Merge tag 'x86-urgent-2022-04-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of x86 fixes and updates:

   - Make the prctl() for enabling dynamic XSTATE components correct so
     it adds the newly requested feature to the permission bitmap
     instead of overwriting it. Add a selftest which validates that.

   - Unroll string MMIO for encrypted SEV guests as the hypervisor
     cannot emulate it.

   - Handle supervisor states correctly in the FPU/XSTATE code so it
     takes the feature set of the fpstate buffer into account. The
     feature sets can differ between host and guest buffers. Guest
     buffers do not contain supervisor states. So far this was not an
     issue, but with enabling PASID it needs to be handled in the buffer
     offset calculation and in the permission bitmaps.

   - Avoid a gazillion of repeated CPUID invocations in by caching the
     values early in the FPU/XSTATE code.

   - Enable CONFIG_WERROR in x86 defconfig.

   - Make the X86 defconfigs more useful by adapting them to Y2022
     reality"

* tag 'x86-urgent-2022-04-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu/xstate: Consolidate size calculations
  x86/fpu/xstate: Handle supervisor states in XSTATE permissions
  x86/fpu/xsave: Handle compacted offsets correctly with supervisor states
  x86/fpu: Cache xfeature flags from CPUID
  x86/fpu/xsave: Initialize offset/size cache early
  x86/fpu: Remove unused supervisor only offsets
  x86/fpu: Remove redundant XCOMP_BV initialization
  x86/sev: Unroll string mmio with CC_ATTR_GUEST_UNROLL_STRING_IO
  x86/config: Make the x86 defconfigs a bit more usable
  x86/defconfig: Enable WERROR
  selftests/x86/amx: Update the ARCH_REQ_XCOMP_PERM test
  x86/fpu/xstate: Fix the ARCH_REQ_XCOMP_PERM implementation

1 files changed, 57 insertions, 8 deletions

diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index df50451d94ef..3e2f33fc33de 100644
--- a/arch/x86/lib/iomem.c
+++ b/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);