9 files changed, 45 insertions, 28 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1430ef6b4f9..738bdc6b0f8b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1913,25 +1913,26 @@ config DMAR_DEFAULT_ON
           recommended you say N here while the DMAR code remains
           experimental.
 
-config DMAR_GFX_WA
-        def_bool y
-        prompt "Support for Graphics workaround"
+config DMAR_BROKEN_GFX_WA
+        def_bool n
+        prompt "Workaround broken graphics drivers (going away soon)"
         depends on DMAR
         ---help---
           Current Graphics drivers tend to use physical address
           for DMA and avoid using DMA APIs. Setting this config
           option permits the IOMMU driver to set a unity map for
           all the OS-visible memory. Hence the driver can continue
-          to use physical addresses for DMA.
+          to use physical addresses for DMA, at least until this
+          option is removed in the 2.6.32 kernel.
 
 config DMAR_FLOPPY_WA
         def_bool y
         depends on DMAR
         ---help---
-          Floppy disk drivers are know to bypass DMA API calls
+          Floppy disk drivers are known to bypass DMA API calls
           thereby failing to work when IOMMU is enabled. This
           workaround will setup a 1:1 mapping for the first
-          16M to make floppy (an ISA device) work.
+          16MiB to make floppy (an ISA device) work.
 
 config INTR_REMAP
         bool "Support for Interrupt Remapping (EXPERIMENTAL)"
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 927958d13c19..1ff685ca221c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void);
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG)
 
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
                 dma_addr_t ADDR_NAME;
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 5fb33e160ea0..fa64e401589d 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -87,6 +87,9 @@ union cpuid10_edx {
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
+
+#define PERF_COUNTER_INDEX_OFFSET                       0
+
 #else
 static inline void init_hw_perf_counters(void)          { }
 static inline void perf_counters_lapic_init(void)       { }
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 49fb3ecf3bb3..621f56d73121 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -22,7 +22,14 @@ extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
-#define round_down(x, y) ((x) & ~((y) - 1))
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6c327b852e23..430d5b24af7b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,6 +26,8 @@ CFLAGS_tsc.o		:= $(nostackp)
 CFLAGS_paravirt.o       := $(nostackp)
 GCOV_PROFILE_vsyscall_64.o      := n
 GCOV_PROFILE_hpet.o             := n
+GCOV_PROFILE_tsc.o              := n
+GCOV_PROFILE_paravirt.o         := n
 
 obj-y                   := process_$(BITS).o signal.o entry_$(BITS).o
 obj-y                   += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 76dfef23f789..d4cf4ce19aac 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids
                 [ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
         },
         [ C(OP_WRITE) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
+                [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
                 [ C(RESULT_MISS)   ] = 0,
         },
         [ C(OP_PREFETCH) ] = {
@@ -912,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter,
         err = checking_wrmsrl(hwc->counter_base + idx,
                              (u64)(-left) & x86_pmu.counter_mask);
 
+        perf_counter_update_userpage(counter);
+
         return ret;
 }
 
@@ -969,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
         if (!x86_pmu.num_counters_fixed)
                 return -1;
 
-        /*
-         * Quirk, IA32_FIXED_CTRs do not work on current Atom processors:
-         */
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-                                        boot_cpu_data.x86_model == 28)
-                return -1;
-
         event = hwc->config & ARCH_PERFMON_EVENT_MASK;
 
         if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
@@ -1041,6 +1036,8 @@ try_generic:
         x86_perf_counter_set_period(counter, hwc, idx);
         x86_pmu.enable(hwc, idx);
 
+        perf_counter_update_userpage(counter);
+
         return 0;
 }
 
@@ -1133,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter)
         x86_perf_counter_update(counter, hwc, idx);
         cpuc->counters[idx] = NULL;
         clear_bit(idx, cpuc->used_mask);
+
+        perf_counter_update_userpage(counter);
 }
 
 /*
@@ -1428,8 +1427,6 @@ static int intel_pmu_init(void)
          */
         x86_pmu.num_counters_fixed      = max((int)edx.split.num_counters_fixed, 3);
 
-        rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
-
         /*
          * Install the hw-cache-events table:
          */
@@ -1499,21 +1496,22 @@ void __init init_hw_perf_counters(void)
         pr_cont("%s PMU driver.\n", x86_pmu.name);
 
         if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
-                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
                 WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
                      x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
         }
         perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
         perf_max_counters = x86_pmu.num_counters;
 
         if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
-                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
                 WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
                      x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
         }
 
         perf_counter_mask |=
                 ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+        x86_pmu.intel_ctrl = perf_counter_mask;
 
         perf_counters_lapic_init();
         register_die_notifier(&perf_counter_nmi_notifier);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7271fa33d791..c4ca89d9aaf4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1383,6 +1383,8 @@ static unsigned long ram_alignment(resource_size_t pos)
         return 32*1024*1024;
 }
 
+#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
+
 void __init e820_reserve_resources_late(void)
 {
         int i;
@@ -1400,17 +1402,19 @@ void __init e820_reserve_resources_late(void)
          * avoid stolen RAM:
          */
         for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *entry = &e820_saved.map[i];
-                resource_size_t start, end;
+                struct e820entry *entry = &e820.map[i];
+                u64 start, end;
 
                 if (entry->type != E820_RAM)
                         continue;
                 start = entry->addr + entry->size;
-                end = round_up(start, ram_alignment(start));
-                if (start == end)
+                end = round_up(start, ram_alignment(start)) - 1;
+                if (end > MAX_RESOURCE_SIZE)
+                        end = MAX_RESOURCE_SIZE;
+                if (start >= end)
                         continue;
-                reserve_region_with_split(&iomem_resource, start,
-                                                  end - 1, "RAM buffer");
+                reserve_region_with_split(&iomem_resource, start, end,
+                                          "RAM buffer");
         }
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 47630479b067..1a041bcf506b 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -211,11 +211,11 @@ static __init int iommu_setup(char *p)
 #ifdef CONFIG_SWIOTLB
                 if (!strncmp(p, "soft", 4))
                         swiotlb = 1;
+#endif
                 if (!strncmp(p, "pt", 2)) {
                         iommu_pass_through = 1;
                         return 1;
                 }
-#endif
 
                 gart_parse_options(p);
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c4378f4fd4a5..b177652251a4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -598,6 +598,8 @@ void __init paging_init(void)
 
         sparse_memory_present_with_active_regions(MAX_NUMNODES);
         sparse_init();
+        /* clear the default setting with node 0 */
+        nodes_clear(node_states[N_NORMAL_MEMORY]);
         free_area_init_nodes(max_zone_pfns);
 }