Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757917AbZDDOiQ (ORCPT ); Sat, 4 Apr 2009 10:38:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756464AbZDDOhM (ORCPT ); Sat, 4 Apr 2009 10:37:12 -0400 Received: from mx2.redhat.com ([66.187.237.31]:35060 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754317AbZDDOhF (ORCPT ); Sat, 4 Apr 2009 10:37:05 -0400 From: Izik Eidus To: akpm@linux-foundation.org Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, avi@redhat.com, aarcange@redhat.com, chrisw@redhat.com, mtosatti@redhat.com, hugh@veritas.com, kamezawa.hiroyu@jp.fujitsu.com, Izik Eidus Subject: [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Date: Sat, 4 Apr 2009 17:35:19 +0300 Message-Id: <1238855722-32606-2-git-send-email-ieidus@redhat.com> In-Reply-To: <1238855722-32606-1-git-send-email-ieidus@redhat.com> References: <1238855722-32606-1-git-send-email-ieidus@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5667 Lines: 164 this macro allow setting the pte in the shadow page tables directly instead of flushing the shadow page table entry and then get vmexit in order to set it. This function is optimzation for kvm/users of mmu_notifiers for COW pages, it is useful for kvm when ksm is used beacuse it allow kvm not to have to recive VMEXIT and only then map the shared page into the mmu shadow pages, but instead map it directly at the same time linux map the page into the host page table. this mmu notifer macro is working by calling to callback that will map directly the physical page into the shadow page tables. (users of mmu_notifiers that didnt implement the set_pte_at_notify() call back will just recive the mmu_notifier_invalidate_page callback) Signed-off-by: Izik Eidus --- include/linux/mmu_notifier.h | 34 ++++++++++++++++++++++++++++++++++ mm/memory.c | 10 ++++++++-- mm/mmu_notifier.c | 20 ++++++++++++++++++++ 3 files changed, 62 insertions(+), 2 deletions(-) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index b77486d..8bb245f 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -61,6 +61,15 @@ struct mmu_notifier_ops { struct mm_struct *mm, unsigned long address); + /* + * change_pte is called in cases that pte mapping into page is changed + * for example when ksm mapped pte to point into a new shared page. + */ + void (*change_pte)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address, + pte_t pte); + /* * Before this is invoked any secondary MMU is still ok to * read/write to the page previously pointed to by the Linux @@ -154,6 +163,8 @@ extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long address); +extern void __mmu_notifier_change_pte(struct mm_struct *mm, + unsigned long address, pte_t pte); extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, @@ -175,6 +186,13 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline void mmu_notifier_change_pte(struct mm_struct *mm, + unsigned long address, pte_t pte) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_change_pte(mm, address, pte); +} + static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address) { @@ -236,6 +254,16 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define set_pte_at_notify(__mm, __address, __ptep, __pte) \ +({ \ + struct mm_struct *___mm = __mm; \ + unsigned long ___address = __address; \ + pte_t ___pte = __pte; \ + \ + set_pte_at(__mm, __address, __ptep, ___pte); \ + mmu_notifier_change_pte(___mm, ___address, ___pte); \ +}) + #else /* CONFIG_MMU_NOTIFIER */ static inline void mmu_notifier_release(struct mm_struct *mm) @@ -248,6 +276,11 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline void mmu_notifier_change_pte(struct mm_struct *mm, + unsigned long address, pte_t pte) +{ +} + static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address) { @@ -273,6 +306,7 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_young_notify ptep_clear_flush_young #define ptep_clear_flush_notify ptep_clear_flush +#define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/mm/memory.c b/mm/memory.c index cf6873e..1e1a14b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2051,9 +2051,15 @@ gotten: * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush_notify(vma, address, page_table); + ptep_clear_flush(vma, address, page_table); page_add_new_anon_rmap(new_page, vma, address); - set_pte_at(mm, address, page_table, entry); + /* + * We call here the notify macro beacuse in cases of using + * secondary mmu page table like kvm shadow page, tables we want + * the new page to be mapped directly into the secondary page + * table + */ + set_pte_at_notify(mm, address, page_table, entry); update_mmu_cache(vma, address, entry); if (old_page) { /* diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 5f4ef02..c3e8779 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -99,6 +99,26 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, return young; } +void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, + pte_t pte) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->change_pte) + mn->ops->change_pte(mn, mm, address, pte); + /* + * some drivers dont have change_pte and therefor we must call + * for invalidate_page in that case + */ + else if (mn->ops->invalidate_page) + mn->ops->invalidate_page(mn, mm, address); + } + rcu_read_unlock(); +} + void __mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address) { -- 1.5.6.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/