X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=4c9e6bbf3772c771775057404a1e0f314b90045c;hb=a98d3984c85222aa9efc63c4f9dd3d805ce469f2;hp=8c20aed62b9c350715db24004fa953cf5ebbd515;hpb=7f09ca51e925ba62e9ebfd4979f093e97e38adeb;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8c20aed..4c9e6bb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2,13 +2,14 @@ * Generic hugetlb support. * (C) William Irwin, April 2004 */ -#include #include #include #include #include +#include #include #include +#include #include #include #include @@ -16,11 +17,14 @@ #include #include #include +#include #include #include +#include #include +#include #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; @@ -217,6 +221,36 @@ static pgoff_t vma_hugecache_offset(struct hstate *h, } /* + * 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. + */ +#ifndef vma_mmu_pagesize +unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) +{ + return vma_kernel_pagesize(vma); +} +#endif + +/* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. @@ -260,7 +294,7 @@ struct resv_map { struct list_head regions; }; -struct resv_map *resv_map_alloc(void) +static struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); if (!resv_map) @@ -272,7 +306,7 @@ struct resv_map *resv_map_alloc(void) return resv_map; } -void resv_map_release(struct kref *ref) +static void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); @@ -284,16 +318,16 @@ void resv_map_release(struct kref *ref) 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)) + if (!(vma->vm_flags & VM_MAYSHARE)) return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); - return 0; + return NULL; } 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) | (unsigned long)map); @@ -302,7 +336,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *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); } @@ -321,7 +355,7 @@ static void decrement_hugepage_resv_vma(struct hstate *h, if (vma->vm_flags & VM_NORESERVE) return; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { /* Shared mappings always use reserves */ h->resv_huge_pages--; } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { @@ -337,25 +371,42 @@ static void decrement_hugepage_resv_vma(struct hstate *h, 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_reserves(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_SHARED) + if (vma->vm_flags & VM_MAYSHARE) return 1; if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; return 0; } +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 < sz/PAGE_SIZE; i++) { cond_resched(); @@ -363,12 +414,34 @@ static void clear_huge_page(struct page *page, } } +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 < pages_per_huge_page(h); i++) { cond_resched(); @@ -384,24 +457,6 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page(struct hstate *h) -{ - int nid; - struct page *page = NULL; - - for (nid = 0; nid < MAX_NUMNODES; ++nid) { - if (!list_empty(&h->hugepage_freelists[nid])) { - page = list_entry(h->hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; - break; - } - } - return page; -} - static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve) @@ -453,6 +508,8 @@ static void update_and_free_page(struct hstate *h, struct page *page) { int 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++) { @@ -489,6 +546,7 @@ static void free_huge_page(struct page *page) mapping = (struct address_space *) page_private(page); set_page_private(page, 0); + page->mapping = NULL; BUG_ON(page_count(page)); INIT_LIST_HEAD(&page->lru); @@ -505,41 +563,6 @@ static void free_huge_page(struct page *page) 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(struct hstate *h, int delta) -{ - static int prev_nid; - int nid = prev_nid; - int ret = 0; - - 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); - - /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !h->surplus_huge_pages_node[nid]) - continue; - /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) - continue; - - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (nid != prev_nid); - - prev_nid = nid; - return ret; -} - static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { set_compound_page_dtor(page, free_huge_page); @@ -550,6 +573,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) put_page(page); /* free it into the hugepage allocator */ } +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; + } +} + +int PageHuge(struct page *page) +{ + compound_page_dtor *dtor; + + if (!PageCompound(page)) + return 0; + + page = compound_head(page); + dtor = get_compound_page_dtor(page); + + return dtor == free_huge_page; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; @@ -557,13 +608,13 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) if (h->order >= MAX_ORDER) return NULL; - page = alloc_pages_node(nid, + page = alloc_pages_exact_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, 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; } prep_new_huge_page(h, page, nid); @@ -573,41 +624,66 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) } /* - * 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. + * 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 hstate_next_node(struct hstate *h) +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { - int next_nid; - next_nid = next_node(h->hugetlb_next_nid, node_online_map); - if (next_nid == MAX_NUMNODES) - next_nid = first_node(node_online_map); - h->hugetlb_next_nid = next_nid; - return next_nid; + 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; } -static int alloc_fresh_huge_page(struct hstate *h) +/* + * 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 = h->hugetlb_next_nid; + start_nid = hstate_next_node_to_alloc(h, nodes_allowed); + next_nid = start_nid; do { - page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid); - if (page) + page = alloc_fresh_huge_page_node(h, next_nid); + if (page) { ret = 1; - next_nid = hstate_next_node(h); - } while (!page && h->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); @@ -617,6 +693,67 @@ static int alloc_fresh_huge_page(struct hstate *h) return ret; } +/* + * 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) { @@ -663,6 +800,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, __GFP_REPEAT|__GFP_NOWARN, 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) { /* @@ -783,22 +925,13 @@ 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(struct hstate *h, unsigned long unused_resv_pages) { - static int nid = -1; - struct page *page; unsigned long nr_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. - */ - unsigned long remaining_iterations = num_online_nodes(); - /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; @@ -808,26 +941,17 @@ static void return_unused_surplus_pages(struct hstate *h, nr_pages = min(unused_resv_pages, h->surplus_huge_pages); - while (remaining_iterations-- && nr_pages) { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); - - if (!h->surplus_huge_pages_node[nid]) - continue; - - if (!list_empty(&h->hugepage_freelists[nid])) { - page = list_entry(h->hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - update_and_free_page(h, page); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; - h->surplus_huge_pages--; - h->surplus_huge_pages_node[nid]--; - nr_pages--; - remaining_iterations = num_online_nodes(); - } + /* + * We want to release as many surplus pages as possible, spread + * 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. + */ + while (nr_pages--) { + if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1)) + break; } } @@ -840,13 +964,13 @@ static void return_unused_surplus_pages(struct hstate *h, * an instantiated the change should be committed via vma_commit_reservation. * No action is required on failure. */ -static int vma_needs_reservation(struct hstate *h, +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_SHARED) { + 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); @@ -855,7 +979,7 @@ static int vma_needs_reservation(struct hstate *h, return 1; } else { - int err; + long err; pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); @@ -871,7 +995,7 @@ static void vma_commit_reservation(struct hstate *h, struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - if (vma->vm_flags & VM_SHARED) { + 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); @@ -891,7 +1015,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *page; struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - unsigned int chg; + long chg; /* * Processes that did not create the mapping will have no reserves and @@ -915,7 +1039,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page(h, vma, addr); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); - return ERR_PTR(-VM_FAULT_OOM); + return ERR_PTR(-VM_FAULT_SIGBUS); } } @@ -927,16 +1051,17 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return page; } -__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h) +int __weak alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; - int nr_nodes = nodes_weight(node_online_map); + int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); while (nr_nodes) { void *addr; addr = __alloc_bootmem_node_nopanic( - NODE_DATA(h->hugetlb_next_nid), + NODE_DATA(hstate_next_node_to_alloc(h, + &node_states[N_HIGH_MEMORY])), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -946,10 +1071,8 @@ __attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h) * puts them into the mem_map). */ m = addr; - if (m) - goto found; + goto found; } - hstate_next_node(h); nr_nodes--; } return 0; @@ -962,6 +1085,14 @@ found: 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) { @@ -972,7 +1103,7 @@ static void __init gather_bootmem_prealloc(void) struct hstate *h = m->hstate; __ClearPageReserved(page); WARN_ON(page_count(page) != 1); - prep_compound_page(page, h->order); + prep_compound_huge_page(page, h->order); prep_new_huge_page(h, page, page_to_nid(page)); } } @@ -985,7 +1116,8 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) if (h->order >= MAX_ORDER) { if (!alloc_bootmem_huge_page(h)) break; - } else if (!alloc_fresh_huge_page(h)) + } else if (!alloc_fresh_huge_page(h, + &node_states[N_HIGH_MEMORY])) break; } h->max_huge_pages = i; @@ -1026,16 +1158,16 @@ static void __init report_hugepages(void) } } -#ifdef CONFIG_SYSCTL #ifdef CONFIG_HIGHMEM -static void try_to_free_low(struct hstate *h, unsigned long count) +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 (i = 0; i < MAX_NUMNODES; ++i) { + 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) { @@ -1051,13 +1183,67 @@ static void try_to_free_low(struct hstate *h, unsigned long count) } } #else -static inline void try_to_free_low(struct hstate *h, unsigned long count) +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) +static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, + nodemask_t *nodes_allowed) { unsigned long min_count, ret; @@ -1077,7 +1263,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) */ spin_lock(&hugetlb_lock); while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { - if (!adjust_pool_surplus(h, -1)) + if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } @@ -1088,11 +1274,14 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) * and reducing the surplus. */ spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(h); + 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; } /* @@ -1112,15 +1301,13 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) */ 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); + try_to_free_low(h, min_count, nodes_allowed); while (min_count < persistent_huge_pages(h)) { - struct page *page = dequeue_huge_page(h); - if (!page) + if (!free_pool_huge_page(h, nodes_allowed, 0)) break; - update_and_free_page(h, page); } while (count < persistent_huge_pages(h)) { - if (!adjust_pool_surplus(h, 1)) + if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: @@ -1139,43 +1326,117 @@ out: static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; -static struct hstate *kobj_to_hstate(struct kobject *kobj) +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 (hstate_kobjs[i] == kobj) { + if (nidp) + *nidp = NUMA_NO_NODE; return &hstates[i]; - BUG(); - return NULL; + } + + return kobj_to_node_hstate(kobj, nidp); } -static ssize_t nr_hugepages_show(struct kobject *kobj, +static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - struct hstate *h = kobj_to_hstate(kobj); - return sprintf(buf, "%lu\n", h->nr_huge_pages); + 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(struct kobject *kobj, - struct kobj_attribute *attr, const char *buf, size_t count) +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; - unsigned long input; - struct hstate *h = kobj_to_hstate(kobj); + int nid; + unsigned long count; + struct hstate *h; + NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); - err = strict_strtoul(buf, 10, &input); + err = strict_strtoul(buf, 10, &count); if (err) return 0; - h->max_huge_pages = set_max_huge_pages(h, input); + 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); - return count; + 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); + 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, @@ -1183,7 +1444,7 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, { int err; unsigned long input; - struct hstate *h = kobj_to_hstate(kobj); + struct hstate *h = kobj_to_hstate(kobj, NULL); err = strict_strtoul(buf, 10, &input); if (err) @@ -1200,15 +1461,24 @@ HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - struct hstate *h = kobj_to_hstate(kobj); - return sprintf(buf, "%lu\n", h->free_huge_pages); + 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); + struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); @@ -1216,8 +1486,17 @@ HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - struct hstate *h = kobj_to_hstate(kobj); - return sprintf(buf, "%lu\n", h->surplus_huge_pages); + 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); @@ -1227,6 +1506,9 @@ static struct attribute *hstate_attrs[] = { &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, +#ifdef CONFIG_NUMA + &nr_hugepages_mempolicy_attr.attr, +#endif NULL, }; @@ -1234,19 +1516,20 @@ static struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; -static int __init hugetlb_sysfs_add_hstate(struct hstate *h) +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[h - hstates] = kobject_create_and_add(h->name, - hugepages_kobj); - if (!hstate_kobjs[h - hstates]) + hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); + if (!hstate_kobjs[hi]) return -ENOMEM; - retval = sysfs_create_group(hstate_kobjs[h - hstates], - &hstate_attr_group); + retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) - kobject_put(hstate_kobjs[h - hstates]); + kobject_put(hstate_kobjs[hi]); return retval; } @@ -1261,17 +1544,184 @@ static void __init hugetlb_sysfs_init(void) return; for_each_hstate(h) { - err = hugetlb_sysfs_add_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; + + 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; + } + } +} + +/* + * 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 void hugetlb_register_all_nodes(void) +{ + int nid; + + for_each_node_state(nid, N_HIGH_MEMORY) { + struct node *node = &node_devices[nid]; + if (node->sysdev.id == nid) + hugetlb_register_node(node); + } + + /* + * 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); +} +#else /* !CONFIG_NUMA */ + +static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) +{ + BUG(); + if (nidp) + *nidp = -1; + return NULL; +} + +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]); } @@ -1282,7 +1732,12 @@ module_exit(hugetlb_exit); static int __init hugetlb_init(void) { - BUILD_BUG_ON(HPAGE_SHIFT == 0); + /* 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 + */ + if (HPAGE_SHIFT == 0) + return 0; if (!size_to_hstate(default_hstate_size)) { default_hstate_size = HPAGE_SIZE; @@ -1301,6 +1756,8 @@ static int __init hugetlb_init(void) hugetlb_sysfs_init(); + hugetlb_register_all_nodes(); + return 0; } module_init(hugetlb_init); @@ -1324,7 +1781,8 @@ void __init hugetlb_add_hstate(unsigned order) h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); - h->hugetlb_next_nid = first_node(node_online_map); + 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); @@ -1386,9 +1844,10 @@ static unsigned int cpuset_mems_nr(unsigned int *array) return nr; } -int hugetlb_sysctl_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, - size_t *length, loff_t *ppos) +#ifdef CONFIG_SYSCTL +static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; @@ -1398,19 +1857,47 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); - if (write) - h->max_huge_pages = set_max_huge_pages(h, tmp); + 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]; + } + h->max_huge_pages = set_max_huge_pages(h, tmp, nodes_allowed); + + if (nodes_allowed != &node_states[N_HIGH_MEMORY]) + NODEMASK_FREE(nodes_allowed); + } return 0; } +int hugetlb_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + + return hugetlb_sysctl_handler_common(false, table, write, + buffer, length, ppos); +} + +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + 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 @@ -1419,7 +1906,7 @@ 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) { struct hstate *h = &default_hstate; @@ -1430,7 +1917,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) { spin_lock(&hugetlb_lock); @@ -1443,15 +1930,15 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, #endif /* CONFIG_SYSCTL */ -int hugetlb_report_meminfo(char *buf) +void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h = &default_hstate; - return sprintf(buf, - "HugePages_Total: %5lu\n" - "HugePages_Free: %5lu\n" - "HugePages_Rsvd: %5lu\n" - "HugePages_Surp: %5lu\n" - "Hugepagesize: %5lu kB\n", + 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, @@ -1552,8 +2039,10 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) kref_put(&reservations->refs, resv_map_release); - if (reserve) + if (reserve) { hugetlb_acct_memory(h, -reserve); + hugetlb_put_quota(vma->vm_file->f_mapping, reserve); + } } } @@ -1569,7 +2058,7 @@ 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, @@ -1599,7 +2088,7 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) { - update_mmu_cache(vma, address, entry); + update_mmu_cache(vma, address, ptep); } } @@ -1670,6 +2159,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, 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 += sz) { ptep = huge_pte_offset(mm, address); @@ -1711,6 +2201,7 @@ 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); @@ -1731,11 +2222,10 @@ 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; @@ -1745,11 +2235,17 @@ 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) @@ -1763,10 +2259,11 @@ 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; } @@ -1800,12 +2297,15 @@ 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)) { @@ -1823,19 +2323,25 @@ 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); + /* + * 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 */ @@ -1863,8 +2369,28 @@ static struct page *hugetlbfs_pagecache_page(struct hstate *h, 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; @@ -1907,7 +2433,7 @@ retry: 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; @@ -1922,10 +2448,24 @@ retry: spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); - } else + } else { lock_page(page); + page->mapping = HUGETLB_POISON; + } } + /* + * 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) >> huge_page_shift(h); if (idx >= size) @@ -1939,7 +2479,7 @@ 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); } @@ -1951,17 +2491,19 @@ 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); @@ -1977,26 +2519,59 @@ 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(h, 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, ptep); + +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; @@ -2014,7 +2589,7 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, 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; @@ -2024,28 +2599,42 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *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 & 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; } @@ -2053,8 +2642,8 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, 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) @@ -2077,7 +2666,7 @@ same_page: *length = remainder; *position = vaddr; - return i; + return i ? i : -EFAULT; } void hugetlb_change_protection(struct vm_area_struct *vma, @@ -2114,12 +2703,18 @@ 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; /* @@ -2128,7 +2723,7 @@ 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(); @@ -2144,14 +2739,32 @@ int hugetlb_reserve_pages(struct inode *inode, if (chg < 0) return chg; + /* There must be enough filesystem quota for the mapping */ if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; + + /* + * 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; } @@ -2162,7 +2775,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) long chg = region_truncate(&inode->i_mapping->private_list, offset); spin_lock(&inode->i_lock); - inode->i_blocks -= blocks_per_huge_page(h); + inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); hugetlb_put_quota(inode->i_mapping, (chg - freed));