Messages in this thread |  | | Date | Fri, 1 Nov 2013 16:22:32 +0100 | From | Oleg Nesterov <> | Subject | Re: [PATCH 10/13] tracing/uprobes: Fetch args before reserving a ring buffer |
| |
On 11/01, Oleg Nesterov wrote: > > Hi Namhyung, > > Sorry if this was already discussed. But I can't really understand > the idea of this per-cpu buffer... > > On 10/29, Namhyung Kim wrote: > > > > Fetching from user space should be done in a non-atomic context. So > > use a per-cpu buffer and copy its content to the ring buffer > > atomically. Note that we can migrate during accessing user memory > > thus use a per-cpu mutex to protect concurrent accesses. > > And if the task migrates or just sleeps in page fault, another task > which hits another uprobe on the same CPU should wait. > > Why we can't simply add trace_uprobe->buffer instead? Only to save > some memory? But every uprobe is very expensive in this sense anyway.
Ah, please ignore... handler_chain() is not self-serialized, so tu->buffer needs locking/waiting too.
Oleg.
|  |