summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/process.c
diff options
context:
space:
mode:
authorAndy Lutomirski <luto@kernel.org>2017-02-20 08:56:14 -0800
committerPaolo Bonzini <pbonzini@redhat.com>2017-02-21 12:45:08 +0100
commitb7ffc44d5b2ea163899d09289ca7743d5c32e926 (patch)
treec41439937c5810b701a895d1f9e060b57573d540 /arch/x86/kernel/process.c
parentd3273deac9c0cdae32eb46f928487433eaa37f87 (diff)
downloadlinux-b7ffc44d5b2ea163899d09289ca7743d5c32e926.tar.gz
linux-b7ffc44d5b2ea163899d09289ca7743d5c32e926.tar.bz2
linux-b7ffc44d5b2ea163899d09289ca7743d5c32e926.zip
x86/kvm/vmx: Defer TR reload after VM exit
Intel's VMX is daft and resets the hidden TSS limit register to 0x67 on VMX reload, 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@kernel.org> [Force-reload TR in invalidate_tss_limit. - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kernel/process.c')
-rw-r--r--arch/x86/kernel/process.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b615a1113f58..7780efa635b9 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: