On Thu, 16 Feb 2017 02:17:28 -0800 Joel Fernandes <joe...@google.com> wrote:
> Comments related to list of pages in the ring buffer seem to be incorrect. > This patch corrects them. > > Signed-off-by: Joel Fernandes <joe...@google.com> > --- > kernel/trace/trace.c | 10 +++++----- > 1 file changed, 5 insertions(+), 5 deletions(-) > > diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c > index d7449783987a..94d508c08c7e 100644 > --- a/kernel/trace/trace.c > +++ b/kernel/trace/trace.c > @@ -262,11 +262,11 @@ unsigned long long ns2usecs(u64 nsec) > /* > * The global_trace is the descriptor that holds the tracing > * buffers for the live tracing. For each CPU, it contains > - * a link list of pages that will store trace entries. The > - * page descriptor of the pages in the memory is used to hold > - * the link list by linking the lru item in the page descriptor > - * to each of the pages in the buffer per CPU. Wow, that's a description of the very first (and poor) implementation of the ring buffer. > - * > + * a link list of pages that will store trace entries. > + * Each page is wrapped by a buffer_page descriptor which contains > + * a list element used to hold the list of pages by linking with > + * other list elements of other buffer_page descriptors (for each > + * of the pages) in the ring buffer per CPU. Actually, this comment doesn't even belong here anymore. The code lives elsewhere. Want to send another patch that just nukes this? Thanks! -- Steve > * For each active CPU there is a data field that holds the > * pages for the buffer for that CPU. Each CPU has the same number > * of pages allocated for its buffer.