Quieten cache information at boot
PATCH 1/1 Quieten cache information at boot
After 6 years the ppc64 kernel still thinks its important to tell me my cache line size is 0x80 bytes. I think most people who care know that by now. The rest probably cant even understand the hex output.
Since we might have misconfigured firmware or cpus that have a linesize that isnt 128 bytes, I still print it out for those cases. If people would prefer to remove it completely, lets do it.
Also for lpar remove the htab_address printout since its not used.
Anton
ppc64 boot log usability expert
---
arch/powerpc/kernel/setup_64.c +8 -5
@@ -426,11 +426,14 @@ void __init setup_system(void)printk ("-----------------------------------------------------\n" );printk ("ppc64_pft_size = 0x%lx\n" , ppc64_pft_size);printk ("physicalMemorySize = 0x%lx\n" ,lmb_phys_mem_size ()); -printk ("ppc64_caches.dcache_line_size = 0x%x\n" , - ppc64_caches.dline_size); -printk ("ppc64_caches.icache_line_size = 0x%x\n" , - ppc64_caches.iline_size); -printk ("htab_address = 0x%p\n" , htab_address); +if (ppc64_caches.dline_size !=0x80 ) +printk ("ppc64_caches.dcache_line_size = 0x%x\n" , + ppc64_caches.dline_size); +if (ppc64_caches.iline_size !=0x80 ) +printk ("ppc64_caches.icache_line_size = 0x%x\n" , + ppc64_caches.iline_size); +if (htab_address) +printk ("htab_address = 0x%p\n" , htab_address);printk ("htab_hash_mask = 0x%lx\n" , htab_hash_mask);#if PHYSICAL_START >0 printk ("physical_start = 0x%x\n" ,PHYSICAL_START );
Quoted 8 lines · Anton Blanchard
After 6 years the ppc64 kernel still thinks its important to tell me my cache line size is
0x80bytes. I think most people who care know that by now. The rest probably cant even understand the hex output.Since we might have misconfigured firmware or cpus that have a linesize that isnt 128 bytes, I still print it out for those cases. If people would prefer to remove it completely, lets do it.
Let's just remove it completely. I have yet to see a bug because of it, and we have 0x40 byte cache lines.
If anything, compare firmware setting to cputable one and print a warning.
Should maybe give them loglevels too, since you're touching them? I suggest KERN_DEBUG -- if needed it's there in dmesg, and if you need it on the console you can just add "debug" to the kernel command line.
-Olof
Hi,
Quoted 2 lines
Let's just remove it completely. I have yet to see a bug because of it, and we have
0x40byte cache lines.
Yeah I completely support killing it too :)
Quoted 5 lines
If anything, compare firmware setting to cputable one and print a warning.
Should maybe give them loglevels too, since you're touching them? I suggest
KERN_DEBUG-- if needed it's there in dmesg, and if you need it on the console you can just add "debug" to the kernel command line.
I started playing with loglevels but theres some ordering issues since the options to change loglevel (eg the "debug" boot option) doesnt get parsed until later in a __setup function.
Anton
Quoted 6 lines · Olof Johansson
Quoted 5 lines · Anton Blanchard
After 6 years the ppc64 kernel still thinks its important to tell me my cache line size is
0x80bytes. I think most people who care know that by now. The rest probably cant even understand the hex output.
Quoted 6 lines
Quoted 3 lines
Since we might have misconfigured firmware or cpus that have a linesize that isnt 128 bytes, I still print it out for those cases. If people would prefer to remove it completely, lets do it.
Let's just remove it completely. I have yet to see a bug because of it, and we have
0x40byte cache lines.
I did have issues because of incorrect cache line sizes recently... this printk was actually useful for me :-)
Ben.
Quoted 9 lines · Anton Blanchard
After 6 years the ppc64 kernel still thinks its important to tell me my cache line size is
0x80bytes. I think most people who care know that by now. The rest probably cant even understand the hex output.Since we might have misconfigured firmware or cpus that have a linesize that isnt 128 bytes, I still print it out for those cases. If people would prefer to remove it completely, lets do it.
Also for lpar remove the
htab_addressprintout since its not used.
Why not also make those KERN_DEBUG ?
Ben.