From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759541AbYAAPyP (ORCPT ); Tue, 1 Jan 2008 10:54:15 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755421AbYAAPhO (ORCPT ); Tue, 1 Jan 2008 10:37:14 -0500 Received: from il.qumranet.com ([82.166.9.18]:33801 "EHLO il.qumranet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755125AbYAAPg3 (ORCPT ); Tue, 1 Jan 2008 10:36:29 -0500 From: Avi Kivity To: linux-kernel@vger.kernel.org, kvm-devel@lists.sourceforge.net Cc: Marcelo Tosatti Subject: [PATCH 41/54] KVM: MMU: Use cmpxchg for pte updates on walk_addr() Date: Tue, 1 Jan 2008 17:36:07 +0200 Message-Id: <1199201780-14001-42-git-send-email-avi@qumranet.com> X-Mailer: git-send-email 1.5.3.7 In-Reply-To: <1199201780-14001-1-git-send-email-avi@qumranet.com> References: <1199201780-14001-1-git-send-email-avi@qumranet.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Marcelo Tosatti In preparation for multi-threaded guest pte walking, use cmpxchg() when updating guest pte's. This guarantees that the assignment of the dirty bit can't be lost if two CPU's are faulting the same address simultaneously. [avi: fix kunmap_atomic() parameters] Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- drivers/kvm/paging_tmpl.h | 36 ++++++++++++++++++++++++++++++++++-- 1 files changed, 34 insertions(+), 2 deletions(-) diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h index 3c40a59..8086f82 100644 --- a/drivers/kvm/paging_tmpl.h +++ b/drivers/kvm/paging_tmpl.h @@ -34,7 +34,9 @@ #define PT_LEVEL_BITS PT64_LEVEL_BITS #ifdef CONFIG_X86_64 #define PT_MAX_FULL_LEVELS 4 + #define CMPXCHG cmpxchg #else + #define CMPXCHG cmpxchg64 #define PT_MAX_FULL_LEVELS 2 #endif #elif PTTYPE == 32 @@ -48,6 +50,7 @@ #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level) #define PT_LEVEL_BITS PT32_LEVEL_BITS #define PT_MAX_FULL_LEVELS 2 + #define CMPXCHG cmpxchg #else #error Invalid PTTYPE value #endif @@ -78,6 +81,26 @@ static gfn_t gpte_to_gfn_pde(pt_element_t gpte) return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; } +static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, + gfn_t table_gfn, unsigned index, + pt_element_t orig_pte, pt_element_t new_pte) +{ + pt_element_t ret; + pt_element_t *table; + struct page *page; + + page = gfn_to_page(kvm, table_gfn); + table = kmap_atomic(page, KM_USER0); + + ret = CMPXCHG(&table[index], orig_pte, new_pte); + + kunmap_atomic(table, KM_USER0); + + kvm_release_page_dirty(page); + + return (ret != orig_pte); +} + /* * Fetch a guest pte for a guest virtual address */ @@ -91,6 +114,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, gpa_t pte_gpa; pgprintk("%s: addr %lx\n", __FUNCTION__, addr); +walk: walker->level = vcpu->mmu.root_level; pte = vcpu->cr3; #if PTTYPE == 64 @@ -135,8 +159,10 @@ static int FNAME(walk_addr)(struct guest_walker *walker, if (!(pte & PT_ACCESSED_MASK)) { mark_page_dirty(vcpu->kvm, table_gfn); + if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, + index, pte, pte|PT_ACCESSED_MASK)) + goto walk; pte |= PT_ACCESSED_MASK; - kvm_write_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); } if (walker->level == PT_PAGE_TABLE_LEVEL) { @@ -159,9 +185,14 @@ static int FNAME(walk_addr)(struct guest_walker *walker, } if (write_fault && !is_dirty_pte(pte)) { + bool ret; + mark_page_dirty(vcpu->kvm, table_gfn); + ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte, + pte|PT_DIRTY_MASK); + if (ret) + goto walk; pte |= PT_DIRTY_MASK; - kvm_write_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte)); } @@ -484,3 +515,4 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, #undef PT_MAX_FULL_LEVELS #undef gpte_to_gfn #undef gpte_to_gfn_pde +#undef CMPXCHG -- 1.5.3.7