Re: [PATCH] rte_memcpy: fix off by one for size 16 and 32

2024-03-02 Thread Mattias Rönnblom
On 2024-03-02 21:49, Stephen Hemminger wrote: The rte_memcpy code would do extra instructions for size 16 and 32 which potentially could reference past end of data. For size of 16, only single mov16 is needed. same for size of 32, only single mov32. Fixes: f5472703c0bd ("eal: optimize aligned m

Re: [PATCH] rte_memcpy: fix off by one for size 16 and 32

2024-03-02 Thread Mattias Rönnblom
On 2024-03-02 21:56, Stephen Hemminger wrote: On Sat, 2 Mar 2024 12:49:23 -0800 Stephen Hemminger wrote: The rte_memcpy code would do extra instructions for size 16 and 32 which potentially could reference past end of data. For size of 16, only single mov16 is needed. same for size of 32, on

RE: [PATCH] rte_memcpy: fix off by one for size 16 and 32

2024-03-02 Thread Morten Brørup
> From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Saturday, 2 March 2024 21.49 > > The rte_memcpy code would do extra instructions for size 16 > and 32 which potentially could reference past end of data. It's a somewhat weird concept, but they don't reference past end of data.

RE: [PATCH] rte_memcpy: fix off by one for size 16 and 32

2024-03-02 Thread Morten Brørup
nanyev; Zhihong Wang; > Yuanhan Liu; Xiaoyun Li > Subject: Re: [PATCH] rte_memcpy: fix off by one for size 16 and 32 > > On Sat, 2 Mar 2024 12:49:23 -0800 > Stephen Hemminger wrote: > > > The rte_memcpy code would do extra instructions for size 16 > > and 32