Merge commit 'v3.2.14' into rt-3.2.14-rt23v3.2.14-rt23

9 files changed, 151 insertions, 26 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index a026507893e9..70ea6fd69c1b 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -189,6 +189,9 @@ struct x86_emulate_ops {
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
+
+	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+			 u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -297,6 +300,19 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
 			       X86EMUL_MODE_PROT64)
 
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
 enum x86_intercept_stage {
 	X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
 	X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 91527bc8a621..e568a3c9d810 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3964,18 +3964,36 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 static __init int bad_ioapic(unsigned long address)
 {
 	if (nr_ioapics >= MAX_IO_APICS) {
-		printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded "
-		       "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics);
+		pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
+			MAX_IO_APICS, nr_ioapics);
 		return 1;
 	}
 	if (!address) {
-		printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address"
-		       " found in table, skipping!\n");
+		pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n");
 		return 1;
 	}
 	return 0;
 }
 
+static __init int bad_ioapic_register(int idx)
+{
+	union IO_APIC_reg_00 reg_00;
+	union IO_APIC_reg_01 reg_01;
+	union IO_APIC_reg_02 reg_02;
+
+	reg_00.raw = io_apic_read(idx, 0);
+	reg_01.raw = io_apic_read(idx, 1);
+	reg_02.raw = io_apic_read(idx, 2);
+
+	if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) {
+		pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n",
+			mpc_ioapic_addr(idx));
+		return 1;
+	}
+
+	return 0;
+}
+
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 {
 	int idx = 0;
@@ -3992,6 +4010,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	ioapics[idx].mp_config.apicaddr = address;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+
+	if (bad_ioapic_register(idx)) {
+		clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+		return;
+	}
+
 	ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
 	ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
 
@@ -4012,10 +4036,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	if (gsi_cfg->gsi_end >= gsi_top)
 		gsi_top = gsi_cfg->gsi_end + 1;
 
-	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
-	       "GSI %d-%d\n", idx, mpc_ioapic_id(idx),
-	       mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
-	       gsi_cfg->gsi_base, gsi_cfg->gsi_end);
+	pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n",
+		idx, mpc_ioapic_id(idx),
+		mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
+		gsi_cfg->gsi_base, gsi_cfg->gsi_end);
 
 	nr_ioapics++;
 }
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 3e660d2cebb6..426cf512fdef 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -99,12 +99,6 @@
 #endif
 .endm
 
-#ifdef CONFIG_VM86
-#define resume_userspace_sig	check_userspace
-#else
-#define resume_userspace_sig	resume_userspace
-#endif
-
 /*
  * User gs save/restore
  *
@@ -328,10 +322,19 @@ ret_from_exception:
 	preempt_stop(CLBR_ANY)
 ret_from_intr:
 	GET_THREAD_INFO(%ebp)
-check_userspace:
+resume_userspace_sig:
+#ifdef CONFIG_VM86
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS and CS
 	movb PT_CS(%esp), %al
 	andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+	/*
+	 * We can be coming here from a syscall done in the kernel space,
+	 * e.g. a failed kernel_execve().
+	 */
+	movl PT_CS(%esp), %eax
+	andl $SEGMENT_RPL_MASK, %eax
+#endif
 	cmpl $USER_RPL, %eax
 	jb resume_kernel		# not returning to v8086 or userspace
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6bb7b8579e70..bcfec2d23769 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -163,7 +163,7 @@ int regset_tls_get(struct task_struct *target, const struct user_regset *regset,
 {
 	const struct desc_struct *tls;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
@@ -198,7 +198,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
 
-	if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
 	    (count % sizeof(struct user_desc)) != 0)
 		return -EINVAL;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index db483369f10b..3fe298abc7cf 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -934,6 +934,16 @@ static int __init init_tsc_clocksource(void)
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
+
+	/*
+	 * Trust the results of the earlier calibration on systems
+	 * exporting a reliable TSC.
+	 */
+	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+		return 0;
+	}
+
 	schedule_delayed_work(&tsc_irqwork, 0);
 	return 0;
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 863f8753ab0a..04b87269edfb 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -172,6 +172,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	spinlock_t *ptl;
 	int i;
 
+	down_write(&mm->mmap_sem);
 	pgd = pgd_offset(mm, 0xA0000);
 	if (pgd_none_or_clear_bad(pgd))
 		goto out;
@@ -190,6 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	}
 	pte_unmap_unlock(pte, ptl);
 out:
+	up_write(&mm->mmap_sem);
 	flush_tlb();
 }
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index f1e3be18a08f..f5302da9af21 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1877,6 +1877,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	ss->p = 1;
 }
 
+static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
+{
+	struct x86_emulate_ops *ops = ctxt->ops;
+	u32 eax, ebx, ecx, edx;
+
+	/*
+	 * syscall should always be enabled in longmode - so only become
+	 * vendor specific (cpuid) if other modes are active...
+	 */
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return true;
+
+	eax = 0x00000000;
+	ecx = 0x00000000;
+	if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) {
+		/*
+		 * Intel ("GenuineIntel")
+		 * remark: Intel CPUs only support "syscall" in 64bit
+		 * longmode. Also an 64bit guest with a
+		 * 32bit compat-app running will #UD !! While this
+		 * behaviour can be fixed (by emulating) into AMD
+		 * response - CPUs of AMD can't behave like Intel.
+		 */
+		if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx)
+			return false;
+
+		/* AMD ("AuthenticAMD") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+			return true;
+
+		/* AMD ("AMDisbetter!") */
+		if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx &&
+		    ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx &&
+		    edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
+			return true;
+	}
+
+	/* default: (not Intel, not AMD), apply Intel's stricter rules... */
+	return false;
+}
+
 static int em_syscall(struct x86_emulate_ctxt *ctxt)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -1890,9 +1935,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 	    ctxt->mode == X86EMUL_MODE_VM86)
 		return emulate_ud(ctxt);
 
+	if (!(em_syscall_is_enabled(ctxt)))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_EFER, &efer);
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
+	if (!(efer & EFER_SCE))
+		return emulate_ud(ctxt);
+
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9aac6d69bffa..66d2844fd705 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4655,6 +4655,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 	return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
 }
 
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+			       u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+	struct kvm_cpuid_entry2 *cpuid = NULL;
+
+	if (eax && ecx)
+		cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt),
+					    *eax, *ecx);
+
+	if (cpuid) {
+		*eax = cpuid->eax;
+		*ecx = cpuid->ecx;
+		if (ebx)
+			*ebx = cpuid->ebx;
+		if (edx)
+			*edx = cpuid->edx;
+		return true;
+	}
+
+	return false;
+}
+
 static struct x86_emulate_ops emulate_ops = {
 	.read_std            = kvm_read_guest_virt_system,
 	.write_std           = kvm_write_guest_virt_system,
@@ -4685,6 +4707,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.get_fpu             = emulator_get_fpu,
 	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
+	.get_cpuid           = emulator_get_cpuid,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7c1b765ecc59..5671752f8d9c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -475,8 +475,10 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_LD_W_ABS:
 				func = sk_load_word;
 common_load:			seen |= SEEN_DATAREF;
-				if ((int)K < 0)
+				if ((int)K < 0) {
+					/* Abort the JIT because __load_pointer() is needed. */
 					goto out;
+				}
 				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call */
@@ -489,14 +491,8 @@ common_load:			seen |= SEEN_DATAREF;
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
 				if ((int)K < 0) {
-					if (pc_ret0 > 0) {
-						/* addrs[pc_ret0 - 1] is the start address */
-						EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]);
-						break;
-					}
-					CLEAR_A();
-					EMIT_JMP(cleanup_addr - addrs[i]);
-					break;
+					/* Abort the JIT because __load_pointer() is needed. */
+					goto out;
 				}
 				seen |= SEEN_DATAREF | SEEN_XREG;
 				t_offset = sk_load_byte_msh - (image + addrs[i]);