Re: [PATCH v2 2/6] x86/tdx: Support vmalloc() for tdx_enc_status_changed()

[Zhi Wang]

On Tue,  6 Dec 2022 16:33:21 -0800
Dexuan Cui <decui@xxxxxxxxxxxxx> wrote:

> When a TDX guest runs on Hyper-V, the hv_netvsc driver's
> netvsc_init_buf() allocates buffers using vzalloc(), and needs to share
> the buffers with the host OS by calling set_memory_decrypted(), which is
> not working for vmalloc() yet. Add the support by handling the pages one
> by one.
> 

It seems calling set_memory_decrypted() in netvsc_init_buf() is missing in
this patch series. I guess there should be another one extra patch to cover
that.

> Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
> 
> ---
> 
> Changes in v2:
>   Changed tdx_enc_status_changed() in place.
>   
> Hi, Dave, I checked the huge vmalloc mapping code, but still don't know
> how to get the underlying huge page info (if huge page is in use) and
> try to use PG_LEVEL_2M/1G in try_accept_page() for vmalloc: I checked
> is_vm_area_hugepages() and  __vfree() -> __vunmap(), and I think the
> underlying page allocation info is internal to the mm code, and there
> is no mm API to for me get the info in tdx_enc_status_changed().
> 
> Hi, Kirill, the load_unaligned_zeropad() issue is not addressed in
> this patch. The issue looks like a generic issue that also happens to
> AMD SNP vTOM mode and C-bit mode. Will need to figure out how to
> address the issue. If we decide to adjust direct mapping to have the
> shared bit set, it lools like we need to do the below for each
> 'start_va' vmalloc page:
>   pa = slow_virt_to_phys(start_va);
>   set_memory_decrypted(phys_to_virt(pa), 1); -- this line calls
> tdx_enc_status_changed() the second time for the page, which is bad.
> It looks like we need to find a way to reuse the cpa_flush() related
> code in __set_memory_enc_pgtable() and make sure we call
> tdx_enc_status_changed() only once for a vmalloc page?
> 
>   
>  arch/x86/coco/tdx/tdx.c | 69 ++++++++++++++++++++++++++---------------
>  1 file changed, 44 insertions(+), 25 deletions(-)
> 
> diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
> index cdeda698d308..795ac56f06b8 100644
> --- a/arch/x86/coco/tdx/tdx.c
> +++ b/arch/x86/coco/tdx/tdx.c
> @@ -5,6 +5,7 @@
>  #define pr_fmt(fmt)     "tdx: " fmt
>  
>  #include <linux/cpufeature.h>
> +#include <linux/mm.h>
>  #include <asm/coco.h>
>  #include <asm/tdx.h>
>  #include <asm/vmx.h>
> @@ -693,6 +694,34 @@ static bool try_accept_one(phys_addr_t *start,
> unsigned long len, return true;
>  }
>  
> +static bool try_accept_page(phys_addr_t start, phys_addr_t end)
> +{
> +	/*
> +	 * For shared->private conversion, accept the page using
> +	 * TDX_ACCEPT_PAGE TDX module call.
> +	 */
> +	while (start < end) {
> +		unsigned long len = end - start;
> +
> +		/*
> +		 * Try larger accepts first. It gives chance to VMM to
> keep
> +		 * 1G/2M SEPT entries where possible and speeds up
> process by
> +		 * cutting number of hypercalls (if successful).
> +		 */
> +
> +		if (try_accept_one(&start, len, PG_LEVEL_1G))
> +			continue;
> +
> +		if (try_accept_one(&start, len, PG_LEVEL_2M))
> +			continue;
> +
> +		if (!try_accept_one(&start, len, PG_LEVEL_4K))
> +			return false;
> +	}
> +
> +	return true;
> +}
> +
>  /*
>   * Notify the VMM about page mapping conversion. More info about ABI
>   * can be found in TDX Guest-Host-Communication Interface (GHCI),
> @@ -749,37 +778,27 @@ static bool tdx_map_gpa(phys_addr_t start,
> phys_addr_t end, bool enc) */
>  static bool tdx_enc_status_changed(unsigned long vaddr, int numpages,
> bool enc) {
> -	phys_addr_t start = __pa(vaddr);
> -	phys_addr_t end   = __pa(vaddr + numpages * PAGE_SIZE);
> +	bool is_vmalloc = is_vmalloc_addr((void *)vaddr);
> +	unsigned long len = numpages * PAGE_SIZE;
> +	void *start_va = (void *)vaddr, *end_va = start_va + len;
> +	phys_addr_t start_pa, end_pa;
>  
> -	if (!tdx_map_gpa(start, end, enc))
> +	if (offset_in_page(start_va) != 0)
>  		return false;
>  
> -	/* private->shared conversion  requires only MapGPA call */
> -	if (!enc)
> -		return true;
> -
> -	/*
> -	 * For shared->private conversion, accept the page using
> -	 * TDX_ACCEPT_PAGE TDX module call.
> -	 */
> -	while (start < end) {
> -		unsigned long len = end - start;
> -
> -		/*
> -		 * Try larger accepts first. It gives chance to VMM to
> keep
> -		 * 1G/2M SEPT entries where possible and speeds up
> process by
> -		 * cutting number of hypercalls (if successful).
> -		 */
> -
> -		if (try_accept_one(&start, len, PG_LEVEL_1G))
> -			continue;
> +	while (start_va < end_va) {
> +		start_pa = is_vmalloc ? slow_virt_to_phys(start_va) :
> +					__pa(start_va);
> +		end_pa = start_pa + (is_vmalloc ? PAGE_SIZE : len);
>  
> -		if (try_accept_one(&start, len, PG_LEVEL_2M))
> -			continue;
> +		if (!tdx_map_gpa(start_pa, end_pa, enc))
> +			return false;
>  
> -		if (!try_accept_one(&start, len, PG_LEVEL_4K))
> +		/* private->shared conversion requires only MapGPA call
> */
> +		if (enc && !try_accept_page(start_pa, end_pa))
>  			return false;
> +
> +		start_va += is_vmalloc ? PAGE_SIZE : len;
>  	}
>  
>  	return true;