I've been maintaining a patchset for internal use on and off
for a while, and have decided to publish it externally. It's
based on 2.5.47 partly because I'm slow and boring, but also
because I don't particularly want anything from 49, and there's
some bleeding edge stuff in it I'd rather not cut myself on.
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
Next additions will probably be timer fixes, moving NUMA-Q to
subarch, Summit support, and shared pagetables.
http://www.aracnet.com/~fletch/linux/2.5.47/patch-2.5.47-mjb3
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
rcu_stats Dipankar Sarma
Gives rcu statistics
dcache_rcu Dipankar Sarma
Use read copy update locking for the directory entry cache
noearlyirq Martin Bligh
Don't allow irqs on secondary cpus during IO-APIC init until __cpu_up
Else your machine may go belly up on boot.
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
use_generic_topo Matt Dobson
Something to do with tolopology that I forget.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
frameptr Martin Bligh
Disable -fomit_frame_pointer
confighz Dave Hansen
Make HZ a config option
mjb3 Martin Bligh
Add a tag to the makefile
On Sun, Dec 08, 2002 at 10:11:19PM -0800, Martin J. Bligh wrote:
> Speed up page init on boot (Bill Irwin)
This needs a one-liner to go from fls() to ffs() since alignment is
required and things falling on alignment boundaries have fls(n) == ffs(n)
Very straightforward indeed; one-liners off from the 3rd or 4th boot
must be very obvious observations.
Bill
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
http://www.aracnet.com/~fletch/linux/2.5.50/patch-2.5.50-mjb1.bz2
Since 2.5.47-mjb3:
merged by Linus:
- noearlyirq Martin Bligh et al.
all screwed up at the moment:
- dcache_rcu Dipankar Sarma
added:
merged up to 2.5.50 base
+ devclass_panic Bill Irwin
+ shpte Dave McCracken
+ subarch reorg John Stultz
+ numaq_makefile Martin Bligh
+ numaq_apic James Cleverdon / Martin Bligh
+ numaq_mpparse1 James Cleverdon / Martin Bligh
+ config_page_offset Dave Hansen / Andrea
+ vmalloc_stats Dave Hansen
+ notsc Martin Bligh
Pending:
Speed up page init on boot (Bill Irwin)
Move more of NUMA-Q to subarch (James C / Martin / John)
Full Summit support (James C / John)
RCU routecache (?)
Per-cpu interrupt stacks (bcrl / Dave)
4K Kernel stacks config option (Dave)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
The revenge of dcache_rcu (Dipankar)
/proc/meminfo.numa (Me and others).
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
rcu_stats Dipankar Sarma
Gives rcu statistics
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
use_generic_topo Matt Dobson
Something to do with tolopology that I forget.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
frameptr Martin Bligh
Disable -fomit_frame_pointer
confighz Dave Hansen
Make HZ a config option
devclass_panic Bill Irwin
Reorder sysfs init for topo to avoid panic
shpte Dave McCracken
Shared pagetables (as a config option)
subarch reorg John Stultz
Move the header files for subarch under include/asm-i386
numaq_makefile Martin Bligh
Create shell of NUMA-Q subarch support.
numaq_apic James Cleverdon / Martin Bligh
Break out some apic stuff for NUMA-Q into subarch
numaq_mpparse1 James Cleverdon / Martin Bligh
Break out some mpparse stuff for NUMA-Q into subarch
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mjb1 Martin Bligh
Add a tag to the makefile
Sorry, previous patch seemed to have some problems on non-NUMA boxen.
This one seems to work fine on a 4x machine at least ... next release
will have more substance ;-)
--------------------------
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
http://www.aracnet.com/~fletch/linux/2.5.50/patch-2.5.50-mjb2.bz2
Since 2.5.50-mjb1
Returned from the dead:
+ dcache_rcu Dipankar Sarma
Gone to renegotiate with it's maker (seems to cause problems on standard
SMP):
- numaq_makefile Martin Bligh
- numaq_apic James Cleverdon / Martin Bligh
- numaq_mpparse1 James Cleverdon / Martin Bligh
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
Move more of NUMA-Q to subarch (James C / Martin / John)
Full Summit support (James C / John)
RCU routecache (?)
Per-cpu interrupt stacks (bcrl / Dave)
4K Kernel stacks config option (Dave)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
/proc/meminfo.numa (Me and others).
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
rcu_stats Dipankar Sarma
Gives rcu statistics
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
use_generic_topo Matt Dobson
Something to do with tolopology that I forget.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
frameptr Martin Bligh
Disable -fomit_frame_pointer
confighz Dave Hansen
Make HZ a config option
devclass_panic Bill Irwin
Reorder sysfs init for topo to avoid panic
shpte Dave McCracken
Shared pagetables (as a config option)
subarch reorg John Stultz
Move the header files for subarch under include/asm-i386
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
dcache_rcu
Use RCU type locking for the dentry cache.
mjb2 Martin Bligh
Add a tag to the makefile
On Mon, Dec 09, 2002 at 10:42:03PM -0800, Martin J. Bligh wrote:
> Speed up page init on boot (Bill Irwin)
Hang on until I push the fixes for this guy out (probably tonight).
On Mon, Dec 09, 2002 at 10:42:03PM -0800, Martin J. Bligh wrote:
> devclass_panic Bill Irwin
> Reorder sysfs init for topo to avoid panic
That really needs to go straight to Linus and fast, I'll push.
Thanks,
Bill
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
http://www.aracnet.com/~fletch/linux/2.5.52/patch-2.5.52-mjb1.bz2
Since 2.5.50-mjb2
+ thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
+ interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
+ stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
+ 4k_stack (4K stacks pt 4) Dave Hansen
+ numameminfo Martin Bligh / Keith Mannthey
Returned from the dead:
+ numaq_makefile Martin Bligh
+ numaq_apic James Cleverdon / Martin Bligh
+ numaq_mpparse1 James Cleverdon / Martin Bligh
+ numaq_mpparse2 James Cleverdon / Martin Bligh
Merged:
- devclass_panic Bill Irwin
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
Move more of NUMA-Q to subarch (James C / Martin / John)
Full Summit support (James C / John)
RCU routecache (?)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
noframeptr Martin Bligh
Disable -fomit_frame_pointer
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
use_generic_topo Matt Dobson
Something to do with tolopology that I forget.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Dave Hansen
Make HZ a config option
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
shpte Dave McCracken
Shared pagetables (as a config option)
subarch reorg John Stultz
Move the header files for subarch under include/asm-i386
numaq_makefile James Cleverdon / Martin Bligh
Numa-Q subarch splitup
numaq_apic James Cleverdon / Martin Bligh
Numa-Q subarch splitup
numaq_mpparse1 James Cleverdon / Martin Bligh
Numa-Q subarch splitup
numaq_mpparse2 James Cleverdon / Martin Bligh
Numa-Q subarch splitup
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
mjb1 Martin Bligh
Add a tag to the makefile
On Tue, Dec 17, 2002 at 12:10:29AM -0800, Martin J. Bligh wrote:
> The patchset contains mainly scalability and NUMA stuff, and
> anything else that stops things from irritating me. It's meant
> to be pretty stable, not so much a testing ground for new stuff.
> I'd be very interested in feedback from other people running
> large SMP or NUMA boxes.
> http://www.aracnet.com/~fletch/linux/2.5.52/patch-2.5.52-mjb1.bz2
BTW, the mem_map initialization stuff has been pretty well shaken down,
so it's safe to slurp that up now.
Bill
On Tue, Dec 17, 2002 at 12:10:29AM -0800, Martin J. Bligh wrote:
> The patchset contains mainly scalability and NUMA stuff, and
> anything else that stops things from irritating me. It's meant
> to be pretty stable, not so much a testing ground for new stuff.
> I'd be very interested in feedback from other people running
> large SMP or NUMA boxes.
> http://www.aracnet.com/~fletch/linux/2.5.52/patch-2.5.52-mjb1.bz2
pfn_to_nid() got lots of icache misses. Try using a macro.
arch/i386/kernel/i386_ksyms.c | 1 -
arch/i386/kernel/numaq.c | 15 ++-------------
include/asm-i386/numaq.h | 3 ++-
3 files changed, 4 insertions(+), 15 deletions(-)
diff -urpN linux-2.5.52-mm1/arch/i386/kernel/i386_ksyms.c mm1-2.5.52-1/arch/i386/kernel/i386_ksyms.c
--- linux-2.5.52-mm1/arch/i386/kernel/i386_ksyms.c 2002-12-16 19:29:45.000000000 -0800
+++ mm1-2.5.52-1/arch/i386/kernel/i386_ksyms.c 2002-12-17 08:47:25.000000000 -0800
@@ -67,7 +67,6 @@ EXPORT_SYMBOL(EISA_bus);
EXPORT_SYMBOL(MCA_bus);
#ifdef CONFIG_DISCONTIGMEM
EXPORT_SYMBOL(node_data);
-EXPORT_SYMBOL(pfn_to_nid);
#endif
#ifdef CONFIG_X86_NUMAQ
EXPORT_SYMBOL(xquad_portio);
diff -urpN linux-2.5.52-mm1/arch/i386/kernel/numaq.c mm1-2.5.52-1/arch/i386/kernel/numaq.c
--- linux-2.5.52-mm1/arch/i386/kernel/numaq.c 2002-12-15 18:08:13.000000000 -0800
+++ mm1-2.5.52-1/arch/i386/kernel/numaq.c 2002-12-17 08:51:44.000000000 -0800
@@ -27,6 +27,7 @@
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/mmzone.h>
+#include <linux/module.h>
#include <asm/numaq.h>
/* These are needed before the pgdat's are created */
@@ -82,19 +83,7 @@ static void __init smp_dump_qct(void)
* physnode_map[8- ] = -1;
*/
int physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
-
-#define PFN_TO_ELEMENT(pfn) (pfn / PAGES_PER_ELEMENT)
-#define PA_TO_ELEMENT(pa) (PFN_TO_ELEMENT(pa >> PAGE_SHIFT))
-
-int pfn_to_nid(unsigned long pfn)
-{
- int nid = physnode_map[PFN_TO_ELEMENT(pfn)];
-
- if (nid == -1)
- BUG(); /* address is not present */
-
- return nid;
-}
+EXPORT_SYMBOL(physnode_map);
/*
* for each node mark the regions
diff -urpN linux-2.5.52-mm1/include/asm-i386/numaq.h mm1-2.5.52-1/include/asm-i386/numaq.h
--- linux-2.5.52-mm1/include/asm-i386/numaq.h 2002-12-15 18:08:09.000000000 -0800
+++ mm1-2.5.52-1/include/asm-i386/numaq.h 2002-12-17 08:45:19.000000000 -0800
@@ -38,10 +38,11 @@
#define MAX_ELEMENTS 256
#define PAGES_PER_ELEMENT (16777216/256)
+extern int physnode_map[];
+#define pfn_to_nid(pfn) ({ physnode_map[(pfn) / PAGES_PER_ELEMENT]; })
#define pfn_to_pgdat(pfn) NODE_DATA(pfn_to_nid(pfn))
#define PHYSADDR_TO_NID(pa) pfn_to_nid(pa >> PAGE_SHIFT)
#define MAX_NUMNODES 8
-extern int pfn_to_nid(unsigned long);
extern void get_memcfg_numaq(void);
#define get_memcfg_numa() get_memcfg_numaq()
>> The patchset contains mainly scalability and NUMA stuff, and
>> anything else that stops things from irritating me. It's meant
>> to be pretty stable, not so much a testing ground for new stuff.
>> I'd be very interested in feedback from other people running
>> large SMP or NUMA boxes.
>> http://www.aracnet.com/~fletch/linux/2.5.52/patch-2.5.52-mjb1.bz2
>
> pfn_to_nid() got lots of icache misses. Try using a macro.
How much difference does this make?
M.
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
http://www.aracnet.com/~fletch/linux/2.5.53/patch-2.5.53-mjb1.bz2
Since 2.5.52-mjb1
- config_hz Dave Hansen
+ config_hz (new version) Andrew Morton / Dave Hansen
- i386_topo Matt Dobson
+ i386_topo (new version) Matt Dobson
Merged:
- numaq_makefile Martin Bligh
- numaq_apic James Cleverdon / Martin
Bligh
- numaq_mpparse1 James Cleverdon / Martin
Bligh
- numaq_mpparse2 James Cleverdon / Martin
Bligh
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
Final bits of NUMA-Q / clustered_apic_mode to subarch (Martin)
Full Summit support (James C / John)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
Lockless xtime structures (Andi)
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
noframeptr Martin Bligh
Disable -fomit_frame_pointer
use_generic_topo Matt Dobson
Make non-NUMA PPC64 use generic topology functions
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
shpte Dave McCracken
Shared pagetables (as a config option)
more_numaq1 James Cleverdon / Martin Bligh
yet more Numa-Q subarch splitup
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
mjb1 Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and
anything else that stops things from irritating me. It's meant
to be pretty stable, not so much a testing ground for new stuff.
I'd be very interested in feedback from other people running
large SMP or NUMA boxes.
http://www.aracnet.com/~fletch/linux/2.5.54/patch-2.5.54-mjb1.bz2
Since 2.5.53-mjb1 (nothing very interesting going on, apart from
a critical bugfix to the config_hz stuff).
- config_hz Andrew Morton / Dave Hansen
+ config_hz (new version) Andrew Morton / Dave Hansen
- use_generic_topo Matt Dobson
+ apicid_to_node Martin Bligh
- i386_topo Matt Dobson
+ i386_topo (new version) Matt Dobson / Martin Bligh
+ fix_starfire_warning Martin Bligh
+ kallsyms fix Andi Kleen / Daniel Ritz
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
Final bits of NUMA-Q / clustered_apic_mode to subarch (Martin)
Full Summit support (James C / John)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
Lockless xtime structures (Andi)
kgdb Various People
The older version of kgdb, not the shiny new stuff in Andrew's tree.
Yes, I'm boring and slow.
noframeptr Martin Bligh
Disable -fomit_frame_pointer
apicid_to_node Martin Bligh
Create an machine specific apicid_to_node for everyone
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
fix_starfire_warning Martin Bligh
Fix trivial starfire compile warning that keeps annoying me.
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
shpte Dave McCracken
Shared pagetables (as a config option)
more_numaq1 James Cleverdon / Martin Bligh
yet more Numa-Q subarch splitup
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kallsyms Andi Kleen / Daniel Ritz
Fix some bug.
mjb1 Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.54/patch-2.5.54-mjb2.bz2
Since 2.5.54-mjb1 (mainly finished moving NUMA-Q into subarch).
- kgdb
+ kgdb (new version) Andrew Morton / Various People
~ i386_caching_topo (rejigged)
+ cleanup_cpu_apicid Martin Bligh
+ smpboot_cam Martin Bligh
+ nuke_clustered_apic Martin Bligh
~ interrupt_stacks (fixed a warning)
~ stack_usage_check (fixed a warning)
+ do_boot_error (this was in -mjb1, but I forgot it in the notes)
Also reordered a bunch of stuff.
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
Full Summit support (James C / John)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
Lockless xtime structures (Andi)
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
apicid_to_node Martin Bligh
Create an machine specific apicid_to_node for everyone
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
do_boot_error James Cleverdon
Change do_boot_cpu to return an error code instead of fishing globally
fix_starfire_warning Martin Bligh
Fix trivial starfire compile warning that keeps annoying me.
shpte Dave McCracken
Shared pagetables (as a config option)
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
more_numaq1 James Cleverdon / Martin Bligh
yet more Numa-Q subarch splitup
cleanup_cpu_apicid Martin J. Bligh
Cleanup & simplify the apicid <-> cpu mapping stuff I put in ages ago.
smpboot_cam Martin J. Bligh
Remove clustered_apic_mode stuff from smpboot.c
nuke_clustered_apic Martin J. Bligh
Kill clustered_apic_mode and CONFIG_CLUSTERED_APIC forever.
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kallsyms Andi Kleen / Daniel Ritz
Fix some bug.
-mjb Martin Bligh
Add a tag to the makefile
Yeah, I know I'm "fashionably late", but I wanted to clear down some
stuff before porting to 2.5.55. Will do that tommorow.
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.54/patch-2.5.54-mjb3.bz2
Since 2.5.54-mjb2 (tweaked NUMA-Q patches, added Summit support)
~ cleanup_cpu_apicid Martin J. Bligh
~ smpboot_cam Martin J. Bligh
+ summit1 James Cleverdon / John Stultz
+ summit2 James Cleverdon / John Stultz
+ summit3 James Cleverdon / John Stultz
+ summit4 James Cleverdon / John Stultz
Also reordered a bunch of stuff.
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
Lockless xtime structures (Andi)
kallsyms Andi Kleen / Daniel Ritz
Fix stem compression bug.
apicid_to_node Martin Bligh
Create an machine specific apicid_to_node for everyone
i386_topo Matt Dobson
Some i386 topology cleanups to make it cache the data.
do_boot_error James Cleverdon
Change do_boot_cpu to return an error code instead of fishing globally
more_numaq1 James Cleverdon / Martin Bligh
yet more Numa-Q subarch splitup
cleanup_cpu_apicid Martin J. Bligh
Cleanup & simplify the apicid <-> cpu mapping stuff I put in ages ago.
smpboot_cam Martin J. Bligh
Remove clustered_apic_mode stuff from smpboot.c
nuke_clustered_apic Martin J. Bligh
Kill clustered_apic_mode and CONFIG_CLUSTERED_APIC forever.
fix_starfire_warning Martin Bligh
Fix trivial starfire compile warning that keeps annoying me.
shpte Dave McCracken
Shared pagetables (as a config option)
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.55/patch-2.5.55-mjb1.bz2
Since 2.5.54-mjb3
merged with Linus:
- kallsyms Andi Kleen / Daniel Ritz
- apicid_to_node Martin Bligh
- i386_topo Matt Dobson
- do_boot_error James Cleverdon
- more_numaq1 James Cleverdon / Martin Bligh
- cleanup_cpu_apicid Martin J. Bligh
- smpboot_cam Martin J. Bligh
- nuke_clustered_apic Martin J. Bligh
- fix_starfire_warning Martin J. Bligh
Other:
~ summit2 James Cleverdon / John Stultz
- shpte Dave McCracken
(dropped temporarily until Dave merges up with 2.5.55)
~ interrupt_stacks Dave Hansen / Ben LaHaise
~ stack_usage_check Dave Hansen / Ben LaHaise
+ ksymsoff Hugh Dickins
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Scheduler tunables (rml)
Lockless xtime structures (Andi)
P4 oprofile support (movement)
summit1 James Cleverdon / John Stultz
Summit support part 1
summit2 James Cleverdon / John Stultz
Summit support part 2
summit3 James Cleverdon / John Stultz
Summit support part 3
summit4 James Cleverdon / John Stultz
Summit support part 4
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
numasched1 Erich Focht
Numa scheduler general foundation work + pooling
numasched2 Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ksymoff Hugh Dickins
Fix off by one error in kksymoops
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.58/patch-2.5.58-mjb1.bz2
Since 2.5.55-mjb1
Notes:
The interrupt distribution on Summit should be fixed now.
I put the new minimal NUMA scheduler in, no node-balance code yet (real soon).
The summit code will break the new bigsmp subarch for now.
- ksymsoff Hugh Dickens
(kind of part merged, and I don't have an updated ver)
- numasched1 Erich Focht
+ summit1 James Cleverdon / John Stultz
~ summit2 John Stultz
+ min_numasched Martin J. Bligh
+ sched_tunables Robert Love
Pending:
NUMA node rebalancer (Erich Focht)
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Lockless xtime structures (Andi)
P4 oprofile support (movement)
summit1 James Cleverdon / John Stultz
Summit support part 1
summit2 James Cleverdon / John Stultz
Summit support part 2
summit3 James Cleverdon / John Stultz
Summit support part 3
summit4 James Cleverdon / John Stultz
Summit support part 4
summit5 James Cleverdon / John Stultz
Summit support part 5
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
min_numasched Martin J. Bligh
Minimal NUMA scheduler to make balancing node-local
numasched_ilb Michael Hohnbaum
Numa scheduler lightweight initial load balancing.
sched_tunables Robert Love
Provide tunable parameters for the scheduler
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.58/patch-2.5.58-mjb2.bz2
Since 2.5.58-mjb1 (~ = changed, + = added, - = dropped)
~ summit1 James Cleverdon / John Stultz
~ summit2 James Cleverdon / John Stultz
~ summit3 James Cleverdon / John Stultz
~ summit4 James Cleverdon / John Stultz
~ summit5 James Cleverdon / John Stultz
~ min_numasched Martin J. Bligh
~ numasched_ilb Michael Hohnbaum
+ numa_rebalancer Erich Focht
+ mpc_apic_id Martin J. Bligh
+ doaction Martin J. Bligh
+ vm_enough_memory Martin J. Bligh
+ discontig_x440 Pat Gaughen / Chandra
+ topo_hack Pat Gaughen
Notes:
NUMA scheduler is fully there now. Please let me know of tuning data.
Summit code should be fully working, with no more interrupt distribution
problems. Discontigmem code for x440 may not work without a small ACPI fix.
Pending:
Speed up page init on boot (Bill Irwin)
Notsc automatic enablement (someone, please ... anyone?)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Lockless xtime structures (Andi)
P4 oprofile support (movement)
Child runs first (akpm)
New starfire driver (Ion)
New qlogic driver (Badari ??)
summit1 James Cleverdon / John Stultz
Summit support part 1
summit2 James Cleverdon / John Stultz
Summit support part 2
summit3 James Cleverdon / John Stultz
Summit support part 3
summit4 James Cleverdon / John Stultz
Summit support part 4
summit5 James Cleverdon / John Stultz
Summit support part 5
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
min_numasched Martin J. Bligh
Minimal NUMA scheduler to make balancing node-local
numasched_ilb Michael Hohnbaum
NUMA scheduler lightweight initial load balancing.
numa_rebalancer Erich Focht
NUMA inter-node rebalancer tunable by architecture.
sched_tunables Robert Love
Provide tunable parameters for the scheduler
local_pgdat Bill Irwin
Move the pgdat structure into the remapped space with lmem_map
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
vm_enough_memory Martin J. Bligh
Make vm_enough_memory more efficient (for overcommit = 2)
discontig_x440 Pat Gaughen / Chandra
SLIT/SRAT parsing for x440 discontigmem
topo_hack Pat Gaughen
Disable some topo stuff for Summit because we're cowards.
-mjb Martin Bligh
Add a tag to the makefile
On Thu, Jan 16, 2003 at 11:11:54PM -0800, Martin J. Bligh wrote:
> Speed up page init on boot (Bill Irwin)
> local_pgdat Bill Irwin
> Move the pgdat structure into the remapped space with lmem_map
Any chance you could push these Linus-ward? akpm appears to have
lost the intestinal fortitude to carry NUMA-Q/Summit -specific stuff
himself, which is fine, I'd just rather not see these lost in the
shuffle, esp. as a day or two was burned on each.
Thanks,
Bill
>> Speed up page init on boot (Bill Irwin)
>> local_pgdat Bill Irwin
>> Move the pgdat structure into the remapped space with lmem_map
>
> Any chance you could push these Linus-ward? akpm appears to have
> lost the intestinal fortitude to carry NUMA-Q/Summit -specific stuff
> himself, which is fine, I'd just rather not see these lost in the
> shuffle, esp. as a day or two was burned on each.
The first one isn't in the tree as yet ... I just haven't been excited
enough about speeding up boot speed, to be perfectly honest, seeing as
it still takes 5 minutes anyway. It might make more sense once kexec
works, and the percentage improvement would become significant.
The local_pgdat stuff definitely makes sense ... I'd kind of prefer it
to go after the mem_map so I don't have to think about alignment
issues so much, but it's been stable for ages, so I guess I'll push it
as soon as Linus returns from vacation ...
M.
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb1.bz2
Since 2.5.58-mjb2 (~ = changed, + = added, - = dropped)
Notes:
Lots of good stuff merged up with Linus. x440 distcontigmem seems to have
problems in some circumstances, but APCI should work in this release.
merged with Linus:
- summit1 James Cleverdon / John Stultz
- summit2 James Cleverdon / John Stultz
- summit3 James Cleverdon / John Stultz
- summit4 James Cleverdon / John Stultz
- summit5 James Cleverdon / John Stultz
- min_numasched Martin J. Bligh
- numasched_ilb Michael Hohnbaum
- numa_rebalancer Erich Focht
- vm_enough_memory Martin J. Bligh
Other:
+ ingosched Ingo Molar
~ sched_tunables Robert Love
+ acpi_x440_hack Anonymous Coward
+ numaq_ioapicids William Lee Irwin
+ oprofile_p4 John Levon
+ starfire Ion Badulescu
Pending:
Notsc automatic enablement (someone, please ... anyone?)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Lockless xtime structures (Andi)
Child runs first (akpm)
New qlogic driver (Badari ??)
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
discontig_x440 Pat Gaughen / Chandra
SLIT/SRAT parsing for x440 discontigmem
topo_hack Pat Gaughen
Disable some topo stuff for Summit because we're cowards.
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb2.bz2
Since 2.5.59-mjb1 (~ = changed, + = added, - = dropped)
Notes:
Added frlock xtime patches, cyclone timer fixes, sched stats.
I have new code for 4K stacks, but haven't applied it yet (next release).
+ schedstat Rick Lindsley
~ sched_tuneables Robert Love
- topo_hack Pat Gaughen
+ sysfs_fix Pat Gaughen
+ cyclone_fixes John Stultz
+ enable_cyclone John Stultz
+ lost_tick John Stultz
+ frlock_xtime Stephen Hemminger et al.
+ frlock_xtime-i386 Stephen Hemminger et al.
+ frlock_xtime-ia64 Stephen Hemminger et al.
+ frlock_xtime-other Stephen Hemminger et al.
+ tcp_fix Alexey
+ numa_pci_fix Dave Hansen
Pending:
Revised 4K stacks code
Notsc automatic enablement (someone, please ... anyone?)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Child runs first (akpm)
New qlogic driver (Badari ??)
Kexec
Linux Kernel Crash Dump
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
schedstat Rick Lindsley
Provide stats about the scheduler under /proc/stat
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
discontig_x440 Pat Gaughen / Chandra
SLIT/SRAT parsing for x440 discontigmem
sysfs_fix Pat Gaughen
Fix sysfs for x440 machines instead of some topo hack ;-)
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
cyclone_fixes John Stultz
Fix up some stuff for the x440's cyclone timer
enable_cyclone John Stultz
Enable the x440's cyclone timer
lost_tick John Stultz
Detect lost timer ticks
frlock_xtime Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-i386 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-ia64 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-other Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
tcp_fix Alexey
Stop some tcp problem with hardware checksumming (e1000?)
numa_pci_fix Dave Hansen
Fix a potential error in the numa pci code from Stanford Checker
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb3.bz2
Since 2.5.59-mjb2 (~ = changed, + = added, - = dropped)
Notes:
Added frlock xtime patches, cyclone timer fixes, sched stats.
I have new code for 4K stacks, but haven't applied it yet (next release).
~ early_printk Dave Hansen et al.
~ interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
- sysfs_fix Pat Gaughen
+ srat_fixes Pat Gaughen
+ summit_smp John Stultz
+ pgd_ctor William Lee Irwin
+ pfn_to_nid William Lee Irwin
+ pidmaps_nodepages Dave Hansen
Pending:
auto_disable_tsc (John Stultz)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Child runs first (akpm)
New qlogic driver (Badari ??)
Kexec
Linux Kernel Crash Dump
Kprobes
e1000 fixes
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
schedstat Rick Lindsley
Provide stats about the scheduler under /proc/stat
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
discontig_x440 Pat Gaughen / Chandra
SLIT/SRAT parsing for x440 discontigmem
srat_fixes Pat Gaughen
Fix sysfs for x440 machines, and make srat conditional on NUMA
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
summit_smp John Stultz
Make Summit config options work on standard SMP
cyclone_fixes John Stultz
Fix up some stuff for the x440's cyclone timer
enable_cyclone John Stultz
Enable the x440's cyclone timer
lost_tick John Stultz
Detect lost timer ticks
frlock_xtime Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-i386 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-ia64 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-other Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
tcp_fix Alexey
Stop some tcp problem with hardware checksumming (e1000?)
numa_pci_fix Dave Hansen
Fix a potential error in the numa pci code from Stanford Checker
pgd_ctor William Lee Irwin
Use slabs for pgd
pfn_to_nid William Lee Irwin
Turn pfn_to_nid into a macro
pidmaps_nodepages Dave Hansen
Display NUMA information in /proc/pid/maps
-mjb Martin Bligh
Add a tag to the makefile
On Sun, 2003-02-02 at 18:08, Martin J. Bligh wrote:
> The patchset contains mainly scalability and NUMA stuff, and anything
> else that stops things from irritating me. It's meant to be pretty stable,
> not so much a testing ground for new stuff.
>
> I'd be very interested in feedback from anyone willing to test on any
> platform, however large or small.
>
> http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb3.bz2
>
I tried 2.5.59-mjb3 today on our 16 processor numaq and got a boot
hang. I had been running 2.5.59-mjb2 previously. I have included the
console output and my config file.
--
Mark Haverkamp <[email protected]>
>> The patchset contains mainly scalability and NUMA stuff, and anything
>> else that stops things from irritating me. It's meant to be pretty stable,
>> not so much a testing ground for new stuff.
>>
>> I'd be very interested in feedback from anyone willing to test on any
>> platform, however large or small.
>>
>> http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb3.bz2
>>
>
> I tried 2.5.59-mjb3 today on our 16 processor numaq and got a boot
> hang. I had been running 2.5.59-mjb2 previously. I have included the
> console output and my config file.
What gcc are you using? I'm betting 3.2 ... 2.95 seems to work fine.
(still might be an issue with the patch, just trying to track it down)
M.
On Mon, 2003-02-03 at 10:42, Martin J. Bligh wrote:
> >> The patchset contains mainly scalability and NUMA stuff, and anything
> >> else that stops things from irritating me. It's meant to be pretty stable,
> >> not so much a testing ground for new stuff.
> >>
> >> I'd be very interested in feedback from anyone willing to test on any
> >> platform, however large or small.
> >>
> >> http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb3.bz2
> >>
> >
> > I tried 2.5.59-mjb3 today on our 16 processor numaq and got a boot
> > hang. I had been running 2.5.59-mjb2 previously. I have included the
> > console output and my config file.
>
> What gcc are you using? I'm betting 3.2 ... 2.95 seems to work fine.
You are right, I am using:
gcc (GCC) 3.2 20020903 (Red Hat Linux 8.0 3.2-7)
> (still might be an issue with the patch, just trying to track it down)
>
> M.
--
Mark Haverkamp <[email protected]>
>> What gcc are you using? I'm betting 3.2 ... 2.95 seems to work fine.
>
> You are right, I am using:
>
> gcc (GCC) 3.2 20020903 (Red Hat Linux 8.0 3.2-7)
>
>
>> (still might be an issue with the patch, just trying to track it down)
Could you find the definition of cpu_online_map, and remove the "=1"
initialisation from it ... see if that fixes it? (I just added that)
Seems suspiciously closely related ... if that doesn't do it, I'll
try to diagnose here.
Thanks,
M.
On Mon, 2003-02-03 at 11:03, Martin J. Bligh wrote:
> >> What gcc are you using? I'm betting 3.2 ... 2.95 seems to work fine.
> >
> > You are right, I am using:
> >
> > gcc (GCC) 3.2 20020903 (Red Hat Linux 8.0 3.2-7)
> >
> >
> >> (still might be an issue with the patch, just trying to track it down)
>
> Could you find the definition of cpu_online_map, and remove the "=1"
> initialisation from it ... see if that fixes it? (I just added that)
> Seems suspiciously closely related ... if that doesn't do it, I'll
> try to diagnose here.
>
> Thanks,
>
> M.
I removed the = 1 from cpu_online_map in arch/i386/kernel/smpboot.c and
got the boot hang in the same place.
Mark.
--
Mark Haverkamp <[email protected]>
>> > I tried 2.5.59-mjb3 today on our 16 processor numaq and got a boot
>> > hang. I had been running 2.5.59-mjb2 previously. I have included the
>> > console output and my config file.
>>
>> What gcc are you using? I'm betting 3.2 ... 2.95 seems to work fine.
>
> You are right, I am using:
>
> gcc (GCC) 3.2 20020903 (Red Hat Linux 8.0 3.2-7)
>
>> (still might be an issue with the patch, just trying to track it down)
OK, it's the attatched patch's fault. Can you patch -R it, and confirm that
fixes it? (does for me).
Dave, can you take a look at why this breaks with gcc 3.2?
Thanks,
M.
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb4.bz2
additional:
http://www.aracnet.com/~fletch/linux/2.5.59/pidmaps_nodepages
http://www.aracnet.com/~fletch/linux/2.5.59/mjb4-stacks
Since 2.5.59-mjb3 (~ = changed, + = added, - = dropped)
Notes:
Very, very boring ... just getting one (hopefully) rock-solid stabilisation
point for lots of stuff that's pending I have to merge somehow ...
I've broken out the pidmaps_nodepages and 4K stacks patches that were
causing some problems ... will return soon. Available seperately (as above)
- thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
- interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
- stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
- 4k_stack (4K stacks pt 4) Dave Hansen
- pidmaps_nodepages Dave Hansen
Pending:
Kprobes
Linux Kernel Crash Dump
kirq interrupt balancing patch (Nitin Kamble)
auto_disable_tsc (John Stultz)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Child runs first (akpm)
Feral qlogic driver (Matthew Jacob and the SCSI crew)
Kexec
e1000 fixes
Non-PAE aligned kernel splits (Dave Hansen)
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
schedstat Rick Lindsley
Provide stats about the scheduler under /proc/stat
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
# thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
# interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
# stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
# 4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
discontig_x440 Pat Gaughen / Chandra
SLIT/SRAT parsing for x440 discontigmem
srat_fixes Pat Gaughen
Fix sysfs for x440 machines, and make srat conditional on NUMA
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
summit_smp John Stultz
Make Summit config options work on standard SMP
cyclone_fixes John Stultz
Fix up some stuff for the x440's cyclone timer
enable_cyclone John Stultz
Enable the x440's cyclone timer
lost_tick John Stultz
Detect lost timer ticks
frlock_xtime Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-i386 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-ia64 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-other Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
tcp_fix Alexey
Stop some tcp problem with hardware checksumming (e1000?)
numa_pci_fix Dave Hansen
Fix a potential error in the numa pci code from Stanford Checker
pgd_ctor William Lee Irwin
Use slabs for pgd
pfn_to_nid William Lee Irwin
Turn pfn_to_nid into a macro
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb5.bz2
additional:
http://www.aracnet.com/~fletch/linux/2.5.59/pidmaps_nodepages
http://www.aracnet.com/~fletch/linux/2.5.59/mjb4-stacks
Since 2.5.59-mjb4 (~ = changed, + = added, - = dropped)
Notes:
Shared pagetables pt. 2 ... the revenge of shared pagetables.
~ discontig_x440 Pat Gaughen / IBM NUMA team
- srat_fixes Pat Gaughen
+ kprobes Vamsi Krishna S
+ dmc_exit1 Dave McCracken
+ dmc_exit2 Dave McCracken
+ shpte Dave McCracken
Pending:
Linux Kernel Crash Dump
kirq interrupt balancing patch (Nitin Kamble)
auto_disable_tsc (John Stultz)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Child runs first (akpm)
Feral qlogic driver (Matthew Jacob and the SCSI crew)
Kexec
e1000 fixes
Non-PAE aligned kernel splits (Dave Hansen)
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
schedstat Rick Lindsley
Provide stats about the scheduler under /proc/stat
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
# thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
# interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
# stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
# 4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
discontig_x440 Pat Gaughen / IBM NUMA team
SLIT/SRAT parsing for x440 discontigmem
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
summit_smp John Stultz
Make Summit config options work on standard SMP
cyclone_fixes John Stultz
Fix up some stuff for the x440's cyclone timer
enable_cyclone John Stultz
Enable the x440's cyclone timer
lost_tick John Stultz
Detect lost timer ticks
frlock_xtime Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-i386 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-ia64 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-other Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
tcp_fix Alexey
Stop some tcp problem with hardware checksumming (e1000?)
numa_pci_fix Dave Hansen
Fix a potential error in the numa pci code from Stanford Checker
pgd_ctor William Lee Irwin
Use slabs for pgd
pfn_to_nid William Lee Irwin
Turn pfn_to_nid into a macro
-mjb Martin Bligh
Add a tag to the makefile
The patchset contains mainly scalability and NUMA stuff, and anything
else that stops things from irritating me. It's meant to be pretty stable,
not so much a testing ground for new stuff.
I'd be very interested in feedback from anyone willing to test on any
platform, however large or small.
http://www.aracnet.com/~fletch/linux/2.5.59/patch-2.5.59-mjb6.bz2
additional:
http://www.aracnet.com/~fletch/linux/2.5.59/pidmaps_nodepages
Since 2.5.59-mjb5 (~ = changed, + = added, - = dropped)
Notes:
Fixed bug between NFS and dcache, and some oprofile bug on UP.
4K stacks are back and crash dump support has arrived (thanks to Suparna
for help merging and bufixing)
+ dcache_sunrpc Maneesh
~ cyclone_fixes John Stultz
+ oprofile_fixes John Levon
+ thread_info_cleanup Dave Hansen / Ben LaHaise
+ interrupt_stacks Dave Hansen / Ben LaHaise
+ stack_usage_check Dave Hansen / Ben LaHaise
+ 4k_stack Dave Hansen
+ fix_kgdb Dave Hansen
+ stacks_from_slab Bill Irwin
+ thread_under_page Bill Irwin
+ lkcd LKCD team
+ alt_sysrq_t Russell King
Pending:
kirq interrupt balancing patch (Nitin Kamble)
auto_disable_tsc (John Stultz)
scheduler callers profiling (Anton)
PPC64 NUMA patches (Anton)
Child runs first (akpm)
Kexec
e1000 fixes
Non-PAE aligned kernel splits (Dave Hansen)
Update the lost timer ticks code
Ingo scheduler updates
dcache_rcu Dipankar / Maneesh
Use RCU type locking for the dentry cache.
dcache_sunrpc Maneesh
Fix up NFS to work properly with dcache
early_printk Dave Hansen et al.
Allow printk before console_init
confighz Andrew Morton / Dave Hansen
Make HZ a config option of 100 Hz or 1000 Hz
config_page_offset Dave Hansen / Andrea
Make PAGE_OFFSET a config option
vmalloc_stats Dave Hansen
Expose useful vmalloc statistics
local_pgdat William Lee Irwin
Move the pgdat structure into the remapped space with lmem_map
numameminfo Martin Bligh / Keith Mannthey
Expose NUMA meminfo information under /proc/meminfo.numa
notsc Martin Bligh
Enable notsc option for NUMA-Q (new version for new config system)
mpc_apic_id Martin J. Bligh
Fix null ptr dereference (optimised away, but ...)
doaction Martin J. Bligh
Fix cruel torture of macros and small furry animals in io_apic.c
kgdb Andrew Morton / Various People
The older version of kgdb, synched with 2.5.54-mm1
noframeptr Martin Bligh
Disable -fomit_frame_pointer
ingosched Ingo Molnar
Modify NUMA scheduler to have independant tick basis.
schedstat Rick Lindsley
Provide stats about the scheduler under /proc/stat
sched_tunables Robert Love
Provide tunable parameters for the scheduler (+ NUMA scheduler)
discontig_x440 Pat Gaughen / IBM NUMA team
SLIT/SRAT parsing for x440 discontigmem
acpi_x440_hack Anonymous Coward
Stops x440 crashing, but owner is ashamed of it ;-)
summit_smp John Stultz
Make Summit config options work on standard SMP
cyclone_fixes John Stultz
Fix up some stuff for the x440's cyclone timer
enable_cyclone John Stultz
Enable the x440's cyclone timer
lost_tick John Stultz
Detect lost timer ticks
frlock_xtime Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-i386 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-ia64 Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
frlock-xtime-other Stephen Hemminger et al.
Turn xtime_lock into an frlock to reduce contention
numaq_ioapicids William Lee Irwin
Stop 8 quad NUMA-Qs from panicing due to phys apicid "exhaustion".
oprofile_p4 John Levon
Updates for oprofile for P4s. Needs new userspace tools.
starfire Ion Badulescu
64 bit aware starfire driver
tcp_fix Alexey
Stop some tcp problem with hardware checksumming (e1000?)
numa_pci_fix Dave Hansen
Fix a potential error in the numa pci code from Stanford Checker
pgd_ctor William Lee Irwin
Use slabs for pgd
pfn_to_nid William Lee Irwin
Turn pfn_to_nid into a macro
oprofile_fixes John Levon
fix a couple of bugs in oprofile
kprobes Vamsi Krishna S
Add kernel probes hooks to the kernel
dmc_exit1 Dave McCracken
Speed up the exit path, pt 1.
dmc_exit2 Dave McCracken
Speed up the exit path, pt 1.
shpte Dave McCracken
Shared pagetables (as a config option)
thread_info_cleanup (4K stacks pt 1) Dave Hansen / Ben LaHaise
Prep work to reduce kernel stacks to 4K
interrupt_stacks (4K stacks pt 2) Dave Hansen / Ben LaHaise
Create a per-cpu interrupt stack.
stack_usage_check (4K stacks pt 3) Dave Hansen / Ben LaHaise
Check for kernel stack overflows.
4k_stack (4K stacks pt 4) Dave Hansen
Config option to reduce kernel stacks to 4K
fix_kgdb Dave Hansen
Fix interaction between kgdb and 4K stacks
stacks_from_slab William Lee Irwin
Take kernel stacks from the slab cache, not page allocation.
thread_under_page William Lee Irwin
Fix THREAD_SIZE < PAGE_SIZE case
lkcd LKCD team
Linux kernel crash dump support
alt_sysrq_t Russell King
Fix up ALT+sysrq+t
-mjb Martin Bligh
Add a tag to the makefile