Re: [PATCH v2 2/4] arch/x86: Refactor tlbflush and l1d flush

[Kees Cook]

On Mon, Apr 06, 2020 at 01:19:44PM +1000, Balbir Singh wrote:
> Refactor the existing assembly bits into smaller helper functions
> and also abstract L1D_FLUSH into a helper function. Use these
> functions in kvm for L1D flushing.
> 
> Signed-off-by: Balbir Singh <sblbir@xxxxxxxxxx>
> ---
>  arch/x86/include/asm/cacheflush.h |  3 ++
>  arch/x86/kernel/l1d_flush.c       | 49 +++++++++++++++++++++++++++++++
>  arch/x86/kvm/vmx/vmx.c            | 31 ++++---------------
>  3 files changed, 57 insertions(+), 26 deletions(-)
> 
> diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
> index 6419a4cef0e8..66a46db7aadd 100644
> --- a/arch/x86/include/asm/cacheflush.h
> +++ b/arch/x86/include/asm/cacheflush.h
> @@ -10,5 +10,8 @@
>  void clflush_cache_range(void *addr, unsigned int size);
>  void *alloc_l1d_flush_pages(void);
>  void cleanup_l1d_flush_pages(void *l1d_flush_pages);
> +void populate_tlb_with_flush_pages(void *l1d_flush_pages);
> +void flush_l1d_cache_sw(void *l1d_flush_pages);
> +int flush_l1d_cache_hw(void);
>  
>  #endif /* _ASM_X86_CACHEFLUSH_H */
> diff --git a/arch/x86/kernel/l1d_flush.c b/arch/x86/kernel/l1d_flush.c
> index 05f375c33423..60499f773046 100644
> --- a/arch/x86/kernel/l1d_flush.c
> +++ b/arch/x86/kernel/l1d_flush.c
> @@ -34,3 +34,52 @@ void cleanup_l1d_flush_pages(void *l1d_flush_pages)
>  	free_pages((unsigned long)l1d_flush_pages, L1D_CACHE_ORDER);
>  }
>  EXPORT_SYMBOL_GPL(cleanup_l1d_flush_pages);
> +
> +void populate_tlb_with_flush_pages(void *l1d_flush_pages)
> +{
> +	int size = PAGE_SIZE << L1D_CACHE_ORDER;
> +
> +	asm volatile(
> +		/* First ensure the pages are in the TLB */
> +		"xorl	%%eax, %%eax\n"
> +		".Lpopulate_tlb:\n\t"
> +		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
> +		"addl	$4096, %%eax\n\t"
> +		"cmpl	%%eax, %[size]\n\t"
> +		"jne	.Lpopulate_tlb\n\t"
> +		"xorl	%%eax, %%eax\n\t"
> +		"cpuid\n\t"
> +		:: [flush_pages] "r" (l1d_flush_pages),
> +		    [size] "r" (size)
> +		: "eax", "ebx", "ecx", "edx");
> +}
> +EXPORT_SYMBOL_GPL(populate_tlb_with_flush_pages);
> +
> +int flush_l1d_cache_hw(void)
> +{
> +	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
> +		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
> +		return 1;
> +	}
> +	return 0;
> +}

This return value is backwards from the kernel's normal use of "int". I
would expect 0 to mean "success" and non-zero to mean "failure". How
about:

int flush_l1d_cache_hw(void)
{
     if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
             wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
             return 0;
     }
     return -ENOTSUPP;
}


> +EXPORT_SYMBOL_GPL(flush_l1d_cache_hw);
> +
> +void flush_l1d_cache_sw(void *l1d_flush_pages)
> +{
> +	int size = PAGE_SIZE << L1D_CACHE_ORDER;
> +
> +	asm volatile(
> +			/* Fill the cache */
> +			"xorl	%%eax, %%eax\n"
> +			".Lfill_cache:\n"
> +			"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
> +			"addl	$64, %%eax\n\t"
> +			"cmpl	%%eax, %[size]\n\t"
> +			"jne	.Lfill_cache\n\t"
> +			"lfence\n"
> +			:: [flush_pages] "r" (l1d_flush_pages),
> +			[size] "r" (size)
> +			: "eax", "ecx");
> +}
> +EXPORT_SYMBOL_GPL(flush_l1d_cache_sw);
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 209e63798435..29dc5a5bb6ab 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -5956,8 +5956,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu,
>   */
>  static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
>  {
> -	int size = PAGE_SIZE << L1D_CACHE_ORDER;
> -
>  	/*
>  	 * This code is only executed when the the flush mode is 'cond' or
>  	 * 'always'
> @@ -5986,32 +5984,13 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
>  
>  	vcpu->stat.l1d_flush++;
>  
> -	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
> -		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
> +	if (flush_l1d_cache_hw())
>  		return;
> -	}

Then this becomes:

	if (flush_l1d_cache_hw() == 0)
		return;

(Or change it to a "bool" with and use true/false and leave the above
call as-is.)

Either way:

Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>

-Kees

>  
> -	asm volatile(
> -		/* First ensure the pages are in the TLB */
> -		"xorl	%%eax, %%eax\n"
> -		".Lpopulate_tlb:\n\t"
> -		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
> -		"addl	$4096, %%eax\n\t"
> -		"cmpl	%%eax, %[size]\n\t"
> -		"jne	.Lpopulate_tlb\n\t"
> -		"xorl	%%eax, %%eax\n\t"
> -		"cpuid\n\t"
> -		/* Now fill the cache */
> -		"xorl	%%eax, %%eax\n"
> -		".Lfill_cache:\n"
> -		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
> -		"addl	$64, %%eax\n\t"
> -		"cmpl	%%eax, %[size]\n\t"
> -		"jne	.Lfill_cache\n\t"
> -		"lfence\n"
> -		:: [flush_pages] "r" (vmx_l1d_flush_pages),
> -		    [size] "r" (size)
> -		: "eax", "ebx", "ecx", "edx");
> +	preempt_disable();
> +	populate_tlb_with_flush_pages(vmx_l1d_flush_pages);
> +	flush_l1d_cache_sw(vmx_l1d_flush_pages);
> +	preempt_enable();
>  }
>  
>  static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
> -- 
> 2.17.1
> 


-- 
Kees Cook