8 files changed, 101 insertions, 19 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4428fd178bce..6774c17a5576 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -340,9 +340,6 @@ int x86_setup_perfctr(struct perf_event *event)
                 /* BTS is currently only allowed for user-mode. */
                 if (!attr->exclude_kernel)
                         return -EOPNOTSUPP;
-
-                if (!attr->exclude_guest)
-                        return -EOPNOTSUPP;
         }
 
         hwc->config |= config;
@@ -385,9 +382,6 @@ int x86_pmu_hw_config(struct perf_event *event)
         if (event->attr.precise_ip) {
                 int precise = 0;
 
-                if (!event->attr.exclude_guest)
-                        return -EOPNOTSUPP;
-
                 /* Support for constant skid */
                 if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
                         precise++;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 3cf3d97cce3a..b43200dbfe7e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2500,7 +2500,7 @@ static bool pcidrv_registered;
 /*
  * add a pci uncore device
  */
-static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 {
         struct intel_uncore_pmu *pmu;
         struct intel_uncore_box *box;
@@ -2571,8 +2571,8 @@ static void uncore_pci_remove(struct pci_dev *pdev)
         kfree(box);
 }
 
-static int __devinit uncore_pci_probe(struct pci_dev *pdev,
-                                const struct pci_device_id *id)
+static int uncore_pci_probe(struct pci_dev *pdev,
+                            const struct pci_device_id *id)
 {
         struct intel_uncore_type *type;
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index ff84d5469d77..6ed91d9980e2 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1065,7 +1065,6 @@ ENTRY(xen_failsafe_callback)
         lea 16(%esp),%esp
         CFI_ADJUST_CFA_OFFSET -16
         jz 5f
-        addl $16,%esp
         jmp iret_exc
 5:      pushl_cfi $-1 /* orig_ax = -1 => not a system call */
         SAVE_ALL
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 08b973f64032..9c2bd8bd4b4c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -43,6 +43,7 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/kvm_guest.h>
+#include <asm/context_tracking.h>
 
 static int kvmapf = 1;
 
@@ -121,6 +122,8 @@ void kvm_async_pf_task_wait(u32 token)
         struct kvm_task_sleep_node n, *e;
         DEFINE_WAIT(wait);
 
+        rcu_irq_enter();
+
         spin_lock(&b->lock);
         e = _find_apf_task(b, token);
         if (e) {
@@ -128,6 +131,8 @@ void kvm_async_pf_task_wait(u32 token)
                 hlist_del(&e->link);
                 kfree(e);
                 spin_unlock(&b->lock);
+
+                rcu_irq_exit();
                 return;
         }
 
@@ -152,13 +157,16 @@ void kvm_async_pf_task_wait(u32 token)
                         /*
                          * We cannot reschedule. So halt.
                          */
+                        rcu_irq_exit();
                         native_safe_halt();
+                        rcu_irq_enter();
                         local_irq_disable();
                 }
         }
         if (!n.halted)
                 finish_wait(&n.wq, &wait);
 
+        rcu_irq_exit();
         return;
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
@@ -252,10 +260,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
                 break;
         case KVM_PV_REASON_PAGE_NOT_PRESENT:
                 /* page is swapped out by the host. */
-                rcu_irq_enter();
+                exception_enter(regs);
                 exit_idle();
                 kvm_async_pf_task_wait((u32)read_cr2());
-                rcu_irq_exit();
+                exception_exit(regs);
                 break;
         case KVM_PV_REASON_PAGE_READY:
                 rcu_irq_enter();
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index de2b7ad70273..0f5dec5c80e0 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -265,7 +265,7 @@ rootfs_initcall(pci_iommu_init);
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
 
-static __devinit void via_no_dac(struct pci_dev *dev)
+static void via_no_dac(struct pci_dev *dev)
 {
         if (forbid_dac == 0) {
                 dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 1b27de563561..26ee48a33dc4 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -8,7 +8,7 @@
 
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
-static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
+static void quirk_intel_irqbalance(struct pci_dev *dev)
 {
         u8 config;
         u16 word;
@@ -512,7 +512,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 
 #if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
 /* Set correct numa_node information for AMD NB functions */
-static void __devinit quirk_amd_nb_node(struct pci_dev *dev)
+static void quirk_amd_nb_node(struct pci_dev *dev)
 {
         struct pci_dev *nb_ht;
         unsigned int devfn;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 23ddd558fbd5..00f6c1472b85 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -610,6 +610,83 @@ static __init void reserve_ibft_region(void)
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
+static bool __init snb_gfx_workaround_needed(void)
+{
+#ifdef CONFIG_PCI
+        int i;
+        u16 vendor, devid;
+        static const __initconst u16 snb_ids[] = {
+                0x0102,
+                0x0112,
+                0x0122,
+                0x0106,
+                0x0116,
+                0x0126,
+                0x010a,
+        };
+
+        /* Assume no if something weird is going on with PCI */
+        if (!early_pci_allowed())
+                return false;
+
+        vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+        if (vendor != 0x8086)
+                return false;
+
+        devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+        for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+                if (devid == snb_ids[i])
+                        return true;
+#endif
+
+        return false;
+}
+
+/*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+static void __init trim_snb_memory(void)
+{
+        static const __initconst unsigned long bad_pages[] = {
+                0x20050000,
+                0x20110000,
+                0x20130000,
+                0x20138000,
+                0x40004000,
+        };
+        int i;
+
+        if (!snb_gfx_workaround_needed())
+                return;
+
+        printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+        /*
+         * Reserve all memory below the 1 MB mark that has not
+         * already been reserved.
+         */
+        memblock_reserve(0, 1<<20);
+        
+        for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+                if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+                        printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+                               bad_pages[i]);
+        }
+}
+
+/*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+static void __init trim_platform_memory_ranges(void)
+{
+        trim_snb_memory();
+}
+
 static void __init trim_bios_range(void)
 {
         /*
@@ -630,6 +707,7 @@ static void __init trim_bios_range(void)
          * take them out.
          */
         e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
@@ -908,6 +986,8 @@ void __init setup_arch(char **cmdline_p)
 
         setup_real_mode();
 
+        trim_platform_memory_ranges();
+
         init_gbpages();
 
         /* max_pfn_mapped is updated here */
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index cd3b2438a980..9b4d51d0c0d0 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -165,10 +165,11 @@ void set_task_blockstep(struct task_struct *task, bool on)
          * Ensure irq/preemption can't change debugctl in between.
          * Note also that both TIF_BLOCKSTEP and debugctl should
          * be changed atomically wrt preemption.
-         * FIXME: this means that set/clear TIF_BLOCKSTEP is simply
-         * wrong if task != current, SIGKILL can wakeup the stopped
-         * tracee and set/clear can play with the running task, this
-         * can confuse the next __switch_to_xtra().
+         *
+         * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if
+         * task is current or it can't be running, otherwise we can race
+         * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but
+         * PTRACE_KILL is not safe.
          */
         local_irq_disable();
         debugctl = get_debugctlmsr();