Re: LLE reference leak in the L2 cache

2017-03-24 Thread Mike Karels
On 23 Mar 2017, at 9:02, Andrey V. Elsukov wrote: On 20.03.2017 03:46, Mike Karels wrote: The context has gotten messy here, so I’m going to break down and top-post. I started review https://reviews.freebsd.org/D10059 with a fix for the reference-count leak. It changes the semantics so on

Re: LLE reference leak in the L2 cache

2017-03-23 Thread Andrey V. Elsukov
On 20.03.2017 03:46, Mike Karels wrote: > The context has gotten messy here, so I’m going to break down and top-post. > > I started review https://reviews.freebsd.org/D10059 with a fix for the > reference-count leak. > It changes the semantics so only routes within an in_pcb automatically > do L2

Re: LLE reference leak in the L2 cache

2017-03-19 Thread Mike Karels
The context has gotten messy here, so I’m going to break down and top-post. I started review https://reviews.freebsd.org/D10059 with a fix for the reference-count leak. It changes the semantics so only routes within an in_pcb automatically do L2 caching. I’ll put the tcp_output change for V6

Re: LLE reference leak in the L2 cache

2017-03-14 Thread Mike Karels
On 14 Mar 2017, at 3:50, Andrey V. Elsukov wrote: > On 14.03.2017 11:40, Mike Karels wrote: >>> Hi All, >> >>> Eugene has reported about the following assertion in the ARP code: >>> http://www.grosbein.net/freebsd/crash/arp-kassert.txt >> >>> After some investigation I found that L2 cache ha

Re: LLE reference leak in the L2 cache

2017-03-14 Thread Andrey V. Elsukov
On 14.03.2017 11:40, Mike Karels wrote: >> Hi All, > >> Eugene has reported about the following assertion in the ARP code: >> http://www.grosbein.net/freebsd/crash/arp-kassert.txt > >> After some investigation I found that L2 cache has reference leak, that >> can lead to integer overflow and

Re: LLE reference leak in the L2 cache

2017-03-14 Thread Mike Karels
> Hi All, > Eugene has reported about the following assertion in the ARP code: > http://www.grosbein.net/freebsd/crash/arp-kassert.txt > After some investigation I found that L2 cache has reference leak, that > can lead to integer overflow and this assertion. > The one of the ways to reprod

LLE reference leak in the L2 cache

2017-03-13 Thread Andrey V. Elsukov
Hi All, Eugene has reported about the following assertion in the ARP code: http://www.grosbein.net/freebsd/crash/arp-kassert.txt After some investigation I found that L2 cache has reference leak, that can lead to integer overflow and this assertion. The one of the ways to reproduce this o