On Wed, Mar 06, 2024 at 05:44:04PM -0500, Joel Fernandes wrote: > On Wed, Mar 6, 2024 at 5:31 PM Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote: > > > > > > > > On 3/5/2024 2:57 PM, Uladzislau Rezki (Sony) wrote: > > > Fix a below race by not releasing a wait-head from the > > > GP-kthread as it can lead for reusing it whereas a worker > > > can still access it thus execute newly added callbacks too > > > early. > > > > [...] > > There might a way to prevent queuing new work as fast-path optimization, incase > > the CBs per GP will always be < SR_MAX_USERS_WAKE_FROM_GP but I could not find a > > workqueue API that helps there, and work_busy() has comments saying not to use that. > > One way to do this would be to maintain a count of how many CBs are in > flight via the worker route, and then fast-path-free the thing if the > count is 0. Should I send a patch around something like that? It saves > 1 more wakeup per synchronize_rcu() I think. > We can release the last wait-head if we know that the worker is not pending/running. Then we guarantee that Frederic's case is not possible. >From the other hand it will introduce again more mess because the idea was, in the begging, to start with something really simple :) -- Uladzislau Rezki
