Merge 4.0-rc3 into char-misc-next

We want the mei fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

16 files changed, 124 insertions, 63 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c2fb8a87dccb..b7d31ca55187 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -499,6 +499,7 @@ config X86_INTEL_QUARK
         depends on X86_IO_APIC
         select IOSF_MBI
         select INTEL_IMR
+        select COMMON_CLK
         ---help---
           Select to include support for Quark X1000 SoC.
           Say Y here if you have a Quark based system such as the Arduino
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 5fa9770035dc..c9a6d68b8d62 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -82,18 +82,15 @@ static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
         if (boot_cpu_has(X86_FEATURE_XSAVES))
                 asm volatile("1:"XSAVES"\n\t"
                         "2:\n\t"
-                        : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+                             xstate_fault
+                        : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
                         :   "memory");
         else
                 asm volatile("1:"XSAVE"\n\t"
                         "2:\n\t"
-                        : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+                             xstate_fault
+                        : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
                         :   "memory");
-
-        asm volatile(xstate_fault
-                     : "0" (0)
-                     : "memory");
-
         return err;
 }
 
@@ -112,18 +109,15 @@ static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
         if (boot_cpu_has(X86_FEATURE_XSAVES))
                 asm volatile("1:"XRSTORS"\n\t"
                         "2:\n\t"
-                        : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+                             xstate_fault
+                        : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
                         :   "memory");
         else
                 asm volatile("1:"XRSTOR"\n\t"
                         "2:\n\t"
-                        : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+                             xstate_fault
+                        : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
                         :   "memory");
-
-        asm volatile(xstate_fault
-                     : "0" (0)
-                     : "memory");
-
         return err;
 }
 
@@ -149,9 +143,9 @@ static inline int xsave_state(struct xsave_struct *fx, u64 mask)
          */
         alternative_input_2(
                 "1:"XSAVE,
-                "1:"XSAVEOPT,
+                XSAVEOPT,
                 X86_FEATURE_XSAVEOPT,
-                "1:"XSAVES,
+                XSAVES,
                 X86_FEATURE_XSAVES,
                 [fx] "D" (fx), "a" (lmask), "d" (hmask) :
                 "memory");
@@ -178,7 +172,7 @@ static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
          */
         alternative_input(
                 "1: " XRSTOR,
-                "1: " XRSTORS,
+                XRSTORS,
                 X86_FEATURE_XSAVES,
                 "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
                 : "memory");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b5c8ff5e9dfc..2346c95c6ab1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1396,6 +1396,12 @@ void cpu_init(void)
 
         wait_for_master_cpu(cpu);
 
+        /*
+         * Initialize the CR4 shadow before doing anything that could
+         * try to read it.
+         */
+        cr4_init_shadow();
+
         show_ucode_info_early();
 
         printk(KERN_INFO "Initializing CPU#%d\n", cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 94d7dcb12145..50163fa9034f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -565,8 +565,8 @@ static const struct _tlb_table intel_tlb_table[] = {
         { 0xb2, TLB_INST_4K,            64,     " TLB_INST 4KByte pages, 4-way set associative" },
         { 0xb3, TLB_DATA_4K,            128,    " TLB_DATA 4 KByte pages, 4-way set associative" },
         { 0xb4, TLB_DATA_4K,            256,    " TLB_DATA 4 KByte pages, 4-way associative" },
-        { 0xb5, TLB_INST_4K,            64,     " TLB_INST 4 KByte pages, 8-way set ssociative" },
-        { 0xb6, TLB_INST_4K,            128,    " TLB_INST 4 KByte pages, 8-way set ssociative" },
+        { 0xb5, TLB_INST_4K,            64,     " TLB_INST 4 KByte pages, 8-way set associative" },
+        { 0xb6, TLB_INST_4K,            128,    " TLB_INST 4 KByte pages, 8-way set associative" },
         { 0xba, TLB_DATA_4K,            64,     " TLB_DATA 4 KByte pages, 4-way associative" },
         { 0xc0, TLB_DATA_4K_4M,         8,      " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
         { 0xc1, STLB_4K_2M,             1024,   " STLB 4 KByte and 2 MByte pages, 8-way associative" },
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d4199b03e..31e2d5bf3e38 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:      mov %esp, %eax
         call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+        call xen_maybe_preempt_hcall
+#endif
         jmp  ret_from_intr
         CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index db13655c3a2a..1d74d161687c 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -269,11 +269,14 @@ ENTRY(ret_from_fork)
         testl $3, CS-ARGOFFSET(%rsp)            # from kernel_thread?
         jz   1f
 
-        testl $_TIF_IA32, TI_flags(%rcx)        # 32-bit compat task needs IRET
-        jnz  int_ret_from_sys_call
-
-        RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
-        jmp ret_from_sys_call                   # go to the SYSRET fastpath
+        /*
+         * By the time we get here, we have no idea whether our pt_regs,
+         * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+         * the slow path, or one of the ia32entry paths.
+         * Use int_ret_from_sys_call to return, since it can safely handle
+         * all of the above.
+         */
+        jmp  int_ret_from_sys_call
 
 1:
         subq $REST_SKIP, %rsp   # leave space for volatiles
@@ -1208,6 +1211,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
         popq %rsp
         CFI_DEF_CFA_REGISTER rsp
         decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+        call xen_maybe_preempt_hcall
+#endif
         jmp  error_exit
         CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6a1146ea4d4d..4e3d5a9621fe 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -223,27 +223,48 @@ static unsigned long
 __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
         struct kprobe *kp;
+        unsigned long faddr;
 
         kp = get_kprobe((void *)addr);
-        /* There is no probe, return original address */
-        if (!kp)
+        faddr = ftrace_location(addr);
+        /*
+         * Addresses inside the ftrace location are refused by
+         * arch_check_ftrace_location(). Something went terribly wrong
+         * if such an address is checked here.
+         */
+        if (WARN_ON(faddr && faddr != addr))
+                return 0UL;
+        /*
+         * Use the current code if it is not modified by Kprobe
+         * and it cannot be modified by ftrace.
+         */
+        if (!kp && !faddr)
                 return addr;
 
         /*
-         *  Basically, kp->ainsn.insn has an original instruction.
-         *  However, RIP-relative instruction can not do single-stepping
-         *  at different place, __copy_instruction() tweaks the displacement of
-         *  that instruction. In that case, we can't recover the instruction
-         *  from the kp->ainsn.insn.
+         * Basically, kp->ainsn.insn has an original instruction.
+         * However, RIP-relative instruction can not do single-stepping
+         * at different place, __copy_instruction() tweaks the displacement of
+         * that instruction. In that case, we can't recover the instruction
+         * from the kp->ainsn.insn.
          *
-         *  On the other hand, kp->opcode has a copy of the first byte of
-         *  the probed instruction, which is overwritten by int3. And
-         *  the instruction at kp->addr is not modified by kprobes except
-         *  for the first byte, we can recover the original instruction
-         *  from it and kp->opcode.
+         * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+         * of the first byte of the probed instruction, which is overwritten
+         * by int3. And the instruction at kp->addr is not modified by kprobes
+         * except for the first byte, we can recover the original instruction
+         * from it and kp->opcode.
+         *
+         * In case of Kprobes using ftrace, we do not have a copy of
+         * the original instruction. In fact, the ftrace location might
+         * be modified at anytime and even could be in an inconsistent state.
+         * Fortunately, we know that the original code is the ideal 5-byte
+         * long NOP.
          */
-        memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-        buf[0] = kp->opcode;
+        memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+        if (faddr)
+                memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+        else
+                buf[0] = kp->opcode;
         return (unsigned long)buf;
 }
 
@@ -251,6 +272,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr)
                  * normally used, we just go through if there is no kprobe.
                  */
                 __addr = recover_probed_instruction(buf, addr);
+                if (!__addr)
+                        return 0;
                 kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
                 insn_get_length(&insn);
 
@@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src)
         unsigned long recovered_insn =
                 recover_probed_instruction(buf, (unsigned long)src);
 
+        if (!recovered_insn)
+                return 0;
         kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
         insn_get_length(&insn);
         /* Another subsystem puts a breakpoint, failed to recover */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 0dd8d089c315..7b3b9d15c47a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr)
                          */
                         return 0;
                 recovered_insn = recover_probed_instruction(buf, addr);
+                if (!recovered_insn)
+                        return 0;
                 kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
                 insn_get_length(&insn);
                 /* Another subsystem puts a breakpoint */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e0b794a84c35..106c01557f2b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4950,7 +4950,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
                         goto done;
                 }
         }
-        ctxt->dst.orig_val = ctxt->dst.val;
+        /* Copy full 64-bit value for CMPXCHG8B.  */
+        ctxt->dst.orig_val64 = ctxt->dst.val64;
 
 special_insn:
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e55b5fc344eb..bd4e34de24c7 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1572,7 +1572,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
                 apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
         }
         apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
-        apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
+        apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
         apic->highest_isr_cache = -1;
         update_divide_count(apic);
         atomic_set(&apic->lapic_timer.pending, 0);
@@ -1782,7 +1782,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
         update_divide_count(apic);
         start_apic_timer(apic);
         apic->irr_pending = true;
-        apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+        apic->isr_count = kvm_x86_ops->hwapic_isr_update ?
                                 1 : count_vectors(apic->regs + APIC_ISR);
         apic->highest_isr_cache = -1;
         if (kvm_x86_ops->hwapic_irr_update)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d319e0c24758..cc618c882f90 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3649,11 +3649,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
         return;
 }
 
-static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
-{
-        return;
-}
-
 static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
         return;
@@ -4403,7 +4398,6 @@ static struct kvm_x86_ops svm_x86_ops = {
         .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
         .vm_has_apicv = svm_vm_has_apicv,
         .load_eoi_exitmap = svm_load_eoi_exitmap,
-        .hwapic_isr_update = svm_hwapic_isr_update,
         .sync_pir_to_irr = svm_sync_pir_to_irr,
 
         .set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14c1a18d206a..f7b20b417a3a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4367,6 +4367,18 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
         return 0;
 }
 
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_SMP
+        if (vcpu->mode == IN_GUEST_MODE) {
+                apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
+                                POSTED_INTR_VECTOR);
+                return true;
+        }
+#endif
+        return false;
+}
+
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
                                                 int vector)
 {
@@ -4375,9 +4387,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
         if (is_guest_mode(vcpu) &&
             vector == vmx->nested.posted_intr_nv) {
                 /* the PIR and ON have been set by L1. */
-                if (vcpu->mode == IN_GUEST_MODE)
-                        apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-                                POSTED_INTR_VECTOR);
+                kvm_vcpu_trigger_posted_interrupt(vcpu);
                 /*
                  * If a posted intr is not recognized by hardware,
                  * we will accomplish it in the next vmentry.
@@ -4409,12 +4419,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 
         r = pi_test_and_set_on(&vmx->pi_desc);
         kvm_make_request(KVM_REQ_EVENT, vcpu);
-#ifdef CONFIG_SMP
-        if (!r && (vcpu->mode == IN_GUEST_MODE))
-                apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-                                POSTED_INTR_VECTOR);
-        else
-#endif
+        if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu))
                 kvm_vcpu_kick(vcpu);
 }
 
diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig
index 4a0890f815c4..08f41caada45 100644
--- a/arch/x86/lguest/Kconfig
+++ b/arch/x86/lguest/Kconfig
@@ -1,6 +1,6 @@
 config LGUEST_GUEST
         bool "Lguest guest support"
-        depends on X86_32 && PARAVIRT
+        depends on X86_32 && PARAVIRT && PCI
         select TTY
         select VIRTUALIZATION
         select VIRTIO
@@ -8,7 +8,7 @@ config LGUEST_GUEST
         help
           Lguest is a tiny in-kernel hypervisor.  Selecting this will
           allow your kernel to boot under lguest.  This option will increase
-          your kernel size by about 6k.  If in doubt, say N.
+          your kernel size by about 10k.  If in doubt, say N.
 
           If you say Y here, make sure you say Y (or M) to the virtio block
           and net drivers which lguest needs.
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 6ac273832f28..e4695985f9de 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -331,7 +331,7 @@ static void probe_pci_root_info(struct pci_root_info *info,
                                 struct list_head *list)
 {
         int ret;
-        struct resource_entry *entry;
+        struct resource_entry *entry, *tmp;
 
         sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
         info->bridge = device;
@@ -345,8 +345,13 @@ static void probe_pci_root_info(struct pci_root_info *info,
                 dev_dbg(&device->dev,
                         "no IO and memory resources present in _CRS\n");
         else
-                resource_list_for_each_entry(entry, list)
-                        entry->res->name = info->name;
+                resource_list_for_each_entry_safe(entry, tmp, list) {
+                        if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
+                            (entry->res->flags & IORESOURCE_DISABLED))
+                                resource_list_destroy_entry(entry);
+                        else
+                                entry->res->name = info->name;
+                }
 }
 
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 1bbedc4b0f88..3005f0c89f2e 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -130,7 +130,7 @@ static void intel_mid_arch_setup(void)
                 intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
         else {
                 intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-                pr_info("ARCH: Uknown SoC, assuming PENWELL!\n");
+                pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
         }
 
 out:
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bd8b8459c3d0..5240f563076d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1070,6 +1070,23 @@ static inline void xen_write_cr8(unsigned long val)
         BUG_ON(val);
 }
 #endif
+
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+        u64 val;
+
+        val = native_read_msr_safe(msr, err);
+        switch (msr) {
+        case MSR_IA32_APICBASE:
+#ifdef CONFIG_X86_X2APIC
+                if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
+#endif
+                        val &= ~X2APIC_ENABLE;
+                break;
+        }
+        return val;
+}
+
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
         int ret;
@@ -1240,7 +1257,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
         .wbinvd = native_wbinvd,
 
-        .read_msr = native_read_msr_safe,
+        .read_msr = xen_read_msr_safe,
         .write_msr = xen_write_msr_safe,
 
         .read_tsc = native_read_tsc,
@@ -1741,6 +1758,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #ifdef CONFIG_X86_32
         i386_start_kernel();
 #else
+        cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
         x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }