Zachary Amsden
2007-Apr-18 13:02 UTC
[PATCH 1/4] Pte drop ptep_get_and_clear paravirt op.patch
In shadow mode hypervisors, ptep_get_and_clear achieves the desired purpose of keeping the shadows in sync by issuing a native_get_and_clear, followed by a call to pte_update, which indicates the PTE has been modified. Direct mode hypervisors (Xen) have no need for this anyway, and will trap the update using writable pagetables. This means no hypervisor makes use of ptep_get_and_clear; there is no reason to have it in the paravirt-ops structure. Change confusing terminology about raw vs. native functions into consistent use of native_pte_xxx for operations which do not invoke paravirt-ops. Signed-off-by: Zachary Amsden <zach@vmware.com> diff -r c02c6f5e882c arch/i386/kernel/paravirt.c --- a/arch/i386/kernel/paravirt.c Wed Apr 11 16:25:09 2007 -0700 +++ b/arch/i386/kernel/paravirt.c Wed Apr 11 17:09:55 2007 -0700 @@ -315,8 +315,6 @@ struct paravirt_ops paravirt_ops = { .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, - .ptep_get_and_clear = native_ptep_get_and_clear, - #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = kmap_atomic, #endif diff -r c02c6f5e882c include/asm-i386/paravirt.h --- a/include/asm-i386/paravirt.h Wed Apr 11 16:25:09 2007 -0700 +++ b/include/asm-i386/paravirt.h Wed Apr 11 17:12:03 2007 -0700 @@ -187,8 +187,6 @@ struct paravirt_ops void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void (*pte_update_defer)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - - pte_t (*ptep_get_and_clear)(pte_t *ptep); #ifdef CONFIG_HIGHPTE void *(*kmap_atomic_pte)(struct page *page, enum km_type type); @@ -859,12 +857,8 @@ static inline void pmd_clear(pmd_t *pmdp PVOP_VCALL1(pmd_clear, pmdp); } -static inline pte_t raw_ptep_get_and_clear(pte_t *p) -{ - unsigned long long val = PVOP_CALL1(unsigned long long, ptep_get_and_clear, p); - return (pte_t) { val, val >> 32 }; -} #else /* !CONFIG_X86_PAE */ + static inline pte_t __pte(unsigned long val) { return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) }; @@ -899,11 +893,6 @@ static inline void set_pmd(pmd_t *pmdp, static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval) { PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd); -} - -static inline pte_t raw_ptep_get_and_clear(pte_t *p) -{ - return (pte_t) { PVOP_CALL1(unsigned long, ptep_get_and_clear, p) }; } #endif /* CONFIG_X86_PAE */ diff -r c02c6f5e882c include/asm-i386/pgtable.h --- a/include/asm-i386/pgtable.h Wed Apr 11 16:25:09 2007 -0700 +++ b/include/asm-i386/pgtable.h Wed Apr 11 17:11:22 2007 -0700 @@ -265,8 +265,6 @@ static inline pte_t pte_mkhuge(pte_t pte */ #define pte_update(mm, addr, ptep) do { } while (0) #define pte_update_defer(mm, addr, ptep) do { } while (0) - -#define raw_ptep_get_and_clear(xp) native_ptep_get_and_clear(xp) #endif /* @@ -340,7 +338,7 @@ do { \ #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_t pte = raw_ptep_get_and_clear(ptep); + pte_t pte = native_ptep_get_and_clear(ptep); pte_update(mm, addr, ptep); return pte; }
Jeremy Fitzhardinge
2007-Apr-18 13:02 UTC
[PATCH 1/4] Pte drop ptep_get_and_clear paravirt op.patch
Zachary Amsden wrote:> In shadow mode hypervisors, ptep_get_and_clear achieves the desired > purpose of keeping the shadows in sync by issuing a native_get_and_clear, > followed by a call to pte_update, which indicates the PTE has been > modified. > > Direct mode hypervisors (Xen) have no need for this anyway, and will trap > the update using writable pagetables. > > This means no hypervisor makes use of ptep_get_and_clear; there is no > reason to have it in the paravirt-ops structure. Change confusing > terminology about raw vs. native functions into consistent use of > native_pte_xxx for operations which do not invoke paravirt-ops. >Looks OK to me. Are you going to put this into the pvops queue? Acked-by: Jeremy Fitzhardinge <jeremy@xensource.com> J
Jeremy Fitzhardinge
2007-Apr-18 13:02 UTC
[PATCH 1/4] Pte drop ptep_get_and_clear paravirt op.patch
Zachary Amsden wrote:> In shadow mode hypervisors, ptep_get_and_clear achieves the desired > purpose of keeping the shadows in sync by issuing a native_get_and_clear, > followed by a call to pte_update, which indicates the PTE has been > modified. > > Direct mode hypervisors (Xen) have no need for this anyway, and will trap > the update using writable pagetables. >Jan Beulich just posted a patch for Xen/linux which specialzes ptep_get_and_clear, which apparently improves kernel-compile performance by 25-30% on some configurations. I think we'll want to keep this. J
Reasonably Related Threads
- [PATCH 1/4] Pte drop ptep_get_and_clear paravirt op.patch
- [PATCH 3/5] Fix missing pte update.patch
- [PATCH 3/5] Fix missing pte update.patch
- [PATCH] x86/paravirt: remove no longer used paravirt functions
- [PATCH] x86/paravirt: remove no longer used paravirt functions