Merge branch 'master' of

git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-2.6.33.y

Conflicts:
	Makefile

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

15 files changed, 106 insertions, 66 deletions

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 4fddc509e78e..6b84a0471171 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -170,8 +170,8 @@ not_angel:
 
 		.text
 		adr	r0, LC0
- ARM(		ldmia	r0, {r1, r2, r3, r4, r5, r6, ip, sp}	)
- THUMB(		ldmia	r0, {r1, r2, r3, r4, r5, r6, ip}	)
+ ARM(		ldmia	r0, {r1, r2, r3, r4, r5, r6, r11, ip, sp})
+ THUMB(		ldmia	r0, {r1, r2, r3, r4, r5, r6, r11, ip}	)
  THUMB(		ldr	sp, [r0, #28]				)
 		subs	r0, r0, r1		@ calculate the delta offset
 
@@ -182,12 +182,13 @@ not_angel:
 		/*
 		 * We're running at a different address.  We need to fix
 		 * up various pointers:
-		 *   r5 - zImage base address
-		 *   r6 - GOT start
+		 *   r5 - zImage base address (_start)
+		 *   r6 - size of decompressed image
+		 *   r11 - GOT start
 		 *   ip - GOT end
 		 */
 		add	r5, r5, r0
-		add	r6, r6, r0
+		add	r11, r11, r0
 		add	ip, ip, r0
 
 #ifndef CONFIG_ZBOOT_ROM
@@ -205,10 +206,10 @@ not_angel:
 		/*
 		 * Relocate all entries in the GOT table.
 		 */
-1:		ldr	r1, [r6, #0]		@ relocate entries in the GOT
+1:		ldr	r1, [r11, #0]		@ relocate entries in the GOT
 		add	r1, r1, r0		@ table.  This fixes up the
-		str	r1, [r6], #4		@ C references.
-		cmp	r6, ip
+		str	r1, [r11], #4		@ C references.
+		cmp	r11, ip
 		blo	1b
 #else
 
@@ -216,12 +217,12 @@ not_angel:
 		 * Relocate entries in the GOT table.  We only relocate
 		 * the entries that are outside the (relocated) BSS region.
 		 */
-1:		ldr	r1, [r6, #0]		@ relocate entries in the GOT
+1:		ldr	r1, [r11, #0]		@ relocate entries in the GOT
 		cmp	r1, r2			@ entry < bss_start ||
 		cmphs	r3, r1			@ _end < entry
 		addlo	r1, r1, r0		@ table.  This fixes up the
-		str	r1, [r6], #4		@ C references.
-		cmp	r6, ip
+		str	r1, [r11], #4		@ C references.
+		cmp	r11, ip
 		blo	1b
 #endif
 
@@ -247,6 +248,7 @@ not_relocated:	mov	r0, #0
  * Check to see if we will overwrite ourselves.
  *   r4 = final kernel address
  *   r5 = start of this image
+ *   r6 = size of decompressed image
  *   r2 = end of malloc space (and therefore this image)
  * We basically want:
  *   r4 >= r2 -> OK
@@ -254,8 +256,7 @@ not_relocated:	mov	r0, #0
  */
 		cmp	r4, r2
 		bhs	wont_overwrite
-		sub	r3, sp, r5		@ > compressed kernel size
-		add	r0, r4, r3, lsl #2	@ allow for 4x expansion
+		add	r0, r4, r6
 		cmp	r0, r5
 		bls	wont_overwrite
 
@@ -271,7 +272,6 @@ not_relocated:	mov	r0, #0
  * r1-r3  = unused
  * r4     = kernel execution address
  * r5     = decompressed kernel start
- * r6     = processor ID
  * r7     = architecture ID
  * r8     = atags pointer
  * r9-r12,r14 = corrupted
@@ -312,7 +312,8 @@ LC0:		.word	LC0			@ r1
 		.word	_end			@ r3
 		.word	zreladdr		@ r4
 		.word	_start			@ r5
-		.word	_got_start		@ r6
+		.word	_image_size		@ r6
+		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	user_stack+4096		@ sp
 LC1:		.word	reloc_end - reloc_start
@@ -336,7 +337,6 @@ params:		ldr	r0, =params_phys
  *
  * On entry,
  *  r4 = kernel execution address
- *  r6 = processor ID
  *  r7 = architecture number
  *  r8 = atags pointer
  *  r9 = run-time address of "start"  (???)
@@ -542,7 +542,6 @@ __common_mmu_cache_on:
  * r1-r3  = unused
  * r4     = kernel execution address
  * r5     = decompressed kernel start
- * r6     = processor ID
  * r7     = architecture ID
  * r8     = atags pointer
  * r9-r12,r14 = corrupted
@@ -581,19 +580,19 @@ call_kernel:	bl	cache_clean_flush
  *  r1  = corrupted
  *  r2  = corrupted
  *  r3  = block offset
- *  r6  = corrupted
+ *  r9  = corrupted
  *  r12 = corrupted
  */
 
 call_cache_fn:	adr	r12, proc_types
 #ifdef CONFIG_CPU_CP15
-		mrc	p15, 0, r6, c0, c0	@ get processor ID
+		mrc	p15, 0, r9, c0, c0	@ get processor ID
 #else
-		ldr	r6, =CONFIG_PROCESSOR_ID
+		ldr	r9, =CONFIG_PROCESSOR_ID
 #endif
 1:		ldr	r1, [r12, #0]		@ get value
 		ldr	r2, [r12, #4]		@ get mask
-		eor	r1, r1, r6		@ (real ^ match)
+		eor	r1, r1, r9		@ (real ^ match)
 		tst	r1, r2			@       & mask
  ARM(		addeq	pc, r12, r3		) @ call cache function
  THUMB(		addeq	r12, r3			)
@@ -778,8 +777,7 @@ proc_types:
  * Turn off the Cache and MMU.  ARMv3 does not support
  * reading the control register, but ARMv4 does.
  *
- * On entry,  r6 = processor ID
- * On exit,   r0, r1, r2, r3, r12 corrupted
+ * On exit, r0, r1, r2, r3, r9, r12 corrupted
  * This routine must preserve: r4, r6, r7
  */
 		.align	5
@@ -852,10 +850,8 @@ __armv3_mmu_cache_off:
 /*
  * Clean and flush the cache to maintain consistency.
  *
- * On entry,
- *  r6 = processor ID
  * On exit,
- *  r1, r2, r3, r11, r12 corrupted
+ *  r1, r2, r3, r9, r11, r12 corrupted
  * This routine must preserve:
  *  r0, r4, r5, r6, r7
  */
@@ -967,7 +963,7 @@ __armv4_mmu_cache_flush:
 		mov	r2, #64*1024		@ default: 32K dcache size (*2)
 		mov	r11, #32		@ default: 32 byte line size
 		mrc	p15, 0, r3, c0, c0, 1	@ read cache type
-		teq	r3, r6			@ cache ID register present?
+		teq	r3, r9			@ cache ID register present?
 		beq	no_cache_id
 		mov	r1, r3, lsr #18
 		and	r1, r1, #7
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
index 7ca9ecff652f..d08168941bd6 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -43,6 +43,9 @@ SECTIONS
 
   _etext = .;
 
+  /* Assume size of decompressed image is 4x the compressed image */
+  _image_size = (_etext - _text) * 4;
+
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 1eb85fbf53a5..a3c0a32c4628 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1164,10 +1164,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 * Finally record data if requested.
 	 */
 	if (record) {
-		struct perf_sample_data data = {
-			.addr	= ~0ULL,
-			.period	= event->hw.last_period,
-		};
+		struct perf_sample_data data;
+
+		perf_sample_data_init(&data, ~0ULL);
+		data.period = event->hw.last_period;
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
diff --git a/arch/sh/boot/compressed/misc.c b/arch/sh/boot/compressed/misc.c
index b51b1fc4baae..d3cc94fcdc36 100644
--- a/arch/sh/boot/compressed/misc.c
+++ b/arch/sh/boot/compressed/misc.c
@@ -132,7 +132,7 @@ void decompress_kernel(void)
 	output_addr = (CONFIG_MEMORY_START + 0x2000);
 #else
 	output_addr = __pa((unsigned long)&_text+PAGE_SIZE);
-#ifdef CONFIG_29BIT
+#if defined(CONFIG_29BIT) || defined(CONFIG_PMB_LEGACY)
 	output_addr |= P2SEG;
 #endif
 #endif
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index e856456ec02f..8c70d3e831dc 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1189,7 +1189,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1337,7 +1337,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->tpc);
 
-	ufp = regs->u_regs[UREG_I6];
+	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
 		struct sparc_stackf32 *usf, sf;
 		unsigned long pc;
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index 4b7c937bba61..2d8b70d397f1 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -32,10 +32,9 @@ extern void prom_cif_interface(void);
 extern void prom_cif_callback(void);
 
 /*
- * This provides SMP safety on the p1275buf. prom_callback() drops this lock
- * to allow recursuve acquisition.
+ * This provides SMP safety on the p1275buf.
  */
-DEFINE_SPINLOCK(prom_entry_lock);
+DEFINE_RAW_SPINLOCK(prom_entry_lock);
 
 long p1275_cmd(const char *service, long fmt, ...)
 {
@@ -47,7 +46,9 @@ long p1275_cmd(const char *service, long fmt, ...)
 	
 	p = p1275buf.prom_buffer;
 
-	spin_lock_irqsave(&prom_entry_lock, flags);
+	raw_local_save_flags(flags);
+	raw_local_irq_restore(PIL_NMI);
+	raw_spin_lock(&prom_entry_lock);
 
 	p1275buf.prom_args[0] = (unsigned long)p;		/* service */
 	strcpy (p, service);
@@ -139,7 +140,8 @@ long p1275_cmd(const char *service, long fmt, ...)
 	va_end(list);
 	x = p1275buf.prom_args [nargs + 3];
 
-	spin_unlock_irqrestore(&prom_entry_lock, flags);
+	raw_spin_unlock(&prom_entry_lock);
+	raw_local_irq_restore(flags);
 
 	return x;
 }
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 14f9890eb495..c22a1648113d 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -82,6 +82,9 @@ enum fixed_addresses {
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 #endif
@@ -126,9 +129,6 @@ enum fixed_addresses {
 	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
 			(__end_of_permanent_fixed_addresses & 255),
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
 #ifdef CONFIG_X86_32
 	FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1cd58cdbc03f..4604e6a54d36 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -105,6 +105,8 @@
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_NB_CFG		0xc001001f
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 879666f4d871..7e1cca13af35 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -70,7 +70,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		sched_clock_stable = 1;
+		if (!check_tsc_unstable())
+			sched_clock_stable = 1;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8c1c07073ccc..98819b32bb5f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1636,10 +1636,9 @@ static void intel_pmu_drain_bts_buffer(struct cpu_hw_events *cpuc)
 
 	ds->bts_index = ds->bts_buffer_base;
 
+	perf_sample_data_init(&data, 0);
 
 	data.period	= event->hw.last_period;
-	data.addr	= 0;
-	data.raw	= NULL;
 	regs.ip		= 0;
 
 	/*
@@ -1756,8 +1755,7 @@ static int p6_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1802,8 +1800,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	int bit, loops;
 	u64 ack, status;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index bd49ca5cc40c..9c0393ad255a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,9 +129,15 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
 {
 #ifdef CONFIG_FRAME_POINTER
 	struct stack_frame *frame = (struct stack_frame *)bp;
+	unsigned long next;
 
-	if (!in_irq_stack(stack, irq_stack, irq_stack_end))
-		return (unsigned long)frame->next_frame;
+	if (!in_irq_stack(stack, irq_stack, irq_stack_end)) {
+		if (!probe_kernel_address(&frame->next_frame, next))
+			return next;
+		else
+			WARN_ONCE(1, "Perf: bad frame pointer = %p in "
+				  "callchain\n", &frame->next_frame);
+	}
 #endif
 	return bp;
 }
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index bb6006e3e295..1e8ceadc0d6a 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -531,8 +531,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
-
-void hw_breakpoint_pmu_unthrottle(struct perf_event *bp)
-{
-	/* TODO */
-}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c9b3522b6b46..999c8a6a4e7a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -519,21 +519,37 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for AMD CPUs, which have potentially C1E support
+ * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
+ * For more information see
+ * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
+ * - Erratum #365 for family 0x11 (not affected because C1e not in use)
  */
 static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 {
+	u64 val;
 	if (c->x86_vendor != X86_VENDOR_AMD)
-		return 0;
-
-	if (c->x86 < 0x0F)
-		return 0;
+		goto no_c1e_idle;
 
 	/* Family 0x0f models < rev F do not have C1E */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
+	if (c->x86 == 0x0F && c->x86_model >= 0x40)
+		return 1;
 
-	return 1;
+	if (c->x86 == 0x10) {
+		/*
+		 * check OSVW bit for CPUs that are not affected
+		 * by erratum #400
+		 */
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+		if (val >= 2) {
+			rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+			if (!(val & BIT(1)))
+				goto no_c1e_idle;
+		}
+		return 1;
+	}
+
+no_c1e_idle:
+	return 0;
 }
 
 static cpumask_var_t c1e_mask;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 43e16bfcc41b..d325c6345bab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1351,6 +1351,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XEN_HVM:
 	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
+	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a84a759a17c3..02e58e54cb83 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -291,8 +291,29 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	 */
 	if (kernel_set_to_readonly &&
 	    within(address, (unsigned long)_text,
-		   (unsigned long)__end_rodata_hpage_align))
-		pgprot_val(forbidden) |= _PAGE_RW;
+		   (unsigned long)__end_rodata_hpage_align)) {
+		unsigned int level;
+
+		/*
+		 * Don't enforce the !RW mapping for the kernel text mapping,
+		 * if the current mapping is already using small page mapping.
+		 * No need to work hard to preserve large page mappings in this
+		 * case.
+		 *
+		 * This also fixes the Linux Xen paravirt guest boot failure
+		 * (because of unexpected read-only mappings for kernel identity
+		 * mappings). In this paravirt guest case, the kernel text
+		 * mapping and the kernel identity mapping share the same
+		 * page-table pages. Thus we can't really use different
+		 * protections for the kernel text and identity mappings. Also,
+		 * these shared mappings are made of small page mappings.
+		 * Thus this don't enforce !RW mapping for small page kernel
+		 * text mapping logic will help Linux Xen parvirt guest boot
+		 * aswell.
+		 */
+		if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
+			pgprot_val(forbidden) |= _PAGE_RW;
+	}
 #endif
 
 	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));