17 files changed, 97 insertions, 55 deletions

diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 69b4d06..042fdc2 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -101,10 +101,10 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
  */
 static int iommu_completion_wait(struct amd_iommu *iommu)
 {
-	int ret, ready = 0;
+	int ret = 0, ready = 0;
 	unsigned status = 0;
 	struct iommu_cmd cmd;
-	unsigned long i = 0;
+	unsigned long flags, i = 0;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
@@ -112,10 +112,12 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
 	iommu->need_sync = 0;
 
-	ret = iommu_queue_command(iommu, &cmd);
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	ret = __iommu_queue_command(iommu, &cmd);
 
 	if (ret)
-		return ret;
+		goto out;
 
 	while (!ready && (i < EXIT_LOOP_COUNT)) {
 		++i;
@@ -130,6 +132,8 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
 	if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
 		printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
+out:
+	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return 0;
 }
@@ -140,6 +144,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_cmd cmd;
+	int ret;
 
 	BUG_ON(iommu == NULL);
 
@@ -147,9 +152,11 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
 	CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY);
 	cmd.data[0] = devid;
 
+	ret = iommu_queue_command(iommu, &cmd);
+
 	iommu->need_sync = 1;
 
-	return iommu_queue_command(iommu, &cmd);
+	return ret;
 }
 
 /*
@@ -159,6 +166,7 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
 		u64 address, u16 domid, int pde, int s)
 {
 	struct iommu_cmd cmd;
+	int ret;
 
 	memset(&cmd, 0, sizeof(cmd));
 	address &= PAGE_MASK;
@@ -171,9 +179,11 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
 	if (pde) /* PDE bit - we wan't flush everything not only the PTEs */
 		cmd.data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 
+	ret = iommu_queue_command(iommu, &cmd);
+
 	iommu->need_sync = 1;
 
-	return iommu_queue_command(iommu, &cmd);
+	return ret;
 }
 
 /*
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 9ee24e6..732d1f4 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -234,6 +234,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/i8253.h>
+#include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
 
@@ -2217,7 +2218,7 @@ static int __init apm_init(void)
 
 	dmi_check_system(apm_dmi_table);
 
-	if (apm_info.bios.version == 0 || paravirt_enabled()) {
+	if (apm_info.bios.version == 0 || paravirt_enabled() || machine_is_olpc()) {
 		printk(KERN_INFO "apm: BIOS not found.\n");
 		return -ENODEV;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8aab851..4e456bd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -344,31 +344,15 @@ static void __init early_cpu_detect(void)
 
 /*
  * The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6, unfortunately, that's not true in practice because
+ * family >= 6; unfortunately, that's not true in practice because
  * of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect.  Hence, probe for it based on first
- * principles.
+ * are not easy to detect.  In the latter case it doesn't even *fail*
+ * reliably, so probing for it doesn't even work.  Disable it completely
+ * unless we can find a reliable way to detect all the broken cases.
  */
 static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 {
-	const u32 nopl_signature = 0x888c53b1; /* Random number */
-	u32 has_nopl = nopl_signature;
-
 	clear_cpu_cap(c, X86_FEATURE_NOPL);
-	if (c->x86 >= 6) {
-		asm volatile("\n"
-			     "1:      .byte 0x0f,0x1f,0xc0\n" /* nopl %eax */
-			     "2:\n"
-			     "        .section .fixup,\"ax\"\n"
-			     "3:      xor %0,%0\n"
-			     "        jmp 2b\n"
-			     "        .previous\n"
-			     _ASM_EXTABLE(1b,3b)
-			     : "+a" (has_nopl));
-
-		if (has_nopl == nopl_signature)
-			set_cpu_cap(c, X86_FEATURE_NOPL);
-	}
 }
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index f2d43bc..ff7d3b0 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -139,6 +139,7 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 		if (PageHighMem(pg)) {
 			data = ioremap_cache(pa_data, sizeof(*data));
 			if (!data) {
+				kfree(node);
 				error = -ENXIO;
 				goto err_dir;
 			}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index f47f0eb..8282a21 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -69,6 +69,9 @@ static int gdb_x86vector = -1;
  */
 void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	gdb_regs[GDB_AX]	= regs->ax;
 	gdb_regs[GDB_BX]	= regs->bx;
 	gdb_regs[GDB_CX]	= regs->cx;
@@ -76,9 +79,9 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	gdb_regs[GDB_SI]	= regs->si;
 	gdb_regs[GDB_DI]	= regs->di;
 	gdb_regs[GDB_BP]	= regs->bp;
-	gdb_regs[GDB_PS]	= regs->flags;
 	gdb_regs[GDB_PC]	= regs->ip;
 #ifdef CONFIG_X86_32
+	gdb_regs[GDB_PS]	= regs->flags;
 	gdb_regs[GDB_DS]	= regs->ds;
 	gdb_regs[GDB_ES]	= regs->es;
 	gdb_regs[GDB_CS]	= regs->cs;
@@ -94,6 +97,9 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	gdb_regs[GDB_R13]	= regs->r13;
 	gdb_regs[GDB_R14]	= regs->r14;
 	gdb_regs[GDB_R15]	= regs->r15;
+	gdb_regs32[GDB_PS]	= regs->flags;
+	gdb_regs32[GDB_CS]	= regs->cs;
+	gdb_regs32[GDB_SS]	= regs->ss;
 #endif
 	gdb_regs[GDB_SP]	= regs->sp;
 }
@@ -112,6 +118,9 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
  */
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	gdb_regs[GDB_AX]	= 0;
 	gdb_regs[GDB_BX]	= 0;
 	gdb_regs[GDB_CX]	= 0;
@@ -129,8 +138,10 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 	gdb_regs[GDB_FS]	= 0xFFFF;
 	gdb_regs[GDB_GS]	= 0xFFFF;
 #else
-	gdb_regs[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
-	gdb_regs[GDB_PC]	= 0;
+	gdb_regs32[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
+	gdb_regs32[GDB_CS]	= __KERNEL_CS;
+	gdb_regs32[GDB_SS]	= __KERNEL_DS;
+	gdb_regs[GDB_PC]	= p->thread.ip;
 	gdb_regs[GDB_R8]	= 0;
 	gdb_regs[GDB_R9]	= 0;
 	gdb_regs[GDB_R10]	= 0;
@@ -153,6 +164,9 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
  */
 void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
+#ifndef CONFIG_X86_32
+	u32 *gdb_regs32 = (u32 *)gdb_regs;
+#endif
 	regs->ax		= gdb_regs[GDB_AX];
 	regs->bx		= gdb_regs[GDB_BX];
 	regs->cx		= gdb_regs[GDB_CX];
@@ -160,9 +174,9 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	regs->si		= gdb_regs[GDB_SI];
 	regs->di		= gdb_regs[GDB_DI];
 	regs->bp		= gdb_regs[GDB_BP];
-	regs->flags		= gdb_regs[GDB_PS];
 	regs->ip		= gdb_regs[GDB_PC];
 #ifdef CONFIG_X86_32
+	regs->flags		= gdb_regs[GDB_PS];
 	regs->ds		= gdb_regs[GDB_DS];
 	regs->es		= gdb_regs[GDB_ES];
 	regs->cs		= gdb_regs[GDB_CS];
@@ -175,6 +189,9 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	regs->r13		= gdb_regs[GDB_R13];
 	regs->r14		= gdb_regs[GDB_R14];
 	regs->r15		= gdb_regs[GDB_R15];
+	regs->flags		= gdb_regs32[GDB_PS];
+	regs->cs		= gdb_regs32[GDB_CS];
+	regs->ss		= gdb_regs32[GDB_SS];
 #endif
 }
 
@@ -378,10 +395,8 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 		if (remcomInBuffer[0] == 's') {
 			linux_regs->flags |= X86_EFLAGS_TF;
 			kgdb_single_step = 1;
-			if (kgdb_contthread) {
-				atomic_set(&kgdb_cpu_doing_single_step,
-					   raw_smp_processor_id());
-			}
+			atomic_set(&kgdb_cpu_doing_single_step,
+				   raw_smp_processor_id());
 		}
 
 		get_debugreg(dr6, 6);
@@ -466,9 +481,15 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 
 	case DIE_DEBUG:
 		if (atomic_read(&kgdb_cpu_doing_single_step) ==
-			raw_smp_processor_id() &&
-			user_mode(regs))
-			return single_step_cont(regs, args);
+		    raw_smp_processor_id()) {
+			if (user_mode(regs))
+				return single_step_cont(regs, args);
+			break;
+		} else if (test_thread_flag(TIF_SINGLESTEP))
+			/* This means a user thread is single stepping
+			 * a system call which should be ignored
+			 */
+			return NOTIFY_DONE;
 		/* fall through */
 	default:
 		if (user_mode(regs))
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7fc4d5b..876e918 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -246,6 +246,14 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 	return 1;
 }
 
+static cpumask_t c1e_mask = CPU_MASK_NONE;
+static int c1e_detected;
+
+void c1e_remove_cpu(int cpu)
+{
+	cpu_clear(cpu, c1e_mask);
+}
+
 /*
  * C1E aware idle routine. We check for C1E active in the interrupt
  * pending message MSR. If we detect C1E, then we handle it the same
@@ -253,9 +261,6 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
  */
 static void c1e_idle(void)
 {
-	static cpumask_t c1e_mask = CPU_MASK_NONE;
-	static int c1e_detected;
-
 	if (need_resched())
 		return;
 
@@ -265,8 +270,10 @@ static void c1e_idle(void)
 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
 		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
 			c1e_detected = 1;
-			mark_tsc_unstable("TSC halt in C1E");
-			printk(KERN_INFO "System has C1E enabled\n");
+			if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+				mark_tsc_unstable("TSC halt in AMD C1E");
+			printk(KERN_INFO "System has AMD C1E enabled\n");
+			set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E);
 		}
 	}
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 3b7a1dd..31f40b2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,6 +55,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
 #include <asm/kdebug.h>
+#include <asm/idle.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -88,6 +89,7 @@ static void cpu_exit_clear(void)
 	cpu_clear(cpu, cpu_callin_map);
 
 	numa_remove_cpu(cpu);
+	c1e_remove_cpu(cpu);
 }
 
 /* We don't actually take CPU down, just spin without interrupts. */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71553b6..e12e0e4 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -93,6 +93,8 @@ DECLARE_PER_CPU(int, cpu_state);
 static inline void play_dead(void)
 {
 	idle_task_exit();
+	c1e_remove_cpu(raw_smp_processor_id());
+
 	mb();
 	/* Ack it */
 	__get_cpu_var(cpu_state) = CPU_DEAD;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 362d4e7..9838f25 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -670,6 +670,10 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+#ifdef CONFIG_X86_64
+	check_efer();
+#endif
+
 #if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
 	/*
 	 * Must be before kernel pagetables are setup
@@ -738,7 +742,6 @@ void __init setup_arch(char **cmdline_p)
 #else
 	num_physpages = max_pfn;
 
-	check_efer();
 
 	/* How many end-of-memory variables you have, grandma! */
 	/* need this before calling reserve_initrd */
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 0c029e8..7766d36 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -61,7 +61,7 @@ static void vsmp_irq_enable(void)
 	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
 }
 
-static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf,
+static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
 				  unsigned long addr, unsigned len)
 {
 	switch (type) {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 0bfe2bd..3da2508 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -711,6 +711,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
 	u64 *spte;
 	int young = 0;
 
+	/* always return old for EPT */
+	if (!shadow_accessed_mask)
+		return 0;
+
 	spte = rmap_next(kvm, rmapp, NULL);
 	while (spte) {
 		int _young;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e2ee264..8233b86 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -62,6 +62,7 @@ static int npt = 1;
 module_param(npt, int, S_IRUGO);
 
 static void kvm_reput_irq(struct vcpu_svm *svm);
+static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {
@@ -878,6 +879,10 @@ set:
 static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+	unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
+
+	if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
+		force_new_asid(vcpu);
 
 	vcpu->arch.cr4 = cr4;
 	if (!npt_enabled)
@@ -1027,6 +1032,13 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 		KVMTRACE_3D(TDP_FAULT, &svm->vcpu, error_code,
 			    (u32)fault_address, (u32)(fault_address >> 32),
 			    handler);
+	/*
+	 * FIXME: Tis shouldn't be necessary here, but there is a flush
+	 * missing in the MMU code. Until we find this bug, flush the
+	 * complete TLB here on an NPF
+	 */
+	if (npt_enabled)
+		svm_flush_tlb(&svm->vcpu);
 
 	if (event_injection)
 		kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2a69773..7041cc5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3301,8 +3301,7 @@ static int __init vmx_init(void)
 		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
 			VMX_EPT_WRITABLE_MASK |
 			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
-		kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK,
-				VMX_EPT_FAKE_DIRTY_MASK, 0ull,
+		kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
 				VMX_EPT_EXECUTABLE_MASK);
 		kvm_enable_tdp();
 	} else
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 425a134..23e8373 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -370,8 +370,6 @@ enum vmcs_field {
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
-#define VMX_EPT_FAKE_ACCESSED_MASK		(1ull << 62)
-#define VMX_EPT_FAKE_DIRTY_MASK			(1ull << 63)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index d37f293..60ec1d0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -458,11 +458,7 @@ static void __init pagetable_init(void)
 {
 	pgd_t *pgd_base = swapper_pg_dir;
 
-	paravirt_pagetable_setup_start(pgd_base);
-
 	permanent_kmaps_init(pgd_base);
-
-	paravirt_pagetable_setup_done(pgd_base);
 }
 
 #ifdef CONFIG_ACPI_SLEEP
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 0227694..8a5f161 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -295,10 +295,12 @@ static void nmi_cpu_shutdown(void *dummy)
 
 static void nmi_shutdown(void)
 {
-	struct op_msrs *msrs = &get_cpu_var(cpu_msrs);
+	struct op_msrs *msrs;
+
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 1);
 	unregister_die_notifier(&profile_exceptions_nb);
+	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);
 	free_msrs();
 	put_cpu_var(cpu_msrs);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b6acc3a..d679010 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -42,7 +42,7 @@ char * __init xen_memory_setup(void)
 
 	e820.nr_map = 0;
 
-	e820_add_region(0, PFN_PHYS(max_pfn), E820_RAM);
+	e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
 
 	/*
 	 * Even though this is normal, usable memory under Xen, reserve