linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ben Gardon <bgardon@google.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Peter Shier <pshier@google.com>,
	Peter Feiner <pfeiner@google.com>,
	Junaid Shahid <junaids@google.com>,
	Jim Mattson <jmattson@google.com>,
	Yulei Zhang <yulei.kernel@gmail.com>,
	Wanpeng Li <kernellwp@gmail.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
	Ben Gardon <bgardon@google.com>
Subject: [PATCH v2 13/13] KVM: x86/mmu: Tear down roots in fast invalidation thread
Date: Thu,  1 Apr 2021 16:37:36 -0700	[thread overview]
Message-ID: <20210401233736.638171-14-bgardon@google.com> (raw)
In-Reply-To: <20210401233736.638171-1-bgardon@google.com>

To avoid saddling a vCPU thread with the work of tearing down an entire
paging structure, take a reference on each root before they become
obsolete, so that the thread initiating the fast invalidation can tear
down the paging structure and (most likely) release the last reference.
As a bonus, this teardown can happen under the MMU lock in read mode so
as not to block the progress of vCPU threads.

Signed-off-by: Ben Gardon <bgardon@google.com>
---

Changelog
v2:
--	rename kvm_tdp_mmu_zap_all_fast to
	kvm_tdp_mmu_zap_invalidated_roots

 arch/x86/kvm/mmu/mmu.c     | 21 +++++++++++-
 arch/x86/kvm/mmu/tdp_mmu.c | 68 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu/tdp_mmu.h |  1 +
 3 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ba0c65076200..5f2064ee7220 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5441,6 +5441,18 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 		 * will drop their references and allow the root count to
 		 * go to 0.
 		 *
+		 * Also take a reference on all roots so that this thread
+		 * can do the bulk of the work required to free the roots
+		 * once they are invalidated. Without this reference, a
+		 * vCPU thread might drop the last reference to a root and
+		 * get stuck with tearing down the entire paging structure.
+		 *
+		 * Roots which have a zero refcount should be skipped as
+		 * they're already being torn down.
+		 * Already invalid roots should be referenced again so that
+		 * they aren't freed before kvm_tdp_mmu_zap_all_fast is
+		 * done with them.
+		 *
 		 * This has essentially the same effect for the TDP MMU
 		 * as updating mmu_valid_gen above does for the shadow
 		 * MMU.
@@ -5452,7 +5464,8 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 		 * could drop the MMU lock and yield.
 		 */
 		list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link)
-			root->role.invalid = true;
+			if (refcount_inc_not_zero(&root->tdp_mmu_root_count))
+				root->role.invalid = true;
 	}
 
 	/*
@@ -5468,6 +5481,12 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 	kvm_zap_obsolete_pages(kvm);
 
 	write_unlock(&kvm->mmu_lock);
+
+	if (is_tdp_mmu_enabled(kvm)) {
+		read_lock(&kvm->mmu_lock);
+		kvm_tdp_mmu_zap_invalidated_roots(kvm);
+		read_unlock(&kvm->mmu_lock);
+	}
 }
 
 static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 501722a524a7..0adcfa5750f6 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -798,6 +798,74 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 		kvm_flush_remote_tlbs(kvm);
 }
 
+static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm,
+						  struct kvm_mmu_page *prev_root)
+{
+	struct kvm_mmu_page *next_root;
+
+	if (prev_root)
+		next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						  &prev_root->link,
+						  typeof(*prev_root), link);
+	else
+		next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						   typeof(*next_root), link);
+
+	while (next_root && !(next_root->role.invalid &&
+			      refcount_read(&next_root->tdp_mmu_root_count)))
+		next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						  &next_root->link,
+						  typeof(*next_root), link);
+
+	return next_root;
+}
+
+/*
+ * Since kvm_mmu_zap_all_fast has acquired a reference to each
+ * invalidated root, they will not be freed until this function drops the
+ * reference. Before dropping that reference, tear down the paging
+ * structure so that whichever thread does drop the last reference
+ * only has to do a trivial ammount of work. Since the roots are invalid,
+ * no new SPTEs should be created under them.
+ */
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
+{
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
+	struct kvm_mmu_page *next_root;
+	struct kvm_mmu_page *root;
+	bool flush = false;
+
+	lockdep_assert_held_read(&kvm->mmu_lock);
+
+	rcu_read_lock();
+
+	root = next_invalidated_root(kvm, NULL);
+
+	while (root) {
+		next_root = next_invalidated_root(kvm, root);
+
+		rcu_read_unlock();
+
+		flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush,
+				      true);
+
+		/*
+		 * Put the reference acquired in
+		 * kvm_tdp_mmu_invalidate_roots
+		 */
+		kvm_tdp_mmu_put_root(kvm, root, true);
+
+		root = next_root;
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+}
+
 /*
  * Installs a last-level SPTE to handle a TDP page fault.
  * (NPT/EPT violation/misconfiguration)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 8fa3e7421a93..f8db381e3059 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -47,6 +47,7 @@ static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 					   sp->gfn, end, false, false, false);
 }
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 		    int map_writable, int max_level, kvm_pfn_t pfn,
-- 
2.31.0.208.g409f899ff0-goog


  parent reply	other threads:[~2021-04-01 23:38 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-01 23:37 [PATCH v2 00/13] More parallel operations for the TDP MMU Ben Gardon
2021-04-01 23:37 ` [PATCH v2 01/13] KVM: x86/mmu: Re-add const qualifier in kvm_tdp_mmu_zap_collapsible_sptes Ben Gardon
2021-05-26 21:25   ` Sean Christopherson
2021-04-01 23:37 ` [PATCH v2 02/13] KVM: x86/mmu: Move kvm_mmu_(get|put)_root to TDP MMU Ben Gardon
2021-04-01 23:37 ` [PATCH v2 03/13] KVM: x86/mmu: use tdp_mmu_free_sp to free roots Ben Gardon
2021-04-01 23:37 ` [PATCH v2 04/13] KVM: x86/mmu: Merge TDP MMU put and free root Ben Gardon
2021-04-01 23:37 ` [PATCH v2 05/13] KVM: x86/mmu: Refactor yield safe root iterator Ben Gardon
2021-04-01 23:37 ` [PATCH v2 06/13] KVM: x86/mmu: Make TDP MMU root refcount atomic Ben Gardon
2021-04-01 23:37 ` [PATCH v2 07/13] KVM: x86/mmu: handle cmpxchg failure in kvm_tdp_mmu_get_root Ben Gardon
2021-04-01 23:37 ` [PATCH v2 08/13] KVM: x86/mmu: Protect the tdp_mmu_roots list with RCU Ben Gardon
2021-04-01 23:37 ` [PATCH v2 09/13] KVM: x86/mmu: Allow zap gfn range to operate under the mmu read lock Ben Gardon
2021-04-02  7:53   ` Paolo Bonzini
2021-04-12 18:21     ` Ben Gardon
2021-04-01 23:37 ` [PATCH v2 10/13] KVM: x86/mmu: Allow zapping collapsible SPTEs to use MMU " Ben Gardon
2021-04-02 11:14   ` Paolo Bonzini
2021-04-01 23:37 ` [PATCH v2 11/13] KVM: x86/mmu: Allow enabling / disabling dirty logging under " Ben Gardon
2021-04-01 23:37 ` [PATCH v2 12/13] KVM: x86/mmu: Fast invalidation for TDP MMU Ben Gardon
2021-04-01 23:37 ` Ben Gardon [this message]
2021-04-02 11:43 ` [PATCH v2 00/13] More parallel operations for the " Paolo Bonzini
2021-05-26 21:34   ` Sean Christopherson
2021-05-27 11:41     ` Paolo Bonzini
2021-05-27 15:26       ` Sean Christopherson

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=20210401233736.638171-14-bgardon@google.com \
    --to=bgardon@google.com \
    --cc=jmattson@google.com \
    --cc=junaids@google.com \
    --cc=kernellwp@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pfeiner@google.com \
    --cc=pshier@google.com \
    --cc=seanjc@google.com \
    --cc=vkuznets@redhat.com \
    --cc=xiaoguangrong.eric@gmail.com \
    --cc=yulei.kernel@gmail.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).