> -----Original Message-----
> From: Charlie Jenkins <charlie@xxxxxxxxxxxx>
> Sent: Saturday, November 18, 2023 5:28 AM
> To: Charlie Jenkins <charlie@xxxxxxxxxxxx>; Palmer Dabbelt
> <palmer@xxxxxxxxxxx>; Conor Dooley <conor@xxxxxxxxxx>; Samuel Holland
> <samuel.holland@xxxxxxxxxx>; David Laight <David.Laight@xxxxxxxxxx>;
> Wang, Xiao W <xiao.w.wang@xxxxxxxxx>; Evan Green <evan@xxxxxxxxxxxx>;
> linux-riscv@xxxxxxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; linux-
> arch@xxxxxxxxxxxxxxx
> Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>; Albert Ou
> <aou@xxxxxxxxxxxxxxxxx>; Arnd Bergmann <arnd@xxxxxxxx>; Conor Dooley
> <conor.dooley@xxxxxxxxxxxxx>
> Subject: [PATCH v11 4/5] riscv: Add checksum library
>
> Provide a 32 and 64 bit version of do_csum. When compiled for 32-bit
> will load from the buffer in groups of 32 bits, and when compiled for
> 64-bit will load in groups of 64 bits.
>
> Additionally provide riscv optimized implementation of csum_ipv6_magic.
>
> Signed-off-by: Charlie Jenkins <charlie@xxxxxxxxxxxx>
> Acked-by: Conor Dooley <conor.dooley@xxxxxxxxxxxxx>
> ---
> arch/riscv/include/asm/checksum.h | 13 +-
> arch/riscv/lib/Makefile | 1 +
> arch/riscv/lib/csum.c | 326
> ++++++++++++++++++++++++++++++++++++++
> 3 files changed, 339 insertions(+), 1 deletion(-)
>
> diff --git a/arch/riscv/include/asm/checksum.h
> b/arch/riscv/include/asm/checksum.h
> index 2fcf864186e7..3fa04ff1eda8 100644
> --- a/arch/riscv/include/asm/checksum.h
> +++ b/arch/riscv/include/asm/checksum.h
> @@ -12,6 +12,17 @@
>
[...]
> + * misaligned accesses, or when buff is known to be aligned.
> + */
> +static inline __no_sanitize_address unsigned int
> +do_csum_no_alignment(const unsigned char *buff, int len)
> +{
> + unsigned long csum, data;
> + const unsigned long *ptr, *end;
> +
> + ptr = (const unsigned long *)(buff);
> + data = *(ptr++);
> +
> + kasan_check_read(buff, len);
> +
> + end = (const unsigned long *)(buff + len);
> + csum = do_csum_common(ptr, end, data);
> +
> + /*
> + * Zbb support saves 6 instructions, so not worth checking without
> + * alternatives if supported
> + */
> + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
> + IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
> + unsigned long fold_temp;
> +
> + /*
> + * Zbb is likely available when the kernel is compiled with Zbb
> + * support, so nop when Zbb is available and jump when Zbb
> is
> + * not available.
> + */
> + asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
> + RISCV_ISA_EXT_ZBB, 1)
> + :
> + :
> + :
> + : no_zbb);
> +
> +#ifdef 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 /* !CONFIG_32BIT */
> + 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)
> + :
> + : );
> +#endif /* !CONFIG_32BIT */
> + return csum >> 16;
> + }
> +no_zbb:
> +#ifndef CONFIG_32BIT
> + csum += ror64(csum, 32);
> + csum >>= 32;
> +#endif
> + csum = (u32)csum + ror32((u32)csum, 16);
> + return csum >> 16;
> +}
> +
> +/*
> + * Perform a checksum on an arbitrary memory address.
> + * Will do a light-weight address alignment if buff is misaligned, unless
> + * cpu supports fast misaligned accesses.
> + */
> +unsigned int do_csum(const unsigned char *buff, int len)
> +{
> + if (unlikely(len <= 0))
> + return 0;
> +
> + /*
> + * Significant performance gains can be seen by not doing alignment
> + * on machines with fast misaligned accesses.
> + *
> + * There is some duplicate code between the "with_alignment" and
> + * "no_alignment" implmentations, but the overlap is too awkward to
> be
> + * able to fit in one function without introducing multiple static
> + * branches. The largest chunk of overlap was delegated into the
> + * do_csum_common function.
> + */
> + if (static_branch_likely(&fast_misaligned_access_speed_key))
> + return do_csum_no_alignment(buff, len);
> +
> + if (((unsigned long)buff & OFFSET_MASK) == 0)
> + return do_csum_no_alignment(buff, len);
> +
> + return do_csum_with_alignment(buff, len);
> +}
>
> --
> 2.34.1
Reviewed-by: Xiao Wang <xiao.w.wang@xxxxxxxxx>
BRs,
Xiao
