Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
From:   Charlie Jenkins <charlie@rivosinc.com>
Date:   Fri, 15 Sep 2023 10:01:18 -0700
Subject: [PATCH v6 2/4] riscv: Checksum header
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Message-Id: <20230915-optimize_checksum-v6-2-14a6cf61c618@rivosinc.com>
References: <20230915-optimize_checksum-v6-0-14a6cf61c618@rivosinc.com>
In-Reply-To: <20230915-optimize_checksum-v6-0-14a6cf61c618@rivosinc.com>
To:     Charlie Jenkins <charlie@rivosinc.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Conor Dooley <conor@kernel.org>,
        Samuel Holland <samuel.holland@sifive.com>,
        David Laight <David.Laight@aculab.com>,
        linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
        linux-arch@vger.kernel.org
Cc:     Paul Walmsley <paul.walmsley@sifive.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Arnd Bergmann <arnd@arndb.de>
Precedence: bulk

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 | 79 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 000000000000..dc0dd89f2a13
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,79 @@
+/* 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>
+
+#define ip_fast_csum ip_fast_csum
+
+#include <asm-generic/checksum.h>
+
+/*
+ * 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)
+{
+	unsigned long 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)) {
+		unsigned long 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\
+				not	%[fold_temp], %[csum]		\n\
+				rori	%[csum], %[csum], 16		\n\
+				sub	%[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\
+				not	%[fold_temp], %[csum]		\n\
+				roriw	%[csum], %[csum], 16		\n\
+				subw	%[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);
+}
+
+#endif // __ASM_RISCV_CHECKSUM_H

-- 
2.42.0