Re: [PATCH v6 01/11] x86/virt/tdx: Simplify tdmr_get_pamt_sz()

[Kiryl Shutsemau <kas@kernel.org>]

On Mon, May 25, 2026 at 07:35:05PM -0700, Rick Edgecombe wrote:
> For each memory region that the TDX module might use (called TDMR), three
> separate traditional PAMT allocations are needed. One for each supported
> page size (1GB, 2MB, 4KB). These store information on each page in the
> TDMR. In Linux, they are allocated out of one physically contiguous block,
> in order to more efficiently use some internal TDX module book keeping
> resources. So some simple math is needed to break the single large
> allocation into three smaller allocations for each page size.
> 
> There are some commonalities in the math needed to calculate the base and
> size for each smaller allocation, and so an effort was made to share logic
> across the three. Unfortunately doing this turned out unnaturally tortured,
> with a loop iterating over the three page sizes, only to call into a
> function with cases statement for each page size. In the future Dynamic
> PAMT will add more logic that is special to the 4KB page size, making the
> benefit of the math sharing even more questionable.
> 
> Three is not a very high number, so get rid of the loop and just duplicate
> the small calculation three times. In doing so, setup for future Dynamic
> PAMT changes.
> 
> Since the loop that iterates over it is gone, further simplify the code by
> dropping the array of intermediate size and base storage. Just store the
> values to their final locations. Accept the small complication of having
> to clear tdmr->pamt_4k_base in the error path, so that tdmr_do_pamt_func()
> will not try to operate on the TDMR struct when attempting to free it.
> 
> Assisted-by: GitHub Copilot:claude-opus-4-6 Claude:claude-opus-4-7
> Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>

Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>

Couple of nits below.

> ---
> v6:
>  - Drop {} by moving a comment (Binbin)
>  - Log tweaks
> 
> v4:
>  - Just refer to global var instead of passing pamt_entry_size around
>    (Xiaoyao)
>  - Remove setting pamt_4k_base to zero, because it already is zero.
>    Adjust the comment appropriately (Kai)
> 
> v3:
>  - New patch
> ---
>  arch/x86/virt/vmx/tdx/tdx.c | 93 ++++++++++++-------------------------
>  1 file changed, 29 insertions(+), 64 deletions(-)
> 
> diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
> index 967482ae3c801..487f389f52f4b 100644
> --- a/arch/x86/virt/vmx/tdx/tdx.c
> +++ b/arch/x86/virt/vmx/tdx/tdx.c
> @@ -516,31 +516,21 @@ static __init int fill_out_tdmrs(struct list_head *tmb_list,
>   * Calculate PAMT size given a TDMR and a page size.  The returned
>   * PAMT size is always aligned up to 4K page boundary.
>   */
> -static __init unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz,
> -					     u16 pamt_entry_size)
> +static __init unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz)
>  {
>  	unsigned long pamt_sz, nr_pamt_entries;
> +	const int tdx_pg_size_shift[] = { PAGE_SHIFT, PMD_SHIFT, PUD_SHIFT };
> +	const u16 pamt_entry_size[TDX_PS_NR] = {
> +		tdx_sysinfo.tdmr.pamt_4k_entry_size,
> +		tdx_sysinfo.tdmr.pamt_2m_entry_size,
> +		tdx_sysinfo.tdmr.pamt_1g_entry_size,
> +	};
>  
> -	switch (pgsz) {
> -	case TDX_PS_4K:
> -		nr_pamt_entries = tdmr->size >> PAGE_SHIFT;
> -		break;
> -	case TDX_PS_2M:
> -		nr_pamt_entries = tdmr->size >> PMD_SHIFT;
> -		break;
> -	case TDX_PS_1G:
> -		nr_pamt_entries = tdmr->size >> PUD_SHIFT;
> -		break;
> -	default:
> -		WARN_ON_ONCE(1);
> -		return 0;
> -	}
> +	nr_pamt_entries = tdmr->size >> tdx_pg_size_shift[pgsz];
> +	pamt_sz = nr_pamt_entries * pamt_entry_size[pgsz];
>  
> -	pamt_sz = nr_pamt_entries * pamt_entry_size;
>  	/* TDX requires PAMT size must be 4K aligned */
> -	pamt_sz = ALIGN(pamt_sz, PAGE_SIZE);
> -
> -	return pamt_sz;
> +	return PAGE_ALIGN(pamt_sz);
>  }
>  
>  /*
> @@ -578,28 +568,21 @@ static __init int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_lis
>   * within @tdmr, and set up PAMTs for @tdmr.
>   */
>  static __init int tdmr_set_up_pamt(struct tdmr_info *tdmr,
> -				   struct list_head *tmb_list,
> -				   u16 pamt_entry_size[])
> +				   struct list_head *tmb_list)
>  {
> -	unsigned long pamt_base[TDX_PS_NR];
> -	unsigned long pamt_size[TDX_PS_NR];
> -	unsigned long tdmr_pamt_base;
>  	unsigned long tdmr_pamt_size;
>  	struct page *pamt;
> -	int pgsz, nid;
> -
> +	int nid;

Add a newline here?

>  	nid = tdmr_get_nid(tdmr, tmb_list);
>  
>  	/*
>  	 * Calculate the PAMT size for each TDX supported page size
>  	 * and the total PAMT size.
>  	 */
> -	tdmr_pamt_size = 0;
> -	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
> -		pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz,
> -					pamt_entry_size[pgsz]);
> -		tdmr_pamt_size += pamt_size[pgsz];
> -	}
> +	tdmr->pamt_4k_size = tdmr_get_pamt_sz(tdmr, TDX_PS_4K);
> +	tdmr->pamt_2m_size = tdmr_get_pamt_sz(tdmr, TDX_PS_2M);
> +	tdmr->pamt_1g_size = tdmr_get_pamt_sz(tdmr, TDX_PS_1G);
> +	tdmr_pamt_size = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size;
>  
>  	/*
>  	 * Allocate one chunk of physically contiguous memory for all
> @@ -607,26 +590,18 @@ static __init int tdmr_set_up_pamt(struct tdmr_info *tdmr,
>  	 * in overlapped TDMRs.
>  	 */
>  	pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL,
> -			nid, &node_online_map);
> +				  nid, &node_online_map);
> +

Looks like unrelated whitespace change. Is it intentional?

> +	/*
> +	 * tdmr->pamt_4k_base is still zero so the error
> +	 * path of the caller will skip freeing the pamt.
> +	 */
>  	if (!pamt)
>  		return -ENOMEM;
>  
> -	/*
> -	 * Break the contiguous allocation back up into the
> -	 * individual PAMTs for each page size.
> -	 */
> -	tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT;
> -	for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) {
> -		pamt_base[pgsz] = tdmr_pamt_base;
> -		tdmr_pamt_base += pamt_size[pgsz];
> -	}
> -
> -	tdmr->pamt_4k_base = pamt_base[TDX_PS_4K];
> -	tdmr->pamt_4k_size = pamt_size[TDX_PS_4K];
> -	tdmr->pamt_2m_base = pamt_base[TDX_PS_2M];
> -	tdmr->pamt_2m_size = pamt_size[TDX_PS_2M];
> -	tdmr->pamt_1g_base = pamt_base[TDX_PS_1G];
> -	tdmr->pamt_1g_size = pamt_size[TDX_PS_1G];
> +	tdmr->pamt_4k_base = page_to_phys(pamt);
> +	tdmr->pamt_2m_base = tdmr->pamt_4k_base + tdmr->pamt_4k_size;
> +	tdmr->pamt_1g_base = tdmr->pamt_2m_base + tdmr->pamt_2m_size;
>  
>  	return 0;
>  }
> @@ -657,10 +632,7 @@ static __init void tdmr_do_pamt_func(struct tdmr_info *tdmr,
>  	tdmr_get_pamt(tdmr, &pamt_base, &pamt_size);
>  
>  	/* Do nothing if PAMT hasn't been allocated for this TDMR */
> -	if (!pamt_size)
> -		return;
> -
> -	if (WARN_ON_ONCE(!pamt_base))
> +	if (!pamt_base)
>  		return;
>  
>  	pamt_func(pamt_base, pamt_size);
> @@ -686,14 +658,12 @@ static __init void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list)
>  
>  /* Allocate and set up PAMTs for all TDMRs */
>  static __init int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list,
> -					struct list_head *tmb_list,
> -					u16 pamt_entry_size[])
> +				 struct list_head *tmb_list)
>  {
>  	int i, ret = 0;
>  
>  	for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) {
> -		ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list,
> -				pamt_entry_size);
> +		ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list);
>  		if (ret)
>  			goto err;
>  	}
> @@ -970,18 +940,13 @@ static __init int construct_tdmrs(struct list_head *tmb_list,
>  				  struct tdmr_info_list *tdmr_list,
>  				  struct tdx_sys_info_tdmr *sysinfo_tdmr)
>  {
> -	u16 pamt_entry_size[TDX_PS_NR] = {
> -		sysinfo_tdmr->pamt_4k_entry_size,
> -		sysinfo_tdmr->pamt_2m_entry_size,
> -		sysinfo_tdmr->pamt_1g_entry_size,
> -	};
>  	int ret;
>  
>  	ret = fill_out_tdmrs(tmb_list, tdmr_list);
>  	if (ret)
>  		return ret;
>  
> -	ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, pamt_entry_size);
> +	ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list);
>  	if (ret)
>  		return ret;
>  
> -- 
> 2.54.0
> 

-- 
  Kiryl Shutsemau / Kirill A. Shutemov