Re: [PATCH 6/7] mm,hwpoison: Disable pcplists before grabbing a refcount

2020-11-27 Thread Andrew Morton
On Thu, 26 Nov 2020 14:45:30 +0100 Vlastimil Babka wrote: > Note as you say the series should go after [1] above, which means after > mm-page_alloc-disable-pcplists-during-memory-offline.patch in mmots, but > currently it's ordered before, where zone_pcp_disable() etc doesn't yet > exist. >

Re: [PATCH 6/7] mm,hwpoison: Disable pcplists before grabbing a refcount

2020-11-26 Thread Vlastimil Babka
On 11/19/20 11:57 AM, Oscar Salvador wrote: Currently, we have a sort of retry mechanism to make sure pages in pcp-lists are spilled to the buddy system, so we can handle those. We can save us this extra checks with the new disable-pcplist mechanism that is available with [1].

Re: [PATCH 6/7] mm,hwpoison: Disable pcplists before grabbing a refcount

2020-11-19 Thread 堀口 直也
On Thu, Nov 19, 2020 at 11:57:15AM +0100, Oscar Salvador wrote: > Currently, we have a sort of retry mechanism to make sure pages in > pcp-lists are spilled to the buddy system, so we can handle those. > > We can save us this extra checks with the new disable-pcplist mechanism > that is available

[PATCH 6/7] mm,hwpoison: Disable pcplists before grabbing a refcount

2020-11-19 Thread Oscar Salvador
Currently, we have a sort of retry mechanism to make sure pages in pcp-lists are spilled to the buddy system, so we can handle those. We can save us this extra checks with the new disable-pcplist mechanism that is available with [1]. zone_pcplist_disable makes sure to 1) disable pcplists, so any