| Message ID | 20171207141413.2008240-1-arnd@arndb.de |
|---|---|
| State | New |
| Headers | show |
| Series | drm/i915: add FTRACE dependency for DRM_I915_TRACE_GEM | expand |
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index fa36491495b1..1a1b9732f657 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -18,6 +18,7 @@ config DRM_I915_WERROR config DRM_I915_DEBUG bool "Enable additional driver debugging" depends on DRM_I915 + depends on FTRACE # for DRM_I915_TRACE_GEM select DEBUG_FS select PREEMPT_COUNT select I2C_CHARDEV @@ -53,6 +54,7 @@ config DRM_I915_DEBUG_GEM config DRM_I915_TRACE_GEM bool "Insert extra ftrace output from the GEM internals" + depends on FTRACE select TRACING default n help
The new trace option gratuitously added a 'select TRACING' statement, which now causes build failures in other code that assumed tracepoints were only available with FTRACE: ERROR: "__tracepoint_ucsi_command" [drivers/usb/typec/ucsi/typec_ucsi.ko] undefined! ERROR: "__tracepoint_ucsi_register_port" [drivers/usb/typec/ucsi/typec_ucsi.ko] undefined! ERROR: "__tracepoint_ucsi_notify" [drivers/usb/typec/ucsi/typec_ucsi.ko] undefined! ERROR: "__tracepoint_ucsi_reset_ppm" [drivers/usb/typec/ucsi/typec_ucsi.ko] undefined! ERROR: "__tracepoint_ucsi_run_command" [drivers/usb/typec/ucsi/typec_ucsi.ko] undefined! drivers/usb/dwc3/gadget.o: In function `__dwc3_prepare_one_trb': gadget.c:(.text+0x1c5): undefined reference to `__tracepoint_dwc3_prepare_trb' drivers/usb/dwc3/gadget.o: In function `__dwc3_cleanup_done_trbs': gadget.c:(.text+0x3f0): undefined reference to `__tracepoint_dwc3_complete_trb' drivers/usb/dwc3/gadget.o: In function `dwc3_gadget_ep_free_request': gadget.c:(.text+0x666): undefined reference to `__tracepoint_dwc3_free_request' This adds an explicit FTRACE dependency here, to ensure this is already the case. This matches what the other drivers have that select TRACING. Generally speaking, there is a bigger problem with CONFIG_DRM_I915_DEBUG though, it selects several other partially related symbols (DEBUGFS, I2C_CHARDEV, PREEMPT_COUNT, X86_MSR, etc that are each user-visible and that other symbols in turn depend on. This can easily lead to circular dependencies and should be avoided. I tried turning those all into 'depends on', which is normally a good strategy, but that seems to completely defeat the intention of CONFIG_DRM_I915_DEBUG. It might be better to just remove this completely, possibly replace it with a Kconfig fragment. Fixes: bccd3b831185 ("drm/i915: Use trace_printk to provide a death rattle for GEM") Signed-off-by: Arnd Bergmann <arnd@arndb.de> --- drivers/gpu/drm/i915/Kconfig.debug | 2 ++ 1 file changed, 2 insertions(+) -- 2.9.0