Merge commit 'v2.6.32-rc7' into perf/core

Merge reason: pick up perf fixlets

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

16 files changed, 88 insertions, 28 deletions

diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index ac95995b7bad..4b180897e6b5 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -31,6 +31,7 @@ extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_shutdown(void);
+extern void amd_iommu_apply_erratum_63(u16 devid);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index e8de2f6f5ca5..617bd56b3070 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -288,7 +288,7 @@ static inline void load_LDT(mm_context_t *pc)
 
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
-        return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
+        return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
 }
 
 static inline void set_desc_base(struct desc_struct *desc, unsigned long base)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0ee770d23d0e..6a25d5d42836 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -14,6 +14,12 @@
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifdef CONFIG_ISA
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
+#else
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
+#endif
+
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
@@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
                 return memory;
 
-        if (!dev) {
+        if (!dev)
                 dev = &x86_dma_fallback_dev;
-                gfp |= GFP_DMA;
-        }
 
         if (!is_device_dma_capable(dev))
                 return NULL;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c3429e8b2424..c9786480f0fe 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -1000,7 +1000,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define thread_saved_pc(t)      (*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)       ((struct pt_regs *)(tsk)->thread.sp0 - 1)
-#define KSTK_ESP(tsk)           -1 /* sorry. doesn't work for syscall. */
+extern unsigned long KSTK_ESP(struct task_struct *task);
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d823c245f63b..40e37b10c6c0 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,7 +143,7 @@ extern unsigned long node_remap_size[];
                                 | 1*SD_BALANCE_FORK                     \
                                 | 0*SD_BALANCE_WAKE                     \
                                 | 1*SD_WAKE_AFFINE                      \
-                                | 1*SD_PREFER_LOCAL                     \
+                                | 0*SD_PREFER_LOCAL                     \
                                 | 0*SD_SHARE_CPUPOWER                   \
                                 | 0*SD_POWERSAVINGS_BALANCE             \
                                 | 0*SD_SHARE_PKG_RESOURCES              \
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 98f230f6a28d..0285521e0a99 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1220,6 +1220,8 @@ static void __detach_device(struct protection_domain *domain, u16 devid)
         amd_iommu_dev_table[devid].data[1] = 0;
         amd_iommu_dev_table[devid].data[2] = 0;
 
+        amd_iommu_apply_erratum_63(devid);
+
         /* decrease reference counter */
         domain->dev_cnt -= 1;
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index b4b61d462dcc..c20001e4f556 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -240,7 +240,7 @@ static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
         writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
 }
 
-static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 {
         u32 ctrl;
 
@@ -519,6 +519,26 @@ static void set_dev_entry_bit(u16 devid, u8 bit)
         amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
 }
 
+static int get_dev_entry_bit(u16 devid, u8 bit)
+{
+        int i = (bit >> 5) & 0x07;
+        int _bit = bit & 0x1f;
+
+        return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit;
+}
+
+
+void amd_iommu_apply_erratum_63(u16 devid)
+{
+        int sysmgt;
+
+        sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
+                 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);
+
+        if (sysmgt == 0x01)
+                set_dev_entry_bit(devid, DEV_ENTRY_IW);
+}
+
 /* Writes the specific IOMMU for a device into the rlookup table */
 static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
 {
@@ -547,6 +567,8 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
         if (flags & ACPI_DEVFLAG_LINT1)
                 set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
 
+        amd_iommu_apply_erratum_63(devid);
+
         set_iommu_for_device(iommu, devid);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 315738c74aad..73c86db5acbe 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -846,7 +846,7 @@ int __init mtrr_cleanup(unsigned address_bits)
         sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
 
         range_sums = sum_ranges(range, nr_range);
-        printk(KERN_INFO "total RAM coverred: %ldM\n",
+        printk(KERN_INFO "total RAM covered: %ldM\n",
                range_sums >> (20 - PAGE_SHIFT));
 
         if (mtrr_chunk_size && mtrr_gran_size) {
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 366baa179913..f4c538b681ca 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -317,6 +317,12 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
                 return UCODE_NFOUND;
         }
 
+        if (*(u32 *)firmware->data != UCODE_MAGIC) {
+                printk(KERN_ERR "microcode: invalid UCODE_MAGIC (0x%08x)\n",
+                       *(u32 *)firmware->data);
+                return UCODE_ERROR;
+        }
+
         ret = generic_load_microcode(cpu, firmware->data, firmware->size);
 
         release_firmware(firmware);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index b2a71dca5642..a6e804d16c35 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -45,12 +45,10 @@ int iommu_pass_through __read_mostly;
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);
 
-/* Dummy device used for NULL arguments (normally ISA). Better would
-   be probably a smaller DMA mask, but this is bug-to-bug compatible
-   to older i386. */
+/* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
         .init_name = "fallback device",
-        .coherent_dma_mask = DMA_BIT_MASK(32),
+        .coherent_dma_mask = ISA_DMA_BIT_MASK,
         .dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
 EXPORT_SYMBOL(x86_dma_fallback_dev);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ad535b683170..eb62cbcaa490 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -664,3 +664,8 @@ long sys_arch_prctl(int code, unsigned long addr)
         return do_arch_prctl(current, code, addr);
 }
 
+unsigned long KSTK_ESP(struct task_struct *task)
+{
+        return (test_tsk_thread_flag(task, TIF_IA32)) ?
+                        (task_pt_regs(task)->sp) : ((task)->thread.usersp);
+}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index a1a3cdda06e1..f93078746e00 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -436,6 +436,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"),
                 },
         },
+        {       /* Handle problems with rebooting on Apple Macmini3,1 */
+                .callback = set_pci_reboot,
+                .ident = "Apple Macmini3,1",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"),
+                },
+        },
         { }
 };
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e09f0e2c14b5..2a34f9c5be21 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -660,6 +660,13 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
                 },
         },
         {
+                .callback = dmi_low_memory_corruption,
+                .ident = "Phoenix/MSC BIOS",
+                .matches = {
+                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
+                },
+        },
+        {
         /*
          * AMI BIOS with low memory corruption was found on Intel DG45ID board.
          * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b9695322f56..ae07d261527c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1692,7 +1692,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
         unsigned bank_num = mcg_cap & 0xff, bank;
 
         r = -EINVAL;
-        if (!bank_num)
+        if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
                 goto out;
         if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
                 goto out;
@@ -4051,7 +4051,7 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
         return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu);
 }
 
-static u32 get_tss_base_addr(struct kvm_vcpu *vcpu,
+static gpa_t get_tss_base_addr(struct kvm_vcpu *vcpu,
                              struct desc_struct *seg_desc)
 {
         u32 base_addr = get_desc_base(seg_desc);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 334e63ca7b2b..2feb9bdedaaf 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -170,8 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
                                 (unsigned long long)phys_addr,
                                 (unsigned long long)(phys_addr + size),
                                 prot_val, new_prot_val);
-                        free_memtype(phys_addr, phys_addr + size);
-                        return NULL;
+                        goto err_free_memtype;
                 }
                 prot_val = new_prot_val;
         }
@@ -197,26 +196,25 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
          */
         area = get_vm_area_caller(size, VM_IOREMAP, caller);
         if (!area)
-                return NULL;
+                goto err_free_memtype;
         area->phys_addr = phys_addr;
         vaddr = (unsigned long) area->addr;
 
-        if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
-                free_memtype(phys_addr, phys_addr + size);
-                free_vm_area(area);
-                return NULL;
-        }
+        if (kernel_map_sync_memtype(phys_addr, size, prot_val))
+                goto err_free_area;
 
-        if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
-                free_memtype(phys_addr, phys_addr + size);
-                free_vm_area(area);
-                return NULL;
-        }
+        if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
+                goto err_free_area;
 
         ret_addr = (void __iomem *) (vaddr + offset);
         mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
 
         return ret_addr;
+err_free_area:
+        free_vm_area(area);
+err_free_memtype:
+        free_memtype(phys_addr, phys_addr + size);
+        return NULL;
 }
 
 /**
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 23a4d80fb39e..dfbf70e65860 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -178,6 +178,7 @@ static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
                       unsigned int *cx, unsigned int *dx)
 {
+        unsigned maskebx = ~0;
         unsigned maskecx = ~0;
         unsigned maskedx = ~0;
 
@@ -185,9 +186,16 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
          * Mask out inconvenient features, to try and disable as many
          * unsupported kernel subsystems as possible.
          */
-        if (*ax == 1) {
+        switch (*ax) {
+        case 1:
                 maskecx = cpuid_leaf1_ecx_mask;
                 maskedx = cpuid_leaf1_edx_mask;
+                break;
+
+        case 0xb:
+                /* Suppress extended topology stuff */
+                maskebx = 0;
+                break;
         }
 
         asm(XEN_EMULATE_PREFIX "cpuid"
@@ -197,6 +205,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
                   "=d" (*dx)
                 : "0" (*ax), "2" (*cx));
 
+        *bx &= maskebx;
         *cx &= maskecx;
         *dx &= maskedx;
 }