x86/sev: Unroll string mmio with CC_ATTR_GUEST_UNROLL_STRING_IO

The io-specific memcpy/memset functions use string mmio accesses to do
their work. Under SEV, the hypervisor can't emulate these instructions
because they read/write directly from/to encrypted memory.

KVM will inject a page fault exception into the guest when it is asked
to emulate string mmio instructions for an SEV guest:

  BUG: unable to handle page fault for address: ffffc90000065068
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 8000100000067 P4D 8000100000067 PUD 80001000fb067 PMD 80001000fc067 PTE 80000000fed40173
  Oops: 0000 [#1] PREEMPT SMP NOPTI
  CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-rc7 #3

As string mmio for an SEV guest can not be supported by the
hypervisor, unroll the instructions for CC_ATTR_GUEST_UNROLL_STRING_IO
enabled kernels.

This issue appears when kernels are launched in recent libvirt-managed
SEV virtual machines, because virt-install started to add a tpm-crb
device to the guest by default and proactively because, raisins:

  eb58c09f48

and as that commit says, the default adding of a TPM can be disabled
with "virt-install ... --tpm none".

The kernel driver for tpm-crb uses memcpy_to/from_io() functions to
access MMIO memory, resulting in a page-fault injected by KVM and
crashing the kernel at boot.

  [ bp: Massage and extend commit message. ]

Fixes: d8aa7eea78 ('x86/mm: Add Secure Encrypted Virtualization (SEV) support')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20220321093351.23976-1-joro@8bytes.org

arch/x86/lib/iomem.c

@@ -22,7 +22,7 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
 		     : "memory");
 }
 
-void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -38,9 +38,8 @@ void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 	}
 	rep_movs(to, (const void *)from, n);
 }
-EXPORT_SYMBOL(memcpy_fromio);
 
-void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 {
 	if (unlikely(!n))
 		return;
@@ -56,14 +55,64 @@ void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 	}
 	rep_movs((void *)to, (const void *) from, n);
 }
+
+static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	const volatile char __iomem *in = from;
+	char *out = to;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		out[i] = readb(&in[i]);
+}
+
+static void unrolled_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	volatile char __iomem *out = to;
+	const char *in = from;
+	int i;
+
+	for (i = 0; i < n; ++i)
+		writeb(in[i], &out[i]);
+}
+
+static void unrolled_memset_io(volatile void __iomem *a, int b, size_t c)
+{
+	volatile char __iomem *mem = a;
+	int i;
+
+	for (i = 0; i < c; ++i)
+		writeb(b, &mem[i]);
+}
+
+void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_fromio(to, from, n);
+	else
+		string_memcpy_fromio(to, from, n);
+}
+EXPORT_SYMBOL(memcpy_fromio);
+
+void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+		unrolled_memcpy_toio(to, from, n);
+	else
+		string_memcpy_toio(to, from, n);
+}
 EXPORT_SYMBOL(memcpy_toio);
 
 void memset_io(volatile void __iomem *a, int b, size_t c)
 {
-	/*
-	 * TODO: memset can mangle the IO patterns quite a bit.
-	 * perhaps it would be better to use a dumb one:
-	 */
-	memset((void *)a, b, c);
+	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {
+		unrolled_memset_io(a, b, c);
+	} else {
+		/*
+		 * TODO: memset can mangle the IO patterns quite a bit.
+		 * perhaps it would be better to use a dumb one:
+		 */
+		memset((void *)a, b, c);
+	}
 }
 EXPORT_SYMBOL(memset_io);