search for: seqlocky

...rker to finish the read before it can > do things like setting dirty pages and unmapping page.? It looks to me > seqlock doesn't provide things like this.? The seqlock is usually used to prevent a 2nd thread from accessing the VA while it is being changed by the mm. ie you use something seqlocky instead of the ugly mmu_notifier_unregister/register cycle. You are supposed to use something simple like a spinlock or mutex inside the invalidate_range_start to serialized tear down of the SPTEs with their accessors. > write_seqcount_begin() > > map = vq->map[X] > > write or...

...rker to finish the read before it can > do things like setting dirty pages and unmapping page.? It looks to me > seqlock doesn't provide things like this.? The seqlock is usually used to prevent a 2nd thread from accessing the VA while it is being changed by the mm. ie you use something seqlocky instead of the ugly mmu_notifier_unregister/register cycle. You are supposed to use something simple like a spinlock or mutex inside the invalidate_range_start to serialized tear down of the SPTEs with their accessors. > write_seqcount_begin() > > map = vq->map[X] > > write or...

...> > > do things like setting dirty pages and unmapping page.? It looks to me > > > seqlock doesn't provide things like this. > > The seqlock is usually used to prevent a 2nd thread from accessing the > > VA while it is being changed by the mm. ie you use something seqlocky > > instead of the ugly mmu_notifier_unregister/register cycle. > > > Yes, so we have two mappings: > > [1] vring address to VA > [2] VA to PA > > And have several readers and writers > > 1) set_vring_num_addr(): writer of both [1] and [2] > 2) MMU notifi...

...> > > do things like setting dirty pages and unmapping page.? It looks to me > > > seqlock doesn't provide things like this. > > The seqlock is usually used to prevent a 2nd thread from accessing the > > VA while it is being changed by the mm. ie you use something seqlocky > > instead of the ugly mmu_notifier_unregister/register cycle. > > > Yes, so we have two mappings: > > [1] vring address to VA > [2] VA to PA > > And have several readers and writers > > 1) set_vring_num_addr(): writer of both [1] and [2] > 2) MMU notifi...

...gt;> do things like setting dirty pages and unmapping page.? It looks to me >>>> seqlock doesn't provide things like this. >>> The seqlock is usually used to prevent a 2nd thread from accessing the >>> VA while it is being changed by the mm. ie you use something seqlocky >>> instead of the ugly mmu_notifier_unregister/register cycle. >> >> Yes, so we have two mappings: >> >> [1] vring address to VA >> [2] VA to PA >> >> And have several readers and writers >> >> 1) set_vring_num_addr(): writer of both [...

...the read before it can >> do things like setting dirty pages and unmapping page.? It looks to me >> seqlock doesn't provide things like this. > The seqlock is usually used to prevent a 2nd thread from accessing the > VA while it is being changed by the mm. ie you use something seqlocky > instead of the ugly mmu_notifier_unregister/register cycle. Yes, so we have two mappings: [1] vring address to VA [2] VA to PA And have several readers and writers 1) set_vring_num_addr(): writer of both [1] and [2] 2) MMU notifier: reader of [1] writer of [2] 3) GUP: reader of [1] writer...

On Wed, Jul 31, 2019 at 04:46:53AM -0400, Jason Wang wrote: > We used to use RCU to synchronize MMU notifier with worker. This leads > calling synchronize_rcu() in invalidate_range_start(). But on a busy > system, there would be many factors that may slow down the > synchronize_rcu() which makes it unsuitable to be called in MMU > notifier. > > A solution is SRCU but its

On Wed, Jul 31, 2019 at 04:46:53AM -0400, Jason Wang wrote: > We used to use RCU to synchronize MMU notifier with worker. This leads > calling synchronize_rcu() in invalidate_range_start(). But on a busy > system, there would be many factors that may slow down the > synchronize_rcu() which makes it unsuitable to be called in MMU > notifier. > > A solution is SRCU but its