On Wed, May 18, 2011, Marcelo Tosatti wrote about "Re: [PATCH 08/31] nVMX: Fix local_vcpus_link handling":
> Humpf, right. OK, you can handle the x86.c usage with
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>...
Hi Avi and Marcelo, here is a the new first patch to the nvmx patch set,
which overhauls the handling of vmcss on cpus, as you asked.
As you guessed, the nested entry and exit code becomes much simpler and
cleaner, with the whole VMCS switching code on entry, for example, reduced
to:
cpu = get_cpu();
vmx->loaded_vmcs = vmcs02;
vmx_vcpu_put(vcpu);
vmx_vcpu_load(vcpu, cpu);
vcpu->cpu = cpu;
put_cpu();
You can apply this patch separately from the rest of the patch set, if you
wish. I'm sending just this one, like you asked - and can send the rest of
the patches when you ask me to.
Subject: [PATCH 01/31] nVMX: Keep list of loaded VMCSs, instead of vcpus.
In VMX, before we bring down a CPU we must VMCLEAR all VMCSs loaded on it
because (at least in theory) the processor might not have written all of its
content back to memory. Since a patch from June 26, 2008, this is done using
a per-cpu "vcpus_on_cpu" linked list of vcpus loaded on each CPU.
The problem is that with nested VMX, we no longer have the concept of a
vcpu being loaded on a cpu: A vcpu has multiple VMCSs (one for L1, a pool for
L2s), and each of those may be have been last loaded on a different cpu.
So instead of linking the vcpus, we link the VMCSs, using a new structure
loaded_vmcs. This structure contains the VMCS, and the information pertaining
to its loading on a specific cpu (namely, the cpu number, and whether it
was already launched on this cpu once). In nested we will also use the same
structure to hold L2 VMCSs, and vmx->loaded_vmcs is a pointer to the
currently active VMCS.
Signed-off-by: Nadav Har'El <nyh@xxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 129 ++++++++++++++++++++++++++-----------------
arch/x86/kvm/x86.c | 3 -
2 files changed, 80 insertions(+), 52 deletions(-)
--- .before/arch/x86/kvm/x86.c 2011-05-22 11:41:57.000000000 +0300
+++ .after/arch/x86/kvm/x86.c 2011-05-22 11:41:57.000000000 +0300
@@ -2119,7 +2119,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu
if (need_emulate_wbinvd(vcpu)) {
if (kvm_x86_ops->has_wbinvd_exit())
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
- else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
+ else if (vcpu->cpu != -1 && vcpu->cpu != cpu
+ && cpu_online(vcpu->cpu))
smp_call_function_single(vcpu->cpu,
wbinvd_ipi, NULL, 1);
}
--- .before/arch/x86/kvm/vmx.c 2011-05-22 11:41:57.000000000 +0300
+++ .after/arch/x86/kvm/vmx.c 2011-05-22 11:41:58.000000000 +0300
@@ -116,6 +116,18 @@ struct vmcs {
char data[0];
};
+/*
+ * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also
+ * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs
+ * loaded on this CPU (so we can clear them if the CPU goes down).
+ */
+struct loaded_vmcs {
+ struct vmcs *vmcs;
+ int cpu;
+ int launched;
+ struct list_head loaded_vmcss_on_cpu_link;
+};
+
struct shared_msr_entry {
unsigned index;
u64 data;
@@ -124,9 +136,7 @@ struct shared_msr_entry {
struct vcpu_vmx {
struct kvm_vcpu vcpu;
- struct list_head local_vcpus_link;
unsigned long host_rsp;
- int launched;
u8 fail;
u8 cpl;
bool nmi_known_unmasked;
@@ -140,7 +150,14 @@ struct vcpu_vmx {
u64 msr_host_kernel_gs_base;
u64 msr_guest_kernel_gs_base;
#endif
- struct vmcs *vmcs;
+ /*
+ * loaded_vmcs points to the VMCS currently used in this vcpu. For a
+ * non-nested (L1) guest, it always points to vmcs01. For a nested
+ * guest (L2), it points to a different VMCS.
+ */
+ struct loaded_vmcs vmcs01;
+ struct loaded_vmcs *loaded_vmcs;
+ bool __launched; /* temporary, used in vmx_vcpu_run */
struct msr_autoload {
unsigned nr;
struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
@@ -200,7 +217,11 @@ static int vmx_set_tss_addr(struct kvm *
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
-static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
+/*
+ * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed
+ * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it.
+ */
+static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
static unsigned long *vmx_io_bitmap_a;
@@ -514,25 +535,25 @@ static void vmcs_load(struct vmcs *vmcs)
vmcs, phys_addr);
}
-static void __vcpu_clear(void *arg)
+static void __loaded_vmcs_clear(void *arg)
{
- struct vcpu_vmx *vmx = arg;
+ struct loaded_vmcs *loaded_vmcs = arg;
int cpu = raw_smp_processor_id();
- if (vmx->vcpu.cpu == cpu)
- vmcs_clear(vmx->vmcs);
- if (per_cpu(current_vmcs, cpu) == vmx->vmcs)
+ if (loaded_vmcs->cpu == cpu)
+ vmcs_clear(loaded_vmcs->vmcs);
+ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
per_cpu(current_vmcs, cpu) = NULL;
- list_del(&vmx->local_vcpus_link);
- vmx->vcpu.cpu = -1;
- vmx->launched = 0;
+ list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
+ loaded_vmcs->cpu = -1;
+ loaded_vmcs->launched = 0;
}
-static void vcpu_clear(struct vcpu_vmx *vmx)
+static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
{
- if (vmx->vcpu.cpu == -1)
- return;
- smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1);
+ if (loaded_vmcs->cpu != -1)
+ smp_call_function_single(
+ loaded_vmcs->cpu, __loaded_vmcs_clear, loaded_vmcs, 1);
}
static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx)
@@ -971,22 +992,22 @@ static void vmx_vcpu_load(struct kvm_vcp
if (!vmm_exclusive)
kvm_cpu_vmxon(phys_addr);
- else if (vcpu->cpu != cpu)
- vcpu_clear(vmx);
+ else if (vmx->loaded_vmcs->cpu != cpu)
+ loaded_vmcs_clear(vmx->loaded_vmcs);
- if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
- per_cpu(current_vmcs, cpu) = vmx->vmcs;
- vmcs_load(vmx->vmcs);
+ if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+ per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
+ vmcs_load(vmx->loaded_vmcs->vmcs);
}
- if (vcpu->cpu != cpu) {
+ if (vmx->loaded_vmcs->cpu != cpu) {
struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
unsigned long sysenter_esp;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
local_irq_disable();
- list_add(&vmx->local_vcpus_link,
- &per_cpu(vcpus_on_cpu, cpu));
+ list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
+ &per_cpu(loaded_vmcss_on_cpu, cpu));
local_irq_enable();
/*
@@ -999,13 +1020,15 @@ static void vmx_vcpu_load(struct kvm_vcp
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
}
+ vmx->loaded_vmcs->cpu = cpu;
}
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
__vmx_load_host_state(to_vmx(vcpu));
if (!vmm_exclusive) {
- __vcpu_clear(to_vmx(vcpu));
+ __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs);
+ vcpu->cpu = -1;
kvm_cpu_vmxoff();
}
}
@@ -1469,7 +1492,7 @@ static int hardware_enable(void *garbage
if (read_cr4() & X86_CR4_VMXE)
return -EBUSY;
- INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
+ INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
test_bits = FEATURE_CONTROL_LOCKED;
@@ -1493,14 +1516,14 @@ static int hardware_enable(void *garbage
return 0;
}
-static void vmclear_local_vcpus(void)
+static void vmclear_local_loaded_vmcss(void)
{
int cpu = raw_smp_processor_id();
- struct vcpu_vmx *vmx, *n;
+ struct loaded_vmcs *v, *n;
- list_for_each_entry_safe(vmx, n, &per_cpu(vcpus_on_cpu, cpu),
- local_vcpus_link)
- __vcpu_clear(vmx);
+ list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu),
+ loaded_vmcss_on_cpu_link)
+ __loaded_vmcs_clear(v);
}
@@ -1515,7 +1538,7 @@ static void kvm_cpu_vmxoff(void)
static void hardware_disable(void *garbage)
{
if (vmm_exclusive) {
- vmclear_local_vcpus();
+ vmclear_local_loaded_vmcss();
kvm_cpu_vmxoff();
}
write_cr4(read_cr4() & ~X86_CR4_VMXE);
@@ -1696,6 +1719,18 @@ static void free_vmcs(struct vmcs *vmcs)
free_pages((unsigned long)vmcs, vmcs_config.order);
}
+/*
+ * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded
+ */
+static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
+{
+ if (!loaded_vmcs->vmcs)
+ return;
+ loaded_vmcs_clear(loaded_vmcs);
+ free_vmcs(loaded_vmcs->vmcs);
+ loaded_vmcs->vmcs = NULL;
+}
+
static void free_kvm_area(void)
{
int cpu;
@@ -4166,6 +4201,7 @@ static void __noclone vmx_vcpu_run(struc
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
@@ -4236,7 +4272,7 @@ static void __noclone vmx_vcpu_run(struc
"pop %%"R"bp; pop %%"R"dx \n\t"
"setbe %c[fail](%0) \n\t"
: : "c"(vmx), "d"((unsigned long)HOST_RSP),
- [launched]"i"(offsetof(struct vcpu_vmx, launched)),
+ [launched]"i"(offsetof(struct vcpu_vmx, __launched)),
[fail]"i"(offsetof(struct vcpu_vmx, fail)),
[host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)),
[rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])),
@@ -4276,7 +4312,7 @@ static void __noclone vmx_vcpu_run(struc
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
- vmx->launched = 1;
+ vmx->loaded_vmcs->launched = 1;
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
@@ -4288,23 +4324,12 @@ static void __noclone vmx_vcpu_run(struc
#undef R
#undef Q
-static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- if (vmx->vmcs) {
- vcpu_clear(vmx);
- free_vmcs(vmx->vmcs);
- vmx->vmcs = NULL;
- }
-}
-
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
free_vpid(vmx);
- vmx_free_vmcs(vcpu);
+ free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
@@ -4344,11 +4369,13 @@ static struct kvm_vcpu *vmx_create_vcpu(
goto uninit_vcpu;
}
- vmx->vmcs = alloc_vmcs();
- if (!vmx->vmcs)
+ vmx->loaded_vmcs = &vmx->vmcs01;
+ vmx->loaded_vmcs->vmcs = alloc_vmcs();
+ if (!vmx->loaded_vmcs->vmcs)
goto free_msrs;
-
- vmcs_init(vmx->vmcs);
+ vmcs_init(vmx->loaded_vmcs->vmcs);
+ vmx->loaded_vmcs->cpu = -1;
+ vmx->loaded_vmcs->launched = 0;
cpu = get_cpu();
vmx_vcpu_load(&vmx->vcpu, cpu);
@@ -4377,7 +4404,7 @@ static struct kvm_vcpu *vmx_create_vcpu(
return &vmx->vcpu;
free_vmcs:
- free_vmcs(vmx->vmcs);
+ free_vmcs(vmx->loaded_vmcs->vmcs);
free_msrs:
kfree(vmx->guest_msrs);
uninit_vcpu:
--
Nadav Har'El | Sunday, May 22 2011, 18 Iyyar 5771
nyh@xxxxxxxxxxxxxxxxxxx |-----------------------------------------
Phone +972-523-790466, ICQ 13349191 |I think therefore I am. My computer
http://nadav.harel.org.il |thinks for me, therefore I am not.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
