From: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Subject: mm: honor PF_MEMALLOC_PIN for all movable pages PF_MEMALLOC_PIN is only honored for CMA pages, extend this flag to work for any allocations from ZONE_MOVABLE by removing __GFP_MOVABLE from gfp_mask when this flag is passed in the current context. Add is_pinnable_page() to return true if page is in a pinnable page. A pinnable page is not in ZONE_MOVABLE and not of MIGRATE_CMA type. Link: https://lkml.kernel.org/r/20210215161349.246722-8-pasha.tatashin@xxxxxxxxxx Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Ira Weiny <ira.weiny@xxxxxxxxx> Cc: James Morris <jmorris@xxxxxxxxx> Cc: Jason Gunthorpe <jgg@xxxxxxxxxx> Cc: Jason Gunthorpe <jgg@xxxxxxxx> Cc: John Hubbard <jhubbard@xxxxxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Sasha Levin <sashal@xxxxxxxxxx> Cc: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx> Cc: Tyler Hicks <tyhicks@xxxxxxxxxxxxxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mm.h | 18 ++++++++++++++++++ include/linux/sched/mm.h | 6 +++++- mm/hugetlb.c | 2 +- mm/page_alloc.c | 20 +++++++++----------- 4 files changed, 33 insertions(+), 13 deletions(-) --- a/include/linux/mm.h~mm-honor-pf_memalloc_pin-for-all-movable-pages +++ a/include/linux/mm.h @@ -1141,6 +1141,11 @@ static inline bool is_zone_device_page(c } #endif +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} + #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); @@ -1550,6 +1555,19 @@ static inline unsigned long page_to_sect } #endif +/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ +#ifdef CONFIG_MIGRATION +static inline bool is_pinnable_page(struct page *page) +{ + return !is_zone_movable_page(page) && !is_migrate_cma_page(page); +} +#else +static inline bool is_pinnable_page(struct page *page) +{ + return true; +} +#endif + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); --- a/include/linux/sched/mm.h~mm-honor-pf_memalloc_pin-for-all-movable-pages +++ a/include/linux/sched/mm.h @@ -151,12 +151,13 @@ static inline bool in_vfork(struct task_ * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS + * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence @@ -165,6 +166,9 @@ static inline gfp_t current_gfp_context( flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; + + if (pflags & PF_MEMALLOC_PIN) + flags &= ~__GFP_MOVABLE; } return flags; } --- a/mm/hugetlb.c~mm-honor-pf_memalloc_pin-for-all-movable-pages +++ a/mm/hugetlb.c @@ -1083,7 +1083,7 @@ static struct page *dequeue_huge_page_no lockdep_assert_held(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { - if (pin && is_migrate_cma_page(page)) + if (pin && !is_pinnable_page(page)) continue; if (PageHWPoison(page)) --- a/mm/page_alloc.c~mm-honor-pf_memalloc_pin-for-all-movable-pages +++ a/mm/page_alloc.c @@ -3859,16 +3859,13 @@ alloc_flags_nofragment(struct zone *zone return alloc_flags; } -static inline unsigned int current_alloc_flags(gfp_t gfp_mask, - unsigned int alloc_flags) +/* Must be called after current_gfp_context() which can change gfp_mask */ +static inline unsigned int gfp_to_alloc_flags_cma(gfp_t gfp_mask, + unsigned int alloc_flags) { #ifdef CONFIG_CMA - unsigned int pflags = current->flags; - - if (!(pflags & PF_MEMALLOC_PIN) && - gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) + if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; - #endif return alloc_flags; } @@ -4526,7 +4523,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) } else if (unlikely(rt_task(current)) && !in_interrupt()) alloc_flags |= ALLOC_HARDER; - alloc_flags = current_alloc_flags(gfp_mask, alloc_flags); + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); return alloc_flags; } @@ -4828,7 +4825,7 @@ retry: reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); if (reserve_flags) - alloc_flags = current_alloc_flags(gfp_mask, reserve_flags); + alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, reserve_flags); /* * Reset the nodemask and zonelist iterators if memory policies can be @@ -4997,7 +4994,7 @@ static inline bool prepare_alloc_pages(g if (should_fail_alloc_page(gfp_mask, order)) return false; - *alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags); + *alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags); /* Dirty zone balancing only done in the fast path */ ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); @@ -5184,7 +5181,8 @@ struct page *__alloc_pages(gfp_t gfp, un * Apply scoped allocation constraints. This is mainly about GFP_NOFS * resp. GFP_NOIO which has to be inherited for all allocation requests * from a particular context which has been marked by - * memalloc_no{fs,io}_{save,restore}. + * memalloc_no{fs,io}_{save,restore}. And PF_MEMALLOC_PIN which ensures + * movable zones are not used during allocation. */ gfp = current_gfp_context(gfp); alloc_gfp = gfp; _
