Merge branch 'perfcounters/urgent' into perfcounters/core

Merge reason: We are going to modify a place modified by
              perfcounters/urgent.

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

18 files changed, 126 insertions, 134 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e2ff504b4dd..f8ed0658404 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -4,7 +4,7 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o
+targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3cc06e3fceb..16748077559 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_PGTABLE_H
 
 #include <asm/page.h>
+#include <asm/e820.h>
 
 #include <asm/pgtable_types.h>
 
@@ -269,10 +270,17 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
-static inline int is_new_memtype_allowed(unsigned long flags,
-						unsigned long new_flags)
+static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
+					 unsigned long flags,
+					 unsigned long new_flags)
 {
 	/*
+	 * PAT type is always WB for ISA. So no need to check.
+	 */
+	if (is_ISA_range(paddr, paddr + size - 1))
+		return 1;
+
+	/*
 	 * Certain new memtypes are not allowed with certain
 	 * requested memtype:
 	 * - request is uncached, return cannot be write-back
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index bddd44f2f0a..80e2984f521 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -133,7 +133,7 @@ struct bau_msg_payload {
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
 struct bau_msg_header {
-	unsigned int dest_subnodeid:6;	/* must be zero */
+	unsigned int dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
 	unsigned int base_dest_nodeid:15; /* nasid>>1 (pnode) of */
 	/* bits 20:6 */			  /* first bit in node_map */
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index dbf5445727a..6ef00ba4c88 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -106,6 +106,9 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
 	unsigned long mask = cpumask_bits(cpumask)[0];
 	unsigned long flags;
 
+	if (WARN_ONCE(!mask, "empty IPI mask"))
+		return;
+
 	local_irq_save(flags);
 	WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]);
 	__default_send_IPI_dest_field(mask, vector, apic->dest_logical);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 832e908adcb..601159374e8 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -46,7 +46,7 @@ static int early_get_nodeid(void)
 	return node_id.s.node_id;
 }
 
-static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
 		if (!strcmp(oem_table_id, "UVL"))
@@ -253,7 +253,7 @@ static void uv_send_IPI_self(int vector)
 	apic_write(APIC_SELF_IPI, vector);
 }
 
-struct apic apic_x2apic_uv_x = {
+struct apic __refdata apic_x2apic_uv_x = {
 
 	.name				= "UV large system",
 	.probe				= NULL,
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 3efcb2b96a1..c1f253dac15 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -7,6 +7,10 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_common.o = -pg
 endif
 
+# Make sure load_percpu_segment has no stackprotector
+nostackp := $(call cc-option, -fno-stack-protector)
+CFLAGS_common.o		:= $(nostackp)
+
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
 obj-y			+= vmware.o hypervisor.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 1cfb623ce11..01213048f62 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1226,8 +1226,13 @@ static void mce_init(void)
 }
 
 /* Add per CPU specific workarounds here */
-static void mce_cpu_quirks(struct cpuinfo_x86 *c)
+static int mce_cpu_quirks(struct cpuinfo_x86 *c)
 {
+	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
+		pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
+		return -EOPNOTSUPP;
+	}
+
 	/* This should be disabled by the BIOS, but isn't always */
 	if (c->x86_vendor == X86_VENDOR_AMD) {
 		if (c->x86 == 15 && banks > 4) {
@@ -1273,11 +1278,20 @@ static void mce_cpu_quirks(struct cpuinfo_x86 *c)
 		if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
 			monarch_timeout < 0)
 			monarch_timeout = USEC_PER_SEC;
+
+		/*
+		 * There are also broken BIOSes on some Pentium M and
+		 * earlier systems:
+		 */
+		if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
+			mce_bootlog = 0;
 	}
 	if (monarch_timeout < 0)
 		monarch_timeout = 0;
 	if (mce_bootlog != 0)
 		mce_panic_timeout = 30;
+
+	return 0;
 }
 
 static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
@@ -1338,11 +1352,10 @@ void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
 	if (!mce_available(c))
 		return;
 
-	if (mce_cap_init() < 0) {
+	if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) {
 		mce_disabled = 1;
 		return;
 	}
-	mce_cpu_quirks(c);
 
 	machine_check_vector = do_machine_check;
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 8bc64cfbe93..5957a93e517 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -116,11 +116,14 @@ static int therm_throt_process(int curr)
 		       cpu, __get_cpu_var(thermal_throttle_count));
 
 		add_taint(TAINT_MACHINE_CHECK);
-	} else if (was_throttled) {
+		return 1;
+	}
+	if (was_throttled) {
 		printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
+		return 1;
 	}
 
-	return 1;
+	return 0;
 }
 
 #ifdef CONFIG_SYSFS
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 0d98a01cbdb..cc827ac9e8d 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -261,9 +261,7 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
  * which will be freed later
  */
 
-#ifndef CONFIG_HOTPLUG_CPU
-.section .init.text,"ax",@progbits
-#endif
+__CPUINIT
 
 #ifdef CONFIG_SMP
 ENTRY(startup_32_smp)
@@ -602,11 +600,7 @@ ignore_int:
 #endif
 	iret
 
-#ifndef CONFIG_HOTPLUG_CPU
-	__CPUINITDATA
-#else
 	__REFDATA
-#endif
 .align 4
 ENTRY(initial_code)
 	.long i386_start_kernel
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 994dd6a4a2a..071166a4ba8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -519,16 +519,12 @@ static void c1e_idle(void)
 		if (!cpumask_test_cpu(cpu, c1e_mask)) {
 			cpumask_set_cpu(cpu, c1e_mask);
 			/*
-			 * Force broadcast so ACPI can not interfere. Needs
-			 * to run with interrupts enabled as it uses
-			 * smp_function_call.
+			 * Force broadcast so ACPI can not interfere.
 			 */
-			local_irq_enable();
 			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
 					   &cpu);
 			printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
 			       cpu);
-			local_irq_disable();
 		}
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 29a3eef7cf4..07d81916f21 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -165,7 +165,7 @@ static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 
 	if (!chosen) {
 		size_t vm_size = VMALLOC_END - VMALLOC_START;
-		size_t tot_size = num_possible_cpus() * PMD_SIZE;
+		size_t tot_size = nr_cpu_ids * PMD_SIZE;
 
 		/* on non-NUMA, embedding is better */
 		if (!pcpu_need_numa())
@@ -199,7 +199,7 @@ static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 	dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
 
 	/* allocate pointer array and alloc large pages */
-	map_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpul_map[0]));
+	map_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpul_map[0]));
 	pcpul_map = alloc_bootmem(map_size);
 
 	for_each_possible_cpu(cpu) {
@@ -228,7 +228,7 @@ static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 
 	/* allocate address and map */
 	pcpul_vm.flags = VM_ALLOC;
-	pcpul_vm.size = num_possible_cpus() * PMD_SIZE;
+	pcpul_vm.size = nr_cpu_ids * PMD_SIZE;
 	vm_area_register_early(&pcpul_vm, PMD_SIZE);
 
 	for_each_possible_cpu(cpu) {
@@ -250,8 +250,8 @@ static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 				     PMD_SIZE, pcpul_vm.addr, NULL);
 
 	/* sort pcpul_map array for pcpu_lpage_remapped() */
-	for (i = 0; i < num_possible_cpus() - 1; i++)
-		for (j = i + 1; j < num_possible_cpus(); j++)
+	for (i = 0; i < nr_cpu_ids - 1; i++)
+		for (j = i + 1; j < nr_cpu_ids; j++)
 			if (pcpul_map[i].ptr > pcpul_map[j].ptr) {
 				struct pcpul_ent tmp = pcpul_map[i];
 				pcpul_map[i] = pcpul_map[j];
@@ -288,7 +288,7 @@ void *pcpu_lpage_remapped(void *kaddr)
 {
 	void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
 	unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
-	int left = 0, right = num_possible_cpus() - 1;
+	int left = 0, right = nr_cpu_ids - 1;
 	int pos;
 
 	/* pcpul in use at all? */
@@ -377,7 +377,7 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
 	pcpu4k_nr_static_pages = PFN_UP(static_size);
 
 	/* unaligned allocations can't be freed, round up to page size */
-	pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * num_possible_cpus()
+	pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * nr_cpu_ids
 			       * sizeof(pcpu4k_pages[0]));
 	pcpu4k_pages = alloc_bootmem(pages_size);
 
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 8ccabb8a2f6..77b9689f8ed 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -744,6 +744,7 @@ uv_activation_descriptor_init(int node, int pnode)
 		 * note that base_dest_nodeid is actually a nasid.
 		 */
 		ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1;
+		ad2->header.dest_subnodeid = 0x10; /* the LB */
 		ad2->header.command = UV_NET_ENDPOINT_INTD;
 		ad2->header.int_both = 1;
 		/*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 78d185d797d..9fc178255c0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -46,11 +46,10 @@ PHDRS {
 	data PT_LOAD FLAGS(7);          /* RWE */
 #ifdef CONFIG_X86_64
 	user PT_LOAD FLAGS(7);          /* RWE */
-	data.init PT_LOAD FLAGS(7);     /* RWE */
 #ifdef CONFIG_SMP
 	percpu PT_LOAD FLAGS(7);        /* RWE */
 #endif
-	data.init2 PT_LOAD FLAGS(7);    /* RWE */
+	init PT_LOAD FLAGS(7);          /* RWE */
 #endif
 	note PT_NOTE FLAGS(0);          /* ___ */
 }
@@ -103,65 +102,43 @@ SECTIONS
 		__stop___ex_table = .;
 	} :text = 0x9090
 
-	RODATA
+	RO_DATA(PAGE_SIZE)
 
 	/* Data */
-	. = ALIGN(PAGE_SIZE);
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
 		/* Start of data section */
 		_sdata = .;
-		DATA_DATA
-		CONSTRUCTORS
-	} :data
+
+		/* init_task */
+		INIT_TASK_DATA(THREAD_SIZE)
 
 #ifdef CONFIG_X86_32
-	/* 32 bit has nosave before _edata */
-	. = ALIGN(PAGE_SIZE);
-	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-		__nosave_begin = .;
-		*(.data.nosave)
-		. = ALIGN(PAGE_SIZE);
-		__nosave_end = .;
-	}
+		/* 32 bit has nosave before _edata */
+		NOSAVE_DATA
 #endif
 
-	. = ALIGN(PAGE_SIZE);
-	.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-		*(.data.page_aligned)
+		PAGE_ALIGNED_DATA(PAGE_SIZE)
 		*(.data.idt)
-	}
 
-#ifdef CONFIG_X86_32
-	. = ALIGN(32);
-#else
-	. = ALIGN(PAGE_SIZE);
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-#endif
-	.data.cacheline_aligned :
-		AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-		*(.data.cacheline_aligned)
-	}
+		CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
 
-	/* rarely changed data like cpu maps */
-#ifdef CONFIG_X86_32
-	. = ALIGN(32);
-#else
-	. = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
-#endif
-	.data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-		*(.data.read_mostly)
+		DATA_DATA
+		CONSTRUCTORS
+
+		/* rarely changed data like cpu maps */
+		READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES)
 
 		/* End of data section */
 		_edata = .;
-	}
+	} :data
 
 #ifdef CONFIG_X86_64
 
 #define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
-                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
-                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \
+                            PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \
+                            PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
 
 #define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
 #define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
@@ -227,35 +204,29 @@ SECTIONS
 
 #endif /* CONFIG_X86_64 */
 
-	/* init_task */
-	. = ALIGN(THREAD_SIZE);
-	.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-		*(.data.init_task)
+	/* Init code and data - will be freed after init */
+	. = ALIGN(PAGE_SIZE);
+	.init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) {
+		__init_begin = .; /* paired with __init_end */
 	}
-#ifdef CONFIG_X86_64
-	 :data.init
-#endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
 	/*
-	 * smp_locks might be freed after init
-	 * start/end must be page aligned
+	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
+	 * output PHDR, so the next output section - .init.text - should
+	 * start another segment - init.
 	 */
-	. = ALIGN(PAGE_SIZE);
-	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
-		__smp_locks = .;
-		*(.smp_locks)
-		__smp_locks_end = .;
-		. = ALIGN(PAGE_SIZE);
-	}
+	PERCPU_VADDR(0, :percpu)
+#endif
 
-	/* Init code and data - will be freed after init */
-	. = ALIGN(PAGE_SIZE);
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-		__init_begin = .; /* paired with __init_end */
 		_sinittext = .;
 		INIT_TEXT
 		_einittext = .;
 	}
+#ifdef CONFIG_X86_64
+	:init
+#endif
 
 	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
 		INIT_DATA
@@ -326,17 +297,7 @@ SECTIONS
 	}
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
-	/*
-	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-	 * output PHDR, so the next output section - __data_nosave - should
-	 * start another section data.init2.  Also, pda should be at the head of
-	 * percpu area.  Preallocate it and define the percpu offset symbol
-	 * so that it can be accessed as a percpu variable.
-	 */
-	. = ALIGN(PAGE_SIZE);
-	PERCPU_VADDR(0, :percpu)
-#else
+#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
 	PERCPU(PAGE_SIZE)
 #endif
 
@@ -347,15 +308,22 @@ SECTIONS
 		__init_end = .;
 	}
 
+	/*
+	 * smp_locks might be freed after init
+	 * start/end must be page aligned
+	 */
+	. = ALIGN(PAGE_SIZE);
+	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+		__smp_locks = .;
+		*(.smp_locks)
+		__smp_locks_end = .;
+		. = ALIGN(PAGE_SIZE);
+	}
+
 #ifdef CONFIG_X86_64
 	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-		. = ALIGN(PAGE_SIZE);
-		__nosave_begin = .;
-		*(.data.nosave)
-		. = ALIGN(PAGE_SIZE);
-		__nosave_end = .;
-	} :data.init2
-	/* use another section data.init2, see PERCPU_VADDR() above */
+		NOSAVE_DATA
+	}
 #endif
 
 	/* BSS */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6176fe8f29e..ea56b8cbb6a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -796,7 +796,7 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 		return ret;
 
 #else
-	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+	reserve_bootmem(phys, len, flags);
 #endif
 
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index e6718bb2806..352aa9e927e 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -623,7 +623,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		return ret;
 
 	if (flags != want_flags) {
-		if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) {
+		if (strict_prot ||
+		    !is_new_memtype_allowed(paddr, size, want_flags, flags)) {
 			free_memtype(paddr, paddr + size);
 			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
 				" for %Lx-%Lx, got %s\n",
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 821e97017e9..c814e144a3f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -183,18 +183,17 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
 	f->flush_mm = mm;
 	f->flush_va = va;
-	cpumask_andnot(to_cpumask(f->flush_cpumask),
-		       cpumask, cpumask_of(smp_processor_id()));
-
-	/*
-	 * We have to send the IPI only to
-	 * CPUs affected.
-	 */
-	apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
-		      INVALIDATE_TLB_VECTOR_START + sender);
+	if (cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id()))) {
+		/*
+		 * We have to send the IPI only to
+		 * CPUs affected.
+		 */
+		apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
+			      INVALIDATE_TLB_VECTOR_START + sender);
 
-	while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
-		cpu_relax();
+		while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
+			cpu_relax();
+	}
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 172438f86a0..7410640db17 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -5,6 +5,10 @@ CFLAGS_REMOVE_time.o = -pg
 CFLAGS_REMOVE_irq.o = -pg
 endif
 
+# Make sure early boot has no stackprotector
+nostackp := $(call cc-option, -fno-stack-protector)
+CFLAGS_enlighten.o		:= $(nostackp)
+
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0a1700a2be9..e90540a46a0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -974,10 +974,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_domain_type = XEN_PV_DOMAIN;
 
-	BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
-
-	xen_setup_features();
-
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
@@ -986,8 +982,15 @@ asmlinkage void __init xen_start_kernel(void)
 	pv_apic_ops = xen_apic_ops;
 	pv_mmu_ops = xen_mmu_ops;
 
-	xen_init_irq_ops();
+#ifdef CONFIG_X86_64
+	/*
+	 * Setup percpu state.  We only need to do this for 64-bit
+	 * because 32-bit already has %fs set properly.
+	 */
+	load_percpu_segment(0);
+#endif
 
+	xen_init_irq_ops();
 	xen_init_cpuid_mask();
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -997,6 +1000,8 @@ asmlinkage void __init xen_start_kernel(void)
 	set_xen_basic_apic_ops();
 #endif
 
+	xen_setup_features();
+
 	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
 		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
 		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
@@ -1004,13 +1009,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	machine_ops = xen_machine_ops;
 
-#ifdef CONFIG_X86_64
-	/*
-	 * Setup percpu state.  We only need to do this for 64-bit
-	 * because 32-bit already has %fs set properly.
-	 */
-	load_percpu_segment(0);
-#endif
 	/*
 	 * The only reliable way to retain the initial address of the
 	 * percpu gdt_page is to remember it here, so we can go and