lib/crc: x86: Reorganize crc-pclmul static_call initialization

Reorganize the crc-pclmul static_call initialization to place more of
the logic in the *_mod_init_arch() functions instead of in the
INIT_CRC_PCLMUL macro. This provides the flexibility to do more than a
single static_call update for each CPU feature check. Right away,
optimize crc64_mod_init_arch() to check the CPU features just once
instead of twice, doing both the crc64_msb and crc64_lsb static_call
updates together. A later commit will also use this to initialize an
additional static_key when crc32_lsb_vpclmul_avx512() is enabled.

Acked-by: Ard Biesheuvel <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Eric Biggers <[e-mail]>

lib/crc/x86/crc-pclmul-template.h

···
 			      const void *consts_ptr);			\
 DEFINE_STATIC_CALL(prefix##_pclmul, prefix##_pclmul_sse)
 
-#define INIT_CRC_PCLMUL(prefix)						\
-do {									\
-	if (boot_cpu_has(X86_FEATURE_VPCLMULQDQ) &&			\
-	    boot_cpu_has(X86_FEATURE_AVX2) &&				\
-	    cpu_has_xfeatures(XFEATURE_MASK_YMM, NULL)) {		\
-		if (boot_cpu_has(X86_FEATURE_AVX512BW) &&		\
-		    boot_cpu_has(X86_FEATURE_AVX512VL) &&		\
-		    !boot_cpu_has(X86_FEATURE_PREFER_YMM) &&		\
-		    cpu_has_xfeatures(XFEATURE_MASK_AVX512, NULL)) {	\
-			static_call_update(prefix##_pclmul,		\
-					   prefix##_vpclmul_avx512);	\
-		} else {						\
-			static_call_update(prefix##_pclmul,		\
-					   prefix##_vpclmul_avx2);	\
-		}							\
-	}								\
-} while (0)
+static inline bool have_vpclmul(void)
+{
+	return boot_cpu_has(X86_FEATURE_VPCLMULQDQ) &&
+	       boot_cpu_has(X86_FEATURE_AVX2) &&
+	       cpu_has_xfeatures(XFEATURE_MASK_YMM, NULL);
+}
+
+static inline bool have_avx512(void)
+{
+	return boot_cpu_has(X86_FEATURE_AVX512BW) &&
+	       boot_cpu_has(X86_FEATURE_AVX512VL) &&
+	       !boot_cpu_has(X86_FEATURE_PREFER_YMM) &&
+	       cpu_has_xfeatures(XFEATURE_MASK_AVX512, NULL);
+}
 
 /*
  * Call a [V]PCLMULQDQ optimized CRC function if the data length is at least 16

lib/crc/x86/crc-t10dif.h

···
 {
 	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
 		static_branch_enable(&have_pclmulqdq);
-		INIT_CRC_PCLMUL(crc16_msb);
+		if (have_vpclmul()) {
+			if (have_avx512())
+				static_call_update(crc16_msb_pclmul,
+						   crc16_msb_vpclmul_avx512);
+			else
+				static_call_update(crc16_msb_pclmul,
+						   crc16_msb_vpclmul_avx2);
+		}
 	}
 }

lib/crc/x86/crc32.h

···
 		static_branch_enable(&have_crc32);
 	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
 		static_branch_enable(&have_pclmulqdq);
-		INIT_CRC_PCLMUL(crc32_lsb);
+		if (have_vpclmul()) {
+			if (have_avx512()) {
+				static_call_update(crc32_lsb_pclmul,
+						   crc32_lsb_vpclmul_avx512);
+			} else {
+				static_call_update(crc32_lsb_pclmul,
+						   crc32_lsb_vpclmul_avx2);
+			}
+		}
 	}
 }
 

lib/crc/x86/crc64.h

···
 {
 	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
 		static_branch_enable(&have_pclmulqdq);
-		INIT_CRC_PCLMUL(crc64_msb);
-		INIT_CRC_PCLMUL(crc64_lsb);
+		if (have_vpclmul()) {
+			if (have_avx512()) {
+				static_call_update(crc64_msb_pclmul,
+						   crc64_msb_vpclmul_avx512);
+				static_call_update(crc64_lsb_pclmul,
+						   crc64_lsb_vpclmul_avx512);
+			} else {
+				static_call_update(crc64_msb_pclmul,
+						   crc64_msb_vpclmul_avx2);
+				static_call_update(crc64_lsb_pclmul,
+						   crc64_lsb_vpclmul_avx2);
+			}
+		}
 	}
 }