Merge branch 'x86-mm' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc into x86/mm

10 files changed, 70 insertions, 203 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc6c53a..8db4fbf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1223,6 +1223,10 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
+config HAVE_ARCH_ALLOC_REMAP
+	def_bool y
+	depends on X86_32 && NUMA
+
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
@@ -1231,13 +1235,9 @@ config NEED_NODE_MEMMAP_SIZE
 	def_bool y
 	depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool y
@@ -1247,20 +1247,16 @@ config ARCH_DISCONTIGMEM_DEFAULT
 	def_bool y
 	depends on NUMA && X86_32
 
-config ARCH_PROC_KCORE_TEXT
-	def_bool y
-	depends on X86_64 && PROC_KCORE
-
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool y
+	depends on X86_64
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SPARSEMEM_ENABLE
@@ -1269,6 +1265,10 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+	depends on X86_64 && PROC_KCORE
+
 config ILLEGAL_POINTER_VALUE
        hex
        default 0 if X86_32
@@ -1703,10 +1703,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 	depends on MEMORY_HOTPLUG
 
-config HAVE_ARCH_EARLY_PFN_TO_NID
-	def_bool X86_64
-	depends on NUMA
-
 config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 91f3e087..50c0d30 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -207,8 +207,7 @@ extern const char * const x86_power_flags[32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define cpu_has(c, bit)							\
-	(__builtin_constant_p(bit) &&					\
+#define REQUIRED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
 	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
 	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
@@ -218,10 +217,16 @@ extern const char * const x86_power_flags[32];
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
 	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
 	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )	\
-	  ? 1 :								\
+	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit)							\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
 
+#define this_cpu_has(bit)						\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
+	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index 288b96f..b3f88d7 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -4,36 +4,13 @@
 #ifndef _ASM_X86_MMZONE_64_H
 #define _ASM_X86_MMZONE_64_H
 
-
 #ifdef CONFIG_NUMA
 
 #include <linux/mmdebug.h>
-
 #include <asm/smp.h>
 
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
-	int shift;
-	unsigned int mapsize;
-	s16 *map;
-	s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
 extern struct pglist_data *node_data[];
 
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
-	unsigned nid;
-	VIRTUAL_BUG_ON(!memnodemap);
-	nid = memnodemap[addr >> memnode_shift];
-	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
-	return nid;
-}
-
 #define NODE_DATA(nid)		(node_data[nid])
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d475b43..76042d9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -542,6 +542,33 @@ do {									\
 	old__;								\
 })
 
+static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+                        const unsigned long __percpu *addr)
+{
+	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+	return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+}
+
+static inline int x86_this_cpu_variable_test_bit(int nr,
+                        const unsigned long __percpu *addr)
+{
+	int oldbit;
+
+	asm volatile("bt "__percpu_arg(2)",%1\n\t"
+			"sbb %0,%0"
+			: "=r" (oldbit)
+			: "m" (*(unsigned long *)addr), "Ir" (nr));
+
+	return oldbit;
+}
+
+#define x86_this_cpu_test_bit(nr, addr)			\
+	(__builtin_constant_p((nr))			\
+	 ? x86_this_cpu_constant_test_bit((nr), (addr))	\
+	 : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index fabf01e..2bc503b 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -505,7 +505,7 @@ static void __cpuinit setup_APIC_timer(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
-	if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) {
+	if (this_cpu_has(X86_FEATURE_ARAT)) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
 		/* Make LAPIC timer preferrable over percpu HPET */
 		lapic_clockevent.rating = 150;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9..6b0f4cd 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -355,7 +355,6 @@ static void notify_thresholds(__u64 msr_val)
 static void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
-	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
@@ -367,19 +366,19 @@ static void intel_thermal_interrupt(void)
 				CORE_LEVEL) != 0)
 		mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
 
-	if (cpu_has(c, X86_FEATURE_PLN))
+	if (this_cpu_has(X86_FEATURE_PLN))
 		if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
 					CORE_LEVEL) != 0)
 			mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
 
-	if (cpu_has(c, X86_FEATURE_PTS)) {
+	if (this_cpu_has(X86_FEATURE_PTS)) {
 		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
 		if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
 					THERMAL_THROTTLING_EVENT,
 					PACKAGE_LEVEL) != 0)
 			mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
-		if (cpu_has(c, X86_FEATURE_PLN))
+		if (this_cpu_has(X86_FEATURE_PLN))
 			if (therm_throt_process(msr_val &
 					PACKAGE_THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index d46cbe4..88a90a9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -449,7 +449,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
 	if (!need_resched()) {
-		if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
@@ -465,7 +465,7 @@ static void mwait_idle(void)
 	if (!need_resched()) {
 		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
 		trace_cpu_idle(1, smp_processor_id());
-		if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR))
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2871d3..a3c430b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1332,9 +1332,9 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-	if (!(cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)))
+	if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
 		return;
-	if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH))
+	if (!this_cpu_has(X86_FEATURE_CLFLSH))
 		return;
 	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
 		return;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc..13f5b06 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -28,125 +28,10 @@ EXPORT_SYMBOL(node_data);
 
 nodemask_t numa_nodes_parsed __initdata;
 
-struct memnode memnode;
-
-static unsigned long __initdata nodemap_addr;
-static unsigned long __initdata nodemap_size;
-
 static struct numa_meminfo numa_meminfo __initdata;
-
 static int numa_distance_cnt;
 static u8 *numa_distance;
 
-/*
- * Given a shift value, try to populate memnodemap[]
- * Returns :
- * 1 if OK
- * 0 if memnodmap[] too small (of shift too small)
- * -1 if node overlap or lost ram (shift too big)
- */
-static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift)
-{
-	unsigned long addr, end;
-	int i, res = -1;
-
-	memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
-	for (i = 0; i < mi->nr_blks; i++) {
-		addr = mi->blk[i].start;
-		end = mi->blk[i].end;
-		if (addr >= end)
-			continue;
-		if ((end >> shift) >= memnodemapsize)
-			return 0;
-		do {
-			if (memnodemap[addr >> shift] != NUMA_NO_NODE)
-				return -1;
-			memnodemap[addr >> shift] = mi->blk[i].nid;
-			addr += (1UL << shift);
-		} while (addr < end);
-		res = 1;
-	}
-	return res;
-}
-
-static int __init allocate_cachealigned_memnodemap(void)
-{
-	unsigned long addr;
-
-	memnodemap = memnode.embedded_map;
-	if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
-		return 0;
-
-	addr = 0x8000;
-	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = memblock_find_in_range(addr, get_max_mapped(),
-				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == MEMBLOCK_ERROR) {
-		printk(KERN_ERR
-		       "NUMA: Unable to allocate Memory to Node hash map\n");
-		nodemap_addr = nodemap_size = 0;
-		return -1;
-	}
-	memnodemap = phys_to_virt(nodemap_addr);
-	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
-
-	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
-	       nodemap_addr, nodemap_addr + nodemap_size);
-	return 0;
-}
-
-/*
- * The LSB of all start and end addresses in the node map is the value of the
- * maximum possible shift.
- */
-static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi)
-{
-	int i, nodes_used = 0;
-	unsigned long start, end;
-	unsigned long bitfield = 0, memtop = 0;
-
-	for (i = 0; i < mi->nr_blks; i++) {
-		start = mi->blk[i].start;
-		end = mi->blk[i].end;
-		if (start >= end)
-			continue;
-		bitfield |= start;
-		nodes_used++;
-		if (end > memtop)
-			memtop = end;
-	}
-	if (nodes_used <= 1)
-		i = 63;
-	else
-		i = find_first_bit(&bitfield, sizeof(unsigned long)*8);
-	memnodemapsize = (memtop >> i)+1;
-	return i;
-}
-
-static int __init compute_hash_shift(const struct numa_meminfo *mi)
-{
-	int shift;
-
-	shift = extract_lsb_from_nodes(mi);
-	if (allocate_cachealigned_memnodemap())
-		return -1;
-	printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
-		shift);
-
-	if (populate_memnodemap(mi, shift) != 1) {
-		printk(KERN_INFO "Your memory is not aligned you need to "
-		       "rebuild your kernel with a bigger NODEMAPSIZE "
-		       "shift=%d\n", shift);
-		return -1;
-	}
-	return shift;
-}
-
-int __meminit  __early_pfn_to_nid(unsigned long pfn)
-{
-	return phys_to_nid(pfn << PAGE_SHIFT);
-}
-
 static void * __init early_node_mem(int nodeid, unsigned long start,
 				    unsigned long end, unsigned long size,
 				    unsigned long align)
@@ -270,7 +155,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
-	nid = phys_to_nid(nodedata_phys);
+	nid = early_pfn_to_nid(nodedata_phys >> PAGE_SHIFT);
 	if (nid != nodeid)
 		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
 
@@ -527,12 +412,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	if (WARN_ON(nodes_empty(node_possible_map)))
 		return -EINVAL;
 
-	memnode_shift = compute_hash_shift(mi);
-	if (memnode_shift < 0) {
-		printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n");
-		return -EINVAL;
-	}
-
 	for (i = 0; i < mi->nr_blks; i++)
 		memblock_x86_register_active_regions(mi->blk[i].nid,
 					mi->blk[i].start >> PAGE_SHIFT,
@@ -626,17 +505,13 @@ static int __init numa_init(int (*init_func)(void))
 
 void __init initmem_init(void)
 {
-	int ret;
-
 	if (!numa_off) {
 #ifdef CONFIG_ACPI_NUMA
-		ret = numa_init(x86_acpi_numa_init);
-		if (!ret)
+		if (!numa_init(x86_acpi_numa_init))
 			return;
 #endif
 #ifdef CONFIG_AMD_NUMA
-		ret = numa_init(amd_numa_init);
-		if (!ret)
+		if (!numa_init(amd_numa_init))
 			return;
 #endif
 	}
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index fa84e97..6f2c6d9 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -710,20 +710,14 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr)
 }
 
 #ifdef CONFIG_X86
-static int acpi_throttling_rdmsr(struct acpi_processor *pr,
-					u64 *value)
+static int acpi_throttling_rdmsr(u64 *value)
 {
-	struct cpuinfo_x86 *c;
 	u64 msr_high, msr_low;
-	unsigned int cpu;
 	u64 msr = 0;
 	int ret = -1;
 
-	cpu = pr->id;
-	c = &cpu_data(cpu);
-
-	if ((c->x86_vendor != X86_VENDOR_INTEL) ||
-		!cpu_has(c, X86_FEATURE_ACPI)) {
+	if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) ||
+		!this_cpu_has(X86_FEATURE_ACPI)) {
 		printk(KERN_ERR PREFIX
 			"HARDWARE addr space,NOT supported yet\n");
 	} else {
@@ -738,18 +732,13 @@ static int acpi_throttling_rdmsr(struct acpi_processor *pr,
 	return ret;
 }
 
-static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
+static int acpi_throttling_wrmsr(u64 value)
 {
-	struct cpuinfo_x86 *c;
-	unsigned int cpu;
 	int ret = -1;
 	u64 msr;
 
-	cpu = pr->id;
-	c = &cpu_data(cpu);
-
-	if ((c->x86_vendor != X86_VENDOR_INTEL) ||
-		!cpu_has(c, X86_FEATURE_ACPI)) {
+	if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) ||
+		!this_cpu_has(X86_FEATURE_ACPI)) {
 		printk(KERN_ERR PREFIX
 			"HARDWARE addr space,NOT supported yet\n");
 	} else {
@@ -761,15 +750,14 @@ static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
 	return ret;
 }
 #else
-static int acpi_throttling_rdmsr(struct acpi_processor *pr,
-				u64 *value)
+static int acpi_throttling_rdmsr(u64 *value)
 {
 	printk(KERN_ERR PREFIX
 		"HARDWARE addr space,NOT supported yet\n");
 	return -1;
 }
 
-static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value)
+static int acpi_throttling_wrmsr(u64 value)
 {
 	printk(KERN_ERR PREFIX
 		"HARDWARE addr space,NOT supported yet\n");
@@ -801,7 +789,7 @@ static int acpi_read_throttling_status(struct acpi_processor *pr,
 		ret = 0;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
-		ret = acpi_throttling_rdmsr(pr, value);
+		ret = acpi_throttling_rdmsr(value);
 		break;
 	default:
 		printk(KERN_ERR PREFIX "Unknown addr space %d\n",
@@ -834,7 +822,7 @@ static int acpi_write_throttling_state(struct acpi_processor *pr,
 		ret = 0;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
-		ret = acpi_throttling_wrmsr(pr, value);
+		ret = acpi_throttling_wrmsr(value);
 		break;
 	default:
 		printk(KERN_ERR PREFIX "Unknown addr space %d\n",