Merge x86-64 update from Andi

4060994c · Linus Torvalds <[email protected]> · 2005-11-14 19:56:02 -08:00

Commit: 4060994c3e337b40e0f6fa8ce2cc178e021baf3d
Parents: 0174f72f · d3ee871e

Merge commit. Changes below are compared with the first parent: 0174f72f.

Changes

82 files changed · +1481 −1097

File	Status	Add	Del	Content
Documentation/x86_64/boot-options.txt	modified	+10	−2	View file
Documentation/x86_64/mm.txt	modified	+5	−1	View file
arch/i386/kernel/acpi/boot.c	modified	+8	−9	View file
arch/i386/kernel/cpu/amd.c	modified	+6	−6	View file
arch/i386/kernel/cpu/common.c	modified	+16	−24	View file
arch/i386/kernel/cpu/intel.c	modified	+1	−1	View file
arch/i386/kernel/cpu/intel_cacheinfo.c	modified	+32	−14	View file
arch/i386/kernel/cpu/mtrr/main.c	modified	+8	−0	View file
arch/i386/kernel/cpu/proc.c	modified	+3	−4	View file
arch/i386/kernel/smpboot.c	modified	+53	−20	View file
arch/i386/kernel/srat.c	modified	+2	−2	View file
arch/ia64/Kconfig	modified	+4	−0	View file
arch/x86_64/Kconfig	modified	+41	−16	View file
arch/x86_64/Kconfig.debug	modified	+0	−9	View file
arch/x86_64/defconfig	modified	+83	−15	View file
arch/x86_64/ia32/ia32_aout.c	modified	+0	−3	View file
arch/x86_64/ia32/ia32_binfmt.c	modified	+3	−1	View file
arch/x86_64/kernel/Makefile	modified	+1	−0	View file
arch/x86_64/kernel/aperture.c	modified	+1	−1	View file
arch/x86_64/kernel/apic.c	modified	+10	−0	View file
arch/x86_64/kernel/e820.c	modified	+1	−2	View file
arch/x86_64/kernel/entry.S	modified	+3	−0	View file
arch/x86_64/kernel/head.S	modified	+23	−14	View file
arch/x86_64/kernel/head64.c	modified	+10	−4	View file
arch/x86_64/kernel/i8259.c	modified	+2	−0	View file
arch/x86_64/kernel/io_apic.c	modified	+73	−7	View file
arch/x86_64/kernel/mce.c	modified	+12	−5	View file
arch/x86_64/kernel/mce_amd.c	added	+538	−0	View file
arch/x86_64/kernel/mpparse.c	modified	+15	−8	View file
arch/x86_64/kernel/pci-gart.c	modified	+7	−1	View file
arch/x86_64/kernel/process.c	modified	+27	−20	View file
arch/x86_64/kernel/reboot.c	modified	+4	−3	View file
arch/x86_64/kernel/setup.c	modified	+41	−48	View file
arch/x86_64/kernel/setup64.c	modified	+1	−1	View file
arch/x86_64/kernel/signal.c	modified	+17	−0	View file
arch/x86_64/kernel/smp.c	modified	+3	−4	View file
arch/x86_64/kernel/smpboot.c	modified	+91	−20	View file
arch/x86_64/kernel/sys_x86_64.c	modified	+0	−14	View file
arch/x86_64/kernel/traps.c	modified	+4	−40	View file
arch/x86_64/kernel/vmlinux.lds.S	modified	+1	−1	View file
arch/x86_64/kernel/x8664_ksyms.c	modified	+3	−0	View file
arch/x86_64/lib/clear_page.S	modified	+0	−38	View file
arch/x86_64/lib/copy_page.S	modified	+0	−87	View file
arch/x86_64/lib/memcpy.S	modified	+2	−91	View file
arch/x86_64/lib/memset.S	modified	+0	−94	View file
arch/x86_64/mm/fault.c	modified	+7	−12	View file
arch/x86_64/mm/init.c	modified	+79	−50	View file
arch/x86_64/mm/k8topology.c	modified	+1	−0	View file
arch/x86_64/mm/numa.c	modified	+73	−49	View file
arch/x86_64/mm/srat.c	modified	+1	−5	View file
drivers/char/agp/amd64-agp.c	modified	+14	−3	View file
include/asm-generic/sections.h	modified	+1	−0	View file
include/asm-i386/mach-default/mach_reboot.h	modified	+1	−1	View file
include/asm-i386/processor.h	modified	+3	−1	View file
include/asm-x86_64/apic.h	modified	+2	−0	View file
include/asm-x86_64/cache.h	modified	+1	−1	View file
include/asm-x86_64/desc.h	modified	+3	−0	View file
include/asm-x86_64/dma.h	modified	+9	−2	View file
include/asm-x86_64/hpet.h	modified	+21	−14	View file
include/asm-x86_64/hw_irq.h	modified	+1	−1	View file
include/asm-x86_64/ia32.h	modified	+5	−0	View file
include/asm-x86_64/mce.h	modified	+10	−0	View file
include/asm-x86_64/mmzone.h	modified	+3	−6	View file
include/asm-x86_64/mpspec.h	modified	+4	−3	View file
include/asm-x86_64/msr.h	modified	+1	−1	View file
include/asm-x86_64/numa.h	modified	+2	−0	View file
include/asm-x86_64/page.h	modified	+1	−1	View file
include/asm-x86_64/pda.h	modified	+1	−0	View file
include/asm-x86_64/pgtable.h	modified	+3	−2	View file
include/asm-x86_64/processor.h	modified	+3	−1	View file
include/asm-x86_64/proto.h	modified	+4	−0	View file
include/asm-x86_64/rwsem.h	deleted	+0	−283	View before deletion
include/asm-x86_64/smp.h	modified	+2	−1	View file
include/asm-x86_64/spinlock.h	modified	+6	−6	View file
include/asm-x86_64/topology.h	modified	+2	−0	View file
include/asm-x86_64/unistd.h	modified	+2	−1	View file
include/linux/bitops.h	modified	+10	−0	View file
include/linux/gfp.h	modified	+11	−0	View file
include/linux/mm.h	modified	+2	−8	View file
include/linux/mmzone.h	modified	+12	−8	View file
mm/filemap.c	modified	+1	−1	View file
mm/page_alloc.c	modified	+14	−6	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/x86_64/boot-options.txt

View file

diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt
index ffe1c06..e566aff 100644
--- a/Documentation/x86_64/boot-options.txt
+++ b/Documentation/x86_64/boot-options.txt
@@ -7,10 +7,12 @@ Machine check
 
    mce=off disable machine check
    mce=bootlog Enable logging of machine checks left over from booting.
-               Disabled by default because some BIOS leave bogus ones.
+               Disabled by default on AMD because some BIOS leave bogus ones.
                If your BIOS doesn't do that it's a good idea to enable though
                to make sure you log even machine check events that result
-               in a reboot.
+               in a reboot. On Intel systems it is enabled by default.
+   mce=nobootlog
+		Disable boot machine check logging.
    mce=tolerancelevel (number)
 		0: always panic, 1: panic if deadlock possible,
 		2: try to avoid panic, 3: never panic or exit (for testing)
@@ -122,6 +124,9 @@ SMP
 
   cpumask=MASK   only use cpus with bits set in mask
 
+  additional_cpus=NUM Allow NUM more CPUs for hotplug
+		 (defaults are specified by the BIOS or half the available CPUs)
+
 NUMA
 
   numa=off	Only set up a single NUMA node spanning all memory.
@@ -188,6 +193,9 @@ Debugging
 
   kstack=N   Print that many words from the kernel stack in oops dumps.
 
+  pagefaulttrace Dump all page faults. Only useful for extreme debugging
+		and will create a lot of output.
+
 Misc
 
   noreplacement  Don't replace instructions with more appropiate ones

Documentation/x86_64/mm.txt

View file

diff --git a/Documentation/x86_64/mm.txt b/Documentation/x86_64/mm.txt
index 662b739..133561b 100644
--- a/Documentation/x86_64/mm.txt
+++ b/Documentation/x86_64/mm.txt
@@ -6,7 +6,7 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46bits) direct mapping of phys. memory
+ffff810000000000 - ffffc0ffffffffff (=46bits) direct mapping of all phys. memory
 ffffc10000000000 - ffffc1ffffffffff (=40bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45bits) vmalloc/ioremap space
 ... unused hole ...
@@ -14,6 +14,10 @@ ffffffff80000000 - ffffffff82800000 (=40MB)   kernel text mapping, from phys 0
 ... unused hole ...
 ffffffff88000000 - fffffffffff00000 (=1919MB) module mapping space
 
+The direct mapping covers all memory in the system upto the highest
+memory address (this means in some cases it can also include PCI memory
+holes)
+
 vmalloc space is lazily synchronized into the different PML4 pages of
 the processes using the page fault handler, with init_level4_pgt as
 reference.

arch/i386/kernel/acpi/boot.c

View file

diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index b66c13c..f366772 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -39,17 +39,14 @@
 
 #ifdef	CONFIG_X86_64
 
-static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-}
 extern void __init clustered_apic_check(void);
-static inline int ioapic_setup_disabled(void)
-{
-	return 0;
-}
 
+extern int gsi_irq_sharing(int gsi);
 #include <asm/proto.h>
 
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return 0; }
+
+
 #else				/* X86 */
 
 #ifdef	CONFIG_X86_LOCAL_APIC
@@ -57,6 +54,8 @@ static inline int ioapic_setup_disabled(void)
 #include <mach_mpparse.h>
 #endif				/* CONFIG_X86_LOCAL_APIC */
 
+static inline int gsi_irq_sharing(int gsi) { return gsi; }
+
 #endif				/* X86 */
 
 #define BAD_MADT_ENTRY(entry, end) (					    \
@@ -459,7 +458,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
 		*irq = IO_APIC_VECTOR(gsi);
 	else
 #endif
-		*irq = gsi;
+		*irq = gsi_irq_sharing(gsi);
 	return 0;
 }
 
@@ -543,7 +542,7 @@ acpi_scan_rsdp(unsigned long start, unsigned long length)
 	 * RSDP signature.
 	 */
 	for (offset = 0; offset < length; offset += 16) {
-		if (strncmp((char *)(start + offset), "RSD PTR ", sig_len))
+		if (strncmp((char *)(phys_to_virt(start) + offset), "RSD PTR ", sig_len))
 			continue;
 		return (start + offset);
 	}

arch/i386/kernel/cpu/amd.c

View file

diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index 53a1681..e344ef8 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -206,9 +206,9 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 	display_cacheinfo(c);
 
 	if (cpuid_eax(0x80000000) >= 0x80000008) {
-		c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
-		if (c->x86_num_cores & (c->x86_num_cores - 1))
-			c->x86_num_cores = 1;
+		c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+		if (c->x86_max_cores & (c->x86_max_cores - 1))
+			c->x86_max_cores = 1;
 	}
 
 #ifdef CONFIG_X86_HT
@@ -217,15 +217,15 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 	 * distingush the cores.  Assumes number of cores is a power
 	 * of two.
 	 */
-	if (c->x86_num_cores > 1) {
+	if (c->x86_max_cores > 1) {
 		int cpu = smp_processor_id();
 		unsigned bits = 0;
-		while ((1 << bits) < c->x86_num_cores)
+		while ((1 << bits) < c->x86_max_cores)
 			bits++;
 		cpu_core_id[cpu] = phys_proc_id[cpu] & ((1<<bits)-1);
 		phys_proc_id[cpu] >>= bits;
 		printk(KERN_INFO "CPU %d(%d) -> Core %d\n",
-		       cpu, c->x86_num_cores, cpu_core_id[cpu]);
+		       cpu, c->x86_max_cores, cpu_core_id[cpu]);
 	}
 #endif
 }

arch/i386/kernel/cpu/common.c

View file

diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index c145fb3..31e344b 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -231,10 +231,10 @@ static void __init early_cpu_detect(void)
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
 		c->x86 = (tfms >> 8) & 15;
 		c->x86_model = (tfms >> 4) & 15;
-		if (c->x86 == 0xf) {
+		if (c->x86 == 0xf)
 			c->x86 += (tfms >> 20) & 0xff;
+		if (c->x86 >= 0x6)
 			c->x86_model += ((tfms >> 16) & 0xF) << 4;
-		}
 		c->x86_mask = tfms & 15;
 		if (cap0 & (1<<19))
 			c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
@@ -333,7 +333,7 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
-	c->x86_num_cores = 1;
+	c->x86_max_cores = 1;
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 
 	if (!have_cpuid_p()) {
@@ -443,52 +443,44 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 void __devinit detect_ht(struct cpuinfo_x86 *c)
 {
 	u32 	eax, ebx, ecx, edx;
-	int 	index_msb, tmp;
+	int 	index_msb, core_bits;
 	int 	cpu = smp_processor_id();
 
+	cpuid(1, &eax, &ebx, &ecx, &edx);
+
+	c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0);
+
 	if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
 		return;
 
-	cpuid(1, &eax, &ebx, &ecx, &edx);
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
 	if (smp_num_siblings == 1) {
 		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
 	} else if (smp_num_siblings > 1 ) {
-		index_msb = 31;
 
 		if (smp_num_siblings > NR_CPUS) {
 			printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings);
 			smp_num_siblings = 1;
 			return;
 		}
-		tmp = smp_num_siblings;
-		while ((tmp & 0x80000000 ) == 0) {
-			tmp <<=1 ;
-			index_msb--;
-		}
-		if (smp_num_siblings & (smp_num_siblings - 1))
-			index_msb++;
+
+		index_msb = get_count_order(smp_num_siblings);
 		phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
 
 		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
 		       phys_proc_id[cpu]);
 
-		smp_num_siblings = smp_num_siblings / c->x86_num_cores;
+		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
 
-		tmp = smp_num_siblings;
-		index_msb = 31;
-		while ((tmp & 0x80000000) == 0) {
-			tmp <<=1 ;
-			index_msb--;
-		}
+		index_msb = get_count_order(smp_num_siblings) ;
 
-		if (smp_num_siblings & (smp_num_siblings - 1))
-			index_msb++;
+		core_bits = get_count_order(c->x86_max_cores);
 
-		cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
+		cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) &
+					       ((1 << core_bits) - 1);
 
-		if (c->x86_num_cores > 1)
+		if (c->x86_max_cores > 1)
 			printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
 			       cpu_core_id[cpu]);
 	}

arch/i386/kernel/cpu/intel.c

View file

diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c
index c28d26f..5e2da70 100644
--- a/arch/i386/kernel/cpu/intel.c
+++ b/arch/i386/kernel/cpu/intel.c
@@ -158,7 +158,7 @@ static void __devinit init_intel(struct cpuinfo_x86 *c)
 	if ( p )
 		strcpy(c->x86_model_id, p);
 	
-	c->x86_num_cores = num_cpu_cores(c);
+	c->x86_max_cores = num_cpu_cores(c);
 
 	detect_ht(c);
 

arch/i386/kernel/cpu/intel_cacheinfo.c

View file

diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
index 4dc42a1..fbfd374 100644
--- a/arch/i386/kernel/cpu/intel_cacheinfo.c
+++ b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -293,29 +293,45 @@ static struct _cpuid4_info *cpuid4_info[NR_CPUS];
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf;
+	struct _cpuid4_info	*this_leaf, *sibling_leaf;
 	unsigned long num_threads_sharing;
-#ifdef CONFIG_X86_HT
-	struct cpuinfo_x86 *c = cpu_data + cpu;
-#endif
+	int index_msb, i;
+	struct cpuinfo_x86 *c = cpu_data;
 
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
 
 	if (num_threads_sharing == 1)
 		cpu_set(cpu, this_leaf->shared_cpu_map);
-#ifdef CONFIG_X86_HT
-	else if (num_threads_sharing == smp_num_siblings)
-		this_leaf->shared_cpu_map = cpu_sibling_map[cpu];
-	else if (num_threads_sharing == (c->x86_num_cores * smp_num_siblings))
-		this_leaf->shared_cpu_map = cpu_core_map[cpu];
-	else
-		printk(KERN_DEBUG "Number of CPUs sharing cache didn't match "
-				"any known set of CPUs\n");
-#endif
+	else {
+		index_msb = get_count_order(num_threads_sharing);
+
+		for_each_online_cpu(i) {
+			if (c[i].apicid >> index_msb ==
+			    c[cpu].apicid >> index_msb) {
+				cpu_set(i, this_leaf->shared_cpu_map);
+				if (i != cpu && cpuid4_info[i])  {
+					sibling_leaf = CPUID4_INFO_IDX(i, index);
+					cpu_set(cpu, sibling_leaf->shared_cpu_map);
+				}
+			}
+		}
+	}
+}
+static void __devinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+{
+	struct _cpuid4_info	*this_leaf, *sibling_leaf;
+	int sibling;
+
+	this_leaf = CPUID4_INFO_IDX(cpu, index);
+	for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) {
+		sibling_leaf = CPUID4_INFO_IDX(sibling, index);	
+		cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+	}
 }
 #else
 static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
+static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
 #endif
 
 static void free_cache_attributes(unsigned int cpu)
@@ -574,8 +590,10 @@ static void __cpuexit cache_remove_dev(struct sys_device * sys_dev)
 	unsigned int cpu = sys_dev->id;
 	unsigned long i;
 
-	for (i = 0; i < num_cache_leaves; i++)
+	for (i = 0; i < num_cache_leaves; i++) {
+		cache_remove_shared_cpu_map(cpu, i);
 		kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
+	}
 	kobject_unregister(cache_kobject[cpu]);
 	cpuid4_cache_sysfs_exit(cpu);
 	return;

arch/i386/kernel/cpu/mtrr/main.c

View file

diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index dd4ebd6..1e9db19 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -626,6 +626,14 @@ void __init mtrr_bp_init(void)
 		if (cpuid_eax(0x80000000) >= 0x80000008) {
 			u32 phys_addr;
 			phys_addr = cpuid_eax(0x80000008) & 0xff;
+			/* CPUID workaround for Intel 0F33/0F34 CPU */
+			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+			    boot_cpu_data.x86 == 0xF &&
+			    boot_cpu_data.x86_model == 0x3 &&
+			    (boot_cpu_data.x86_mask == 0x3 ||
+			     boot_cpu_data.x86_mask == 0x4))
+				phys_addr = 36;
+
 			size_or_mask = ~((1 << (phys_addr - PAGE_SHIFT)) - 1);
 			size_and_mask = ~size_or_mask & 0xfff00000;
 		} else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR &&

arch/i386/kernel/cpu/proc.c

View file

diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c
index 41b871e..e792131 100644
--- a/arch/i386/kernel/cpu/proc.c
+++ b/arch/i386/kernel/cpu/proc.c
@@ -94,12 +94,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (c->x86_cache_size >= 0)
 		seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
 #ifdef CONFIG_X86_HT
-	if (c->x86_num_cores * smp_num_siblings > 1) {
+	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", phys_proc_id[n]);
-		seq_printf(m, "siblings\t: %d\n",
-				c->x86_num_cores * smp_num_siblings);
+		seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[n]));
 		seq_printf(m, "core id\t\t: %d\n", cpu_core_id[n]);
-		seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores);
+		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	}
 #endif
 	

arch/i386/kernel/smpboot.c

View file

diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index bc5a9d9..d16520d 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -72,9 +72,11 @@ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
 /* Core ID of each logical CPU */
 int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
 
+/* representing HT siblings of each logical CPU */
 cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_sibling_map);
 
+/* representing HT and core siblings of each logical CPU */
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
@@ -442,35 +444,60 @@ static void __devinit smp_callin(void)
 
 static int cpucount;
 
+/* representing cpus for which sibling maps can be computed */
+static cpumask_t cpu_sibling_setup_map;
+
 static inline void
 set_cpu_sibling_map(int cpu)
 {
 	int i;
+	struct cpuinfo_x86 *c = cpu_data;
+
+	cpu_set(cpu, cpu_sibling_setup_map);
 
 	if (smp_num_siblings > 1) {
-		for (i = 0; i < NR_CPUS; i++) {
-			if (!cpu_isset(i, cpu_callout_map))
-				continue;
-			if (cpu_core_id[cpu] == cpu_core_id[i]) {
+		for_each_cpu_mask(i, cpu_sibling_setup_map) {
+			if (phys_proc_id[cpu] == phys_proc_id[i] &&
+			    cpu_core_id[cpu] == cpu_core_id[i]) {
 				cpu_set(i, cpu_sibling_map[cpu]);
 				cpu_set(cpu, cpu_sibling_map[i]);
+				cpu_set(i, cpu_core_map[cpu]);
+				cpu_set(cpu, cpu_core_map[i]);
 			}
 		}
 	} else {
 		cpu_set(cpu, cpu_sibling_map[cpu]);
 	}
 
-	if (current_cpu_data.x86_num_cores > 1) {
-		for (i = 0; i < NR_CPUS; i++) {
-			if (!cpu_isset(i, cpu_callout_map))
-				continue;
-			if (phys_proc_id[cpu] == phys_proc_id[i]) {
-				cpu_set(i, cpu_core_map[cpu]);
-				cpu_set(cpu, cpu_core_map[i]);
-			}
-		}
-	} else {
+	if (current_cpu_data.x86_max_cores == 1) {
 		cpu_core_map[cpu] = cpu_sibling_map[cpu];
+		c[cpu].booted_cores = 1;
+		return;
+	}
+
+	for_each_cpu_mask(i, cpu_sibling_setup_map) {
+		if (phys_proc_id[cpu] == phys_proc_id[i]) {
+			cpu_set(i, cpu_core_map[cpu]);
+			cpu_set(cpu, cpu_core_map[i]);
+			/*
+			 *  Does this new cpu bringup a new core?
+			 */
+			if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+				/*
+				 * for each core in package, increment
+				 * the booted_cores for this new cpu
+				 */
+				if (first_cpu(cpu_sibling_map[i]) == i)
+					c[cpu].booted_cores++;
+				/*
+				 * increment the core count for all
+				 * the other cpus in this package
+				 */
+				if (i != cpu)
+					c[i].booted_cores++;
+			} else if (i != cpu && !c[cpu].booted_cores)
+				c[cpu].booted_cores = c[i].booted_cores;
+		}
 	}
 }
 
@@ -1095,11 +1122,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 
 	current_thread_info()->cpu = 0;
 	smp_tune_scheduling();
-	cpus_clear(cpu_sibling_map[0]);
-	cpu_set(0, cpu_sibling_map[0]);
 
-	cpus_clear(cpu_core_map[0]);
-	cpu_set(0, cpu_core_map[0]);
+	set_cpu_sibling_map(0);
 
 	/*
 	 * If we couldn't find an SMP configuration at boot time,
@@ -1278,15 +1302,24 @@ static void
 remove_siblinginfo(int cpu)
 {
 	int sibling;
+	struct cpuinfo_x86 *c = cpu_data;
 
+	for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
+		cpu_clear(cpu, cpu_core_map[sibling]);
+		/*
+		 * last thread sibling in this cpu core going down
+		 */
+		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+			c[sibling].booted_cores--;
+	}
+			
 	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
 		cpu_clear(cpu, cpu_sibling_map[sibling]);
-	for_each_cpu_mask(sibling, cpu_core_map[cpu])
-		cpu_clear(cpu, cpu_core_map[sibling]);
 	cpus_clear(cpu_sibling_map[cpu]);
 	cpus_clear(cpu_core_map[cpu]);
 	phys_proc_id[cpu] = BAD_APICID;
 	cpu_core_id[cpu] = BAD_APICID;
+	cpu_clear(cpu, cpu_sibling_setup_map);
 }
 
 int __cpu_disable(void)

arch/i386/kernel/srat.c

View file

diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c
index 8de658d..52b3ed5 100644
--- a/arch/i386/kernel/srat.c
+++ b/arch/i386/kernel/srat.c
@@ -137,8 +137,8 @@ static void __init parse_memory_affinity_structure (char *sratp)
 		 "enabled and removable" : "enabled" ) );
 }
 
-#if MAX_NR_ZONES != 3
-#error "MAX_NR_ZONES != 3, chunk_to_zone requires review"
+#if MAX_NR_ZONES != 4
+#error "MAX_NR_ZONES != 4, chunk_to_zone requires review"
 #endif
 /* Take a chunk of pages from page frame cstart to cend and count the number
  * of pages in each zone, returned via zones[].

arch/ia64/Kconfig

View file

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 8796e12..b76ce1f 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -58,6 +58,10 @@ config IA64_UNCACHED_ALLOCATOR
 	bool
 	select GENERIC_ALLOCATOR
 
+config ZONE_DMA_IS_DMA32
+	bool
+	default y
+
 choice
 	prompt "System type"
 	default IA64_GENERIC

arch/x86_64/Kconfig

View file

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 4cce2f6..6ece645 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -226,22 +226,42 @@ config SCHED_SMT
 
 source "kernel/Kconfig.preempt"
 
-config K8_NUMA
-       bool "K8 NUMA support"
-       select NUMA
+config NUMA
+       bool "Non Uniform Memory Access (NUMA) Support"
        depends on SMP
        help
-	  Enable NUMA (Non Unified Memory Architecture) support for
-	  AMD Opteron Multiprocessor systems. The kernel will try to allocate
-	  memory used by a CPU on the local memory controller of the CPU
-	  and add some more NUMA awareness to the kernel.
-	  This code is recommended on all multiprocessor Opteron systems
-	  and normally doesn't hurt on others.
+	 Enable NUMA (Non Uniform Memory Access) support. The kernel 
+	 will try to allocate memory used by a CPU on the local memory 
+	 controller of the CPU and add some more NUMA awareness to the kernel.
+	 This code is recommended on all multiprocessor Opteron systems.
+	 If the system is EM64T, you should say N unless your system is EM64T 
+	 NUMA. 
+
+config K8_NUMA
+       bool "Old style AMD Opteron NUMA detection"
+       depends on NUMA
+       default y
+       help
+	 Enable K8 NUMA node topology detection.  You should say Y here if
+	 you have a multi processor AMD K8 system. This uses an old
+	 method to read the NUMA configurtion directly from the builtin
+	 Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA
+	 instead, which also takes priority if both are compiled in.   
+
+# Dummy CONFIG option to select ACPI_NUMA from drivers/acpi/Kconfig.
+
+config X86_64_ACPI_NUMA
+       bool "ACPI NUMA detection"
+       depends on NUMA
+       select ACPI 
+       select ACPI_NUMA
+       default y
+       help
+	 Enable ACPI SRAT based node topology detection.
 
 config NUMA_EMU
-	bool "NUMA emulation support"
-	select NUMA
-	depends on SMP
+	bool "NUMA emulation"
+	depends on NUMA
 	help
 	  Enable NUMA emulation. A flat machine will be split
 	  into virtual nodes when booted with "numa=fake=N", where N is the
@@ -252,9 +272,6 @@ config ARCH_DISCONTIGMEM_ENABLE
        depends on NUMA
        default y
 
-config NUMA
-       bool
-       default n
 
 config ARCH_DISCONTIGMEM_ENABLE