From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
Andy Lutomirski <luto@amacapital.net>,
Vivek Goyal <vgoyal@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Andy Lutomirski <luto@kernel.org>,
LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
kvm list <kvm@vger.kernel.org>, stable <stable@vger.kernel.org>
Subject: Re: [PATCH v2] x86/kvm: Disable KVM_ASYNC_PF_SEND_ALWAYS
Date: Wed, 8 Apr 2020 08:34:14 -0700 [thread overview]
Message-ID: <20200408153413.GA11322@linux.intel.com> (raw)
In-Reply-To: <274f3d14-08ac-e5cc-0b23-e6e0274796c8@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 916 bytes --]
On Wed, Apr 08, 2020 at 10:23:58AM +0200, Paolo Bonzini wrote:
> Page-not-present async page faults are almost a perfect match for the
> hardware use of #VE (and it might even be possible to let the processor
> deliver the exceptions).
My "async" page fault knowledge is limited, but if the desired behavior is
to reflect a fault into the guest for select EPT Violations, then yes,
enabling EPT Violation #VEs in hardware is doable. The big gotcha is that
KVM needs to set the suppress #VE bit for all EPTEs when allocating a new
MMU page, otherwise not-present faults on zero-initialized EPTEs will get
reflected.
Attached a patch that does the prep work in the MMU. The VMX usage would be:
kvm_mmu_set_spte_init_value(VMX_EPT_SUPPRESS_VE_BIT);
when EPT Violation #VEs are enabled. It's 64-bit only as it uses stosq to
initialize EPTEs. 32-bit could also be supported by doing memcpy() from
a static page.
[-- Attachment #2: 0001-KVM-x86-mmu-Allow-non-zero-init-value-for-shadow-PTE.patch --]
[-- Type: text/x-diff, Size: 5340 bytes --]
From 078b485e8a64e6d72ebad58bf66f950763ba30bb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Mon, 29 Jul 2019 19:23:46 -0700
Subject: [PATCH] KVM: x86/mmu: Allow non-zero init value for shadow PTE
Add support for using a non-zero "init" value for shadow PTEs, which is
required to enable EPT Violation #VEs in hardware. When #VEs are
enabled, KVM needs to set the "suppress #VE" bit in unused PTEs to avoid
unintentionally reflecting not-present EPT Violations into the guest.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
arch/x86/kvm/mmu.h | 1 +
arch/x86/kvm/mmu/mmu.c | 43 ++++++++++++++++++++++++++++------
arch/x86/kvm/mmu/paging_tmpl.h | 2 +-
3 files changed, 38 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 8a3b1bce722a..139db8a125d6 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -52,6 +52,7 @@ static inline u64 rsvd_bits(int s, int e)
}
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask);
+void kvm_mmu_set_spte_init_value(u64 init_value);
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8071952e9cf2..742ea9c254c4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -250,6 +250,8 @@ static u64 __read_mostly shadow_mmio_access_mask;
static u64 __read_mostly shadow_present_mask;
static u64 __read_mostly shadow_me_mask;
+static u64 __read_mostly shadow_init_value;
+
/*
* SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
* shadow_acc_track_mask is the set of bits to be cleared in non-accessed
@@ -538,6 +540,13 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
+void kvm_mmu_set_spte_init_value(u64 init_value)
+{
+ WARN_ON(!IS_ENABLED(CONFIG_X86_64) && init_value);
+ shadow_init_value = init_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_spte_init_value);
+
static u8 kvm_get_shadow_phys_bits(void)
{
/*
@@ -569,6 +578,7 @@ static void kvm_mmu_reset_all_pte_masks(void)
shadow_mmio_mask = 0;
shadow_present_mask = 0;
shadow_acc_track_mask = 0;
+ shadow_init_value = 0;
shadow_phys_bits = kvm_get_shadow_phys_bits();
@@ -610,7 +620,7 @@ static int is_nx(struct kvm_vcpu *vcpu)
static int is_shadow_present_pte(u64 pte)
{
- return (pte != 0) && !is_mmio_spte(pte);
+ return (pte != 0 && pte != shadow_init_value && !is_mmio_spte(pte));
}
static int is_large_pte(u64 pte)
@@ -921,9 +931,9 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
u64 old_spte = *sptep;
if (!spte_has_volatile_bits(old_spte))
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, shadow_init_value);
else
- old_spte = __update_clear_spte_slow(sptep, 0ull);
+ old_spte = __update_clear_spte_slow(sptep, shadow_init_value);
if (!is_shadow_present_pte(old_spte))
return 0;
@@ -953,7 +963,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
*/
static void mmu_spte_clear_no_track(u64 *sptep)
{
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, shadow_init_value);
}
static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -2473,6 +2483,20 @@ static void clear_sp_write_flooding_count(u64 *spte)
__clear_sp_write_flooding_count(sp);
}
+#ifdef CONFIG_X86_64
+static inline void kvm_clear_ptes(void *page)
+{
+ int ign;
+
+ asm volatile (
+ "rep stosq\n\t"
+ : "=c"(ign), "=D"(page)
+ : "a"(shadow_init_value), "c"(4096/8), "D"(page)
+ : "memory"
+ );
+}
+#endif
+
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
gva_t gaddr,
@@ -2553,7 +2577,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
}
- clear_page(sp->spt);
+#ifdef CONFIG_X86_64
+ if (shadow_init_value)
+ kvm_clear_ptes(sp->spt);
+ else
+#endif
+ clear_page(sp->spt);
trace_kvm_mmu_get_page(sp, true);
kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
@@ -3515,7 +3544,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
struct kvm_shadow_walk_iterator iterator;
struct kvm_mmu_page *sp;
bool fault_handled = false;
- u64 spte = 0ull;
+ u64 spte = shadow_init_value;
uint retry_count = 0;
if (!page_fault_can_be_fast(error_code))
@@ -3951,7 +3980,7 @@ static bool
walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
{
struct kvm_shadow_walk_iterator iterator;
- u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull;
+ u64 sptes[PT64_ROOT_MAX_LEVEL], spte = shadow_init_value;
struct rsvd_bits_validate *rsvd_check;
int root, leaf;
bool reserved = false;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 9bdf9b7d9a96..949deed15933 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -1025,7 +1025,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gpa_t pte_gpa;
gfn_t gfn;
- if (!sp->spt[i])
+ if (!sp->spt[i] || sp->spt[i] == shadow_init_value)
continue;
pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
--
2.24.1
next prev parent reply other threads:[~2020-04-08 15:34 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-07 2:26 [PATCH v2] x86/kvm: Disable KVM_ASYNC_PF_SEND_ALWAYS Andy Lutomirski
2020-03-07 15:03 ` Andy Lutomirski
2020-03-07 15:47 ` Thomas Gleixner
2020-03-07 15:59 ` Andy Lutomirski
2020-03-07 19:01 ` Thomas Gleixner
2020-03-07 19:34 ` Andy Lutomirski
2020-03-08 7:23 ` Thomas Gleixner
2020-03-09 6:57 ` Thomas Gleixner
2020-03-09 8:40 ` Paolo Bonzini
2020-03-09 9:09 ` Thomas Gleixner
2020-03-09 18:14 ` Andy Lutomirski
2020-03-09 19:05 ` Thomas Gleixner
2020-03-09 20:22 ` Peter Zijlstra
2020-04-06 19:09 ` Vivek Goyal
2020-04-06 20:25 ` Peter Zijlstra
2020-04-06 20:32 ` Andy Lutomirski
2020-04-06 20:42 ` Andy Lutomirski
2020-04-07 17:21 ` Vivek Goyal
2020-04-07 17:38 ` Andy Lutomirski
2020-04-07 20:20 ` Thomas Gleixner
2020-04-07 21:41 ` Andy Lutomirski
2020-04-07 22:07 ` Paolo Bonzini
2020-04-07 22:29 ` Andy Lutomirski
2020-04-08 0:30 ` Paolo Bonzini
2020-05-21 15:55 ` Vivek Goyal
2020-04-07 22:48 ` Thomas Gleixner
2020-04-08 4:48 ` Andy Lutomirski
2020-04-08 9:32 ` Borislav Petkov
2020-04-08 10:12 ` Thomas Gleixner
2020-04-08 18:23 ` Vivek Goyal
2020-04-07 22:49 ` Vivek Goyal
2020-04-08 10:01 ` Borislav Petkov
2020-04-07 22:04 ` Paolo Bonzini
2020-04-07 23:21 ` Thomas Gleixner
2020-04-08 8:23 ` Paolo Bonzini
2020-04-08 13:01 ` Thomas Gleixner
2020-04-08 15:38 ` Peter Zijlstra
2020-04-08 16:41 ` Thomas Gleixner
2020-04-09 9:03 ` Paolo Bonzini
2020-04-08 15:34 ` Sean Christopherson [this message]
2020-04-08 16:50 ` Paolo Bonzini
2020-04-08 18:01 ` Thomas Gleixner
2020-04-08 20:34 ` Vivek Goyal
2020-04-08 23:06 ` Thomas Gleixner
2020-04-08 23:14 ` Thomas Gleixner
2020-04-09 4:50 ` Andy Lutomirski
2020-04-09 9:43 ` Paolo Bonzini
2020-04-09 11:36 ` Andrew Cooper
2020-04-09 12:47 ` Paolo Bonzini
2020-04-09 14:13 ` Andrew Cooper
2020-04-09 14:32 ` Paolo Bonzini
2020-04-09 15:03 ` Andy Lutomirski
2020-04-09 15:17 ` Paolo Bonzini
2020-04-09 17:32 ` Andy Lutomirski
2020-04-06 21:32 ` Thomas Gleixner
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=20200408153413.GA11322@linux.intel.com \
--to=sean.j.christopherson@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=luto@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=vgoyal@redhat.com \
--cc=x86@kernel.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;
as well as URLs for NNTP newsgroup(s).