The patch titled hugetlb: multiple hstates for multiple page sizes has been removed from the -mm tree. Its filename was hugetlb-multiple-hstates-for-multiple-page-sizes.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: hugetlb: multiple hstates for multiple page sizes From: Nick Piggin <npiggin@xxxxxxx> Add basic support for more than one hstate in hugetlbfs. This is the key to supporting multiple hugetlbfs page sizes at once. - Rather than a single hstate, we now have an array, with an iterator - default_hstate continues to be the struct hstate which we use by default - Add functions for architectures to register new hstates [akpm@xxxxxxxxxxxxxxxxxxxx: coding-style fixes] Acked-by: Adam Litke <agl@xxxxxxxxxx> Acked-by: Nishanth Aravamudan <nacc@xxxxxxxxxx> Signed-off-by: Andi Kleen <ak@xxxxxxx> Signed-off-by: Nick Piggin <npiggin@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/hugetlb.h | 19 ++++ kernel/sysctl.c | 8 +- mm/hugetlb.c | 148 +++++++++++++++++++++++++++++++------- 3 files changed, 142 insertions(+), 33 deletions(-) diff -puN include/linux/hugetlb.h~hugetlb-multiple-hstates-for-multiple-page-sizes include/linux/hugetlb.h --- a/include/linux/hugetlb.h~hugetlb-multiple-hstates-for-multiple-page-sizes +++ a/include/linux/hugetlb.h @@ -36,8 +36,6 @@ int hugetlb_reserve_pages(struct inode * struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); -extern unsigned long max_huge_pages; -extern unsigned long sysctl_overcommit_huge_pages; extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; @@ -181,7 +179,17 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; }; -extern struct hstate default_hstate; +void __init hugetlb_add_hstate(unsigned order); +struct hstate *size_to_hstate(unsigned long size); + +#ifndef HUGE_MAX_HSTATE +#define HUGE_MAX_HSTATE 1 +#endif + +extern struct hstate hstates[HUGE_MAX_HSTATE]; +extern unsigned int default_hstate_idx; + +#define default_hstate (hstates[default_hstate_idx]) static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { @@ -230,6 +238,11 @@ static inline unsigned int blocks_per_hu #include <asm/hugetlb.h> +static inline struct hstate *page_hstate(struct page *page) +{ + return size_to_hstate(PAGE_SIZE << compound_order(page)); +} + #else struct hstate {}; #define hstate_file(f) NULL diff -puN kernel/sysctl.c~hugetlb-multiple-hstates-for-multiple-page-sizes kernel/sysctl.c --- a/kernel/sysctl.c~hugetlb-multiple-hstates-for-multiple-page-sizes +++ a/kernel/sysctl.c @@ -947,7 +947,7 @@ static struct ctl_table vm_table[] = { #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", - .data = &max_huge_pages, + .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_sysctl_handler, @@ -973,10 +973,12 @@ static struct ctl_table vm_table[] = { { .ctl_name = CTL_UNNUMBERED, .procname = "nr_overcommit_hugepages", - .data = &sysctl_overcommit_huge_pages, - .maxlen = sizeof(sysctl_overcommit_huge_pages), + .data = NULL, + .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_overcommit_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, }, #endif { diff -puN mm/hugetlb.c~hugetlb-multiple-hstates-for-multiple-page-sizes mm/hugetlb.c --- a/mm/hugetlb.c~hugetlb-multiple-hstates-for-multiple-page-sizes +++ a/mm/hugetlb.c @@ -22,12 +22,19 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -unsigned long max_huge_pages; -unsigned long sysctl_overcommit_huge_pages; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -struct hstate default_hstate; +static int max_hstate; +unsigned int default_hstate_idx; +struct hstate hstates[HUGE_MAX_HSTATE]; + +/* for command line parsing */ +static struct hstate * __initdata parsed_hstate; +static unsigned long __initdata default_hstate_max_huge_pages; + +#define for_each_hstate(h) \ + for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++) /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages @@ -454,13 +461,24 @@ static void update_and_free_page(struct __free_pages(page, huge_page_order(h)); } +struct hstate *size_to_hstate(unsigned long size) +{ + struct hstate *h; + + for_each_hstate(h) { + if (huge_page_size(h) == size) + return h; + } + return NULL; +} + static void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the * compound page destructor. */ - struct hstate *h = &default_hstate; + struct hstate *h = page_hstate(page); int nid = page_to_nid(page); struct address_space *mapping; @@ -887,39 +905,94 @@ static struct page *alloc_huge_page(stru return page; } -static int __init hugetlb_init(void) +static void __init hugetlb_init_one_hstate(struct hstate *h) { unsigned long i; - struct hstate *h = &default_hstate; - - if (HPAGE_SHIFT == 0) - return 0; - - if (!h->order) { - h->order = HPAGE_SHIFT - PAGE_SHIFT; - h->mask = HPAGE_MASK; - } for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); h->hugetlb_next_nid = first_node(node_online_map); - for (i = 0; i < max_huge_pages; ++i) { + for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_fresh_huge_page(h)) break; } - max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; - printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n", - h->free_huge_pages); + h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; +} + +static void __init hugetlb_init_hstates(void) +{ + struct hstate *h; + + for_each_hstate(h) { + hugetlb_init_one_hstate(h); + } +} + +static void __init report_hugepages(void) +{ + struct hstate *h; + + for_each_hstate(h) { + printk(KERN_INFO "Total HugeTLB memory allocated, " + "%ld %dMB pages\n", + h->free_huge_pages, + 1 << (h->order + PAGE_SHIFT - 20)); + } +} + +static int __init hugetlb_init(void) +{ + BUILD_BUG_ON(HPAGE_SHIFT == 0); + + if (!size_to_hstate(HPAGE_SIZE)) { + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; + } + default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; + + hugetlb_init_hstates(); + + report_hugepages(); + return 0; } module_init(hugetlb_init); +/* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_add_hstate(unsigned order) +{ + struct hstate *h; + if (size_to_hstate(PAGE_SIZE << order)) { + printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + return; + } + BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(order == 0); + h = &hstates[max_hstate++]; + h->order = order; + h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); + hugetlb_init_one_hstate(h); + parsed_hstate = h; +} + static int __init hugetlb_setup(char *s) { - if (sscanf(s, "%lu", &max_huge_pages) <= 0) - max_huge_pages = 0; + unsigned long *mhp; + + /* + * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * so this hugepages= parameter goes to the "default hstate". + */ + if (!max_hstate) + mhp = &default_hstate_max_huge_pages; + else + mhp = &parsed_hstate->max_huge_pages; + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + return 1; } __setup("hugepages=", hugetlb_setup); @@ -950,7 +1023,7 @@ static void try_to_free_low(struct hstat if (PageHighMem(page)) continue; list_del(&page->lru); - update_and_free_page(page); + update_and_free_page(h, page); h->free_huge_pages--; h->free_huge_pages_node[page_to_nid(page)]--; } @@ -963,10 +1036,9 @@ static inline void try_to_free_low(struc #endif #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) -static unsigned long set_max_huge_pages(unsigned long count) +static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) { unsigned long min_count, ret; - struct hstate *h = &default_hstate; /* * Increase the pool size @@ -1037,8 +1109,19 @@ int hugetlb_sysctl_handler(struct ctl_ta struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { + struct hstate *h = &default_hstate; + unsigned long tmp; + + if (!write) + tmp = h->max_huge_pages; + + table->data = &tmp; + table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - max_huge_pages = set_max_huge_pages(max_huge_pages); + + if (write) + h->max_huge_pages = set_max_huge_pages(h, tmp); + return 0; } @@ -1059,10 +1142,21 @@ int hugetlb_overcommit_handler(struct ct size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; + unsigned long tmp; + + if (!write) + tmp = h->nr_overcommit_huge_pages; + + table->data = &tmp; + table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - spin_lock(&hugetlb_lock); - h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; - spin_unlock(&hugetlb_lock); + + if (write) { + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = tmp; + spin_unlock(&hugetlb_lock); + } + return 0; } _ Patches currently in -mm which might be from npiggin@xxxxxxx are origin.patch linux-next.patch mmu-notifiers-add-list_del_init_rcu.patch mmu-notifiers-add-mm_take_all_locks-operation.patch mmu-notifier-core.patch x86-implement-pte_special.patch x86-implement-pte_special-fix.patch mm-introduce-get_user_pages_fast.patch mm-introduce-get_user_pages_fast-fix.patch mm-introduce-get_user_pages_fast-checkpatch-fixes.patch x86-lockless-get_user_pages_fast.patch x86-lockless-get_user_pages_fast-checkpatch-fixes.patch x86-lockless-get_user_pages_fast-fix.patch x86-lockless-get_user_pages_fast-fix-2.patch x86-lockless-get_user_pages_fast-fix-2-fix-fix.patch x86-lockless-get_user_pages_fast-fix-warning.patch dio-use-get_user_pages_fast.patch splice-use-get_user_pages_fast.patch x86-support-1gb-hugepages-with-get_user_pages_lockless.patch mm-readahead-scan-lockless.patch radix-tree-add-gang_lookup_slot-gang_lookup_slot_tag.patch mm-speculative-page-references.patch mm-speculative-page-references-fix.patch mm-speculative-page-references-fix-add_to_page_cache.patch mm-speculative-page-references-fix-add_to_page_cache-fix.patch mm-lockless-pagecache.patch mm-spinlock-tree_lock.patch powerpc-implement-pte_special.patch powerpc-implement-pte_special-update.patch powerpc-lockless-get_user_pages.patch vmscan-move-isolate_lru_page-to-vmscanc.patch vmscan-move-isolate_lru_page-to-vmscanc-fix.patch vmscan-split-lru-lists-into-anon-file-sets-splitlru-bdi_cap_swap_backed.patch mlock-mlocked-pages-are-unevictable.patch mlock-mlocked-pages-are-unevictable-fix.patch mlock-mlocked-pages-are-unevictable-fix-fix.patch mlock-mlocked-pages-are-unevictable-fix-3.patch mlock-mlocked-pages-are-unevictable-fix-fix-munlock-page-table-walk-now-requires-mm.patch mmap-handle-mlocked-pages-during-map-remap-unmap.patch mmap-handle-mlocked-pages-during-map-remap-unmap-cleanup.patch fix-double-unlock_page-in-2626-rc5-mm3-kernel-bug-at-mm-filemapc-575.patch vmstat-mlocked-pages-statistics.patch vmstat-mlocked-pages-statistics-fix-incorrect-mlocked-field-of-proc-meminfo.patch reiser4.patch likeliness-accounting-change-and-cleanup.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