From: Charlie Jenkins <charlie@rivosinc.com>
To: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>,
linux-kernel@vger.kernel.org, Conor Dooley <conor@kernel.org>,
David Laight <David.Laight@aculab.com>,
Palmer Dabbelt <palmer@dabbelt.com>,
Paul Walmsley <paul.walmsley@sifive.com>,
linux-riscv@lists.infradead.org
Subject: Re: [PATCH v4 1/5] riscv: Checksum header
Date: Tue, 12 Sep 2023 19:38:03 -0700 [thread overview]
Message-ID: <ZQEgi9v1gt6MlkDv@ghost> (raw)
In-Reply-To: <CAJM55Z-kj8eWKvR32At4kx+PPPn9OMaR88BhEqppQHSL03n50Q@mail.gmail.com>
On Tue, Sep 12, 2023 at 03:24:29AM -0700, Emil Renner Berthing wrote:
> 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>
> > ---
> > arch/riscv/include/asm/checksum.h | 95 +++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 95 insertions(+)
> >
> > diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
> > new file mode 100644
> > index 000000000000..0d7fc8275a5e
> > --- /dev/null
> > +++ b/arch/riscv/include/asm/checksum.h
> > @@ -0,0 +1,95 @@
> > +/* 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
>
> Hi Charlie,
>
> Isn't unsigned long already 32bit on 32bit RISC-V, so why is this #ifdef
> needed?
Oh, I wasn't sure so I ran sizeof(long) in qemu-system-riscv32 and it
gave me 8 so assumed a long was 8 bytes. Do you think it would make what
is going on more clear if I use u32 and u64 or would you recommend just
using long?
>
> > +
> > +/*
> > + * Fold a partial checksum without adding pseudo headers
> > + */
> > +static inline __sum16 csum_fold(__wsum sum)
> > +{
> > + return (~sum - ror32(sum, 16)) >> 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\
> > + 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;
>
> The indentation seems off here.
>
> /Emil
>
> > +#endif
> > + return csum_fold((__force __wsum)csum);
> > +}
> > +
> > +#define ip_fast_csum ip_fast_csum
> > +
> > +#include <asm-generic/checksum.h>
> > +
> > +#endif // __ASM_RISCV_CHECKSUM_H
> >
> > --
> > 2.42.0
> >
> >
> > _______________________________________________
> > linux-riscv mailing list
> > linux-riscv@lists.infradead.org
> > http://lists.inradead.org/mailman/listinfo/linux-riscv
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
WARNING: multiple messages have this Message-ID (diff)
From: Charlie Jenkins <charlie@rivosinc.com>
To: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Cc: 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,
Paul Walmsley <paul.walmsley@sifive.com>,
Albert Ou <aou@eecs.berkeley.edu>
Subject: Re: [PATCH v4 1/5] riscv: Checksum header
Date: Tue, 12 Sep 2023 19:38:03 -0700 [thread overview]
Message-ID: <ZQEgi9v1gt6MlkDv@ghost> (raw)
In-Reply-To: <CAJM55Z-kj8eWKvR32At4kx+PPPn9OMaR88BhEqppQHSL03n50Q@mail.gmail.com>
On Tue, Sep 12, 2023 at 03:24:29AM -0700, Emil Renner Berthing wrote:
> 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>
> > ---
> > arch/riscv/include/asm/checksum.h | 95 +++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 95 insertions(+)
> >
> > diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
> > new file mode 100644
> > index 000000000000..0d7fc8275a5e
> > --- /dev/null
> > +++ b/arch/riscv/include/asm/checksum.h
> > @@ -0,0 +1,95 @@
> > +/* 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
>
> Hi Charlie,
>
> Isn't unsigned long already 32bit on 32bit RISC-V, so why is this #ifdef
> needed?
Oh, I wasn't sure so I ran sizeof(long) in qemu-system-riscv32 and it
gave me 8 so assumed a long was 8 bytes. Do you think it would make what
is going on more clear if I use u32 and u64 or would you recommend just
using long?
>
> > +
> > +/*
> > + * Fold a partial checksum without adding pseudo headers
> > + */
> > +static inline __sum16 csum_fold(__wsum sum)
> > +{
> > + return (~sum - ror32(sum, 16)) >> 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\
> > + 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;
>
> The indentation seems off here.
>
> /Emil
>
> > +#endif
> > + return csum_fold((__force __wsum)csum);
> > +}
> > +
> > +#define ip_fast_csum ip_fast_csum
> > +
> > +#include <asm-generic/checksum.h>
> > +
> > +#endif // __ASM_RISCV_CHECKSUM_H
> >
> > --
> > 2.42.0
> >
> >
> > _______________________________________________
> > linux-riscv mailing list
> > linux-riscv@lists.infradead.org
> > http://lists.inradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2023-09-13 2:38 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-11 22:57 [PATCH v4 0/5] riscv: Add fine-tuned checksum functions Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
2023-09-11 22:57 ` [PATCH v4 1/5] riscv: Checksum header Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
2023-09-12 10:24 ` Emil Renner Berthing
2023-09-12 10:24 ` Emil Renner Berthing
2023-09-13 2:38 ` Charlie Jenkins [this message]
2023-09-13 2:38 ` Charlie Jenkins
2023-09-13 9:19 ` Emil Renner Berthing
2023-09-13 9:19 ` Emil Renner Berthing
2023-09-11 22:57 ` [PATCH v4 2/5] riscv: Add checksum library Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
2023-09-12 8:45 ` David Laight
2023-09-12 8:45 ` David Laight
2023-09-13 3:09 ` Charlie Jenkins
2023-09-13 3:09 ` Charlie Jenkins
2023-09-13 8:47 ` David Laight
2023-09-13 8:47 ` David Laight
2023-09-13 23:18 ` Charlie Jenkins
2023-09-13 23:18 ` Charlie Jenkins
2023-09-14 0:41 ` Charlie Jenkins
2023-09-14 0:41 ` Charlie Jenkins
2023-09-14 12:25 ` Conor Dooley
2023-09-14 12:25 ` Conor Dooley
2023-09-14 17:58 ` Charlie Jenkins
2023-09-14 17:58 ` Charlie Jenkins
2023-09-14 18:02 ` Conor Dooley
2023-09-14 18:02 ` Conor Dooley
2023-09-14 23:30 ` Charlie Jenkins
2023-09-14 23:30 ` Charlie Jenkins
2023-09-11 22:57 ` [PATCH v4 3/5] riscv: Vector checksum header Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
2023-09-11 22:57 ` [PATCH v4 4/5] riscv: Vector checksum library Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
2023-09-14 12:46 ` Conor Dooley
2023-09-14 12:46 ` Conor Dooley
2023-09-14 16:14 ` Charlie Jenkins
2023-09-14 16:14 ` Charlie Jenkins
2023-09-14 16:29 ` Conor Dooley
2023-09-14 16:29 ` Conor Dooley
2023-09-14 17:29 ` Charlie Jenkins
2023-09-14 17:29 ` Charlie Jenkins
2023-09-14 17:36 ` Conor Dooley
2023-09-14 17:36 ` Conor Dooley
2023-09-14 20:59 ` Charlie Jenkins
2023-09-14 20:59 ` Charlie Jenkins
2023-09-11 22:57 ` [PATCH v4 5/5] riscv: Test checksum functions Charlie Jenkins
2023-09-11 22:57 ` Charlie Jenkins
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ZQEgi9v1gt6MlkDv@ghost \
--to=charlie@rivosinc.com \
--cc=David.Laight@aculab.com \
--cc=aou@eecs.berkeley.edu \
--cc=conor@kernel.org \
--cc=emil.renner.berthing@canonical.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.