Merge branch 'kvm-no-struct-page' into HEAD

TL;DR: Eliminate KVM's long-standing (and heinous) behavior of essentially
guessing which pfns are refcounted pages (see kvm_pfn_to_refcounted_page()).

Getting there requires "fixing" arch code that isn't obviously broken.
Specifically, to get rid of kvm_pfn_to_refcounted_page(), KVM needs to
stop marking pages/folios dirty/accessed based solely on the pfn that's
stored in KVM's stage-2 page tables.

Instead of tracking which SPTEs correspond to refcounted pages, simply
remove all of the code that operates on "struct page" based ona the pfn
in stage-2 PTEs.  This is the back ~40-50% of the series.

For x86 in particular, which sets accessed/dirty status when that info
would be "lost", e.g. when SPTEs are zapped or KVM clears the dirty flag
in a SPTE, foregoing the updates provides very measurable performance
improvements for related operations.  E.g. when clearing dirty bits as
part of dirty logging, and zapping SPTEs to reconstitue huge pages when
disabling dirty logging.

The front ~40% of the series is cleanups and prep work, and most of it is
x86 focused (purely because x86 added the most special cases, *sigh*).
E.g. several of the inputs to hva_to_pfn() (and it's myriad wrappers),
can be removed by cleaning up and deduplicating x86 code.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 8 insertions, 18 deletions

diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index c17157e700c0..d2c3b6b41f18 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -484,8 +484,6 @@ static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa,
 	struct kvm *kvm = vcpu->kvm;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	pte_t *ptep;
-	kvm_pfn_t pfn = 0;	/* silence bogus GCC warning */
-	bool pfn_valid = false;
 	int ret = 0;
 
 	spin_lock(&kvm->mmu_lock);
@@ -498,12 +496,9 @@ static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa,
 	}
 
 	/* Track access to pages marked old */
-	if (!pte_young(*ptep)) {
+	if (!pte_young(*ptep))
 		set_pte(ptep, pte_mkyoung(*ptep));
-		pfn = pte_pfn(*ptep);
-		pfn_valid = true;
-		/* call kvm_set_pfn_accessed() after unlock */
-	}
+
 	if (write_fault && !pte_dirty(*ptep)) {
 		if (!pte_write(*ptep)) {
 			ret = -EFAULT;
@@ -512,9 +507,7 @@ static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa,
 
 		/* Track dirtying of writeable pages */
 		set_pte(ptep, pte_mkdirty(*ptep));
-		pfn = pte_pfn(*ptep);
 		mark_page_dirty(kvm, gfn);
-		kvm_set_pfn_dirty(pfn);
 	}
 
 	if (out_entry)
@@ -524,8 +517,6 @@ static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa,
 
 out:
 	spin_unlock(&kvm->mmu_lock);
-	if (pfn_valid)
-		kvm_set_pfn_accessed(pfn);
 	return ret;
 }
 
@@ -566,6 +557,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
 	bool writeable;
 	unsigned long prot_bits;
 	unsigned long mmu_seq;
+	struct page *page;
 
 	/* Try the fast path to handle old / clean pages */
 	srcu_idx = srcu_read_lock(&kvm->srcu);
@@ -587,7 +579,7 @@ retry:
 	mmu_seq = kvm->mmu_invalidate_seq;
 	/*
 	 * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads
-	 * in gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
+	 * in kvm_faultin_pfn() (which calls get_user_pages()), so that we don't
 	 * risk the page we get a reference to getting unmapped before we have a
 	 * chance to grab the mmu_lock without mmu_invalidate_retry() noticing.
 	 *
@@ -599,7 +591,7 @@ retry:
 	smp_rmb();
 
 	/* Slow path - ask KVM core whether we can access this GPA */
-	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writeable);
+	pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writeable, &page);
 	if (is_error_noslot_pfn(pfn)) {
 		err = -EFAULT;
 		goto out;
@@ -611,10 +603,10 @@ retry:
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by
-		 * gfn_to_pfn_prot().
+		 * kvm_faultin_pfn().
 		 */
 		spin_unlock(&kvm->mmu_lock);
-		kvm_release_pfn_clean(pfn);
+		kvm_release_page_unused(page);
 		goto retry;
 	}
 
@@ -628,7 +620,6 @@ retry:
 		if (write_fault) {
 			prot_bits |= __WRITEABLE;
 			mark_page_dirty(kvm, gfn);
-			kvm_set_pfn_dirty(pfn);
 		}
 	}
 	entry = pfn_pte(pfn, __pgprot(prot_bits));
@@ -642,9 +633,8 @@ retry:
 	if (out_buddy)
 		*out_buddy = *ptep_buddy(ptep);
 
+	kvm_release_faultin_page(kvm, page, false, writeable);
 	spin_unlock(&kvm->mmu_lock);
-	kvm_release_pfn_clean(pfn);
-	kvm_set_pfn_accessed(pfn);
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return err;