Re: lmbench lat_mmap slowdown with CONFIG_PARAVIRT

[Zachary Amsden <zach@vmware.com>]

[-- Attachment #1: Type: text/plain, Size: 650 bytes --]

On Thu, 2009-01-22 at 15:04 -0800, Ingo Molnar wrote:
> * Jeremy Fitzhardinge <jeremy@goop.org> wrote:

> In any case, it is rather inefficient of me proxy-testing your patches, 
> you can do these measurements yourself too on any Core2 or later Intel 
> CPU, by running tip/master plus picking up these two utilities:

Eek, I have no time to spend on this right now, but if anyone is curious
to run this patch (which heavily breaks Xen), I suspect it will cure
most of the performance ailments.

Back when we did the VMI prototyping, we never saw any significant
benchmark reductions until the introduction of the M-to-P conversion
functions.

Zach

[-- Attachment #2: paravirt-drop-mpn-ops.patch --]
[-- Type: text/x-patch, Size: 4338 bytes --]

diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index e9873a2..e5b39db 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -155,10 +155,6 @@ static inline pteval_t native_pte_flags(pte_t pte)
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else  /* !CONFIG_PARAVIRT */
-
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)
 
@@ -176,6 +172,8 @@ static inline pteval_t native_pte_flags(pte_t pte)
 #define pte_flags(x)	native_pte_flags(x)
 #define __pte(x)	native_make_pte(x)
 
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
 #endif	/* CONFIG_PARAVIRT */
 
 #define __pa(x)		__phys_addr((unsigned long)(x))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ba3e2ff..7de3169 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -278,13 +278,6 @@ struct pv_mmu_ops {
 	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
 					pte_t *ptep, pte_t pte);
 
-	pteval_t (*pte_val)(pte_t);
-	pteval_t (*pte_flags)(pte_t);
-	pte_t (*make_pte)(pteval_t pte);
-
-	pgdval_t (*pgd_val)(pgd_t);
-	pgd_t (*make_pgd)(pgdval_t pgd);
-
 #if PAGETABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
 	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
@@ -298,13 +291,7 @@ struct pv_mmu_ops {
 
 	void (*set_pud)(pud_t *pudp, pud_t pudval);
 
-	pmdval_t (*pmd_val)(pmd_t);
-	pmd_t (*make_pmd)(pmdval_t pmd);
-
 #if PAGETABLE_LEVELS == 4
-	pudval_t (*pud_val)(pud_t);
-	pud_t (*make_pud)(pudval_t pud);
-
 	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
 #endif	/* PAGETABLE_LEVELS == 4 */
 #endif	/* PAGETABLE_LEVELS >= 3 */
@@ -1054,81 +1041,6 @@ static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
 	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
 }
 
-static inline pte_t __pte(pteval_t val)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val);
-
-	return (pte_t) { .pte = ret };
-}
-
-static inline pteval_t pte_val(pte_t pte)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte);
-
-	return ret;
-}
-
-static inline pteval_t pte_flags(pte_t pte)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte);
-
-#ifdef CONFIG_PARAVIRT_DEBUG
-	BUG_ON(ret & PTE_PFN_MASK);
-#endif
-	return ret;
-}
-
-static inline pgd_t __pgd(pgdval_t val)
-{
-	pgdval_t ret;
-
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
-				 val);
-
-	return (pgd_t) { ret };
-}
-
-static inline pgdval_t pgd_val(pgd_t pgd)
-{
-	pgdval_t ret;
-
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd, (u64)pgd.pgd >> 32);
-	else
-		ret =  PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd);
-
-	return ret;
-}
-
 #define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
 static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 					   pte_t *ptep)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb6..ac48a2d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -424,23 +424,12 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.pmd_clear = native_pmd_clear,
 #endif
 	.set_pud = native_set_pud,
-	.pmd_val = native_pmd_val,
-	.make_pmd = native_make_pmd,
 
 #if PAGETABLE_LEVELS == 4
-	.pud_val = native_pud_val,
-	.make_pud = native_make_pud,
 	.set_pgd = native_set_pgd,
 #endif
 #endif /* PAGETABLE_LEVELS >= 3 */
 
-	.pte_val = native_pte_val,
-	.pte_flags = native_pte_flags,
-	.pgd_val = native_pgd_val,
-
-	.make_pte = native_make_pte,
-	.make_pgd = native_make_pgd,
-
 	.dup_mmap = paravirt_nop,
 	.exit_mmap = paravirt_nop,
 	.activate_mm = paravirt_nop,