The patch titled Allow huge page allocations to use GFP_HIGH_MOVABLE has been added to the -mm tree. Its filename is allow-huge-page-allocations-to-use-gfp_high_movable.patch *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find out what to do about this ------------------------------------------------------ Subject: Allow huge page allocations to use GFP_HIGH_MOVABLE From: Mel Gorman <mel@xxxxxxxxx> Huge pages are not movable so are not allocated from ZONE_MOVABLE. However, as ZONE_MOVABLE will always have pages that can be migrated or reclaimed, it can be used to satisfy hugepage allocations even when the system has been running a long time. This allows an administrator to resize the hugepage pool at runtime depending on the size of ZONE_MOVABLE. This patch adds a new sysctl called hugepages_treat_as_movable. When a non-zero value is written to it, future allocations for the huge page pool will use ZONE_MOVABLE. Despite huge pages being non-movable, we do not introduce additional external fragmentation of note as huge pages are always the largest contiguous block we care about. Signed-off-by: Mel Gorman <mel@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/hugetlb.h | 3 +++ include/linux/mempolicy.h | 6 +++--- include/linux/sysctl.h | 1 + kernel/sysctl.c | 8 ++++++++ mm/hugetlb.c | 23 ++++++++++++++++++++--- mm/mempolicy.c | 5 +++-- 6 files changed, 38 insertions(+), 8 deletions(-) diff -puN include/linux/hugetlb.h~allow-huge-page-allocations-to-use-gfp_high_movable include/linux/hugetlb.h --- a/include/linux/hugetlb.h~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/include/linux/hugetlb.h @@ -15,6 +15,7 @@ static inline int is_vm_hugetlb_page(str } int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); @@ -29,6 +30,8 @@ int hugetlb_reserve_pages(struct inode * void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; +extern unsigned long hugepages_treat_as_movable; +extern gfp_t htlb_alloc_mask; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; diff -puN include/linux/mempolicy.h~allow-huge-page-allocations-to-use-gfp_high_movable include/linux/mempolicy.h --- a/include/linux/mempolicy.h~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/include/linux/mempolicy.h @@ -159,7 +159,7 @@ extern void mpol_fix_fork_child_flag(str extern struct mempolicy default_policy; extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr); + unsigned long addr, gfp_t gfp_flags); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -256,9 +256,9 @@ static inline void mpol_fix_fork_child_f #define set_cpuset_being_rebound(x) do {} while (0) static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, gfp_t gfp_flags) { - return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER); + return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags); } static inline int do_migrate_pages(struct mm_struct *mm, diff -puN include/linux/sysctl.h~allow-huge-page-allocations-to-use-gfp_high_movable include/linux/sysctl.h --- a/include/linux/sysctl.h~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/include/linux/sysctl.h @@ -207,6 +207,7 @@ enum VM_PANIC_ON_OOM=33, /* panic at out-of-memory */ VM_VDSO_ENABLED=34, /* map VDSO into new processes? */ VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */ + VM_HUGETLB_TREAT_MOVABLE=36, /* Allocate hugepages from ZONE_MOVABLE */ /* s390 vm cmm sysctls */ VM_CMM_PAGES=1111, diff -puN kernel/sysctl.c~allow-huge-page-allocations-to-use-gfp_high_movable kernel/sysctl.c --- a/kernel/sysctl.c~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/kernel/sysctl.c @@ -722,6 +722,14 @@ static ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .ctl_name = VM_HUGETLB_TREAT_MOVABLE, + .procname = "hugepages_treat_as_movable", + .data = &hugepages_treat_as_movable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &hugetlb_treat_movable_handler, + }, #endif { .ctl_name = VM_LOWMEM_RESERVE_RATIO, diff -puN mm/hugetlb.c~allow-huge-page-allocations-to-use-gfp_high_movable mm/hugetlb.c --- a/mm/hugetlb.c~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/mm/hugetlb.c @@ -27,6 +27,9 @@ unsigned long max_huge_pages; static struct list_head hugepage_freelists[MAX_NUMNODES]; static unsigned int nr_huge_pages_node[MAX_NUMNODES]; static unsigned int free_huge_pages_node[MAX_NUMNODES]; +gfp_t htlb_alloc_mask = GFP_HIGHUSER; +unsigned long hugepages_treat_as_movable; + /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages */ @@ -68,12 +71,13 @@ static struct page *dequeue_huge_page(st { int nid = numa_node_id(); struct page *page = NULL; - struct zonelist *zonelist = huge_zonelist(vma, address); + struct zonelist *zonelist = huge_zonelist(vma, address, + htlb_alloc_mask); struct zone **z; for (z = zonelist->zones; *z; z++) { nid = zone_to_nid(*z); - if (cpuset_zone_allowed_softwall(*z, GFP_HIGHUSER) && + if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) && !list_empty(&hugepage_freelists[nid])) break; } @@ -103,7 +107,7 @@ static int alloc_fresh_huge_page(void) { static int nid = 0; struct page *page; - page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN, + page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN, HUGETLB_PAGE_ORDER); nid = next_node(nid, node_online_map); if (nid == MAX_NUMNODES) @@ -243,6 +247,19 @@ int hugetlb_sysctl_handler(struct ctl_ta max_huge_pages = set_max_huge_pages(max_huge_pages); return 0; } + +int hugetlb_treat_movable_handler(struct ctl_table *table, int write, + struct file *file, void __user *buffer, + size_t *length, loff_t *ppos) +{ + proc_dointvec(table, write, file, buffer, length, ppos); + if (hugepages_treat_as_movable) + htlb_alloc_mask = GFP_HIGH_MOVABLE; + else + htlb_alloc_mask = GFP_HIGHUSER; + return 0; +} + #endif /* CONFIG_SYSCTL */ int hugetlb_report_meminfo(char *buf) diff -puN mm/mempolicy.c~allow-huge-page-allocations-to-use-gfp_high_movable mm/mempolicy.c --- a/mm/mempolicy.c~allow-huge-page-allocations-to-use-gfp_high_movable +++ a/mm/mempolicy.c @@ -1202,7 +1202,8 @@ static inline unsigned interleave_nid(st #ifdef CONFIG_HUGETLBFS /* Return a zonelist suitable for a huge page allocation. */ -struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr) +struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, + gfp_t gfp_flags) { struct mempolicy *pol = get_vma_policy(current, vma, addr); @@ -1210,7 +1211,7 @@ struct zonelist *huge_zonelist(struct vm unsigned nid; nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT); - return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER); + return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags); } return zonelist_policy(GFP_HIGHUSER, pol); } _ Patches currently in -mm which might be from mel@xxxxxxxxx are add-a-bitmap-that-is-used-to-track-flags-affecting-a-block-of-pages.patch add-__gfp_movable-for-callers-to-flag-allocations-from-high-memory-that-may-be-migrated.patch add-__gfp_movable-for-callers-to-flag-allocations-from-low-memory-that-may-be-migrated.patch split-the-free-lists-for-movable-and-unmovable-allocations.patch choose-pages-from-the-per-cpu-list-based-on-migration-type.patch add-a-configure-option-to-group-pages-by-mobility.patch drain-per-cpu-lists-when-high-order-allocations-fail.patch move-free-pages-between-lists-on-steal.patch group-short-lived-and-reclaimable-kernel-allocations.patch group-high-order-atomic-allocations.patch bias-the-placement-of-kernel-pages-at-lower-pfns.patch be-more-agressive-about-stealing-when-migrate_reclaimable-allocations-fallback.patch create-the-zone_movable-zone.patch allow-huge-page-allocations-to-use-gfp_high_movable.patch x86-specify-amount-of-kernel-memory-at-boot-time.patch ppc-and-powerpc-specify-amount-of-kernel-memory-at-boot-time.patch x86_64-specify-amount-of-kernel-memory-at-boot-time.patch ia64-specify-amount-of-kernel-memory-at-boot-time.patch add-documentation-for-additional-boot-parameter-and-sysctl.patch ext2-reservations.patch add-__gfp_movable-for-callers-to-flag-allocations-from-high-memory-that-may-be-migrated-swap-prefetch.patch add-debugging-aid-for-memory-initialisation-problems.patch add-debugging-aid-for-memory-initialisation-problems-fix.patch - To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html