This is a note to let you know that I've just added the patch titled
x86/kvm/vmx: Defer TR reload after VM exit
to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git%3Ba=su...
The filename of the patch is: x86-kvm-vmx-defer-tr-reload-after-vm-exit.patch and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let stable@vger.kernel.org know about it.
From b7ffc44d5b2ea163899d09289ca7743d5c32e926 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski luto@kernel.org Date: Mon, 20 Feb 2017 08:56:14 -0800 Subject: x86/kvm/vmx: Defer TR reload after VM exit
From: Andy Lutomirski luto@kernel.org
commit b7ffc44d5b2ea163899d09289ca7743d5c32e926 upstream.
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 Signed-off-by: Eduardo Valentin eduval@amazon.com Signed-off-by: Eduardo Valentin edubezval@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/desc.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/ioport.c | 5 ++++ arch/x86/kernel/process.c | 10 +++++++++ arch/x86/kvm/vmx.c | 23 ++++++++------------- 4 files changed, 72 insertions(+), 14 deletions(-)
--- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -213,6 +213,54 @@ static inline void native_load_tr_desc(v asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); }
+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(); +} + +DECLARE_PER_CPU(bool, need_tr_refresh); + +static inline void refresh_TR(void) +{ + WARN_ON(preemptible()); + + if (unlikely(this_cpu_read(need_tr_refresh))) { + force_reload_TR(); + this_cpu_write(need_tr_refresh, 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) +{ + WARN_ON(preemptible()); + + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(need_tr_refresh, true); +} + static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); --- 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 memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; set_thread_flag(TIF_IO_BITMAP); + + preempt_disable(); + refresh_TR(); + preempt_enable(); }
/* --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -33,6 +33,7 @@ #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, @@ -82,6 +83,9 @@ void idle_notifier_unregister(struct not EXPORT_SYMBOL_GPL(idle_notifier_unregister); #endif
+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. @@ -227,6 +231,12 @@ void __switch_to_xtra(struct task_struct */ 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: --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1959,19 +1959,6 @@ static void add_atomic_switch_msr(struct 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; @@ -2141,7 +2128,7 @@ static void __vmx_load_host_state(struct 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 @@ -2265,6 +2252,14 @@ static void vmx_vcpu_load(struct kvm_vcp vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ vmcs_writel(HOST_GDTR_BASE, gdt->address); /* 22.2.4 */
+ /* + * 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 */
Patches currently in stable-queue which might be from luto@kernel.org are
queue-4.9/x86-mm-refactor-flush_tlb_mm_range-to-merge-local-and-remote-cases.patch queue-4.9/x86-mm-pass-flush_tlb_info-to-flush_tlb_others-etc.patch queue-4.9/x86-mm-rework-lazy-tlb-to-track-the-actual-loaded-mm.patch queue-4.9/x86-mm-kvm-teach-kvm-s-vmx-code-that-cr3-isn-t-a-constant.patch queue-4.9/x86-mm-use-new-merged-flush-logic-in-arch_tlbbatch_flush.patch queue-4.9/x86-kvm-vmx-simplify-segment_base.patch queue-4.9/x86-entry-unwind-create-stack-frames-for-saved-interrupt-registers.patch queue-4.9/x86-mm-reduce-indentation-in-flush_tlb_func.patch queue-4.9/x86-mm-remove-the-up-asm-tlbflush.h-code-always-use-the-formerly-smp-code.patch queue-4.9/x86-mm-reimplement-flush_tlb_page-using-flush_tlb_mm_range.patch queue-4.9/mm-x86-mm-make-the-batched-unmap-tlb-flush-api-more-generic.patch queue-4.9/x86-kvm-vmx-defer-tr-reload-after-vm-exit.patch queue-4.9/x86-mm-change-the-leave_mm-condition-for-local-tlb-flushes.patch queue-4.9/x86-mm-be-more-consistent-wrt-page_shift-vs-page_size-in-tlb-flush-code.patch