Re: [PATCH 2/7] Nested VMX patch 2 implements vmclear

[Gleb Natapov <gleb@redhat.com>]

On Thu, Dec 10, 2009 at 08:38:24PM +0200, oritw@il.ibm.com wrote:
> From: Orit Wasserman <oritw@il.ibm.com>
> 
> ---
>  arch/x86/kvm/vmx.c |  235 +++++++++++++++++++++++++++++++++++++++++++++++++++-
>  arch/x86/kvm/x86.c |    5 +-
>  arch/x86/kvm/x86.h |    3 +
>  3 files changed, 240 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 2726a6c..a7ffd5e 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -93,13 +93,39 @@ struct shared_msr_entry {
>  };
>  
>  struct __attribute__ ((__packed__)) level_state {
> +	/* Has the level1 guest done vmclear? */
> +	bool vmclear;
> +};
> +
> +/*
> + * This structure is mapped to guest memory.
> + * It is packed in order to preseve the binary content
> + * after live migration.
> + * If there are changed in the content or layout the revision_id must be updated.
> + */
> +struct __attribute__ ((__packed__)) nested_vmcs_page {
> +	u32 revision_id;
> +	u32 abort;
> +	struct level_state l2_state;
> +};
> +
> +struct nested_vmcs_list {
> +	struct list_head list;
> +	gpa_t vmcs_addr;
> +	struct vmcs *l2_vmcs;
>  };
>  
>  struct nested_vmx {
>  	/* Has the level1 guest done vmxon? */
>  	bool vmxon;
> +	/* What is the location of the current vmcs l1 keeps for l2 */
> +	gpa_t current_vmptr;
>  	/* Level 1 state for switching to level 2 and back */
>  	struct level_state *l1_state;
> +	/* list of vmcs for each l2 guest created by l1 */
> +	struct list_head l2_vmcs_list;
> +	/* l2 page corresponding to the current vmcs set by l1 */
> +	struct nested_vmcs_page *current_l2_page;
>  };
>  
>  struct vcpu_vmx {
> @@ -156,6 +182,76 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
>  	return container_of(vcpu, struct vcpu_vmx, vcpu);
>  }
>  
> +static struct page *nested_get_page(struct kvm_vcpu *vcpu,
> +				    u64 vmcs_addr)
> +{
> +	struct page *vmcs_page = NULL;
> +
> +	down_read(&current->mm->mmap_sem);
> +	vmcs_page = gfn_to_page(vcpu->kvm, vmcs_addr >> PAGE_SHIFT);
> +	up_read(&current->mm->mmap_sem);
> +
> +	if (is_error_page(vmcs_page)) {
> +		printk(KERN_ERR "%s error allocating page 0x%llx\n",
> +		       __func__, vmcs_addr);
> +		kvm_release_page_clean(vmcs_page);
> +		return NULL;
> +	}
> +
> +	return vmcs_page;
> +
> +}
> +
> +static int nested_map_current(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	struct page *vmcs_page =
> +		nested_get_page(vcpu, vmx->nested.current_vmptr);
> +	struct nested_vmcs_page *mapped_page;
> +
> +	if (vmcs_page == NULL) {
> +		printk(KERN_INFO "%s: failure in nested_get_page\n", __func__);
> +		return 0;
> +	}
> +
> +	if (vmx->nested.current_l2_page) {
> +		printk(KERN_INFO "%s: shadow vmcs already mapped\n", __func__);
> +		WARN_ON(1);
> +		return 0;
> +	}
> +
> +	mapped_page = kmap_atomic(vmcs_page, KM_USER0);
> +
> +	if (!mapped_page) {
> +		printk(KERN_INFO "%s: error in kmap_atomic\n", __func__);
> +		return 0;
> +	}
> +
> +	vmx->nested.current_l2_page = mapped_page;
> +
> +	return 1;
> +}
> +
> +static void nested_unmap_current(struct kvm_vcpu *vcpu)
> +{
> +	struct page *page;
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +
> +	if (!vmx->nested.current_l2_page) {
> +		printk(KERN_INFO "Shadow vmcs already unmapped\n");
> +		WARN_ON(1);
> +		return;
> +	}
> +
> +	page = kmap_atomic_to_page(vmx->nested.current_l2_page);
> +
> +	kunmap_atomic(vmx->nested.current_l2_page, KM_USER0);
> +
> +	kvm_release_page_dirty(page);
> +
> +	vmx->nested.current_l2_page = NULL;
> +}
> +
>  static int init_rmode(struct kvm *kvm);
>  static u64 construct_eptp(unsigned long root_hpa);
>  
> @@ -1144,6 +1240,35 @@ static int nested_vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
>  	return 0;
>  }
>  
> +static int read_guest_vmcs_gpa(struct kvm_vcpu *vcpu, gva_t gva, u64 *gentry)
> +{
> +	int r = 0;
> +	uint size;
> +
> +	*gentry = 0;
> +
> +	if (is_long_mode(vcpu))
> +		size = sizeof(u64);
> +	else
> +		size = sizeof(u32);
> +
> +	r = kvm_read_guest_virt(gva, gentry,
> +				size, vcpu);
> +	if (r) {
> +		printk(KERN_ERR "%s cannot read guest vmcs addr %lx : %d\n",
> +		       __func__, vcpu->arch.regs[VCPU_REGS_RAX], r);
> +		return r;
> +	}
> +
> +	if (!IS_ALIGNED(*gentry, PAGE_SIZE)) {
> +		printk(KERN_DEBUG "%s addr %llx not aligned\n",
> +		       __func__, *gentry);
> +		return 1;
> +	}
> +
> +	return 0;
> +}
> +
>  /*
>   * Writes msr value into into the appropriate "register".
>   * Returns 0 on success, non-0 otherwise.
> @@ -1316,6 +1441,7 @@ static int create_l1_state(struct kvm_vcpu *vcpu)
>  	} else
>  		return 0;
>  
> +	INIT_LIST_HEAD(&(vmx->nested.l2_vmcs_list));
>  	return 0;
>  }
>  
> @@ -1488,15 +1614,35 @@ static void free_vmcs(struct vmcs *vmcs)
>  	free_pages((unsigned long)vmcs, vmcs_config.order);
>  }
>  
> +static void nested_free_current_vmcs(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	struct nested_vmcs_list *list_item, *n;
> +
> +	list_for_each_entry_safe(list_item, n, &vmx->nested.l2_vmcs_list, list)
> +		if (list_item->vmcs_addr == vmx->nested.current_vmptr) {
> +			free_vmcs(list_item->l2_vmcs);
> +			list_del(&(list_item->list));
> +			return;
> +		}
> +}
> +
>  static void free_l1_state(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	struct nested_vmcs_list *list_item, *n;
>  
>  	if (!vmx->nested.l1_state)
>  		return;
>  
>  	kfree(vmx->nested.l1_state);
>  	vmx->nested.l1_state = NULL;
> +
> +	list_for_each_entry_safe(list_item, n, &vmx->nested.l2_vmcs_list,
> +				 list) {
> +		free_vmcs(list_item->l2_vmcs);
> +		list_del(&(list_item->list));
> +	}
>  }
>  
>  
> @@ -3352,6 +3498,93 @@ static int handle_vmx_insn(struct kvm_vcpu *vcpu)
>  	return 1;
>  }
>  
> +static void clear_rflags_cf_zf(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long rflags;
> +	rflags = vmx_get_rflags(vcpu);
> +	rflags &= ~(X86_EFLAGS_CF | X86_EFLAGS_ZF);
> +	vmx_set_rflags(vcpu, rflags);
> +}
> +
> +/*
> + * Decode the memory address (operand) of a vmx instruction according to Table 23-12/23-11
> + * For additional information regarding offset calculation see 3.7.5
> + */
> +static gva_t get_vmx_mem_address(struct kvm_vcpu *vcpu,
> +				 unsigned long exit_qualification,
> +				 u32 vmx_instruction_info)
> +{
> +	int  scaling        = vmx_instruction_info & 3;             /* bits 0:1 scaling */
> +	int  addr_size      = (vmx_instruction_info >> 7) & 7;      /* bits 7:9 address size, 0=16bit, 1=32bit, 2=64bit */
> +	bool is_reg         = vmx_instruction_info & (1u << 10);    /* bit  10  1=register operand, 0= memory */
> +	int  seg_reg        = (vmx_instruction_info >> 15) & 7;     /* bits 15:17 segment register */
> +	int  index_reg      = (vmx_instruction_info >> 18) & 0xf;   /* bits 18:21 index register */
> +	bool index_is_valid = !(vmx_instruction_info & (1u << 22)); /* bit  22 index register validity, 0=valid, 1=invalid */
> +	int  base_reg       = (vmx_instruction_info >> 23) & 0xf;   /* bits 23:26 index register */
> +	bool base_is_valid  = !(vmx_instruction_info & (1u << 27)); /* bit  27 base register validity, 0=valid, 1=invalid */
> +	gva_t addr;
> +
> +	if (is_reg)
> +		return 0;
> +
> +	switch (addr_size) {
> +	case 1:
> +		exit_qualification &= 0xffffffff; /* 32 high bits are undefied according to the spec, page 23-7 */
> +		break;
> +	case 2:
> +		break;
> +	default:
> +		return 0;
> +	}
> +
> +	/* Addr = segment_base + offset */
> +	/* offfset = Base + [Index * Scale] + Displacement, see Figure 3-11 */
> +	addr = vmx_get_segment_base(vcpu, seg_reg);
> +	if (base_is_valid)
> +		addr += kvm_register_read(vcpu, base_reg);
> +	if (index_is_valid)
> +		addr += kvm_register_read(vcpu, index_reg)*scaling;
> +	addr += exit_qualification; /* exit qualification holds the displacement, spec page 23-7 */
> +
> +	return addr;
> +}
> +
> +static int handle_vmclear(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vmx *vmx = to_vmx(vcpu);
> +	struct level_state *l2_state;
> +	gpa_t guest_vmcs_addr;
> +	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
> +	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
> +	gva_t vmcs_gva;
> +
> +	if (!nested_vmx_check_permission(vcpu))
> +		return 1;
> +
> +	vmcs_gva = get_vmx_mem_address(vcpu, exit_qualification,
> +				       vmx_instruction_info);
> +
> +	if (read_guest_vmcs_gpa(vcpu, vmcs_gva, &guest_vmcs_addr))
> +		return 1;
> +
Should check that vmcs address is 4K aligned and given address is not equal
to vmxon pointer.

> +	vmx->nested.current_vmptr = guest_vmcs_addr;
vmclear doesn't change current vmcs pointer.

> +	if (!nested_map_current(vcpu))
> +		return 1;
> +
> +	l2_state = &(to_vmx(vcpu)->nested.current_l2_page->l2_state);
> +	l2_state->vmclear = 1;
> +	nested_free_current_vmcs(vcpu);
> +
> +	vmx->nested.current_vmptr = -1ull;
> +
vmclear reset current vmcs pointer to -1 only if it was called with
current vmcs pointer as an argument.

> +	nested_unmap_current(vcpu);
> +
> +	skip_emulated_instruction(vcpu);
> +	clear_rflags_cf_zf(vcpu);
> +
> +	return 1;
> +}
> +
>  static int handle_vmoff(struct kvm_vcpu *vcpu)
>  {
>  	struct vcpu_vmx *vmx = to_vmx(vcpu);
> @@ -3695,7 +3928,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
>  	[EXIT_REASON_HLT]                     = handle_halt,
>  	[EXIT_REASON_INVLPG]		      = handle_invlpg,
>  	[EXIT_REASON_VMCALL]                  = handle_vmcall,
> -	[EXIT_REASON_VMCLEAR]	              = handle_vmx_insn,
> +	[EXIT_REASON_VMCLEAR]	              = handle_vmclear,
>  	[EXIT_REASON_VMLAUNCH]                = handle_vmx_insn,
>  	[EXIT_REASON_VMPTRLD]                 = handle_vmx_insn,
>  	[EXIT_REASON_VMPTRST]                 = handle_vmx_insn,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index b698952..e5acf22 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -2773,8 +2773,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
>  	return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v);
>  }
>  
> -static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
> -			       struct kvm_vcpu *vcpu)
> +int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
> +			struct kvm_vcpu *vcpu)
>  {
>  	void *data = val;
>  	int r = X86EMUL_CONTINUE;
> @@ -2802,6 +2802,7 @@ static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
>  out:
>  	return r;
>  }
> +EXPORT_SYMBOL_GPL(kvm_read_guest_virt);
>  
>  static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
>  				struct kvm_vcpu *vcpu)
> diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> index 57204cb..2d7b2dc 100644
> --- a/arch/x86/kvm/x86.h
> +++ b/arch/x86/kvm/x86.h
> @@ -35,6 +35,9 @@ static inline bool kvm_exception_is_soft(unsigned int nr)
>  struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
>                                               u32 function, u32 index);
>  
> +int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
> +			struct kvm_vcpu *vcpu);
> +
>  extern int nested;
>  
>  #endif
> -- 
> 1.6.0.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
			Gleb.