search for: page_poison_en

...g makes sense, yes. And we inform it via the poison feature, if > possible. This discussion is about "what happens if the poison feature > is not there, but we do have want_init_on_free()." My preference is to err on the side of caution. I view want_init_on free() as equivalent to page_poison_enabled with CONFIG_PAGE_POISONING_ZERO and treated the same way. So if we are going to let one by then we would want to let the other by as well. > > want_init_on_free rather than not providing that information to QEMU. > > This way, if in the future we decide to change the implementatio...

...omments to explain about access to cmd_id_received without > locks; > - add_one_sg: add TODO to comments about possible improvement. > v29->v30: > - mm/walk_free_mem_block: add cond_sched() for each order > v28->v29: > - mm/page_poison: only expose page_poison_enabled(), rather than more > changes did in v28, as we are not 100% confident about that for now. > - virtio-balloon: use a separate buffer for the stop cmd, instead of > having the start and stop cmd use the same buffer. This avoids the > corner case that the start...

On Mon, Apr 27, 2020 at 1:08 AM David Hildenbrand <david at redhat.com> wrote: > > On 24.04.20 18:24, Alexander Duyck wrote: > > From: Alexander Duyck <alexander.h.duyck at linux.intel.com> > > > > We should disable free page reporting if page poisoning is enabled in the > > kernel but we cannot report it via the balloon interface. This way we can >

On Mon, Apr 27, 2020 at 1:08 AM David Hildenbrand <david at redhat.com> wrote: > > On 24.04.20 18:24, Alexander Duyck wrote: > > From: Alexander Duyck <alexander.h.duyck at linux.intel.com> > > > > We should disable free page reporting if page poisoning is enabled in the > > kernel but we cannot report it via the balloon interface. This way we can >

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...- Live Migration Time (average) Optimization v.s. Legacy = 1260ms v.s. 2634ms --> ~51% reduction - Linux Compilation Time Optimization v.s. Legacy = 4min58s v.s. 5min3s --> no obvious difference ChangeLog: v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...ms v.s. 2634ms --> ~51% reduction - Linux Compilation Time Optimization v.s. Legacy = 4min56s v.s. 5min3s --> no obvious difference ChangeLog: v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...

...host; and add more comments to explain about access to cmd_id_received without locks; - add_one_sg: add TODO to comments about possible improvement. v29->v30: - mm/walk_free_mem_block: add cond_sched() for each order v28->v29: - mm/page_poison: only expose page_poison_enabled(), rather than more changes did in v28, as we are not 100% confident about that for now. - virtio-balloon: use a separate buffer for the stop cmd, instead of having the start and stop cmd use the same buffer. This avoids the corner case that the start cmd is overridden by...