[PATCH] 1/6 Share common physnode_map code between NUMA-Q and Summit

[PATCH] 1/6 Share common physnode_map code between NUMA-Q and Summit

[Martin J. Bligh]

>From Andy Whitcroft

Share a common physnode_map structure between NUMA-Q and Summit.

diff -urpN -X /home/fletch/.diff.exclude 000-virgin/arch/i386/kernel/i386_ksyms.c 010-common_physmap/arch/i386/kernel/i386_ksyms.c
--- 000-virgin/arch/i386/kernel/i386_ksyms.c	Wed Mar  5 07:36:57 2003
+++ 010-common_physmap/arch/i386/kernel/i386_ksyms.c	Wed Mar  5 08:44:17 2003
@@ -68,6 +68,7 @@ EXPORT_SYMBOL(EISA_bus);
 EXPORT_SYMBOL(MCA_bus);
 #ifdef CONFIG_DISCONTIGMEM
 EXPORT_SYMBOL(node_data);
+EXPORT_SYMBOL(physnode_map);
 #endif
 #ifdef CONFIG_X86_NUMAQ
 EXPORT_SYMBOL(xquad_portio);
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/arch/i386/kernel/numaq.c 010-common_physmap/arch/i386/kernel/numaq.c
--- 000-virgin/arch/i386/kernel/numaq.c	Wed Mar  5 07:36:57 2003
+++ 010-common_physmap/arch/i386/kernel/numaq.c	Wed Mar  5 08:44:17 2003
@@ -31,8 +31,7 @@
 #include <asm/numaq.h>
 
 /* These are needed before the pgdat's are created */
-unsigned long node_start_pfn[MAX_NUMNODES];
-unsigned long node_end_pfn[MAX_NUMNODES];
+extern long node_start_pfn[], node_end_pfn[];
 
 #define	MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
 
@@ -65,25 +64,7 @@ static void __init smp_dump_qct(void)
 	}
 }
 
-/*
- * -----------------------------------------
- *
- * functions related to physnode_map
- *
- * -----------------------------------------
- */
-/*
- * physnode_map keeps track of the physical memory layout of the
- * numaq nodes on a 256Mb break (each element of the array will
- * represent 256Mb of memory and will be marked by the node id.  so,
- * if the first gig is on node 0, and the second gig is on node 1
- * physnode_map will contain:
- * physnode_map[0-3] = 0;
- * physnode_map[4-7] = 1;
- * physnode_map[8- ] = -1;
- */
-int physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
-EXPORT_SYMBOL(physnode_map);
+extern int physnode_map[];
 
 /*
  * for each node mark the regions
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/arch/i386/kernel/srat.c 010-common_physmap/arch/i386/kernel/srat.c
--- 000-virgin/arch/i386/kernel/srat.c	Wed Mar  5 07:36:57 2003
+++ 010-common_physmap/arch/i386/kernel/srat.c	Wed Mar  5 08:44:17 2003
@@ -57,8 +57,7 @@ static int num_memory_chunks;		/* total 
 static int zholes_size_init;
 static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES];
 
-unsigned long node_start_pfn[MAX_NUMNODES];
-unsigned long node_end_pfn[MAX_NUMNODES];
+extern unsigned long node_start_pfn[], node_end_pfn[];
 
 extern void * boot_ioremap(unsigned long, unsigned long);
 
@@ -182,30 +181,19 @@ static __init void chunk_to_zones(unsign
 	}
 }
 
-/*
- * physnode_map keeps track of the physical memory layout of the
- * numaq nodes on a 256Mb break (each element of the array will
- * represent 256Mb of memory and will be marked by the node id.  so,
- * if the first gig is on node 0, and the second gig is on node 1
- * physnode_map will contain:
- * physnode_map[0-3] = 0;
- * physnode_map[4-7] = 1;
- * physnode_map[8- ] = -1;
- */
-int pfnnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
-EXPORT_SYMBOL(pfnnode_map);
-
-static void __init initialize_pfnnode_map(void)
+static void __init initialize_physnode_map(void)
 {
-	unsigned long topofchunk, cur = 0;
 	int i;
-	
-	for (i = 0; i < num_memory_chunks; i++) {
-		cur = node_memory_chunk[i].start_pfn;
-		topofchunk = node_memory_chunk[i].end_pfn;
-		while (cur < topofchunk) {
-			pfnnode_map[PFN_TO_ELEMENT(cur)] = node_memory_chunk[i].nid;
-			cur ++;
+	unsigned long pfn;
+	struct node_memory_chunk_s *nmcp;
+
+	/* Run the list of memory chunks and fill in the phymap. */
+	nmcp = node_memory_chunk;
+	for (i = num_memory_chunks; --i >= 0; nmcp++) {
+		for (pfn = nmcp->start_pfn; pfn <= nmcp->end_pfn;
+						pfn += PAGES_PER_ELEMENT)
+		{
+			physnode_map[pfn / PAGES_PER_ELEMENT] = (int)nmcp->nid;
 		}
 	}
 }
@@ -272,7 +260,7 @@ static int __init acpi20_parse_srat(stru
 	for (i = 0; i < num_memory_chunks; i++)
 		node_memory_chunk[i].nid = pxm_to_nid_map[node_memory_chunk[i].pxm];
 
-	initialize_pfnnode_map();
+	initialize_physnode_map();
 	
 	printk("pxm bitmap: ");
 	for (i = 0; i < sizeof(pxm_bitmap); i++) {
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/arch/i386/mm/discontig.c 010-common_physmap/arch/i386/mm/discontig.c
--- 000-virgin/arch/i386/mm/discontig.c	Wed Mar  5 07:36:57 2003
+++ 010-common_physmap/arch/i386/mm/discontig.c	Wed Mar  5 08:44:17 2003
@@ -36,11 +36,36 @@
 struct pglist_data *node_data[MAX_NUMNODES];
 bootmem_data_t node0_bdata;
 
+/*
+ * numa interface - we expect the numa architecture specfic code to have
+ *                  populated the following initialisation.
+ *
+ * 1) numnodes         - the total number of nodes configured in the system
+ * 2) physnode_map     - the mapping between a pfn and owning node
+ * 3) node_start_pfn   - the starting page frame number for a node
+ * 3) node_end_pfn     - the ending page fram number for a node
+ */
+
+/*
+ * physnode_map keeps track of the physical memory layout of a generic
+ * numa node on a 256Mb break (each element of the array will
+ * represent 256Mb of memory and will be marked by the node id.  so,
+ * if the first gig is on node 0, and the second gig is on node 1
+ * physnode_map will contain:
+ *
+ *     physnode_map[0-3] = 0;
+ *     physnode_map[4-7] = 1;
+ *     physnode_map[8- ] = -1;
+ */
+int physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+
+unsigned long node_start_pfn[MAX_NUMNODES];
+unsigned long node_end_pfn[MAX_NUMNODES];
+
 extern unsigned long find_max_low_pfn(void);
 extern void find_max_pfn(void);
 extern void one_highpage_init(struct page *, int, int);
 
-extern unsigned long node_start_pfn[], node_end_pfn[];
 extern struct e820map e820;
 extern char _end;
 extern unsigned long highend_pfn, highstart_pfn;
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/include/asm-i386/mmzone.h 010-common_physmap/include/asm-i386/mmzone.h
--- 000-virgin/include/asm-i386/mmzone.h	Wed Mar  5 08:23:16 2003
+++ 010-common_physmap/include/asm-i386/mmzone.h	Wed Mar  5 08:44:27 2003
@@ -10,14 +10,6 @@
 
 #ifdef CONFIG_DISCONTIGMEM
 
-#ifdef CONFIG_X86_NUMAQ
-#include <asm/numaq.h>
-#elif CONFIG_X86_SUMMIT
-#include <asm/srat.h>
-#else
-#define pfn_to_nid(pfn)		(0)
-#endif /* CONFIG_X86_NUMAQ */
-
 extern struct pglist_data *node_data[];
 
 /*
@@ -101,5 +93,38 @@ extern struct pglist_data *node_data[];
  * ( pfn_to_pgdat(pfn) && ((pfn) < node_end_pfn(pfn_to_nid(pfn))) ) 
  */ 
 #define pfn_valid(pfn)          ((pfn) < num_physpages)
+
+/*
+ * generic node memory support, the following assumptions apply:
+ *
+ * 1) memory comes in 256Mb contigious chunks which are either present or not
+ * 2) we will not have more than 64Gb in total
+ *
+ * for now assume that 64Gb is max amount of RAM for whole system
+ *    64Gb / 4096bytes/page = 16777216 pages
+ */
+#define MAX_NR_PAGES 16777216
+#define MAX_ELEMENTS 256
+#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
+
+extern int physnode_map[];
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+	return(physnode_map[(pfn) / PAGES_PER_ELEMENT]);
+}
+static inline struct pglist_data *pfn_to_pgdat(unsigned long pfn)
+{
+	return(NODE_DATA(pfn_to_nid(pfn)));
+}
+
+#ifdef CONFIG_X86_NUMAQ
+#include <asm/numaq.h>
+#elif CONFIG_X86_SUMMIT
+#include <asm/srat.h>
+#else
+#define pfn_to_nid(pfn)		(0)
+#endif /* CONFIG_X86_NUMAQ */
+
 #endif /* CONFIG_DISCONTIGMEM */
 #endif /* _ASM_MMZONE_H_ */
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/include/asm-i386/numaq.h 010-common_physmap/include/asm-i386/numaq.h
--- 000-virgin/include/asm-i386/numaq.h	Wed Mar  5 07:37:06 2003
+++ 010-common_physmap/include/asm-i386/numaq.h	Wed Mar  5 08:44:17 2003
@@ -28,18 +28,8 @@
 
 #ifdef CONFIG_X86_NUMAQ
 
-/*
- * for now assume that 64Gb is max amount of RAM for whole system
- *    64Gb / 4096bytes/page = 16777216 pages
- */
-#define MAX_NR_PAGES 16777216
-#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 void get_memcfg_numaq(void);
 #define get_memcfg_numa() get_memcfg_numaq()
diff -urpN -X /home/fletch/.diff.exclude 000-virgin/include/asm-i386/srat.h 010-common_physmap/include/asm-i386/srat.h
--- 000-virgin/include/asm-i386/srat.h	Wed Mar  5 07:37:06 2003
+++ 010-common_physmap/include/asm-i386/srat.h	Wed Mar  5 08:44:17 2003
@@ -27,17 +27,7 @@
 #ifndef _ASM_SRAT_H_
 #define _ASM_SRAT_H_
 
-/*
- * each element in pfnnode_map represents 256 MB (2^28) of pages.
- * so, to represent 64GB we need 256 elements.
- */
-#define MAX_ELEMENTS 256
-#define PFN_TO_ELEMENT(pfn) ((pfn)>>(28 - PAGE_SHIFT))
-
-extern int pfnnode_map[];
-#define pfn_to_nid(pfn) ({ pfnnode_map[PFN_TO_ELEMENT(pfn)]; })
-#define pfn_to_pgdat(pfn) NODE_DATA(pfn_to_nid(pfn))
-#define PHYSADDR_TO_NID(pa) pfn_to_nid(pa >> PAGE_SHIFT)
+extern int physnode_map[];
 #define MAX_NUMNODES		8
 extern void get_memcfg_from_srat(void);
 extern unsigned long *get_zholes_size(int);

[PATCH] 2/6 Make CONFIG_NUMA work on non-numa machines.

[Martin J. Bligh]

>From Andy Whitcroft

A few very simple changes in order to make CONFIG_NUMA work everywhere, so 
the distros can build one common binary kernel for distributions.

diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/Kconfig 013-numa_x86_pc/arch/i386/Kconfig
--- 012-pfn_valid/arch/i386/Kconfig	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/Kconfig	Wed Mar  5 07:41:54 2003
@@ -488,7 +488,7 @@ config NR_CPUS
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation Support"
-	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI && !ACPI_HT_ONLY)))
+	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI && !ACPI_HT_ONLY))) || X86_PC
 
 config DISCONTIGMEM
 	bool
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/kernel/smpboot.c 013-numa_x86_pc/arch/i386/kernel/smpboot.c
--- 012-pfn_valid/arch/i386/kernel/smpboot.c	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/kernel/smpboot.c	Wed Mar  5 07:41:54 2003
@@ -966,6 +966,7 @@ static void __init smp_boot_cpus(unsigne
 		if (APIC_init_uniprocessor())
 			printk(KERN_NOTICE "Local APIC not detected."
 					   " Using dummy APIC emulation.\n");
+		map_cpu_to_logical_apicid();
 		return;
 	}
 
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/mm/discontig.c 013-numa_x86_pc/arch/i386/mm/discontig.c
--- 012-pfn_valid/arch/i386/mm/discontig.c	Wed Mar  5 07:41:52 2003
+++ 013-numa_x86_pc/arch/i386/mm/discontig.c	Wed Mar  5 07:41:54 2003
@@ -82,6 +82,36 @@ void *node_remap_start_vaddr[MAX_NUMNODE
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 /*
+ * FLAT - support for basic PC memory model with discontig enabled, essentially
+ *        a single node with all available processors in it with a flat
+ *        memory map.
+ */
+void __init get_memcfg_numa_flat(void)
+{
+	int pfn;
+
+	printk("NUMA - single node, flat memory mode\n");
+
+	/* Run the memory configuration and find the top of memory. */
+	find_max_pfn();
+	node_start_pfn[0]  = 0;
+	node_end_pfn[0]	  = max_pfn;
+
+	/* Fill in the physnode_map with our simplistic memory model,
+	* all memory is in node 0.
+	*/
+	for (pfn = node_start_pfn[0]; pfn <= node_end_pfn[0];
+	       pfn += PAGES_PER_ELEMENT)
+	{
+		physnode_map[pfn / PAGES_PER_ELEMENT] = 0;
+	}
+
+         /* Indicate there is one node available. */
+	node_set_online(0);
+	numnodes = 1;
+}
+
+/*
  * Find the highest page frame number we have available for the node
  */
 static void __init find_max_pfn_node(int nid)
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/include/asm-i386/mmzone.h 013-numa_x86_pc/include/asm-i386/mmzone.h
--- 012-pfn_valid/include/asm-i386/mmzone.h	Wed Mar  5 07:41:53 2003
+++ 013-numa_x86_pc/include/asm-i386/mmzone.h	Wed Mar  5 07:41:54 2003
@@ -123,6 +123,9 @@ static inline struct pglist_data *pfn_to
 #include <asm/numaq.h>
 #elif CONFIG_X86_SUMMIT
 #include <asm/srat.h>
+#elif CONFIG_X86_PC
+#define get_memcfg_numa get_memcfg_numa_flat
+#define get_zholes_size(n) (0)
 #else
 #define pfn_to_nid(pfn)		(0)
 #endif /* CONFIG_X86_NUMAQ */

[PATCH] 3/6 Convert physnode_map to u8

[Martin J. Bligh]

>From Andy Whitcroft

Convert physnode_map from an int to a u8 to save cachelines.

diff -urpN -X /home/fletch/.diff.exclude 013-numa_x86_pc/arch/i386/kernel/numaq.c 014-physnode_map_u8/arch/i386/kernel/numaq.c
--- 013-numa_x86_pc/arch/i386/kernel/numaq.c	Wed Mar  5 07:41:52 2003
+++ 014-physnode_map_u8/arch/i386/kernel/numaq.c	Wed Mar  5 07:41:55 2003
@@ -64,8 +64,6 @@ static void __init smp_dump_qct(void)
 	}
 }
 
-extern int physnode_map[];
-
 /*
  * for each node mark the regions
  *        TOPOFMEM = hi_shrd_mem_start + hi_shrd_mem_size
diff -urpN -X /home/fletch/.diff.exclude 013-numa_x86_pc/arch/i386/mm/discontig.c 014-physnode_map_u8/arch/i386/mm/discontig.c
--- 013-numa_x86_pc/arch/i386/mm/discontig.c	Wed Mar  5 07:41:54 2003
+++ 014-physnode_map_u8/arch/i386/mm/discontig.c	Wed Mar  5 07:41:55 2003
@@ -57,7 +57,7 @@ bootmem_data_t node0_bdata;
  *     physnode_map[4-7] = 1;
  *     physnode_map[8- ] = -1;
  */
-int physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+u8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
 
 unsigned long node_start_pfn[MAX_NUMNODES];
 unsigned long node_end_pfn[MAX_NUMNODES];
diff -urpN -X /home/fletch/.diff.exclude 013-numa_x86_pc/include/asm-i386/mmzone.h 014-physnode_map_u8/include/asm-i386/mmzone.h
--- 013-numa_x86_pc/include/asm-i386/mmzone.h	Wed Mar  5 07:41:54 2003
+++ 014-physnode_map_u8/include/asm-i386/mmzone.h	Wed Mar  5 07:41:55 2003
@@ -107,7 +107,7 @@ extern struct pglist_data *node_data[];
 #define MAX_ELEMENTS 256
 #define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
 
-extern int physnode_map[];
+extern u8 physnode_map[];
 
 static inline int pfn_to_nid(unsigned long pfn)
 {
diff -urpN -X /home/fletch/.diff.exclude 013-numa_x86_pc/include/asm-i386/numaq.h 014-physnode_map_u8/include/asm-i386/numaq.h
--- 013-numa_x86_pc/include/asm-i386/numaq.h	Wed Mar  5 07:41:52 2003
+++ 014-physnode_map_u8/include/asm-i386/numaq.h	Wed Mar  5 07:41:55 2003
@@ -28,8 +28,6 @@
 
 #ifdef CONFIG_X86_NUMAQ
 
-extern int physnode_map[];
-
 #define MAX_NUMNODES		8
 extern void get_memcfg_numaq(void);
 #define get_memcfg_numa() get_memcfg_numaq()
diff -urpN -X /home/fletch/.diff.exclude 013-numa_x86_pc/include/asm-i386/srat.h 014-physnode_map_u8/include/asm-i386/srat.h
--- 013-numa_x86_pc/include/asm-i386/srat.h	Wed Mar  5 07:41:52 2003
+++ 014-physnode_map_u8/include/asm-i386/srat.h	Wed Mar  5 07:41:55 2003
@@ -27,7 +27,6 @@
 #ifndef _ASM_SRAT_H_
 #define _ASM_SRAT_H_
 
-extern int physnode_map[];
 #define MAX_NUMNODES		8
 extern void get_memcfg_from_srat(void);
 extern unsigned long *get_zholes_size(int);

[PATCH] 4/6 Fix the type of get_zholes_size for NUMA-Q

[Martin J. Bligh]

>From Andy Whitcroft

Fix the type of get_zholes_size for NUMA-Q

diff -urpN -X /home/fletch/.diff.exclude 014-physnode_map_u8/include/asm-i386/numaq.h 015-numaq_zholes_warning/include/asm-i386/numaq.h
--- 014-physnode_map_u8/include/asm-i386/numaq.h	Wed Mar  5 07:41:55 2003
+++ 015-numaq_zholes_warning/include/asm-i386/numaq.h	Wed Mar  5 07:43:31 2003
@@ -157,7 +157,7 @@ struct sys_cfg_data {
         struct	eachquadmem eq[MAX_NUMNODES];	/* indexed by quad id */
 };
 
-static inline unsigned long get_zholes_size(int nid)
+static inline unsigned long *get_zholes_size(int nid)
 {
 	return 0;
 }

[PATCH] 5/6 Provide basic documentation for profiling

[Martin J. Bligh]

People keep asking for this info, and Andrew asked me to put it under the
Documentation directory ... provides really simple instructions for taking
a profile so that users can report performance changes in a useful way.

diff -urpN -X /home/fletch/.diff.exclude 015-numaq_zholes_warning/Documentation/basic_profiling.txt 020-prof_docs/Documentation/basic_profiling.txt
--- 015-numaq_zholes_warning/Documentation/basic_profiling.txt	Wed Dec 31 16:00:00 1969
+++ 020-prof_docs/Documentation/basic_profiling.txt	Wed Mar  5 07:48:44 2003
@@ -0,0 +1,48 @@
+These instructions are deliberately very basic. If you want something clever,
+go read the real docs ;-) Please don't add more stuff, but feel free to 
+correct my mistakes ;-)    (mbligh@aracnet.com)
+Thanks to John Levon, Dave Hansen, et al. for help writing this.
+
+<test> is the thing you're trying to measure.
+Make sure you have the correct System.map / vmlinux referenced!
+IMHO it's easier to use "make install" for linux and hack /sbin/installkernel
+to copy config files, system.map, vmlinux to /boot.
+
+Readprofile
+-----------
+You need a fixed readprofile command for 2.5 ... either get hold of
+a current version from:
+http://www.kernel.org/pub/linux/utils/util-linux/
+or get readprofile binary fixed for 2.5 / akpm's 2.5 patch from 
+ftp://ftp.kernel.org/pub/linux/kernel/people/mbligh/tools/readprofile/
+
+Add "profile=2" to the kernel command line.
+
+clear		readprofile -r
+		<test>
+dump output	readprofile -m /boot/System.map > captured_profile
+
+Oprofile
+--------
+get source (I use 0.5) from http://oprofile.sourceforge.net/
+add "idle=poll" to the kernel command line 
+Configure with CONFIG_PROFILING=y and CONFIG_OPROFILE=y & reboot on new kernel
+./configure --with-kernel-support
+make install
+
+One time setup (pick appropriate one for your CPU):
+P3		opcontrol --setup --vmlinux=/boot/vmlinux \
+		--ctr0-event=CPU_CLK_UNHALTED --ctr0-count=100000
+Athlon/x86-64	opcontrol --setup --vmlinux=/boot/vmlinux \
+		--ctr0-event=RETIRED_INSNS --ctr0-count=100000
+P4		opcontrol --setup --vmlinux=/boot/vmlinux \
+		--ctr0-event=GLOBAL_POWER_EVENTS \
+		--ctr0-unit-mask=1 --ctr0-count=100000
+
+start daemon	opcontrol --start-daemon
+clear		opcontrol --reset
+start		opcontrol --start
+		<test>
+stop		opcontrol --stop
+dump output	oprofpp -dl -i /boot/vmlinux  >  output_file
+

[PATCH] 6/6 cacheline align files_lock

[Martin J. Bligh]

I'm getting a lot of cacheline bounce from .text.lock.file_table due to 
false sharing of the cahceline. The following patch just aligns the lock
in it's own cacheline.

only changes in profile under 50 ticks are:

 -4832   -22.2% .text.lock.file_table
 -6357   -12.8% default_idle
-10374    -6.2% total

Difference in results below (note system times as well as elapsed).

Kernbench: (make -j N vmlinux, where N = 2 x num_cpus)
                              Elapsed      System        User         CPU
                 no-align       44.09       94.38      557.26     1477.00
                    align       44.38       94.18      558.00     1468.25

Kernbench: (make -j N vmlinux, where N = 16 x num_cpus)
                              Elapsed      System        User         CPU
                 no-align       45.53      118.06      560.48     1489.50
                    align       44.84      111.77      560.63     1502.50

Kernbench: (make -j vmlinux, maximal tasks)
                              Elapsed      System        User         CPU
                 no-align       45.17      117.80      560.62     1500.50
                    align       44.94      113.36      560.59     1500.00

diff -urpN -X /home/fletch/.diff.exclude 020-prof_docs/fs/file_table.c 030-align_files_lock/fs/file_table.c
--- 020-prof_docs/fs/file_table.c	Tue Feb 25 23:03:49 2003
+++ 030-align_files_lock/fs/file_table.c	Wed Mar  5 07:49:20 2003
@@ -27,7 +27,7 @@ static LIST_HEAD(anon_list);
 /* And here the free ones sit */
 static LIST_HEAD(free_list);
 /* public *and* exported. Not pretty! */
-spinlock_t files_lock = SPIN_LOCK_UNLOCKED;
+spinlock_t files_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
 
 /* Find an unused file structure and return a pointer to it.
  * Returns NULL, if there are no more free file structures or

[PATCH] 2/6 Make CONFIG_NUMA work on non-numa machines.

[Martin J. Bligh]

>From Andy Whitcroft

A few very simple changes in order to make CONFIG_NUMA work everywhere, so 
the distros can build one common binary kernel for distributions.

diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/Kconfig 013-numa_x86_pc/arch/i386/Kconfig
--- 012-pfn_valid/arch/i386/Kconfig	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/Kconfig	Wed Mar  5 07:41:54 2003
@@ -488,7 +488,7 @@ config NR_CPUS
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation Support"
-	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI && !ACPI_HT_ONLY)))
+	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI && !ACPI_HT_ONLY))) || X86_PC
 
 config DISCONTIGMEM
 	bool
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/kernel/smpboot.c 013-numa_x86_pc/arch/i386/kernel/smpboot.c
--- 012-pfn_valid/arch/i386/kernel/smpboot.c	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/kernel/smpboot.c	Wed Mar  5 07:41:54 2003
@@ -966,6 +966,7 @@ static void __init smp_boot_cpus(unsigne
 		if (APIC_init_uniprocessor())
 			printk(KERN_NOTICE "Local APIC not detected."
 					   " Using dummy APIC emulation.\n");
+		map_cpu_to_logical_apicid();
 		return;
 	}
 
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/mm/discontig.c 013-numa_x86_pc/arch/i386/mm/discontig.c
--- 012-pfn_valid/arch/i386/mm/discontig.c	Wed Mar  5 07:41:52 2003
+++ 013-numa_x86_pc/arch/i386/mm/discontig.c	Wed Mar  5 07:41:54 2003
@@ -82,6 +82,36 @@ void *node_remap_start_vaddr[MAX_NUMNODE
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 /*
+ * FLAT - support for basic PC memory model with discontig enabled, essentially
+ *        a single node with all available processors in it with a flat
+ *        memory map.
+ */
+void __init get_memcfg_numa_flat(void)
+{
+	int pfn;
+
+	printk("NUMA - single node, flat memory mode\n");
+
+	/* Run the memory configuration and find the top of memory. */
+	find_max_pfn();
+	node_start_pfn[0]  = 0;
+	node_end_pfn[0]	  = max_pfn;
+
+	/* Fill in the physnode_map with our simplistic memory model,
+	* all memory is in node 0.
+	*/
+	for (pfn = node_start_pfn[0]; pfn <= node_end_pfn[0];
+	       pfn += PAGES_PER_ELEMENT)
+	{
+		physnode_map[pfn / PAGES_PER_ELEMENT] = 0;
+	}
+
+         /* Indicate there is one node available. */
+	node_set_online(0);
+	numnodes = 1;
+}
+
+/*
  * Find the highest page frame number we have available for the node
  */
 static void __init find_max_pfn_node(int nid)
diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/include/asm-i386/mmzone.h 013-numa_x86_pc/include/asm-i386/mmzone.h
--- 012-pfn_valid/include/asm-i386/mmzone.h	Wed Mar  5 07:41:53 2003
+++ 013-numa_x86_pc/include/asm-i386/mmzone.h	Wed Mar  5 07:41:54 2003
@@ -123,6 +123,9 @@ static inline struct pglist_data *pfn_to
 #include <asm/numaq.h>
 #elif CONFIG_X86_SUMMIT
 #include <asm/srat.h>
+#elif CONFIG_X86_PC
+#define get_memcfg_numa get_memcfg_numa_flat
+#define get_zholes_size(n) (0)
 #else
 #define pfn_to_nid(pfn)		(0)
 #endif /* CONFIG_X86_NUMAQ */

[PATCH] 2/6 Make CONFIG_NUMA work on non-numa machines.

[Martin J. Bligh]

>From Andy Whitcroft

A few very simple changes in order to make CONFIG_NUMA work everywhere, so 
the distros can build one common binary kernel for distributions.

diff -urpN -X /home/fletch/.diff.exclude 012-pfn_valid/arch/i386/Kconfig
013-numa_x86_pc/arch/i386/Kconfig
--- 012-pfn_valid/arch/i386/Kconfig	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/Kconfig	Wed Mar  5 07:41:54 2003
@@ -488,7 +488,7 @@ config NR_CPUS
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation Support"
-	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI &&
!ACPI_HT_ONLY)))
+	depends on (HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT && ACPI &&
!ACPI_HT_ONLY))) || X86_PC
 
 config DISCONTIGMEM
 	bool
diff -urpN -X /home/fletch/.diff.exclude
012-pfn_valid/arch/i386/kernel/smpboot.c
013-numa_x86_pc/arch/i386/kernel/smpboot.c
--- 012-pfn_valid/arch/i386/kernel/smpboot.c	Wed Mar  5 07:36:57 2003
+++ 013-numa_x86_pc/arch/i386/kernel/smpboot.c	Wed Mar  5 07:41:54 2003
@@ -966,6 +966,7 @@ static void __init smp_boot_cpus(unsigne
 		if (APIC_init_uniprocessor())
 			printk(KERN_NOTICE "Local APIC not detected."
 					   " Using dummy APIC emulation.\n");
+		map_cpu_to_logical_apicid();
 		return;
 	}
 
diff -urpN -X /home/fletch/.diff.exclude
012-pfn_valid/arch/i386/mm/discontig.c
013-numa_x86_pc/arch/i386/mm/discontig.c
--- 012-pfn_valid/arch/i386/mm/discontig.c	Wed Mar  5 07:41:52 2003
+++ 013-numa_x86_pc/arch/i386/mm/discontig.c	Wed Mar  5 07:41:54 2003
@@ -82,6 +82,36 @@ void *node_remap_start_vaddr[MAX_NUMNODE
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 /*
+ * FLAT - support for basic PC memory model with discontig enabled,
essentially
+ *        a single node with all available processors in it with a flat
+ *        memory map.
+ */
+void __init get_memcfg_numa_flat(void)
+{
+	int pfn;
+
+	printk("NUMA - single node, flat memory mode\n");
+
+	/* Run the memory configuration and find the top of memory. */
+	find_max_pfn();
+	node_start_pfn[0]  = 0;
+	node_end_pfn[0]	  = max_pfn;
+
+	/* Fill in the physnode_map with our simplistic memory model,
+	* all memory is in node 0.
+	*/
+	for (pfn = node_start_pfn[0]; pfn <= node_end_pfn[0];
+	       pfn += PAGES_PER_ELEMENT)
+	{
+		physnode_map[pfn / PAGES_PER_ELEMENT] = 0;
+	}
+
+         /* Indicate there is one node available. */
+	node_set_online(0);
+	numnodes = 1;
+}
+
+/*
  * Find the highest page frame number we have available for the node
  */
 static void __init find_max_pfn_node(int nid)
diff -urpN -X /home/fletch/.diff.exclude
012-pfn_valid/include/asm-i386/mmzone.h
013-numa_x86_pc/include/asm-i386/mmzone.h
--- 012-pfn_valid/include/asm-i386/mmzone.h	Wed Mar  5 07:41:53 2003
+++ 013-numa_x86_pc/include/asm-i386/mmzone.h	Wed Mar  5 07:41:54 2003
@@ -123,6 +123,9 @@ static inline struct pglist_data *pfn_to
 #include <asm/numaq.h>
 #elif CONFIG_X86_SUMMIT
 #include <asm/srat.h>
+#elif CONFIG_X86_PC
+#define get_memcfg_numa get_memcfg_numa_flat
+#define get_zholes_size(n) (0)
 #else
 #define pfn_to_nid(pfn)		(0)
 #endif /* CONFIG_X86_NUMAQ */