X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=2d16fa6b8c2d8fb6a40ea5b3f9ea57c77a34d1af;hb=e0572325d23b8c89930a08e0b8b3850a6fe75d7d;hp=72acbb29d2cc68ca50161af90d3cbe042c9852aa;hpb=c37f9fb11c976ffc08200d631dada6dcbfd07ea4;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 72acbb2..2d16fa6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7,33 +7,43 @@ #include #include #include +#include #include #include +#include #include #include #include #include #include +#include +#include #include #include +#include #include +#include #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages; -static unsigned long surplus_huge_pages; -static unsigned long nr_overcommit_huge_pages; -unsigned long max_huge_pages; -unsigned long sysctl_overcommit_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]; -static unsigned int surplus_huge_pages_node[MAX_NUMNODES]; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -static int hugetlb_next_nid; + +static int max_hstate; +unsigned int default_hstate_idx; +struct hstate hstates[HUGE_MAX_HSTATE]; + +__initdata LIST_HEAD(huge_boot_pages); + +/* for command line parsing */ +static struct hstate * __initdata parsed_hstate; +static unsigned long __initdata default_hstate_max_huge_pages; +static unsigned long __initdata default_hstate_size; + +#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 @@ -43,6 +53,16 @@ static DEFINE_SPINLOCK(hugetlb_lock); /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. + * + * The region data structures are protected by a combination of the mmap_sem + * and the hugetlb_instantion_mutex. To access or modify a region the caller + * must either hold the mmap_sem for write, or the mmap_sem for read and + * the hugetlb_instantiation mutex: + * + * down_write(&mm->mmap_sem); + * or + * down_read(&mm->mmap_sem); + * mutex_lock(&hugetlb_instantiation_mutex); */ struct file_region { struct list_head link; @@ -165,31 +185,80 @@ static long region_truncate(struct list_head *head, long end) return chg; } +static long region_count(struct list_head *head, long f, long t) +{ + struct file_region *rg; + long chg = 0; + + /* Locate each segment we overlap with, and count that overlap. */ + list_for_each_entry(rg, head, link) { + int seg_from; + int seg_to; + + if (rg->to <= f) + continue; + if (rg->from >= t) + break; + + seg_from = max(rg->from, f); + seg_to = min(rg->to, t); + + chg += seg_to - seg_from; + } + + return chg; +} + /* * Convert the address within this vma to the page offset within - * the mapping, in base page units. + * the mapping, in pagecache page units; huge pages here. */ -static pgoff_t vma_page_offset(struct vm_area_struct *vma, - unsigned long address) +static pgoff_t vma_hugecache_offset(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { - return ((address - vma->vm_start) >> PAGE_SHIFT) + - (vma->vm_pgoff >> PAGE_SHIFT); + return ((address - vma->vm_start) >> huge_page_shift(h)) + + (vma->vm_pgoff >> huge_page_order(h)); } /* - * Convert the address within this vma to the page offset within - * the mapping, in pagecache page units; huge pages here. + * Return the size of the pages allocated when backing a VMA. In the majority + * cases this will be same size as used by the page table entries. + */ +unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) +{ + struct hstate *hstate; + + if (!is_vm_hugetlb_page(vma)) + return PAGE_SIZE; + + hstate = hstate_vma(vma); + + return 1UL << (hstate->order + PAGE_SHIFT); +} +EXPORT_SYMBOL_GPL(vma_kernel_pagesize); + +/* + * Return the page size being used by the MMU to back a VMA. In the majority + * of cases, the page size used by the kernel matches the MMU size. On + * architectures where it differs, an architecture-specific version of this + * function is required. */ -static pgoff_t vma_pagecache_offset(struct vm_area_struct *vma, - unsigned long address) +#ifndef vma_mmu_pagesize +unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { - return ((address - vma->vm_start) >> HPAGE_SHIFT) + - (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + return vma_kernel_pagesize(vma); } +#endif -#define HPAGE_RESV_OWNER (1UL << (BITS_PER_LONG - 1)) -#define HPAGE_RESV_UNMAPPED (1UL << (BITS_PER_LONG - 2)) +/* + * Flags for MAP_PRIVATE reservations. These are stored in the bottom + * bits of the reservation map pointer, which are always clear due to + * alignment. + */ +#define HPAGE_RESV_OWNER (1UL << 0) +#define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) + /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() @@ -199,6 +268,15 @@ static pgoff_t vma_pagecache_offset(struct vm_area_struct *vma, * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. + * + * The private mapping reservation is represented in a subtly different + * manner to a shared mapping. A shared mapping has a region map associated + * with the underlying file, this region map represents the backing file + * pages which have ever had a reservation assigned which this persists even + * after the page is instantiated. A private mapping has a region map + * associated with the original mmap which is attached to all VMAs which + * reference it, this region map represents those offsets which have consumed + * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { @@ -211,28 +289,54 @@ static void set_vma_private_data(struct vm_area_struct *vma, vma->vm_private_data = (void *)value; } -static unsigned long vma_resv_huge_pages(struct vm_area_struct *vma) +struct resv_map { + struct kref refs; + struct list_head regions; +}; + +static struct resv_map *resv_map_alloc(void) +{ + struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); + if (!resv_map) + return NULL; + + kref_init(&resv_map->refs); + INIT_LIST_HEAD(&resv_map->regions); + + return resv_map; +} + +static void resv_map_release(struct kref *ref) +{ + struct resv_map *resv_map = container_of(ref, struct resv_map, refs); + + /* Clear out any active regions before we release the map. */ + region_truncate(&resv_map->regions, 0); + kfree(resv_map); +} + +static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) - return get_vma_private_data(vma) & ~HPAGE_RESV_MASK; - return 0; + if (!(vma->vm_flags & VM_MAYSHARE)) + return (struct resv_map *)(get_vma_private_data(vma) & + ~HPAGE_RESV_MASK); + return NULL; } -static void set_vma_resv_huge_pages(struct vm_area_struct *vma, - unsigned long reserve) +static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); - set_vma_private_data(vma, - (get_vma_private_data(vma) & HPAGE_RESV_MASK) | reserve); + set_vma_private_data(vma, (get_vma_private_data(vma) & + HPAGE_RESV_MASK) | (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } @@ -245,27 +349,21 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) } /* Decrement the reserved pages in the hugepage pool by one */ -static void decrement_hugepage_resv_vma(struct vm_area_struct *vma) +static void decrement_hugepage_resv_vma(struct hstate *h, + struct vm_area_struct *vma) { if (vma->vm_flags & VM_NORESERVE) return; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { /* Shared mappings always use reserves */ - resv_huge_pages--; - } else { + h->resv_huge_pages--; + } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Only the process that called mmap() has reserves for * private mappings. */ - if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - unsigned long flags, reserve; - resv_huge_pages--; - flags = (unsigned long)vma->vm_private_data & - HPAGE_RESV_MASK; - reserve = (unsigned long)vma->vm_private_data - 1; - vma->vm_private_data = (void *)(reserve | flags); - } + h->resv_huge_pages--; } } @@ -273,70 +371,94 @@ static void decrement_hugepage_resv_vma(struct vm_area_struct *vma) void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) vma->vm_private_data = (void *)0; } /* Returns true if the VMA has associated reserve pages */ -static int vma_has_private_reserves(struct vm_area_struct *vma) +static int vma_has_reserves(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_SHARED) - return 0; - if (!vma_resv_huge_pages(vma)) - return 0; - return 1; + if (vma->vm_flags & VM_MAYSHARE) + return 1; + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + return 1; + return 0; } -static void clear_huge_page(struct page *page, unsigned long addr) +static void clear_gigantic_page(struct page *page, + unsigned long addr, unsigned long sz) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} +static void clear_huge_page(struct page *page, + unsigned long addr, unsigned long sz) { int i; + if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) { + clear_gigantic_page(page, addr, sz); + return; + } + might_sleep(); - for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) { + for (i = 0; i < sz/PAGE_SIZE; i++) { cond_resched(); clear_user_highpage(page + i, addr + i * PAGE_SIZE); } } +static void copy_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma) +{ + int i; + struct hstate *h = hstate_vma(vma); + struct page *dst_base = dst; + struct page *src_base = src; + might_sleep(); + for (i = 0; i < pages_per_huge_page(h); ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} static void copy_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; + struct hstate *h = hstate_vma(vma); + + if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { + copy_gigantic_page(dst, src, addr, vma); + return; + } might_sleep(); - for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) { + for (i = 0; i < pages_per_huge_page(h); i++) { cond_resched(); copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } } -static void enqueue_huge_page(struct page *page) +static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); - list_add(&page->lru, &hugepage_freelists[nid]); - free_huge_pages++; - free_huge_pages_node[nid]++; -} - -static struct page *dequeue_huge_page(void) -{ - int nid; - struct page *page = NULL; - - for (nid = 0; nid < MAX_NUMNODES; ++nid) { - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; - break; - } - } - return page; + list_add(&page->lru, &h->hugepage_freelists[nid]); + h->free_huge_pages++; + h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, +static struct page *dequeue_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, unsigned long address, int avoid_reserve) { int nid; @@ -353,27 +475,27 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ - if (!vma_has_private_reserves(vma) && - free_huge_pages - resv_huge_pages == 0) + if (!vma_has_reserves(vma) && + h->free_huge_pages - h->resv_huge_pages == 0) return NULL; /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && free_huge_pages - resv_huge_pages == 0) + if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) return NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { nid = zone_to_nid(zone); if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) && - !list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + !list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; if (!avoid_reserve) - decrement_hugepage_resv_vma(vma); + decrement_hugepage_resv_vma(h, vma); break; } @@ -382,12 +504,15 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, return page; } -static void update_and_free_page(struct page *page) +static void update_and_free_page(struct hstate *h, struct page *page) { int i; - nr_huge_pages--; - nr_huge_pages_node[page_to_nid(page)]--; - for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) { + + VM_BUG_ON(h->order >= MAX_ORDER); + + h->nr_huge_pages--; + h->nr_huge_pages_node[page_to_nid(page)]--; + for (i = 0; i < pages_per_huge_page(h); i++) { page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1<< PG_writeback); @@ -395,11 +520,27 @@ static void update_and_free_page(struct page *page) set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(page); - __free_pages(page, HUGETLB_PAGE_ORDER); + __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 = page_hstate(page); int nid = page_to_nid(page); struct address_space *mapping; @@ -409,106 +550,139 @@ static void free_huge_page(struct page *page) INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); - if (surplus_huge_pages_node[nid]) { - update_and_free_page(page); - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; + if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + update_and_free_page(h, page); + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; } else { - enqueue_huge_page(page); + enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); if (mapping) hugetlb_put_quota(mapping, 1); } -/* - * Increment or decrement surplus_huge_pages. Keep node-specific counters - * balanced by operating on them in a round-robin fashion. - * Returns 1 if an adjustment was made. - */ -static int adjust_pool_surplus(int delta) +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { - static int prev_nid; - int nid = prev_nid; - int ret = 0; + set_compound_page_dtor(page, free_huge_page); + spin_lock(&hugetlb_lock); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + spin_unlock(&hugetlb_lock); + put_page(page); /* free it into the hugepage allocator */ +} - VM_BUG_ON(delta != -1 && delta != 1); - do { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); +static void prep_compound_gigantic_page(struct page *page, unsigned long order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + /* we rely on prep_new_huge_page to set the destructor */ + set_compound_order(page, order); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + __SetPageTail(p); + p->first_page = page; + } +} - /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !surplus_huge_pages_node[nid]) - continue; - /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && surplus_huge_pages_node[nid] >= - nr_huge_pages_node[nid]) - continue; +int PageHuge(struct page *page) +{ + compound_page_dtor *dtor; - surplus_huge_pages += delta; - surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (nid != prev_nid); + if (!PageCompound(page)) + return 0; - prev_nid = nid; - return ret; + page = compound_head(page); + dtor = get_compound_page_dtor(page); + + return dtor == free_huge_page; } -static struct page *alloc_fresh_huge_page_node(int nid) +static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; - page = alloc_pages_node(nid, + if (h->order >= MAX_ORDER) + return NULL; + + page = alloc_pages_exact_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); if (page) { if (arch_prepare_hugepage(page)) { - __free_pages(page, HUGETLB_PAGE_ORDER); + __free_pages(page, huge_page_order(h)); return NULL; } - set_compound_page_dtor(page, free_huge_page); - spin_lock(&hugetlb_lock); - nr_huge_pages++; - nr_huge_pages_node[nid]++; - spin_unlock(&hugetlb_lock); - put_page(page); /* free it into the hugepage allocator */ + prep_new_huge_page(h, page, nid); } return page; } -static int alloc_fresh_huge_page(void) +/* + * common helper functions for hstate_next_node_to_{alloc|free}. + * We may have allocated or freed a huge page based on a different + * nodes_allowed previously, so h->next_node_to_{alloc|free} might + * be outside of *nodes_allowed. Ensure that we use an allowed + * node for alloc or free. + */ +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + nid = next_node(nid, *nodes_allowed); + if (nid == MAX_NUMNODES) + nid = first_node(*nodes_allowed); + VM_BUG_ON(nid >= MAX_NUMNODES); + + return nid; +} + +static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) +{ + if (!node_isset(nid, *nodes_allowed)) + nid = next_node_allowed(nid, nodes_allowed); + return nid; +} + +/* + * returns the previously saved node ["this node"] from which to + * allocate a persistent huge page for the pool and advance the + * next node from which to allocate, handling wrap at end of node + * mask. + */ +static int hstate_next_node_to_alloc(struct hstate *h, + nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); + h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { struct page *page; int start_nid; int next_nid; int ret = 0; - start_nid = hugetlb_next_nid; + start_nid = hstate_next_node_to_alloc(h, nodes_allowed); + next_nid = start_nid; do { - page = alloc_fresh_huge_page_node(hugetlb_next_nid); - if (page) + page = alloc_fresh_huge_page_node(h, next_nid); + if (page) { ret = 1; - /* - * Use a helper variable to find the next node and then - * copy it back to hugetlb_next_nid afterwards: - * otherwise there's a window in which a racer might - * pass invalid nid MAX_NUMNODES to alloc_pages_node. - * But we don't need to use a spin_lock here: it really - * doesn't matter if occasionally a racer chooses the - * same nid as we do. Move nid forward in the mask even - * if we just successfully allocated a hugepage so that - * the next caller gets hugepages on the next node. - */ - next_nid = next_node(hugetlb_next_nid, node_online_map); - if (next_nid == MAX_NUMNODES) - next_nid = first_node(node_online_map); - hugetlb_next_nid = next_nid; - } while (!page && hugetlb_next_nid != start_nid); + break; + } + next_nid = hstate_next_node_to_alloc(h, nodes_allowed); + } while (next_nid != start_nid); if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -518,12 +692,76 @@ static int alloc_fresh_huge_page(void) return ret; } -static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, - unsigned long address) +/* + * helper for free_pool_huge_page() - return the previously saved + * node ["this node"] from which to free a huge page. Advance the + * next node id whether or not we find a free huge page to free so + * that the next attempt to free addresses the next node. + */ +static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) +{ + int nid; + + VM_BUG_ON(!nodes_allowed); + + nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); + h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); + + return nid; +} + +/* + * Free huge page from pool from next node to free. + * Attempt to keep persistent huge pages more or less + * balanced over allowed nodes. + * Called with hugetlb_lock locked. + */ +static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, + bool acct_surplus) +{ + int start_nid; + int next_nid; + int ret = 0; + + start_nid = hstate_next_node_to_free(h, nodes_allowed); + next_nid = start_nid; + + do { + /* + * If we're returning unused surplus pages, only examine + * nodes with surplus pages. + */ + if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) && + !list_empty(&h->hugepage_freelists[next_nid])) { + struct page *page = + list_entry(h->hugepage_freelists[next_nid].next, + struct page, lru); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[next_nid]--; + if (acct_surplus) { + h->surplus_huge_pages--; + h->surplus_huge_pages_node[next_nid]--; + } + update_and_free_page(h, page); + ret = 1; + break; + } + next_nid = hstate_next_node_to_free(h, nodes_allowed); + } while (next_nid != start_nid); + + return ret; +} + +static struct page *alloc_buddy_huge_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct page *page; unsigned int nid; + if (h->order >= MAX_ORDER) + return NULL; + /* * Assume we will successfully allocate the surplus page to * prevent racing processes from causing the surplus to exceed @@ -548,18 +786,23 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * per-node value is checked there. */ spin_lock(&hugetlb_lock); - if (surplus_huge_pages >= nr_overcommit_huge_pages) { + if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { spin_unlock(&hugetlb_lock); return NULL; } else { - nr_huge_pages++; - surplus_huge_pages++; + h->nr_huge_pages++; + h->surplus_huge_pages++; } spin_unlock(&hugetlb_lock); page = alloc_pages(htlb_alloc_mask|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); + + if (page && arch_prepare_hugepage(page)) { + __free_pages(page, huge_page_order(h)); + return NULL; + } spin_lock(&hugetlb_lock); if (page) { @@ -574,12 +817,12 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, /* * We incremented the global counters already */ - nr_huge_pages_node[nid]++; - surplus_huge_pages_node[nid]++; + h->nr_huge_pages_node[nid]++; + h->surplus_huge_pages_node[nid]++; __count_vm_event(HTLB_BUDDY_PGALLOC); } else { - nr_huge_pages--; - surplus_huge_pages--; + h->nr_huge_pages--; + h->surplus_huge_pages--; __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); } spin_unlock(&hugetlb_lock); @@ -591,16 +834,16 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * Increase the hugetlb pool such that it can accomodate a reservation * of size 'delta'. */ -static int gather_surplus_pages(int delta) +static int gather_surplus_pages(struct hstate *h, int delta) { struct list_head surplus_list; struct page *page, *tmp; int ret, i; int needed, allocated; - needed = (resv_huge_pages + delta) - free_huge_pages; + needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { - resv_huge_pages += delta; + h->resv_huge_pages += delta; return 0; } @@ -611,7 +854,7 @@ static int gather_surplus_pages(int delta) retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { - page = alloc_buddy_huge_page(NULL, 0); + page = alloc_buddy_huge_page(h, NULL, 0); if (!page) { /* * We were not able to allocate enough pages to @@ -632,7 +875,8 @@ retry: * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock(&hugetlb_lock); - needed = (resv_huge_pages + delta) - (free_huge_pages + allocated); + needed = (h->resv_huge_pages + delta) - + (h->free_huge_pages + allocated); if (needed > 0) goto retry; @@ -645,7 +889,7 @@ retry: * before they are reserved. */ needed += allocated; - resv_huge_pages += delta; + h->resv_huge_pages += delta; ret = 0; free: /* Free the needed pages to the hugetlb pool */ @@ -653,7 +897,7 @@ free: if ((--needed) < 0) break; list_del(&page->lru); - enqueue_huge_page(page); + enqueue_huge_page(h, page); } /* Free unnecessary surplus pages to the buddy allocator */ @@ -680,158 +924,913 @@ free: * When releasing a hugetlb pool reservation, any surplus pages that were * allocated to satisfy the reservation must be explicitly freed if they were * never used. + * Called with hugetlb_lock held. */ -static void return_unused_surplus_pages(unsigned long unused_resv_pages) +static void return_unused_surplus_pages(struct hstate *h, + unsigned long unused_resv_pages) { - static int nid = -1; - struct page *page; unsigned long nr_pages; + /* Uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; + + /* Cannot return gigantic pages currently */ + if (h->order >= MAX_ORDER) + return; + + nr_pages = min(unused_resv_pages, h->surplus_huge_pages); + /* * We want to release as many surplus pages as possible, spread - * evenly across all nodes. Iterate across all nodes until we - * can no longer free unreserved surplus pages. This occurs when - * the nodes with surplus pages have no free pages. + * evenly across all nodes with memory. Iterate across these nodes + * until we can no longer free unreserved surplus pages. This occurs + * when the nodes with surplus pages have no free pages. + * free_pool_huge_page() will balance the the freed pages across the + * on-line nodes with memory and will handle the hstate accounting. */ - unsigned long remaining_iterations = num_online_nodes(); + while (nr_pages--) { + if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1)) + break; + } +} - /* Uncommit the reservation */ - resv_huge_pages -= unused_resv_pages; +/* + * Determine if the huge page at addr within the vma has an associated + * reservation. Where it does not we will need to logically increase + * reservation and actually increase quota before an allocation can occur. + * Where any new reservation would be required the reservation change is + * prepared, but not committed. Once the page has been quota'd allocated + * an instantiated the change should be committed via vma_commit_reservation. + * No action is required on failure. + */ +static long vma_needs_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + + if (vma->vm_flags & VM_MAYSHARE) { + pgoff_t idx = vma_hugecache_offset(h, vma, addr); + return region_chg(&inode->i_mapping->private_list, + idx, idx + 1); - nr_pages = min(unused_resv_pages, surplus_huge_pages); + } else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + return 1; - while (remaining_iterations-- && nr_pages) { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); + } else { + long err; + pgoff_t idx = vma_hugecache_offset(h, vma, addr); + struct resv_map *reservations = vma_resv_map(vma); - if (!surplus_huge_pages_node[nid]) - continue; + err = region_chg(&reservations->regions, idx, idx + 1); + if (err < 0) + return err; + return 0; + } +} +static void vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + + if (vma->vm_flags & VM_MAYSHARE) { + pgoff_t idx = vma_hugecache_offset(h, vma, addr); + region_add(&inode->i_mapping->private_list, idx, idx + 1); + + } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + pgoff_t idx = vma_hugecache_offset(h, vma, addr); + struct resv_map *reservations = vma_resv_map(vma); + + /* Mark this page used in the map. */ + region_add(&reservations->regions, idx, idx + 1); + } +} + +static struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve) +{ + struct hstate *h = hstate_vma(vma); + struct page *page; + struct address_space *mapping = vma->vm_file->f_mapping; + struct inode *inode = mapping->host; + long chg; + + /* + * Processes that did not create the mapping will have no reserves and + * will not have accounted against quota. Check that the quota can be + * made before satisfying the allocation + * MAP_NORESERVE mappings may also need pages and quota allocated + * if no reserve mapping overlaps. + */ + chg = vma_needs_reservation(h, vma, addr); + if (chg < 0) + return ERR_PTR(chg); + if (chg) + if (hugetlb_get_quota(inode->i_mapping, chg)) + return ERR_PTR(-ENOSPC); + + spin_lock(&hugetlb_lock); + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); + spin_unlock(&hugetlb_lock); + + if (!page) { + page = alloc_buddy_huge_page(h, vma, addr); + if (!page) { + hugetlb_put_quota(inode->i_mapping, chg); + return ERR_PTR(-VM_FAULT_OOM); + } + } + + set_page_refcounted(page); + set_page_private(page, (unsigned long) mapping); + + vma_commit_reservation(h, vma, addr); + + return page; +} + +int __weak alloc_bootmem_huge_page(struct hstate *h) +{ + struct huge_bootmem_page *m; + int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); + + while (nr_nodes) { + void *addr; + + addr = __alloc_bootmem_node_nopanic( + NODE_DATA(hstate_next_node_to_alloc(h, + &node_states[N_HIGH_MEMORY])), + huge_page_size(h), huge_page_size(h), 0); + + if (addr) { + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + m = addr; + goto found; + } + nr_nodes--; + } + return 0; + +found: + BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1)); + /* Put them into a private list first because mem_map is not up yet */ + list_add(&m->list, &huge_boot_pages); + m->hstate = h; + return 1; +} + +static void prep_compound_huge_page(struct page *page, int order) +{ + if (unlikely(order > (MAX_ORDER - 1))) + prep_compound_gigantic_page(page, order); + else + prep_compound_page(page, order); +} + +/* Put bootmem huge pages into the standard lists after mem_map is up */ +static void __init gather_bootmem_prealloc(void) +{ + struct huge_bootmem_page *m; + + list_for_each_entry(m, &huge_boot_pages, list) { + struct page *page = virt_to_page(m); + struct hstate *h = m->hstate; + __ClearPageReserved(page); + WARN_ON(page_count(page) != 1); + prep_compound_huge_page(page, h->order); + prep_new_huge_page(h, page, page_to_nid(page)); + } +} + +static void __init hugetlb_hstate_alloc_pages(struct hstate *h) +{ + unsigned long i; + + for (i = 0; i < h->max_huge_pages; ++i) { + if (h->order >= MAX_ORDER) { + if (!alloc_bootmem_huge_page(h)) + break; + } else if (!alloc_fresh_huge_page(h, + &node_states[N_HIGH_MEMORY])) + break; + } + h->max_huge_pages = i; +} + +static void __init hugetlb_init_hstates(void) +{ + struct hstate *h; + + for_each_hstate(h) { + /* oversize hugepages were init'ed in early boot */ + if (h->order < MAX_ORDER) + hugetlb_hstate_alloc_pages(h); + } +} + +static char * __init memfmt(char *buf, unsigned long n) +{ + if (n >= (1UL << 30)) + sprintf(buf, "%lu GB", n >> 30); + else if (n >= (1UL << 20)) + sprintf(buf, "%lu MB", n >> 20); + else + sprintf(buf, "%lu KB", n >> 10); + return buf; +} + +static void __init report_hugepages(void) +{ + struct hstate *h; + + for_each_hstate(h) { + char buf[32]; + printk(KERN_INFO "HugeTLB registered %s page size, " + "pre-allocated %ld pages\n", + memfmt(buf, huge_page_size(h)), + h->free_huge_pages); + } +} + +#ifdef CONFIG_HIGHMEM +static void try_to_free_low(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) +{ + int i; + + if (h->order >= MAX_ORDER) + return; + + for_each_node_mask(i, *nodes_allowed) { + struct page *page, *next; + struct list_head *freel = &h->hugepage_freelists[i]; + list_for_each_entry_safe(page, next, freel, lru) { + if (count >= h->nr_huge_pages) + return; + if (PageHighMem(page)) + continue; + list_del(&page->lru); + update_and_free_page(h, page); + h->free_huge_pages--; + h->free_huge_pages_node[page_to_nid(page)]--; + } + } +} +#else +static inline void try_to_free_low(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) +{ +} +#endif + +/* + * Increment or decrement surplus_huge_pages. Keep node-specific counters + * balanced by operating on them in a round-robin fashion. + * Returns 1 if an adjustment was made. + */ +static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, + int delta) +{ + int start_nid, next_nid; + int ret = 0; + + VM_BUG_ON(delta != -1 && delta != 1); + + if (delta < 0) + start_nid = hstate_next_node_to_alloc(h, nodes_allowed); + else + start_nid = hstate_next_node_to_free(h, nodes_allowed); + next_nid = start_nid; + + do { + int nid = next_nid; + if (delta < 0) { + /* + * To shrink on this node, there must be a surplus page + */ + if (!h->surplus_huge_pages_node[nid]) { + next_nid = hstate_next_node_to_alloc(h, + nodes_allowed); + continue; + } + } + if (delta > 0) { + /* + * Surplus cannot exceed the total number of pages + */ + if (h->surplus_huge_pages_node[nid] >= + h->nr_huge_pages_node[nid]) { + next_nid = hstate_next_node_to_free(h, + nodes_allowed); + continue; + } + } + + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[nid] += delta; + ret = 1; + break; + } while (next_nid != start_nid); + + return ret; +} + +#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) +static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) +{ + unsigned long min_count, ret; + + if (h->order >= MAX_ORDER) + return h->max_huge_pages; + + /* + * Increase the pool size + * First take pages out of surplus state. Then make up the + * remaining difference by allocating fresh huge pages. + * + * We might race with alloc_buddy_huge_page() here and be unable + * to convert a surplus huge page to a normal huge page. That is + * not critical, though, it just means the overall size of the + * pool might be one hugepage larger than it needs to be, but + * within all the constraints specified by the sysctls. + */ + spin_lock(&hugetlb_lock); + while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, nodes_allowed, -1)) + break; + } + + while (count > persistent_huge_pages(h)) { + /* + * If this allocation races such that we no longer need the + * page, free_huge_page will handle it by freeing the page + * and reducing the surplus. + */ + spin_unlock(&hugetlb_lock); + ret = alloc_fresh_huge_page(h, nodes_allowed); + spin_lock(&hugetlb_lock); + if (!ret) + goto out; + + /* Bail for signals. Probably ctrl-c from user */ + if (signal_pending(current)) + goto out; + } + + /* + * Decrease the pool size + * First return free pages to the buddy allocator (being careful + * to keep enough around to satisfy reservations). Then place + * pages into surplus state as needed so the pool will shrink + * to the desired size as pages become free. + * + * By placing pages into the surplus state independent of the + * overcommit value, we are allowing the surplus pool size to + * exceed overcommit. There are few sane options here. Since + * alloc_buddy_huge_page() is checking the global counter, + * though, we'll note that we're not allowed to exceed surplus + * and won't grow the pool anywhere else. Not until one of the + * sysctls are changed, or the surplus pages go out of use. + */ + min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; + min_count = max(count, min_count); + try_to_free_low(h, min_count, nodes_allowed); + while (min_count < persistent_huge_pages(h)) { + if (!free_pool_huge_page(h, nodes_allowed, 0)) + break; + } + while (count < persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, nodes_allowed, 1)) + break; + } +out: + ret = persistent_huge_pages(h); + spin_unlock(&hugetlb_lock); + return ret; +} + +#define HSTATE_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define HSTATE_ATTR(_name) \ + static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +static struct kobject *hugepages_kobj; +static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; + +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); + +static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) +{ + int i; + + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (hstate_kobjs[i] == kobj) { + if (nidp) + *nidp = NUMA_NO_NODE; + return &hstates[i]; + } + + return kobj_to_node_hstate(kobj, nidp); +} + +static ssize_t nr_hugepages_show_common(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long nr_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + nr_huge_pages = h->nr_huge_pages; + else + nr_huge_pages = h->nr_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", nr_huge_pages); +} +static ssize_t nr_hugepages_store_common(bool obey_mempolicy, + struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) +{ + int err; + int nid; + unsigned long count; + struct hstate *h; + NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); + + err = strict_strtoul(buf, 10, &count); + if (err) + return 0; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) { + /* + * global hstate attribute + */ + if (!(obey_mempolicy && + init_nodemask_of_mempolicy(nodes_allowed))) { + NODEMASK_FREE(nodes_allowed); + nodes_allowed = &node_states[N_HIGH_MEMORY]; + } + } else if (nodes_allowed) { + /* + * per node hstate attribute: adjust count to global, + * but restrict alloc/free to the specified node. + */ + count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; + init_nodemask_of_node(nodes_allowed, nid); + } else + nodes_allowed = &node_states[N_HIGH_MEMORY]; + + h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed); + + if (nodes_allowed != &node_states[N_HIGH_MEMORY]) + NODEMASK_FREE(nodes_allowed); + + return len; +} + +static ssize_t nr_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(false, kobj, attr, buf, len); +} +HSTATE_ATTR(nr_hugepages); + +#ifdef CONFIG_NUMA + +/* + * hstate attribute for optionally mempolicy-based constraint on persistent + * huge page alloc/free. + */ +static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(true, kobj, attr, buf, len); +} +HSTATE_ATTR(nr_hugepages_mempolicy); +#endif + + +static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj, NULL); + return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); +} +static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj, NULL); + + err = strict_strtoul(buf, 10, &input); + if (err) + return 0; + + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = input; + spin_unlock(&hugetlb_lock); + + return count; +} +HSTATE_ATTR(nr_overcommit_hugepages); + +static ssize_t free_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long free_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + free_huge_pages = h->free_huge_pages; + else + free_huge_pages = h->free_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", free_huge_pages); +} +HSTATE_ATTR_RO(free_hugepages); + +static ssize_t resv_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj, NULL); + return sprintf(buf, "%lu\n", h->resv_huge_pages); +} +HSTATE_ATTR_RO(resv_hugepages); + +static ssize_t surplus_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h; + unsigned long surplus_huge_pages; + int nid; + + h = kobj_to_hstate(kobj, &nid); + if (nid == NUMA_NO_NODE) + surplus_huge_pages = h->surplus_huge_pages; + else + surplus_huge_pages = h->surplus_huge_pages_node[nid]; + + return sprintf(buf, "%lu\n", surplus_huge_pages); +} +HSTATE_ATTR_RO(surplus_hugepages); + +static struct attribute *hstate_attrs[] = { + &nr_hugepages_attr.attr, + &nr_overcommit_hugepages_attr.attr, + &free_hugepages_attr.attr, + &resv_hugepages_attr.attr, + &surplus_hugepages_attr.attr, +#ifdef CONFIG_NUMA + &nr_hugepages_mempolicy_attr.attr, +#endif + NULL, +}; + +static struct attribute_group hstate_attr_group = { + .attrs = hstate_attrs, +}; + +static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, + struct kobject **hstate_kobjs, + struct attribute_group *hstate_attr_group) +{ + int retval; + int hi = h - hstates; + + hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); + if (!hstate_kobjs[hi]) + return -ENOMEM; + + retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); + if (retval) + kobject_put(hstate_kobjs[hi]); + + return retval; +} + +static void __init hugetlb_sysfs_init(void) +{ + struct hstate *h; + int err; + + hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); + if (!hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, + hstate_kobjs, &hstate_attr_group); + if (err) + printk(KERN_ERR "Hugetlb: Unable to add hstate %s", + h->name); + } +} + +#ifdef CONFIG_NUMA + +/* + * node_hstate/s - associate per node hstate attributes, via their kobjects, + * with node sysdevs in node_devices[] using a parallel array. The array + * index of a node sysdev or _hstate == node id. + * This is here to avoid any static dependency of the node sysdev driver, in + * the base kernel, on the hugetlb module. + */ +struct node_hstate { + struct kobject *hugepages_kobj; + struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; +}; +struct node_hstate node_hstates[MAX_NUMNODES]; + +/* + * A subset of global hstate attributes for node sysdevs + */ +static struct attribute *per_node_hstate_attrs[] = { + &nr_hugepages_attr.attr, + &free_hugepages_attr.attr, + &surplus_hugepages_attr.attr, + NULL, +}; + +static struct attribute_group per_node_hstate_attr_group = { + .attrs = per_node_hstate_attrs, +}; + +/* + * kobj_to_node_hstate - lookup global hstate for node sysdev hstate attr kobj. + * Returns node id via non-NULL nidp. + */ +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) +{ + int nid; + + for (nid = 0; nid < nr_node_ids; nid++) { + struct node_hstate *nhs = &node_hstates[nid]; + int i; + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (nhs->hstate_kobjs[i] == kobj) { + if (nidp) + *nidp = nid; + return &hstates[i]; + } + } + + BUG(); + return NULL; +} + +/* + * Unregister hstate attributes from a single node sysdev. + * No-op if no hstate attributes attached. + */ +void hugetlb_unregister_node(struct node *node) +{ + struct hstate *h; + struct node_hstate *nhs = &node_hstates[node->sysdev.id]; + + if (!nhs->hugepages_kobj) + return; /* no hstate attributes */ + + for_each_hstate(h) + if (nhs->hstate_kobjs[h - hstates]) { + kobject_put(nhs->hstate_kobjs[h - hstates]); + nhs->hstate_kobjs[h - hstates] = NULL; + } + + kobject_put(nhs->hugepages_kobj); + nhs->hugepages_kobj = NULL; +} + +/* + * hugetlb module exit: unregister hstate attributes from node sysdevs + * that have them. + */ +static void hugetlb_unregister_all_nodes(void) +{ + int nid; + + /* + * disable node sysdev registrations. + */ + register_hugetlbfs_with_node(NULL, NULL); + + /* + * remove hstate attributes from any nodes that have them. + */ + for (nid = 0; nid < nr_node_ids; nid++) + hugetlb_unregister_node(&node_devices[nid]); +} + +/* + * Register hstate attributes for a single node sysdev. + * No-op if attributes already registered. + */ +void hugetlb_register_node(struct node *node) +{ + struct hstate *h; + struct node_hstate *nhs = &node_hstates[node->sysdev.id]; + int err; + + if (nhs->hugepages_kobj) + return; /* already allocated */ + + nhs->hugepages_kobj = kobject_create_and_add("hugepages", + &node->sysdev.kobj); + if (!nhs->hugepages_kobj) + return; - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[nid]--; - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; - nr_pages--; - remaining_iterations = num_online_nodes(); + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, + nhs->hstate_kobjs, + &per_node_hstate_attr_group); + if (err) { + printk(KERN_ERR "Hugetlb: Unable to add hstate %s" + " for node %d\n", + h->name, node->sysdev.id); + hugetlb_unregister_node(node); + break; } } } /* - * Determine if the huge page at addr within the vma has an associated - * reservation. Where it does not we will need to logically increase - * reservation and actually increase quota before an allocation can occur. - * Where any new reservation would be required the reservation change is - * prepared, but not committed. Once the page has been quota'd allocated - * an instantiated the change should be committed via vma_commit_reservation. - * No action is required on failure. + * hugetlb init time: register hstate attributes for all registered node + * sysdevs of nodes that have memory. All on-line nodes should have + * registered their associated sysdev by this time. */ -static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) +static void hugetlb_register_all_nodes(void) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - - if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_pagecache_offset(vma, addr); - return region_chg(&inode->i_mapping->private_list, - idx, idx + 1); + int nid; - } else { - if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) - return 1; + for_each_node_state(nid, N_HIGH_MEMORY) { + struct node *node = &node_devices[nid]; + if (node->sysdev.id == nid) + hugetlb_register_node(node); } - return 0; + /* + * Let the node sysdev driver know we're here so it can + * [un]register hstate attributes on node hotplug. + */ + register_hugetlbfs_with_node(hugetlb_register_node, + hugetlb_unregister_node); } -static void vma_commit_reservation(struct vm_area_struct *vma, - unsigned long addr) +#else /* !CONFIG_NUMA */ + +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; + BUG(); + if (nidp) + *nidp = -1; + return NULL; +} - if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_pagecache_offset(vma, addr); - region_add(&inode->i_mapping->private_list, idx, idx + 1); +static void hugetlb_unregister_all_nodes(void) { } + +static void hugetlb_register_all_nodes(void) { } + +#endif + +static void __exit hugetlb_exit(void) +{ + struct hstate *h; + + hugetlb_unregister_all_nodes(); + + for_each_hstate(h) { + kobject_put(hstate_kobjs[h - hstates]); } + + kobject_put(hugepages_kobj); } +module_exit(hugetlb_exit); -static struct page *alloc_huge_page(struct vm_area_struct *vma, - unsigned long addr, int avoid_reserve) +static int __init hugetlb_init(void) { - struct page *page; - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; - unsigned int chg; - - /* - * Processes that did not create the mapping will have no reserves and - * will not have accounted against quota. Check that the quota can be - * made before satisfying the allocation - * MAP_NORESERVE mappings may also need pages and quota allocated - * if no reserve mapping overlaps. + /* Some platform decide whether they support huge pages at boot + * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when + * there is no such support */ - chg = vma_needs_reservation(vma, addr); - if (chg < 0) - return ERR_PTR(chg); - if (chg) - if (hugetlb_get_quota(inode->i_mapping, chg)) - return ERR_PTR(-ENOSPC); - - spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(vma, addr, avoid_reserve); - spin_unlock(&hugetlb_lock); + if (HPAGE_SHIFT == 0) + return 0; - if (!page) { - page = alloc_buddy_huge_page(vma, addr); - if (!page) { - hugetlb_put_quota(inode->i_mapping, chg); - return ERR_PTR(-VM_FAULT_OOM); - } + if (!size_to_hstate(default_hstate_size)) { + default_hstate_size = HPAGE_SIZE; + if (!size_to_hstate(default_hstate_size)) + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } + default_hstate_idx = size_to_hstate(default_hstate_size) - hstates; + if (default_hstate_max_huge_pages) + default_hstate.max_huge_pages = default_hstate_max_huge_pages; - set_page_refcounted(page); - set_page_private(page, (unsigned long) mapping); + hugetlb_init_hstates(); - vma_commit_reservation(vma, addr); + gather_bootmem_prealloc(); - return page; + report_hugepages(); + + hugetlb_sysfs_init(); + + hugetlb_register_all_nodes(); + + return 0; } +module_init(hugetlb_init); -static int __init hugetlb_init(void) +/* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_add_hstate(unsigned order) { + struct hstate *h; unsigned long i; - if (HPAGE_SHIFT == 0) - return 0; - + 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); + h->nr_huge_pages = 0; + h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) - INIT_LIST_HEAD(&hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_freelists[i]); + h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]); + h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]); + snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", + huge_page_size(h)/1024); - hugetlb_next_nid = first_node(node_online_map); + parsed_hstate = h; +} - for (i = 0; i < max_huge_pages; ++i) { - if (!alloc_fresh_huge_page()) - break; +static int __init hugetlb_nrpages_setup(char *s) +{ + unsigned long *mhp; + static unsigned long *last_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 (mhp == last_mhp) { + printk(KERN_WARNING "hugepages= specified twice without " + "interleaving hugepagesz=, ignoring\n"); + return 1; } - max_huge_pages = free_huge_pages = nr_huge_pages = i; - printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages); - return 0; + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + + /* + * Global state is always initialized later in hugetlb_init. + * But we need to allocate >= MAX_ORDER hstates here early to still + * use the bootmem allocator. + */ + if (max_hstate && parsed_hstate->order >= MAX_ORDER) + hugetlb_hstate_alloc_pages(parsed_hstate); + + last_mhp = mhp; + + return 1; } -module_init(hugetlb_init); +__setup("hugepages=", hugetlb_nrpages_setup); -static int __init hugetlb_setup(char *s) +static int __init hugetlb_default_setup(char *s) { - if (sscanf(s, "%lu", &max_huge_pages) <= 0) - max_huge_pages = 0; + default_hstate_size = memparse(s, &s); return 1; } -__setup("hugepages=", hugetlb_setup); +__setup("default_hugepagesz=", hugetlb_default_setup); static unsigned int cpuset_mems_nr(unsigned int *array) { @@ -845,115 +1844,59 @@ static unsigned int cpuset_mems_nr(unsigned int *array) } #ifdef CONFIG_SYSCTL -#ifdef CONFIG_HIGHMEM -static void try_to_free_low(unsigned long count) +static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) { - int i; - - for (i = 0; i < MAX_NUMNODES; ++i) { - struct page *page, *next; - list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) { - if (count >= nr_huge_pages) - return; - if (PageHighMem(page)) - continue; - list_del(&page->lru); - update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[page_to_nid(page)]--; + 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, buffer, length, ppos); + + if (write) { + NODEMASK_ALLOC(nodemask_t, nodes_allowed, + GFP_KERNEL | __GFP_NORETRY); + if (!(obey_mempolicy && + init_nodemask_of_mempolicy(nodes_allowed))) { + NODEMASK_FREE(nodes_allowed); + nodes_allowed = &node_states[N_HIGH_MEMORY]; } - } -} -#else -static inline void try_to_free_low(unsigned long count) -{ -} -#endif - -#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages) -static unsigned long set_max_huge_pages(unsigned long count) -{ - unsigned long min_count, ret; + h->max_huge_pages = set_max_huge_pages(h, tmp, nodes_allowed); - /* - * Increase the pool size - * First take pages out of surplus state. Then make up the - * remaining difference by allocating fresh huge pages. - * - * We might race with alloc_buddy_huge_page() here and be unable - * to convert a surplus huge page to a normal huge page. That is - * not critical, though, it just means the overall size of the - * pool might be one hugepage larger than it needs to be, but - * within all the constraints specified by the sysctls. - */ - spin_lock(&hugetlb_lock); - while (surplus_huge_pages && count > persistent_huge_pages) { - if (!adjust_pool_surplus(-1)) - break; + if (nodes_allowed != &node_states[N_HIGH_MEMORY]) + NODEMASK_FREE(nodes_allowed); } - while (count > persistent_huge_pages) { - /* - * If this allocation races such that we no longer need the - * page, free_huge_page will handle it by freeing the page - * and reducing the surplus. - */ - spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(); - spin_lock(&hugetlb_lock); - if (!ret) - goto out; + return 0; +} - } +int hugetlb_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ - /* - * Decrease the pool size - * First return free pages to the buddy allocator (being careful - * to keep enough around to satisfy reservations). Then place - * pages into surplus state as needed so the pool will shrink - * to the desired size as pages become free. - * - * By placing pages into the surplus state independent of the - * overcommit value, we are allowing the surplus pool size to - * exceed overcommit. There are few sane options here. Since - * alloc_buddy_huge_page() is checking the global counter, - * though, we'll note that we're not allowed to exceed surplus - * and won't grow the pool anywhere else. Not until one of the - * sysctls are changed, or the surplus pages go out of use. - */ - min_count = resv_huge_pages + nr_huge_pages - free_huge_pages; - min_count = max(count, min_count); - try_to_free_low(min_count); - while (min_count < persistent_huge_pages) { - struct page *page = dequeue_huge_page(); - if (!page) - break; - update_and_free_page(page); - } - while (count < persistent_huge_pages) { - if (!adjust_pool_surplus(1)) - break; - } -out: - ret = persistent_huge_pages; - spin_unlock(&hugetlb_lock); - return ret; + return hugetlb_sysctl_handler_common(false, table, write, + buffer, length, ppos); } -int hugetlb_sysctl_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, - size_t *length, loff_t *ppos) +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - max_huge_pages = set_max_huge_pages(max_huge_pages); - return 0; + return hugetlb_sysctl_handler_common(true, table, write, + buffer, length, ppos); } +#endif /* CONFIG_NUMA */ int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (hugepages_treat_as_movable) htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; else @@ -962,51 +1905,66 @@ int hugetlb_treat_movable_handler(struct ctl_table *table, int write, } int hugetlb_overcommit_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - spin_lock(&hugetlb_lock); - nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; - spin_unlock(&hugetlb_lock); + 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, buffer, length, ppos); + + if (write) { + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = tmp; + spin_unlock(&hugetlb_lock); + } + return 0; } #endif /* CONFIG_SYSCTL */ -int hugetlb_report_meminfo(char *buf) +void hugetlb_report_meminfo(struct seq_file *m) { - return sprintf(buf, - "HugePages_Total: %5lu\n" - "HugePages_Free: %5lu\n" - "HugePages_Rsvd: %5lu\n" - "HugePages_Surp: %5lu\n" - "Hugepagesize: %5lu kB\n", - nr_huge_pages, - free_huge_pages, - resv_huge_pages, - surplus_huge_pages, - HPAGE_SIZE/1024); + struct hstate *h = &default_hstate; + seq_printf(m, + "HugePages_Total: %5lu\n" + "HugePages_Free: %5lu\n" + "HugePages_Rsvd: %5lu\n" + "HugePages_Surp: %5lu\n" + "Hugepagesize: %8lu kB\n", + h->nr_huge_pages, + h->free_huge_pages, + h->resv_huge_pages, + h->surplus_huge_pages, + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); } int hugetlb_report_node_meminfo(int nid, char *buf) { + struct hstate *h = &default_hstate; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", - nid, nr_huge_pages_node[nid], - nid, free_huge_pages_node[nid], - nid, surplus_huge_pages_node[nid]); + nid, h->nr_huge_pages_node[nid], + nid, h->free_huge_pages_node[nid], + nid, h->surplus_huge_pages_node[nid]); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { - return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE); + struct hstate *h = &default_hstate; + return h->nr_huge_pages * pages_per_huge_page(h); } -static int hugetlb_acct_memory(long delta) +static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; @@ -1029,29 +1987,62 @@ static int hugetlb_acct_memory(long delta) * semantics that cpuset has. */ if (delta > 0) { - if (gather_surplus_pages(delta) < 0) + if (gather_surplus_pages(h, delta) < 0) goto out; - if (delta > cpuset_mems_nr(free_huge_pages_node)) { - return_unused_surplus_pages(delta); + if (delta > cpuset_mems_nr(h->free_huge_pages_node)) { + return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) - return_unused_surplus_pages((unsigned long) -delta); + return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock(&hugetlb_lock); return ret; } +static void hugetlb_vm_op_open(struct vm_area_struct *vma) +{ + struct resv_map *reservations = vma_resv_map(vma); + + /* + * This new VMA should share its siblings reservation map if present. + * The VMA will only ever have a valid reservation map pointer where + * it is being copied for another still existing VMA. As that VMA + * has a reference to the reservation map it cannot dissappear until + * after this open call completes. It is therefore safe to take a + * new reference here without additional locking. + */ + if (reservations) + kref_get(&reservations->refs); +} + static void hugetlb_vm_op_close(struct vm_area_struct *vma) { - unsigned long reserve = vma_resv_huge_pages(vma); - if (reserve) - hugetlb_acct_memory(-reserve); + struct hstate *h = hstate_vma(vma); + struct resv_map *reservations = vma_resv_map(vma); + unsigned long reserve; + unsigned long start; + unsigned long end; + + if (reservations) { + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); + + reserve = (end - start) - + region_count(&reservations->regions, start, end); + + kref_put(&reservations->refs, resv_map_release); + + if (reserve) { + hugetlb_acct_memory(h, -reserve); + hugetlb_put_quota(vma->vm_file->f_mapping, reserve); + } + } } /* @@ -1066,8 +2057,9 @@ static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -struct vm_operations_struct hugetlb_vm_ops = { +const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, + .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, }; @@ -1107,14 +2099,16 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct page *ptepage; unsigned long addr; int cow; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; - for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, addr); + dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) goto nomem; @@ -1150,6 +2144,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, pte_t pte; struct page *page; struct page *tmp; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + /* * A page gathering list, protected by per file i_mmap_lock. The * lock is used to avoid list corruption from multiple unmapping @@ -1158,11 +2155,12 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, LIST_HEAD(page_list); WARN_ON(!is_vm_hugetlb_page(vma)); - BUG_ON(start & ~HPAGE_MASK); - BUG_ON(end & ~HPAGE_MASK); + BUG_ON(start & ~huge_page_mask(h)); + BUG_ON(end & ~huge_page_mask(h)); + mmu_notifier_invalidate_range_start(mm, start, end); spin_lock(&mm->page_table_lock); - for (address = start; address < end; address += HPAGE_SIZE) { + for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1202,6 +2200,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { list_del(&page->lru); put_page(page); @@ -1211,19 +2210,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { - /* - * It is undesirable to test vma->vm_file as it should be non-null - * for valid hugetlb area. However, vm_file will be NULL in the error - * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file before calling this function - * to clean up. Since no pte has actually been setup, it is safe to - * do nothing in this case. - */ - if (vma->vm_file) { - spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); - __unmap_hugepage_range(vma, start, end, ref_page); - spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); - } + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); + __unmap_hugepage_range(vma, start, end, ref_page); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); } /* @@ -1232,11 +2221,10 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ -int unmap_ref_private(struct mm_struct *mm, - struct vm_area_struct *vma, - struct page *page, - unsigned long address) +static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, + struct page *page, unsigned long address) { + struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; struct prio_tree_iter iter; @@ -1246,11 +2234,17 @@ int unmap_ref_private(struct mm_struct *mm, * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ - address = address & huge_page_mask(hstate_vma(vma)); + address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + (vma->vm_pgoff >> PAGE_SHIFT); mapping = (struct address_space *)page_private(page); + /* + * Take the mapping lock for the duration of the table walk. As + * this mapping should be shared between all the VMAs, + * __unmap_hugepage_range() is called as the lock is already held + */ + spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) @@ -1264,10 +2258,11 @@ int unmap_ref_private(struct mm_struct *mm, * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) - unmap_hugepage_range(iter_vma, - address, address + HPAGE_SIZE, + __unmap_hugepage_range(iter_vma, + address, address + huge_page_size(h), page); } + spin_unlock(&mapping->i_mmap_lock); return 1; } @@ -1276,6 +2271,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, struct page *pagecache_page) { + struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; int avoidcopy; int outside_reserve = 0; @@ -1300,12 +2296,15 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_SHARED) && + if (!(vma->vm_flags & VM_MAYSHARE) && is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; page_cache_get(old_page); + + /* Drop page_table_lock as buddy allocator may be called */ + spin_unlock(&mm->page_table_lock); new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { @@ -1323,20 +2322,26 @@ retry_avoidcopy: if (unmap_ref_private(mm, vma, old_page, address)) { BUG_ON(page_count(old_page) != 1); BUG_ON(huge_pte_none(pte)); + spin_lock(&mm->page_table_lock); goto retry_avoidcopy; } WARN_ON_ONCE(1); } + /* Caller expects lock to be held */ + spin_lock(&mm->page_table_lock); return -PTR_ERR(new_page); } - spin_unlock(&mm->page_table_lock); copy_huge_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); - spin_lock(&mm->page_table_lock); - ptep = huge_pte_offset(mm, address & HPAGE_MASK); + /* + * Retake the page_table_lock to check for racing updates + * before the page tables are altered + */ + spin_lock(&mm->page_table_lock); + ptep = huge_pte_offset(mm, address & huge_page_mask(h)); if (likely(pte_same(huge_ptep_get(ptep), pte))) { /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); @@ -1351,21 +2356,42 @@ retry_avoidcopy: } /* Return the pagecache page at a given address within a VMA */ -static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, - unsigned long address) +static struct page *hugetlbfs_pagecache_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; mapping = vma->vm_file->f_mapping; - idx = vma_pagecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); return find_lock_page(mapping, idx); } +/* + * Return whether there is a pagecache page to back given address within VMA. + * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page. + */ +static bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct address_space *mapping; + pgoff_t idx; + struct page *page; + + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + + page = find_get_page(mapping, idx); + if (page) + put_page(page); + return page != NULL; +} + static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, int write_access) + unsigned long address, pte_t *ptep, unsigned int flags) { + struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; pgoff_t idx; unsigned long size; @@ -1386,7 +2412,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, } mapping = vma->vm_file->f_mapping; - idx = vma_pagecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); /* * Use page lock to guard against racing truncation @@ -1395,7 +2421,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, retry: page = find_lock_page(mapping, idx); if (!page) { - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; page = alloc_huge_page(vma, address, 0); @@ -1403,10 +2429,10 @@ retry: ret = -PTR_ERR(page); goto out; } - clear_huge_page(page, address); + clear_huge_page(page, address, huge_page_size(h)); __SetPageUptodate(page); - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { int err; struct inode *inode = mapping->host; @@ -1419,14 +2445,26 @@ retry: } spin_lock(&inode->i_lock); - inode->i_blocks += BLOCKS_PER_HUGEPAGE; + inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); } else lock_page(page); } + /* + * If we are going to COW a private mapping later, we examine the + * pending reservations for this page now. This will ensure that + * any allocations necessary to record that reservation occur outside + * the spinlock. + */ + if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) + if (vma_needs_reservation(h, vma, address) < 0) { + ret = VM_FAULT_OOM; + goto backout_unlocked; + } + spin_lock(&mm->page_table_lock); - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto backout; @@ -1438,7 +2476,7 @@ retry: && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); - if (write_access && !(vma->vm_flags & VM_SHARED)) { + if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page); } @@ -1450,20 +2488,23 @@ out: backout: spin_unlock(&mm->page_table_lock); +backout_unlocked: unlock_page(page); put_page(page); goto out; } int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access) + unsigned long address, unsigned int flags) { pte_t *ptep; pte_t entry; int ret; + struct page *pagecache_page = NULL; static DEFINE_MUTEX(hugetlb_instantiation_mutex); + struct hstate *h = hstate_vma(vma); - ptep = huge_pte_alloc(mm, address); + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); if (!ptep) return VM_FAULT_OOM; @@ -1475,74 +2516,131 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, mutex_lock(&hugetlb_instantiation_mutex); entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, address, ptep, write_access); - mutex_unlock(&hugetlb_instantiation_mutex); - return ret; + ret = hugetlb_no_page(mm, vma, address, ptep, flags); + goto out_mutex; } ret = 0; + /* + * If we are going to COW the mapping later, we examine the pending + * reservations for this page now. This will ensure that any + * allocations necessary to record that reservation occur outside the + * spinlock. For private mappings, we also lookup the pagecache + * page now as it is used to determine if a reservation has been + * consumed. + */ + if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) { + if (vma_needs_reservation(h, vma, address) < 0) { + ret = VM_FAULT_OOM; + goto out_mutex; + } + + if (!(vma->vm_flags & VM_MAYSHARE)) + pagecache_page = hugetlbfs_pagecache_page(h, + vma, address); + } + spin_lock(&mm->page_table_lock); /* Check for a racing update before calling hugetlb_cow */ - if (likely(pte_same(entry, huge_ptep_get(ptep)))) - if (write_access && !pte_write(entry)) { - struct page *page; - page = hugetlbfs_pagecache_page(vma, address); - ret = hugetlb_cow(mm, vma, address, ptep, entry, page); - if (page) { - unlock_page(page); - put_page(page); - } + if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) + goto out_page_table_lock; + + + if (flags & FAULT_FLAG_WRITE) { + if (!pte_write(entry)) { + ret = hugetlb_cow(mm, vma, address, ptep, entry, + pagecache_page); + goto out_page_table_lock; } + entry = pte_mkdirty(entry); + } + entry = pte_mkyoung(entry); + if (huge_ptep_set_access_flags(vma, address, ptep, entry, + flags & FAULT_FLAG_WRITE)) + update_mmu_cache(vma, address, entry); + +out_page_table_lock: spin_unlock(&mm->page_table_lock); + + if (pagecache_page) { + unlock_page(pagecache_page); + put_page(pagecache_page); + } + +out_mutex: mutex_unlock(&hugetlb_instantiation_mutex); return ret; } +/* Can be overriden by architectures */ +__attribute__((weak)) struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, int *length, int i, - int write) + unsigned int flags) { unsigned long pfn_offset; unsigned long vaddr = *position; int remainder = *length; + struct hstate *h = hstate_vma(vma); spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { pte_t *pte; + int absent; struct page *page; /* * Some archs (sparc64, sh*) have multiple pte_ts to - * each hugepage. We have to make * sure we get the + * each hugepage. We have to make sure we get the * first, for the page indexing below to work. */ - pte = huge_pte_offset(mm, vaddr & HPAGE_MASK); + pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); + absent = !pte || huge_pte_none(huge_ptep_get(pte)); + + /* + * When coredumping, it suits get_dump_page if we just return + * an error where there's an empty slot with no huge pagecache + * to back it. This way, we avoid allocating a hugepage, and + * the sparse dumpfile avoids allocating disk blocks, but its + * huge holes still show up with zeroes where they need to be. + */ + if (absent && (flags & FOLL_DUMP) && + !hugetlbfs_pagecache_present(h, vma, vaddr)) { + remainder = 0; + break; + } - if (!pte || huge_pte_none(huge_ptep_get(pte)) || - (write && !pte_write(huge_ptep_get(pte)))) { + if (absent || + ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) { int ret; spin_unlock(&mm->page_table_lock); - ret = hugetlb_fault(mm, vma, vaddr, write); + ret = hugetlb_fault(mm, vma, vaddr, + (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0); spin_lock(&mm->page_table_lock); if (!(ret & VM_FAULT_ERROR)) continue; remainder = 0; - if (!i) - i = -EFAULT; break; } - pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT; + pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); same_page: if (pages) { - get_page(page); - pages[i] = page + pfn_offset; + pages[i] = mem_map_offset(page, pfn_offset); + get_page(pages[i]); } if (vmas) @@ -1553,7 +2651,7 @@ same_page: --remainder; ++i; if (vaddr < vma->vm_end && remainder && - pfn_offset < HPAGE_SIZE/PAGE_SIZE) { + pfn_offset < pages_per_huge_page(h)) { /* * We use pfn_offset to avoid touching the pageframes * of this compound page. @@ -1565,7 +2663,7 @@ same_page: *length = remainder; *position = vaddr; - return i; + return i ? i : -EFAULT; } void hugetlb_change_protection(struct vm_area_struct *vma, @@ -1575,13 +2673,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long start = address; pte_t *ptep; pte_t pte; + struct hstate *h = hstate_vma(vma); BUG_ON(address >= end); flush_cache_range(vma, address, end); spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); spin_lock(&mm->page_table_lock); - for (; address < end; address += HPAGE_SIZE) { + for (; address < end; address += huge_page_size(h)) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1601,11 +2700,18 @@ void hugetlb_change_protection(struct vm_area_struct *vma, int hugetlb_reserve_pages(struct inode *inode, long from, long to, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int acctflag) { long ret, chg; + struct hstate *h = hstate_inode(inode); - if (vma && vma->vm_flags & VM_NORESERVE) + /* + * Only apply hugepage reservation if asked. At fault time, an + * attempt will be made for VM_NORESERVE to allocate a page + * and filesystem quota without using reserves + */ + if (acctflag & VM_NORESERVE) return 0; /* @@ -1614,37 +2720,61 @@ int hugetlb_reserve_pages(struct inode *inode, * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ - if (!vma || vma->vm_flags & VM_SHARED) + if (!vma || vma->vm_flags & VM_MAYSHARE) chg = region_chg(&inode->i_mapping->private_list, from, to); else { + struct resv_map *resv_map = resv_map_alloc(); + if (!resv_map) + return -ENOMEM; + chg = to - from; - set_vma_resv_huge_pages(vma, chg); + + set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) return chg; + /* There must be enough filesystem quota for the mapping */ if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; - ret = hugetlb_acct_memory(chg); + + /* + * Check enough hugepages are available for the reservation. + * Hand back the quota if there are not + */ + ret = hugetlb_acct_memory(h, chg); if (ret < 0) { hugetlb_put_quota(inode->i_mapping, chg); return ret; } - if (!vma || vma->vm_flags & VM_SHARED) + + /* + * Account for the reservations made. Shared mappings record regions + * that have reservations as they are shared by multiple VMAs. + * When the last VMA disappears, the region map says how much + * the reservation was and the page cache tells how much of + * the reservation was consumed. Private mappings are per-VMA and + * only the consumed reservations are tracked. When the VMA + * disappears, the original reservation is the VMA size and the + * consumed reservations are stored in the map. Hence, nothing + * else has to be done for private mappings here + */ + if (!vma || vma->vm_flags & VM_MAYSHARE) region_add(&inode->i_mapping->private_list, from, to); return 0; } void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { + struct hstate *h = hstate_inode(inode); long chg = region_truncate(&inode->i_mapping->private_list, offset); spin_lock(&inode->i_lock); - inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed; + inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); hugetlb_put_quota(inode->i_mapping, (chg - freed)); - hugetlb_acct_memory(-(chg - freed)); + hugetlb_acct_memory(h, -(chg - freed)); }