public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH] x86: make mm/gup.c more virtualization friendly
@ 2008-09-17 15:48 Jan Beulich
  2008-09-18 10:15 ` Ingo Molnar
  2008-09-23  4:42 ` Nick Piggin
  0 siblings, 2 replies; 3+ messages in thread
From: Jan Beulich @ 2008-09-17 15:48 UTC (permalink / raw)
  To: mingo, tglx, hpa; +Cc: Nick Piggin, linux-kernel

Since pte_flags() is much cheaper than pte_val() in some virtualized
environments (namely, Xen), use the former whereever possible.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Cc: Nick Piggin <npiggin@suse.de>

---
 arch/x86/mm/gup.c         |   10 +++++-----
 include/asm-x86/pgtable.h |    2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

--- linux-2.6.27-rc6/arch/x86/mm/gup.c	2008-08-21 14:37:29.000000000 +0200
+++ 2.6.27-rc6-x86-gup-virt/arch/x86/mm/gup.c	2008-09-02 13:33:42.000000000 +0200
@@ -82,7 +82,7 @@ static noinline int gup_pte_range(pmd_t 
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
-		if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
 		}
@@ -116,10 +116,10 @@ static noinline int gup_huge_pmd(pmd_t p
 	mask = _PAGE_PRESENT|_PAGE_USER;
 	if (write)
 		mask |= _PAGE_RW;
-	if ((pte_val(pte) & mask) != mask)
+	if ((pte_flags(pte) & mask) != mask)
 		return 0;
 	/* hugepages are never "special" */
-	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
 	refs = 0;
@@ -173,10 +173,10 @@ static noinline int gup_huge_pud(pud_t p
 	mask = _PAGE_PRESENT|_PAGE_USER;
 	if (write)
 		mask |= _PAGE_RW;
-	if ((pte_val(pte) & mask) != mask)
+	if ((pte_flags(pte) & mask) != mask)
 		return 0;
 	/* hugepages are never "special" */
-	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
 	refs = 0;
--- linux-2.6.27-rc6/include/asm-x86/pgtable.h	2008-08-21 14:37:34.000000000 +0200
+++ 2.6.27-rc6-x86-gup-virt/include/asm-x86/pgtable.h	2008-09-02 13:31:50.000000000 +0200
@@ -183,7 +183,7 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_SPECIAL;
+	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
 static inline int pmd_large(pmd_t pte)




^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] x86: make mm/gup.c more virtualization friendly
  2008-09-17 15:48 [PATCH] x86: make mm/gup.c more virtualization friendly Jan Beulich
@ 2008-09-18 10:15 ` Ingo Molnar
  2008-09-23  4:42 ` Nick Piggin
  1 sibling, 0 replies; 3+ messages in thread
From: Ingo Molnar @ 2008-09-18 10:15 UTC (permalink / raw)
  To: Jan Beulich; +Cc: tglx, hpa, Nick Piggin, linux-kernel, Jeremy Fitzhardinge


* Jan Beulich <jbeulich@novell.com> wrote:

> Since pte_flags() is much cheaper than pte_val() in some virtualized
> environments (namely, Xen), use the former whereever possible.
> 
> Signed-off-by: Jan Beulich <jbeulich@novell.com>
> Cc: Nick Piggin <npiggin@suse.de>

applied to tip/x86/core, thanks Jan.

	Ingo

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] x86: make mm/gup.c more virtualization friendly
  2008-09-17 15:48 [PATCH] x86: make mm/gup.c more virtualization friendly Jan Beulich
  2008-09-18 10:15 ` Ingo Molnar
@ 2008-09-23  4:42 ` Nick Piggin
  1 sibling, 0 replies; 3+ messages in thread
From: Nick Piggin @ 2008-09-23  4:42 UTC (permalink / raw)
  To: Jan Beulich; +Cc: mingo, tglx, hpa, linux-kernel

No objections from me.

On Wed, Sep 17, 2008 at 04:48:17PM +0100, Jan Beulich wrote:
> Since pte_flags() is much cheaper than pte_val() in some virtualized
> environments (namely, Xen), use the former whereever possible.
> 
> Signed-off-by: Jan Beulich <jbeulich@novell.com>
> Cc: Nick Piggin <npiggin@suse.de>
> 
> ---
>  arch/x86/mm/gup.c         |   10 +++++-----
>  include/asm-x86/pgtable.h |    2 +-
>  2 files changed, 6 insertions(+), 6 deletions(-)
> 
> --- linux-2.6.27-rc6/arch/x86/mm/gup.c	2008-08-21 14:37:29.000000000 +0200
> +++ 2.6.27-rc6-x86-gup-virt/arch/x86/mm/gup.c	2008-09-02 13:33:42.000000000 +0200
> @@ -82,7 +82,7 @@ static noinline int gup_pte_range(pmd_t 
>  		pte_t pte = gup_get_pte(ptep);
>  		struct page *page;
>  
> -		if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) {
> +		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
>  			pte_unmap(ptep);
>  			return 0;
>  		}
> @@ -116,10 +116,10 @@ static noinline int gup_huge_pmd(pmd_t p
>  	mask = _PAGE_PRESENT|_PAGE_USER;
>  	if (write)
>  		mask |= _PAGE_RW;
> -	if ((pte_val(pte) & mask) != mask)
> +	if ((pte_flags(pte) & mask) != mask)
>  		return 0;
>  	/* hugepages are never "special" */
> -	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
> +	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
>  	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
>  
>  	refs = 0;
> @@ -173,10 +173,10 @@ static noinline int gup_huge_pud(pud_t p
>  	mask = _PAGE_PRESENT|_PAGE_USER;
>  	if (write)
>  		mask |= _PAGE_RW;
> -	if ((pte_val(pte) & mask) != mask)
> +	if ((pte_flags(pte) & mask) != mask)
>  		return 0;
>  	/* hugepages are never "special" */
> -	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
> +	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
>  	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
>  
>  	refs = 0;
> --- linux-2.6.27-rc6/include/asm-x86/pgtable.h	2008-08-21 14:37:34.000000000 +0200
> +++ 2.6.27-rc6-x86-gup-virt/include/asm-x86/pgtable.h	2008-09-02 13:31:50.000000000 +0200
> @@ -183,7 +183,7 @@ static inline int pte_exec(pte_t pte)
>  
>  static inline int pte_special(pte_t pte)
>  {
> -	return pte_val(pte) & _PAGE_SPECIAL;
> +	return pte_flags(pte) & _PAGE_SPECIAL;
>  }
>  
>  static inline int pmd_large(pmd_t pte)
> 
> 

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2008-09-23  4:43 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-09-17 15:48 [PATCH] x86: make mm/gup.c more virtualization friendly Jan Beulich
2008-09-18 10:15 ` Ingo Molnar
2008-09-23  4:42 ` Nick Piggin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox