This is a note to let you know that I've just added the patch titled
KVM: nVMX: Eliminate vmcs02 pool
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
kvm-nvmx-eliminate-vmcs02-pool.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@xxxxxxxxxxxxxxx> know about it.
>From de3a0021a60635de96aa92713c1a31a96747d72c Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@xxxxxxxxxx>
Date: Mon, 27 Nov 2017 17:22:25 -0600
Subject: KVM: nVMX: Eliminate vmcs02 pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
From: Jim Mattson <jmattson@xxxxxxxxxx>
commit de3a0021a60635de96aa92713c1a31a96747d72c upstream.
The potential performance advantages of a vmcs02 pool have never been
realized. To simplify the code, eliminate the pool. Instead, a single
vmcs02 is allocated per VCPU when the VCPU enters VMX operation.
Cc: stable@xxxxxxxxxxxxxxx # prereq for Spectre mitigation
Signed-off-by: Jim Mattson <jmattson@xxxxxxxxxx>
Signed-off-by: Mark Kanda <mark.kanda@xxxxxxxxxx>
Reviewed-by: Ameya More <ameya.more@xxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 146 ++++++++---------------------------------------------
1 file changed, 23 insertions(+), 123 deletions(-)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -173,7 +173,6 @@ module_param(ple_window_max, int, S_IRUG
extern const ulong vmx_return;
#define NR_AUTOLOAD_MSRS 8
-#define VMCS02_POOL_SIZE 1
struct vmcs {
u32 revision_id;
@@ -207,7 +206,7 @@ struct shared_msr_entry {
* stored in guest memory specified by VMPTRLD, but is opaque to the guest,
* which must access it using VMREAD/VMWRITE/VMCLEAR instructions.
* More than one of these structures may exist, if L1 runs multiple L2 guests.
- * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the
+ * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the
* underlying hardware which will be used to run L2.
* This structure is packed to ensure that its layout is identical across
* machines (necessary for live migration).
@@ -386,13 +385,6 @@ struct __packed vmcs12 {
*/
#define VMCS12_SIZE 0x1000
-/* Used to remember the last vmcs02 used for some recently used vmcs12s */
-struct vmcs02_list {
- struct list_head list;
- gpa_t vmptr;
- struct loaded_vmcs vmcs02;
-};
-
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -419,15 +411,15 @@ struct nested_vmx {
*/
bool sync_shadow_vmcs;
- /* vmcs02_list cache of VMCSs recently used to run L2 guests */
- struct list_head vmcs02_pool;
- int vmcs02_num;
bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
+
+ struct loaded_vmcs vmcs02;
+
/*
- * Guest pages referred to in vmcs02 with host-physical pointers, so
- * we must keep them pinned while L2 runs.
+ * Guest pages referred to in the vmcs02 with host-physical
+ * pointers, so we must keep them pinned while L2 runs.
*/
struct page *apic_access_page;
struct page *virtual_apic_page;
@@ -6684,94 +6676,6 @@ static int handle_monitor(struct kvm_vcp
}
/*
- * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12.
- * We could reuse a single VMCS for all the L2 guests, but we also want the
- * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this
- * allows keeping them loaded on the processor, and in the future will allow
- * optimizations where prepare_vmcs02 doesn't need to set all the fields on
- * every entry if they never change.
- * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE
- * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first.
- *
- * The following functions allocate and free a vmcs02 in this pool.
- */
-
-/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */
-static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
-{
- struct vmcs02_list *item;
- list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
- if (item->vmptr == vmx->nested.current_vmptr) {
- list_move(&item->list, &vmx->nested.vmcs02_pool);
- return &item->vmcs02;
- }
-
- if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
- /* Recycle the least recently used VMCS. */
- item = list_last_entry(&vmx->nested.vmcs02_pool,
- struct vmcs02_list, list);
- item->vmptr = vmx->nested.current_vmptr;
- list_move(&item->list, &vmx->nested.vmcs02_pool);
- return &item->vmcs02;
- }
-
- /* Create a new VMCS */
- item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
- if (!item)
- return NULL;
- item->vmcs02.vmcs = alloc_vmcs();
- item->vmcs02.shadow_vmcs = NULL;
- if (!item->vmcs02.vmcs) {
- kfree(item);
- return NULL;
- }
- loaded_vmcs_init(&item->vmcs02);
- item->vmptr = vmx->nested.current_vmptr;
- list_add(&(item->list), &(vmx->nested.vmcs02_pool));
- vmx->nested.vmcs02_num++;
- return &item->vmcs02;
-}
-
-/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */
-static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
-{
- struct vmcs02_list *item;
- list_for_each_entry(item, &vmx->nested.vmcs02_pool, list)
- if (item->vmptr == vmptr) {
- free_loaded_vmcs(&item->vmcs02);
- list_del(&item->list);
- kfree(item);
- vmx->nested.vmcs02_num--;
- return;
- }
-}
-
-/*
- * Free all VMCSs saved for this vcpu, except the one pointed by
- * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
- * must be &vmx->vmcs01.
- */
-static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
-{
- struct vmcs02_list *item, *n;
-
- WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
- list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
- /*
- * Something will leak if the above WARN triggers. Better than
- * a use-after-free.
- */
- if (vmx->loaded_vmcs == &item->vmcs02)
- continue;
-
- free_loaded_vmcs(&item->vmcs02);
- list_del(&item->list);
- kfree(item);
- vmx->nested.vmcs02_num--;
- }
-}
-
-/*
* The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
* set the success or error code of an emulated VMX instruction, as specified
* by Vol 2B, VMX Instruction Reference, "Conventions".
@@ -7084,6 +6988,12 @@ static int handle_vmon(struct kvm_vcpu *
return 1;
}
+ vmx->nested.vmcs02.vmcs = alloc_vmcs();
+ vmx->nested.vmcs02.shadow_vmcs = NULL;
+ if (!vmx->nested.vmcs02.vmcs)
+ goto out_vmcs02;
+ loaded_vmcs_init(&vmx->nested.vmcs02);
+
if (cpu_has_vmx_msr_bitmap()) {
vmx->nested.msr_bitmap =
(unsigned long *)__get_free_page(GFP_KERNEL);
@@ -7106,9 +7016,6 @@ static int handle_vmon(struct kvm_vcpu *
vmx->vmcs01.shadow_vmcs = shadow_vmcs;
}
- INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
- vmx->nested.vmcs02_num = 0;
-
hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
@@ -7126,6 +7033,9 @@ out_cached_vmcs12:
free_page((unsigned long)vmx->nested.msr_bitmap);
out_msr_bitmap:
+ free_loaded_vmcs(&vmx->nested.vmcs02);
+
+out_vmcs02:
return -ENOMEM;
}
@@ -7211,7 +7121,7 @@ static void free_nested(struct vcpu_vmx
vmx->vmcs01.shadow_vmcs = NULL;
}
kfree(vmx->nested.cached_vmcs12);
- /* Unpin physical memory we referred to in current vmcs02 */
+ /* Unpin physical memory we referred to in the vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
@@ -7227,7 +7137,7 @@ static void free_nested(struct vcpu_vmx
vmx->nested.pi_desc = NULL;
}
- nested_free_all_saved_vmcss(vmx);
+ free_loaded_vmcs(&vmx->nested.vmcs02);
}
/* Emulate the VMXOFF instruction */
@@ -7261,8 +7171,6 @@ static int handle_vmclear(struct kvm_vcp
vmptr + offsetof(struct vmcs12, launch_state),
&zero, sizeof(zero));
- nested_free_vmcs02(vmx, vmptr);
-
skip_emulated_instruction(vcpu);
nested_vmx_succeed(vcpu);
return 1;
@@ -8051,10 +7959,11 @@ static bool nested_vmx_exit_handled(stru
/*
* The host physical addresses of some pages of guest memory
- * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
- * may write to these pages via their host physical address while
- * L2 is running, bypassing any address-translation-based dirty
- * tracking (e.g. EPT write protection).
+ * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
+ * Page). The CPU may write to these pages via their host
+ * physical address while L2 is running, bypassing any
+ * address-translation-based dirty tracking (e.g. EPT write
+ * protection).
*
* Mark them dirty on every exit from L2 to prevent them from
* getting out of sync with dirty tracking.
@@ -10223,7 +10132,6 @@ static int nested_vmx_run(struct kvm_vcp
struct vmcs12 *vmcs12;
struct vcpu_vmx *vmx = to_vmx(vcpu);
int cpu;
- struct loaded_vmcs *vmcs02;
bool ia32e;
u32 msr_entry_idx;
@@ -10363,17 +10271,13 @@ static int nested_vmx_run(struct kvm_vcp
* the nested entry.
*/
- vmcs02 = nested_get_current_vmcs02(vmx);
- if (!vmcs02)
- return -ENOMEM;
-
enter_guest_mode(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
cpu = get_cpu();
- vmx->loaded_vmcs = vmcs02;
+ vmx->loaded_vmcs = &vmx->nested.vmcs02;
vmx_vcpu_put(vcpu);
vmx_vcpu_load(vcpu, cpu);
vcpu->cpu = cpu;
@@ -10888,10 +10792,6 @@ static void nested_vmx_vmexit(struct kvm
vm_exit_controls_reset_shadow(vmx);
vmx_segment_cache_clear(vmx);
- /* if no vmcs02 cache requested, remove the one we used */
- if (VMCS02_POOL_SIZE == 0)
- nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
-
load_vmcs12_host_state(vcpu, vmcs12);
/* Update any VMCS fields that might have changed while L2 ran */
Patches currently in stable-queue which might be from jmattson@xxxxxxxxxx are
queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch
queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch
queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch
queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch