Merge remote-tracking branch 'tip/perf/urgent' into perf/core

Merge reason: We are going to queue up a dependent patch:

"perf tools: Move parse event automated tests to separated object"

That depends on:

commit e7c72d8
perf tools: Add 'G' and 'H' modifiers to event parsing

Conflicts:
	tools/perf/builtin-stat.c

Conflicted with the recent 'perf_target' patches when checking the
result of perf_evsel open routines to see if a retry is needed to cope
with older kernels where the exclude guest/host perf_event_attr bits
were not used.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

26 files changed, 135 insertions, 79 deletions

diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index a0559930a180..c85e3ac99bba 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -33,6 +33,9 @@
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
+	jmp	preferred_addr
+
+	.balign	0x10
 	/*
 	 * We don't need the return address, so set up the stack so
 	 * efi_main() can find its arugments.
@@ -41,12 +44,17 @@ ENTRY(startup_32)
 
 	call	efi_main
 	cmpl	$0, %eax
-	je	preferred_addr
 	movl	%eax, %esi
-	call	1f
+	jne	2f
 1:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	1b
+2:
+	call	3f
+3:
 	popl	%eax
-	subl	$1b, %eax
+	subl	$3b, %eax
 	subl	BP_pref_address(%esi), %eax
 	add	BP_code32_start(%esi), %eax
 	leal	preferred_addr(%eax), %eax
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 558d76ce23bc..87e03a13d8e3 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -200,18 +200,28 @@ ENTRY(startup_64)
 	 * entire text+data+bss and hopefully all of memory.
 	 */
 #ifdef CONFIG_EFI_STUB
-	pushq	%rsi
+	/*
+	 * The entry point for the PE/COFF executable is 0x210, so only
+	 * legacy boot loaders will execute this jmp.
+	 */
+	jmp	preferred_addr
+
+	.org 0x210
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
 	call	efi_main
-	popq	%rsi
-	cmpq	$0,%rax
-	je	preferred_addr
 	movq	%rax,%rsi
-	call	1f
+	cmpq	$0,%rax
+	jne	2f
 1:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	1b
+2:
+	call	3f
+3:
 	popq	%rax
-	subq	$1b, %rax
+	subq	$3b, %rax
 	subq	BP_pref_address(%rsi), %rax
 	add	BP_code32_start(%esi), %eax
 	leaq	preferred_addr(%rax), %rax
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index ed549767a231..24443a332083 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -205,8 +205,13 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
 
 #ifdef CONFIG_X86_32
-	/* Address of entry point */
-	put_unaligned_le32(i, &buf[pe_header + 0x28]);
+	/*
+	 * Address of entry point.
+	 *
+	 * The EFI stub entry point is +16 bytes from the start of
+	 * the .text section.
+	 */
+	put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
 
 	/* .text size */
 	put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
@@ -217,9 +222,11 @@ int main(int argc, char ** argv)
 	/*
 	 * Address of entry point. startup_32 is at the beginning and
 	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after.
+	 * after. The EFI stub entry point is 16 bytes after that, as
+	 * the first instruction allows legacy loaders to jump over
+	 * the EFI stub initialisation
 	 */
-	put_unaligned_le32(i + 512, &buf[pe_header + 0x28]);
+	put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
 
 	/* .text size */
 	put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index 3427b7798dbc..7ef7c3020e5c 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,9 +7,9 @@
 #else
 # ifdef __i386__
 #  include "posix_types_32.h"
-# elif defined(__LP64__)
-#  include "posix_types_64.h"
-# else
+# elif defined(__ILP32__)
 #  include "posix_types_x32.h"
+# else
+#  include "posix_types_64.h"
 # endif
 #endif
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 4a085383af27..5ca71c065eef 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -257,7 +257,7 @@ struct sigcontext {
 	__u64 oldmask;
 	__u64 cr2;
 	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-#ifndef __LP64__
+#ifdef __ILP32__
 	__u32 __fpstate_pad;
 #endif
 	__u64 reserved1[8];
diff --git a/arch/x86/include/asm/siginfo.h b/arch/x86/include/asm/siginfo.h
index fc1aa5535646..34c47b3341c0 100644
--- a/arch/x86/include/asm/siginfo.h
+++ b/arch/x86/include/asm/siginfo.h
@@ -2,7 +2,13 @@
 #define _ASM_X86_SIGINFO_H
 
 #ifdef __x86_64__
-# define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+# ifdef __ILP32__ /* x32 */
+typedef long long __kernel_si_clock_t __attribute__((aligned(4)));
+#  define __ARCH_SI_CLOCK_T		__kernel_si_clock_t
+#  define __ARCH_SI_ATTRIBUTES		__attribute__((aligned(8)))
+# else /* x86-64 */
+#  define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+# endif
 #endif
 
 #include <asm-generic/siginfo.h>
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 37cdc9d99bb1..4437001d8e3d 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -63,10 +63,10 @@
 #else
 # ifdef __i386__
 #  include <asm/unistd_32.h>
-# elif defined(__LP64__)
-#  include <asm/unistd_64.h>
-# else
+# elif defined(__ILP32__)
 #  include <asm/unistd_x32.h>
+# else
+#  include <asm/unistd_64.h>
 # endif
 #endif
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index baaca8defec8..764b66a4cf89 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -195,6 +195,5 @@ extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
-extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node);
 
 #endif
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 103b6ab368d3..146a49c763a4 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -24,6 +24,10 @@ unsigned long acpi_realmode_flags;
 static char temp_stack[4096];
 #endif
 
+asmlinkage void acpi_enter_s3(void)
+{
+	acpi_enter_sleep_state(3, wake_sleep_flags);
+}
 /**
  * acpi_suspend_lowlevel - save kernel state
  *
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 416d4be13fef..d68677a2a010 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -3,12 +3,16 @@
  */
 
 #include <asm/trampoline.h>
+#include <linux/linkage.h>
 
 extern unsigned long saved_video_mode;
 extern long saved_magic;
 
 extern int wakeup_pmode_return;
 
+extern u8 wake_sleep_flags;
+extern asmlinkage void acpi_enter_s3(void);
+
 extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 extern void wakeup_long64(void);
 
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 13ab720573e3..72610839f03b 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -74,9 +74,7 @@ restore_registers:
 ENTRY(do_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
-	pushl	$3
-	call	acpi_enter_sleep_state
-	addl	$4, %esp
+	call	acpi_enter_s3
 
 #	In case of S3 failure, we'll emerge here.  Jump
 # 	to ret_point to recover
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8ea5164cbd04..014d1d28c397 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -71,9 +71,7 @@ ENTRY(do_suspend_lowlevel)
 	movq	%rsi, saved_rsi
 
 	addq	$8, %rsp
-	movl	$3, %edi
-	xorl	%eax, %eax
-	call	acpi_enter_sleep_state
+	call	acpi_enter_s3
 	/* in case something went wrong, restore the machine status and go on */
 	jmp	resume_point
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 11544d8f1e97..edc24480469f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1637,9 +1637,11 @@ static int __init apic_verify(void)
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 
 	/* The BIOS may have set up the APIC at some other address */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (l & MSR_IA32_APICBASE_ENABLE)
-		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (l & MSR_IA32_APICBASE_ENABLE)
+			mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	}
 
 	pr_info("Found and enabled local APIC!\n");
 	return 0;
@@ -1657,13 +1659,15 @@ int __init apic_force_enable(unsigned long addr)
 	 * MSR. This can only be done in software for Intel P6 or later
 	 * and AMD K7 (Model > 1) or later.
 	 */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-		pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
-		enabled_via_apicbase = 1;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+			enabled_via_apicbase = 1;
+		}
 	}
 	return apic_verify();
 }
@@ -2209,10 +2213,12 @@ static void lapic_resume(void)
 		 * FIXME! This will be wrong if we ever support suspend on
 		 * SMP! We'll need to do this as part of the CPU restore!
 		 */
-		rdmsr(MSR_IA32_APICBASE, l, h);
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
+		if (boot_cpu_data.x86 >= 6) {
+			rdmsr(MSR_IA32_APICBASE, l, h);
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+		}
 	}
 
 	maxlvt = lapic_get_maxlvt();
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 899803e03214..23e75422e013 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -207,8 +207,11 @@ static void __init map_csrs(void)
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	c->phys_proc_id = node;
-	per_cpu(cpu_llc_id, smp_processor_id()) = node;
+
+	if (c->phys_proc_id != node) {
+		c->phys_proc_id = node;
+		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	}
 }
 
 static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8a778db45e3a..991e315f4227 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -24,6 +24,12 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (x2apic_phys)
 		return x2apic_enabled();
+	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
+		x2apic_enabled()) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return 1;
+	}
 	else
 		return 0;
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0a44b90602b0..1c67ca100e4c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -26,7 +26,8 @@
  *	contact AMD for precise details and a CPU swap.
  *
  *	See	http://www.multimania.com/poulot/k6bug.html
- *		http://www.amd.com/K6/k6docs/revgd.html
+ *	and	section 2.6.2 of "AMD-K6 Processor Revision Guide - Model 6"
+ *		(Publication # 21266  Issue Date: August 1998)
  *
  *	The following test is erm.. interesting. AMD neglected to up
  *	the chip setting when fixing the bug but they also tweaked some
@@ -94,7 +95,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 				"system stability may be impaired when more than 32 MB are used.\n");
 		else
 			printk(KERN_CONT "probably OK (after B9730xxxx).\n");
-		printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
 	}
 
 	/* K6 with old style WHCR */
@@ -353,10 +353,11 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 		node = per_cpu(cpu_llc_id, cpu);
 
 	/*
-	 * If core numbers are inconsistent, it's likely a multi-fabric platform,
-	 * so invoke platform-specific handler
+	 * On multi-fabric platform (e.g. Numascale NumaChip) a
+	 * platform-specific handler needs to be called to fixup some
+	 * IDs of the CPU.
 	 */
-	if (c->phys_proc_id != node)
+	if (x86_cpuinit.fixup_cpu_id)
 		x86_cpuinit.fixup_cpu_id(c, node);
 
 	if (!node_online(node)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 67e258362a3d..cf79302198a6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1163,15 +1163,6 @@ static void dbg_restore_debug_regs(void)
 #endif /* ! CONFIG_KGDB */
 
 /*
- * Prints an error where the NUMA and configured core-number mismatch and the
- * platform didn't override this to fix it up
- */
-void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node)
-{
-	pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id);
-}
-
-/*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 73d08ed98a64..b8f3653dddbc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -433,14 +433,14 @@ int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
 	/*  check if @slot is already used or the index is already disabled */
 	ret = amd_get_l3_disable_slot(nb, slot);
 	if (ret >= 0)
-		return -EINVAL;
+		return -EEXIST;
 
 	if (index > nb->l3_cache.indices)
 		return -EINVAL;
 
 	/* check whether the other slot has disabled the same index already */
 	if (index == amd_get_l3_disable_slot(nb, !slot))
-		return -EINVAL;
+		return -EEXIST;
 
 	amd_l3_disable_index(nb, cpu, slot, index);
 
@@ -468,8 +468,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
 	if (err) {
 		if (err == -EEXIST)
-			printk(KERN_WARNING "L3 disable slot %d in use!\n",
-					    slot);
+			pr_warning("L3 slot %d in use/index already disabled!\n",
+				   slot);
 		return err;
 	}
 	return count;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 7734bcbb5a3a..2d6e6498c176 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -235,6 +235,7 @@ int init_fpu(struct task_struct *tsk)
 	if (tsk_used_math(tsk)) {
 		if (HAVE_HWFP && tsk == current)
 			unlazy_fpu(tsk);
+		tsk->thread.fpu.last_cpu = ~0;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 73465aab28f8..8a2ce8fd41c0 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -82,11 +82,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
-		return -1;
-	}
-
 	csig->rev = c->microcode;
 	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
 
@@ -380,6 +375,13 @@ static struct microcode_ops microcode_amd_ops = {
 
 struct microcode_ops * __init init_amd_microcode(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
 	patch = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!patch)
 		return NULL;
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 87a0f8688301..c9bda6d6035c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -419,10 +419,8 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif)
 	if (err)
 		return err;
 
-	if (microcode_init_cpu(cpu) == UCODE_ERROR) {
-		sysfs_remove_group(&dev->kobj, &mc_attr_group);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
 		return -EINVAL;
-	}
 
 	return err;
 }
@@ -528,11 +526,11 @@ static int __init microcode_init(void)
 		microcode_ops = init_intel_microcode();
 	else if (c->x86_vendor == X86_VENDOR_AMD)
 		microcode_ops = init_amd_microcode();
-
-	if (!microcode_ops) {
+	else
 		pr_err("no support for this CPU vendor\n");
+
+	if (!microcode_ops)
 		return -ENODEV;
-	}
 
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e9f265fd79ae..9cf71d0b2d37 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -93,7 +93,6 @@ struct x86_init_ops x86_init __initdata = {
 struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
 	.early_percpu_clock_init	= x86_init_noop,
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
-	.fixup_cpu_id			= x86_default_fixup_cpu_id,
 };
 
 static void default_nmi_init(void) { };
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e0a37233c0af..e31bcd8f2eee 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -805,7 +805,7 @@ void intel_scu_devices_create(void)
 		} else
 			i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
 	}
-	intel_scu_notifier_post(SCU_AVAILABLE, 0L);
+	intel_scu_notifier_post(SCU_AVAILABLE, NULL);
 }
 EXPORT_SYMBOL_GPL(intel_scu_devices_create);
 
@@ -814,7 +814,7 @@ void intel_scu_devices_destroy(void)
 {
 	int i;
 
-	intel_scu_notifier_post(SCU_DOWN, 0L);
+	intel_scu_notifier_post(SCU_DOWN, NULL);
 
 	for (i = 0; i < ipc_next_dev; i++)
 		platform_device_del(ipc_devs[i]);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 4f51bebac02c..a8f8844b8d32 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -261,7 +261,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 
 static bool __init xen_check_mwait(void)
 {
-#ifdef CONFIG_ACPI
+#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
+	!defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
 	struct xen_platform_op op = {
 		.cmd			= XENPF_set_processor_pminfo,
 		.u.set_pminfo.id	= -1,
@@ -349,7 +350,6 @@ static void __init xen_init_cpuid_mask(void)
 	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
 	if ((cx & xsave_mask) != xsave_mask)
 		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
-
 	if (xen_check_mwait())
 		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 5fac6919b957..0503c0c493a9 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -178,6 +178,7 @@ static void __init xen_fill_possible_map(void)
 static void __init xen_filter_cpu_maps(void)
 {
 	int i, rc;
+	unsigned int subtract = 0;
 
 	if (!xen_initial_domain())
 		return;
@@ -192,8 +193,22 @@ static void __init xen_filter_cpu_maps(void)
 		} else {
 			set_cpu_possible(i, false);
 			set_cpu_present(i, false);
+			subtract++;
 		}
 	}
+#ifdef CONFIG_HOTPLUG_CPU
+	/* This is akin to using 'nr_cpus' on the Linux command line.
+	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
+	 * have up to X, while nr_cpu_ids is greater than X. This
+	 * normally is not a problem, except when CPU hotplugging
+	 * is involved and then there might be more than X CPUs
+	 * in the guest - which will not work as there is no
+	 * hypercall to expand the max number of VCPUs an already
+	 * running guest has. So cap it up to X. */
+	if (subtract)
+		nr_cpu_ids = nr_cpu_ids - subtract;
+#endif
+
 }
 
 static void __init xen_smp_prepare_boot_cpu(void)
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 79d7362ad6d1..3e45aa000718 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct)
 
 	/* check for unmasked and pending */
 	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jz 1f
+	jnz 1f
 2:	call check_events
 1:
 ENDPATCH(xen_restore_fl_direct)