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 08/13] KVM: x86/mmu: Protect the tdp_mmu_roots list with RCU
Date: Thu, 1 Apr 2021 16:37:31 -0700 [thread overview]
Message-ID: <20210401233736.638171-9-bgardon@google.com> (raw)
In-Reply-To: <20210401233736.638171-1-bgardon@google.com>
Protect the contents of the TDP MMU roots list with RCU in preparation
for a future patch which will allow the iterator macro to be used under
the MMU lock in read mode.
Signed-off-by: Ben Gardon <bgardon@google.com>
---
Changelog
v2:
-- add lockdep condition for tdp_mmu_pages_lock to for_each_tdp_mmu_root
-- fix problem with unexported lockdep function
-- updated comments in kvm_host.h
arch/x86/include/asm/kvm_host.h | 21 +++++++---
arch/x86/kvm/mmu/tdp_mmu.c | 69 +++++++++++++++++++--------------
2 files changed, 55 insertions(+), 35 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 99778ac51243..e02e8b8a875b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1050,25 +1050,36 @@ struct kvm_arch {
bool tdp_mmu_enabled;
/*
- * List of struct kvmp_mmu_pages being used as roots.
+ * List of struct kvm_mmu_pages being used as roots.
* All struct kvm_mmu_pages in the list should have
* tdp_mmu_page set.
- * All struct kvm_mmu_pages in the list should have a positive
- * root_count except when a thread holds the MMU lock and is removing
- * an entry from the list.
+ *
+ * For reads, this list is protected by:
+ * the MMU lock in read mode + RCU or
+ * the MMU lock in write mode
+ *
+ * For writes, this list is protected by:
+ * the MMU lock in read mode + the tdp_mmu_pages_lock or
+ * the MMU lock in write mode
+ *
+ * Roots will remain in the list until their tdp_mmu_root_count
+ * drops to zero, at which point the thread that decremented the
+ * count to zero should removed the root from the list and clean
+ * it up, freeing the root after an RCU grace period.
*/
struct list_head tdp_mmu_roots;
/*
* List of struct kvmp_mmu_pages not being used as roots.
* All struct kvm_mmu_pages in the list should have
- * tdp_mmu_page set and a root_count of 0.
+ * tdp_mmu_page set and a tdp_mmu_root_count of 0.
*/
struct list_head tdp_mmu_pages;
/*
* Protects accesses to the following fields when the MMU lock
* is held in read mode:
+ * - tdp_mmu_roots (above)
* - tdp_mmu_pages (above)
* - the link field of struct kvm_mmu_pages used by the TDP MMU
* - lpage_disallowed_mmu_pages
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 886bc170f2a5..c1d7f6b86870 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -50,6 +50,22 @@ static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
kmem_cache_free(mmu_page_header_cache, sp);
}
+/*
+ * This is called through call_rcu in order to free TDP page table memory
+ * safely with respect to other kernel threads that may be operating on
+ * the memory.
+ * By only accessing TDP MMU page table memory in an RCU read critical
+ * section, and freeing it after a grace period, lockless access to that
+ * memory won't use it after it is freed.
+ */
+static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
+{
+ struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
+ rcu_head);
+
+ tdp_mmu_free_sp(sp);
+}
+
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
{
gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
@@ -61,11 +77,13 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
WARN_ON(!root->tdp_mmu_page);
- list_del(&root->link);
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_del_rcu(&root->link);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
zap_gfn_range(kvm, root, 0, max_gfn, false, false);
- tdp_mmu_free_sp(root);
+ call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
}
/*
@@ -82,18 +100,21 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
lockdep_assert_held_write(&kvm->mmu_lock);
+ rcu_read_lock();
+
if (prev_root)
- next_root = list_next_entry(prev_root, link);
+ next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ &prev_root->link,
+ typeof(*prev_root), link);
else
- next_root = list_first_entry(&kvm->arch.tdp_mmu_roots,
- typeof(*next_root), link);
+ next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ typeof(*next_root), link);
- while (!list_entry_is_head(next_root, &kvm->arch.tdp_mmu_roots, link) &&
- !kvm_tdp_mmu_get_root(kvm, next_root))
- next_root = list_next_entry(next_root, link);
+ while (next_root && !kvm_tdp_mmu_get_root(kvm, next_root))
+ next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ &next_root->link, typeof(*next_root), link);
- if (list_entry_is_head(next_root, &kvm->arch.tdp_mmu_roots, link))
- next_root = NULL;
+ rcu_read_unlock();
if (prev_root)
kvm_tdp_mmu_put_root(kvm, prev_root);
@@ -107,15 +128,17 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
* if exiting the loop early, the caller must drop the reference to the most
* recent root. (Unless keeping a live reference is desirable.)
*/
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \
for (_root = tdp_mmu_next_root(_kvm, NULL); \
_root; \
_root = tdp_mmu_next_root(_kvm, _root)) \
if (kvm_mmu_page_as_id(_root) != _as_id) { \
} else
-#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \
- list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \
+#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \
+ list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link, \
+ lockdep_is_held_type(&kvm->mmu_lock, 0) || \
+ lockdep_is_help(&kvm->arch.tdp_mmu_pages_lock)) \
if (kvm_mmu_page_as_id(_root) != _as_id) { \
} else
@@ -171,28 +194,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
root = alloc_tdp_mmu_page(vcpu, 0, vcpu->arch.mmu->shadow_root_level);
refcount_set(&root->tdp_mmu_root_count, 1);
- list_add(&root->link, &kvm->arch.tdp_mmu_roots);
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
out:
return __pa(root->spt);
}
-/*
- * This is called through call_rcu in order to free TDP page table memory
- * safely with respect to other kernel threads that may be operating on
- * the memory.
- * By only accessing TDP MMU page table memory in an RCU read critical
- * section, and freeing it after a grace period, lockless access to that
- * memory won't use it after it is freed.
- */
-static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
-{
- struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
- rcu_head);
-
- tdp_mmu_free_sp(sp);
-}
-
static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
u64 old_spte, u64 new_spte, int level,
bool shared);
--
2.31.0.208.g409f899ff0-goog
next prev 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 ` Ben Gardon [this message]
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 ` [PATCH v2 13/13] KVM: x86/mmu: Tear down roots in fast invalidation thread Ben Gardon
2021-04-02 11:43 ` [PATCH v2 00/13] More parallel operations for the TDP MMU 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=20210401233736.638171-9-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).