| Message ID | 20231031-optimize_checksum-v9-3-ea018e69b229@rivosinc.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | riscv: Add fine-tuned checksum functions | expand |
On Tue, Oct 31, 2023 at 05:18:53PM -0700, Charlie Jenkins wrote: > 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> > Acked-by: Conor Dooley <conor.dooley@microchip.com> > --- > arch/riscv/include/asm/checksum.h | 81 +++++++++++++++++++++++++++++++++++++++ > 1 file changed, 81 insertions(+) > > diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h > new file mode 100644 > index 000000000000..3d77cac338fe > --- /dev/null > +++ b/arch/riscv/include/asm/checksum.h > @@ -0,0 +1,81 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * 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 > + > +/* Define riscv versions of functions before importing asm-generic/checksum.h */ > +#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 given that NET_IP_ALIGN is set to 2 on > + * riscv, defining IP headers to be 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) This looks like a open coding of riscv_has_extension_*, so if we use the it, the code could be rewritten as: if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { if (32bit) { asm(...) } else { asm(...) } return csum >> 16; } #ifndef CONFIG_32BIT csum += ror64(csum, 32); csum >>= 32; #endif return csum_fold((__force __wsum)csum); The code readability is improved and make it a bit easier to refactor the asm(...) code in the future. And IMHO, the generated code should be the same. Thanks > > + : > + : > + : > + : 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 += ror64(csum, 32); > + csum >>= 32; > +#endif > + return csum_fold((__force __wsum)csum); > +} > + > +#endif /* __ASM_RISCV_CHECKSUM_H */ > > -- > 2.34.1 > > > _______________________________________________ > linux-riscv mailing list > linux-riscv@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-riscv
On Wed, Nov 01, 2023 at 11:22:52PM +0800, Jisheng Zhang wrote: > On Tue, Oct 31, 2023 at 05:18:53PM -0700, Charlie Jenkins wrote: > > 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> > > Acked-by: Conor Dooley <conor.dooley@microchip.com> > > --- > > arch/riscv/include/asm/checksum.h | 81 +++++++++++++++++++++++++++++++++++++++ > > 1 file changed, 81 insertions(+) > > > > diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h > > new file mode 100644 > > index 000000000000..3d77cac338fe > > --- /dev/null > > +++ b/arch/riscv/include/asm/checksum.h > > @@ -0,0 +1,81 @@ > > +/* SPDX-License-Identifier: GPL-2.0 */ > > +/* > > + * 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 > > + > > +/* Define riscv versions of functions before importing asm-generic/checksum.h */ > > +#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 given that NET_IP_ALIGN is set to 2 on > > + * riscv, defining IP headers to be 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) > > This looks like a open coding of riscv_has_extension_*, so if > we use the it, the code could be rewritten as: > > if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { > if (32bit) { > asm(...) > > } else { > asm(...) > } > return csum >> 16; > } > #ifndef CONFIG_32BIT > csum += ror64(csum, 32); > csum >>= 32; > #endif > return csum_fold((__force __wsum)csum); > > The code readability is improved and make it a bit easier to refactor > the asm(...) code in the future. > > And IMHO, the generated code should be the same. > > Thanks It is unfortunately not the same. riscv_has_extension_likely checks at runtime for ZBB if alternatives is not supported. That is why the comment is there. I can reference riscv_has_extension_likely to avoid confusion. - Charlie > > > > > > + : > > + : > > + : > > + : 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 += ror64(csum, 32); > > + csum >>= 32; > > +#endif > > + return csum_fold((__force __wsum)csum); > > +} > > + > > +#endif /* __ASM_RISCV_CHECKSUM_H */ > > > > -- > > 2.34.1 > > > > > > _______________________________________________ > > linux-riscv mailing list > > linux-riscv@lists.infradead.org > > http://lists.infradead.org/mailman/listinfo/linux-riscv
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h new file mode 100644 index 000000000000..3d77cac338fe --- /dev/null +++ b/arch/riscv/include/asm/checksum.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * 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 + +/* Define riscv versions of functions before importing asm-generic/checksum.h */ +#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 given that NET_IP_ALIGN is set to 2 on + * riscv, defining IP headers to be 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 += ror64(csum, 32); + csum >>= 32; +#endif + return csum_fold((__force __wsum)csum); +} + +#endif /* __ASM_RISCV_CHECKSUM_H */