From: Frederic Weisbecker <fweisbec@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
Ingo Molnar <mingo@kernel.org>,
Li Zhong <zhong@linux.vnet.ibm.com>,
Namhyung Kim <namhyung.kim@lge.com>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Paul Gortmaker <paul.gortmaker@windriver.com>,
Peter Zijlstra <peterz@infradead.org>,
Steven Rostedt <rostedt@goodmis.org>,
Thomas Gleixner <tglx@linutronix.de>,
Gleb Natapov <gleb@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Tony Luck <tony.luck@intel.com>,
Fenghua Yu <fenghua.yu@intel.com>
Subject: [PATCH 0/8] cputime: Full dynticks task/cputime accounting v6
Date: Wed, 23 Jan 2013 01:03:54 +0100 [thread overview]
Message-ID: <1358899442-3110-1-git-send-email-fweisbec@gmail.com> (raw)
Hi,
This version fixes everything I had on the TODO list. I'm just not very
happy with the dependency on CONFIG_64BIT. It is necessary because cputime_t
maps to unsigned long long in order to implement a per nanosec granularity
fitting in a reasonable range. And 32 bits archs can't read 64 bits cputime_t
safely (they read low and high part separately, this can race against an update
that does an arithmetic carry after incrementing the low part).
Usual utime/stime/gtime/... are fine because they are protected with the
new seqcount. But kernel_cpustat is not protected on the read side.
I don't know what the right fix is. May be we could use per cpu spinlocks
or seqlocks from both read/update side of kernel_cpustat. Hmm, or perhaps
take curr_task(cpu)->vtime_seqlock before reading it. This requires rq
lock though.
Anyway I believe that specific issue can wait for now. The patchset is already
complicated enough and it depends on context_tracking that is only implemented
on x86-64 yet. I guess once that gets merged and we get a 32 arch to support
the context_tracking, we can start to think about that.
This set is pullable from:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
vtime/generic-v6
Changes since v5:
- Handle guest cputime
- Handle idle tasks. Those were special because they don't start from schedule()
so they need their own initializations.
- Fix build error with CONFIG_IRQ_TIME_ACCOUNTING (thanks Wu Fenguang)
- Depend on 64 bits archs to make kern_cpustat reading to be atomic
Thanks.
---
Frederic Weisbecker (8):
context_tracking: Export context state for generic vtime
cputime: Librarize per nsecs resolution cputime definitions
cputime: Move default nsecs_to_cputime() to jiffies based cputime
file
cputime: Generic on-demand virtual cputime accounting
cputime: Allow dynamic switch between tick/virtual based cputime
accounting
cputime: Use accessors to read task cputime stats
kvm: Prepare to add generic guest entry/exit callbacks
cputime: Safely read cputime of full dynticks CPUs
arch/alpha/kernel/osf_sys.c | 6 +-
arch/ia64/include/asm/cputime.h | 92 +--------
arch/ia64/include/asm/thread_info.h | 4 +-
arch/ia64/include/asm/xen/minstate.h | 2 +-
arch/ia64/kernel/asm-offsets.c | 2 +-
arch/ia64/kernel/entry.S | 16 +-
arch/ia64/kernel/fsys.S | 4 +-
arch/ia64/kernel/head.S | 4 +-
arch/ia64/kernel/ivt.S | 8 +-
arch/ia64/kernel/minstate.h | 2 +-
arch/ia64/kernel/time.c | 4 +-
arch/powerpc/configs/chroma_defconfig | 2 +-
arch/powerpc/configs/corenet64_smp_defconfig | 2 +-
arch/powerpc/configs/pasemi_defconfig | 2 +-
arch/powerpc/include/asm/cputime.h | 6 +-
arch/powerpc/include/asm/lppaca.h | 2 +-
arch/powerpc/include/asm/ppc_asm.h | 4 +-
arch/powerpc/kernel/entry_64.S | 4 +-
arch/powerpc/kernel/time.c | 4 +-
arch/powerpc/platforms/pseries/dtl.c | 6 +-
arch/powerpc/platforms/pseries/setup.c | 6 +-
arch/s390/kernel/vtime.c | 6 +-
arch/x86/kernel/apm_32.c | 11 +-
drivers/isdn/mISDN/stack.c | 7 +-
fs/binfmt_elf.c | 8 +-
fs/binfmt_elf_fdpic.c | 7 +-
fs/proc/array.c | 4 +-
include/asm-generic/cputime.h | 66 +-----
include/asm-generic/cputime_jiffies.h | 72 ++++++
include/asm-generic/cputime_nsecs.h | 104 +++++++++
include/linux/context_tracking.h | 28 +++
include/linux/hardirq.h | 4 +-
include/linux/init_task.h | 11 +
include/linux/kernel_stat.h | 2 +-
include/linux/kvm_host.h | 55 ++++-
include/linux/sched.h | 40 ++++
include/linux/tsacct_kern.h | 3 +
include/linux/vtime.h | 59 ++++--
init/Kconfig | 23 ++-
kernel/acct.c | 6 +-
kernel/context_tracking.c | 41 ++--
kernel/cpu.c | 4 +-
kernel/delayacct.c | 7 +-
kernel/exit.c | 10 +-
kernel/fork.c | 6 +
kernel/posix-cpu-timers.c | 28 ++-
kernel/sched/core.c | 1 +
kernel/sched/cputime.c | 298 +++++++++++++++++++++++---
kernel/signal.c | 12 +-
kernel/softirq.c | 6 +-
kernel/time/tick-sched.c | 5 +-
kernel/tsacct.c | 44 +++-
52 files changed, 840 insertions(+), 320 deletions(-)
create mode 100644 include/asm-generic/cputime_jiffies.h
create mode 100644 include/asm-generic/cputime_nsecs.h
--
1.7.5.4
next reply other threads:[~2013-01-23 0:04 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-23 0:03 Frederic Weisbecker [this message]
2013-01-23 0:03 ` [PATCH 1/8] context_tracking: Export context state for generic vtime Frederic Weisbecker
2013-01-23 0:03 ` [PATCH 2/8] cputime: Librarize per nsecs resolution cputime definitions Frederic Weisbecker
2013-01-23 0:03 ` [PATCH 3/8] cputime: Move default nsecs_to_cputime() to jiffies based cputime file Frederic Weisbecker
2013-01-23 0:03 ` [PATCH 4/8] cputime: Generic on-demand virtual cputime accounting Frederic Weisbecker
2013-01-23 0:03 ` [PATCH 5/8] cputime: Allow dynamic switch between tick/virtual based " Frederic Weisbecker
2013-01-23 0:04 ` [PATCH 6/8] cputime: Use accessors to read task cputime stats Frederic Weisbecker
2013-01-23 0:04 ` [PATCH 7/8] kvm: Prepare to add generic guest entry/exit callbacks Frederic Weisbecker
2013-01-23 0:04 ` [PATCH 8/8] cputime: Safely read cputime of full dynticks CPUs Frederic Weisbecker
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=1358899442-3110-1-git-send-email-fweisbec@gmail.com \
--to=fweisbec@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=fenghua.yu@intel.com \
--cc=gleb@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mtosatti@redhat.com \
--cc=namhyung.kim@lge.com \
--cc=paul.gortmaker@windriver.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=zhong@linux.vnet.ibm.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 NNTP newsgroup(s).