Merge branch 'linus' into perf/core

Refresh the branch to a v3.14-rc base before queueing up new devel patches.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 128 insertions, 53 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 6c0b43bd024b..1dac94265b59 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -46,7 +46,6 @@
 
 #include "sleep.h" /* To include x86_acpi_suspend_lowlevel */
 static int __initdata acpi_force = 0;
-u32 acpi_rsdt_forced;
 int acpi_disabled;
 EXPORT_SYMBOL(acpi_disabled);
 
@@ -1034,9 +1033,7 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
 
         if (!acpi_ioapic)
                 return 0;
-        if (!dev)
-                return 0;
-        if (dev->bus != &pci_bus_type)
+        if (!dev || !dev_is_pci(dev))
                 return 0;
 
         pdev = to_pci_dev(dev);
@@ -1564,7 +1561,7 @@ static int __init parse_acpi(char *arg)
         }
         /* acpi=rsdt use RSDT instead of XSDT */
         else if (strcmp(arg, "rsdt") == 0) {
-                acpi_rsdt_forced = 1;
+                acpi_gbl_do_not_use_xsdt = TRUE;
         }
         /* "acpi=noirq" disables ACPI interrupt routing */
         else if (strcmp(arg, "noirq") == 0) {
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dca96ec..dec8de4e1663 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu)
         return (mask >> (4 * cuid)) & 0xf;
 }
 
-int amd_set_subcaches(int cpu, int mask)
+int amd_set_subcaches(int cpu, unsigned long mask)
 {
         static unsigned int reset, ban;
         struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 5d5b9eb2b7a4..2c621a6b901a 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -20,9 +20,7 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 
-#ifdef CONFIG_ACPI
-#include <acpi/acpi_bus.h>
-#endif
+#include <linux/acpi.h>
 
 static struct apic apic_physflat;
 static struct apic apic_flat;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index a43f068ebec1..6ad4658de705 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -37,9 +37,6 @@
 #include <linux/kthread.h>
 #include <linux/jiffies.h>      /* time_after() */
 #include <linux/slab.h>
-#ifdef CONFIG_ACPI
-#include <acpi/acpi_bus.h>
-#endif
 #include <linux/bootmem.h>
 #include <linux/dmar.h>
 #include <linux/hpet.h>
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ad0dc0428baf..d263b1307de1 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -980,7 +980,6 @@ void __init uv_system_init(void)
         uv_nmi_setup();
         uv_cpu_init();
         uv_scir_register_cpu_notifier();
-        uv_register_nmi_notifier();
         proc_mkdir("sgi_uv", NULL);
 
         /* register Legacy VGA I/O redirection handler */
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index e2dbcb7dabdd..83a7995625a6 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -91,7 +91,7 @@ void __init setup_bios_corruption_check(void)
 
         corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-        for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
+        for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {
                 start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
                                 PAGE_SIZE, corruption_check_size);
                 end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d3153e281d72..c67ffa686064 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -767,10 +767,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 
 static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-        tlb_flushall_shift = 5;
-
-        if (c->x86 <= 0x11)
-                tlb_flushall_shift = 4;
+        tlb_flushall_shift = 6;
 }
 
 static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3db61c644e44..5cd9bfabd645 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -640,21 +640,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
         case 0x61d: /* six-core 45 nm xeon "Dunnington" */
                 tlb_flushall_shift = -1;
                 break;
+        case 0x63a: /* Ivybridge */
+                tlb_flushall_shift = 2;
+                break;
         case 0x61a: /* 45 nm nehalem, "Bloomfield" */
         case 0x61e: /* 45 nm nehalem, "Lynnfield" */
         case 0x625: /* 32 nm nehalem, "Clarkdale" */
         case 0x62c: /* 32 nm nehalem, "Gulftown" */
         case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
         case 0x62f: /* 32 nm Xeon E7 */
-                tlb_flushall_shift = 6;
-                break;
         case 0x62a: /* SandyBridge */
         case 0x62d: /* SandyBridge, "Romely-EP" */
-                tlb_flushall_shift = 5;
-                break;
-        case 0x63a: /* Ivybridge */
-                tlb_flushall_shift = 1;
-                break;
         default:
                 tlb_flushall_shift = 6;
         }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a6ff747aaad..8fffd845e22b 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -433,7 +433,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
         if (c->x86 >= 0x15)
                 snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
-        if (request_firmware(&fw, (const char *)fw_name, device)) {
+        if (request_firmware_direct(&fw, (const char *)fw_name, device)) {
                 pr_debug("failed to load file %s\n", fw_name);
                 goto out;
         }
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 8384c0fa206f..617a9e284245 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
 
         uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
+
+static void __init get_bsp_sig(void)
+{
+        unsigned int bsp = boot_cpu_data.cpu_index;
+        struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+        if (!uci->cpu_sig.sig)
+                smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+}
 #else
 void load_ucode_amd_ap(void)
 {
@@ -337,31 +346,37 @@ void load_ucode_amd_ap(void)
 
 int __init save_microcode_in_initrd_amd(void)
 {
+        unsigned long cont;
         enum ucode_state ret;
         u32 eax;
 
-#ifdef CONFIG_X86_32
-        unsigned int bsp = boot_cpu_data.cpu_index;
-        struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
-
-        if (!uci->cpu_sig.sig)
-                smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+        if (!container)
+                return -EINVAL;
 
+#ifdef CONFIG_X86_32
+        get_bsp_sig();
+        cont = (unsigned long)container;
+#else
         /*
-         * Take into account the fact that the ramdisk might get relocated
-         * and therefore we need to recompute the container's position in
-         * virtual memory space.
+         * We need the physical address of the container for both bitness since
+         * boot_params.hdr.ramdisk_image is a physical address.
          */
-        container = (u8 *)(__va((u32)relocated_ramdisk) +
-                           ((u32)container - boot_params.hdr.ramdisk_image));
+        cont = __pa(container);
 #endif
+
+        /*
+         * Take into account the fact that the ramdisk might get relocated and
+         * therefore we need to recompute the container's position in virtual
+         * memory space.
+         */
+        if (relocated_ramdisk)
+                container = (u8 *)(__va(relocated_ramdisk) +
+                             (cont - boot_params.hdr.ramdisk_image));
+
         if (ucode_new_rev)
                 pr_info("microcode: updated early to new patch_level=0x%08x\n",
                         ucode_new_rev);
 
-        if (!container)
-                return -EINVAL;
-
         eax   = cpuid_eax(0x00000001);
         eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 5fb2cebf556b..a276fa75d9b5 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -278,7 +278,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
         sprintf(name, "intel-ucode/%02x-%02x-%02x",
                 c->x86, c->x86_model, c->x86_mask);
 
-        if (request_firmware(&firmware, name, device)) {
+        if (request_firmware_direct(&firmware, name, device)) {
                 pr_debug("data file %s load failed\n", name);
                 return UCODE_NFOUND;
         }
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2c3e4f..0e25a1bc5ab5 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
         }
 
         /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-        count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
         __flush_tlb();
 
         /* Save MTRR state */
@@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
         /* Flush TLBs (no need to flush caches - they are disabled) */
-        count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
         __flush_tlb();
 
         /* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 174da5fc5a7b..988c00a1f60d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1120,7 +1120,7 @@ void __init memblock_find_dma_reserve(void)
                 nr_pages += end_pfn - start_pfn;
         }
 
-        for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) {
+        for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {
                 start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
                 end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
                 if (start_pfn < end_pfn)
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index dbb60878b744..d99f31d9a750 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
 /*
  * This cpu is going to be removed and its vectors migrated to the remaining
  * online cpus.  Check to see if there are enough vectors in the remaining cpus.
@@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void)
         unsigned int this_cpu, vector, this_count, count;
         struct irq_desc *desc;
         struct irq_data *data;
-        struct cpumask affinity_new, online_new;
 
         this_cpu = smp_processor_id();
         cpumask_copy(&online_new, cpu_online_mask);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 6dd802c6d780..713f1b3bad52 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -500,6 +500,38 @@ void __init kvm_guest_init(void)
 #endif
 }
 
+static noinline uint32_t __kvm_cpuid_base(void)
+{
+        if (boot_cpu_data.cpuid_level < 0)
+                return 0;       /* So we don't blow up on old processors */
+
+        if (cpu_has_hypervisor)
+                return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
+
+        return 0;
+}
+
+static inline uint32_t kvm_cpuid_base(void)
+{
+        static int kvm_cpuid_base = -1;
+
+        if (kvm_cpuid_base == -1)
+                kvm_cpuid_base = __kvm_cpuid_base();
+
+        return kvm_cpuid_base;
+}
+
+bool kvm_para_available(void)
+{
+        return kvm_cpuid_base() != 0;
+}
+EXPORT_SYMBOL_GPL(kvm_para_available);
+
+unsigned int kvm_arch_para_features(void)
+{
+        return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
+}
+
 static uint32_t __init kvm_detect(void)
 {
         return kvm_cpuid_base();
@@ -673,7 +705,7 @@ static cpumask_t waiting_cpus;
 /* Track spinlock on which a cpu is waiting */
 static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting);
 
-static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
+__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
         struct kvm_lock_waiting *w;
         int cpu;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2e4c02..7c6acd4b8995 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
                         quirk_amd_nb_node);
 
 #endif
+
+#ifdef CONFIG_PCI
+/*
+ * Processor does not ensure DRAM scrub read/write sequence
+ * is atomic wrt accesses to CC6 save state area. Therefore
+ * if a concurrent scrub read/write access is to same address
+ * the entry may appear as if it is not written. This quirk
+ * applies to Fam16h models 00h-0Fh
+ *
+ * See "Revision Guide" for AMD F16h models 00h-0fh,
+ * document 51810 rev. 3.04, Nov 2013
+ */
+static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
+{
+        u32 val;
+
+        /*
+         * Suggested workaround:
+         * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b
+         */
+        pci_read_config_dword(dev, 0x58, &val);
+        if (val & 0x1F) {
+                val &= ~(0x1F);
+                pci_write_config_dword(dev, 0x58, val);
+        }
+
+        pci_read_config_dword(dev, 0x5C, &val);
+        if (val & BIT(0)) {
+                val &= ~BIT(0);
+                pci_write_config_dword(dev, 0x5c, val);
+        }
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
+                        amd_disable_seq_and_redirect_scrub);
+
+#endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a3acbac2ee72..19e5adb49a27 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -180,7 +180,7 @@ static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
 
 static void cyc2ns_data_init(struct cyc2ns_data *data)
 {
-        data->cyc2ns_mul = 1U << CYC2NS_SCALE_FACTOR;
+        data->cyc2ns_mul = 0;
         data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
         data->cyc2ns_offset = 0;
         data->__count = 0;
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 992f890283e9..f6584a90aba3 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -33,7 +33,7 @@
  * and vice versa.
  */
 
-static unsigned long vsmp_save_fl(void)
+asmlinkage unsigned long vsmp_save_fl(void)
 {
         unsigned long flags = native_save_fl();
 
@@ -43,7 +43,7 @@ static unsigned long vsmp_save_fl(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
 
-static void vsmp_restore_fl(unsigned long flags)
+__visible void vsmp_restore_fl(unsigned long flags)
 {
         if (flags & X86_EFLAGS_IF)
                 flags &= ~X86_EFLAGS_AC;
@@ -53,7 +53,7 @@ static void vsmp_restore_fl(unsigned long flags)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
 
-static void vsmp_irq_disable(void)
+asmlinkage void vsmp_irq_disable(void)
 {
         unsigned long flags = native_save_fl();
 
@@ -61,7 +61,7 @@ static void vsmp_irq_disable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
 
-static void vsmp_irq_enable(void)
+asmlinkage void vsmp_irq_enable(void)
 {
         unsigned long flags = native_save_fl();
 
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 021783b1f46a..e48b674639cc 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -136,9 +136,9 @@ void arch_teardown_msi_irq(unsigned int irq)
         x86_msi.teardown_msi_irq(irq);
 }
 
-void arch_restore_msi_irqs(struct pci_dev *dev, int irq)
+void arch_restore_msi_irqs(struct pci_dev *dev)
 {
-        x86_msi.restore_msi_irqs(dev, irq);
+        x86_msi.restore_msi_irqs(dev);
 }
 u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {