kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sean Christopherson <seanjc@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, Sean Christopherson <seanjc@google.com>
Subject: [kvm-unit-tests PATCH 02/39] x86/access: Cache CR3 to improve performance
Date: Thu, 25 Nov 2021 01:28:20 +0000	[thread overview]
Message-ID: <20211125012857.508243-3-seanjc@google.com> (raw)
In-Reply-To: <20211125012857.508243-1-seanjc@google.com>

Add a shadow for CR3, which avoids a significant number of VM-Exits when
KVM is using shadow paging.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 x86/access.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/x86/access.c b/x86/access.c
index 2e0636a..eb0ba60 100644
--- a/x86/access.c
+++ b/x86/access.c
@@ -189,6 +189,7 @@ typedef struct {
 static void ac_test_show(ac_test_t *at);
 
 static unsigned long shadow_cr0;
+static unsigned long shadow_cr3;
 static unsigned long shadow_cr4;
 static unsigned long long shadow_efer;
 
@@ -515,7 +516,7 @@ static void ac_set_expected_status(ac_test_t *at)
 static void __ac_setup_specific_pages(ac_test_t *at, ac_pool_t *pool, bool reuse,
 				      u64 pd_page, u64 pt_page)
 {
-	unsigned long root = read_cr3();
+	unsigned long root = shadow_cr3;
 	int flags = at->flags;
 	bool skip = true;
 
@@ -635,7 +636,7 @@ static void ac_setup_specific_pages(ac_test_t *at, ac_pool_t *pool,
 
 static void dump_mapping(ac_test_t *at)
 {
-	unsigned long root = read_cr3();
+	unsigned long root = shadow_cr3;
 	int flags = at->flags;
 	int i;
 
@@ -1084,6 +1085,7 @@ int ac_test_run(int page_table_levels)
 
 	shadow_cr0 = read_cr0();
 	shadow_cr4 = read_cr4();
+	shadow_cr3 = read_cr3();
 	shadow_efer = rdmsr(MSR_EFER);
 
 	if (cpuid_maxphyaddr() >= 52) {
-- 
2.34.0.rc2.393.gf8c9666880-goog


  parent reply	other threads:[~2021-11-25  1:57 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-25  1:28 [kvm-unit-tests PATCH 00/39] x86/access: nVMX: Big overhaul Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 01/39] x86/access: Add proper defines for hardcoded addresses Sean Christopherson
2021-11-25  1:28 ` Sean Christopherson [this message]
2021-11-25  1:28 ` [kvm-unit-tests PATCH 03/39] x86/access: Use do-while loop for what is obviously a do-while loop Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 04/39] x86/access: Stop pretending the test is SMP friendly Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 05/39] x86/access: Refactor so called "page table pool" logic Sean Christopherson
2021-11-26 18:03   ` Paolo Bonzini
2021-11-25  1:28 ` [kvm-unit-tests PATCH 06/39] x86/access: Stash root page table level in test environment Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 07/39] x86/access: Hoist page table allocator helpers above "init" helper Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 08/39] x86/access: Rename variables in page table walkers Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 09/39] x86/access: Abort if page table insertion hits an unexpected level Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 10/39] x86/access: Make SMEP place nice with 5-level paging Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 11/39] x86/access: Use upper half of virtual address space Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 12/39] x86/access: Print the index when dumping PTEs Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 13/39] x86/access: Pre-allocate all page tables at (sub)test init Sean Christopherson
2021-11-26 18:15   ` Paolo Bonzini
2021-11-25  1:28 ` [kvm-unit-tests PATCH 14/39] x86/access: Don't write page tables if desired PTE is same as current PTE Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 15/39] x86/access: Preserve A/D bits when writing paging structure entries Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 16/39] x86/access: Make toggling of PRESENT bit a "higher order" action Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 17/39] x86/access: Manually override PMD in effective permissions sub-test Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 18/39] x86/access: Remove manual override of PUD/PMD in prefetch sub-test Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 19/39] x86/access: Remove PMD/PT target overrides Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 20/39] x86/access: Remove timeout overrides now that performance doesn't suck Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 21/39] nVMX: Skip EPT tests if INVEPT(SINGLE_CONTEXT) is unsupported Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 22/39] nVMX: Hoist assert macros to the top of vmx.h Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 23/39] nVMX: Add a non-reporting assertion macro Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 24/39] nVMX: Assert success in unchecked INVEPT/INVVPID helpers Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 25/39] nVMX: Drop less-than-useless ept_sync() wrapper Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 26/39] nVMX: Move EPT capability check helpers to vmx.h Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 27/39] nVMX: Drop unused and useless vpid_sync() helper Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 28/39] nVMX: Remove "v1" version of INVVPID test Sean Christopherson
2021-11-26 18:28   ` Paolo Bonzini
2021-11-25  1:28 ` [kvm-unit-tests PATCH 29/39] nVMX: Add helper to check if INVVPID type is supported Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 30/39] nVMX: Add helper to check if INVVPID " Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 31/39] nVMX: Add helper to get first supported INVVPID type Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 32/39] nVMX: Use helper to check for EPT A/D support Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 33/39] nVMX: Add helpers to check for 4/5-level EPT support Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 34/39] nVMX: Fix name of macro defining EPT execute only capability Sean Christopherson
2021-11-26 18:31   ` Paolo Bonzini
2021-11-25  1:28 ` [kvm-unit-tests PATCH 35/39] nVMX: Add helper to check if a memtype is supported for EPT structures Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 36/39] nVMX: Get rid of horribly named "ctrl" boolean in test_ept_eptp() Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 37/39] nVMX: Rename awful "ctrl" booleans to "is_ctrl_valid" Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 38/39] nVMX: Add helper to check if VPID is supported Sean Christopherson
2021-11-25  1:28 ` [kvm-unit-tests PATCH 39/39] x86/access: nVMX: Add "access" test variants to invalidate via (INV)VPID Sean Christopherson
2021-11-26 18:43 ` [kvm-unit-tests PATCH 00/39] x86/access: nVMX: Big overhaul Paolo Bonzini
2021-11-29 19:04   ` Sean Christopherson
2021-11-29 19:15     ` 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=20211125012857.508243-3-seanjc@google.com \
    --to=seanjc@google.com \
    --cc=kvm@vger.kernel.org \
    --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;
as well as URLs for NNTP newsgroup(s).