Merge tag 'v3.8-rc5' into next/cleanup

Linux 3.8-rc5

Signed-off-by: Olof Johansson <olof@lixom.net>

8 files changed, 114 insertions, 27 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index b1942e222768..18e329ca108e 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -302,7 +302,7 @@ static efi_status_t setup_efi_pci(struct boot_params *params)
 		if (status != EFI_SUCCESS)
 			continue;
 
-		if (!attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)
+		if (!(attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM))
 			continue;
 
 		if (!pci->romimage || !pci->romsize)
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/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/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();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 76f54461f7cb..c243b81e3c74 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -120,7 +120,7 @@ struct kvm_shared_msrs {
 };
 
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
-static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);
+static struct kvm_shared_msrs __percpu *shared_msrs;
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
@@ -191,10 +191,10 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 
 static void shared_msr_update(unsigned slot, u32 msr)
 {
-	struct kvm_shared_msrs *smsr;
 	u64 value;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
-	smsr = &__get_cpu_var(shared_msrs);
 	/* only read, and nobody should modify it at this time,
 	 * so don't need lock */
 	if (slot >= shared_msrs_global.nr) {
@@ -226,7 +226,8 @@ static void kvm_shared_msr_cpu_online(void)
 
 void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 {
-	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
 	if (((value ^ smsr->values[slot].curr) & mask) == 0)
 		return;
@@ -242,7 +243,8 @@ EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
 static void drop_user_return_notifiers(void *ignore)
 {
-	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
 	if (smsr->registered)
 		kvm_on_user_return(&smsr->urn);
@@ -5233,9 +5235,16 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
+	r = -ENOMEM;
+	shared_msrs = alloc_percpu(struct kvm_shared_msrs);
+	if (!shared_msrs) {
+		printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n");
+		goto out;
+	}
+
 	r = kvm_mmu_module_init();
 	if (r)
-		goto out;
+		goto out_free_percpu;
 
 	kvm_set_mmio_spte_mask();
 	kvm_init_msr_list();
@@ -5258,6 +5267,8 @@ int kvm_arch_init(void *opaque)
 
 	return 0;
 
+out_free_percpu:
+	free_percpu(shared_msrs);
 out:
 	return r;
 }
@@ -5275,6 +5286,7 @@ void kvm_arch_exit(void)
 #endif
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
+	free_percpu(shared_msrs);
 }
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4f7d2599b484..34bc4cee8887 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -432,13 +432,6 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
-	/*
-	 * Balance out the preempt calls - as we are running in cpu_idle
-	 * loop which has been called at bootup from cpu_bringup_and_idle.
-	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
-	 * preempt_disable() So this preempt_enable will balance it out.
-	 */
-	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */