Merge branch 'perf/core' into perf/probes

Resolved merge conflict in tools/perf/Makefile

Merge reason: we want to queue up a dependent patch.

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

16 files changed, 100 insertions, 27 deletions

diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 7da00b799cda..060fff8f5c5b 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -57,5 +57,8 @@ SECTIONS
                 *(.note*)
         }
 
+        /*
+         * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+         */
         . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!");
 }
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/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f5f5886a6b53..326c25477d3d 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -352,14 +352,14 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 
         for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
                 alias.v = uv_read_local_mmr(redir_addrs[i].alias);
-                if (alias.s.base == 0) {
+                if (alias.s.enable && alias.s.base == 0) {
                         *size = (1UL << alias.s.m_alias);
                         redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
                         *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
                         return;
                 }
         }
-        BUG();
+        *base = *size = 0;
 }
 
 enum map_type {map_wb, map_uc};
@@ -619,12 +619,12 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
                 uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
                 uv_cpu_hub_info(cpu)->m_val = m_val;
-                uv_cpu_hub_info(cpu)->n_val = m_val;
+                uv_cpu_hub_info(cpu)->n_val = n_val;
                 uv_cpu_hub_info(cpu)->numa_blade_id = blade;
                 uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
                 uv_cpu_hub_info(cpu)->pnode = pnode;
                 uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
-                uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+                uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
                 uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
                 uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
                 uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b1598a9436d0..721a77ca8115 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1214,7 +1214,8 @@ static int __cpuinit mce_cap_init(void)
         rdmsrl(MSR_IA32_MCG_CAP, cap);
 
         b = cap & MCG_BANKCNT_MASK;
-        printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
+        if (!banks)
+                printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
 
         if (b > MAX_NR_BANKS) {
                 printk(KERN_WARNING
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/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2e20bca3cca1..bd8743024204 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -245,7 +245,7 @@ static u64 __read_mostly hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX];
 
-static const u64 nehalem_hw_cache_event_ids
+static __initconst u64 nehalem_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -336,7 +336,7 @@ static const u64 nehalem_hw_cache_event_ids
  },
 };
 
-static const u64 core2_hw_cache_event_ids
+static __initconst u64 core2_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -427,7 +427,7 @@ static const u64 core2_hw_cache_event_ids
  },
 };
 
-static const u64 atom_hw_cache_event_ids
+static __initconst u64 atom_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -536,7 +536,7 @@ static u64 intel_pmu_raw_event(u64 hw_event)
         return hw_event & CORE_EVNTSEL_MASK;
 }
 
-static const u64 amd_hw_cache_event_ids
+static __initconst u64 amd_hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -1964,7 +1964,7 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = {
         .priority               = 1
 };
 
-static struct x86_pmu p6_pmu = {
+static __initconst struct x86_pmu p6_pmu = {
         .name                   = "p6",
         .handle_irq             = p6_pmu_handle_irq,
         .disable_all            = p6_pmu_disable_all,
@@ -1992,7 +1992,7 @@ static struct x86_pmu p6_pmu = {
         .get_event_idx          = intel_get_event_idx,
 };
 
-static struct x86_pmu intel_pmu = {
+static __initconst struct x86_pmu intel_pmu = {
         .name                   = "Intel",
         .handle_irq             = intel_pmu_handle_irq,
         .disable_all            = intel_pmu_disable_all,
@@ -2016,7 +2016,7 @@ static struct x86_pmu intel_pmu = {
         .get_event_idx          = intel_get_event_idx,
 };
 
-static struct x86_pmu amd_pmu = {
+static __initconst struct x86_pmu amd_pmu = {
         .name                   = "AMD",
         .handle_irq             = amd_pmu_handle_irq,
         .disable_all            = amd_pmu_disable_all,
@@ -2037,7 +2037,7 @@ static struct x86_pmu amd_pmu = {
         .get_event_idx          = gen_get_event_idx,
 };
 
-static int p6_pmu_init(void)
+static __init int p6_pmu_init(void)
 {
         switch (boot_cpu_data.x86_model) {
         case 1:
@@ -2071,7 +2071,7 @@ static int p6_pmu_init(void)
         return 0;
 }
 
-static int intel_pmu_init(void)
+static __init int intel_pmu_init(void)
 {
         union cpuid10_edx edx;
         union cpuid10_eax eax;
@@ -2144,7 +2144,7 @@ static int intel_pmu_init(void)
         return 0;
 }
 
-static int amd_pmu_init(void)
+static __init int amd_pmu_init(void)
 {
         /* Performance-monitoring supported from K7 and later: */
         if (boot_cpu_data.x86 < 6)
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index f7cdb3b457aa..cd97ce18c29d 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -16,6 +16,22 @@ static void *kdump_buf_page;
 /* Stores the physical address of elf header of crash image. */
 unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
 
+static inline bool is_crashed_pfn_valid(unsigned long pfn)
+{
+#ifndef CONFIG_X86_PAE
+        /*
+         * non-PAE kdump kernel executed from a PAE one will crop high pte
+         * bits and poke unwanted space counting again from address 0, we
+         * don't want that. pte must fit into unsigned long. In fact the
+         * test checks high 12 bits for being zero (pfn will be shifted left
+         * by PAGE_SHIFT).
+         */
+        return pte_pfn(pfn_pte(pfn, __pgprot(0))) == pfn;
+#else
+        return true;
+#endif
+}
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
@@ -41,6 +57,9 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
         if (!csize)
                 return 0;
 
+        if (!is_crashed_pfn_valid(pfn))
+                return -EFAULT;
+
         vaddr = kmap_atomic_pfn(pfn, KM_PTE0);
 
         if (!userbuf) {
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index ad5bd988fb79..cdcfb122f256 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -454,8 +454,10 @@ void __init efi_init(void)
         if (add_efi_memmap)
                 do_add_efi_memmap();
 
+#ifdef CONFIG_X86_32
         x86_platform.get_wallclock = efi_get_time;
         x86_platform.set_wallclock = efi_set_rtc_mmss;
+#endif
 
         /* Setup for EFI runtime service */
         reboot_type = BOOT_EFI;
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/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 503c1f2e8835..1740c85e24bb 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -23,8 +23,6 @@
 static struct bau_control       **uv_bau_table_bases __read_mostly;
 static int                      uv_bau_retry_limit __read_mostly;
 
-/* position of pnode (which is nasid>>1): */
-static int                      uv_nshift __read_mostly;
 /* base pnode in this partition */
 static int                      uv_partition_base_pnode __read_mostly;
 
@@ -723,7 +721,7 @@ uv_activation_descriptor_init(int node, int pnode)
         BUG_ON(!adp);
 
         pa = uv_gpa(adp); /* need the real nasid*/
-        n = pa >> uv_nshift;
+        n = uv_gpa_to_pnode(pa);
         m = pa & uv_mmask;
 
         uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
@@ -778,7 +776,7 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
          * need the pnode of where the memory was really allocated
          */
         pa = uv_gpa(pqp);
-        pn = pa >> uv_nshift;
+        pn = uv_gpa_to_pnode(pa);
         uv_write_global_mmr64(pnode,
                               UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
                               ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
@@ -843,8 +841,7 @@ static int __init uv_bau_init(void)
                                        GFP_KERNEL, cpu_to_node(cur_cpu));
 
         uv_bau_retry_limit = 1;
-        uv_nshift = uv_hub_info->n_val;
-        uv_mmask = (1UL << uv_hub_info->n_val) - 1;
+        uv_mmask = (1UL << uv_hub_info->m_val) - 1;
         nblades = uv_num_possible_blades();
 
         uv_bau_table_bases = (struct bau_control **)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 92929fb3f9fa..3c68fe2d46cf 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -305,6 +305,9 @@ SECTIONS
 
 
 #ifdef CONFIG_X86_32
+/*
+ * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
            "kernel image bigger than KERNEL_IMAGE_SIZE");
 #else