KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Sean Christopherson <seanjc@google.com>
To: Marc Zyngier <maz@kernel.org>,
	Huacai Chen <chenhuacai@kernel.org>,
	Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>,
	Paul Mackerras <paulus@ozlabs.org>,
	Paolo Bonzini <pbonzini@redhat.com>
Cc: James Morse <james.morse@arm.com>,
	Julien Thierry <julien.thierry.kdev@gmail.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	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>,
	linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, linux-mips@vger.kernel.org,
	kvm@vger.kernel.org, kvm-ppc@vger.kernel.org,
	linux-kernel@vger.kernel.org, Ben Gardon <bgardon@google.com>
Subject: [PATCH v2 07/10] KVM: Move MMU notifier's mmu_lock acquisition into common helper
Date: Thu,  1 Apr 2021 17:56:55 -0700
Message-ID: <20210402005658.3024832-8-seanjc@google.com> (raw)
In-Reply-To: <20210402005658.3024832-1-seanjc@google.com>

Acquire and release mmu_lock in the __kvm_handle_hva_range() helper
instead of requiring the caller to do the same.  This paves the way for
future patches to take mmu_lock if and only if an overlapping memslot is
found, without also having to introduce the on_lock() shenanigans used
to manipulate the notifier count and sequence.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---

Note, the WARN_ON_ONCE that asserts on_lock and handler aren't both null
is optimized out of all functions on recent gcc (for x86).  I wanted to
make it a BUILD_BUG_ON, but older versions of gcc aren't agressive/smart
enough to optimize it out, and using __builtin_constant_p() to get it to
build on older compilers prevents the assertion from firing on newer
compilers when given bad input.

I'm also a-ok dropping the check altogether, it just felt wrong having
the semi-funky on_lock -> !handler combo without documenting that handler
isn't allowed to be null in the common case.

 virt/kvm/kvm_main.c | 125 +++++++++++++++++++++++++++++---------------
 1 file changed, 82 insertions(+), 43 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2e809d73c7f1..25ecb5235e17 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -453,28 +453,57 @@ static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
 
 typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
+typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
+			     unsigned long end);
+
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
 	pte_t pte;
 	hva_handler_t handler;
+	on_lock_fn_t on_lock;
 	bool flush_on_ret;
 	bool may_block;
 };
 
+/*
+ * Use a dedicated stub instead of NULL to indicate that there is no callback
+ * function/handler.  The compiler technically can't guarantee that a real
+ * function will have a non-zero address, and so it will generate code to
+ * check for !NULL, whereas comparing against a stub will be elided at compile
+ * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
+ */
+static void kvm_null_fn(void)
+{
+
+}
+#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
+
 static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 						  const struct kvm_hva_range *range)
 {
-	struct kvm_memory_slot *slot;
-	struct kvm_memslots *slots;
 	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
 	bool ret = false;
 	int i, idx;
 
-	lockdep_assert_held_write(&kvm->mmu_lock);
+	/* A null handler is allowed if and only if on_lock() is provided. */
+	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
+			 IS_KVM_NULL_FN(range->handler)))
+		return 0;
+
+	KVM_MMU_LOCK(kvm);
 
 	idx = srcu_read_lock(&kvm->srcu);
 
+	if (!IS_KVM_NULL_FN(range->on_lock)) {
+		range->on_lock(kvm, range->start, range->end);
+
+		if (IS_KVM_NULL_FN(range->handler))
+			goto out_unlock;
+	}
+
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		slots = __kvm_memslots(kvm, i);
 		kvm_for_each_memslot(slot, slots) {
@@ -510,6 +539,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && (ret || kvm->tlbs_dirty))
 		kvm_flush_remote_tlbs(kvm);
 
+out_unlock:
+	KVM_MMU_UNLOCK(kvm);
+
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	/* The notifiers are averse to booleans. :-( */
@@ -528,16 +560,12 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.end		= end,
 		.pte		= pte,
 		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
-	int ret;
 
-	KVM_MMU_LOCK(kvm);
-	ret = __kvm_handle_hva_range(kvm, &range);
-	KVM_MMU_UNLOCK(kvm);
-
-	return ret;
+	return __kvm_handle_hva_range(kvm, &range);
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
@@ -551,16 +579,12 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.end		= end,
 		.pte		= __pte(0),
 		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
-	int ret;
 
-	KVM_MMU_LOCK(kvm);
-	ret = __kvm_handle_hva_range(kvm, &range);
-	KVM_MMU_UNLOCK(kvm);
-
-	return ret;
+	return __kvm_handle_hva_range(kvm, &range);
 }
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
@@ -581,22 +605,9 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
 }
 
-static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
-					const struct mmu_notifier_range *range)
+static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
-		.start		= range->start,
-		.end		= range->end,
-		.pte		= __pte(0),
-		.handler	= kvm_unmap_gfn_range,
-		.flush_on_ret	= true,
-		.may_block	= mmu_notifier_range_blockable(range),
-	};
-
-	trace_kvm_unmap_hva_range(range->start, range->end);
-
-	KVM_MMU_LOCK(kvm);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
@@ -604,8 +615,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 */
 	kvm->mmu_notifier_count++;
 	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = range->start;
-		kvm->mmu_notifier_range_end = range->end;
+		kvm->mmu_notifier_range_start = start;
+		kvm->mmu_notifier_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has dimishing
@@ -617,24 +628,36 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		 * complete.
 		 */
 		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, range->start);
+			min(kvm->mmu_notifier_range_start, start);
 		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, range->end);
+			max(kvm->mmu_notifier_range_end, end);
 	}
-
-	__kvm_handle_hva_range(kvm, &hva_range);
-
-	KVM_MMU_UNLOCK(kvm);
-
-	return 0;
 }
 
-static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= kvm_unmap_gfn_range,
+		.on_lock	= kvm_inc_notifier_count,
+		.flush_on_ret	= true,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
 
-	KVM_MMU_LOCK(kvm);
+	trace_kvm_unmap_hva_range(range->start, range->end);
+
+	__kvm_handle_hva_range(kvm, &hva_range);
+
+	return 0;
+}
+
+static void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
+{
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -648,7 +671,23 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 * in conjunction with the smp_rmb in mmu_notifier_retry().
 	 */
 	kvm->mmu_notifier_count--;
-	KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+					const struct mmu_notifier_range *range)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= (void *)kvm_null_fn,
+		.on_lock	= kvm_dec_notifier_count,
+		.flush_on_ret	= true,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
+
+	__kvm_handle_hva_range(kvm, &hva_range);
 
 	BUG_ON(kvm->mmu_notifier_count < 0);
 }
-- 
2.31.0.208.g409f899ff0-goog


  parent reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-02  0:56 [PATCH v2 00/10] KVM: Consolidate and optimize MMU notifiers Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 01/10] KVM: Assert that notifier count is elevated in .change_pte() Sean Christopherson
2021-04-02 11:08   ` Paolo Bonzini
2021-04-02  0:56 ` [PATCH v2 02/10] KVM: Move x86's MMU notifier memslot walkers to generic code Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 03/10] KVM: arm64: Convert to the gfn-based MMU notifier callbacks Sean Christopherson
2021-04-12 10:12   ` Marc Zyngier
2021-04-02  0:56 ` [PATCH v2 04/10] KVM: MIPS/MMU: " Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 05/10] KVM: PPC: " Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 06/10] KVM: Kill off the old hva-based " Sean Christopherson
2021-04-02  0:56 ` Sean Christopherson [this message]
2021-04-02  9:35   ` [PATCH v2 07/10] KVM: Move MMU notifier's mmu_lock acquisition into common helper Paolo Bonzini
2021-04-02 14:59     ` Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 08/10] KVM: Take mmu_lock when handling MMU notifier iff the hva hits a memslot Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 09/10] KVM: Don't take mmu_lock for range invalidation unless necessary Sean Christopherson
2021-04-02  9:34   ` Paolo Bonzini
2021-04-02 14:59     ` Sean Christopherson
2021-04-19  8:49   ` Wanpeng Li
2021-04-19 13:50     ` Paolo Bonzini
2021-04-19 15:09       ` Sean Christopherson
2021-04-19 22:09         ` Paolo Bonzini
2021-04-20  1:17           ` Sean Christopherson
2021-04-02  0:56 ` [PATCH v2 10/10] KVM: x86/mmu: Allow yielding during MMU notifier unmap/zap, if possible Sean Christopherson
2021-04-02 12:17 ` [PATCH v2 00/10] KVM: Consolidate and optimize MMU notifiers Paolo Bonzini
2021-04-12 10:27   ` Marc Zyngier

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=20210402005658.3024832-8-seanjc@google.com \
    --to=seanjc@google.com \
    --cc=aleksandar.qemu.devel@gmail.com \
    --cc=bgardon@google.com \
    --cc=chenhuacai@kernel.org \
    --cc=james.morse@arm.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=julien.thierry.kdev@gmail.com \
    --cc=kvm-ppc@vger.kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=paulus@ozlabs.org \
    --cc=pbonzini@redhat.com \
    --cc=suzuki.poulose@arm.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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git