[PATCH v2 2/8] um: Check for missing AVX and AVX-512 xstate bits

If the CPU declares AVX or AVX-512 support, verify that all the
corresponding bits are set in the XCR0 register.  If any are missing,
warn and don't set the corresponding X86_FEATURE_* flags.

This eliminates the perceived need for UML-supporting AVX and AVX-512
optimized code in the kernel (that is, lib/raid/ currently) to start
checking the XCR0 bits in addition to X86_FEATURE_AVX*.

This aligns UML with the vast majority of userspace programs, which
check the XCR0 bits before considering AVX and AVX-512 to be supported,
as per the procedure documented in Intel's CPU manual.

Signed-off-by: Eric Biggers <[email protected]>
---
 arch/um/kernel/um_arch.c | 78 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 77 insertions(+), 1 deletion(-)

diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 2141f5f1f5a20..aafbaef2ae82f 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -264,12 +264,88 @@ unsigned long brk_start;
 
 #define MIN_VMALLOC (32 * 1024 * 1024)
 
+static u64 __init read_xcr0(void)
+{
+	u32 a, b, c, d;
+
+	asm volatile("cpuid"
+		     : "=a"(a), "=b"(b), "=c"(c), "=d"(d)
+		     : "a"(0), "c"(0));
+	if (a >= 1) { /* max_leaf >= 1 */
+		asm volatile("cpuid"
+			     : "=a"(a), "=b"(b), "=c"(c), "=d"(d)
+			     : "a"(1), "c"(0));
+		if (c & (1 << 27)) { /* XSAVE enabled by OS */
+			asm volatile("xgetbv" : "=d"(d), "=a"(a) : "c"(0));
+			return ((u64)d << 32) | a;
+		}
+	}
+	return 0;
+}
+
+static void __init validate_and_set_cpu_cap(int cap, u64 xcr0)
+{
+	/*
+	 * Check for missing xstate features right away, so that there's no
+	 * perceived need for all optimized code in the kernel to do so.
+	 */
+	switch (cap) {
+	case X86_FEATURE_AVX:
+	case X86_FEATURE_AVX2:
+	case X86_FEATURE_AVX_VNNI:
+	case X86_FEATURE_FMA:
+	case X86_FEATURE_VAES:
+	case X86_FEATURE_VPCLMULQDQ:
+		if ((xcr0 & 0x7) != 0x7) {
+			static bool warned;
+
+			if (!warned) {
+				os_warn("Disabling AVX support due to missing xstate features\n");
+				warned = true;
+			}
+			return;
+		}
+		break;
+	case X86_FEATURE_AVX512F:
+	case X86_FEATURE_AVX512BW:
+	case X86_FEATURE_AVX512CD:
+	case X86_FEATURE_AVX512DQ:
+	case X86_FEATURE_AVX512ER:
+	case X86_FEATURE_AVX512IFMA:
+	case X86_FEATURE_AVX512PF:
+	case X86_FEATURE_AVX512VBMI:
+	case X86_FEATURE_AVX512VL:
+	case X86_FEATURE_AVX512_4FMAPS:
+	case X86_FEATURE_AVX512_4VNNIW:
+	case X86_FEATURE_AVX512_BF16:
+	case X86_FEATURE_AVX512_BITALG:
+	case X86_FEATURE_AVX512_FP16:
+	case X86_FEATURE_AVX512_VBMI2:
+	case X86_FEATURE_AVX512_VNNI:
+	case X86_FEATURE_AVX512_VP2INTERSECT:
+	case X86_FEATURE_AVX512_VPOPCNTDQ:
+		if ((xcr0 & 0xe7) != 0xe7) {
+			static bool warned;
+
+			if (!warned) {
+				os_warn("Disabling AVX-512 support due to missing xstate features\n");
+				warned = true;
+			}
+			return;
+		}
+		break;
+	}
+	set_cpu_cap(&boot_cpu_data, cap);
+}
+
 static void __init parse_host_cpu_flags(char *line)
 {
+	u64 xcr0 = read_xcr0();
 	int i;
+
 	for (i = 0; i < 32*NCAPINTS; i++) {
 		if ((x86_cap_flags[i] != NULL) && strstr(line, x86_cap_flags[i]))
-			set_cpu_cap(&boot_cpu_data, i);
+			validate_and_set_cpu_cap(i, xcr0);
 	}
 }
 
-- 
2.55.0