[PATCH v2 3/5] KVM: x86: Use __try_cmpxchg_user() to update guest PTE A/D bits

From: Sean Christopherson <seanjc@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
	Nathan Chancellor <nathan@kernel.org>,
	 Nick Desaulniers <ndesaulniers@google.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>,
	kvm@vger.kernel.org, llvm@lists.linux.dev,
	 linux-kernel@vger.kernel.org,
	Peter Zijlstra <peterz@infradead.org>,
	 Tadeusz Struk <tadeusz.struk@linaro.org>,
	 syzbot+6cde2282daa792c49ab8@syzkaller.appspotmail.com
Subject: [PATCH v2 3/5] KVM: x86: Use __try_cmpxchg_user() to update guest PTE A/D bits
Date: Wed,  2 Feb 2022 00:49:43 +0000	[thread overview]
Message-ID: <20220202004945.2540433-4-seanjc@google.com> (raw)
In-Reply-To: <20220202004945.2540433-1-seanjc@google.com>

Use the recently introduced __try_cmpxchg_user() to update guest PTE A/D
bits instead of mapping the PTE into kernel address space.  The VM_PFNMAP
path is broken as it assumes that vm_pgoff is the base pfn of the mapped
VMA range, which is conceptually wrong as vm_pgoff is the offset relative
to the file and has nothing to do with the pfn.  The horrific hack worked
for the original use case (backing guest memory with /dev/mem), but leads
to accessing "random" pfns for pretty much any other VM_PFNMAP case.

Fixes: bd53cb35a3e9 ("X86/KVM: Handle PFNs outside of kernel reach when touching GPTEs")
Debugged-by: Tadeusz Struk <tadeusz.struk@linaro.org>
Tested-by: Tadeusz Struk <tadeusz.struk@linaro.org>
Reported-by: syzbot+6cde2282daa792c49ab8@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/paging_tmpl.h | 45 +---------------------------------
 1 file changed, 1 insertion(+), 44 deletions(-)

diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5b5bdac97c7b..551de15f342f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -143,49 +143,6 @@ static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
 	       FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
 }
 
-static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-			       pt_element_t __user *ptep_user, unsigned index,
-			       pt_element_t orig_pte, pt_element_t new_pte)
-{
-	int npages;
-	pt_element_t ret;
-	pt_element_t *table;
-	struct page *page;
-
-	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
-	if (likely(npages == 1)) {
-		table = kmap_atomic(page);
-		ret = CMPXCHG(&table[index], orig_pte, new_pte);
-		kunmap_atomic(table);
-
-		kvm_release_page_dirty(page);
-	} else {
-		struct vm_area_struct *vma;
-		unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
-		unsigned long pfn;
-		unsigned long paddr;
-
-		mmap_read_lock(current->mm);
-		vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
-		if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
-			mmap_read_unlock(current->mm);
-			return -EFAULT;
-		}
-		pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		paddr = pfn << PAGE_SHIFT;
-		table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
-		if (!table) {
-			mmap_read_unlock(current->mm);
-			return -EFAULT;
-		}
-		ret = CMPXCHG(&table[index], orig_pte, new_pte);
-		memunmap(table);
-		mmap_read_unlock(current->mm);
-	}
-
-	return (ret != orig_pte);
-}
-
 static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
@@ -284,7 +241,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 		if (unlikely(!walker->pte_writable[level - 1]))
 			continue;
 
-		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
+		ret = __try_cmpxchg_user(ptep_user, &orig_pte, pte, fault);
 		if (ret)
 			return ret;
 
-- 
2.35.0.rc2.247.g8bbb082509-goog

