From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul Mackerras <paulus@ozlabs.org>,
Sean Christopherson <sean.j.christopherson@intel.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Dave Hansen <dave.hansen@linux.intel.com>,
Andy Lutomirski <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
Julien Thierry <julien.thierry.kdev@gmail.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
kvm-ppc@vger.kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
kvmarm@lists.cs.columbia.edu,
syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com,
Andrea Arcangeli <aarcange@redhat.com>,
Dan Williams <dan.j.williams@intel.com>,
Barret Rhoden <brho@google.com>,
David Hildenbrand <david@redhat.com>,
Jason Zeng <jason.zeng@intel.com>,
Dave Jiang <dave.jiang@intel.com>,
Liran Alon <liran.alon@oracle.com>,
linux-nvdimm <linux-nvdimm@lists.01.org>
Subject: [PATCH 02/14] mm: thp: KVM: Explicitly check for THP when populating secondary MMU
Date: Wed, 8 Jan 2020 12:24:36 -0800 [thread overview]
Message-ID: <20200108202448.9669-3-sean.j.christopherson@intel.com> (raw)
In-Reply-To: <20200108202448.9669-1-sean.j.christopherson@intel.com>
Add a helper, is_transparent_hugepage(), to explicitly check whether a
compound page is a THP and use it when populating KVM's secondary MMU.
The explicit check fixes a bug where a remapped compound page, e.g. for
an XDP Rx socket, is mapped into a KVM guest and is mistaken for a THP,
which results in KVM incorrectly creating a huge page in its secondary
MMU.
Fixes: 936a5fe6e6148 ("thp: kvm mmu transparent hugepage support")
Reported-by: syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
arch/x86/kvm/mmu/mmu.c | 4 ++--
include/linux/huge_mm.h | 6 ++++++
include/linux/kvm_host.h | 1 +
mm/huge_memory.c | 11 +++++++++++
virt/kvm/arm/mmu.c | 8 +-------
virt/kvm/kvm_main.c | 10 ++++++++++
6 files changed, 31 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8e822c09170d..ca14c84c4f4b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3344,7 +3344,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
*/
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
!kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
- PageTransCompoundMap(pfn_to_page(pfn))) {
+ kvm_is_transparent_hugepage(pfn)) {
unsigned long mask;
/*
@@ -5959,7 +5959,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
*/
if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
!kvm_is_zone_device_pfn(pfn) &&
- PageTransCompoundMap(pfn_to_page(pfn))) {
+ kvm_is_transparent_hugepage(pfn)) {
pte_list_remove(rmap_head, sptep);
if (kvm_available_flush_tlb_with_range())
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 93d5cf0bc716..5e154fad2f98 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -160,6 +160,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp,
extern void prep_transhuge_page(struct page *page);
extern void free_transhuge_page(struct page *page);
+bool is_transparent_hugepage(struct page *page);
bool can_split_huge_page(struct page *page, int *pextra_pins);
int split_huge_page_to_list(struct page *page, struct list_head *list);
@@ -310,6 +311,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
static inline void prep_transhuge_page(struct page *page) {}
+static inline bool is_transparent_hugepage(struct page *page)
+{
+ return false;
+}
+
#define transparent_hugepage_flags 0UL
#define thp_get_unmapped_area NULL
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 339de08e5fa2..411b71a02f25 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -985,6 +985,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn);
struct kvm_irq_ack_notifier {
struct hlist_node link;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 13cc93785006..94c85a5da041 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -527,6 +527,17 @@ void prep_transhuge_page(struct page *page)
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
+bool is_transparent_hugepage(struct page *page)
+{
+ if (!PageCompound(page))
+ return 0;
+
+ page = compound_head(page);
+ return is_huge_zero_page(page) ||
+ page[1].compound_dtor == TRANSHUGE_PAGE_DTOR;
+}
+EXPORT_SYMBOL_GPL(is_transparent_hugepage);
+
static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
loff_t off, unsigned long flags, unsigned long size)
{
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 38b4c910b6c3..6e29d0c5062c 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1372,14 +1372,8 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
gfn_t gfn = *ipap >> PAGE_SHIFT;
- struct page *page = pfn_to_page(pfn);
- /*
- * PageTransCompoundMap() returns true for THP and
- * hugetlbfs. Make sure the adjustment is done only for THP
- * pages.
- */
- if (!PageHuge(page) && PageTransCompoundMap(page)) {
+ if (kvm_is_transparent_hugepage(pfn)) {
unsigned long mask;
/*
* The address we faulted on is backed by a transparent huge
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3aa21bec028d..e8ca8bf12320 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -191,6 +191,16 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
return true;
}
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+
+ if (!PageTransCompoundMap(page))
+ return false;
+
+ return is_transparent_hugepage(compound_head(page));
+}
+
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
--
2.24.1
next prev parent reply other threads:[~2020-01-08 20:27 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-08 20:24 [PATCH 00/14] KVM: x86/mmu: Huge page fixes, cleanup, and DAX Sean Christopherson
2020-01-08 20:24 ` [PATCH 01/14] KVM: x86/mmu: Enforce max_level on HugeTLB mappings Sean Christopherson
2020-01-08 20:24 ` Sean Christopherson [this message]
2020-01-08 20:24 ` [PATCH 03/14] KVM: Use vcpu-specific gva->hva translation when querying host page size Sean Christopherson
2020-01-08 20:24 ` [PATCH 04/14] KVM: Play nice with read-only memslots " Sean Christopherson
2020-01-21 14:24 ` Paolo Bonzini
2020-01-08 20:24 ` [PATCH 05/14] x86/mm: Introduce lookup_address_in_mm() Sean Christopherson
2020-01-09 21:04 ` Thomas Gleixner
2020-01-21 14:26 ` Paolo Bonzini
2020-01-08 20:24 ` [PATCH 06/14] KVM: x86/mmu: Refactor THP adjust to prep for changing query Sean Christopherson
2020-01-08 20:24 ` [PATCH 07/14] KVM: x86/mmu: Walk host page tables to find THP mappings Sean Christopherson
2020-01-21 14:40 ` Paolo Bonzini
2020-01-08 20:24 ` [PATCH 08/14] KVM: x86/mmu: Drop level optimization from fast_page_fault() Sean Christopherson
2020-01-08 20:24 ` [PATCH 09/14] KVM: x86/mmu: Rely on host page tables to find HugeTLB mappings Sean Christopherson
2020-01-08 20:24 ` [PATCH 10/14] KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch) Sean Christopherson
2020-01-08 20:24 ` [PATCH 11/14] KVM: x86/mmu: Zap any compound page when collapsing sptes Sean Christopherson
2020-01-08 20:24 ` [PATCH 12/14] KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust() Sean Christopherson
2020-01-21 15:12 ` Paolo Bonzini
2020-01-08 20:24 ` [PATCH 13/14] KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte() Sean Christopherson
2020-01-08 20:24 ` [PATCH 14/14] KVM: x86/mmu: Use huge pages for DAX-backed files Sean Christopherson
2020-01-09 19:47 ` [PATCH 00/14] KVM: x86/mmu: Huge page fixes, cleanup, and DAX Barret Rhoden
2020-01-21 15:10 ` Paolo Bonzini
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=20200108202448.9669-3-sean.j.christopherson@intel.com \
--to=sean.j.christopherson@intel.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=brho@google.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=dave.jiang@intel.com \
--cc=david@redhat.com \
--cc=james.morse@arm.com \
--cc=jason.zeng@intel.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=julien.thierry.kdev@gmail.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvdimm@lists.01.org \
--cc=liran.alon@oracle.com \
--cc=luto@kernel.org \
--cc=maz@kernel.org \
--cc=paulus@ozlabs.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=suzuki.poulose@arm.com \
--cc=syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.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;
as well as URLs for NNTP newsgroup(s).