Merge commit 'v2.6.38-rc4' into x86/cpu

Merge reason: pick up the latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

14 files changed, 77 insertions, 91 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 4a2d4e0c18d..8b5393ec108 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -36,8 +36,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	unsigned cpu = smp_processor_id();
 
 	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 #ifdef CONFIG_SMP
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		percpu_write(cpu_tlbstate.active_mm, next);
@@ -47,6 +45,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Re-load page tables */
 		load_cr3(next->pgd);
 
+		/* stop flush ipis for the previous mm */
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+
 		/*
 		 * load the LDT, if the LDT is different:
 		 */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 2071a8b2b32..ebbc4d8ab17 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -558,13 +558,12 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
 {
-#if PAGETABLE_LEVELS >= 3
 	if (sizeof(pmdval_t) > sizeof(long))
 		/* 5 arg words */
 		pv_mmu_ops.set_pmd_at(mm, addr, pmdp, pmd);
 	else
-		PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp, pmd.pmd);
-#endif
+		PVOP_VCALL4(pv_mmu_ops.set_pmd_at, mm, addr, pmdp,
+			    native_pmd_val(pmd));
 }
 #endif
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 3788f4649db..7e172955ee5 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -273,34 +273,34 @@ do {									\
 	typeof(var) pxo_new__ = (nval);					\
 	switch (sizeof(var)) {						\
 	case 1:								\
-		asm("\n1:mov "__percpu_arg(1)",%%al"			\
-		    "\n\tcmpxchgb %2, "__percpu_arg(1)			\
+		asm("\n\tmov "__percpu_arg(1)",%%al"			\
+		    "\n1:\tcmpxchgb %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
-			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "=&a" (pxo_ret__), "+m" (var)		\
 			    : "q" (pxo_new__)				\
 			    : "memory");				\
 		break;							\
 	case 2:								\
-		asm("\n1:mov "__percpu_arg(1)",%%ax"			\
-		    "\n\tcmpxchgw %2, "__percpu_arg(1)			\
+		asm("\n\tmov "__percpu_arg(1)",%%ax"			\
+		    "\n1:\tcmpxchgw %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
-			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "=&a" (pxo_ret__), "+m" (var)		\
 			    : "r" (pxo_new__)				\
 			    : "memory");				\
 		break;							\
 	case 4:								\
-		asm("\n1:mov "__percpu_arg(1)",%%eax"			\
-		    "\n\tcmpxchgl %2, "__percpu_arg(1)			\
+		asm("\n\tmov "__percpu_arg(1)",%%eax"			\
+		    "\n1:\tcmpxchgl %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
-			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "=&a" (pxo_ret__), "+m" (var)		\
 			    : "r" (pxo_new__)				\
 			    : "memory");				\
 		break;							\
 	case 8:								\
-		asm("\n1:mov "__percpu_arg(1)",%%rax"			\
-		    "\n\tcmpxchgq %2, "__percpu_arg(1)			\
+		asm("\n\tmov "__percpu_arg(1)",%%rax"			\
+		    "\n1:\tcmpxchgq %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
-			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "=&a" (pxo_ret__), "+m" (var)		\
 			    : "r" (pxo_new__)				\
 			    : "memory");				\
 		break;							\
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 3597825a311..bc6f84e11d3 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -47,10 +47,7 @@ DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 /* Static state in head.S used to set up a CPU */
-extern struct {
-	void *sp;
-	unsigned short ss;
-} stack_start;
+extern unsigned long stack_start; /* Initial stack pointer address */
 
 struct smp_ops {
 	void (*smp_prepare_boot_cpu)(void);
diff --git a/arch/x86/include/asm/system_64.h b/arch/x86/include/asm/system_64.h
deleted file mode 100644
index 1159e091ad0..00000000000
--- a/arch/x86/include/asm/system_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_64_H
-#define _ASM_X86_SYSTEM_64_H
-
-#include <asm/segment.h>
-#include <asm/cmpxchg.h>
-
-
-static inline unsigned long read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-
-#include <linux/irqflags.h>
-
-#endif /* _ASM_X86_SYSTEM_64_H */
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 69fd72aa559..68d1537b8c8 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -12,10 +12,8 @@
 #include <linux/cpumask.h>
 #include <asm/segment.h>
 #include <asm/desc.h>
-
-#ifdef CONFIG_X86_32
 #include <asm/pgtable.h>
-#endif
+#include <asm/cacheflush.h>
 
 #include "realmode/wakeup.h"
 #include "sleep.h"
@@ -100,7 +98,7 @@ int acpi_save_state_mem(void)
 #else /* CONFIG_64BIT */
 	header->trampoline_segment = setup_trampoline() >> 4;
 #ifdef CONFIG_SMP
-	stack_start.sp = temp_stack + sizeof(temp_stack);
+	stack_start = (unsigned long)temp_stack + sizeof(temp_stack);
 	early_gdt_descr.address =
 			(unsigned long)get_cpu_gdt_table(smp_processor_id());
 	initial_gs = per_cpu_offset(smp_processor_id());
@@ -149,6 +147,15 @@ void __init acpi_reserve_wakeup_memory(void)
 	memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
+int __init acpi_configure_wakeup_memory(void)
+{
+	if (acpi_realmode)
+		set_memory_x(acpi_realmode, WAKEUP_SIZE >> PAGE_SHIFT);
+
+	return 0;
+}
+arch_initcall(acpi_configure_wakeup_memory);
+
 
 static int __init acpi_sleep_setup(char *str)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 01c0f3ee6cc..bebabec5b44 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -793,13 +793,21 @@ void set_mtrr_aps_delayed_init(void)
 }
 
 /*
- * MTRR initialization for all AP's
+ * Delayed MTRR initialization for all AP's
  */
 void mtrr_aps_init(void)
 {
 	if (!use_intel())
 		return;
 
+	/*
+	 * Check if someone has requested the delay of AP MTRR initialization,
+	 * by doing set_mtrr_aps_delayed_init(), prior to this point. If not,
+	 * then we are done.
+	 */
+	if (!mtrr_aps_delayed_init)
+		return;
+
 	set_mtrr(~0U, 0, 0, 0);
 	mtrr_aps_delayed_init = false;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index e56b9bfbabd..f7a0993c1e7 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -682,7 +682,7 @@ static int p4_validate_raw_event(struct perf_event *event)
 	 * if an event is shared accross the logical threads
 	 * the user needs special permissions to be able to use it
 	 */
-	if (p4_event_bind_map[v].shared) {
+	if (p4_ht_active() && p4_event_bind_map[v].shared) {
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return -EACCES;
 	}
@@ -727,7 +727,8 @@ static int p4_hw_config(struct perf_event *event)
 		event->hw.config = p4_set_ht_bit(event->hw.config);
 
 	if (event->attr.type == PERF_TYPE_RAW) {
-
+		struct p4_event_bind *bind;
+		unsigned int esel;
 		/*
 		 * Clear bits we reserve to be managed by kernel itself
 		 * and never allowed from a user space
@@ -743,6 +744,13 @@ static int p4_hw_config(struct perf_event *event)
 		 * bits since we keep additional info here (for cache events and etc)
 		 */
 		event->hw.config |= event->attr.config;
+		bind = p4_config_get_bind(event->attr.config);
+		if (!bind) {
+			rc = -EINVAL;
+			goto out;
+		}
+		esel = P4_OPCODE_ESEL(bind->opcode);
+		event->hw.config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel));
 	}
 
 	rc = x86_setup_perfctr(event);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 64101335de1..a6b6fcf7f0a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -149,13 +149,13 @@ void dump_trace(struct task_struct *task,
 	unsigned used = 0;
 	struct thread_info *tinfo;
 	int graph = 0;
+	unsigned long dummy;
 	unsigned long bp;
 
 	if (!task)
 		task = current;
 
 	if (!stack) {
-		unsigned long dummy;
 		stack = &dummy;
 		if (task && task != current)
 			stack = (unsigned long *)task->thread.sp;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index fc293dc8dc3..767d6c43de3 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -85,6 +85,8 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE)
  */
 __HEAD
 ENTRY(startup_32)
+	movl pa(stack_start),%ecx
+	
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
 		us to not reload segments */
 	testb $(1<<6), BP_loadflags(%esi)
@@ -99,7 +101,9 @@ ENTRY(startup_32)
 	movl %eax,%es
 	movl %eax,%fs
 	movl %eax,%gs
+	movl %eax,%ss
 2:
+	leal -__PAGE_OFFSET(%ecx),%esp
 
 /*
  * Clear BSS first so that there are no surprises...
@@ -145,8 +149,6 @@ ENTRY(startup_32)
  * _brk_end is set up to point to the first "safe" location.
  * Mappings are created both at virtual address 0 (identity mapping)
  * and PAGE_OFFSET for up to _end.
- *
- * Note that the stack is not yet set up!
  */
 #ifdef CONFIG_X86_PAE
 
@@ -282,6 +284,9 @@ ENTRY(startup_32_smp)
 	movl %eax,%es
 	movl %eax,%fs
 	movl %eax,%gs
+	movl pa(stack_start),%ecx
+	movl %eax,%ss
+	leal -__PAGE_OFFSET(%ecx),%esp
 #endif /* CONFIG_SMP */
 default_entry:
 
@@ -347,8 +352,8 @@ default_entry:
 	movl %eax,%cr0		/* ..and set paging (PG) bit */
 	ljmp $__BOOT_CS,$1f	/* Clear prefetch and normalize %eip */
 1:
-	/* Set up the stack pointer */
-	lss stack_start,%esp
+	/* Shift the stack pointer to a virtual address */
+	addl $__PAGE_OFFSET, %esp
 
 /*
  * Initialize eflags.  Some BIOS's leave bits like NT set.  This would
@@ -360,9 +365,7 @@ default_entry:
 
 #ifdef CONFIG_SMP
 	cmpb $0, ready
-	jz  1f				/* Initial CPU cleans BSS */
-	jmp checkCPUtype
-1:
+	jnz checkCPUtype
 #endif /* CONFIG_SMP */
 
 /*
@@ -470,14 +473,7 @@ is386:	movl $2,%ecx		# set MP
 
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
-#ifdef CONFIG_SMP
-	movb ready, %cl
 	movb $1, ready
-	cmpb $0,%cl		# the first CPU calls start_kernel
-	je   1f
-	movl (stack_start), %esp
-1:
-#endif /* CONFIG_SMP */
 	jmp *(initial_code)
 
 /*
@@ -670,15 +666,15 @@ ENTRY(initial_page_table)
 #endif
 
 .data
+.balign 4
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
-	.long __BOOT_DS
-
-ready:	.byte 0
 
 early_recursion_flag:
 	.long 0
 
+ready:	.byte 0
+
 int_msg:
 	.asciz "Unknown interrupt or fault at: %p %p %p\n"
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a7a3d1acc63..592214d99b4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -620,7 +620,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	 * target processor state.
 	 */
 	startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
-			 (unsigned long)stack_start.sp);
+			 stack_start);
 
 	/*
 	 * Run STARTUP IPI loop.
@@ -767,7 +767,7 @@ do_rest:
 #endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
-	stack_start.sp = (void *) c_idle.idle->thread.sp;
+	stack_start  = c_idle.idle->thread.sp;
 
 	/* start_ip had better be page-aligned! */
 	start_ip = setup_trampoline();
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8b830ca14ac..d343b3c81f3 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -256,7 +256,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 				   unsigned long pfn)
 {
 	pgprot_t forbidden = __pgprot(0);
-	pgprot_t required = __pgprot(0);
 
 	/*
 	 * The BIOS area between 640k and 1Mb needs to be executable for
@@ -282,12 +281,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
 		   __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
-	/*
-	 * .data and .bss should always be writable.
-	 */
-	if (within(address, (unsigned long)_sdata, (unsigned long)_edata) ||
-	    within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop))
-		pgprot_val(required) |= _PAGE_RW;
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
 	/*
@@ -327,7 +320,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 #endif
 
 	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
-	prot = __pgprot(pgprot_val(prot) | pgprot_val(required));
 
 	return prot;
 }
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index ddc81a06edb..fd12d7ce7ff 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -241,21 +241,15 @@ void __init xen_build_dynamic_phys_to_machine(void)
 		 * As long as the mfn_list has enough entries to completely
 		 * fill a p2m page, pointing into the array is ok. But if
 		 * not the entries beyond the last pfn will be undefined.
-		 * And guessing that the 'what-ever-there-is' does not take it
-		 * too kindly when changing it to invalid markers, a new page
-		 * is allocated, initialized and filled with the valid part.
 		 */
 		if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) {
 			unsigned long p2midx;
-			unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_init(p2m);
-
-			for (p2midx = 0; pfn + p2midx < max_pfn; p2midx++) {
-				p2m[p2midx] = mfn_list[pfn + p2midx];
-			}
-			p2m_top[topidx][mididx] = p2m;
-		} else
-			p2m_top[topidx][mididx] = &mfn_list[pfn];
+
+			p2midx = max_pfn % P2M_PER_PAGE;
+			for ( ; p2midx < P2M_PER_PAGE; p2midx++)
+				mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY;
+		}
+		p2m_top[topidx][mididx] = &mfn_list[pfn];
 	}
 
 	m2p_override_init();
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b5a7f928234..a8a66a50d44 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -179,8 +179,13 @@ char * __init xen_memory_setup(void)
 	e820.nr_map = 0;
 	xen_extra_mem_start = mem_end;
 	for (i = 0; i < memmap.nr_entries; i++) {
-		unsigned long long end = map[i].addr + map[i].size;
+		unsigned long long end;
 
+		/* Guard against non-page aligned E820 entries. */
+		if (map[i].type == E820_RAM)
+			map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE;
+
+		end = map[i].addr + map[i].size;
 		if (map[i].type == E820_RAM && end > mem_end) {
 			/* RAM off the end - may be partially included */
 			u64 delta = min(map[i].size, end - mem_end);
@@ -350,6 +355,7 @@ void __init xen_arch_setup(void)
 	boot_cpu_data.hlt_works_ok = 1;
 #endif
 	pm_idle = default_idle;
+	boot_option_idle_override = IDLE_HALT;
 
 	fiddle_vdso();
 }