Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (36 commits)
  x86, mm: Correct the implementation of is_untracked_pat_range()
  x86/pat: Trivial: don't create debugfs for memtype if pat is disabled
  x86, mtrr: Fix sorting of mtrr after subtracting
  x86: Move find_smp_config() earlier and avoid bootmem usage
  x86, platform: Change is_untracked_pat_range() to bool; cleanup init
  x86: Change is_ISA_range() into an inline function
  x86, mm: is_untracked_pat_range() takes a normal semiclosed range
  x86, mm: Call is_untracked_pat_range() rather than is_ISA_range()
  x86: UV SGI: Don't track GRU space in PAT
  x86: SGI UV: Fix BAU initialization
  x86, numa: Use near(er) online node instead of roundrobin for NUMA
  x86, numa, bootmem: Only free bootmem on NUMA failure path
  x86: Change crash kernel to reserve via reserve_early()
  x86: Eliminate redundant/contradicting cache line size config options
  x86: When cleaning MTRRs, do not fold WP into UC
  x86: remove "extern" from function prototypes in <asm/proto.h>
  x86, mm: Report state of NX protections during boot
  x86, mm: Clean up and simplify NX enablement
  x86, pageattr: Make set_memory_(x|nx) aware of NX support
  x86, sleep: Always save the value of EFER
  ...

Fix up conflicts (added both iommu_shutdown and is_untracked_pat_range)
to 'struct x86_platform_ops') in
	arch/x86/include/asm/x86_init.h
	arch/x86/kernel/x86_init.c

arch/x86/Kconfig.cpu

@@ -301,15 +301,11 @@ config X86_CPU
 
 #
 # Define implied options from the CPU selection here
-config X86_L1_CACHE_BYTES
+config X86_INTERNODE_CACHE_SHIFT
 	int
-	default "128" if MPSC
-	default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32
-
-config X86_INTERNODE_CACHE_BYTES
-	int
-	default "4096" if X86_VSMP
-	default X86_L1_CACHE_BYTES if !X86_VSMP
+	default "12" if X86_VSMP
+	default "7" if NUMA
+	default X86_L1_CACHE_SHIFT
 
 config X86_CMPXCHG
 	def_bool X86_64 || (X86_32 && !M386)
@@ -317,9 +313,9 @@ config X86_CMPXCHG
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
 	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
 
 config X86_XADD
 	def_bool y

arch/x86/boot/compressed/head_64.S

@@ -107,8 +107,7 @@ ENTRY(startup_32)
 	lgdt	gdt(%ebp)
 
 	/* Enable PAE mode */
-	xorl	%eax, %eax
-	orl	$(X86_CR4_PAE), %eax
+	movl	$(X86_CR4_PAE), %eax
 	movl	%eax, %cr4
 
  /*

arch/x86/boot/compressed/vmlinux.lds.S

@@ -4,6 +4,7 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
 
 #undef i386
 
+#include <asm/cache.h>
 #include <asm/page_types.h>
 
 #ifdef CONFIG_X86_64
@@ -46,7 +47,7 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.bss : {
 		_bss = . ;
 		*(.bss)

arch/x86/include/asm/acpi.h

@@ -118,7 +118,7 @@ extern void acpi_restore_state_mem(void);
 extern unsigned long acpi_wakeup_address;
 
 /* early initialization routine */
-extern void acpi_reserve_bootmem(void);
+extern void acpi_reserve_wakeup_memory(void);
 
 /*
  * Check if the CPU can handle C2 and deeper
@@ -158,6 +158,7 @@ struct bootnode;
 
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
+extern int acpi_get_nodes(struct bootnode *physnodes);
 extern int acpi_scan_nodes(unsigned long start, unsigned long end);
 #define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
 extern void acpi_fake_nodes(const struct bootnode *fake_nodes,

arch/x86/include/asm/cache.h

@@ -9,12 +9,13 @@
 
 #define __read_mostly __attribute__((__section__(".data.read_mostly")))
 
+#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
+#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
+
 #ifdef CONFIG_X86_VSMP
-/* vSMP Internode cacheline shift */
-#define INTERNODE_CACHE_SHIFT (12)
 #ifdef CONFIG_SMP
 #define __cacheline_aligned_in_smp					\
-	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))	\
+	__attribute__((__aligned__(INTERNODE_CACHE_BYTES)))		\
 	__page_aligned_data
 #endif
 #endif

arch/x86/include/asm/cacheflush.h

@@ -177,6 +177,7 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
 #else

arch/x86/include/asm/e820.h

@@ -61,6 +61,12 @@ struct e820map {
 	struct e820entry map[E820_X_MAX];
 };
 
+#define ISA_START_ADDRESS	0xa0000
+#define ISA_END_ADDRESS		0x100000
+
+#define BIOS_BEGIN		0x000a0000
+#define BIOS_END		0x00100000
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
@@ -126,16 +132,19 @@ extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
+
+/*
+ * Returns true iff the specified range [s,e) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 s, u64 e)
+{
+	return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
-#define ISA_START_ADDRESS	0xa0000
-#define ISA_END_ADDRESS		0x100000
-#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
-
-#define BIOS_BEGIN		0x000a0000
-#define BIOS_END		0x00100000
-
 #ifdef __KERNEL__
 #include <linux/ioport.h>
 

arch/x86/include/asm/k8.h

@@ -4,13 +4,16 @@
 #include <linux/pci.h>
 
 extern struct pci_device_id k8_nb_ids[];
+struct bootnode;
 
 extern int early_is_k8_nb(u32 value);
 extern struct pci_dev **k8_northbridges;
 extern int num_k8_northbridges;
 extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
-extern int k8_scan_nodes(unsigned long start, unsigned long end);
+extern int k8_get_nodes(struct bootnode *nodes);
+extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
+extern int k8_scan_nodes(void);
 
 #ifdef CONFIG_K8_NB
 static inline struct pci_dev *node_to_k8_nb_misc(int node)

arch/x86/include/asm/mpspec.h

@@ -71,12 +71,7 @@ static inline void early_get_smp_config(void)
 
 static inline void find_smp_config(void)
 {
-	x86_init.mpparse.find_smp_config(1);
-}
-
-static inline void early_find_smp_config(void)
-{
-	x86_init.mpparse.find_smp_config(0);
+	x86_init.mpparse.find_smp_config();
 }
 
 #ifdef CONFIG_X86_MPPARSE
@@ -89,7 +84,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
 # else
 #  define default_mpc_oem_bus_info NULL
 # endif
-extern void default_find_smp_config(unsigned int reserve);
+extern void default_find_smp_config(void);
 extern void default_get_smp_config(unsigned int early);
 #else
 static inline void early_reserve_e820_mpc_new(void) { }
@@ -97,7 +92,7 @@ static inline void early_reserve_e820_mpc_new(void) { }
 #define default_mpc_apic_id NULL
 #define default_smp_read_mpc_oem NULL
 #define default_mpc_oem_bus_info NULL
-#define default_find_smp_config x86_init_uint_noop
+#define default_find_smp_config x86_init_noop
 #define default_get_smp_config x86_init_uint_noop
 #endif
 

arch/x86/include/asm/page_types.h

@@ -49,7 +49,8 @@ extern unsigned long max_pfn_mapped;
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn,
+				int acpi, int k8);
 extern void free_initmem(void);
 
 #endif	/* !__ASSEMBLY__ */

arch/x86/include/asm/pgtable.h

@@ -16,6 +16,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/x86_init.h>
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -270,9 +272,9 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 					 unsigned long new_flags)
 {
 	/*
-	 * PAT type is always WB for ISA. So no need to check.
+	 * PAT type is always WB for untracked ranges, so no need to check.
 	 */
-	if (is_ISA_range(paddr, paddr + size - 1))
+	if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
 		return 1;
 
 	/*

arch/x86/include/asm/proto.h

@@ -5,18 +5,19 @@
 
 /* misc architecture specific prototypes */
 
-extern void early_idt_handler(void);
+void early_idt_handler(void);
 
-extern void system_call(void);
-extern void syscall_init(void);
+void system_call(void);
+void syscall_init(void);
 
-extern void ia32_syscall(void);
-extern void ia32_cstar_target(void);
-extern void ia32_sysenter_target(void);
+void ia32_syscall(void);
+void ia32_cstar_target(void);
+void ia32_sysenter_target(void);
 
-extern void syscall32_cpu_init(void);
+void syscall32_cpu_init(void);
 
-extern void check_efer(void);
+void x86_configure_nx(void);
+void x86_report_nx(void);
 
 extern int reboot_force;
 

arch/x86/include/asm/sections.h

@@ -2,7 +2,13 @@
 #define _ASM_X86_SECTIONS_H
 
 #include <asm-generic/sections.h>
+#include <asm/uaccess.h>
 
 extern char __brk_base[], __brk_limit[];
+extern struct exception_table_entry __stop___ex_table[];
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+extern char __end_rodata_hpage_align[];
+#endif
 
 #endif	/* _ASM_X86_SECTIONS_H */

arch/x86/include/asm/x86_init.h

@@ -26,7 +26,7 @@ struct x86_init_mpparse {
 	void (*smp_read_mpc_oem)(struct mpc_table *mpc);
 	void (*mpc_oem_pci_bus)(struct mpc_bus *m);
 	void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
-	void (*find_smp_config)(unsigned int reserve);
+	void (*find_smp_config)(void);
 	void (*get_smp_config)(unsigned int early);
 };
 
@@ -125,12 +125,14 @@ struct x86_cpuinit_ops {
  * @calibrate_tsc:		calibrate TSC
  * @get_wallclock:		get time from HW clock like RTC etc.
  * @set_wallclock:		set time back to HW clock
+ * @is_untracked_pat_range	exclude from PAT logic
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
 	unsigned long (*get_wallclock)(void);
 	int (*set_wallclock)(unsigned long nowtime);
 	void (*iommu_shutdown)(void);
+	bool (*is_untracked_pat_range)(u64 start, u64 end);
 };
 
 extern struct x86_init_ops x86_init;

arch/x86/kernel/acpi/sleep.c

@@ -78,12 +78,9 @@ int acpi_save_state_mem(void)
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
-	header->pmode_efer_low = nx_enabled;
-	if (header->pmode_efer_low & 1) {
-		/* This is strange, why not save efer, always? */
-		rdmsr(MSR_EFER, header->pmode_efer_low,
-			header->pmode_efer_high);
-	}
+	if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low,
+		       &header->pmode_efer_high))
+		header->pmode_efer_low = header->pmode_efer_high = 0;
 #endif /* !CONFIG_64BIT */
 
 	header->pmode_cr0 = read_cr0();
@@ -119,29 +116,32 @@ void acpi_restore_state_mem(void)
 
 
 /**
- * acpi_reserve_bootmem - do _very_ early ACPI initialisation
+ * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation
  *
  * We allocate a page from the first 1MB of memory for the wakeup
  * routine for when we come back from a sleep state. The
  * runtime allocator allows specification of <16MB pages, but not
  * <1MB pages.
  */
-void __init acpi_reserve_bootmem(void)
+void __init acpi_reserve_wakeup_memory(void)
 {
+	unsigned long mem;
+
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
 		       "ACPI: Wakeup code way too big, S3 disabled.\n");
 		return;
 	}
 
-	acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE);
+	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (!acpi_realmode) {
+	if (mem == -1L) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
-
-	acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
+	acpi_realmode = (unsigned long) phys_to_virt(mem);
+	acpi_wakeup_address = mem;
+	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 

arch/x86/kernel/apic/numaq_32.c

@@ -263,11 +263,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 
 static __init void early_check_numaq(void)
 {
-	/*
-	 * Find possible boot-time SMP configuration:
-	 */
-	early_find_smp_config();
-
 	/*
 	 * get boot-time SMP configuration:
 	 */

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -30,10 +30,22 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 #include <asm/smp.h>
+#include <asm/x86_init.h>
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
+static u64 gru_start_paddr, gru_end_paddr;
+
+static inline bool is_GRU_range(u64 start, u64 end)
+{
+	return start >= gru_start_paddr && end <= gru_end_paddr;
+}
+
+static bool uv_is_untracked_pat_range(u64 start, u64 end)
+{
+	return is_ISA_range(start, end) || is_GRU_range(start, end);
+}
 
 static int early_get_nodeid(void)
 {
@@ -49,6 +61,7 @@ static int early_get_nodeid(void)
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
+		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		if (!strcmp(oem_table_id, "UVL"))
 			uv_system_type = UV_LEGACY_APIC;
 		else if (!strcmp(oem_table_id, "UVX"))
@@ -385,8 +398,12 @@ static __init void map_gru_high(int max_pnode)
 	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
 
 	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
-	if (gru.s.enable)
+	if (gru.s.enable) {
 		map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
+		gru_start_paddr = ((u64)gru.s.base << shift);
+		gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
+
+	}
 }
 
 static __init void map_mmr_high(int max_pnode)

arch/x86/kernel/cpu/common.c

@@ -1136,7 +1136,7 @@ void __cpuinit cpu_init(void)
 	wrmsrl(MSR_KERNEL_GS_BASE, 0);
 	barrier();
 
-	check_efer();
+	x86_configure_nx();
 	if (cpu != 0)
 		enable_x2apic();
 

arch/x86/kernel/cpu/intel.c

@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
+	if (node == NUMA_NO_NODE)
 		node = first_node(node_online_map);
+	else if (!node_online(node)) {
+		/* reuse the value from init_cpu_to_node() */
+		node = cpu_to_node(cpu);
+	}
 	numa_set_node(cpu, node);
 
 	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);

arch/x86/kernel/cpu/mtrr/cleanup.c

@@ -170,6 +170,41 @@ static int __init cmp_range(const void *x1, const void *x2)
 	return start1 - start2;
 }
 
+static int __init clean_sort_range(struct res_range *range, int az)
+{
+	int i, j, k = az - 1, nr_range = 0;
+
+	for (i = 0; i < k; i++) {
+		if (range[i].end)
+			continue;
+		for (j = k; j > i; j--) {
+			if (range[j].end) {
+				k = j;
+				break;
+			}
+		}
+		if (j == i)
+			break;
+		range[i].start = range[k].start;
+		range[i].end   = range[k].end;
+		range[k].start = 0;
+		range[k].end   = 0;
+		k--;
+	}
+	/* count it */
+	for (i = 0; i < az; i++) {
+		if (!range[i].end) {
+			nr_range = i;
+			break;
+		}
+	}
+
+	/* sort them */
+	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+
+	return nr_range;
+}
+
 #define BIOS_BUG_MSG KERN_WARNING \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
@@ -223,22 +258,18 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 		subtract_range(range, extra_remove_base,
 				 extra_remove_base + extra_remove_size  - 1);
 
-	/* get new range num */
-	nr_range = 0;
-	for (i = 0; i < RANGE_NUM; i++) {
-		if (!range[i].end)
-			continue;
-		nr_range++;
-	}
 	if  (debug_print) {
 		printk(KERN_DEBUG "After UC checking\n");
-		for (i = 0; i < nr_range; i++)
+		for (i = 0; i < RANGE_NUM; i++) {
+			if (!range[i].end)
+				continue;
 			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
 				 range[i].start, range[i].end + 1);
+		}
 	}
 
 	/* sort the ranges */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	nr_range = clean_sort_range(range, RANGE_NUM);
 	if  (debug_print) {
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
@@ -689,8 +720,6 @@ static int __init mtrr_need_cleanup(void)
 			continue;
 		if (!size)
 			type = MTRR_NUM_TYPES;
-		if (type == MTRR_TYPE_WRPROT)
-			type = MTRR_TYPE_UNCACHABLE;
 		num[type]++;
 	}