't seem great when the rest of of_device.h would never be needed. of_device.h being everything that works on a struct device is not a great split because several types of users deal with struct device. The better split seems to be by user (subsys driver vs. consumer) which several subsystems now do. For of_device.h, the users can primarily be split between bus implementations and device drivers. Device drivers also typically need of.h to read properties. So let's move of_device.h towards just bus related functions and move device driver related functions to of.h. This series is just the first step. It makes a couple of clean-ups to replace some includes with forward declarations. It moves of_device_get_match_data() and of_cpu_device_node_get() to of.h. The former move is transparent for now and preparation for the next series. The last part of the series updates drivers using of_cpu_device_node_get() and/or relying on the implicit cpu.h include which is removed in the last patch. Signed-off-by: Rob Herring <robh@kernel.org> --- Rob Herring (19): of: Make devtree_lock declaration private of: Move of_device_(add|register|unregister) to of_platform.h of: Move of_device_get_match_data() declaration of: Move CPU node related functions to their own file of: Drop unnecessary includes in headers ARM: sunxi: Drop of_device.h include ARM: cpuidle: Drop of_device.h include riscv: Add explicit include for cpu.h riscv: cacheinfo: Adjust includes to remove of_device.h cacheinfo: Adjust includes to remove of_device.h clocksource: ingenic: Add explicit include for cpuhotplug.h thermal: cpuidle_cooling: Adjust includes to remove of_device.h soc: mediatek: mtk-svs: Add explicit include for cpu.h cpufreq: Adjust includes to remove of_device.h cpufreq: sun50i: Add explicit include for cpu.h cpuidle: Adjust includes to remove of_device.h irqchip: loongson-eiointc: Add explicit include for cpuhotplug.h OPP: Adjust includes to remove of_device.h of: Drop cpu.h include from of_device.h arch/arm/kernel/cpuidle.c | 1 - arch/arm/mach-sunxi/mc_smp.c | 1 - arch/riscv/kernel/cacheinfo.c | 1 - arch/riscv/kernel/setup.c | 2 +- arch/sparc/include/asm/prom.h | 3 + drivers/base/cacheinfo.c | 2 +- drivers/clocksource/ingenic-timer.c | 3 +- drivers/cpufreq/cpufreq-dt-platdev.c | 1 - drivers/cpufreq/kirkwood-cpufreq.c | 2 +- drivers/cpufreq/maple-cpufreq.c | 2 +- drivers/cpufreq/pmac32-cpufreq.c | 2 +- drivers/cpufreq/pmac64-cpufreq.c | 2 +- drivers/cpufreq/qcom-cpufreq-hw.c | 4 +- drivers/cpufreq/spear-cpufreq.c | 2 +- drivers/cpufreq/sun50i-cpufreq-nvmem.c | 3 +- drivers/cpufreq/tegra124-cpufreq.c | 1 - drivers/cpufreq/tegra20-cpufreq.c | 2 +- drivers/cpuidle/cpuidle-psci.c | 1 - drivers/cpuidle/cpuidle-qcom-spm.c | 3 +- drivers/cpuidle/cpuidle-riscv-sbi.c | 2 +- drivers/cpuidle/dt_idle_states.c | 1 - drivers/irqchip/irq-loongson-eiointc.c | 5 +- drivers/of/Makefile | 2 +- drivers/of/base.c | 187 ----------------------------- drivers/of/cpu.c | 210 +++++++++++++++++++++++++++++++++ drivers/of/of_private.h | 1 + drivers/opp/of.c | 2 +- drivers/soc/mediatek/mtk-svs.c | 1 + drivers/thermal/cpuidle_cooling.c | 3 +- include/linux/cpufreq.h | 1 - include/linux/of.h | 28 +++-- include/linux/of_device.h | 24 +--- include/linux/of_platform.h | 10 +- 33 files changed, 261 insertions(+), 254 deletions(-) --- base-commit: fe15c26ee26efa11741a7b632e9f23b01aca4cc6 change-id: 20230329-dt-cpu-header-cleanups-c7bed8c0b352 Best regards,