From: Sean Christopherson <seanjc@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Janosch Frank <frankja@linux.ibm.com>,
Claudio Imbrenda <imbrenda@linux.ibm.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>,
David Hildenbrand <david@redhat.com>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
David Matlack <dmatlack@google.com>,
Ben Gardon <bgardon@google.com>,
Mingwei Zhang <mizhang@google.com>
Subject: [PATCH v3 20/28] KVM: x86/mmu: Allow yielding when zapping GFNs for defunct TDP MMU root
Date: Sat, 26 Feb 2022 00:15:38 +0000 [thread overview]
Message-ID: <20220226001546.360188-21-seanjc@google.com> (raw)
In-Reply-To: <20220226001546.360188-1-seanjc@google.com>
Allow yielding when zapping SPTEs after the last reference to a valid
root is put. Because KVM must drop all SPTEs in response to relevant
mmu_notifier events, mark defunct roots invalid and reset their refcount
prior to zapping the root. Keeping the refcount elevated while the zap
is in-progress ensures the root is reachable via mmu_notifier until the
zap completes and the last reference to the invalid, defunct root is put.
Allowing kvm_tdp_mmu_put_root() to yield fixes soft lockup issues if the
root in being put has a massive paging structure, e.g. zapping a root
that is backed entirely by 4kb pages for a guest with 32tb of memory can
take hundreds of seconds to complete.
watchdog: BUG: soft lockup - CPU#49 stuck for 485s! [max_guest_memor:52368]
RIP: 0010:kvm_set_pfn_dirty+0x30/0x50 [kvm]
__handle_changed_spte+0x1b2/0x2f0 [kvm]
handle_removed_tdp_mmu_page+0x1a7/0x2b8 [kvm]
__handle_changed_spte+0x1f4/0x2f0 [kvm]
handle_removed_tdp_mmu_page+0x1a7/0x2b8 [kvm]
__handle_changed_spte+0x1f4/0x2f0 [kvm]
tdp_mmu_zap_root+0x307/0x4d0 [kvm]
kvm_tdp_mmu_put_root+0x7c/0xc0 [kvm]
kvm_mmu_free_roots+0x22d/0x350 [kvm]
kvm_mmu_reset_context+0x20/0x60 [kvm]
kvm_arch_vcpu_ioctl_set_sregs+0x5a/0xc0 [kvm]
kvm_vcpu_ioctl+0x5bd/0x710 [kvm]
__se_sys_ioctl+0x77/0xc0
__x64_sys_ioctl+0x1d/0x20
do_syscall_64+0x44/0xa0
entry_SYSCALL_64_after_hwframe+0x44/0xae
KVM currently doesn't put a root from a non-preemptible context, so other
than the mmu_notifier wrinkle, yielding when putting a root is safe.
Yield-unfriendly iteration uses for_each_tdp_mmu_root(), which doesn't
take a reference to each root (it requires mmu_lock be held for the
entire duration of the walk).
tdp_mmu_next_root() is used only by the yield-friendly iterator.
kvm_tdp_mmu_zap_invalidated_roots() is explicitly yield friendly.
kvm_mmu_free_roots() => mmu_free_root_page() is a much bigger fan-out,
but is still yield-friendly in all call sites, as all callers can be
traced back to some combination of vcpu_run(), kvm_destroy_vm(), and/or
kvm_create_vm().
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/mmu/tdp_mmu.c | 122 ++++++++++++++++++++++++-------------
1 file changed, 81 insertions(+), 41 deletions(-)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 3031b42c27a6..b838cfa984ad 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -91,21 +91,66 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
WARN_ON(!root->tdp_mmu_page);
- spin_lock(&kvm->arch.tdp_mmu_pages_lock);
- list_del_rcu(&root->link);
- spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ /*
+ * Ensure root->role.invalid is read after the refcount reaches zero to
+ * avoid zapping the root multiple times, e.g. if a different task
+ * acquires a reference (after the root was marked invalid) and puts
+ * the last reference, all while holding mmu_lock for read. Pairs
+ * with the smp_mb__before_atomic() below.
+ */
+ smp_mb__after_atomic();
+
+ /*
+ * Free the root if it's already invalid. Invalid roots must be zapped
+ * before their last reference is put, i.e. there's no work to be done,
+ * and all roots must be invalidated (see below) before they're freed.
+ * Re-zapping invalid roots would put KVM into an infinite loop (again,
+ * see below).
+ */
+ if (root->role.invalid) {
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_del_rcu(&root->link);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+
+ call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
+ return;
+ }
+
+ /*
+ * Invalidate the root to prevent it from being reused by a vCPU, and
+ * so that KVM doesn't re-zap the root when its last reference is put
+ * again (see above).
+ */
+ root->role.invalid = true;
+
+ /*
+ * Ensure role.invalid is visible if a concurrent reader acquires a
+ * reference after the root's refcount is reset. Pairs with the
+ * smp_mb__after_atomic() above.
+ */
+ smp_mb__before_atomic();
+
+ /*
+ * Note, if mmu_lock is held for read this can race with other readers,
+ * e.g. they may acquire a reference without seeing the root as invalid,
+ * and the refcount may be reset after the root is skipped. Both races
+ * are benign, as flows that must visit all roots, e.g. need to zap
+ * SPTEs for correctness, must take mmu_lock for write to block page
+ * faults, and the only flow that must not consume an invalid root is
+ * allocating a new root for a vCPU, which also takes mmu_lock for write.
+ */
+ refcount_set(&root->tdp_mmu_root_count, 1);
/*
- * A TLB flush is not necessary as KVM performs a local TLB flush when
- * allocating a new root (see kvm_mmu_load()), and when migrating vCPU
- * to a different pCPU. Note, the local TLB flush on reuse also
- * invalidates any paging-structure-cache entries, i.e. TLB entries for
- * intermediate paging structures, that may be zapped, as such entries
- * are associated with the ASID on both VMX and SVM.
+ * Zap the root, then put the refcount "acquired" above. Recursively
+ * call kvm_tdp_mmu_put_root() to test the above logic for avoiding an
+ * infinite loop by freeing invalid roots. By design, the root is
+ * reachable while it's being zapped, thus a different task can put its
+ * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for a
+ * defunct root is unavoidable.
*/
tdp_mmu_zap_root(kvm, root, shared);
-
- call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
+ kvm_tdp_mmu_put_root(kvm, root, shared);
}
enum tdp_mmu_roots_iter_type {
@@ -760,12 +805,23 @@ static inline gfn_t tdp_mmu_max_gfn_host(void)
static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared)
{
- bool root_is_unreachable = !refcount_read(&root->tdp_mmu_root_count);
struct tdp_iter iter;
gfn_t end = tdp_mmu_max_gfn_host();
gfn_t start = 0;
+ /*
+ * The root must have an elevated refcount so that it's reachable via
+ * mmu_notifier callbacks, which allows this path to yield and drop
+ * mmu_lock. When handling an unmap/release mmu_notifier command, KVM
+ * must drop all references to relevant pages prior to completing the
+ * callback. Dropping mmu_lock with an unreachable root would result
+ * in zapping SPTEs after a relevant mmu_notifier callback completes
+ * and lead to use-after-free as zapping a SPTE triggers "writeback" of
+ * dirty accessed bits to the SPTE's associated struct page.
+ */
+ WARN_ON_ONCE(!refcount_read(&root->tdp_mmu_root_count));
+
kvm_lockdep_assert_mmu_lock_held(kvm, shared);
rcu_read_lock();
@@ -776,42 +832,16 @@ static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
*/
for_each_tdp_pte_min_level(iter, root, root->role.level, start, end) {
retry:
- /*
- * Yielding isn't allowed when zapping an unreachable root as
- * the root won't be processed by mmu_notifier callbacks. When
- * handling an unmap/release mmu_notifier command, KVM must
- * drop all references to relevant pages prior to completing
- * the callback. Dropping mmu_lock can result in zapping SPTEs
- * for an unreachable root after a relevant callback completes,
- * which leads to use-after-free as zapping a SPTE triggers
- * "writeback" of dirty/accessed bits to the SPTE's associated
- * struct page.
- */
- if (!root_is_unreachable &&
- tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
continue;
if (!is_shadow_present_pte(iter.old_spte))
continue;
- if (!shared) {
+ if (!shared)
tdp_mmu_set_spte(kvm, &iter, 0);
- } else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0)) {
- /*
- * cmpxchg() shouldn't fail if the root is unreachable.
- * Retry so as not to leak the page and its children.
- */
- WARN_ONCE(root_is_unreachable,
- "Contended TDP MMU SPTE in unreachable root.");
+ else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
goto retry;
- }
-
- /*
- * WARN if the root is invalid and is unreachable, all SPTEs
- * should've been zapped by kvm_tdp_mmu_zap_invalidated_roots(),
- * and inserting new SPTEs under an invalid root is a KVM bug.
- */
- WARN_ON_ONCE(root_is_unreachable && root->role.invalid);
}
rcu_read_unlock();
@@ -906,6 +936,9 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
int i;
/*
+ * Zap all roots, including invalid roots, as all SPTEs must be dropped
+ * before returning to the caller.
+ *
* A TLB flush is unnecessary, KVM zaps everything if and only the VM
* is being destroyed or the userspace VMM has exited. In both cases,
* KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
@@ -931,6 +964,13 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
for_each_invalid_tdp_mmu_root_yield_safe(kvm, root) {
/*
+ * Zap the root regardless of what marked it invalid, e.g. even
+ * if the root was marked invalid by kvm_tdp_mmu_put_root() due
+ * to its last reference being put. All SPTEs must be dropped
+ * before returning to the caller, e.g. if a memslot is deleted
+ * or moved, the memslot's associated SPTEs are unreachable via
+ * the mmu_notifier once the memslot update completes.
+ *
* A TLB flush is unnecessary, invalidated roots are guaranteed
* to be unreachable by the guest (see kvm_tdp_mmu_put_root()
* for more details), and unlike the legacy MMU, no vCPU kick
--
2.35.1.574.g5d30c73bfb-goog
next prev parent reply other threads:[~2022-02-26 0:19 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-26 0:15 [PATCH v3 00/28] KVM: x86/mmu: Overhaul TDP MMU zapping and flushing Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 01/28] KVM: x86/mmu: Use common iterator for walking invalid TDP MMU roots Sean Christopherson
2022-03-02 19:08 ` Mingwei Zhang
2022-03-02 19:51 ` Sean Christopherson
2022-03-03 0:57 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 02/28] KVM: x86/mmu: Check for present SPTE when clearing dirty bit in TDP MMU Sean Christopherson
2022-03-02 19:50 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 03/28] KVM: x86/mmu: Fix wrong/misleading comments in TDP MMU fast zap Sean Christopherson
2022-02-28 23:15 ` Ben Gardon
2022-02-26 0:15 ` [PATCH v3 04/28] KVM: x86/mmu: Formalize TDP MMU's (unintended?) deferred TLB flush logic Sean Christopherson
2022-03-02 23:59 ` Mingwei Zhang
2022-03-03 0:12 ` Sean Christopherson
2022-03-03 1:20 ` Mingwei Zhang
2022-03-03 1:41 ` Sean Christopherson
2022-03-03 4:50 ` Mingwei Zhang
2022-03-03 16:45 ` Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 05/28] KVM: x86/mmu: Document that zapping invalidated roots doesn't need to flush Sean Christopherson
2022-02-28 23:17 ` Ben Gardon
2022-02-26 0:15 ` [PATCH v3 06/28] KVM: x86/mmu: Require mmu_lock be held for write in unyielding root iter Sean Christopherson
2022-02-28 23:26 ` Ben Gardon
2022-02-26 0:15 ` [PATCH v3 07/28] KVM: x86/mmu: Check for !leaf=>leaf, not PFN change, in TDP MMU SP removal Sean Christopherson
2022-03-01 0:11 ` Ben Gardon
2022-03-03 18:02 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 08/28] KVM: x86/mmu: Batch TLB flushes from TDP MMU for MMU notifier change_spte Sean Christopherson
2022-03-03 18:08 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 09/28] KVM: x86/mmu: Drop RCU after processing each root in MMU notifier hooks Sean Christopherson
2022-03-03 18:24 ` Mingwei Zhang
2022-03-03 18:32 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 10/28] KVM: x86/mmu: Add helpers to read/write TDP MMU SPTEs and document RCU Sean Christopherson
2022-03-03 18:34 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 11/28] KVM: x86/mmu: WARN if old _or_ new SPTE is REMOVED in non-atomic path Sean Christopherson
2022-03-03 18:37 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 12/28] KVM: x86/mmu: Refactor low-level TDP MMU set SPTE helper to take raw vals Sean Christopherson
2022-03-03 18:47 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 13/28] KVM: x86/mmu: Zap only the target TDP MMU shadow page in NX recovery Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 14/28] KVM: x86/mmu: Skip remote TLB flush when zapping all of TDP MMU Sean Christopherson
2022-03-01 0:19 ` Ben Gardon
2022-03-03 18:50 ` Mingwei Zhang
2022-02-26 0:15 ` [PATCH v3 15/28] KVM: x86/mmu: Add dedicated helper to zap TDP MMU root shadow page Sean Christopherson
2022-03-01 0:32 ` Ben Gardon
2022-03-03 21:19 ` Mingwei Zhang
2022-03-03 21:24 ` Mingwei Zhang
2022-03-03 23:06 ` Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 16/28] KVM: x86/mmu: Require mmu_lock be held for write to zap TDP MMU range Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 17/28] KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range() Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 18/28] KVM: x86/mmu: Do remote TLB flush before dropping RCU in TDP MMU resched Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 19/28] KVM: x86/mmu: Defer TLB flush to caller when freeing TDP MMU shadow pages Sean Christopherson
2022-02-26 0:15 ` Sean Christopherson [this message]
2022-03-01 18:21 ` [PATCH v3 20/28] KVM: x86/mmu: Allow yielding when zapping GFNs for defunct TDP MMU root Paolo Bonzini
2022-03-01 19:43 ` Sean Christopherson
2022-03-01 20:12 ` Paolo Bonzini
2022-03-02 2:13 ` Sean Christopherson
2022-03-02 14:54 ` Paolo Bonzini
2022-03-02 17:43 ` Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 21/28] KVM: x86/mmu: Zap roots in two passes to avoid inducing RCU stalls Sean Christopherson
2022-03-01 0:43 ` Ben Gardon
2022-02-26 0:15 ` [PATCH v3 22/28] KVM: x86/mmu: Zap defunct roots via asynchronous worker Sean Christopherson
2022-03-01 17:57 ` Ben Gardon
2022-03-02 17:25 ` Paolo Bonzini
2022-03-02 17:35 ` Sean Christopherson
2022-03-02 18:33 ` David Matlack
2022-03-02 18:36 ` Paolo Bonzini
2022-03-02 18:01 ` Sean Christopherson
2022-03-02 18:20 ` Paolo Bonzini
2022-03-02 19:33 ` Sean Christopherson
2022-03-02 20:14 ` Paolo Bonzini
2022-03-02 20:47 ` Sean Christopherson
2022-03-02 21:22 ` Paolo Bonzini
2022-03-02 22:25 ` Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 23/28] KVM: x86/mmu: Check for a REMOVED leaf SPTE before making the SPTE Sean Christopherson
2022-03-01 18:06 ` Ben Gardon
2022-02-26 0:15 ` [PATCH v3 24/28] KVM: x86/mmu: WARN on any attempt to atomically update REMOVED SPTE Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 25/28] KVM: selftests: Move raw KVM_SET_USER_MEMORY_REGION helper to utils Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 26/28] KVM: selftests: Split out helper to allocate guest mem via memfd Sean Christopherson
2022-02-28 23:36 ` David Woodhouse
2022-03-02 18:36 ` Paolo Bonzini
2022-03-02 21:55 ` David Woodhouse
2022-02-26 0:15 ` [PATCH v3 27/28] KVM: selftests: Define cpu_relax() helpers for s390 and x86 Sean Christopherson
2022-02-26 0:15 ` [PATCH v3 28/28] KVM: selftests: Add test to populate a VM with the max possible guest mem 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=20220226001546.360188-21-seanjc@google.com \
--to=seanjc@google.com \
--cc=bgardon@google.com \
--cc=borntraeger@linux.ibm.com \
--cc=david@redhat.com \
--cc=dmatlack@google.com \
--cc=frankja@linux.ibm.com \
--cc=imbrenda@linux.ibm.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mizhang@google.com \
--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).