Bug 5431
Summary: | C2,C3 on SMP systems by AMD | ||
---|---|---|---|
Product: | ACPI | Reporter: | Stuart Rowan (kernel-bugs) |
Component: | Power-Processor | Assignee: | Len Brown (lenb) |
Status: | REJECTED INVALID | ||
Severity: | normal | CC: | acpi-bugzilla |
Priority: | P2 | ||
Hardware: | i386 | ||
OS: | Linux | ||
Kernel Version: | 2.6.13.3 | Subsystem: | |
Regression: | --- | Bisected commit-id: | |
Attachments: | "acpidump -o acpidump.txt" |
Description
Stuart Rowan
2005-10-13 06:56:31 UTC
Interesting patch, but it is a chip-set specific driver, not generic ACPI code, or even related to the ACPI sub-system. If the BIOS really supports SMP C2 and C3 on these systems, then there should not be a chip-set specific driver necessary. Please make sure you've got the latest BIOS for your board and attach the output from acpidump, available in pmtools here: http://ftp.kernel.org/pub/linux/kernel/people/lenb/acpi/utils/ note also, that the C8 thing it the Linux limit, corresponding the a simple array size, and does not reflect a hardware limit. Please paste in the output from /proc/acpi/processor/<pick a cpu>/power and lets see what ACPI thinks of what this board offers. It thinks C1 is possible! stuart@strr:~$ cat /proc/acpi/processor/CPU0/power active state: C1 max_cstate: C8 bus master activity: 00000000 states: *C1: type[C1] promotion[--] demotion[--] latency[000] usage[00005129] Created attachment 6298 [details]
"acpidump -o acpidump.txt"
acpidump as requested.
BIOS sets C2 and C3 latency to 0x65 (101) and 0x3e9 (1001) respectively, or greater than allowed max latency for those states -- 100 and 1000. This is used to mark these states as *disabled*. Closing the bug as INVALID |