From: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
To: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
Cc: akpm-3NddpPZAyC0@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: [PATCH 6/33] KVM: MMU: Use the guest pdptrs instead of mapping cr3 in pae mode
Date: Thu, 04 Jan 2007 15:55:06 -0000 [thread overview]
Message-ID: <20070104155506.3BAD9250048@il.qumranet.com> (raw)
In-Reply-To: <459D21DD.5090506-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
This lets us not write protect a partial page, and is anyway what a
real processor does.
Signed-off-by: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
Index: linux-2.6/drivers/kvm/paging_tmpl.h
===================================================================
--- linux-2.6.orig/drivers/kvm/paging_tmpl.h
+++ linux-2.6/drivers/kvm/paging_tmpl.h
@@ -67,18 +67,28 @@ static void FNAME(walk_addr)(struct gues
hpa_t hpa;
struct kvm_memory_slot *slot;
pt_element_t *ptep;
+ pt_element_t root;
walker->level = vcpu->mmu.root_level;
- walker->table_gfn = (vcpu->cr3 & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+ walker->table = NULL;
+ root = vcpu->cr3;
+#if PTTYPE == 64
+ if (!is_long_mode(vcpu)) {
+ walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
+ root = *walker->ptep;
+ if (!(root & PT_PRESENT_MASK))
+ return;
+ --walker->level;
+ }
+#endif
+ walker->table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
slot = gfn_to_memslot(vcpu->kvm, walker->table_gfn);
- hpa = safe_gpa_to_hpa(vcpu, vcpu->cr3 & PT64_BASE_ADDR_MASK);
+ hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK);
walker->table = kmap_atomic(pfn_to_page(hpa >> PAGE_SHIFT), KM_USER0);
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
(vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) == 0);
- walker->table = (pt_element_t *)( (unsigned long)walker->table |
- (unsigned long)(vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) );
walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
for (;;) {
@@ -89,11 +99,8 @@ static void FNAME(walk_addr)(struct gues
ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
((unsigned long)ptep & PAGE_MASK));
- /* Don't set accessed bit on PAE PDPTRs */
- if (vcpu->mmu.root_level != 3 || walker->level != 3)
- if ((*ptep & (PT_PRESENT_MASK | PT_ACCESSED_MASK))
- == PT_PRESENT_MASK)
- *ptep |= PT_ACCESSED_MASK;
+ if (is_present_pte(*ptep) && !(*ptep & PT_ACCESSED_MASK))
+ *ptep |= PT_ACCESSED_MASK;
if (!is_present_pte(*ptep) ||
walker->level == PT_PAGE_TABLE_LEVEL ||
@@ -116,7 +123,8 @@ static void FNAME(walk_addr)(struct gues
static void FNAME(release_walker)(struct guest_walker *walker)
{
- kunmap_atomic(walker->table, KM_USER0);
+ if (walker->table)
+ kunmap_atomic(walker->table, KM_USER0);
}
static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
Index: linux-2.6/drivers/kvm/kvm_main.c
===================================================================
--- linux-2.6.orig/drivers/kvm/kvm_main.c
+++ linux-2.6/drivers/kvm/kvm_main.c
@@ -1491,6 +1491,8 @@ static int kvm_dev_ioctl_set_sregs(struc
mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
+ if (!is_long_mode(vcpu) && is_pae(vcpu))
+ load_pdptrs(vcpu, vcpu->cr3);
if (mmu_reset_needed)
kvm_mmu_reset_context(vcpu);
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
next prev parent reply other threads:[~2007-01-04 15:55 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-04 15:48 [PATCH 0/33] KVM: MMU: Cache shadow page tables Avi Kivity
2007-01-04 15:50 ` [PATCH 1/33] KVM: MMU: Implement simple reverse mapping Avi Kivity
2007-01-04 16:05 ` [PATCH 16/33] KVM: MMU: kvm_mmu_put_page() only removes one link to the page Avi Kivity
2007-01-04 16:09 ` [PATCH 20/33] KVM: MMU: Handle misaligned accesses to write protected guest page tables Avi Kivity
2007-01-04 16:12 ` [PATCH 23/33] KVM: MMU: If an empty shadow page is not empty, report more info Avi Kivity
[not found] ` <459D21DD.5090506-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-04 15:51 ` [PATCH 2/33] KVM: MMU: Teach the page table walker to track guest page table gfns Avi Kivity
2007-01-04 15:52 ` [PATCH 3/33] KVM: MMU: Load the pae pdptrs on cr3 change like the processor does Avi Kivity
2007-01-04 15:53 ` [PATCH 4/33] KVM: MMU: Fold fetch_guest() into init_walker() Avi Kivity
2007-01-04 15:54 ` [PATCH 5/33] KVM: MU: Special treatment for shadow pae root pages Avi Kivity
2007-01-04 15:55 ` Avi Kivity [this message]
2007-01-04 15:56 ` [PATCH 7/33] KVM: MMU: Make the shadow page tables also special-case pae Avi Kivity
2007-01-04 15:57 ` [PATCH 8/33] KVM: MMU: Make kvm_mmu_alloc_page() return a kvm_mmu_page pointer Avi Kivity
2007-01-04 15:58 ` [PATCH 9/33] KVM: MMU: Shadow page table caching Avi Kivity
2007-01-04 15:59 ` [PATCH 10/33] KVM: MMU: Write protect guest pages when a shadow is created for them Avi Kivity
2007-01-04 16:00 ` [PATCH 11/33] KVM: MMU: Let the walker extract the target page gfn from the pte Avi Kivity
2007-01-04 16:01 ` [PATCH 12/33] KVM: MMU: Support emulated writes into RAM Avi Kivity
2007-01-04 16:02 ` [PATCH 13/33] KVM: MMU: Zap shadow page table entries on writes to guest page tables Avi Kivity
2007-01-04 16:03 ` [PATCH 14/33] KVM: MMU: If emulating an instruction fails, try unprotecting the page Avi Kivity
2007-01-04 16:04 ` [PATCH 15/33] KVM: MMU: Implement child shadow unlinking Avi Kivity
2007-01-04 16:06 ` [PATCH 17/33] KVM: MMU: oom handling Avi Kivity
2007-01-04 16:07 ` [PATCH 18/33] KVM: MMU: Remove invlpg interception Avi Kivity
2007-01-04 16:08 ` [PATCH 19/33] KVM: MMU: Remove release_pt_page_64() Avi Kivity
2007-01-04 16:10 ` [PATCH 21/33] KVM: MMU: <ove is_empty_shadow_page() above kvm_mmu_free_page() Avi Kivity
2007-01-04 16:11 ` [PATCH 22/33] KVM: MMU: Ensure freed shadow pages are clean Avi Kivity
2007-01-04 16:13 ` [PATCH 24/33] KVM: MMU: Page table write flood protection Avi Kivity
2007-01-04 16:14 ` [PATCH 25/33] KVM: MMU: Never free a shadow page actively serving as a root Avi Kivity
2007-01-04 16:15 ` [PATCH 26/33] KVM: MMU: Fix cmpxchg8b emulation Avi Kivity
2007-01-04 16:16 ` [PATCH 27/33] KVM: MMU: Treat user-mode faults as a hint that a page is no longer a page table Avi Kivity
2007-01-04 16:17 ` [PATCH 28/33] KVM: MMU: Free pages on kvm destruction Avi Kivity
2007-01-04 16:18 ` [PATCH 29/33] KVM: MMU: Replace atomic allocations by preallocated objects Avi Kivity
2007-01-04 16:19 ` [PATCH 30/33] KVM: MMU: Detect oom conditions and propagate error to userspace Avi Kivity
2007-01-04 16:20 ` [PATCH 31/33] KVM: MMU: Flush guest tlb when reducing permissions on a pte Avi Kivity
2007-01-04 16:21 ` [PATCH 32/33] KVM: MMU: Destroy mmu while we still have a vcpu left Avi Kivity
2007-01-04 16:22 ` [PATCH 33/33] KVM: MMU: add audit code to check mappings, etc are correct Avi Kivity
2007-01-04 17:22 ` [PATCH 0/33] KVM: MMU: Cache shadow page tables Andrew Morton
[not found] ` <20070104092226.91fa2dfe.akpm-3NddpPZAyC0@public.gmane.org>
2007-01-04 17:41 ` Avi Kivity
[not found] ` <459D3C65.2090703-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-01-04 18:02 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20070104155506.3BAD9250048@il.qumranet.com \
--to=avi-atkuwr5tajbwk0htik3j/w@public.gmane.org \
--cc=akpm-3NddpPZAyC0@public.gmane.org \
--cc=kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox