diff mbox series

[v3,1/5] riscv: Checksum header

Message ID 20230907-optimize_checksum-v3-1-c502d34d9d73@rivosinc.com (mailing list archive)
State Superseded
Headers show
Series riscv: Add fine-tuned checksum functions | expand

Checks

Context Check Description
conchuod/cover_letter success Series has a cover letter
conchuod/tree_selection success Guessed tree name to be for-next at HEAD accb14aa1e69
conchuod/fixes_present success Fixes tag not required for -next series
conchuod/maintainers_pattern success MAINTAINERS pattern errors before the patch: 2 and now 2
conchuod/verify_signedoff success Signed-off-by tag matches author and committer
conchuod/kdoc success Errors and warnings before: 0 this patch: 0
conchuod/build_rv64_clang_allmodconfig fail Errors and warnings before: 9 this patch: 1506
conchuod/module_param success Was 0 now: 0
conchuod/build_rv64_gcc_allmodconfig fail Errors and warnings before: 9 this patch: 231
conchuod/build_rv32_defconfig success Build OK
conchuod/dtb_warn_rv64 success Errors and warnings before: 39 this patch: 39
conchuod/header_inline success No static functions without inline keyword in header files
conchuod/checkpatch warning WARNING: Avoid line continuations in quoted strings WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: do not add new typedefs WARNING: unnecessary whitespace before a quoted newline
conchuod/build_rv64_nommu_k210_defconfig success Build OK
conchuod/verify_fixes success No Fixes tag
conchuod/build_rv64_nommu_virt_defconfig success Build OK

Commit Message

Charlie Jenkins Sept. 8, 2023, 5:14 a.m. UTC
Provide checksum algorithms that have been designed to leverage riscv
instructions such as rotate. In 64-bit, can take advantage of the larger
register to avoid some overflow checking.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/riscv/include/asm/checksum.h | 94 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 000000000000..bddfc571f93f
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,94 @@ 
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * IP checksum routines
+ *
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#ifndef __ASM_RISCV_CHECKSUM_H
+#define __ASM_RISCV_CHECKSUM_H
+
+#include <linux/in6.h>
+#include <linux/uaccess.h>
+
+#ifdef CONFIG_32BIT
+typedef unsigned int csum_t;
+#else
+typedef unsigned long csum_t;
+#endif
+
+/*
+ *	Fold a partial checksum without adding pseudo headers
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+	sum += (sum >> 16) | (sum << 16);
+	return (__force __sum16)(~(sum >> 16));
+}
+
+#define csum_fold csum_fold
+
+/*
+ * Quickly compute an IP checksum with the assumption that IPv4 headers will
+ * always be in multiples of 32-bits, and have an ihl of at least 5.
+ * @ihl is the number of 32 bit segments and must be greater than or equal to 5.
+ * @iph is assumed to be word aligned.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	csum_t csum = 0;
+	int pos = 0;
+
+	do {
+		csum += ((const unsigned int *)iph)[pos];
+		if (IS_ENABLED(CONFIG_32BIT))
+			csum += csum < ((const unsigned int *)iph)[pos];
+	} while (++pos < ihl);
+
+	/*
+	 * ZBB only saves three instructions on 32-bit and five on 64-bit so not
+	 * worth checking if supported without Alternatives.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
+	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		csum_t fold_temp;
+
+		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+					      RISCV_ISA_EXT_ZBB, 1)
+		    :
+		    :
+		    :
+		    : no_zbb);
+
+		if (IS_ENABLED(CONFIG_32BIT)) {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				rori	%[fold_temp],%[csum],16		\n\
+				add	%[csum],%[fold_temp],%[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		} else {
+			asm(".option push				\n\
+			.option arch,+zbb				\n\
+				rori	%[fold_temp], %[csum], 32	\n\
+				add	%[csum], %[fold_temp], %[csum]	\n\
+				srli	%[csum], %[csum], 32		\n\
+				roriw	%[fold_temp], %[csum], 16	\n\
+				addw	%[csum], %[fold_temp], %[csum]	\n\
+			.option pop"
+			: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+		}
+		return ~(csum >> 16);
+	}
+no_zbb:
+#ifndef CONFIG_32BIT
+		csum += (csum >> 32) | (csum << 32);
+		csum >>= 32;
+#endif
+	return csum_fold((__force __wsum)csum);
+}
+
+#define ip_fast_csum ip_fast_csum
+
+#include <asm-generic/checksum.h>
+
+#endif // __ASM_RISCV_CHECKSUM_H