22 files changed, 196 insertions, 125 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9e13763b6092..1e994754d323 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 850657d1b0ed..78218135b48e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -52,7 +52,6 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
-#include <asm/atomic.h>
 
 unsigned int num_processors;
 
@@ -1390,6 +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/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index cefd6942f0e9..62f6e1e55b90 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,15 +17,16 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
 u64 hw_nmi_get_sample_period(void)
 {
 	return (u64)(cpu_khz) * 1000 * 60;
 }
 
 #ifdef ARCH_HAS_NMI_WATCHDOG
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
 void arch_trigger_all_cpu_backtrace(void)
 {
 	int i;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7cc0a721f628..fadcd743a74f 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 f9e4e6a54073..d8c4a6feb286 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/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ed4118de249e..c1c52c341f40 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -44,6 +44,8 @@ static u64 gru_start_paddr, gru_end_paddr;
 static union uvh_apicid uvh_apicid;
 int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+unsigned int uv_apicid_hibits;
+EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 static DEFINE_SPINLOCK(uv_nmi_lock);
 
 static inline bool is_GRU_range(u64 start, u64 end)
@@ -85,6 +87,23 @@ static void __init early_get_apic_pnode_shift(void)
 		uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT;
 }
 
+/*
+ * Add an extra bit as dictated by bios to the destination apicid of
+ * interrupts potentially passing through the UV HUB.  This prevents
+ * a deadlock between interrupts and IO port operations.
+ */
+static void __init uv_set_apicid_hibit(void)
+{
+	union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
+	unsigned long *mmr;
+
+	mmr = early_ioremap(UV_LOCAL_MMR_BASE |
+		UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK, sizeof(*mmr));
+	apicid_mask.v = *mmr;
+	early_iounmap(mmr, sizeof(*mmr));
+	uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
+}
+
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	int nodeid;
@@ -102,6 +121,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 			__get_cpu_var(x2apic_extra_bits) =
 				nodeid << (uvh_apicid.s.pnode_shift - 1);
 			uv_system_type = UV_NON_UNIQUE_APIC;
+			uv_set_apicid_hibit();
 			return 1;
 		}
 	}
@@ -155,6 +175,7 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri
 	int pnode;
 
 	pnode = uv_apicid_to_pnode(phys_apicid);
+	phys_apicid |= uv_apicid_hibits;
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
@@ -236,7 +257,7 @@ static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask)
 	int cpu = cpumask_first(cpumask);
 
 	if ((unsigned)cpu < nr_cpu_ids)
-		return per_cpu(x86_cpu_to_apicid, cpu);
+		return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits;
 	else
 		return BAD_APICID;
 }
@@ -255,7 +276,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
 			break;
 	}
-	return per_cpu(x86_cpu_to_apicid, cpu);
+	return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits;
 }
 
 static unsigned int x2apic_get_apic_id(unsigned long x)
@@ -379,14 +400,14 @@ struct redir_addr {
 #define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
 
 static __initdata struct redir_addr redir_addrs[] = {
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR},
 };
 
 static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 {
-	union uvh_si_alias0_overlay_config_u alias;
+	union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias;
 	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
 	int i;
 
@@ -660,7 +681,7 @@ void uv_nmi_init(void)
 
 void __init uv_system_init(void)
 {
-	union uvh_si_addr_map_config_u m_n_config;
+	union uvh_rh_gam_config_mmr_u  m_n_config;
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
@@ -670,7 +691,7 @@ void __init uv_system_init(void)
 
 	map_low_mmrs();
 
-	m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
+	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
 	mmr_base =
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ed6310183efb..6d75b9145b13 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -381,6 +381,20 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
+static bool check_hw_exists(void)
+{
+	u64 val, val_new = 0;
+	int ret = 0;
+
+	val = 0xabcdUL;
+	ret |= checking_wrmsrl(x86_pmu.perfctr, val);
+	ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+	if (ret || val != val_new)
+		return false;
+
+	return true;
+}
+
 static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
@@ -1372,6 +1386,12 @@ void __init init_hw_perf_events(void)
 
 	pmu_check_apic();
 
+	/* sanity check that the hardware exists or is emulated */
+	if (!check_hw_exists()) {
+		pr_cont("Broken PMU hardware detected, software events only.\n");
+		return;
+	}
+
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	if (x86_pmu.quirks)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 46d58448c3af..e421b8cd6944 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -280,11 +280,11 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	struct amd_nb *nb;
 	int i;
 
-	nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+	nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
+			  cpu_to_node(cpu));
 	if (!nb)
 		return NULL;
 
-	memset(nb, 0, sizeof(*nb));
 	nb->nb_id = nb_id;
 
 	/*
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 1b7b31ab7d86..212a6a42527c 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -33,7 +33,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 59e175e89599..591e60104278 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -395,7 +395,7 @@ sysenter_past_esp:
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
-	pushl_cfi (TI_sysenter_return-THREAD_SIZE_asm+8+4*4)(%esp)
+	pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
 	CFI_REL_OFFSET eip, 0
 
 	pushl_cfi %eax
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index fe2690d71c0c..e3ba417e8697 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64)
 	.endm
 
 /* save partial stack frame */
+	.pushsection .kprobes.text, "ax"
 ENTRY(save_args)
 	XCPT_FRAME
 	cld
@@ -334,6 +335,7 @@ ENTRY(save_args)
 	ret
 	CFI_ENDPROC
 END(save_args)
+	.popsection
 
 ENTRY(save_rest)
 	PARTIAL_FRAME 1 REST_SKIP+8
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 8e09aa3aa6d6..01c3d455e576 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 ae03cab4352e..4ff5968f12d2 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/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ff15c9dcc25d..42c594254507 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 	dr6_p = (unsigned long *)ERR_PTR(args->err);
 	dr6 = *dr6_p;
 
+	/* If it's a single step, TRAP bits are random */
+	if (dr6 & DR_STEP)
+		return NOTIFY_DONE;
+
 	/* Do an early return if no trap bits are set in DR6 */
 	if ((dr6 & DR_TRAP_BITS) == 0)
 		return NOTIFY_DONE;
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index ec592caac4b4..cd21b654dec6 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void)
 		if (!breakinfo[i].enabled)
 			continue;
 		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
-		if (bp->attr.disabled == 1)
+		if (!bp->attr.disabled) {
+			arch_uninstall_hw_breakpoint(bp);
+			bp->attr.disabled = 1;
 			continue;
+		}
 		if (dbg_is_early)
 			early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
 						 breakinfo[i].type);
-		else
-			arch_uninstall_hw_breakpoint(bp);
-		bp->attr.disabled = 1;
+		else if (hw_break_release_slot(i))
+			printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n",
+			       breakinfo[i].addr);
+		breakinfo[i].enabled = 0;
 	}
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index e1af7c055c7d..ce0cb4721c9a 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -212,7 +212,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 		return 0;
 	}
 
-	equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size);
+	equiv_cpu_table = vmalloc(size);
 	if (!equiv_cpu_table) {
 		pr_err("failed to allocate equivalent CPU table\n");
 		return 0;
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 71825806cd44..ac861b8348e2 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -25,7 +25,6 @@ struct pci_hostbridge_probe {
 };
 
 static u64 __cpuinitdata fam10h_pci_mmconf_base;
-static int __cpuinitdata fam10h_pci_mmconf_base_status;
 
 static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
 	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 },
@@ -44,10 +43,12 @@ static int __cpuinit cmp_range(const void *x1, const void *x2)
 	return start1 - start2;
 }
 
-/*[47:0] */
-/* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */
+#define MMCONF_UNIT (1ULL << FAM10H_MMIO_CONF_BASE_SHIFT)
+#define MMCONF_MASK (~(MMCONF_UNIT - 1))
+#define MMCONF_SIZE (MMCONF_UNIT << 8)
+/* need to avoid (0xfd<<32), (0xfe<<32), and (0xff<<32), ht used space */
 #define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32)
-#define BASE_VALID(b) ((b != (0xfdULL << 32)) && (b != (0xfeULL << 32)))
+#define BASE_VALID(b) ((b) + MMCONF_SIZE <= (0xfdULL<<32) || (b) >= (1ULL<<40))
 static void __cpuinit get_fam10h_pci_mmconf_base(void)
 {
 	int i;
@@ -64,12 +65,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 	struct range range[8];
 
 	/* only try to get setting from BSP */
-	/* -1 or 1 */
-	if (fam10h_pci_mmconf_base_status)
+	if (fam10h_pci_mmconf_base)
 		return;
 
 	if (!early_pci_allowed())
-		goto fail;
+		return;
 
 	found = 0;
 	for (i = 0; i < ARRAY_SIZE(pci_probes); i++) {
@@ -91,7 +91,7 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 	}
 
 	if (!found)
-		goto fail;
+		return;
 
 	/* SYS_CFG */
 	address = MSR_K8_SYSCFG;
@@ -99,16 +99,16 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 
 	/* TOP_MEM2 is not enabled? */
 	if (!(val & (1<<21))) {
-		tom2 = 0;
+		tom2 = 1ULL << 32;
 	} else {
 		/* TOP_MEM2 */
 		address = MSR_K8_TOP_MEM2;
 		rdmsrl(address, val);
-		tom2 = val & (0xffffULL<<32);
+		tom2 = max(val & 0xffffff800000ULL, 1ULL << 32);
 	}
 
 	if (base <= tom2)
-		base = tom2 + (1ULL<<32);
+		base = (tom2 + 2 * MMCONF_UNIT - 1) & MMCONF_MASK;
 
 	/*
 	 * need to check if the range is in the high mmio range that is
@@ -123,11 +123,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 		if (!(reg & 3))
 			continue;
 
-		start = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/
+		start = (u64)(reg & 0xffffff00) << 8; /* 39:16 on 31:8*/
 		reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3));
-		end = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/
+		end = ((u64)(reg & 0xffffff00) << 8) | 0xffff; /* 39:16 on 31:8*/
 
-		if (!end)
+		if (end < tom2)
 			continue;
 
 		range[hi_mmio_num].start = start;
@@ -143,32 +143,27 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void)
 
 	if (range[hi_mmio_num - 1].end < base)
 		goto out;
-	if (range[0].start > base)
+	if (range[0].start > base + MMCONF_SIZE)
 		goto out;
 
 	/* need to find one window */
-	base = range[0].start - (1ULL << 32);
+	base = (range[0].start & MMCONF_MASK) - MMCONF_UNIT;
 	if ((base > tom2) && BASE_VALID(base))
 		goto out;
-	base = range[hi_mmio_num - 1].end + (1ULL << 32);
-	if ((base > tom2) && BASE_VALID(base))
+	base = (range[hi_mmio_num - 1].end + MMCONF_UNIT) & MMCONF_MASK;
+	if (BASE_VALID(base))
 		goto out;
 	/* need to find window between ranges */
-	if (hi_mmio_num > 1)
-	for (i = 0; i < hi_mmio_num - 1; i++) {
-		if (range[i + 1].start > (range[i].end + (1ULL << 32))) {
-			base = range[i].end + (1ULL << 32);
-			if ((base > tom2) && BASE_VALID(base))
-				goto out;
-		}
+	for (i = 1; i < hi_mmio_num; i++) {
+		base = (range[i - 1].end + MMCONF_UNIT) & MMCONF_MASK;
+		val = range[i].start & MMCONF_MASK;
+		if (val >= base + MMCONF_SIZE && BASE_VALID(base))
+			goto out;
 	}
-
-fail:
-	fam10h_pci_mmconf_base_status = -1;
 	return;
+
 out:
 	fam10h_pci_mmconf_base = base;
-	fam10h_pci_mmconf_base_status = 1;
 }
 
 void __cpuinit fam10h_check_enable_mmcfg(void)
@@ -190,11 +185,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
 
 		/* only trust the one handle 256 buses, if acpi=off */
 		if (!acpi_pci_disabled || busnbits >= 8) {
-			u64 base;
-			base = val & (0xffffULL << 32);
-			if (fam10h_pci_mmconf_base_status <= 0) {
+			u64 base = val & MMCONF_MASK;
+
+			if (!fam10h_pci_mmconf_base) {
 				fam10h_pci_mmconf_base = base;
-				fam10h_pci_mmconf_base_status = 1;
 				return;
 			} else if (fam10h_pci_mmconf_base ==  base)
 				return;
@@ -206,8 +200,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
 	 * with 256 buses
 	 */
 	get_fam10h_pci_mmconf_base();
-	if (fam10h_pci_mmconf_base_status <= 0)
+	if (!fam10h_pci_mmconf_base) {
+		pci_probe &= ~PCI_CHECK_ENABLE_AMD_MMCONF;
 		return;
+	}
 
 	printk(KERN_INFO "Enable MMCONFIG on AMD Family 10h\n");
 	val &= ~((FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT) |
@@ -217,13 +213,13 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
 	wrmsrl(address, val);
 }
 
-static int __devinit set_check_enable_amd_mmconf(const struct dmi_system_id *d)
+static int __init set_check_enable_amd_mmconf(const struct dmi_system_id *d)
 {
         pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF;
         return 0;
 }
 
-static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = {
+static const struct dmi_system_id __initconst mmconf_dmi_table[] = {
         {
                 .callback = set_check_enable_amd_mmconf,
                 .ident = "Sun Microsystems Machine",
@@ -234,7 +230,8 @@ static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = {
 	{}
 };
 
-void __cpuinit check_enable_amd_mmconf_dmi(void)
+/* Called from a __cpuinit function, but only on the BSP. */
+void __ref check_enable_amd_mmconf_dmi(void)
 {
 	dmi_check_system(mmconf_dmi_table);
 }
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7bf2dc4c8f70..12fcbe2c143e 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -30,7 +30,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index bab3b9e6f66d..42eb3300dfc6 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -41,44 +41,6 @@ void pvclock_set_flags(u8 flags)
 	valid_flags = flags;
 }
 
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
-	u64 product;
-#ifdef __i386__
-	u32 tmp1, tmp2;
-#endif
-
-	if (shift < 0)
-		delta >>= -shift;
-	else
-		delta <<= shift;
-
-#ifdef __i386__
-	__asm__ (
-		"mul  %5       ; "
-		"mov  %4,%%eax ; "
-		"mov  %%edx,%4 ; "
-		"mul  %5       ; "
-		"xor  %5,%5    ; "
-		"add  %4,%%eax ; "
-		"adc  %5,%%edx ; "
-		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
-		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif defined(__x86_64__)
-	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
-	return product;
-}
-
 static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
 {
 	u64 delta = native_read_tsc() - shadow->tsc_timestamp;
@@ -121,6 +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 000000000000..2a26819bb6a8
--- /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 21c6746338af..85268f8eadf6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -769,7 +769,6 @@ 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 9c253bd65e24..547128546cc3 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();