Message ID | 20231027-optimize_checksum-v8-3-feb7101d128d@rivosinc.com (mailing list archive) |
---|---|
State | Superseded |
Headers | show |
Series | riscv: Add fine-tuned checksum functions | expand |
Context | Check | Description |
---|---|---|
conchuod/vmtest-fixes-PR | fail | PR summary |
conchuod/patch-3-test-1 | fail | .github/scripts/patches/build_rv32_defconfig.sh |
conchuod/patch-3-test-2 | fail | .github/scripts/patches/build_rv64_clang_allmodconfig.sh |
conchuod/patch-3-test-3 | fail | .github/scripts/patches/build_rv64_gcc_allmodconfig.sh |
conchuod/patch-3-test-4 | fail | .github/scripts/patches/build_rv64_nommu_k210_defconfig.sh |
conchuod/patch-3-test-5 | fail | .github/scripts/patches/build_rv64_nommu_virt_defconfig.sh |
conchuod/patch-3-test-6 | warning | .github/scripts/patches/checkpatch.sh |
conchuod/patch-3-test-7 | success | .github/scripts/patches/dtb_warn_rv64.sh |
conchuod/patch-3-test-8 | success | .github/scripts/patches/header_inline.sh |
conchuod/patch-3-test-9 | success | .github/scripts/patches/kdoc.sh |
conchuod/patch-3-test-10 | success | .github/scripts/patches/module_param.sh |
conchuod/patch-3-test-11 | success | .github/scripts/patches/verify_fixes.sh |
conchuod/patch-3-test-12 | success | .github/scripts/patches/verify_signedoff.sh |
> -----Original Message----- > From: Charlie Jenkins <charlie@rivosinc.com> > Sent: Saturday, October 28, 2023 6:44 AM > 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>; > Wang, Xiao W <xiao.w.wang@intel.com>; Evan Green <evan@rivosinc.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>; Conor Dooley > <conor.dooley@microchip.com> > Subject: [PATCH v8 3/5] riscv: Checksum header > > 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 | 92 > +++++++++++++++++++++++++++++++++++++++ > 1 file changed, 92 insertions(+) > > diff --git a/arch/riscv/include/asm/checksum.h > b/arch/riscv/include/asm/checksum.h > new file mode 100644 > index 000000000000..9fd4b1b80641 > --- /dev/null > +++ b/arch/riscv/include/asm/checksum.h > @@ -0,0 +1,92 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * IP checksum routines The checksum helpers' usage may not be limited to IP protocol. > + * > + * 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 > + > +extern unsigned int do_csum(const unsigned char *buff, int len); > +#define do_csum do_csum > + > +/* Default version is sufficient for 32 bit */ > +#ifdef CONFIG_64BIT > +#define _HAVE_ARCH_IPV6_CSUM > +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, > + const struct in6_addr *daddr, > + __u32 len, __u8 proto, __wsum sum); > +#endif The do_csum and csum_ipv6_magic helpers are implemented in patch 4/5, so the declarations should be moved there. Otherwise, build would fail at this patch. > + > +/* 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 += (csum >> 32) | (csum << 32); Just like the next patch does, we can call ror64(csum, 32). BRs, Xiao > + csum >>= 32; > +#endif > + return csum_fold((__force __wsum)csum); > +} > + > +#endif /* __ASM_RISCV_CHECKSUM_H */ > > -- > 2.42.0
On Tue, Oct 31, 2023 at 09:11:07AM +0000, Wang, Xiao W wrote: > > > > -----Original Message----- > > From: Charlie Jenkins <charlie@rivosinc.com> > > Sent: Saturday, October 28, 2023 6:44 AM > > 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>; > > Wang, Xiao W <xiao.w.wang@intel.com>; Evan Green <evan@rivosinc.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>; Conor Dooley > > <conor.dooley@microchip.com> > > Subject: [PATCH v8 3/5] riscv: Checksum header > > > > 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 | 92 > > +++++++++++++++++++++++++++++++++++++++ > > 1 file changed, 92 insertions(+) > > > > diff --git a/arch/riscv/include/asm/checksum.h > > b/arch/riscv/include/asm/checksum.h > > new file mode 100644 > > index 000000000000..9fd4b1b80641 > > --- /dev/null > > +++ b/arch/riscv/include/asm/checksum.h > > @@ -0,0 +1,92 @@ > > +/* SPDX-License-Identifier: GPL-2.0 */ > > +/* > > + * IP checksum routines > > The checksum helpers' usage may not be limited to IP protocol. > Will remove IP from the wording. > > + * > > + * 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 > > + > > +extern unsigned int do_csum(const unsigned char *buff, int len); > > +#define do_csum do_csum > > + > > +/* Default version is sufficient for 32 bit */ > > +#ifdef CONFIG_64BIT > > +#define _HAVE_ARCH_IPV6_CSUM > > +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, > > + const struct in6_addr *daddr, > > + __u32 len, __u8 proto, __wsum sum); > > +#endif > > The do_csum and csum_ipv6_magic helpers are implemented in patch 4/5, so the > declarations should be moved there. Otherwise, build would fail at this patch. > Oops, that snuck into this patch somehow. > > + > > +/* 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 += (csum >> 32) | (csum << 32); > > Just like the next patch does, we can call ror64(csum, 32). I meant to change this last time, thank you for pointing it out again. - Charlie > > BRs, > Xiao > > > + csum >>= 32; > > +#endif > > + return csum_fold((__force __wsum)csum); > > +} > > + > > +#endif /* __ASM_RISCV_CHECKSUM_H */ > > > > -- > > 2.42.0 >
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h new file mode 100644 index 000000000000..9fd4b1b80641 --- /dev/null +++ b/arch/riscv/include/asm/checksum.h @@ -0,0 +1,92 @@ +/* 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 + +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + +/* Default version is sufficient for 32 bit */ +#ifdef CONFIG_64BIT +#define _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum); +#endif + +/* 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 += (csum >> 32) | (csum << 32); + csum >>= 32; +#endif + return csum_fold((__force __wsum)csum); +} + +#endif /* __ASM_RISCV_CHECKSUM_H */