Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

6 files changed, 54 insertions, 3 deletions

diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 210927e..99332f5 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,6 +13,10 @@ static char syscalls_ia32[] = {
 #include <asm/syscalls_32.h>
 };
 
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#include <asm/kvm_para.h>
+#endif
+
 int main(void)
 {
 #ifdef CONFIG_PARAVIRT
@@ -22,6 +26,11 @@ int main(void)
 	BLANK();
 #endif
 
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+	OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted);
+	BLANK();
+#endif
+
 #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
 	ENTRY(bx);
 	ENTRY(cx);
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 589b319..b01bc8517 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <linux/bitmap.h>
 #include <asm/syscalls.h>
+#include <asm/desc.h>
 
 /*
  * this changes the io permissions bitmap in the current task.
@@ -45,6 +46,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 		memset(bitmap, 0xff, IO_BITMAP_BYTES);
 		t->io_bitmap_ptr = bitmap;
 		set_thread_flag(TIF_IO_BITMAP);
+
+		preempt_disable();
+		refresh_TR();
+		preempt_enable();
 	}
 
 	/*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 099fcba..14f65a5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -589,7 +589,8 @@ out:
 	local_irq_restore(flags);
 }
 
-__visible bool __kvm_vcpu_is_preempted(int cpu)
+#ifdef CONFIG_X86_32
+__visible bool __kvm_vcpu_is_preempted(long cpu)
 {
 	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
 
@@ -597,6 +598,29 @@ __visible bool __kvm_vcpu_is_preempted(int cpu)
 }
 PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
 
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+"ret;"
+".popsection");
+
+#endif
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 542710b..bae6ea6 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -28,6 +28,7 @@
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
+#include <asm/kvmclock.h>
 
 static int kvmclock __ro_after_init = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
@@ -49,6 +50,7 @@ struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
 {
 	return hv_clock;
 }
+EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va);
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -174,13 +176,14 @@ bool kvm_check_and_clear_guest_paused(void)
 	return ret;
 }
 
-static struct clocksource kvm_clock = {
+struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
+EXPORT_SYMBOL_GPL(kvm_clock);
 
 int kvm_register_clock(char *txt)
 {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 6259327..8f2d1c9 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -20,7 +20,7 @@ bool pv_is_native_spin_unlock(void)
 		__raw_callee_save___native_queued_spin_unlock;
 }
 
-__visible bool __native_vcpu_is_preempted(int cpu)
+__visible bool __native_vcpu_is_preempted(long cpu)
 {
 	return false;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b615a11..7780efa 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -32,6 +32,7 @@
 #include <asm/mce.h>
 #include <asm/vm86.h>
 #include <asm/switch_to.h>
+#include <asm/desc.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -64,6 +65,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
+DEFINE_PER_CPU(bool, need_tr_refresh);
+EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh);
+
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -209,6 +213,12 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 */
 		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
 		       max(prev->io_bitmap_max, next->io_bitmap_max));
+
+		/*
+		 * Make sure that the TSS limit is correct for the CPU
+		 * to notice the IO bitmap.
+		 */
+		refresh_TR();
 	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
 		/*
 		 * Clear any possible leftover bits: