From: Sean Christopherson <seanjc@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Ben Gardon <bgardon@google.com>
Subject: [PATCH 20/24] KVM: x86/mmu: Use a dedicated bit to track shadow/MMU-present SPTEs
Date: Thu, 25 Feb 2021 12:47:45 -0800 [thread overview]
Message-ID: <20210225204749.1512652-21-seanjc@google.com> (raw)
In-Reply-To: <20210225204749.1512652-1-seanjc@google.com>
Introduce MMU_PRESENT to explicitly track which SPTEs are "present" from
the MMU's perspective. Checking for shadow-present SPTEs is a very
common operation for the MMU, particularly in hot paths such as page
faults. With the addition of "removed" SPTEs for the TDP MMU,
identifying shadow-present SPTEs is quite costly especially since it
requires checking multiple 64-bit values.
On 64-bit KVM, this reduces the footprint of kvm.ko's .text by ~2k bytes.
On 32-bit KVM, this increases the footprint by ~200 bytes, but only
because gcc now inlines several more MMU helpers, e.g. drop_parent_pte().
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/mmu/spte.c | 8 ++++----
arch/x86/kvm/mmu/spte.h | 11 ++++++++++-
2 files changed, 14 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index d12acf5eb871..e07aabb23b8a 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -94,7 +94,7 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level,
bool can_unsync, bool host_writable, bool ad_disabled,
u64 *new_spte)
{
- u64 spte = 0;
+ u64 spte = SPTE_MMU_PRESENT_MASK;
int ret = 0;
if (ad_disabled)
@@ -183,10 +183,10 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level,
u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
{
- u64 spte;
+ u64 spte = SPTE_MMU_PRESENT_MASK;
- spte = __pa(child_pt) | shadow_present_mask | PT_WRITABLE_MASK |
- shadow_user_mask | shadow_x_mask | shadow_me_mask;
+ spte |= __pa(child_pt) | shadow_present_mask | PT_WRITABLE_MASK |
+ shadow_user_mask | shadow_x_mask | shadow_me_mask;
if (ad_disabled)
spte |= SPTE_TDP_AD_DISABLED_MASK;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 8996baa8da15..645e9bc2d4a2 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -5,6 +5,15 @@
#include "mmu_internal.h"
+/*
+ * A MMU present SPTE is backed by actual memory and may or may not be present
+ * in hardware. E.g. MMIO SPTEs are not considered present. Use bit 11, as it
+ * is ignored by all flavors of SPTEs and checking a low bit often generates
+ * better code than for a high bit, e.g. 56+. MMU present checks are pervasive
+ * enough that the improved code generation is noticeable in KVM's footprint.
+ */
+#define SPTE_MMU_PRESENT_MASK BIT_ULL(11)
+
/*
* TDP SPTES (more specifically, EPT SPTEs) may not have A/D bits, and may also
* be restricted to using write-protection (for L2 when CPU dirty logging, i.e.
@@ -241,7 +250,7 @@ static inline bool is_access_track_spte(u64 spte)
static inline bool is_shadow_present_pte(u64 pte)
{
- return (pte != 0) && !is_mmio_spte(pte) && !is_removed_spte(pte);
+ return !!(pte & SPTE_MMU_PRESENT_MASK);
}
static inline bool is_large_pte(u64 pte)
--
2.30.1.766.gb4fecdf3b7-goog
next prev parent reply other threads:[~2021-02-25 20:55 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-25 20:47 [PATCH 00/24] KVM: x86/mmu: Introduce MMU_PRESENT and fix bugs Sean Christopherson
2021-02-25 20:47 ` [PATCH 01/24] KVM: x86/mmu: Set SPTE_AD_WRPROT_ONLY_MASK if and only if PML is enabled Sean Christopherson
2021-02-25 20:47 ` [PATCH 02/24] KVM: x86/mmu: Check for shadow-present SPTE before querying A/D status Sean Christopherson
2021-02-25 20:47 ` [PATCH 03/24] KVM: x86/mmu: Bail from fast_page_fault() if SPTE is not shadow-present Sean Christopherson
2021-02-25 20:47 ` [PATCH 04/24] KVM: x86/mmu: Disable MMIO caching if MMIO value collides with L1TF Sean Christopherson
2021-02-25 20:47 ` [PATCH 05/24] KVM: x86/mmu: Retry page faults that hit an invalid memslot Sean Christopherson
2021-02-25 20:47 ` [PATCH 06/24] KVM: x86/mmu: Don't install bogus MMIO SPTEs if MMIO caching is disabled Sean Christopherson
2021-02-25 20:47 ` [PATCH 07/24] KVM: x86/mmu: Handle MMIO SPTEs directly in mmu_set_spte() Sean Christopherson
2021-02-25 20:47 ` [PATCH 08/24] KVM: x86/mmu: Drop redundant trace_kvm_mmu_set_spte() in the TDP MMU Sean Christopherson
2021-02-25 20:47 ` [PATCH 09/24] KVM: x86/mmu: Rename 'mask' to 'spte' in MMIO SPTE helpers Sean Christopherson
2021-02-25 20:47 ` [PATCH 10/24] KVM: x86/mmu: Stop using software available bits to denote MMIO SPTEs Sean Christopherson
2021-02-25 20:47 ` [PATCH 11/24] KVM: x86/mmu: Add module param to disable MMIO caching (for testing) Sean Christopherson
2021-02-25 20:47 ` [PATCH 12/24] KVM: x86/mmu: Rename and document A/D scheme for TDP SPTEs Sean Christopherson
2021-02-25 20:47 ` [PATCH 13/24] KVM: x86/mmu: Use MMIO SPTE bits 53 and 52 for the MMIO generation Sean Christopherson
2021-02-25 20:47 ` [PATCH 14/24] KVM: x86/mmu: Document dependency bewteen TDP A/D type and saved bits Sean Christopherson
2021-02-25 20:47 ` [PATCH 15/24] KVM: x86/mmu: Move initial kvm_mmu_set_mask_ptes() call into MMU proper Sean Christopherson
2021-02-25 20:47 ` [PATCH 16/24] KVM: x86/mmu: Co-locate code for setting various SPTE masks Sean Christopherson
2021-02-25 20:47 ` [PATCH 17/24] KVM: x86/mmu: Move logic for setting SPTE masks for EPT into the MMU proper Sean Christopherson
2021-02-25 20:47 ` [PATCH 18/24] KVM: x86/mmu: Make Host-writable and MMU-writable bit locations dynamic Sean Christopherson
2021-02-25 20:47 ` [PATCH 19/24] KVM: x86/mmu: Use high bits for host/mmu writable masks for EPT SPTEs Sean Christopherson
2021-02-25 20:47 ` Sean Christopherson [this message]
2021-03-08 18:52 ` [PATCH 20/24] KVM: x86/mmu: Use a dedicated bit to track shadow/MMU-present SPTEs Tom Lendacky
2021-03-08 19:48 ` Paolo Bonzini
2021-03-08 20:11 ` Sean Christopherson
2021-03-08 21:49 ` Sean Christopherson
2021-02-25 20:47 ` [PATCH 21/24] KVM: x86/mmu: Tweak auditing WARN for A/D bits to !PRESENT (was MMIO) Sean Christopherson
2021-05-06 23:05 ` Matteo Croce
2021-05-07 7:38 ` Paolo Bonzini
2021-02-25 20:47 ` [PATCH 22/24] KVM: x86/mmu: Use is_removed_spte() instead of open coded equivalents Sean Christopherson
2021-02-25 20:47 ` [PATCH 23/24] KVM: x86/mmu: Use low available bits for removed SPTEs Sean Christopherson
2021-02-25 20:47 ` [PATCH 24/24] KVM: x86/mmu: Dump reserved bits if they're detected on non-MMIO SPTE Sean Christopherson
2021-02-26 9:38 ` [PATCH 00/24] KVM: x86/mmu: Introduce MMU_PRESENT and fix bugs 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=20210225204749.1512652-21-seanjc@google.com \
--to=seanjc@google.com \
--cc=bgardon@google.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.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).