On Tue, 19 Feb 2008, Eric Dumazet wrote:Right. The alloc fastpath assumes that the object is not modified while it is allocated... Du! This shoots my nice scheme in the foot and there does not seem to be an easy way to fix it. This means we also need to revert the page->end patch. Useless if we do not have the cmpxchg_local. --
| Jeremy Fitzhardinge | Re: [RFC 00/15] x86_64: Optimize percpu accesses |
| jmerkey | [ANNOUNCE] mdb: Merkey's Linux Kernel Debugger 2.6.27-rc4 released |
| Greg Kroah-Hartman | [PATCH 021/196] ISDN: Convert from class_device to device for ISDN capi |
| Ingo Molnar | Re: [PATCH 00/23] per device dirty throttling -v8 |
git: | |
| Linus Torvalds | Re: VCS comparison table |
| Peter Stahlir | Git as a filesystem |
| Johannes Schindelin | Re: git on MacOSX and files with decomposed utf-8 file names |
| Bill Lear | Meaning of "fatal: protocol error: bad line length character"? |
| Mayuresh Kathe | Re: What is our ultimate goal?? |
| Richard Stallman | Real men don't attack straw men |
| bofh | Re: web development on OpenBSD |
| Kevin | uvm_mapent_alloc: out of static map entries on 4.3 i386 |
| Mark Lord | Re: 2.6.25-rc8: FTP transfer errors |
| Evgeniy Polyakov | Re: [BUG] New Kernel Bugs |
| Jarek Poplawski | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Andi Kleen | [PATCH RFC] [1/9] Core module symbol namespaces code and intro. |
