[PATCH v2 6/7] x86/kvm/vmx: Defer TR reload after VM exit

[Andy Lutomirski]

Intel's VMX is daft and resets the hidden TSS limit register to 0x67
on VM exit, and the 0x67 is not configurable.  KVM currently reloads
TR using the LTR instruction on every exit, but this is quite slow
because LTR is serializing.

The 0x67 limit is entirely harmless unless ioperm() is in use, so
defer the reload until a task using ioperm() is actually running.

Here's some poorly done benchmarking using kvm-unit-tests:

Before:

cpuid 1313
vmcall 1195
mov_from_cr8 11
mov_to_cr8 17
inl_from_pmtimer 6770
inl_from_qemu 6856
inl_from_kernel 2435
outl_to_kernel 1402

After:

cpuid 1291
vmcall 1181
mov_from_cr8 11
mov_to_cr8 16
inl_from_pmtimer 6457
inl_from_qemu 6209
inl_from_kernel 2339
outl_to_kernel 1391

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/include/asm/desc.h | 52 +++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/ioport.c    | 11 ++++++++++
 arch/x86/kernel/process.c   | 10 +++++++++
 arch/x86/kvm/vmx.c          | 23 ++++++++------------
 4 files changed, 82 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 2e781bcc5e12..178e58336f67 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -205,6 +205,58 @@ static inline void native_load_tr_desc(void)
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
 }
 
+DECLARE_PER_CPU(bool, __tss_limit_invalid);
+
+static inline void force_reload_TR(void)
+{
+	struct desc_struct *d = get_cpu_gdt_table(smp_processor_id());
+	tss_desc tss;
+
+	memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc));
+
+	/*
+	 * LTR requires an available TSS, and the TSS is currently
+	 * busy.  Make it be available so that LTR will work.
+	 */
+	tss.type = DESC_TSS;
+	write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS);
+
+	load_TR_desc();
+	this_cpu_write(__tss_limit_invalid, false);
+}
+
+/*
+ * If you do something evil that corrupts the cached TSS limit (I'm looking
+ * at you, VMX exits), call this function.
+ *
+ * The optimization here is that the TSS limit only matters for Linux if the
+ * IO bitmap is in use.  If the TSS limit gets forced to its minimum value,
+ * everything works except that IO bitmap will be ignored and all CPL 3 IO
+ * instructions will #GP, which is exactly what we want for normal tasks.
+ */
+static inline void invalidate_tss_limit(void)
+{
+	DEBUG_LOCKS_WARN_ON(preemptible());
+
+	if (unlikely(test_thread_flag(TIF_IO_BITMAP)))
+		force_reload_TR();
+	else
+		this_cpu_write(__tss_limit_invalid, true);
+}
+
+/*
+ * Call this if you need the TSS limit to be correct, which should be the case
+ * if and only if you have TIF_IO_BITMAP set or you're switching to a task
+ * with TIF_IO_BITMAP set.
+ */
+static inline void refresh_tss_limit(void)
+{
+	DEBUG_LOCKS_WARN_ON(preemptible());
+
+	if (unlikely(this_cpu_read(__tss_limit_invalid)))
+		force_reload_TR();
+}
+
 static inline void native_load_gdt(const struct desc_ptr *dtr)
 {
 	asm volatile("lgdt %0"::"m" (*dtr));
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 589b3193f102..875d3d25dd6a 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 +46,16 @@ 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);
+
+		/*
+		 * Now that we have an IO bitmap, we need our TSS limit to be
+		 * correct.  It's fine if we are preempted after doing this:
+		 * with TIF_IO_BITMAP set, context switches will keep our TSS
+		 * limit correct.
+		 */
+		preempt_disable();
+		refresh_tss_limit();
+		preempt_enable();
 	}
 
 	/*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b615a1113f58..0b302591b51f 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, __tss_limit_invalid);
+EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
+
 /*
  * 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_tss_limit();
 	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
 		/*
 		 * Clear any possible leftover bits:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 17ef11c64702..733c8a3c912e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1992,19 +1992,6 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	m->host[i].value = host_val;
 }
 
-static void reload_tss(void)
-{
-	/*
-	 * VT restores TR but not its size.  Useless.
-	 */
-	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
-	struct desc_struct *descs;
-
-	descs = (void *)gdt->address;
-	descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
-	load_TR_desc();
-}
-
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 {
 	u64 guest_efer = vmx->vcpu.arch.efer;
@@ -2174,7 +2161,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 		loadsegment(es, vmx->host_state.es_sel);
 	}
 #endif
-	reload_tss();
+	invalidate_tss_limit();
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
@@ -2295,6 +2282,14 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			    (unsigned long)this_cpu_ptr(&cpu_tss));
 		vmcs_writel(HOST_GDTR_BASE, gdt->address);
 
+		/*
+		 * VM exits change the host TR limit to 0x67 after a VM
+		 * exit.  This is okay, since 0x67 covers everything except
+		 * the IO bitmap and have have code to handle the IO bitmap
+		 * being lost after a VM exit.
+		 */
+		BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67);
+
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 
-- 
2.9.3