a simple hardware detector for lattency as well as throughput

The rfc patch reuses some code and idea from jcm's hwlat_detector but
target for a broader problem that sometime we need to run a simple few minutes
hardware test to understand if there is any hardware latency as well as
throughput problem exposed on bare metal or left behind by BIOS or
interfered by SMI. Currently the patch test hardware features (tsc, tsc freq, and rdrandom which is new instruction to get random number) in stop_machine context. I will add more if it looks interesting and useful to guys especially for those who want to directly play with new hardware functions on bare metal. Any comments are wellcome.

--

 Kconfig   |    7
 Makefile  |    2
 hw_test.c |  954
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 963 insertions(+)

index c779509..f66ad56 100644
@@ -123,6 +123,13 @@ config IBM_ASM
 	  for information on the specific driver level and support statement
 	  for your IBM server.
 
+config HW_TEST
+	tristate "Testing module to detect hardware lattency and throughput"
+	depends on DEBUG_FS
+	depends on RING_BUFFER
+	depends on X86
+	default m
+
 config PHANTOM
 	tristate "Sensable PHANToM (PCI)"
 	depends on PCI

index 3e1d801..ec1de86 100644
@@ -48,4 +48,6 @@ obj-y				+= lis3lv02d/
 obj-y				+= carma/
 obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o
 obj-$(CONFIG_ALTERA_STAPL)	+=altera-stapl/
+obj-$(CONFIG_HW_TEST)		+= hw_test.o
+
 obj-$(CONFIG_MAX8997_MUIC)	+= max8997-muic.o

Hey thanks. This is totally something I hoped would eventually go upstream, but I never got around to cleaning it up enough for mass consumption beyond the use case we had in mind (beating certain folks over the head when they have "value add" in BIOS code that causes huge SMIs, and the like, for RT).

Did anyone ever get back to you on this one? I never saw any followup. I will be happy to do some testing and help you get this mainlined.

Jon.

So far you are the only one. :-)
If you can find a maintainer for it, and find a way into mainline, We probably can make it become a popular tool for hardware enabling.

/l