| From: |
| Thomas Gleixner <tglx@linutronix.de> |
| To: |
| Andrew Morton <akpm@osdl.org> |
| Subject: |
| [patch 00/46] High resolution timer / dynamic tick update |
| Date: |
| Tue, 23 Jan 2007 22:00:55 -0000 |
| Cc: |
| LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>,
John Stultz <johnstul@us.ibm.com>,
Arjan van de Veen <arjan@infradead.org>,
Roman Zippel <zippel@linux-m68k.org> |
| Archive-link: |
| Article,
Thread
|
This is a full replacement queue for the high resolution timer / dynamic
ticks implemementation in -mm.
This version includes the following improvements:
- Seperate clockevents management of devices and users
- Provide a generic tick managament infrastructure, which makes use
of the clock events management layer. This provides:
- periodic tick management
- broadcast management (e.g. to solve the APIC stops in C3 power
state problem)
- dynamic tick core functionality
- high resolution timer core infrastructure
This allows to provide dynamic ticks with low and high resolution
timers by sharing the infrastructure. [read: CONFIG_NO_HZ=y is now
available without CONFIG_HIGH_RES_TIMERS as well.]
( The dynamic tick implementation also contains a fix for the
generic next_timer_interrupt() function, which did not do the
cascade lookups correctly. )
- Provide a generic way to verify clocksources. TSC needs
verification due to broken hardware and BIOS implementations. The
previous attempt to allow TSC usage for high resolution and/or
dynamic ticks only in combination with the PM-Timer made hardwired
assumptions, which are ugly to maintain. The new verification code
solves this by chosing the best available clocksource for
verification and handles the usability check for highres / dynamic
ticks. This makes TSC code agnostic of other hardware available in
the system.
- Removed the dynamic tick specific parts from the high resolution
timer code.
- Dynamic ticks and high resolution timers can be disabled separately
at compile time or at run time from the kernel command line.
Thomas, Ingo
P.S:
Sorry for the resend. Did not notice my list typo. :(
--