KVM: x86: fix vcpu->mmio_fragments overflow

After commit b3356bf0 (KVM: emulator: optimize "rep ins" handling),
the pieces of io data can be collected and write them to the guest memory
or MMIO together

Unfortunately, kvm splits the mmio access into 8 bytes and store them to
vcpu->mmio_fragments. If the guest uses "rep ins" to move large data, it
will cause vcpu->mmio_fragments overflow

The bug can be exposed by isapc (-M isapc):

[23154.818733] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
[ ......]
[23154.858083] Call Trace:
[23154.859874]  [<ffffffffa04f0e17>] kvm_get_cr8+0x1d/0x28 [kvm]
[23154.861677]  [<ffffffffa04fa6d4>] kvm_arch_vcpu_ioctl_run+0xcda/0xe45 [kvm]
[23154.863604]  [<ffffffffa04f5a1a>] ? kvm_arch_vcpu_load+0x17b/0x180 [kvm]

Actually, we can use one mmio_fragment to store a large mmio access then
split it when we pass the mmio-exit-info to userspace. After that, we only
need two entries to store mmio info for the cross-mmio pages access
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/kvm/x86.c

@@ -3779,7 +3779,7 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 {
 	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
 
-	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3832,18 +3832,11 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 	bytes -= handled;
 	val += handled;
 
-	while (bytes) {
-		unsigned now = min(bytes, 8U);
-
+	WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
 	frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
 	frag->gpa = gpa;
 	frag->data = val;
-		frag->len = now;
-
-		gpa += now;
-		val += now;
-		bytes -= now;
-	}
+	frag->len = bytes;
 	return X86EMUL_CONTINUE;
 }
 
@@ -3890,7 +3883,7 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_cur_fragment = 0;
 
-	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
 	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
 	vcpu->run->exit_reason = KVM_EXIT_MMIO;
 	vcpu->run->mmio.phys_addr = gpa;
@@ -5522,6 +5515,7 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
  *
  * read:
  *   for each fragment
+ *     for each mmio piece in the fragment
  *       write gpa, len
  *       exit
  *       copy data
@@ -5529,6 +5523,7 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
  *
  * write:
  *   for each fragment
+ *     for each mmio piece in the fragment
  *       write gpa, len
  *       copy data
  *       exit
@@ -5537,13 +5532,27 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	struct kvm_mmio_fragment *frag;
+	unsigned len;
 
 	BUG_ON(!vcpu->mmio_needed);
 
 	/* Complete previous fragment */
-	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
 	if (!vcpu->mmio_is_write)
-		memcpy(frag->data, run->mmio.data, frag->len);
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 		if (vcpu->mmio_is_write)
@@ -5551,13 +5560,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		vcpu->mmio_read_completed = 1;
 		return complete_emulated_io(vcpu);
 	}
-	/* Initiate next fragment */
-	++frag;
+
 	run->exit_reason = KVM_EXIT_MMIO;
 	run->mmio.phys_addr = frag->gpa;
 	if (vcpu->mmio_is_write)
-		memcpy(run->mmio.data, frag->data, frag->len);
-	run->mmio.len = frag->len;
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->mmio.len = min(8u, frag->len);
 	run->mmio.is_write = vcpu->mmio_is_write;
 	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	return 0;

include/linux/kvm_host.h

@@ -42,19 +42,8 @@
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
 
-/*
- * If we support unaligned MMIO, at most one fragment will be split into two:
- */
-#ifdef KVM_UNALIGNED_MMIO
-#  define KVM_EXTRA_MMIO_FRAGMENTS 1
-#else
-#  define KVM_EXTRA_MMIO_FRAGMENTS 0
-#endif
-
-#define KVM_USER_MMIO_SIZE 8
-
-#define KVM_MAX_MMIO_FRAGMENTS \
-	(KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
+/* Two fragments for cross MMIO pages. */
+#define KVM_MAX_MMIO_FRAGMENTS	2
 
 /*
  * For the normal pfn, the highest 12 bits should be zero,