12 files changed, 106 insertions, 30 deletions

diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 94c27df8a549..f247304299a2 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -240,7 +240,7 @@ fold_64:
         pand    %xmm3, %xmm1
         PCLMULQDQ 0x00, CONSTANT, %xmm1
         pxor    %xmm2, %xmm1
-        pextrd  $0x01, %xmm1, %eax
+        PEXTRD  0x01, %xmm1, %eax
 
         ret
 ENDPROC(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 56610c4bf31b..642f15687a0a 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -118,7 +118,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 98d3c391da81..f833b74d902b 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -111,7 +111,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 280bf7fb6aba..3e115273ed88 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -9,12 +9,68 @@
 
 #define REG_NUM_INVALID         100
 
-#define REG_TYPE_R64            0
-#define REG_TYPE_XMM            1
+#define REG_TYPE_R32            0
+#define REG_TYPE_R64            1
+#define REG_TYPE_XMM            2
 #define REG_TYPE_INVALID        100
 
+        .macro R32_NUM opd r32
+        \opd = REG_NUM_INVALID
+        .ifc \r32,%eax
+        \opd = 0
+        .endif
+        .ifc \r32,%ecx
+        \opd = 1
+        .endif
+        .ifc \r32,%edx
+        \opd = 2
+        .endif
+        .ifc \r32,%ebx
+        \opd = 3
+        .endif
+        .ifc \r32,%esp
+        \opd = 4
+        .endif
+        .ifc \r32,%ebp
+        \opd = 5
+        .endif
+        .ifc \r32,%esi
+        \opd = 6
+        .endif
+        .ifc \r32,%edi
+        \opd = 7
+        .endif
+#ifdef CONFIG_X86_64
+        .ifc \r32,%r8d
+        \opd = 8
+        .endif
+        .ifc \r32,%r9d
+        \opd = 9
+        .endif
+        .ifc \r32,%r10d
+        \opd = 10
+        .endif
+        .ifc \r32,%r11d
+        \opd = 11
+        .endif
+        .ifc \r32,%r12d
+        \opd = 12
+        .endif
+        .ifc \r32,%r13d
+        \opd = 13
+        .endif
+        .ifc \r32,%r14d
+        \opd = 14
+        .endif
+        .ifc \r32,%r15d
+        \opd = 15
+        .endif
+#endif
+        .endm
+
         .macro R64_NUM opd r64
         \opd = REG_NUM_INVALID
+#ifdef CONFIG_X86_64
         .ifc \r64,%rax
         \opd = 0
         .endif
@@ -63,6 +119,7 @@
         .ifc \r64,%r15
         \opd = 15
         .endif
+#endif
         .endm
 
         .macro XMM_NUM opd xmm
@@ -118,10 +175,13 @@
         .endm
 
         .macro REG_TYPE type reg
+        R32_NUM reg_type_r32 \reg
         R64_NUM reg_type_r64 \reg
         XMM_NUM reg_type_xmm \reg
         .if reg_type_r64 <> REG_NUM_INVALID
         \type = REG_TYPE_R64
+        .elseif reg_type_r32 <> REG_NUM_INVALID
+        \type = REG_TYPE_R32
         .elseif reg_type_xmm <> REG_NUM_INVALID
         \type = REG_TYPE_XMM
         .else
@@ -162,6 +222,16 @@
         .byte \imm8
         .endm
 
+        .macro PEXTRD imm8 xmm gpr
+        R32_NUM extrd_opd1 \gpr
+        XMM_NUM extrd_opd2 \xmm
+        PFX_OPD_SIZE
+        PFX_REX extrd_opd1 extrd_opd2
+        .byte 0x0f, 0x3a, 0x16
+        MODRM 0xc0 extrd_opd1 extrd_opd2
+        .byte \imm8
+        .endm
+
         .macro AESKEYGENASSIST rcon xmm1 xmm2
         XMM_NUM aeskeygen_opd1 \xmm1
         XMM_NUM aeskeygen_opd2 \xmm2
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 08f7e8039099..321d65ebaffe 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -115,8 +115,10 @@ startup_64:
         movq    %rdi, %rax
         shrq    $PUD_SHIFT, %rax
         andl    $(PTRS_PER_PUD-1), %eax
-        movq    %rdx, (4096+0)(%rbx,%rax,8)
-        movq    %rdx, (4096+8)(%rbx,%rax,8)
+        movq    %rdx, 4096(%rbx,%rax,8)
+        incl    %eax
+        andl    $(PTRS_PER_PUD-1), %eax
+        movq    %rdx, 4096(%rbx,%rax,8)
 
         addq    $8192, %rbx
         movq    %rdi, %rax
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 245a71db401a..cb339097b9ea 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -22,23 +22,19 @@
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * For now, with eagerfpu we will return interrupted kernel FPU
- * state as not-idle. TBD: Ideally we can change the return value
- * to something like __thread_has_fpu(current). But we need to
- * be careful of doing __thread_clear_has_fpu() before saving
- * the FPU etc for supporting nested uses etc. For now, take
- * the simple route!
- *
  * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return 1 unless we've already
+ * been eager and saved the state in kernel_fpu_begin().
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
         if (use_eager_fpu())
-                return 0;
+                return __thread_has_fpu(current);
 
         return !__thread_has_fpu(current) &&
                 (read_cr0() & X86_CR0_TS);
@@ -78,8 +74,8 @@ void __kernel_fpu_begin(void)
         struct task_struct *me = current;
 
         if (__thread_has_fpu(me)) {
-                __save_init_fpu(me);
                 __thread_clear_has_fpu(me);
+                __save_init_fpu(me);
                 /* We do 'stts()' in __kernel_fpu_end() */
         } else if (!use_eager_fpu()) {
                 this_cpu_write(fpu_owner_task, NULL);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8db0010ed150..5953dcea752d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
         ctxt->modrm_seg = VCPU_SREG_DS;
 
         if (ctxt->modrm_mod == 3) {
+                int highbyte_regs = ctxt->rex_prefix == 0;
+
                 op->type = OP_REG;
                 op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
-                op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp);
+                op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+                                               highbyte_regs && (ctxt->d & ByteOp));
                 if (ctxt->d & Sse) {
                         op->type = OP_XMM;
                         op->bytes = 16;
@@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = {
         DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
         N, D(ImplicitOps | ModRM), N, N,
         /* 0x10 - 0x1F */
-        N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N,
+        N, N, N, N, N, N, N, N,
+        D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
         /* 0x20 - 0x2F */
         DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
         DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
@@ -4836,6 +4840,7 @@ twobyte_insn:
         case 0x08:              /* invd */
         case 0x0d:              /* GrpP (prefetch) */
         case 0x18:              /* Grp16 (prefetch/nop) */
+        case 0x1f:              /* nop */
                 break;
         case 0x20: /* mov cr, reg */
                 ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e1adbb4aca75..0eee2c8b64d1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
         struct kvm_lapic *apic = vcpu->arch.apic;
         unsigned int sipi_vector;
+        unsigned long pe;
 
-        if (!kvm_vcpu_has_lapic(vcpu))
+        if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
                 return;
 
-        if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
+        pe = xchg(&apic->pending_events, 0);
+
+        if (test_bit(KVM_APIC_INIT, &pe)) {
                 kvm_lapic_reset(vcpu);
                 kvm_vcpu_reset(vcpu);
                 if (kvm_vcpu_is_bsp(apic->vcpu))
@@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
                 else
                         vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
         }
-        if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) &&
+        if (test_bit(KVM_APIC_SIPI, &pe) &&
             vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
                 /* evaluate pending_events before reading the vector */
                 smp_rmb();
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 305c68b8d538..981c2dbd72cc 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -628,7 +628,9 @@ int pcibios_add_device(struct pci_dev *dev)
 
         pa_data = boot_params.hdr.setup_data;
         while (pa_data) {
-                data = phys_to_virt(pa_data);
+                data = ioremap(pa_data, sizeof(*rom));
+                if (!data)
+                        return -ENOMEM;
 
                 if (data->type == SETUP_PCI) {
                         rom = (struct pci_setup_rom *)data;
@@ -645,6 +647,7 @@ int pcibios_add_device(struct pci_dev *dev)
                         }
                 }
                 pa_data = data->next;
+                iounmap(data);
         }
         return 0;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 55856b2310d3..82089d8b1954 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -206,7 +206,7 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
         }
 
         if (boot_used_size && !finished) {
-                unsigned long size;
+                unsigned long size = 0;
                 u32 attr;
                 efi_status_t s;
                 void *tmp;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8ff37995d54e..fb44426fe931 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -576,24 +576,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 {
         unsigned cpu;
         unsigned int this_cpu = smp_processor_id();
+        int xen_vector = xen_map_vector(vector);
 
-        if (!(num_online_cpus() > 1))
+        if (!(num_online_cpus() > 1) || (xen_vector < 0))
                 return;
 
         for_each_cpu_and(cpu, mask, cpu_online_mask) {
                 if (this_cpu == cpu)
                         continue;
 
-                xen_smp_send_call_function_single_ipi(cpu);
+                xen_send_IPI_one(cpu, xen_vector);
         }
 }
 
 void xen_send_IPI_allbutself(int vector)
 {
-        int xen_vector = xen_map_vector(vector);
-
-        if (xen_vector >= 0)
-                xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+        xen_send_IPI_mask_allbutself(cpu_online_mask, vector);
 }
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index 8981a76d081a..c7c2d89efd76 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask,
 extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
                                 int vector);
 extern void xen_send_IPI_allbutself(int vector);
-extern void physflat_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);