From: Andreas Larsson <andreas@gaisler.com>
To: GNU C Library <libc-alpha@sourceware.org>
Cc: Adhemerval Zanella <adhemerval.zanella@linaro.org>,
Carlos O'Donell <carlos@redhat.com>,
David Miller <davem@davemloft.net>,
Torvald Riegel <triegel@redhat.com>,
software@gaisler.com
Subject: [RFC][PATCH 0/2] Make sparcv8 work again on cas enabled hardware
Date: Tue, 01 Nov 2016 15:08:00 -0000 [thread overview]
Message-ID: <1478012867-6031-1-git-send-email-andreas@gaisler.com> (raw)
This patch series:
1) Fixes a sparcv8 bug introduced since the #error was added to
sysdeps/sparc/sparc32/pthread_barrier_wait.c in 2.23. This fix stops
incorrect usage of sendmsg and recvmsg Linux system calls for sparcv8.
2) Makes use of the CASA compare and swap instruction for atomic_*
functions sparcv8, that is available for most LEON3 and LEON4 designs
and implied by -mcpu=leon3, but not part of the sparcv8 standard. To
allow for easy kernel emulation on systems that lack the instruction,
the CASA instruction is used for all writing atomic_* functions. This
approach is discussed in thread [1].
Any comments are most welcome. The spin lock based sparcv8 semaphore
implementation is currently unchanged by this patchset, but I would say
that that should go as well. I will look into that as well, but I have
not tested that yet.
[1] https://sourceware.org/ml/libc-alpha/2016-10/msg00344.html
Andreas Larsson (2):
sparc32: Mark sendmsg and recvmsg system calls as unsupported
sparc32: Use cas for atomic_* operations and use general
pthread_barrier_wait
sysdeps/sparc/sparc32/atomic-machine.h | 228 +++++------------------
sysdeps/sparc/sparc32/pthread_barrier_wait.c | 1 -
sysdeps/unix/sysv/linux/sparc/kernel-features.h | 4 +-
3 files changed, 53 insertions(+), 180 deletions(-)
delete mode 100644 sysdeps/sparc/sparc32/pthread_barrier_wait.c
next reply other threads:[~2016-11-01 15:08 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-01 15:08 Andreas Larsson [this message]
2016-11-01 15:08 ` [RFC][PATCH 1/2] sparc32: Mark sendmsg and recvmsg system calls as unsupported Andreas Larsson
2016-11-01 17:28 ` Adhemerval Zanella
2016-11-02 11:38 ` Andreas Larsson
2016-11-02 12:49 ` Adhemerval Zanella
2016-11-04 18:36 ` David Miller
2016-11-01 15:08 ` [RFC][PATCH 2/2] sparc32: Use cas for atomic_* operations and use general pthread_barrier_wait Andreas Larsson
2016-11-04 18:37 ` David Miller
2016-11-04 18:44 ` David Miller
2016-11-01 16:00 ` [RFC][PATCH 0/2] Make sparcv8 work again on cas enabled hardware Torvald Riegel
2016-11-01 16:09 ` David Miller
2016-11-01 16:46 ` Torvald Riegel
2016-11-01 16:51 ` David Miller
2016-11-02 10:05 ` Torvald Riegel
2016-11-02 11:29 ` Andreas Larsson
2016-11-02 15:32 ` David Miller
2016-11-02 22:33 ` Torvald Riegel
2016-11-03 2:52 ` David Miller
2016-11-03 15:39 ` Torvald Riegel
2016-11-03 17:22 ` David Miller
2016-11-03 18:41 ` Adhemerval Zanella
2016-11-03 20:33 ` David Miller
2016-11-03 21:29 ` Adhemerval Zanella
2016-11-03 22:25 ` Torvald Riegel
2016-11-04 10:28 ` Andreas Larsson
2016-11-04 15:23 ` David Miller
2016-11-04 13:55 ` Richard Henderson
2016-11-04 15:31 ` David Miller
2016-11-04 16:10 ` Richard Henderson
2016-11-04 14:04 ` Richard Henderson
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=1478012867-6031-1-git-send-email-andreas@gaisler.com \
--to=andreas@gaisler.com \
--cc=adhemerval.zanella@linaro.org \
--cc=carlos@redhat.com \
--cc=davem@davemloft.net \
--cc=libc-alpha@sourceware.org \
--cc=software@gaisler.com \
--cc=triegel@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).