Merge branch 'linus' into perf/core

Merge reason: Pick up the latest perf fixes.

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

14 files changed, 61 insertions, 56 deletions

diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 519b54327d75..baa579c8e038 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -142,6 +142,7 @@ struct x86_cpuinit_ops {
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
+ * @i8042_detect		pre-detect if i8042 controller exists
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
@@ -150,6 +151,7 @@ struct x86_platform_ops {
 	void (*iommu_shutdown)(void);
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
+	int (*i8042_detect)(void);
 };
 
 extern struct x86_init_ops x86_init;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c02cc692985c..a96489ee6cab 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -921,7 +921,7 @@ void disable_local_APIC(void)
 	unsigned int value;
 
 	/* APIC hasn't been mapped yet */
-	if (!apic_phys)
+	if (!x2apic_mode && !apic_phys)
 		return;
 
 	clear_local_APIC();
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85cf2686..e5cc7e82e60d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,6 +18,7 @@
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/hpet.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -191,6 +192,21 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
+/*
+ * Force the read back of the CMP register in hpet_next_event()
+ * to work around the problem that the CMP register write seems to be
+ * delayed. See hpet_next_event() for details.
+ *
+ * We do this on all SMBUS incarnations for now until we have more
+ * information about the affected chipsets.
+ */
+static void __init ati_hpet_bugs(int num, int slot, int func)
+{
+#ifdef CONFIG_HPET_TIMER
+	hpet_readback_cmp = 1;
+#endif
+}
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -220,6 +236,8 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
+	{ PCI_VENDOR_ID_ATI, PCI_ANY_ID,
+	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs },
 	{}
 };
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 175f85ceace3..1bfb6cf4dd55 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -642,8 +642,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	/* Skip cs, ip, orig_ax and gs. */	\
 	"	subl $16, %esp\n"	\
 	"	pushl %fs\n"		\
-	"	pushl %ds\n"		\
 	"	pushl %es\n"		\
+	"	pushl %ds\n"		\
 	"	pushl %eax\n"		\
 	"	pushl %ebp\n"		\
 	"	pushl %edi\n"		\
diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c
index e796448f0eb5..5915e0b33303 100644
--- a/arch/x86/kernel/mrst.c
+++ b/arch/x86/kernel/mrst.c
@@ -216,6 +216,12 @@ static void __init mrst_setup_boot_clock(void)
 		setup_boot_APIC_clock();
 };
 
+/* MID systems don't have i8042 controller */
+static int mrst_i8042_detect(void)
+{
+	return 0;
+}
+
 /*
  * Moorestown specific x86_init function overrides and early setup
  * calls.
@@ -233,6 +239,7 @@ void __init x86_mrst_early_setup(void)
 	x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock;
 
 	x86_platform.calibrate_tsc = mrst_calibrate_tsc;
+	x86_platform.i8042_detect = mrst_i8042_detect;
 	x86_init.pci.init = pci_mrst_init;
 	x86_init.pci.fixup_irqs = x86_init_noop;
 
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 0b96b5589f08..078d4ec1a9d9 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -110,7 +110,7 @@ int use_calgary __read_mostly = 0;
  * x3950 (PCIE): 8 chassis, 32 PHBs per chassis   = 256
  * x3950 (PCIX): 8 chassis, 16 PHBs per chassis   = 128
  */
-#define MAX_PHB_BUS_NUM		384
+#define MAX_PHB_BUS_NUM		256
 
 #define PHBS_PER_CALGARY	  4
 
@@ -1056,8 +1056,6 @@ static int __init calgary_init_one(struct pci_dev *dev)
 	struct iommu_table *tbl;
 	int ret;
 
-	BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM);
-
 	bbar = busno_to_bbar(dev->bus->number);
 	ret = calgary_setup_tar(dev, bbar);
 	if (ret)
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e72d3fc6547d..939b9e98245f 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -498,15 +498,10 @@ void force_hpet_resume(void)
  * See erratum #27 (Misinterpreted MSI Requests May Result in
  * Corrupted LPC DMA Data) in AMD Publication #46837,
  * "SB700 Family Product Errata", Rev. 1.0, March 2010.
- *
- * Also force the read back of the CMP register in hpet_next_event()
- * to work around the problem that the CMP register write seems to be
- * delayed. See hpet_next_event() for details.
  */
 static void force_disable_hpet_msi(struct pci_dev *unused)
 {
 	hpet_msi_disable = 1;
-	hpet_readback_cmp = 1;
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index de3b63ae3da2..a60df9ae6454 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -238,6 +238,15 @@ void __init setup_per_cpu_areas(void)
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
+		/*
+		 * Ensure that the boot cpu numa_node is correct when the boot
+		 * cpu is on a node that doesn't have memory installed.
+		 * Also cpu_up() will call cpu_to_node() for APs when
+		 * MEMORY_HOTPLUG is defined, before per_cpu(numa_node) is set
+		 * up later with c_init aka intel_init/amd_init.
+		 * So set them all (boot cpu and all APs).
+		 */
+		set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
 #endif
 #endif
 		/*
@@ -257,14 +266,6 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
-	/*
-	 * make sure boot cpu numa_node is right, when boot cpu is on the
-	 * node that doesn't have mem installed
-	 */
-	set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id));
-#endif
-
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
 
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 61a1e8c7e19f..cd6da6bf3eca 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -5,6 +5,7 @@
  */
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/module.h>
 
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
@@ -85,6 +86,7 @@ struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
 };
 
 static void default_nmi_init(void) { };
+static int default_i8042_detect(void) { return 1; };
 
 struct x86_platform_ops x86_platform = {
 	.calibrate_tsc			= native_calibrate_tsc,
@@ -92,5 +94,8 @@ struct x86_platform_ops x86_platform = {
 	.set_wallclock			= mach_set_rtc_mmss,
 	.iommu_shutdown			= iommu_shutdown_noop,
 	.is_untracked_pat_range		= is_ISA_range,
-	.nmi_init			= default_nmi_init
+	.nmi_init			= default_nmi_init,
+	.i8042_detect			= default_i8042_detect
 };
+
+EXPORT_SYMBOL_GPL(x86_platform);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index a6f695d76928..b1ed0a1a5913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1879,6 +1879,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			pgprintk("hfn old %lx new %lx\n",
 				 spte_to_pfn(*sptep), pfn);
 			rmap_remove(vcpu->kvm, sptep);
+			__set_spte(sptep, shadow_trap_nonpresent_pte);
+			kvm_flush_remote_tlbs(vcpu->kvm);
 		} else
 			was_rmapped = 1;
 	}
@@ -2924,7 +2926,7 @@ static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm)
 	return kvm_mmu_zap_page(kvm, page) + 1;
 }
 
-static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
 	struct kvm *kvm;
 	struct kvm *kvm_freed = NULL;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 859a01a07dbf..ee03679efe78 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1744,18 +1744,15 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 			     (guest_tr_ar & ~AR_TYPE_MASK)
 			     | AR_TYPE_BUSY_64_TSS);
 	}
-	vcpu->arch.efer |= EFER_LMA;
-	vmx_set_efer(vcpu, vcpu->arch.efer);
+	vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
 }
 
 static void exit_lmode(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.efer &= ~EFER_LMA;
-
 	vmcs_write32(VM_ENTRY_CONTROLS,
 		     vmcs_read32(VM_ENTRY_CONTROLS)
 		     & ~VM_ENTRY_IA32E_MODE);
-	vmx_set_efer(vcpu, vcpu->arch.efer);
+	vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
 }
 
 #endif
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index f20eeec85a86..8acaddd0fb21 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -34,8 +34,7 @@
  * memtype_lock protects the rbtree.
  */
 
-static void memtype_rb_augment_cb(struct rb_node *node);
-static struct rb_root memtype_rbroot = RB_AUGMENT_ROOT(&memtype_rb_augment_cb);
+static struct rb_root memtype_rbroot = RB_ROOT;
 
 static int is_node_overlap(struct memtype *node, u64 start, u64 end)
 {
@@ -56,7 +55,7 @@ static u64 get_subtree_max_end(struct rb_node *node)
 }
 
 /* Update 'subtree_max_end' for a node, based on node and its children */
-static void update_node_max_end(struct rb_node *node)
+static void memtype_rb_augment_cb(struct rb_node *node, void *__unused)
 {
 	struct memtype *data;
 	u64 max_end, child_max_end;
@@ -78,25 +77,6 @@ static void update_node_max_end(struct rb_node *node)
 	data->subtree_max_end = max_end;
 }
 
-/* Update 'subtree_max_end' for a node and all its ancestors */
-static void update_path_max_end(struct rb_node *node)
-{
-	u64 old_max_end, new_max_end;
-
-	while (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
-
-		old_max_end = data->subtree_max_end;
-		update_node_max_end(node);
-		new_max_end = data->subtree_max_end;
-
-		if (new_max_end == old_max_end)
-			break;
-
-		node = rb_parent(node);
-	}
-}
-
 /* Find the first (lowest start addr) overlapping range from rb tree */
 static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
 				u64 start, u64 end)
@@ -190,12 +170,6 @@ failure:
 	return -EBUSY;
 }
 
-static void memtype_rb_augment_cb(struct rb_node *node)
-{
-	if (node)
-		update_path_max_end(node);
-}
-
 static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
 {
 	struct rb_node **node = &(root->rb_node);
@@ -213,6 +187,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
 
 	rb_link_node(&newdata->rb, parent, node);
 	rb_insert_color(&newdata->rb, root);
+	rb_augment_insert(&newdata->rb, memtype_rb_augment_cb, NULL);
 }
 
 int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
@@ -234,13 +209,16 @@ int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
 
 struct memtype *rbt_memtype_erase(u64 start, u64 end)
 {
+	struct rb_node *deepest;
 	struct memtype *data;
 
 	data = memtype_rb_exact_match(&memtype_rbroot, start, end);
 	if (!data)
 		goto out;
 
+	deepest = rb_augment_erase_begin(&data->rb);
 	rb_erase(&data->rb, &memtype_rbroot);
+	rb_augment_erase_end(deepest, memtype_rb_augment_cb, NULL);
 out:
 	return data;
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 6fdb3ec30c31..55253095be84 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -184,6 +184,7 @@ static void __init pcibios_allocate_resources(int pass)
 					idx, r, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
 					/* We'll assign a new address later */
+					dev->fw_addr[idx] = r->start;
 					r->end -= r->start;
 					r->start = 0;
 				}
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 7ef3a2735df3..cb29191cee58 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -66,8 +66,9 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
 					  devfn, pos, 4, &pcie_cap))
 			return 0;
 
-		if (pcie_cap == 0xffffffff)
-			return 0;
+		if (PCI_EXT_CAP_ID(pcie_cap) == 0x0000 ||
+			PCI_EXT_CAP_ID(pcie_cap) == 0xffff)
+			break;
 
 		if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) {
 			raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
@@ -76,7 +77,7 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
 				return pos;
 		}
 
-		pos = pcie_cap >> 20;
+		pos = PCI_EXT_CAP_NEXT(pcie_cap);
 	}
 
 	return 0;