From: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
To: gleb@redhat.com
Cc: avi.kivity@gmail.com, mtosatti@redhat.com, pbonzini@redhat.com,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Subject: [PATCH v2 08/15] KVM: MMU: introduce nulls desc
Date: Thu, 5 Sep 2013 18:29:11 +0800 [thread overview]
Message-ID: <1378376958-27252-9-git-send-email-xiaoguangrong@linux.vnet.ibm.com> (raw)
In-Reply-To: <1378376958-27252-1-git-send-email-xiaoguangrong@linux.vnet.ibm.com>
It likes nulls list and we use the pte-list as the nulls which can help us to
detect whether the "desc" is moved to anther rmap then we can re-walk the rmap
if that happened
kvm->slots_lock is held when we do lockless walking that prevents rmap
is reused (free rmap need to hold that lock) so that we can not see the same
nulls used on different rmaps
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
---
arch/x86/kvm/mmu.c | 35 +++++++++++++++++++++++++++++------
1 file changed, 29 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 08fb4e2..c5f1b27 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -913,6 +913,24 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
return level - 1;
}
+static void desc_mark_nulls(unsigned long *pte_list, struct pte_list_desc *desc)
+{
+ unsigned long marker;
+
+ marker = (unsigned long)pte_list | 1UL;
+ desc->more = (struct pte_list_desc *)marker;
+}
+
+static bool desc_is_a_nulls(struct pte_list_desc *desc)
+{
+ return (unsigned long)desc & 1;
+}
+
+static unsigned long *desc_get_nulls_value(struct pte_list_desc *desc)
+{
+ return (unsigned long *)((unsigned long)desc & ~1);
+}
+
static int __find_first_free(struct pte_list_desc *desc)
{
int i;
@@ -951,7 +969,7 @@ static int count_spte_number(struct pte_list_desc *desc)
first_free = __find_first_free(desc);
- for (desc_num = 0; desc->more; desc = desc->more)
+ for (desc_num = 0; !desc_is_a_nulls(desc->more); desc = desc->more)
desc_num++;
return first_free + desc_num * PTE_LIST_EXT;
@@ -985,6 +1003,7 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
desc = mmu_alloc_pte_list_desc(vcpu);
desc->sptes[0] = (u64 *)*pte_list;
desc->sptes[1] = spte;
+ desc_mark_nulls(pte_list, desc);
*pte_list = (unsigned long)desc | 1;
return 1;
}
@@ -1030,7 +1049,7 @@ pte_list_desc_remove_entry(unsigned long *pte_list,
/*
* Only one entry existing but still use a desc to store it?
*/
- WARN_ON(!next_desc);
+ WARN_ON(desc_is_a_nulls(next_desc));
mmu_free_pte_list_desc(first_desc);
*pte_list = (unsigned long)next_desc | 1ul;
@@ -1041,7 +1060,7 @@ pte_list_desc_remove_entry(unsigned long *pte_list,
* Only one entry in this desc, move the entry to the head
* then the desc can be freed.
*/
- if (!first_desc->sptes[1] && !first_desc->more) {
+ if (!first_desc->sptes[1] && desc_is_a_nulls(first_desc->more)) {
*pte_list = (unsigned long)first_desc->sptes[0];
mmu_free_pte_list_desc(first_desc);
}
@@ -1070,7 +1089,7 @@ static void pte_list_remove(u64 *spte, unsigned long *pte_list)
rmap_printk("pte_list_remove: %p many->many\n", spte);
desc = (struct pte_list_desc *)(*pte_list & ~1ul);
- while (desc) {
+ while (!desc_is_a_nulls(desc)) {
for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
if (desc->sptes[i] == spte) {
pte_list_desc_remove_entry(pte_list,
@@ -1097,11 +1116,13 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
return fn((u64 *)*pte_list);
desc = (struct pte_list_desc *)(*pte_list & ~1ul);
- while (desc) {
+ while (!desc_is_a_nulls(desc)) {
for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
fn(desc->sptes[i]);
desc = desc->more;
}
+
+ WARN_ON(desc_get_nulls_value(desc) != pte_list);
}
static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
@@ -1184,6 +1205,7 @@ static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter)
iter->desc = (struct pte_list_desc *)(rmap & ~1ul);
iter->pos = 0;
+ WARN_ON(desc_is_a_nulls(iter->desc));
return iter->desc->sptes[iter->pos];
}
@@ -1204,7 +1226,8 @@ static u64 *rmap_get_next(struct rmap_iterator *iter)
return sptep;
}
- iter->desc = iter->desc->more;
+ iter->desc = desc_is_a_nulls(iter->desc->more) ?
+ NULL : iter->desc->more;
if (iter->desc) {
iter->pos = 0;
--
1.8.1.4
next prev parent reply other threads:[~2013-09-05 10:32 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-05 10:29 [PATCH v2 00/15] KVM: MMU: locklessly wirte-protect Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 01/15] KVM: MMU: fix the count of spte number Xiao Guangrong
2013-09-08 12:19 ` Gleb Natapov
2013-09-08 13:55 ` Xiao Guangrong
2013-09-08 14:01 ` Gleb Natapov
2013-09-08 14:24 ` Xiao Guangrong
2013-09-08 14:26 ` Gleb Natapov
2013-09-05 10:29 ` [PATCH v2 02/15] KVM: MMU: properly check last spte in fast_page_fault() Xiao Guangrong
2013-09-30 21:23 ` Marcelo Tosatti
2013-10-03 6:16 ` Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 03/15] KVM: MMU: lazily drop large spte Xiao Guangrong
2013-09-30 22:39 ` Marcelo Tosatti
2013-10-03 6:29 ` Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 04/15] KVM: MMU: flush tlb if the spte can be locklessly modified Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 05/15] KVM: MMU: flush tlb out of mmu lock when write-protect the sptes Xiao Guangrong
2013-09-30 23:05 ` Marcelo Tosatti
2013-10-03 6:46 ` Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 06/15] KVM: MMU: update spte and add it into rmap before dirty log Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 07/15] KVM: MMU: redesign the algorithm of pte_list Xiao Guangrong
2013-09-05 10:29 ` Xiao Guangrong [this message]
2013-09-05 10:29 ` [PATCH v2 09/15] KVM: MMU: introduce pte-list lockless walker Xiao Guangrong
2013-09-08 12:03 ` Xiao Guangrong
2013-09-16 12:42 ` Gleb Natapov
2013-09-16 13:52 ` Xiao Guangrong
2013-09-16 15:04 ` Gleb Natapov
2013-09-05 10:29 ` [PATCH v2 10/15] KVM: MMU: initialize the pointers in pte_list_desc properly Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 11/15] KVM: MMU: reintroduce kvm_mmu_isolate_page() Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 12/15] KVM: MMU: allow locklessly access shadow page table out of vcpu thread Xiao Guangrong
2013-10-08 1:23 ` Marcelo Tosatti
2013-10-08 4:02 ` Xiao Guangrong
2013-10-09 1:56 ` Marcelo Tosatti
2013-10-09 10:45 ` Xiao Guangrong
2013-10-10 1:47 ` Marcelo Tosatti
2013-10-10 12:08 ` Gleb Natapov
2013-10-10 16:42 ` Marcelo Tosatti
2013-10-10 19:16 ` Gleb Natapov
2013-10-10 21:03 ` Marcelo Tosatti
2013-10-11 5:38 ` Gleb Natapov
2013-10-11 20:30 ` Marcelo Tosatti
2013-10-12 5:53 ` Gleb Natapov
2013-10-14 19:29 ` Marcelo Tosatti
2013-10-15 3:57 ` Gleb Natapov
2013-10-15 22:21 ` Marcelo Tosatti
2013-10-16 0:41 ` Xiao Guangrong
2013-10-16 9:12 ` Gleb Natapov
2013-10-16 20:43 ` Marcelo Tosatti
2013-09-05 10:29 ` [PATCH v2 13/15] KVM: MMU: locklessly write-protect the page Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 14/15] KVM: MMU: clean up spte_write_protect Xiao Guangrong
2013-09-05 10:29 ` [PATCH v2 15/15] KVM: MMU: use rcu functions to access the pointer Xiao Guangrong
2013-09-15 10:26 ` [PATCH v2 00/15] KVM: MMU: locklessly wirte-protect Gleb Natapov
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=1378376958-27252-9-git-send-email-xiaoguangrong@linux.vnet.ibm.com \
--to=xiaoguangrong@linux.vnet.ibm.com \
--cc=avi.kivity@gmail.com \
--cc=gleb@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=pbonzini@redhat.com \
/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
all inboxes | Powered by JetHome®