From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AH8x227bD4rn/vppv/rEFxIb8nJ3aAC5MapDL5y3x7U9YVAwtr3BvxB0oYLHtkWvbRLGdhFjBx0u ARC-Seal: i=1; a=rsa-sha256; t=1518183839; cv=none; d=google.com; s=arc-20160816; b=etSPhxCjGPrZ/Db71i60n+TaxYcGmx/RDjjIcX7qOymklDr48Xw5Bqoe+oeFYnPOIx 9f+RuOhSQv/J5zwO5riRqTWLOLEQ5MxMaum1JPeW0sgQR3CPDxR87N90tpP9FV+We52d l38FtxEyWjMUlr+KjaBbSN4IkK5jJAZElXO1Y3qWL2BGVzz6oR1zBuuPxss4kOREyZAd 19DY0YevJR1dsa9beq5LLAYx+buLtaAsH+Su1c0hWl7s/FvbivFuzgevcoA0ZgCbklQU xwHFRupLTcQec3vAZcAj2hmmw+p3IlHOW+Uo5T6yLUgDYsOz0zYJrNkhAlThZTjdu22S ke9g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=mime-version:user-agent:references:in-reply-to:message-id:date :subject:cc:to:from:arc-authentication-results; bh=u6Zj8wxBZbp0QXclzbgRAUlb1KBlpAsB3+2AqZS87Ek=; b=wQtDpnKepPHOsjaFXaz9jAxr/c8A7xVEGvtTtVEf3i/PgWoHkuMbMd+R6MrCthvT2n bnpWwHneeF3aHC2IZpg9znQVigxD2/mR0KGRf+7qg3ophx+h7q/4LsGlKAiXchBP0QkP Ke1qIg4Xqmzp+y7lTbuuE/MLYs0TvO/CDnrIHQVns8+oba0hn9vpfYfB3KXpB4hIGDFz ev1+QJ6HuciTRfMLPE49gcQafHeio4pUhobZdVBG1l6vOyAdv6b/H7tzsEshr9fcb9AC bzbkADU9R/HWunmxf4Yjlpc7MFTvofJhdH9WqWX24knDIZ52vBQdw/ndzw8OHGbBdbs+ LulQ== ARC-Authentication-Results: i=1; mx.google.com; spf=softfail (google.com: domain of transitioning gregkh@linuxfoundation.org does not designate 90.92.71.90 as permitted sender) smtp.mailfrom=gregkh@linuxfoundation.org Authentication-Results: mx.google.com; spf=softfail (google.com: domain of transitioning gregkh@linuxfoundation.org does not designate 90.92.71.90 as permitted sender) smtp.mailfrom=gregkh@linuxfoundation.org From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Jim Mattson , Mark Kanda , Ameya More , David Hildenbrand , Paolo Bonzini , =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= , David Woodhouse Subject: [PATCH 4.9 79/92] KVM: nVMX: Eliminate vmcs02 pool Date: Fri, 9 Feb 2018 14:39:48 +0100 Message-Id: <20180209133936.891018935@linuxfoundation.org> X-Mailer: git-send-email 2.16.1 In-Reply-To: <20180209133931.211869118@linuxfoundation.org> References: <20180209133931.211869118@linuxfoundation.org> User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-LABELS: =?utf-8?b?IlxcU2VudCI=?= X-GMAIL-THRID: =?utf-8?q?1591931138070351113?= X-GMAIL-MSGID: =?utf-8?q?1591931138070351113?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Jim Mattson (cherry picked from commit de3a0021a60635de96aa92713c1a31a96747d72c) 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@vger.kernel.org # prereq for Spectre mitigation Signed-off-by: Jim Mattson Signed-off-by: Mark Kanda Reviewed-by: Ameya More Reviewed-by: David Hildenbrand Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- 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 @@ -174,7 +174,6 @@ 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; @@ -208,7 +207,7 @@ 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). @@ -387,13 +386,6 @@ 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. @@ -420,15 +412,15 @@ 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; @@ -6678,94 +6670,6 @@ 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". @@ -7078,6 +6982,12 @@ 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); @@ -7100,9 +7010,6 @@ 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; @@ -7120,6 +7027,9 @@ out_cached_vmcs12: free_page((unsigned long)vmx->nested.msr_bitmap); out_msr_bitmap: + free_loaded_vmcs(&vmx->nested.vmcs02); + +out_vmcs02: return -ENOMEM; } @@ -7205,7 +7115,7 @@ 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; @@ -7221,7 +7131,7 @@ 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 */ @@ -7255,8 +7165,6 @@ 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; @@ -8045,10 +7953,11 @@ 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. @@ -10212,7 +10121,6 @@ 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; @@ -10352,17 +10260,13 @@ 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; @@ -10877,10 +10781,6 @@ 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 */