Merge remote branch 'gcl/next' into next

32 files changed, 290 insertions, 120 deletions

diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 23f315c..325c052 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
 #else
-	if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
+	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
 		error("Destination address too large");
 #endif
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index cbcc8d8..7a6e68e 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -10,6 +10,7 @@
  * by the Free Software Foundation.
  */
 
+#include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 5be1542..e99d55d 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -72,6 +72,9 @@ struct e820map {
 #define BIOS_BEGIN		0x000a0000
 #define BIOS_END		0x00100000
 
+#define BIOS_ROM_BASE		0xffe00000
+#define BIOS_ROM_END		0xffffffff
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9e6fe39..f702f82 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,7 +79,7 @@
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7f7e577..31d84ac 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -11,6 +11,7 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct pvclock_vcpu_time_info *vcpu,
 			    struct timespec *ts);
+void pvclock_resume(void);
 
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9e13763..1e99475 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -45,6 +45,7 @@ obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
+obj-y			+= resource.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3f838d5..7821813 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1389,6 +1389,14 @@ void __cpuinit end_local_APIC_setup(void)
 
 	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
+
+	/*
+	 * Now that local APIC setup is completed for BP, configure the fault
+	 * handling for interrupt remapping.
+	 */
+	if (!smp_processor_id() && intr_remapping_enabled)
+		enable_drhd_fault_handling();
+
 }
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7cc0a72..fadcd74 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2430,13 +2430,12 @@ static void ack_apic_level(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	int i, do_unmask_irq = 0, irq = data->irq;
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
 
 	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
+	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_ioapic(cfg);
 	}
@@ -3413,6 +3412,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index f9e4e6a..d8c4a6f 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void)
 		/* need to update phys_pkg_id */
 		apic->phys_pkg_id = apicid_phys_pkg_id;
 	}
-
-	/*
-	 * Now that apic routing model is selected, configure the
-	 * fault handling for intr remapping.
-	 */
-	if (intr_remapping_enabled)
-		enable_drhd_fault_handling();
 }
 
 /* Same for both flat and physical. */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index bcece91..c0dbd9a 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -60,16 +60,18 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
+/* Number of possible pages in the lowmem region */
+LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
+	
 /* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
-	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
 /*
  * Worst-case size of the kernel mapping we need to make:
- * the worst-case size of the kernel itself, plus the extra we need
- * to map for the linear map.
+ * a relocatable kernel can live anywhere in lowmem, so we need to be able
+ * to map all of lowmem.
  */
-KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT
+KERNEL_PAGES = LOWMEM_PAGES
 
 INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
 RESERVE_BRK(pagetables, INIT_MAP_SIZE)
@@ -620,13 +622,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-initial_pg_pmd:
+ENTRY(initial_pg_pmd)
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
 	.fill 1024,4,0
 #endif
-initial_pg_fixmap:
+ENTRY(initial_pg_fixmap)
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ae03cab..4ff5968 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -27,6 +27,9 @@
 #define HPET_DEV_FSB_CAP		0x1000
 #define HPET_DEV_PERI_CAP		0x2000
 
+#define HPET_MIN_CYCLES			128
+#define HPET_MIN_PROG_DELTA		(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+
 #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt)
 
 /*
@@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void)
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
-	/* 5 usec minimum reprogramming delta. */
-	hpet_clockevent.min_delta_ns = 5000;
+	/* Setup minimum reprogramming delta. */
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
+							   &hpet_clockevent);
 
 	/*
 	 * Start hpet with the boot cpu mask and make it
@@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta,
 	 * the wraparound into account) nor a simple count down event
 	 * mode. Further the write to the comparator register is
 	 * delayed internally up to two HPET clock cycles in certain
-	 * chipsets (ATI, ICH9,10). We worked around that by reading
-	 * back the compare register, but that required another
-	 * workaround for ICH9,10 chips where the first readout after
-	 * write can return the old stale value. We already have a
-	 * minimum delta of 5us enforced, but a NMI or SMI hitting
+	 * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even
+	 * longer delays. We worked around that by reading back the
+	 * compare register, but that required another workaround for
+	 * ICH9,10 chips where the first readout after write can
+	 * return the old stale value. We already had a minimum
+	 * programming delta of 5us enforced, but a NMI or SMI hitting
 	 * between the counter readout and the comparator write can
 	 * move us behind that point easily. Now instead of reading
 	 * the compare register back several times, we make the ETIME
 	 * decision based on the following: Return ETIME if the
-	 * counter value after the write is less than 8 HPET cycles
+	 * counter value after the write is less than HPET_MIN_CYCLES
 	 * away from the event or if the counter is already ahead of
-	 * the event.
+	 * the event. The minimum programming delta for the generic
+	 * clockevents code is set to 1.5 * HPET_MIN_CYCLES.
 	 */
 	res = (s32)(cnt - hpet_readl(HPET_COUNTER));
 
-	return res < 8 ? -ETIME : 0;
+	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index dcb65cc..1a1b606 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -364,8 +364,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		/* For performance reasons, reuse mc area when possible */
 		if (!mc || mc_size > curr_mc_size) {
-			if (mc)
-				vfree(mc);
+			vfree(mc);
 			mc = vmalloc(mc_size);
 			if (!mc)
 				break;
@@ -374,13 +373,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
 		    microcode_sanity_check(mc) < 0) {
-			vfree(mc);
 			break;
 		}
 
 		if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) {
-			if (new_mc)
-				vfree(new_mc);
+			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
 			mc = NULL;	/* trigger new vmalloc */
@@ -390,12 +387,10 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (mc)
-		vfree(mc);
+	vfree(mc);
 
 	if (leftover) {
-		if (new_mc)
-			vfree(new_mc);
+		vfree(new_mc);
 		state = UCODE_ERROR;
 		goto out;
 	}
@@ -405,8 +400,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		goto out;
 	}
 
-	if (uci->mc)
-		vfree(uci->mc);
+	vfree(uci->mc);
 	uci->mc = (struct microcode_intel *)new_mc;
 
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 008b91e..42eb330 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -83,6 +83,11 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
 
 static atomic64_t last_value = ATOMIC64_INIT(0);
 
+void pvclock_resume(void)
+{
+	atomic64_set(&last_value, 0);
+}
+
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 {
 	struct pvclock_shadow_time shadow;
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
new file mode 100644
index 0000000..2a26819
--- /dev/null
+++ b/arch/x86/kernel/resource.c
@@ -0,0 +1,48 @@
+#include <linux/ioport.h>
+#include <asm/e820.h>
+
+static void resource_clip(struct resource *res, resource_size_t start,
+			  resource_size_t end)
+{
+	resource_size_t low = 0, high = 0;
+
+	if (res->end < start || res->start > end)
+		return;		/* no conflict */
+
+	if (res->start < start)
+		low = start - res->start;
+
+	if (res->end > end)
+		high = res->end - end;
+
+	/* Keep the area above or below the conflict, whichever is larger */
+	if (low > high)
+		res->end = start - 1;
+	else
+		res->start = end + 1;
+}
+
+static void remove_e820_regions(struct resource *avail)
+{
+	int i;
+	struct e820entry *entry;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		entry = &e820.map[i];
+
+		resource_clip(avail, entry->addr,
+			      entry->addr + entry->size - 1);
+	}
+}
+
+void arch_remove_reservations(struct resource *avail)
+{
+	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	if (avail->flags & IORESOURCE_MEM) {
+		if (avail->start < BIOS_END)
+			avail->start = BIOS_END;
+		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
+
+		remove_e820_regions(avail);
+	}
+}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 21c6746..a0f52af 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -501,7 +501,18 @@ static inline unsigned long long get_total_mem(void)
 	return total << PAGE_SHIFT;
 }
 
-#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF
+/*
+ * Keep the crash kernel below this limit.  On 32 bits earlier kernels
+ * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
+ * limit once kexec-tools are fixed.
+ */
+#ifdef CONFIG_X86_32
+# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+#else
+# define CRASH_KERNEL_ADDR_MAX	(896 << 20)
+#endif
+
 static void __init reserve_crashkernel(void)
 {
 	unsigned long long total_mem;
@@ -520,10 +531,10 @@ static void __init reserve_crashkernel(void)
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
 		/*
-		 *  kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX
+		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment);
+			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
 
 		if (crash_base == MEMBLOCK_ERROR) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
@@ -769,7 +780,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
-	resource_alloc_from_bottom = 0;
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 9c253bd..5471285 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -394,7 +394,8 @@ static void __init setup_xstate_init(void)
 	 * Setup init_xstate_buf to represent the init state of
 	 * all the features managed by the xsave
 	 */
-	init_xstate_buf = alloc_bootmem(xstate_size);
+	init_xstate_buf = alloc_bootmem_align(xstate_size,
+					      __alignof__(struct xsave_struct));
 	init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
 
 	clts();
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1ca1229..b81a9b7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
+	case 0x00000001:
+		/* Mask out xsave bit as long as it is not supported by SVM */
+		entry->ecx &= ~(bit(X86_FEATURE_XSAVE));
+		break;
 	case 0x80000001:
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ff21fdd..81fcbe9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4227,11 +4227,6 @@ static int vmx_get_lpage_level(void)
 		return PT_PDPE_LEVEL;
 }
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cdac9e5..b989e1f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 u64 __read_mostly host_xcr0;
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
@@ -4569,9 +4564,11 @@ static void kvm_timer_init(void)
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
 		memset(&policy, 0, sizeof(policy));
-		cpufreq_get_policy(&policy, get_cpu());
+		cpu = get_cpu();
+		cpufreq_get_policy(&policy, cpu);
 		if (policy.cpuinfo.max_freq)
 			max_tsc_khz = policy.cpuinfo.max_freq;
+		put_cpu();
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
@@ -5522,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
+	if (sregs->cr4 & X86_CR4_OSXSAVE)
+		update_cpuid(vcpu);
 	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
 		mmu_reset_needed = 1;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2cea414..c600da8 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+static inline u32 bit(int bitno)
+{
+	return 1 << (bitno & 31);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 73b1e1a..4996cf5 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -531,7 +531,10 @@ static void lguest_write_cr3(unsigned long cr3)
 {
 	lguest_data.pgdir = cr3;
 	lazy_hcall1(LHCALL_NEW_PGTABLE, cr3);
-	cr3_changed = true;
+
+	/* These two page tables are simple, linear, and used during boot */
+	if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table))
+		cr3_changed = true;
 }
 
 static unsigned long lguest_read_cr3(void)
@@ -703,9 +706,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval)
  * to forget all of them.  Fortunately, this is very rare.
  *
  * ... except in early boot when the kernel sets up the initial pagetables,
- * which makes booting astonishingly slow: 1.83 seconds!  So we don't even tell
- * the Host anything changed until we've done the first page table switch,
- * which brings boot back to 0.25 seconds.
+ * which makes booting astonishingly slow: 48 seconds!  So we don't even tell
+ * the Host anything changed until we've done the first real page table switch,
+ * which brings boot back to 4.3 seconds.
  */
 static void lguest_set_pte(pte_t *ptep, pte_t pteval)
 {
@@ -1002,7 +1005,7 @@ static void lguest_time_init(void)
 	clockevents_register_device(&lguest_clockevent);
 
 	/* Finally, we unblock the timer interrupt. */
-	enable_lguest_irq(0);
+	clear_bit(0, lguest_data.blocked_interrupts);
 }
 
 /*
@@ -1349,9 +1352,6 @@ __init void lguest_init(void)
 	 */
 	switch_to_new_gdt(0);
 
-	/* We actually boot with all memory mapped, but let's say 128MB. */
-	max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
-
 	/*
 	 * The Host<->Guest Switcher lives at the top of our address space, and
 	 * the Host told us how big it is when we made LGUEST_INIT hypercall:
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 4f420c2f..e7d5382 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -4,6 +4,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
+#include <asm/pgtable.h>
 
 /*G:020
  * Our story starts with the kernel booting into startup_32 in
@@ -37,9 +38,113 @@ ENTRY(lguest_entry)
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 
+	call init_pagetables
+
 	/* Jumps are relative: we're running __PAGE_OFFSET too low. */
 	jmp lguest_init+__PAGE_OFFSET
 
+/*
+ * Initialize page tables.  This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base.  The variable
+ * _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.
+ *
+ * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they
+ * don't have a stack at this point, so we can't just use call and ret.
+ */
+init_pagetables:
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+#define pa(X) ((X) - __PAGE_OFFSET)
+
+/* Enough space to fit pagetables for the low memory linear map */
+MAPPING_BEYOND_END = \
+	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+#ifdef CONFIG_X86_PAE
+
+	/*
+	 * In PAE mode initial_page_table is statically defined to contain
+	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+	 * entries). The identity mapping is handled by pointing two PGD entries
+	 * to the first kernel PMD.
+	 *
+	 * Note the upper half of each PMD or PTE are always zero at this stage.
+	 */
+
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
+
+	xorl %ebx,%ebx				/* %ebx is kept at zero */
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_pg_pmd), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
+	movl %ecx,(%edx)			/* Store PMD entry */
+						/* Upper half already zero */
+	addl $8,%edx
+	movl $512,%ecx
+11:
+	stosl
+	xchgl %eax,%ebx
+	stosl
+	xchgl %eax,%ebx
+	addl $0x1000,%eax
+	loop 11b
+
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+1:
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
+#else	/* Not PAE */
+
+page_pde_offset = (__PAGE_OFFSET >> 20);
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_page_table), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
+	movl %ecx,(%edx)			/* Store identity PDE entry */
+	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
+	addl $4,%edx
+	movl $1024, %ecx
+11:
+	stosl
+	addl $0x1000,%eax
+	loop 11b
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_page_table+0xffc)
+#endif
+	ret
+
 /*G:055
  * We create a macro which puts the assembler code between lgstart_ and lgend_
  * markers.  These templates are put in the .text section: they can't be
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index c4bb261c..b1805b7 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -65,21 +65,13 @@ pcibios_align_resource(void *data, const struct resource *res,
 			resource_size_t size, resource_size_t align)
 {
 	struct pci_dev *dev = data;
-	resource_size_t start = round_down(res->end - size + 1, align);
+	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO) {
-
-		/*
-		 * If we're avoiding ISA aliases, the largest contiguous I/O
-		 * port space is 256 bytes.  Clearing bits 9 and 10 preserves
-		 * all 256-byte and smaller alignments, so the result will
-		 * still be correctly aligned.
-		 */
-		if (!skip_isa_ioresource_align(dev))
-			start &= ~0x300;
-	} else if (res->flags & IORESOURCE_MEM) {
-		if (start < BIOS_END)
-			start = res->end;	/* fail; no space */
+		if (skip_isa_ioresource_align(dev))
+			return start;
+		if (start & 0x300)
+			start = (start + 0x3ff) & ~0x3ff;
 	}
 	return start;
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index d7b5109..25cd4a0 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -70,6 +70,9 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 struct xen_pci_frontend_ops *xen_pci_frontend;
 EXPORT_SYMBOL_GPL(xen_pci_frontend);
 
+#define XEN_PIRQ_MSI_DATA  (MSI_DATA_TRIGGER_EDGE | \
+		MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0))
+
 static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		struct msi_msg *msg)
 {
@@ -83,12 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		MSI_ADDR_REDIRECTION_CPU |
 		MSI_ADDR_DEST_ID(pirq);
 
-	msg->data =
-		MSI_DATA_TRIGGER_EDGE |
-		MSI_DATA_LEVEL_ASSERT |
-		/* delivery mode reserved */
-		(3 << 8) |
-		MSI_DATA_VECTOR(0);
+	msg->data = XEN_PIRQ_MSI_DATA;
 }
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -98,8 +96,23 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	struct msi_msg msg;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
+		__read_msi_msg(msidesc, &msg);
+		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
+			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
+		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
+			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
+					"msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
+			if (irq < 0)
+				goto error;
+			ret = set_irq_msi(irq, msidesc);
+			if (ret < 0)
+				goto error_while;
+			printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
+					" pirq=%d\n", irq, pirq);
+			return 0;
+		}
 		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq);
+				"msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
 		if (irq < 0 || pirq < 0)
 			goto error;
 		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 4a2afa1..b6552b1 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -25,7 +25,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
 
 export CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -Wl,-soname=linux-vdso.so.1 \
+VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 		      	-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
@@ -69,7 +69,7 @@ vdso32.so-$(VDSO32-y)		+= sysenter
 vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1
 
 # This makes sure the $(obj) subdirectory exists even though vdso32/
 # is not a kbuild sub-make subdirectory.
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 02c710b..44dcad4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1021,10 +1021,6 @@ static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
 
-#ifdef CONFIG_SMP
-	stop_other_cpus();
-#endif
-
 	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a1feff9..44924e5 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2415,8 +2415,6 @@ void __init xen_init_mmu_ops(void)
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;
 
-	vmap_lazy_unmap = false;
-
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
 
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 0f45638..25c52f9 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -68,7 +68,7 @@ static int __init check_platform_magic(void)
 	return 0;
 }
 
-void __init xen_unplug_emulated_devices(void)
+void xen_unplug_emulated_devices(void)
 {
 	int r;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 01afd8a..b5a7f92 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -181,24 +181,21 @@ char * __init xen_memory_setup(void)
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end = map[i].addr + map[i].size;
 
-		if (map[i].type == E820_RAM) {
-			if (map[i].addr < mem_end && end > mem_end) {
-				/* Truncate region to max_mem. */
-				u64 delta = end - mem_end;
+		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);
 
-				map[i].size -= delta;
-				extra_pages += PFN_DOWN(delta);
+			map[i].size -= delta;
+			end -= delta;
 
-				end = mem_end;
-			}
+			extra_pages += PFN_DOWN(delta);
 		}
 
-		if (end > xen_extra_mem_start)
+		if (map[i].size > 0 && end > xen_extra_mem_start)
 			xen_extra_mem_start = end;
 
-		/* If region is non-RAM or below mem_end, add what remains */
-		if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
-		    map[i].size > 0)
+		/* Add region if any remains */
+		if (map[i].size > 0)
 			e820_add_region(map[i].addr, map[i].size, map[i].type);
 	}
 
@@ -252,20 +249,6 @@ char * __init xen_memory_setup(void)
 	return "Xen";
 }
 
-static void xen_idle(void)
-{
-	local_irq_disable();
-
-	if (need_resched())
-		local_irq_enable();
-	else {
-		current_thread_info()->status &= ~TS_POLLING;
-		smp_mb__after_clear_bit();
-		safe_halt();
-		current_thread_info()->status |= TS_POLLING;
-	}
-}
-
 /*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
@@ -362,7 +345,11 @@ void __init xen_arch_setup(void)
 	       MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ?
 	       COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
 
-	pm_idle = xen_idle;
+	/* Set up idle, making sure it calls safe_halt() pvop */
+#ifdef CONFIG_X86_32
+	boot_cpu_data.hlt_works_ok = 1;
+#endif
+	pm_idle = default_idle;
 
 	fiddle_vdso();
 }
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 1d789d5..9bbd63a 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -31,6 +31,7 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 	int cpu;
 	xen_hvm_init_shared_info();
 	xen_callback_vector();
+	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		for_each_online_cpu(cpu) {
 			xen_setup_runstate_info(cpu);
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index b2bb5aa3..5da5e53 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -426,6 +426,8 @@ void xen_timer_resume(void)
 {
 	int cpu;
 
+	pvclock_resume();
+
 	if (xen_clockevent != &xen_vcpuop_clockevent)
 		return;
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 6404474..9d41bf9 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -43,7 +43,7 @@ void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
 void xen_hvm_init_shared_info(void);
-void __init xen_unplug_emulated_devices(void);
+void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);