Messages in this thread | | | Date | Wed, 22 Sep 1999 15:38:33 +0200 (CEST) | From | Ingo Molnar <> | Subject | [x86,SMP,patch] smp-2.3.18-F8, please test. |
| |
this is the latest version of the x86 SMP/APIC/IOAPIC code:
http://www.redhat.com/~mingo/smp-2.3.18-F8
(patch is 160k, applies cleanly against all vanilla and ac- 2.3.18 kernels)
The main, externally visible feature of the patchset is the default-on NMI-watchdog.
Changes in smp-2.3.18-F8:
- continuing quest to make 82489DX based (and other older) systems work, typo fixes and comment updates. (Maciej W. Rozycki)
- 'local APIC timer interrupt interleaving', this is both a fix for a potential bug, and preparation for next generation per-CPU timer handling. (me)
- tons of further cleanups, separated smp.c into smpboot.c and smp.c, cleaned up both. (me)
- potential double-write bug fixed - this might fix the booting problem on those old ALR dual- and quad-Pentium boards? (if anyone got one) (me)
- other smaller fixes i forgot about
Changes in smp-2.3.18-B1:
- unconditional NMI oopser. It turned out that we can do this on 99% (maybe 100%) of x86 SMP boxes without impacting timer IRQ performance. See Documentation/nmi_watchdog.txt. (me)
- old external IOAPICs and 486-based SMP boxes should work now (Maciej W. Rozycki)
- unused variable space cleanups, initialize_secondary() cleanup (Manfred Spraul)
- moved all IO-APIC and IPI APIC messages to logical destination mode, fixed LDR initialization bug, cleaned up irq-vector space. (me)
- 'timer-sync' feature, all CPUs synchronize their time stamp counters, errors get reported and fixed. This fixes certain dual-PIII boards. (me)
- the 'set the destination CPU mask to 0' IOAPIC-edge trick is actually not valid and triggers APIC bugs. Exchanged it for an equivalent but safe method. (me)
- 8259A init moved out of setup.S (Maciej W. Rozycki)
- spurious 8259A interrupts get reported properly, APIC error vector exported and logged properly (me)
- a 'noapic' bug fixed - fixes instability in noapic mode. (me)
- we can inline ack_APIC() on P6 boxes: smaller and faster IRQ code. (me)
- other stuff.
reports, comments, suggestions welcome.
-- mingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |